Continuando a série de artigos sobre BPF - a máquina virtual de uso geral do kernel do Linux - nesta edição, vamos falar sobre quais tipos de programas BPF existem e como eles são usados ​​no mundo real do dinheiro capitalista. Além disso, no final do artigo há vários links, em particular, para dois livros e meio existentes sobre BPF.
O kernel 5.9 do Linux define mais de trinta tipos diferentes de programas BPF, e vou escrever vários artigos sobre alguns desses tipos, entĂŁo este artigo, inevitavelmente, Ă© uma visĂŁo geral e nĂŁo contĂ©m tantos detalhes tĂ©cnicos quanto os anteriores. Mas, no entanto, tentaremos finalmente responder Ă questĂŁo de por que tudo isso Ă© necessário e por que há tanto ruĂdo em torno do BPF.
Se você quiser saber exatamente como o BPF ajuda a resolver com eficácia os problemas de proteção contra ataques DDoS, balanceamento de carga em servidores, implementação da pilha de rede kubernetes, proteção de sistemas contra ataques, rastreamento eficiente de sistemas 24x7 direto em produção e muitos outros, então seja bem-vindo ao cat.
Tipos de programa e Ăndice
Todos os tipos de programas BPF existentes sĂŁo registrados no arquivo include/uapi/linux/bpf.h
kernel do Linux. Nas seções a seguir, tentei agrupá-los em grupos lógicos (os asteriscos marcam as subseções do programa educacional técnico):
- Microkernel Linux
- Rastreamento de BPF e programas de coleta de dados
- Módulos de Segurança Linux
- Estendendo dinamicamente programas BPF
- Controle remoto infravermelho Linux
- Programas de programação de rede BPF
BPF .
, - , , BPF_PROG_*
.
0975 |
Alexei\ Starovoitov | 2014-09-26 | BPF_PROG_TYPE_UNSPEC |
ddd8 |
Alexei Starovoitov | 2014-12-01 | BPF_PROG_TYPE_SOCKET_FILTER |
2541 |
Alexei Starovoitov | 2015-03-25 | BPF_PROG_TYPE_KPROBE |
96be |
Daniel Borkmann | 2015-03-01 | BPF_PROG_TYPE_SCHED_CLS |
94ca |
Daniel Borkmann | 2015-03-20 | BPF_PROG_TYPE_SCHED_ACT |
98b5 |
Alexei Starovoitov | 2016-04-06 | BPF_PROG_TYPE_TRACEPOINT |
6a77 |
Brenden Blanco | 2016-07-19 | BPF_PROG_TYPE_XDP |
0515 |
Alexei Starovoitov | 2016-09-01 | BPF_PROG_TYPE_PERF_EVENT |
0e33 |
Daniel Mack | 2016-11-23 | BPF_PROG_TYPE_CGROUP_SKB |
6102 |
David Ahern | 2016-12-01 | BPF_PROG_TYPE_CGROUP_SOCK |
3a0a |
Thomas Graf | 2016-11-30 | BPF_PROG_TYPE_LWT_IN |
3a0a |
Thomas Graf | 2016-11-30 | BPF_PROG_TYPE_LWT_OUT |
3a0a |
Thomas Graf | 2016-11-30 | BPF_PROG_TYPE_LWT_XMIT |
4030 |
Lawrence Brakmo | 2017-06-30 | BPF_PROG_TYPE_SOCK_OPS |
b005 |
John Fastabend | 2017-08-15 | BPF_PROG_TYPE_SK_SKB |
ebc6 |
Roman Gushchin | 2017-11-05 | BPF_PROG_TYPE_CGROUP_DEVICE |
4f73 |
John Fastabend | 2018-03-18 | BPF_PROG_TYPE_SK_MSG |
c4f6 |
Alexei Starovoitov | 2018-03-28 | BPF_PROG_TYPE_RAW_TRACEPOINT |
4fba |
Andrey Ignatov | 2018-03-30 | BPF_PROG_TYPE_CGROUP_SOCK_ADDR |
004d |
Mathieu\ Xhonneux | 2018-05-20 | BPF_PROG_TYPE_LWT_SEG6LOCAL |
f436 |
Sean Young | 2018-05-27 | BPF_PROG_TYPE_LIRC_MODE2 |
2dbb |
Martin KaFai Lau | 2018-08-08 | BPF_PROG_TYPE_SK_REUSEPORT |
d58e |
Petar Penkov | 2018-09-14 | BPF_PROG_TYPE_FLOW_DISSECTOR |
7b14 |
Andrey Ignatov | 2019-02-27 | BPF_PROG_TYPE_CGROUP_SYSCTL |
9df1 |
Matt Mullins | 2019-04-26 | BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE |
0d01 |
Stanislav\ Fomichev | 2019-06-27 | BPF_PROG_TYPE_CGROUP_SOCKOPT |
f1b9 |
Alexei Starovoitov | 2019-10-30 | BPF_PROG_TYPE_TRACING |
27ae |
Martin KaFai Lau | 2020-01-08 | BPF_PROG_TYPE_STRUCT_OPS |
be87 |
Alexei Starovoitov | 2020-01-20 | BPF_PROG_TYPE_EXT |
fc61 |
KP Singh | 2020-03-29 | BPF_PROG_TYPE_LSM |
e9dd |
Jakub Sitnicki | 2020-07-17 | BPF_PROG_TYPE_SK_LOOKUP |
Linux
1992 «» (- ) ( ). , «LINUX is obsolete» , Linux ( 1992 ) , . «» , , , :
«, linux , , . , , , . ( ) linux . GNU , : , , . Linux , GNU " "»
, — BPF Linux . 2020 Martin KaFai Lau , . — - , , - .
BPF: BPF_PROG_TYPE_STRUCT_OPS
. , Daniel Borkman , BPF — , .
, BPF. - , . BPF tcp_congestion_ops
, TCP congestion control. — DCTCP CUBIC BPF.
, , BPF, , , (, BPF ) . , , — . . BPF Summit.
BPF
BPF Brendan Gregg, , Linux . bcc, bpftrace, «BPF Performance Tools», , BPF, .. Facebook Netflix, , BPF, 24x7. BPF — BPF .
? . BPF :
- () Linux
- tracepoint
- perf, software hardware
maps, , . , BPF, , , .
( bpftrace
, ):
#! /usr/bin/env bpftrace
#include <linux/skbuff.h>
#include <linux/ip.h>
k:icmp_echo {
$skb = (struct sk_buff *) arg0;
$iphdr = (struct iphdr *) ($skb->head + $skb->network_header);
@pingstats[ntop($iphdr->saddr), ntop($iphdr->daddr)]++;
}
, . kprobe icmp_echo
, ICMPv4 echo request. , arg0
, — sk_buff
, . IP @pingstats
. , , IP ! , kprobe, user space, .
BPF, tracing:
BPF_PROG_TYPE_KPROBE
: BPF kprobe, kretprobe, uprobe uretprobe. , (.. ), , , .BPF_PROG_TYPE_PERF_EVENT
: BPF perf.BPF_PROG_TYPE_TRACEPOINT
: BPF tracepoint. , kprobes? , tracepoints — API ( , / tracepoint ) , tracepoints ( ).BPF_PROG_TYPE_RAW_TRACEPOINT
: tracepoints . raw tracepoints BPF «» , ,BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE
: tracepoints (. )BPF_PROG_TYPE_TRACING
: , : tracepoints, , , ( :sudo cat /sys/kernel/debug/error_injection/list
), «». , BTF — .
, — Linux BPF, .
Linux Security Modules
Linux (security hooks), , , , .. Linux (Linux Security Modules LSM) SELinux, AppArmor, .., .
, . , API Kernel Runtime Security Instrumentation LSS-NA 2019. BPF, BPF_PROG_TYPE_LSM
, , BPF LSM . , , BPF, ..
, , BPF, . , BPF. , LSM . user mode helper, BPF libbpf, libbpf .
KRSI KP Singh, KRSI, BPF Summit.
BPF
Tail calls
, , BPF . , BPF 4096 . , BPF . — . tail calls.
tail calls . , , —
.
BPF_MAP_TYPE_PROG_ARRAY
, BPF ( ):
-
bpf_tail_call
. , ,
bpf_tail_call(&map, ctx, 1)
, ctx
— , . , long jump, . 32, , .
, 5.1 , , . tail calls, .
, , tail calls . , bpf_tail_call
, ? — , .
, XDP .
, tail calls — XDP features. XDP, , «» XDP . , , «» . , , , . tail calls, , . , , , - , « » — , , , .
tail calls . BPF, BPF_PROG_TYPE_EXT
, . BPF trampoline TRACING , — , .
, , xdp-dispatcher — , XDP . «» -, XDP , - . . Multiple XDP programs on a single interface—status and next steps Toke Høiland-Jørgensen Linux Plumbers 2020.
LIRC: Linux Infrared Remote Control
, BPF BPF_PROG_TYPE_LIRC_MODE2
. lwn Sean Young, , , .
, BPF , / . BPF , , , map. , - , -. , , bpf_rc_keydown
:
, , lirc? Sean Young , BPF , , API: IR userspace ( ).
BPF
BPF Berkeley Labs, BPF Linux, , BPF .
«» — XDP Linux — - , / Linux.
Linux:
, BPF , , XDP, Linux. . ( , XDP, , .)
, Linux . , DMA , CPU. , , CPU, RAM.
Linux — top half bottom half. — , , (top half), (bottom half), softirq . , bottom halves, , softirq NET_RX
.
softirq , struct sk_buff
. sk_buff
, socket buffer, — Linux. Linux sk_buff
. , : , , -, .., .. , sk_buff
.
. , head
end
, data
tail
, net_header
transport_hdr
, , .. data
— «» .
netif_receive_skb
. ? Netfilter wiki:
sk_buff
, (ingress qdisc ), , netfiler. , (sk_buff
) , — .
, ( ). start, softirq, eBPF XDP , ...
— Express Data Path
sk_buff
— , , VLAN .. BPF XDP (Express Data Path) sk_buff
.
XDP , , , RAM . struct xdp_md
, , , . — — XDP (XDP_DROP
), , (XDP_TX
), (XDP_REDIRECT
), (XDP_PASS
):
, / , , , , , MAC , XDP , / .
XDP AF_XDP
, , , zero copy. , DPDK, :
AF_XDP
: AF_XDP
(rx queue), . XDP, . , , , . ( , , , . , UDP 65784 AF_XDP
, 13, , , : ethtool -N flow-type udp4 dst-port 65784 action 13
.)
, XDP , . , , CPU 0%. Netronome, , .
«» XDP, : DDoS . , Facebook, load balancer katran, XDP, Cloudfare XDP DDoS load balancing, cilium XDP , .. R&D , XDP P4 , , ( NPU — Networking Processing Unit).
XDP , — , . , XDP, XDP Tutorial, , , — kozlyuk .
struct __sk_buff
BPF, . , Linux sk_buff
, . len
— , network_header
— L3, dev
— struct net_device
, .
, — sk_buff
( XDP, sk_buff
), , BPF sk_buff
. , — BPF struct __sk_buff
:
struct __sk_buff {
__u32 len;
__u32 pkt_type;
__u32 mark;
__u32 queue_mapping;
__u32 protocol;
__u32 vlan_present;
...
};
__sk_buff
sk_buff
, Verifier , . BPF __sk_buff
:
int bpf_prog(struct __sk_buf *ctx)
{
__u32 len = ctx->len;
__u32 type = ctx->pkt_type;
...
}
, Verifier . , pkt_type
, 3, Verifier , .
, / . , , , .
skbuff.c
( -, ):
#include <linux/bpf.h>
__attribute__((section("socket/test")))
int bpf_prog(struct __sk_buff *ctx)
{
__u32 len = ctx->len;
__u32 type = ctx->pkt_type;
return len + type;
}
:
clang -target bpf -O2 skbuff.c -o skbuff.o -c
(, , , ):
mkdir mnt
sudo mount -t bpf none ./mnt
bpftool prog load ./skbuff.o ./mnt/xxx
:
$ llvm-objdump -D ./skbuff.o --section socket/test
0: 61 12 00 00 00 00 00 00 r2 = *(u32 *)(r1 + 0)
1: 61 10 04 00 00 00 00 00 r0 = *(u32 *)(r1 + 4)
2: 0f 20 00 00 00 00 00 00 r0 += r2
3: 95 00 00 00 00 00 00 00 exit
, :
$ sudo bpftool prog dump xlated pinned ./mnt/xxx
0: (61) r2 = *(u32 *)(r1 +104)
1: (71) r0 = *(u8 *)(r1 +120)
2: (54) w0 &= 7
3: (0f) r0 += r2
4: (95) exit
Linux
Linux, , , sk_buff
, ingress qdisc. , , , egress qdisc — , , / netfilter.
Qdisc queueing discipline Linux — Traffic Control (TC). egress qdisc — , . , - , .
— classful classless — . — , . , egress qdisc, pfifo_fast
, TOS IPv4 IPv6 ( . lartc 9.2):
— qdisc noqueue
, , , .
Classful qdiscs . qdiscs. , . . , , : (classifiers) (actions). , , , , . : u32
, flower
.. : drop
( ), reclassify
( , , , VLAN tag), ..
, qdiscs , . qdiscs , C ? BPF, BPF_PROG_TYPE_SCHED_CLS
BPF_PROG_TYPE_SCHED_ACT
, , . , qdisc clsact
, egress, ingress, BPF BPF_PROG_TYPE_SCHED_CLS
direct action. — BPF — actions, .. .
BPF TC, — BPF Reference Guide Daniel Borkman cilium
— CNI kubernetes, Alibaba Google.
BPF
BPF — BPF , . eBPF cBPF, , eBPF cBPF. , BPF BPF_PROG_TYPE_SOCKET_FILTER
SO_ATTACH_BPF
. , , CAP_SYS_ADMIN
.
BPF BPF_PROG_TYPE_SOCKET_FILTER
, :
- , BPF, BPF, , (
sk_buff
) : , (, ). , RAW , .BPF_PROG_TYPE_SOCKET_FILTER
Evil eBPF In-Depth DEFCONF 27. -
AF_PACKET
PACKET_FANOUT
, . , , DPI. Linux . 2015 fanoutPACKET_FANOUT_DATA
, BPF. - 2007
xt_bpf
netfilter. BPF, . 2016 eBPF — eBPFBPF_PROG_TYPE_SOCKET_FILTER
. - , , , tun , , , , VM. .
TUNSETFILTEREBPF
. - tun BPF . .
TUNSETSTEERINGEBPF
. - Kernel Connection Multiplexor TCP datagram (. lwn, kcm). TCP BPF
BPF_PROG_TYPE_SOCKET_FILTER
,AF_KCM
SIOCKCMATTACH
(. , ). - ,
BPF_PROG_TYPE_SOCKET_FILTER
SO_ATTACH_REUSEPORT_EBPF
, . Perfect locality and three epic SystemTap scripts.
« » flower
__skb_flow_dissect
, , Linux flow dissector — - . , , ingress Linux, flower.
, , , . BPF — BPF_PROG_TYPE_FLOW_DISSECTOR
, BPF. namespace.
BPF
(cgroups) . , BPF : BPF cgroup. , ( , ) -, . cgroups , , , , - . BPF. , .
BPF_PROG_TYPE_CGROUP_SKB
BPF (ingress) (egress) . 1, , 0, . , . , , .. : BPF systemd.
, BPF . , BPF BPF_PROG_TYPE_CGROUP_SOCK
, struct sock
. sk_bound_dev_if
, . bind(2) / .
, , BPF BPF_PROG_TYPE_CGROUP_SOCK_ADDR
. bind
IP , ( use case : cgroup , , . ). connect, getpeername, getsockname, sendmsg recvmsg. , , , cilium iptables k8s.
BPF_PROG_TYPE_CGROUP_SOCKOPT
setsockopt.
BPF_PROG_TYPE_CGROUP_DEVICE
cgroupv2 , device
cgroupsv1.
BPF_PROG_TYPE_CGROUP_SYSCTL
sysctl , , , cgroup .
.
BPF
BPF_PROG_TYPE_SK_SKB
. : SOCKMAP, . , , recvmsg
, BPF, sk_buff
. , Isovalent CNI cilium k8s, Cloudfare, . SOCKMAP — TCP splicing of the future.
BPF_PROG_TYPE_SK_SKB
, BPF_PROG_TYPE_SK_MSG
, sendmsg
sendpage
, L7 — , . BPF_PROG_TYPE_SK_SKB
, sockmap
.
BPF_PROG_TYPE_SK_REUSEPORT
, SO_REUSEPORT
. BPF, , .
BPF_PROG_TYPE_SK_LOOKUP
, . : , IP , , , . namespaces.
, , TCP — BPF_PROG_TYPE_SOCK_OPS
. cgroupv2, BPF_PROG_TYPE_CGROUP_SOCKOPT
, , .., . , TCP , .
LWT:
, , . . , IPv4- IPv6-, VPN, .
, , . , , , , .
, Linux, : ip link add name ipip0 type ipip...
.. 2015 Linux . , , , — .
BPF_PROG_TYPE_LWT_IN
:lwtunnel_input
BPF_PROG_TYPE_LWT_OUT
:lwtunnel_output
BPF_PROG_TYPE_LWT_XMIT
:lwtunnel_xmit
input , output — , xmit — . struct __sk_buff
, (BPF_OK
), (BPF_DROP
), (BPF_REDIRECT
) , , (BPF_DROP
). , xmit — , .
netlink . - , BPF iproute2, :
ip route add 10.0.0.0/24 encap bpf xmit obj <prog.o> section <section> dev <dev>
<prog.o>
— BPF ELF, <section>
— .
2018 , BPF_PROG_TYPE_LWT_SEG6LOCAL
, seg6local
, . Using SRv6.
BPF: BPF_PROG_TYPE_UNSPEC
. , , / . bpf(2) .
, ! 99% , . , BPF Linux BPF_PROG_TYPE_UNSPEC
BPF, , , , tcpdump
wireshark
Linux, .
,
BPF Linux, , - . BPF , , Linux. , BPF Linux.
(, , ) Linux — BPF kprobes, tracepoints perf events, — libbpf
, bcc
bpftrace
.
2,5
- Brendan Gregg, «BPF Performance Tools». BPF Linux — BCC, . BPF .
- Brendan Gregg, «Systems Performance: Enterprise and the Cloud, 2nd Edition (2020)». «Systems Performance». : BPF, Solaris, . «BPF Performance Tools» «?», «?»
- David Calavera and Lorenzo Fontana, «Linux Observability with BPF». . BPF, , , .
Online-,
Existem muitos artigos e relatórios sobre o BPF. Portanto, aproveitaremos o fato de que a citada empresa Isovalent está tentando liderar a coleta da safra hype com o BPF e, em particular, criou recentemente este site com documentação e realizou uma cúpula do BPF - uma mini-conferência sobre o BPF. Curiosidade: os participantes do mencionado BPF Summit escolheram um novo mascote do BPF, a abelha, e surgiram com o nome eufônico de Ebee: