linux/samples/sockmap/sockmap_kern.c
John Fastabend 34f79502bb bpf: avoid preempt enable/disable in sockmap using tcp_skb_cb region
SK_SKB BPF programs are run from the socket/tcp context but early in
the stack before much of the TCP metadata is needed in tcp_skb_cb. So
we can use some unused fields to place BPF metadata needed for SK_SKB
programs when implementing the redirect function.

This allows us to drop the preempt disable logic. It does however
require an API change so sk_redirect_map() has been updated to
additionally provide ctx_ptr to skb. Note, we do however continue to
disable/enable preemption around actual BPF program running to account
for map updates.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-20 13:01:29 +01:00

109 lines
2.7 KiB
C

/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#include <uapi/linux/bpf.h>
#include <uapi/linux/if_ether.h>
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include "../../tools/testing/selftests/bpf/bpf_helpers.h"
#include "../../tools/testing/selftests/bpf/bpf_endian.h"
/* Sockmap sample program connects a client and a backend together
* using cgroups.
*
* client:X <---> frontend:80 client:X <---> backend:80
*
* For simplicity we hard code values here and bind 1:1. The hard
* coded values are part of the setup in sockmap.sh script that
* is associated with this BPF program.
*
* The bpf_printk is verbose and prints information as connections
* are established and verdicts are decided.
*/
#define bpf_printk(fmt, ...) \
({ \
char ____fmt[] = fmt; \
bpf_trace_printk(____fmt, sizeof(____fmt), \
##__VA_ARGS__); \
})
struct bpf_map_def SEC("maps") sock_map = {
.type = BPF_MAP_TYPE_SOCKMAP,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 20,
};
SEC("sk_skb1")
int bpf_prog1(struct __sk_buff *skb)
{
return skb->len;
}
SEC("sk_skb2")
int bpf_prog2(struct __sk_buff *skb)
{
__u32 lport = skb->local_port;
__u32 rport = skb->remote_port;
int ret = 0;
if (lport == 10000)
ret = 10;
else
ret = 1;
bpf_printk("sockmap: %d -> %d @ %d\n", lport, bpf_ntohl(rport), ret);
return bpf_sk_redirect_map(skb, &sock_map, ret, 0);
}
SEC("sockops")
int bpf_sockmap(struct bpf_sock_ops *skops)
{
__u32 lport, rport;
int op, err = 0, index, key, ret;
op = (int) skops->op;
switch (op) {
case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
lport = skops->local_port;
rport = skops->remote_port;
if (lport == 10000) {
ret = 1;
err = bpf_sock_map_update(skops, &sock_map, &ret,
BPF_NOEXIST);
bpf_printk("passive(%i -> %i) map ctx update err: %d\n",
lport, bpf_ntohl(rport), err);
}
break;
case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
lport = skops->local_port;
rport = skops->remote_port;
if (bpf_ntohl(rport) == 10001) {
ret = 10;
err = bpf_sock_map_update(skops, &sock_map, &ret,
BPF_NOEXIST);
bpf_printk("active(%i -> %i) map ctx update err: %d\n",
lport, bpf_ntohl(rport), err);
}
break;
default:
break;
}
return 0;
}
char _license[] SEC("license") = "GPL";