/*
- * Copyright (c) 2009 Nicira Networks.
- * Distributed under the terms of the GNU GPL version 2.
+ * Copyright (c) 2007-2012 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
*/
-/* Interface exported by openvswitch_mod. */
-
#ifndef DATAPATH_H
#define DATAPATH_H 1
#include <asm/page.h>
#include <linux/kernel.h>
#include <linux/mutex.h>
-#include <linux/netlink.h>
#include <linux/netdevice.h>
-#include <linux/workqueue.h>
#include <linux/skbuff.h>
-#include <linux/version.h>
-#include "flow.h"
-#include "brc_sysfs.h"
-
-/* Mask for the priority bits in a vlan header. If we ever merge upstream
- * then this should go into include/linux/if_vlan.h. */
-#define VLAN_PCP_MASK 0xe000
-
-#define DP_MAX_PORTS 256
-#define DP_MAX_GROUPS 16
-
-#define DP_L2_BITS (PAGE_SHIFT - ilog2(sizeof(struct sw_flow*)))
-#define DP_L2_SIZE (1 << DP_L2_BITS)
-#define DP_L2_SHIFT 0
-
-#define DP_L1_BITS (PAGE_SHIFT - ilog2(sizeof(struct sw_flow**)))
-#define DP_L1_SIZE (1 << DP_L1_BITS)
-#define DP_L1_SHIFT DP_L2_BITS
-
-#define DP_MAX_BUCKETS (DP_L1_SIZE * DP_L2_SIZE)
-
-struct dp_table {
- unsigned int n_buckets;
- struct sw_flow ***flows[2];
- struct rcu_head rcu;
-};
-
-#define DP_N_QUEUES 2
-#define DP_MAX_QUEUE_LEN 100
+#include <linux/u64_stats_sync.h>
+#include "checksum.h"
+#include "compat.h"
+#include "flow.h"
+#include "tunnel.h"
+#include "vlan.h"
+#include "vport.h"
+
+#define DP_MAX_PORTS USHRT_MAX
+#define DP_VPORT_HASH_BUCKETS 1024
+
+#define SAMPLE_ACTION_DEPTH 3
+
+/**
+ * struct dp_stats_percpu - per-cpu packet processing statistics for a given
+ * datapath.
+ * @n_hit: Number of received packets for which a matching flow was found in
+ * the flow table.
+ * @n_miss: Number of received packets that had no matching flow in the flow
+ * table. The sum of @n_hit and @n_miss is the number of packets that have
+ * been received by the datapath.
+ * @n_lost: Number of received packets that had no matching flow in the flow
+ * table that could not be sent to userspace (normally due to an overflow in
+ * one of the datapath's queues).
+ */
struct dp_stats_percpu {
- u64 n_frags;
u64 n_hit;
u64 n_missed;
u64 n_lost;
+ struct u64_stats_sync sync;
};
-struct dp_port_group {
- struct rcu_head rcu;
- int n_ports;
- u16 ports[];
-};
-
+/**
+ * struct datapath - datapath for flow-based packet switching
+ * @rcu: RCU callback head for deferred destruction.
+ * @list_node: Element in global 'dps' list.
+ * @n_flows: Number of flows currently in flow table.
+ * @table: Current flow table. Protected by genl_lock and RCU.
+ * @ports: Hash table for ports. %OVSP_LOCAL port always exists. Protected by
+ * RTNL and RCU.
+ * @stats_percpu: Per-CPU datapath statistics.
+ * @net: Reference to net namespace.
+ *
+ * Context: See the comment on locking at the top of datapath.c for additional
+ * locking information.
+ */
struct datapath {
- struct mutex mutex;
- int dp_idx;
-
-#ifdef CONFIG_SYSFS
-#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,25)
- struct kobject ifobj;
-#else
- struct kobject *ifobj;
-#endif
-#endif
-
- int drop_frags;
-
- /* Queued data. */
- struct sk_buff_head queues[DP_N_QUEUES];
- wait_queue_head_t waitqueue;
+ struct rcu_head rcu;
+ struct list_head list_node;
/* Flow table. */
- unsigned int n_flows;
- struct dp_table *table;
-
- /* Port groups. */
- struct dp_port_group *groups[DP_MAX_GROUPS];
+ struct flow_table __rcu *table;
/* Switch ports. */
- unsigned int n_ports;
- struct net_bridge_port *ports[DP_MAX_PORTS];
- struct list_head port_list; /* All ports, including local_port. */
+ struct hlist_head *ports;
/* Stats. */
- struct dp_stats_percpu *stats_percpu;
+ struct dp_stats_percpu __percpu *stats_percpu;
+
+#ifdef CONFIG_NET_NS
+ /* Network namespace ref. */
+ struct net *net;
+#endif
};
-struct net_bridge_port {
- u16 port_no;
- struct datapath *dp;
- struct net_device *dev;
-#ifdef CONFIG_SYSFS
- struct kobject kobj;
+/**
+ * struct ovs_skb_cb - OVS data in skb CB
+ * @flow: The flow associated with this packet. May be %NULL if no flow.
+ * @tun_key: Key for the tunnel that encapsulated this packet. NULL if the
+ * packet is not being tunneled.
+ * @ip_summed: Consistently stores L4 checksumming status across different
+ * kernel versions.
+ * @csum_start: Stores the offset from which to start checksumming independent
+ * of the transport header on all kernel versions.
+ * packet was not received on a tunnel.
+ * @vlan_tci: Provides a substitute for the skb->vlan_tci field on kernels
+ * before 2.6.27.
+ */
+struct ovs_skb_cb {
+ struct sw_flow *flow;
+ struct ovs_key_ipv4_tunnel *tun_key;
+#ifdef NEED_CSUM_NORMALIZE
+ enum csum_type ip_summed;
+ u16 csum_start;
+#endif
+#ifdef NEED_VLAN_FIELD
+ u16 vlan_tci;
#endif
- struct list_head node; /* Element in datapath.ports. */
};
+#define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
+
+/**
+ * struct dp_upcall - metadata to include with a packet to send to userspace
+ * @cmd: One of %OVS_PACKET_CMD_*.
+ * @key: Becomes %OVS_PACKET_ATTR_KEY. Must be nonnull.
+ * @userdata: If nonnull, its u64 value is extracted and passed to userspace as
+ * %OVS_PACKET_ATTR_USERDATA.
+ * @portid: Netlink PID to which packet should be sent. If @portid is 0 then no
+ * packet is sent and the packet is accounted in the datapath's @n_lost
+ * counter.
+ */
+struct dp_upcall_info {
+ u8 cmd;
+ const struct sw_flow_key *key;
+ const struct nlattr *userdata;
+ u32 portid;
+};
+
+/**
+ * struct ovs_net - Per net-namespace data for ovs.
+ * @dps: List of datapaths to enable dumping them all out.
+ * Protected by genl_mutex.
+ * @vport_net: Per network namespace data for vport.
+ */
+struct ovs_net {
+ struct list_head dps;
+ struct vport_net vport_net;
+};
+
+extern int ovs_net_id;
-extern struct notifier_block dp_device_notifier;
-extern int (*dp_ioctl_hook)(struct net_device *dev, struct ifreq *rq, int cmd);
-extern int (*dp_add_dp_hook)(struct datapath *dp);
-extern int (*dp_del_dp_hook)(struct datapath *dp);
-extern int (*dp_add_if_hook)(struct net_bridge_port *p);
-extern int (*dp_del_if_hook)(struct net_bridge_port *p);
-
-/* Flow table. */
-struct dp_table *dp_table_create(unsigned int n_buckets);
-void dp_table_destroy(struct dp_table *, int free_flows);
-struct sw_flow *dp_table_lookup(struct dp_table *, const struct odp_flow_key *);
-struct sw_flow **dp_table_lookup_for_insert(struct dp_table *, const struct odp_flow_key *);
-int dp_table_delete(struct dp_table *, struct sw_flow *);
-int dp_table_expand(struct datapath *);
-int dp_table_flush(struct datapath *);
-int dp_table_foreach(struct dp_table *table,
- int (*callback)(struct sw_flow *flow, void *aux),
- void *aux);
-
-void dp_process_received_packet(struct sk_buff *, struct net_bridge_port *);
-int dp_del_port(struct net_bridge_port *);
-int dp_output_control(struct datapath *, struct sk_buff *, int, u32 arg);
-
-struct datapath *get_dp(int dp_idx);
-
-static inline const char *dp_name(const struct datapath *dp)
+static inline struct net *ovs_dp_get_net(struct datapath *dp)
{
- return dp->ports[ODPP_LOCAL]->dev->name;
+ return read_pnet(&dp->net);
}
-#ifdef CONFIG_XEN
-int skb_checksum_setup(struct sk_buff *skb);
-#else
-static inline int skb_checksum_setup(struct sk_buff *skb)
+static inline void ovs_dp_set_net(struct datapath *dp, struct net *net)
{
- return 0;
+ write_pnet(&dp->net, net);
}
-#endif
-int vswitch_skb_checksum_setup(struct sk_buff *skb);
+struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no);
+
+static inline struct vport *ovs_vport_rcu(const struct datapath *dp, int port_no)
+{
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ return ovs_lookup_vport(dp, port_no);
+}
+
+static inline struct vport *ovs_vport_rtnl_rcu(const struct datapath *dp, int port_no)
+{
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rtnl_is_locked());
+ return ovs_lookup_vport(dp, port_no);
+}
+
+static inline struct vport *ovs_vport_rtnl(const struct datapath *dp, int port_no)
+{
+ ASSERT_RTNL();
+ return ovs_lookup_vport(dp, port_no);
+}
+
+extern struct notifier_block ovs_dp_device_notifier;
+extern struct genl_multicast_group ovs_dp_vport_multicast_group;
+
+void ovs_dp_process_received_packet(struct vport *, struct sk_buff *);
+void ovs_dp_detach_port(struct vport *);
+int ovs_dp_upcall(struct datapath *, struct sk_buff *,
+ const struct dp_upcall_info *);
+
+const char *ovs_dp_name(const struct datapath *dp);
+struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 portid, u32 seq,
+ u8 cmd);
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb);
#endif /* datapath.h */
git://git.onelab.eu / sliver-openvswitch.git / blobdiff