linux/samples/bpf/sockex3_kern.c
Rong Tao e5659e4e19 samples/bpf: Fix sockex3 error: Missing BPF prog type
since commit 450b167fb9be("libbpf: clean up SEC() handling"),
sec_def_matches() does not recognize "socket/xxx" as "socket", therefore,
the BPF program type is not recognized.

Instead of sockex3_user.c parsing section names to get the BPF program fd.
We use the program array map to assign a static index to each BPF program
(get inspired by selftests/bpf progs/test_prog_array_init.c).
Therefore, use SEC("socket") as section name instead of SEC("socket/xxx"),
so that the BPF program is parsed to SOCKET_FILTER type. The "missing BPF
prog type" problem is solved.

How to reproduce this error:
$ cd samples/bpf
$ sudo ./sockex3
libbpf: prog 'bpf_func_PARSE_IP': missing BPF prog type, check ELF section name 'socket/3'
libbpf: prog 'bpf_func_PARSE_IP': failed to load: -22
libbpf: failed to load object './sockex3_kern.o'
ERROR: loading BPF object file failed

Signed-off-by: Rong Tao <rongtao@cestc.cn>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/tencent_EBA3C18864069E42175946973C2ACBAF5408@qq.com
2022-11-07 17:13:35 -08:00

305 lines
6.5 KiB
C

/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com
*
* 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.
*/
#include <uapi/linux/bpf.h>
#include <uapi/linux/in.h>
#include <uapi/linux/if.h>
#include <uapi/linux/if_ether.h>
#include <uapi/linux/ip.h>
#include <uapi/linux/ipv6.h>
#include <uapi/linux/if_tunnel.h>
#include <uapi/linux/mpls.h>
#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
#define IP_MF 0x2000
#define IP_OFFSET 0x1FFF
#define PARSE_VLAN 1
#define PARSE_MPLS 2
#define PARSE_IP 3
#define PARSE_IPV6 4
struct vlan_hdr {
__be16 h_vlan_TCI;
__be16 h_vlan_encapsulated_proto;
};
struct flow_key_record {
__be32 src;
__be32 dst;
union {
__be32 ports;
__be16 port16[2];
};
__u32 ip_proto;
};
static inline void parse_eth_proto(struct __sk_buff *skb, u32 proto);
static inline int ip_is_fragment(struct __sk_buff *ctx, __u64 nhoff)
{
return load_half(ctx, nhoff + offsetof(struct iphdr, frag_off))
& (IP_MF | IP_OFFSET);
}
static inline __u32 ipv6_addr_hash(struct __sk_buff *ctx, __u64 off)
{
__u64 w0 = load_word(ctx, off);
__u64 w1 = load_word(ctx, off + 4);
__u64 w2 = load_word(ctx, off + 8);
__u64 w3 = load_word(ctx, off + 12);
return (__u32)(w0 ^ w1 ^ w2 ^ w3);
}
struct globals {
struct flow_key_record flow;
};
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__type(key, __u32);
__type(value, struct globals);
__uint(max_entries, 32);
} percpu_map SEC(".maps");
/* user poor man's per_cpu until native support is ready */
static struct globals *this_cpu_globals(void)
{
u32 key = bpf_get_smp_processor_id();
return bpf_map_lookup_elem(&percpu_map, &key);
}
/* some simple stats for user space consumption */
struct pair {
__u64 packets;
__u64 bytes;
};
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__type(key, struct flow_key_record);
__type(value, struct pair);
__uint(max_entries, 1024);
} hash_map SEC(".maps");
static void update_stats(struct __sk_buff *skb, struct globals *g)
{
struct flow_key_record key = g->flow;
struct pair *value;
value = bpf_map_lookup_elem(&hash_map, &key);
if (value) {
__sync_fetch_and_add(&value->packets, 1);
__sync_fetch_and_add(&value->bytes, skb->len);
} else {
struct pair val = {1, skb->len};
bpf_map_update_elem(&hash_map, &key, &val, BPF_ANY);
}
}
static __always_inline void parse_ip_proto(struct __sk_buff *skb,
struct globals *g, __u32 ip_proto)
{
__u32 nhoff = skb->cb[0];
int poff;
switch (ip_proto) {
case IPPROTO_GRE: {
struct gre_hdr {
__be16 flags;
__be16 proto;
};
__u32 gre_flags = load_half(skb,
nhoff + offsetof(struct gre_hdr, flags));
__u32 gre_proto = load_half(skb,
nhoff + offsetof(struct gre_hdr, proto));
if (gre_flags & (GRE_VERSION|GRE_ROUTING))
break;
nhoff += 4;
if (gre_flags & GRE_CSUM)
nhoff += 4;
if (gre_flags & GRE_KEY)
nhoff += 4;
if (gre_flags & GRE_SEQ)
nhoff += 4;
skb->cb[0] = nhoff;
parse_eth_proto(skb, gre_proto);
break;
}
case IPPROTO_IPIP:
parse_eth_proto(skb, ETH_P_IP);
break;
case IPPROTO_IPV6:
parse_eth_proto(skb, ETH_P_IPV6);
break;
case IPPROTO_TCP:
case IPPROTO_UDP:
g->flow.ports = load_word(skb, nhoff);
case IPPROTO_ICMP:
g->flow.ip_proto = ip_proto;
update_stats(skb, g);
break;
default:
break;
}
}
SEC("socket")
int bpf_func_ip(struct __sk_buff *skb)
{
struct globals *g = this_cpu_globals();
__u32 nhoff, verlen, ip_proto;
if (!g)
return 0;
nhoff = skb->cb[0];
if (unlikely(ip_is_fragment(skb, nhoff)))
return 0;
ip_proto = load_byte(skb, nhoff + offsetof(struct iphdr, protocol));
if (ip_proto != IPPROTO_GRE) {
g->flow.src = load_word(skb, nhoff + offsetof(struct iphdr, saddr));
g->flow.dst = load_word(skb, nhoff + offsetof(struct iphdr, daddr));
}
verlen = load_byte(skb, nhoff + 0/*offsetof(struct iphdr, ihl)*/);
nhoff += (verlen & 0xF) << 2;
skb->cb[0] = nhoff;
parse_ip_proto(skb, g, ip_proto);
return 0;
}
SEC("socket")
int bpf_func_ipv6(struct __sk_buff *skb)
{
struct globals *g = this_cpu_globals();
__u32 nhoff, ip_proto;
if (!g)
return 0;
nhoff = skb->cb[0];
ip_proto = load_byte(skb,
nhoff + offsetof(struct ipv6hdr, nexthdr));
g->flow.src = ipv6_addr_hash(skb,
nhoff + offsetof(struct ipv6hdr, saddr));
g->flow.dst = ipv6_addr_hash(skb,
nhoff + offsetof(struct ipv6hdr, daddr));
nhoff += sizeof(struct ipv6hdr);
skb->cb[0] = nhoff;
parse_ip_proto(skb, g, ip_proto);
return 0;
}
SEC("socket")
int bpf_func_vlan(struct __sk_buff *skb)
{
__u32 nhoff, proto;
nhoff = skb->cb[0];
proto = load_half(skb, nhoff + offsetof(struct vlan_hdr,
h_vlan_encapsulated_proto));
nhoff += sizeof(struct vlan_hdr);
skb->cb[0] = nhoff;
parse_eth_proto(skb, proto);
return 0;
}
SEC("socket")
int bpf_func_mpls(struct __sk_buff *skb)
{
__u32 nhoff, label;
nhoff = skb->cb[0];
label = load_word(skb, nhoff);
nhoff += sizeof(struct mpls_label);
skb->cb[0] = nhoff;
if (label & MPLS_LS_S_MASK) {
__u8 verlen = load_byte(skb, nhoff);
if ((verlen & 0xF0) == 4)
parse_eth_proto(skb, ETH_P_IP);
else
parse_eth_proto(skb, ETH_P_IPV6);
} else {
parse_eth_proto(skb, ETH_P_MPLS_UC);
}
return 0;
}
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
__uint(key_size, sizeof(u32));
__uint(max_entries, 8);
__array(values, u32 (void *));
} prog_array_init SEC(".maps") = {
.values = {
[PARSE_VLAN] = (void *)&bpf_func_vlan,
[PARSE_IP] = (void *)&bpf_func_ip,
[PARSE_IPV6] = (void *)&bpf_func_ipv6,
[PARSE_MPLS] = (void *)&bpf_func_mpls,
},
};
/* Protocol dispatch routine. It tail-calls next BPF program depending
* on eth proto. Note, we could have used ...
*
* bpf_tail_call(skb, &prog_array_init, proto);
*
* ... but it would need large prog_array and cannot be optimised given
* the map key is not static.
*/
static inline void parse_eth_proto(struct __sk_buff *skb, u32 proto)
{
switch (proto) {
case ETH_P_8021Q:
case ETH_P_8021AD:
bpf_tail_call(skb, &prog_array_init, PARSE_VLAN);
break;
case ETH_P_MPLS_UC:
case ETH_P_MPLS_MC:
bpf_tail_call(skb, &prog_array_init, PARSE_MPLS);
break;
case ETH_P_IP:
bpf_tail_call(skb, &prog_array_init, PARSE_IP);
break;
case ETH_P_IPV6:
bpf_tail_call(skb, &prog_array_init, PARSE_IPV6);
break;
}
}
SEC("socket")
int main_prog(struct __sk_buff *skb)
{
__u32 nhoff = ETH_HLEN;
__u32 proto = load_half(skb, 12);
skb->cb[0] = nhoff;
parse_eth_proto(skb, proto);
return 0;
}
char _license[] SEC("license") = "GPL";