From 65888d95c9d75f7a118e7c8baacb38bffb39b4e4 Mon Sep 17 00:00:00 2001 From: Jordan Whited Date: Fri, 14 Jun 2024 08:45:24 -0700 Subject: [PATCH] derp/xdp,cmd/xdpderper: initial skeleton (#12390) This commit introduces a userspace program for managing an experimental eBPF XDP STUN server program. derp/xdp contains the eBPF pseudo-C along with a Go pkg for loading it and exporting its metrics. cmd/xdpderper is a package main user of derp/xdp. Updates tailscale/corp#20689 Signed-off-by: Jordan Whited --- .github/workflows/test.yml | 4 +- cmd/xdpderper/xdpderper.go | 76 + derp/xdp/bpf_bpfeb.go | 166 + derp/xdp/bpf_bpfeb.o | Bin 0 -> 23640 bytes derp/xdp/bpf_bpfel.go | 166 + derp/xdp/bpf_bpfel.o | Bin 0 -> 23808 bytes derp/xdp/headers/LICENSE.BSD-2-Clause | 32 + derp/xdp/headers/bpf_endian.h | 99 + derp/xdp/headers/bpf_helper_defs.h | 4766 +++++++++++++++++++++++++ derp/xdp/headers/bpf_helpers.h | 410 +++ derp/xdp/headers/bpf_tracing.h | 922 +++++ derp/xdp/headers/update.go | 99 + derp/xdp/xdp.c | 585 +++ derp/xdp/xdp.go | 45 + derp/xdp/xdp_default.go | 28 + derp/xdp/xdp_linux.go | 282 ++ derp/xdp/xdp_linux_test.go | 975 +++++ go.mod | 5 +- go.sum | 14 +- net/stun/stun_test.go | 16 + scripts/check_license_headers.sh | 3 + tsweb/promvarz/promvarz.go | 2 +- 22 files changed, 8684 insertions(+), 11 deletions(-) create mode 100644 cmd/xdpderper/xdpderper.go create mode 100644 derp/xdp/bpf_bpfeb.go create mode 100644 derp/xdp/bpf_bpfeb.o create mode 100644 derp/xdp/bpf_bpfel.go create mode 100644 derp/xdp/bpf_bpfel.o create mode 100644 derp/xdp/headers/LICENSE.BSD-2-Clause create mode 100644 derp/xdp/headers/bpf_endian.h create mode 100644 derp/xdp/headers/bpf_helper_defs.h create mode 100644 derp/xdp/headers/bpf_helpers.h create mode 100644 derp/xdp/headers/bpf_tracing.h create mode 100644 derp/xdp/headers/update.go create mode 100644 derp/xdp/xdp.c create mode 100644 derp/xdp/xdp.go create mode 100644 derp/xdp/xdp_default.go create mode 100644 derp/xdp/xdp_linux.go create mode 100644 derp/xdp/xdp_linux_test.go diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml index c2c75173b..35cf0a5a1 100644 --- a/.github/workflows/test.yml +++ b/.github/workflows/test.yml @@ -194,7 +194,7 @@ jobs: - name: chown run: chown -R $(id -u):$(id -g) $PWD - name: privileged tests - run: ./tool/go test ./util/linuxfw + run: ./tool/go test ./util/linuxfw ./derp/xdp vm: runs-on: ["self-hosted", "linux", "vm"] @@ -480,7 +480,7 @@ jobs: uses: actions/checkout@v4 - name: check that 'go generate' is clean run: | - pkgs=$(./tool/go list ./... | grep -Ev 'dnsfallback|k8s-operator') + pkgs=$(./tool/go list ./... | grep -Ev 'dnsfallback|k8s-operator|xdp') ./tool/go generate $pkgs echo echo diff --git a/cmd/xdpderper/xdpderper.go b/cmd/xdpderper/xdpderper.go new file mode 100644 index 000000000..8d52e9353 --- /dev/null +++ b/cmd/xdpderper/xdpderper.go @@ -0,0 +1,76 @@ +// Copyright (c) Tailscale Inc & AUTHORS +// SPDX-License-Identifier: BSD-3-Clause + +package main + +import ( + "flag" + "log" + "net/http" + "os" + "os/signal" + "strings" + "syscall" + + "github.com/prometheus/client_golang/prometheus" + "tailscale.com/derp/xdp" + "tailscale.com/tsweb" +) + +var ( + flagDevice = flag.String("device", "", "target device name") + flagPort = flag.Int("dst-port", 0, "destination UDP port to serve") + flagVerbose = flag.Bool("verbose", false, "verbose output including verifier errors") + flagMode = flag.String("mode", "xdp", "XDP mode; valid modes: [xdp, xdpgeneric, xdpdrv, xdpoffload]") + flagHTTP = flag.String("http", ":8230", "HTTP listen address") +) + +func main() { + flag.Parse() + var attachFlags xdp.XDPAttachFlags + switch strings.ToLower(*flagMode) { + case "xdp": + attachFlags = 0 + case "xdpgeneric": + attachFlags = xdp.XDPGenericMode + case "xdpdrv": + attachFlags = xdp.XDPDriverMode + case "xdpoffload": + attachFlags = xdp.XDPOffloadMode + default: + log.Fatal("invalid mode") + } + server, err := xdp.NewSTUNServer(&xdp.STUNServerConfig{ + DeviceName: *flagDevice, + DstPort: *flagPort, + AttachFlags: attachFlags, + FullVerifierErr: *flagVerbose, + }) + if err != nil { + log.Fatalf("failed to init XDP STUN server: %v", err) + } + defer server.Close() + err = prometheus.Register(server) + if err != nil { + log.Fatalf("failed to register XDP STUN server as a prometheus collector: %v", err) + } + log.Println("XDP STUN server started") + + mux := http.NewServeMux() + tsweb.Debugger(mux) + errCh := make(chan error, 1) + go func() { + err := http.ListenAndServe(*flagHTTP, mux) + errCh <- err + }() + + sigCh := make(chan os.Signal, 1) + signal.Notify(sigCh, syscall.SIGINT, syscall.SIGTERM) + select { + case err := <-errCh: + log.Printf("HTTP serve err: %v", err) + case sig := <-sigCh: + log.Printf("received signal: %s", sig) + } + +} diff --git a/derp/xdp/bpf_bpfeb.go b/derp/xdp/bpf_bpfeb.go new file mode 100644 index 000000000..1883d52fe --- /dev/null +++ b/derp/xdp/bpf_bpfeb.go @@ -0,0 +1,166 @@ +// Code generated by bpf2go; DO NOT EDIT. +//go:build mips || mips64 || ppc64 || s390x + +package xdp + +import ( + "bytes" + _ "embed" + "fmt" + "io" + + "github.com/cilium/ebpf" +) + +type bpfConfig struct{ DstPort uint16 } + +type bpfCounterKeyAf uint32 + +const ( + bpfCounterKeyAfCOUNTER_KEY_AF_UNKNOWN bpfCounterKeyAf = 0 + bpfCounterKeyAfCOUNTER_KEY_AF_IPV4 bpfCounterKeyAf = 1 + bpfCounterKeyAfCOUNTER_KEY_AF_IPV6 bpfCounterKeyAf = 2 + bpfCounterKeyAfCOUNTER_KEY_AF_LEN bpfCounterKeyAf = 3 +) + +type bpfCounterKeyPacketsBytesAction uint32 + +const ( + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL bpfCounterKeyPacketsBytesAction = 0 + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL bpfCounterKeyPacketsBytesAction = 1 + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_ABORTED_TOTAL bpfCounterKeyPacketsBytesAction = 2 + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_ABORTED_TOTAL bpfCounterKeyPacketsBytesAction = 3 + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_TX_TOTAL bpfCounterKeyPacketsBytesAction = 4 + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_TX_TOTAL bpfCounterKeyPacketsBytesAction = 5 + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_DROP_TOTAL bpfCounterKeyPacketsBytesAction = 6 + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_DROP_TOTAL bpfCounterKeyPacketsBytesAction = 7 + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_BYTES_ACTION_LEN bpfCounterKeyPacketsBytesAction = 8 +) + +type bpfCounterKeyProgEnd uint32 + +const ( + bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED bpfCounterKeyProgEnd = 0 + bpfCounterKeyProgEndCOUNTER_KEY_END_UNEXPECTED_FIRST_STUN_ATTR bpfCounterKeyProgEnd = 1 + bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_UDP_CSUM bpfCounterKeyProgEnd = 2 + bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_IP_CSUM bpfCounterKeyProgEnd = 3 + bpfCounterKeyProgEndCOUNTER_KEY_END_NOT_STUN_PORT bpfCounterKeyProgEnd = 4 + bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_SW_ATTR_VAL bpfCounterKeyProgEnd = 5 + bpfCounterKeyProgEndCOUNTER_KEY_END_LEN bpfCounterKeyProgEnd = 6 +) + +type bpfCountersKey struct { + Unused uint8 + Af uint8 + Pba uint8 + ProgEnd uint8 +} + +// loadBpf returns the embedded CollectionSpec for bpf. +func loadBpf() (*ebpf.CollectionSpec, error) { + reader := bytes.NewReader(_BpfBytes) + spec, err := ebpf.LoadCollectionSpecFromReader(reader) + if err != nil { + return nil, fmt.Errorf("can't load bpf: %w", err) + } + + return spec, err +} + +// loadBpfObjects loads bpf and converts it into a struct. +// +// The following types are suitable as obj argument: +// +// *bpfObjects +// *bpfPrograms +// *bpfMaps +// +// See ebpf.CollectionSpec.LoadAndAssign documentation for details. +func loadBpfObjects(obj interface{}, opts *ebpf.CollectionOptions) error { + spec, err := loadBpf() + if err != nil { + return err + } + + return spec.LoadAndAssign(obj, opts) +} + +// bpfSpecs contains maps and programs before they are loaded into the kernel. +// +// It can be passed ebpf.CollectionSpec.Assign. +type bpfSpecs struct { + bpfProgramSpecs + bpfMapSpecs +} + +// bpfSpecs contains programs before they are loaded into the kernel. +// +// It can be passed ebpf.CollectionSpec.Assign. +type bpfProgramSpecs struct { + XdpProgFunc *ebpf.ProgramSpec `ebpf:"xdp_prog_func"` +} + +// bpfMapSpecs contains maps before they are loaded into the kernel. +// +// It can be passed ebpf.CollectionSpec.Assign. +type bpfMapSpecs struct { + ConfigMap *ebpf.MapSpec `ebpf:"config_map"` + CountersMap *ebpf.MapSpec `ebpf:"counters_map"` +} + +// bpfObjects contains all objects after they have been loaded into the kernel. +// +// It can be passed to loadBpfObjects or ebpf.CollectionSpec.LoadAndAssign. +type bpfObjects struct { + bpfPrograms + bpfMaps +} + +func (o *bpfObjects) Close() error { + return _BpfClose( + &o.bpfPrograms, + &o.bpfMaps, + ) +} + +// bpfMaps contains all maps after they have been loaded into the kernel. +// +// It can be passed to loadBpfObjects or ebpf.CollectionSpec.LoadAndAssign. +type bpfMaps struct { + ConfigMap *ebpf.Map `ebpf:"config_map"` + CountersMap *ebpf.Map `ebpf:"counters_map"` +} + +func (m *bpfMaps) Close() error { + return _BpfClose( + m.ConfigMap, + m.CountersMap, + ) +} + +// bpfPrograms contains all programs after they have been loaded into the kernel. +// +// It can be passed to loadBpfObjects or ebpf.CollectionSpec.LoadAndAssign. +type bpfPrograms struct { + XdpProgFunc *ebpf.Program `ebpf:"xdp_prog_func"` +} + +func (p *bpfPrograms) Close() error { + return _BpfClose( + p.XdpProgFunc, + ) +} + +func _BpfClose(closers ...io.Closer) error { + for _, closer := range closers { + if err := closer.Close(); err != nil { + return err + } + } + return nil +} + +// Do not access this directly. +// +//go:embed bpf_bpfeb.o +var _BpfBytes []byte diff --git a/derp/xdp/bpf_bpfeb.o b/derp/xdp/bpf_bpfeb.o new file mode 100644 index 0000000000000000000000000000000000000000..15a96f5ba38fea9ccb755ea799b4e9f10ee5333b GIT binary patch literal 23640 zcmchfe{5XWmEZ3Sf6Pdx$l))W*{b!EEz2WClt;8gGwWD8lte{}6>%(5mYl3IGvW_% zRunnn3@xfkyHji(DCq*Fcb!&$r0pbe8o66=tSfbh+4eD=bp%08LS0 zH$~a5feNh=_Iu7fcX;QBRMMu{2hZI1Ip^GS?>+bDdqeq`M^2vzheM`*h0OoNy(g$^ zaPw9lQ&PTnm{4Vy@6FwWq%lszH@~sIN_W|2)68j+<)(7krjZP%?RQg_@7jC@`5utu z?y|^BoQC={p((n%_M+Lr=`*H{(#tkqbhL{I`2tSN&2L&iy)kpjm@ogwdO6DPxmf7) z#zc+iLzQQ2{)qMaoURAzcb_c!W1%rhUA}8i6FpvU_&)>jc-`(9!zF0HutPmfr?bmF zV|vKnd9KGVtZ!m}jP!N6t#7^kl|j-PQ~9!_lQzAZw=(*!1ol3?%ckc!Szo_y<*^Q%nj71#|BCd_bz9F^M`M3Ax&CtPx9whE zzguF*A;jkes=;I9BxUs#Y5%j*54jf&OX~3vKNq_~J1Ivb&-wOw{;DL=_Wk(~du%ag z59@6?_3^F7%b?Uhto?Z7hR3ZNFSebgW2<~pB>lFx_(KK)`af{oQBXpRk}l5+2XE^U-;&C>^#@)z1U^`8`)P%^li+|Z_7B4 zb-=}a;v4H9lfJT#zR@oM_44}1G~WD6#%D;zuetGgTi;$|{+R44c4acpLO@sUuw8eY z{l#wc?@2D)oD=`K7fhJs7k8OIptOQfMi?BF%+He`_q3gtxf6E%>5%mg za`xD9kgV8_$4%}{(@xy+27R-f`K4`)RHW zSbwiIuYW{$t{xpCuRL${;xB}Hy+{&-o8z06eym9QuiJRUT)WOE$$EX=#V0#x+f|YJ zYrWL7o*!}AMjo6$SHHiYIQ`zw5GS4&*Cc*!z3vOtJ|N>gE%A2kx9b|>Ci;quBOTwn zNs5jMJNt7nlc5qSy(~Af5APH^)8A))ku;dMJkp%}TwvaUIFxyk5=N= z-?MJN3W(R&u}<(jboLhqOo}vW9SEGhKWH z)W$>d^=;v=4f6X`pDP14{t-LB4`Cmwk{tEo@+)rq$T)mf`qAxk?~t)E!{;!?=*G#j ze?!ilF29UF8BgsPM?5cGdA)&ogY!!{vR(|LznfXky@h=tNo0=npS1OBF=mVecT4nb znq(gg-?i%qoo81`;qe1z+g?+_D4`4M?LA82kK=greK`kPKlSs5loOKvcr3r$hqFE8 z4FjiW>yLJFxrJ}8|2fGEAFTfmN-IuZ!s|Ixl*BYyT8eZ#(SpI+N) zpRVw3iFl!%*w1UdM(SbP-2*=V1(?fZtb?~ZL>;U7x7 zKCtb=d8M{lIoiMY4gI8cbjb6^mV>;IJNJ!}msV>XSX zINeuyTI7>9?Z2@8A>CDuT8<<+-PwO~{U6btk_V7~hvb;wRZ4r4_I#o24#Do5q?h`K zuk1DfaZbwlPLgO>7v#KNWryu}CONIc6T4;KJ!<#S>>GBy{wE`p&lu==hG&o3a~AYG zVm$qRvXk-?l`s*;nN9j&&m+IZSih?Nan%2-WGeYXKdJs=x0}wnjR%;^5q%WQ^>F)2Z^E3VoY{kRoVfEM z#$6A|M-S0AoQ@uyd~z-dke~fR&-DRwK2IM|zTAL~o10e{r`&&6o+mBl@4GgQEOQ#~zrFqv-O0M0 zEOgm^tDk%JTKg+qHhz^)S(be_+CQ}ZB1v)*p9)76?;p4yagLMq270c)$2=Z9w$B?I z_8c!y&+%~V_OUD7<^YwC`tkhE?ULsvsRx+PSsfe9arZc&{2q5H=Jm+ab3b{^{opaL zs2=a}{ax#n=N~>b)Yp?k7_4+YGnKzX-xwF4kag};cHB(-y5)&?E$6zVp9icx`q%dJ zF3a`j+E0l7U8|S#M6&R%9iQ%eaphe(&vJC?vm|1a-%wtBDg z9rm}r?&>4sbZ7tVAOA5G>Ea{u9^KB0wEuiS*6Ztd?&5Le_B~l&Vy=JAC#+q4TyZ{( zr%U$v_e$1|+pIjNYyZyAbsM*sd#=WN8eShAOZ?&$=@0i@*x&c#3e~{%L;XFb_2=eg zy&wJp;?C>%-4fNxw8%NCS?bs1&ZRBp$G^!IKjYV*{R3XMd2PT^uV_DAzejF)K;vwT z+Ynnpi8LS`FaC66&1h{W^A=}^`v4#3gWI%89?Iuzczxf*hF!vtYy*6#2c;NZTQGG^ z5+7OzNnXN-W+m-^ReX-{iyXt_f%8ebcwBB$9{F>1;;ft4a9za@kCex3!V&hP>dkvD z+|!!q*PGsrm++x_)ALXjpHourPTc$TruFYl_@$Uqzg@(q7azJV;Y0TUK3C*EiF8r! zGf3Z&`x4UkO>8@; zZhr|MTpiQmANxqhtoWyFh+oG|X=}Z2#ox2geMMr3q=Q!H03Tc(e-B>)K5*MnmV5H` zzT6`=9Un@WyKw(qDU%Y)Qu;;&ml#( z#}131=dHdzb}$}eufq?mL+}%uMT#r-x9~-N?jR*U{{|`f`BS8@>!fjuvC&EXk-c*m zDP)~rM2dQM{)&{h2kh5-A9TNg43wYzRFUH9`~kjT*F|!a*A+*K^14nUgLou9kB7iRrO zoc2}UJfLe!bC~9)gLvK9RBhAa3pZvxOg&xuK&mkHKjNoy!KjfDLX40c`Tirhnb~01Yr)~*OJ6eEwrwL3moPEU@>8kQ+0pUQ z^tt0Hv51q&^g{M>dVYF3*yB~>R4VVzj%I5zh9Bky@)SCR5Z3|Py#f7=xufrHcbI2wN zUX!R-s2Apn^D_mGOL4xKo}HTGcDoJ?`n@)7+Czg+>Y~B^BX486rpnOq>D*GU`x{ffanpS>|VpPhVC?G`8VoLzd#PFc)s1Ux~Zw==^|Wy}oeKg{X$ z?EL(d#e8~dcIs+;&&FKeA2@&)>OBhBt_d!rF?J}r|Hu;p=c=|zuF0uFk>fpq8CWQ$ z^YaVfo6=u7EFSr{F-k~~FH9{?&Ijm!j$k1>Ik|8kH#eAGJg_*JCOSCyh1^9{bi)!Q zQ_LXqgq(fyr^&uCN&QZvSWM3^1aVq_avWbIpQb^}Yv-#V)N;U9yD){x0^E0LaT*yZ z25yo-LSrZR^lOdlh3!IV1%^8qQ-x+OH@cyPqU7<*TA5gz8IcEW_hw4=z}n3`_>tIH zW8A244T>*JUE6dvP^+QqKSKKr4f+j#W8>$}q>r9DbNtkq&!o?eym4-1jFz68HdJmN z%-ZZ%vzK!ifpEatJ~#ZCQ^(krLlk6-MQlyza9U;J6EoR`VBcOhllRh8c0#sv)pvyy zY$3>hxj4h6)E(910x-`4f}3lmep7xgsa z`H((=o=lCN9Z#c6sb9naEqGr@T!fFU*3Xv*NWbBAHtx+ba^!o;{RB_Ye=)ElXel@O zgIWu9_K!w z6Nud`WH7j00VhbP>@Gkm%8nfVppzj;)v(Q*Iye|mFGx|It;8n z9&(i1e?3~hL!Q_O}F*`O%5xJu(b z4Hw5o&z%_`Ih%fcrQSTWiEL2IuzIONT{(WS`Rv4%sbT>e zIyT<4-ToRprG}5aJ~BR*P7RNZrN>9dhfg=CkG?fNvZd1H9X^V^45yNyFXrr~RdFTMDnA>nuK$eH8l-Lcfju~R2b zjU3-ZH*x_=3fYNMXUE3V^)udMrl-!lIehvQ+#OG)kBy!C+?ED-DX^*j%&54h^Tw9B z$Ihquh>5};v)L*%uH^?V6$<76j%o#ZuO;u)1G>jW?`!et`p5WGNq~#qjortG-`^pn z_qg;P8L|-GM8(|f--KHyNlX}Uw45WZlVzK3^sW=3&d_^+9! z8oh(Q?J?P}3V&dlenjtfA9;-ThM}nNzco!CBY!CH7;Ou=@_%TWn_(L|DSBeqhAvnR zx0>cC-iL-V9^?IAXvuPj{8M?iME?t>c_-d4ho$`Rmrdvq-a&?Aq9?}d%5a~@c>f)a z3;!z<`k3@X9;3ZsSD!z}8%fkBJY)4uA=A7Y<%gyGCj9C;g#HNM7CkZPR}?=Ie%&t>y$zfZdt$uvZgS-l?*hB>i79_o?0>^FSMhss(?gG;Z|+l^ z6#i4w5{*KivW#!OnlB*1_`%OPEp3Qbb4mEPX^9~|%~F2zsA&oIfNzVQnDloP-xGev zv?Ngf=BmeJe_!#cWqkA1TthdpQ-8O1 zVk*Ku67v}4MWp?$gC_iS(g&g^ru=csG=9pYPg-t~ctu=1BwqZl3{W1&4`oM6%Ko0P z#3ORwW5g@+z+=QSQnQS2zM?54@Q?MTWftQ-D&@C+-n87p`Www#Ju~u0mxO=WwA@C2 zMsImc`eotYHZAWHmlfX;u9=p5Sf8R&|Hvmy%lELJMypoOO!-$8OM4`^D z81@J$w1J8MTiY>%q2|$GgFO9+Q0_{9V(!6SmuiJSP1~;XgF3hY+uADa98Q zXB5vU&MRJ0TvB{X@v`FEipz@cC|*%~PjOZ8s_;jq^*xHmBg@fd)4Gh`(zZv151ZCm zjQ8y^%lPJNdlCuy!(H1?T8_Y975=uTEZ6lCkLaXn{Q>E3S$&DhJS)MgK2M z>yNM=Y`+ZQ&JwzJK?oG;Ih@@ zJQV&B@k7heKQZA)*iWB&WZBsxB;5Y!x(VOM{Avr7K5lv2t0w$?)Tb>WeA(!JclJ9@iv1Tc6|jEqkn%zwn8<$AcgKv? zGb0{5%9gP{L{g+*@fh{ranCa5Yb1mDy5qjbq?dS8{ENgjtKT+fB45IJV27(eG0MXc zirc&GYbJ6l2965R&ztPI`>-(SFk70dUG=w6|U2SI?jE^pt*U;awTcZEZCh`&1=a`h=)@CA)(4U=sR^Rrb ziF_ObUl2ZGq54!Xf(x0@vJ=RJG!zvMCLOP)RHZ+T4mWzU}Uw>>6(*|R789gj)B z;@Ok_p2wuGdiJEh?=k6DJ$uqW@R;;9&z|%TJtqB{FrA-qcg^XvO)f6pCZ%&+@Y-il|B{_eTwG3oDHcF!k0s~+R|r00RKJfHN`Jf{2)ExYHF zo=2A3f8RtOVDagVdW?AY_6dJ%qCZ6ZdNYkhfNGFIOmq8?kRKJ1Oj`O-`QhEuhE zyevXWsO`>=Uv7Rw-j*Umd-1zK=fBTM5r-J=Mb76br+Ty@=W~z9`5mIzcl&YJ zoS%Pz2r4JM*6eks@6lWCY6_*q*D=sTuQCwBL zs<@_jt&w>f@Y>%JQ~E%0LUB@YN^wSUUU5nBvf{Gh6~$G>tBPxi*BY6(O|Si}F{KX_ zCln_Yrxa%t=M|R}FDou9UQt|CysEgSc&(9f)NWY+_;&~|9+5!l6N;0HQ;IW+^NLG~ zmlc;4uPCl6UR7LEyw=E3puhh`V~PXC3B^gpDa9GZdBr8g%Zkg2R}@zjuPUx7UTb7L zN;b5gf7kH(e_NpR3B^gpDa9GZdBr8g%Zkg2R}@zjuPUx7UTb8$N@-|6|IXmGe|wc6aZ+(g zaYk`oaY^yA;ZDo!cRD9$S`DPC4wR=lFP zs(4j#P4QYI$AJF+A0vU+{#c+mp*X2Hr8uKFuehXmS#eqMisGu`RmC;MYmJOIH4W|U zj42KjCln_Yrxa%t=M|R}FDou9UQt|CysEgSc&(B7cQCKN`FAg$17)93oK&1roKc)t zTvEKOxU6_ZaaHlE<2^6N)t?d<=x>S5fg=75q&cuKHGAOb_=y7y8-MIca{AZ4^*@-l z|N6N850UGCR?UAA&3~M{>7Uacn4Nw5D*tN;{KMjndXS$D+VFutq~6T4`)kyOe{F0I z;2%{MvzL(GxXP)t#hgBRG?9MgQ#KuxbU@NqUJ<#Z1CqWnDESWC^suA@k{*vbv4)P@IjltEa`xxLkY2$^kqp8CeV}rf3E)kH|o8yb9{cx z-i4}8A}P%Qcj5OHUK5G+d*&nwH@V#VQBu8vkMp-hetwVbyWs~j5xk6)A5@SgMJCCy zn%tz2(qYcE)8&sr7RSf2(?dkp(@st{{^jH(>&M5{f2;gSGW0G#|DQqb@_Qz9`}9dG zc;*eI@Z!EjlFOCe|3UD#kHZne*!(fsP!_+ZL(xrin!q)OSVthT`ia5 zh7`HvE^RVOTiUS$B`t95HED&ScV%q_QCs+q%@t>%7jzeg_Mkf$R~}llD&V3ETn=Zn zIbhqmsBmZ0_kHu;><*tvIoGu4z{~l4-n@A;^XC6=SN@s)b7w*g4aS8A^LM6BPHIf~ zx%zY5KE}-sXqNV{{H-k#BXbCk*B)N`fF$YoR-2H1+D4}IBFEt-V|L>4tw!dzq|j>* z-?jPP+9vXdvGs{IU9}psbK7mg?CcI3Ux5@VX0ToKsc?jAN7znV!{^P{|I8~#*&S`T z+(7xM9#lYSmU0^t1{^@F>v8SjJGOq&h8IY^mTxvq^kMzchG!f4NiOzhXCK-`?~4t) zJiXj3JN5!f`AL+h>oMB!443cPV+nfF{!+#kV@eYepW*l|bO%{>e!up>ZQGvLAlr{m zX^izsU+38M>t1XB1FK6ZB`GJloAoXrqSTilZ^3i3q%W?p{Zc#Yy#zZpU6|@iL&x=( z^Aok3?7b!ZKiUv&unakc+Bk9jCh|wpoSvJbQjB>=>ZAR4sr^x#BOEs72=waXuWZ|> z^`qgBTm44!DQlPXsfli!`{SmE?4e$iuI<#vPph@(#tpT%dY^ow4LcfANS~E)v6=nR zhKL(lJjE0(&LYxS1=m)if-CXhW6<;Xb2L)5DJIJ&g^k1UslY-Ff@q_OyG z?3cENCv8G5&GR=m#_LrxqsgUtTsF6I{#^QFte>UT5c8(ZM$lvb=28!^oU@tc1gAHj za(V~tLvD;_FY?#Q2`uNbdu{COHp@EQ+;7Dw=K$-CJ0RXXg+DJj0X#eldHIg?pUZdY(S*(5uMYtvE@?@U&SvfPL0$4~@i{otID5?4Y~MEOaT1hT^7(cy@>#KN>n= z(w13aH1s)>v&@bk4Sm*3Sw4url)u+ZTjudT8tO4KmU&)}hPus|W!?uzLtQ2dw)1rl z*1TqMRGcRPIhy@Ode!^SbJEyHnfMXT6{z7Jj(qL zh8>z>i?2)hysa5G&fL6yg@^ar9O8Pov=lh|W1^f;}%Ft9Kre{gl<~=N?iVt@VoT|3v_LO!zR&MEFZW%~nio!{--={~ZG^ZV0W|HaqYUg5~!Si6N^ z{%aeTo@Kql^MA$i&sMoy6iQXTcBEqY5kB@Be_yZOXJ0S9!FH)%E6{7RyE57-exQD^ z_IY_VCFhUVB_GNs`>s9u{NUyh^*{M%@z*L$?YqAS=#l>+^%b1;r9GvwWE2K z>wE1Z+VPR~U*U1`Z8m58ad-f-=qvx8`wMfFLg_fi;YL3HmeS0nGaN@>dz1AKiXMgm z&DiLxzwse?VCCPn^2M7x|Jt_lxufLer}-Iu^>wRf{SU`ao}}DZ2Sx9@D5o83?c_A#ZfLrV_3G(IZ90`7!&51+XmETr zRO56T=W8@<*RMZWj=uWMdi^l~KdSyz4%L{>>vlg$0T8G>Dxq|k2`Qfr(1bk)b+%FH9cM*(ycuHGo75CZsq+h)5-bMt${V1 z>Ev?Ktp|m<9*b|VolGa&q4N>t$aJ!u#W%Pp3IoHnpntPP>C%c#@xf%8x5l2#CANNP?Ui|Z{{|@Rw7AN;{J~}T@nB2$x zrHcx zt^n|`CLh#$ot-wut(XOM<*XYEX}p7~kC zq<0H3+4--C$pK%xNmG12L6%7BQ7Kj+n~(CSoe@-ylZVc^H2v-|uj`^}@#~1%c{uz&`QwC%xwm z@A=c-a|w1(zO} z?kidIVtQ&m%a2#n3(4$saW0oFn9R)dc>TX4j`Clk<;vnfd8L?#gs_ET9T!iVKFy z$j{AONsiA?XNb(P$BsRQ_*jM-6|76|C=}=BGc3G1794?r!@)JP?ZufKi0VmI44w)) zSaP^yYG(S%VW>qQK#%2OTwI+2Ta->7es)a3XNlZ1JRowCITmYD#e? zcX7NzNae?@1DM z_Pmh0go@TRQ8M`qGEZo;kNqgw>yy;)H1fsx%v{hx>rc-57t!Zv(Au^0Nf2t;#nmok zFrC;2xn|hDkr^AL5gXf3)eOJ%k#OZVs0A8 z+pC%UBAw}y#j7~!$l;E=w4Vw0i8g2vyj2yb_JXuk;JaTM#amF_Hq`9djVs|hzrG{WP{}^tC0>U) zf5W#&`w#Vtl@^Or8@fhLvm3i5N8QTV`OpisdUf4F*y*fmAP&+0pJ)F}LA)P5;VjvE z1KlK&<5Rgjt^ihp`&68@amA5{TKT6aNU(?$XOh+?d0t(=?qA^}hhgBTpZ_TCIaD3U z?_Xg)D;sxi#RVJZwE7jcFo9VCq}4qsy0!Z=HWx`U>2Z_4oHq8BOE+kk>8)F#Q%v26 zY*3V2OeOK0go#swqvuEZhmz0qKbPz~lN>$&%=y6!=e2ks@oe`7vK}qN>ZJ;G<@m+s z)0xR^v49O78*h@gzjc-peW#x39~n+2`i6&-BZDJ-=hh{kd~T$F(?plI?BR>P3BPmu&!0x` z4k!9g4V)S1KfOU(|3xH{%gzi84UZ&iXS@%o4xE3s@7w^)olYcA4Uc|dQw6*f*f9P4 zpqQug#-_Q4FC^^|6NP<9XEWEhmLI!ZD41h7suk#!7rj%bcUu(beJy?7!Hce{yzHX) zXLsBN7J&!L-J?DvPnqyayZ;{sH0$-qfD; zH~>?0K5hR0#>ZN>CLmCAnx z@t&XCYI;2mgX6-ph`0X={NwQ+@PxBsvPxf5>33CnMcB3HU8UcG7xmP?u0DbAQRr!QPNr@Hhg#uJp^o-++G8>5y6TcsID>F{M|9--Q1Dp9`6L!hZn% z#B#_)@P!7|pLiR%MVRz=L4U9CdzAjIkO@3~2;AZEc5tsSebvA1M##iH{sj1}a1W*b zO2{NU-VRO)TYs&&0)-B$WlVdpRU!i3sOO#W)|nEbU@*p2_|!gf8H z!h95d9`$d%j``%qaYdN=anEhcPvL!N$H%|l zXzqF31a85XTGSp&C*CXE58jQz9rL&e92d@!{`Mww*5h_?!sCPBiyo7HO89%o-?G2S zEO^`mzApTSNDp^6nPtT{6t5`0rFd2GZN+89cNDKFzN@&R_+7p)e3jP*$<84Xtbzy4{lYd#I-xeN&y{31X%pJvdg};sT z;N2!u5&m89{vS4(cZDxvpKp4v$=p+H@I^Vb&z6sGKU;+D{))vT@Hh;!2iN-d`$?SMtbO-uz6Q_k+_2X!DWNW{~qxV!sfQ{d({8cu(>1rKat)J;a>cP zfb_R-M}OW!{|SEz-10vBDSU#`gNRuXz6jp8KVohPFMzinjF?qVe<$>B3;#=`hkGOD zj^ew*zm4?W=OU&e{NKUB>4>QcH)33W>}feR*J=jcJJPw2R3cK@G zAWY}02d1!ocueQNn5X{$&ZE5^)A=;+=~I6Ctp%0u&T9!zpYmVynDVDQeab)KF_oY9 z^eO+6@CCGQ=go+@?xmBxWiLP3yCIx|{`M90mzPfVZ+ZF2{;J1h@3yB;_R1bp{yUyN zDc02vdJj{uYlZ|6Wg@@&_JM`5nS^ zp58|1X^-iA9T#@z>y+>};m_7c#7qdk0e)y}#N>s`;2ql|X2H|n0sSRmH-D}RyZN&$ z?B>r6PoL(`E#W_g{RjUA=9lmf!TU!drYzisb!gW`%rB3d!FPo}gY+FK%rD{3gCk=R z6T=G(@~^vp_j*kC@3_Zw|2`}1?%x+Zru%nFxOV>*{u-4(0e=bG`Fb1v@;D4$5=ND5 zSQh>c^6&pWjAvmQ-#hQXKf>-lvMTKEBV~{2K61y?r~Am7u)B}k^_cD>6_4pYQWbXh zk$b{+e!d+s5&TGx{AuSO>enJn`gC8}E9~wofyZ=Ti3z*=N?iC4(Eid&&U>(4chsXy-uyZ)>QcVpk#@h;Zij|f}n1&RtQI2+P0 z)#z;Jhub2@F>YOmi#&!o?}tF-H!<3bDl5EkJqKD$i4a|040(7!q-c|d>=*uS{rBi?1OaY%68NyU=fv5S96 z;ocv8ZlbwKs2u?mB(wdmJeC*Bcs2ah0A>oKl=u zyrg(p@rvSA#bw27iYtn%irp4KVrox|YzdA7#WBTk#R#`Vk74=*WMPzf#R6r zxZ;H3l;XVNCB@5%R}`-*E-PMBTv1$A><%Wi_RB%VaiBP+IIcLMIHfqRcu6r{^Vs0Z zUs1fOxU6_haYb=evBA4c3a-2s#dwXoEwm?8;+SH0e{uN}Dm|r`zLW9& zxun?LGo8H^mAmOH~P@GbnSG=TnS@DYERmEk+ zYl(`)Tl94L+{jw?#r!WFz4cGtPdI-B zis?I@b^Wh6p*W>DuXsuEvf>rRtBT8t*A!P2R~6eIw4p(+y)7;4+ZQN~DUK^nC{8KP zD_&B(tawH7s^YTZHN_RhRmFHoV?(X|iUY+l#c{<6#VN&k#Y>8p6|X2>Ra{oQrnsWG zsu(ZR*0*1Apg5*Dt~jAMr8uv6N%6Ac6~(KH%Zk?&R}@zj8+q^O`v1_UI@C{<3-nuM zbF7GeV`+}fWv7mv9658$LjA|2B&UB(T>C*b|Lf-3KXk7BY}@|g+Wz=?!=LLOo0@v@ zs{Pj%_=n5&dXSwu)otL1+8bGRzjj^subIs;{G-ic`ZD6ht2UOlm~$sj#*$BbhT|TI zyCi<%36V?OCGitIlJ7Xj$0hEPxKrZZZcgu#`1s?(68CnA9f^A+#=qXS^*Y|k@#7MA zN!%M_d5^@8OWYab@%-cd{Sz3FS0(FA{of0W?!B8!l-Ftw4ZXG|nOrw(@_6lO{R53Z zKRf}rUw-%A+vSmKjYIP|p6I9_uSxjf;%SZ(BB$dJwbSL7<=f$G0m{>);zN>ABJIEb1^Gtpza{O@OFn8pU5Q=!uKn~b zeWUV!Kn+7^QQueS^6CGlu~GSZ`)zjnT{=Bc`J|`IzXsWsb05qgTEeFm?#cMme${pT dbL5a$owdC5a4*i75(AWv{$C%ieD^)Z{{zL;+1LO8 literal 0 HcmV?d00001 diff --git a/derp/xdp/headers/LICENSE.BSD-2-Clause b/derp/xdp/headers/LICENSE.BSD-2-Clause new file mode 100644 index 000000000..bce40aa98 --- /dev/null +++ b/derp/xdp/headers/LICENSE.BSD-2-Clause @@ -0,0 +1,32 @@ +Valid-License-Identifier: BSD-2-Clause +SPDX-URL: https://spdx.org/licenses/BSD-2-Clause.html +Usage-Guide: + To use the BSD 2-clause "Simplified" License put the following SPDX + tag/value pair into a comment according to the placement guidelines in + the licensing rules documentation: + SPDX-License-Identifier: BSD-2-Clause +License-Text: + +Copyright (c) 2015 The Libbpf Authors. All rights reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + +1. Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + +2. Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. diff --git a/derp/xdp/headers/bpf_endian.h b/derp/xdp/headers/bpf_endian.h new file mode 100644 index 000000000..ec9db4fec --- /dev/null +++ b/derp/xdp/headers/bpf_endian.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_ENDIAN__ +#define __BPF_ENDIAN__ + +/* + * Isolate byte #n and put it into byte #m, for __u##b type. + * E.g., moving byte #6 (nnnnnnnn) into byte #1 (mmmmmmmm) for __u64: + * 1) xxxxxxxx nnnnnnnn xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx mmmmmmmm xxxxxxxx + * 2) nnnnnnnn xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx mmmmmmmm xxxxxxxx 00000000 + * 3) 00000000 00000000 00000000 00000000 00000000 00000000 00000000 nnnnnnnn + * 4) 00000000 00000000 00000000 00000000 00000000 00000000 nnnnnnnn 00000000 + */ +#define ___bpf_mvb(x, b, n, m) ((__u##b)(x) << (b-(n+1)*8) >> (b-8) << (m*8)) + +#define ___bpf_swab16(x) ((__u16)( \ + ___bpf_mvb(x, 16, 0, 1) | \ + ___bpf_mvb(x, 16, 1, 0))) + +#define ___bpf_swab32(x) ((__u32)( \ + ___bpf_mvb(x, 32, 0, 3) | \ + ___bpf_mvb(x, 32, 1, 2) | \ + ___bpf_mvb(x, 32, 2, 1) | \ + ___bpf_mvb(x, 32, 3, 0))) + +#define ___bpf_swab64(x) ((__u64)( \ + ___bpf_mvb(x, 64, 0, 7) | \ + ___bpf_mvb(x, 64, 1, 6) | \ + ___bpf_mvb(x, 64, 2, 5) | \ + ___bpf_mvb(x, 64, 3, 4) | \ + ___bpf_mvb(x, 64, 4, 3) | \ + ___bpf_mvb(x, 64, 5, 2) | \ + ___bpf_mvb(x, 64, 6, 1) | \ + ___bpf_mvb(x, 64, 7, 0))) + +/* LLVM's BPF target selects the endianness of the CPU + * it compiles on, or the user specifies (bpfel/bpfeb), + * respectively. The used __BYTE_ORDER__ is defined by + * the compiler, we cannot rely on __BYTE_ORDER from + * libc headers, since it doesn't reflect the actual + * requested byte order. + * + * Note, LLVM's BPF target has different __builtin_bswapX() + * semantics. It does map to BPF_ALU | BPF_END | BPF_TO_BE + * in bpfel and bpfeb case, which means below, that we map + * to cpu_to_be16(). We could use it unconditionally in BPF + * case, but better not rely on it, so that this header here + * can be used from application and BPF program side, which + * use different targets. + */ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +# define __bpf_ntohs(x) __builtin_bswap16(x) +# define __bpf_htons(x) __builtin_bswap16(x) +# define __bpf_constant_ntohs(x) ___bpf_swab16(x) +# define __bpf_constant_htons(x) ___bpf_swab16(x) +# define __bpf_ntohl(x) __builtin_bswap32(x) +# define __bpf_htonl(x) __builtin_bswap32(x) +# define __bpf_constant_ntohl(x) ___bpf_swab32(x) +# define __bpf_constant_htonl(x) ___bpf_swab32(x) +# define __bpf_be64_to_cpu(x) __builtin_bswap64(x) +# define __bpf_cpu_to_be64(x) __builtin_bswap64(x) +# define __bpf_constant_be64_to_cpu(x) ___bpf_swab64(x) +# define __bpf_constant_cpu_to_be64(x) ___bpf_swab64(x) +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +# define __bpf_ntohs(x) (x) +# define __bpf_htons(x) (x) +# define __bpf_constant_ntohs(x) (x) +# define __bpf_constant_htons(x) (x) +# define __bpf_ntohl(x) (x) +# define __bpf_htonl(x) (x) +# define __bpf_constant_ntohl(x) (x) +# define __bpf_constant_htonl(x) (x) +# define __bpf_be64_to_cpu(x) (x) +# define __bpf_cpu_to_be64(x) (x) +# define __bpf_constant_be64_to_cpu(x) (x) +# define __bpf_constant_cpu_to_be64(x) (x) +#else +# error "Fix your compiler's __BYTE_ORDER__?!" +#endif + +#define bpf_htons(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_htons(x) : __bpf_htons(x)) +#define bpf_ntohs(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_ntohs(x) : __bpf_ntohs(x)) +#define bpf_htonl(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_htonl(x) : __bpf_htonl(x)) +#define bpf_ntohl(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_ntohl(x) : __bpf_ntohl(x)) +#define bpf_cpu_to_be64(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_cpu_to_be64(x) : __bpf_cpu_to_be64(x)) +#define bpf_be64_to_cpu(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_be64_to_cpu(x) : __bpf_be64_to_cpu(x)) + +#endif /* __BPF_ENDIAN__ */ diff --git a/derp/xdp/headers/bpf_helper_defs.h b/derp/xdp/headers/bpf_helper_defs.h new file mode 100644 index 000000000..6f13d1f1d --- /dev/null +++ b/derp/xdp/headers/bpf_helper_defs.h @@ -0,0 +1,4766 @@ +/* This is auto-generated file. See bpf_doc.py for details. */ + +/* Forward declarations of BPF structs */ +struct bpf_fib_lookup; +struct bpf_sk_lookup; +struct bpf_perf_event_data; +struct bpf_perf_event_value; +struct bpf_pidns_info; +struct bpf_redir_neigh; +struct bpf_sock; +struct bpf_sock_addr; +struct bpf_sock_ops; +struct bpf_sock_tuple; +struct bpf_spin_lock; +struct bpf_sysctl; +struct bpf_tcp_sock; +struct bpf_tunnel_key; +struct bpf_xfrm_state; +struct linux_binprm; +struct pt_regs; +struct sk_reuseport_md; +struct sockaddr; +struct tcphdr; +struct seq_file; +struct tcp6_sock; +struct tcp_sock; +struct tcp_timewait_sock; +struct tcp_request_sock; +struct udp6_sock; +struct unix_sock; +struct task_struct; +struct cgroup; +struct __sk_buff; +struct sk_msg_md; +struct xdp_md; +struct path; +struct btf_ptr; +struct inode; +struct socket; +struct file; +struct bpf_timer; +struct mptcp_sock; +struct bpf_dynptr; +struct iphdr; +struct ipv6hdr; + +/* + * bpf_map_lookup_elem + * + * Perform a lookup in *map* for an entry associated to *key*. + * + * Returns + * Map value associated to *key*, or **NULL** if no entry was + * found. + */ +static void *(* const bpf_map_lookup_elem)(void *map, const void *key) = (void *) 1; + +/* + * bpf_map_update_elem + * + * Add or update the value of the entry associated to *key* in + * *map* with *value*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * Flag value **BPF_NOEXIST** cannot be used for maps of types + * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all + * elements always exist), the helper would return an error. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_map_update_elem)(void *map, const void *key, const void *value, __u64 flags) = (void *) 2; + +/* + * bpf_map_delete_elem + * + * Delete entry with *key* from *map*. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_map_delete_elem)(void *map, const void *key) = (void *) 3; + +/* + * bpf_probe_read + * + * For tracing programs, safely attempt to read *size* bytes from + * kernel space address *unsafe_ptr* and store the data in *dst*. + * + * Generally, use **bpf_probe_read_user**\ () or + * **bpf_probe_read_kernel**\ () instead. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_probe_read)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 4; + +/* + * bpf_ktime_get_ns + * + * Return the time elapsed since system boot, in nanoseconds. + * Does not include time the system was suspended. + * See: **clock_gettime**\ (**CLOCK_MONOTONIC**) + * + * Returns + * Current *ktime*. + */ +static __u64 (* const bpf_ktime_get_ns)(void) = (void *) 5; + +/* + * bpf_trace_printk + * + * This helper is a "printk()-like" facility for debugging. It + * prints a message defined by format *fmt* (of size *fmt_size*) + * to file *\/sys/kernel/tracing/trace* from TraceFS, if + * available. It can take up to three additional **u64** + * arguments (as an eBPF helpers, the total number of arguments is + * limited to five). + * + * Each time the helper is called, it appends a line to the trace. + * Lines are discarded while *\/sys/kernel/tracing/trace* is + * open, use *\/sys/kernel/tracing/trace_pipe* to avoid this. + * The format of the trace is customizable, and the exact output + * one will get depends on the options set in + * *\/sys/kernel/tracing/trace_options* (see also the + * *README* file under the same directory). However, it usually + * defaults to something like: + * + * :: + * + * telnet-470 [001] .N.. 419421.045894: 0x00000001: + * + * In the above: + * + * * ``telnet`` is the name of the current task. + * * ``470`` is the PID of the current task. + * * ``001`` is the CPU number on which the task is + * running. + * * In ``.N..``, each character refers to a set of + * options (whether irqs are enabled, scheduling + * options, whether hard/softirqs are running, level of + * preempt_disabled respectively). **N** means that + * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED** + * are set. + * * ``419421.045894`` is a timestamp. + * * ``0x00000001`` is a fake value used by BPF for the + * instruction pointer register. + * * ```` is the message formatted with + * *fmt*. + * + * The conversion specifiers supported by *fmt* are similar, but + * more limited than for printk(). They are **%d**, **%i**, + * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**, + * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size + * of field, padding with zeroes, etc.) is available, and the + * helper will return **-EINVAL** (but print nothing) if it + * encounters an unknown specifier. + * + * Also, note that **bpf_trace_printk**\ () is slow, and should + * only be used for debugging purposes. For this reason, a notice + * block (spanning several lines) is printed to kernel logs and + * states that the helper should not be used "for production use" + * the first time this helper is used (or more precisely, when + * **trace_printk**\ () buffers are allocated). For passing values + * to user space, perf events should be preferred. + * + * Returns + * The number of bytes written to the buffer, or a negative error + * in case of failure. + */ +static long (* const bpf_trace_printk)(const char *fmt, __u32 fmt_size, ...) = (void *) 6; + +/* + * bpf_get_prandom_u32 + * + * Get a pseudo-random number. + * + * From a security point of view, this helper uses its own + * pseudo-random internal state, and cannot be used to infer the + * seed of other random functions in the kernel. However, it is + * essential to note that the generator used by the helper is not + * cryptographically secure. + * + * Returns + * A random 32-bit unsigned value. + */ +static __u32 (* const bpf_get_prandom_u32)(void) = (void *) 7; + +/* + * bpf_get_smp_processor_id + * + * Get the SMP (symmetric multiprocessing) processor id. Note that + * all programs run with migration disabled, which means that the + * SMP processor id is stable during all the execution of the + * program. + * + * Returns + * The SMP id of the processor running the program. + */ +static __u32 (* const bpf_get_smp_processor_id)(void) = (void *) 8; + +/* + * bpf_skb_store_bytes + * + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. *flags* are a combination of + * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the + * checksum for the packet after storing the bytes) and + * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ + * **->swhash** and *skb*\ **->l4hash** to 0). + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_store_bytes)(struct __sk_buff *skb, __u32 offset, const void *from, __u32 len, __u64 flags) = (void *) 9; + +/* + * bpf_l3_csum_replace + * + * Recompute the layer 3 (e.g. IP) checksum for the packet + * associated to *skb*. Computation is incremental, so the helper + * must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored in *size*. + * Alternatively, it is possible to store the difference between + * the previous and the new values of the header field in *to*, by + * setting *from* and *size* to 0. For both methods, *offset* + * indicates the location of the IP checksum within the packet. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_l3_csum_replace)(struct __sk_buff *skb, __u32 offset, __u64 from, __u64 to, __u64 size) = (void *) 10; + +/* + * bpf_l4_csum_replace + * + * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the + * packet associated to *skb*. Computation is incremental, so the + * helper must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored on the lowest + * four bits of *flags*. Alternatively, it is possible to store + * the difference between the previous and the new values of the + * header field in *to*, by setting *from* and the four lowest + * bits of *flags* to 0. For both methods, *offset* indicates the + * location of the IP checksum within the packet. In addition to + * the size of the field, *flags* can be added (bitwise OR) actual + * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left + * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and + * for updates resulting in a null checksum the value is set to + * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates + * the checksum is to be computed against a pseudo-header. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_l4_csum_replace)(struct __sk_buff *skb, __u32 offset, __u64 from, __u64 to, __u64 flags) = (void *) 11; + +/* + * bpf_tail_call + * + * This special helper is used to trigger a "tail call", or in + * other words, to jump into another eBPF program. The same stack + * frame is used (but values on stack and in registers for the + * caller are not accessible to the callee). This mechanism allows + * for program chaining, either for raising the maximum number of + * available eBPF instructions, or to execute given programs in + * conditional blocks. For security reasons, there is an upper + * limit to the number of successive tail calls that can be + * performed. + * + * Upon call of this helper, the program attempts to jump into a + * program referenced at index *index* in *prog_array_map*, a + * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes + * *ctx*, a pointer to the context. + * + * If the call succeeds, the kernel immediately runs the first + * instruction of the new program. This is not a function call, + * and it never returns to the previous program. If the call + * fails, then the helper has no effect, and the caller continues + * to run its subsequent instructions. A call can fail if the + * destination program for the jump does not exist (i.e. *index* + * is superior to the number of entries in *prog_array_map*), or + * if the maximum number of tail calls has been reached for this + * chain of programs. This limit is defined in the kernel by the + * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), + * which is currently set to 33. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_tail_call)(void *ctx, void *prog_array_map, __u32 index) = (void *) 12; + +/* + * bpf_clone_redirect + * + * Clone and redirect the packet associated to *skb* to another + * net device of index *ifindex*. Both ingress and egress + * interfaces can be used for redirection. The **BPF_F_INGRESS** + * value in *flags* is used to make the distinction (ingress path + * is selected if the flag is present, egress path otherwise). + * This is the only flag supported for now. + * + * In comparison with **bpf_redirect**\ () helper, + * **bpf_clone_redirect**\ () has the associated cost of + * duplicating the packet buffer, but this can be executed out of + * the eBPF program. Conversely, **bpf_redirect**\ () is more + * efficient, but it is handled through an action code where the + * redirection happens only after the eBPF program has returned. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. Positive + * error indicates a potential drop or congestion in the target + * device. The particular positive error codes are not defined. + */ +static long (* const bpf_clone_redirect)(struct __sk_buff *skb, __u32 ifindex, __u64 flags) = (void *) 13; + +/* + * bpf_get_current_pid_tgid + * + * Get the current pid and tgid. + * + * Returns + * A 64-bit integer containing the current tgid and pid, and + * created as such: + * *current_task*\ **->tgid << 32 \|** + * *current_task*\ **->pid**. + */ +static __u64 (* const bpf_get_current_pid_tgid)(void) = (void *) 14; + +/* + * bpf_get_current_uid_gid + * + * Get the current uid and gid. + * + * Returns + * A 64-bit integer containing the current GID and UID, and + * created as such: *current_gid* **<< 32 \|** *current_uid*. + */ +static __u64 (* const bpf_get_current_uid_gid)(void) = (void *) 15; + +/* + * bpf_get_current_comm + * + * Copy the **comm** attribute of the current task into *buf* of + * *size_of_buf*. The **comm** attribute contains the name of + * the executable (excluding the path) for the current task. The + * *size_of_buf* must be strictly positive. On success, the + * helper makes sure that the *buf* is NUL-terminated. On failure, + * it is filled with zeroes. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_get_current_comm)(void *buf, __u32 size_of_buf) = (void *) 16; + +/* + * bpf_get_cgroup_classid + * + * Retrieve the classid for the current task, i.e. for the net_cls + * cgroup to which *skb* belongs. + * + * This helper can be used on TC egress path, but not on ingress. + * + * The net_cls cgroup provides an interface to tag network packets + * based on a user-provided identifier for all traffic coming from + * the tasks belonging to the related cgroup. See also the related + * kernel documentation, available from the Linux sources in file + * *Documentation/admin-guide/cgroup-v1/net_cls.rst*. + * + * The Linux kernel has two versions for cgroups: there are + * cgroups v1 and cgroups v2. Both are available to users, who can + * use a mixture of them, but note that the net_cls cgroup is for + * cgroup v1 only. This makes it incompatible with BPF programs + * run on cgroups, which is a cgroup-v2-only feature (a socket can + * only hold data for one version of cgroups at a time). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to + * "**y**" or to "**m**". + * + * Returns + * The classid, or 0 for the default unconfigured classid. + */ +static __u32 (* const bpf_get_cgroup_classid)(struct __sk_buff *skb) = (void *) 17; + +/* + * bpf_skb_vlan_push + * + * Push a *vlan_tci* (VLAN tag control information) of protocol + * *vlan_proto* to the packet associated to *skb*, then update + * the checksum. Note that if *vlan_proto* is different from + * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to + * be **ETH_P_8021Q**. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_vlan_push)(struct __sk_buff *skb, __be16 vlan_proto, __u16 vlan_tci) = (void *) 18; + +/* + * bpf_skb_vlan_pop + * + * Pop a VLAN header from the packet associated to *skb*. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_vlan_pop)(struct __sk_buff *skb) = (void *) 19; + +/* + * bpf_skb_get_tunnel_key + * + * Get tunnel metadata. This helper takes a pointer *key* to an + * empty **struct bpf_tunnel_key** of **size**, that will be + * filled with tunnel metadata for the packet associated to *skb*. + * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which + * indicates that the tunnel is based on IPv6 protocol instead of + * IPv4. + * + * The **struct bpf_tunnel_key** is an object that generalizes the + * principal parameters used by various tunneling protocols into a + * single struct. This way, it can be used to easily make a + * decision based on the contents of the encapsulation header, + * "summarized" in this struct. In particular, it holds the IP + * address of the remote end (IPv4 or IPv6, depending on the case) + * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also, + * this struct exposes the *key*\ **->tunnel_id**, which is + * generally mapped to a VNI (Virtual Network Identifier), making + * it programmable together with the **bpf_skb_set_tunnel_key**\ + * () helper. + * + * Let's imagine that the following code is part of a program + * attached to the TC ingress interface, on one end of a GRE + * tunnel, and is supposed to filter out all messages coming from + * remote ends with IPv4 address other than 10.0.0.1: + * + * :: + * + * int ret; + * struct bpf_tunnel_key key = {}; + * + * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + * if (ret < 0) + * return TC_ACT_SHOT; // drop packet + * + * if (key.remote_ipv4 != 0x0a000001) + * return TC_ACT_SHOT; // drop packet + * + * return TC_ACT_OK; // accept packet + * + * This interface can also be used with all encapsulation devices + * that can operate in "collect metadata" mode: instead of having + * one network device per specific configuration, the "collect + * metadata" mode only requires a single device where the + * configuration can be extracted from this helper. + * + * This can be used together with various tunnels such as VXLan, + * Geneve, GRE or IP in IP (IPIP). + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_get_tunnel_key)(struct __sk_buff *skb, struct bpf_tunnel_key *key, __u32 size, __u64 flags) = (void *) 20; + +/* + * bpf_skb_set_tunnel_key + * + * Populate tunnel metadata for packet associated to *skb.* The + * tunnel metadata is set to the contents of *key*, of *size*. The + * *flags* can be set to a combination of the following values: + * + * **BPF_F_TUNINFO_IPV6** + * Indicate that the tunnel is based on IPv6 protocol + * instead of IPv4. + * **BPF_F_ZERO_CSUM_TX** + * For IPv4 packets, add a flag to tunnel metadata + * indicating that checksum computation should be skipped + * and checksum set to zeroes. + * **BPF_F_DONT_FRAGMENT** + * Add a flag to tunnel metadata indicating that the + * packet should not be fragmented. + * **BPF_F_SEQ_NUMBER** + * Add a flag to tunnel metadata indicating that a + * sequence number should be added to tunnel header before + * sending the packet. This flag was added for GRE + * encapsulation, but might be used with other protocols + * as well in the future. + * **BPF_F_NO_TUNNEL_KEY** + * Add a flag to tunnel metadata indicating that no tunnel + * key should be set in the resulting tunnel header. + * + * Here is a typical usage on the transmit path: + * + * :: + * + * struct bpf_tunnel_key key; + * populate key ... + * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0); + * + * See also the description of the **bpf_skb_get_tunnel_key**\ () + * helper for additional information. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_set_tunnel_key)(struct __sk_buff *skb, struct bpf_tunnel_key *key, __u32 size, __u64 flags) = (void *) 21; + +/* + * bpf_perf_event_read + * + * Read the value of a perf event counter. This helper relies on a + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of + * the perf event counter is selected when *map* is updated with + * perf event file descriptors. The *map* is an array whose size + * is the number of available CPUs, and each cell contains a value + * relative to one CPU. The value to retrieve is indicated by + * *flags*, that contains the index of the CPU to look up, masked + * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * Note that before Linux 4.13, only hardware perf event can be + * retrieved. + * + * Also, be aware that the newer helper + * **bpf_perf_event_read_value**\ () is recommended over + * **bpf_perf_event_read**\ () in general. The latter has some ABI + * quirks where error and counter value are used as a return code + * (which is wrong to do since ranges may overlap). This issue is + * fixed with **bpf_perf_event_read_value**\ (), which at the same + * time provides more features over the **bpf_perf_event_read**\ + * () interface. Please refer to the description of + * **bpf_perf_event_read_value**\ () for details. + * + * Returns + * The value of the perf event counter read from the map, or a + * negative error code in case of failure. + */ +static __u64 (* const bpf_perf_event_read)(void *map, __u64 flags) = (void *) 22; + +/* + * bpf_redirect + * + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_clone_redirect**\ + * (), except that the packet is not cloned, which provides + * increased performance. + * + * Except for XDP, both ingress and egress interfaces can be used + * for redirection. The **BPF_F_INGRESS** value in *flags* is used + * to make the distinction (ingress path is selected if the flag + * is present, egress path otherwise). Currently, XDP only + * supports redirection to the egress interface, and accepts no + * flag at all. + * + * The same effect can also be attained with the more generic + * **bpf_redirect_map**\ (), which uses a BPF map to store the + * redirect target instead of providing it directly to the helper. + * + * Returns + * For XDP, the helper returns **XDP_REDIRECT** on success or + * **XDP_ABORTED** on error. For other program types, the values + * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on + * error. + */ +static long (* const bpf_redirect)(__u32 ifindex, __u64 flags) = (void *) 23; + +/* + * bpf_get_route_realm + * + * Retrieve the realm or the route, that is to say the + * **tclassid** field of the destination for the *skb*. The + * identifier retrieved is a user-provided tag, similar to the + * one used with the net_cls cgroup (see description for + * **bpf_get_cgroup_classid**\ () helper), but here this tag is + * held by a route (a destination entry), not by a task. + * + * Retrieving this identifier works with the clsact TC egress hook + * (see also **tc-bpf(8)**), or alternatively on conventional + * classful egress qdiscs, but not on TC ingress path. In case of + * clsact TC egress hook, this has the advantage that, internally, + * the destination entry has not been dropped yet in the transmit + * path. Therefore, the destination entry does not need to be + * artificially held via **netif_keep_dst**\ () for a classful + * qdisc until the *skb* is freed. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_IP_ROUTE_CLASSID** configuration option. + * + * Returns + * The realm of the route for the packet associated to *skb*, or 0 + * if none was found. + */ +static __u32 (* const bpf_get_route_realm)(struct __sk_buff *skb) = (void *) 24; + +/* + * bpf_perf_event_output + * + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * The context of the program *ctx* needs also be passed to the + * helper. + * + * On user space, a program willing to read the values needs to + * call **perf_event_open**\ () on the perf event (either for + * one or for all CPUs) and to store the file descriptor into the + * *map*. This must be done before the eBPF program can send data + * into it. An example is available in file + * *samples/bpf/trace_output_user.c* in the Linux kernel source + * tree (the eBPF program counterpart is in + * *samples/bpf/trace_output_kern.c*). + * + * **bpf_perf_event_output**\ () achieves better performance + * than **bpf_trace_printk**\ () for sharing data with user + * space, and is much better suitable for streaming data from eBPF + * programs. + * + * Note that this helper is not restricted to tracing use cases + * and can be used with programs attached to TC or XDP as well, + * where it allows for passing data to user space listeners. Data + * can be: + * + * * Only custom structs, + * * Only the packet payload, or + * * A combination of both. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_perf_event_output)(void *ctx, void *map, __u64 flags, void *data, __u64 size) = (void *) 25; + +/* + * bpf_skb_load_bytes + * + * This helper was provided as an easy way to load data from a + * packet. It can be used to load *len* bytes from *offset* from + * the packet associated to *skb*, into the buffer pointed by + * *to*. + * + * Since Linux 4.7, usage of this helper has mostly been replaced + * by "direct packet access", enabling packet data to be + * manipulated with *skb*\ **->data** and *skb*\ **->data_end** + * pointing respectively to the first byte of packet data and to + * the byte after the last byte of packet data. However, it + * remains useful if one wishes to read large quantities of data + * at once from a packet into the eBPF stack. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_load_bytes)(const void *skb, __u32 offset, void *to, __u32 len) = (void *) 26; + +/* + * bpf_get_stackid + * + * Walk a user or a kernel stack and return its id. To achieve + * this, the helper needs *ctx*, which is a pointer to the context + * on which the tracing program is executed, and a pointer to a + * *map* of type **BPF_MAP_TYPE_STACK_TRACE**. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * a combination of the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_FAST_STACK_CMP** + * Compare stacks by hash only. + * **BPF_F_REUSE_STACKID** + * If two different stacks hash into the same *stackid*, + * discard the old one. + * + * The stack id retrieved is a 32 bit long integer handle which + * can be further combined with other data (including other stack + * ids) and used as a key into maps. This can be useful for + * generating a variety of graphs (such as flame graphs or off-cpu + * graphs). + * + * For walking a stack, this helper is an improvement over + * **bpf_probe_read**\ (), which can be used with unrolled loops + * but is not efficient and consumes a lot of eBPF instructions. + * Instead, **bpf_get_stackid**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack= + * + * Returns + * The positive or null stack id on success, or a negative error + * in case of failure. + */ +static long (* const bpf_get_stackid)(void *ctx, void *map, __u64 flags) = (void *) 27; + +/* + * bpf_csum_diff + * + * Compute a checksum difference, from the raw buffer pointed by + * *from*, of length *from_size* (that must be a multiple of 4), + * towards the raw buffer pointed by *to*, of size *to_size* + * (same remark). An optional *seed* can be added to the value + * (this can be cascaded, the seed may come from a previous call + * to the helper). + * + * This is flexible enough to be used in several ways: + * + * * With *from_size* == 0, *to_size* > 0 and *seed* set to + * checksum, it can be used when pushing new data. + * * With *from_size* > 0, *to_size* == 0 and *seed* set to + * checksum, it can be used when removing data from a packet. + * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it + * can be used to compute a diff. Note that *from_size* and + * *to_size* do not need to be equal. + * + * This helper can be used in combination with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to + * which one can feed in the difference computed with + * **bpf_csum_diff**\ (). + * + * Returns + * The checksum result, or a negative error code in case of + * failure. + */ +static __s64 (* const bpf_csum_diff)(__be32 *from, __u32 from_size, __be32 *to, __u32 to_size, __wsum seed) = (void *) 28; + +/* + * bpf_skb_get_tunnel_opt + * + * Retrieve tunnel options metadata for the packet associated to + * *skb*, and store the raw tunnel option data to the buffer *opt* + * of *size*. + * + * This helper can be used with encapsulation devices that can + * operate in "collect metadata" mode (please refer to the related + * note in the description of **bpf_skb_get_tunnel_key**\ () for + * more details). A particular example where this can be used is + * in combination with the Geneve encapsulation protocol, where it + * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper) + * and retrieving arbitrary TLVs (Type-Length-Value headers) from + * the eBPF program. This allows for full customization of these + * headers. + * + * Returns + * The size of the option data retrieved. + */ +static long (* const bpf_skb_get_tunnel_opt)(struct __sk_buff *skb, void *opt, __u32 size) = (void *) 29; + +/* + * bpf_skb_set_tunnel_opt + * + * Set tunnel options metadata for the packet associated to *skb* + * to the option data contained in the raw buffer *opt* of *size*. + * + * See also the description of the **bpf_skb_get_tunnel_opt**\ () + * helper for additional information. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_set_tunnel_opt)(struct __sk_buff *skb, void *opt, __u32 size) = (void *) 30; + +/* + * bpf_skb_change_proto + * + * Change the protocol of the *skb* to *proto*. Currently + * supported are transition from IPv4 to IPv6, and from IPv6 to + * IPv4. The helper takes care of the groundwork for the + * transition, including resizing the socket buffer. The eBPF + * program is expected to fill the new headers, if any, via + * **skb_store_bytes**\ () and to recompute the checksums with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ + * (). The main case for this helper is to perform NAT64 + * operations out of an eBPF program. + * + * Internally, the GSO type is marked as dodgy so that headers are + * checked and segments are recalculated by the GSO/GRO engine. + * The size for GSO target is adapted as well. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_change_proto)(struct __sk_buff *skb, __be16 proto, __u64 flags) = (void *) 31; + +/* + * bpf_skb_change_type + * + * Change the packet type for the packet associated to *skb*. This + * comes down to setting *skb*\ **->pkt_type** to *type*, except + * the eBPF program does not have a write access to *skb*\ + * **->pkt_type** beside this helper. Using a helper here allows + * for graceful handling of errors. + * + * The major use case is to change incoming *skb*s to + * **PACKET_HOST** in a programmatic way instead of having to + * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for + * example. + * + * Note that *type* only allows certain values. At this time, they + * are: + * + * **PACKET_HOST** + * Packet is for us. + * **PACKET_BROADCAST** + * Send packet to all. + * **PACKET_MULTICAST** + * Send packet to group. + * **PACKET_OTHERHOST** + * Send packet to someone else. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_change_type)(struct __sk_buff *skb, __u32 type) = (void *) 32; + +/* + * bpf_skb_under_cgroup + * + * Check whether *skb* is a descendant of the cgroup2 held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * + * Returns + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* failed the cgroup2 descendant test. + * * 1, if the *skb* succeeded the cgroup2 descendant test. + * * A negative error code, if an error occurred. + */ +static long (* const bpf_skb_under_cgroup)(struct __sk_buff *skb, void *map, __u32 index) = (void *) 33; + +/* + * bpf_get_hash_recalc + * + * Retrieve the hash of the packet, *skb*\ **->hash**. If it is + * not set, in particular if the hash was cleared due to mangling, + * recompute this hash. Later accesses to the hash can be done + * directly with *skb*\ **->hash**. + * + * Calling **bpf_set_hash_invalid**\ (), changing a packet + * prototype with **bpf_skb_change_proto**\ (), or calling + * **bpf_skb_store_bytes**\ () with the + * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear + * the hash and to trigger a new computation for the next call to + * **bpf_get_hash_recalc**\ (). + * + * Returns + * The 32-bit hash. + */ +static __u32 (* const bpf_get_hash_recalc)(struct __sk_buff *skb) = (void *) 34; + +/* + * bpf_get_current_task + * + * Get the current task. + * + * Returns + * A pointer to the current task struct. + */ +static __u64 (* const bpf_get_current_task)(void) = (void *) 35; + +/* + * bpf_probe_write_user + * + * Attempt in a safe way to write *len* bytes from the buffer + * *src* to *dst* in memory. It only works for threads that are in + * user context, and *dst* must be a valid user space address. + * + * This helper should not be used to implement any kind of + * security mechanism because of TOC-TOU attacks, but rather to + * debug, divert, and manipulate execution of semi-cooperative + * processes. + * + * Keep in mind that this feature is meant for experiments, and it + * has a risk of crashing the system and running programs. + * Therefore, when an eBPF program using this helper is attached, + * a warning including PID and process name is printed to kernel + * logs. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_probe_write_user)(void *dst, const void *src, __u32 len) = (void *) 36; + +/* + * bpf_current_task_under_cgroup + * + * Check whether the probe is being run is the context of a given + * subset of the cgroup2 hierarchy. The cgroup2 to test is held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * + * Returns + * The return value depends on the result of the test, and can be: + * + * * 1, if current task belongs to the cgroup2. + * * 0, if current task does not belong to the cgroup2. + * * A negative error code, if an error occurred. + */ +static long (* const bpf_current_task_under_cgroup)(void *map, __u32 index) = (void *) 37; + +/* + * bpf_skb_change_tail + * + * Resize (trim or grow) the packet associated to *skb* to the + * new *len*. The *flags* are reserved for future usage, and must + * be left at zero. + * + * The basic idea is that the helper performs the needed work to + * change the size of the packet, then the eBPF program rewrites + * the rest via helpers like **bpf_skb_store_bytes**\ (), + * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ () + * and others. This helper is a slow path utility intended for + * replies with control messages. And because it is targeted for + * slow path, the helper itself can afford to be slow: it + * implicitly linearizes, unclones and drops offloads from the + * *skb*. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_change_tail)(struct __sk_buff *skb, __u32 len, __u64 flags) = (void *) 38; + +/* + * bpf_skb_pull_data + * + * Pull in non-linear data in case the *skb* is non-linear and not + * all of *len* are part of the linear section. Make *len* bytes + * from *skb* readable and writable. If a zero value is passed for + * *len*, then all bytes in the linear part of *skb* will be made + * readable and writable. + * + * This helper is only needed for reading and writing with direct + * packet access. + * + * For direct packet access, testing that offsets to access + * are within packet boundaries (test on *skb*\ **->data_end**) is + * susceptible to fail if offsets are invalid, or if the requested + * data is in non-linear parts of the *skb*. On failure the + * program can just bail out, or in the case of a non-linear + * buffer, use a helper to make the data available. The + * **bpf_skb_load_bytes**\ () helper is a first solution to access + * the data. Another one consists in using **bpf_skb_pull_data** + * to pull in once the non-linear parts, then retesting and + * eventually access the data. + * + * At the same time, this also makes sure the *skb* is uncloned, + * which is a necessary condition for direct write. As this needs + * to be an invariant for the write part only, the verifier + * detects writes and adds a prologue that is calling + * **bpf_skb_pull_data()** to effectively unclone the *skb* from + * the very beginning in case it is indeed cloned. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_pull_data)(struct __sk_buff *skb, __u32 len) = (void *) 39; + +/* + * bpf_csum_update + * + * Add the checksum *csum* into *skb*\ **->csum** in case the + * driver has supplied a checksum for the entire packet into that + * field. Return an error otherwise. This helper is intended to be + * used in combination with **bpf_csum_diff**\ (), in particular + * when the checksum needs to be updated after data has been + * written into the packet through direct packet access. + * + * Returns + * The checksum on success, or a negative error code in case of + * failure. + */ +static __s64 (* const bpf_csum_update)(struct __sk_buff *skb, __wsum csum) = (void *) 40; + +/* + * bpf_set_hash_invalid + * + * Invalidate the current *skb*\ **->hash**. It can be used after + * mangling on headers through direct packet access, in order to + * indicate that the hash is outdated and to trigger a + * recalculation the next time the kernel tries to access this + * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * + * Returns + * void. + */ +static void (* const bpf_set_hash_invalid)(struct __sk_buff *skb) = (void *) 41; + +/* + * bpf_get_numa_node_id + * + * Return the id of the current NUMA node. The primary use case + * for this helper is the selection of sockets for the local NUMA + * node, when the program is attached to sockets using the + * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**), + * but the helper is also available to other eBPF program types, + * similarly to **bpf_get_smp_processor_id**\ (). + * + * Returns + * The id of current NUMA node. + */ +static long (* const bpf_get_numa_node_id)(void) = (void *) 42; + +/* + * bpf_skb_change_head + * + * Grows headroom of packet associated to *skb* and adjusts the + * offset of the MAC header accordingly, adding *len* bytes of + * space. It automatically extends and reallocates memory as + * required. + * + * This helper can be used on a layer 3 *skb* to push a MAC header + * for redirection into a layer 2 device. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_change_head)(struct __sk_buff *skb, __u32 len, __u64 flags) = (void *) 43; + +/* + * bpf_xdp_adjust_head + * + * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that + * it is possible to use a negative value for *delta*. This helper + * can be used to prepare the packet for pushing or popping + * headers. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_xdp_adjust_head)(struct xdp_md *xdp_md, int delta) = (void *) 44; + +/* + * bpf_probe_read_str + * + * Copy a NUL terminated string from an unsafe kernel address + * *unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for + * more details. + * + * Generally, use **bpf_probe_read_user_str**\ () or + * **bpf_probe_read_kernel_str**\ () instead. + * + * Returns + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + */ +static long (* const bpf_probe_read_str)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 45; + +/* + * bpf_get_socket_cookie + * + * If the **struct sk_buff** pointed by *skb* has a known socket, + * retrieve the cookie (generated by the kernel) of this socket. + * If no cookie has been set yet, generate a new cookie. Once + * generated, the socket cookie remains stable for the life of the + * socket. This helper can be useful for monitoring per socket + * networking traffic statistics as it provides a global socket + * identifier that can be assumed unique. + * + * Returns + * A 8-byte long unique number on success, or 0 if the socket + * field is missing inside *skb*. + */ +static __u64 (* const bpf_get_socket_cookie)(void *ctx) = (void *) 46; + +/* + * bpf_get_socket_uid + * + * Get the owner UID of the socked associated to *skb*. + * + * Returns + * The owner UID of the socket associated to *skb*. If the socket + * is **NULL**, or if it is not a full socket (i.e. if it is a + * time-wait or a request socket instead), **overflowuid** value + * is returned (note that **overflowuid** might also be the actual + * UID value for the socket). + */ +static __u32 (* const bpf_get_socket_uid)(struct __sk_buff *skb) = (void *) 47; + +/* + * bpf_set_hash + * + * Set the full hash for *skb* (set the field *skb*\ **->hash**) + * to value *hash*. + * + * Returns + * 0 + */ +static long (* const bpf_set_hash)(struct __sk_buff *skb, __u32 hash) = (void *) 48; + +/* + * bpf_setsockopt + * + * Emulate a call to **setsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **setsockopt(2)** for more information. + * The option value of length *optlen* is pointed by *optval*. + * + * *bpf_socket* should be one of the following: + * + * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. + * + * This helper actually implements a subset of **setsockopt()**. + * It supports the following *level*\ s: + * + * * **SOL_SOCKET**, which supports the following *optname*\ s: + * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**, + * **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**. + * * **IPPROTO_TCP**, which supports the following *optname*\ s: + * **TCP_CONGESTION**, **TCP_BPF_IW**, + * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, + * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**, + * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**, + * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**, + * **TCP_BPF_RTO_MIN**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports the following *optname*\ s: + * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_setsockopt)(void *bpf_socket, int level, int optname, void *optval, int optlen) = (void *) 49; + +/* + * bpf_skb_adjust_room + * + * Grow or shrink the room for data in the packet associated to + * *skb* by *len_diff*, and according to the selected *mode*. + * + * By default, the helper will reset any offloaded checksum + * indicator of the skb to CHECKSUM_NONE. This can be avoided + * by the following flag: + * + * * **BPF_F_ADJ_ROOM_NO_CSUM_RESET**: Do not reset offloaded + * checksum data of the skb to CHECKSUM_NONE. + * + * There are two supported modes at this time: + * + * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer + * (room space is added or removed between the layer 2 and + * layer 3 headers). + * + * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer + * (room space is added or removed between the layer 3 and + * layer 4 headers). + * + * The following flags are supported at this time: + * + * * **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size. + * Adjusting mss in this way is not allowed for datagrams. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4**, + * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6**: + * Any new space is reserved to hold a tunnel header. + * Configure skb offsets and other fields accordingly. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L4_GRE**, + * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP**: + * Use with ENCAP_L3 flags to further specify the tunnel type. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L2**\ (*len*): + * Use with ENCAP_L3/L4 flags to further specify the tunnel + * type; *len* is the length of the inner MAC header. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L2_ETH**: + * Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the + * L2 type as Ethernet. + * + * * **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**, + * **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**: + * Indicate the new IP header version after decapsulating the outer + * IP header. Used when the inner and outer IP versions are different. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_adjust_room)(struct __sk_buff *skb, __s32 len_diff, __u32 mode, __u64 flags) = (void *) 50; + +/* + * bpf_redirect_map + * + * Redirect the packet to the endpoint referenced by *map* at + * index *key*. Depending on its type, this *map* can contain + * references to net devices (for forwarding packets through other + * ports), or to CPUs (for redirecting XDP frames to another CPU; + * but this is only implemented for native XDP (with driver + * support) as of this writing). + * + * The lower two bits of *flags* are used as the return code if + * the map lookup fails. This is so that the return value can be + * one of the XDP program return codes up to **XDP_TX**, as chosen + * by the caller. The higher bits of *flags* can be set to + * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below. + * + * With BPF_F_BROADCAST the packet will be broadcasted to all the + * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress + * interface will be excluded when do broadcasting. + * + * See also **bpf_redirect**\ (), which only supports redirecting + * to an ifindex, but doesn't require a map to do so. + * + * Returns + * **XDP_REDIRECT** on success, or the value of the two lower bits + * of the *flags* argument on error. + */ +static long (* const bpf_redirect_map)(void *map, __u64 key, __u64 flags) = (void *) 51; + +/* + * bpf_sk_redirect_map + * + * Redirect the packet to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * + * Returns + * **SK_PASS** on success, or **SK_DROP** on error. + */ +static long (* const bpf_sk_redirect_map)(struct __sk_buff *skb, void *map, __u32 key, __u64 flags) = (void *) 52; + +/* + * bpf_sock_map_update + * + * Add an entry to, or update a *map* referencing sockets. The + * *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_sock_map_update)(struct bpf_sock_ops *skops, void *map, void *key, __u64 flags) = (void *) 53; + +/* + * bpf_xdp_adjust_meta + * + * Adjust the address pointed by *xdp_md*\ **->data_meta** by + * *delta* (which can be positive or negative). Note that this + * operation modifies the address stored in *xdp_md*\ **->data**, + * so the latter must be loaded only after the helper has been + * called. + * + * The use of *xdp_md*\ **->data_meta** is optional and programs + * are not required to use it. The rationale is that when the + * packet is processed with XDP (e.g. as DoS filter), it is + * possible to push further meta data along with it before passing + * to the stack, and to give the guarantee that an ingress eBPF + * program attached as a TC classifier on the same device can pick + * this up for further post-processing. Since TC works with socket + * buffers, it remains possible to set from XDP the **mark** or + * **priority** pointers, or other pointers for the socket buffer. + * Having this scratch space generic and programmable allows for + * more flexibility as the user is free to store whatever meta + * data they need. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_xdp_adjust_meta)(struct xdp_md *xdp_md, int delta) = (void *) 54; + +/* + * bpf_perf_event_read_value + * + * Read the value of a perf event counter, and store it into *buf* + * of size *buf_size*. This helper relies on a *map* of type + * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event + * counter is selected when *map* is updated with perf event file + * descriptors. The *map* is an array whose size is the number of + * available CPUs, and each cell contains a value relative to one + * CPU. The value to retrieve is indicated by *flags*, that + * contains the index of the CPU to look up, masked with + * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * This helper behaves in a way close to + * **bpf_perf_event_read**\ () helper, save that instead of + * just returning the value observed, it fills the *buf* + * structure. This allows for additional data to be retrieved: in + * particular, the enabled and running times (in *buf*\ + * **->enabled** and *buf*\ **->running**, respectively) are + * copied. In general, **bpf_perf_event_read_value**\ () is + * recommended over **bpf_perf_event_read**\ (), which has some + * ABI issues and provides fewer functionalities. + * + * These values are interesting, because hardware PMU (Performance + * Monitoring Unit) counters are limited resources. When there are + * more PMU based perf events opened than available counters, + * kernel will multiplex these events so each event gets certain + * percentage (but not all) of the PMU time. In case that + * multiplexing happens, the number of samples or counter value + * will not reflect the case compared to when no multiplexing + * occurs. This makes comparison between different runs difficult. + * Typically, the counter value should be normalized before + * comparing to other experiments. The usual normalization is done + * as follows. + * + * :: + * + * normalized_counter = counter * t_enabled / t_running + * + * Where t_enabled is the time enabled for event and t_running is + * the time running for event since last normalization. The + * enabled and running times are accumulated since the perf event + * open. To achieve scaling factor between two invocations of an + * eBPF program, users can use CPU id as the key (which is + * typical for perf array usage model) to remember the previous + * value and do the calculation inside the eBPF program. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_perf_event_read_value)(void *map, __u64 flags, struct bpf_perf_event_value *buf, __u32 buf_size) = (void *) 55; + +/* + * bpf_perf_prog_read_value + * + * For an eBPF program attached to a perf event, retrieve the + * value of the event counter associated to *ctx* and store it in + * the structure pointed by *buf* and of size *buf_size*. Enabled + * and running times are also stored in the structure (see + * description of helper **bpf_perf_event_read_value**\ () for + * more details). + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_perf_prog_read_value)(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, __u32 buf_size) = (void *) 56; + +/* + * bpf_getsockopt + * + * Emulate a call to **getsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **getsockopt(2)** for more information. + * The retrieved value is stored in the structure pointed by + * *opval* and of length *optlen*. + * + * *bpf_socket* should be one of the following: + * + * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. + * + * This helper actually implements a subset of **getsockopt()**. + * It supports the same set of *optname*\ s that is supported by + * the **bpf_setsockopt**\ () helper. The exceptions are + * **TCP_BPF_*** is **bpf_setsockopt**\ () only and + * **TCP_SAVED_SYN** is **bpf_getsockopt**\ () only. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_getsockopt)(void *bpf_socket, int level, int optname, void *optval, int optlen) = (void *) 57; + +/* + * bpf_override_return + * + * Used for error injection, this helper uses kprobes to override + * the return value of the probed function, and to set it to *rc*. + * The first argument is the context *regs* on which the kprobe + * works. + * + * This helper works by setting the PC (program counter) + * to an override function which is run in place of the original + * probed function. This means the probed function is not run at + * all. The replacement function just returns with the required + * value. + * + * This helper has security implications, and thus is subject to + * restrictions. It is only available if the kernel was compiled + * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration + * option, and in this case it only works on functions tagged with + * **ALLOW_ERROR_INJECTION** in the kernel code. + * + * Also, the helper is only available for the architectures having + * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, + * x86 architecture is the only one to support this feature. + * + * Returns + * 0 + */ +static long (* const bpf_override_return)(struct pt_regs *regs, __u64 rc) = (void *) 58; + +/* + * bpf_sock_ops_cb_flags_set + * + * Attempt to set the value of the **bpf_sock_ops_cb_flags** field + * for the full TCP socket associated to *bpf_sock_ops* to + * *argval*. + * + * The primary use of this field is to determine if there should + * be calls to eBPF programs of type + * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP + * code. A program of the same type can change its value, per + * connection and as necessary, when the connection is + * established. This field is directly accessible for reading, but + * this helper must be used for updates in order to return an + * error if an eBPF program tries to set a callback that is not + * supported in the current kernel. + * + * *argval* is a flag array which can combine these flags: + * + * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) + * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) + * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT) + * + * Therefore, this function can be used to clear a callback flag by + * setting the appropriate bit to zero. e.g. to disable the RTO + * callback: + * + * **bpf_sock_ops_cb_flags_set(bpf_sock,** + * **bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)** + * + * Here are some examples of where one could call such eBPF + * program: + * + * * When RTO fires. + * * When a packet is retransmitted. + * * When the connection terminates. + * * When a packet is sent. + * * When a packet is received. + * + * Returns + * Code **-EINVAL** if the socket is not a full TCP socket; + * otherwise, a positive number containing the bits that could not + * be set is returned (which comes down to 0 if all bits were set + * as required). + */ +static long (* const bpf_sock_ops_cb_flags_set)(struct bpf_sock_ops *bpf_sock, int argval) = (void *) 59; + +/* + * bpf_msg_redirect_map + * + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * + * Returns + * **SK_PASS** on success, or **SK_DROP** on error. + */ +static long (* const bpf_msg_redirect_map)(struct sk_msg_md *msg, void *map, __u32 key, __u64 flags) = (void *) 60; + +/* + * bpf_msg_apply_bytes + * + * For socket policies, apply the verdict of the eBPF program to + * the next *bytes* (number of bytes) of message *msg*. + * + * For example, this helper can be used in the following cases: + * + * * A single **sendmsg**\ () or **sendfile**\ () system call + * contains multiple logical messages that the eBPF program is + * supposed to read and for which it should apply a verdict. + * * An eBPF program only cares to read the first *bytes* of a + * *msg*. If the message has a large payload, then setting up + * and calling the eBPF program repeatedly for all bytes, even + * though the verdict is already known, would create unnecessary + * overhead. + * + * When called from within an eBPF program, the helper sets a + * counter internal to the BPF infrastructure, that is used to + * apply the last verdict to the next *bytes*. If *bytes* is + * smaller than the current data being processed from a + * **sendmsg**\ () or **sendfile**\ () system call, the first + * *bytes* will be sent and the eBPF program will be re-run with + * the pointer for start of data pointing to byte number *bytes* + * **+ 1**. If *bytes* is larger than the current data being + * processed, then the eBPF verdict will be applied to multiple + * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are + * consumed. + * + * Note that if a socket closes with the internal counter holding + * a non-zero value, this is not a problem because data is not + * being buffered for *bytes* and is sent as it is received. + * + * Returns + * 0 + */ +static long (* const bpf_msg_apply_bytes)(struct sk_msg_md *msg, __u32 bytes) = (void *) 61; + +/* + * bpf_msg_cork_bytes + * + * For socket policies, prevent the execution of the verdict eBPF + * program for message *msg* until *bytes* (byte number) have been + * accumulated. + * + * This can be used when one needs a specific number of bytes + * before a verdict can be assigned, even if the data spans + * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme + * case would be a user calling **sendmsg**\ () repeatedly with + * 1-byte long message segments. Obviously, this is bad for + * performance, but it is still valid. If the eBPF program needs + * *bytes* bytes to validate a header, this helper can be used to + * prevent the eBPF program to be called again until *bytes* have + * been accumulated. + * + * Returns + * 0 + */ +static long (* const bpf_msg_cork_bytes)(struct sk_msg_md *msg, __u32 bytes) = (void *) 62; + +/* + * bpf_msg_pull_data + * + * For socket policies, pull in non-linear data from user space + * for *msg* and set pointers *msg*\ **->data** and *msg*\ + * **->data_end** to *start* and *end* bytes offsets into *msg*, + * respectively. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it can only parse data that the (**data**, **data_end**) + * pointers have already consumed. For **sendmsg**\ () hooks this + * is likely the first scatterlist element. But for calls relying + * on the **sendpage** handler (e.g. **sendfile**\ ()) this will + * be the range (**0**, **0**) because the data is shared with + * user space and by default the objective is to avoid allowing + * user space to modify data while (or after) eBPF verdict is + * being decided. This helper can be used to pull in data and to + * set the start and end pointer to given values. Data will be + * copied if necessary (i.e. if data was not linear and if start + * and end pointers do not point to the same chunk). + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_msg_pull_data)(struct sk_msg_md *msg, __u32 start, __u32 end, __u64 flags) = (void *) 63; + +/* + * bpf_bind + * + * Bind the socket associated to *ctx* to the address pointed by + * *addr*, of length *addr_len*. This allows for making outgoing + * connection from the desired IP address, which can be useful for + * example when all processes inside a cgroup should use one + * single IP address on a host that has multiple IP configured. + * + * This helper works for IPv4 and IPv6, TCP and UDP sockets. The + * domain (*addr*\ **->sa_family**) must be **AF_INET** (or + * **AF_INET6**). It's advised to pass zero port (**sin_port** + * or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like + * behavior and lets the kernel efficiently pick up an unused + * port as long as 4-tuple is unique. Passing non-zero port might + * lead to degraded performance. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_bind)(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) = (void *) 64; + +/* + * bpf_xdp_adjust_tail + * + * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is + * possible to both shrink and grow the packet tail. + * Shrink done via *delta* being a negative integer. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_xdp_adjust_tail)(struct xdp_md *xdp_md, int delta) = (void *) 65; + +/* + * bpf_skb_get_xfrm_state + * + * Retrieve the XFRM state (IP transform framework, see also + * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*. + * + * The retrieved value is stored in the **struct bpf_xfrm_state** + * pointed by *xfrm_state* and of length *size*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_XFRM** configuration option. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_get_xfrm_state)(struct __sk_buff *skb, __u32 index, struct bpf_xfrm_state *xfrm_state, __u32 size, __u64 flags) = (void *) 66; + +/* + * bpf_get_stack + * + * Return a user or a kernel stack in bpf program provided buffer. + * To achieve this, the helper needs *ctx*, which is a pointer + * to the context on which the tracing program is executed. + * To store the stacktrace, the bpf program provides *buf* with + * a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_USER_BUILD_ID** + * Collect (build_id, file_offset) instead of ips for user + * stack, only valid if **BPF_F_USER_STACK** is also + * specified. + * + * *file_offset* is an offset relative to the beginning + * of the executable or shared object file backing the vma + * which the *ip* falls in. It is *not* an offset relative + * to that object's base address. Accordingly, it must be + * adjusted by adding (sh_addr - sh_offset), where + * sh_{addr,offset} correspond to the executable section + * containing *file_offset* in the object, for comparisons + * to symbols' st_value to be valid. + * + * **bpf_get_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack= + * + * Returns + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. + */ +static long (* const bpf_get_stack)(void *ctx, void *buf, __u32 size, __u64 flags) = (void *) 67; + +/* + * bpf_skb_load_bytes_relative + * + * This helper is similar to **bpf_skb_load_bytes**\ () in that + * it provides an easy way to load *len* bytes from *offset* + * from the packet associated to *skb*, into the buffer pointed + * by *to*. The difference to **bpf_skb_load_bytes**\ () is that + * a fifth argument *start_header* exists in order to select a + * base offset to start from. *start_header* can be one of: + * + * **BPF_HDR_START_MAC** + * Base offset to load data from is *skb*'s mac header. + * **BPF_HDR_START_NET** + * Base offset to load data from is *skb*'s network header. + * + * In general, "direct packet access" is the preferred method to + * access packet data, however, this helper is in particular useful + * in socket filters where *skb*\ **->data** does not always point + * to the start of the mac header and where "direct packet access" + * is not available. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_load_bytes_relative)(const void *skb, __u32 offset, void *to, __u32 len, __u32 start_header) = (void *) 68; + +/* + * bpf_fib_lookup + * + * Do FIB lookup in kernel tables using parameters in *params*. + * If lookup is successful and result shows packet is to be + * forwarded, the neighbor tables are searched for the nexthop. + * If successful (ie., FIB lookup shows forwarding and nexthop + * is resolved), the nexthop address is returned in ipv4_dst + * or ipv6_dst based on family, smac is set to mac address of + * egress device, dmac is set to nexthop mac address, rt_metric + * is set to metric from route (IPv4/IPv6 only), and ifindex + * is set to the device index of the nexthop from the FIB lookup. + * + * *plen* argument is the size of the passed in struct. + * *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_FIB_LOOKUP_DIRECT** + * Do a direct table lookup vs full lookup using FIB + * rules. + * **BPF_FIB_LOOKUP_TBID** + * Used with BPF_FIB_LOOKUP_DIRECT. + * Use the routing table ID present in *params*->tbid + * for the fib lookup. + * **BPF_FIB_LOOKUP_OUTPUT** + * Perform lookup from an egress perspective (default is + * ingress). + * **BPF_FIB_LOOKUP_SKIP_NEIGH** + * Skip the neighbour table lookup. *params*->dmac + * and *params*->smac will not be set as output. A common + * use case is to call **bpf_redirect_neigh**\ () after + * doing **bpf_fib_lookup**\ (). + * **BPF_FIB_LOOKUP_SRC** + * Derive and set source IP addr in *params*->ipv{4,6}_src + * for the nexthop. If the src addr cannot be derived, + * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this + * case, *params*->dmac and *params*->smac are not set either. + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** tc cls_act programs. + * + * Returns + * * < 0 if any input argument is invalid + * * 0 on success (packet is forwarded, nexthop neighbor exists) + * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the + * packet is not forwarded or needs assist from full stack + * + * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU + * was exceeded and output params->mtu_result contains the MTU. + */ +static long (* const bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params, int plen, __u32 flags) = (void *) 69; + +/* + * bpf_sock_hash_update + * + * Add an entry to, or update a sockhash *map* referencing sockets. + * The *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_sock_hash_update)(struct bpf_sock_ops *skops, void *map, void *key, __u64 flags) = (void *) 70; + +/* + * bpf_msg_redirect_hash + * + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * + * Returns + * **SK_PASS** on success, or **SK_DROP** on error. + */ +static long (* const bpf_msg_redirect_hash)(struct sk_msg_md *msg, void *map, void *key, __u64 flags) = (void *) 71; + +/* + * bpf_sk_redirect_hash + * + * This helper is used in programs implementing policies at the + * skb socket level. If the sk_buff *skb* is allowed to pass (i.e. + * if the verdict eBPF program returns **SK_PASS**), redirect it + * to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress otherwise). This is the only flag supported for now. + * + * Returns + * **SK_PASS** on success, or **SK_DROP** on error. + */ +static long (* const bpf_sk_redirect_hash)(struct __sk_buff *skb, void *map, void *key, __u64 flags) = (void *) 72; + +/* + * bpf_lwt_push_encap + * + * Encapsulate the packet associated to *skb* within a Layer 3 + * protocol header. This header is provided in the buffer at + * address *hdr*, with *len* its size in bytes. *type* indicates + * the protocol of the header and can be one of: + * + * **BPF_LWT_ENCAP_SEG6** + * IPv6 encapsulation with Segment Routing Header + * (**struct ipv6_sr_hdr**). *hdr* only contains the SRH, + * the IPv6 header is computed by the kernel. + * **BPF_LWT_ENCAP_SEG6_INLINE** + * Only works if *skb* contains an IPv6 packet. Insert a + * Segment Routing Header (**struct ipv6_sr_hdr**) inside + * the IPv6 header. + * **BPF_LWT_ENCAP_IP** + * IP encapsulation (GRE/GUE/IPIP/etc). The outer header + * must be IPv4 or IPv6, followed by zero or more + * additional headers, up to **LWT_BPF_MAX_HEADROOM** + * total bytes in all prepended headers. Please note that + * if **skb_is_gso**\ (*skb*) is true, no more than two + * headers can be prepended, and the inner header, if + * present, should be either GRE or UDP/GUE. + * + * **BPF_LWT_ENCAP_SEG6**\ \* types can be called by BPF programs + * of type **BPF_PROG_TYPE_LWT_IN**; **BPF_LWT_ENCAP_IP** type can + * be called by bpf programs of types **BPF_PROG_TYPE_LWT_IN** and + * **BPF_PROG_TYPE_LWT_XMIT**. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_lwt_push_encap)(struct __sk_buff *skb, __u32 type, void *hdr, __u32 len) = (void *) 73; + +/* + * bpf_lwt_seg6_store_bytes + * + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. Only the flags, tag and TLVs + * inside the outermost IPv6 Segment Routing Header can be + * modified through this helper. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_lwt_seg6_store_bytes)(struct __sk_buff *skb, __u32 offset, const void *from, __u32 len) = (void *) 74; + +/* + * bpf_lwt_seg6_adjust_srh + * + * Adjust the size allocated to TLVs in the outermost IPv6 + * Segment Routing Header contained in the packet associated to + * *skb*, at position *offset* by *delta* bytes. Only offsets + * after the segments are accepted. *delta* can be as well + * positive (growing) as negative (shrinking). + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_lwt_seg6_adjust_srh)(struct __sk_buff *skb, __u32 offset, __s32 delta) = (void *) 75; + +/* + * bpf_lwt_seg6_action + * + * Apply an IPv6 Segment Routing action of type *action* to the + * packet associated to *skb*. Each action takes a parameter + * contained at address *param*, and of length *param_len* bytes. + * *action* can be one of: + * + * **SEG6_LOCAL_ACTION_END_X** + * End.X action: Endpoint with Layer-3 cross-connect. + * Type of *param*: **struct in6_addr**. + * **SEG6_LOCAL_ACTION_END_T** + * End.T action: Endpoint with specific IPv6 table lookup. + * Type of *param*: **int**. + * **SEG6_LOCAL_ACTION_END_B6** + * End.B6 action: Endpoint bound to an SRv6 policy. + * Type of *param*: **struct ipv6_sr_hdr**. + * **SEG6_LOCAL_ACTION_END_B6_ENCAP** + * End.B6.Encap action: Endpoint bound to an SRv6 + * encapsulation policy. + * Type of *param*: **struct ipv6_sr_hdr**. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_lwt_seg6_action)(struct __sk_buff *skb, __u32 action, void *param, __u32 param_len) = (void *) 76; + +/* + * bpf_rc_repeat + * + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. + * + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Returns + * 0 + */ +static long (* const bpf_rc_repeat)(void *ctx) = (void *) 77; + +/* + * bpf_rc_keydown + * + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown**\ () again with the same values, or calling + * **bpf_rc_repeat**\ (). + * + * Some protocols include a toggle bit, in case the button was + * released and pressed again between consecutive scancodes. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Returns + * 0 + */ +static long (* const bpf_rc_keydown)(void *ctx, __u32 protocol, __u64 scancode, __u32 toggle) = (void *) 78; + +/* + * bpf_skb_cgroup_id + * + * Return the cgroup v2 id of the socket associated with the *skb*. + * This is roughly similar to the **bpf_get_cgroup_classid**\ () + * helper for cgroup v1 by providing a tag resp. identifier that + * can be matched on or used for map lookups e.g. to implement + * policy. The cgroup v2 id of a given path in the hierarchy is + * exposed in user space through the f_handle API in order to get + * to the same 64-bit id. + * + * This helper can be used on TC egress path, but not on ingress, + * and is available only if the kernel was compiled with the + * **CONFIG_SOCK_CGROUP_DATA** configuration option. + * + * Returns + * The id is returned or 0 in case the id could not be retrieved. + */ +static __u64 (* const bpf_skb_cgroup_id)(struct __sk_buff *skb) = (void *) 79; + +/* + * bpf_get_current_cgroup_id + * + * Get the current cgroup id based on the cgroup within which + * the current task is running. + * + * Returns + * A 64-bit integer containing the current cgroup id based + * on the cgroup within which the current task is running. + */ +static __u64 (* const bpf_get_current_cgroup_id)(void) = (void *) 80; + +/* + * bpf_get_local_storage + * + * Get the pointer to the local storage area. + * The type and the size of the local storage is defined + * by the *map* argument. + * The *flags* meaning is specific for each map type, + * and has to be 0 for cgroup local storage. + * + * Depending on the BPF program type, a local storage area + * can be shared between multiple instances of the BPF program, + * running simultaneously. + * + * A user should care about the synchronization by himself. + * For example, by using the **BPF_ATOMIC** instructions to alter + * the shared data. + * + * Returns + * A pointer to the local storage area. + */ +static void *(* const bpf_get_local_storage)(void *map, __u64 flags) = (void *) 81; + +/* + * bpf_sk_select_reuseport + * + * Select a **SO_REUSEPORT** socket from a + * **BPF_MAP_TYPE_REUSEPORT_SOCKARRAY** *map*. + * It checks the selected socket is matching the incoming + * request in the socket buffer. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_sk_select_reuseport)(struct sk_reuseport_md *reuse, void *map, void *key, __u64 flags) = (void *) 82; + +/* + * bpf_skb_ancestor_cgroup_id + * + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *skb* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *skb*, then return value will be same as that + * of **bpf_skb_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *skb*. + * + * The format of returned id and helper limitations are same as in + * **bpf_skb_cgroup_id**\ (). + * + * Returns + * The id is returned or 0 in case the id could not be retrieved. + */ +static __u64 (* const bpf_skb_ancestor_cgroup_id)(struct __sk_buff *skb, int ancestor_level) = (void *) 83; + +/* + * bpf_sk_lookup_tcp + * + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * + * Returns + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + */ +static struct bpf_sock *(* const bpf_sk_lookup_tcp)(void *ctx, struct bpf_sock_tuple *tuple, __u32 tuple_size, __u64 netns, __u64 flags) = (void *) 84; + +/* + * bpf_sk_lookup_udp + * + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * + * Returns + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + */ +static struct bpf_sock *(* const bpf_sk_lookup_udp)(void *ctx, struct bpf_sock_tuple *tuple, __u32 tuple_size, __u64 netns, __u64 flags) = (void *) 85; + +/* + * bpf_sk_release + * + * Release the reference held by *sock*. *sock* must be a + * non-**NULL** pointer that was returned from + * **bpf_sk_lookup_xxx**\ (). + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_sk_release)(void *sock) = (void *) 86; + +/* + * bpf_map_push_elem + * + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is + * removed to make room for this. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_map_push_elem)(void *map, const void *value, __u64 flags) = (void *) 87; + +/* + * bpf_map_pop_elem + * + * Pop an element from *map*. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_map_pop_elem)(void *map, void *value) = (void *) 88; + +/* + * bpf_map_peek_elem + * + * Get an element from *map* without removing it. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_map_peek_elem)(void *map, void *value) = (void *) 89; + +/* + * bpf_msg_push_data + * + * For socket policies, insert *len* bytes into *msg* at offset + * *start*. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it may want to insert metadata or options into the *msg*. + * This can later be read and used by any of the lower layer BPF + * hooks. + * + * This helper may fail if under memory pressure (a malloc + * fails) in these cases BPF programs will get an appropriate + * error and BPF programs will need to handle them. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_msg_push_data)(struct sk_msg_md *msg, __u32 start, __u32 len, __u64 flags) = (void *) 90; + +/* + * bpf_msg_pop_data + * + * Will remove *len* bytes from a *msg* starting at byte *start*. + * This may result in **ENOMEM** errors under certain situations if + * an allocation and copy are required due to a full ring buffer. + * However, the helper will try to avoid doing the allocation + * if possible. Other errors can occur if input parameters are + * invalid either due to *start* byte not being valid part of *msg* + * payload and/or *pop* value being to large. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_msg_pop_data)(struct sk_msg_md *msg, __u32 start, __u32 len, __u64 flags) = (void *) 91; + +/* + * bpf_rc_pointer_rel + * + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded pointer movement. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Returns + * 0 + */ +static long (* const bpf_rc_pointer_rel)(void *ctx, __s32 rel_x, __s32 rel_y) = (void *) 92; + +/* + * bpf_spin_lock + * + * Acquire a spinlock represented by the pointer *lock*, which is + * stored as part of a value of a map. Taking the lock allows to + * safely update the rest of the fields in that value. The + * spinlock can (and must) later be released with a call to + * **bpf_spin_unlock**\ (\ *lock*\ ). + * + * Spinlocks in BPF programs come with a number of restrictions + * and constraints: + * + * * **bpf_spin_lock** objects are only allowed inside maps of + * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this + * list could be extended in the future). + * * BTF description of the map is mandatory. + * * The BPF program can take ONE lock at a time, since taking two + * or more could cause dead locks. + * * Only one **struct bpf_spin_lock** is allowed per map element. + * * When the lock is taken, calls (either BPF to BPF or helpers) + * are not allowed. + * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not + * allowed inside a spinlock-ed region. + * * The BPF program MUST call **bpf_spin_unlock**\ () to release + * the lock, on all execution paths, before it returns. + * * The BPF program can access **struct bpf_spin_lock** only via + * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ () + * helpers. Loading or storing data into the **struct + * bpf_spin_lock** *lock*\ **;** field of a map is not allowed. + * * To use the **bpf_spin_lock**\ () helper, the BTF description + * of the map value must be a struct and have **struct + * bpf_spin_lock** *anyname*\ **;** field at the top level. + * Nested lock inside another struct is not allowed. + * * The **struct bpf_spin_lock** *lock* field in a map value must + * be aligned on a multiple of 4 bytes in that value. + * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy + * the **bpf_spin_lock** field to user space. + * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from + * a BPF program, do not update the **bpf_spin_lock** field. + * * **bpf_spin_lock** cannot be on the stack or inside a + * networking packet (it can only be inside of a map values). + * * **bpf_spin_lock** is available to root only. + * * Tracing programs and socket filter programs cannot use + * **bpf_spin_lock**\ () due to insufficient preemption checks + * (but this may change in the future). + * * **bpf_spin_lock** is not allowed in inner maps of map-in-map. + * + * Returns + * 0 + */ +static long (* const bpf_spin_lock)(struct bpf_spin_lock *lock) = (void *) 93; + +/* + * bpf_spin_unlock + * + * Release the *lock* previously locked by a call to + * **bpf_spin_lock**\ (\ *lock*\ ). + * + * Returns + * 0 + */ +static long (* const bpf_spin_unlock)(struct bpf_spin_lock *lock) = (void *) 94; + +/* + * bpf_sk_fullsock + * + * This helper gets a **struct bpf_sock** pointer such + * that all the fields in this **bpf_sock** can be accessed. + * + * Returns + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + */ +static struct bpf_sock *(* const bpf_sk_fullsock)(struct bpf_sock *sk) = (void *) 95; + +/* + * bpf_tcp_sock + * + * This helper gets a **struct bpf_tcp_sock** pointer from a + * **struct bpf_sock** pointer. + * + * Returns + * A **struct bpf_tcp_sock** pointer on success, or **NULL** in + * case of failure. + */ +static struct bpf_tcp_sock *(* const bpf_tcp_sock)(struct bpf_sock *sk) = (void *) 96; + +/* + * bpf_skb_ecn_set_ce + * + * Set ECN (Explicit Congestion Notification) field of IP header + * to **CE** (Congestion Encountered) if current value is **ECT** + * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6 + * and IPv4. + * + * Returns + * 1 if the **CE** flag is set (either by the current helper call + * or because it was already present), 0 if it is not set. + */ +static long (* const bpf_skb_ecn_set_ce)(struct __sk_buff *skb) = (void *) 97; + +/* + * bpf_get_listener_sock + * + * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state. + * **bpf_sk_release**\ () is unnecessary and not allowed. + * + * Returns + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + */ +static struct bpf_sock *(* const bpf_get_listener_sock)(struct bpf_sock *sk) = (void *) 98; + +/* + * bpf_skc_lookup_tcp + * + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * This function is identical to **bpf_sk_lookup_tcp**\ (), except + * that it also returns timewait or request sockets. Use + * **bpf_sk_fullsock**\ () or **bpf_tcp_sock**\ () to access the + * full structure. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * + * Returns + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + */ +static struct bpf_sock *(* const bpf_skc_lookup_tcp)(void *ctx, struct bpf_sock_tuple *tuple, __u32 tuple_size, __u64 netns, __u64 flags) = (void *) 99; + +/* + * bpf_tcp_check_syncookie + * + * Check whether *iph* and *th* contain a valid SYN cookie ACK for + * the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ipv6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * + * Returns + * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative + * error otherwise. + */ +static long (* const bpf_tcp_check_syncookie)(void *sk, void *iph, __u32 iph_len, struct tcphdr *th, __u32 th_len) = (void *) 100; + +/* + * bpf_sysctl_get_name + * + * Get name of sysctl in /proc/sys/ and copy it into provided by + * program buffer *buf* of size *buf_len*. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * + * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is + * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name + * only (e.g. "tcp_mem"). + * + * Returns + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + */ +static long (* const bpf_sysctl_get_name)(struct bpf_sysctl *ctx, char *buf, unsigned long buf_len, __u64 flags) = (void *) 101; + +/* + * bpf_sysctl_get_current_value + * + * Get current value of sysctl as it is presented in /proc/sys + * (incl. newline, etc), and copy it as a string into provided + * by program buffer *buf* of size *buf_len*. + * + * The whole value is copied, no matter what file position user + * space issued e.g. sys_read at. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * + * Returns + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if current value was unavailable, e.g. because + * sysctl is uninitialized and read returns -EIO for it. + */ +static long (* const bpf_sysctl_get_current_value)(struct bpf_sysctl *ctx, char *buf, unsigned long buf_len) = (void *) 102; + +/* + * bpf_sysctl_get_new_value + * + * Get new value being written by user space to sysctl (before + * the actual write happens) and copy it as a string into + * provided by program buffer *buf* of size *buf_len*. + * + * User space may write new value at file position > 0. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * + * Returns + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if sysctl is being read. + */ +static long (* const bpf_sysctl_get_new_value)(struct bpf_sysctl *ctx, char *buf, unsigned long buf_len) = (void *) 103; + +/* + * bpf_sysctl_set_new_value + * + * Override new value being written by user space to sysctl with + * value provided by program in buffer *buf* of size *buf_len*. + * + * *buf* should contain a string in same form as provided by user + * space on sysctl write. + * + * User space may write new value at file position > 0. To override + * the whole sysctl value file position should be set to zero. + * + * Returns + * 0 on success. + * + * **-E2BIG** if the *buf_len* is too big. + * + * **-EINVAL** if sysctl is being read. + */ +static long (* const bpf_sysctl_set_new_value)(struct bpf_sysctl *ctx, const char *buf, unsigned long buf_len) = (void *) 104; + +/* + * bpf_strtol + * + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to a long integer according to the given base + * and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)) followed by a single + * optional '**-**' sign. + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtol**\ (3). + * + * Returns + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + */ +static long (* const bpf_strtol)(const char *buf, unsigned long buf_len, __u64 flags, long *res) = (void *) 105; + +/* + * bpf_strtoul + * + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to an unsigned long integer according to the + * given base and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)). + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtoul**\ (3). + * + * Returns + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + */ +static long (* const bpf_strtoul)(const char *buf, unsigned long buf_len, __u64 flags, unsigned long *res) = (void *) 106; + +/* + * bpf_sk_storage_get + * + * Get a bpf-local-storage from a *sk*. + * + * Logically, it could be thought of getting the value from + * a *map* with *sk* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *sk*) except this + * helper enforces the key must be a full socket and the map must + * be a **BPF_MAP_TYPE_SK_STORAGE** also. + * + * Underneath, the value is stored locally at *sk* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf-local-storages residing at *sk*. + * + * *sk* is a kernel **struct sock** pointer for LSM program. + * *sk* is a **struct bpf_sock** pointer for other program types. + * + * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf-local-storage will be + * created if one does not exist. *value* can be used + * together with **BPF_SK_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf-local-storage. If *value* is + * **NULL**, the new bpf-local-storage will be zero initialized. + * + * Returns + * A bpf-local-storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf-local-storage. + */ +static void *(* const bpf_sk_storage_get)(void *map, void *sk, void *value, __u64 flags) = (void *) 107; + +/* + * bpf_sk_storage_delete + * + * Delete a bpf-local-storage from a *sk*. + * + * Returns + * 0 on success. + * + * **-ENOENT** if the bpf-local-storage cannot be found. + * **-EINVAL** if sk is not a fullsock (e.g. a request_sock). + */ +static long (* const bpf_sk_storage_delete)(void *map, void *sk) = (void *) 108; + +/* + * bpf_send_signal + * + * Send signal *sig* to the process of the current task. + * The signal may be delivered to any of this process's threads. + * + * Returns + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. + */ +static long (* const bpf_send_signal)(__u32 sig) = (void *) 109; + +/* + * bpf_tcp_gen_syncookie + * + * Try to issue a SYN cookie for the packet with corresponding + * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ipv6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header with options (at least + * **sizeof**\ (**struct tcphdr**)). + * + * Returns + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** SYN cookie cannot be issued due to error + * + * **-ENOENT** SYN cookie should not be issued (no SYN flood) + * + * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies + * + * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 + */ +static __s64 (* const bpf_tcp_gen_syncookie)(void *sk, void *iph, __u32 iph_len, struct tcphdr *th, __u32 th_len) = (void *) 110; + +/* + * bpf_skb_output + * + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct sk_buff. + * + * This helper is similar to **bpf_perf_event_output**\ () but + * restricted to raw_tracepoint bpf programs. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_skb_output)(void *ctx, void *map, __u64 flags, void *data, __u64 size) = (void *) 111; + +/* + * bpf_probe_read_user + * + * Safely attempt to read *size* bytes from user space address + * *unsafe_ptr* and store the data in *dst*. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_probe_read_user)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 112; + +/* + * bpf_probe_read_kernel + * + * Safely attempt to read *size* bytes from kernel space address + * *unsafe_ptr* and store the data in *dst*. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_probe_read_kernel)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 113; + +/* + * bpf_probe_read_user_str + * + * Copy a NUL terminated string from an unsafe user address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, returns the number of bytes that were written, + * including the terminal NUL. This makes this helper useful in + * tracing programs for reading strings, and more importantly to + * get its length at runtime. See the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_user_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read_user**\ () helper here + * instead to read the string would require to estimate the length + * at compile time, and would often result in copying more memory + * than necessary. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * + * Returns + * On success, the strictly positive length of the output string, + * including the trailing NUL character. On error, a negative + * value. + */ +static long (* const bpf_probe_read_user_str)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 114; + +/* + * bpf_probe_read_kernel_str + * + * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr* + * to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply. + * + * Returns + * On success, the strictly positive length of the string, including + * the trailing NUL character. On error, a negative value. + */ +static long (* const bpf_probe_read_kernel_str)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 115; + +/* + * bpf_tcp_send_ack + * + * Send out a tcp-ack. *tp* is the in-kernel struct **tcp_sock**. + * *rcv_nxt* is the ack_seq to be sent out. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_tcp_send_ack)(void *tp, __u32 rcv_nxt) = (void *) 116; + +/* + * bpf_send_signal_thread + * + * Send signal *sig* to the thread corresponding to the current task. + * + * Returns + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. + */ +static long (* const bpf_send_signal_thread)(__u32 sig) = (void *) 117; + +/* + * bpf_jiffies64 + * + * Obtain the 64bit jiffies + * + * Returns + * The 64 bit jiffies + */ +static __u64 (* const bpf_jiffies64)(void) = (void *) 118; + +/* + * bpf_read_branch_records + * + * For an eBPF program attached to a perf event, retrieve the + * branch records (**struct perf_branch_entry**) associated to *ctx* + * and store it in the buffer pointed by *buf* up to size + * *size* bytes. + * + * Returns + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to + * instead return the number of bytes required to store all the + * branch entries. If this flag is set, *buf* may be NULL. + * + * **-EINVAL** if arguments invalid or **size** not a multiple + * of **sizeof**\ (**struct perf_branch_entry**\ ). + * + * **-ENOENT** if architecture does not support branch records. + */ +static long (* const bpf_read_branch_records)(struct bpf_perf_event_data *ctx, void *buf, __u32 size, __u64 flags) = (void *) 119; + +/* + * bpf_get_ns_current_pid_tgid + * + * Returns 0 on success, values for *pid* and *tgid* as seen from the current + * *namespace* will be returned in *nsdata*. + * + * Returns + * 0 on success, or one of the following in case of failure: + * + * **-EINVAL** if dev and inum supplied don't match dev_t and inode number + * with nsfs of current task, or if dev conversion to dev_t lost high bits. + * + * **-ENOENT** if pidns does not exists for the current task. + */ +static long (* const bpf_get_ns_current_pid_tgid)(__u64 dev, __u64 ino, struct bpf_pidns_info *nsdata, __u32 size) = (void *) 120; + +/* + * bpf_xdp_output + * + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct xdp_buff. + * + * This helper is similar to **bpf_perf_eventoutput**\ () but + * restricted to raw_tracepoint bpf programs. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_xdp_output)(void *ctx, void *map, __u64 flags, void *data, __u64 size) = (void *) 121; + +/* + * bpf_get_netns_cookie + * + * Retrieve the cookie (generated by the kernel) of the network + * namespace the input *ctx* is associated with. The network + * namespace cookie remains stable for its lifetime and provides + * a global identifier that can be assumed unique. If *ctx* is + * NULL, then the helper returns the cookie for the initial + * network namespace. The cookie itself is very similar to that + * of **bpf_get_socket_cookie**\ () helper, but for network + * namespaces instead of sockets. + * + * Returns + * A 8-byte long opaque number. + */ +static __u64 (* const bpf_get_netns_cookie)(void *ctx) = (void *) 122; + +/* + * bpf_get_current_ancestor_cgroup_id + * + * Return id of cgroup v2 that is ancestor of the cgroup associated + * with the current task at the *ancestor_level*. The root cgroup + * is at *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with the current task, then return value will be the + * same as that of **bpf_get_current_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with the current task. + * + * The format of returned id and helper limitations are same as in + * **bpf_get_current_cgroup_id**\ (). + * + * Returns + * The id is returned or 0 in case the id could not be retrieved. + */ +static __u64 (* const bpf_get_current_ancestor_cgroup_id)(int ancestor_level) = (void *) 123; + +/* + * bpf_sk_assign + * + * Helper is overloaded depending on BPF program type. This + * description applies to **BPF_PROG_TYPE_SCHED_CLS** and + * **BPF_PROG_TYPE_SCHED_ACT** programs. + * + * Assign the *sk* to the *skb*. When combined with appropriate + * routing configuration to receive the packet towards the socket, + * will cause *skb* to be delivered to the specified socket. + * Subsequent redirection of *skb* via **bpf_redirect**\ (), + * **bpf_clone_redirect**\ () or other methods outside of BPF may + * interfere with successful delivery to the socket. + * + * This operation is only valid from TC ingress path. + * + * The *flags* argument must be zero. + * + * Returns + * 0 on success, or a negative error in case of failure: + * + * **-EINVAL** if specified *flags* are not supported. + * + * **-ENOENT** if the socket is unavailable for assignment. + * + * **-ENETUNREACH** if the socket is unreachable (wrong netns). + * + * **-EOPNOTSUPP** if the operation is not supported, for example + * a call from outside of TC ingress. + */ +static long (* const bpf_sk_assign)(void *ctx, void *sk, __u64 flags) = (void *) 124; + +/* + * bpf_ktime_get_boot_ns + * + * Return the time elapsed since system boot, in nanoseconds. + * Does include the time the system was suspended. + * See: **clock_gettime**\ (**CLOCK_BOOTTIME**) + * + * Returns + * Current *ktime*. + */ +static __u64 (* const bpf_ktime_get_boot_ns)(void) = (void *) 125; + +/* + * bpf_seq_printf + * + * **bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print + * out the format string. + * The *m* represents the seq_file. The *fmt* and *fmt_size* are for + * the format string itself. The *data* and *data_len* are format string + * arguments. The *data* are a **u64** array and corresponding format string + * values are stored in the array. For strings and pointers where pointees + * are accessed, only the pointer values are stored in the *data* array. + * The *data_len* is the size of *data* in bytes - must be a multiple of 8. + * + * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. + * Reading kernel memory may fail due to either invalid address or + * valid address but requiring a major memory fault. If reading kernel memory + * fails, the string for **%s** will be an empty string, and the ip + * address for **%p{i,I}{4,6}** will be 0. Not returning error to + * bpf program is consistent with what **bpf_trace_printk**\ () does for now. + * + * Returns + * 0 on success, or a negative error in case of failure: + * + * **-EBUSY** if per-CPU memory copy buffer is busy, can try again + * by returning 1 from bpf program. + * + * **-EINVAL** if arguments are invalid, or if *fmt* is invalid/unsupported. + * + * **-E2BIG** if *fmt* contains too many format specifiers. + * + * **-EOVERFLOW** if an overflow happened: The same object will be tried again. + */ +static long (* const bpf_seq_printf)(struct seq_file *m, const char *fmt, __u32 fmt_size, const void *data, __u32 data_len) = (void *) 126; + +/* + * bpf_seq_write + * + * **bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data. + * The *m* represents the seq_file. The *data* and *len* represent the + * data to write in bytes. + * + * Returns + * 0 on success, or a negative error in case of failure: + * + * **-EOVERFLOW** if an overflow happened: The same object will be tried again. + */ +static long (* const bpf_seq_write)(struct seq_file *m, const void *data, __u32 len) = (void *) 127; + +/* + * bpf_sk_cgroup_id + * + * Return the cgroup v2 id of the socket *sk*. + * + * *sk* must be a non-**NULL** pointer to a socket, e.g. one + * returned from **bpf_sk_lookup_xxx**\ (), + * **bpf_sk_fullsock**\ (), etc. The format of returned id is + * same as in **bpf_skb_cgroup_id**\ (). + * + * This helper is available only if the kernel was compiled with + * the **CONFIG_SOCK_CGROUP_DATA** configuration option. + * + * Returns + * The id is returned or 0 in case the id could not be retrieved. + */ +static __u64 (* const bpf_sk_cgroup_id)(void *sk) = (void *) 128; + +/* + * bpf_sk_ancestor_cgroup_id + * + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *sk* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *sk*, then return value will be same as that + * of **bpf_sk_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *sk*. + * + * The format of returned id and helper limitations are same as in + * **bpf_sk_cgroup_id**\ (). + * + * Returns + * The id is returned or 0 in case the id could not be retrieved. + */ +static __u64 (* const bpf_sk_ancestor_cgroup_id)(void *sk, int ancestor_level) = (void *) 129; + +/* + * bpf_ringbuf_output + * + * Copy *size* bytes from *data* into a ring buffer *ringbuf*. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. + * If **0** is specified in *flags*, an adaptive notification + * of new data availability is sent. + * + * An adaptive notification is a notification sent whenever the user-space + * process has caught up and consumed all available payloads. In case the user-space + * process is still processing a previous payload, then no notification is needed + * as it will process the newly added payload automatically. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_ringbuf_output)(void *ringbuf, void *data, __u64 size, __u64 flags) = (void *) 130; + +/* + * bpf_ringbuf_reserve + * + * Reserve *size* bytes of payload in a ring buffer *ringbuf*. + * *flags* must be 0. + * + * Returns + * Valid pointer with *size* bytes of memory available; NULL, + * otherwise. + */ +static void *(* const bpf_ringbuf_reserve)(void *ringbuf, __u64 size, __u64 flags) = (void *) 131; + +/* + * bpf_ringbuf_submit + * + * Submit reserved ring buffer sample, pointed to by *data*. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. + * If **0** is specified in *flags*, an adaptive notification + * of new data availability is sent. + * + * See 'bpf_ringbuf_output()' for the definition of adaptive notification. + * + * Returns + * Nothing. Always succeeds. + */ +static void (* const bpf_ringbuf_submit)(void *data, __u64 flags) = (void *) 132; + +/* + * bpf_ringbuf_discard + * + * Discard reserved ring buffer sample, pointed to by *data*. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. + * If **0** is specified in *flags*, an adaptive notification + * of new data availability is sent. + * + * See 'bpf_ringbuf_output()' for the definition of adaptive notification. + * + * Returns + * Nothing. Always succeeds. + */ +static void (* const bpf_ringbuf_discard)(void *data, __u64 flags) = (void *) 133; + +/* + * bpf_ringbuf_query + * + * Query various characteristics of provided ring buffer. What + * exactly is queries is determined by *flags*: + * + * * **BPF_RB_AVAIL_DATA**: Amount of data not yet consumed. + * * **BPF_RB_RING_SIZE**: The size of ring buffer. + * * **BPF_RB_CONS_POS**: Consumer position (can wrap around). + * * **BPF_RB_PROD_POS**: Producer(s) position (can wrap around). + * + * Data returned is just a momentary snapshot of actual values + * and could be inaccurate, so this facility should be used to + * power heuristics and for reporting, not to make 100% correct + * calculation. + * + * Returns + * Requested value, or 0, if *flags* are not recognized. + */ +static __u64 (* const bpf_ringbuf_query)(void *ringbuf, __u64 flags) = (void *) 134; + +/* + * bpf_csum_level + * + * Change the skbs checksum level by one layer up or down, or + * reset it entirely to none in order to have the stack perform + * checksum validation. The level is applicable to the following + * protocols: TCP, UDP, GRE, SCTP, FCOE. For example, a decap of + * | ETH | IP | UDP | GUE | IP | TCP | into | ETH | IP | TCP | + * through **bpf_skb_adjust_room**\ () helper with passing in + * **BPF_F_ADJ_ROOM_NO_CSUM_RESET** flag would require one call + * to **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_DEC** since + * the UDP header is removed. Similarly, an encap of the latter + * into the former could be accompanied by a helper call to + * **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_INC** if the + * skb is still intended to be processed in higher layers of the + * stack instead of just egressing at tc. + * + * There are three supported level settings at this time: + * + * * **BPF_CSUM_LEVEL_INC**: Increases skb->csum_level for skbs + * with CHECKSUM_UNNECESSARY. + * * **BPF_CSUM_LEVEL_DEC**: Decreases skb->csum_level for skbs + * with CHECKSUM_UNNECESSARY. + * * **BPF_CSUM_LEVEL_RESET**: Resets skb->csum_level to 0 and + * sets CHECKSUM_NONE to force checksum validation by the stack. + * * **BPF_CSUM_LEVEL_QUERY**: No-op, returns the current + * skb->csum_level. + * + * Returns + * 0 on success, or a negative error in case of failure. In the + * case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level + * is returned or the error code -EACCES in case the skb is not + * subject to CHECKSUM_UNNECESSARY. + */ +static long (* const bpf_csum_level)(struct __sk_buff *skb, __u64 level) = (void *) 135; + +/* + * bpf_skc_to_tcp6_sock + * + * Dynamically cast a *sk* pointer to a *tcp6_sock* pointer. + * + * Returns + * *sk* if casting is valid, or **NULL** otherwise. + */ +static struct tcp6_sock *(* const bpf_skc_to_tcp6_sock)(void *sk) = (void *) 136; + +/* + * bpf_skc_to_tcp_sock + * + * Dynamically cast a *sk* pointer to a *tcp_sock* pointer. + * + * Returns + * *sk* if casting is valid, or **NULL** otherwise. + */ +static struct tcp_sock *(* const bpf_skc_to_tcp_sock)(void *sk) = (void *) 137; + +/* + * bpf_skc_to_tcp_timewait_sock + * + * Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer. + * + * Returns + * *sk* if casting is valid, or **NULL** otherwise. + */ +static struct tcp_timewait_sock *(* const bpf_skc_to_tcp_timewait_sock)(void *sk) = (void *) 138; + +/* + * bpf_skc_to_tcp_request_sock + * + * Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer. + * + * Returns + * *sk* if casting is valid, or **NULL** otherwise. + */ +static struct tcp_request_sock *(* const bpf_skc_to_tcp_request_sock)(void *sk) = (void *) 139; + +/* + * bpf_skc_to_udp6_sock + * + * Dynamically cast a *sk* pointer to a *udp6_sock* pointer. + * + * Returns + * *sk* if casting is valid, or **NULL** otherwise. + */ +static struct udp6_sock *(* const bpf_skc_to_udp6_sock)(void *sk) = (void *) 140; + +/* + * bpf_get_task_stack + * + * Return a user or a kernel stack in bpf program provided buffer. + * Note: the user stack will only be populated if the *task* is + * the current task; all other tasks will return -EOPNOTSUPP. + * To achieve this, the helper needs *task*, which is a valid + * pointer to **struct task_struct**. To store the stacktrace, the + * bpf program provides *buf* with a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * The *task* must be the current task. + * **BPF_F_USER_BUILD_ID** + * Collect buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **bpf_get_task_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack= + * + * Returns + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. + */ +static long (* const bpf_get_task_stack)(struct task_struct *task, void *buf, __u32 size, __u64 flags) = (void *) 141; + +/* + * bpf_load_hdr_opt + * + * Load header option. Support reading a particular TCP header + * option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**). + * + * If *flags* is 0, it will search the option from the + * *skops*\ **->skb_data**. The comment in **struct bpf_sock_ops** + * has details on what skb_data contains under different + * *skops*\ **->op**. + * + * The first byte of the *searchby_res* specifies the + * kind that it wants to search. + * + * If the searching kind is an experimental kind + * (i.e. 253 or 254 according to RFC6994). It also + * needs to specify the "magic" which is either + * 2 bytes or 4 bytes. It then also needs to + * specify the size of the magic by using + * the 2nd byte which is "kind-length" of a TCP + * header option and the "kind-length" also + * includes the first 2 bytes "kind" and "kind-length" + * itself as a normal TCP header option also does. + * + * For example, to search experimental kind 254 with + * 2 byte magic 0xeB9F, the searchby_res should be + * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ]. + * + * To search for the standard window scale option (3), + * the *searchby_res* should be [ 3, 0, 0, .... 0 ]. + * Note, kind-length must be 0 for regular option. + * + * Searching for No-Op (0) and End-of-Option-List (1) are + * not supported. + * + * *len* must be at least 2 bytes which is the minimal size + * of a header option. + * + * Supported flags: + * + * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the + * saved_syn packet or the just-received syn packet. + * + * + * Returns + * > 0 when found, the header option is copied to *searchby_res*. + * The return value is the total length copied. On failure, a + * negative error code is returned: + * + * **-EINVAL** if a parameter is invalid. + * + * **-ENOMSG** if the option is not found. + * + * **-ENOENT** if no syn packet is available when + * **BPF_LOAD_HDR_OPT_TCP_SYN** is used. + * + * **-ENOSPC** if there is not enough space. Only *len* number of + * bytes are copied. + * + * **-EFAULT** on failure to parse the header options in the + * packet. + * + * **-EPERM** if the helper cannot be used under the current + * *skops*\ **->op**. + */ +static long (* const bpf_load_hdr_opt)(struct bpf_sock_ops *skops, void *searchby_res, __u32 len, __u64 flags) = (void *) 142; + +/* + * bpf_store_hdr_opt + * + * Store header option. The data will be copied + * from buffer *from* with length *len* to the TCP header. + * + * The buffer *from* should have the whole option that + * includes the kind, kind-length, and the actual + * option data. The *len* must be at least kind-length + * long. The kind-length does not have to be 4 byte + * aligned. The kernel will take care of the padding + * and setting the 4 bytes aligned value to th->doff. + * + * This helper will check for duplicated option + * by searching the same option in the outgoing skb. + * + * This helper can only be called during + * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**. + * + * + * Returns + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** If param is invalid. + * + * **-ENOSPC** if there is not enough space in the header. + * Nothing has been written + * + * **-EEXIST** if the option already exists. + * + * **-EFAULT** on failure to parse the existing header options. + * + * **-EPERM** if the helper cannot be used under the current + * *skops*\ **->op**. + */ +static long (* const bpf_store_hdr_opt)(struct bpf_sock_ops *skops, const void *from, __u32 len, __u64 flags) = (void *) 143; + +/* + * bpf_reserve_hdr_opt + * + * Reserve *len* bytes for the bpf header option. The + * space will be used by **bpf_store_hdr_opt**\ () later in + * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**. + * + * If **bpf_reserve_hdr_opt**\ () is called multiple times, + * the total number of bytes will be reserved. + * + * This helper can only be called during + * **BPF_SOCK_OPS_HDR_OPT_LEN_CB**. + * + * + * Returns + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** if a parameter is invalid. + * + * **-ENOSPC** if there is not enough space in the header. + * + * **-EPERM** if the helper cannot be used under the current + * *skops*\ **->op**. + */ +static long (* const bpf_reserve_hdr_opt)(struct bpf_sock_ops *skops, __u32 len, __u64 flags) = (void *) 144; + +/* + * bpf_inode_storage_get + * + * Get a bpf_local_storage from an *inode*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *inode* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this + * helper enforces the key must be an inode and the map must also + * be a **BPF_MAP_TYPE_INODE_STORAGE**. + * + * Underneath, the value is stored locally at *inode* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf_local_storage residing at *inode*. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * + * Returns + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + */ +static void *(* const bpf_inode_storage_get)(void *map, void *inode, void *value, __u64 flags) = (void *) 145; + +/* + * bpf_inode_storage_delete + * + * Delete a bpf_local_storage from an *inode*. + * + * Returns + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. + */ +static int (* const bpf_inode_storage_delete)(void *map, void *inode) = (void *) 146; + +/* + * bpf_d_path + * + * Return full path for given **struct path** object, which + * needs to be the kernel BTF *path* object. The path is + * returned in the provided buffer *buf* of size *sz* and + * is zero terminated. + * + * + * Returns + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + */ +static long (* const bpf_d_path)(struct path *path, char *buf, __u32 sz) = (void *) 147; + +/* + * bpf_copy_from_user + * + * Read *size* bytes from user space address *user_ptr* and store + * the data in *dst*. This is a wrapper of **copy_from_user**\ (). + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_copy_from_user)(void *dst, __u32 size, const void *user_ptr) = (void *) 148; + +/* + * bpf_snprintf_btf + * + * Use BTF to store a string representation of *ptr*->ptr in *str*, + * using *ptr*->type_id. This value should specify the type + * that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1) + * can be used to look up vmlinux BTF type ids. Traversing the + * data structure using BTF, the type information and values are + * stored in the first *str_size* - 1 bytes of *str*. Safe copy of + * the pointer data is carried out to avoid kernel crashes during + * operation. Smaller types can use string space on the stack; + * larger programs can use map data to store the string + * representation. + * + * The string can be subsequently shared with userspace via + * bpf_perf_event_output() or ring buffer interfaces. + * bpf_trace_printk() is to be avoided as it places too small + * a limit on string size to be useful. + * + * *flags* is a combination of + * + * **BTF_F_COMPACT** + * no formatting around type information + * **BTF_F_NONAME** + * no struct/union member names/types + * **BTF_F_PTR_RAW** + * show raw (unobfuscated) pointer values; + * equivalent to printk specifier %px. + * **BTF_F_ZERO** + * show zero-valued struct/union members; they + * are not displayed by default + * + * + * Returns + * The number of bytes that were written (or would have been + * written if output had to be truncated due to string size), + * or a negative error in cases of failure. + */ +static long (* const bpf_snprintf_btf)(char *str, __u32 str_size, struct btf_ptr *ptr, __u32 btf_ptr_size, __u64 flags) = (void *) 149; + +/* + * bpf_seq_printf_btf + * + * Use BTF to write to seq_write a string representation of + * *ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf(). + * *flags* are identical to those used for bpf_snprintf_btf. + * + * Returns + * 0 on success or a negative error in case of failure. + */ +static long (* const bpf_seq_printf_btf)(struct seq_file *m, struct btf_ptr *ptr, __u32 ptr_size, __u64 flags) = (void *) 150; + +/* + * bpf_skb_cgroup_classid + * + * See **bpf_get_cgroup_classid**\ () for the main description. + * This helper differs from **bpf_get_cgroup_classid**\ () in that + * the cgroup v1 net_cls class is retrieved only from the *skb*'s + * associated socket instead of the current process. + * + * Returns + * The id is returned or 0 in case the id could not be retrieved. + */ +static __u64 (* const bpf_skb_cgroup_classid)(struct __sk_buff *skb) = (void *) 151; + +/* + * bpf_redirect_neigh + * + * Redirect the packet to another net device of index *ifindex* + * and fill in L2 addresses from neighboring subsystem. This helper + * is somewhat similar to **bpf_redirect**\ (), except that it + * populates L2 addresses as well, meaning, internally, the helper + * relies on the neighbor lookup for the L2 address of the nexthop. + * + * The helper will perform a FIB lookup based on the skb's + * networking header to get the address of the next hop, unless + * this is supplied by the caller in the *params* argument. The + * *plen* argument indicates the len of *params* and should be set + * to 0 if *params* is NULL. + * + * The *flags* argument is reserved and must be 0. The helper is + * currently only supported for tc BPF program types, and enabled + * for IPv4 and IPv6 protocols. + * + * Returns + * The helper returns **TC_ACT_REDIRECT** on success or + * **TC_ACT_SHOT** on error. + */ +static long (* const bpf_redirect_neigh)(__u32 ifindex, struct bpf_redir_neigh *params, int plen, __u64 flags) = (void *) 152; + +/* + * bpf_per_cpu_ptr + * + * Take a pointer to a percpu ksym, *percpu_ptr*, and return a + * pointer to the percpu kernel variable on *cpu*. A ksym is an + * extern variable decorated with '__ksym'. For ksym, there is a + * global var (either static or global) defined of the same name + * in the kernel. The ksym is percpu if the global var is percpu. + * The returned pointer points to the global percpu var on *cpu*. + * + * bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the + * kernel, except that bpf_per_cpu_ptr() may return NULL. This + * happens if *cpu* is larger than nr_cpu_ids. The caller of + * bpf_per_cpu_ptr() must check the returned value. + * + * Returns + * A pointer pointing to the kernel percpu variable on *cpu*, or + * NULL, if *cpu* is invalid. + */ +static void *(* const bpf_per_cpu_ptr)(const void *percpu_ptr, __u32 cpu) = (void *) 153; + +/* + * bpf_this_cpu_ptr + * + * Take a pointer to a percpu ksym, *percpu_ptr*, and return a + * pointer to the percpu kernel variable on this cpu. See the + * description of 'ksym' in **bpf_per_cpu_ptr**\ (). + * + * bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in + * the kernel. Different from **bpf_per_cpu_ptr**\ (), it would + * never return NULL. + * + * Returns + * A pointer pointing to the kernel percpu variable on this cpu. + */ +static void *(* const bpf_this_cpu_ptr)(const void *percpu_ptr) = (void *) 154; + +/* + * bpf_redirect_peer + * + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_redirect**\ (), except + * that the redirection happens to the *ifindex*' peer device and + * the netns switch takes place from ingress to ingress without + * going through the CPU's backlog queue. + * + * The *flags* argument is reserved and must be 0. The helper is + * currently only supported for tc BPF program types at the + * ingress hook and for veth and netkit target device types. The + * peer device must reside in a different network namespace. + * + * Returns + * The helper returns **TC_ACT_REDIRECT** on success or + * **TC_ACT_SHOT** on error. + */ +static long (* const bpf_redirect_peer)(__u32 ifindex, __u64 flags) = (void *) 155; + +/* + * bpf_task_storage_get + * + * Get a bpf_local_storage from the *task*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *task* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this + * helper enforces the key must be a task_struct and the map must also + * be a **BPF_MAP_TYPE_TASK_STORAGE**. + * + * Underneath, the value is stored locally at *task* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf_local_storage residing at *task*. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * + * Returns + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + */ +static void *(* const bpf_task_storage_get)(void *map, struct task_struct *task, void *value, __u64 flags) = (void *) 156; + +/* + * bpf_task_storage_delete + * + * Delete a bpf_local_storage from a *task*. + * + * Returns + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. + */ +static long (* const bpf_task_storage_delete)(void *map, struct task_struct *task) = (void *) 157; + +/* + * bpf_get_current_task_btf + * + * Return a BTF pointer to the "current" task. + * This pointer can also be used in helpers that accept an + * *ARG_PTR_TO_BTF_ID* of type *task_struct*. + * + * Returns + * Pointer to the current task. + */ +static struct task_struct *(* const bpf_get_current_task_btf)(void) = (void *) 158; + +/* + * bpf_bprm_opts_set + * + * Set or clear certain options on *bprm*: + * + * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit + * which sets the **AT_SECURE** auxv for glibc. The bit + * is cleared if the flag is not specified. + * + * Returns + * **-EINVAL** if invalid *flags* are passed, zero otherwise. + */ +static long (* const bpf_bprm_opts_set)(struct linux_binprm *bprm, __u64 flags) = (void *) 159; + +/* + * bpf_ktime_get_coarse_ns + * + * Return a coarse-grained version of the time elapsed since + * system boot, in nanoseconds. Does not include time the system + * was suspended. + * + * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) + * + * Returns + * Current *ktime*. + */ +static __u64 (* const bpf_ktime_get_coarse_ns)(void) = (void *) 160; + +/* + * bpf_ima_inode_hash + * + * Returns the stored IMA hash of the *inode* (if it's available). + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * + * Returns + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * invalid arguments are passed. + */ +static long (* const bpf_ima_inode_hash)(struct inode *inode, void *dst, __u32 size) = (void *) 161; + +/* + * bpf_sock_from_file + * + * If the given file represents a socket, returns the associated + * socket. + * + * Returns + * A pointer to a struct socket on success or NULL if the file is + * not a socket. + */ +static struct socket *(* const bpf_sock_from_file)(struct file *file) = (void *) 162; + +/* + * bpf_check_mtu + * + * Check packet size against exceeding MTU of net device (based + * on *ifindex*). This helper will likely be used in combination + * with helpers that adjust/change the packet size. + * + * The argument *len_diff* can be used for querying with a planned + * size change. This allows to check MTU prior to changing packet + * ctx. Providing a *len_diff* adjustment that is larger than the + * actual packet size (resulting in negative packet size) will in + * principle not exceed the MTU, which is why it is not considered + * a failure. Other BPF helpers are needed for performing the + * planned size change; therefore the responsibility for catching + * a negative packet size belongs in those helpers. + * + * Specifying *ifindex* zero means the MTU check is performed + * against the current net device. This is practical if this isn't + * used prior to redirect. + * + * On input *mtu_len* must be a valid pointer, else verifier will + * reject BPF program. If the value *mtu_len* is initialized to + * zero then the ctx packet size is use. When value *mtu_len* is + * provided as input this specify the L3 length that the MTU check + * is done against. Remember XDP and TC length operate at L2, but + * this value is L3 as this correlate to MTU and IP-header tot_len + * values which are L3 (similar behavior as bpf_fib_lookup). + * + * The Linux kernel route table can configure MTUs on a more + * specific per route level, which is not provided by this helper. + * For route level MTU checks use the **bpf_fib_lookup**\ () + * helper. + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** for tc cls_act programs. + * + * The *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_MTU_CHK_SEGS** + * This flag will only works for *ctx* **struct sk_buff**. + * If packet context contains extra packet segment buffers + * (often knows as GSO skb), then MTU check is harder to + * check at this point, because in transmit path it is + * possible for the skb packet to get re-segmented + * (depending on net device features). This could still be + * a MTU violation, so this flag enables performing MTU + * check against segments, with a different violation + * return code to tell it apart. Check cannot use len_diff. + * + * On return *mtu_len* pointer contains the MTU value of the net + * device. Remember the net device configured MTU is the L3 size, + * which is returned here and XDP and TC length operate at L2. + * Helper take this into account for you, but remember when using + * MTU value in your BPF-code. + * + * + * Returns + * * 0 on success, and populate MTU value in *mtu_len* pointer. + * + * * < 0 if any input argument is invalid (*mtu_len* not updated) + * + * MTU violations return positive values, but also populate MTU + * value in *mtu_len* pointer, as this can be needed for + * implementing PMTU handing: + * + * * **BPF_MTU_CHK_RET_FRAG_NEEDED** + * * **BPF_MTU_CHK_RET_SEGS_TOOBIG** + */ +static long (* const bpf_check_mtu)(void *ctx, __u32 ifindex, __u32 *mtu_len, __s32 len_diff, __u64 flags) = (void *) 163; + +/* + * bpf_for_each_map_elem + * + * For each element in **map**, call **callback_fn** function with + * **map**, **callback_ctx** and other map-specific parameters. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. + * + * The following are a list of supported map types and their + * respective expected callback signatures: + * + * BPF_MAP_TYPE_HASH, BPF_MAP_TYPE_PERCPU_HASH, + * BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH, + * BPF_MAP_TYPE_ARRAY, BPF_MAP_TYPE_PERCPU_ARRAY + * + * long (\*callback_fn)(struct bpf_map \*map, const void \*key, void \*value, void \*ctx); + * + * For per_cpu maps, the map_value is the value on the cpu where the + * bpf_prog is running. + * + * If **callback_fn** return 0, the helper will continue to the next + * element. If return value is 1, the helper will skip the rest of + * elements and return. Other return values are not used now. + * + * + * Returns + * The number of traversed map elements for success, **-EINVAL** for + * invalid **flags**. + */ +static long (* const bpf_for_each_map_elem)(void *map, void *callback_fn, void *callback_ctx, __u64 flags) = (void *) 164; + +/* + * bpf_snprintf + * + * Outputs a string into the **str** buffer of size **str_size** + * based on a format string stored in a read-only map pointed by + * **fmt**. + * + * Each format specifier in **fmt** corresponds to one u64 element + * in the **data** array. For strings and pointers where pointees + * are accessed, only the pointer values are stored in the *data* + * array. The *data_len* is the size of *data* in bytes - must be + * a multiple of 8. + * + * Formats **%s** and **%p{i,I}{4,6}** require to read kernel + * memory. Reading kernel memory may fail due to either invalid + * address or valid address but requiring a major memory fault. If + * reading kernel memory fails, the string for **%s** will be an + * empty string, and the ip address for **%p{i,I}{4,6}** will be 0. + * Not returning error to bpf program is consistent with what + * **bpf_trace_printk**\ () does for now. + * + * + * Returns + * The strictly positive length of the formatted string, including + * the trailing zero character. If the return value is greater than + * **str_size**, **str** contains a truncated string, guaranteed to + * be zero-terminated except when **str_size** is 0. + * + * Or **-EBUSY** if the per-CPU memory copy buffer is busy. + */ +static long (* const bpf_snprintf)(char *str, __u32 str_size, const char *fmt, __u64 *data, __u32 data_len) = (void *) 165; + +/* + * bpf_sys_bpf + * + * Execute bpf syscall with given arguments. + * + * Returns + * A syscall result. + */ +static long (* const bpf_sys_bpf)(__u32 cmd, void *attr, __u32 attr_size) = (void *) 166; + +/* + * bpf_btf_find_by_name_kind + * + * Find BTF type with given name and kind in vmlinux BTF or in module's BTFs. + * + * Returns + * Returns btf_id and btf_obj_fd in lower and upper 32 bits. + */ +static long (* const bpf_btf_find_by_name_kind)(char *name, int name_sz, __u32 kind, int flags) = (void *) 167; + +/* + * bpf_sys_close + * + * Execute close syscall for given FD. + * + * Returns + * A syscall result. + */ +static long (* const bpf_sys_close)(__u32 fd) = (void *) 168; + +/* + * bpf_timer_init + * + * Initialize the timer. + * First 4 bits of *flags* specify clockid. + * Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed. + * All other bits of *flags* are reserved. + * The verifier will reject the program if *timer* is not from + * the same *map*. + * + * Returns + * 0 on success. + * **-EBUSY** if *timer* is already initialized. + * **-EINVAL** if invalid *flags* are passed. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + */ +static long (* const bpf_timer_init)(struct bpf_timer *timer, void *map, __u64 flags) = (void *) 169; + +/* + * bpf_timer_set_callback + * + * Configure the timer to call *callback_fn* static function. + * + * Returns + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + */ +static long (* const bpf_timer_set_callback)(struct bpf_timer *timer, void *callback_fn) = (void *) 170; + +/* + * bpf_timer_start + * + * Set timer expiration N nanoseconds from the current time. The + * configured callback will be invoked in soft irq context on some cpu + * and will not repeat unless another bpf_timer_start() is made. + * In such case the next invocation can migrate to a different cpu. + * Since struct bpf_timer is a field inside map element the map + * owns the timer. The bpf_timer_set_callback() will increment refcnt + * of BPF program to make sure that callback_fn code stays valid. + * When user space reference to a map reaches zero all timers + * in a map are cancelled and corresponding program's refcnts are + * decremented. This is done to make sure that Ctrl-C of a user + * process doesn't leave any timers running. If map is pinned in + * bpffs the callback_fn can re-arm itself indefinitely. + * bpf_map_update/delete_elem() helpers and user space sys_bpf commands + * cancel and free the timer in the given map element. + * The map can contain timers that invoke callback_fn-s from different + * programs. The same callback_fn can serve different timers from + * different maps if key/value layout matches across maps. + * Every bpf_timer_set_callback() can have different callback_fn. + * + * *flags* can be one of: + * + * **BPF_F_TIMER_ABS** + * Start the timer in absolute expire value instead of the + * default relative one. + * **BPF_F_TIMER_CPU_PIN** + * Timer will be pinned to the CPU of the caller. + * + * + * Returns + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier + * or invalid *flags* are passed. + */ +static long (* const bpf_timer_start)(struct bpf_timer *timer, __u64 nsecs, __u64 flags) = (void *) 171; + +/* + * bpf_timer_cancel + * + * Cancel the timer and wait for callback_fn to finish if it was running. + * + * Returns + * 0 if the timer was not active. + * 1 if the timer was active. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its + * own timer which would have led to a deadlock otherwise. + */ +static long (* const bpf_timer_cancel)(struct bpf_timer *timer) = (void *) 172; + +/* + * bpf_get_func_ip + * + * Get address of the traced function (for tracing and kprobe programs). + * + * When called for kprobe program attached as uprobe it returns + * probe address for both entry and return uprobe. + * + * + * Returns + * Address of the traced function for kprobe. + * 0 for kprobes placed within the function (not at the entry). + * Address of the probe for uprobe and return uprobe. + */ +static __u64 (* const bpf_get_func_ip)(void *ctx) = (void *) 173; + +/* + * bpf_get_attach_cookie + * + * Get bpf_cookie value provided (optionally) during the program + * attachment. It might be different for each individual + * attachment, even if BPF program itself is the same. + * Expects BPF program context *ctx* as a first argument. + * + * Supported for the following program types: + * - kprobe/uprobe; + * - tracepoint; + * - perf_event. + * + * Returns + * Value specified by user at BPF link creation/attachment time + * or 0, if it was not specified. + */ +static __u64 (* const bpf_get_attach_cookie)(void *ctx) = (void *) 174; + +/* + * bpf_task_pt_regs + * + * Get the struct pt_regs associated with **task**. + * + * Returns + * A pointer to struct pt_regs. + */ +static long (* const bpf_task_pt_regs)(struct task_struct *task) = (void *) 175; + +/* + * bpf_get_branch_snapshot + * + * Get branch trace from hardware engines like Intel LBR. The + * hardware engine is stopped shortly after the helper is + * called. Therefore, the user need to filter branch entries + * based on the actual use case. To capture branch trace + * before the trigger point of the BPF program, the helper + * should be called at the beginning of the BPF program. + * + * The data is stored as struct perf_branch_entry into output + * buffer *entries*. *size* is the size of *entries* in bytes. + * *flags* is reserved for now and must be zero. + * + * + * Returns + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-ENOENT** if architecture does not support branch records. + */ +static long (* const bpf_get_branch_snapshot)(void *entries, __u32 size, __u64 flags) = (void *) 176; + +/* + * bpf_trace_vprintk + * + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * + * Returns + * The number of bytes written to the buffer, or a negative error + * in case of failure. + */ +static long (* const bpf_trace_vprintk)(const char *fmt, __u32 fmt_size, const void *data, __u32 data_len) = (void *) 177; + +/* + * bpf_skc_to_unix_sock + * + * Dynamically cast a *sk* pointer to a *unix_sock* pointer. + * + * Returns + * *sk* if casting is valid, or **NULL** otherwise. + */ +static struct unix_sock *(* const bpf_skc_to_unix_sock)(void *sk) = (void *) 178; + +/* + * bpf_kallsyms_lookup_name + * + * Get the address of a kernel symbol, returned in *res*. *res* is + * set to 0 if the symbol is not found. + * + * Returns + * On success, zero. On error, a negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-EINVAL** if string *name* is not the same size as *name_sz*. + * + * **-ENOENT** if symbol is not found. + * + * **-EPERM** if caller does not have permission to obtain kernel address. + */ +static long (* const bpf_kallsyms_lookup_name)(const char *name, int name_sz, int flags, __u64 *res) = (void *) 179; + +/* + * bpf_find_vma + * + * Find vma of *task* that contains *addr*, call *callback_fn* + * function with *task*, *vma*, and *callback_ctx*. + * The *callback_fn* should be a static function and + * the *callback_ctx* should be a pointer to the stack. + * The *flags* is used to control certain aspects of the helper. + * Currently, the *flags* must be 0. + * + * The expected callback signature is + * + * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx); + * + * + * Returns + * 0 on success. + * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. + * **-EBUSY** if failed to try lock mmap_lock. + * **-EINVAL** for invalid **flags**. + */ +static long (* const bpf_find_vma)(struct task_struct *task, __u64 addr, void *callback_fn, void *callback_ctx, __u64 flags) = (void *) 180; + +/* + * bpf_loop + * + * For **nr_loops**, call **callback_fn** function + * with **callback_ctx** as the context parameter. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. Currently, nr_loops is + * limited to 1 << 23 (~8 million) loops. + * + * long (\*callback_fn)(u32 index, void \*ctx); + * + * where **index** is the current index in the loop. The index + * is zero-indexed. + * + * If **callback_fn** returns 0, the helper will continue to the next + * loop. If return value is 1, the helper will skip the rest of + * the loops and return. Other return values are not used now, + * and will be rejected by the verifier. + * + * + * Returns + * The number of loops performed, **-EINVAL** for invalid **flags**, + * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. + */ +static long (* const bpf_loop)(__u32 nr_loops, void *callback_fn, void *callback_ctx, __u64 flags) = (void *) 181; + +/* + * bpf_strncmp + * + * Do strncmp() between **s1** and **s2**. **s1** doesn't need + * to be null-terminated and **s1_sz** is the maximum storage + * size of **s1**. **s2** must be a read-only string. + * + * Returns + * An integer less than, equal to, or greater than zero + * if the first **s1_sz** bytes of **s1** is found to be + * less than, to match, or be greater than **s2**. + */ +static long (* const bpf_strncmp)(const char *s1, __u32 s1_sz, const char *s2) = (void *) 182; + +/* + * bpf_get_func_arg + * + * Get **n**-th argument register (zero based) of the traced function (for tracing programs) + * returned in **value**. + * + * + * Returns + * 0 on success. + * **-EINVAL** if n >= argument register count of traced function. + */ +static long (* const bpf_get_func_arg)(void *ctx, __u32 n, __u64 *value) = (void *) 183; + +/* + * bpf_get_func_ret + * + * Get return value of the traced function (for tracing programs) + * in **value**. + * + * + * Returns + * 0 on success. + * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN. + */ +static long (* const bpf_get_func_ret)(void *ctx, __u64 *value) = (void *) 184; + +/* + * bpf_get_func_arg_cnt + * + * Get number of registers of the traced function (for tracing programs) where + * function arguments are stored in these registers. + * + * + * Returns + * The number of argument registers of the traced function. + */ +static long (* const bpf_get_func_arg_cnt)(void *ctx) = (void *) 185; + +/* + * bpf_get_retval + * + * Get the BPF program's return value that will be returned to the upper layers. + * + * This helper is currently supported by cgroup programs and only by the hooks + * where BPF program's return value is returned to the userspace via errno. + * + * Returns + * The BPF program's return value. + */ +static int (* const bpf_get_retval)(void) = (void *) 186; + +/* + * bpf_set_retval + * + * Set the BPF program's return value that will be returned to the upper layers. + * + * This helper is currently supported by cgroup programs and only by the hooks + * where BPF program's return value is returned to the userspace via errno. + * + * Note that there is the following corner case where the program exports an error + * via bpf_set_retval but signals success via 'return 1': + * + * bpf_set_retval(-EPERM); + * return 1; + * + * In this case, the BPF program's return value will use helper's -EPERM. This + * still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case. + * + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (* const bpf_set_retval)(int retval) = (void *) 187; + +/* + * bpf_xdp_get_buff_len + * + * Get the total size of a given xdp buff (linear and paged area) + * + * Returns + * The total size of a given xdp buffer. + */ +static __u64 (* const bpf_xdp_get_buff_len)(struct xdp_md *xdp_md) = (void *) 188; + +/* + * bpf_xdp_load_bytes + * + * This helper is provided as an easy way to load data from a + * xdp buffer. It can be used to load *len* bytes from *offset* from + * the frame associated to *xdp_md*, into the buffer pointed by + * *buf*. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_xdp_load_bytes)(struct xdp_md *xdp_md, __u32 offset, void *buf, __u32 len) = (void *) 189; + +/* + * bpf_xdp_store_bytes + * + * Store *len* bytes from buffer *buf* into the frame + * associated to *xdp_md*, at *offset*. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_xdp_store_bytes)(struct xdp_md *xdp_md, __u32 offset, void *buf, __u32 len) = (void *) 190; + +/* + * bpf_copy_from_user_task + * + * Read *size* bytes from user space address *user_ptr* in *tsk*'s + * address space, and stores the data in *dst*. *flags* is not + * used yet and is provided for future extensibility. This helper + * can only be used by sleepable programs. + * + * Returns + * 0 on success, or a negative error in case of failure. On error + * *dst* buffer is zeroed out. + */ +static long (* const bpf_copy_from_user_task)(void *dst, __u32 size, const void *user_ptr, struct task_struct *tsk, __u64 flags) = (void *) 191; + +/* + * bpf_skb_set_tstamp + * + * Change the __sk_buff->tstamp_type to *tstamp_type* + * and set *tstamp* to the __sk_buff->tstamp together. + * + * If there is no need to change the __sk_buff->tstamp_type, + * the tstamp value can be directly written to __sk_buff->tstamp + * instead. + * + * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that + * will be kept during bpf_redirect_*(). A non zero + * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO + * *tstamp_type*. + * + * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used + * with a zero *tstamp*. + * + * Only IPv4 and IPv6 skb->protocol are supported. + * + * This function is most useful when it needs to set a + * mono delivery time to __sk_buff->tstamp and then + * bpf_redirect_*() to the egress of an iface. For example, + * changing the (rcv) timestamp in __sk_buff->tstamp at + * ingress to a mono delivery time and then bpf_redirect_*() + * to sch_fq@phy-dev. + * + * Returns + * 0 on success. + * **-EINVAL** for invalid input + * **-EOPNOTSUPP** for unsupported protocol + */ +static long (* const bpf_skb_set_tstamp)(struct __sk_buff *skb, __u64 tstamp, __u32 tstamp_type) = (void *) 192; + +/* + * bpf_ima_file_hash + * + * Returns a calculated IMA hash of the *file*. + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * + * Returns + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * invalid arguments are passed. + */ +static long (* const bpf_ima_file_hash)(struct file *file, void *dst, __u32 size) = (void *) 193; + +/* + * bpf_kptr_xchg + * + * Exchange kptr at pointer *map_value* with *ptr*, and return the + * old value. *ptr* can be NULL, otherwise it must be a referenced + * pointer which will be released when this helper is called. + * + * Returns + * The old value of kptr (which can be NULL). The returned pointer + * if not NULL, is a reference which must be released using its + * corresponding release function, or moved into a BPF map before + * program exit. + */ +static void *(* const bpf_kptr_xchg)(void *map_value, void *ptr) = (void *) 194; + +/* + * bpf_map_lookup_percpu_elem + * + * Perform a lookup in *percpu map* for an entry associated to + * *key* on *cpu*. + * + * Returns + * Map value associated to *key* on *cpu*, or **NULL** if no entry + * was found or *cpu* is invalid. + */ +static void *(* const bpf_map_lookup_percpu_elem)(void *map, const void *key, __u32 cpu) = (void *) 195; + +/* + * bpf_skc_to_mptcp_sock + * + * Dynamically cast a *sk* pointer to a *mptcp_sock* pointer. + * + * Returns + * *sk* if casting is valid, or **NULL** otherwise. + */ +static struct mptcp_sock *(* const bpf_skc_to_mptcp_sock)(void *sk) = (void *) 196; + +/* + * bpf_dynptr_from_mem + * + * Get a dynptr to local memory *data*. + * + * *data* must be a ptr to a map value. + * The maximum *size* supported is DYNPTR_MAX_SIZE. + * *flags* is currently unused. + * + * Returns + * 0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE, + * -EINVAL if flags is not 0. + */ +static long (* const bpf_dynptr_from_mem)(void *data, __u32 size, __u64 flags, struct bpf_dynptr *ptr) = (void *) 197; + +/* + * bpf_ringbuf_reserve_dynptr + * + * Reserve *size* bytes of payload in a ring buffer *ringbuf* + * through the dynptr interface. *flags* must be 0. + * + * Please note that a corresponding bpf_ringbuf_submit_dynptr or + * bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the + * reservation fails. This is enforced by the verifier. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static long (* const bpf_ringbuf_reserve_dynptr)(void *ringbuf, __u32 size, __u64 flags, struct bpf_dynptr *ptr) = (void *) 198; + +/* + * bpf_ringbuf_submit_dynptr + * + * Submit reserved ring buffer sample, pointed to by *data*, + * through the dynptr interface. This is a no-op if the dynptr is + * invalid/null. + * + * For more information on *flags*, please see + * 'bpf_ringbuf_submit'. + * + * Returns + * Nothing. Always succeeds. + */ +static void (* const bpf_ringbuf_submit_dynptr)(struct bpf_dynptr *ptr, __u64 flags) = (void *) 199; + +/* + * bpf_ringbuf_discard_dynptr + * + * Discard reserved ring buffer sample through the dynptr + * interface. This is a no-op if the dynptr is invalid/null. + * + * For more information on *flags*, please see + * 'bpf_ringbuf_discard'. + * + * Returns + * Nothing. Always succeeds. + */ +static void (* const bpf_ringbuf_discard_dynptr)(struct bpf_dynptr *ptr, __u64 flags) = (void *) 200; + +/* + * bpf_dynptr_read + * + * Read *len* bytes from *src* into *dst*, starting from *offset* + * into *src*. + * *flags* is currently unused. + * + * Returns + * 0 on success, -E2BIG if *offset* + *len* exceeds the length + * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if + * *flags* is not 0. + */ +static long (* const bpf_dynptr_read)(void *dst, __u32 len, const struct bpf_dynptr *src, __u32 offset, __u64 flags) = (void *) 201; + +/* + * bpf_dynptr_write + * + * Write *len* bytes from *src* into *dst*, starting from *offset* + * into *dst*. + * + * *flags* must be 0 except for skb-type dynptrs. + * + * For skb-type dynptrs: + * * All data slices of the dynptr are automatically + * invalidated after **bpf_dynptr_write**\ (). This is + * because writing may pull the skb and change the + * underlying packet buffer. + * + * * For *flags*, please see the flags accepted by + * **bpf_skb_store_bytes**\ (). + * + * Returns + * 0 on success, -E2BIG if *offset* + *len* exceeds the length + * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* + * is a read-only dynptr or if *flags* is not correct. For skb-type dynptrs, + * other errors correspond to errors returned by **bpf_skb_store_bytes**\ (). + */ +static long (* const bpf_dynptr_write)(const struct bpf_dynptr *dst, __u32 offset, void *src, __u32 len, __u64 flags) = (void *) 202; + +/* + * bpf_dynptr_data + * + * Get a pointer to the underlying dynptr data. + * + * *len* must be a statically known value. The returned data slice + * is invalidated whenever the dynptr is invalidated. + * + * skb and xdp type dynptrs may not use bpf_dynptr_data. They should + * instead use bpf_dynptr_slice and bpf_dynptr_slice_rdwr. + * + * Returns + * Pointer to the underlying dynptr data, NULL if the dynptr is + * read-only, if the dynptr is invalid, or if the offset and length + * is out of bounds. + */ +static void *(* const bpf_dynptr_data)(const struct bpf_dynptr *ptr, __u32 offset, __u32 len) = (void *) 203; + +/* + * bpf_tcp_raw_gen_syncookie_ipv4 + * + * Try to issue a SYN cookie for the packet with corresponding + * IPv4/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * + * Returns + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + */ +static __s64 (* const bpf_tcp_raw_gen_syncookie_ipv4)(struct iphdr *iph, struct tcphdr *th, __u32 th_len) = (void *) 204; + +/* + * bpf_tcp_raw_gen_syncookie_ipv6 + * + * Try to issue a SYN cookie for the packet with corresponding + * IPv6/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * + * Returns + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + */ +static __s64 (* const bpf_tcp_raw_gen_syncookie_ipv6)(struct ipv6hdr *iph, struct tcphdr *th, __u32 th_len) = (void *) 205; + +/* + * bpf_tcp_raw_check_syncookie_ipv4 + * + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the TCP header. + * + * Returns + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + */ +static long (* const bpf_tcp_raw_check_syncookie_ipv4)(struct iphdr *iph, struct tcphdr *th) = (void *) 206; + +/* + * bpf_tcp_raw_check_syncookie_ipv6 + * + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the TCP header. + * + * Returns + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + */ +static long (* const bpf_tcp_raw_check_syncookie_ipv6)(struct ipv6hdr *iph, struct tcphdr *th) = (void *) 207; + +/* + * bpf_ktime_get_tai_ns + * + * A nonsettable system-wide clock derived from wall-clock time but + * ignoring leap seconds. This clock does not experience + * discontinuities and backwards jumps caused by NTP inserting leap + * seconds as CLOCK_REALTIME does. + * + * See: **clock_gettime**\ (**CLOCK_TAI**) + * + * Returns + * Current *ktime*. + */ +static __u64 (* const bpf_ktime_get_tai_ns)(void) = (void *) 208; + +/* + * bpf_user_ringbuf_drain + * + * Drain samples from the specified user ring buffer, and invoke + * the provided callback for each such sample: + * + * long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx); + * + * If **callback_fn** returns 0, the helper will continue to try + * and drain the next sample, up to a maximum of + * BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1, + * the helper will skip the rest of the samples and return. Other + * return values are not used now, and will be rejected by the + * verifier. + * + * Returns + * The number of drained samples if no error was encountered while + * draining samples, or 0 if no samples were present in the ring + * buffer. If a user-space producer was epoll-waiting on this map, + * and at least one sample was drained, they will receive an event + * notification notifying them of available space in the ring + * buffer. If the BPF_RB_NO_WAKEUP flag is passed to this + * function, no wakeup notification will be sent. If the + * BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will + * be sent even if no sample was drained. + * + * On failure, the returned value is one of the following: + * + * **-EBUSY** if the ring buffer is contended, and another calling + * context was concurrently draining the ring buffer. + * + * **-EINVAL** if user-space is not properly tracking the ring + * buffer due to the producer position not being aligned to 8 + * bytes, a sample not being aligned to 8 bytes, or the producer + * position not matching the advertised length of a sample. + * + * **-E2BIG** if user-space has tried to publish a sample which is + * larger than the size of the ring buffer, or which cannot fit + * within a struct bpf_dynptr. + */ +static long (* const bpf_user_ringbuf_drain)(void *map, void *callback_fn, void *ctx, __u64 flags) = (void *) 209; + +/* + * bpf_cgrp_storage_get + * + * Get a bpf_local_storage from the *cgroup*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *cgroup* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this + * helper enforces the key must be a cgroup struct and the map must also + * be a **BPF_MAP_TYPE_CGRP_STORAGE**. + * + * In reality, the local-storage value is embedded directly inside of the + * *cgroup* object itself, rather than being located in the + * **BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is + * queried for some *map* on a *cgroup* object, the kernel will perform an + * O(n) iteration over all of the live local-storage values for that + * *cgroup* object until the local-storage value for the *map* is found. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * + * Returns + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + */ +static void *(* const bpf_cgrp_storage_get)(void *map, struct cgroup *cgroup, void *value, __u64 flags) = (void *) 210; + +/* + * bpf_cgrp_storage_delete + * + * Delete a bpf_local_storage from a *cgroup*. + * + * Returns + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. + */ +static long (* const bpf_cgrp_storage_delete)(void *map, struct cgroup *cgroup) = (void *) 211; + + diff --git a/derp/xdp/headers/bpf_helpers.h b/derp/xdp/headers/bpf_helpers.h new file mode 100644 index 000000000..cd17f6d07 --- /dev/null +++ b/derp/xdp/headers/bpf_helpers.h @@ -0,0 +1,410 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_HELPERS__ +#define __BPF_HELPERS__ + +/* + * Note that bpf programs need to include either + * vmlinux.h (auto-generated from BTF) or linux/types.h + * in advance since bpf_helper_defs.h uses such types + * as __u64. + */ +#include "bpf_helper_defs.h" + +#define __uint(name, val) int (*name)[val] +#define __type(name, val) typeof(val) *name +#define __array(name, val) typeof(val) *name[] +#define __ulong(name, val) enum { ___bpf_concat(__unique_value, __COUNTER__) = val } name + +/* + * Helper macro to place programs, maps, license in + * different sections in elf_bpf file. Section names + * are interpreted by libbpf depending on the context (BPF programs, BPF maps, + * extern variables, etc). + * To allow use of SEC() with externs (e.g., for extern .maps declarations), + * make sure __attribute__((unused)) doesn't trigger compilation warning. + */ +#if __GNUC__ && !__clang__ + +/* + * Pragma macros are broken on GCC + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55578 + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90400 + */ +#define SEC(name) __attribute__((section(name), used)) + +#else + +#define SEC(name) \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wignored-attributes\"") \ + __attribute__((section(name), used)) \ + _Pragma("GCC diagnostic pop") \ + +#endif + +/* Avoid 'linux/stddef.h' definition of '__always_inline'. */ +#undef __always_inline +#define __always_inline inline __attribute__((always_inline)) + +#ifndef __noinline +#define __noinline __attribute__((noinline)) +#endif +#ifndef __weak +#define __weak __attribute__((weak)) +#endif + +/* + * Use __hidden attribute to mark a non-static BPF subprogram effectively + * static for BPF verifier's verification algorithm purposes, allowing more + * extensive and permissive BPF verification process, taking into account + * subprogram's caller context. + */ +#define __hidden __attribute__((visibility("hidden"))) + +/* When utilizing vmlinux.h with BPF CO-RE, user BPF programs can't include + * any system-level headers (such as stddef.h, linux/version.h, etc), and + * commonly-used macros like NULL and KERNEL_VERSION aren't available through + * vmlinux.h. This just adds unnecessary hurdles and forces users to re-define + * them on their own. So as a convenience, provide such definitions here. + */ +#ifndef NULL +#define NULL ((void *)0) +#endif + +#ifndef KERNEL_VERSION +#define KERNEL_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + ((c) > 255 ? 255 : (c))) +#endif + +/* + * Helper macros to manipulate data structures + */ + +/* offsetof() definition that uses __builtin_offset() might not preserve field + * offset CO-RE relocation properly, so force-redefine offsetof() using + * old-school approach which works with CO-RE correctly + */ +#undef offsetof +#define offsetof(type, member) ((unsigned long)&((type *)0)->member) + +/* redefined container_of() to ensure we use the above offsetof() macro */ +#undef container_of +#define container_of(ptr, type, member) \ + ({ \ + void *__mptr = (void *)(ptr); \ + ((type *)(__mptr - offsetof(type, member))); \ + }) + +/* + * Compiler (optimization) barrier. + */ +#ifndef barrier +#define barrier() asm volatile("" ::: "memory") +#endif + +/* Variable-specific compiler (optimization) barrier. It's a no-op which makes + * compiler believe that there is some black box modification of a given + * variable and thus prevents compiler from making extra assumption about its + * value and potential simplifications and optimizations on this variable. + * + * E.g., compiler might often delay or even omit 32-bit to 64-bit casting of + * a variable, making some code patterns unverifiable. Putting barrier_var() + * in place will ensure that cast is performed before the barrier_var() + * invocation, because compiler has to pessimistically assume that embedded + * asm section might perform some extra operations on that variable. + * + * This is a variable-specific variant of more global barrier(). + */ +#ifndef barrier_var +#define barrier_var(var) asm volatile("" : "+r"(var)) +#endif + +/* + * Helper macro to throw a compilation error if __bpf_unreachable() gets + * built into the resulting code. This works given BPF back end does not + * implement __builtin_trap(). This is useful to assert that certain paths + * of the program code are never used and hence eliminated by the compiler. + * + * For example, consider a switch statement that covers known cases used by + * the program. __bpf_unreachable() can then reside in the default case. If + * the program gets extended such that a case is not covered in the switch + * statement, then it will throw a build error due to the default case not + * being compiled out. + */ +#ifndef __bpf_unreachable +# define __bpf_unreachable() __builtin_trap() +#endif + +/* + * Helper function to perform a tail call with a constant/immediate map slot. + */ +#if __clang_major__ >= 8 && defined(__bpf__) +static __always_inline void +bpf_tail_call_static(void *ctx, const void *map, const __u32 slot) +{ + if (!__builtin_constant_p(slot)) + __bpf_unreachable(); + + /* + * Provide a hard guarantee that LLVM won't optimize setting r2 (map + * pointer) and r3 (constant map index) from _different paths_ ending + * up at the _same_ call insn as otherwise we won't be able to use the + * jmpq/nopl retpoline-free patching by the x86-64 JIT in the kernel + * given they mismatch. See also d2e4c1e6c294 ("bpf: Constant map key + * tracking for prog array pokes") for details on verifier tracking. + * + * Note on clobber list: we need to stay in-line with BPF calling + * convention, so even if we don't end up using r0, r4, r5, we need + * to mark them as clobber so that LLVM doesn't end up using them + * before / after the call. + */ + asm volatile("r1 = %[ctx]\n\t" + "r2 = %[map]\n\t" + "r3 = %[slot]\n\t" + "call 12" + :: [ctx]"r"(ctx), [map]"r"(map), [slot]"i"(slot) + : "r0", "r1", "r2", "r3", "r4", "r5"); +} +#endif + +enum libbpf_pin_type { + LIBBPF_PIN_NONE, + /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ + LIBBPF_PIN_BY_NAME, +}; + +enum libbpf_tristate { + TRI_NO = 0, + TRI_YES = 1, + TRI_MODULE = 2, +}; + +#define __kconfig __attribute__((section(".kconfig"))) +#define __ksym __attribute__((section(".ksyms"))) +#define __kptr_untrusted __attribute__((btf_type_tag("kptr_untrusted"))) +#define __kptr __attribute__((btf_type_tag("kptr"))) +#define __percpu_kptr __attribute__((btf_type_tag("percpu_kptr"))) + +#define bpf_ksym_exists(sym) ({ \ + _Static_assert(!__builtin_constant_p(!!sym), #sym " should be marked as __weak"); \ + !!sym; \ +}) + +#define __arg_ctx __attribute__((btf_decl_tag("arg:ctx"))) +#define __arg_nonnull __attribute((btf_decl_tag("arg:nonnull"))) +#define __arg_nullable __attribute((btf_decl_tag("arg:nullable"))) +#define __arg_trusted __attribute((btf_decl_tag("arg:trusted"))) +#define __arg_arena __attribute((btf_decl_tag("arg:arena"))) + +#ifndef ___bpf_concat +#define ___bpf_concat(a, b) a ## b +#endif +#ifndef ___bpf_apply +#define ___bpf_apply(fn, n) ___bpf_concat(fn, n) +#endif +#ifndef ___bpf_nth +#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N +#endif +#ifndef ___bpf_narg +#define ___bpf_narg(...) \ + ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +#endif + +#define ___bpf_fill0(arr, p, x) do {} while (0) +#define ___bpf_fill1(arr, p, x) arr[p] = x +#define ___bpf_fill2(arr, p, x, args...) arr[p] = x; ___bpf_fill1(arr, p + 1, args) +#define ___bpf_fill3(arr, p, x, args...) arr[p] = x; ___bpf_fill2(arr, p + 1, args) +#define ___bpf_fill4(arr, p, x, args...) arr[p] = x; ___bpf_fill3(arr, p + 1, args) +#define ___bpf_fill5(arr, p, x, args...) arr[p] = x; ___bpf_fill4(arr, p + 1, args) +#define ___bpf_fill6(arr, p, x, args...) arr[p] = x; ___bpf_fill5(arr, p + 1, args) +#define ___bpf_fill7(arr, p, x, args...) arr[p] = x; ___bpf_fill6(arr, p + 1, args) +#define ___bpf_fill8(arr, p, x, args...) arr[p] = x; ___bpf_fill7(arr, p + 1, args) +#define ___bpf_fill9(arr, p, x, args...) arr[p] = x; ___bpf_fill8(arr, p + 1, args) +#define ___bpf_fill10(arr, p, x, args...) arr[p] = x; ___bpf_fill9(arr, p + 1, args) +#define ___bpf_fill11(arr, p, x, args...) arr[p] = x; ___bpf_fill10(arr, p + 1, args) +#define ___bpf_fill12(arr, p, x, args...) arr[p] = x; ___bpf_fill11(arr, p + 1, args) +#define ___bpf_fill(arr, args...) \ + ___bpf_apply(___bpf_fill, ___bpf_narg(args))(arr, 0, args) + +/* + * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values + * in a structure. + */ +#define BPF_SEQ_PRINTF(seq, fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_seq_printf(seq, ___fmt, sizeof(___fmt), \ + ___param, sizeof(___param)); \ +}) + +/* + * BPF_SNPRINTF wraps the bpf_snprintf helper with variadic arguments instead of + * an array of u64. + */ +#define BPF_SNPRINTF(out, out_size, fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_snprintf(out, out_size, ___fmt, \ + ___param, sizeof(___param)); \ +}) + +#ifdef BPF_NO_GLOBAL_DATA +#define BPF_PRINTK_FMT_MOD +#else +#define BPF_PRINTK_FMT_MOD static const +#endif + +#define __bpf_printk(fmt, ...) \ +({ \ + BPF_PRINTK_FMT_MOD char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +/* + * __bpf_vprintk wraps the bpf_trace_vprintk helper with variadic arguments + * instead of an array of u64. + */ +#define __bpf_vprintk(fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_trace_vprintk(___fmt, sizeof(___fmt), \ + ___param, sizeof(___param)); \ +}) + +/* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args + * Otherwise use __bpf_vprintk + */ +#define ___bpf_pick_printk(...) \ + ___bpf_nth(_, ##__VA_ARGS__, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ + __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ + __bpf_vprintk, __bpf_vprintk, __bpf_printk /*3*/, __bpf_printk /*2*/,\ + __bpf_printk /*1*/, __bpf_printk /*0*/) + +/* Helper macro to print out debug messages */ +#define bpf_printk(fmt, args...) ___bpf_pick_printk(args)(fmt, ##args) + +struct bpf_iter_num; + +extern int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end) __weak __ksym; +extern int *bpf_iter_num_next(struct bpf_iter_num *it) __weak __ksym; +extern void bpf_iter_num_destroy(struct bpf_iter_num *it) __weak __ksym; + +#ifndef bpf_for_each +/* bpf_for_each(iter_type, cur_elem, args...) provides generic construct for + * using BPF open-coded iterators without having to write mundane explicit + * low-level loop logic. Instead, it provides for()-like generic construct + * that can be used pretty naturally. E.g., for some hypothetical cgroup + * iterator, you'd write: + * + * struct cgroup *cg, *parent_cg = <...>; + * + * bpf_for_each(cgroup, cg, parent_cg, CG_ITER_CHILDREN) { + * bpf_printk("Child cgroup id = %d", cg->cgroup_id); + * if (cg->cgroup_id == 123) + * break; + * } + * + * I.e., it looks almost like high-level for each loop in other languages, + * supports continue/break, and is verifiable by BPF verifier. + * + * For iterating integers, the difference betwen bpf_for_each(num, i, N, M) + * and bpf_for(i, N, M) is in that bpf_for() provides additional proof to + * verifier that i is in [N, M) range, and in bpf_for_each() case i is `int + * *`, not just `int`. So for integers bpf_for() is more convenient. + * + * Note: this macro relies on C99 feature of allowing to declare variables + * inside for() loop, bound to for() loop lifetime. It also utilizes GCC + * extension: __attribute__((cleanup())), supported by both GCC and + * Clang. + */ +#define bpf_for_each(type, cur, args...) for ( \ + /* initialize and define destructor */ \ + struct bpf_iter_##type ___it __attribute__((aligned(8), /* enforce, just in case */, \ + cleanup(bpf_iter_##type##_destroy))), \ + /* ___p pointer is just to call bpf_iter_##type##_new() *once* to init ___it */ \ + *___p __attribute__((unused)) = ( \ + bpf_iter_##type##_new(&___it, ##args), \ + /* this is a workaround for Clang bug: it currently doesn't emit BTF */ \ + /* for bpf_iter_##type##_destroy() when used from cleanup() attribute */ \ + (void)bpf_iter_##type##_destroy, (void *)0); \ + /* iteration and termination check */ \ + (((cur) = bpf_iter_##type##_next(&___it))); \ +) +#endif /* bpf_for_each */ + +#ifndef bpf_for +/* bpf_for(i, start, end) implements a for()-like looping construct that sets + * provided integer variable *i* to values starting from *start* through, + * but not including, *end*. It also proves to BPF verifier that *i* belongs + * to range [start, end), so this can be used for accessing arrays without + * extra checks. + * + * Note: *start* and *end* are assumed to be expressions with no side effects + * and whose values do not change throughout bpf_for() loop execution. They do + * not have to be statically known or constant, though. + * + * Note: similarly to bpf_for_each(), it relies on C99 feature of declaring for() + * loop bound variables and cleanup attribute, supported by GCC and Clang. + */ +#define bpf_for(i, start, end) for ( \ + /* initialize and define destructor */ \ + struct bpf_iter_num ___it __attribute__((aligned(8), /* enforce, just in case */ \ + cleanup(bpf_iter_num_destroy))), \ + /* ___p pointer is necessary to call bpf_iter_num_new() *once* to init ___it */ \ + *___p __attribute__((unused)) = ( \ + bpf_iter_num_new(&___it, (start), (end)), \ + /* this is a workaround for Clang bug: it currently doesn't emit BTF */ \ + /* for bpf_iter_num_destroy() when used from cleanup() attribute */ \ + (void)bpf_iter_num_destroy, (void *)0); \ + ({ \ + /* iteration step */ \ + int *___t = bpf_iter_num_next(&___it); \ + /* termination and bounds check */ \ + (___t && ((i) = *___t, (i) >= (start) && (i) < (end))); \ + }); \ +) +#endif /* bpf_for */ + +#ifndef bpf_repeat +/* bpf_repeat(N) performs N iterations without exposing iteration number + * + * Note: similarly to bpf_for_each(), it relies on C99 feature of declaring for() + * loop bound variables and cleanup attribute, supported by GCC and Clang. + */ +#define bpf_repeat(N) for ( \ + /* initialize and define destructor */ \ + struct bpf_iter_num ___it __attribute__((aligned(8), /* enforce, just in case */ \ + cleanup(bpf_iter_num_destroy))), \ + /* ___p pointer is necessary to call bpf_iter_num_new() *once* to init ___it */ \ + *___p __attribute__((unused)) = ( \ + bpf_iter_num_new(&___it, 0, (N)), \ + /* this is a workaround for Clang bug: it currently doesn't emit BTF */ \ + /* for bpf_iter_num_destroy() when used from cleanup() attribute */ \ + (void)bpf_iter_num_destroy, (void *)0); \ + bpf_iter_num_next(&___it); \ + /* nothing here */ \ +) +#endif /* bpf_repeat */ + +#endif diff --git a/derp/xdp/headers/bpf_tracing.h b/derp/xdp/headers/bpf_tracing.h new file mode 100644 index 000000000..1c13f8e88 --- /dev/null +++ b/derp/xdp/headers/bpf_tracing.h @@ -0,0 +1,922 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_TRACING_H__ +#define __BPF_TRACING_H__ + +#include "bpf_helpers.h" + +/* Scan the ARCH passed in from ARCH env variable (see Makefile) */ +#if defined(__TARGET_ARCH_x86) + #define bpf_target_x86 + #define bpf_target_defined +#elif defined(__TARGET_ARCH_s390) + #define bpf_target_s390 + #define bpf_target_defined +#elif defined(__TARGET_ARCH_arm) + #define bpf_target_arm + #define bpf_target_defined +#elif defined(__TARGET_ARCH_arm64) + #define bpf_target_arm64 + #define bpf_target_defined +#elif defined(__TARGET_ARCH_mips) + #define bpf_target_mips + #define bpf_target_defined +#elif defined(__TARGET_ARCH_powerpc) + #define bpf_target_powerpc + #define bpf_target_defined +#elif defined(__TARGET_ARCH_sparc) + #define bpf_target_sparc + #define bpf_target_defined +#elif defined(__TARGET_ARCH_riscv) + #define bpf_target_riscv + #define bpf_target_defined +#elif defined(__TARGET_ARCH_arc) + #define bpf_target_arc + #define bpf_target_defined +#elif defined(__TARGET_ARCH_loongarch) + #define bpf_target_loongarch + #define bpf_target_defined +#else + +/* Fall back to what the compiler says */ +#if defined(__x86_64__) + #define bpf_target_x86 + #define bpf_target_defined +#elif defined(__s390__) + #define bpf_target_s390 + #define bpf_target_defined +#elif defined(__arm__) + #define bpf_target_arm + #define bpf_target_defined +#elif defined(__aarch64__) + #define bpf_target_arm64 + #define bpf_target_defined +#elif defined(__mips__) + #define bpf_target_mips + #define bpf_target_defined +#elif defined(__powerpc__) + #define bpf_target_powerpc + #define bpf_target_defined +#elif defined(__sparc__) + #define bpf_target_sparc + #define bpf_target_defined +#elif defined(__riscv) && __riscv_xlen == 64 + #define bpf_target_riscv + #define bpf_target_defined +#elif defined(__arc__) + #define bpf_target_arc + #define bpf_target_defined +#elif defined(__loongarch__) + #define bpf_target_loongarch + #define bpf_target_defined +#endif /* no compiler target */ + +#endif + +#ifndef __BPF_TARGET_MISSING +#define __BPF_TARGET_MISSING "GCC error \"Must specify a BPF target arch via __TARGET_ARCH_xxx\"" +#endif + +#if defined(bpf_target_x86) + +/* + * https://en.wikipedia.org/wiki/X86_calling_conventions#System_V_AMD64_ABI + */ + +#if defined(__KERNEL__) || defined(__VMLINUX_H__) + +#define __PT_PARM1_REG di +#define __PT_PARM2_REG si +#define __PT_PARM3_REG dx +#define __PT_PARM4_REG cx +#define __PT_PARM5_REG r8 +#define __PT_PARM6_REG r9 +/* + * Syscall uses r10 for PARM4. See arch/x86/entry/entry_64.S:entry_SYSCALL_64 + * comments in Linux sources. And refer to syscall(2) manpage. + */ +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG r10 +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + +#define __PT_RET_REG sp +#define __PT_FP_REG bp +#define __PT_RC_REG ax +#define __PT_SP_REG sp +#define __PT_IP_REG ip + +#else + +#ifdef __i386__ + +/* i386 kernel is built with -mregparm=3 */ +#define __PT_PARM1_REG eax +#define __PT_PARM2_REG edx +#define __PT_PARM3_REG ecx +/* i386 syscall ABI is very different, refer to syscall(2) manpage */ +#define __PT_PARM1_SYSCALL_REG ebx +#define __PT_PARM2_SYSCALL_REG ecx +#define __PT_PARM3_SYSCALL_REG edx +#define __PT_PARM4_SYSCALL_REG esi +#define __PT_PARM5_SYSCALL_REG edi +#define __PT_PARM6_SYSCALL_REG ebp + +#define __PT_RET_REG esp +#define __PT_FP_REG ebp +#define __PT_RC_REG eax +#define __PT_SP_REG esp +#define __PT_IP_REG eip + +#else /* __i386__ */ + +#define __PT_PARM1_REG rdi +#define __PT_PARM2_REG rsi +#define __PT_PARM3_REG rdx +#define __PT_PARM4_REG rcx +#define __PT_PARM5_REG r8 +#define __PT_PARM6_REG r9 + +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG r10 +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + +#define __PT_RET_REG rsp +#define __PT_FP_REG rbp +#define __PT_RC_REG rax +#define __PT_SP_REG rsp +#define __PT_IP_REG rip + +#endif /* __i386__ */ + +#endif /* __KERNEL__ || __VMLINUX_H__ */ + +#elif defined(bpf_target_s390) + +/* + * https://github.com/IBM/s390x-abi/releases/download/v1.6/lzsabi_s390x.pdf + */ + +struct pt_regs___s390 { + unsigned long orig_gpr2; +}; + +/* s390 provides user_pt_regs instead of struct pt_regs to userspace */ +#define __PT_REGS_CAST(x) ((const user_pt_regs *)(x)) +#define __PT_PARM1_REG gprs[2] +#define __PT_PARM2_REG gprs[3] +#define __PT_PARM3_REG gprs[4] +#define __PT_PARM4_REG gprs[5] +#define __PT_PARM5_REG gprs[6] + +#define __PT_PARM1_SYSCALL_REG orig_gpr2 +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG gprs[7] +#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) +#define PT_REGS_PARM1_CORE_SYSCALL(x) \ + BPF_CORE_READ((const struct pt_regs___s390 *)(x), __PT_PARM1_SYSCALL_REG) + +#define __PT_RET_REG gprs[14] +#define __PT_FP_REG gprs[11] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG gprs[2] +#define __PT_SP_REG gprs[15] +#define __PT_IP_REG psw.addr + +#elif defined(bpf_target_arm) + +/* + * https://github.com/ARM-software/abi-aa/blob/main/aapcs32/aapcs32.rst#machine-registers + */ + +#define __PT_PARM1_REG uregs[0] +#define __PT_PARM2_REG uregs[1] +#define __PT_PARM3_REG uregs[2] +#define __PT_PARM4_REG uregs[3] + +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG uregs[4] +#define __PT_PARM6_SYSCALL_REG uregs[5] +#define __PT_PARM7_SYSCALL_REG uregs[6] + +#define __PT_RET_REG uregs[14] +#define __PT_FP_REG uregs[11] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG uregs[0] +#define __PT_SP_REG uregs[13] +#define __PT_IP_REG uregs[12] + +#elif defined(bpf_target_arm64) + +/* + * https://github.com/ARM-software/abi-aa/blob/main/aapcs64/aapcs64.rst#machine-registers + */ + +struct pt_regs___arm64 { + unsigned long orig_x0; +}; + +/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ +#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x)) +#define __PT_PARM1_REG regs[0] +#define __PT_PARM2_REG regs[1] +#define __PT_PARM3_REG regs[2] +#define __PT_PARM4_REG regs[3] +#define __PT_PARM5_REG regs[4] +#define __PT_PARM6_REG regs[5] +#define __PT_PARM7_REG regs[6] +#define __PT_PARM8_REG regs[7] + +#define __PT_PARM1_SYSCALL_REG orig_x0 +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG +#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) +#define PT_REGS_PARM1_CORE_SYSCALL(x) \ + BPF_CORE_READ((const struct pt_regs___arm64 *)(x), __PT_PARM1_SYSCALL_REG) + +#define __PT_RET_REG regs[30] +#define __PT_FP_REG regs[29] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG regs[0] +#define __PT_SP_REG sp +#define __PT_IP_REG pc + +#elif defined(bpf_target_mips) + +/* + * N64 ABI is assumed right now. + * https://en.wikipedia.org/wiki/MIPS_architecture#Calling_conventions + */ + +#define __PT_PARM1_REG regs[4] +#define __PT_PARM2_REG regs[5] +#define __PT_PARM3_REG regs[6] +#define __PT_PARM4_REG regs[7] +#define __PT_PARM5_REG regs[8] +#define __PT_PARM6_REG regs[9] +#define __PT_PARM7_REG regs[10] +#define __PT_PARM8_REG regs[11] + +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG /* only N32/N64 */ +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG /* only N32/N64 */ + +#define __PT_RET_REG regs[31] +#define __PT_FP_REG regs[30] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG regs[2] +#define __PT_SP_REG regs[29] +#define __PT_IP_REG cp0_epc + +#elif defined(bpf_target_powerpc) + +/* + * http://refspecs.linux-foundation.org/elf/elfspec_ppc.pdf (page 3-14, + * section "Function Calling Sequence") + */ + +#define __PT_PARM1_REG gpr[3] +#define __PT_PARM2_REG gpr[4] +#define __PT_PARM3_REG gpr[5] +#define __PT_PARM4_REG gpr[6] +#define __PT_PARM5_REG gpr[7] +#define __PT_PARM6_REG gpr[8] +#define __PT_PARM7_REG gpr[9] +#define __PT_PARM8_REG gpr[10] + +/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx +#define __PT_PARM1_SYSCALL_REG orig_gpr3 +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG +#if !defined(__arch64__) +#define __PT_PARM7_SYSCALL_REG __PT_PARM7_REG /* only powerpc (not powerpc64) */ +#endif + +#define __PT_RET_REG regs[31] +#define __PT_FP_REG __unsupported__ +#define __PT_RC_REG gpr[3] +#define __PT_SP_REG sp +#define __PT_IP_REG nip + +#elif defined(bpf_target_sparc) + +/* + * https://en.wikipedia.org/wiki/Calling_convention#SPARC + */ + +#define __PT_PARM1_REG u_regs[UREG_I0] +#define __PT_PARM2_REG u_regs[UREG_I1] +#define __PT_PARM3_REG u_regs[UREG_I2] +#define __PT_PARM4_REG u_regs[UREG_I3] +#define __PT_PARM5_REG u_regs[UREG_I4] +#define __PT_PARM6_REG u_regs[UREG_I5] + +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + +#define __PT_RET_REG u_regs[UREG_I7] +#define __PT_FP_REG __unsupported__ +#define __PT_RC_REG u_regs[UREG_I0] +#define __PT_SP_REG u_regs[UREG_FP] +/* Should this also be a bpf_target check for the sparc case? */ +#if defined(__arch64__) +#define __PT_IP_REG tpc +#else +#define __PT_IP_REG pc +#endif + +#elif defined(bpf_target_riscv) + +/* + * https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#risc-v-calling-conventions + */ + +/* riscv provides struct user_regs_struct instead of struct pt_regs to userspace */ +#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) +#define __PT_PARM1_REG a0 +#define __PT_PARM2_REG a1 +#define __PT_PARM3_REG a2 +#define __PT_PARM4_REG a3 +#define __PT_PARM5_REG a4 +#define __PT_PARM6_REG a5 +#define __PT_PARM7_REG a6 +#define __PT_PARM8_REG a7 + +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + +#define __PT_RET_REG ra +#define __PT_FP_REG s0 +#define __PT_RC_REG a0 +#define __PT_SP_REG sp +#define __PT_IP_REG pc + +#elif defined(bpf_target_arc) + +/* + * Section "Function Calling Sequence" (page 24): + * https://raw.githubusercontent.com/wiki/foss-for-synopsys-dwc-arc-processors/toolchain/files/ARCv2_ABI.pdf + */ + +/* arc provides struct user_regs_struct instead of struct pt_regs to userspace */ +#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) +#define __PT_PARM1_REG scratch.r0 +#define __PT_PARM2_REG scratch.r1 +#define __PT_PARM3_REG scratch.r2 +#define __PT_PARM4_REG scratch.r3 +#define __PT_PARM5_REG scratch.r4 +#define __PT_PARM6_REG scratch.r5 +#define __PT_PARM7_REG scratch.r6 +#define __PT_PARM8_REG scratch.r7 + +/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + +#define __PT_RET_REG scratch.blink +#define __PT_FP_REG scratch.fp +#define __PT_RC_REG scratch.r0 +#define __PT_SP_REG scratch.sp +#define __PT_IP_REG scratch.ret + +#elif defined(bpf_target_loongarch) + +/* + * https://docs.kernel.org/loongarch/introduction.html + * https://loongson.github.io/LoongArch-Documentation/LoongArch-ELF-ABI-EN.html + */ + +/* loongarch provides struct user_pt_regs instead of struct pt_regs to userspace */ +#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x)) +#define __PT_PARM1_REG regs[4] +#define __PT_PARM2_REG regs[5] +#define __PT_PARM3_REG regs[6] +#define __PT_PARM4_REG regs[7] +#define __PT_PARM5_REG regs[8] +#define __PT_PARM6_REG regs[9] +#define __PT_PARM7_REG regs[10] +#define __PT_PARM8_REG regs[11] + +/* loongarch does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + +#define __PT_RET_REG regs[1] +#define __PT_FP_REG regs[22] +#define __PT_RC_REG regs[4] +#define __PT_SP_REG regs[3] +#define __PT_IP_REG csr_era + +#endif + +#if defined(bpf_target_defined) + +struct pt_regs; + +/* allow some architectures to override `struct pt_regs` */ +#ifndef __PT_REGS_CAST +#define __PT_REGS_CAST(x) (x) +#endif + +/* + * Different architectures support different number of arguments passed + * through registers. i386 supports just 3, some arches support up to 8. + */ +#ifndef __PT_PARM4_REG +#define __PT_PARM4_REG __unsupported__ +#endif +#ifndef __PT_PARM5_REG +#define __PT_PARM5_REG __unsupported__ +#endif +#ifndef __PT_PARM6_REG +#define __PT_PARM6_REG __unsupported__ +#endif +#ifndef __PT_PARM7_REG +#define __PT_PARM7_REG __unsupported__ +#endif +#ifndef __PT_PARM8_REG +#define __PT_PARM8_REG __unsupported__ +#endif +/* + * Similarly, syscall-specific conventions might differ between function call + * conventions within each architecutre. All supported architectures pass + * either 6 or 7 syscall arguments in registers. + * + * See syscall(2) manpage for succinct table with information on each arch. + */ +#ifndef __PT_PARM7_SYSCALL_REG +#define __PT_PARM7_SYSCALL_REG __unsupported__ +#endif + +#define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG) +#define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG) +#define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG) +#define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG) +#define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG) +#define PT_REGS_PARM6(x) (__PT_REGS_CAST(x)->__PT_PARM6_REG) +#define PT_REGS_PARM7(x) (__PT_REGS_CAST(x)->__PT_PARM7_REG) +#define PT_REGS_PARM8(x) (__PT_REGS_CAST(x)->__PT_PARM8_REG) +#define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG) +#define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG) +#define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG) +#define PT_REGS_SP(x) (__PT_REGS_CAST(x)->__PT_SP_REG) +#define PT_REGS_IP(x) (__PT_REGS_CAST(x)->__PT_IP_REG) + +#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_REG) +#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_REG) +#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG) +#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG) +#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG) +#define PT_REGS_PARM6_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM6_REG) +#define PT_REGS_PARM7_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM7_REG) +#define PT_REGS_PARM8_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM8_REG) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG) +#define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG) +#define PT_REGS_SP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_SP_REG) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_IP_REG) + +#if defined(bpf_target_powerpc) + +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) +#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP + +#elif defined(bpf_target_sparc) + +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) +#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP + +#else + +#define BPF_KPROBE_READ_RET_IP(ip, ctx) \ + ({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); }) +#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) \ + ({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) + +#endif + +#ifndef PT_REGS_PARM1_SYSCALL +#define PT_REGS_PARM1_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM1_SYSCALL_REG) +#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_SYSCALL_REG) +#endif +#ifndef PT_REGS_PARM2_SYSCALL +#define PT_REGS_PARM2_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM2_SYSCALL_REG) +#define PT_REGS_PARM2_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_SYSCALL_REG) +#endif +#ifndef PT_REGS_PARM3_SYSCALL +#define PT_REGS_PARM3_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM3_SYSCALL_REG) +#define PT_REGS_PARM3_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_SYSCALL_REG) +#endif +#ifndef PT_REGS_PARM4_SYSCALL +#define PT_REGS_PARM4_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM4_SYSCALL_REG) +#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_SYSCALL_REG) +#endif +#ifndef PT_REGS_PARM5_SYSCALL +#define PT_REGS_PARM5_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM5_SYSCALL_REG) +#define PT_REGS_PARM5_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_SYSCALL_REG) +#endif +#ifndef PT_REGS_PARM6_SYSCALL +#define PT_REGS_PARM6_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM6_SYSCALL_REG) +#define PT_REGS_PARM6_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM6_SYSCALL_REG) +#endif +#ifndef PT_REGS_PARM7_SYSCALL +#define PT_REGS_PARM7_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM7_SYSCALL_REG) +#define PT_REGS_PARM7_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM7_SYSCALL_REG) +#endif + +#else /* defined(bpf_target_defined) */ + +#define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM6(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM7(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM8(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_RET(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_FP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_RC(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_SP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_IP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#define PT_REGS_PARM1_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM6_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM7_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM8_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_RET_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_FP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_RC_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_SP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_IP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM6_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM7_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM6_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM7_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#endif /* defined(bpf_target_defined) */ + +/* + * When invoked from a syscall handler kprobe, returns a pointer to a + * struct pt_regs containing syscall arguments and suitable for passing to + * PT_REGS_PARMn_SYSCALL() and PT_REGS_PARMn_CORE_SYSCALL(). + */ +#ifndef PT_REGS_SYSCALL_REGS +/* By default, assume that the arch selects ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ((struct pt_regs *)PT_REGS_PARM1(ctx)) +#endif + +#ifndef ___bpf_concat +#define ___bpf_concat(a, b) a ## b +#endif +#ifndef ___bpf_apply +#define ___bpf_apply(fn, n) ___bpf_concat(fn, n) +#endif +#ifndef ___bpf_nth +#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N +#endif +#ifndef ___bpf_narg +#define ___bpf_narg(...) ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +#endif + +#define ___bpf_ctx_cast0() ctx +#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0] +#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1] +#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2] +#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3] +#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4] +#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5] +#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6] +#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7] +#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8] +#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9] +#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10] +#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11] +#define ___bpf_ctx_cast(args...) ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args) + +/* + * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and + * similar kinds of BPF programs, that accept input arguments as a single + * pointer to untyped u64 array, where each u64 can actually be a typed + * pointer or integer of different size. Instead of requring user to write + * manual casts and work with array elements by index, BPF_PROG macro + * allows user to declare a list of named and typed input arguments in the + * same syntax as for normal C function. All the casting is hidden and + * performed transparently, while user code can just assume working with + * function arguments of specified type and name. + * + * Original raw context argument is preserved as well as 'ctx' argument. + * This is useful when using BPF helpers that expect original context + * as one of the parameters (e.g., for bpf_perf_event_output()). + */ +#define BPF_PROG(name, args...) \ +name(unsigned long long *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx, ##args); \ +typeof(name(0)) name(unsigned long long *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_ctx_cast(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx, ##args) + +#ifndef ___bpf_nth2 +#define ___bpf_nth2(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13, \ + _14, _15, _16, _17, _18, _19, _20, _21, _22, _23, _24, N, ...) N +#endif +#ifndef ___bpf_narg2 +#define ___bpf_narg2(...) \ + ___bpf_nth2(_, ##__VA_ARGS__, 12, 12, 11, 11, 10, 10, 9, 9, 8, 8, 7, 7, \ + 6, 6, 5, 5, 4, 4, 3, 3, 2, 2, 1, 1, 0) +#endif + +#define ___bpf_treg_cnt(t) \ + __builtin_choose_expr(sizeof(t) == 1, 1, \ + __builtin_choose_expr(sizeof(t) == 2, 1, \ + __builtin_choose_expr(sizeof(t) == 4, 1, \ + __builtin_choose_expr(sizeof(t) == 8, 1, \ + __builtin_choose_expr(sizeof(t) == 16, 2, \ + (void)0))))) + +#define ___bpf_reg_cnt0() (0) +#define ___bpf_reg_cnt1(t, x) (___bpf_reg_cnt0() + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt2(t, x, args...) (___bpf_reg_cnt1(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt3(t, x, args...) (___bpf_reg_cnt2(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt4(t, x, args...) (___bpf_reg_cnt3(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt5(t, x, args...) (___bpf_reg_cnt4(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt6(t, x, args...) (___bpf_reg_cnt5(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt7(t, x, args...) (___bpf_reg_cnt6(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt8(t, x, args...) (___bpf_reg_cnt7(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt9(t, x, args...) (___bpf_reg_cnt8(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt10(t, x, args...) (___bpf_reg_cnt9(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt11(t, x, args...) (___bpf_reg_cnt10(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt12(t, x, args...) (___bpf_reg_cnt11(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt(args...) ___bpf_apply(___bpf_reg_cnt, ___bpf_narg2(args))(args) + +#define ___bpf_union_arg(t, x, n) \ + __builtin_choose_expr(sizeof(t) == 1, ({ union { __u8 z[1]; t x; } ___t = { .z = {ctx[n]}}; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 2, ({ union { __u16 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 4, ({ union { __u32 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 8, ({ union { __u64 z[1]; t x; } ___t = {.z = {ctx[n]} }; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 16, ({ union { __u64 z[2]; t x; } ___t = {.z = {ctx[n], ctx[n + 1]} }; ___t.x; }), \ + (void)0))))) + +#define ___bpf_ctx_arg0(n, args...) +#define ___bpf_ctx_arg1(n, t, x) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt1(t, x)) +#define ___bpf_ctx_arg2(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt2(t, x, args)) ___bpf_ctx_arg1(n, args) +#define ___bpf_ctx_arg3(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt3(t, x, args)) ___bpf_ctx_arg2(n, args) +#define ___bpf_ctx_arg4(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt4(t, x, args)) ___bpf_ctx_arg3(n, args) +#define ___bpf_ctx_arg5(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt5(t, x, args)) ___bpf_ctx_arg4(n, args) +#define ___bpf_ctx_arg6(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt6(t, x, args)) ___bpf_ctx_arg5(n, args) +#define ___bpf_ctx_arg7(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt7(t, x, args)) ___bpf_ctx_arg6(n, args) +#define ___bpf_ctx_arg8(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt8(t, x, args)) ___bpf_ctx_arg7(n, args) +#define ___bpf_ctx_arg9(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt9(t, x, args)) ___bpf_ctx_arg8(n, args) +#define ___bpf_ctx_arg10(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt10(t, x, args)) ___bpf_ctx_arg9(n, args) +#define ___bpf_ctx_arg11(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt11(t, x, args)) ___bpf_ctx_arg10(n, args) +#define ___bpf_ctx_arg12(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt12(t, x, args)) ___bpf_ctx_arg11(n, args) +#define ___bpf_ctx_arg(args...) ___bpf_apply(___bpf_ctx_arg, ___bpf_narg2(args))(___bpf_reg_cnt(args), args) + +#define ___bpf_ctx_decl0() +#define ___bpf_ctx_decl1(t, x) , t x +#define ___bpf_ctx_decl2(t, x, args...) , t x ___bpf_ctx_decl1(args) +#define ___bpf_ctx_decl3(t, x, args...) , t x ___bpf_ctx_decl2(args) +#define ___bpf_ctx_decl4(t, x, args...) , t x ___bpf_ctx_decl3(args) +#define ___bpf_ctx_decl5(t, x, args...) , t x ___bpf_ctx_decl4(args) +#define ___bpf_ctx_decl6(t, x, args...) , t x ___bpf_ctx_decl5(args) +#define ___bpf_ctx_decl7(t, x, args...) , t x ___bpf_ctx_decl6(args) +#define ___bpf_ctx_decl8(t, x, args...) , t x ___bpf_ctx_decl7(args) +#define ___bpf_ctx_decl9(t, x, args...) , t x ___bpf_ctx_decl8(args) +#define ___bpf_ctx_decl10(t, x, args...) , t x ___bpf_ctx_decl9(args) +#define ___bpf_ctx_decl11(t, x, args...) , t x ___bpf_ctx_decl10(args) +#define ___bpf_ctx_decl12(t, x, args...) , t x ___bpf_ctx_decl11(args) +#define ___bpf_ctx_decl(args...) ___bpf_apply(___bpf_ctx_decl, ___bpf_narg2(args))(args) + +/* + * BPF_PROG2 is an enhanced version of BPF_PROG in order to handle struct + * arguments. Since each struct argument might take one or two u64 values + * in the trampoline stack, argument type size is needed to place proper number + * of u64 values for each argument. Therefore, BPF_PROG2 has different + * syntax from BPF_PROG. For example, for the following BPF_PROG syntax: + * + * int BPF_PROG(test2, int a, int b) { ... } + * + * the corresponding BPF_PROG2 syntax is: + * + * int BPF_PROG2(test2, int, a, int, b) { ... } + * + * where type and the corresponding argument name are separated by comma. + * + * Use BPF_PROG2 macro if one of the arguments might be a struct/union larger + * than 8 bytes: + * + * int BPF_PROG2(test_struct_arg, struct bpf_testmod_struct_arg_1, a, int, b, + * int, c, int, d, struct bpf_testmod_struct_arg_2, e, int, ret) + * { + * // access a, b, c, d, e, and ret directly + * ... + * } + */ +#define BPF_PROG2(name, args...) \ +name(unsigned long long *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx ___bpf_ctx_decl(args)); \ +typeof(name(0)) name(unsigned long long *ctx) \ +{ \ + return ____##name(ctx ___bpf_ctx_arg(args)); \ +} \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx ___bpf_ctx_decl(args)) + +struct pt_regs; + +#define ___bpf_kprobe_args0() ctx +#define ___bpf_kprobe_args1(x) ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx) +#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx) +#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx) +#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx) +#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx) +#define ___bpf_kprobe_args6(x, args...) ___bpf_kprobe_args5(args), (void *)PT_REGS_PARM6(ctx) +#define ___bpf_kprobe_args7(x, args...) ___bpf_kprobe_args6(args), (void *)PT_REGS_PARM7(ctx) +#define ___bpf_kprobe_args8(x, args...) ___bpf_kprobe_args7(args), (void *)PT_REGS_PARM8(ctx) +#define ___bpf_kprobe_args(args...) ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) + +/* + * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for + * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific + * low-level way of getting kprobe input arguments from struct pt_regs, and + * provides a familiar typed and named function arguments syntax and + * semantics of accessing kprobe input paremeters. + * + * Original struct pt_regs* context is preserved as 'ctx' argument. This might + * be necessary when using BPF helpers like bpf_perf_event_output(). + */ +#define BPF_KPROBE(name, args...) \ +name(struct pt_regs *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_kprobe_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args) + +#define ___bpf_kretprobe_args0() ctx +#define ___bpf_kretprobe_args1(x) ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx) +#define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args) + +/* + * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional + * return value (in addition to `struct pt_regs *ctx`), but no input + * arguments, because they will be clobbered by the time probed function + * returns. + */ +#define BPF_KRETPROBE(name, args...) \ +name(struct pt_regs *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_kretprobe_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) + +/* If kernel has CONFIG_ARCH_HAS_SYSCALL_WRAPPER, read pt_regs directly */ +#define ___bpf_syscall_args0() ctx +#define ___bpf_syscall_args1(x) ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_SYSCALL(regs) +#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_SYSCALL(regs) +#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_SYSCALL(regs) +#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_SYSCALL(regs) +#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_SYSCALL(regs) +#define ___bpf_syscall_args6(x, args...) ___bpf_syscall_args5(args), (void *)PT_REGS_PARM6_SYSCALL(regs) +#define ___bpf_syscall_args7(x, args...) ___bpf_syscall_args6(args), (void *)PT_REGS_PARM7_SYSCALL(regs) +#define ___bpf_syscall_args(args...) ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args) + +/* If kernel doesn't have CONFIG_ARCH_HAS_SYSCALL_WRAPPER, we have to BPF_CORE_READ from pt_regs */ +#define ___bpf_syswrap_args0() ctx +#define ___bpf_syswrap_args1(x) ___bpf_syswrap_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args2(x, args...) ___bpf_syswrap_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args6(x, args...) ___bpf_syswrap_args5(args), (void *)PT_REGS_PARM6_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args7(x, args...) ___bpf_syswrap_args6(args), (void *)PT_REGS_PARM7_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args(args...) ___bpf_apply(___bpf_syswrap_args, ___bpf_narg(args))(args) + +/* + * BPF_KSYSCALL is a variant of BPF_KPROBE, which is intended for + * tracing syscall functions, like __x64_sys_close. It hides the underlying + * platform-specific low-level way of getting syscall input arguments from + * struct pt_regs, and provides a familiar typed and named function arguments + * syntax and semantics of accessing syscall input parameters. + * + * Original struct pt_regs * context is preserved as 'ctx' argument. This might + * be necessary when using BPF helpers like bpf_perf_event_output(). + * + * At the moment BPF_KSYSCALL does not transparently handle all the calling + * convention quirks for the following syscalls: + * + * - mmap(): __ARCH_WANT_SYS_OLD_MMAP. + * - clone(): CONFIG_CLONE_BACKWARDS, CONFIG_CLONE_BACKWARDS2 and + * CONFIG_CLONE_BACKWARDS3. + * - socket-related syscalls: __ARCH_WANT_SYS_SOCKETCALL. + * - compat syscalls. + * + * This may or may not change in the future. User needs to take extra measures + * to handle such quirks explicitly, if necessary. + * + * This macro relies on BPF CO-RE support and virtual __kconfig externs. + */ +#define BPF_KSYSCALL(name, args...) \ +name(struct pt_regs *ctx); \ +extern _Bool LINUX_HAS_SYSCALL_WRAPPER __kconfig; \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + struct pt_regs *regs = LINUX_HAS_SYSCALL_WRAPPER \ + ? (struct pt_regs *)PT_REGS_PARM1(ctx) \ + : ctx; \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + if (LINUX_HAS_SYSCALL_WRAPPER) \ + return ____##name(___bpf_syswrap_args(args)); \ + else \ + return ____##name(___bpf_syscall_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args) + +#define BPF_KPROBE_SYSCALL BPF_KSYSCALL + +/* BPF_UPROBE and BPF_URETPROBE are identical to BPF_KPROBE and BPF_KRETPROBE, + * but are named way less confusingly for SEC("uprobe") and SEC("uretprobe") + * use cases. + */ +#define BPF_UPROBE(name, args...) BPF_KPROBE(name, ##args) +#define BPF_URETPROBE(name, args...) BPF_KRETPROBE(name, ##args) + +#endif diff --git a/derp/xdp/headers/update.go b/derp/xdp/headers/update.go new file mode 100644 index 000000000..171c9ea2e --- /dev/null +++ b/derp/xdp/headers/update.go @@ -0,0 +1,99 @@ +// Copyright (c) Tailscale Inc & AUTHORS +// SPDX-License-Identifier: BSD-3-Clause + +package main + +import ( + "archive/tar" + "compress/gzip" + "flag" + "fmt" + "io" + "log" + "net/http" + "os" + "path/filepath" + "strings" +) + +const ( + libbpfVersion = "1.4.3" + prefix = "libbpf-" + libbpfVersion +) + +var ( + filesToExtract = map[string]struct{}{ + prefix + "/LICENSE.BSD-2-Clause": {}, + prefix + "/src/bpf_endian.h": {}, + prefix + "/src/bpf_helper_defs.h": {}, + prefix + "/src/bpf_helpers.h": {}, + prefix + "/src/bpf_tracing.h": {}, + } +) + +var ( + flagDest = flag.String("dest", ".", "destination directory") +) + +// TODO(jwhited): go generate strategy for derp/xdp +func main() { + flag.Parse() + + f, err := os.CreateTemp("", "libbpf") + if err != nil { + log.Panic(err) + } + defer os.Remove(f.Name()) + + resp, err := http.Get(fmt.Sprintf("https://github.com/libbpf/libbpf/archive/refs/tags/v%s.tar.gz", libbpfVersion)) + if err != nil { + log.Panic(err) + } + defer resp.Body.Close() + + _, err = io.Copy(f, resp.Body) + if err != nil { + log.Panic(err) + } + + _, err = f.Seek(0, 0) + if err != nil { + log.Panic(err) + } + g, err := gzip.NewReader(f) + if err != nil { + log.Panic(err) + } + defer g.Close() + t := tar.NewReader(g) + + seen := make(map[string]bool, len(filesToExtract)) + for { + h, err := t.Next() + if err != nil { + log.Panic(err) + } + if strings.Contains(h.Name, "..") { + continue + } + _, ok := filesToExtract[h.Name] + if ok { + if seen[h.Name] { + log.Panicf("saw %s more than once in archive", h.Name) + } + seen[h.Name] = true + p := filepath.Join(*flagDest, filepath.Base(h.Name)) + e, err := os.Create(p) + if err != nil { + log.Panic(err) + } + _, err = io.Copy(e, t) + if err != nil { + log.Panic(err) + } + if len(seen) == len(filesToExtract) { + break + } + } + } +} diff --git a/derp/xdp/xdp.c b/derp/xdp/xdp.c new file mode 100644 index 000000000..d18a4190b --- /dev/null +++ b/derp/xdp/xdp.c @@ -0,0 +1,585 @@ +//go:build ignore + +#include +#include +#include +#include +#include +#include +#include +#include + +struct config { + // TODO(jwhited): if we add more fields consider endianness consistency in + // the context of the data. cilium/ebpf uses native endian encoding for map + // encoding even if we use big endian types here, e.g. __be16. + __u16 dst_port; +}; +struct config *unused_config __attribute__((unused)); // required by bpf2go -type + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct config)); + __uint(max_entries, 1); +} config_map SEC(".maps"); + +struct counters_key { + __u8 unused; + __u8 af; + __u8 pba; + __u8 prog_end; +}; +struct counters_key *unused_counters_key __attribute__((unused)); // required by bpf2go -type + +enum counter_key_af { + COUNTER_KEY_AF_UNKNOWN, + COUNTER_KEY_AF_IPV4, + COUNTER_KEY_AF_IPV6, + COUNTER_KEY_AF_LEN +}; +enum counter_key_af *unused_counter_key_af __attribute__((unused)); // required by bpf2go -type + +enum counter_key_packets_bytes_action { + COUNTER_KEY_PACKETS_PASS_TOTAL, + COUNTER_KEY_BYTES_PASS_TOTAL, + COUNTER_KEY_PACKETS_ABORTED_TOTAL, + COUNTER_KEY_BYTES_ABORTED_TOTAL, + COUNTER_KEY_PACKETS_TX_TOTAL, + COUNTER_KEY_BYTES_TX_TOTAL, + COUNTER_KEY_PACKETS_DROP_TOTAL, + COUNTER_KEY_BYTES_DROP_TOTAL, + COUNTER_KEY_PACKETS_BYTES_ACTION_LEN +}; +enum counter_key_packets_bytes_action *unused_counter_key_packets_bytes_action __attribute__((unused)); // required by bpf2go -type + +enum counter_key_prog_end { + COUNTER_KEY_END_UNSPECIFIED, + COUNTER_KEY_END_UNEXPECTED_FIRST_STUN_ATTR, + COUNTER_KEY_END_INVALID_UDP_CSUM, + COUNTER_KEY_END_INVALID_IP_CSUM, + COUNTER_KEY_END_NOT_STUN_PORT, + COUNTER_KEY_END_INVALID_SW_ATTR_VAL, + COUNTER_KEY_END_LEN +}; +enum counter_key_prog_end *unused_counter_key_prog_end __attribute__((unused)); // required by bpf2go -type + +#define COUNTERS_MAP_MAX_ENTRIES ((COUNTER_KEY_AF_LEN - 1) << 16) | \ + ((COUNTER_KEY_PACKETS_BYTES_ACTION_LEN - 1) << 8) | \ + (COUNTER_KEY_END_LEN - 1) + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(key_size, sizeof(struct counters_key)); + __uint(value_size, sizeof(__u64)); + __uint(max_entries, COUNTERS_MAP_MAX_ENTRIES); +} counters_map SEC(".maps"); + +struct stunreq { + __be16 type; + __be16 length; + __be32 magic; + __be32 txid[3]; + // attributes follow +}; + +struct stunattr { + __be16 num; + __be16 length; +}; + +struct stunxor { + __u8 unused; + __u8 family; + __be16 port; + __be32 addr; +}; + +struct stunxor6 { + __u8 unused; + __u8 family; + __be16 port; + __be32 addr[4]; +}; + +#define STUN_BINDING_REQUEST 1 + +#define STUN_MAGIC 0x2112a442 + +#define STUN_ATTR_SW 0x8022 + +#define STUN_ATTR_XOR_MAPPED_ADDR 0x0020 + +#define STUN_BINDING_RESPONSE 0x0101 + +#define STUN_MAGIC_FOR_PORT_XOR 0x2112 + +#define MAX_UDP_LEN_IPV4 1480 + +#define MAX_UDP_LEN_IPV6 1460 + +#define IP_MF 0x2000 +#define IP_OFFSET 0x1fff + +static __always_inline __u16 csum_fold_flip(__u32 csum) { + __u32 sum; + sum = (csum >> 16) + (csum & 0xffff); // maximum value 0x1fffe + sum += (sum >> 16); // maximum value 0xffff + return ~sum; +} + +// csum_const_size is an alternative to bpf_csum_diff. It's a verifier +// workaround for when we are forced to use a constant max_size + bounds +// checking. The alternative being passing a dynamic length to bpf_csum_diff +// {from,to}_size arguments, which the verifier can't follow. For further info +// see: https://github.com/iovisor/bcc/issues/2463#issuecomment-512503958 +static __always_inline __u16 csum_const_size(__u32 seed, void* from, void* data_end, int max_size) { + __u16 *buf = from; + for (int i = 0; i < max_size; i += 2) { + if ((void *)(buf + 1) > data_end) { + break; + } + seed += *buf; + buf++; + } + if ((void *)buf + 1 <= data_end) { + seed += *(__u8 *)buf; + } + return csum_fold_flip(seed); +} + +static __always_inline __u32 pseudo_sum_ipv6(struct ipv6hdr* ip6, __u16 udp_len) { + __u32 pseudo = 0; // TODO(jwhited): __u64 for intermediate checksum values to reduce number of ops + for (int i = 0; i < 8; i ++) { + pseudo += ip6->saddr.in6_u.u6_addr16[i]; + pseudo += ip6->daddr.in6_u.u6_addr16[i]; + } + pseudo += bpf_htons(ip6->nexthdr); + pseudo += udp_len; + return pseudo; +} + +static __always_inline __u32 pseudo_sum_ipv4(struct iphdr* ip, __u16 udp_len) { + __u32 pseudo = (__u16)ip->saddr; + pseudo += (__u16)(ip->saddr >> 16); + pseudo += (__u16)ip->daddr; + pseudo += (__u16)(ip->daddr >> 16); + pseudo += bpf_htons(ip->protocol); + pseudo += udp_len; + return pseudo; +} + +struct packet_context { + enum counter_key_af af; + enum counter_key_prog_end prog_end; +}; + +static __always_inline int inc_counter(struct counters_key key, __u64 val) { + __u64 *counter = bpf_map_lookup_elem(&counters_map, &key); + if (!counter) { + return bpf_map_update_elem(&counters_map, &key, &val, BPF_ANY); + } + *counter += val; + return bpf_map_update_elem(&counters_map, &key, counter, BPF_ANY); +} + +static __always_inline int handle_counters(struct xdp_md *ctx, int action, struct packet_context *pctx) { + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + + __u64 bytes = data_end - data; + enum counter_key_packets_bytes_action packets_pba = COUNTER_KEY_PACKETS_PASS_TOTAL; + enum counter_key_packets_bytes_action bytes_pba = COUNTER_KEY_BYTES_PASS_TOTAL; + + switch (action) { + case XDP_ABORTED: + packets_pba = COUNTER_KEY_PACKETS_ABORTED_TOTAL; + bytes_pba = COUNTER_KEY_BYTES_ABORTED_TOTAL; + break; + case XDP_PASS: + packets_pba = COUNTER_KEY_PACKETS_PASS_TOTAL; + bytes_pba = COUNTER_KEY_BYTES_PASS_TOTAL; + break; + case XDP_TX: + packets_pba = COUNTER_KEY_PACKETS_TX_TOTAL; + bytes_pba = COUNTER_KEY_BYTES_TX_TOTAL; + break; + case XDP_DROP: + packets_pba = COUNTER_KEY_PACKETS_DROP_TOTAL; + bytes_pba = COUNTER_KEY_BYTES_DROP_TOTAL; + break; + } + + struct counters_key packets_key = { + .af = pctx->af, + .pba = packets_pba, + .prog_end = pctx->prog_end, + }; + + struct counters_key bytes_key = { + .af = pctx->af, + .pba = bytes_pba, + .prog_end = pctx->prog_end, + }; + + inc_counter(packets_key, 1); + inc_counter(bytes_key, bytes); + + return 0; +} + +#define is_ipv6 (pctx->af == COUNTER_KEY_AF_IPV6) +static __always_inline int handle_packet(struct xdp_md *ctx, struct packet_context *pctx) { + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + pctx->af = COUNTER_KEY_AF_UNKNOWN; + pctx->prog_end = COUNTER_KEY_END_UNSPECIFIED; + + struct ethhdr *eth = data; + if ((void *)(eth + 1) > data_end) { + return XDP_PASS; + } + + struct iphdr *ip; + struct ipv6hdr *ip6; + struct udphdr *udp; + + int validate_udp_csum; + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + pctx->af = COUNTER_KEY_AF_IPV4; + ip = (void *)(eth + 1); + if ((void *)(ip + 1) > data_end) { + return XDP_PASS; + } + + if (ip->ihl != 5 || + ip->version != 4 || + ip->protocol != IPPROTO_UDP || + (ip->frag_off & bpf_htons(IP_MF | IP_OFFSET)) != 0) { + return XDP_PASS; + } + + // validate ipv4 header checksum + __u32 cs_unfolded = bpf_csum_diff(0, 0, (void *)ip, sizeof(*ip), 0); + __u16 cs = csum_fold_flip(cs_unfolded); + if (cs != 0) { + pctx->prog_end = COUNTER_KEY_END_INVALID_IP_CSUM; + return XDP_PASS; + } + + if (bpf_ntohs(ip->tot_len) != data_end - (void *)ip) { + return XDP_PASS; + } + + udp = (void *)(ip + 1); + if ((void *)(udp + 1) > data_end) { + return XDP_PASS; + } + + if (udp->check != 0) { + // https://datatracker.ietf.org/doc/html/rfc768#page-3 + // If the computed checksum is zero, it is transmitted as all + // ones (the equivalent in one's complement arithmetic). An all + // zero transmitted checksum value means that the transmitter + // generated no checksum (for debugging or for higher level + // protocols that don't care). + validate_udp_csum = 1; + } + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + pctx->af = COUNTER_KEY_AF_IPV6; + ip6 = (void *)(eth + 1); + if ((void *)(ip6 + 1) > data_end) { + return XDP_PASS; + } + + if (ip6->version != 6 || ip6->nexthdr != IPPROTO_UDP) { + return XDP_PASS; + } + + udp = (void *)(ip6 + 1); + if ((void *)(udp + 1) > data_end) { + return XDP_PASS; + } + + if (bpf_ntohs(ip6->payload_len) != data_end - (void *)udp) { + return XDP_PASS; + } + + // https://datatracker.ietf.org/doc/html/rfc8200#page-28 + // Unlike IPv4, the default behavior when UDP packets are + // originated by an IPv6 node is that the UDP checksum is not + // optional. That is, whenever originating a UDP packet, an IPv6 + // node must compute a UDP checksum over the packet and the + // pseudo-header, and, if that computation yields a result of + // zero, it must be changed to hex FFFF for placement in the UDP + // header. IPv6 receivers must discard UDP packets containing a + // zero checksum and should log the error. + validate_udp_csum = 1; + } else { + return XDP_PASS; + } + + __u32 config_key = 0; + struct config *c = bpf_map_lookup_elem(&config_map, &config_key); + if (!c) { + return XDP_PASS; + } + + if (bpf_ntohs(udp->len) != data_end - (void *)udp) { + return XDP_PASS; + } + + if (bpf_ntohs(udp->dest) != c->dst_port) { + pctx->prog_end = COUNTER_KEY_END_NOT_STUN_PORT; + return XDP_PASS; + } + + if (validate_udp_csum) { + __u16 cs; + __u32 pseudo_sum; + if (is_ipv6) { + pseudo_sum = pseudo_sum_ipv6(ip6, udp->len); + cs = csum_const_size(pseudo_sum, udp, data_end, MAX_UDP_LEN_IPV6); + } else { + pseudo_sum = pseudo_sum_ipv4(ip, udp->len); + cs = csum_const_size(pseudo_sum, udp, data_end, MAX_UDP_LEN_IPV4); + } + if (cs != 0) { + pctx->prog_end = COUNTER_KEY_END_INVALID_UDP_CSUM; + return XDP_PASS; + } + } + + struct stunreq *req = (void *)(udp + 1); + if ((void *)(req + 1) > data_end) { + return XDP_PASS; + } + + if (req->type != bpf_htons(STUN_BINDING_REQUEST)) { + return XDP_PASS; + } + if (bpf_ntohl(req->magic) != STUN_MAGIC) { + return XDP_PASS; + } + + void *attrs = (void *)(req + 1); + __u16 attrs_len = ((char *)data_end) - ((char *)attrs); + if (bpf_ntohs(req->length) != attrs_len) { + return XDP_PASS; + } + + struct stunattr *sa = attrs; + if ((void *)(sa + 1) > data_end) { + return XDP_PASS; + } + + // Assume the order and contents of attributes. We *could* loop through + // them, but parsing their lengths and performing arithmetic against the + // packet pointer is more pain than it's worth. Bounds checks are invisible + // to the verifier in certain circumstances where things move from registers + // to the stack and/or compilation optimizations remove them entirely. There + // have only ever been two attributes included by the client, and we are + // only interested in one of them, anyway. Verify the software attribute, + // but ignore the fingerprint attribute as it's only useful where STUN is + // multiplexed with other traffic on the same port/socket, which is not the + // case here. + void *attr_data = (void *)(sa + 1); + if (bpf_ntohs(sa->length) != 8 || bpf_ntohs(sa->num) != STUN_ATTR_SW) { + pctx->prog_end = COUNTER_KEY_END_UNEXPECTED_FIRST_STUN_ATTR; + return XDP_PASS; + } + if (attr_data + 8 > data_end) { + return XDP_PASS; + } + char want_sw[] = {0x74, 0x61, 0x69, 0x6c, 0x6e, 0x6f, 0x64, 0x65}; // tailnode + char *got_sw = attr_data; + for (int j = 0; j < 8; j++) { + if (got_sw[j] != want_sw[j]) { + pctx->prog_end = COUNTER_KEY_END_INVALID_SW_ATTR_VAL; + return XDP_PASS; + } + } + + // Begin transforming packet into a STUN_BINDING_RESPONSE. From here + // onwards we return XDP_ABORTED instead of XDP_PASS when transformations or + // bounds checks fail as it would be nonsensical to pass a mangled packet + // through to the kernel, and we may be interested in debugging via + // tracepoint. + + // Set success response and new length. Magic cookie and txid remain the + // same. + req->type = bpf_htons(STUN_BINDING_RESPONSE); + if (is_ipv6) { + req->length = bpf_htons(sizeof(struct stunattr) + sizeof(struct stunxor6)); + } else { + req->length = bpf_htons(sizeof(struct stunattr) + sizeof(struct stunxor)); + } + + // Set attr type. Length remains unchanged, but set it again for future + // safety reasons. + sa->num = bpf_htons(STUN_ATTR_XOR_MAPPED_ADDR); + if (is_ipv6) { + sa->length = bpf_htons(sizeof(struct stunxor6)); + } else { + sa->length = bpf_htons(sizeof(struct stunxor)); + } + + struct stunxor *xor; + struct stunxor6 *xor6; + + // Adjust tail and reset header pointers. + int adjust_tail_by; + if (is_ipv6) { + xor6 = attr_data; + adjust_tail_by = (void *)(xor6 + 1) - data_end; + } else { + xor = attr_data; + adjust_tail_by = (void *)(xor + 1) - data_end; + } + if (bpf_xdp_adjust_tail(ctx, adjust_tail_by)) { + return XDP_ABORTED; + } + data_end = (void *)(long)ctx->data_end; + data = (void *)(long)ctx->data; + eth = data; + if ((void *)(eth + 1) > data_end) { + return XDP_ABORTED; + } + if (is_ipv6) { + ip6 = (void *)(eth + 1); + if ((void *)(ip6 + 1) > data_end) { + return XDP_ABORTED; + } + udp = (void *)(ip6 + 1); + if ((void *)(udp + 1) > data_end) { + return XDP_ABORTED; + } + } else { + ip = (void *)(eth + 1); + if ((void *)(ip + 1) > data_end) { + return XDP_ABORTED; + } + udp = (void *)(ip + 1); + if ((void *)(udp + 1) > data_end) { + return XDP_ABORTED; + } + } + req = (void *)(udp + 1); + if ((void *)(req + 1) > data_end) { + return XDP_ABORTED; + } + sa = (void *)(req + 1); + if ((void *)(sa + 1) > data_end) { + return XDP_ABORTED; + } + + // Set attr data. + if (is_ipv6) { + xor6 = (void *)(sa + 1); + if ((void *)(xor6 + 1) > data_end) { + return XDP_ABORTED; + } + xor6->unused = 0x00; // unused byte + xor6->family = 0x02; + xor6->port = udp->source ^ bpf_htons(STUN_MAGIC_FOR_PORT_XOR); + xor6->addr[0] = ip6->saddr.in6_u.u6_addr32[0] ^ bpf_htonl(STUN_MAGIC); + for (int i = 1; i < 4; i++) { + // All three are __be32, no endianness flips. + xor6->addr[i] = ip6->saddr.in6_u.u6_addr32[i] ^ req->txid[i-1]; + } + } else { + xor = (void *)(sa + 1); + if ((void *)(xor + 1) > data_end) { + return XDP_ABORTED; + } + xor->unused = 0x00; // unused byte + xor->family = 0x01; + xor->port = udp->source ^ bpf_htons(STUN_MAGIC_FOR_PORT_XOR); + xor->addr = ip->saddr ^ bpf_htonl(STUN_MAGIC); + } + + // Flip ethernet header source and destination address. + __u8 eth_tmp[ETH_ALEN]; + __builtin_memcpy(eth_tmp, eth->h_source, ETH_ALEN); + __builtin_memcpy(eth->h_source, eth->h_dest, ETH_ALEN); + __builtin_memcpy(eth->h_dest, eth_tmp, ETH_ALEN); + + // Flip ip header source and destination address. + if (is_ipv6) { + struct in6_addr ip_tmp = ip6->saddr; + ip6->saddr = ip6->daddr; + ip6->daddr = ip_tmp; + } else { + __be32 ip_tmp = ip->saddr; + ip->saddr = ip->daddr; + ip->daddr = ip_tmp; + } + + // Flip udp header source and destination ports; + __be16 port_tmp = udp->source; + udp->source = udp->dest; + udp->dest = port_tmp; + + // Update total length, TTL, and checksum. + __u32 cs = 0; + if (is_ipv6) { + if ((void *)(ip6 +1) > data_end) { + return XDP_ABORTED; + } + __u16 payload_len = data_end - (void *)(ip6 + 1); + ip6->payload_len = bpf_htons(payload_len); + ip6->hop_limit = IPDEFTTL; + } else { + __u16 tot_len = data_end - (void *)ip; + ip->tot_len = bpf_htons(tot_len); + ip->ttl = IPDEFTTL; + ip->check = 0; + cs = bpf_csum_diff(0, 0, (void *)ip, sizeof(*ip), cs); + ip->check = csum_fold_flip(cs); + } + + // Avoid dynamic length math against the packet pointer, which is just a big + // verifier headache. Instead sizeof() all the things. + int to_csum_len = sizeof(*udp) + sizeof(*req) + sizeof(*sa); + // Update udp header length and checksum. + if (is_ipv6) { + to_csum_len += sizeof(*xor6); + udp = (void *)(ip6 + 1); + if ((void *)(udp +1) > data_end) { + return XDP_ABORTED; + } + __u16 udp_len = data_end - (void *)udp; + udp->len = bpf_htons(udp_len); + udp->check = 0; + cs = pseudo_sum_ipv6(ip6, udp->len); + } else { + to_csum_len += sizeof(*xor); + udp = (void *)(ip + 1); + if ((void *)(udp +1) > data_end) { + return XDP_ABORTED; + } + __u16 udp_len = data_end - (void *)udp; + udp->len = bpf_htons(udp_len); + udp->check = 0; + cs = pseudo_sum_ipv4(ip, udp->len); + } + if ((void *)udp + to_csum_len > data_end) { + return XDP_ABORTED; + } + cs = bpf_csum_diff(0, 0, (void*)udp, to_csum_len, cs); + udp->check = csum_fold_flip(cs); + return XDP_TX; +} +#undef is_ipv6 + +SEC("xdp") +int xdp_prog_func(struct xdp_md *ctx) { + struct packet_context pctx = { + .af = COUNTER_KEY_AF_UNKNOWN, + .prog_end = COUNTER_KEY_END_UNSPECIFIED, + }; + int action = XDP_PASS; + action = handle_packet(ctx, &pctx); + handle_counters(ctx, action, &pctx); + return action; +} diff --git a/derp/xdp/xdp.go b/derp/xdp/xdp.go new file mode 100644 index 000000000..3c1fa7329 --- /dev/null +++ b/derp/xdp/xdp.go @@ -0,0 +1,45 @@ +// Copyright (c) Tailscale Inc & AUTHORS +// SPDX-License-Identifier: BSD-3-Clause + +package xdp + +// XDPAttachFlags represents how XDP program will be attached to interface. This +// is a mirror of cilium/ebpf/link.AttachFlags, without pulling it in for +// non-Linux. +type XDPAttachFlags uint32 + +const ( + // XDPDriverFallbackGenericMode attempts XDPDriverMode, and falls back to + // XDPGenericMode if the driver does not support XDP. + XDPDriverFallbackGenericMode = 0 +) + +const ( + // XDPGenericMode (SKB) links XDP BPF program for drivers which do + // not yet support native XDP. + XDPGenericMode XDPAttachFlags = 1 << (iota + 1) + // XDPDriverMode links XDP BPF program into the driver’s receive path. + XDPDriverMode + // XDPOffloadMode offloads the entire XDP BPF program into hardware. + XDPOffloadMode +) + +// STUNServerConfig represents the configuration of a STUNServer. +type STUNServerConfig struct { + DeviceName string + DstPort int + AttachFlags XDPAttachFlags + // Return XDP verifier errors in their entirety. This is a multiline error + // that can be very long. Full verifier errors are primarily useful during + // development, but should be mostly unexpected in a production environment. + FullVerifierErr bool +} + +type STUNServerOption interface { + apply(*stunServerOptions) +} + +type stunServerOptions struct { + //lint:ignore U1000 used in xdp_linux_test.go + noAttach bool +} diff --git a/derp/xdp/xdp_default.go b/derp/xdp/xdp_default.go new file mode 100644 index 000000000..35fd659ca --- /dev/null +++ b/derp/xdp/xdp_default.go @@ -0,0 +1,28 @@ +// Copyright (c) Tailscale Inc & AUTHORS +// SPDX-License-Identifier: BSD-3-Clause + +//go:build !linux + +package xdp + +import ( + "errors" + + "github.com/prometheus/client_golang/prometheus" +) + +// STUNServer is unimplemented on these platforms, see xdp_linux.go. +type STUNServer struct { +} + +func NewSTUNServer(config *STUNServerConfig, opts ...STUNServerOption) (*STUNServer, error) { + return nil, errors.New("unimplemented on this GOOS") +} + +func (s *STUNServer) Close() error { + return errors.New("unimplemented on this GOOS") +} + +func (s *STUNServer) Describe(descCh chan<- *prometheus.Desc) {} + +func (s *STUNServer) Collect(metricCh chan<- prometheus.Metric) {} diff --git a/derp/xdp/xdp_linux.go b/derp/xdp/xdp_linux.go new file mode 100644 index 000000000..f2d47a372 --- /dev/null +++ b/derp/xdp/xdp_linux.go @@ -0,0 +1,282 @@ +// Copyright (c) Tailscale Inc & AUTHORS +// SPDX-License-Identifier: BSD-3-Clause + +package xdp + +import ( + "errors" + "fmt" + "log" + "math" + "net" + "sync" + + "github.com/cilium/ebpf" + "github.com/cilium/ebpf/link" + "github.com/prometheus/client_golang/prometheus" +) + +//go:generate go run github.com/cilium/ebpf/cmd/bpf2go -type config -type counters_key -type counter_key_af -type counter_key_packets_bytes_action -type counter_key_prog_end bpf xdp.c -- -I headers + +// STUNServer manages loading and unloading of an eBPF XDP program that serves +// the STUN protocol. It exports statistics for the XDP program via its +// implementation of the prometheus.Collector interface. +type STUNServer struct { + mu sync.Mutex + objs *bpfObjects + metrics *stunServerMetrics +} + +//lint:ignore U1000 used in xdp_linux_test.go, which has a build tag +type noAttachOption struct{} + +//lint:ignore u1000 Used in xdp_linux_test.go, which has a build tag +func (n noAttachOption) apply(opts *stunServerOptions) { + opts.noAttach = true +} + +func (s *STUNServerConfig) validate() error { + if len(s.DeviceName) < 1 { + return errors.New("DeviceName is unspecified") + } + if s.DstPort < 0 || s.DstPort > math.MaxUint16 { + return errors.New("DstPort is outside of uint16 bounds") + } + return nil +} + +// NewSTUNServer returns an instance of a STUNServer that has attached the STUN +// XDP program to the netdev and destination port specified by config. +func NewSTUNServer(config *STUNServerConfig, opts ...STUNServerOption) (*STUNServer, error) { + o := &stunServerOptions{} + for _, opt := range opts { + opt.apply(o) + } + err := config.validate() + if err != nil { + return nil, fmt.Errorf("invalid config: %v", err) + } + objs := new(bpfObjects) + err = loadBpfObjects(objs, nil) + if err != nil { + var ve *ebpf.VerifierError + if config.FullVerifierErr && errors.As(err, &ve) { + err = fmt.Errorf("verifier error: %+v", ve) + } + return nil, fmt.Errorf("error loading XDP program: %w", err) + } + server := &STUNServer{ + objs: objs, + metrics: newSTUNServerMetrics(), + } + var key uint32 + xdpConfig := bpfConfig{ + DstPort: uint16(config.DstPort), + } + err = objs.ConfigMap.Put(key, &xdpConfig) + if err != nil { + return nil, fmt.Errorf("error loading config in eBPF map: %w", err) + } + if o.noAttach { + return server, nil + } + iface, err := net.InterfaceByName(config.DeviceName) + if err != nil { + return nil, fmt.Errorf("error finding device: %w", err) + } + _, err = link.AttachXDP(link.XDPOptions{ + Program: objs.XdpProgFunc, + Interface: iface.Index, + Flags: link.XDPAttachFlags(config.AttachFlags), + }) + if err != nil { + return nil, fmt.Errorf("error attaching XDP program to dev: %w", err) + } + return server, nil +} + +// Close unloads the XDP program and associated maps. +func (s *STUNServer) Close() error { + s.mu.Lock() + defer s.mu.Unlock() + return s.objs.Close() +} + +type stunServerMetrics struct { + last map[bpfCountersKey]uint64 + registry *prometheus.Registry + packets *prometheus.CounterVec + bytes *prometheus.CounterVec +} + +func newSTUNServerMetrics() *stunServerMetrics { + last := make(map[bpfCountersKey]uint64) + registry := prometheus.NewRegistry() + packets := prometheus.NewCounterVec(prometheus.CounterOpts{ + Namespace: "xdp", + Subsystem: "stun_server", + Name: "packets_total", + }, []string{addressFamilyKey, xdpOutcomeKey, progEndKey}) + bytes := prometheus.NewCounterVec(prometheus.CounterOpts{ + Namespace: "xdp", + Subsystem: "stun_server", + Name: "bytes_total", + }, []string{addressFamilyKey, xdpOutcomeKey, progEndKey}) + registry.MustRegister(packets, bytes) + return &stunServerMetrics{ + last: last, + registry: registry, + packets: packets, + bytes: bytes, + } +} + +const ( + xdpOutcomeKey = "xdp_outcome" + progEndKey = "prog_end" +) + +const ( + xdpOutcomePass = "pass" + xdpOutcomeAborted = "aborted" + xdpOutcomeDrop = "drop" + xdpOutcomeTX = "tx" +) + +func sum(vals []uint64) uint64 { + var s uint64 + for _, v := range vals { + s += v + } + return s +} + +const ( + addressFamilyKey = "address_family" +) + +const ( + addressFamilyUnknown = "unknown" + addressFamilyIPv4 = "ipv4" + addressFamilyIPv6 = "ipv6" +) + +var ( + // TODO(jwhited): go generate these maps or equivalent switch logic behind bpf2go + pbaToOutcomeLV = map[bpfCounterKeyPacketsBytesAction]string{ + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL: xdpOutcomePass, + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL: xdpOutcomePass, + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_ABORTED_TOTAL: xdpOutcomeAborted, + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_ABORTED_TOTAL: xdpOutcomeAborted, + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_TX_TOTAL: xdpOutcomeTX, + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_TX_TOTAL: xdpOutcomeTX, + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_DROP_TOTAL: xdpOutcomeDrop, + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_DROP_TOTAL: xdpOutcomeDrop, + } + + progEndLV = map[bpfCounterKeyProgEnd]string{ + bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED: "unspecified", + bpfCounterKeyProgEndCOUNTER_KEY_END_UNEXPECTED_FIRST_STUN_ATTR: "unexpected_first_stun_attr", + bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_UDP_CSUM: "invalid_udp_csum", + bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_IP_CSUM: "invalid_ip_csum", + bpfCounterKeyProgEndCOUNTER_KEY_END_NOT_STUN_PORT: "not_stun_port", + bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_SW_ATTR_VAL: "invalid_sw_attr_val", + } + + packetCounterKeys = map[bpfCounterKeyPacketsBytesAction]bool{ + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL: true, + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_ABORTED_TOTAL: true, + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_TX_TOTAL: true, + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_DROP_TOTAL: true, + } + + //lint:ignore U1000 used in xdp_linux_test.go, which has a build tag + bytesCounterKeys = map[bpfCounterKeyPacketsBytesAction]bool{ + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL: true, + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_ABORTED_TOTAL: true, + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_TX_TOTAL: true, + bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_DROP_TOTAL: true, + } +) + +// increase returns the difference between "from" and "to" assuming they +// originated from the same counter gathered at different times, i.e. "from" +// was incremented by a non-negative value into "to". In the case of wraps +// increase returns the difference between "to" and zero. +func increase(from, to uint64) uint64 { + if to >= from { + return to - from + } + return to +} + +func (s *stunServerMetrics) updateFromMapKV(key bpfCountersKey, vals []uint64) error { + if key.Unused != 0 || + key.Af >= uint8(bpfCounterKeyAfCOUNTER_KEY_AF_LEN) || + key.Pba >= uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_BYTES_ACTION_LEN) || + key.ProgEnd >= uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_LEN) { + return fmt.Errorf("unexpected counter key: %+v", key) + } + previousAllCPUs := s.last[key] + allCPUs := sum(vals) + s.last[key] = allCPUs + inc := increase(previousAllCPUs, allCPUs) + if inc == 0 { + return nil + } + var af string + switch key.Af { + case uint8(bpfCounterKeyAfCOUNTER_KEY_AF_UNKNOWN): + af = addressFamilyUnknown + case uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4): + af = addressFamilyIPv4 + case uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6): + af = addressFamilyIPv6 + } + labels := prometheus.Labels{ + addressFamilyKey: af, + xdpOutcomeKey: pbaToOutcomeLV[bpfCounterKeyPacketsBytesAction(key.Pba)], + progEndKey: progEndLV[bpfCounterKeyProgEnd(key.ProgEnd)], + } + var metric *prometheus.CounterVec + if packetCounterKeys[bpfCounterKeyPacketsBytesAction(key.Pba)] { + metric = s.packets + } else { + metric = s.bytes + } + metric.With(labels).Add(float64(inc)) + return nil +} + +// Describe is part of the implementation of prometheus.Collector. +func (s *STUNServer) Describe(descCh chan<- *prometheus.Desc) { + s.metrics.registry.Describe(descCh) +} + +// Collect is part of the implementation of prometheus.Collector. +func (s *STUNServer) Collect(metricCh chan<- prometheus.Metric) { + err := s.updateMetrics() + if err != nil { + log.Printf("xdp: error collecting metrics: %v", err) + } + s.metrics.registry.Collect(metricCh) +} + +func (s *STUNServer) updateMetrics() error { + s.mu.Lock() + defer s.mu.Unlock() + iter := s.objs.CountersMap.Iterate() + var key bpfCountersKey + numCPU, err := ebpf.PossibleCPU() + if err != nil { + return err + } + vals := make([]uint64, numCPU) + for iter.Next(&key, &vals) { + err := s.metrics.updateFromMapKV(key, vals) + if err != nil { + return err + } + } + return iter.Err() +} diff --git a/derp/xdp/xdp_linux_test.go b/derp/xdp/xdp_linux_test.go new file mode 100644 index 000000000..ae14780be --- /dev/null +++ b/derp/xdp/xdp_linux_test.go @@ -0,0 +1,975 @@ +// Copyright (c) Tailscale Inc & AUTHORS +// SPDX-License-Identifier: BSD-3-Clause + +//go:build linux + +package xdp + +import ( + "bytes" + "errors" + "fmt" + "net/netip" + "testing" + + "github.com/cilium/ebpf" + "golang.org/x/sys/unix" + "gvisor.dev/gvisor/pkg/tcpip" + "gvisor.dev/gvisor/pkg/tcpip/checksum" + "gvisor.dev/gvisor/pkg/tcpip/header" + "tailscale.com/net/stun" +) + +type xdpAction uint32 + +func (x xdpAction) String() string { + switch x { + case xdpActionAborted: + return "XDP_ABORTED" + case xdpActionDrop: + return "XDP_DROP" + case xdpActionPass: + return "XDP_PASS" + case xdpActionTX: + return "XDP_TX" + case xdpActionRedirect: + return "XDP_REDIRECT" + default: + return fmt.Sprintf("unknown(%d)", x) + } +} + +const ( + xdpActionAborted xdpAction = iota + xdpActionDrop + xdpActionPass + xdpActionTX + xdpActionRedirect +) + +const ( + ethHLen = 14 + udpHLen = 8 + ipv4HLen = 20 + ipv6HLen = 40 +) + +const ( + defaultSTUNPort = 3478 + defaultTTL = 64 + reqSrcPort = uint16(1025) +) + +var ( + reqEthSrc = tcpip.LinkAddress([]byte{0x00, 0x00, 0x5e, 0x00, 0x53, 0x01}) + reqEthDst = tcpip.LinkAddress([]byte{0x00, 0x00, 0x5e, 0x00, 0x53, 0x02}) + reqIPv4Src = netip.MustParseAddr("192.0.2.1") + reqIPv4Dst = netip.MustParseAddr("192.0.2.2") + reqIPv6Src = netip.MustParseAddr("2001:db8::1") + reqIPv6Dst = netip.MustParseAddr("2001:db8::2") +) + +var testTXID = stun.TxID([12]byte{0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b}) + +type ipv4Mutations struct { + ipHeaderFn func(header.IPv4) + udpHeaderFn func(header.UDP) + stunReqFn func([]byte) +} + +func getIPv4STUNBindingReq(mutations *ipv4Mutations) []byte { + req := stun.Request(testTXID) + if mutations != nil && mutations.stunReqFn != nil { + mutations.stunReqFn(req) + } + payloadLen := len(req) + totalLen := ipv4HLen + udpHLen + payloadLen + b := make([]byte, ethHLen+totalLen) + ipv4H := header.IPv4(b[ethHLen:]) + ethH := header.Ethernet(b) + ethFields := header.EthernetFields{ + SrcAddr: reqEthSrc, + DstAddr: reqEthDst, + Type: unix.ETH_P_IP, + } + ethH.Encode(ðFields) + ipFields := header.IPv4Fields{ + SrcAddr: tcpip.AddrFrom4(reqIPv4Src.As4()), + DstAddr: tcpip.AddrFrom4(reqIPv4Dst.As4()), + Protocol: unix.IPPROTO_UDP, + TTL: defaultTTL, + TotalLength: uint16(totalLen), + } + ipv4H.Encode(&ipFields) + ipv4H.SetChecksum(^ipv4H.CalculateChecksum()) + if mutations != nil && mutations.ipHeaderFn != nil { + mutations.ipHeaderFn(ipv4H) + } + udpH := header.UDP(b[ethHLen+ipv4HLen:]) + udpFields := header.UDPFields{ + SrcPort: reqSrcPort, + DstPort: defaultSTUNPort, + Length: uint16(udpHLen + payloadLen), + Checksum: 0, + } + udpH.Encode(&udpFields) + copy(b[ethHLen+ipv4HLen+udpHLen:], req) + cs := header.PseudoHeaderChecksum( + unix.IPPROTO_UDP, + ipv4H.SourceAddress(), + ipv4H.DestinationAddress(), + uint16(udpHLen+payloadLen), + ) + cs = checksum.Checksum(req, cs) + udpH.SetChecksum(^udpH.CalculateChecksum(cs)) + if mutations != nil && mutations.udpHeaderFn != nil { + mutations.udpHeaderFn(udpH) + } + return b +} + +type ipv6Mutations struct { + ipHeaderFn func(header.IPv6) + udpHeaderFn func(header.UDP) + stunReqFn func([]byte) +} + +func getIPv6STUNBindingReq(mutations *ipv6Mutations) []byte { + req := stun.Request(testTXID) + if mutations != nil && mutations.stunReqFn != nil { + mutations.stunReqFn(req) + } + payloadLen := len(req) + src := netip.MustParseAddr("2001:db8::1") + dst := netip.MustParseAddr("2001:db8::2") + b := make([]byte, ethHLen+ipv6HLen+udpHLen+payloadLen) + ipv6H := header.IPv6(b[ethHLen:]) + ethH := header.Ethernet(b) + ethFields := header.EthernetFields{ + SrcAddr: tcpip.LinkAddress([]byte{0x00, 0x00, 0x5e, 0x00, 0x53, 0x01}), + DstAddr: tcpip.LinkAddress([]byte{0x00, 0x00, 0x5e, 0x00, 0x53, 0x02}), + Type: unix.ETH_P_IPV6, + } + ethH.Encode(ðFields) + ipFields := header.IPv6Fields{ + SrcAddr: tcpip.AddrFrom16(src.As16()), + DstAddr: tcpip.AddrFrom16(dst.As16()), + TransportProtocol: unix.IPPROTO_UDP, + HopLimit: 64, + PayloadLength: uint16(udpHLen + payloadLen), + } + ipv6H.Encode(&ipFields) + if mutations != nil && mutations.ipHeaderFn != nil { + mutations.ipHeaderFn(ipv6H) + } + udpH := header.UDP(b[ethHLen+ipv6HLen:]) + udpFields := header.UDPFields{ + SrcPort: 1025, + DstPort: defaultSTUNPort, + Length: uint16(udpHLen + payloadLen), + Checksum: 0, + } + udpH.Encode(&udpFields) + copy(b[ethHLen+ipv6HLen+udpHLen:], req) + cs := header.PseudoHeaderChecksum( + unix.IPPROTO_UDP, + ipv6H.SourceAddress(), + ipv6H.DestinationAddress(), + uint16(udpHLen+payloadLen), + ) + cs = checksum.Checksum(req, cs) + udpH.SetChecksum(^udpH.CalculateChecksum(cs)) + if mutations != nil && mutations.udpHeaderFn != nil { + mutations.udpHeaderFn(udpH) + } + return b +} + +func getIPv4STUNBindingResp() []byte { + addrPort := netip.AddrPortFrom(reqIPv4Src, reqSrcPort) + resp := stun.Response(testTXID, addrPort) + payloadLen := len(resp) + totalLen := ipv4HLen + udpHLen + payloadLen + b := make([]byte, ethHLen+totalLen) + ipv4H := header.IPv4(b[ethHLen:]) + ethH := header.Ethernet(b) + ethFields := header.EthernetFields{ + SrcAddr: reqEthDst, + DstAddr: reqEthSrc, + Type: unix.ETH_P_IP, + } + ethH.Encode(ðFields) + ipFields := header.IPv4Fields{ + SrcAddr: tcpip.AddrFrom4(reqIPv4Dst.As4()), + DstAddr: tcpip.AddrFrom4(reqIPv4Src.As4()), + Protocol: unix.IPPROTO_UDP, + TTL: defaultTTL, + TotalLength: uint16(totalLen), + } + ipv4H.Encode(&ipFields) + ipv4H.SetChecksum(^ipv4H.CalculateChecksum()) + udpH := header.UDP(b[ethHLen+ipv4HLen:]) + udpFields := header.UDPFields{ + SrcPort: defaultSTUNPort, + DstPort: reqSrcPort, + Length: uint16(udpHLen + payloadLen), + Checksum: 0, + } + udpH.Encode(&udpFields) + copy(b[ethHLen+ipv4HLen+udpHLen:], resp) + cs := header.PseudoHeaderChecksum( + unix.IPPROTO_UDP, + ipv4H.SourceAddress(), + ipv4H.DestinationAddress(), + uint16(udpHLen+payloadLen), + ) + cs = checksum.Checksum(resp, cs) + udpH.SetChecksum(^udpH.CalculateChecksum(cs)) + return b +} + +func getIPv6STUNBindingResp() []byte { + addrPort := netip.AddrPortFrom(reqIPv6Src, reqSrcPort) + resp := stun.Response(testTXID, addrPort) + payloadLen := len(resp) + totalLen := ipv6HLen + udpHLen + payloadLen + b := make([]byte, ethHLen+totalLen) + ipv6H := header.IPv6(b[ethHLen:]) + ethH := header.Ethernet(b) + ethFields := header.EthernetFields{ + SrcAddr: reqEthDst, + DstAddr: reqEthSrc, + Type: unix.ETH_P_IPV6, + } + ethH.Encode(ðFields) + ipFields := header.IPv6Fields{ + SrcAddr: tcpip.AddrFrom16(reqIPv6Dst.As16()), + DstAddr: tcpip.AddrFrom16(reqIPv6Src.As16()), + TransportProtocol: unix.IPPROTO_UDP, + HopLimit: defaultTTL, + PayloadLength: uint16(udpHLen + payloadLen), + } + ipv6H.Encode(&ipFields) + udpH := header.UDP(b[ethHLen+ipv6HLen:]) + udpFields := header.UDPFields{ + SrcPort: defaultSTUNPort, + DstPort: reqSrcPort, + Length: uint16(udpHLen + payloadLen), + Checksum: 0, + } + udpH.Encode(&udpFields) + copy(b[ethHLen+ipv6HLen+udpHLen:], resp) + cs := header.PseudoHeaderChecksum( + unix.IPPROTO_UDP, + ipv6H.SourceAddress(), + ipv6H.DestinationAddress(), + uint16(udpHLen+payloadLen), + ) + cs = checksum.Checksum(resp, cs) + udpH.SetChecksum(^udpH.CalculateChecksum(cs)) + return b +} + +func TestXDP(t *testing.T) { + ipv4STUNBindingReqTX := getIPv4STUNBindingReq(nil) + ipv6STUNBindingReqTX := getIPv6STUNBindingReq(nil) + + ipv4STUNBindingReqIPCsumPass := getIPv4STUNBindingReq(&ipv4Mutations{ + ipHeaderFn: func(ipv4H header.IPv4) { + oldCS := ipv4H.Checksum() + newCS := oldCS + for newCS == 0 || newCS == oldCS { + newCS++ + } + ipv4H.SetChecksum(newCS) + }, + }) + + ipv4STUNBindingReqIHLPass := getIPv4STUNBindingReq(&ipv4Mutations{ + ipHeaderFn: func(ipv4H header.IPv4) { + ipv4H[0] &= 0xF0 + }, + }) + + ipv4STUNBindingReqIPVerPass := getIPv4STUNBindingReq(&ipv4Mutations{ + ipHeaderFn: func(ipv4H header.IPv4) { + ipv4H[0] &= 0x0F + }, + }) + + ipv4STUNBindingReqIPProtoPass := getIPv4STUNBindingReq(&ipv4Mutations{ + ipHeaderFn: func(ipv4H header.IPv4) { + ipv4H[9] = unix.IPPROTO_TCP + }, + }) + + ipv4STUNBindingReqFragOffsetPass := getIPv4STUNBindingReq(&ipv4Mutations{ + ipHeaderFn: func(ipv4H header.IPv4) { + ipv4H.SetFlagsFragmentOffset(ipv4H.Flags(), 8) + }, + }) + + ipv4STUNBindingReqFlagsMFPass := getIPv4STUNBindingReq(&ipv4Mutations{ + ipHeaderFn: func(ipv4H header.IPv4) { + ipv4H.SetFlagsFragmentOffset(header.IPv4FlagMoreFragments, 0) + }, + }) + + ipv4STUNBindingReqTotLenPass := getIPv4STUNBindingReq(&ipv4Mutations{ + ipHeaderFn: func(ipv4H header.IPv4) { + ipv4H.SetTotalLength(ipv4H.TotalLength() + 1) + ipv4H.SetChecksum(0) + ipv4H.SetChecksum(^ipv4H.CalculateChecksum()) + }, + }) + + ipv6STUNBindingReqIPVerPass := getIPv6STUNBindingReq(&ipv6Mutations{ + ipHeaderFn: func(ipv6H header.IPv6) { + ipv6H[0] &= 0x0F + }, + udpHeaderFn: func(udp header.UDP) {}, + }) + + ipv6STUNBindingReqNextHdrPass := getIPv6STUNBindingReq(&ipv6Mutations{ + ipHeaderFn: func(ipv6H header.IPv6) { + ipv6H.SetNextHeader(unix.IPPROTO_TCP) + }, + udpHeaderFn: func(udp header.UDP) {}, + }) + + ipv6STUNBindingReqPayloadLenPass := getIPv6STUNBindingReq(&ipv6Mutations{ + ipHeaderFn: func(ipv6H header.IPv6) { + ipv6H.SetPayloadLength(ipv6H.PayloadLength() + 1) + }, + udpHeaderFn: func(udp header.UDP) {}, + }) + + ipv4STUNBindingReqUDPCsumPass := getIPv4STUNBindingReq(&ipv4Mutations{ + udpHeaderFn: func(udpH header.UDP) { + oldCS := udpH.Checksum() + newCS := oldCS + for newCS == 0 || newCS == oldCS { + newCS++ + } + udpH.SetChecksum(newCS) + }, + }) + + ipv6STUNBindingReqUDPCsumPass := getIPv6STUNBindingReq(&ipv6Mutations{ + udpHeaderFn: func(udpH header.UDP) { + oldCS := udpH.Checksum() + newCS := oldCS + for newCS == 0 || newCS == oldCS { + newCS++ + } + udpH.SetChecksum(newCS) + }, + }) + + ipv4STUNBindingReqSTUNTypePass := getIPv4STUNBindingReq(&ipv4Mutations{ + stunReqFn: func(req []byte) { + req[1] = ^req[1] + }, + }) + + ipv6STUNBindingReqSTUNTypePass := getIPv6STUNBindingReq(&ipv6Mutations{ + stunReqFn: func(req []byte) { + req[1] = ^req[1] + }, + }) + + ipv4STUNBindingReqSTUNMagicPass := getIPv4STUNBindingReq(&ipv4Mutations{ + stunReqFn: func(req []byte) { + req[4] = ^req[4] + }, + }) + + ipv6STUNBindingReqSTUNMagicPass := getIPv6STUNBindingReq(&ipv6Mutations{ + stunReqFn: func(req []byte) { + req[4] = ^req[4] + }, + }) + + ipv4STUNBindingReqSTUNAttrsLenPass := getIPv4STUNBindingReq(&ipv4Mutations{ + stunReqFn: func(req []byte) { + req[2] = ^req[2] + }, + }) + + ipv6STUNBindingReqSTUNAttrsLenPass := getIPv6STUNBindingReq(&ipv6Mutations{ + stunReqFn: func(req []byte) { + req[2] = ^req[2] + }, + }) + + ipv4STUNBindingReqSTUNSWValPass := getIPv4STUNBindingReq(&ipv4Mutations{ + stunReqFn: func(req []byte) { + req[24] = ^req[24] + }, + }) + + ipv6STUNBindingReqSTUNSWValPass := getIPv6STUNBindingReq(&ipv6Mutations{ + stunReqFn: func(req []byte) { + req[24] = ^req[24] + }, + }) + + ipv4STUNBindingReqSTUNFirstAttrPass := getIPv4STUNBindingReq(&ipv4Mutations{ + stunReqFn: func(req []byte) { + req[21] = ^req[21] + }, + }) + + ipv6STUNBindingReqSTUNFirstAttrPass := getIPv6STUNBindingReq(&ipv6Mutations{ + stunReqFn: func(req []byte) { + req[21] = ^req[21] + }, + }) + + cases := []struct { + name string + packetIn []byte + wantCode xdpAction + wantPacketOut []byte + wantMetrics map[bpfCountersKey]uint64 + }{ + { + name: "ipv4 STUN Binding Request TX", + packetIn: ipv4STUNBindingReqTX, + wantCode: xdpActionTX, + wantPacketOut: getIPv4STUNBindingResp(), + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_TX_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_TX_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(getIPv4STUNBindingResp())), + }, + }, + { + name: "ipv6 STUN Binding Request TX", + packetIn: ipv6STUNBindingReqTX, + wantCode: xdpActionTX, + wantPacketOut: getIPv6STUNBindingResp(), + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_TX_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_TX_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(getIPv6STUNBindingResp())), + }, + }, + { + name: "ipv4 STUN Binding Request invalid ip csum PASS", + packetIn: ipv4STUNBindingReqIPCsumPass, + wantCode: xdpActionPass, + wantPacketOut: ipv4STUNBindingReqIPCsumPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_IP_CSUM), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_IP_CSUM), + }: uint64(len(ipv4STUNBindingReqIPCsumPass)), + }, + }, + { + name: "ipv4 STUN Binding Request ihl PASS", + packetIn: ipv4STUNBindingReqIHLPass, + wantCode: xdpActionPass, + wantPacketOut: ipv4STUNBindingReqIHLPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv4STUNBindingReqIHLPass)), + }, + }, + { + name: "ipv4 STUN Binding Request ip version PASS", + packetIn: ipv4STUNBindingReqIPVerPass, + wantCode: xdpActionPass, + wantPacketOut: ipv4STUNBindingReqIPVerPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv4STUNBindingReqIPVerPass)), + }, + }, + { + name: "ipv4 STUN Binding Request ip proto PASS", + packetIn: ipv4STUNBindingReqIPProtoPass, + wantCode: xdpActionPass, + wantPacketOut: ipv4STUNBindingReqIPProtoPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv4STUNBindingReqIPProtoPass)), + }, + }, + { + name: "ipv4 STUN Binding Request frag offset PASS", + packetIn: ipv4STUNBindingReqFragOffsetPass, + wantCode: xdpActionPass, + wantPacketOut: ipv4STUNBindingReqFragOffsetPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv4STUNBindingReqFragOffsetPass)), + }, + }, + { + name: "ipv4 STUN Binding Request flags mf PASS", + packetIn: ipv4STUNBindingReqFlagsMFPass, + wantCode: xdpActionPass, + wantPacketOut: ipv4STUNBindingReqFlagsMFPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv4STUNBindingReqFlagsMFPass)), + }, + }, + { + name: "ipv4 STUN Binding Request tot len PASS", + packetIn: ipv4STUNBindingReqTotLenPass, + wantCode: xdpActionPass, + wantPacketOut: ipv4STUNBindingReqTotLenPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv4STUNBindingReqTotLenPass)), + }, + }, + { + name: "ipv6 STUN Binding Request ip version PASS", + packetIn: ipv6STUNBindingReqIPVerPass, + wantCode: xdpActionPass, + wantPacketOut: ipv6STUNBindingReqIPVerPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv6STUNBindingReqIPVerPass)), + }, + }, + { + name: "ipv6 STUN Binding Request next hdr PASS", + packetIn: ipv6STUNBindingReqNextHdrPass, + wantCode: xdpActionPass, + wantPacketOut: ipv6STUNBindingReqNextHdrPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv6STUNBindingReqNextHdrPass)), + }, + }, + { + name: "ipv6 STUN Binding Request payload len PASS", + packetIn: ipv6STUNBindingReqPayloadLenPass, + wantCode: xdpActionPass, + wantPacketOut: ipv6STUNBindingReqPayloadLenPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv6STUNBindingReqPayloadLenPass)), + }, + }, + { + name: "ipv4 STUN Binding Request UDP csum PASS", + packetIn: ipv4STUNBindingReqUDPCsumPass, + wantCode: xdpActionPass, + wantPacketOut: ipv4STUNBindingReqUDPCsumPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_UDP_CSUM), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_UDP_CSUM), + }: uint64(len(ipv4STUNBindingReqUDPCsumPass)), + }, + }, + { + name: "ipv6 STUN Binding Request UDP csum PASS", + packetIn: ipv6STUNBindingReqUDPCsumPass, + wantCode: xdpActionPass, + wantPacketOut: ipv6STUNBindingReqUDPCsumPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_UDP_CSUM), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_UDP_CSUM), + }: uint64(len(ipv6STUNBindingReqUDPCsumPass)), + }, + }, + { + name: "ipv4 STUN Binding Request STUN type PASS", + packetIn: ipv4STUNBindingReqSTUNTypePass, + wantCode: xdpActionPass, + wantPacketOut: ipv4STUNBindingReqSTUNTypePass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv4STUNBindingReqSTUNTypePass)), + }, + }, + { + name: "ipv6 STUN Binding Request STUN type PASS", + packetIn: ipv6STUNBindingReqSTUNTypePass, + wantCode: xdpActionPass, + wantPacketOut: ipv6STUNBindingReqSTUNTypePass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv6STUNBindingReqSTUNTypePass)), + }, + }, + { + name: "ipv4 STUN Binding Request STUN magic PASS", + packetIn: ipv4STUNBindingReqSTUNMagicPass, + wantCode: xdpActionPass, + wantPacketOut: ipv4STUNBindingReqSTUNMagicPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv4STUNBindingReqSTUNMagicPass)), + }, + }, + { + name: "ipv6 STUN Binding Request STUN magic PASS", + packetIn: ipv6STUNBindingReqSTUNMagicPass, + wantCode: xdpActionPass, + wantPacketOut: ipv6STUNBindingReqSTUNMagicPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv6STUNBindingReqSTUNMagicPass)), + }, + }, + { + name: "ipv4 STUN Binding Request STUN attrs len PASS", + packetIn: ipv4STUNBindingReqSTUNAttrsLenPass, + wantCode: xdpActionPass, + wantPacketOut: ipv4STUNBindingReqSTUNAttrsLenPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv4STUNBindingReqSTUNAttrsLenPass)), + }, + }, + { + name: "ipv6 STUN Binding Request STUN attrs len PASS", + packetIn: ipv6STUNBindingReqSTUNAttrsLenPass, + wantCode: xdpActionPass, + wantPacketOut: ipv6STUNBindingReqSTUNAttrsLenPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNSPECIFIED), + }: uint64(len(ipv6STUNBindingReqSTUNAttrsLenPass)), + }, + }, + { + name: "ipv4 STUN Binding Request STUN SW val PASS", + packetIn: ipv4STUNBindingReqSTUNSWValPass, + wantCode: xdpActionPass, + wantPacketOut: ipv4STUNBindingReqSTUNSWValPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_SW_ATTR_VAL), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_SW_ATTR_VAL), + }: uint64(len(ipv4STUNBindingReqSTUNSWValPass)), + }, + }, + { + name: "ipv6 STUN Binding Request STUN SW val PASS", + packetIn: ipv6STUNBindingReqSTUNSWValPass, + wantCode: xdpActionPass, + wantPacketOut: ipv6STUNBindingReqSTUNSWValPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_SW_ATTR_VAL), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_INVALID_SW_ATTR_VAL), + }: uint64(len(ipv6STUNBindingReqSTUNSWValPass)), + }, + }, + { + name: "ipv4 STUN Binding Request STUN first attr PASS", + packetIn: ipv4STUNBindingReqSTUNFirstAttrPass, + wantCode: xdpActionPass, + wantPacketOut: ipv4STUNBindingReqSTUNFirstAttrPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNEXPECTED_FIRST_STUN_ATTR), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV4), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNEXPECTED_FIRST_STUN_ATTR), + }: uint64(len(ipv4STUNBindingReqSTUNFirstAttrPass)), + }, + }, + { + name: "ipv6 STUN Binding Request STUN first attr PASS", + packetIn: ipv6STUNBindingReqSTUNFirstAttrPass, + wantCode: xdpActionPass, + wantPacketOut: ipv6STUNBindingReqSTUNFirstAttrPass, + wantMetrics: map[bpfCountersKey]uint64{ + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNEXPECTED_FIRST_STUN_ATTR), + }: 1, + { + Af: uint8(bpfCounterKeyAfCOUNTER_KEY_AF_IPV6), + Pba: uint8(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_BYTES_PASS_TOTAL), + ProgEnd: uint8(bpfCounterKeyProgEndCOUNTER_KEY_END_UNEXPECTED_FIRST_STUN_ATTR), + }: uint64(len(ipv6STUNBindingReqSTUNFirstAttrPass)), + }, + }, + } + + server, err := NewSTUNServer(&STUNServerConfig{DeviceName: "fake", DstPort: defaultSTUNPort}, + &noAttachOption{}) + if err != nil { + if errors.Is(err, unix.EPERM) { + // TODO(jwhited): get this running + t.Skip("skipping due to EPERM error; test requires elevated privileges") + } + t.Fatalf("error constructing STUN server: %v", err) + } + defer server.Close() + + clearCounters := func() error { + server.metrics.last = make(map[bpfCountersKey]uint64) + var cur, next bpfCountersKey + keys := make([]bpfCountersKey, 0) + for err = server.objs.CountersMap.NextKey(nil, &next); ; err = server.objs.CountersMap.NextKey(cur, &next) { + if err != nil { + if errors.Is(err, ebpf.ErrKeyNotExist) { + break + } + return err + } + keys = append(keys, next) + cur = next + } + for _, key := range keys { + err = server.objs.CountersMap.Delete(&key) + if err != nil { + return err + } + } + err = server.objs.CountersMap.NextKey(nil, &next) + if !errors.Is(err, ebpf.ErrKeyNotExist) { + return errors.New("counters map is not empty") + } + return nil + } + + for _, c := range cases { + t.Run(c.name, func(t *testing.T) { + err = clearCounters() + if err != nil { + t.Fatalf("error clearing counters: %v", err) + } + opts := ebpf.RunOptions{ + Data: c.packetIn, + DataOut: make([]byte, 1514), + } + got, err := server.objs.XdpProgFunc.Run(&opts) + if err != nil { + t.Fatalf("error running program: %v", err) + } + if xdpAction(got) != c.wantCode { + t.Fatalf("got code: %s != %s", xdpAction(got), c.wantCode) + } + if !bytes.Equal(opts.DataOut, c.wantPacketOut) { + t.Fatal("packets not equal") + } + err = server.updateMetrics() + if err != nil { + t.Fatalf("error updating metrics: %v", err) + } + if c.wantMetrics != nil { + for k, v := range c.wantMetrics { + gotCounter, ok := server.metrics.last[k] + if !ok { + t.Errorf("expected counter at key %+v not found", k) + } + if gotCounter != v { + t.Errorf("key: %+v gotCounter: %d != %d", k, gotCounter, v) + } + } + for k := range server.metrics.last { + _, ok := c.wantMetrics[k] + if !ok { + t.Errorf("counter at key: %+v incremented unexpectedly", k) + } + } + } + }) + } +} + +func TestCountersMapKey(t *testing.T) { + if bpfCounterKeyAfCOUNTER_KEY_AF_LEN > 256 { + t.Error("COUNTER_KEY_AF_LEN no longer fits within uint8") + } + if bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_BYTES_ACTION_LEN > 256 { + t.Error("COUNTER_KEY_PACKETS_BYTES_ACTION no longer fits within uint8") + } + if bpfCounterKeyProgEndCOUNTER_KEY_END_LEN > 256 { + t.Error("COUNTER_KEY_END_LEN no longer fits within uint8") + } + if len(pbaToOutcomeLV) != int(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_BYTES_ACTION_LEN) { + t.Error("pbaToOutcomeLV is not in sync with xdp.c") + } + if len(progEndLV) != int(bpfCounterKeyProgEndCOUNTER_KEY_END_LEN) { + t.Error("progEndLV is not in sync with xdp.c") + } + if len(packetCounterKeys)+len(bytesCounterKeys) != int(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_BYTES_ACTION_LEN) { + t.Error("packetCounterKeys and/or bytesCounterKeys is not in sync with xdp.c") + } + if len(pbaToOutcomeLV) != int(bpfCounterKeyPacketsBytesActionCOUNTER_KEY_PACKETS_BYTES_ACTION_LEN) { + t.Error("pbaToOutcomeLV is not in sync with xdp.c") + } +} diff --git a/go.mod b/go.mod index 8b88c7609..c1a59af5d 100644 --- a/go.mod +++ b/go.mod @@ -16,6 +16,7 @@ require ( github.com/aws/aws-sdk-go-v2/service/s3 v1.33.0 github.com/aws/aws-sdk-go-v2/service/ssm v1.44.7 github.com/bramvdbogaerde/go-scp v1.4.0 + github.com/cilium/ebpf v0.15.0 github.com/coreos/go-iptables v0.7.1-0.20240112124308-65c67c9f46e6 github.com/coreos/go-systemd v0.0.0-20191104093116-d3cd4ed1dbcf github.com/creack/pty v1.1.21 @@ -65,8 +66,8 @@ require ( github.com/pkg/errors v0.9.1 github.com/pkg/sftp v1.13.6 github.com/prometheus-community/pro-bing v0.4.0 - github.com/prometheus/client_golang v1.18.0 - github.com/prometheus/common v0.46.0 + github.com/prometheus/client_golang v1.19.1 + github.com/prometheus/common v0.48.0 github.com/prometheus/prometheus v0.49.2-0.20240125131847-c3b8ef1694ff github.com/safchain/ethtool v0.3.0 github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e diff --git a/go.sum b/go.sum index 9ab32f028..12d36629b 100644 --- a/go.sum +++ b/go.sum @@ -206,8 +206,8 @@ github.com/chavacava/garif v0.0.0-20230227094218-b8c73b2037b8/go.mod h1:gakxgyXa github.com/chzyer/logex v1.1.10/go.mod h1:+Ywpsq7O8HXn0nuIou7OrIPyXbp3wmkHB+jjWRnGsAI= github.com/chzyer/readline v0.0.0-20180603132655-2972be24d48e/go.mod h1:nSuG5e5PlCu98SY8svDHJxuZscDgtXS6KTTbou5AhLI= github.com/chzyer/test v0.0.0-20180213035817-a1ea475d72b1/go.mod h1:Q3SI9o4m/ZMnBNeIyt5eFwwo7qiLfzFZmjNmxjkiQlU= -github.com/cilium/ebpf v0.12.3 h1:8ht6F9MquybnY97at+VDZb3eQQr8ev79RueWeVaEcG4= -github.com/cilium/ebpf v0.12.3/go.mod h1:TctK1ivibvI3znr66ljgi4hqOT8EYQjz1KWBfb1UVgM= +github.com/cilium/ebpf v0.15.0 h1:7NxJhNiBT3NG8pZJ3c+yfrVdHY8ScgKD27sScgjLMMk= +github.com/cilium/ebpf v0.15.0/go.mod h1:DHp1WyrLeiBh19Cf/tfiSMhqheEiK8fXFZ4No0P1Hso= github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw= github.com/cloudflare/circl v1.3.3/go.mod h1:5XYMA4rFBvNIrhs50XuiBJ15vF2pZn4nnUKZrLbUZFA= github.com/cloudflare/circl v1.3.7 h1:qlCDlTPz2n9fu58M0Nh1J/JzcFpfgkFHHX3O35r5vcU= @@ -342,6 +342,8 @@ github.com/go-openapi/jsonreference v0.20.4 h1:bKlDxQxQJgwpUSgOENiMPzCTBVuc7vTdX github.com/go-openapi/jsonreference v0.20.4/go.mod h1:5pZJyJP2MnYCpoeoMAql78cCHauHj0V9Lhc506VOpw4= github.com/go-openapi/swag v0.22.7 h1:JWrc1uc/P9cSomxfnsFSVWoE1FW6bNbrVPmpQYpCcR8= github.com/go-openapi/swag v0.22.7/go.mod h1:Gl91UqO+btAM0plGGxHqJcQZ1ZTy6jbmridBTsDy8A0= +github.com/go-quicktest/qt v1.101.0 h1:O1K29Txy5P2OK0dGo59b7b0LR6wKfIhttaAhHUyn7eI= +github.com/go-quicktest/qt v1.101.0/go.mod h1:14Bz/f7NwaXPtdYEgzsx46kqSxVwTbzVZsDC26tQJow= github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY= github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572 h1:tfuBGBXKqDEevZMzYi5KSi8KkcZtzBcTgAUUtapy0OI= github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572/go.mod h1:9Pwr4B2jHnOSGXyyzV8ROjYa2ojvAY6HCGYYfMoC3Ls= @@ -758,8 +760,8 @@ github.com/prometheus/client_golang v1.0.0/go.mod h1:db9x61etRT2tGnBNRi70OPL5Fsn github.com/prometheus/client_golang v1.7.1/go.mod h1:PY5Wy2awLA44sXw4AOSfFBetzPP4j5+D6mVACh+pe2M= github.com/prometheus/client_golang v1.11.0/go.mod h1:Z6t4BnS23TR94PD6BsDNk8yVqroYurpAkEiz0P2BEV0= github.com/prometheus/client_golang v1.12.1/go.mod h1:3Z9XVyYiZYEO+YQWt3RD2R3jrbd179Rt297l4aS6nDY= -github.com/prometheus/client_golang v1.18.0 h1:HzFfmkOzH5Q8L8G+kSJKUx5dtG87sewO+FoDDqP5Tbk= -github.com/prometheus/client_golang v1.18.0/go.mod h1:T+GXkCk5wSJyOqMIzVgvvjFDlkOQntgjkJWKrN5txjA= +github.com/prometheus/client_golang v1.19.1 h1:wZWJDwK+NameRJuPGDhlnFgx8e8HN3XHQeLaYJFJBOE= +github.com/prometheus/client_golang v1.19.1/go.mod h1:mP78NwGzrVks5S2H6ab8+ZZGJLZUq1hoULYBAYBw1Ho= github.com/prometheus/client_model v0.0.0-20180712105110-5c3871d89910/go.mod h1:MbSGuTsp3dbXC40dX6PRTWyKYBIrTGTE9sqQNg2J8bo= github.com/prometheus/client_model v0.0.0-20190129233127-fd36f4220a90/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA= github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA= @@ -770,8 +772,8 @@ github.com/prometheus/common v0.4.1/go.mod h1:TNfzLD0ON7rHzMJeJkieUDPYmFC7Snx/y8 github.com/prometheus/common v0.10.0/go.mod h1:Tlit/dnDKsSWFlCLTWaA1cyBgKHSMdTB80sz/V91rCo= github.com/prometheus/common v0.26.0/go.mod h1:M7rCNAaPfAosfx8veZJCuw84e35h3Cfd9VFqTh1DIvc= github.com/prometheus/common v0.32.1/go.mod h1:vu+V0TpY+O6vW9J44gczi3Ap/oXXR10b+M/gUGO4Hls= -github.com/prometheus/common v0.46.0 h1:doXzt5ybi1HBKpsZOL0sSkaNHJJqkyfEWZGGqqScV0Y= -github.com/prometheus/common v0.46.0/go.mod h1:Tp0qkxpb9Jsg54QMe+EAmqXkSV7Evdy1BTn+g2pa/hQ= +github.com/prometheus/common v0.48.0 h1:QO8U2CdOzSn1BBsmXJXduaaW+dY/5QLjfB8svtSzKKE= +github.com/prometheus/common v0.48.0/go.mod h1:0/KsvlIEfPQCQ5I2iNSAWKPZziNCvRs5EC6ILDTlAPc= github.com/prometheus/procfs v0.0.0-20181005140218-185b4288413d/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk= github.com/prometheus/procfs v0.0.2/go.mod h1:TjEm7ze935MbeOT/UhFTIMYKhuLP4wbCsTZCD3I8kEA= github.com/prometheus/procfs v0.1.3/go.mod h1:lV6e/gmhEcM9IjHGsFOCxxuZ+z1YqCvr4OA4YeYWdaU= diff --git a/net/stun/stun_test.go b/net/stun/stun_test.go index d5cb27222..05fc4d2ba 100644 --- a/net/stun/stun_test.go +++ b/net/stun/stun_test.go @@ -283,3 +283,19 @@ func TestResponse(t *testing.T) { } } } + +func TestAttrOrderForXdpDERP(t *testing.T) { + // package derp/xdp assumes attribute order. This test ensures we don't + // drift and break that assumption. + txID := stun.NewTxID() + req := stun.Request(txID) + if len(req) < 20+12 { + t.Fatal("too short") + } + if !bytes.Equal(req[20:22], []byte{0x80, 0x22}) { + t.Fatal("the first attr is not of type software") + } + if !bytes.Equal(req[24:32], []byte("tailnode")) { + t.Fatal("unexpected software attr value") + } +} diff --git a/scripts/check_license_headers.sh b/scripts/check_license_headers.sh index aedb83fd5..8345afab7 100755 --- a/scripts/check_license_headers.sh +++ b/scripts/check_license_headers.sh @@ -56,6 +56,9 @@ for file in $(find $1 \( -name '*.go' -or -name '*.tsx' -or -name '*.ts' -not -n # Generated kube deepcopy funcs file starts with a Go build tag + an empty line header="$(head -5 $file | tail -n+3 )" ;; + $1/derp/xdp/bpf_bpfe*.go) + # Generated eBPF management code + ;; *) header="$(head -2 $file)" ;; diff --git a/tsweb/promvarz/promvarz.go b/tsweb/promvarz/promvarz.go index 9740aeeca..d0e1e52ba 100644 --- a/tsweb/promvarz/promvarz.go +++ b/tsweb/promvarz/promvarz.go @@ -28,7 +28,7 @@ func Handler(w http.ResponseWriter, r *http.Request) { // gatherNativePrometheusMetrics writes metrics from the default // metric registry in text format. func gatherNativePrometheusMetrics(w http.ResponseWriter) error { - enc := expfmt.NewEncoder(w, expfmt.FmtText) + enc := expfmt.NewEncoder(w, expfmt.NewFormat(expfmt.TypeTextPlain)) mfs, err := prometheus.DefaultGatherer.Gather() if err != nil { return fmt.Errorf("could not gather metrics from DefaultGatherer: %w", err)