From a31f1adc0948930fba9ab5a111ccd735a5d864c6 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 18 Sep 2015 14:33:04 -0500
Subject: netfilter: nf_conntrack: Add a struct net parameter to
 l4_pkt_to_tuple

As gre does not have the srckey in the packet gre_pkt_to_tuple
needs to perform a lookup in it's per network namespace tables.

Pass in the proper network namespace to all pkt_to_tuple
implementations to ensure gre (and any similar protocols) can get this
right.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/openvswitch/conntrack.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net/openvswitch')

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e8e524ad8a01..aaf5cbd6d9ae 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -345,7 +345,7 @@ ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone,
 {
 	struct nf_conntrack_tuple tuple;
 
-	if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, &tuple))
+	if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, net, &tuple))
 		return NULL;
 	return __nf_ct_expect_find(net, zone, &tuple);
 }
-- 
cgit v1.2.3


From 92c14d9b5ee86fd6cf136c01b6a87353522aebdd Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Tue, 22 Sep 2015 18:56:43 +0200
Subject: genetlink: simplify genl_notify

The genl_notify function has too many arguments for no real reason - all
callers use genl_info to get them anyway. Just pass the genl_info down to
genl_notify.

Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/mac80211_hwsim.c |  5 ++---
 include/net/genetlink.h               |  5 ++---
 net/netlink/genetlink.c               | 12 ++++++------
 net/openvswitch/datapath.c            |  3 +--
 4 files changed, 11 insertions(+), 14 deletions(-)

(limited to 'net/openvswitch')

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 520bef80747f..66c963dbc3fd 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2190,9 +2190,8 @@ static void hwsim_mcast_config_msg(struct sk_buff *mcast_skb,
 				   struct genl_info *info)
 {
 	if (info)
-		genl_notify(&hwsim_genl_family, mcast_skb,
-			    genl_info_net(info), info->snd_portid,
-			    HWSIM_MCGRP_CONFIG, info->nlhdr, GFP_KERNEL);
+		genl_notify(&hwsim_genl_family, mcast_skb, info,
+			    HWSIM_MCGRP_CONFIG, GFP_KERNEL);
 	else
 		genlmsg_multicast(&hwsim_genl_family, mcast_skb, 0,
 				  HWSIM_MCGRP_CONFIG, GFP_KERNEL);
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index a9af1cc8c1bc..1b6b6dcb018d 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -183,9 +183,8 @@ _genl_register_family_with_ops_grps(struct genl_family *family,
 					    (grps), ARRAY_SIZE(grps))
 
 int genl_unregister_family(struct genl_family *family);
-void genl_notify(struct genl_family *family,
-		 struct sk_buff *skb, struct net *net, u32 portid,
-		 u32 group, struct nlmsghdr *nlh, gfp_t flags);
+void genl_notify(struct genl_family *family, struct sk_buff *skb,
+		 struct genl_info *info, u32 group, gfp_t flags);
 
 struct sk_buff *genlmsg_new_unicast(size_t payload, struct genl_info *info,
 				    gfp_t flags);
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 2ed5f964772e..75724a96aef2 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1136,19 +1136,19 @@ int genlmsg_multicast_allns(struct genl_family *family, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(genlmsg_multicast_allns);
 
-void genl_notify(struct genl_family *family,
-		 struct sk_buff *skb, struct net *net, u32 portid, u32 group,
-		 struct nlmsghdr *nlh, gfp_t flags)
+void genl_notify(struct genl_family *family, struct sk_buff *skb,
+		 struct genl_info *info, u32 group, gfp_t flags)
 {
+	struct net *net = genl_info_net(info);
 	struct sock *sk = net->genl_sock;
 	int report = 0;
 
-	if (nlh)
-		report = nlmsg_report(nlh);
+	if (info->nlhdr)
+		report = nlmsg_report(info->nlhdr);
 
 	if (WARN_ON_ONCE(group >= family->n_mcgrps))
 		return;
 	group = family->mcgrp_offset + group;
-	nlmsg_notify(sk, skb, portid, group, report, flags);
+	nlmsg_notify(sk, skb, info->snd_portid, group, report, flags);
 }
 EXPORT_SYMBOL(genl_notify);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6fbd2decb19e..2913594c5123 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -91,8 +91,7 @@ static bool ovs_must_notify(struct genl_family *family, struct genl_info *info,
 static void ovs_notify(struct genl_family *family,
 		       struct sk_buff *skb, struct genl_info *info)
 {
-	genl_notify(family, skb, genl_info_net(info), info->snd_portid,
-		    0, info->nlhdr, GFP_KERNEL);
+	genl_notify(family, skb, info, 0, GFP_KERNEL);
 }
 
 /**
-- 
cgit v1.2.3


From b1be00a6c39fda2ec380e168d7bcf96fb8c9da42 Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Thu, 24 Sep 2015 13:50:02 +0200
Subject: vxlan: support both IPv4 and IPv6 sockets in a single vxlan device

For metadata based vxlan interface, open both IPv4 and IPv6 socket. This is
much more user friendly: it's not necessary to create two vxlan interfaces
and pay attention to using the right one in routing rules.

Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c           | 128 +++++++++++++++++++++++++++++-------------
 include/net/vxlan.h           |  14 ++++-
 net/openvswitch/vport-vxlan.c |   3 +-
 3 files changed, 103 insertions(+), 42 deletions(-)

(limited to 'net/openvswitch')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a86613011977..ce704df7681b 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -993,19 +993,30 @@ static bool vxlan_snoop(struct net_device *dev,
 static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev)
 {
 	struct vxlan_dev *vxlan;
+	unsigned short family = dev->default_dst.remote_ip.sa.sa_family;
 
 	/* The vxlan_sock is only used by dev, leaving group has
 	 * no effect on other vxlan devices.
 	 */
-	if (atomic_read(&dev->vn_sock->refcnt) == 1)
+	if (family == AF_INET && dev->vn4_sock &&
+	    atomic_read(&dev->vn4_sock->refcnt) == 1)
 		return false;
+#if IS_ENABLED(CONFIG_IPV6)
+	if (family == AF_INET6 && dev->vn6_sock &&
+	    atomic_read(&dev->vn6_sock->refcnt) == 1)
+		return false;
+#endif
 
 	list_for_each_entry(vxlan, &vn->vxlan_list, next) {
 		if (!netif_running(vxlan->dev) || vxlan == dev)
 			continue;
 
-		if (vxlan->vn_sock != dev->vn_sock)
+		if (family == AF_INET && vxlan->vn4_sock != dev->vn4_sock)
 			continue;
+#if IS_ENABLED(CONFIG_IPV6)
+		if (family == AF_INET6 && vxlan->vn6_sock != dev->vn6_sock)
+			continue;
+#endif
 
 		if (!vxlan_addr_equal(&vxlan->default_dst.remote_ip,
 				      &dev->default_dst.remote_ip))
@@ -1021,16 +1032,16 @@ static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev)
 	return false;
 }
 
-static void vxlan_sock_release(struct vxlan_dev *vxlan)
+static void __vxlan_sock_release(struct vxlan_sock *vs)
 {
-	struct vxlan_sock *vs = vxlan->vn_sock;
-	struct sock *sk = vs->sock->sk;
-	struct net *net = sock_net(sk);
-	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+	struct vxlan_net *vn;
 
+	if (!vs)
+		return;
 	if (!atomic_dec_and_test(&vs->refcnt))
 		return;
 
+	vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id);
 	spin_lock(&vn->sock_lock);
 	hlist_del_rcu(&vs->hlist);
 	vxlan_notify_del_rx_port(vs);
@@ -1039,32 +1050,43 @@ static void vxlan_sock_release(struct vxlan_dev *vxlan)
 	queue_work(vxlan_wq, &vs->del_work);
 }
 
+static void vxlan_sock_release(struct vxlan_dev *vxlan)
+{
+	__vxlan_sock_release(vxlan->vn4_sock);
+#if IS_ENABLED(CONFIG_IPV6)
+	__vxlan_sock_release(vxlan->vn6_sock);
+#endif
+}
+
 /* Update multicast group membership when first VNI on
  * multicast address is brought up
  */
 static int vxlan_igmp_join(struct vxlan_dev *vxlan)
 {
-	struct vxlan_sock *vs = vxlan->vn_sock;
-	struct sock *sk = vs->sock->sk;
+	struct sock *sk;
 	union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
 	int ifindex = vxlan->default_dst.remote_ifindex;
 	int ret = -EINVAL;
 
-	lock_sock(sk);
 	if (ip->sa.sa_family == AF_INET) {
 		struct ip_mreqn mreq = {
 			.imr_multiaddr.s_addr	= ip->sin.sin_addr.s_addr,
 			.imr_ifindex		= ifindex,
 		};
 
+		sk = vxlan->vn4_sock->sock->sk;
+		lock_sock(sk);
 		ret = ip_mc_join_group(sk, &mreq);
+		release_sock(sk);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
+		sk = vxlan->vn6_sock->sock->sk;
+		lock_sock(sk);
 		ret = ipv6_stub->ipv6_sock_mc_join(sk, ifindex,
 						   &ip->sin6.sin6_addr);
+		release_sock(sk);
 #endif
 	}
-	release_sock(sk);
 
 	return ret;
 }
@@ -1072,27 +1094,30 @@ static int vxlan_igmp_join(struct vxlan_dev *vxlan)
 /* Inverse of vxlan_igmp_join when last VNI is brought down */
 static int vxlan_igmp_leave(struct vxlan_dev *vxlan)
 {
-	struct vxlan_sock *vs = vxlan->vn_sock;
-	struct sock *sk = vs->sock->sk;
+	struct sock *sk;
 	union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
 	int ifindex = vxlan->default_dst.remote_ifindex;
 	int ret = -EINVAL;
 
-	lock_sock(sk);
 	if (ip->sa.sa_family == AF_INET) {
 		struct ip_mreqn mreq = {
 			.imr_multiaddr.s_addr	= ip->sin.sin_addr.s_addr,
 			.imr_ifindex		= ifindex,
 		};
 
+		sk = vxlan->vn4_sock->sock->sk;
+		lock_sock(sk);
 		ret = ip_mc_leave_group(sk, &mreq);
+		release_sock(sk);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
+		sk = vxlan->vn6_sock->sock->sk;
+		lock_sock(sk);
 		ret = ipv6_stub->ipv6_sock_mc_drop(sk, ifindex,
 						   &ip->sin6.sin6_addr);
+		release_sock(sk);
 #endif
 	}
-	release_sock(sk);
 
 	return ret;
 }
@@ -1873,8 +1898,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 {
 	struct ip_tunnel_info *info;
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct sock *sk = vxlan->vn_sock->sock->sk;
-	unsigned short family = vxlan_get_sk_family(vxlan->vn_sock);
+	struct sock *sk;
 	struct rtable *rt = NULL;
 	const struct iphdr *old_iph;
 	struct flowi4 fl4;
@@ -1901,13 +1925,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 				  dev->name);
 			goto drop;
 		}
-		if (family != ip_tunnel_info_af(info))
-			goto drop;
-
 		dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;
 		vni = be64_to_cpu(info->key.tun_id);
-		remote_ip.sa.sa_family = family;
-		if (family == AF_INET)
+		remote_ip.sa.sa_family = ip_tunnel_info_af(info);
+		if (remote_ip.sa.sa_family == AF_INET)
 			remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst;
 		else
 			remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst;
@@ -1952,6 +1973,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	if (dst->sa.sa_family == AF_INET) {
+		if (!vxlan->vn4_sock)
+			goto drop;
+		sk = vxlan->vn4_sock->sock->sk;
+
 		if (info && (info->key.tun_flags & TUNNEL_DONT_FRAGMENT))
 			df = htons(IP_DF);
 
@@ -2013,6 +2038,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		struct flowi6 fl6;
 		u32 rt6i_flags;
 
+		if (!vxlan->vn6_sock)
+			goto drop;
+		sk = vxlan->vn6_sock->sock->sk;
+
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_oif = rdst ? rdst->remote_ifindex : 0;
 		fl6.daddr = dst->sin6.sin6_addr;
@@ -2204,7 +2233,6 @@ static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan)
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 	__u32 vni = vxlan->default_dst.remote_vni;
 
-	vxlan->vn_sock = vs;
 	spin_lock(&vn->sock_lock);
 	hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni));
 	spin_unlock(&vn->sock_lock);
@@ -2535,14 +2563,13 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
 }
 
 /* Create new listen socket if needed */
-static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
-					      u32 flags)
+static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,
+					      __be16 port, u32 flags)
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_sock *vs;
 	struct socket *sock;
 	unsigned int h;
-	bool ipv6 = !!(flags & VXLAN_F_IPV6);
 	struct udp_tunnel_sock_cfg tunnel_cfg;
 
 	vs = kzalloc(sizeof(*vs), GFP_KERNEL);
@@ -2587,11 +2614,10 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
 	return vs;
 }
 
-static int vxlan_sock_add(struct vxlan_dev *vxlan)
+static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
 {
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 	struct vxlan_sock *vs = NULL;
-	bool ipv6 = vxlan->flags & VXLAN_F_IPV6;
 
 	if (!vxlan->cfg.no_share) {
 		spin_lock(&vn->sock_lock);
@@ -2604,20 +2630,46 @@ static int vxlan_sock_add(struct vxlan_dev *vxlan)
 		spin_unlock(&vn->sock_lock);
 	}
 	if (!vs)
-		vs = vxlan_socket_create(vxlan->net, vxlan->cfg.dst_port,
-					 vxlan->flags);
+		vs = vxlan_socket_create(vxlan->net, ipv6,
+					 vxlan->cfg.dst_port, vxlan->flags);
 	if (IS_ERR(vs))
 		return PTR_ERR(vs);
+#if IS_ENABLED(CONFIG_IPV6)
+	if (ipv6)
+		vxlan->vn6_sock = vs;
+	else
+#endif
+		vxlan->vn4_sock = vs;
 	vxlan_vs_add_dev(vs, vxlan);
 	return 0;
 }
 
+static int vxlan_sock_add(struct vxlan_dev *vxlan)
+{
+	bool ipv6 = vxlan->flags & VXLAN_F_IPV6;
+	bool metadata = vxlan->flags & VXLAN_F_COLLECT_METADATA;
+	int ret = 0;
+
+	vxlan->vn4_sock = NULL;
+#if IS_ENABLED(CONFIG_IPV6)
+	vxlan->vn6_sock = NULL;
+	if (ipv6 || metadata)
+		ret = __vxlan_sock_add(vxlan, true);
+#endif
+	if (!ret && (!ipv6 || metadata))
+		ret = __vxlan_sock_add(vxlan, false);
+	if (ret < 0)
+		vxlan_sock_release(vxlan);
+	return ret;
+}
+
 static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 			       struct vxlan_config *conf)
 {
 	struct vxlan_net *vn = net_generic(src_net, vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_rdst *dst = &vxlan->default_dst;
+	unsigned short needed_headroom = ETH_HLEN;
 	int err;
 	bool use_ipv6 = false;
 	__be16 default_port = vxlan->cfg.dst_port;
@@ -2637,6 +2689,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 		if (!IS_ENABLED(CONFIG_IPV6))
 			return -EPFNOSUPPORT;
 		use_ipv6 = true;
+		vxlan->flags |= VXLAN_F_IPV6;
 	}
 
 	if (conf->remote_ifindex) {
@@ -2657,22 +2710,21 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 				pr_info("IPv6 is disabled via sysctl\n");
 				return -EPERM;
 			}
-			vxlan->flags |= VXLAN_F_IPV6;
 		}
 #endif
 
 		if (!conf->mtu)
 			dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
 
-		dev->needed_headroom = lowerdev->hard_header_len +
-				       (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
-	} else if (use_ipv6) {
-		vxlan->flags |= VXLAN_F_IPV6;
-		dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM;
-	} else {
-		dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
+		needed_headroom = lowerdev->hard_header_len;
 	}
 
+	if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA)
+		needed_headroom += VXLAN6_HEADROOM;
+	else
+		needed_headroom += VXLAN_HEADROOM;
+	dev->needed_headroom = needed_headroom;
+
 	memcpy(&vxlan->cfg, conf, sizeof(*conf));
 	if (!vxlan->cfg.dst_port)
 		vxlan->cfg.dst_port = default_port;
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 480a319b4c92..c1c899c3a51b 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -152,7 +152,10 @@ struct vxlan_config {
 struct vxlan_dev {
 	struct hlist_node hlist;	/* vni hash table */
 	struct list_head  next;		/* vxlan's per namespace list */
-	struct vxlan_sock *vn_sock;	/* listening socket */
+	struct vxlan_sock *vn4_sock;	/* listening socket for IPv4 */
+#if IS_ENABLED(CONFIG_IPV6)
+	struct vxlan_sock *vn6_sock;	/* listening socket for IPv6 */
+#endif
 	struct net_device *dev;
 	struct net	  *net;		/* netns for packet i/o */
 	struct vxlan_rdst default_dst;	/* default destination */
@@ -195,9 +198,14 @@ struct vxlan_dev {
 struct net_device *vxlan_dev_create(struct net *net, const char *name,
 				    u8 name_assign_type, struct vxlan_config *conf);
 
-static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan)
+static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan,
+					unsigned short family)
 {
-	return inet_sk(vxlan->vn_sock->sock->sk)->inet_sport;
+#if IS_ENABLED(CONFIG_IPV6)
+	if (family == AF_INET6)
+		return inet_sk(vxlan->vn6_sock->sock->sk)->inet_sport;
+#endif
+	return inet_sk(vxlan->vn4_sock->sock->sk)->inet_sport;
 }
 
 static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index c11413d5075f..fb3cdb85905d 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -151,7 +151,8 @@ static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
 {
 	struct vxlan_dev *vxlan = netdev_priv(vport->dev);
 	struct net *net = ovs_dp_get_net(vport->dp);
-	__be16 dst_port = vxlan_dev_dst_port(vxlan);
+	unsigned short family = ip_tunnel_info_af(upcall->egress_tun_info);
+	__be16 dst_port = vxlan_dev_dst_port(vxlan, family);
 	__be16 src_port;
 	int port_min;
 	int port_max;
-- 
cgit v1.2.3


From 188515fbc6b18e6bc6f2fa4629f1a77308197371 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 14 Sep 2015 20:08:51 -0500
Subject: openvswitch: Pass net into ovs_vport_output

When struct net starts being passed through the ipv4 and ipv6 fragment
routines ovs_vport_output will need to take a net parameter.
Prepare ovs_vport_output before that is needed and introduce
ovs_vport_output_skk for the call sites that still need the old
calling conventions.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 net/openvswitch/actions.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

(limited to 'net/openvswitch')

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 315f5330b6e5..f00c641ecd93 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -620,7 +620,7 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	return 0;
 }
 
-static int ovs_vport_output(struct sock *sock, struct sk_buff *skb)
+static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage);
 	struct vport *vport = data->vport;
@@ -645,6 +645,11 @@ static int ovs_vport_output(struct sock *sock, struct sk_buff *skb)
 	ovs_vport_send(vport, skb);
 	return 0;
 }
+static int ovs_vport_output_sk(struct sock *sk, struct sk_buff *skb)
+{
+	struct net *net = dev_net(skb_dst(skb)->dev);
+	return ovs_vport_output(net, sk, skb);
+}
 
 static unsigned int
 ovs_dst_get_mtu(const struct dst_entry *dst)
@@ -700,7 +705,7 @@ static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
 		skb_dst_set_noref(skb, &ovs_dst);
 		IPCB(skb)->frag_max_size = mru;
 
-		ip_do_fragment(skb->sk, skb, ovs_vport_output);
+		ip_do_fragment(skb->sk, skb, ovs_vport_output_sk);
 		refdst_drop(orig_dst);
 	} else if (ethertype == htons(ETH_P_IPV6)) {
 		const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
@@ -722,7 +727,7 @@ static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
 		skb_dst_set_noref(skb, &ovs_rt.dst);
 		IP6CB(skb)->frag_max_size = mru;
 
-		v6ops->fragment(skb->sk, skb, ovs_vport_output);
+		v6ops->fragment(skb->sk, skb, ovs_vport_output_sk);
 		refdst_drop(orig_dst);
 	} else {
 		WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
-- 
cgit v1.2.3


From c559cd3ad32ba729bb810283c5fc6838d2473c2e Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 14 Sep 2015 20:10:28 -0500
Subject: openvswitch: Pass net into ovs_fragment

In preparation for the ipv4 and ipv6 fragmentation code taking a net
parameter pass a struct net into ovs_fragment where the v4 and v6
fragmentation code is called.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 net/openvswitch/actions.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'net/openvswitch')

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index f00c641ecd93..ba38662f9f5e 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -684,8 +684,8 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb)
 	skb_pull(skb, hlen);
 }
 
-static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
-			 __be16 ethertype)
+static void ovs_fragment(struct net *net, struct vport *vport,
+			 struct sk_buff *skb, u16 mru, __be16 ethertype)
 {
 	if (skb_network_offset(skb) > MAX_L2_LEN) {
 		OVS_NLERR(1, "L2 header too long to fragment");
@@ -748,6 +748,7 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 		if (likely(!mru || (skb->len <= mru + ETH_HLEN))) {
 			ovs_vport_send(vport, skb);
 		} else if (mru <= vport->dev->mtu) {
+			struct net *net = read_pnet(&dp->net);
 			__be16 ethertype = key->eth.type;
 
 			if (!is_flow_key_valid(key)) {
@@ -757,7 +758,7 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 					ethertype = vlan_get_protocol(skb);
 			}
 
-			ovs_fragment(vport, skb, mru, ethertype);
+			ovs_fragment(net, vport, skb, mru, ethertype);
 		} else {
 			kfree_skb(skb);
 		}
-- 
cgit v1.2.3


From 694869b3c5440e0d821583ec8811b6cb5d03742d Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 12 Jun 2015 21:55:31 -0500
Subject: ipv4: Pass struct net through ip_fragment

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/net/ip.h                |  4 ++--
 net/bridge/br_netfilter_hooks.c |  6 +++---
 net/ipv4/ip_output.c            | 44 +++++++++++++++++++----------------------
 net/openvswitch/actions.c       |  2 +-
 4 files changed, 26 insertions(+), 30 deletions(-)

(limited to 'net/openvswitch')

diff --git a/include/net/ip.h b/include/net/ip.h
index 91a6b2c88341..b783141b0671 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -109,8 +109,8 @@ int ip_local_deliver(struct sk_buff *skb);
 int ip_mr_input(struct sk_buff *skb);
 int ip_output(struct sock *sk, struct sk_buff *skb);
 int ip_mc_output(struct sock *sk, struct sk_buff *skb);
-int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
-		   int (*output)(struct sock *, struct sk_buff *));
+int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+		   int (*output)(struct net *, struct sock *, struct sk_buff *));
 void ip_send_check(struct iphdr *ip);
 int __ip_local_out(struct sk_buff *skb);
 int ip_local_out_sk(struct sock *sk, struct sk_buff *skb);
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 13f03671c88d..00e356c236cf 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -701,7 +701,7 @@ static int br_nf_push_frag_xmit_sk(struct sock *sk, struct sk_buff *skb)
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
 static int
 br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
-		  int (*output)(struct sock *, struct sk_buff *))
+		  int (*output)(struct net *, struct sock *, struct sk_buff *))
 {
 	unsigned int mtu = ip_skb_dst_mtu(skb);
 	struct iphdr *iph = ip_hdr(skb);
@@ -714,7 +714,7 @@ br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		return -EMSGSIZE;
 	}
 
-	return ip_do_fragment(sk, skb, output);
+	return ip_do_fragment(net, sk, skb, output);
 }
 #endif
 
@@ -763,7 +763,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff
 		skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
 						 data->size);
 
-		return br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit_sk);
+		return br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit);
 	}
 #endif
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index aff6766922e8..911ea739049a 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -83,9 +83,10 @@
 int sysctl_ip_default_ttl __read_mostly = IPDEFTTL;
 EXPORT_SYMBOL(sysctl_ip_default_ttl);
 
-static int ip_fragment(struct sock *sk, struct sk_buff *skb,
-		       unsigned int mtu,
-		       int (*output)(struct sock *, struct sk_buff *));
+static int
+ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+	    unsigned int mtu,
+	    int (*output)(struct net *, struct sock *, struct sk_buff *));
 
 /* Generate a checksum for an outgoing IP datagram. */
 void ip_send_check(struct iphdr *iph)
@@ -176,12 +177,11 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
 }
 EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
 
-static int ip_finish_output2(struct sock *sk, struct sk_buff *skb)
+static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct rtable *rt = (struct rtable *)dst;
 	struct net_device *dev = dst->dev;
-	struct net *net = dev_net(dev);
 	unsigned int hh_len = LL_RESERVED_SPACE(dev);
 	struct neighbour *neigh;
 	u32 nexthop;
@@ -225,8 +225,8 @@ static int ip_finish_output2(struct sock *sk, struct sk_buff *skb)
 	return -EINVAL;
 }
 
-static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb,
-				unsigned int mtu)
+static int ip_finish_output_gso(struct net *net, struct sock *sk,
+				struct sk_buff *skb, unsigned int mtu)
 {
 	netdev_features_t features;
 	struct sk_buff *segs;
@@ -235,7 +235,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb,
 	/* common case: locally created skb or seglen is <= mtu */
 	if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
 	      skb_gso_network_seglen(skb) <= mtu)
-		return ip_finish_output2(sk, skb);
+		return ip_finish_output2(net, sk, skb);
 
 	/* Slowpath -  GSO segment length is exceeding the dst MTU.
 	 *
@@ -258,7 +258,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb,
 		int err;
 
 		segs->next = NULL;
-		err = ip_fragment(sk, segs, mtu, ip_finish_output2);
+		err = ip_fragment(net, sk, segs, mtu, ip_finish_output2);
 
 		if (err && ret == 0)
 			ret = err;
@@ -281,12 +281,12 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk
 #endif
 	mtu = ip_skb_dst_mtu(skb);
 	if (skb_is_gso(skb))
-		return ip_finish_output_gso(sk, skb, mtu);
+		return ip_finish_output_gso(net, sk, skb, mtu);
 
 	if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU))
-		return ip_fragment(sk, skb, mtu, ip_finish_output2);
+		return ip_fragment(net, sk, skb, mtu, ip_finish_output2);
 
-	return ip_finish_output2(sk, skb);
+	return ip_finish_output2(net, sk, skb);
 }
 
 int ip_mc_output(struct sock *sk, struct sk_buff *skb)
@@ -495,20 +495,18 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	skb_copy_secmark(to, from);
 }
 
-static int ip_fragment(struct sock *sk, struct sk_buff *skb,
+static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		       unsigned int mtu,
-		       int (*output)(struct sock *, struct sk_buff *))
+		       int (*output)(struct net *, struct sock *, struct sk_buff *))
 {
 	struct iphdr *iph = ip_hdr(skb);
 
 	if ((iph->frag_off & htons(IP_DF)) == 0)
-		return ip_do_fragment(sk, skb, output);
+		return ip_do_fragment(net, sk, skb, output);
 
 	if (unlikely(!skb->ignore_df ||
 		     (IPCB(skb)->frag_max_size &&
 		      IPCB(skb)->frag_max_size > mtu))) {
-		struct net *net = dev_net(skb_rtable(skb)->dst.dev);
-
 		IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 			  htonl(mtu));
@@ -516,7 +514,7 @@ static int ip_fragment(struct sock *sk, struct sk_buff *skb,
 		return -EMSGSIZE;
 	}
 
-	return ip_do_fragment(sk, skb, output);
+	return ip_do_fragment(net, sk, skb, output);
 }
 
 /*
@@ -526,8 +524,8 @@ static int ip_fragment(struct sock *sk, struct sk_buff *skb,
  *	single device frame, and queue such a frame for sending.
  */
 
-int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
-		   int (*output)(struct sock *, struct sk_buff *))
+int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+		   int (*output)(struct net *, struct sock *, struct sk_buff *))
 {
 	struct iphdr *iph;
 	int ptr;
@@ -537,11 +535,9 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
 	int offset;
 	__be16 not_last_frag;
 	struct rtable *rt = skb_rtable(skb);
-	struct net *net;
 	int err = 0;
 
 	dev = rt->dst.dev;
-	net = dev_net(dev);
 
 	/*
 	 *	Point into the IP datagram header.
@@ -631,7 +627,7 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
 				ip_send_check(iph);
 			}
 
-			err = output(sk, skb);
+			err = output(net, sk, skb);
 
 			if (!err)
 				IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
@@ -771,7 +767,7 @@ slow_path:
 
 		ip_send_check(iph);
 
-		err = output(sk, skb2);
+		err = output(net, sk, skb2);
 		if (err)
 			goto fail;
 
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index ba38662f9f5e..b281b2b76c3f 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -705,7 +705,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
 		skb_dst_set_noref(skb, &ovs_dst);
 		IPCB(skb)->frag_max_size = mru;
 
-		ip_do_fragment(skb->sk, skb, ovs_vport_output_sk);
+		ip_do_fragment(net, skb->sk, skb, ovs_vport_output);
 		refdst_drop(orig_dst);
 	} else if (ethertype == htons(ETH_P_IPV6)) {
 		const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
-- 
cgit v1.2.3


From 7d8c6e391575ee86c870b88635a163743fca9eac Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 12 Jun 2015 22:12:04 -0500
Subject: ipv6: Pass struct net through ip6_fragment

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 include/linux/netfilter_ipv6.h  |  4 ++--
 include/net/ip6_route.h         |  4 ++--
 net/bridge/br_netfilter_hooks.c |  2 +-
 net/ipv6/ip6_output.c           | 16 +++++++---------
 net/ipv6/xfrm6_output.c         | 10 ++++++++--
 net/openvswitch/actions.c       |  2 +-
 6 files changed, 21 insertions(+), 17 deletions(-)

(limited to 'net/openvswitch')

diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index 2ac8369fa96c..47c6b04c28c0 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -17,8 +17,8 @@ struct nf_ipv6_ops {
 	int (*chk_addr)(struct net *net, const struct in6_addr *addr,
 			const struct net_device *dev, int strict);
 	void (*route_input)(struct sk_buff *skb);
-	int (*fragment)(struct sock *sk, struct sk_buff *skb,
-			int (*output)(struct sock *, struct sk_buff *));
+	int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb,
+			int (*output)(struct net *, struct sock *, struct sk_buff *));
 };
 
 #ifdef CONFIG_NETFILTER
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 297629aadb19..2bfb2ad2fab1 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -173,8 +173,8 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst,
 		 ipv6_addr_equal(&rt->rt6i_dst.addr, daddr));
 }
 
-int ip6_fragment(struct sock *sk, struct sk_buff *skb,
-		 int (*output)(struct sock *, struct sk_buff *));
+int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+		 int (*output)(struct net *, struct sock *, struct sk_buff *));
 
 static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
 {
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 00e356c236cf..815994d5b02d 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -786,7 +786,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff
 						 data->size);
 
 		if (v6ops)
-			return v6ops->fragment(sk, skb, br_nf_push_frag_xmit_sk);
+			return v6ops->fragment(net, sk, skb, br_nf_push_frag_xmit);
 
 		kfree_skb(skb);
 		return -EMSGSIZE;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a598fe2c0849..caf7d14a1bdd 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -56,11 +56,10 @@
 #include <net/checksum.h>
 #include <linux/mroute6.h>
 
-static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb)
+static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
-	struct net *net = dev_net(dev);
 	struct neighbour *neigh;
 	struct in6_addr *nexthop;
 	int ret;
@@ -126,9 +125,9 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
 	    dst_allfrag(skb_dst(skb)) ||
 	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
-		return ip6_fragment(sk, skb, ip6_finish_output2);
+		return ip6_fragment(net, sk, skb, ip6_finish_output2);
 	else
-		return ip6_finish_output2(sk, skb);
+		return ip6_finish_output2(net, sk, skb);
 }
 
 int ip6_output(struct sock *sk, struct sk_buff *skb)
@@ -554,8 +553,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	skb_copy_secmark(to, from);
 }
 
-int ip6_fragment(struct sock *sk, struct sk_buff *skb,
-		 int (*output)(struct sock *, struct sk_buff *))
+int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+		 int (*output)(struct net *, struct sock *, struct sk_buff *))
 {
 	struct sk_buff *frag;
 	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
@@ -568,7 +567,6 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
 	__be32 frag_id;
 	int ptr, offset = 0, err = 0;
 	u8 *prevhdr, nexthdr = 0;
-	struct net *net = dev_net(skb_dst(skb)->dev);
 
 	hlen = ip6_find_1stfragopt(skb, &prevhdr);
 	nexthdr = *prevhdr;
@@ -688,7 +686,7 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
 				ip6_copy_metadata(frag, skb);
 			}
 
-			err = output(sk, skb);
+			err = output(net, sk, skb);
 			if (!err)
 				IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 					      IPSTATS_MIB_FRAGCREATES);
@@ -816,7 +814,7 @@ slow_path:
 		/*
 		 *	Put this fragment into the sending queue.
 		 */
-		err = output(sk, frag);
+		err = output(net, sk, frag);
 		if (err)
 			goto fail;
 
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 0c3e9ffcf231..335066a64b45 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -131,6 +131,12 @@ int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb)
 	return xfrm_output(sk, skb);
 }
 
+static int __xfrm6_output_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	struct xfrm_state *x = skb_dst(skb)->xfrm;
+	return x->outer_mode->afinfo->output_finish(sk, skb);
+}
+
 static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -160,8 +166,8 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (x->props.mode == XFRM_MODE_TUNNEL &&
 	    ((skb->len > mtu && !skb_is_gso(skb)) ||
 		dst_allfrag(skb_dst(skb)))) {
-		return ip6_fragment(sk, skb,
-				    x->outer_mode->afinfo->output_finish);
+		return ip6_fragment(net, sk, skb,
+				    __xfrm6_output_finish);
 	}
 	return x->outer_mode->afinfo->output_finish(sk, skb);
 }
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index b281b2b76c3f..f33c627f97b3 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -727,7 +727,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
 		skb_dst_set_noref(skb, &ovs_rt.dst);
 		IP6CB(skb)->frag_max_size = mru;
 
-		v6ops->fragment(skb->sk, skb, ovs_vport_output_sk);
+		v6ops->fragment(net, skb->sk, skb, ovs_vport_output);
 		refdst_drop(orig_dst);
 	} else {
 		WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
-- 
cgit v1.2.3


From 184e16d79d38634cbb7b7c1cd3832caf89595c9a Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 14 Sep 2015 20:14:45 -0500
Subject: openvswitch: Remove ovs_vport_output_sk

This was a compatibility function needed while the ipv4 and ipv6
fragmentation code was being modified to pass a struct net through
them.  Now that is complete this function has no more users so remove
it.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 net/openvswitch/actions.c | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'net/openvswitch')

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index f33c627f97b3..1d21ab9d2b5c 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -645,11 +645,6 @@ static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *sk
 	ovs_vport_send(vport, skb);
 	return 0;
 }
-static int ovs_vport_output_sk(struct sock *sk, struct sk_buff *skb)
-{
-	struct net *net = dev_net(skb_dst(skb)->dev);
-	return ovs_vport_output(net, sk, skb);
-}
 
 static unsigned int
 ovs_dst_get_mtu(const struct dst_entry *dst)
-- 
cgit v1.2.3


From 00a93babd06aaad31d23384cda576ede0f586a8c Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Mon, 5 Oct 2015 13:09:46 +0200
Subject: openvswitch: add tunnel protocol to sw_flow_key

Store tunnel protocol (AF_INET or AF_INET6) in sw_flow_key. This field now
also acts as an indicator whether the flow contains tunnel data (this was
previously indicated by tun_key.u.ipv4.dst being set but with IPv6 addresses
in an union with IPv4 ones this won't work anymore).

The new field was added to a hole in sw_flow_key.

Signed-off-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow.c         |  4 ++--
 net/openvswitch/flow.h         |  1 +
 net/openvswitch/flow_netlink.c | 10 ++++++++--
 net/openvswitch/flow_table.c   |  2 +-
 4 files changed, 12 insertions(+), 5 deletions(-)

(limited to 'net/openvswitch')

diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index c8db44ab2ee7..0ea128eeeab2 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -698,8 +698,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 {
 	/* Extract metadata from packet. */
 	if (tun_info) {
-		if (ip_tunnel_info_af(tun_info) != AF_INET)
-			return -EINVAL;
+		key->tun_proto = ip_tunnel_info_af(tun_info);
 		memcpy(&key->tun_key, &tun_info->key, sizeof(key->tun_key));
 
 		if (tun_info->options_len) {
@@ -714,6 +713,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 			key->tun_opts_len = 0;
 		}
 	} else  {
+		key->tun_proto = 0;
 		key->tun_opts_len = 0;
 		memset(&key->tun_key, 0, sizeof(key->tun_key));
 	}
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index fe527d2dd4b7..5688e33e2de6 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -63,6 +63,7 @@ struct sw_flow_key {
 		u32	skb_mark;	/* SKB mark. */
 		u16	in_port;	/* Input switch port (or DP_MAX_PORTS). */
 	} __packed phy; /* Safe when right after 'tun_key'. */
+	u8 tun_proto;			/* Protocol of encapsulating tunnel. */
 	u32 ovs_flow_hash;		/* Datapath computed hash value.  */
 	u32 recirc_id;			/* Recirculation ID.  */
 	struct {
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 5c030a4d7338..6be701f6b31b 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -643,6 +643,10 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 	}
 
 	SW_FLOW_KEY_PUT(match, tun_key.tun_flags, tun_flags, is_mask);
+	if (is_mask)
+		SW_FLOW_KEY_MEMSET_FIELD(match, tun_proto, 0xff, true);
+	else
+		SW_FLOW_KEY_PUT(match, tun_proto, AF_INET, false);
 
 	if (rem > 0) {
 		OVS_NLERR(log, "IPv4 tunnel attribute has %d unknown bytes.",
@@ -1194,7 +1198,7 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match,
 			/* The userspace does not send tunnel attributes that
 			 * are 0, but we should not wildcard them nonetheless.
 			 */
-			if (match->key->tun_key.u.ipv4.dst)
+			if (match->key->tun_proto)
 				SW_FLOW_KEY_MEMSET_FIELD(match, tun_key,
 							 0xff, true);
 
@@ -1367,7 +1371,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 	if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority))
 		goto nla_put_failure;
 
-	if ((swkey->tun_key.u.ipv4.dst || is_mask)) {
+	if ((swkey->tun_proto || is_mask)) {
 		const void *opts = NULL;
 
 		if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT)
@@ -1913,6 +1917,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 
 	tun_info = &tun_dst->u.tun_info;
 	tun_info->mode = IP_TUNNEL_INFO_TX;
+	if (key.tun_proto == AF_INET6)
+		tun_info->mode |= IP_TUNNEL_INFO_IPV6;
 	tun_info->key = key.tun_key;
 
 	/* We need to store the options in the action itself since
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index f2ea83ba4763..95dbcedf0bd4 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -427,7 +427,7 @@ static u32 flow_hash(const struct sw_flow_key *key,
 
 static int flow_key_start(const struct sw_flow_key *key)
 {
-	if (key->tun_key.u.ipv4.dst)
+	if (key->tun_proto)
 		return 0;
 	else
 		return rounddown(offsetof(struct sw_flow_key, phy),
-- 
cgit v1.2.3


From 6b26ba3a7d952e611dcde1f3f77ce63bcc70540a Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Mon, 5 Oct 2015 13:09:47 +0200
Subject: openvswitch: netlink attributes for IPv6 tunneling

Add netlink attributes for IPv6 tunnel addresses. This enables IPv6 support
for tunnels.

Signed-off-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/openvswitch.h |   2 +
 net/openvswitch/flow_netlink.c   | 121 +++++++++++++++++++++++++++------------
 2 files changed, 86 insertions(+), 37 deletions(-)

(limited to 'net/openvswitch')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 32e07d8cbaf4..4036e1b1980f 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -349,6 +349,8 @@ enum ovs_tunnel_key_attr {
 	OVS_TUNNEL_KEY_ATTR_TP_SRC,		/* be16 src Transport Port. */
 	OVS_TUNNEL_KEY_ATTR_TP_DST,		/* be16 dst Transport Port. */
 	OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS,		/* Nested OVS_VXLAN_EXT_* */
+	OVS_TUNNEL_KEY_ATTR_IPV6_SRC,		/* struct in6_addr src IPv6 address. */
+	OVS_TUNNEL_KEY_ATTR_IPV6_DST,		/* struct in6_addr dst IPv6 address. */
 	__OVS_TUNNEL_KEY_ATTR_MAX
 };
 
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 6be701f6b31b..77850f177a47 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -262,8 +262,8 @@ size_t ovs_tun_key_attr_size(void)
 	 * updating this function.
 	 */
 	return    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(16)   /* OVS_TUNNEL_KEY_ATTR_IPV[46]_SRC */
+		+ nla_total_size(16)   /* OVS_TUNNEL_KEY_ATTR_IPV[46]_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 */
@@ -323,6 +323,8 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1]
 	[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS]   = { .len = OVS_ATTR_VARIABLE },
 	[OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS]    = { .len = OVS_ATTR_NESTED,
 						.next = ovs_vxlan_ext_key_lens },
+	[OVS_TUNNEL_KEY_ATTR_IPV6_SRC]      = { .len = sizeof(struct in6_addr) },
+	[OVS_TUNNEL_KEY_ATTR_IPV6_DST]      = { .len = sizeof(struct in6_addr) },
 };
 
 /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute.  */
@@ -542,14 +544,14 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr,
 	return 0;
 }
 
-static int ipv4_tun_from_nlattr(const struct nlattr *attr,
-				struct sw_flow_match *match, bool is_mask,
-				bool log)
+static int ip_tun_from_nlattr(const struct nlattr *attr,
+			      struct sw_flow_match *match, bool is_mask,
+			      bool log)
 {
 	struct nlattr *a;
 	int rem;
 	bool ttl = false;
-	__be16 tun_flags = 0;
+	__be16 tun_flags = 0, ipv4 = false, ipv6 = false;
 	int opts_type = 0;
 
 	nla_for_each_nested(a, attr, rem) {
@@ -578,10 +580,22 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 		case OVS_TUNNEL_KEY_ATTR_IPV4_SRC:
 			SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.src,
 					nla_get_in_addr(a), is_mask);
+			ipv4 = true;
 			break;
 		case OVS_TUNNEL_KEY_ATTR_IPV4_DST:
 			SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.dst,
 					nla_get_in_addr(a), is_mask);
+			ipv4 = true;
+			break;
+		case OVS_TUNNEL_KEY_ATTR_IPV6_SRC:
+			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+					nla_get_in6_addr(a), is_mask);
+			ipv6 = true;
+			break;
+		case OVS_TUNNEL_KEY_ATTR_IPV6_DST:
+			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+					nla_get_in6_addr(a), is_mask);
+			ipv6 = true;
 			break;
 		case OVS_TUNNEL_KEY_ATTR_TOS:
 			SW_FLOW_KEY_PUT(match, tun_key.tos,
@@ -636,7 +650,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 			opts_type = type;
 			break;
 		default:
-			OVS_NLERR(log, "Unknown IPv4 tunnel attribute %d",
+			OVS_NLERR(log, "Unknown IP tunnel attribute %d",
 				  type);
 			return -EINVAL;
 		}
@@ -646,22 +660,36 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 	if (is_mask)
 		SW_FLOW_KEY_MEMSET_FIELD(match, tun_proto, 0xff, true);
 	else
-		SW_FLOW_KEY_PUT(match, tun_proto, AF_INET, false);
+		SW_FLOW_KEY_PUT(match, tun_proto, ipv6 ? AF_INET6 : AF_INET,
+				false);
 
 	if (rem > 0) {
-		OVS_NLERR(log, "IPv4 tunnel attribute has %d unknown bytes.",
+		OVS_NLERR(log, "IP tunnel attribute has %d unknown bytes.",
 			  rem);
 		return -EINVAL;
 	}
 
+	if (ipv4 && ipv6) {
+		OVS_NLERR(log, "Mixed IPv4 and IPv6 tunnel attributes");
+		return -EINVAL;
+	}
+
 	if (!is_mask) {
-		if (!match->key->tun_key.u.ipv4.dst) {
+		if (!ipv4 && !ipv6) {
+			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 (ipv6 && ipv6_addr_any(&match->key->tun_key.u.ipv6.dst)) {
+			OVS_NLERR(log, "IPv6 tunnel dst address is zero");
+			return -EINVAL;
+		}
 
 		if (!ttl) {
-			OVS_NLERR(log, "IPv4 tunnel TTL not specified.");
+			OVS_NLERR(log, "IP tunnel TTL not specified.");
 			return -EINVAL;
 		}
 	}
@@ -686,21 +714,36 @@ static int vxlan_opt_to_nlattr(struct sk_buff *skb,
 	return 0;
 }
 
-static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
-				const struct ip_tunnel_key *output,
-				const void *tun_opts, int swkey_tun_opts_len)
+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)
 {
 	if (output->tun_flags & TUNNEL_KEY &&
 	    nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id))
 		return -EMSGSIZE;
-	if (output->u.ipv4.src &&
-	    nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC,
-			    output->u.ipv4.src))
-		return -EMSGSIZE;
-	if (output->u.ipv4.dst &&
-	    nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST,
-			    output->u.ipv4.dst))
-		return -EMSGSIZE;
+	switch (tun_proto) {
+	case AF_INET:
+		if (output->u.ipv4.src &&
+		    nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC,
+				    output->u.ipv4.src))
+			return -EMSGSIZE;
+		if (output->u.ipv4.dst &&
+		    nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST,
+				    output->u.ipv4.dst))
+			return -EMSGSIZE;
+		break;
+	case AF_INET6:
+		if (!ipv6_addr_any(&output->u.ipv6.src) &&
+		    nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_SRC,
+				     &output->u.ipv6.src))
+			return -EMSGSIZE;
+		if (!ipv6_addr_any(&output->u.ipv6.dst) &&
+		    nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_DST,
+				     &output->u.ipv6.dst))
+			return -EMSGSIZE;
+		break;
+	}
 	if (output->tos &&
 	    nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->tos))
 		return -EMSGSIZE;
@@ -734,9 +777,10 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
 	return 0;
 }
 
-static int ipv4_tun_to_nlattr(struct sk_buff *skb,
-			      const struct ip_tunnel_key *output,
-			      const void *tun_opts, int swkey_tun_opts_len)
+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)
 {
 	struct nlattr *nla;
 	int err;
@@ -745,7 +789,8 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb,
 	if (!nla)
 		return -EMSGSIZE;
 
-	err = __ipv4_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len);
+	err = __ip_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len,
+				 tun_proto);
 	if (err)
 		return err;
 
@@ -757,9 +802,10 @@ int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb,
 				  const struct ip_tunnel_info *egress_tun_info,
 				  const void *egress_tun_opts)
 {
-	return __ipv4_tun_to_nlattr(skb, &egress_tun_info->key,
-				    egress_tun_opts,
-				    egress_tun_info->options_len);
+	return __ip_tun_to_nlattr(skb, &egress_tun_info->key,
+				  egress_tun_opts,
+				  egress_tun_info->options_len,
+				  ip_tunnel_info_af(egress_tun_info));
 }
 
 static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
@@ -810,8 +856,8 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
 		*attrs &= ~(1 << OVS_KEY_ATTR_SKB_MARK);
 	}
 	if (*attrs & (1 << OVS_KEY_ATTR_TUNNEL)) {
-		if (ipv4_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match,
-					 is_mask, log) < 0)
+		if (ip_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match,
+				       is_mask, log) < 0)
 			return -EINVAL;
 		*attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL);
 	}
@@ -1377,8 +1423,8 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 		if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT)
 			opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len);
 
-		if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts,
-				       swkey->tun_opts_len))
+		if (ip_tun_to_nlattr(skb, &output->tun_key, opts,
+				     swkey->tun_opts_len, swkey->tun_proto))
 			goto nla_put_failure;
 	}
 
@@ -1881,7 +1927,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	int err = 0, start, opts_type;
 
 	ovs_match_init(&match, &key, NULL);
-	opts_type = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log);
+	opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log);
 	if (opts_type < 0)
 		return opts_type;
 
@@ -2380,10 +2426,11 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
 		if (!start)
 			return -EMSGSIZE;
 
-		err = ipv4_tun_to_nlattr(skb, &tun_info->key,
-					 tun_info->options_len ?
+		err = ip_tun_to_nlattr(skb, &tun_info->key,
+				       tun_info->options_len ?
 					     ip_tunnel_info_opts(tun_info) : NULL,
-					 tun_info->options_len);
+				       tun_info->options_len,
+				       ip_tunnel_info_af(tun_info));
 		if (err)
 			return err;
 		nla_nest_end(skb, start);
-- 
cgit v1.2.3


From 19bcf9f203c82c2028f5a0881b1f0690e3207190 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 9 Oct 2015 13:44:54 -0500
Subject: ipv4: Pass struct net into ip_defrag and ip_check_defrag

The function ip_defrag is called on both the input and the output
paths of the networking stack.  In particular conntrack when it is
tracking outbound packets from the local machine calls ip_defrag.

So add a struct net parameter and stop making ip_defrag guess which
network namespace it needs to defragment packets in.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c               | 2 +-
 include/net/ip.h                    | 6 +++---
 net/ipv4/ip_fragment.c              | 7 +++----
 net/ipv4/ip_input.c                 | 7 ++++---
 net/ipv4/netfilter/nf_defrag_ipv4.c | 7 ++++---
 net/netfilter/ipvs/ip_vs_core.c     | 2 +-
 net/openvswitch/conntrack.c         | 2 +-
 net/packet/af_packet.c              | 6 +++---
 8 files changed, 20 insertions(+), 19 deletions(-)

(limited to 'net/openvswitch')

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 47da43595ac2..86f6c6292c27 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -412,7 +412,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 
 	port = macvlan_port_get_rcu(skb->dev);
 	if (is_multicast_ether_addr(eth->h_dest)) {
-		skb = ip_check_defrag(skb, IP_DEFRAG_MACVLAN);
+		skb = ip_check_defrag(dev_net(skb->dev), skb, IP_DEFRAG_MACVLAN);
 		if (!skb)
 			return RX_HANDLER_CONSUMED;
 		eth = eth_hdr(skb);
diff --git a/include/net/ip.h b/include/net/ip.h
index 3c904a28d5e5..1a98f1ca1638 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -506,11 +506,11 @@ static inline bool ip_defrag_user_in_between(u32 user,
 	return user >= lower_bond && user <= upper_bond;
 }
 
-int ip_defrag(struct sk_buff *skb, u32 user);
+int ip_defrag(struct net *net, struct sk_buff *skb, u32 user);
 #ifdef CONFIG_INET
-struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user);
+struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user);
 #else
-static inline struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
+static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 {
 	return skb;
 }
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 9772b789adf3..5482745d5d68 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -654,11 +654,10 @@ out_fail:
 }
 
 /* Process an incoming IP datagram fragment. */
-int ip_defrag(struct sk_buff *skb, u32 user)
+int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
 {
 	struct net_device *dev = skb->dev ? : skb_dst(skb)->dev;
 	int vif = l3mdev_master_ifindex_rcu(dev);
-	struct net *net = dev_net(dev);
 	struct ipq *qp;
 
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
@@ -683,7 +682,7 @@ int ip_defrag(struct sk_buff *skb, u32 user)
 }
 EXPORT_SYMBOL(ip_defrag);
 
-struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
+struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 {
 	struct iphdr iph;
 	int netoff;
@@ -712,7 +711,7 @@ struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
 			if (pskb_trim_rcsum(skb, netoff + len))
 				return skb;
 			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
-			if (ip_defrag(skb, user))
+			if (ip_defrag(net, skb, user))
 				return NULL;
 			skb_clear_hash(skb);
 		}
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 804b86fd615f..b1209b63381f 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -170,7 +170,7 @@ bool ip_call_ra_chain(struct sk_buff *skb)
 		     sk->sk_bound_dev_if == dev->ifindex) &&
 		    net_eq(sock_net(sk), net)) {
 			if (ip_is_fragment(ip_hdr(skb))) {
-				if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN))
+				if (ip_defrag(net, skb, IP_DEFRAG_CALL_RA_CHAIN))
 					return true;
 			}
 			if (last) {
@@ -247,14 +247,15 @@ int ip_local_deliver(struct sk_buff *skb)
 	/*
 	 *	Reassemble IP fragments.
 	 */
+	struct net *net = dev_net(skb->dev);
 
 	if (ip_is_fragment(ip_hdr(skb))) {
-		if (ip_defrag(skb, IP_DEFRAG_LOCAL_DELIVER))
+		if (ip_defrag(net, skb, IP_DEFRAG_LOCAL_DELIVER))
 			return 0;
 	}
 
 	return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN,
-		       dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+		       net, NULL, skb, skb->dev, NULL,
 		       ip_local_deliver_finish);
 }
 
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index b246346ee849..bf25f45b23d2 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -22,14 +22,15 @@
 #endif
 #include <net/netfilter/nf_conntrack_zones.h>
 
-static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
+static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb,
+				   u_int32_t user)
 {
 	int err;
 
 	skb_orphan(skb);
 
 	local_bh_disable();
-	err = ip_defrag(skb, user);
+	err = ip_defrag(net, skb, user);
 	local_bh_enable();
 
 	if (!err) {
@@ -85,7 +86,7 @@ static unsigned int ipv4_conntrack_defrag(void *priv,
 		enum ip_defrag_users user =
 			nf_ct_defrag_user(state->hook, skb);
 
-		if (nf_ct_ipv4_gather_frags(skb, user))
+		if (nf_ct_ipv4_gather_frags(state->net, skb, user))
 			return NF_STOLEN;
 	}
 	return NF_ACCEPT;
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 37dd77a3d0fb..07a791ecdfba 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -694,7 +694,7 @@ static inline int ip_vs_gather_frags(struct netns_ipvs *ipvs,
 	int err;
 
 	local_bh_disable();
-	err = ip_defrag(skb, user);
+	err = ip_defrag(ipvs->net, skb, user);
 	local_bh_enable();
 	if (!err)
 		ip_send_check(ip_hdr(skb));
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index eb759e3a88ca..cb76076a7a42 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -304,7 +304,7 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
 		int err;
 
 		memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
-		err = ip_defrag(skb, user);
+		err = ip_defrag(net, skb, user);
 		if (err)
 			return err;
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 396b3f1e7cc0..691660b9b7ef 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1439,17 +1439,17 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 {
 	struct packet_fanout *f = pt->af_packet_priv;
 	unsigned int num = READ_ONCE(f->num_members);
+	struct net *net = read_pnet(&f->net);
 	struct packet_sock *po;
 	unsigned int idx;
 
-	if (!net_eq(dev_net(dev), read_pnet(&f->net)) ||
-	    !num) {
+	if (!net_eq(dev_net(dev), net) || !num) {
 		kfree_skb(skb);
 		return 0;
 	}
 
 	if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) {
-		skb = ip_check_defrag(skb, IP_DEFRAG_AF_PACKET);
+		skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET);
 		if (!skb)
 			return 0;
 	}
-- 
cgit v1.2.3


From b72775977c39dcd380777ff5ea8041fdf67ee382 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 9 Oct 2015 13:44:55 -0500
Subject: ipv6: Pass struct net into nf_ct_frag6_gather

The function nf_ct_frag6_gather is called on both the input and the
output paths of the networking stack.  In particular ipv6_defrag which
calls nf_ct_frag6_gather is called from both the the PRE_ROUTING chain
on input and the LOCAL_OUT chain on output.

The addition of a net parameter makes it explicit which network
namespace the packets are being reassembled in, and removes the need
for nf_ct_frag6_gather to guess.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netfilter/ipv6/nf_defrag_ipv6.h | 2 +-
 net/ipv6/netfilter/nf_conntrack_reasm.c     | 4 +---
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c   | 3 ++-
 net/openvswitch/conntrack.c                 | 2 +-
 4 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'net/openvswitch')

diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
index 27666d8a0bd0..fb7da5bb76cc 100644
--- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -5,7 +5,7 @@ void nf_defrag_ipv6_enable(void);
 
 int nf_ct_frag6_init(void);
 void nf_ct_frag6_cleanup(void);
-struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user);
+struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user);
 void nf_ct_frag6_consume_orig(struct sk_buff *skb);
 
 struct inet_frags_ctl;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 701cd2bae0a9..2fb86a99bf5f 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -563,12 +563,10 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
 	return 0;
 }
 
-struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
+struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 {
 	struct sk_buff *clone;
 	struct net_device *dev = skb->dev;
-	struct net *net = skb_dst(skb) ? dev_net(skb_dst(skb)->dev)
-				       : dev_net(skb->dev);
 	struct frag_hdr *fhdr;
 	struct frag_queue *fq;
 	struct ipv6hdr *hdr;
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index a99baf63eccf..5173a89a238e 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -63,7 +63,8 @@ static unsigned int ipv6_defrag(void *priv,
 		return NF_ACCEPT;
 #endif
 
-	reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(state->hook, skb));
+	reasm = nf_ct_frag6_gather(state->net, skb,
+				   nf_ct6_defrag_user(state->hook, skb));
 	/* queued */
 	if (reasm == NULL)
 		return NF_STOLEN;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index cb76076a7a42..ad614267cc2a 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -315,7 +315,7 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
 		struct sk_buff *reasm;
 
 		memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
-		reasm = nf_ct_frag6_gather(skb, user);
+		reasm = nf_ct_frag6_gather(net, skb, user);
 		if (!reasm)
 			return -EINPROGRESS;
 
-- 
cgit v1.2.3


From 99e28f18e3f4daa2091802e07ebeb4f541631320 Mon Sep 17 00:00:00 2001
From: Pravin B Shelar <pshelar@nicira.com>
Date: Tue, 20 Oct 2015 20:47:46 -0700
Subject: openvswitch: Fix incorrect type use.

Patch fixes following sparse warning.
net/openvswitch/flow_netlink.c:583:30: warning: incorrect type in assignment (different base types)
net/openvswitch/flow_netlink.c:583:30:    expected restricted __be16 [usertype] ipv4
net/openvswitch/flow_netlink.c:583:30:    got int

Fixes: 6b26ba3a7d ("openvswitch: netlink attributes for IPv6 tunneling")
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'net/openvswitch')

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 6799c8d470c6..80e1f09397c0 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -548,11 +548,11 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			      struct sw_flow_match *match, bool is_mask,
 			      bool log)
 {
+	bool ttl = false, ipv4 = false, ipv6 = false;
+	__be16 tun_flags = 0;
+	int opts_type = 0;
 	struct nlattr *a;
 	int rem;
-	bool ttl = false;
-	__be16 tun_flags = 0, ipv4 = false, ipv6 = false;
-	int opts_type = 0;
 
 	nla_for_each_nested(a, attr, rem) {
 		int type = nla_type(a);
-- 
cgit v1.2.3


From aec15924740edc9886051593bc7769873be9498b Mon Sep 17 00:00:00 2001
From: Pravin B Shelar <pshelar@nicira.com>
Date: Tue, 20 Oct 2015 23:00:10 -0700
Subject: openvswitch: Use dev_queue_xmit for vport send.

With use of lwtunnel, we can directly call dev_queue_xmit()
rather than calling netdev vport send operation.
Following change make tunnel vport code bit cleaner.

Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/vport-geneve.c       |  2 +-
 net/openvswitch/vport-gre.c          |  2 +-
 net/openvswitch/vport-internal_dev.c |  8 ++++----
 net/openvswitch/vport-netdev.c       | 33 +--------------------------------
 net/openvswitch/vport-netdev.h       |  1 -
 net/openvswitch/vport-vxlan.c        |  2 +-
 net/openvswitch/vport.c              | 30 ++++++++++++++++++++++++++++++
 net/openvswitch/vport.h              |  7 ++-----
 8 files changed, 40 insertions(+), 45 deletions(-)

(limited to 'net/openvswitch')

diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c
index 2735e9c4a3b8..7a568ca8da54 100644
--- a/net/openvswitch/vport-geneve.c
+++ b/net/openvswitch/vport-geneve.c
@@ -128,7 +128,7 @@ static struct vport_ops ovs_geneve_vport_ops = {
 	.create		= geneve_create,
 	.destroy	= ovs_netdev_tunnel_destroy,
 	.get_options	= geneve_get_options,
-	.send		= ovs_netdev_send,
+	.send		= dev_queue_xmit,
 	.owner          = THIS_MODULE,
 	.get_egress_tun_info	= geneve_get_egress_tun_info,
 };
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index 4d24481669c9..cdb758ab01cf 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -94,7 +94,7 @@ static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
 static struct vport_ops ovs_gre_vport_ops = {
 	.type		= OVS_VPORT_TYPE_GRE,
 	.create		= gre_create,
-	.send		= ovs_netdev_send,
+	.send		= dev_queue_xmit,
 	.get_egress_tun_info	= gre_get_egress_tun_info,
 	.destroy	= ovs_netdev_tunnel_destroy,
 	.owner		= THIS_MODULE,
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 388b8a6bf112..7f0a8bd08857 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -202,22 +202,21 @@ static void internal_dev_destroy(struct vport *vport)
 	rtnl_unlock();
 }
 
-static void internal_dev_recv(struct vport *vport, struct sk_buff *skb)
+static netdev_tx_t internal_dev_recv(struct sk_buff *skb)
 {
-	struct net_device *netdev = vport->dev;
+	struct net_device *netdev = skb->dev;
 	struct pcpu_sw_netstats *stats;
 
 	if (unlikely(!(netdev->flags & IFF_UP))) {
 		kfree_skb(skb);
 		netdev->stats.rx_dropped++;
-		return;
+		return NETDEV_TX_OK;
 	}
 
 	skb_dst_drop(skb);
 	nf_reset(skb);
 	secpath_reset(skb);
 
-	skb->dev = netdev;
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = eth_type_trans(skb, netdev);
 	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
@@ -229,6 +228,7 @@ static void internal_dev_recv(struct vport *vport, struct sk_buff *skb)
 	u64_stats_update_end(&stats->syncp);
 
 	netif_rx(skb);
+	return NETDEV_TX_OK;
 }
 
 static struct vport_ops ovs_internal_vport_ops = {
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index f7e8dcce7ada..b327368a3848 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -190,37 +190,6 @@ void ovs_netdev_tunnel_destroy(struct vport *vport)
 }
 EXPORT_SYMBOL_GPL(ovs_netdev_tunnel_destroy);
 
-static unsigned int packet_length(const struct sk_buff *skb)
-{
-	unsigned int length = skb->len - ETH_HLEN;
-
-	if (skb->protocol == htons(ETH_P_8021Q))
-		length -= VLAN_HLEN;
-
-	return length;
-}
-
-void ovs_netdev_send(struct vport *vport, struct sk_buff *skb)
-{
-	int mtu = vport->dev->mtu;
-
-	if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) {
-		net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n",
-				     vport->dev->name,
-				     packet_length(skb), mtu);
-		vport->dev->stats.tx_errors++;
-		goto drop;
-	}
-
-	skb->dev = vport->dev;
-	dev_queue_xmit(skb);
-	return;
-
-drop:
-	kfree_skb(skb);
-}
-EXPORT_SYMBOL_GPL(ovs_netdev_send);
-
 /* Returns null if this device is not attached to a datapath. */
 struct vport *ovs_netdev_get_vport(struct net_device *dev)
 {
@@ -235,7 +204,7 @@ static struct vport_ops ovs_netdev_vport_ops = {
 	.type		= OVS_VPORT_TYPE_NETDEV,
 	.create		= netdev_create,
 	.destroy	= netdev_destroy,
-	.send		= ovs_netdev_send,
+	.send		= dev_queue_xmit,
 };
 
 int __init ovs_netdev_init(void)
diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h
index bf22fcedbc69..19e29c12adcc 100644
--- a/net/openvswitch/vport-netdev.h
+++ b/net/openvswitch/vport-netdev.h
@@ -27,7 +27,6 @@
 struct vport *ovs_netdev_get_vport(struct net_device *dev);
 
 struct vport *ovs_netdev_link(struct vport *vport, const char *name);
-void ovs_netdev_send(struct vport *vport, struct sk_buff *skb);
 void ovs_netdev_detach_dev(struct vport *);
 
 int __init ovs_netdev_init(void);
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index fb3cdb85905d..6f700710d413 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -170,7 +170,7 @@ static struct vport_ops ovs_vxlan_netdev_vport_ops = {
 	.create			= vxlan_create,
 	.destroy		= ovs_netdev_tunnel_destroy,
 	.get_options		= vxlan_get_options,
-	.send			= ovs_netdev_send,
+	.send			= dev_queue_xmit,
 	.get_egress_tun_info	= vxlan_get_egress_tun_info,
 };
 
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 12a36ac21eda..ef19d0b77d13 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -537,3 +537,33 @@ int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
 
 	return vport->ops->get_egress_tun_info(vport, skb, upcall);
 }
+
+static unsigned int packet_length(const struct sk_buff *skb)
+{
+	unsigned int length = skb->len - ETH_HLEN;
+
+	if (skb->protocol == htons(ETH_P_8021Q))
+		length -= VLAN_HLEN;
+
+	return length;
+}
+
+void ovs_vport_send(struct vport *vport, struct sk_buff *skb)
+{
+	int mtu = vport->dev->mtu;
+
+	if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) {
+		net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n",
+				     vport->dev->name,
+				     packet_length(skb), mtu);
+		vport->dev->stats.tx_errors++;
+		goto drop;
+	}
+
+	skb->dev = vport->dev;
+	vport->ops->send(skb);
+	return;
+
+drop:
+	kfree_skb(skb);
+}
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index a413f3ae6a7b..885607f28d56 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -153,7 +153,7 @@ struct vport_ops {
 	int (*set_options)(struct vport *, struct nlattr *);
 	int (*get_options)(const struct vport *, struct sk_buff *);
 
-	void (*send)(struct vport *, struct sk_buff *);
+	netdev_tx_t (*send) (struct sk_buff *skb);
 	int (*get_egress_tun_info)(struct vport *, struct sk_buff *,
 				   struct dp_upcall_info *upcall);
 
@@ -234,9 +234,6 @@ static inline struct rtable *ovs_tunnel_route_lookup(struct net *net,
 	return rt;
 }
 
-static inline void ovs_vport_send(struct vport *vport, struct sk_buff *skb)
-{
-	vport->ops->send(vport, skb);
-}
+void ovs_vport_send(struct vport *vport, struct sk_buff *skb);
 
 #endif /* vport.h */
-- 
cgit v1.2.3