1 files changed, 230 insertions, 60 deletions

diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index b409f5279601..62db02ba36bc 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2013 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
@@ -16,8 +16,6 @@
  * 02110-1301, USA
  */
 
-#include "flow.h"
-#include "datapath.h"
 #include <linux/uaccess.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
@@ -35,6 +33,7 @@
 #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>
@@ -45,6 +44,10 @@
 #include <net/ipv6.h>
 #include <net/ndisc.h>
 
+#include "datapath.h"
+#include "flow.h"
+#include "flow_netlink.h"
+
 u64 ovs_flow_used_time(unsigned long flow_jiffies)
 {
 	struct timespec cur_ts;
@@ -60,23 +63,113 @@ 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, __be16 tcp_flags,
+			   struct sk_buff *skb)
 {
-	__be16 tcp_flags = 0;
+	struct flow_stats *stats;
+	int node = numa_node_id();
+
+	stats = rcu_dereference(flow->stats[node]);
+
+	/* Check if already have node-specific stats. */
+	if (likely(stats)) {
+		spin_lock(&stats->lock);
+		/* Mark if we write on the pre-allocated stats. */
+		if (node == 0 && unlikely(flow->stats_last_writer != node))
+			flow->stats_last_writer = node;
+	} else {
+		stats = rcu_dereference(flow->stats[0]); /* Pre-allocated. */
+		spin_lock(&stats->lock);
+
+		/* If the current NUMA-node is the only writer on the
+		 * pre-allocated stats keep using them.
+		 */
+		if (unlikely(flow->stats_last_writer != node)) {
+			/* A previous locker may have already allocated the
+			 * stats, so we need to check again.  If node-specific
+			 * stats were already allocated, we update the pre-
+			 * allocated stats as we have already locked them.
+			 */
+			if (likely(flow->stats_last_writer != NUMA_NO_NODE)
+			    && likely(!rcu_access_pointer(flow->stats[node]))) {
+				/* Try to allocate node-specific stats. */
+				struct flow_stats *new_stats;
+
+				new_stats =
+					kmem_cache_alloc_node(flow_stats_cache,
+							      GFP_THISNODE |
+							      __GFP_NOMEMALLOC,
+							      node);
+				if (likely(new_stats)) {
+					new_stats->used = jiffies;
+					new_stats->packet_count = 1;
+					new_stats->byte_count = skb->len;
+					new_stats->tcp_flags = tcp_flags;
+					spin_lock_init(&new_stats->lock);
+
+					rcu_assign_pointer(flow->stats[node],
+							   new_stats);
+					goto unlock;
+				}
+			}
+			flow->stats_last_writer = node;
+		}
+	}
+
+	stats->used = jiffies;
+	stats->packet_count++;
+	stats->byte_count += skb->len;
+	stats->tcp_flags |= tcp_flags;
+unlock:
+	spin_unlock(&stats->lock);
+}
+
+/* Must be called with rcu_read_lock or ovs_mutex. */
+void ovs_flow_stats_get(const struct sw_flow *flow,
+			struct ovs_flow_stats *ovs_stats,
+			unsigned long *used, __be16 *tcp_flags)
+{
+	int node;
+
+	*used = 0;
+	*tcp_flags = 0;
+	memset(ovs_stats, 0, sizeof(*ovs_stats));
 
-	if ((flow->key.eth.type == htons(ETH_P_IP) ||
-	     flow->key.eth.type == htons(ETH_P_IPV6)) &&
-	    flow->key.ip.proto == IPPROTO_TCP &&
-	    likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) {
-		tcp_flags = TCP_FLAGS_BE16(tcp_hdr(skb));
+	for_each_node(node) {
+		struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[node]);
+
+		if (stats) {
+			/* Local CPU may write on non-local stats, so we must
+			 * block bottom-halves here.
+			 */
+			spin_lock_bh(&stats->lock);
+			if (!*used || 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_bh(&stats->lock);
+		}
 	}
+}
 
-	spin_lock(&flow->lock);
-	flow->used = jiffies;
-	flow->packet_count++;
-	flow->byte_count += skb->len;
-	flow->tcp_flags |= tcp_flags;
-	spin_unlock(&flow->lock);
+/* Called with ovs_mutex. */
+void ovs_flow_stats_clear(struct sw_flow *flow)
+{
+	int node;
+
+	for_each_node(node) {
+		struct flow_stats *stats = ovsl_dereference(flow->stats[node]);
+
+		if (stats) {
+			spin_lock_bh(&stats->lock);
+			stats->used = 0;
+			stats->packet_count = 0;
+			stats->byte_count = 0;
+			stats->tcp_flags = 0;
+			spin_unlock_bh(&stats->lock);
+		}
+	}
 }
 
 static int check_header(struct sk_buff *skb, int len)
@@ -263,8 +356,8 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
 	/* The ICMPv6 type and code fields use the 16-bit transport port
 	 * fields, so we need to store them in 16-bit network byte order.
 	 */
-	key->ipv6.tp.src = htons(icmp->icmp6_type);
-	key->ipv6.tp.dst = htons(icmp->icmp6_code);
+	key->tp.src = htons(icmp->icmp6_type);
+	key->tp.dst = htons(icmp->icmp6_code);
 
 	if (icmp->icmp6_code == 0 &&
 	    (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION ||
@@ -303,14 +396,14 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
 			    && opt_len == 8) {
 				if (unlikely(!is_zero_ether_addr(key->ipv6.nd.sll)))
 					goto invalid;
-				memcpy(key->ipv6.nd.sll,
-				    &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
+				ether_addr_copy(key->ipv6.nd.sll,
+						&nd->opt[offset+sizeof(*nd_opt)]);
 			} else if (nd_opt->nd_opt_type == ND_OPT_TARGET_LL_ADDR
 				   && opt_len == 8) {
 				if (unlikely(!is_zero_ether_addr(key->ipv6.nd.tll)))
 					goto invalid;
-				memcpy(key->ipv6.nd.tll,
-				    &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
+				ether_addr_copy(key->ipv6.nd.tll,
+						&nd->opt[offset+sizeof(*nd_opt)]);
 			}
 
 			icmp_len -= opt_len;
@@ -329,10 +422,9 @@ invalid:
 }
 
 /**
- * ovs_flow_extract - extracts a flow key from an Ethernet frame.
+ * key_extract - extracts a flow key from an Ethernet frame.
  * @skb: sk_buff that contains the frame, with skb->data pointing to the
  * Ethernet header
- * @in_port: port number on which @skb was received.
  * @key: output flow key
  *
  * The caller must ensure that skb->len >= ETH_HLEN.
@@ -351,18 +443,13 @@ invalid:
  *      of a correct length, otherwise the same as skb->network_header.
  *      For other key->eth.type values it is left untouched.
  */
-int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
+static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 {
 	int error;
 	struct ethhdr *eth;
 
-	memset(key, 0, sizeof(*key));
-
-	key->phy.priority = skb->priority;
-	if (OVS_CB(skb)->tun_key)
-		memcpy(&key->tun_key, OVS_CB(skb)->tun_key, sizeof(key->tun_key));
-	key->phy.in_port = in_port;
-	key->phy.skb_mark = skb->mark;
+	/* Flags are always used as part of stats */
+	key->tp.flags = 0;
 
 	skb_reset_mac_header(skb);
 
@@ -370,14 +457,15 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 	 * header in the linear data area.
 	 */
 	eth = eth_hdr(skb);
-	memcpy(key->eth.src, eth->h_source, ETH_ALEN);
-	memcpy(key->eth.dst, eth->h_dest, ETH_ALEN);
+	ether_addr_copy(key->eth.src, eth->h_source);
+	ether_addr_copy(key->eth.dst, eth->h_dest);
 
 	__skb_pull(skb, 2 * ETH_ALEN);
 	/* We are going to push all headers that we pull, so no need to
 	 * update skb->csum here.
 	 */
 
+	key->eth.tci = 0;
 	if (vlan_tx_tag_present(skb))
 		key->eth.tci = htons(skb->vlan_tci);
 	else if (eth->h_proto == htons(ETH_P_8021Q))
@@ -398,6 +486,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 
 		error = check_iphdr(skb);
 		if (unlikely(error)) {
+			memset(&key->ip, 0, sizeof(key->ip));
+			memset(&key->ipv4, 0, sizeof(key->ipv4));
 			if (error == -EINVAL) {
 				skb->transport_header = skb->network_header;
 				error = 0;
@@ -419,28 +509,37 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 			return 0;
 		}
 		if (nh->frag_off & htons(IP_MF) ||
-			 skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+			skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
 			key->ip.frag = OVS_FRAG_TYPE_FIRST;
+		else
+			key->ip.frag = OVS_FRAG_TYPE_NONE;
 
 		/* Transport layer. */
 		if (key->ip.proto == IPPROTO_TCP) {
 			if (tcphdr_ok(skb)) {
 				struct tcphdr *tcp = tcp_hdr(skb);
-				key->ipv4.tp.src = tcp->source;
-				key->ipv4.tp.dst = tcp->dest;
-				key->ipv4.tp.flags = TCP_FLAGS_BE16(tcp);
+				key->tp.src = tcp->source;
+				key->tp.dst = tcp->dest;
+				key->tp.flags = TCP_FLAGS_BE16(tcp);
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
 			}
+
 		} else if (key->ip.proto == IPPROTO_UDP) {
 			if (udphdr_ok(skb)) {
 				struct udphdr *udp = udp_hdr(skb);
-				key->ipv4.tp.src = udp->source;
-				key->ipv4.tp.dst = udp->dest;
+				key->tp.src = udp->source;
+				key->tp.dst = udp->dest;
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
 			}
 		} else if (key->ip.proto == IPPROTO_SCTP) {
 			if (sctphdr_ok(skb)) {
 				struct sctphdr *sctp = sctp_hdr(skb);
-				key->ipv4.tp.src = sctp->source;
-				key->ipv4.tp.dst = sctp->dest;
+				key->tp.src = sctp->source;
+				key->tp.dst = sctp->dest;
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
 			}
 		} else if (key->ip.proto == IPPROTO_ICMP) {
 			if (icmphdr_ok(skb)) {
@@ -448,35 +547,46 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 				/* The ICMP type and code fields use the 16-bit
 				 * transport port fields, so we need to store
 				 * them in 16-bit network byte order. */
-				key->ipv4.tp.src = htons(icmp->type);
-				key->ipv4.tp.dst = htons(icmp->code);
+				key->tp.src = htons(icmp->type);
+				key->tp.dst = htons(icmp->code);
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
 			}
 		}
 
-	} else if ((key->eth.type == htons(ETH_P_ARP) ||
-		   key->eth.type == htons(ETH_P_RARP)) && arphdr_ok(skb)) {
+	} else if (key->eth.type == htons(ETH_P_ARP) ||
+		   key->eth.type == htons(ETH_P_RARP)) {
 		struct arp_eth_header *arp;
 
 		arp = (struct arp_eth_header *)skb_network_header(skb);
 
-		if (arp->ar_hrd == htons(ARPHRD_ETHER)
-				&& arp->ar_pro == htons(ETH_P_IP)
-				&& arp->ar_hln == ETH_ALEN
-				&& arp->ar_pln == 4) {
+		if (arphdr_ok(skb) &&
+		    arp->ar_hrd == htons(ARPHRD_ETHER) &&
+		    arp->ar_pro == htons(ETH_P_IP) &&
+		    arp->ar_hln == ETH_ALEN &&
+		    arp->ar_pln == 4) {
 
 			/* We only match on the lower 8 bits of the opcode. */
 			if (ntohs(arp->ar_op) <= 0xff)
 				key->ip.proto = ntohs(arp->ar_op);
+			else
+				key->ip.proto = 0;
+
 			memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src));
 			memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst));
-			memcpy(key->ipv4.arp.sha, arp->ar_sha, ETH_ALEN);
-			memcpy(key->ipv4.arp.tha, arp->ar_tha, ETH_ALEN);
+			ether_addr_copy(key->ipv4.arp.sha, arp->ar_sha);
+			ether_addr_copy(key->ipv4.arp.tha, arp->ar_tha);
+		} else {
+			memset(&key->ip, 0, sizeof(key->ip));
+			memset(&key->ipv4, 0, sizeof(key->ipv4));
 		}
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
 		int nh_len;             /* IPv6 Header + Extensions */
 
 		nh_len = parse_ipv6hdr(skb, key);
 		if (unlikely(nh_len < 0)) {
+			memset(&key->ip, 0, sizeof(key->ip));
+			memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr));
 			if (nh_len == -EINVAL) {
 				skb->transport_header = skb->network_header;
 				error = 0;
@@ -495,30 +605,90 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 		if (key->ip.proto == NEXTHDR_TCP) {
 			if (tcphdr_ok(skb)) {
 				struct tcphdr *tcp = tcp_hdr(skb);
-				key->ipv6.tp.src = tcp->source;
-				key->ipv6.tp.dst = tcp->dest;
-				key->ipv6.tp.flags = TCP_FLAGS_BE16(tcp);
+				key->tp.src = tcp->source;
+				key->tp.dst = tcp->dest;
+				key->tp.flags = TCP_FLAGS_BE16(tcp);
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
 			}
 		} else if (key->ip.proto == NEXTHDR_UDP) {
 			if (udphdr_ok(skb)) {
 				struct udphdr *udp = udp_hdr(skb);
-				key->ipv6.tp.src = udp->source;
-				key->ipv6.tp.dst = udp->dest;
+				key->tp.src = udp->source;
+				key->tp.dst = udp->dest;
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
 			}
 		} else if (key->ip.proto == NEXTHDR_SCTP) {
 			if (sctphdr_ok(skb)) {
 				struct sctphdr *sctp = sctp_hdr(skb);
-				key->ipv6.tp.src = sctp->source;
-				key->ipv6.tp.dst = sctp->dest;
+				key->tp.src = sctp->source;
+				key->tp.dst = sctp->dest;
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
 			}
 		} else if (key->ip.proto == NEXTHDR_ICMP) {
 			if (icmp6hdr_ok(skb)) {
 				error = parse_icmpv6(skb, key, nh_len);
 				if (error)
 					return error;
+			} else {
+				memset(&key->tp, 0, sizeof(key->tp));
 			}
 		}
 	}
-
 	return 0;
 }
+
+int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	return key_extract(skb, key);
+}
+
+int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
+			 struct sk_buff *skb, struct sw_flow_key *key)
+{
+	/* Extract metadata from packet. */
+	if (tun_info) {
+		memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key));
+
+		if (tun_info->options) {
+			BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) *
+						   8)) - 1
+					> sizeof(key->tun_opts));
+			memcpy(GENEVE_OPTS(key, tun_info->options_len),
+			       tun_info->options, tun_info->options_len);
+			key->tun_opts_len = tun_info->options_len;
+		} else {
+			key->tun_opts_len = 0;
+		}
+	} else  {
+		key->tun_opts_len = 0;
+		memset(&key->tun_key, 0, sizeof(key->tun_key));
+	}
+
+	key->phy.priority = skb->priority;
+	key->phy.in_port = OVS_CB(skb)->input_vport->port_no;
+	key->phy.skb_mark = skb->mark;
+	key->ovs_flow_hash = 0;
+	key->recirc_id = 0;
+
+	/* Flags are always used as part of stats */
+	key->tp.flags = 0;
+
+	return key_extract(skb, key);
+}
+
+int ovs_flow_key_extract_userspace(const struct nlattr *attr,
+				   struct sk_buff *skb,
+				   struct sw_flow_key *key)
+{
+	int err;
+
+	/* Extract metadata from netlink attributes. */
+	err = ovs_nla_get_flow_metadata(attr, key);
+	if (err)
+		return err;
+
+	return key_extract(skb, key);
+}