1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
|
/* Copyright (C) 2020 CZ.NIC, z.s.p.o. <knot-dns@labs.nic.cz>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
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.
You should have received a copy of the GNU General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
*/
#include <linux/if_ether.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/udp.h>
#include "bpf-consts.h"
#include "../../contrib/libbpf/include/uapi/linux/bpf.h"
#include "../../contrib/libbpf/bpf/bpf_endian.h"
#include "../../contrib/libbpf/bpf/bpf_helpers.h"
/* Don't fragment flag. */
#define IP_DF 0x4000
/* Assume netdev has no more than 128 queues. */
#define QUEUE_MAX 128
/* A set entry here means that the corresponding queue_id
* has an active AF_XDP socket bound to it. */
struct bpf_map_def SEC("maps") qidconf_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = QUEUE_MAX,
};
struct bpf_map_def SEC("maps") xsks_map = {
.type = BPF_MAP_TYPE_XSKMAP,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = QUEUE_MAX,
};
struct ipv6_frag_hdr {
unsigned char nexthdr;
unsigned char whatever[7];
} __attribute__((packed));
SEC("xdp_redirect_udp")
int xdp_redirect_udp_func(struct xdp_md *ctx)
{
const void *data = (void *)(long)ctx->data;
const void *data_end = (void *)(long)ctx->data_end;
const struct ethhdr *eth = data;
const struct iphdr *ip4;
const struct ipv6hdr *ip6;
const struct udphdr *udp;
__u8 ip_proto;
__u8 fragmented = 0;
/* Parse Ethernet header. */
if ((void *)eth + sizeof(*eth) > data_end) {
return XDP_DROP;
}
data += sizeof(*eth);
/* Parse IPv4 or IPv6 header. */
switch (eth->h_proto) {
case __constant_htons(ETH_P_IP):
ip4 = data;
if ((void *)ip4 + sizeof(*ip4) > data_end) {
return XDP_DROP;
}
if (ip4->version != 4) {
return XDP_DROP;
}
if (ip4->frag_off != 0 &&
ip4->frag_off != __constant_htons(IP_DF)) {
fragmented = 1;
}
ip_proto = ip4->protocol;
udp = data + ip4->ihl * 4;
break;
case __constant_htons(ETH_P_IPV6):
ip6 = data;
if ((void *)ip6 + sizeof(*ip6) > data_end) {
return XDP_DROP;
}
if (ip6->version != 6) {
return XDP_DROP;
}
ip_proto = ip6->nexthdr;
data += sizeof(*ip6);
if (ip_proto == IPPROTO_FRAGMENT) {
fragmented = 1;
const struct ipv6_frag_hdr *frag = data;
if ((void *)frag + sizeof(*frag) > data_end) {
return XDP_DROP;
}
ip_proto = frag->nexthdr;
data += sizeof(*frag);
}
udp = data;
break;
default:
/* Also applies to VLAN. */
return XDP_PASS;
}
/* Treat UDP only. */
if (ip_proto != IPPROTO_UDP) {
return XDP_PASS;
}
/* Parse UDP header. */
if ((void *)udp + sizeof(*udp) > data_end) {
return XDP_DROP;
}
/* Check the UDP length. */
if (data_end - (void *)udp < __bpf_ntohs(udp->len)) {
return XDP_DROP;
}
/* Get the queue options. */
int index = ctx->rx_queue_index;
int *qidconf = bpf_map_lookup_elem(&qidconf_map, &index);
if (!qidconf) {
return XDP_ABORTED;
}
/* Treat specified destination ports only. */
__u32 port_info = *qidconf;
switch (port_info & KNOT_XDP_LISTEN_PORT_MASK) {
case KNOT_XDP_LISTEN_PORT_DROP:
return XDP_DROP;
case KNOT_XDP_LISTEN_PORT_ALL:
break;
default:
if (udp->dest != port_info) {
return XDP_PASS;
}
}
/* Drop fragmented UDP datagrams. */
if (fragmented) {
return XDP_DROP;
}
/* Forward the packet to user space. */
return bpf_redirect_map(&xsks_map, index, 0);
}
|
