summaryrefslogtreecommitdiff
path: root/src/ebpf/xdp_router.c
blob: 4fb5c7cb1376112dfc1d872292e8db951b5bb942 (plain)
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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
/* SPDX-License-Identifier: GPL-2.0 */

// Code thankfully copied from:
// https://medium.com/swlh/building-a-xdp-express-data-path-based-peering-router-20db4995da66

#include <linux/bpf.h>
#include <linux/if_ether.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/udp.h>
#include <linux/socket.h>

#include <bpf/bpf_endian.h>
#include <bpf/bpf_helpers.h>

#include <stdint.h>

#ifndef XDP_ACTION_MAX
#define XDP_ACTION_MAX (XDP_REDIRECT + 1)
#endif

#ifndef memcpy
#define memcpy(dest, src, n) __builtin_memcpy((dest), (src), (n))
#endif

#ifndef AF_INET
#define AF_INET 2
#endif

#ifndef AF_INET6
#define AF_INET6 10
#endif

#ifndef IPV6_FLOWINFO_MASK
#define IPV6_FLOWINFO_MASK bpf_htonl(0x0FFFFFFF)
#endif

/* This is the data record stored in the map */
struct datarec {
	__u64 rx_packets;
	__u64 rx_bytes;
};

/* Keeps stats per (enum) xdp_action */
struct bpf_map_def SEC("maps") xdp_stats_map = {
	.type        = BPF_MAP_TYPE_PERCPU_ARRAY,
	.key_size    = sizeof(__u32),
	.value_size  = sizeof(struct datarec),
	.max_entries = XDP_ACTION_MAX,
};

struct bpf_map_def SEC("maps") tx_port = {
	.type = BPF_MAP_TYPE_DEVMAP,
	.key_size = sizeof(int),
	.value_size = sizeof(int),
	.max_entries = 256,
};

/* from include/net/ip.h */
static __always_inline int ip_decrease_ttl(struct iphdr *iph)
{
	__u32 check = iph->check;
	check += bpf_htons(0x0100);
	iph->check = (__u16)(check + (check >= 0xFFFF));
	return --iph->ttl;
}

static __always_inline
__u32 xdp_stats_record_action(struct xdp_md *ctx, __u32 action)
{
	if (action >= XDP_ACTION_MAX)
		return XDP_ABORTED;

	/* Lookup in kernel BPF-side return pointer to actual data record */
	struct datarec *rec = bpf_map_lookup_elem(&xdp_stats_map, &action);
	if (!rec)
		return XDP_ABORTED;

	/* BPF_MAP_TYPE_PERCPU_ARRAY returns a data record specific to current
	 * CPU and XDP hooks runs under Softirq, which makes it safe to update
	 * without atomic operations.
	 */
	rec->rx_packets++;
	rec->rx_bytes += (ctx->data_end - ctx->data);

	return action;
}

/* xdp_router is the name of the xdp program */
SEC("prog")
int xdp_router_func(struct xdp_md *ctx)
{
	/* this is the packet context*/
	void *data_end = (void *)(long)ctx->data_end;
	void *data = (void *)(long)ctx->data;
	struct bpf_fib_lookup fib_params = {};
	struct ethhdr *eth = data;
	struct ipv6hdr *ip6h;
	struct iphdr *iph;
	__u16 h_proto;
	__u64 nh_off;
	int rc;
	/* default action is to pass */
	int action = XDP_PASS;

	nh_off = sizeof(*eth);
	if (data + nh_off > data_end) {
		action = XDP_DROP;
		goto out;
	}

	/* determine if this is IP4 or IPv6 by looking at the Ethernet protocol field */
	h_proto = eth->h_proto;
	if (h_proto == bpf_htons(ETH_P_IP)) {
		/* IPv4 part of the code */
		iph = data + nh_off;

		if (iph + 1 > data_end) {
			action = XDP_DROP;
			goto out;
		}
		/* as a real router, we need to check the TTL to prevent never ending loops*/
		if (iph->ttl <= 1)
			goto out;

		/* populate the fib_params fields to prepare for the lookup */
		fib_params.family	= AF_INET;
		fib_params.tos		= iph->tos;
		fib_params.l4_protocol	= iph->protocol;
		fib_params.sport	= 0;
		fib_params.dport	= 0;
		fib_params.tot_len	= bpf_ntohs(iph->tot_len);
		fib_params.ipv4_src	= iph->saddr;
		fib_params.ipv4_dst	= iph->daddr;
	} else if (h_proto == bpf_htons(ETH_P_IPV6)) {
		/* IPv6 part of the code */
		struct in6_addr *src = (struct in6_addr *) fib_params.ipv6_src;
		struct in6_addr *dst = (struct in6_addr *) fib_params.ipv6_dst;

		ip6h = data + nh_off;
		if (ip6h + 1 > data_end) {
			action = XDP_DROP;
			goto out;
		}
		/* as a real router, we need to check the TTL to prevent never ending loops*/
		if (ip6h->hop_limit <= 1)
			goto out;

		/* populate the fib_params fields to prepare for the lookup */
		fib_params.family	= AF_INET6;
		fib_params.flowinfo	= *(__be32 *) ip6h & IPV6_FLOWINFO_MASK;
		fib_params.l4_protocol	= ip6h->nexthdr;
		fib_params.sport	= 0;
		fib_params.dport	= 0;
		fib_params.tot_len	= bpf_ntohs(ip6h->payload_len);
		*src			= ip6h->saddr;
		*dst			= ip6h->daddr;
	} else {
		goto out;
	}

	fib_params.ifindex = ctx->ingress_ifindex;

	/* this is where the FIB lookup happens. If the lookup is successful */
	/* it will populate the fib_params.ifindex with the egress interface index */

	rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), 0);
	switch (rc) {
	case BPF_FIB_LKUP_RET_SUCCESS:         /* lookup successful */
		   /* we are a router, so we need to decrease the ttl */
		if (h_proto == bpf_htons(ETH_P_IP))
			ip_decrease_ttl(iph);
		else if (h_proto == bpf_htons(ETH_P_IPV6))
			ip6h->hop_limit--;
		/* set the correct new source and destionation mac addresses */
		/* can be found in fib_params.dmac and fib_params.smac */
		memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN);
		memcpy(eth->h_source, fib_params.smac, ETH_ALEN);
		/* and done, now we set the action to bpf_redirect_map with fib_params.ifindex which is the egress port as paramater */
		action = bpf_redirect_map(&tx_port, fib_params.ifindex, 0);
		break;
	case BPF_FIB_LKUP_RET_BLACKHOLE:    /* dest is blackholed; can be dropped */
	case BPF_FIB_LKUP_RET_UNREACHABLE:  /* dest is unreachable; can be dropped */
	case BPF_FIB_LKUP_RET_PROHIBIT:     /* dest not allowed; can be dropped */
		action = XDP_DROP;
		break;
	case BPF_FIB_LKUP_RET_NOT_FWDED:    /* packet is not forwarded */
	case BPF_FIB_LKUP_RET_FWD_DISABLED: /* fwding is not enabled on ingress */
	case BPF_FIB_LKUP_RET_UNSUPP_LWT:   /* fwd requires encapsulation */
	case BPF_FIB_LKUP_RET_NO_NEIGH:     /* no neighbor entry for nh */
	case BPF_FIB_LKUP_RET_FRAG_NEEDED:  /* fragmentation required to fwd */
		/* PASS */
		break;
	}

out:
	/* and done, update stats and return action */
	return xdp_stats_record_action(ctx, action);
}

char _license[] SEC("license") = "GPL";