/*
- * Copyright (c) 2009 Nicira Networks.
+ * Copyright (c) 2009, 2010, 2011 Nicira Networks.
* Distributed under the terms of the GNU GPL version 2.
*
* Significant portions of this file may be copied from parts of the Linux
#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/seqlock.h>
#include <linux/skbuff.h>
+#include <linux/version.h>
+
+#include "checksum.h"
#include "flow.h"
-#include "brc_sysfs.h"
+#include "dp_sysfs.h"
+
+struct vport;
/* 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
-
+#define VLAN_PCP_SHIFT 13
+
+#define DP_MAX_PORTS 1024
+
+/**
+ * struct dp_stats_percpu - per-cpu packet processing statistics for a given
+ * datapath.
+ * @n_frags: Number of IP fragments processed by 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;
+ seqcount_t seqlock;
};
-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.
+ * @dp_ifindex: ifindex of local port.
+ * @list_node: Element in global 'dps' list.
+ * @ifobj: Represents /sys/class/net/<devname>/brif. Protected by RTNL.
+ * @drop_frags: Drop all IP fragments if nonzero.
+ * @n_flows: Number of flows currently in flow table.
+ * @table: Current flow table. Protected by genl_lock and RCU.
+ * @ports: Map from port number to &struct vport. %ODPP_LOCAL port
+ * always exists, other ports may be %NULL. Protected by RTNL and RCU.
+ * @port_list: List of all ports in @ports in arbitrary order. RTNL required
+ * to iterate or modify.
+ * @stats_percpu: Per-CPU datapath statistics.
+ * @sflow_probability: Number of packets out of UINT_MAX to sample to the
+ * %ODP_PACKET_CMD_SAMPLE multicast group, e.g. (@sflow_probability/UINT_MAX)
+ * is the probability of sampling a given packet.
+ *
+ * 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 SUPPORT_SYSFS
+ struct rcu_head rcu;
+ int dp_ifindex;
+ struct list_head list_node;
struct kobject ifobj;
-#endif
int drop_frags;
- /* Queued data. */
- struct sk_buff_head queues[DP_N_QUEUES];
- wait_queue_head_t waitqueue;
-
/* Flow table. */
- unsigned int n_flows;
- struct dp_table *table;
-
- /* Port groups. */
- struct dp_port_group *groups[DP_MAX_GROUPS];
+ struct tbl __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 vport __rcu *ports[DP_MAX_PORTS];
+ struct list_head port_list;
/* Stats. */
- struct dp_stats_percpu *stats_percpu;
+ struct dp_stats_percpu __percpu *stats_percpu;
+
+ /* sFlow Sampling */
+ unsigned int sflow_probability;
};
-struct net_bridge_port {
- u16 port_no;
- struct datapath *dp;
- struct net_device *dev;
-#ifdef SUPPORT_SYSFS
- struct kobject kobj;
+/**
+ * struct ovs_skb_cb - OVS data in skb CB
+ * @vport: The datapath port on which the skb entered the switch.
+ * @flow: The flow associated with this packet. May be %NULL if no flow.
+ * @ip_summed: Consistently stores L4 checksumming status across different
+ * kernel versions.
+ * @tun_id: ID of the tunnel that encapsulated this packet. It is 0 if the
+ * packet was not received on a tunnel.
+ */
+struct ovs_skb_cb {
+ struct vport *vport;
+ struct sw_flow *flow;
+#ifdef NEED_CSUM_NORMALIZE
+ enum csum_type ip_summed;
#endif
- struct list_head node; /* Element in datapath.ports. */
+ __be64 tun_id;
+};
+#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 %ODP_PACKET_CMD_*.
+ * @key: Becomes %ODP_PACKET_ATTR_KEY. Must be nonnull.
+ * @userdata: Becomes %ODP_PACKET_ATTR_USERDATA if nonzero.
+ * @sample_pool: Becomes %ODP_PACKET_ATTR_SAMPLE_POOL if nonzero.
+ * @actions: Becomes %ODP_PACKET_ATTR_ACTIONS if nonnull.
+ * @actions_len: Number of bytes in @actions.
+*/
+struct dp_upcall_info {
+ u8 cmd;
+ const struct sw_flow_key *key;
+ u64 userdata;
+ u32 sample_pool;
+ const struct nlattr *actions;
+ u32 actions_len;
};
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);
+
+void dp_process_received_packet(struct vport *, struct sk_buff *);
+int dp_detach_port(struct vport *);
+int dp_upcall(struct datapath *, struct sk_buff *, const struct dp_upcall_info *);
int dp_min_mtu(const struct datapath *dp);
+void set_internal_devs_mtu(const struct datapath *dp);
struct datapath *get_dp(int dp_idx);
-
-static inline const char *dp_name(const struct datapath *dp)
-{
- return dp->ports[ODPP_LOCAL]->dev->name;
-}
-
-#ifdef CONFIG_XEN
-int skb_checksum_setup(struct sk_buff *skb);
-#else
-static inline int skb_checksum_setup(struct sk_buff *skb)
-{
- return 0;
-}
-#endif
+const char *dp_name(const struct datapath *dp);
#endif /* datapath.h */