/*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2015 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
* 02110-1301, USA
*/
-#include "flow.h"
-#include "datapath.h"
#include <linux/uaccess.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/if_arp.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
+#include <linux/mpls.h>
#include <linux/sctp.h>
#include <linux/smp.h>
#include <linux/tcp.h>
#include <linux/rculist.h>
#include <net/ip.h>
#include <net/ipv6.h>
+#include <net/mpls.h>
#include <net/ndisc.h>
+#include "datapath.h"
+#include "conntrack.h"
+#include "flow.h"
+#include "flow_netlink.h"
+#include "vport.h"
#include "vlan.h"
u64 ovs_flow_used_time(unsigned long flow_jiffies)
#define TCP_FLAGS_BE16(tp) (*(__be16 *)&tcp_flag_word(tp) & htons(0x0FFF))
-void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb)
+void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
+ const 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.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));
+ int node = numa_node_id();
+ int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
+
+ 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_NOWAIT |
+ __GFP_THISNODE |
+ __GFP_NOWARN |
+ __GFP_NOMEMALLOC,
+ node);
+ if (likely(new_stats)) {
+ new_stats->used = jiffies;
+ new_stats->packet_count = 1;
+ new_stats->byte_count = 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;
+ }
}
- spin_lock(&stats->lock);
stats->used = jiffies;
stats->packet_count++;
- stats->byte_count += skb->len;
+ stats->byte_count += len;
stats->tcp_flags |= tcp_flags;
+unlock:
spin_unlock(&stats->lock);
}
-static void stats_read(struct flow_stats *stats, bool lock_bh,
- struct ovs_flow_stats *ovs_stats,
- unsigned long *used, __be16 *tcp_flags)
-{
- if (lock_bh)
- spin_lock_bh(&stats->lock);
- else
- 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;
-
- if (lock_bh)
- spin_unlock_bh(&stats->lock);
- else
- spin_unlock(&stats->lock);
-}
-
-void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats,
+/* 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 cpu, cur_cpu;
+ int node;
*used = 0;
*tcp_flags = 0;
memset(ovs_stats, 0, sizeof(*ovs_stats));
- if (!flow->stats.is_percpu) {
- stats_read(flow->stats.stat, true, ovs_stats, used, tcp_flags);
- } else {
- cur_cpu = get_cpu();
-
- for_each_possible_cpu(cpu) {
- struct flow_stats *stats;
- bool lock_bh;
+ for_each_node(node) {
+ struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[node]);
- stats = per_cpu_ptr(flow->stats.cpu_stats, cpu);
- lock_bh = (cpu == cur_cpu);
- stats_read(stats, lock_bh, ovs_stats, used, tcp_flags);
+ 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);
}
- put_cpu();
}
}
-static void stats_reset(struct flow_stats *stats, bool lock_bh)
-{
- if (lock_bh)
- spin_lock_bh(&stats->lock);
- else
- spin_lock(&stats->lock);
-
- stats->used = 0;
- stats->packet_count = 0;
- stats->byte_count = 0;
- stats->tcp_flags = 0;
-
- if (lock_bh)
- spin_unlock_bh(&stats->lock);
- else
- spin_unlock(&stats->lock);
-}
-
+/* Called with ovs_mutex. */
void ovs_flow_stats_clear(struct sw_flow *flow)
{
- int cpu, cur_cpu;
-
- if (!flow->stats.is_percpu) {
- stats_reset(flow->stats.stat, true);
- } else {
- cur_cpu = get_cpu();
-
- for_each_possible_cpu(cpu) {
- bool lock_bh;
-
- lock_bh = (cpu == cur_cpu);
- stats_reset(per_cpu_ptr(flow->stats.cpu_stats, cpu), lock_bh);
+ 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);
}
- put_cpu();
}
}
key->ip.frag = OVS_FRAG_TYPE_LATER;
else
key->ip.frag = OVS_FRAG_TYPE_FIRST;
+ } else {
+ key->ip.frag = OVS_FRAG_TYPE_NONE;
}
nh_len = payload_ofs - nh_ofs;
proto = *(__be16 *) skb->data;
__skb_pull(skb, sizeof(__be16));
- if (ntohs(proto) >= ETH_P_802_3_MIN)
+ if (eth_proto_is_802_3(proto))
return proto;
if (skb->len < sizeof(struct llc_snap_hdr))
__skb_pull(skb, sizeof(struct llc_snap_hdr));
- if (ntohs(llc->ethertype) >= ETH_P_802_3_MIN)
+ if (eth_proto_is_802_3(llc->ethertype))
return llc->ethertype;
return htons(ETH_P_802_2);
/* 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);
+ memset(&key->ipv6.nd, 0, sizeof(key->ipv6.nd));
if (icmp->icmp6_code == 0 &&
(icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION ||
&& 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;
}
/**
- * 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.
* 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);
* 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. */
+ * update skb->csum here.
+ */
- if (vlan_tx_tag_present(skb))
+ key->eth.tci = 0;
+ if (skb_vlan_tag_present(skb))
key->eth.tci = htons(vlan_get_tci(skb));
else if (eth->h_proto == htons(ETH_P_8021Q))
if (unlikely(parse_vlan(skb, key)))
return -ENOMEM;
skb_reset_network_header(skb);
+ skb_reset_mac_len(skb);
__skb_push(skb, skb->data - skb_mac_header(skb));
/* Network layer. */
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;
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)) {
struct icmphdr *icmp = icmp_hdr(skb);
/* 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);
+ * them in 16-bit network byte order.
+ */
+ 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;
+ bool arp_available = arphdr_ok(skb);
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 (arp_available &&
+ 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 (eth_p_mpls(key->eth.type)) {
+ size_t stack_len = MPLS_HLEN;
+
+ /* In the presence of an MPLS label stack the end of the L2
+ * header and the beginning of the L3 header differ.
+ *
+ * Advance network_header to the beginning of the L3
+ * header. mac_len corresponds to the end of the L2 header.
+ */
+ while (1) {
+ __be32 lse;
+
+ error = check_header(skb, skb->mac_len + stack_len);
+ if (unlikely(error))
+ return 0;
+
+ memcpy(&lse, skb_network_header(skb), MPLS_HLEN);
+
+ if (stack_len == MPLS_HLEN)
+ memcpy(&key->mpls.top_lse, &lse, MPLS_HLEN);
+
+ skb_set_network_header(skb, skb->mac_len + stack_len);
+ if (lse & htonl(MPLS_LS_S_MASK))
+ break;
+
+ stack_len += MPLS_HLEN;
}
} 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;
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(const struct ip_tunnel_info *tun_info,
+ struct sk_buff *skb, struct sw_flow_key *key)
+{
+ /* Extract metadata from packet. */
+ if (tun_info) {
+ if (ip_tunnel_info_af(tun_info) != AF_INET)
+ return -EINVAL;
+
+ memcpy(&key->tun_key, &tun_info->key, sizeof(key->tun_key));
+ BUILD_BUG_ON(((1 << (sizeof(tun_info->options_len) * 8)) - 1) >
+ sizeof(key->tun_opts));
+
+ if (tun_info->options_len) {
+ ip_tunnel_info_opts_get(TUN_METADATA_OPTS(key, tun_info->options_len),
+ tun_info);
+ 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;
+ ovs_ct_fill_key(skb, key);
+ key->ovs_flow_hash = 0;
+ key->recirc_id = 0;
+
+ return key_extract(skb, key);
+}
+
+int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr,
+ struct sk_buff *skb,
+ struct sw_flow_key *key, bool log)
+{
+ int err;
+
+ /* Extract metadata from netlink attributes. */
+ err = ovs_nla_get_flow_metadata(net, attr, key, log);
+ if (err)
+ return err;
+
+ return key_extract(skb, key);
+}
projects / cascardo / ovs.git / blobdiff