datapath: Enable memory mapped Netlink i/o

Use memory mapped Netlink i/o for all unicast openvswitch
communication if a ring has been set up.

Benchmark
  * pktgen -> ovs internal port
  * 5M pkts, 5M flows
  * 4 threads, 8 cores

Before:
Result: OK: 67418743(c67108212+d310530) usec, 5000000 (9000byte,0frags)
  74163pps 5339Mb/sec (5339736000bps) errors: 0
	+   2.98%     ovs-vswitchd  [k] copy_user_generic_string
	+   2.49%     ovs-vswitchd  [k] memcpy
	+   1.84%       kpktgend_2  [k] memcpy
	+   1.81%       kpktgend_1  [k] memcpy
	+   1.81%       kpktgend_3  [k] memcpy
	+   1.78%       kpktgend_0  [k] memcpy

After:
Result: OK: 24229690(c24127165+d102524) usec, 5000000 (9000byte,0frags)
  206358pps 14857Mb/sec (14857776000bps) errors: 0
	+   2.80%     ovs-vswitchd  [k] memcpy
	+   1.31%       kpktgend_2  [k] memcpy
	+   1.23%       kpktgend_0  [k] memcpy
	+   1.09%       kpktgend_1  [k] memcpy
	+   1.04%       kpktgend_3  [k] memcpy
	+   0.96%     ovs-vswitchd  [k] copy_user_generic_string

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Reviewed-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>

diff --git a/datapath/datapath.c b/datapath/datapath.c
index 75edd17..1a5bffb 100644 (file)
--- a/datapath/datapath.c
+++ b/datapath/datapath.c
@@ -404,6 +404,13 @@ static int queue_userspace_packet(struct net *net, int dp_ifindex,
        struct sk_buff *nskb = NULL;
        struct sk_buff *user_skb; /* to be queued to userspace */
        struct nlattr *nla;
+       struct genl_info info = {
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3,14,0)
+               .dst_sk = net->genl_sock,
+#endif
+               .snd_portid = upcall_info->portid,
+       };
+       size_t len;
        int err;
 
        if (vlan_tx_tag_present(skb)) {
@@ -425,7 +432,8 @@ static int queue_userspace_packet(struct net *net, int dp_ifindex,
                goto out;
        }
 
-       user_skb = genlmsg_new(upcall_msg_size(skb, upcall_info->userdata), GFP_ATOMIC);
+       len = upcall_msg_size(skb, upcall_info->userdata);
+       user_skb = genlmsg_new_unicast(len, &info, GFP_ATOMIC);
        if (!user_skb) {
                err = -ENOMEM;
                goto out;
@@ -719,27 +727,30 @@ error:
        return err;
 }
 
-static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow)
+static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow,
+                                              struct genl_info *info)
 {
-       const struct sw_flow_actions *sf_acts;
+       size_t len;
 
-       sf_acts = ovsl_dereference(flow->sf_acts);
+       len = ovs_flow_cmd_msg_size(ovsl_dereference(flow->sf_acts));
 
-       return genlmsg_new(ovs_flow_cmd_msg_size(sf_acts), GFP_KERNEL);
+       return genlmsg_new_unicast(len, info, GFP_KERNEL);
 }
 
 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)
 {
        struct sk_buff *skb;
        int retval;
 
-       skb = ovs_flow_cmd_alloc_info(flow);
+       skb = ovs_flow_cmd_alloc_info(flow, info);
        if (!skb)
                return ERR_PTR(-ENOMEM);
 
-       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;
 }
@@ -819,8 +830,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
                        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);
        } else {
                /* We found a matching flow. */
                struct sw_flow_actions *old_acts;
@@ -848,8 +858,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
                rcu_assign_pointer(flow->sf_acts, acts);
                ovs_nla_free_flow_actions(old_acts);
 
-               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);
 
                /* Clear stats. */
                if (a[OVS_FLOW_ATTR_CLEAR])
@@ -908,8 +917,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
                goto unlock;
        }
 
-       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);
        if (IS_ERR(reply)) {
                err = PTR_ERR(reply);
                goto unlock;
@@ -956,7 +964,7 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
                goto unlock;
        }
 
-       reply = ovs_flow_cmd_alloc_info(flow);
+       reply = ovs_flow_cmd_alloc_info(flow, info);
        if (!reply) {
                err = -ENOMEM;
                goto unlock;
@@ -1108,17 +1116,17 @@ error:
        return -EMSGSIZE;
 }
 
-static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, u32 portid,
-                                            u32 seq, u8 cmd)
+static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp,
+                                            struct genl_info *info, u8 cmd)
 {
        struct sk_buff *skb;
        int retval;
 
-       skb = genlmsg_new(ovs_dp_cmd_msg_size(), GFP_KERNEL);
+       skb = genlmsg_new_unicast(ovs_dp_cmd_msg_size(), info, GFP_KERNEL);
        if (!skb)
                return ERR_PTR(-ENOMEM);
 
-       retval = ovs_dp_cmd_fill_info(dp, skb, portid, seq, 0, cmd);
+       retval = ovs_dp_cmd_fill_info(dp, skb, info->snd_portid, info->snd_seq, 0, cmd);
        if (retval < 0) {
                kfree_skb(skb);
                return ERR_PTR(retval);
@@ -1207,8 +1215,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
                goto err_destroy_ports_array;
        }
 
-       reply = ovs_dp_cmd_build_info(dp, info->snd_portid,
-                                     info->snd_seq, OVS_DP_CMD_NEW);
+       reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW);
        err = PTR_ERR(reply);
        if (IS_ERR(reply))
                goto err_destroy_local_port;
@@ -1274,8 +1281,7 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info)
        if (IS_ERR(dp))
                goto unlock;
 
-       reply = ovs_dp_cmd_build_info(dp, info->snd_portid,
-                                     info->snd_seq, OVS_DP_CMD_DEL);
+       reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_DEL);
        err = PTR_ERR(reply);
        if (IS_ERR(reply))
                goto unlock;
@@ -1303,8 +1309,7 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info)
        if (IS_ERR(dp))
                goto unlock;
 
-       reply = ovs_dp_cmd_build_info(dp, info->snd_portid,
-                                     info->snd_seq, OVS_DP_CMD_NEW);
+       reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW);
        if (IS_ERR(reply)) {
                err = PTR_ERR(reply);
                netlink_set_err(sock_net(skb->sk)->genl_sock, 0,
@@ -1335,8 +1340,7 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info)
                goto unlock;
        }
 
-       reply = ovs_dp_cmd_build_info(dp, info->snd_portid,
-                                     info->snd_seq, OVS_DP_CMD_NEW);
+       reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW);
        if (IS_ERR(reply)) {
                err = PTR_ERR(reply);
                goto unlock;