1 files changed, 138 insertions, 38 deletions

diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index d830a95f03a4..53001b020ca7 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2012 Nicira, Inc.
+ * Copyright (c) 2007-2014 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
@@ -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[] = {
@@ -45,6 +48,9 @@ static const struct vport_ops *vport_ops_list[] = {
 #ifdef CONFIG_OPENVSWITCH_VXLAN
 	&ovs_vxlan_vport_ops,
 #endif
+#ifdef CONFIG_OPENVSWITCH_GENEVE
+	&ovs_geneve_vport_ops,
+#endif
 };
 
 /* Protected by RCU read lock for reading, ovs_mutex for writing. */
@@ -118,7 +124,6 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
 {
 	struct vport *vport;
 	size_t alloc_size;
-	int i;
 
 	alloc_size = sizeof(struct vport);
 	if (priv_size) {
@@ -132,25 +137,20 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
 
 	vport->dp = parms->dp;
 	vport->port_no = parms->port_no;
-	vport->upcall_portid = parms->upcall_portid;
 	vport->ops = ops;
 	INIT_HLIST_NODE(&vport->dp_hash_node);
 
-	vport->percpu_stats = alloc_percpu(struct pcpu_tstats);
-	if (!vport->percpu_stats) {
+	if (ovs_vport_set_upcall_portids(vport, parms->upcall_portids)) {
 		kfree(vport);
-		return ERR_PTR(-ENOMEM);
+		return ERR_PTR(-EINVAL);
 	}
 
-	for_each_possible_cpu(i) {
-		struct pcpu_tstats *vport_stats;
-		vport_stats = per_cpu_ptr(vport->percpu_stats, i);
-		u64_stats_init(&vport_stats->syncp);
+	vport->percpu_stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!vport->percpu_stats) {
+		kfree(vport);
+		return ERR_PTR(-ENOMEM);
 	}
 
-
-	spin_lock_init(&vport->stats_lock);
-
 	return vport;
 }
 
@@ -166,6 +166,10 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
  */
 void ovs_vport_free(struct vport *vport)
 {
+	/* vport is freed from RCU callback or error path, Therefore
+	 * it is safe to use raw dereference.
+	 */
+	kfree(rcu_dereference_raw(vport->upcall_portids));
 	free_percpu(vport->percpu_stats);
 	kfree(vport);
 }
@@ -265,26 +269,22 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats)
 	 * netdev-stats can be directly read over netlink-ioctl.
 	 */
 
-	spin_lock_bh(&vport->stats_lock);
-
-	stats->rx_errors	= vport->err_stats.rx_errors;
-	stats->tx_errors	= vport->err_stats.tx_errors;
-	stats->tx_dropped	= vport->err_stats.tx_dropped;
-	stats->rx_dropped	= vport->err_stats.rx_dropped;
-
-	spin_unlock_bh(&vport->stats_lock);
+	stats->rx_errors  = atomic_long_read(&vport->err_stats.rx_errors);
+	stats->tx_errors  = atomic_long_read(&vport->err_stats.tx_errors);
+	stats->tx_dropped = atomic_long_read(&vport->err_stats.tx_dropped);
+	stats->rx_dropped = atomic_long_read(&vport->err_stats.rx_dropped);
 
 	for_each_possible_cpu(i) {
-		const struct pcpu_tstats *percpu_stats;
-		struct pcpu_tstats local_stats;
+		const struct pcpu_sw_netstats *percpu_stats;
+		struct pcpu_sw_netstats local_stats;
 		unsigned int start;
 
 		percpu_stats = per_cpu_ptr(vport->percpu_stats, i);
 
 		do {
-			start = u64_stats_fetch_begin_bh(&percpu_stats->syncp);
+			start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
 			local_stats = *percpu_stats;
-		} while (u64_stats_fetch_retry_bh(&percpu_stats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
 
 		stats->rx_bytes		+= local_stats.rx_bytes;
 		stats->rx_packets	+= local_stats.rx_packets;
@@ -332,6 +332,99 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
 }
 
 /**
+ *	ovs_vport_set_upcall_portids - set upcall portids of @vport.
+ *
+ * @vport: vport to modify.
+ * @ids: new configuration, an array of port ids.
+ *
+ * Sets the vport's upcall_portids to @ids.
+ *
+ * Returns 0 if successful, -EINVAL if @ids is zero length or cannot be parsed
+ * as an array of U32.
+ *
+ * Must be called with ovs_mutex.
+ */
+int ovs_vport_set_upcall_portids(struct vport *vport,  struct nlattr *ids)
+{
+	struct vport_portids *old, *vport_portids;
+
+	if (!nla_len(ids) || nla_len(ids) % sizeof(u32))
+		return -EINVAL;
+
+	old = ovsl_dereference(vport->upcall_portids);
+
+	vport_portids = kmalloc(sizeof(*vport_portids) + nla_len(ids),
+				GFP_KERNEL);
+	if (!vport_portids)
+		return -ENOMEM;
+
+	vport_portids->n_ids = nla_len(ids) / sizeof(u32);
+	vport_portids->rn_ids = reciprocal_value(vport_portids->n_ids);
+	nla_memcpy(vport_portids->ids, ids, nla_len(ids));
+
+	rcu_assign_pointer(vport->upcall_portids, vport_portids);
+
+	if (old)
+		kfree_rcu(old, rcu);
+	return 0;
+}
+
+/**
+ *	ovs_vport_get_upcall_portids - get the upcall_portids of @vport.
+ *
+ * @vport: vport from which to retrieve the portids.
+ * @skb: sk_buff where portids should be appended.
+ *
+ * Retrieves the configuration of the given vport, appending the
+ * %OVS_VPORT_ATTR_UPCALL_PID attribute which is the array of upcall
+ * portids to @skb.
+ *
+ * Returns 0 if successful, -EMSGSIZE if @skb has insufficient room.
+ * If an error occurs, @skb is left unmodified.  Must be called with
+ * ovs_mutex or rcu_read_lock.
+ */
+int ovs_vport_get_upcall_portids(const struct vport *vport,
+				 struct sk_buff *skb)
+{
+	struct vport_portids *ids;
+
+	ids = rcu_dereference_ovsl(vport->upcall_portids);
+
+	if (vport->dp->user_features & OVS_DP_F_VPORT_PIDS)
+		return nla_put(skb, OVS_VPORT_ATTR_UPCALL_PID,
+			       ids->n_ids * sizeof(u32), (void *)ids->ids);
+	else
+		return nla_put_u32(skb, OVS_VPORT_ATTR_UPCALL_PID, ids->ids[0]);
+}
+
+/**
+ *	ovs_vport_find_upcall_portid - find the upcall portid to send upcall.
+ *
+ * @vport: vport from which the missed packet is received.
+ * @skb: skb that the missed packet was received.
+ *
+ * Uses the skb_get_hash() to select the upcall portid to send the
+ * upcall.
+ *
+ * Returns the portid of the target socket.  Must be called with rcu_read_lock.
+ */
+u32 ovs_vport_find_upcall_portid(const struct vport *p, struct sk_buff *skb)
+{
+	struct vport_portids *ids;
+	u32 ids_index;
+	u32 hash;
+
+	ids = rcu_dereference(p->upcall_portids);
+
+	if (ids->n_ids == 1 && ids->ids[0] == 0)
+		return 0;
+
+	hash = skb_get_hash(skb);
+	ids_index = hash - ids->n_ids * reciprocal_divide(hash, ids->rn_ids);
+	return ids->ids[ids_index];
+}
+
+/**
  *	ovs_vport_receive - pass up received packet to the datapath for processing
  *
  * @vport: vport that received the packet
@@ -342,9 +435,11 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
  * skb->data should point to the Ethernet header.
  */
 void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
-		       struct ovs_key_ipv4_tunnel *tun_key)
+		       struct ovs_tunnel_info *tun_info)
 {
-	struct pcpu_tstats *stats;
+	struct pcpu_sw_netstats *stats;
+	struct sw_flow_key key;
+	int error;
 
 	stats = this_cpu_ptr(vport->percpu_stats);
 	u64_stats_update_begin(&stats->syncp);
@@ -352,8 +447,15 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
 	stats->rx_bytes += skb->len;
 	u64_stats_update_end(&stats->syncp);
 
-	OVS_CB(skb)->tun_key = tun_key;
-	ovs_dp_process_received_packet(vport, skb);
+	OVS_CB(skb)->input_vport = vport;
+	OVS_CB(skb)->egress_tun_info = NULL;
+	/* Extract flow from 'skb' into 'key'. */
+	error = ovs_flow_key_extract(tun_info, skb, &key);
+	if (unlikely(error)) {
+		kfree_skb(skb);
+		return;
+	}
+	ovs_dp_process_packet(skb, &key);
 }
 
 /**
@@ -370,7 +472,7 @@ int ovs_vport_send(struct vport *vport, struct sk_buff *skb)
 	int sent = vport->ops->send(vport, skb);
 
 	if (likely(sent > 0)) {
-		struct pcpu_tstats *stats;
+		struct pcpu_sw_netstats *stats;
 
 		stats = this_cpu_ptr(vport->percpu_stats);
 
@@ -396,29 +498,27 @@ 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);
-
 	switch (err_type) {
 	case VPORT_E_RX_DROPPED:
-		vport->err_stats.rx_dropped++;
+		atomic_long_inc(&vport->err_stats.rx_dropped);
 		break;
 
 	case VPORT_E_RX_ERROR:
-		vport->err_stats.rx_errors++;
+		atomic_long_inc(&vport->err_stats.rx_errors);
 		break;
 
 	case VPORT_E_TX_DROPPED:
-		vport->err_stats.tx_dropped++;
+		atomic_long_inc(&vport->err_stats.tx_dropped);
 		break;
 
 	case VPORT_E_TX_ERROR:
-		vport->err_stats.tx_errors++;
+		atomic_long_inc(&vport->err_stats.tx_errors);
 		break;
 	}
 
-	spin_unlock(&vport->stats_lock);
 }
 
 static void free_vport_rcu(struct rcu_head *rcu)