Merge tag 'v3.2.20' into v3.2-rt

This is the 3.2.20 stable release

16 files changed, 122 insertions, 122 deletions

diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index bc2528624583..0cccca85284e 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -156,7 +156,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
 		skb = __vlan_hwaccel_put_tag(skb, vlan_tci);
 	}
 
-	skb_set_dev(skb, vlan_dev_info(dev)->real_dev);
+	skb->dev = vlan_dev_info(dev)->real_dev;
 	len = skb->len;
 	ret = dev_queue_xmit(skb);
 
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index ee64287f1290..e221f88ebb8d 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -47,6 +47,7 @@ int br_dev_queue_push_xmit(struct sk_buff *skb)
 		kfree_skb(skb);
 	} else {
 		skb_push(skb, ETH_HLEN);
+		br_drop_fake_rtable(skb);
 		dev_queue_xmit(skb);
 	}
 
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index fa8b8f763580..577ea5df8282 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -147,7 +147,7 @@ void br_netfilter_rtable_init(struct net_bridge *br)
 	rt->dst.dev = br->dev;
 	rt->dst.path = &rt->dst;
 	dst_init_metrics(&rt->dst, br_dst_default_metrics, true);
-	rt->dst.flags	= DST_NOXFRM | DST_NOPEER;
+	rt->dst.flags	= DST_NOXFRM | DST_NOPEER | DST_FAKE_RTABLE;
 	rt->dst.ops = &fake_dst_ops;
 }
 
@@ -687,11 +687,7 @@ static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb,
 				   const struct net_device *out,
 				   int (*okfn)(struct sk_buff *))
 {
-	struct rtable *rt = skb_rtable(skb);
-
-	if (rt && rt == bridge_parent_rtable(in))
-		skb_dst_drop(skb);
-
+	br_drop_fake_rtable(skb);
 	return NF_ACCEPT;
 }
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 578a74dbe084..9085ef7bd419 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1607,10 +1607,14 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
-	skb_set_dev(skb, dev);
+	skb->dev = dev;
+	skb_dst_drop(skb);
 	skb->tstamp.tv64 = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = eth_type_trans(skb, dev);
+	skb->mark = 0;
+	secpath_reset(skb);
+	nf_reset(skb);
 	return netif_rx(skb);
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
@@ -1867,36 +1871,6 @@ void netif_device_attach(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_device_attach);
 
-/**
- * skb_dev_set -- assign a new device to a buffer
- * @skb: buffer for the new device
- * @dev: network device
- *
- * If an skb is owned by a device already, we have to reset
- * all data private to the namespace a device belongs to
- * before assigning it a new device.
- */
-#ifdef CONFIG_NET_NS
-void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
-{
-	skb_dst_drop(skb);
-	if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) {
-		secpath_reset(skb);
-		nf_reset(skb);
-		skb_init_secmark(skb);
-		skb->mark = 0;
-		skb->priority = 0;
-		skb->nf_trace = 0;
-		skb->ipvs_property = 0;
-#ifdef CONFIG_NET_SCHED
-		skb->tc_index = 0;
-#endif
-	}
-	skb->dev = dev;
-}
-EXPORT_SYMBOL(skb_set_dev);
-#endif /* CONFIG_NET_NS */
-
 /*
  * Invalidate hardware checksum when packet is to be mangled, and
  * complete checksum manually on outgoing path.
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index a5b413416da3..530787bc1990 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -457,28 +457,22 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu)
 	struct esp_data *esp = x->data;
 	u32 blksize = ALIGN(crypto_aead_blocksize(esp->aead), 4);
 	u32 align = max_t(u32, blksize, esp->padlen);
-	u32 rem;
-
-	mtu -= x->props.header_len + crypto_aead_authsize(esp->aead);
-	rem = mtu & (align - 1);
-	mtu &= ~(align - 1);
+	unsigned int net_adj;
 
 	switch (x->props.mode) {
-	case XFRM_MODE_TUNNEL:
-		break;
-	default:
 	case XFRM_MODE_TRANSPORT:
-		/* The worst case */
-		mtu -= blksize - 4;
-		mtu += min_t(u32, blksize - 4, rem);
-		break;
 	case XFRM_MODE_BEET:
-		/* The worst case. */
-		mtu += min_t(u32, IPV4_BEET_PHMAXLEN, rem);
+		net_adj = sizeof(struct iphdr);
 		break;
+	case XFRM_MODE_TUNNEL:
+		net_adj = 0;
+		break;
+	default:
+		BUG();
 	}
 
-	return mtu - 2;
+	return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) -
+		 net_adj) & ~(align - 1)) + (net_adj - 2);
 }
 
 static void esp4_err(struct sk_buff *skb, u32 info)
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 80106d89d548..d01f9c658dec 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -146,6 +146,12 @@ static void free_fib_info_rcu(struct rcu_head *head)
 {
 	struct fib_info *fi = container_of(head, struct fib_info, rcu);
 
+	change_nexthops(fi) {
+		if (nexthop_nh->nh_dev)
+			dev_put(nexthop_nh->nh_dev);
+	} endfor_nexthops(fi);
+
+	release_net(fi->fib_net);
 	if (fi->fib_metrics != (u32 *) dst_default_metrics)
 		kfree(fi->fib_metrics);
 	kfree(fi);
@@ -157,13 +163,7 @@ void free_fib_info(struct fib_info *fi)
 		pr_warning("Freeing alive fib_info %p\n", fi);
 		return;
 	}
-	change_nexthops(fi) {
-		if (nexthop_nh->nh_dev)
-			dev_put(nexthop_nh->nh_dev);
-		nexthop_nh->nh_dev = NULL;
-	} endfor_nexthops(fi);
 	fib_info_cnt--;
-	release_net(fi->fib_net);
 	call_rcu(&fi->rcu, free_fib_info_rcu);
 }
 
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 3ce23f9d9363..cd2d639541bc 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1372,6 +1372,8 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
 
 			if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
 				continue;
+			if (fi->fib_dead)
+				continue;
 			if (fa->fa_info->fib_scope < flp->flowi4_scope)
 				continue;
 			fib_alias_accessed(fa);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 1ac7938dd9ec..65dd5433f08b 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -411,19 +411,15 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu)
 	struct esp_data *esp = x->data;
 	u32 blksize = ALIGN(crypto_aead_blocksize(esp->aead), 4);
 	u32 align = max_t(u32, blksize, esp->padlen);
-	u32 rem;
+	unsigned int net_adj;
 
-	mtu -= x->props.header_len + crypto_aead_authsize(esp->aead);
-	rem = mtu & (align - 1);
-	mtu &= ~(align - 1);
-
-	if (x->props.mode != XFRM_MODE_TUNNEL) {
-		u32 padsize = ((blksize - 1) & 7) + 1;
-		mtu -= blksize - padsize;
-		mtu += min_t(u32, blksize - padsize, rem);
-	}
+	if (x->props.mode != XFRM_MODE_TUNNEL)
+		net_adj = sizeof(struct ipv6hdr);
+	else
+		net_adj = 0;
 
-	return mtu - 2;
+	return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) -
+		 net_adj) & ~(align - 1)) + (net_adj - 2);
 }
 
 static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f7f07e2e7c1a..ae98e09ca8e7 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1178,6 +1178,29 @@ static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src,
 	return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
 }
 
+static void ip6_append_data_mtu(int *mtu,
+				int *maxfraglen,
+				unsigned int fragheaderlen,
+				struct sk_buff *skb,
+				struct rt6_info *rt)
+{
+	if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
+		if (skb == NULL) {
+			/* first fragment, reserve header_len */
+			*mtu = *mtu - rt->dst.header_len;
+
+		} else {
+			/*
+			 * this fragment is not first, the headers
+			 * space is regarded as data space.
+			 */
+			*mtu = dst_mtu(rt->dst.path);
+		}
+		*maxfraglen = ((*mtu - fragheaderlen) & ~7)
+			      + fragheaderlen - sizeof(struct frag_hdr);
+	}
+}
+
 int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	int offset, int len, int odd, struct sk_buff *skb),
 	void *from, int length, int transhdrlen,
@@ -1187,7 +1210,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct inet_cork *cork;
-	struct sk_buff *skb;
+	struct sk_buff *skb, *skb_prev = NULL;
 	unsigned int maxfraglen, fragheaderlen;
 	int exthdrlen;
 	int dst_exthdrlen;
@@ -1245,8 +1268,12 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		inet->cork.fl.u.ip6 = *fl6;
 		np->cork.hop_limit = hlimit;
 		np->cork.tclass = tclass;
-		mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
-		      rt->dst.dev->mtu : dst_mtu(&rt->dst);
+		if (rt->dst.flags & DST_XFRM_TUNNEL)
+			mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+			      rt->dst.dev->mtu : dst_mtu(&rt->dst);
+		else
+			mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+			      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
 		if (np->frag_size < mtu) {
 			if (np->frag_size)
 				mtu = np->frag_size;
@@ -1342,25 +1369,27 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 			unsigned int fraglen;
 			unsigned int fraggap;
 			unsigned int alloclen;
-			struct sk_buff *skb_prev;
 alloc_new_skb:
-			skb_prev = skb;
-
 			/* There's no room in the current skb */
-			if (skb_prev)
-				fraggap = skb_prev->len - maxfraglen;
+			if (skb)
+				fraggap = skb->len - maxfraglen;
 			else
 				fraggap = 0;
+			/* update mtu and maxfraglen if necessary */
+			if (skb == NULL || skb_prev == NULL)
+				ip6_append_data_mtu(&mtu, &maxfraglen,
+						    fragheaderlen, skb, rt);
+
+			skb_prev = skb;
 
 			/*
 			 * If remaining data exceeds the mtu,
 			 * we know we need more fragment(s).
 			 */
 			datalen = length + fraggap;
-			if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
-				datalen = maxfraglen - fragheaderlen;
 
-			fraglen = datalen + fragheaderlen;
+			if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
+				datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
 			if ((flags & MSG_MORE) &&
 			    !(rt->dst.dev->features&NETIF_F_SG))
 				alloclen = mtu;
@@ -1369,13 +1398,16 @@ alloc_new_skb:
 
 			alloclen += dst_exthdrlen;
 
-			/*
-			 * The last fragment gets additional space at tail.
-			 * Note: we overallocate on fragments with MSG_MODE
-			 * because we have no idea if we're the last one.
-			 */
-			if (datalen == length + fraggap)
-				alloclen += rt->dst.trailer_len;
+			if (datalen != length + fraggap) {
+				/*
+				 * this is not the last fragment, the trailer
+				 * space is regarded as data space.
+				 */
+				datalen += rt->dst.trailer_len;
+			}
+
+			alloclen += rt->dst.trailer_len;
+			fraglen = datalen + fragheaderlen;
 
 			/*
 			 * We just reserve space for fragment header.
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 2a2a3e7f5f83..2fbbe1ffd481 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -251,9 +251,16 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *) uaddr;
-	int ret = -EINVAL;
+	int ret;
 	int chk_addr_ret;
 
+	if (!sock_flag(sk, SOCK_ZAPPED))
+		return -EINVAL;
+	if (addr_len < sizeof(struct sockaddr_l2tpip))
+		return -EINVAL;
+	if (addr->l2tp_family != AF_INET)
+		return -EINVAL;
+
 	ret = -EADDRINUSE;
 	read_lock_bh(&l2tp_ip_lock);
 	if (__l2tp_ip_bind_lookup(&init_net, addr->l2tp_addr.s_addr, sk->sk_bound_dev_if, addr->l2tp_conn_id))
@@ -283,6 +290,8 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	sk_del_node_init(sk);
 	write_unlock_bh(&l2tp_ip_lock);
 	ret = 0;
+	sock_reset_flag(sk, SOCK_ZAPPED);
+
 out:
 	release_sock(sk);
 
@@ -303,13 +312,14 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 	__be32 saddr;
 	int oif, rc;
 
-	rc = -EINVAL;
+	if (sock_flag(sk, SOCK_ZAPPED)) /* Must bind first - autobinding does not work */
+		return -EINVAL;
+
 	if (addr_len < sizeof(*lsa))
-		goto out;
+		return -EINVAL;
 
-	rc = -EAFNOSUPPORT;
 	if (lsa->l2tp_family != AF_INET)
-		goto out;
+		return -EAFNOSUPPORT;
 
 	lock_sock(sk);
 
@@ -363,6 +373,14 @@ out:
 	return rc;
 }
 
+static int l2tp_ip_disconnect(struct sock *sk, int flags)
+{
+	if (sock_flag(sk, SOCK_ZAPPED))
+		return 0;
+
+	return udp_disconnect(sk, flags);
+}
+
 static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr,
 			   int *uaddr_len, int peer)
 {
@@ -598,7 +616,7 @@ static struct proto l2tp_ip_prot = {
 	.close		   = l2tp_ip_close,
 	.bind		   = l2tp_ip_bind,
 	.connect	   = l2tp_ip_connect,
-	.disconnect	   = udp_disconnect,
+	.disconnect	   = l2tp_ip_disconnect,
 	.ioctl		   = udp_ioctl,
 	.destroy	   = l2tp_ip_destroy_sock,
 	.setsockopt	   = ip_setsockopt,
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index d5230ecc784d..7095ae599d95 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1111,6 +1111,12 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		}
 	}
 
+	/* add back keys */
+	list_for_each_entry(sdata, &local->interfaces, list)
+		if (ieee80211_sdata_running(sdata))
+			ieee80211_enable_keys(sdata);
+
+ wake_up:
 	/*
 	 * Clear the WLAN_STA_BLOCK_BA flag so new aggregation
 	 * sessions can be established after a resume.
@@ -1132,12 +1138,6 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		mutex_unlock(&local->sta_mtx);
 	}
 
-	/* add back keys */
-	list_for_each_entry(sdata, &local->interfaces, list)
-		if (ieee80211_sdata_running(sdata))
-			ieee80211_enable_keys(sdata);
-
- wake_up:
 	ieee80211_wake_queues_by_reason(hw,
 			IEEE80211_QUEUE_STOP_REASON_SUSPEND);
 
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 817174eb5f41..8fc4dcd294ab 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -377,9 +377,7 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	 */
 	skb_set_owner_w(nskb, sk);
 
-	/* The 'obsolete' field of dst is set to 2 when a dst is freed. */
-	if (!dst || (dst->obsolete > 1)) {
-		dst_release(dst);
+	if (!sctp_transport_dst_check(tp)) {
 		sctp_transport_route(tp, NULL, sctp_sk(sk));
 		if (asoc && (asoc->param_flags & SPP_PMTUD_ENABLE)) {
 			sctp_assoc_sync_pmtu(asoc);
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 394c57ca2f54..8da4481ed30a 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -226,23 +226,6 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk)
 		transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
 }
 
-/* this is a complete rip-off from __sk_dst_check
- * the cookie is always 0 since this is how it's used in the
- * pmtu code
- */
-static struct dst_entry *sctp_transport_dst_check(struct sctp_transport *t)
-{
-	struct dst_entry *dst = t->dst;
-
-	if (dst && dst->obsolete && dst->ops->check(dst, 0) == NULL) {
-		dst_release(t->dst);
-		t->dst = NULL;
-		return NULL;
-	}
-
-	return dst;
-}
-
 void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
 {
 	struct dst_entry *dst;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index f0268ea7e711..b2250da4b598 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -959,6 +959,8 @@ call_reserveresult(struct rpc_task *task)
 	}
 
 	switch (status) {
+	case -ENOMEM:
+		rpc_delay(task, HZ >> 2);
 	case -EAGAIN:	/* woken up; retry */
 		task->tk_action = call_reserve;
 		return;
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index c64c0ef519b5..3ac978989dab 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -977,15 +977,16 @@ static void xprt_alloc_slot(struct rpc_task *task)
 		goto out_init_req;
 	switch (PTR_ERR(req)) {
 	case -ENOMEM:
-		rpc_delay(task, HZ >> 2);
 		dprintk("RPC:       dynamic allocation of request slot "
 				"failed! Retrying\n");
+		task->tk_status = -ENOMEM;
 		break;
 	case -EAGAIN:
 		rpc_sleep_on(&xprt->backlog, task, NULL);
 		dprintk("RPC:       waiting for request slot\n");
+	default:
+		task->tk_status = -EAGAIN;
 	}
-	task->tk_status = -EAGAIN;
 	return;
 out_init_req:
 	task->tk_status = 0;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 9049a5caeb25..01740344c112 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1919,6 +1919,9 @@ no_transform:
 	}
 ok:
 	xfrm_pols_put(pols, drop_pols);
+	if (dst && dst->xfrm &&
+	    dst->xfrm->props.mode == XFRM_MODE_TUNNEL)
+		dst->flags |= DST_XFRM_TUNNEL;
 	return dst;
 
 nopol: