/*
- * Copyright (c) 2007-2011 Nicira, Inc.
+ * Copyright (c) 2007-2014 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
#ifndef FLOW_H
#define FLOW_H 1
+#include <linux/cache.h>
#include <linux/kernel.h>
#include <linux/netlink.h>
#include <linux/openvswitch.h>
struct sk_buff;
-struct sw_flow_actions {
- struct rcu_head rcu;
- u32 actions_len;
- struct nlattr actions[];
+/* Used to memset ovs_key_ipv4_tunnel padding. */
+#define OVS_TUNNEL_KEY_SIZE \
+ (offsetof(struct ovs_key_ipv4_tunnel, tp_dst) + \
+ FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, tp_dst))
+
+struct ovs_key_ipv4_tunnel {
+ __be64 tun_id;
+ __be32 ipv4_src;
+ __be32 ipv4_dst;
+ __be16 tun_flags;
+ u8 ipv4_tos;
+ u8 ipv4_ttl;
+ __be16 tp_src;
+ __be16 tp_dst;
+} __packed __aligned(4); /* Minimize padding. */
+
+struct ovs_tunnel_info {
+ struct ovs_key_ipv4_tunnel tunnel;
+ const void *options;
+ u8 options_len;
};
+/* 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.
+ */
+#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)))
+
+
+static inline void __ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+ __be32 saddr, __be32 daddr,
+ u8 tos, u8 ttl,
+ __be16 tp_src,
+ __be16 tp_dst,
+ __be64 tun_id,
+ __be16 tun_flags,
+ const void *opts,
+ u8 opts_len)
+{
+ tun_info->tunnel.tun_id = tun_id;
+ tun_info->tunnel.ipv4_src = saddr;
+ tun_info->tunnel.ipv4_dst = daddr;
+ tun_info->tunnel.ipv4_tos = tos;
+ tun_info->tunnel.ipv4_ttl = ttl;
+ tun_info->tunnel.tun_flags = tun_flags;
+
+ /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
+ * the upper tunnel are used.
+ * E.g: GRE over IPSEC, the tp_src and tp_port are zero.
+ */
+ tun_info->tunnel.tp_src = tp_src;
+ tun_info->tunnel.tp_dst = tp_dst;
+
+ /* Clear struct padding. */
+ if (sizeof(tun_info->tunnel) != OVS_TUNNEL_KEY_SIZE)
+ memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE,
+ 0, sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
+
+ tun_info->options = opts;
+ tun_info->options_len = opts_len;
+}
+
+static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+ const struct iphdr *iph,
+ __be16 tp_src,
+ __be16 tp_dst,
+ __be64 tun_id,
+ __be16 tun_flags,
+ const void *opts,
+ u8 opts_len)
+{
+ __ovs_flow_tun_info_init(tun_info, iph->saddr, iph->daddr,
+ iph->tos, iph->ttl,
+ tp_src, tp_dst,
+ tun_id, tun_flags,
+ opts, opts_len);
+}
+
+#define OVS_SW_FLOW_KEY_METADATA_SIZE \
+ (offsetof(struct sw_flow_key, recirc_id) + \
+ FIELD_SIZEOF(struct sw_flow_key, recirc_id))
+
struct sw_flow_key {
+ u8 tun_opts[255];
+ u8 tun_opts_len;
struct ovs_key_ipv4_tunnel tun_key; /* Encapsulating tunnel key. */
struct {
u32 priority; /* Packet QoS priority. */
+ u32 skb_mark; /* SKB mark. */
u16 in_port; /* Input switch port (or DP_MAX_PORTS). */
- } phy;
+ } __packed phy; /* Safe when right after 'tun_key'. */
+ u32 ovs_flow_hash; /* Datapath computed hash value. */
+ u32 recirc_id; /* Recirculation ID. */
struct {
u8 src[ETH_ALEN]; /* Ethernet source address. */
u8 dst[ETH_ALEN]; /* Ethernet destination address. */
__be16 tci; /* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */
__be16 type; /* Ethernet frame type. */
} eth;
+ 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;
+ };
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;
+ __be16 src; /* TCP/UDP/SCTP source port. */
+ __be16 dst; /* TCP/UDP/SCTP destination port. */
+ __be16 flags; /* TCP flags. */
+ } tp;
union {
struct {
struct {
__be32 src; /* IP source address. */
__be32 dst; /* IP destination address. */
} addr;
- union {
- struct {
- __be16 src; /* TCP/UDP source port. */
- __be16 dst; /* TCP/UDP destination port. */
- } tp;
- struct {
- u8 sha[ETH_ALEN]; /* ARP source hardware address. */
- u8 tha[ETH_ALEN]; /* ARP target hardware address. */
- } arp;
- };
+ struct {
+ u8 sha[ETH_ALEN]; /* ARP source hardware address. */
+ u8 tha[ETH_ALEN]; /* ARP target hardware address. */
+ } arp;
} ipv4;
struct {
struct {
struct in6_addr dst; /* IPv6 destination address. */
} addr;
__be32 label; /* IPv6 flow label. */
- struct {
- __be16 src; /* TCP/UDP source port. */
- __be16 dst; /* TCP/UDP destination port. */
- } tp;
struct {
struct in6_addr target; /* ND target address. */
u8 sll[ETH_ALEN]; /* ND source link layer address. */
} nd;
} ipv6;
};
+} __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */
+
+struct sw_flow_key_range {
+ unsigned short int start;
+ unsigned short int end;
+};
+
+struct sw_flow_mask {
+ int ref_count;
+ struct rcu_head rcu;
+ 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;
+};
+
+struct sw_flow_actions {
+ struct rcu_head rcu;
+ u32 actions_len;
+ struct nlattr actions[];
+};
+
+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. */
};
struct sw_flow {
struct rcu_head rcu;
struct hlist_node hash_node[2];
u32 hash;
-
+ int stats_last_writer; /* NUMA-node id of the last writer on
+ * 'stats[0]'.
+ */
struct sw_flow_key key;
+ struct sw_flow_key unmasked_key;
+ struct sw_flow_mask *mask;
struct sw_flow_actions __rcu *sf_acts;
-
- spinlock_t lock; /* Lock for values below. */
- unsigned long used; /* Last used time (in jiffies). */
- u64 packet_count; /* Number of packets matched. */
- u64 byte_count; /* Number of bytes matched. */
- u8 tcp_flags; /* Union of seen TCP flags. */
+ struct flow_stats __rcu *stats[]; /* One for each NUMA node. First one
+ * is allocated at flow creation time,
+ * the rest are allocated on demand
+ * while holding the 'stats[0].lock'.
+ */
};
struct arp_eth_header {
unsigned char ar_tip[4]; /* target IP address */
} __packed;
-int ovs_flow_init(void);
-void ovs_flow_exit(void);
-
-struct sw_flow *ovs_flow_alloc(void);
-void ovs_flow_deferred_free(struct sw_flow *);
-void ovs_flow_free(struct sw_flow *);
-
-struct sw_flow_actions *ovs_flow_actions_alloc(const struct nlattr *);
-void ovs_flow_deferred_free_acts(struct sw_flow_actions *);
-
-int ovs_flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *,
- int *key_lenp);
-void ovs_flow_used(struct sw_flow *, struct sk_buff *);
+void ovs_flow_stats_update(struct sw_flow *, __be16 tcp_flags,
+ const struct sk_buff *);
+void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *,
+ unsigned long *used, __be16 *tcp_flags);
+void ovs_flow_stats_clear(struct sw_flow *);
u64 ovs_flow_used_time(unsigned long flow_jiffies);
-/* Upper bound on the length of a nlattr-formatted flow key. The longest
- * nlattr-formatted flow key would be:
- *
- * struct pad nl hdr total
- * ------ --- ------ -----
- * OVS_KEY_ATTR_PRIORITY 4 -- 4 8
- * OVS_KEY_ATTR_TUN_ID 8 -- 4 12
- * OVS_KEY_ATTR_IPV4_TUNNEL 24 -- 4 28
- * OVS_KEY_ATTR_IN_PORT 4 -- 4 8
- * OVS_KEY_ATTR_ETHERNET 12 -- 4 16
- * OVS_KEY_ATTR_ETHERTYPE 2 2 4 8 (outer VLAN ethertype)
- * OVS_KEY_ATTR_8021Q 4 -- 4 8
- * OVS_KEY_ATTR_ENCAP 0 -- 4 4 (VLAN encapsulation)
- * OVS_KEY_ATTR_ETHERTYPE 2 2 4 8 (inner VLAN ethertype)
- * OVS_KEY_ATTR_IPV6 40 -- 4 44
- * OVS_KEY_ATTR_ICMPV6 2 2 4 8
- * OVS_KEY_ATTR_ND 28 -- 4 32
- * -------------------------------------------------
- * total 184
- */
-#define FLOW_BUFSIZE 184
-
-int ovs_flow_to_nlattrs(const struct sw_flow_key *, struct sk_buff *);
-int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp,
- const struct nlattr *);
-int ovs_flow_metadata_from_nlattrs(struct sw_flow *flow, int key_len,
- const struct nlattr *attr);
-
-#define MAX_ACTIONS_BUFSIZE (16 * 1024)
-#define TBL_MIN_BUCKETS 1024
-
-struct flow_table {
- struct flex_array *buckets;
- unsigned int count, n_buckets;
- struct rcu_head rcu;
- int node_ver;
- u32 hash_seed;
- bool keep_flows;
-};
-
-static inline int ovs_flow_tbl_count(struct flow_table *table)
-{
- return table->count;
-}
-
-static inline int ovs_flow_tbl_need_to_expand(struct flow_table *table)
-{
- return (table->count > table->n_buckets);
-}
-
-struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *table,
- struct sw_flow_key *key, int len);
-void ovs_flow_tbl_destroy(struct flow_table *table);
-void ovs_flow_tbl_deferred_destroy(struct flow_table *table);
-struct flow_table *ovs_flow_tbl_alloc(int new_size);
-struct flow_table *ovs_flow_tbl_expand(struct flow_table *table);
-struct flow_table *ovs_flow_tbl_rehash(struct flow_table *table);
-void ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
- struct sw_flow_key *key, int key_len);
-void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow);
-
-struct sw_flow *ovs_flow_tbl_next(struct flow_table *table, u32 *bucket, u32 *idx);
-extern const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1];
+/* Update the non-metadata part of the flow key using skb. */
+int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key);
+int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info,
+ struct sk_buff *skb,
+ struct sw_flow_key *key);
+/* Extract key from packet coming from userspace. */
+int ovs_flow_key_extract_userspace(const struct nlattr *attr,
+ struct sk_buff *skb,
+ struct sw_flow_key *key, bool log);
#endif /* flow.h */