X-Git-Url: http://git.cascardo.eti.br/?a=blobdiff_plain;f=datapath%2Fflow.h;h=c0b628a2948f39cebff9a70389735a5dc182bf06;hb=HEAD;hp=694964051947c901c0937f1348ceec1966793052;hpb=fa54c2d93ba08c61e97b7e04d1bc0c132ad1d81d;p=cascardo%2Fovs.git diff --git a/datapath/flow.h b/datapath/flow.h index 694964051..c0b628a29 100644 --- a/datapath/flow.h +++ b/datapath/flow.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira, Inc. + * Copyright (c) 2007-2015 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 @@ -19,6 +19,7 @@ #ifndef FLOW_H #define FLOW_H 1 +#include #include #include #include @@ -31,69 +32,71 @@ #include #include #include +#include +#include struct sk_buff; -struct sw_flow_actions { - struct rcu_head rcu; - u32 actions_len; - struct nlattr actions[]; -}; +/* 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))) -/* Tunnel flow flags. */ -#define OVS_TNL_F_DONT_FRAGMENT (1 << 0) -#define OVS_TNL_F_CSUM (1 << 1) -#define OVS_TNL_F_KEY (1 << 2) - -/* Used to memset ovs_key_ipv4_tunnel padding. */ -#define OVS_TUNNEL_KEY_SIZE \ - (offsetof(struct ovs_key_ipv4_tunnel, ipv4_ttl) + \ - FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, ipv4_ttl)) - -struct ovs_key_ipv4_tunnel { - __be64 tun_id; - __be32 ipv4_src; - __be32 ipv4_dst; - u16 tun_flags; - u8 ipv4_tos; - u8 ipv4_ttl; +struct ovs_tunnel_info { + struct metadata_dst *tun_dst; }; +#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 { - struct ovs_key_ipv4_tunnel tun_key; /* Encapsulating tunnel key. */ + u8 tun_opts[255]; + u8 tun_opts_len; + struct ip_tunnel_key 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 { @@ -101,10 +104,6 @@ struct sw_flow_key { 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. */ @@ -112,21 +111,77 @@ struct sw_flow_key { } nd; } ipv6; }; + struct { + /* Connection tracking fields. */ + u16 zone; + u32 mark; + u8 state; + struct ovs_key_ct_labels labels; + } ct; + +} __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 { +struct sw_flow_mask { + int ref_count; struct rcu_head rcu; - struct hlist_node hash_node[2]; - u32 hash; + 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; +}; + +#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; + }; +}; + +struct sw_flow_actions { + struct rcu_head rcu; + size_t orig_len; /* From flow_cmd_new netlink actions size */ + 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 { + struct hlist_node node[2]; + u32 hash; + } flow_table, ufid_table; + int stats_last_writer; /* NUMA-node id of the last writer on + * 'stats[0]'. + */ struct sw_flow_key key; + struct sw_flow_id id; + 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 { @@ -143,95 +198,31 @@ 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(int actions_len); -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 *); -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_TUNNEL 0 -- 4 4 - * - OVS_TUNNEL_KEY_ATTR_ID 8 -- 4 12 - * - OVS_TUNNEL_KEY_ATTR_IPV4_SRC 4 -- 4 8 - * - OVS_TUNNEL_KEY_ATTR_IPV4_DST 4 -- 4 8 - * - OVS_TUNNEL_KEY_ATTR_TOS 1 3 4 8 - * - OVS_TUNNEL_KEY_ATTR_TTL 1 3 4 8 - * - OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT 0 -- 4 4 - * - OVS_TUNNEL_KEY_ATTR_CSUM 0 -- 4 4 - * OVS_KEY_ATTR_IN_PORT 4 -- 4 8 - * OVS_KEY_ATTR_SKB_MARK 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 220 - */ -#define FLOW_BUFSIZE 220 - -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) +static inline bool ovs_identifier_is_ufid(const struct sw_flow_id *sfid) { - return table->count; + return sfid->ufid_len; } -static inline int ovs_flow_tbl_need_to_expand(struct flow_table *table) +static inline bool ovs_identifier_is_key(const struct sw_flow_id *sfid) { - return (table->count > table->n_buckets); + return !ovs_identifier_is_ufid(sfid); } -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]; -int ipv4_tun_from_nlattr(const struct nlattr *attr, - struct ovs_key_ipv4_tunnel *tun_key); -int ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ovs_key_ipv4_tunnel *tun_key); +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); + +/* 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 ip_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(struct net *net, const struct nlattr *attr, + struct sk_buff *skb, + struct sw_flow_key *key, bool log); #endif /* flow.h */