6 files changed, 89 insertions, 104 deletions
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index df4692826ead..a3276e3c4feb 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -55,6 +55,7 @@
 
 #include "datapath.h"
 #include "flow.h"
+#include "flow_table.h"
 #include "flow_netlink.h"
 #include "vport-internal_dev.h"
 #include "vport-netdev.h"
@@ -160,7 +161,6 @@ static void destroy_dp_rcu(struct rcu_head *rcu)
 {
 	struct datapath *dp = container_of(rcu, struct datapath, rcu);
 
-	ovs_flow_tbl_destroy(&dp->table);
 	free_percpu(dp->stats_percpu);
 	release_net(ovs_dp_get_net(dp));
 	kfree(dp->ports);
@@ -256,10 +256,10 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb)
 
 out:
 	/* Update datapath statistics. */
-	u64_stats_update_begin(&stats->sync);
+	u64_stats_update_begin(&stats->syncp);
 	(*stats_counter)++;
 	stats->n_mask_hit += n_mask_hit;
-	u64_stats_update_end(&stats->sync);
+	u64_stats_update_end(&stats->syncp);
 }
 
 static struct genl_family dp_packet_genl_family = {
@@ -295,9 +295,9 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 err:
 	stats = this_cpu_ptr(dp->stats_percpu);
 
-	u64_stats_update_begin(&stats->sync);
+	u64_stats_update_begin(&stats->syncp);
 	stats->n_lost++;
-	u64_stats_update_end(&stats->sync);
+	u64_stats_update_end(&stats->syncp);
 
 	return err;
 }
@@ -464,12 +464,24 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	}
 	nla->nla_len = nla_attr_size(skb->len);
 
-	skb_zerocopy(user_skb, skb, skb->len, hlen);
+	err = skb_zerocopy(user_skb, skb, skb->len, hlen);
+	if (err)
+		goto out;
+
+	/* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */
+	if (!(dp->user_features & OVS_DP_F_UNALIGNED)) {
+		size_t plen = NLA_ALIGN(user_skb->len) - user_skb->len;
+
+		if (plen > 0)
+			memset(skb_put(user_skb, plen), 0, plen);
+	}
 
 	((struct nlmsghdr *) user_skb->data)->nlmsg_len = user_skb->len;
 
 	err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid);
 out:
+	if (err)
+		skb_tx_error(skb);
 	kfree_skb(nskb);
 	return err;
 }
@@ -598,9 +610,9 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
 		percpu_stats = per_cpu_ptr(dp->stats_percpu, i);
 
 		do {
-			start = u64_stats_fetch_begin_bh(&percpu_stats->sync);
+			start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
 			local_stats = *percpu_stats;
-		} while (u64_stats_fetch_retry_bh(&percpu_stats->sync, start));
+		} while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
 
 		stats->n_hit += local_stats.n_hit;
 		stats->n_missed += local_stats.n_missed;
@@ -852,11 +864,8 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
 			goto err_unlock_ovs;
 
 		/* The unmasked key has to be the same for flow updates. */
-		error = -EINVAL;
-		if (!ovs_flow_cmp_unmasked_key(flow, &match)) {
-			OVS_NLERR("Flow modification message rejected, unmasked key does not match.\n");
+		if (!ovs_flow_cmp_unmasked_key(flow, &match))
 			goto err_unlock_ovs;
-		}
 
 		/* Update actions. */
 		old_acts = ovsl_dereference(flow->sf_acts);
@@ -1079,6 +1088,7 @@ static size_t ovs_dp_cmd_msg_size(void)
 	msgsize += nla_total_size(IFNAMSIZ);
 	msgsize += nla_total_size(sizeof(struct ovs_dp_stats));
 	msgsize += nla_total_size(sizeof(struct ovs_dp_megaflow_stats));
+	msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_USER_FEATURES */
 
 	return msgsize;
 }
@@ -1168,7 +1178,7 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *in
 	struct datapath *dp;
 
 	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
-	if (!dp)
+	if (IS_ERR(dp))
 		return;
 
 	WARN(dp->user_features, "Dropping previously announced user features\n");
@@ -1209,18 +1219,12 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		goto err_free_dp;
 
-	dp->stats_percpu = alloc_percpu(struct dp_stats_percpu);
+	dp->stats_percpu = netdev_alloc_pcpu_stats(struct dp_stats_percpu);
 	if (!dp->stats_percpu) {
 		err = -ENOMEM;
 		goto err_destroy_table;
 	}
 
-	for_each_possible_cpu(i) {
-		struct dp_stats_percpu *dpath_stats;
-		dpath_stats = per_cpu_ptr(dp->stats_percpu, i);
-		u64_stats_init(&dpath_stats->sync);
-	}
-
 	dp->ports = kmalloc(DP_VPORT_HASH_BUCKETS * sizeof(struct hlist_head),
 			    GFP_KERNEL);
 	if (!dp->ports) {
@@ -1279,7 +1283,7 @@ err_destroy_ports_array:
 err_destroy_percpu:
 	free_percpu(dp->stats_percpu);
 err_destroy_table:
-	ovs_flow_tbl_destroy(&dp->table);
+	ovs_flow_tbl_destroy(&dp->table, false);
 err_free_dp:
 	release_net(ovs_dp_get_net(dp));
 	kfree(dp);
@@ -1306,10 +1310,13 @@ static void __dp_destroy(struct datapath *dp)
 	list_del_rcu(&dp->list_node);
 
 	/* OVSP_LOCAL is datapath internal port. We need to make sure that
-	 * all port in datapath are destroyed first before freeing datapath.
+	 * all ports in datapath are destroyed first before freeing datapath.
 	 */
 	ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL));
 
+	/* RCU destroy the flow table */
+	ovs_flow_tbl_destroy(&dp->table, true);
+
 	call_rcu(&dp->rcu, destroy_dp_rcu);
 }
 
@@ -1753,11 +1760,12 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	int bucket = cb->args[0], skip = cb->args[1];
 	int i, j = 0;
 
+	rcu_read_lock();
 	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
-	if (!dp)
+	if (!dp) {
+		rcu_read_unlock();
 		return -ENODEV;
-
-	rcu_read_lock();
+	}
 	for (i = bucket; i < DP_VPORT_HASH_BUCKETS; i++) {
 		struct vport *vport;
 
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 6be9fbb5e9cb..05317380fc03 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -55,7 +55,7 @@ struct dp_stats_percpu {
 	u64 n_missed;
 	u64 n_lost;
 	u64 n_mask_hit;
-	struct u64_stats_sync sync;
+	struct u64_stats_sync syncp;
 };
 
 /**
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 16f4b46161d4..2998989e76db 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -73,6 +73,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb)
 
 	if ((flow->key.eth.type == htons(ETH_P_IP) ||
 	     flow->key.eth.type == htons(ETH_P_IPV6)) &&
+	    flow->key.ip.frag != OVS_FRAG_TYPE_LATER &&
 	    flow->key.ip.proto == IPPROTO_TCP &&
 	    likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) {
 		tcp_flags = TCP_FLAGS_BE16(tcp_hdr(skb));
@@ -91,7 +92,7 @@ static void stats_read(struct flow_stats *stats,
 		       unsigned long *used, __be16 *tcp_flags)
 {
 	spin_lock(&stats->lock);
-	if (time_after(stats->used, *used))
+	if (!*used || time_after(stats->used, *used))
 		*used = stats->used;
 	*tcp_flags |= stats->tcp_flags;
 	ovs_stats->n_packets += stats->packet_count;
@@ -102,30 +103,24 @@ static void stats_read(struct flow_stats *stats,
 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;
+	int cpu;
 
 	*used = 0;
 	*tcp_flags = 0;
 	memset(ovs_stats, 0, sizeof(*ovs_stats));
 
+	local_bh_disable();
 	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();
 	}
+	local_bh_enable();
 }
 
 static void stats_reset(struct flow_stats *stats)
@@ -140,25 +135,17 @@ static void stats_reset(struct flow_stats *stats)
 
 void ovs_flow_stats_clear(struct sw_flow *flow)
 {
-	int cpu, cur_cpu;
+	int cpu;
 
+	local_bh_disable();
 	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();
 	}
+	local_bh_enable();
 }
 
 static int check_header(struct sk_buff *skb, int len)
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index c58a0fe3c889..3c268b3d71c3 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -153,29 +153,29 @@ static void rcu_free_flow_callback(struct rcu_head *rcu)
 	flow_free(flow);
 }
 
-static void flow_mask_del_ref(struct sw_flow_mask *mask, bool deferred)
-{
-	if (!mask)
-		return;
-
-	BUG_ON(!mask->ref_count);
-	mask->ref_count--;
-
-	if (!mask->ref_count) {
-		list_del_rcu(&mask->list);
-		if (deferred)
-			kfree_rcu(mask, rcu);
-		else
-			kfree(mask);
-	}
-}
-
 void ovs_flow_free(struct sw_flow *flow, bool deferred)
 {
 	if (!flow)
 		return;
 
-	flow_mask_del_ref(flow->mask, deferred);
+	if (flow->mask) {
+		struct sw_flow_mask *mask = flow->mask;
+
+		/* ovs-lock is required to protect mask-refcount and
+		 * mask list.
+		 */
+		ASSERT_OVSL();
+		BUG_ON(!mask->ref_count);
+		mask->ref_count--;
+
+		if (!mask->ref_count) {
+			list_del_rcu(&mask->list);
+			if (deferred)
+				kfree_rcu(mask, rcu);
+			else
+				kfree(mask);
+		}
+	}
 
 	if (deferred)
 		call_rcu(&flow->rcu, rcu_free_flow_callback);
@@ -188,26 +188,9 @@ static void free_buckets(struct flex_array *buckets)
 	flex_array_free(buckets);
 }
 
+
 static void __table_instance_destroy(struct table_instance *ti)
 {
-	int i;
-
-	if (ti->keep_flows)
-		goto skip_flows;
-
-	for (i = 0; i < ti->n_buckets; i++) {
-		struct sw_flow *flow;
-		struct hlist_head *head = flex_array_get(ti->buckets, i);
-		struct hlist_node *n;
-		int ver = ti->node_ver;
-
-		hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
-			hlist_del(&flow->hash_node[ver]);
-			ovs_flow_free(flow, false);
-		}
-	}
-
-skip_flows:
 	free_buckets(ti->buckets);
 	kfree(ti);
 }
@@ -258,20 +241,38 @@ static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
 
 static void table_instance_destroy(struct table_instance *ti, bool deferred)
 {
+	int i;
+
 	if (!ti)
 		return;
 
+	if (ti->keep_flows)
+		goto skip_flows;
+
+	for (i = 0; i < ti->n_buckets; i++) {
+		struct sw_flow *flow;
+		struct hlist_head *head = flex_array_get(ti->buckets, i);
+		struct hlist_node *n;
+		int ver = ti->node_ver;
+
+		hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
+			hlist_del_rcu(&flow->hash_node[ver]);
+			ovs_flow_free(flow, deferred);
+		}
+	}
+
+skip_flows:
 	if (deferred)
 		call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
 	else
 		__table_instance_destroy(ti);
 }
 
-void ovs_flow_tbl_destroy(struct flow_table *table)
+void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred)
 {
 	struct table_instance *ti = ovsl_dereference(table->ti);
 
-	table_instance_destroy(ti, false);
+	table_instance_destroy(ti, deferred);
 }
 
 struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,
@@ -504,16 +505,11 @@ static struct sw_flow_mask *mask_alloc(void)
 
 	mask = kmalloc(sizeof(*mask), GFP_KERNEL);
 	if (mask)
-		mask->ref_count = 0;
+		mask->ref_count = 1;
 
 	return mask;
 }
 
-static void mask_add_ref(struct sw_flow_mask *mask)
-{
-	mask->ref_count++;
-}
-
 static bool mask_equal(const struct sw_flow_mask *a,
 		       const struct sw_flow_mask *b)
 {
@@ -554,9 +550,11 @@ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
 		mask->key = new->key;
 		mask->range = new->range;
 		list_add_rcu(&mask->list, &tbl->mask_list);
+	} else {
+		BUG_ON(!mask->ref_count);
+		mask->ref_count++;
 	}
 
-	mask_add_ref(mask);
 	flow->mask = mask;
 	return 0;
 }
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 1996e34c0fd8..baaeb101924d 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -60,7 +60,7 @@ 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);
+void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred);
 int ovs_flow_tbl_flush(struct flow_table *flow_table);
 
 int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 208dd9a26dd1..42c0f4a0b78c 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -121,7 +121,6 @@ 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) {
@@ -139,19 +138,12 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
 	vport->ops = ops;
 	INIT_HLIST_NODE(&vport->dp_hash_node);
 
-	vport->percpu_stats = alloc_percpu(struct pcpu_sw_netstats);
+	vport->percpu_stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!vport->percpu_stats) {
 		kfree(vport);
 		return ERR_PTR(-ENOMEM);
 	}
 
-	for_each_possible_cpu(i) {
-		struct pcpu_sw_netstats *vport_stats;
-		vport_stats = per_cpu_ptr(vport->percpu_stats, i);
-		u64_stats_init(&vport_stats->syncp);
-	}
-
-
 	spin_lock_init(&vport->stats_lock);
 
 	return vport;
@@ -285,9 +277,9 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats)
 		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;