Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/jesse/openvswitch

Jesse Gross says:

====================
Open vSwitch

A set of updates for net-next/3.13. Major changes are:
 * Restructure flow handling code to be more logically organized and
   easier to read.
 * Rehashing of the flow table is moved from a workqueue to flow
   installation time. Before, heavy load could block the workqueue for
   excessive periods of time.
 * Additional debugging information is provided to help diagnose megaflows.
 * It's now possible to match on TCP flags.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/uapi/linux/openvswitch.h

@@ -63,6 +63,8 @@ enum ovs_datapath_cmd {
  * not be sent.
  * @OVS_DP_ATTR_STATS: Statistics about packets that have passed through the
  * datapath.  Always present in notifications.
+ * @OVS_DP_ATTR_MEGAFLOW_STATS: Statistics about mega flow masks usage for the
+ * datapath. Always present in notifications.
  *
  * These attributes follow the &struct ovs_header within the Generic Netlink
  * payload for %OVS_DP_* commands.
@@ -72,6 +74,7 @@ enum ovs_datapath_attr {
 	OVS_DP_ATTR_NAME,		/* name of dp_ifindex netdev */
 	OVS_DP_ATTR_UPCALL_PID,		/* Netlink PID to receive upcalls */
 	OVS_DP_ATTR_STATS,		/* struct ovs_dp_stats */
+	OVS_DP_ATTR_MEGAFLOW_STATS,	/* struct ovs_dp_megaflow_stats */
 	__OVS_DP_ATTR_MAX
 };
 
@@ -84,6 +87,14 @@ struct ovs_dp_stats {
 	__u64 n_flows;           /* Number of flows present */
 };
 
+struct ovs_dp_megaflow_stats {
+	__u64 n_mask_hit;	 /* Number of masks used for flow lookups. */
+	__u32 n_masks;		 /* Number of masks for the datapath. */
+	__u32 pad0;		 /* Pad for future expension. */
+	__u64 pad1;		 /* Pad for future expension. */
+	__u64 pad2;		 /* Pad for future expension. */
+};
+
 struct ovs_vport_stats {
 	__u64   rx_packets;		/* total packets received       */
 	__u64   tx_packets;		/* total packets transmitted    */
@@ -260,6 +271,7 @@ enum ovs_key_attr {
 	OVS_KEY_ATTR_SKB_MARK,  /* u32 skb mark */
 	OVS_KEY_ATTR_TUNNEL,    /* Nested set of ovs_tunnel attributes */
 	OVS_KEY_ATTR_SCTP,      /* struct ovs_key_sctp */
+	OVS_KEY_ATTR_TCP_FLAGS,	/* be16 TCP flags. */
 
 #ifdef __KERNEL__
 	OVS_KEY_ATTR_IPV4_TUNNEL,  /* struct ovs_key_ipv4_tunnel */

net/openvswitch/Makefile

@@ -9,6 +9,8 @@ openvswitch-y := \
 	datapath.o \
 	dp_notify.o \
 	flow.o \
+	flow_netlink.o \
+	flow_table.o \
 	vport.o \
 	vport-internal_dev.o \
 	vport-netdev.o

net/openvswitch/datapath.h

@@ -27,6 +27,7 @@
 #include <linux/u64_stats_sync.h>
 
 #include "flow.h"
+#include "flow_table.h"
 #include "vport.h"
 
 #define DP_MAX_PORTS           USHRT_MAX
@@ -45,11 +46,15 @@
  * @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).
+ * @n_mask_hit: Number of masks looked up for flow match.
+ *   @n_mask_hit / (@n_hit + @n_missed)  will be the average masks looked
+ *   up per packet.
  */
 struct dp_stats_percpu {
 	u64 n_hit;
 	u64 n_missed;
 	u64 n_lost;
+	u64 n_mask_hit;
 	struct u64_stats_sync sync;
 };
 
@@ -57,7 +62,7 @@ struct dp_stats_percpu {
  * struct datapath - datapath for flow-based packet switching
  * @rcu: RCU callback head for deferred destruction.
  * @list_node: Element in global 'dps' list.
- * @table: Current flow table.  Protected by ovs_mutex and RCU.
+ * @table: flow table.
  * @ports: Hash table for ports.  %OVSP_LOCAL port always exists.  Protected by
  * ovs_mutex and RCU.
  * @stats_percpu: Per-CPU datapath statistics.
@@ -71,7 +76,7 @@ struct datapath {
 	struct list_head list_node;
 
 	/* Flow table. */
-	struct flow_table __rcu *table;
+	struct flow_table table;
 
 	/* Switch ports. */
 	struct hlist_head *ports;

net/openvswitch/flow.h

@@ -33,14 +33,6 @@
 #include <net/inet_ecn.h>
 
 struct sk_buff;
-struct sw_flow_mask;
-struct flow_table;
-
-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					\
@@ -101,6 +93,7 @@ struct sw_flow_key {
 				struct {
 					__be16 src;		/* TCP/UDP/SCTP source port. */
 					__be16 dst;		/* TCP/UDP/SCTP destination port. */
+					__be16 flags;		/* TCP flags. */
 				} tp;
 				struct {
 					u8 sha[ETH_ALEN];	/* ARP source hardware address. */
@@ -117,6 +110,7 @@ struct sw_flow_key {
 			struct {
 				__be16 src;		/* TCP/UDP/SCTP source port. */
 				__be16 dst;		/* TCP/UDP/SCTP destination port. */
+				__be16 flags;		/* TCP flags. */
 			} tp;
 			struct {
 				struct in6_addr target;	/* ND target address. */
@@ -127,6 +121,31 @@ struct sw_flow_key {
 	};
 } __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */
 
+struct sw_flow_key_range {
+	size_t start;
+	size_t end;
+};
+
+struct sw_flow_mask {
+	int ref_count;
+	struct rcu_head rcu;
+	struct list_head list;
+	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 {
 	struct rcu_head rcu;
 	struct hlist_node hash_node[2];
@@ -141,23 +160,9 @@ struct sw_flow {
 	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 sw_flow_key_range {
-	size_t start;
-	size_t end;
+	__be16 tcp_flags;	/* Union of seen TCP flags. */
 };
 
-struct sw_flow_match {
-	struct sw_flow_key *key;
-	struct sw_flow_key_range range;
-	struct sw_flow_mask *mask;
-};
-
-void ovs_match_init(struct sw_flow_match *match,
-		struct sw_flow_key *key, struct sw_flow_mask *mask);
-
 struct arp_eth_header {
 	__be16      ar_hrd;	/* format of hardware address   */
 	__be16      ar_pro;	/* format of protocol address   */
@@ -172,88 +177,9 @@ 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 *, bool deferred);
-
-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 *);
 void ovs_flow_used(struct sw_flow *, struct sk_buff *);
 u64 ovs_flow_used_time(unsigned long flow_jiffies);
-int ovs_flow_to_nlattrs(const struct sw_flow_key *,
-		const struct sw_flow_key *, struct sk_buff *);
-int ovs_match_from_nlattrs(struct sw_flow_match *match,
-		      const struct nlattr *,
-		      const struct nlattr *);
-int ovs_flow_metadata_from_nlattrs(struct sw_flow *flow,
-		const struct nlattr *attr);
 
-#define MAX_ACTIONS_BUFSIZE    (32 * 1024)
-#define TBL_MIN_BUCKETS		1024
-
-struct flow_table {
-	struct flex_array *buckets;
-	unsigned int count, n_buckets;
-	struct rcu_head rcu;
-	struct list_head *mask_list;
-	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_lookup(struct flow_table *,
-				const struct sw_flow_key *);
-struct sw_flow *ovs_flow_lookup_unmasked_key(struct flow_table *table,
-				    struct sw_flow_match *match);
-
-void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred);
-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_insert(struct flow_table *table, struct sw_flow *flow);
-void ovs_flow_remove(struct flow_table *table, struct sw_flow *flow);
-
-struct sw_flow *ovs_flow_dump_next(struct flow_table *table, u32 *bucket, u32 *idx);
-extern const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1];
-int ovs_ipv4_tun_from_nlattr(const struct nlattr *attr,
-			     struct sw_flow_match *match, bool is_mask);
-int ovs_ipv4_tun_to_nlattr(struct sk_buff *skb,
-			   const struct ovs_key_ipv4_tunnel *tun_key,
-			   const struct ovs_key_ipv4_tunnel *output);
-
-bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
-		const struct sw_flow_key *key, int key_end);
-
-struct sw_flow_mask {
-	int ref_count;
-	struct rcu_head rcu;
-	struct list_head list;
-	struct sw_flow_key_range range;
-	struct sw_flow_key key;
-};
+int ovs_flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *);
 
-struct sw_flow_mask *ovs_sw_flow_mask_alloc(void);
-void ovs_sw_flow_mask_add_ref(struct sw_flow_mask *);
-void ovs_sw_flow_mask_del_ref(struct sw_flow_mask *, bool deferred);
-void ovs_sw_flow_mask_insert(struct flow_table *, struct sw_flow_mask *);
-struct sw_flow_mask *ovs_sw_flow_mask_find(const struct flow_table *,
-		const struct sw_flow_mask *);
-void ovs_flow_key_mask(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask);
 #endif /* flow.h */

net/openvswitch/flow_netlink.h

+/*
+ * Copyright (c) 2007-2013 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
+ * 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_NETLINK_H
+#define FLOW_NETLINK_H 1
+
+#include <linux/kernel.h>
+#include <linux/netlink.h>
+#include <linux/openvswitch.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
+#include <linux/jiffies.h>
+#include <linux/time.h>
+#include <linux/flex_array.h>
+
+#include <net/inet_ecn.h>
+#include <net/ip_tunnels.h>
+
+#include "flow.h"
+
+void ovs_match_init(struct sw_flow_match *match,
+		    struct sw_flow_key *key, struct sw_flow_mask *mask);
+
+int ovs_nla_put_flow(const struct sw_flow_key *,
+		     const struct sw_flow_key *, struct sk_buff *);
+int ovs_nla_get_flow_metadata(struct sw_flow *flow,
+			      const struct nlattr *attr);
+int ovs_nla_get_match(struct sw_flow_match *match,
+		      const struct nlattr *,
+		      const struct nlattr *);
+
+int ovs_nla_copy_actions(const struct nlattr *attr,
+			 const struct sw_flow_key *key, int depth,
+			 struct sw_flow_actions **sfa);
+int ovs_nla_put_actions(const struct nlattr *attr,
+			int len, struct sk_buff *skb);
+
+struct sw_flow_actions *ovs_nla_alloc_flow_actions(int actions_len);
+void ovs_nla_free_flow_actions(struct sw_flow_actions *);
+
+#endif /* flow_netlink.h */

net/openvswitch/flow_table.h

+/*
+ * Copyright (c) 2007-2013 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
+ * 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_TABLE_H
+#define FLOW_TABLE_H 1
+
+#include <linux/kernel.h>
+#include <linux/netlink.h>
+#include <linux/openvswitch.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
+#include <linux/jiffies.h>
+#include <linux/time.h>
+#include <linux/flex_array.h>
+
+#include <net/inet_ecn.h>
+#include <net/ip_tunnels.h>
+
+#include "flow.h"
+
+struct table_instance {
+	struct flex_array *buckets;
+	unsigned int n_buckets;
+	struct rcu_head rcu;
+	int node_ver;
+	u32 hash_seed;
+	bool keep_flows;
+};
+
+struct flow_table {
+	struct table_instance __rcu *ti;
+	struct list_head mask_list;
+	unsigned long last_rehash;
+	unsigned int count;
+};
+
+int ovs_flow_init(void);
+void ovs_flow_exit(void);
+
+struct sw_flow *ovs_flow_alloc(void);
+void ovs_flow_free(struct sw_flow *, bool deferred);
+
+int ovs_flow_tbl_init(struct flow_table *);
+int ovs_flow_tbl_count(struct flow_table *table);
+void ovs_flow_tbl_destroy(struct flow_table *table);
+int ovs_flow_tbl_flush(struct flow_table *flow_table);
+
+int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
+			struct sw_flow_mask *mask);
+void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow);
+int  ovs_flow_tbl_num_masks(const struct flow_table *table);
+struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *table,
+				       u32 *bucket, u32 *idx);
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
+				    const struct sw_flow_key *,
+				    u32 *n_mask_hit);
+
+bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
+			       struct sw_flow_match *match);
+
+void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
+		       const struct sw_flow_mask *mask);
+#endif /* flow_table.h */

net/openvswitch/vport-gre.c

@@ -24,8 +24,6 @@
 #include <linux/if_tunnel.h>
 #include <linux/if_vlan.h>
 #include <linux/in.h>
-#include <linux/if_vlan.h>
-#include <linux/in.h>
 #include <linux/in_route.h>
 #include <linux/inetdevice.h>
 #include <linux/jhash.h>

net/openvswitch/vport-internal_dev.c

@@ -134,7 +134,7 @@ static void do_setup(struct net_device *netdev)
 	netdev->tx_queue_len = 0;
 
 	netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST |
-			   NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | NETIF_F_TSO;
+			   NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE;
 
 	netdev->vlan_features = netdev->features;
 	netdev->features |= NETIF_F_HW_VLAN_CTAG_TX;

net/openvswitch/vport-vxlan.c

@@ -29,7 +29,6 @@
 #include <net/ip.h>
 #include <net/udp.h>
 #include <net/ip_tunnels.h>
-#include <net/udp.h>
 #include <net/rtnetlink.h>
 #include <net/route.h>
 #include <net/dsfield.h>