diff mbox series

[ovs-dev,net-next,v5] openvswitch: Make metadata_dst tunnel work in IP_TUNNEL_INFO_BRIDGE mode

Message ID 1553748203-14675-1-git-send-email-wenxu@ucloud.cn
State Awaiting Upstream
Headers show
Series [ovs-dev,net-next,v5] openvswitch: Make metadata_dst tunnel work in IP_TUNNEL_INFO_BRIDGE mode | expand

Commit Message

wenxu March 28, 2019, 4:43 a.m. UTC 
From: wenxu <wenxu@ucloud.cn>

There is currently no support for the multicast/broadcast aspects
of VXLAN in ovs. In the datapath flow the tun_dst must specific.
But in the IP_TUNNEL_INFO_BRIDGE mode the tun_dst can not be specific.
And the packet can forward through the fdb table of vxlan devcice. In
this mode the broadcast/multicast packet can be sent through the
following ways in ovs.

ovs-vsctl add-port br0 vxlan -- set in vxlan type=vxlan \
        options:key=1000 options:remote_ip=flow
ovs-ofctl add-flow br0 in_port=LOCAL,dl_dst=ff:ff:ff:ff:ff:ff, \
        action=output:vxlan

bridge fdb append ff:ff:ff:ff:ff:ff dev vxlan_sys_4789 dst 172.168.0.1 \
        src_vni 1000 vni 1000 self
bridge fdb append ff:ff:ff:ff:ff:ff dev vxlan_sys_4789 dst 172.168.0.2 \
        src_vni 1000 vni 1000 self

Signed-off-by: wenxu <wenxu@ucloud.cn>
---
 include/uapi/linux/openvswitch.h |  1 +
 net/openvswitch/flow_netlink.c   | 46 +++++++++++++++++++++++++++++++---------
 2 files changed, 37 insertions(+), 10 deletions(-)

Comments

Pravin Shelar March 29, 2019, 7:33 p.m. UTC | #1 
On Wed, Mar 27, 2019 at 9:43 PM <wenxu@ucloud.cn> wrote:
>
> From: wenxu <wenxu@ucloud.cn>
>
> There is currently no support for the multicast/broadcast aspects
> of VXLAN in ovs. In the datapath flow the tun_dst must specific.
> But in the IP_TUNNEL_INFO_BRIDGE mode the tun_dst can not be specific.
> And the packet can forward through the fdb table of vxlan devcice. In
> this mode the broadcast/multicast packet can be sent through the
> following ways in ovs.
>
> ovs-vsctl add-port br0 vxlan -- set in vxlan type=vxlan \
>         options:key=1000 options:remote_ip=flow
> ovs-ofctl add-flow br0 in_port=LOCAL,dl_dst=ff:ff:ff:ff:ff:ff, \
>         action=output:vxlan
>
> bridge fdb append ff:ff:ff:ff:ff:ff dev vxlan_sys_4789 dst 172.168.0.1 \
>         src_vni 1000 vni 1000 self
> bridge fdb append ff:ff:ff:ff:ff:ff dev vxlan_sys_4789 dst 172.168.0.2 \
>         src_vni 1000 vni 1000 self
>
> Signed-off-by: wenxu <wenxu@ucloud.cn>
> ---
>  include/uapi/linux/openvswitch.h |  1 +
>  net/openvswitch/flow_netlink.c   | 46 +++++++++++++++++++++++++++++++---------
>  2 files changed, 37 insertions(+), 10 deletions(-)
>

Looks good.
Acked-by: Pravin B Shelar <pshelar@ovn.org>

Thanks,
Pravin.
David Miller March 29, 2019, 8:29 p.m. UTC | #2 
From: wenxu@ucloud.cn
Date: Thu, 28 Mar 2019 12:43:23 +0800

> From: wenxu <wenxu@ucloud.cn>
> 
> There is currently no support for the multicast/broadcast aspects
> of VXLAN in ovs. In the datapath flow the tun_dst must specific.
> But in the IP_TUNNEL_INFO_BRIDGE mode the tun_dst can not be specific.
> And the packet can forward through the fdb table of vxlan devcice. In
> this mode the broadcast/multicast packet can be sent through the
> following ways in ovs.
> 
> ovs-vsctl add-port br0 vxlan -- set in vxlan type=vxlan \
>         options:key=1000 options:remote_ip=flow
> ovs-ofctl add-flow br0 in_port=LOCAL,dl_dst=ff:ff:ff:ff:ff:ff, \
>         action=output:vxlan
> 
> bridge fdb append ff:ff:ff:ff:ff:ff dev vxlan_sys_4789 dst 172.168.0.1 \
>         src_vni 1000 vni 1000 self
> bridge fdb append ff:ff:ff:ff:ff:ff dev vxlan_sys_4789 dst 172.168.0.2 \
>         src_vni 1000 vni 1000 self
> 
> Signed-off-by: wenxu <wenxu@ucloud.cn>

Applied to net-next, thanks.
diff mbox series

Patch

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index dfabace..13737fe 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -364,6 +364,7 @@  enum ovs_tunnel_key_attr {
 	OVS_TUNNEL_KEY_ATTR_IPV6_DST,		/* struct in6_addr dst IPv6 address. */
 	OVS_TUNNEL_KEY_ATTR_PAD,
 	OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS,	/* struct erspan_metadata */
+	OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE,	/* No argument. IPV4_INFO_BRIDGE mode.*/
 	__OVS_TUNNEL_KEY_ATTR_MAX
 };
 
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index b754370..2317ad6 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -404,6 +404,7 @@  size_t ovs_key_attr_size(void)
 	[OVS_TUNNEL_KEY_ATTR_IPV6_SRC]      = { .len = sizeof(struct in6_addr) },
 	[OVS_TUNNEL_KEY_ATTR_IPV6_DST]      = { .len = sizeof(struct in6_addr) },
 	[OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS]   = { .len = OVS_ATTR_VARIABLE },
+	[OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE]   = { .len = 0 },
 };
 
 static const struct ovs_len_tbl
@@ -667,6 +668,7 @@  static int ip_tun_from_nlattr(const struct nlattr *attr,
 			      bool log)
 {
 	bool ttl = false, ipv4 = false, ipv6 = false;
+	bool info_bridge_mode = false;
 	__be16 tun_flags = 0;
 	int opts_type = 0;
 	struct nlattr *a;
@@ -783,6 +785,10 @@  static int ip_tun_from_nlattr(const struct nlattr *attr,
 			tun_flags |= TUNNEL_ERSPAN_OPT;
 			opts_type = type;
 			break;
+		case OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE:
+			info_bridge_mode = true;
+			ipv4 = true;
+			break;
 		default:
 			OVS_NLERR(log, "Unknown IP tunnel attribute %d",
 				  type);
@@ -813,16 +819,29 @@  static int ip_tun_from_nlattr(const struct nlattr *attr,
 			OVS_NLERR(log, "IP tunnel dst address not specified");
 			return -EINVAL;
 		}
-		if (ipv4 && !match->key->tun_key.u.ipv4.dst) {
-			OVS_NLERR(log, "IPv4 tunnel dst address is zero");
-			return -EINVAL;
+		if (ipv4) {
+			if (info_bridge_mode) {
+				if (match->key->tun_key.u.ipv4.src ||
+				    match->key->tun_key.u.ipv4.dst ||
+				    match->key->tun_key.tp_src ||
+				    match->key->tun_key.tp_dst ||
+				    match->key->tun_key.ttl ||
+				    match->key->tun_key.tos ||
+				    tun_flags & ~TUNNEL_KEY) {
+					OVS_NLERR(log, "IPv4 tun info is not correct");
+					return -EINVAL;
+				}
+			} else if (!match->key->tun_key.u.ipv4.dst) {
+				OVS_NLERR(log, "IPv4 tunnel dst address is zero");
+				return -EINVAL;
+			}
 		}
 		if (ipv6 && ipv6_addr_any(&match->key->tun_key.u.ipv6.dst)) {
 			OVS_NLERR(log, "IPv6 tunnel dst address is zero");
 			return -EINVAL;
 		}
 
-		if (!ttl) {
+		if (!ttl && !info_bridge_mode) {
 			OVS_NLERR(log, "IP tunnel TTL not specified.");
 			return -EINVAL;
 		}
@@ -851,12 +870,17 @@  static int vxlan_opt_to_nlattr(struct sk_buff *skb,
 static int __ip_tun_to_nlattr(struct sk_buff *skb,
 			      const struct ip_tunnel_key *output,
 			      const void *tun_opts, int swkey_tun_opts_len,
-			      unsigned short tun_proto)
+			      unsigned short tun_proto, u8 mode)
 {
 	if (output->tun_flags & TUNNEL_KEY &&
 	    nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id,
 			 OVS_TUNNEL_KEY_ATTR_PAD))
 		return -EMSGSIZE;
+
+	if (mode & IP_TUNNEL_INFO_BRIDGE)
+		return nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE)
+		       ? -EMSGSIZE : 0;
+
 	switch (tun_proto) {
 	case AF_INET:
 		if (output->u.ipv4.src &&
@@ -919,7 +943,7 @@  static int __ip_tun_to_nlattr(struct sk_buff *skb,
 static int ip_tun_to_nlattr(struct sk_buff *skb,
 			    const struct ip_tunnel_key *output,
 			    const void *tun_opts, int swkey_tun_opts_len,
-			    unsigned short tun_proto)
+			    unsigned short tun_proto, u8 mode)
 {
 	struct nlattr *nla;
 	int err;
@@ -929,7 +953,7 @@  static int ip_tun_to_nlattr(struct sk_buff *skb,
 		return -EMSGSIZE;
 
 	err = __ip_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len,
-				 tun_proto);
+				 tun_proto, mode);
 	if (err)
 		return err;
 
@@ -943,7 +967,7 @@  int ovs_nla_put_tunnel_info(struct sk_buff *skb,
 	return __ip_tun_to_nlattr(skb, &tun_info->key,
 				  ip_tunnel_info_opts(tun_info),
 				  tun_info->options_len,
-				  ip_tunnel_info_af(tun_info));
+				  ip_tunnel_info_af(tun_info), tun_info->mode);
 }
 
 static int encode_vlan_from_nlattrs(struct sw_flow_match *match,
@@ -1981,7 +2005,7 @@  static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 			opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len);
 
 		if (ip_tun_to_nlattr(skb, &output->tun_key, opts,
-				     swkey->tun_opts_len, swkey->tun_proto))
+				     swkey->tun_opts_len, swkey->tun_proto, 0))
 			goto nla_put_failure;
 	}
 
@@ -2606,6 +2630,8 @@  static int validate_and_copy_set_tun(const struct nlattr *attr,
 	tun_info->mode = IP_TUNNEL_INFO_TX;
 	if (key.tun_proto == AF_INET6)
 		tun_info->mode |= IP_TUNNEL_INFO_IPV6;
+	else if (key.tun_proto == AF_INET && key.tun_key.u.ipv4.dst == 0)
+		tun_info->mode |= IP_TUNNEL_INFO_BRIDGE;
 	tun_info->key = key.tun_key;
 
 	/* We need to store the options in the action itself since
@@ -3367,7 +3393,7 @@  static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
 		err =  ip_tun_to_nlattr(skb, &tun_info->key,
 					ip_tunnel_info_opts(tun_info),
 					tun_info->options_len,
-					ip_tunnel_info_af(tun_info));
+					ip_tunnel_info_af(tun_info), tun_info->mode);
 		if (err)
 			return err;
 		nla_nest_end(skb, start);