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

Jesse Gross says:

====================
[GIT net-next] Open vSwitch

Open vSwitch changes for net-next/3.14. Highlights are:
 * Performance improvements in the mechanism to get packets to userspace
   using memory mapped netlink and skb zero copy where appropriate.
 * Per-cpu flow stats in situations where flows are likely to be shared
   across CPUs. Standard flow stats are used in other situations to save
   memory and allocation time.
 * A handful of code cleanups and rationalization.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

net/openvswitch/datapath.h

@@ -88,6 +88,8 @@ struct datapath {
 	/* Network namespace ref. */
 	struct net *net;
 #endif
+
+	u32 user_features;
 };
 
 /**
@@ -145,6 +147,8 @@ int lockdep_ovsl_is_held(void);
 #define ASSERT_OVSL()		WARN_ON(unlikely(!lockdep_ovsl_is_held()))
 #define ovsl_dereference(p)					\
 	rcu_dereference_protected(p, lockdep_ovsl_is_held())
+#define rcu_dereference_ovsl(p)					\
+	rcu_dereference_check(p, lockdep_ovsl_is_held())
 
 static inline struct net *ovs_dp_get_net(struct datapath *dp)
 {
@@ -178,14 +182,12 @@ static inline struct vport *ovs_vport_ovsl(const struct datapath *dp, int port_n
 
 extern struct notifier_block ovs_dp_device_notifier;
 extern struct genl_family dp_vport_genl_family;
-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 pid, u32 seq,
 					 u8 cmd);
 

net/openvswitch/flow.c

@@ -35,6 +35,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/sctp.h>
+#include <linux/smp.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/icmp.h>
@@ -60,10 +61,16 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies)
 
 #define TCP_FLAGS_BE16(tp) (*(__be16 *)&tcp_flag_word(tp) & htons(0x0FFF))
 
-void ovs_flow_used(struct sw_flow *flow, struct sk_buff *skb)
+void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb)
 {
+	struct flow_stats *stats;
 	__be16 tcp_flags = 0;
 
+	if (!flow->stats.is_percpu)
+		stats = flow->stats.stat;
+	else
+		stats = this_cpu_ptr(flow->stats.cpu_stats);
+
 	if ((flow->key.eth.type == htons(ETH_P_IP) ||
 	     flow->key.eth.type == htons(ETH_P_IPV6)) &&
 	    flow->key.ip.proto == IPPROTO_TCP &&
@@ -71,12 +78,87 @@ void ovs_flow_used(struct sw_flow *flow, struct sk_buff *skb)
 		tcp_flags = TCP_FLAGS_BE16(tcp_hdr(skb));
 	}
 
-	spin_lock(&flow->lock);
-	flow->used = jiffies;
-	flow->packet_count++;
-	flow->byte_count += skb->len;
-	flow->tcp_flags |= tcp_flags;
-	spin_unlock(&flow->lock);
+	spin_lock(&stats->lock);
+	stats->used = jiffies;
+	stats->packet_count++;
+	stats->byte_count += skb->len;
+	stats->tcp_flags |= tcp_flags;
+	spin_unlock(&stats->lock);
+}
+
+static void stats_read(struct flow_stats *stats,
+		       struct ovs_flow_stats *ovs_stats,
+		       unsigned long *used, __be16 *tcp_flags)
+{
+	spin_lock(&stats->lock);
+	if (time_after(stats->used, *used))
+		*used = stats->used;
+	*tcp_flags |= stats->tcp_flags;
+	ovs_stats->n_packets += stats->packet_count;
+	ovs_stats->n_bytes += stats->byte_count;
+	spin_unlock(&stats->lock);
+}
+
+void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats,
+			unsigned long *used, __be16 *tcp_flags)
+{
+	int cpu, cur_cpu;
+
+	*used = 0;
+	*tcp_flags = 0;
+	memset(ovs_stats, 0, sizeof(*ovs_stats));
+
+	if (!flow->stats.is_percpu) {
+		stats_read(flow->stats.stat, ovs_stats, used, tcp_flags);
+	} else {
+		cur_cpu = get_cpu();
+		for_each_possible_cpu(cpu) {
+			struct flow_stats *stats;
+
+			if (cpu == cur_cpu)
+				local_bh_disable();
+
+			stats = per_cpu_ptr(flow->stats.cpu_stats, cpu);
+			stats_read(stats, ovs_stats, used, tcp_flags);
+
+			if (cpu == cur_cpu)
+				local_bh_enable();
+		}
+		put_cpu();
+	}
+}
+
+static void stats_reset(struct flow_stats *stats)
+{
+	spin_lock(&stats->lock);
+	stats->used = 0;
+	stats->packet_count = 0;
+	stats->byte_count = 0;
+	stats->tcp_flags = 0;
+	spin_unlock(&stats->lock);
+}
+
+void ovs_flow_stats_clear(struct sw_flow *flow)
+{
+	int cpu, cur_cpu;
+
+	if (!flow->stats.is_percpu) {
+		stats_reset(flow->stats.stat);
+	} else {
+		cur_cpu = get_cpu();
+
+		for_each_possible_cpu(cpu) {
+
+			if (cpu == cur_cpu)
+				local_bh_disable();
+
+			stats_reset(per_cpu_ptr(flow->stats.cpu_stats, cpu));
+
+			if (cpu == cur_cpu)
+				local_bh_enable();
+		}
+		put_cpu();
+	}
 }
 
 static int check_header(struct sk_buff *skb, int len)

net/openvswitch/flow.h

@@ -19,6 +19,7 @@
 #ifndef FLOW_H
 #define FLOW_H 1
 
+#include <linux/cache.h>
 #include <linux/kernel.h>
 #include <linux/netlink.h>
 #include <linux/openvswitch.h>
@@ -122,8 +123,8 @@ 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;
+	unsigned short int start;
+	unsigned short int end;
 };
 
 struct sw_flow_mask {
@@ -146,6 +147,22 @@ struct sw_flow_actions {
 	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_stats {
+	bool is_percpu;
+	union {
+		struct flow_stats *stat;
+		struct flow_stats __percpu *cpu_stats;
+	};
+};
+
 struct sw_flow {
 	struct rcu_head rcu;
 	struct hlist_node hash_node[2];
@@ -155,12 +172,7 @@ struct sw_flow {
 	struct sw_flow_key unmasked_key;
 	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. */
-	__be16 tcp_flags;	/* Union of seen TCP flags. */
+	struct sw_flow_stats stats;
 };
 
 struct arp_eth_header {
@@ -177,7 +189,10 @@ struct arp_eth_header {
 	unsigned char       ar_tip[4];		/* target IP address        */
 } __packed;
 
-void ovs_flow_used(struct sw_flow *, struct sk_buff *);
+void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb);
+void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *stats,
+			unsigned long *used, __be16 *tcp_flags);
+void ovs_flow_stats_clear(struct sw_flow *flow);
 u64 ovs_flow_used_time(unsigned long flow_jiffies);
 
 int ovs_flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *);

net/openvswitch/flow_netlink.c

@@ -266,6 +266,20 @@ static bool is_all_zero(const u8 *fp, size_t size)
 	return true;
 }
 
+static bool is_all_set(const u8 *fp, size_t size)
+{
+	int i;
+
+	if (!fp)
+		return false;
+
+	for (i = 0; i < size; i++)
+		if (fp[i] != 0xff)
+			return false;
+
+	return true;
+}
+
 static int __parse_flow_nlattrs(const struct nlattr *attr,
 				const struct nlattr *a[],
 				u64 *attrsp, bool nz)
@@ -487,8 +501,9 @@ static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
 	return 0;
 }
 
-static int ovs_key_from_nlattrs(struct sw_flow_match *match,  u64 attrs,
-				const struct nlattr **a, bool is_mask)
+static int ovs_key_from_nlattrs(struct sw_flow_match *match,  bool *exact_5tuple,
+				u64 attrs, const struct nlattr **a,
+				bool is_mask)
 {
 	int err;
 	u64 orig_attrs = attrs;
@@ -545,6 +560,11 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  u64 attrs,
 		SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask);
 	}
 
+	if (is_mask && exact_5tuple) {
+		if (match->mask->key.eth.type != htons(0xffff))
+			*exact_5tuple = false;
+	}
+
 	if (attrs & (1 << OVS_KEY_ATTR_IPV4)) {
 		const struct ovs_key_ipv4 *ipv4_key;
 
@@ -567,6 +587,13 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  u64 attrs,
 		SW_FLOW_KEY_PUT(match, ipv4.addr.dst,
 				ipv4_key->ipv4_dst, is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_IPV4);
+
+		if (is_mask && exact_5tuple && *exact_5tuple) {
+			if (ipv4_key->ipv4_proto != 0xff ||
+			    ipv4_key->ipv4_src != htonl(0xffffffff) ||
+			    ipv4_key->ipv4_dst != htonl(0xffffffff))
+				*exact_5tuple = false;
+		}
 	}
 
 	if (attrs & (1 << OVS_KEY_ATTR_IPV6)) {
@@ -598,6 +625,13 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  u64 attrs,
 				is_mask);
 
 		attrs &= ~(1 << OVS_KEY_ATTR_IPV6);
+
+		if (is_mask && exact_5tuple && *exact_5tuple) {
+			if (ipv6_key->ipv6_proto != 0xff ||
+			    !is_all_set((u8 *)ipv6_key->ipv6_src, sizeof(match->key->ipv6.addr.src)) ||
+			    !is_all_set((u8 *)ipv6_key->ipv6_dst, sizeof(match->key->ipv6.addr.dst)))
+				*exact_5tuple = false;
+		}
 	}
 
 	if (attrs & (1 << OVS_KEY_ATTR_ARP)) {
@@ -640,6 +674,11 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  u64 attrs,
 					tcp_key->tcp_dst, is_mask);
 		}
 		attrs &= ~(1 << OVS_KEY_ATTR_TCP);
+
+		if (is_mask && exact_5tuple && *exact_5tuple &&
+		    (tcp_key->tcp_src != htons(0xffff) ||
+		     tcp_key->tcp_dst != htons(0xffff)))
+			*exact_5tuple = false;
 	}
 
 	if (attrs & (1 << OVS_KEY_ATTR_TCP_FLAGS)) {
@@ -671,6 +710,11 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  u64 attrs,
 					udp_key->udp_dst, is_mask);
 		}
 		attrs &= ~(1 << OVS_KEY_ATTR_UDP);
+
+		if (is_mask && exact_5tuple && *exact_5tuple &&
+		    (udp_key->udp_src != htons(0xffff) ||
+		     udp_key->udp_dst != htons(0xffff)))
+			*exact_5tuple = false;
 	}
 
 	if (attrs & (1 << OVS_KEY_ATTR_SCTP)) {
@@ -756,6 +800,7 @@ static void sw_flow_mask_set(struct sw_flow_mask *mask,
  * attribute specifies the mask field of the wildcarded flow.
  */
 int ovs_nla_get_match(struct sw_flow_match *match,
+		      bool *exact_5tuple,
 		      const struct nlattr *key,
 		      const struct nlattr *mask)
 {
@@ -803,10 +848,13 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 		}
 	}
 
-	err = ovs_key_from_nlattrs(match, key_attrs, a, false);
+	err = ovs_key_from_nlattrs(match, NULL, key_attrs, a, false);
 	if (err)
 		return err;
 
+	if (exact_5tuple)
+		*exact_5tuple = true;
+
 	if (mask) {
 		err = parse_flow_mask_nlattrs(mask, a, &mask_attrs);
 		if (err)
@@ -844,7 +892,7 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 			}
 		}
 
-		err = ovs_key_from_nlattrs(match, mask_attrs, a, true);
+		err = ovs_key_from_nlattrs(match, exact_5tuple, mask_attrs, a, true);
 		if (err)
 			return err;
 	} else {
@@ -1128,19 +1176,11 @@ struct sw_flow_actions *ovs_nla_alloc_flow_actions(int size)
 	return sfa;
 }
 
-/* RCU callback used by ovs_nla_free_flow_actions. */
-static void rcu_free_acts_callback(struct rcu_head *rcu)
-{
-	struct sw_flow_actions *sf_acts = container_of(rcu,
-			struct sw_flow_actions, rcu);
-	kfree(sf_acts);
-}
-
 /* Schedules 'sf_acts' to be freed after the next RCU grace period.
  * The caller must hold rcu_read_lock for this to be sensible. */
 void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
 {
-	call_rcu(&sf_acts->rcu, rcu_free_acts_callback);
+	kfree_rcu(sf_acts, rcu);
 }
 
 static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,

net/openvswitch/flow_netlink.h

@@ -45,6 +45,7 @@ int ovs_nla_put_flow(const struct sw_flow_key *,
 int ovs_nla_get_flow_metadata(struct sw_flow *flow,
 			      const struct nlattr *attr);
 int ovs_nla_get_match(struct sw_flow_match *match,
+		      bool *exact_5tuple,
 		      const struct nlattr *,
 		      const struct nlattr *);
 

net/openvswitch/flow_table.c

@@ -44,8 +44,6 @@
 #include <net/ipv6.h>
 #include <net/ndisc.h>
 
-#include "datapath.h"
-
 #define TBL_MIN_BUCKETS		1024
 #define REHASH_INTERVAL		(10 * 60 * HZ)
 
@@ -72,19 +70,42 @@ void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
 		*d++ = *s++ & *m++;
 }
 
-struct sw_flow *ovs_flow_alloc(void)
+struct sw_flow *ovs_flow_alloc(bool percpu_stats)
 {
 	struct sw_flow *flow;
+	int cpu;
 
 	flow = kmem_cache_alloc(flow_cache, GFP_KERNEL);
 	if (!flow)
 		return ERR_PTR(-ENOMEM);
 
-	spin_lock_init(&flow->lock);
 	flow->sf_acts = NULL;
 	flow->mask = NULL;
 
+	flow->stats.is_percpu = percpu_stats;
+
+	if (!percpu_stats) {
+		flow->stats.stat = kzalloc(sizeof(*flow->stats.stat), GFP_KERNEL);
+		if (!flow->stats.stat)
+			goto err;
+
+		spin_lock_init(&flow->stats.stat->lock);
+	} else {
+		flow->stats.cpu_stats = alloc_percpu(struct flow_stats);
+		if (!flow->stats.cpu_stats)
+			goto err;
+
+		for_each_possible_cpu(cpu) {
+			struct flow_stats *cpu_stats;
+
+			cpu_stats = per_cpu_ptr(flow->stats.cpu_stats, cpu);
+			spin_lock_init(&cpu_stats->lock);
+		}
+	}
 	return flow;
+err:
+	kfree(flow);
+	return ERR_PTR(-ENOMEM);
 }
 
 int ovs_flow_tbl_count(struct flow_table *table)
@@ -118,6 +139,10 @@ static struct flex_array *alloc_buckets(unsigned int n_buckets)
 static void flow_free(struct sw_flow *flow)
 {
 	kfree((struct sf_flow_acts __force *)flow->sf_acts);
+	if (flow->stats.is_percpu)
+		free_percpu(flow->stats.cpu_stats);
+	else
+		kfree(flow->stats.stat);
 	kmem_cache_free(flow_cache, flow);
 }
 
@@ -128,13 +153,6 @@ static void rcu_free_flow_callback(struct rcu_head *rcu)
 	flow_free(flow);
 }
 
-static void rcu_free_sw_flow_mask_cb(struct rcu_head *rcu)
-{
-	struct sw_flow_mask *mask = container_of(rcu, struct sw_flow_mask, rcu);
-
-	kfree(mask);
-}
-
 static void flow_mask_del_ref(struct sw_flow_mask *mask, bool deferred)
 {
 	if (!mask)
@@ -146,7 +164,7 @@ static void flow_mask_del_ref(struct sw_flow_mask *mask, bool deferred)
 	if (!mask->ref_count) {
 		list_del_rcu(&mask->list);
 		if (deferred)
-			call_rcu(&mask->rcu, rcu_free_sw_flow_mask_cb);
+			kfree_rcu(mask, rcu);
 		else
 			kfree(mask);
 	}
@@ -429,11 +447,11 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 	return NULL;
 }
 
-struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
+struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl,
 				    const struct sw_flow_key *key,
 				    u32 *n_mask_hit)
 {
-	struct table_instance *ti = rcu_dereference(tbl->ti);
+	struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
 	struct sw_flow_mask *mask;
 	struct sw_flow *flow;
 
@@ -447,6 +465,14 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
 	return NULL;
 }
 
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
+				    const struct sw_flow_key *key)
+{
+	u32 __always_unused n_mask_hit;
+
+	return ovs_flow_tbl_lookup_stats(tbl, key, &n_mask_hit);
+}
+
 int ovs_flow_tbl_num_masks(const struct flow_table *table)
 {
 	struct sw_flow_mask *mask;
@@ -514,11 +540,7 @@ static struct sw_flow_mask *flow_mask_find(const struct flow_table *tbl,
 	return NULL;
 }
 
-/**
- * add a new mask into the mask list.
- * The caller needs to make sure that 'mask' is not the same
- * as any masks that are already on the list.
- */
+/* Add 'mask' into the mask list, if it is not already there. */
 static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
 			    struct sw_flow_mask *new)
 {

net/openvswitch/flow_table.h

@@ -55,7 +55,7 @@ struct flow_table {
 int ovs_flow_init(void);
 void ovs_flow_exit(void);
 
-struct sw_flow *ovs_flow_alloc(void);
+struct sw_flow *ovs_flow_alloc(bool percpu_stats);
 void ovs_flow_free(struct sw_flow *, bool deferred);
 
 int ovs_flow_tbl_init(struct flow_table *);
@@ -69,9 +69,11 @@ 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 *,
+struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *,
 				    const struct sw_flow_key *,
 				    u32 *n_mask_hit);
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
+				    const struct sw_flow_key *);
 
 bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
 			       struct sw_flow_match *match);

net/openvswitch/vport.c

@@ -33,6 +33,9 @@
 #include "vport.h"
 #include "vport-internal_dev.h"
 
+static void ovs_vport_record_error(struct vport *,
+				   enum vport_err_type err_type);
+
 /* List of statically compiled vport implementations.  Don't forget to also
  * add yours to the list at the bottom of vport.h. */
 static const struct vport_ops *vport_ops_list[] = {
@@ -396,7 +399,8 @@ int ovs_vport_send(struct vport *vport, struct sk_buff *skb)
  * If using the vport generic stats layer indicate that an error of the given
  * type has occurred.
  */
-void ovs_vport_record_error(struct vport *vport, enum vport_err_type err_type)
+static void ovs_vport_record_error(struct vport *vport,
+				   enum vport_err_type err_type)
 {
 	spin_lock(&vport->stats_lock);
 

net/openvswitch/vport.h

@@ -192,7 +192,6 @@ static inline struct vport *vport_from_priv(const void *priv)
 
 void ovs_vport_receive(struct vport *, struct sk_buff *,
 		       struct ovs_key_ipv4_tunnel *);
-void ovs_vport_record_error(struct vport *, enum vport_err_type err_type);
 
 /* List of statically compiled vport implementations.  Don't forget to also
  * add yours to the list at the top of vport.c. */