X-Git-Url: http://git.cascardo.eti.br/?a=blobdiff_plain;f=datapath%2Fflow.h;h=181f21bc323f9de2036b2350bf6609bb09680369;hb=de15b104940fe4c656d948026c8c9bd57c6a3f96;hp=b9af27224f948b9b954ea44afa29be7ab151a469;hpb=bad68a9965215511b305c59d7f1830344ec2241f;p=cascardo%2Fovs.git diff --git a/datapath/flow.h b/datapath/flow.h index b9af27224..181f21bc3 100644 --- a/datapath/flow.h +++ b/datapath/flow.h @@ -1,70 +1,235 @@ /* - * Copyright (c) 2009, 2010, 2011 Nicira Networks. - * Distributed under the terms of the GNU GPL version 2. + * Copyright (c) 2007-2014 Nicira, Inc. * - * Significant portions of this file may be copied from parts of the Linux - * kernel, by Linus Torvalds and others. + * 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 +#include #include #include +#include #include #include #include #include +#include #include #include - -#include "openvswitch/datapath-protocol.h" -#include "table.h" +#include +#include struct sk_buff; +/* 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). */ + } __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 { + __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; + struct { + u8 sha[ETH_ALEN]; /* ARP source hardware address. */ + u8 tha[ETH_ALEN]; /* ARP target hardware address. */ + } arp; + } ipv4; + struct { + struct { + struct in6_addr src; /* IPv6 source address. */ + struct in6_addr dst; /* IPv6 destination address. */ + } addr; + __be32 label; /* IPv6 flow label. */ + 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; + } 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 sw_flow_key { - __be64 tun_id; /* Encapsulating tunnel ID. */ - __be32 nw_src; /* IP source address. */ - __be32 nw_dst; /* IP destination address. */ - u16 in_port; /* Input switch port. */ - __be16 dl_tci; /* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */ - __be16 dl_type; /* Ethernet frame type. */ - __be16 tp_src; /* TCP/UDP source port. */ - __be16 tp_dst; /* TCP/UDP destination port. */ - u8 dl_src[ETH_ALEN]; /* Ethernet source address. */ - u8 dl_dst[ETH_ALEN]; /* Ethernet destination address. */ - u8 nw_proto; /* IP protocol or lower 8 bits of ARP opcode. */ - u8 nw_tos; /* IP ToS (DSCP field, 6 bits). */ - u8 arp_sha[ETH_ALEN]; /* ARP source hardware address. */ - u8 arp_tha[ETH_ALEN]; /* ARP target hardware address. */ +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 tbl_node tbl_node; - + 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; - - atomic_t refcnt; - bool dead; - - 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 -{ +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 */ @@ -78,37 +243,21 @@ struct arp_eth_header unsigned char ar_tip[4]; /* target IP address */ } __packed; -int flow_init(void); -void flow_exit(void); - -struct sw_flow *flow_alloc(void); -void flow_deferred_free(struct sw_flow *); -void flow_free_tbl(struct tbl_node *); - -struct sw_flow_actions *flow_actions_alloc(const struct nlattr *); -void flow_deferred_free_acts(struct sw_flow_actions *); - -void flow_hold(struct sw_flow *); -void flow_put(struct sw_flow *); - -int flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *, bool *is_frag); -void flow_used(struct sw_flow *, struct sk_buff *); -u64 flow_used_time(unsigned long flow_jiffies); - -u32 flow_hash(const struct sw_flow_key *); -int flow_cmp(const struct tbl_node *, void *target); +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); -/* By my calculations currently the longest valid nlattr-formatted flow key is - * 80 bytes long, so this leaves some safety margin. - */ -#define FLOW_BUFSIZE 96 - -int flow_to_nlattrs(const struct sw_flow_key *, struct sk_buff *); -int flow_from_nlattrs(struct sw_flow_key *swkey, const struct nlattr *); - -static inline struct sw_flow *flow_cast(const struct tbl_node *node) -{ - return container_of(node, struct sw_flow, tbl_node); -} +/* 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 */