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

Pull networking fixes from David Miller:

 1) nft_compat accidently truncates ethernet protocol to 8-bits, from
    Arturo Borrero.

 2) Memory leak in ip_vs_proc_conn(), from Julian Anastasov.

 3) Don't allow the space required for nftables rules to exceed the
    maximum value representable in the dlen field.  From Patrick
    McHardy.

 4) bcm63xx_enet can accidently leave interrupts permanently disabled
    due to errors in the NAPI polling exit logic.  Fix from Nicolas
    Schichan.

 5) Fix OOPSes triggerable by the ping protocol module, due to missing
    address family validations etc.  From Lorenzo Colitti.

 6) Don't use RCU locking in sleepable context in team driver, from Jiri
    Pirko.

 7) xen-netback miscalculates statistic offset pointers when reporting
    the stats to userspace.  From David Vrabel.

 8) Fix a leak of up to 256 pages per VIF destroy in xen-netaback, also
    from David Vrabel.

 9) ip_check_defrag() cannot assume that skb_network_offset(),
    particularly when it is used by the AF_PACKET fanout defrag code.
    From Alexander Drozdov.

10) gianfar driver doesn't query OF node names properly when trying to
    determine the number of hw queues available.  Fix it to explicitly
    check for OF nodes named queue-group.  From Tobias Waldekranz.

11) MID field in macb driver should be 12 bits, not 16.  From Punnaiah
    Choudary Kalluri.

12) Fix unintentional regression in traceroute due to timestamp socket
    option changes.  Empty ICMP payloads should be allowed in
    non-timestamp cases.  From Willem de Bruijn.

13) When devices are unregistered, we have to get rid of AF_PACKET
    multicast list entries that point to it via ifindex.  Fix from
    Francesco Ruggeri.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (38 commits)
  tipc: fix bug in link failover handling
  net: delete stale packet_mclist entries
  net: macb: constify macb configuration data
  MAINTAINERS: add Marc Kleine-Budde as co maintainer for CAN networking layer
  MAINTAINERS: linux-can moved to github
  can: kvaser_usb: Read all messages in a bulk-in URB buffer
  can: kvaser_usb: Avoid double free on URB submission failures
  can: peak_usb: fix missing ctrlmode_ init for every dev
  can: add missing initialisations in CAN related skbuffs
  ip: fix error queue empty skb handling
  bgmac: Clean warning messages
  tcp: align tcp_xmit_size_goal() on tcp_tso_autosize()
  net: fec: fix unbalanced clk disable on driver unbind
  net: macb: Correct the MID field length value
  net: gianfar: correctly determine the number of queue groups
  ipv4: ip_check_defrag should not assume that skb_network_offset is zero
  net: bcmgenet: properly disable password matching
  net: eth: xgene: fix booting with devicetree
  bnx2x: Force fundamental reset for EEH recovery
  xen-netback: refactor xenvif_handle_frag_list()
  ...

4 files changed, 43 insertions, 23 deletions

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 2c8d98e728c0..145a50c4d566 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -659,27 +659,30 @@ EXPORT_SYMBOL(ip_defrag);
 struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
 {
 	struct iphdr iph;
+	int netoff;
 	u32 len;
 
 	if (skb->protocol != htons(ETH_P_IP))
 		return skb;
 
-	if (skb_copy_bits(skb, 0, &iph, sizeof(iph)) < 0)
+	netoff = skb_network_offset(skb);
+
+	if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0)
 		return skb;
 
 	if (iph.ihl < 5 || iph.version != 4)
 		return skb;
 
 	len = ntohs(iph.tot_len);
-	if (skb->len < len || len < (iph.ihl * 4))
+	if (skb->len < netoff + len || len < (iph.ihl * 4))
 		return skb;
 
 	if (ip_is_fragment(&iph)) {
 		skb = skb_share_check(skb, GFP_ATOMIC);
 		if (skb) {
-			if (!pskb_may_pull(skb, iph.ihl*4))
+			if (!pskb_may_pull(skb, netoff + iph.ihl * 4))
 				return skb;
-			if (pskb_trim_rcsum(skb, len))
+			if (pskb_trim_rcsum(skb, netoff + len))
 				return skb;
 			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
 			if (ip_defrag(skb, user))
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 31d8c71986b4..5cd99271d3a6 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -432,17 +432,32 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
 		kfree_skb(skb);
 }
 
-static bool ipv4_pktinfo_prepare_errqueue(const struct sock *sk,
-					  const struct sk_buff *skb,
-					  int ee_origin)
+/* IPv4 supports cmsg on all imcp errors and some timestamps
+ *
+ * Timestamp code paths do not initialize the fields expected by cmsg:
+ * the PKTINFO fields in skb->cb[]. Fill those in here.
+ */
+static bool ipv4_datagram_support_cmsg(const struct sock *sk,
+				       struct sk_buff *skb,
+				       int ee_origin)
 {
-	struct in_pktinfo *info = PKTINFO_SKB_CB(skb);
+	struct in_pktinfo *info;
+
+	if (ee_origin == SO_EE_ORIGIN_ICMP)
+		return true;
 
-	if ((ee_origin != SO_EE_ORIGIN_TIMESTAMPING) ||
-	    (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
+	if (ee_origin == SO_EE_ORIGIN_LOCAL)
+		return false;
+
+	/* Support IP_PKTINFO on tstamp packets if requested, to correlate
+	 * timestamp with egress dev. Not possible for packets without dev
+	 * or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
+	 */
+	if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
 	    (!skb->dev))
 		return false;
 
+	info = PKTINFO_SKB_CB(skb);
 	info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
 	info->ipi_ifindex = skb->dev->ifindex;
 	return true;
@@ -483,7 +498,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin && skb->len) {
+	if (sin && serr->port) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) +
 						   serr->addr_offset);
@@ -496,9 +511,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	sin = &errhdr.offender;
 	memset(sin, 0, sizeof(*sin));
 
-	if (skb->len &&
-	    (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
-	     ipv4_pktinfo_prepare_errqueue(sk, skb, serr->ee.ee_origin))) {
+	if (ipv4_datagram_support_cmsg(sk, skb, serr->ee.ee_origin)) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		if (inet_sk(sk)->cmsg_flags)
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index e9f66e1cda50..208d5439e59b 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -259,6 +259,9 @@ int ping_init_sock(struct sock *sk)
 	kgid_t low, high;
 	int ret = 0;
 
+	if (sk->sk_family == AF_INET6)
+		sk->sk_ipv6only = 1;
+
 	inet_get_ping_group_range_net(net, &low, &high);
 	if (gid_lte(low, group) && gid_lte(group, high))
 		return 0;
@@ -305,6 +308,11 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 		if (addr_len < sizeof(*addr))
 			return -EINVAL;
 
+		if (addr->sin_family != AF_INET &&
+		    !(addr->sin_family == AF_UNSPEC &&
+		      addr->sin_addr.s_addr == htonl(INADDR_ANY)))
+			return -EAFNOSUPPORT;
+
 		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
 			 sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));
 
@@ -330,7 +338,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 			return -EINVAL;
 
 		if (addr->sin6_family != AF_INET6)
-			return -EINVAL;
+			return -EAFNOSUPPORT;
 
 		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n",
 			 sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port));
@@ -716,7 +724,7 @@ static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 		if (msg->msg_namelen < sizeof(*usin))
 			return -EINVAL;
 		if (usin->sin_family != AF_INET)
-			return -EINVAL;
+			return -EAFNOSUPPORT;
 		daddr = usin->sin_addr.s_addr;
 		/* no remote port */
 	} else {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9d72a0fcd928..995a2259bcfc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -835,17 +835,13 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
 				       int large_allowed)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 new_size_goal, size_goal, hlen;
+	u32 new_size_goal, size_goal;
 
 	if (!large_allowed || !sk_can_gso(sk))
 		return mss_now;
 
-	/* Maybe we should/could use sk->sk_prot->max_header here ? */
-	hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
-	       inet_csk(sk)->icsk_ext_hdr_len +
-	       tp->tcp_header_len;
-
-	new_size_goal = sk->sk_gso_max_size - 1 - hlen;
+	/* Note : tcp_tso_autosize() will eventually split this later */
+	new_size_goal = sk->sk_gso_max_size - 1 - MAX_TCP_HEADER;
 	new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal);
 
 	/* We try hard to avoid divides here */