/*
- * Copyright (c) 2007-2012 Nicira, Inc.
+ * Copyright (c) 2007-2013 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
#include <linux/openvswitch.h>
#include <linux/rculist.h>
#include <linux/dmi.h>
+#include <linux/genetlink.h>
+#include <net/genetlink.h>
#include <net/genetlink.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
-#include "checksum.h"
#include "datapath.h"
#include "flow.h"
-#include "genl_exec.h"
+#include "flow_table.h"
+#include "flow_netlink.h"
#include "vlan.h"
-#include "tunnel.h"
#include "vport-internal_dev.h"
+#include "vport-netdev.h"
-#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,18) || \
- LINUX_VERSION_CODE >= KERNEL_VERSION(3,9,0)
-#error Kernels before 2.6.18 or after 3.8 are not supported by this version of Open vSwitch.
-#endif
+int ovs_net_id __read_mostly;
-#define REHASH_FLOW_INTERVAL (10 * 60 * HZ)
-static void rehash_flow_table(struct work_struct *work);
-static DECLARE_DELAYED_WORK(rehash_flow_wq, rehash_flow_table);
+/* Check if need to build a reply message.
+ * OVS userspace sets the NLM_F_ECHO flag if it needs the reply. */
+static bool ovs_must_notify(struct genl_info *info,
+ const struct genl_multicast_group *grp)
+{
+ return info->nlhdr->nlmsg_flags & NLM_F_ECHO ||
+ netlink_has_listeners(genl_info_net(info)->genl_sock, grp->id);
+}
-int ovs_net_id __read_mostly;
+static void ovs_notify(struct sk_buff *skb, struct genl_info *info,
+ struct genl_multicast_group *grp)
+{
+ genl_notify(skb, genl_info_net(info), info->snd_portid,
+ grp->id, info->nlhdr, GFP_KERNEL);
+}
/**
* DOC: Locking:
*
- * Writes to device state (add/remove datapath, port, set operations on vports,
- * etc.) are protected by RTNL.
- *
- * Writes to other state (flow table modifications, set miscellaneous datapath
- * parameters, etc.) are protected by genl_mutex. The RTNL lock nests inside
- * genl_mutex.
+ * All writes e.g. Writes to device state (add/remove datapath, port, set
+ * operations on vports, etc.), Writes to other state (flow table
+ * modifications, set miscellaneous datapath parameters, etc.) are protected
+ * by ovs_lock.
*
* Reads are protected by RCU.
*
* There are a few special cases (mostly stats) that have their own
* synchronization but they nest under all of above and don't interact with
* each other.
+ *
+ * The RTNL lock nests inside ovs_mutex.
*/
+static DEFINE_MUTEX(ovs_mutex);
+
+void ovs_lock(void)
+{
+ mutex_lock(&ovs_mutex);
+}
+
+void ovs_unlock(void)
+{
+ mutex_unlock(&ovs_mutex);
+}
+
+#ifdef CONFIG_LOCKDEP
+int lockdep_ovsl_is_held(void)
+{
+ if (debug_locks)
+ return lockdep_is_held(&ovs_mutex);
+ else
+ return 1;
+}
+#endif
+
static struct vport *new_vport(const struct vport_parms *);
-static int queue_gso_packets(struct net *, int dp_ifindex, struct sk_buff *,
+static int queue_gso_packets(struct datapath *dp, struct sk_buff *,
const struct dp_upcall_info *);
-static int queue_userspace_packet(struct net *, int dp_ifindex,
- struct sk_buff *,
+static int queue_userspace_packet(struct datapath *dp, struct sk_buff *,
const struct dp_upcall_info *);
-/* Must be called with rcu_read_lock, genl_mutex, or RTNL lock. */
+/* Must be called with rcu_read_lock or ovs_mutex. */
static struct datapath *get_dp(struct net *net, int dp_ifindex)
{
struct datapath *dp = NULL;
return dp;
}
-/* Must be called with rcu_read_lock or RTNL lock. */
+/* Must be called with rcu_read_lock or ovs_mutex. */
const char *ovs_dp_name(const struct datapath *dp)
{
- struct vport *vport = ovs_vport_rtnl_rcu(dp, OVSP_LOCAL);
+ struct vport *vport = ovs_vport_ovsl_rcu(dp, OVSP_LOCAL);
return vport->ops->get_name(vport);
}
local = ovs_vport_rcu(dp, OVSP_LOCAL);
if (local)
- ifindex = local->ops->get_ifindex(local);
+ ifindex = netdev_vport_priv(local)->dev->ifindex;
else
ifindex = 0;
{
struct datapath *dp = container_of(rcu, struct datapath, rcu);
- ovs_flow_tbl_destroy((__force struct flow_table *)dp->table);
free_percpu(dp->stats_percpu);
release_net(ovs_dp_get_net(dp));
kfree(dp->ports);
return &dp->ports[port_no & (DP_VPORT_HASH_BUCKETS - 1)];
}
+/* Called with ovs_mutex or RCU read lock. */
struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no)
{
struct vport *vport;
- struct hlist_node *n;
struct hlist_head *head;
head = vport_hash_bucket(dp, port_no);
- hlist_for_each_entry_rcu(vport, n, head, dp_hash_node) {
+ hlist_for_each_entry_rcu(vport, head, dp_hash_node) {
if (vport->port_no == port_no)
return vport;
}
return NULL;
}
-/* Called with RTNL lock and genl_lock. */
+/* Called with ovs_mutex. */
static struct vport *new_vport(const struct vport_parms *parms)
{
struct vport *vport;
return vport;
}
-/* Called with RTNL lock. */
void ovs_dp_detach_port(struct vport *p)
{
- ASSERT_RTNL();
+ ASSERT_OVSL();
/* First drop references to device. */
hlist_del_rcu(&p->dp_hash_node);
struct datapath *dp = p->dp;
struct sw_flow *flow;
struct dp_stats_percpu *stats;
+ struct sw_flow_key key;
u64 *stats_counter;
+ u32 n_mask_hit;
int error;
stats = this_cpu_ptr(dp->stats_percpu);
- if (!OVS_CB(skb)->flow) {
- struct sw_flow_key key;
- int key_len;
-
- /* Extract flow from 'skb' into 'key'. */
- error = ovs_flow_extract(skb, p->port_no, &key, &key_len);
- if (unlikely(error)) {
- kfree_skb(skb);
- return;
- }
-
- /* Look up flow. */
- flow = ovs_flow_tbl_lookup(rcu_dereference(dp->table),
- &key, key_len);
- if (unlikely(!flow)) {
- struct dp_upcall_info upcall;
-
- upcall.cmd = OVS_PACKET_CMD_MISS;
- upcall.key = &key;
- upcall.userdata = NULL;
- upcall.portid = p->upcall_portid;
- ovs_dp_upcall(dp, skb, &upcall);
- consume_skb(skb);
- stats_counter = &stats->n_missed;
- goto out;
- }
+ /* Extract flow from 'skb' into 'key'. */
+ error = ovs_flow_extract(skb, p->port_no, &key);
+ if (unlikely(error)) {
+ kfree_skb(skb);
+ return;
+ }
- OVS_CB(skb)->flow = flow;
+ /* Look up flow. */
+ flow = ovs_flow_tbl_lookup_stats(&dp->table, &key, &n_mask_hit);
+ if (unlikely(!flow)) {
+ struct dp_upcall_info upcall;
+
+ upcall.cmd = OVS_PACKET_CMD_MISS;
+ upcall.key = &key;
+ upcall.userdata = NULL;
+ upcall.portid = p->upcall_portid;
+ ovs_dp_upcall(dp, skb, &upcall);
+ consume_skb(skb);
+ stats_counter = &stats->n_missed;
+ goto out;
}
- stats_counter = &stats->n_hit;
- ovs_flow_used(OVS_CB(skb)->flow, skb);
+ OVS_CB(skb)->flow = flow;
+ OVS_CB(skb)->pkt_key = &key;
+
+ ovs_flow_stats_update(OVS_CB(skb)->flow, skb);
ovs_execute_actions(dp, skb);
+ stats_counter = &stats->n_hit;
out:
/* Update datapath statistics. */
u64_stats_update_begin(&stats->sync);
(*stats_counter)++;
+ stats->n_mask_hit += n_mask_hit;
u64_stats_update_end(&stats->sync);
}
.name = OVS_PACKET_FAMILY,
.version = OVS_PACKET_VERSION,
.maxattr = OVS_PACKET_ATTR_MAX,
- SET_NETNSOK
+ .netnsok = true,
+ SET_PARALLEL_OPS
};
int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
const struct dp_upcall_info *upcall_info)
{
struct dp_stats_percpu *stats;
- int dp_ifindex;
int err;
if (upcall_info->portid == 0) {
goto err;
}
- dp_ifindex = get_dpifindex(dp);
- if (!dp_ifindex) {
- err = -ENODEV;
- goto err;
- }
-
- forward_ip_summed(skb, true);
-
if (!skb_is_gso(skb))
- err = queue_userspace_packet(ovs_dp_get_net(dp), dp_ifindex, skb, upcall_info);
+ err = queue_userspace_packet(dp, skb, upcall_info);
else
- err = queue_gso_packets(ovs_dp_get_net(dp), dp_ifindex, skb, upcall_info);
+ err = queue_gso_packets(dp, skb, upcall_info);
if (err)
goto err;
return err;
}
-static int queue_gso_packets(struct net *net, int dp_ifindex,
- struct sk_buff *skb,
+static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
const struct dp_upcall_info *upcall_info)
{
unsigned short gso_type = skb_shinfo(skb)->gso_type;
struct sk_buff *segs, *nskb;
int err;
- segs = __skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM, false);
+ segs = __skb_gso_segment(skb, NETIF_F_SG, false);
if (IS_ERR(segs))
return PTR_ERR(segs);
/* Queue all of the segments. */
skb = segs;
do {
- err = queue_userspace_packet(net, dp_ifindex, skb, upcall_info);
+ err = queue_userspace_packet(dp, skb, upcall_info);
if (err)
break;
return err;
}
-static int queue_userspace_packet(struct net *net, int dp_ifindex,
- struct sk_buff *skb,
+static size_t key_attr_size(void)
+{
+ return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */
+ + nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */
+ + nla_total_size(8) /* OVS_TUNNEL_KEY_ATTR_ID */
+ + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */
+ + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */
+ + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TOS */
+ + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TTL */
+ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
+ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_CSUM */
+ + nla_total_size(4) /* OVS_KEY_ATTR_IN_PORT */
+ + nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */
+ + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */
+ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */
+ + nla_total_size(4) /* OVS_KEY_ATTR_8021Q */
+ + nla_total_size(0) /* OVS_KEY_ATTR_ENCAP */
+ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */
+ + nla_total_size(40) /* OVS_KEY_ATTR_IPV6 */
+ + nla_total_size(2) /* OVS_KEY_ATTR_ICMPV6 */
+ + nla_total_size(28); /* OVS_KEY_ATTR_ND */
+}
+
+static size_t upcall_msg_size(const struct nlattr *userdata,
+ unsigned int hdrlen)
+{
+ size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
+ + nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */
+ + nla_total_size(key_attr_size()); /* OVS_PACKET_ATTR_KEY */
+
+ /* OVS_PACKET_ATTR_USERDATA */
+ if (userdata)
+ size += NLA_ALIGN(userdata->nla_len);
+
+ return size;
+}
+
+static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
const struct dp_upcall_info *upcall_info)
{
struct ovs_header *upcall;
struct sk_buff *nskb = NULL;
struct sk_buff *user_skb; /* to be queued to userspace */
struct nlattr *nla;
- unsigned int len;
- int err;
+ struct genl_info info = {
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3,14,0)
+ .dst_sk = ovs_dp_get_net(dp)->genl_sock,
+#endif
+ .snd_portid = upcall_info->portid,
+ };
+ size_t len;
+ unsigned int hlen;
+ int err, dp_ifindex;
+
+ dp_ifindex = get_dpifindex(dp);
+ if (!dp_ifindex)
+ return -ENODEV;
if (vlan_tx_tag_present(skb)) {
nskb = skb_clone(skb, GFP_ATOMIC);
if (!nskb)
return -ENOMEM;
-
- err = vlan_deaccel_tag(nskb);
- if (err)
- return err;
+
+ nskb = __vlan_put_tag(nskb, nskb->vlan_proto, vlan_tx_tag_get(nskb));
+ if (!nskb)
+ return -ENOMEM;
+
+ vlan_set_tci(nskb, 0);
skb = nskb;
}
goto out;
}
- len = sizeof(struct ovs_header);
- len += nla_total_size(skb->len);
- len += nla_total_size(FLOW_BUFSIZE);
- if (upcall_info->cmd == OVS_PACKET_CMD_ACTION)
- len += nla_total_size(8);
+ /* Complete checksum if needed */
+ if (skb->ip_summed == CHECKSUM_PARTIAL &&
+ (err = skb_checksum_help(skb)))
+ goto out;
+
+ /* Older versions of OVS user space enforce alignment of the last
+ * Netlink attribute to NLA_ALIGNTO which would require extensive
+ * padding logic. Only perform zerocopy if padding is not required.
+ */
+ if (dp->user_features & OVS_DP_F_UNALIGNED)
+ hlen = skb_zerocopy_headlen(skb);
+ else
+ hlen = skb->len;
- user_skb = genlmsg_new(len, GFP_ATOMIC);
+ len = upcall_msg_size(upcall_info->userdata, hlen);
+ user_skb = genlmsg_new_unicast(len, &info, GFP_ATOMIC);
if (!user_skb) {
err = -ENOMEM;
goto out;
upcall->dp_ifindex = dp_ifindex;
nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_KEY);
- ovs_flow_to_nlattrs(upcall_info->key, user_skb);
+ ovs_nla_put_flow(upcall_info->key, upcall_info->key, user_skb);
nla_nest_end(user_skb, nla);
if (upcall_info->userdata)
- nla_put_u64(user_skb, OVS_PACKET_ATTR_USERDATA,
- nla_get_u64(upcall_info->userdata));
-
- nla = __nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, skb->len);
-
- skb_copy_and_csum_dev(skb, nla_data(nla));
-
- err = genlmsg_unicast(net, user_skb, upcall_info->portid);
-
-out:
- kfree_skb(nskb);
- return err;
-}
-
-/* Called with genl_mutex. */
-static int flush_flows(struct datapath *dp)
-{
- struct flow_table *old_table;
- struct flow_table *new_table;
-
- old_table = genl_dereference(dp->table);
- new_table = ovs_flow_tbl_alloc(TBL_MIN_BUCKETS);
- if (!new_table)
- return -ENOMEM;
-
- rcu_assign_pointer(dp->table, new_table);
-
- ovs_flow_tbl_deferred_destroy(old_table);
- return 0;
-}
-
-static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, int attr_len)
-{
-
- struct sw_flow_actions *acts;
- int new_acts_size;
- int req_size = NLA_ALIGN(attr_len);
- int next_offset = offsetof(struct sw_flow_actions, actions) +
- (*sfa)->actions_len;
-
- if (req_size <= (ksize(*sfa) - next_offset))
+ __nla_put(user_skb, OVS_PACKET_ATTR_USERDATA,
+ nla_len(upcall_info->userdata),
+ nla_data(upcall_info->userdata));
+
+ /* Only reserve room for attribute header, packet data is added
+ * in skb_zerocopy() */
+ if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
+ err = -ENOBUFS;
goto out;
-
- new_acts_size = ksize(*sfa) * 2;
-
- if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
- if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size)
- return ERR_PTR(-EMSGSIZE);
- new_acts_size = MAX_ACTIONS_BUFSIZE;
- }
-
- acts = ovs_flow_actions_alloc(new_acts_size);
- if (IS_ERR(acts))
- return (void *)acts;
-
- memcpy(acts->actions, (*sfa)->actions, (*sfa)->actions_len);
- acts->actions_len = (*sfa)->actions_len;
- kfree(*sfa);
- *sfa = acts;
-
-out:
- (*sfa)->actions_len += req_size;
- return (struct nlattr *) ((unsigned char *)(*sfa) + next_offset);
-}
-
-static int add_action(struct sw_flow_actions **sfa, int attrtype, void *data, int len)
-{
- struct nlattr *a;
-
- a = reserve_sfa_size(sfa, nla_attr_size(len));
- if (IS_ERR(a))
- return PTR_ERR(a);
-
- a->nla_type = attrtype;
- a->nla_len = nla_attr_size(len);
-
- if (data)
- memcpy(nla_data(a), data, len);
- memset((unsigned char *) a + a->nla_len, 0, nla_padlen(len));
-
- return 0;
-}
-
-static inline int add_nested_action_start(struct sw_flow_actions **sfa, int attrtype)
-{
- int used = (*sfa)->actions_len;
- int err;
-
- err = add_action(sfa, attrtype, NULL, 0);
- if (err)
- return err;
-
- return used;
-}
-
-static inline void add_nested_action_end(struct sw_flow_actions *sfa, int st_offset)
-{
- struct nlattr *a = (struct nlattr *) ((unsigned char *)sfa->actions + st_offset);
-
- a->nla_len = sfa->actions_len - st_offset;
-}
-
-static int validate_and_copy_actions(const struct nlattr *attr,
- const struct sw_flow_key *key, int depth,
- struct sw_flow_actions **sfa);
-
-static int validate_and_copy_sample(const struct nlattr *attr,
- const struct sw_flow_key *key, int depth,
- struct sw_flow_actions **sfa)
-{
- const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
- const struct nlattr *probability, *actions;
- const struct nlattr *a;
- int rem, start, err, st_acts;
-
- memset(attrs, 0, sizeof(attrs));
- nla_for_each_nested(a, attr, rem) {
- int type = nla_type(a);
- if (!type || type > OVS_SAMPLE_ATTR_MAX || attrs[type])
- return -EINVAL;
- attrs[type] = a;
}
- if (rem)
- return -EINVAL;
+ nla->nla_len = nla_attr_size(skb->len);
- probability = attrs[OVS_SAMPLE_ATTR_PROBABILITY];
- if (!probability || nla_len(probability) != sizeof(u32))
- return -EINVAL;
-
- actions = attrs[OVS_SAMPLE_ATTR_ACTIONS];
- if (!actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN))
- return -EINVAL;
-
- /* validation done, copy sample action. */
- start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE);
- if (start < 0)
- return start;
- err = add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY, nla_data(probability), sizeof(u32));
- if (err)
- return err;
- st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS);
- if (st_acts < 0)
- return st_acts;
-
- err = validate_and_copy_actions(actions, key, depth + 1, sfa);
- if (err)
- return err;
+ skb_zerocopy(user_skb, skb, skb->len, hlen);
- add_nested_action_end(*sfa, st_acts);
- add_nested_action_end(*sfa, start);
+ /* 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;
- return 0;
-}
-
-static int validate_tp_port(const struct sw_flow_key *flow_key)
-{
- if (flow_key->eth.type == htons(ETH_P_IP)) {
- if (flow_key->ipv4.tp.src || flow_key->ipv4.tp.dst)
- return 0;
- } else if (flow_key->eth.type == htons(ETH_P_IPV6)) {
- if (flow_key->ipv6.tp.src || flow_key->ipv6.tp.dst)
- return 0;
+ if (plen > 0)
+ memset(skb_put(user_skb, plen), 0, plen);
}
- return -EINVAL;
-}
-
-static int validate_and_copy_set_tun(const struct nlattr *attr,
- struct sw_flow_actions **sfa)
-{
- struct ovs_key_ipv4_tunnel tun_key;
- int err, start;
-
- err = ipv4_tun_from_nlattr(nla_data(attr), &tun_key);
- if (err)
- return err;
-
- start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET);
- if (start < 0)
- return start;
-
- err = add_action(sfa, OVS_KEY_ATTR_IPV4_TUNNEL, &tun_key, sizeof(tun_key));
- add_nested_action_end(*sfa, start);
+ ((struct nlmsghdr *) user_skb->data)->nlmsg_len = user_skb->len;
+ err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid);
+out:
+ kfree_skb(nskb);
return err;
}
-static int validate_set(const struct nlattr *a,
- const struct sw_flow_key *flow_key,
- struct sw_flow_actions **sfa,
- bool *set_tun)
-{
- const struct nlattr *ovs_key = nla_data(a);
- int key_type = nla_type(ovs_key);
-
- /* There can be only one key in a action */
- if (nla_total_size(nla_len(ovs_key)) != nla_len(a))
- return -EINVAL;
-
- if (key_type > OVS_KEY_ATTR_MAX ||
- (ovs_key_lens[key_type] != nla_len(ovs_key) &&
- ovs_key_lens[key_type] != -1))
- return -EINVAL;
-
- switch (key_type) {
- const struct ovs_key_ipv4 *ipv4_key;
- const struct ovs_key_ipv6 *ipv6_key;
- int err;
-
- case OVS_KEY_ATTR_PRIORITY:
- case OVS_KEY_ATTR_TUN_ID:
- case OVS_KEY_ATTR_ETHERNET:
- break;
-
- case OVS_KEY_ATTR_SKB_MARK:
-#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,20) && !defined(CONFIG_NETFILTER)
- if (nla_get_u32(ovs_key) != 0)
- return -EINVAL;
-#endif
- break;
-
- case OVS_KEY_ATTR_TUNNEL:
- *set_tun = true;
- err = validate_and_copy_set_tun(a, sfa);
- if (err)
- return err;
- break;
-
- case OVS_KEY_ATTR_IPV4:
- if (flow_key->eth.type != htons(ETH_P_IP))
- return -EINVAL;
-
- if (!flow_key->ip.proto)
- return -EINVAL;
-
- ipv4_key = nla_data(ovs_key);
- if (ipv4_key->ipv4_proto != flow_key->ip.proto)
- return -EINVAL;
-
- if (ipv4_key->ipv4_frag != flow_key->ip.frag)
- return -EINVAL;
-
- break;
-
- case OVS_KEY_ATTR_IPV6:
- if (flow_key->eth.type != htons(ETH_P_IPV6))
- return -EINVAL;
-
- if (!flow_key->ip.proto)
- return -EINVAL;
-
- ipv6_key = nla_data(ovs_key);
- if (ipv6_key->ipv6_proto != flow_key->ip.proto)
- return -EINVAL;
-
- if (ipv6_key->ipv6_frag != flow_key->ip.frag)
- return -EINVAL;
-
- if (ntohl(ipv6_key->ipv6_label) & 0xFFF00000)
- return -EINVAL;
-
- break;
-
- case OVS_KEY_ATTR_TCP:
- if (flow_key->ip.proto != IPPROTO_TCP)
- return -EINVAL;
-
- return validate_tp_port(flow_key);
-
- case OVS_KEY_ATTR_UDP:
- if (flow_key->ip.proto != IPPROTO_UDP)
- return -EINVAL;
-
- return validate_tp_port(flow_key);
-
- default:
- return -EINVAL;
- }
-
- return 0;
-}
-
-static int validate_userspace(const struct nlattr *attr)
-{
- static const struct nla_policy userspace_policy[OVS_USERSPACE_ATTR_MAX + 1] = {
- [OVS_USERSPACE_ATTR_PID] = {.type = NLA_U32 },
- [OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_U64 },
- };
- struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
- int error;
-
- error = nla_parse_nested(a, OVS_USERSPACE_ATTR_MAX,
- attr, userspace_policy);
- if (error)
- return error;
-
- if (!a[OVS_USERSPACE_ATTR_PID] ||
- !nla_get_u32(a[OVS_USERSPACE_ATTR_PID]))
- return -EINVAL;
-
- return 0;
-}
-
-static int copy_action(const struct nlattr *from,
- struct sw_flow_actions **sfa)
-{
- int totlen = NLA_ALIGN(from->nla_len);
- struct nlattr *to;
-
- to = reserve_sfa_size(sfa, from->nla_len);
- if (IS_ERR(to))
- return PTR_ERR(to);
-
- memcpy(to, from, totlen);
- return 0;
-}
-
-static int validate_and_copy_actions(const struct nlattr *attr,
- const struct sw_flow_key *key,
- int depth,
- struct sw_flow_actions **sfa)
-{
- const struct nlattr *a;
- int rem, err;
-
- if (depth >= SAMPLE_ACTION_DEPTH)
- return -EOVERFLOW;
-
- nla_for_each_nested(a, attr, rem) {
- /* Expected argument lengths, (u32)-1 for variable length. */
- static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
- [OVS_ACTION_ATTR_OUTPUT] = sizeof(u32),
- [OVS_ACTION_ATTR_USERSPACE] = (u32)-1,
- [OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
- [OVS_ACTION_ATTR_POP_VLAN] = 0,
- [OVS_ACTION_ATTR_SET] = (u32)-1,
- [OVS_ACTION_ATTR_SAMPLE] = (u32)-1
- };
- const struct ovs_action_push_vlan *vlan;
- int type = nla_type(a);
- bool skip_copy;
-
- if (type > OVS_ACTION_ATTR_MAX ||
- (action_lens[type] != nla_len(a) &&
- action_lens[type] != (u32)-1))
- return -EINVAL;
-
- skip_copy = false;
- switch (type) {
- case OVS_ACTION_ATTR_UNSPEC:
- return -EINVAL;
-
- case OVS_ACTION_ATTR_USERSPACE:
- err = validate_userspace(a);
- if (err)
- return err;
- break;
-
- case OVS_ACTION_ATTR_OUTPUT:
- if (nla_get_u32(a) >= DP_MAX_PORTS)
- return -EINVAL;
- break;
-
-
- case OVS_ACTION_ATTR_POP_VLAN:
- break;
-
- case OVS_ACTION_ATTR_PUSH_VLAN:
- vlan = nla_data(a);
- if (vlan->vlan_tpid != htons(ETH_P_8021Q))
- return -EINVAL;
- if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT)))
- return -EINVAL;
- break;
-
- case OVS_ACTION_ATTR_SET:
- err = validate_set(a, key, sfa, &skip_copy);
- if (err)
- return err;
- break;
-
- case OVS_ACTION_ATTR_SAMPLE:
- err = validate_and_copy_sample(a, key, depth, sfa);
- if (err)
- return err;
- skip_copy = true;
- break;
-
- default:
- return -EINVAL;
- }
- if (!skip_copy) {
- err = copy_action(a, sfa);
- if (err)
- return err;
- }
- }
-
- if (rem > 0)
- return -EINVAL;
-
- return 0;
-}
-
-static void clear_stats(struct sw_flow *flow)
-{
- flow->used = 0;
- flow->tcp_flags = 0;
- flow->packet_count = 0;
- flow->byte_count = 0;
-}
-
static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
{
struct ovs_header *ovs_header = info->userhdr;
struct ethhdr *eth;
int len;
int err;
- int key_len;
err = -EINVAL;
if (!a[OVS_PACKET_ATTR_PACKET] || !a[OVS_PACKET_ATTR_KEY] ||
- !a[OVS_PACKET_ATTR_ACTIONS] ||
- nla_len(a[OVS_PACKET_ATTR_PACKET]) < ETH_HLEN)
+ !a[OVS_PACKET_ATTR_ACTIONS])
goto err;
len = nla_len(a[OVS_PACKET_ATTR_PACKET]);
goto err;
skb_reserve(packet, NET_IP_ALIGN);
- memcpy(__skb_put(packet, len), nla_data(a[OVS_PACKET_ATTR_PACKET]), len);
+ nla_memcpy(__skb_put(packet, len), a[OVS_PACKET_ATTR_PACKET], len);
skb_reset_mac_header(packet);
eth = eth_hdr(packet);
/* Normally, setting the skb 'protocol' field would be handled by a
* call to eth_type_trans(), but it assumes there's a sending
* device, which we may not have. */
- if (ntohs(eth->h_proto) >= 1536)
+ if (ntohs(eth->h_proto) >= ETH_P_802_3_MIN)
packet->protocol = eth->h_proto;
else
packet->protocol = htons(ETH_P_802_2);
if (IS_ERR(flow))
goto err_kfree_skb;
- err = ovs_flow_extract(packet, -1, &flow->key, &key_len);
+ err = ovs_flow_extract(packet, -1, &flow->key);
if (err)
goto err_flow_free;
- err = ovs_flow_metadata_from_nlattrs(flow, key_len, a[OVS_PACKET_ATTR_KEY]);
+ err = ovs_nla_get_flow_metadata(flow, a[OVS_PACKET_ATTR_KEY]);
if (err)
goto err_flow_free;
- acts = ovs_flow_actions_alloc(nla_len(a[OVS_PACKET_ATTR_ACTIONS]));
+ acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_PACKET_ATTR_ACTIONS]));
err = PTR_ERR(acts);
if (IS_ERR(acts))
goto err_flow_free;
- err = validate_and_copy_actions(a[OVS_PACKET_ATTR_ACTIONS], &flow->key, 0, &acts);
+ err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS],
+ &flow->key, 0, &acts);
rcu_assign_pointer(flow->sf_acts, acts);
if (err)
goto err_flow_free;
OVS_CB(packet)->flow = flow;
+ OVS_CB(packet)->pkt_key = &flow->key;
packet->priority = flow->key.phy.priority;
- skb_set_mark(packet, flow->key.phy.skb_mark);
+ packet->mark = flow->key.phy.skb_mark;
rcu_read_lock();
dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
local_bh_enable();
rcu_read_unlock();
- ovs_flow_free(flow);
+ ovs_flow_free(flow, false);
return err;
err_unlock:
rcu_read_unlock();
err_flow_free:
- ovs_flow_free(flow);
+ ovs_flow_free(flow, false);
err_kfree_skb:
kfree_skb(packet);
err:
}
static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = {
- [OVS_PACKET_ATTR_PACKET] = { .type = NLA_UNSPEC },
+ [OVS_PACKET_ATTR_PACKET] = { .len = ETH_HLEN },
[OVS_PACKET_ATTR_KEY] = { .type = NLA_NESTED },
[OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED },
};
}
};
-static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats)
+static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
+ struct ovs_dp_megaflow_stats *mega_stats)
{
int i;
- struct flow_table *table = genl_dereference(dp->table);
- stats->n_flows = ovs_flow_tbl_count(table);
+ memset(mega_stats, 0, sizeof(*mega_stats));
+
+ stats->n_flows = ovs_flow_tbl_count(&dp->table);
+ mega_stats->n_masks = ovs_flow_tbl_num_masks(&dp->table);
stats->n_hit = stats->n_missed = stats->n_lost = 0;
+
for_each_possible_cpu(i) {
const struct dp_stats_percpu *percpu_stats;
struct dp_stats_percpu local_stats;
stats->n_hit += local_stats.n_hit;
stats->n_missed += local_stats.n_missed;
stats->n_lost += local_stats.n_lost;
+ mega_stats->n_mask_hit += local_stats.n_mask_hit;
}
}
.name = OVS_FLOW_FAMILY,
.version = OVS_FLOW_VERSION,
.maxattr = OVS_FLOW_ATTR_MAX,
- SET_NETNSOK
+ .netnsok = true,
+ SET_PARALLEL_OPS
};
static struct genl_multicast_group ovs_dp_flow_multicast_group = {
.name = OVS_FLOW_MCGROUP
};
-static int actions_to_attr(const struct nlattr *attr, int len, struct sk_buff *skb);
-static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb)
+static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts)
{
- const struct nlattr *a;
- struct nlattr *start;
- int err = 0, rem;
-
- start = nla_nest_start(skb, OVS_ACTION_ATTR_SAMPLE);
- if (!start)
- return -EMSGSIZE;
-
- nla_for_each_nested(a, attr, rem) {
- int type = nla_type(a);
- struct nlattr *st_sample;
-
- switch (type) {
- case OVS_SAMPLE_ATTR_PROBABILITY:
- if (nla_put(skb, OVS_SAMPLE_ATTR_PROBABILITY, sizeof(u32), nla_data(a)))
- return -EMSGSIZE;
- break;
- case OVS_SAMPLE_ATTR_ACTIONS:
- st_sample = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS);
- if (!st_sample)
- return -EMSGSIZE;
- err = actions_to_attr(nla_data(a), nla_len(a), skb);
- if (err)
- return err;
- nla_nest_end(skb, st_sample);
- break;
- }
- }
-
- nla_nest_end(skb, start);
- return err;
+ return NLMSG_ALIGN(sizeof(struct ovs_header))
+ + nla_total_size(key_attr_size()) /* OVS_FLOW_ATTR_KEY */
+ + nla_total_size(key_attr_size()) /* OVS_FLOW_ATTR_MASK */
+ + nla_total_size(sizeof(struct ovs_flow_stats)) /* OVS_FLOW_ATTR_STATS */
+ + nla_total_size(1) /* OVS_FLOW_ATTR_TCP_FLAGS */
+ + nla_total_size(8) /* OVS_FLOW_ATTR_USED */
+ + nla_total_size(acts->actions_len); /* OVS_FLOW_ATTR_ACTIONS */
}
-static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
-{
- const struct nlattr *ovs_key = nla_data(a);
- int key_type = nla_type(ovs_key);
- struct nlattr *start;
- int err;
-
- switch (key_type) {
- case OVS_KEY_ATTR_IPV4_TUNNEL:
- start = nla_nest_start(skb, OVS_ACTION_ATTR_SET);
- if (!start)
- return -EMSGSIZE;
-
- err = ipv4_tun_to_nlattr(skb, nla_data(ovs_key));
- if (err)
- return err;
- nla_nest_end(skb, start);
- break;
- default:
- if (nla_put(skb, OVS_ACTION_ATTR_SET, nla_len(a), ovs_key))
- return -EMSGSIZE;
- break;
- }
-
- return 0;
-}
-
-static int actions_to_attr(const struct nlattr *attr, int len, struct sk_buff *skb)
-{
- const struct nlattr *a;
- int rem, err;
-
- nla_for_each_attr(a, attr, len, rem) {
- int type = nla_type(a);
-
- switch (type) {
- case OVS_ACTION_ATTR_SET:
- err = set_action_to_attr(a, skb);
- if (err)
- return err;
- break;
-
- case OVS_ACTION_ATTR_SAMPLE:
- err = sample_action_to_attr(a, skb);
- if (err)
- return err;
- break;
- default:
- if (nla_put(skb, type, nla_len(a), nla_data(a)))
- return -EMSGSIZE;
- break;
- }
- }
-
- return 0;
-}
-
-/* Called with genl_lock. */
+/* Called with ovs_mutex or RCU read lock. */
static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
struct sk_buff *skb, u32 portid,
u32 seq, u32 flags, u8 cmd)
{
const int skb_orig_len = skb->len;
- const struct sw_flow_actions *sf_acts;
struct nlattr *start;
struct ovs_flow_stats stats;
+ __be16 tcp_flags;
+ unsigned long used;
struct ovs_header *ovs_header;
struct nlattr *nla;
- unsigned long used;
- u8 tcp_flags;
int err;
- sf_acts = rcu_dereference_protected(flow->sf_acts,
- lockdep_genl_is_held());
-
ovs_header = genlmsg_put(skb, portid, seq, &dp_flow_genl_family, flags, cmd);
if (!ovs_header)
return -EMSGSIZE;
ovs_header->dp_ifindex = get_dpifindex(dp);
- nla = nla_nest_start(skb, OVS_FLOW_ATTR_KEY);
+ /* Fill flow key. */
+ nla = nla_nest_start(skb, OVS_FLOW_ATTR_KEY);
+ if (!nla)
+ goto nla_put_failure;
+
+ err = ovs_nla_put_flow(&flow->unmasked_key, &flow->unmasked_key, skb);
+ if (err)
+ goto error;
+ nla_nest_end(skb, nla);
+
+ nla = nla_nest_start(skb, OVS_FLOW_ATTR_MASK);
if (!nla)
goto nla_put_failure;
- err = ovs_flow_to_nlattrs(&flow->key, skb);
+
+ err = ovs_nla_put_flow(&flow->key, &flow->mask->key, skb);
if (err)
goto error;
- nla_nest_end(skb, nla);
- spin_lock_bh(&flow->lock);
- used = flow->used;
- stats.n_packets = flow->packet_count;
- stats.n_bytes = flow->byte_count;
- tcp_flags = flow->tcp_flags;
- spin_unlock_bh(&flow->lock);
+ nla_nest_end(skb, nla);
+ ovs_flow_stats_get(flow, &stats, &used, &tcp_flags);
if (used &&
nla_put_u64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used)))
goto nla_put_failure;
if (stats.n_packets &&
- nla_put(skb, OVS_FLOW_ATTR_STATS,
- sizeof(struct ovs_flow_stats), &stats))
+ nla_put(skb, OVS_FLOW_ATTR_STATS, sizeof(struct ovs_flow_stats), &stats))
goto nla_put_failure;
- if (tcp_flags &&
- nla_put_u8(skb, OVS_FLOW_ATTR_TCP_FLAGS, tcp_flags))
+ if ((u8)ntohs(tcp_flags) &&
+ nla_put_u8(skb, OVS_FLOW_ATTR_TCP_FLAGS, (u8)ntohs(tcp_flags)))
goto nla_put_failure;
/* If OVS_FLOW_ATTR_ACTIONS doesn't fit, skip dumping the actions if
*/
start = nla_nest_start(skb, OVS_FLOW_ATTR_ACTIONS);
if (start) {
- err = actions_to_attr(sf_acts->actions, sf_acts->actions_len, skb);
+ const struct sw_flow_actions *sf_acts;
+
+ sf_acts = rcu_dereference_ovsl(flow->sf_acts);
+
+ err = ovs_nla_put_actions(sf_acts->actions,
+ sf_acts->actions_len, skb);
if (!err)
nla_nest_end(skb, start);
else {
return err;
}
-static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow)
+/* Must be called with ovs_mutex. */
+static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow,
+ struct genl_info *info,
+ bool always)
{
- const struct sw_flow_actions *sf_acts;
- int len;
+ struct sk_buff *skb;
+ size_t len;
+
+ if (!always && !ovs_must_notify(info, &ovs_dp_flow_multicast_group))
+ return NULL;
- sf_acts = rcu_dereference_protected(flow->sf_acts,
- lockdep_genl_is_held());
+ len = ovs_flow_cmd_msg_size(ovsl_dereference(flow->sf_acts));
- /* OVS_FLOW_ATTR_KEY */
- len = nla_total_size(FLOW_BUFSIZE);
- /* OVS_FLOW_ATTR_ACTIONS */
- len += nla_total_size(sf_acts->actions_len);
- /* OVS_FLOW_ATTR_STATS */
- len += nla_total_size(sizeof(struct ovs_flow_stats));
- /* OVS_FLOW_ATTR_TCP_FLAGS */
- len += nla_total_size(1);
- /* OVS_FLOW_ATTR_USED */
- len += nla_total_size(8);
+ skb = genlmsg_new_unicast(len, info, GFP_KERNEL);
- len += NLMSG_ALIGN(sizeof(struct ovs_header));
+ if (!skb)
+ return ERR_PTR(-ENOMEM);
- return genlmsg_new(len, GFP_KERNEL);
+ return skb;
}
+/* Must be called with ovs_mutex. */
static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow,
struct datapath *dp,
- u32 portid, u32 seq, u8 cmd)
+ struct genl_info *info,
+ u8 cmd, bool always)
{
struct sk_buff *skb;
int retval;
- skb = ovs_flow_cmd_alloc_info(flow);
- if (!skb)
- return ERR_PTR(-ENOMEM);
+ skb = ovs_flow_cmd_alloc_info(flow, info, always);
+ if (!skb || IS_ERR(skb))
+ return skb;
- retval = ovs_flow_cmd_fill_info(flow, dp, skb, portid, seq, 0, cmd);
+ retval = ovs_flow_cmd_fill_info(flow, dp, skb, info->snd_portid,
+ info->snd_seq, 0, cmd);
BUG_ON(retval < 0);
return skb;
}
{
struct nlattr **a = info->attrs;
struct ovs_header *ovs_header = info->userhdr;
- struct sw_flow_key key;
- struct sw_flow *flow;
+ struct sw_flow_key key, masked_key;
+ struct sw_flow *flow = NULL;
+ struct sw_flow_mask mask;
struct sk_buff *reply;
struct datapath *dp;
- struct flow_table *table;
struct sw_flow_actions *acts = NULL;
+ struct sw_flow_match match;
int error;
- int key_len;
/* Extract key. */
error = -EINVAL;
if (!a[OVS_FLOW_ATTR_KEY])
goto error;
- error = ovs_flow_from_nlattrs(&key, &key_len, a[OVS_FLOW_ATTR_KEY]);
+
+ ovs_match_init(&match, &key, &mask);
+ error = ovs_nla_get_match(&match,
+ a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]);
if (error)
goto error;
/* Validate actions. */
if (a[OVS_FLOW_ATTR_ACTIONS]) {
- acts = ovs_flow_actions_alloc(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
+ acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
error = PTR_ERR(acts);
if (IS_ERR(acts))
goto error;
- error = validate_and_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, 0, &acts);
- if (error)
+ ovs_flow_mask_key(&masked_key, &key, &mask);
+ error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS],
+ &masked_key, 0, &acts);
+ if (error) {
+ OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
goto err_kfree;
+ }
} else if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW) {
+ /* OVS_FLOW_CMD_NEW must have actions. */
error = -EINVAL;
goto error;
}
+ ovs_lock();
dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
error = -ENODEV;
if (!dp)
- goto err_kfree;
+ goto err_unlock_ovs;
- table = genl_dereference(dp->table);
- flow = ovs_flow_tbl_lookup(table, &key, key_len);
+ /* Check if this is a duplicate flow */
+ flow = ovs_flow_tbl_lookup(&dp->table, &key);
if (!flow) {
/* Bail out if we're not allowed to create a new flow. */
error = -ENOENT;
if (info->genlhdr->cmd == OVS_FLOW_CMD_SET)
- goto err_kfree;
-
- /* Expand table, if necessary, to make room. */
- if (ovs_flow_tbl_need_to_expand(table)) {
- struct flow_table *new_table;
-
- new_table = ovs_flow_tbl_expand(table);
- if (!IS_ERR(new_table)) {
- rcu_assign_pointer(dp->table, new_table);
- ovs_flow_tbl_deferred_destroy(table);
- table = genl_dereference(dp->table);
- }
- }
+ goto err_unlock_ovs;
/* Allocate flow. */
flow = ovs_flow_alloc();
if (IS_ERR(flow)) {
error = PTR_ERR(flow);
- goto err_kfree;
+ goto err_unlock_ovs;
}
- clear_stats(flow);
+ flow->key = masked_key;
+ flow->unmasked_key = key;
rcu_assign_pointer(flow->sf_acts, acts);
/* Put flow in bucket. */
- ovs_flow_tbl_insert(table, flow, &key, key_len);
+ error = ovs_flow_tbl_insert(&dp->table, flow, &mask);
+ if (error) {
+ acts = NULL;
+ goto err_flow_free;
+ }
- reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid,
- info->snd_seq,
- OVS_FLOW_CMD_NEW);
+ reply = ovs_flow_cmd_build_info(flow, dp, info,
+ OVS_FLOW_CMD_NEW, false);
} else {
/* We found a matching flow. */
- struct sw_flow_actions *old_acts;
-
/* Bail out if we're not allowed to modify an existing flow.
* We accept NLM_F_CREATE in place of the intended NLM_F_EXCL
* because Generic Netlink treats the latter as a dump
error = -EEXIST;
if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW &&
info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL))
- goto err_kfree;
+ goto err_unlock_ovs;
- /* Update actions. */
- old_acts = rcu_dereference_protected(flow->sf_acts,
- lockdep_genl_is_held());
- rcu_assign_pointer(flow->sf_acts, acts);
- ovs_flow_deferred_free_acts(old_acts);
+ /* The unmasked key has to be the same for flow updates. */
+ if (!ovs_flow_cmp_unmasked_key(flow, &match))
+ goto err_unlock_ovs;
- reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid,
- info->snd_seq, OVS_FLOW_CMD_NEW);
+ /* Update actions, if present. */
+ if (acts) {
+ struct sw_flow_actions *old_acts;
- /* Clear stats. */
- if (a[OVS_FLOW_ATTR_CLEAR]) {
- spin_lock_bh(&flow->lock);
- clear_stats(flow);
- spin_unlock_bh(&flow->lock);
+ old_acts = ovsl_dereference(flow->sf_acts);
+ rcu_assign_pointer(flow->sf_acts, acts);
+ ovs_nla_free_flow_actions(old_acts);
}
+ reply = ovs_flow_cmd_build_info(flow, dp, info,
+ OVS_FLOW_CMD_NEW, false);
+
+ /* Clear stats. */
+ if (a[OVS_FLOW_ATTR_CLEAR])
+ ovs_flow_stats_clear(flow);
}
+ ovs_unlock();
- if (!IS_ERR(reply))
- genl_notify(reply, genl_info_net(info), info->snd_portid,
- ovs_dp_flow_multicast_group.id, info->nlhdr,
- GFP_KERNEL);
- else
- netlink_set_err(GENL_SOCK(sock_net(skb->sk)), 0,
- ovs_dp_flow_multicast_group.id, PTR_ERR(reply));
+ if (reply) {
+ if (!IS_ERR(reply))
+ ovs_notify(reply, info, &ovs_dp_flow_multicast_group);
+ else
+ netlink_set_err(sock_net(skb->sk)->genl_sock, 0,
+ ovs_dp_flow_multicast_group.id,
+ PTR_ERR(reply));
+ }
return 0;
+err_flow_free:
+ ovs_flow_free(flow, false);
+err_unlock_ovs:
+ ovs_unlock();
err_kfree:
kfree(acts);
error:
struct sk_buff *reply;
struct sw_flow *flow;
struct datapath *dp;
- struct flow_table *table;
+ struct sw_flow_match match;
int err;
- int key_len;
- if (!a[OVS_FLOW_ATTR_KEY])
+ if (!a[OVS_FLOW_ATTR_KEY]) {
+ OVS_NLERR("Flow get message rejected, Key attribute missing.\n");
return -EINVAL;
- err = ovs_flow_from_nlattrs(&key, &key_len, a[OVS_FLOW_ATTR_KEY]);
+ }
+
+ ovs_match_init(&match, &key, NULL);
+ err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
if (err)
return err;
+ ovs_lock();
dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
- if (!dp)
- return -ENODEV;
+ if (!dp) {
+ err = -ENODEV;
+ goto unlock;
+ }
- table = genl_dereference(dp->table);
- flow = ovs_flow_tbl_lookup(table, &key, key_len);
- if (!flow)
- return -ENOENT;
+ flow = ovs_flow_tbl_lookup(&dp->table, &key);
+ if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) {
+ err = -ENOENT;
+ goto unlock;
+ }
- reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid,
- info->snd_seq, OVS_FLOW_CMD_NEW);
- if (IS_ERR(reply))
- return PTR_ERR(reply);
+ reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW, true);
+ if (IS_ERR(reply)) {
+ err = PTR_ERR(reply);
+ goto unlock;
+ }
+ ovs_unlock();
return genlmsg_reply(reply, info);
+unlock:
+ ovs_unlock();
+ return err;
}
static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
struct sk_buff *reply;
struct sw_flow *flow;
struct datapath *dp;
- struct flow_table *table;
+ struct sw_flow_match match;
int err;
- int key_len;
+ ovs_lock();
dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
- if (!dp)
- return -ENODEV;
+ if (!dp) {
+ err = -ENODEV;
+ goto unlock;
+ }
- if (!a[OVS_FLOW_ATTR_KEY])
- return flush_flows(dp);
+ if (!a[OVS_FLOW_ATTR_KEY]) {
+ err = ovs_flow_tbl_flush(&dp->table);
+ goto unlock;
+ }
- err = ovs_flow_from_nlattrs(&key, &key_len, a[OVS_FLOW_ATTR_KEY]);
+ ovs_match_init(&match, &key, NULL);
+ err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
if (err)
- return err;
+ goto unlock;
- table = genl_dereference(dp->table);
- flow = ovs_flow_tbl_lookup(table, &key, key_len);
- if (!flow)
- return -ENOENT;
+ flow = ovs_flow_tbl_lookup(&dp->table, &key);
+ if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) {
+ err = -ENOENT;
+ goto unlock;
+ }
- reply = ovs_flow_cmd_alloc_info(flow);
- if (!reply)
- return -ENOMEM;
+ reply = ovs_flow_cmd_alloc_info(flow, info, false);
+ if (IS_ERR(reply)) {
+ err = PTR_ERR(reply);
+ goto unlock;
+ }
- ovs_flow_tbl_remove(table, flow);
+ ovs_flow_tbl_remove(&dp->table, flow);
- err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_portid,
- info->snd_seq, 0, OVS_FLOW_CMD_DEL);
- BUG_ON(err < 0);
+ if (reply) {
+ err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_portid,
+ info->snd_seq, 0,
+ OVS_FLOW_CMD_DEL);
+ BUG_ON(err < 0);
+ }
- ovs_flow_deferred_free(flow);
+ ovs_flow_free(flow, true);
+ ovs_unlock();
- genl_notify(reply, genl_info_net(info), info->snd_portid,
- ovs_dp_flow_multicast_group.id, info->nlhdr, GFP_KERNEL);
+ if (reply)
+ ovs_notify(reply, info, &ovs_dp_flow_multicast_group);
return 0;
+unlock:
+ ovs_unlock();
+ return err;
}
static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
struct ovs_header *ovs_header = genlmsg_data(nlmsg_data(cb->nlh));
+ struct table_instance *ti;
struct datapath *dp;
- struct flow_table *table;
+ rcu_read_lock();
dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
- if (!dp)
+ if (!dp) {
+ rcu_read_unlock();
return -ENODEV;
+ }
- table = genl_dereference(dp->table);
-
+ ti = rcu_dereference(dp->table.ti);
for (;;) {
struct sw_flow *flow;
u32 bucket, obj;
bucket = cb->args[0];
obj = cb->args[1];
- flow = ovs_flow_tbl_next(table, &bucket, &obj);
+ flow = ovs_flow_tbl_dump_next(ti, &bucket, &obj);
if (!flow)
break;
cb->args[0] = bucket;
cb->args[1] = obj;
}
+ rcu_read_unlock();
return skb->len;
}
};
static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
-#ifdef HAVE_NLA_NUL_STRING
[OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
-#endif
[OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+ [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 },
};
static struct genl_family dp_datapath_genl_family = {
.name = OVS_DATAPATH_FAMILY,
.version = OVS_DATAPATH_VERSION,
.maxattr = OVS_DP_ATTR_MAX,
- SET_NETNSOK
+ .netnsok = true,
+ SET_PARALLEL_OPS
};
static struct genl_multicast_group ovs_dp_datapath_multicast_group = {
.name = OVS_DATAPATH_MCGROUP
};
+static size_t ovs_dp_cmd_msg_size(void)
+{
+ size_t msgsize = NLMSG_ALIGN(sizeof(struct ovs_header));
+
+ 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;
+}
+
+/* Called with ovs_mutex or RCU read lock. */
static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
u32 portid, u32 seq, u32 flags, u8 cmd)
{
struct ovs_header *ovs_header;
struct ovs_dp_stats dp_stats;
+ struct ovs_dp_megaflow_stats dp_megaflow_stats;
int err;
ovs_header = genlmsg_put(skb, portid, seq, &dp_datapath_genl_family,
ovs_header->dp_ifindex = get_dpifindex(dp);
- rcu_read_lock();
err = nla_put_string(skb, OVS_DP_ATTR_NAME, ovs_dp_name(dp));
- rcu_read_unlock();
if (err)
goto nla_put_failure;
- get_dp_stats(dp, &dp_stats);
- if (nla_put(skb, OVS_DP_ATTR_STATS, sizeof(struct ovs_dp_stats), &dp_stats))
+ get_dp_stats(dp, &dp_stats, &dp_megaflow_stats);
+ if (nla_put(skb, OVS_DP_ATTR_STATS, sizeof(struct ovs_dp_stats),
+ &dp_stats))
+ goto nla_put_failure;
+
+ if (nla_put(skb, OVS_DP_ATTR_MEGAFLOW_STATS,
+ sizeof(struct ovs_dp_megaflow_stats),
+ &dp_megaflow_stats))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, OVS_DP_ATTR_USER_FEATURES, dp->user_features))
goto nla_put_failure;
return genlmsg_end(skb, ovs_header);
return -EMSGSIZE;
}
-static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, u32 portid,
- u32 seq, u8 cmd)
-{
- struct sk_buff *skb;
- int retval;
-
- skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!skb)
- return ERR_PTR(-ENOMEM);
-
- retval = ovs_dp_cmd_fill_info(dp, skb, portid, seq, 0, cmd);
- if (retval < 0) {
- kfree_skb(skb);
- return ERR_PTR(retval);
- }
- return skb;
-}
-
-static int ovs_dp_cmd_validate(struct nlattr *a[OVS_DP_ATTR_MAX + 1])
+static struct sk_buff *ovs_dp_cmd_alloc_info(struct genl_info *info)
{
- return CHECK_NUL_STRING(a[OVS_DP_ATTR_NAME], IFNAMSIZ - 1);
+ return genlmsg_new_unicast(ovs_dp_cmd_msg_size(), info, GFP_KERNEL);
}
-/* Called with genl_mutex and optionally with RTNL lock also. */
+/* Called with rcu_read_lock or ovs_mutex. */
static struct datapath *lookup_datapath(struct net *net,
struct ovs_header *ovs_header,
struct nlattr *a[OVS_DP_ATTR_MAX + 1])
else {
struct vport *vport;
- rcu_read_lock();
vport = ovs_vport_locate(net, nla_data(a[OVS_DP_ATTR_NAME]));
dp = vport && vport->port_no == OVSP_LOCAL ? vport->dp : NULL;
- rcu_read_unlock();
}
return dp ? dp : ERR_PTR(-ENODEV);
}
+static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *info)
+{
+ struct datapath *dp;
+
+ dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
+ if (IS_ERR(dp))
+ return;
+
+ WARN(dp->user_features, "Dropping previously announced user features\n");
+ dp->user_features = 0;
+}
+
+static void ovs_dp_change(struct datapath *dp, struct nlattr **a)
+{
+ if (a[OVS_DP_ATTR_USER_FEATURES])
+ dp->user_features = nla_get_u32(a[OVS_DP_ATTR_USER_FEATURES]);
+}
+
static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
{
struct nlattr **a = info->attrs;
if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID])
goto err;
- err = ovs_dp_cmd_validate(a);
- if (err)
- goto err;
-
- rtnl_lock();
+ reply = ovs_dp_cmd_alloc_info(info);
+ if (!reply)
+ return -ENOMEM;
err = -ENOMEM;
dp = kzalloc(sizeof(*dp), GFP_KERNEL);
if (dp == NULL)
- goto err_unlock_rtnl;
+ goto err_free_reply;
ovs_dp_set_net(dp, hold_net(sock_net(skb->sk)));
/* Allocate table. */
- err = -ENOMEM;
- rcu_assign_pointer(dp->table, ovs_flow_tbl_alloc(TBL_MIN_BUCKETS));
- if (!dp->table)
+ err = ovs_flow_tbl_init(&dp->table);
+ if (err)
goto err_free_dp;
dp->stats_percpu = alloc_percpu(struct dp_stats_percpu);
parms.port_no = OVSP_LOCAL;
parms.upcall_portid = nla_get_u32(a[OVS_DP_ATTR_UPCALL_PID]);
+ ovs_dp_change(dp, a);
+
+ /* So far only local changes have been made, now need the lock. */
+ ovs_lock();
+
vport = new_vport(&parms);
if (IS_ERR(vport)) {
err = PTR_ERR(vport);
if (err == -EBUSY)
err = -EEXIST;
+ if (err == -EEXIST) {
+ /* An outdated user space instance that does not understand
+ * the concept of user_features has attempted to create a new
+ * datapath and is likely to reuse it. Drop all user features.
+ */
+ if (info->genlhdr->version < OVS_DP_VER_FEATURES)
+ ovs_dp_reset_user_features(skb, info);
+ }
+
goto err_destroy_ports_array;
}
- reply = ovs_dp_cmd_build_info(dp, info->snd_portid,
- info->snd_seq, OVS_DP_CMD_NEW);
- err = PTR_ERR(reply);
- if (IS_ERR(reply))
- goto err_destroy_local_port;
+ err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_DP_CMD_NEW);
+ BUG_ON(err < 0);
ovs_net = net_generic(ovs_dp_get_net(dp), ovs_net_id);
- list_add_tail(&dp->list_node, &ovs_net->dps);
+ list_add_tail_rcu(&dp->list_node, &ovs_net->dps);
- rtnl_unlock();
+ ovs_unlock();
- genl_notify(reply, genl_info_net(info), info->snd_portid,
- ovs_dp_datapath_multicast_group.id, info->nlhdr,
- GFP_KERNEL);
+ ovs_notify(reply, info, &ovs_dp_datapath_multicast_group);
return 0;
-err_destroy_local_port:
- ovs_dp_detach_port(ovs_vport_rtnl(dp, OVSP_LOCAL));
err_destroy_ports_array:
+ ovs_unlock();
kfree(dp->ports);
err_destroy_percpu:
free_percpu(dp->stats_percpu);
err_destroy_table:
- ovs_flow_tbl_destroy(genl_dereference(dp->table));
+ ovs_flow_tbl_destroy(&dp->table, false);
err_free_dp:
release_net(ovs_dp_get_net(dp));
kfree(dp);
-err_unlock_rtnl:
- rtnl_unlock();
+err_free_reply:
+ kfree_skb(reply);
err:
return err;
}
-/* Called with genl_mutex. */
+/* Called with ovs_mutex. */
static void __dp_destroy(struct datapath *dp)
{
int i;
- rtnl_lock();
-
for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
struct vport *vport;
- struct hlist_node *node, *n;
+ struct hlist_node *n;
- hlist_for_each_entry_safe(vport, node, n, &dp->ports[i], dp_hash_node)
+ hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node)
if (vport->port_no != OVSP_LOCAL)
ovs_dp_detach_port(vport);
}
- list_del(&dp->list_node);
- ovs_dp_detach_port(ovs_vport_rtnl(dp, OVSP_LOCAL));
+ list_del_rcu(&dp->list_node);
- /* rtnl_unlock() will wait until all the references to devices that
- * are pending unregistration have been dropped. We do it here to
- * ensure that any internal devices (which contain DP pointers) are
- * fully destroyed before freeing the datapath.
+ /* OVSP_LOCAL is datapath internal port. We need to make sure that
+ * all ports in datapath are destroyed first before freeing datapath.
*/
- rtnl_unlock();
+ 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);
}
struct datapath *dp;
int err;
- err = ovs_dp_cmd_validate(info->attrs);
- if (err)
- return err;
+ reply = ovs_dp_cmd_alloc_info(info);
+ if (!reply)
+ return -ENOMEM;
+ ovs_lock();
dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
err = PTR_ERR(dp);
if (IS_ERR(dp))
- return err;
+ goto err_unlock_free;
- reply = ovs_dp_cmd_build_info(dp, info->snd_portid,
- info->snd_seq, OVS_DP_CMD_DEL);
- err = PTR_ERR(reply);
- if (IS_ERR(reply))
- return err;
+ err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_DP_CMD_DEL);
+ BUG_ON(err < 0);
__dp_destroy(dp);
- genl_notify(reply, genl_info_net(info), info->snd_portid,
- ovs_dp_datapath_multicast_group.id, info->nlhdr,
- GFP_KERNEL);
-
+ ovs_unlock();
+ ovs_notify(reply, info, &ovs_dp_datapath_multicast_group);
return 0;
+
+err_unlock_free:
+ ovs_unlock();
+ kfree_skb(reply);
+ return err;
}
static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info)
struct datapath *dp;
int err;
- err = ovs_dp_cmd_validate(info->attrs);
- if (err)
- return err;
+ reply = ovs_dp_cmd_alloc_info(info);
+ if (!reply)
+ return -ENOMEM;
+ ovs_lock();
dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
+ err = PTR_ERR(dp);
if (IS_ERR(dp))
- return PTR_ERR(dp);
+ goto err_unlock_free;
- reply = ovs_dp_cmd_build_info(dp, info->snd_portid,
- info->snd_seq, OVS_DP_CMD_NEW);
- if (IS_ERR(reply)) {
- err = PTR_ERR(reply);
- netlink_set_err(GENL_SOCK(sock_net(skb->sk)), 0,
- ovs_dp_datapath_multicast_group.id, err);
- return 0;
- }
+ ovs_dp_change(dp, info->attrs);
- genl_notify(reply, genl_info_net(info), info->snd_portid,
- ovs_dp_datapath_multicast_group.id, info->nlhdr,
- GFP_KERNEL);
+ err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_DP_CMD_NEW);
+ BUG_ON(err < 0);
+ ovs_unlock();
+ ovs_notify(reply, info, &ovs_dp_datapath_multicast_group);
return 0;
+
+err_unlock_free:
+ ovs_unlock();
+ kfree_skb(reply);
+ return err;
}
static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info)
struct datapath *dp;
int err;
- err = ovs_dp_cmd_validate(info->attrs);
- if (err)
- return err;
+ reply = ovs_dp_cmd_alloc_info(info);
+ if (!reply)
+ return -ENOMEM;
+ rcu_read_lock();
dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
- if (IS_ERR(dp))
- return PTR_ERR(dp);
-
- reply = ovs_dp_cmd_build_info(dp, info->snd_portid,
- info->snd_seq, OVS_DP_CMD_NEW);
- if (IS_ERR(reply))
- return PTR_ERR(reply);
+ if (IS_ERR(dp)) {
+ err = PTR_ERR(dp);
+ goto err_unlock_free;
+ }
+ err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_DP_CMD_NEW);
+ BUG_ON(err < 0);
+ rcu_read_unlock();
return genlmsg_reply(reply, info);
+
+err_unlock_free:
+ rcu_read_unlock();
+ kfree_skb(reply);
+ return err;
}
static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
int skip = cb->args[0];
int i = 0;
- list_for_each_entry(dp, &ovs_net->dps, list_node) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(dp, &ovs_net->dps, list_node) {
if (i >= skip &&
ovs_dp_cmd_fill_info(dp, skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
break;
i++;
}
+ rcu_read_unlock();
cb->args[0] = i;
};
static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
-#ifdef HAVE_NLA_NUL_STRING
[OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
[OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) },
-#else
- [OVS_VPORT_ATTR_STATS] = { .minlen = sizeof(struct ovs_vport_stats) },
-#endif
[OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 },
[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
.name = OVS_VPORT_FAMILY,
.version = OVS_VPORT_VERSION,
.maxattr = OVS_VPORT_ATTR_MAX,
- SET_NETNSOK
+ .netnsok = true,
+ SET_PARALLEL_OPS
};
struct genl_multicast_group ovs_dp_vport_multicast_group = {
.name = OVS_VPORT_MCGROUP
};
-/* Called with RTNL lock or RCU read lock. */
+/* Called with ovs_mutex or RCU read lock. */
static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
u32 portid, u32 seq, u32 flags, u8 cmd)
{
return err;
}
-/* Called with RTNL lock or RCU read lock. */
+static struct sk_buff *ovs_vport_cmd_alloc_info(void)
+{
+ return nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+}
+
+/* Called with ovs_mutex, only via ovs_dp_notify_wq(). */
struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid,
u32 seq, u8 cmd)
{
return ERR_PTR(-ENOMEM);
retval = ovs_vport_cmd_fill_info(vport, skb, portid, seq, 0, cmd);
- if (retval < 0) {
- kfree_skb(skb);
- return ERR_PTR(retval);
- }
- return skb;
-}
+ BUG_ON(retval < 0);
-static int ovs_vport_cmd_validate(struct nlattr *a[OVS_VPORT_ATTR_MAX + 1])
-{
- return CHECK_NUL_STRING(a[OVS_VPORT_ATTR_NAME], IFNAMSIZ - 1);
+ return skb;
}
-/* Called with RTNL lock or RCU read lock. */
+/* Called with ovs_mutex or RCU read lock. */
static struct vport *lookup_vport(struct net *net,
struct ovs_header *ovs_header,
struct nlattr *a[OVS_VPORT_ATTR_MAX + 1])
if (!dp)
return ERR_PTR(-ENODEV);
- vport = ovs_vport_rtnl_rcu(dp, port_no);
+ vport = ovs_vport_ovsl_rcu(dp, port_no);
if (!vport)
return ERR_PTR(-ENODEV);
return vport;
u32 port_no;
int err;
- err = -EINVAL;
if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] ||
!a[OVS_VPORT_ATTR_UPCALL_PID])
- goto exit;
+ return -EINVAL;
- err = ovs_vport_cmd_validate(a);
- if (err)
- goto exit;
+ port_no = a[OVS_VPORT_ATTR_PORT_NO]
+ ? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0;
+ if (port_no >= DP_MAX_PORTS)
+ return -EFBIG;
+
+ reply = ovs_vport_cmd_alloc_info();
+ if (!reply)
+ return -ENOMEM;
- rtnl_lock();
+ ovs_lock();
dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
err = -ENODEV;
if (!dp)
- goto exit_unlock;
-
- if (a[OVS_VPORT_ATTR_PORT_NO]) {
- port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]);
-
- err = -EFBIG;
- if (port_no >= DP_MAX_PORTS)
- goto exit_unlock;
+ goto exit_unlock_free;
- vport = ovs_vport_rtnl(dp, port_no);
+ if (port_no) {
+ vport = ovs_vport_ovsl(dp, port_no);
err = -EBUSY;
if (vport)
- goto exit_unlock;
+ goto exit_unlock_free;
} else {
for (port_no = 1; ; port_no++) {
if (port_no >= DP_MAX_PORTS) {
err = -EFBIG;
- goto exit_unlock;
+ goto exit_unlock_free;
}
- vport = ovs_vport_rtnl(dp, port_no);
+ vport = ovs_vport_ovsl(dp, port_no);
if (!vport)
break;
}
vport = new_vport(&parms);
err = PTR_ERR(vport);
if (IS_ERR(vport))
- goto exit_unlock;
+ goto exit_unlock_free;
err = 0;
if (a[OVS_VPORT_ATTR_STATS])
ovs_vport_set_stats(vport, nla_data(a[OVS_VPORT_ATTR_STATS]));
- reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq,
- OVS_VPORT_CMD_NEW);
- if (IS_ERR(reply)) {
- err = PTR_ERR(reply);
- ovs_dp_detach_port(vport);
- goto exit_unlock;
- }
- genl_notify(reply, genl_info_net(info), info->snd_portid,
- ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL);
+ err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+ BUG_ON(err < 0);
+ ovs_unlock();
+
+ ovs_notify(reply, info, &ovs_dp_vport_multicast_group);
+ return 0;
-exit_unlock:
- rtnl_unlock();
-exit:
+exit_unlock_free:
+ ovs_unlock();
+ kfree_skb(reply);
return err;
}
struct vport *vport;
int err;
- err = ovs_vport_cmd_validate(a);
- if (err)
- goto exit;
+ reply = ovs_vport_cmd_alloc_info();
+ if (!reply)
+ return -ENOMEM;
- rtnl_lock();
+ ovs_lock();
vport = lookup_vport(sock_net(skb->sk), info->userhdr, a);
err = PTR_ERR(vport);
if (IS_ERR(vport))
- goto exit_unlock;
+ goto exit_unlock_free;
- err = 0;
if (a[OVS_VPORT_ATTR_TYPE] &&
- nla_get_u32(a[OVS_VPORT_ATTR_TYPE]) != vport->ops->type)
+ nla_get_u32(a[OVS_VPORT_ATTR_TYPE]) != vport->ops->type) {
err = -EINVAL;
+ goto exit_unlock_free;
+ }
- if (!err && a[OVS_VPORT_ATTR_OPTIONS])
+ if (a[OVS_VPORT_ATTR_OPTIONS]) {
err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]);
- if (err)
- goto exit_unlock;
+ if (err)
+ goto exit_unlock_free;
+ }
if (a[OVS_VPORT_ATTR_STATS])
ovs_vport_set_stats(vport, nla_data(a[OVS_VPORT_ATTR_STATS]));
if (a[OVS_VPORT_ATTR_UPCALL_PID])
vport->upcall_portid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]);
- reply = ovs_vport_cmd_build_info(vport, info->snd_portid,
- info->snd_seq, OVS_VPORT_CMD_NEW);
- if (IS_ERR(reply)) {
- netlink_set_err(GENL_SOCK(sock_net(skb->sk)), 0,
- ovs_dp_vport_multicast_group.id, PTR_ERR(reply));
- goto exit_unlock;
- }
+ err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+ BUG_ON(err < 0);
+ ovs_unlock();
- genl_notify(reply, genl_info_net(info), info->snd_portid,
- ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL);
+ ovs_notify(reply, info, &ovs_dp_vport_multicast_group);
+ return 0;
-exit_unlock:
- rtnl_unlock();
-exit:
+exit_unlock_free:
+ ovs_unlock();
+ kfree_skb(reply);
return err;
}
struct vport *vport;
int err;
- err = ovs_vport_cmd_validate(a);
- if (err)
- goto exit;
+ reply = ovs_vport_cmd_alloc_info();
+ if (!reply)
+ return -ENOMEM;
- rtnl_lock();
+ ovs_lock();
vport = lookup_vport(sock_net(skb->sk), info->userhdr, a);
err = PTR_ERR(vport);
if (IS_ERR(vport))
- goto exit_unlock;
+ goto exit_unlock_free;
if (vport->port_no == OVSP_LOCAL) {
err = -EINVAL;
- goto exit_unlock;
+ goto exit_unlock_free;
}
- reply = ovs_vport_cmd_build_info(vport, info->snd_portid,
- info->snd_seq, OVS_VPORT_CMD_DEL);
- err = PTR_ERR(reply);
- if (IS_ERR(reply))
- goto exit_unlock;
-
- err = 0;
+ err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_VPORT_CMD_DEL);
+ BUG_ON(err < 0);
ovs_dp_detach_port(vport);
+ ovs_unlock();
- genl_notify(reply, genl_info_net(info), info->snd_portid,
- ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL);
+ ovs_notify(reply, info, &ovs_dp_vport_multicast_group);
+ return 0;
-exit_unlock:
- rtnl_unlock();
-exit:
+exit_unlock_free:
+ ovs_unlock();
+ kfree_skb(reply);
return err;
}
struct vport *vport;
int err;
- err = ovs_vport_cmd_validate(a);
- if (err)
- goto exit;
+ reply = ovs_vport_cmd_alloc_info();
+ if (!reply)
+ return -ENOMEM;
rcu_read_lock();
vport = lookup_vport(sock_net(skb->sk), ovs_header, a);
err = PTR_ERR(vport);
if (IS_ERR(vport))
- goto exit_unlock;
-
- reply = ovs_vport_cmd_build_info(vport, info->snd_portid,
- info->snd_seq, OVS_VPORT_CMD_NEW);
- err = PTR_ERR(reply);
- if (IS_ERR(reply))
- goto exit_unlock;
-
+ goto exit_unlock_free;
+ err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+ BUG_ON(err < 0);
rcu_read_unlock();
return genlmsg_reply(reply, info);
-exit_unlock:
+exit_unlock_free:
rcu_read_unlock();
-exit:
+ kfree_skb(reply);
return err;
}
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;
- struct hlist_node *n;
j = 0;
- hlist_for_each_entry_rcu(vport, n, &dp->ports[i], dp_hash_node) {
+ hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) {
if (j >= skip &&
ovs_vport_cmd_fill_info(vport, skb,
NETLINK_CB(cb->skb).portid,
return err;
}
-static int __rehash_flow_table(void *dummy)
-{
- struct datapath *dp;
- struct net *net;
-
- rtnl_lock();
- for_each_net(net) {
- struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
-
- list_for_each_entry(dp, &ovs_net->dps, list_node) {
- struct flow_table *old_table = genl_dereference(dp->table);
- struct flow_table *new_table;
-
- new_table = ovs_flow_tbl_rehash(old_table);
- if (!IS_ERR(new_table)) {
- rcu_assign_pointer(dp->table, new_table);
- ovs_flow_tbl_deferred_destroy(old_table);
- }
- }
- }
- rtnl_unlock();
- return 0;
-}
-
-static void rehash_flow_table(struct work_struct *work)
-{
- genl_exec(__rehash_flow_table, NULL);
- schedule_delayed_work(&rehash_flow_wq, REHASH_FLOW_INTERVAL);
-}
-
-static int dp_destroy_all(void *data)
-{
- struct datapath *dp, *dp_next;
- struct ovs_net *ovs_net = data;
-
- list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node)
- __dp_destroy(dp);
-
- return 0;
-}
-
static int __net_init ovs_init_net(struct net *net)
{
struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
INIT_LIST_HEAD(&ovs_net->dps);
+ INIT_WORK(&ovs_net->dp_notify_work, ovs_dp_notify_wq);
return 0;
}
static void __net_exit ovs_exit_net(struct net *net)
{
+ struct datapath *dp, *dp_next;
struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
- genl_exec(dp_destroy_all, ovs_net);
+ ovs_lock();
+ list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node)
+ __dp_destroy(dp);
+ ovs_unlock();
+
+ cancel_work_sync(&ovs_net->dp_notify_work);
}
static struct pernet_operations ovs_net_ops = {
.size = sizeof(struct ovs_net),
};
+DEFINE_COMPAT_PNET_REG_FUNC(device);
+
static int __init dp_init(void)
{
int err;
pr_info("Open vSwitch switching datapath %s, built "__DATE__" "__TIME__"\n",
VERSION);
- err = genl_exec_init();
- if (err)
- goto error;
-
- err = ovs_workqueues_init();
- if (err)
- goto error_genl_exec;
-
- err = ovs_tnl_init();
- if (err)
- goto error_wq;
-
err = ovs_flow_init();
if (err)
- goto error_tnl_exit;
+ goto error;
err = ovs_vport_init();
if (err)
if (err < 0)
goto error_unreg_notifier;
- schedule_delayed_work(&rehash_flow_wq, REHASH_FLOW_INTERVAL);
-
return 0;
error_unreg_notifier:
ovs_vport_exit();
error_flow_exit:
ovs_flow_exit();
-error_tnl_exit:
- ovs_tnl_exit();
-error_wq:
- ovs_workqueues_exit();
-error_genl_exec:
- genl_exec_exit();
error:
return err;
}
static void dp_cleanup(void)
{
- cancel_delayed_work_sync(&rehash_flow_wq);
dp_unregister_genl(ARRAY_SIZE(dp_genl_families));
unregister_netdevice_notifier(&ovs_dp_device_notifier);
unregister_pernet_device(&ovs_net_ops);
rcu_barrier();
ovs_vport_exit();
ovs_flow_exit();
- ovs_tnl_exit();
- ovs_workqueues_exit();
- genl_exec_exit();
}
module_init(dp_init);