From 090096bf3db1c281ddd034573260045888a68fea Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevic@redhat.com>
Date: Wed, 6 Mar 2013 15:39:42 +0000
Subject: net: generic fdb support for drivers without ndo_fdb_<op>

If the driver does not support the ndo_op use the generic
handler for it. This should work in the majority of cases.
Eventually the fdb_dflt_add call gets translated into a
__dev_set_rx_mode() call which should handle hardware
support for filtering via the IFF_UNICAST_FLT flag.

Namely IFF_UNICAST_FLT indicates if the hardware can do
unicast address filtering. If no support is available
the device is put into promisc mode.

Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 81 ++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 75 insertions(+), 6 deletions(-)

(limited to 'net/core/rtnetlink.c')

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index b376410ff25..f95b6fbc29e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2048,6 +2048,38 @@ errout:
 	rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
 }
 
+/**
+ * ndo_dflt_fdb_add - default netdevice operation to add an FDB entry
+ */
+int ndo_dflt_fdb_add(struct ndmsg *ndm,
+		     struct nlattr *tb[],
+		     struct net_device *dev,
+		     const unsigned char *addr,
+		     u16 flags)
+{
+	int err = -EINVAL;
+
+	/* If aging addresses are supported device will need to
+	 * implement its own handler for this.
+	 */
+	if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) {
+		pr_info("%s: FDB only supports static addresses\n", dev->name);
+		return err;
+	}
+
+	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
+		err = dev_uc_add_excl(dev, addr);
+	else if (is_multicast_ether_addr(addr))
+		err = dev_mc_add_excl(dev, addr);
+
+	/* Only return duplicate errors if NLM_F_EXCL is set */
+	if (err == -EEXIST && !(flags & NLM_F_EXCL))
+		err = 0;
+
+	return err;
+}
+EXPORT_SYMBOL(ndo_dflt_fdb_add);
+
 static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 {
 	struct net *net = sock_net(skb->sk);
@@ -2100,10 +2132,13 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 	}
 
 	/* Embedded bridge, macvlan, and any other device support */
-	if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_add) {
-		err = dev->netdev_ops->ndo_fdb_add(ndm, tb,
-						   dev, addr,
-						   nlh->nlmsg_flags);
+	if ((ndm->ndm_flags & NTF_SELF)) {
+		if (dev->netdev_ops->ndo_fdb_add)
+			err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr,
+							   nlh->nlmsg_flags);
+		else
+			err = ndo_dflt_fdb_add(ndm, tb, dev, addr,
+					       nlh->nlmsg_flags);
 
 		if (!err) {
 			rtnl_fdb_notify(dev, addr, RTM_NEWNEIGH);
@@ -2114,6 +2149,35 @@ out:
 	return err;
 }
 
+/**
+ * ndo_dflt_fdb_del - default netdevice operation to delete an FDB entry
+ */
+int ndo_dflt_fdb_del(struct ndmsg *ndm,
+		     struct nlattr *tb[],
+		     struct net_device *dev,
+		     const unsigned char *addr)
+{
+	int err = -EOPNOTSUPP;
+
+	/* If aging addresses are supported device will need to
+	 * implement its own handler for this.
+	 */
+	if (ndm->ndm_state & NUD_PERMANENT) {
+		pr_info("%s: FDB only supports static addresses\n", dev->name);
+		return -EINVAL;
+	}
+
+	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
+		err = dev_uc_del(dev, addr);
+	else if (is_multicast_ether_addr(addr))
+		err = dev_mc_del(dev, addr);
+	else
+		err = -EINVAL;
+
+	return err;
+}
+EXPORT_SYMBOL(ndo_dflt_fdb_del);
+
 static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 {
 	struct net *net = sock_net(skb->sk);
@@ -2171,8 +2235,11 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 	}
 
 	/* Embedded bridge, macvlan, and any other device support */
-	if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_del) {
-		err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr);
+	if (ndm->ndm_flags & NTF_SELF) {
+		if (dev->netdev_ops->ndo_fdb_del)
+			err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr);
+		else
+			err = ndo_dflt_fdb_del(ndm, tb, dev, addr);
 
 		if (!err) {
 			rtnl_fdb_notify(dev, addr, RTM_DELNEIGH);
@@ -2257,6 +2324,8 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 		if (dev->netdev_ops->ndo_fdb_dump)
 			idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, idx);
+		else
+			ndo_dflt_fdb_dump(skb, cb, dev, idx);
 	}
 	rcu_read_unlock();
 
-- 
cgit v1.2.3-70-g09d2


From 6681712d67eef14c4ce793561c3231659153a320 Mon Sep 17 00:00:00 2001
From: David Stevens <dlstevens@us.ibm.com>
Date: Fri, 15 Mar 2013 04:35:51 +0000
Subject: vxlan: generalize forwarding tables

This patch generalizes VXLAN forwarding table entries allowing an administrator
to:
	1) specify multiple destinations for a given MAC
	2) specify alternate vni's in the VXLAN header
	3) specify alternate destination UDP ports
	4) use multicast MAC addresses as fdb lookup keys
	5) specify multicast destinations
	6) specify the outgoing interface for forwarded packets

The combination allows configuration of more complex topologies using VXLAN
encapsulation.

Changes since v1: rebase to 3.9.0-rc2

Signed-Off-By: David L Stevens <dlstevens@us.ibm.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c            | 263 ++++++++++++++++++++++++++++++++---------
 include/uapi/linux/neighbour.h |   3 +
 net/core/rtnetlink.c           |   2 +-
 3 files changed, 210 insertions(+), 58 deletions(-)

(limited to 'net/core/rtnetlink.c')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index db0df07c18d..33427fd6251 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -81,13 +81,22 @@ struct vxlan_net {
 	struct hlist_head vni_list[VNI_HASH_SIZE];
 };
 
+struct vxlan_rdst {
+	struct rcu_head		 rcu;
+	__be32			 remote_ip;
+	__be16			 remote_port;
+	u32			 remote_vni;
+	u32			 remote_ifindex;
+	struct vxlan_rdst	*remote_next;
+};
+
 /* Forwarding table entry */
 struct vxlan_fdb {
 	struct hlist_node hlist;	/* linked list of entries */
 	struct rcu_head	  rcu;
 	unsigned long	  updated;	/* jiffies */
 	unsigned long	  used;
-	__be32		  remote_ip;
+	struct vxlan_rdst remote;
 	u16		  state;	/* see ndm_state */
 	u8		  eth_addr[ETH_ALEN];
 };
@@ -157,7 +166,8 @@ static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id)
 /* Fill in neighbour message in skbuff. */
 static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 			   const struct vxlan_fdb *fdb,
-			   u32 portid, u32 seq, int type, unsigned int flags)
+			   u32 portid, u32 seq, int type, unsigned int flags,
+			   const struct vxlan_rdst *rdst)
 {
 	unsigned long now = jiffies;
 	struct nda_cacheinfo ci;
@@ -176,7 +186,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 
 	if (type == RTM_GETNEIGH) {
 		ndm->ndm_family	= AF_INET;
-		send_ip = fdb->remote_ip != 0;
+		send_ip = rdst->remote_ip != htonl(INADDR_ANY);
 		send_eth = !is_zero_ether_addr(fdb->eth_addr);
 	} else
 		ndm->ndm_family	= AF_BRIDGE;
@@ -188,7 +198,17 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 	if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
 		goto nla_put_failure;
 
-	if (send_ip && nla_put_be32(skb, NDA_DST, fdb->remote_ip))
+	if (send_ip && nla_put_be32(skb, NDA_DST, rdst->remote_ip))
+		goto nla_put_failure;
+
+	if (rdst->remote_port && rdst->remote_port != vxlan_port &&
+	    nla_put_be16(skb, NDA_PORT, rdst->remote_port))
+		goto nla_put_failure;
+	if (rdst->remote_vni != vxlan->vni &&
+	    nla_put_be32(skb, NDA_VNI, rdst->remote_vni))
+		goto nla_put_failure;
+	if (rdst->remote_ifindex &&
+	    nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex))
 		goto nla_put_failure;
 
 	ci.ndm_used	 = jiffies_to_clock_t(now - fdb->used);
@@ -211,6 +231,9 @@ static inline size_t vxlan_nlmsg_size(void)
 	return NLMSG_ALIGN(sizeof(struct ndmsg))
 		+ nla_total_size(ETH_ALEN) /* NDA_LLADDR */
 		+ nla_total_size(sizeof(__be32)) /* NDA_DST */
+		+ nla_total_size(sizeof(__be32)) /* NDA_PORT */
+		+ nla_total_size(sizeof(__be32)) /* NDA_VNI */
+		+ nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */
 		+ nla_total_size(sizeof(struct nda_cacheinfo));
 }
 
@@ -225,7 +248,7 @@ static void vxlan_fdb_notify(struct vxlan_dev *vxlan,
 	if (skb == NULL)
 		goto errout;
 
-	err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0);
+	err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, &fdb->remote);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -247,7 +270,8 @@ static void vxlan_ip_miss(struct net_device *dev, __be32 ipa)
 
 	memset(&f, 0, sizeof f);
 	f.state = NUD_STALE;
-	f.remote_ip = ipa; /* goes to NDA_DST */
+	f.remote.remote_ip = ipa; /* goes to NDA_DST */
+	f.remote.remote_vni = VXLAN_N_VID;
 
 	vxlan_fdb_notify(vxlan, &f, RTM_GETNEIGH);
 }
@@ -300,10 +324,38 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
 	return NULL;
 }
 
+/* Add/update destinations for multicast */
+static int vxlan_fdb_append(struct vxlan_fdb *f,
+			    __be32 ip, __u32 port, __u32 vni, __u32 ifindex)
+{
+	struct vxlan_rdst *rd_prev, *rd;
+
+	rd_prev = NULL;
+	for (rd = &f->remote; rd; rd = rd->remote_next) {
+		if (rd->remote_ip == ip &&
+		    rd->remote_port == port &&
+		    rd->remote_vni == vni &&
+		    rd->remote_ifindex == ifindex)
+			return 0;
+		rd_prev = rd;
+	}
+	rd = kmalloc(sizeof(*rd), GFP_ATOMIC);
+	if (rd == NULL)
+		return -ENOBUFS;
+	rd->remote_ip = ip;
+	rd->remote_port = port;
+	rd->remote_vni = vni;
+	rd->remote_ifindex = ifindex;
+	rd->remote_next = NULL;
+	rd_prev->remote_next = rd;
+	return 1;
+}
+
 /* Add new entry to forwarding table -- assumes lock held */
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 			    const u8 *mac, __be32 ip,
-			    __u16 state, __u16 flags)
+			    __u16 state, __u16 flags,
+			    __u32 port, __u32 vni, __u32 ifindex)
 {
 	struct vxlan_fdb *f;
 	int notify = 0;
@@ -320,6 +372,14 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 			f->updated = jiffies;
 			notify = 1;
 		}
+		if ((flags & NLM_F_APPEND) &&
+		    is_multicast_ether_addr(f->eth_addr)) {
+			int rc = vxlan_fdb_append(f, ip, port, vni, ifindex);
+
+			if (rc < 0)
+				return rc;
+			notify |= rc;
+		}
 	} else {
 		if (!(flags & NLM_F_CREATE))
 			return -ENOENT;
@@ -333,7 +393,11 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 			return -ENOMEM;
 
 		notify = 1;
-		f->remote_ip = ip;
+		f->remote.remote_ip = ip;
+		f->remote.remote_port = port;
+		f->remote.remote_vni = vni;
+		f->remote.remote_ifindex = ifindex;
+		f->remote.remote_next = NULL;
 		f->state = state;
 		f->updated = f->used = jiffies;
 		memcpy(f->eth_addr, mac, ETH_ALEN);
@@ -349,6 +413,19 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 	return 0;
 }
 
+void vxlan_fdb_free(struct rcu_head *head)
+{
+	struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu);
+
+	while (f->remote.remote_next) {
+		struct vxlan_rdst *rd = f->remote.remote_next;
+
+		f->remote.remote_next = rd->remote_next;
+		kfree(rd);
+	}
+	kfree(f);
+}
+
 static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
 {
 	netdev_dbg(vxlan->dev,
@@ -358,7 +435,7 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
 	vxlan_fdb_notify(vxlan, f, RTM_DELNEIGH);
 
 	hlist_del_rcu(&f->hlist);
-	kfree_rcu(f, rcu);
+	call_rcu(&f->rcu, vxlan_fdb_free);
 }
 
 /* Add static entry (via netlink) */
@@ -367,7 +444,9 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			 const unsigned char *addr, u16 flags)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct net *net = dev_net(vxlan->dev);
 	__be32 ip;
+	u32 port, vni, ifindex;
 	int err;
 
 	if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) {
@@ -384,8 +463,36 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 
 	ip = nla_get_be32(tb[NDA_DST]);
 
+	if (tb[NDA_PORT]) {
+		if (nla_len(tb[NDA_PORT]) != sizeof(u32))
+			return -EINVAL;
+		port = nla_get_u32(tb[NDA_PORT]);
+	} else
+		port = vxlan_port;
+
+	if (tb[NDA_VNI]) {
+		if (nla_len(tb[NDA_VNI]) != sizeof(u32))
+			return -EINVAL;
+		vni = nla_get_u32(tb[NDA_VNI]);
+	} else
+		vni = vxlan->vni;
+
+	if (tb[NDA_IFINDEX]) {
+		struct net_device *dev;
+
+		if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
+			return -EINVAL;
+		ifindex = nla_get_u32(tb[NDA_IFINDEX]);
+		dev = dev_get_by_index(net, ifindex);
+		if (!dev)
+			return -EADDRNOTAVAIL;
+		dev_put(dev);
+	} else
+		ifindex = 0;
+
 	spin_lock_bh(&vxlan->hash_lock);
-	err = vxlan_fdb_create(vxlan, addr, ip, ndm->ndm_state, flags);
+	err = vxlan_fdb_create(vxlan, addr, ip, ndm->ndm_state, flags, port,
+		vni, ifindex);
 	spin_unlock_bh(&vxlan->hash_lock);
 
 	return err;
@@ -423,18 +530,21 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		int err;
 
 		hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) {
-			if (idx < cb->args[0])
-				goto skip;
-
-			err = vxlan_fdb_info(skb, vxlan, f,
-					     NETLINK_CB(cb->skb).portid,
-					     cb->nlh->nlmsg_seq,
-					     RTM_NEWNEIGH,
-					     NLM_F_MULTI);
-			if (err < 0)
-				break;
+			struct vxlan_rdst *rd;
+			for (rd = &f->remote; rd; rd = rd->remote_next) {
+				if (idx < cb->args[0])
+					goto skip;
+
+				err = vxlan_fdb_info(skb, vxlan, f,
+						     NETLINK_CB(cb->skb).portid,
+						     cb->nlh->nlmsg_seq,
+						     RTM_NEWNEIGH,
+						     NLM_F_MULTI, rd);
+				if (err < 0)
+					break;
 skip:
-			++idx;
+				++idx;
+			}
 		}
 	}
 
@@ -454,22 +564,23 @@ static void vxlan_snoop(struct net_device *dev,
 	f = vxlan_find_mac(vxlan, src_mac);
 	if (likely(f)) {
 		f->used = jiffies;
-		if (likely(f->remote_ip == src_ip))
+		if (likely(f->remote.remote_ip == src_ip))
 			return;
 
 		if (net_ratelimit())
 			netdev_info(dev,
 				    "%pM migrated from %pI4 to %pI4\n",
-				    src_mac, &f->remote_ip, &src_ip);
+				    src_mac, &f->remote.remote_ip, &src_ip);
 
-		f->remote_ip = src_ip;
+		f->remote.remote_ip = src_ip;
 		f->updated = jiffies;
 	} else {
 		/* learned new entry */
 		spin_lock(&vxlan->hash_lock);
 		err = vxlan_fdb_create(vxlan, src_mac, src_ip,
 				       NUD_REACHABLE,
-				       NLM_F_EXCL|NLM_F_CREATE);
+				       NLM_F_EXCL|NLM_F_CREATE,
+				       vxlan_port, vxlan->vni, 0);
 		spin_unlock(&vxlan->hash_lock);
 	}
 }
@@ -701,7 +812,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
 		}
 
 		f = vxlan_find_mac(vxlan, n->ha);
-		if (f && f->remote_ip == 0) {
+		if (f && f->remote.remote_ip == htonl(INADDR_ANY)) {
 			/* bridge-local neighbor */
 			neigh_release(n);
 			goto out;
@@ -834,47 +945,26 @@ static int handle_offloads(struct sk_buff *skb)
 	return 0;
 }
 
-/* Transmit local packets over Vxlan
- *
- * Outer IP header inherits ECN and DF from inner header.
- * Outer UDP destination is the VXLAN assigned port.
- *           source port is based on hash of flow
- */
-static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
+				  struct vxlan_rdst *rdst, bool did_rsc)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct rtable *rt;
 	const struct iphdr *old_iph;
-	struct ethhdr *eth;
 	struct iphdr *iph;
 	struct vxlanhdr *vxh;
 	struct udphdr *uh;
 	struct flowi4 fl4;
 	unsigned int pkt_len = skb->len;
 	__be32 dst;
-	__u16 src_port;
+	__u16 src_port, dst_port;
+        u32 vni;
 	__be16 df = 0;
 	__u8 tos, ttl;
-	bool did_rsc = false;
-	const struct vxlan_fdb *f;
-
-	skb_reset_mac_header(skb);
-	eth = eth_hdr(skb);
-
-	if ((vxlan->flags & VXLAN_F_PROXY) && ntohs(eth->h_proto) == ETH_P_ARP)
-		return arp_reduce(dev, skb);
-	else if ((vxlan->flags&VXLAN_F_RSC) && ntohs(eth->h_proto) == ETH_P_IP)
-		did_rsc = route_shortcircuit(dev, skb);
 
-	f = vxlan_find_mac(vxlan, eth->h_dest);
-	if (f == NULL) {
-		did_rsc = false;
-		dst = vxlan->gaddr;
-		if (!dst && (vxlan->flags & VXLAN_F_L2MISS) &&
-		    !is_multicast_ether_addr(eth->h_dest))
-			vxlan_fdb_miss(vxlan, eth->h_dest);
-	} else
-		dst = f->remote_ip;
+	dst_port = rdst->remote_port ? rdst->remote_port : vxlan_port;
+	vni = rdst->remote_vni;
+	dst = rdst->remote_ip;
 
 	if (!dst) {
 		if (did_rsc) {
@@ -922,7 +1012,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	src_port = vxlan_src_port(vxlan, skb);
 
 	memset(&fl4, 0, sizeof(fl4));
-	fl4.flowi4_oif = vxlan->link;
+	fl4.flowi4_oif = rdst->remote_ifindex;
 	fl4.flowi4_tos = RT_TOS(tos);
 	fl4.daddr = dst;
 	fl4.saddr = vxlan->saddr;
@@ -949,13 +1039,13 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
 	vxh->vx_flags = htonl(VXLAN_FLAGS);
-	vxh->vx_vni = htonl(vxlan->vni << 8);
+	vxh->vx_vni = htonl(vni << 8);
 
 	__skb_push(skb, sizeof(*uh));
 	skb_reset_transport_header(skb);
 	uh = udp_hdr(skb);
 
-	uh->dest = htons(vxlan_port);
+	uh->dest = htons(dst_port);
 	uh->source = htons(src_port);
 
 	uh->len = htons(skb->len);
@@ -995,6 +1085,64 @@ tx_free:
 	return NETDEV_TX_OK;
 }
 
+/* Transmit local packets over Vxlan
+ *
+ * Outer IP header inherits ECN and DF from inner header.
+ * Outer UDP destination is the VXLAN assigned port.
+ *           source port is based on hash of flow
+ */
+static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct ethhdr *eth;
+	bool did_rsc = false;
+	struct vxlan_rdst group, *rdst0, *rdst;
+	struct vxlan_fdb *f;
+	int rc1, rc;
+
+	skb_reset_mac_header(skb);
+	eth = eth_hdr(skb);
+
+	if ((vxlan->flags & VXLAN_F_PROXY) && ntohs(eth->h_proto) == ETH_P_ARP)
+		return arp_reduce(dev, skb);
+	else if ((vxlan->flags&VXLAN_F_RSC) && ntohs(eth->h_proto) == ETH_P_IP)
+		did_rsc = route_shortcircuit(dev, skb);
+
+	f = vxlan_find_mac(vxlan, eth->h_dest);
+	if (f == NULL) {
+		did_rsc = false;
+		group.remote_port = vxlan_port;
+		group.remote_vni = vxlan->vni;
+		group.remote_ip = vxlan->gaddr;
+		group.remote_ifindex = vxlan->link;
+		group.remote_next = 0;
+		rdst0 = &group;
+
+		if (group.remote_ip == htonl(INADDR_ANY) &&
+		    (vxlan->flags & VXLAN_F_L2MISS) &&
+		    !is_multicast_ether_addr(eth->h_dest))
+			vxlan_fdb_miss(vxlan, eth->h_dest);
+	} else
+		rdst0 = &f->remote;
+
+	rc = NETDEV_TX_OK;
+
+	/* if there are multiple destinations, send copies */
+	for (rdst = rdst0->remote_next; rdst; rdst = rdst->remote_next) {
+		struct sk_buff *skb1;
+
+		skb1 = skb_clone(skb, GFP_ATOMIC);
+		rc1 = vxlan_xmit_one(skb1, dev, rdst, did_rsc);
+		if (rc == NETDEV_TX_OK)
+			rc = rc1;
+	}
+
+	rc1 = vxlan_xmit_one(skb, dev, rdst0, did_rsc);
+	if (rc == NETDEV_TX_OK)
+		rc = rc1;
+	return rc;
+}
+
 /* Walk the forwarding table and purge stale entries */
 static void vxlan_cleanup(unsigned long arg)
 {
@@ -1558,6 +1706,7 @@ static void __exit vxlan_cleanup_module(void)
 {
 	rtnl_link_unregister(&vxlan_link_ops);
 	unregister_pernet_device(&vxlan_net_ops);
+	rcu_barrier();
 }
 module_exit(vxlan_cleanup_module);
 
diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
index adb068c53c4..f175212420a 100644
--- a/include/uapi/linux/neighbour.h
+++ b/include/uapi/linux/neighbour.h
@@ -21,6 +21,9 @@ enum {
 	NDA_CACHEINFO,
 	NDA_PROBES,
 	NDA_VLAN,
+	NDA_PORT,
+	NDA_VNI,
+	NDA_IFINDEX,
 	__NDA_MAX
 };
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 55b5624a4b0..0e86baf8f80 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2112,7 +2112,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 	}
 
 	addr = nla_data(tb[NDA_LLADDR]);
-	if (!is_valid_ether_addr(addr)) {
+	if (is_zero_ether_addr(addr)) {
 		pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ether address\n");
 		return -EINVAL;
 	}
-- 
cgit v1.2.3-70-g09d2


From 661d2967b3f1b34eeaa7e212e7b9bbe8ee072b59 Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Thu, 21 Mar 2013 07:45:29 +0000
Subject: rtnetlink: Remove passing of attributes into rtnl_doit functions

With decnet converted, we can finally get rid of rta_buf and its
computations around it. It also gets rid of the minimal header
length verification since all message handlers do that explicitly
anyway.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/rtnetlink.h |  2 +-
 net/bridge/br_mdb.c     |  4 +--
 net/can/gw.c            |  5 ++-
 net/core/fib_rules.c    |  4 +--
 net/core/neighbour.c    |  6 ++--
 net/core/rtnetlink.c    | 82 ++++++-------------------------------------------
 net/dcb/dcbnl.c         |  2 +-
 net/decnet/dn_dev.c     |  4 +--
 net/decnet/dn_fib.c     |  4 +--
 net/decnet/dn_route.c   |  2 +-
 net/ipv4/devinet.c      |  7 ++---
 net/ipv4/fib_frontend.c |  4 +--
 net/ipv4/route.c        |  2 +-
 net/ipv6/addrconf.c     | 10 +++---
 net/ipv6/addrlabel.c    |  6 ++--
 net/ipv6/route.c        |  6 ++--
 net/phonet/pn_netlink.c |  4 +--
 net/sched/act_api.c     |  2 +-
 net/sched/cls_api.c     |  2 +-
 net/sched/sch_api.c     |  6 ++--
 20 files changed, 47 insertions(+), 117 deletions(-)

(limited to 'net/core/rtnetlink.c')

diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 5a15fabd6a7..702664833a5 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -4,7 +4,7 @@
 #include <linux/rtnetlink.h>
 #include <net/netlink.h>
 
-typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, void *);
+typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *);
 typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *);
 typedef u16 (*rtnl_calcit_func)(struct sk_buff *, struct nlmsghdr *);
 
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index ee79f3f2038..19942e38fd2 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -382,7 +382,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
 	return ret;
 }
 
-static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct br_mdb_entry *entry;
@@ -458,7 +458,7 @@ unlock:
 	return err;
 }
 
-static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net_device *dev;
 	struct br_mdb_entry *entry;
diff --git a/net/can/gw.c b/net/can/gw.c
index 2d117dc5ebe..2dc619db805 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -778,8 +778,7 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod,
 	return 0;
 }
 
-static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh,
-			  void *arg)
+static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh)
 {
 	struct rtcanmsg *r;
 	struct cgw_job *gwj;
@@ -868,7 +867,7 @@ static void cgw_remove_all_jobs(void)
 	}
 }
 
-static int cgw_remove_job(struct sk_buff *skb,  struct nlmsghdr *nlh, void *arg)
+static int cgw_remove_job(struct sk_buff *skb,  struct nlmsghdr *nlh)
 {
 	struct cgw_job *gwj = NULL;
 	struct hlist_node *nx;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 58a4ba27dfe..d5a9f8ead0d 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -266,7 +266,7 @@ errout:
 	return err;
 }
 
-static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
@@ -415,7 +415,7 @@ errout:
 	return err;
 }
 
-static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 3863b8f639c..c72a646d9f4 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1613,7 +1613,7 @@ int neigh_table_clear(struct neigh_table *tbl)
 }
 EXPORT_SYMBOL(neigh_table_clear);
 
-static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
@@ -1677,7 +1677,7 @@ out:
 	return err;
 }
 
-static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
@@ -1955,7 +1955,7 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = {
 	[NDTPA_LOCKTIME]		= { .type = NLA_U64 },
 };
 
-static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct neigh_table *tbl;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9a9b99e1fb7..751f1244b64 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -515,32 +515,6 @@ out:
 	return err;
 }
 
-static const int rtm_min[RTM_NR_FAMILIES] =
-{
-	[RTM_FAM(RTM_NEWLINK)]      = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
-	[RTM_FAM(RTM_NEWADDR)]      = NLMSG_LENGTH(sizeof(struct ifaddrmsg)),
-	[RTM_FAM(RTM_NEWROUTE)]     = NLMSG_LENGTH(sizeof(struct rtmsg)),
-	[RTM_FAM(RTM_NEWRULE)]      = NLMSG_LENGTH(sizeof(struct fib_rule_hdr)),
-	[RTM_FAM(RTM_NEWQDISC)]     = NLMSG_LENGTH(sizeof(struct tcmsg)),
-	[RTM_FAM(RTM_NEWTCLASS)]    = NLMSG_LENGTH(sizeof(struct tcmsg)),
-	[RTM_FAM(RTM_NEWTFILTER)]   = NLMSG_LENGTH(sizeof(struct tcmsg)),
-	[RTM_FAM(RTM_NEWACTION)]    = NLMSG_LENGTH(sizeof(struct tcamsg)),
-	[RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)),
-	[RTM_FAM(RTM_GETANYCAST)]   = NLMSG_LENGTH(sizeof(struct rtgenmsg)),
-};
-
-static const int rta_max[RTM_NR_FAMILIES] =
-{
-	[RTM_FAM(RTM_NEWLINK)]      = IFLA_MAX,
-	[RTM_FAM(RTM_NEWADDR)]      = IFA_MAX,
-	[RTM_FAM(RTM_NEWROUTE)]     = RTA_MAX,
-	[RTM_FAM(RTM_NEWRULE)]      = FRA_MAX,
-	[RTM_FAM(RTM_NEWQDISC)]     = TCA_MAX,
-	[RTM_FAM(RTM_NEWTCLASS)]    = TCA_MAX,
-	[RTM_FAM(RTM_NEWTFILTER)]   = TCA_MAX,
-	[RTM_FAM(RTM_NEWACTION)]    = TCAA_MAX,
-};
-
 int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo)
 {
 	struct sock *rtnl = net->rtnl;
@@ -1537,7 +1511,7 @@ errout:
 	return err;
 }
 
-static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
@@ -1578,7 +1552,7 @@ errout:
 	return err;
 }
 
-static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	const struct rtnl_link_ops *ops;
@@ -1709,7 +1683,7 @@ static int rtnl_group_changelink(struct net *net, int group,
 	return 0;
 }
 
-static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	const struct rtnl_link_ops *ops;
@@ -1864,7 +1838,7 @@ out:
 	}
 }
 
-static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
@@ -2081,7 +2055,7 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm,
 }
 EXPORT_SYMBOL(ndo_dflt_fdb_add);
 
-static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
@@ -2179,7 +2153,7 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm,
 }
 EXPORT_SYMBOL(ndo_dflt_fdb_del);
 
-static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
@@ -2478,8 +2452,7 @@ errout:
 	return err;
 }
 
-static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
-			       void *arg)
+static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
@@ -2549,8 +2522,7 @@ out:
 	return err;
 }
 
-static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
-			       void *arg)
+static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
@@ -2620,10 +2592,6 @@ out:
 	return err;
 }
 
-/* Protected by RTNL sempahore.  */
-static struct rtattr **rta_buf;
-static int rtattr_max;
-
 /* Process one rtnetlink message. */
 
 static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
@@ -2631,7 +2599,6 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct net *net = sock_net(skb->sk);
 	rtnl_doit_func doit;
 	int sz_idx, kind;
-	int min_len;
 	int family;
 	int type;
 	int err;
@@ -2679,32 +2646,11 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return err;
 	}
 
-	memset(rta_buf, 0, (rtattr_max * sizeof(struct rtattr *)));
-
-	min_len = rtm_min[sz_idx];
-	if (nlh->nlmsg_len < min_len)
-		return -EINVAL;
-
-	if (nlh->nlmsg_len > min_len) {
-		int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len);
-		struct rtattr *attr = (void *)nlh + NLMSG_ALIGN(min_len);
-
-		while (RTA_OK(attr, attrlen)) {
-			unsigned int flavor = attr->rta_type & NLA_TYPE_MASK;
-			if (flavor) {
-				if (flavor > rta_max[sz_idx])
-					return -EINVAL;
-				rta_buf[flavor-1] = attr;
-			}
-			attr = RTA_NEXT(attr, attrlen);
-		}
-	}
-
 	doit = rtnl_get_doit(family, type);
 	if (doit == NULL)
 		return -EOPNOTSUPP;
 
-	return doit(skb, nlh, (void *)&rta_buf[0]);
+	return doit(skb, nlh);
 }
 
 static void rtnetlink_rcv(struct sk_buff *skb)
@@ -2774,16 +2720,6 @@ static struct pernet_operations rtnetlink_net_ops = {
 
 void __init rtnetlink_init(void)
 {
-	int i;
-
-	rtattr_max = 0;
-	for (i = 0; i < ARRAY_SIZE(rta_max); i++)
-		if (rta_max[i] > rtattr_max)
-			rtattr_max = rta_max[i];
-	rta_buf = kmalloc(rtattr_max * sizeof(struct rtattr *), GFP_KERNEL);
-	if (!rta_buf)
-		panic("rtnetlink_init: cannot allocate rta_buf\n");
-
 	if (register_pernet_subsys(&rtnetlink_net_ops))
 		panic("rtnetlink_init: cannot initialize rtnetlink\n");
 
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 21291f1abcd..40d5829ed36 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1658,7 +1658,7 @@ static const struct reply_func reply_funcs[DCB_CMD_MAX+1] = {
 	[DCB_CMD_CEE_GET]	= { RTM_GETDCB, dcbnl_cee_get },
 };
 
-static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct net_device *netdev;
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index c8da116d84a..7d9197063eb 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -563,7 +563,7 @@ static const struct nla_policy dn_ifa_policy[IFA_MAX+1] = {
 				    .len = IFNAMSIZ - 1 },
 };
 
-static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[IFA_MAX+1];
@@ -607,7 +607,7 @@ errout:
 	return err;
 }
 
-static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[IFA_MAX+1];
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index 42a8048fe72..f0930594993 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -511,7 +511,7 @@ static inline u32 rtm_get_table(struct nlattr *attrs[], u8 table)
 	return table;
 }
 
-static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct dn_fib_table *tb;
@@ -536,7 +536,7 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *
 	return tb->delete(tb, r, attrs, nlh, &NETLINK_CB(skb));
 }
 
-static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct dn_fib_table *tb;
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index b4b3508e77f..5904429e8d6 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1616,7 +1616,7 @@ errout:
 /*
  * This is called by both endnodes and routers now.
  */
-static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void *arg)
+static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct rtmsg *rtm = nlmsg_data(nlh);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index af57bbae05b..20a9f9274f3 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -536,7 +536,7 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
 	return NULL;
 }
 
-static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[IFA_MAX+1];
@@ -775,7 +775,7 @@ static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa)
 	return NULL;
 }
 
-static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct in_ifaddr *ifa;
@@ -1730,8 +1730,7 @@ static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = {
 };
 
 static int inet_netconf_get_devconf(struct sk_buff *in_skb,
-				    struct nlmsghdr *nlh,
-				    void *arg)
+				    struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct nlattr *tb[NETCONFA_MAX+1];
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index eb4bb12b3eb..0e74398bc8e 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -604,7 +604,7 @@ errout:
 	return err;
 }
 
-static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_config cfg;
@@ -626,7 +626,7 @@ errout:
 	return err;
 }
 
-static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_config cfg;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6e2851464f8..550781a17b3 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2311,7 +2311,7 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void *arg)
+static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct rtmsg *rtm;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index fa36a677490..15794fdaf02 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -544,8 +544,7 @@ static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = {
 };
 
 static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
-				     struct nlmsghdr *nlh,
-				     void *arg)
+				     struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct nlattr *tb[NETCONFA_MAX+1];
@@ -3578,7 +3577,7 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = {
 };
 
 static int
-inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifaddrmsg *ifm;
@@ -3644,7 +3643,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags,
 }
 
 static int
-inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifaddrmsg *ifm;
@@ -3983,8 +3982,7 @@ static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb)
 	return inet6_dump_addr(skb, cb, type);
 }
 
-static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
-			     void *arg)
+static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct ifaddrmsg *ifm;
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 6f226c850c9..f083a583a05 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -414,8 +414,7 @@ static const struct nla_policy ifal_policy[IFAL_MAX+1] = {
 	[IFAL_LABEL]		= { .len = sizeof(u32), },
 };
 
-static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh,
-			     void *arg)
+static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifaddrlblmsg *ifal;
@@ -530,8 +529,7 @@ static inline int ip6addrlbl_msgsize(void)
 		+ nla_total_size(4);	/* IFAL_LABEL */
 }
 
-static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh,
-			  void *arg)
+static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct ifaddrlblmsg *ifal;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e5fe0041adf..ad0aa6b0b86 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2355,7 +2355,7 @@ beginning:
 	return last_err;
 }
 
-static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh)
 {
 	struct fib6_config cfg;
 	int err;
@@ -2370,7 +2370,7 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *a
 		return ip6_route_del(&cfg);
 }
 
-static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh)
 {
 	struct fib6_config cfg;
 	int err;
@@ -2562,7 +2562,7 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg)
 		     prefix, 0, NLM_F_MULTI);
 }
 
-static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
+static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct nlattr *tb[RTA_MAX+1];
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index 0193630d306..dc15f430080 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -61,7 +61,7 @@ static const struct nla_policy ifa_phonet_policy[IFA_MAX+1] = {
 	[IFA_LOCAL] = { .type = NLA_U8 },
 };
 
-static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *attr)
+static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[IFA_MAX+1];
@@ -224,7 +224,7 @@ static const struct nla_policy rtm_phonet_policy[RTA_MAX+1] = {
 	[RTA_OIF] = { .type = NLA_U32 },
 };
 
-static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *attr)
+static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[RTA_MAX+1];
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 8579c4bb20c..fd7072827a4 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -982,7 +982,7 @@ done:
 	return ret;
 }
 
-static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
+static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tca[TCA_ACT_MAX + 1];
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 964f5e4f4b8..9a04b981bc1 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -118,7 +118,7 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp)
 
 /* Add/change/delete/get a filter node */
 
-static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
+static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tca[TCA_MAX + 1];
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index c297e2a8e2a..0bbce229ac6 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -971,7 +971,7 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w)
  * Delete/get qdisc.
  */
 
-static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
+static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
 {
 	struct net *net = sock_net(skb->sk);
 	struct tcmsg *tcm = nlmsg_data(n);
@@ -1038,7 +1038,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
  * Create/change qdisc.
  */
 
-static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
+static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
 {
 	struct net *net = sock_net(skb->sk);
 	struct tcmsg *tcm;
@@ -1372,7 +1372,7 @@ done:
 
 
 
-static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
+static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n)
 {
 	struct net *net = sock_net(skb->sk);
 	struct tcmsg *tcm = nlmsg_data(n);
-- 
cgit v1.2.3-70-g09d2


From 0465277f6b3fd0535428ae935644ac30ce903de0 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Fri, 22 Mar 2013 06:28:42 +0000
Subject: ipv4: provide addr and netconf dump consistency info

This patch takes benefit of dev_addr_genid and dev_base_seq to check if a change
occurs during a netlink dump. If a change is detected, the flag NLM_F_DUMP_INTR
is set in the first message after the dump was interrupted.

Note that seq and prev_seq must be reset between each family in rtnl_dump_all()
because they are specific to each family.

Reported-by: Junwei Zhang <junwei.zhang@6wind.com>
Reported-by: Hongjun Li <hongjun.li@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 5 ++++-
 net/ipv4/devinet.c   | 6 ++++++
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'net/core/rtnetlink.c')

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 751f1244b64..aeb81316a70 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1929,8 +1929,11 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 		if (rtnl_msg_handlers[idx] == NULL ||
 		    rtnl_msg_handlers[idx][type].dumpit == NULL)
 			continue;
-		if (idx > s_idx)
+		if (idx > s_idx) {
 			memset(&cb->args[0], 0, sizeof(cb->args));
+			cb->prev_seq = 0;
+			cb->seq = 0;
+		}
 		if (rtnl_msg_handlers[idx][type].dumpit(skb, cb))
 			break;
 	}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 20a9f9274f3..5d985e36753 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1499,6 +1499,8 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 		idx = 0;
 		head = &net->dev_index_head[h];
 		rcu_read_lock();
+		cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^
+			  net->dev_base_seq;
 		hlist_for_each_entry_rcu(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
@@ -1519,6 +1521,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 					rcu_read_unlock();
 					goto done;
 				}
+				nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 			}
 cont:
 			idx++;
@@ -1807,6 +1810,8 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb,
 		idx = 0;
 		head = &net->dev_index_head[h];
 		rcu_read_lock();
+		cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^
+			  net->dev_base_seq;
 		hlist_for_each_entry_rcu(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
@@ -1824,6 +1829,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb,
 				rcu_read_unlock();
 				goto done;
 			}
+			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
 			idx++;
 		}
-- 
cgit v1.2.3-70-g09d2


From 573ce260b385a4d14a1ef046558fad9f1daeee42 Mon Sep 17 00:00:00 2001
From: Hong zhi guo <honkiko@gmail.com>
Date: Wed, 27 Mar 2013 06:47:04 +0000
Subject: net-next: replace obsolete NLMSG_* with type safe nlmsg_*

Signed-off-by: Hong Zhiguo <honkiko@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/netfilter/ebt_ulog.c      |  4 ++--
 net/core/rtnetlink.c                 |  4 ++--
 net/decnet/dn_table.c                |  4 ++--
 net/decnet/netfilter/dn_rtmsg.c      | 12 ++++++------
 net/ieee802154/netlink.c             |  4 ++--
 net/ipv4/fib_frontend.c              |  6 +++---
 net/ipv4/ipmr.c                      | 10 +++++-----
 net/ipv4/netfilter/ipt_ULOG.c        |  4 ++--
 net/ipv4/udp_diag.c                  |  6 +++---
 net/ipv6/ip6mr.c                     | 10 +++++-----
 net/netfilter/ipset/ip_set_core.c    |  5 ++---
 net/netfilter/nfnetlink.c            |  7 +++----
 net/netfilter/nfnetlink_log.c        |  4 ++--
 net/netfilter/nfnetlink_queue_core.c |  2 +-
 net/netlink/af_netlink.c             |  4 ++--
 net/sched/cls_api.c                  |  4 ++--
 net/sched/sch_api.c                  |  2 +-
 net/tipc/netlink.c                   |  6 +++---
 18 files changed, 48 insertions(+), 50 deletions(-)

(limited to 'net/core/rtnetlink.c')

diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c
index 442b0321acb..961d870ab28 100644
--- a/net/bridge/netfilter/ebt_ulog.c
+++ b/net/bridge/netfilter/ebt_ulog.c
@@ -35,7 +35,7 @@
 #include <linux/skbuff.h>
 #include <linux/kernel.h>
 #include <linux/timer.h>
-#include <linux/netlink.h>
+#include <net/netlink.h>
 #include <linux/netdevice.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_bridge/ebtables.h>
@@ -134,7 +134,7 @@ static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb,
 	else
 		copy_len = uloginfo->cprange;
 
-	size = NLMSG_SPACE(sizeof(*pm) + copy_len);
+	size = nlmsg_total_size(sizeof(*pm) + copy_len);
 	if (size > nlbufsiz) {
 		pr_debug("Size %Zd needed, but nlbufsiz=%d\n", size, nlbufsiz);
 		return;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index aeb81316a70..6fdfac8978f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2613,10 +2613,10 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	type -= RTM_BASE;
 
 	/* All the messages must have at least 1 byte length */
-	if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(struct rtgenmsg)))
+	if (nlmsg_len(nlh) < sizeof(struct rtgenmsg))
 		return 0;
 
-	family = ((struct rtgenmsg *)NLMSG_DATA(nlh))->rtgen_family;
+	family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family;
 	sz_idx = type>>2;
 	kind = type&3;
 
diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c
index fc42a0afd30..b15c1d1720f 100644
--- a/net/decnet/dn_table.c
+++ b/net/decnet/dn_table.c
@@ -19,7 +19,7 @@
 #include <linux/sockios.h>
 #include <linux/init.h>
 #include <linux/skbuff.h>
-#include <linux/netlink.h>
+#include <net/netlink.h>
 #include <linux/rtnetlink.h>
 #include <linux/proc_fs.h>
 #include <linux/netdevice.h>
@@ -492,7 +492,7 @@ int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	if (!net_eq(net, &init_net))
 		return 0;
 
-	if (NLMSG_PAYLOAD(cb->nlh, 0) >= sizeof(struct rtmsg) &&
+	if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
 		((struct rtmsg *)nlmsg_data(cb->nlh))->rtm_flags&RTM_F_CLONED)
 			return dn_cache_dump(skb, cb);
 
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index dfe42012a04..2a7efe38834 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -19,7 +19,7 @@
 #include <linux/netdevice.h>
 #include <linux/netfilter.h>
 #include <linux/spinlock.h>
-#include <linux/netlink.h>
+#include <net/netlink.h>
 #include <linux/netfilter_decnet.h>
 
 #include <net/sock.h>
@@ -39,21 +39,21 @@ static struct sk_buff *dnrmg_build_message(struct sk_buff *rt_skb, int *errp)
 	unsigned char *ptr;
 	struct nf_dn_rtmsg *rtm;
 
-	size = NLMSG_SPACE(rt_skb->len);
-	size += NLMSG_ALIGN(sizeof(struct nf_dn_rtmsg));
-	skb = alloc_skb(size, GFP_ATOMIC);
+	size = NLMSG_ALIGN(rt_skb->len) +
+	       NLMSG_ALIGN(sizeof(struct nf_dn_rtmsg));
+	skb = nlmsg_new(size, GFP_ATOMIC);
 	if (!skb) {
 		*errp = -ENOMEM;
 		return NULL;
 	}
 	old_tail = skb->tail;
-	nlh = nlmsg_put(skb, 0, 0, 0, size - sizeof(*nlh), 0);
+	nlh = nlmsg_put(skb, 0, 0, 0, size, 0);
 	if (!nlh) {
 		kfree_skb(skb);
 		*errp = -ENOMEM;
 		return NULL;
 	}
-	rtm = (struct nf_dn_rtmsg *)NLMSG_DATA(nlh);
+	rtm = (struct nf_dn_rtmsg *)nlmsg_data(nlh);
 	rtm->nfdn_ifindex = rt_skb->dev->ifindex;
 	ptr = NFDN_RTMSG(rtm);
 	skb_copy_from_linear_data(rt_skb, ptr, rt_skb->len);
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 97351e1d07a..92472528106 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -65,7 +65,7 @@ struct sk_buff *ieee802154_nl_create(int flags, u8 req)
 int ieee802154_nl_mcast(struct sk_buff *msg, unsigned int group)
 {
 	/* XXX: nlh is right at the start of msg */
-	void *hdr = genlmsg_data(NLMSG_DATA(msg->data));
+	void *hdr = genlmsg_data(nlmsg_data(msg->data));
 
 	if (genlmsg_end(msg, hdr) < 0)
 		goto out;
@@ -98,7 +98,7 @@ struct sk_buff *ieee802154_nl_new_reply(struct genl_info *info,
 int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info)
 {
 	/* XXX: nlh is right at the start of msg */
-	void *hdr = genlmsg_data(NLMSG_DATA(msg->data));
+	void *hdr = genlmsg_data(nlmsg_data(msg->data));
 
 	if (genlmsg_end(msg, hdr) < 0)
 		goto out;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 0e74398bc8e..c7629a209f9 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -957,8 +957,8 @@ static void nl_fib_input(struct sk_buff *skb)
 
 	net = sock_net(skb->sk);
 	nlh = nlmsg_hdr(skb);
-	if (skb->len < NLMSG_SPACE(0) || skb->len < nlh->nlmsg_len ||
-	    nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*frn)))
+	if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len ||
+	    nlmsg_len(nlh) < sizeof(*frn))
 		return;
 
 	skb = skb_clone(skb, GFP_KERNEL);
@@ -966,7 +966,7 @@ static void nl_fib_input(struct sk_buff *skb)
 		return;
 	nlh = nlmsg_hdr(skb);
 
-	frn = (struct fib_result_nl *) NLMSG_DATA(nlh);
+	frn = (struct fib_result_nl *) nlmsg_data(nlh);
 	tb = fib_get_table(net, frn->tb_id_in);
 
 	nl_fib_lookup(frn, tb);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index fd61fe16679..9d9610ae785 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -626,9 +626,9 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c)
 		if (ip_hdr(skb)->version == 0) {
 			struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr));
 			nlh->nlmsg_type = NLMSG_ERROR;
-			nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr));
+			nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr));
 			skb_trim(skb, nlh->nlmsg_len);
-			e = NLMSG_DATA(nlh);
+			e = nlmsg_data(nlh);
 			e->error = -ETIMEDOUT;
 			memset(&e->msg, 0, sizeof(e->msg));
 
@@ -910,14 +910,14 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt,
 		if (ip_hdr(skb)->version == 0) {
 			struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr));
 
-			if (__ipmr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) {
+			if (__ipmr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) {
 				nlh->nlmsg_len = skb_tail_pointer(skb) -
 						 (u8 *)nlh;
 			} else {
 				nlh->nlmsg_type = NLMSG_ERROR;
-				nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr));
+				nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr));
 				skb_trim(skb, nlh->nlmsg_len);
-				e = NLMSG_DATA(nlh);
+				e = nlmsg_data(nlh);
 				e->error = -EMSGSIZE;
 				memset(&e->msg, 0, sizeof(e->msg));
 			}
diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index 7d168dcbd13..e7f8cad1139 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -37,7 +37,7 @@
 #include <linux/skbuff.h>
 #include <linux/kernel.h>
 #include <linux/timer.h>
-#include <linux/netlink.h>
+#include <net/netlink.h>
 #include <linux/netdevice.h>
 #include <linux/mm.h>
 #include <linux/moduleparam.h>
@@ -172,7 +172,7 @@ static void ipt_ulog_packet(unsigned int hooknum,
 	else
 		copy_len = loginfo->copy_range;
 
-	size = NLMSG_SPACE(sizeof(*pm) + copy_len);
+	size = nlmsg_total_size(sizeof(*pm) + copy_len);
 
 	ub = &ulog_buffers[groupnum];
 
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 505b30ad918..369a781851a 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -64,9 +64,9 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
 		goto out;
 
 	err = -ENOMEM;
-	rep = alloc_skb(NLMSG_SPACE((sizeof(struct inet_diag_msg) +
-				     sizeof(struct inet_diag_meminfo) +
-				     64)), GFP_KERNEL);
+	rep = nlmsg_new(sizeof(struct inet_diag_msg) +
+			sizeof(struct inet_diag_meminfo) + 64,
+			GFP_KERNEL);
 	if (!rep)
 		goto out;
 
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 96bfb4e4b82..241fb8ad9fc 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -842,9 +842,9 @@ static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c)
 		if (ipv6_hdr(skb)->version == 0) {
 			struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr));
 			nlh->nlmsg_type = NLMSG_ERROR;
-			nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr));
+			nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr));
 			skb_trim(skb, nlh->nlmsg_len);
-			((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -ETIMEDOUT;
+			((struct nlmsgerr *)nlmsg_data(nlh))->error = -ETIMEDOUT;
 			rtnl_unicast(skb, net, NETLINK_CB(skb).portid);
 		} else
 			kfree_skb(skb);
@@ -1100,13 +1100,13 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt,
 		if (ipv6_hdr(skb)->version == 0) {
 			struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr));
 
-			if (__ip6mr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) {
+			if (__ip6mr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) {
 				nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh;
 			} else {
 				nlh->nlmsg_type = NLMSG_ERROR;
-				nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr));
+				nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr));
 				skb_trim(skb, nlh->nlmsg_len);
-				((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -EMSGSIZE;
+				((struct nlmsgerr *)nlmsg_data(nlh))->error = -EMSGSIZE;
 			}
 			rtnl_unicast(skb, net, NETLINK_CB(skb).portid);
 		} else
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 1ba9dbc0e10..86f5e26f39d 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -15,7 +15,6 @@
 #include <linux/ip.h>
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
-#include <linux/netlink.h>
 #include <linux/rculist.h>
 #include <net/netlink.h>
 
@@ -1085,7 +1084,7 @@ static int
 dump_init(struct netlink_callback *cb)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(cb->skb);
-	int min_len = NLMSG_SPACE(sizeof(struct nfgenmsg));
+	int min_len = nlmsg_total_size(sizeof(struct nfgenmsg));
 	struct nlattr *cda[IPSET_ATTR_CMD_MAX+1];
 	struct nlattr *attr = (void *)nlh + min_len;
 	u32 dump_type;
@@ -1301,7 +1300,7 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set,
 		struct sk_buff *skb2;
 		struct nlmsgerr *errmsg;
 		size_t payload = sizeof(*errmsg) + nlmsg_len(nlh);
-		int min_len = NLMSG_SPACE(sizeof(struct nfgenmsg));
+		int min_len = nlmsg_total_size(sizeof(struct nfgenmsg));
 		struct nlattr *cda[IPSET_ATTR_CMD_MAX+1];
 		struct nlattr *cmdattr;
 		u32 *errline;
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 0b1b32cda30..bc4c499adb1 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -24,10 +24,9 @@
 #include <linux/skbuff.h>
 #include <asm/uaccess.h>
 #include <net/sock.h>
-#include <net/netlink.h>
 #include <linux/init.h>
 
-#include <linux/netlink.h>
+#include <net/netlink.h>
 #include <linux/netfilter/nfnetlink.h>
 
 MODULE_LICENSE("GPL");
@@ -144,7 +143,7 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return -EPERM;
 
 	/* All the messages must at least contain nfgenmsg */
-	if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(struct nfgenmsg)))
+	if (nlmsg_len(nlh) < sizeof(struct nfgenmsg))
 		return 0;
 
 	type = nlh->nlmsg_type;
@@ -172,7 +171,7 @@ replay:
 	}
 
 	{
-		int min_len = NLMSG_SPACE(sizeof(struct nfgenmsg));
+		int min_len = nlmsg_total_size(sizeof(struct nfgenmsg));
 		u_int8_t cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type);
 		struct nlattr *cda[ss->cb[cb_id].attr_count + 1];
 		struct nlattr *attr = (void *)nlh + min_len;
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index f248db57297..4a2593f100c 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -19,7 +19,7 @@
 #include <linux/ipv6.h>
 #include <linux/netdevice.h>
 #include <linux/netfilter.h>
-#include <linux/netlink.h>
+#include <net/netlink.h>
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nfnetlink_log.h>
 #include <linux/spinlock.h>
@@ -609,7 +609,7 @@ nfulnl_log_packet(u_int8_t pf,
 	/* FIXME: do we want to make the size calculation conditional based on
 	 * what is actually present?  way more branches and checks, but more
 	 * memory efficient... */
-	size =    NLMSG_SPACE(sizeof(struct nfgenmsg))
+	size =    nlmsg_total_size(sizeof(struct nfgenmsg))
 		+ nla_total_size(sizeof(struct nfulnl_msg_packet_hdr))
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index 19845e34f70..e92c9161e39 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -281,7 +281,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
 	struct nf_conn *ct = NULL;
 	enum ip_conntrack_info uninitialized_var(ctinfo);
 
-	size =    NLMSG_SPACE(sizeof(struct nfgenmsg))
+	size =    nlmsg_total_size(sizeof(struct nfgenmsg))
 		+ nla_total_size(sizeof(struct nfqnl_msg_packet_hdr))
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index a500ce20143..ce2e0064e7f 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1646,7 +1646,7 @@ struct nlmsghdr *
 __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags)
 {
 	struct nlmsghdr *nlh;
-	int size = NLMSG_LENGTH(len);
+	int size = nlmsg_msg_size(len);
 
 	nlh = (struct nlmsghdr*)skb_put(skb, NLMSG_ALIGN(size));
 	nlh->nlmsg_type = type;
@@ -1655,7 +1655,7 @@ __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int fla
 	nlh->nlmsg_pid = portid;
 	nlh->nlmsg_seq = seq;
 	if (!__builtin_constant_p(size) || NLMSG_ALIGN(size) - size != 0)
-		memset(NLMSG_DATA(nlh) + len, 0, NLMSG_ALIGN(size) - size);
+		memset(nlmsg_data(nlh) + len, 0, NLMSG_ALIGN(size) - size);
 	return nlh;
 }
 EXPORT_SYMBOL(__nlmsg_put);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 9d71d4ded53..5c81b260323 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -22,7 +22,7 @@
 #include <linux/skbuff.h>
 #include <linux/init.h>
 #include <linux/kmod.h>
-#include <linux/netlink.h>
+#include <net/netlink.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <net/net_namespace.h>
@@ -428,7 +428,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 	const struct Qdisc_class_ops *cops;
 	struct tcf_dump_args arg;
 
-	if (cb->nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*tcm)))
+	if (nlmsg_len(cb->nlh) < sizeof(*tcm))
 		return skb->len;
 	dev = __dev_get_by_index(net, tcm->tcm_ifindex);
 	if (!dev)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index d7468baf890..2b935e7cfe7 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1642,7 +1642,7 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb)
 	struct net_device *dev;
 	int t, s_t;
 
-	if (cb->nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*tcm)))
+	if (nlmsg_len(cb->nlh) < sizeof(*tcm))
 		return 0;
 	dev = dev_get_by_index(net, tcm->tcm_ifindex);
 	if (!dev)
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 6675914dc59..8bcd4985d0f 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -44,7 +44,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
 	struct nlmsghdr *rep_nlh;
 	struct nlmsghdr *req_nlh = info->nlhdr;
 	struct tipc_genlmsghdr *req_userhdr = info->userhdr;
-	int hdr_space = NLMSG_SPACE(GENL_HDRLEN + TIPC_GENL_HDRLEN);
+	int hdr_space = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN);
 	u16 cmd;
 
 	if ((req_userhdr->cmd & 0xC000) && (!capable(CAP_NET_ADMIN)))
@@ -53,8 +53,8 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
 		cmd = req_userhdr->cmd;
 
 	rep_buf = tipc_cfg_do_cmd(req_userhdr->dest, cmd,
-			NLMSG_DATA(req_nlh) + GENL_HDRLEN + TIPC_GENL_HDRLEN,
-			NLMSG_PAYLOAD(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN),
+			nlmsg_data(req_nlh) + GENL_HDRLEN + TIPC_GENL_HDRLEN,
+			nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN),
 			hdr_space);
 
 	if (rep_buf) {
-- 
cgit v1.2.3-70-g09d2


From 91f3e7b17412d42e933949a9c297072b13a04d41 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Fri, 29 Mar 2013 08:18:37 +0000
Subject: net: rtnetlink: fdb dflt dump must set idx used for cb->arg[0]

In rtnl_fdb_dump() when the fdb_dump ndo op is not populated
we never set the idx value so that cb->arg[0] is always 0.
Resulting in a endless loop of messages.

Introduced with this commit,

commit 090096bf3db1c281ddd034573260045888a68fea
Author: Vlad Yasevich <vyasevic@redhat.com>
Date:   Wed Mar 6 15:39:42 2013 +0000

    net: generic fdb support for drivers without ndo_fdb_<op>

CC: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/core/rtnetlink.c')

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 6fdfac8978f..d2322d7f0f7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2262,7 +2262,7 @@ skip:
  * @dev: netdevice
  *
  * Default netdevice operation to dump the existing unicast address list.
- * Returns zero on success.
+ * Returns number of addresses from list put in skb.
  */
 int ndo_dflt_fdb_dump(struct sk_buff *skb,
 		      struct netlink_callback *cb,
@@ -2303,7 +2303,7 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		if (dev->netdev_ops->ndo_fdb_dump)
 			idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, idx);
 		else
-			ndo_dflt_fdb_dump(skb, cb, dev, idx);
+			idx = ndo_dflt_fdb_dump(skb, cb, dev, idx);
 	}
 	rcu_read_unlock();
 
-- 
cgit v1.2.3-70-g09d2


From 37fe0660981d7a1577409226f77554c2c5123e27 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevic@redhat.com>
Date: Tue, 23 Apr 2013 11:05:23 +0000
Subject: net: fix address check in rtnl_fdb_del

Commit 6681712d67eef14c4ce793561c3231659153a320
	vxlan: generalize forwarding tables

relaxed the address checks in rtnl_fdb_del() to use is_zero_ether_addr().
This allows users to add multicast addresses using the fdb API.  However,
the check in rtnl_fdb_del() still uses a more strict
is_valid_ether_addr() which rejects multicast addresses.  Thus it
is possible to add an fdb that can not be later removed.
Relax the check in rtnl_fdb_del() as well.

Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net/core/rtnetlink.c')

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 18af08a73f0..a08bd2b7fe3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2192,7 +2192,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 	}
 
 	addr = nla_data(tb[NDA_LLADDR]);
-	if (!is_valid_ether_addr(addr)) {
+	if (is_zero_ether_addr(addr)) {
 		pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ether address\n");
 		return -EINVAL;
 	}
-- 
cgit v1.2.3-70-g09d2