Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	include/net/inetpeer.h
	net/ipv6/output_core.c

Changes in net were fixing bugs in code removed in net-next.

Signed-off-by: David S. Miller <davem@davemloft.net>

13 files changed, 131 insertions, 44 deletions

diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 8c7ca811de6..96b66fd30f9 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -415,7 +415,7 @@ batadv_mcast_forw_ipv4_node_get(struct batadv_priv *bat_priv)
 	hlist_for_each_entry_rcu(tmp_orig_node,
 				 &bat_priv->mcast.want_all_ipv4_list,
 				 mcast_want_all_ipv4_node) {
-		if (!atomic_inc_not_zero(&orig_node->refcount))
+		if (!atomic_inc_not_zero(&tmp_orig_node->refcount))
 			continue;
 
 		orig_node = tmp_orig_node;
@@ -442,7 +442,7 @@ batadv_mcast_forw_ipv6_node_get(struct batadv_priv *bat_priv)
 	hlist_for_each_entry_rcu(tmp_orig_node,
 				 &bat_priv->mcast.want_all_ipv6_list,
 				 mcast_want_all_ipv6_node) {
-		if (!atomic_inc_not_zero(&orig_node->refcount))
+		if (!atomic_inc_not_zero(&tmp_orig_node->refcount))
 			continue;
 
 		orig_node = tmp_orig_node;
@@ -493,7 +493,7 @@ batadv_mcast_forw_unsnoop_node_get(struct batadv_priv *bat_priv)
 	hlist_for_each_entry_rcu(tmp_orig_node,
 				 &bat_priv->mcast.want_all_unsnoopables_list,
 				 mcast_want_all_unsnoopables_node) {
-		if (!atomic_inc_not_zero(&orig_node->refcount))
+		if (!atomic_inc_not_zero(&tmp_orig_node->refcount))
 			continue;
 
 		orig_node = tmp_orig_node;
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 2c45c069ea1..b524c36c127 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -538,6 +538,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
 {
 	struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
 	struct net_bridge_fdb_entry *fdb;
+	bool fdb_modified = false;
 
 	/* some users want to always flood. */
 	if (hold_time(br) == 0)
@@ -558,10 +559,15 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
 					source->dev->name);
 		} else {
 			/* fastpath: update of existing entry */
-			fdb->dst = source;
+			if (unlikely(source != fdb->dst)) {
+				fdb->dst = source;
+				fdb_modified = true;
+			}
 			fdb->updated = jiffies;
 			if (unlikely(added_by_user))
 				fdb->added_by_user = 1;
+			if (unlikely(fdb_modified))
+				fdb_notify(br, fdb, RTM_NEWNEIGH);
 		}
 	} else {
 		spin_lock(&br->hash_lock);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 7985deaff52..04d6348fd53 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -147,8 +147,8 @@ static int br_handle_local_finish(struct sk_buff *skb)
 	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
 	u16 vid = 0;
 
-	br_vlan_get_tag(skb, &vid);
-	if (p->flags & BR_LEARNING)
+	/* check if vlan is allowed, to avoid spoofing */
+	if (p->flags & BR_LEARNING && br_should_learn(p, skb, &vid))
 		br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
 	return 0;	 /* process further */
 }
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 53d6e32965f..bc17210d4c5 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -589,6 +589,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 			struct sk_buff *skb, u16 *vid);
 bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v,
 		       const struct sk_buff *skb);
+bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid);
 struct sk_buff *br_handle_vlan(struct net_bridge *br,
 			       const struct net_port_vlans *v,
 			       struct sk_buff *skb);
@@ -660,6 +661,12 @@ static inline bool br_allowed_egress(struct net_bridge *br,
 	return true;
 }
 
+static inline bool br_should_learn(struct net_bridge_port *p,
+				   struct sk_buff *skb, u16 *vid)
+{
+	return true;
+}
+
 static inline struct sk_buff *br_handle_vlan(struct net_bridge *br,
 					     const struct net_port_vlans *v,
 					     struct sk_buff *skb)
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 24c5cc55589..fcc95390f86 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -241,6 +241,34 @@ bool br_allowed_egress(struct net_bridge *br,
 	return false;
 }
 
+/* Called under RCU */
+bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
+{
+	struct net_bridge *br = p->br;
+	struct net_port_vlans *v;
+
+	if (!br->vlan_enabled)
+		return true;
+
+	v = rcu_dereference(p->vlan_info);
+	if (!v)
+		return false;
+
+	br_vlan_get_tag(skb, vid);
+	if (!*vid) {
+		*vid = br_get_pvid(v);
+		if (*vid == VLAN_N_VID)
+			return false;
+
+		return true;
+	}
+
+	if (test_bit(*vid, v->vlan_bitmap))
+		return true;
+
+	return false;
+}
+
 /* Must be protected by RTNL.
  * Must be called with vid in range from 1 to 4094 inclusive.
  */
diff --git a/net/core/dev.c b/net/core/dev.c
index 1ba2cfe3f8e..5367bfba094 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2289,8 +2289,8 @@ EXPORT_SYMBOL(skb_checksum_help);
 
 __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
+	unsigned int vlan_depth = skb->mac_len;
 	__be16 type = skb->protocol;
-	int vlan_depth = skb->mac_len;
 
 	/* Tunnel gso handlers can set protocol to ethernet. */
 	if (type == htons(ETH_P_TEB)) {
@@ -2303,15 +2303,30 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 		type = eth->h_proto;
 	}
 
-	while (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
-		struct vlan_hdr *vh;
-
-		if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN)))
-			return 0;
-
-		vh = (struct vlan_hdr *)(skb->data + vlan_depth);
-		type = vh->h_vlan_encapsulated_proto;
-		vlan_depth += VLAN_HLEN;
+	/* if skb->protocol is 802.1Q/AD then the header should already be
+	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
+	 * ETH_HLEN otherwise
+	 */
+	if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
+		if (vlan_depth) {
+			if (unlikely(WARN_ON(vlan_depth < VLAN_HLEN)))
+				return 0;
+			vlan_depth -= VLAN_HLEN;
+		} else {
+			vlan_depth = ETH_HLEN;
+		}
+		do {
+			struct vlan_hdr *vh;
+
+			if (unlikely(!pskb_may_pull(skb,
+						    vlan_depth + VLAN_HLEN)))
+				return 0;
+
+			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
+			type = vh->h_vlan_encapsulated_proto;
+			vlan_depth += VLAN_HLEN;
+		} while (type == htons(ETH_P_8021Q) ||
+			 type == htons(ETH_P_8021AD));
 	}
 
 	*depth = vlan_depth;
diff --git a/net/core/filter.c b/net/core/filter.c
index 842f8393121..9de0c25323b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1492,8 +1492,13 @@ static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp,
 	fp->jited = 0;
 
 	err = sk_chk_filter(fp->insns, fp->len);
-	if (err)
+	if (err) {
+		if (sk != NULL)
+			sk_filter_uncharge(sk, fp);
+		else
+			kfree(fp);
 		return ERR_PTR(err);
+	}
 
 	/* Probe if we can JIT compile the filter and if so, do
 	 * the compilation of the filter.
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f31268dbc0d..741b22c62ac 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2045,11 +2045,15 @@ replay:
 		if (ops->newlink) {
 			err = ops->newlink(net, dev, tb, data);
 			/* Drivers should call free_netdev() in ->destructor
-			 * and unregister it on failure so that device could be
-			 * finally freed in rtnl_unlock.
+			 * and unregister it on failure after registration
+			 * so that device could be finally freed in rtnl_unlock.
 			 */
-			if (err < 0)
+			if (err < 0) {
+				/* If device is not registered at all, free it now */
+				if (dev->reg_state == NETREG_UNINITIALIZED)
+					free_netdev(dev);
 				goto out;
+			}
 		} else {
 			err = register_netdevice(dev);
 			if (err < 0) {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 350b2072f0a..931529d5daa 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2684,13 +2684,12 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
 	bool recovered = !before(tp->snd_una, tp->high_seq);
 
 	if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
-		if (flag & FLAG_ORIG_SACK_ACKED) {
-			/* Step 3.b. A timeout is spurious if not all data are
-			 * lost, i.e., never-retransmitted data are (s)acked.
-			 */
-			tcp_try_undo_loss(sk, true);
+		/* Step 3.b. A timeout is spurious if not all data are
+		 * lost, i.e., never-retransmitted data are (s)acked.
+		 */
+		if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED))
 			return;
-		}
+
 		if (after(tp->snd_nxt, tp->high_seq) &&
 		    (flag & FLAG_DATA_SACKED || is_dupack)) {
 			tp->frto = 0; /* Loss was real: 2nd part of step 3.a */
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 6179ac186ab..ffa029305a0 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -8,7 +8,6 @@
 #include <net/addrconf.h>
 #include <net/secure_seq.h>
 
-
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
 	u16 offset = sizeof(struct ipv6hdr);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index d9da8c448c7..e6836755c45 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1392,15 +1392,19 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 
 	if (ipip) {
 		__be32 info = ic->un.gateway;
+		__u8 type = ic->type;
+		__u8 code = ic->code;
 
 		/* Update the MTU */
 		if (ic->type == ICMP_DEST_UNREACH &&
 		    ic->code == ICMP_FRAG_NEEDED) {
 			struct ip_vs_dest *dest = cp->dest;
 			u32 mtu = ntohs(ic->un.frag.mtu);
+			__be16 frag_off = cih->frag_off;
 
 			/* Strip outer IP and ICMP, go to IPIP header */
-			__skb_pull(skb, ihl + sizeof(_icmph));
+			if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL)
+				goto ignore_ipip;
 			offset2 -= ihl + sizeof(_icmph);
 			skb_reset_network_header(skb);
 			IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
@@ -1408,7 +1412,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 			ipv4_update_pmtu(skb, dev_net(skb->dev),
 					 mtu, 0, 0, 0, 0);
 			/* Client uses PMTUD? */
-			if (!(cih->frag_off & htons(IP_DF)))
+			if (!(frag_off & htons(IP_DF)))
 				goto ignore_ipip;
 			/* Prefer the resulting PMTU */
 			if (dest) {
@@ -1427,12 +1431,13 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 		/* Strip outer IP, ICMP and IPIP, go to IP header of
 		 * original request.
 		 */
-		__skb_pull(skb, offset2);
+		if (pskb_pull(skb, offset2) == NULL)
+			goto ignore_ipip;
 		skb_reset_network_header(skb);
 		IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
 			&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
-			ic->type, ic->code, ntohl(info));
-		icmp_send(skb, ic->type, ic->code, info);
+			type, code, ntohl(info));
+		icmp_send(skb, type, code, info);
 		/* ICMP can be shorter but anyways, account it */
 		ip_vs_out_stats(cp, skb);
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index e0ccd84d4d6..15c731f03fa 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1377,7 +1377,9 @@ retry:
 bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
 			struct user_namespace *user_ns, int cap)
 {
-	return sk_ns_capable(nsp->sk, user_ns, cap);
+	return ((nsp->flags & NETLINK_SKB_DST) ||
+		file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) &&
+		ns_capable(user_ns, cap);
 }
 EXPORT_SYMBOL(__netlink_ns_capable);
 
@@ -2323,6 +2325,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	struct sk_buff *skb;
 	int err;
 	struct scm_cookie scm;
+	u32 netlink_skb_flags = 0;
 
 	if (msg->msg_flags&MSG_OOB)
 		return -EOPNOTSUPP;
@@ -2344,6 +2347,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		if ((dst_group || dst_portid) &&
 		    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 			goto out;
+		netlink_skb_flags |= NETLINK_SKB_DST;
 	} else {
 		dst_portid = nlk->dst_portid;
 		dst_group = nlk->dst_group;
@@ -2373,6 +2377,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	NETLINK_CB(skb).portid	= nlk->portid;
 	NETLINK_CB(skb).dst_group = dst_group;
 	NETLINK_CB(skb).creds	= siocb->scm->creds;
+	NETLINK_CB(skb).flags	= netlink_skb_flags;
 
 	err = -EFAULT;
 	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index fd9a16a6d1d..412d9dc3a87 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -947,6 +947,20 @@ static struct sk_buff *xfrm_state_netlink(struct sk_buff *in_skb,
 	return skb;
 }
 
+/* A wrapper for nlmsg_multicast() checking that nlsk is still available.
+ * Must be called with RCU read lock.
+ */
+static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb,
+				       u32 pid, unsigned int group)
+{
+	struct sock *nlsk = rcu_dereference(net->xfrm.nlsk);
+
+	if (nlsk)
+		return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC);
+	else
+		return -1;
+}
+
 static inline size_t xfrm_spdinfo_msgsize(void)
 {
 	return NLMSG_ALIGN(4)
@@ -2228,7 +2242,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	if (build_migrate(skb, m, num_migrate, k, sel, dir, type) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MIGRATE, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE);
 }
 #else
 static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
@@ -2419,7 +2433,7 @@ static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c)
 		return -EMSGSIZE;
 	}
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE);
 }
 
 static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event *c)
@@ -2434,7 +2448,7 @@ static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event
 	if (build_aevent(skb, x, c) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_AEVENTS, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_AEVENTS);
 }
 
 static int xfrm_notify_sa_flush(const struct km_event *c)
@@ -2460,7 +2474,7 @@ static int xfrm_notify_sa_flush(const struct km_event *c)
 
 	nlmsg_end(skb, nlh);
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA);
 }
 
 static inline size_t xfrm_sa_len(struct xfrm_state *x)
@@ -2547,7 +2561,7 @@ static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c)
 
 	nlmsg_end(skb, nlh);
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA);
 
 out_free_skb:
 	kfree_skb(skb);
@@ -2638,7 +2652,7 @@ static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt,
 	if (build_acquire(skb, x, xt, xp) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_ACQUIRE, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_ACQUIRE);
 }
 
 /* User gives us xfrm_user_policy_info followed by an array of 0
@@ -2752,7 +2766,7 @@ static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct
 	if (build_polexpire(skb, xp, dir, c) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE);
 }
 
 static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c)
@@ -2814,7 +2828,7 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e
 
 	nlmsg_end(skb, nlh);
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);
 
 out_free_skb:
 	kfree_skb(skb);
@@ -2842,7 +2856,7 @@ static int xfrm_notify_policy_flush(const struct km_event *c)
 
 	nlmsg_end(skb, nlh);
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);
 
 out_free_skb:
 	kfree_skb(skb);
@@ -2911,7 +2925,7 @@ static int xfrm_send_report(struct net *net, u8 proto,
 	if (build_report(skb, proto, sel, addr) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_REPORT, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_REPORT);
 }
 
 static inline size_t xfrm_mapping_msgsize(void)
@@ -2963,7 +2977,7 @@ static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
 	if (build_mapping(skb, x, ipaddr, sport) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MAPPING, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MAPPING);
 }
 
 static bool xfrm_is_alive(const struct km_event *c)