Utilize the new metadata dst to attach encapsulation instructions to
the skb. The existing egress_tun_info via the OVS_CB() is left in
place until all tunnel vports have been converted to the new method.
Signed-off-by: Thomas Graf <tg...@suug.ch>
Signed-off-by: Pravin B Shelar <pshe...@nicira.com>
---
net/openvswitch/actions.c | 10 ++++++-
net/openvswitch/datapath.c | 8 +++---
net/openvswitch/flow.h | 5 ++++
net/openvswitch/flow_netlink.c | 64 +++++++++++++++++++++++++++++++++++++-----
net/openvswitch/flow_netlink.h | 1 +
net/openvswitch/flow_table.c | 4 ++-
6 files changed, 79 insertions(+), 13 deletions(-)
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 27c1687..cf04c2f 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -733,7 +733,15 @@ static int execute_set_action(struct sk_buff *skb,
{
/* Only tunnel set execution is supported without a mask. */
if (nla_type(a) == OVS_KEY_ATTR_TUNNEL_INFO) {
- OVS_CB(skb)->egress_tun_info = nla_data(a);
+ struct ovs_tunnel_info *tun = nla_data(a);
+
+ skb_dst_drop(skb);
+ dst_hold((struct dst_entry *)tun->tun_dst);
+ skb_dst_set(skb, (struct dst_entry *)tun->tun_dst);
+
+ /* FIXME: Remove when all vports have been converted */
+ OVS_CB(skb)->egress_tun_info = &tun->tun_dst->u.tun_info;
+
return 0;
}
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index ff8c4a4..0208210 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1018,7 +1018,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct
genl_info *info)
}
ovs_unlock();
- ovs_nla_free_flow_actions(old_acts);
+ ovs_nla_free_flow_actions_rcu(old_acts);
ovs_flow_free(new_flow, false);
}
@@ -1030,7 +1030,7 @@ err_unlock_ovs:
ovs_unlock();
kfree_skb(reply);
err_kfree_acts:
- kfree(acts);
+ ovs_nla_free_flow_actions(acts);
err_kfree_flow:
ovs_flow_free(new_flow, false);
error:
@@ -1157,7 +1157,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct
genl_info *info)
if (reply)
ovs_notify(&dp_flow_genl_family, reply, info);
if (old_acts)
- ovs_nla_free_flow_actions(old_acts);
+ ovs_nla_free_flow_actions_rcu(old_acts);
return 0;
@@ -1165,7 +1165,7 @@ err_unlock_ovs:
ovs_unlock();
kfree_skb(reply);
err_kfree_acts:
- kfree(acts);
+ ovs_nla_free_flow_actions(acts);
error:
return error;
}
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index cadc6c5..b62cdb3 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -33,6 +33,7 @@
#include <linux/flex_array.h>
#include <net/inet_ecn.h>
#include <net/ip_tunnels.h>
+#include <net/dst_metadata.h>
struct sk_buff;
@@ -45,6 +46,10 @@ struct sk_buff;
#define TUN_METADATA_OPTS(flow_key, opt_len) \
((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len)))
+struct ovs_tunnel_info {
+ struct metadata_dst *tun_dst;
+};
+
#define OVS_SW_FLOW_KEY_METADATA_SIZE \
(offsetof(struct sw_flow_key, recirc_id) + \
FIELD_SIZEOF(struct sw_flow_key, recirc_id))
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index ecfa530..e7906df 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1548,11 +1548,48 @@ static struct sw_flow_actions
*nla_alloc_flow_actions(int size, bool log)
return sfa;
}
+static void ovs_nla_free_set_action(const struct nlattr *a)
+{
+ const struct nlattr *ovs_key = nla_data(a);
+ struct ovs_tunnel_info *ovs_tun;
+
+ switch (nla_type(ovs_key)) {
+ case OVS_KEY_ATTR_TUNNEL_INFO:
+ ovs_tun = nla_data(ovs_key);
+ dst_release((struct dst_entry *)ovs_tun->tun_dst);
+ break;
+ }
+}
+
+void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
+{
+ const struct nlattr *a;
+ int rem;
+
+ if (!sf_acts)
+ return;
+
+ nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) {
+ switch (nla_type(a)) {
+ case OVS_ACTION_ATTR_SET:
+ ovs_nla_free_set_action(a);
+ break;
+ }
+ }
+
+ kfree(sf_acts);
+}
+
+static void __ovs_nla_free_flow_actions(struct rcu_head *head)
+{
+ ovs_nla_free_flow_actions(container_of(head, struct sw_flow_actions,
rcu));
+}
+
/* Schedules 'sf_acts' to be freed after the next RCU grace period.
* The caller must hold rcu_read_lock for this to be sensible. */
-void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
+void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *sf_acts)
{
- kfree_rcu(sf_acts, rcu);
+ call_rcu(&sf_acts->rcu, __ovs_nla_free_flow_actions);
}
static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
@@ -1746,7 +1783,9 @@ static int validate_and_copy_set_tun(const struct nlattr
*attr,
{
struct sw_flow_match match;
struct sw_flow_key key;
+ struct metadata_dst *tun_dst;
struct ip_tunnel_info *tun_info;
+ struct ovs_tunnel_info *ovs_tun;
struct nlattr *a;
int err = 0, start, opts_type;
@@ -1771,12 +1810,22 @@ static int validate_and_copy_set_tun(const struct
nlattr *attr,
if (start < 0)
return start;
+ tun_dst = metadata_dst_alloc(key.tun_opts_len, GFP_KERNEL);
+ if (!tun_dst)
+ return -ENOMEM;
+
a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL,
- sizeof(*tun_info) + key.tun_opts_len, log);
- if (IS_ERR(a))
+ sizeof(*ovs_tun), log);
+ if (IS_ERR(a)) {
+ dst_release((struct dst_entry *)tun_dst);
return PTR_ERR(a);
+ }
+
+ ovs_tun = nla_data(a);
+ ovs_tun->tun_dst = tun_dst;
- tun_info = nla_data(a);
+ tun_info = &tun_dst->u.tun_info;
+ tun_info->mode = IP_TUNNEL_INFO_TX;
tun_info->key = key.tun_key;
tun_info->options_len = key.tun_opts_len;
@@ -2177,7 +2226,7 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
err = __ovs_nla_copy_actions(attr, key, 0, sfa, key->eth.type,
key->eth.tci, log);
if (err)
- kfree(*sfa);
+ ovs_nla_free_flow_actions(*sfa);
return err;
}
@@ -2227,7 +2276,8 @@ static int set_action_to_attr(const struct nlattr *a,
struct sk_buff *skb)
switch (key_type) {
case OVS_KEY_ATTR_TUNNEL_INFO: {
- struct ip_tunnel_info *tun_info = nla_data(ovs_key);
+ struct ovs_tunnel_info *ovs_tun = nla_data(ovs_key);
+ struct ip_tunnel_info *tun_info = &ovs_tun->tun_dst->u.tun_info;
start = nla_nest_start(skb, OVS_ACTION_ATTR_SET);
if (!start)
diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h
index ec53eb6..acd0744 100644
--- a/net/openvswitch/flow_netlink.h
+++ b/net/openvswitch/flow_netlink.h
@@ -69,5 +69,6 @@ int ovs_nla_put_actions(const struct nlattr *attr,
int len, struct sk_buff *skb);
void ovs_nla_free_flow_actions(struct sw_flow_actions *);
+void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *);
#endif /* flow_netlink.h */
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 4613df8..b70d845 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -18,6 +18,7 @@
#include "flow.h"
#include "datapath.h"
+#include "flow_netlink.h"
#include <linux/uaccess.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
@@ -143,7 +144,8 @@ static void flow_free(struct sw_flow *flow)
if (ovs_identifier_is_key(&flow->id))
kfree(flow->id.unmasked_key);
- kfree((struct sw_flow_actions __force *)flow->sf_acts);
+ if (flow->sf_acts)
+ ovs_nla_free_flow_actions((struct sw_flow_actions __force
*)flow->sf_acts);
for_each_node(node)
if (flow->stats[node])
kmem_cache_free(flow_stats_cache,
--
2.4.3
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
