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

Pull networking updates from David Miller:
 "Here is a pile of bug fixes that accumulated while I was in Europe"

 1) In fixing kernel leaks to userspace during copying of socket
    addresses, we broke a case that used to work, namely the user
    providing a buffer larger than the in-kernel generic socket address
    structure.  This broke Ruby amongst other things.  Fix from Dan
    Carpenter.

 2) Fix regression added by byte queue limit support in 8139cp driver,
    from Yang Yingliang.

 3) The addition of MSG_SENDPAGE_NOTLAST buggered up a few sendpage
    implementations, they should just treat it the same as MSG_MORE.
    Fix from Richard Weinberger and Shawn Landden.

 4) Handle icmpv4 errors received on ipv6 SIT tunnels correctly, from
    Oussama Ghorbel.  In particular we should send an ICMPv6 unreachable
    in such situations.

 5) Fix some regressions in the recent genetlink fixes, in particular
    get the pmcraid driver to use the new safer interfaces correctly.
    From Johannes Berg.

 6) macvtap was converted to use a per-cpu set of statistics, but some
    code was still bumping tx_dropped elsewhere.  From Jason Wang.

 7) Fix build failure of xen-netback due to missing include on some
    architectures, from Andy Whitecroft.

 8) macvtap double counts received packets in statistics, fix from Vlad
    Yasevich.

 9) Fix various cases of using *_STATS_BH() when *_STATS() is more
    appropriate.  From Eric Dumazet and Hannes Frederic Sowa.

10) Pktgen ipsec mode doesn't update the ipv4 header length and checksum
    properly after encapsulation.  Fix from Fan Du.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (61 commits)
  net/mlx4_en: Remove selftest TX queues empty condition
  {pktgen, xfrm} Update IPv4 header total len and checksum after tranformation
  virtio_net: make all RX paths handle erors consistently
  virtio_net: fix error handling for mergeable buffers
  virtio_net: Fixed a trivial typo (fitler --> filter)
  netem: fix gemodel loss generator
  netem: fix loss 4 state model
  netem: missing break in ge loss generator
  net/hsr: Support iproute print_opt ('ip -details ...')
  net/hsr: Very small fix of comment style.
  MAINTAINERS: Added net/hsr/ maintainer
  ipv6: fix possible seqlock deadlock in ip6_finish_output2
  ixgbe: Make ixgbe_identify_qsfp_module_generic static
  ixgbe: turn NETIF_F_HW_L2FW_DOFFLOAD off by default
  ixgbe: ixgbe_fwd_ring_down needs to be static
  e1000: fix possible reset_task running after adapter down
  e1000: fix lockdep warning in e1000_reset_task
  e1000: prevent oops when adapter is being closed and reset simultaneously
  igb: Fixed Wake On LAN support
  inet: fix possible seqlock deadlocks
  ...

8 files changed, 70 insertions, 39 deletions

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index a454b0ff57c7..8dfe1f4d3c1a 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -318,7 +318,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
 /*
  *	Handle MSG_ERRQUEUE
  */
-int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
+int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sock_exterr_skb *serr;
@@ -369,6 +369,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
 					       &sin->sin6_addr);
 			sin->sin6_scope_id = 0;
 		}
+		*addr_len = sizeof(*sin);
 	}
 
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
@@ -377,6 +378,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
 	if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
+		sin->sin6_port = 0;
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			sin->sin6_addr = ipv6_hdr(skb)->saddr;
 			if (np->rxopt.all)
@@ -423,7 +425,8 @@ EXPORT_SYMBOL_GPL(ipv6_recv_error);
 /*
  *	Handle IPV6_RECVPATHMTU
  */
-int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
+int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
+		     int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sk_buff *skb;
@@ -457,6 +460,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
 		sin->sin6_port = 0;
 		sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
 		sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr;
+		*addr_len = sizeof(*sin);
 	}
 
 	put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 59df872e2f4d..4acdb63495db 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -116,8 +116,8 @@ static int ip6_finish_output2(struct sk_buff *skb)
 	}
 	rcu_read_unlock_bh();
 
-	IP6_INC_STATS_BH(dev_net(dst->dev),
-			 ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+	IP6_INC_STATS(dev_net(dst->dev),
+		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 	kfree_skb(skb);
 	return -EINVAL;
 }
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 8815e31a87fe..a83243c3d656 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -57,7 +57,8 @@ static struct inet_protosw pingv6_protosw = {
 
 
 /* Compatibility glue so we can support IPv6 when it's compiled as a module */
-static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
+static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
+				 int *addr_len)
 {
 	return -EAFNOSUPPORT;
 }
diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c
index 22d1bd4670da..e048cf1bb6a2 100644
--- a/net/ipv6/protocol.c
+++ b/net/ipv6/protocol.c
@@ -36,10 +36,6 @@ int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol
 }
 EXPORT_SYMBOL(inet6_add_protocol);
 
-/*
- *	Remove a protocol from the hash tables.
- */
-
 int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol)
 {
 	int ret;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index e24ff1df0401..7fb4e14c467f 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -466,10 +466,10 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 		return -EOPNOTSUPP;
 
 	if (flags & MSG_ERRQUEUE)
-		return ipv6_recv_error(sk, msg, len);
+		return ipv6_recv_error(sk, msg, len, addr_len);
 
 	if (np->rxpmtu && np->rxopt.bits.rxpmtu)
-		return ipv6_recv_rxpmtu(sk, msg, len);
+		return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 1b4a4a953675..366fbba3359a 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -478,14 +478,44 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
 	dev_put(dev);
 }
 
+/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
+ * if sufficient data bytes are available
+ */
+static int ipip6_err_gen_icmpv6_unreach(struct sk_buff *skb)
+{
+	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	struct rt6_info *rt;
+	struct sk_buff *skb2;
+
+	if (!pskb_may_pull(skb, iph->ihl * 4 + sizeof(struct ipv6hdr) + 8))
+		return 1;
+
+	skb2 = skb_clone(skb, GFP_ATOMIC);
+
+	if (!skb2)
+		return 1;
+
+	skb_dst_drop(skb2);
+	skb_pull(skb2, iph->ihl * 4);
+	skb_reset_network_header(skb2);
+
+	rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0);
+
+	if (rt && rt->dst.dev)
+		skb2->dev = rt->dst.dev;
+
+	icmpv6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
+
+	if (rt)
+		ip6_rt_put(rt);
+
+	kfree_skb(skb2);
+
+	return 0;
+}
 
 static int ipip6_err(struct sk_buff *skb, u32 info)
 {
-
-/* All the routers (except for Linux) return only
-   8 bytes of packet payload. It means, that precise relaying of
-   ICMP in the real Internet is absolutely infeasible.
- */
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
@@ -500,7 +530,6 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 	case ICMP_DEST_UNREACH:
 		switch (code) {
 		case ICMP_SR_FAILED:
-		case ICMP_PORT_UNREACH:
 			/* Impossible event. */
 			return 0;
 		default:
@@ -545,6 +574,9 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 		goto out;
 
 	err = 0;
+	if (!ipip6_err_gen_icmpv6_unreach(skb))
+		goto out;
+
 	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
 		goto out;
 
@@ -919,7 +951,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		if (!new_skb) {
 			ip_rt_put(rt);
 			dev->stats.tx_dropped++;
-			dev_kfree_skb(skb);
+			kfree_skb(skb);
 			return NETDEV_TX_OK;
 		}
 		if (skb->sk)
@@ -945,7 +977,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 tx_error_icmp:
 	dst_link_failure(skb);
 tx_error:
-	dev_kfree_skb(skb);
+	kfree_skb(skb);
 out:
 	dev->stats.tx_errors++;
 	return NETDEV_TX_OK;
@@ -985,7 +1017,7 @@ static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb,
 
 tx_err:
 	dev->stats.tx_errors++;
-	dev_kfree_skb(skb);
+	kfree_skb(skb);
 	return NETDEV_TX_OK;
 
 }
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index c1097c798900..6d18157dc32c 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -37,34 +37,32 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
 {
 	const struct ipv6hdr *iph = skb_gro_network_header(skb);
 	__wsum wsum;
-	__sum16 sum;
+
+	/* Don't bother verifying checksum if we're going to flush anyway. */
+	if (NAPI_GRO_CB(skb)->flush)
+		goto skip_csum;
+
+	wsum = skb->csum;
 
 	switch (skb->ip_summed) {
+	case CHECKSUM_NONE:
+		wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb),
+				    wsum);
+
+		/* fall through */
+
 	case CHECKSUM_COMPLETE:
 		if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr,
-				  skb->csum)) {
+				  wsum)) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 			break;
 		}
-flush:
+
 		NAPI_GRO_CB(skb)->flush = 1;
 		return NULL;
-
-	case CHECKSUM_NONE:
-		wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr,
-						    skb_gro_len(skb),
-						    IPPROTO_TCP, 0));
-		sum = csum_fold(skb_checksum(skb,
-					     skb_gro_offset(skb),
-					     skb_gro_len(skb),
-					     wsum));
-		if (sum)
-			goto flush;
-
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		break;
 	}
 
+skip_csum:
 	return tcp_gro_receive(head, skb);
 }
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 81eb8cf8389b..bcd5699313c3 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -393,10 +393,10 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	bool slow;
 
 	if (flags & MSG_ERRQUEUE)
-		return ipv6_recv_error(sk, msg, len);
+		return ipv6_recv_error(sk, msg, len, addr_len);
 
 	if (np->rxpmtu && np->rxopt.bits.rxpmtu)
-		return ipv6_recv_rxpmtu(sk, msg, len);
+		return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
 
 try_again:
 	skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),