linux/samples/bpf/sockex3_kern.c
Daniel Borkmann 3652c9a1b1 bpf, libbpf: Guard bpf inline asm from bpf_tail_call_static
Yaniv reported a compilation error after pulling latest libbpf:

  [...]
  ../libbpf/src/root/usr/include/bpf/bpf_helpers.h:99:10: error:
  unknown register name 'r0' in asm
                     : "r0", "r1", "r2", "r3", "r4", "r5");
  [...]

The issue got triggered given Yaniv was compiling tracing programs with native
target (e.g. x86) instead of BPF target, hence no BTF generated vmlinux.h nor
CO-RE used, and later llc with -march=bpf was invoked to compile from LLVM IR
to BPF object file. Given that clang was expecting x86 inline asm and not BPF
one the error complained that these regs don't exist on the former.

Guard bpf_tail_call_static() with defined(__bpf__) where BPF inline asm is valid
to use. BPF tracing programs on more modern kernels use BPF target anyway and
thus the bpf_tail_call_static() function will be available for them. BPF inline
asm is supported since clang 7 (clang <= 6 otherwise throws same above error),
and __bpf_unreachable() since clang 8, therefore include the latter condition
in order to prevent compilation errors for older clang versions. Given even an
old Ubuntu 18.04 LTS has official LLVM packages all the way up to llvm-10, I did
not bother to special case the __bpf_unreachable() inside bpf_tail_call_static()
further.

Also, undo the sockex3_kern's use of bpf_tail_call_static() sample given they
still have the old hacky way to even compile networking progs with native instead
of BPF target so bpf_tail_call_static() won't be defined there anymore.

Fixes: 0e9f6841f6 ("bpf, libbpf: Add bpf_tail_call_static helper for bpf programs")
Reported-by: Yaniv Agman <yanivagman@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Tested-by: Yaniv Agman <yanivagman@gmail.com>
Link: https://lore.kernel.org/bpf/CAMy7=ZUk08w5Gc2Z-EKi4JFtuUCaZYmE4yzhJjrExXpYKR4L8w@mail.gmail.com
Link: https://lore.kernel.org/bpf/20201021203257.26223-1-daniel@iogearbox.net
2020-10-22 01:46:52 +02:00

294 lines
6.2 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 PROG(F) SEC("socket/"__stringify(F)) int bpf_func_##F
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
__uint(key_size, sizeof(u32));
__uint(value_size, sizeof(u32));
__uint(max_entries, 8);
} jmp_table SEC(".maps");
#define PARSE_VLAN 1
#define PARSE_MPLS 2
#define PARSE_IP 3
#define PARSE_IPV6 4
/* Protocol dispatch routine. It tail-calls next BPF program depending
* on eth proto. Note, we could have used ...
*
* bpf_tail_call(skb, &jmp_table, 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, &jmp_table, PARSE_VLAN);
break;
case ETH_P_MPLS_UC:
case ETH_P_MPLS_MC:
bpf_tail_call(skb, &jmp_table, PARSE_MPLS);
break;
case ETH_P_IP:
bpf_tail_call(skb, &jmp_table, PARSE_IP);
break;
case ETH_P_IPV6:
bpf_tail_call(skb, &jmp_table, PARSE_IPV6);
break;
}
}
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 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;
}
}
PROG(PARSE_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;
}
PROG(PARSE_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;
}
PROG(PARSE_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;
}
PROG(PARSE_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;
}
SEC("socket/0")
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";