flow.h 8.4 KB
Newer Older
1
/*
2
 * Copyright (c) 2007-2017 Nicira, Inc.
3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21
 *
 * 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.
 *
 * 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, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
 * 02110-1301, USA
 */

#ifndef FLOW_H
#define FLOW_H 1

22
#include <linux/cache.h>
23 24 25 26 27 28 29 30 31 32 33
#include <linux/kernel.h>
#include <linux/netlink.h>
#include <linux/openvswitch.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/rcupdate.h>
#include <linux/if_ether.h>
#include <linux/in6.h>
#include <linux/jiffies.h>
#include <linux/time.h>
#include <linux/flex_array.h>
34
#include <linux/cpumask.h>
35
#include <net/inet_ecn.h>
36
#include <net/ip_tunnels.h>
37
#include <net/dst_metadata.h>
Y
Yi Yang 已提交
38
#include <net/nsh.h>
39 40 41

struct sk_buff;

42 43 44 45 46 47
enum sw_flow_mac_proto {
	MAC_PROTO_NONE = 0,
	MAC_PROTO_ETHERNET,
};
#define SW_FLOW_KEY_INVALID	0x80

48 49 50 51
/* Store options at the end of the array if they are less than the
 * maximum size. This allows us to get the benefits of variable length
 * matching for small options.
 */
52 53 54 55
#define TUN_METADATA_OFFSET(opt_len) \
	(FIELD_SIZEOF(struct sw_flow_key, tun_opts) - opt_len)
#define TUN_METADATA_OPTS(flow_key, opt_len) \
	((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len)))
56

57 58 59 60
struct ovs_tunnel_info {
	struct metadata_dst	*tun_dst;
};

61 62 63 64 65
struct vlan_head {
	__be16 tpid; /* Vlan type. Generally 802.1q or 802.1ad.*/
	__be16 tci;  /* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */
};

66 67 68 69
#define OVS_SW_FLOW_KEY_METADATA_SIZE			\
	(offsetof(struct sw_flow_key, recirc_id) +	\
	FIELD_SIZEOF(struct sw_flow_key, recirc_id))

Y
Yi Yang 已提交
70 71 72 73 74
struct ovs_key_nsh {
	struct ovs_nsh_key_base base;
	__be32 context[NSH_MD1_CONTEXT_SIZE];
};

75
struct sw_flow_key {
76
	u8 tun_opts[IP_TUNNEL_OPTS_MAX];
77
	u8 tun_opts_len;
78
	struct ip_tunnel_key tun_key;	/* Encapsulating tunnel key. */
79 80
	struct {
		u32	priority;	/* Packet QoS priority. */
81
		u32	skb_mark;	/* SKB mark. */
82
		u16	in_port;	/* Input switch port (or DP_MAX_PORTS). */
83
	} __packed phy; /* Safe when right after 'tun_key'. */
84
	u8 mac_proto;			/* MAC layer protocol (e.g. Ethernet). */
85
	u8 tun_proto;			/* Protocol of encapsulating tunnel. */
86 87
	u32 ovs_flow_hash;		/* Datapath computed hash value.  */
	u32 recirc_id;			/* Recirculation ID.  */
88 89 90
	struct {
		u8     src[ETH_ALEN];	/* Ethernet source address. */
		u8     dst[ETH_ALEN];	/* Ethernet destination address. */
91 92
		struct vlan_head vlan;
		struct vlan_head cvlan;
93 94
		__be16 type;		/* Ethernet frame type. */
	} eth;
95 96 97 98 99
	/* Filling a hole of two bytes. */
	u8 ct_state;
	u8 ct_orig_proto;		/* CT original direction tuple IP
					 * protocol.
					 */
100 101 102 103 104 105 106 107 108 109 110
	union {
		struct {
			__be32 top_lse;	/* top label stack entry */
		} mpls;
		struct {
			u8     proto;	/* IP protocol or lower 8 bits of ARP opcode. */
			u8     tos;	    /* IP ToS. */
			u8     ttl;	    /* IP TTL/hop limit. */
			u8     frag;	/* One of OVS_FRAG_TYPE_*. */
		} ip;
	};
111
	u16 ct_zone;			/* Conntrack zone. */
112 113 114 115 116
	struct {
		__be16 src;		/* TCP/UDP/SCTP source port. */
		__be16 dst;		/* TCP/UDP/SCTP destination port. */
		__be16 flags;		/* TCP flags. */
	} tp;
117 118 119 120 121 122
	union {
		struct {
			struct {
				__be32 src;	/* IP source address. */
				__be32 dst;	/* IP destination address. */
			} addr;
123 124 125 126 127 128 129 130 131 132
			union {
				struct {
					__be32 src;
					__be32 dst;
				} ct_orig;	/* Conntrack original direction fields. */
				struct {
					u8 sha[ETH_ALEN];	/* ARP source hardware address. */
					u8 tha[ETH_ALEN];	/* ARP target hardware address. */
				} arp;
			};
133 134 135 136 137 138 139
		} ipv4;
		struct {
			struct {
				struct in6_addr src;	/* IPv6 source address. */
				struct in6_addr dst;	/* IPv6 destination address. */
			} addr;
			__be32 label;			/* IPv6 flow label. */
140 141 142 143 144 145 146 147 148 149 150
			union {
				struct {
					struct in6_addr src;
					struct in6_addr dst;
				} ct_orig;	/* Conntrack original direction fields. */
				struct {
					struct in6_addr target;	/* ND target address. */
					u8 sll[ETH_ALEN];	/* ND source link layer address. */
					u8 tll[ETH_ALEN];	/* ND target link layer address. */
				} nd;
			};
151
		} ipv6;
Y
Yi Yang 已提交
152
		struct ovs_key_nsh nsh;         /* network service header */
153
	};
J
Joe Stringer 已提交
154
	struct {
155
		/* Connection tracking fields not packed above. */
156 157 158 159
		struct {
			__be16 src;	/* CT orig tuple tp src port. */
			__be16 dst;	/* CT orig tuple tp dst port. */
		} orig_tp;
160
		u32 mark;
J
Joe Stringer 已提交
161
		struct ovs_key_ct_labels labels;
J
Joe Stringer 已提交
162 163
	} ct;

164
} __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */
165

166 167 168 169 170 171 172 173 174
static inline bool sw_flow_key_is_nd(const struct sw_flow_key *key)
{
	return key->eth.type == htons(ETH_P_IPV6) &&
		key->ip.proto == NEXTHDR_ICMP &&
		key->tp.dst == 0 &&
		(key->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) ||
		 key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT));
}

175
struct sw_flow_key_range {
176 177
	unsigned short int start;
	unsigned short int end;
178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193
};

struct sw_flow_mask {
	int ref_count;
	struct rcu_head rcu;
	struct list_head list;
	struct sw_flow_key_range range;
	struct sw_flow_key key;
};

struct sw_flow_match {
	struct sw_flow_key *key;
	struct sw_flow_key_range range;
	struct sw_flow_mask *mask;
};

194 195 196 197 198 199 200 201 202 203
#define MAX_UFID_LENGTH 16 /* 128 bits */

struct sw_flow_id {
	u32 ufid_len;
	union {
		u32 ufid[MAX_UFID_LENGTH / 4];
		struct sw_flow_key *unmasked_key;
	};
};

204 205
struct sw_flow_actions {
	struct rcu_head rcu;
206
	size_t orig_len;	/* From flow_cmd_new netlink actions size */
207 208 209 210
	u32 actions_len;
	struct nlattr actions[];
};

211 212 213 214 215 216 217 218
struct flow_stats {
	u64 packet_count;		/* Number of packets matched. */
	u64 byte_count;			/* Number of bytes matched. */
	unsigned long used;		/* Last used time (in jiffies). */
	spinlock_t lock;		/* Lock for atomic stats update. */
	__be16 tcp_flags;		/* Union of seen TCP flags. */
};

219 220
struct sw_flow {
	struct rcu_head rcu;
221 222 223 224
	struct {
		struct hlist_node node[2];
		u32 hash;
	} flow_table, ufid_table;
225
	int stats_last_writer;		/* CPU id of the last writer on
226 227
					 * 'stats[0]'.
					 */
228
	struct sw_flow_key key;
229
	struct sw_flow_id id;
230
	struct cpumask cpu_used_mask;
231
	struct sw_flow_mask *mask;
232
	struct sw_flow_actions __rcu *sf_acts;
233
	struct flow_stats __rcu *stats[]; /* One for each CPU.  First one
234 235 236 237
					   * is allocated at flow creation time,
					   * the rest are allocated on demand
					   * while holding the 'stats[0].lock'.
					   */
238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253
};

struct arp_eth_header {
	__be16      ar_hrd;	/* format of hardware address   */
	__be16      ar_pro;	/* format of protocol address   */
	unsigned char   ar_hln;	/* length of hardware address   */
	unsigned char   ar_pln;	/* length of protocol address   */
	__be16      ar_op;	/* ARP opcode (command)     */

	/* Ethernet+IPv4 specific members. */
	unsigned char       ar_sha[ETH_ALEN];	/* sender hardware address  */
	unsigned char       ar_sip[4];		/* sender IP address        */
	unsigned char       ar_tha[ETH_ALEN];	/* target hardware address  */
	unsigned char       ar_tip[4];		/* target IP address        */
} __packed;

254 255 256 257 258 259 260 261 262 263 264 265 266 267 268
static inline u8 ovs_key_mac_proto(const struct sw_flow_key *key)
{
	return key->mac_proto & ~SW_FLOW_KEY_INVALID;
}

static inline u16 __ovs_mac_header_len(u8 mac_proto)
{
	return mac_proto == MAC_PROTO_ETHERNET ? ETH_HLEN : 0;
}

static inline u16 ovs_mac_header_len(const struct sw_flow_key *key)
{
	return __ovs_mac_header_len(ovs_key_mac_proto(key));
}

269 270 271 272 273 274 275 276 277 278
static inline bool ovs_identifier_is_ufid(const struct sw_flow_id *sfid)
{
	return sfid->ufid_len;
}

static inline bool ovs_identifier_is_key(const struct sw_flow_id *sfid)
{
	return !ovs_identifier_is_ufid(sfid);
}

279
void ovs_flow_stats_update(struct sw_flow *, __be16 tcp_flags,
280
			   const struct sk_buff *);
281
void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *,
282
			unsigned long *used, __be16 *tcp_flags);
283
void ovs_flow_stats_clear(struct sw_flow *);
284 285
u64 ovs_flow_used_time(unsigned long flow_jiffies);

286
int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key);
287
int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
288
			 struct sk_buff *skb,
289
			 struct sw_flow_key *key);
290
/* Extract key from packet coming from userspace. */
291
int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr,
292
				   struct sk_buff *skb,
293
				   struct sw_flow_key *key, bool log);
294

295
#endif /* flow.h */