sockex3_kern.c 6.1 KB
Newer Older
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
/* 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 "bpf_helpers.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>
#define IP_MF		0x2000
#define IP_OFFSET	0x1FFF

#define PROG(F) SEC("socket/"__stringify(F)) int bpf_func_##F

struct bpf_map_def SEC("maps") jmp_table = {
	.type = BPF_MAP_TYPE_PROG_ARRAY,
	.key_size = sizeof(u32),
	.value_size = sizeof(u32),
	.max_entries = 8,
};

#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
 */
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_keys {
	__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_keys flow;
};

struct bpf_map_def SEC("maps") percpu_map = {
	.type = BPF_MAP_TYPE_ARRAY,
	.key_size = sizeof(__u32),
	.value_size = sizeof(struct globals),
	.max_entries = 32,
};

/* 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 bpf_map_def SEC("maps") hash_map = {
	.type = BPF_MAP_TYPE_HASH,
	.key_size = sizeof(struct flow_keys),
	.value_size = sizeof(struct pair),
	.max_entries = 1024,
};

static void update_stats(struct __sk_buff *skb, struct globals *g)
{
	struct flow_keys 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)
{
141
	__u32 nhoff = skb->cb[0];
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
	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;

167
		skb->cb[0] = nhoff;
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
		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;

197
	nhoff = skb->cb[0];
198 199 200 201 202 203 204 205 206 207 208 209 210 211

	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;

212
	skb->cb[0] = nhoff;
213 214 215 216 217 218 219 220 221 222 223 224
	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;

225
	nhoff = skb->cb[0];
226 227 228 229 230 231 232 233 234

	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);

235
	skb->cb[0] = nhoff;
236 237 238 239 240 241 242 243
	parse_ip_proto(skb, g, ip_proto);
	return 0;
}

PROG(PARSE_VLAN)(struct __sk_buff *skb)
{
	__u32 nhoff, proto;

244
	nhoff = skb->cb[0];
245 246 247 248

	proto = load_half(skb, nhoff + offsetof(struct vlan_hdr,
						h_vlan_encapsulated_proto));
	nhoff += sizeof(struct vlan_hdr);
249
	skb->cb[0] = nhoff;
250 251 252 253 254 255 256 257 258 259

	parse_eth_proto(skb, proto);

	return 0;
}

PROG(PARSE_MPLS)(struct __sk_buff *skb)
{
	__u32 nhoff, label;

260
	nhoff = skb->cb[0];
261 262 263

	label = load_word(skb, nhoff);
	nhoff += sizeof(struct mpls_label);
264
	skb->cb[0] = nhoff;
265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284

	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);

285
	skb->cb[0] = nhoff;
286 287 288 289 290
	parse_eth_proto(skb, proto);
	return 0;
}

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