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

Pull networking fixes from David Miller:

 1) ping_err() ICMP error handler looks at wrong ICMP header, from Li
    Wei.

 2) TCP socket hash function on ipv6 is too weak, from Eric Dumazet.

 3) netif_set_xps_queue() forgets to drop mutex on errors, fix from
    Alexander Duyck.

 4) sum_frag_mem_limit() can deadlock due to lack of BH disabling, fix
    from Eric Dumazet.

 5) TCP SYN data is miscalculated in tcp_send_syn_data(), because the
    amount of TCP option space was not taken into account properly in
    this code path.  Fix from yuchung Cheng.

 6) MLX4 driver allocates device queues with the wrong size, from Kleber
    Sacilotto.

 7) sock_diag can access past the end of the sock_diag_handlers[] array,
    from Mathias Krause.

 8) vlan_set_encap_proto() makes incorrect assumptions about where
    skb->data points, rework the logic so that it works regardless of
    where skb->data happens to be.  From Jesse Gross.

 9) Fix gianfar build failure with NET_POLL enabled, from Paul
    Gortmaker.

10) Fix Ipv4 ID setting and checksum calculations in GRE driver, from
   Pravin B Shelar.

11) bgmac driver does:

        int i;

        for (i = 0; ...; ...) {
                ...
                for (i = 0; ...; ...) {

    effectively corrupting the outer loop index, use a seperate
    variable for the inner loops.  From Rafał Miłecki.

12) Fix suspend bugs in smsc95xx driver, from Ming Lei.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (35 commits)
  usbnet: smsc95xx: rename FEATURE_AUTOSUSPEND
  usbnet: smsc95xx: fix broken runtime suspend
  usbnet: smsc95xx: fix suspend failure
  bgmac: fix indexing of 2nd level loops
  b43: Fix lockdep splat on module unload
  Revert "ip_gre: propogate target device GSO capability to the tunnel device"
  IP_GRE: Fix GRE_CSUM case.
  VXLAN: Use tunnel_ip_select_ident() for tunnel IP-Identification.
  IP_GRE: Fix IP-Identification.
  net/pasemi: Fix missing coding style
  vmxnet3: fix ethtool ring buffer size setting
  vmxnet3: make local function static
  bnx2x: remove dead code and make local funcs static
  gianfar: fix compile fail for NET_POLL=y due to struct packing
  vlan: adjust vlan_set_encap_proto() for its callers
  sock_diag: Simplify sock_diag_handlers[] handling in __sock_diag_rcv_msg
  sock_diag: Fix out-of-bounds access to sock_diag_handlers[]
  vxlan: remove depends on CONFIG_EXPERIMENTAL
  mlx4_en: fix allocation of CPU affinity reverse-map
  mlx4_en: fix allocation of device tx_cq
  ...

8 files changed, 75 insertions, 45 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 17bc535..18d8b5a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1882,8 +1882,10 @@ int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, u16 index)
 
 		if (!new_dev_maps)
 			new_dev_maps = kzalloc(maps_sz, GFP_KERNEL);
-		if (!new_dev_maps)
+		if (!new_dev_maps) {
+			mutex_unlock(&xps_map_mutex);
 			return -ENOMEM;
+		}
 
 		map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) :
 				 NULL;
diff --git a/net/core/sock.c b/net/core/sock.c
index fe96c5d..b261a79 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -186,8 +186,10 @@ void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg)
 static struct lock_class_key af_family_keys[AF_MAX];
 static struct lock_class_key af_family_slock_keys[AF_MAX];
 
+#if defined(CONFIG_MEMCG_KMEM)
 struct static_key memcg_socket_limit_enabled;
 EXPORT_SYMBOL(memcg_socket_limit_enabled);
+#endif
 
 /*
  * Make lock validator output more readable. (we pre-construct these
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 602cd63..a29e90c 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -97,21 +97,6 @@ void sock_diag_unregister(const struct sock_diag_handler *hnld)
 }
 EXPORT_SYMBOL_GPL(sock_diag_unregister);
 
-static const inline struct sock_diag_handler *sock_diag_lock_handler(int family)
-{
-	if (sock_diag_handlers[family] == NULL)
-		request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
-				NETLINK_SOCK_DIAG, family);
-
-	mutex_lock(&sock_diag_table_mutex);
-	return sock_diag_handlers[family];
-}
-
-static inline void sock_diag_unlock_handler(const struct sock_diag_handler *h)
-{
-	mutex_unlock(&sock_diag_table_mutex);
-}
-
 static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	int err;
@@ -121,12 +106,20 @@ static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (nlmsg_len(nlh) < sizeof(*req))
 		return -EINVAL;
 
-	hndl = sock_diag_lock_handler(req->sdiag_family);
+	if (req->sdiag_family >= AF_MAX)
+		return -EINVAL;
+
+	if (sock_diag_handlers[req->sdiag_family] == NULL)
+		request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
+				NETLINK_SOCK_DIAG, req->sdiag_family);
+
+	mutex_lock(&sock_diag_table_mutex);
+	hndl = sock_diag_handlers[req->sdiag_family];
 	if (hndl == NULL)
 		err = -ENOENT;
 	else
 		err = hndl->dump(skb, nlh);
-	sock_diag_unlock_handler(hndl);
+	mutex_unlock(&sock_diag_table_mutex);
 
 	return err;
 }
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e225a4e..68f6a94 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -248,8 +248,12 @@ EXPORT_SYMBOL(inet_listen);
 u32 inet_ehash_secret __read_mostly;
 EXPORT_SYMBOL(inet_ehash_secret);
 
+u32 ipv6_hash_secret __read_mostly;
+EXPORT_SYMBOL(ipv6_hash_secret);
+
 /*
- * inet_ehash_secret must be set exactly once
+ * inet_ehash_secret must be set exactly once, and to a non nul value
+ * ipv6_hash_secret must be set exactly once.
  */
 void build_ehash_secret(void)
 {
@@ -259,7 +263,8 @@ void build_ehash_secret(void)
 		get_random_bytes(&rnd, sizeof(rnd));
 	} while (rnd == 0);
 
-	cmpxchg(&inet_ehash_secret, 0, rnd);
+	if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0)
+		get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret));
 }
 EXPORT_SYMBOL(build_ehash_secret);
 
@@ -1327,8 +1332,10 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 			if (skb->next != NULL)
 				iph->frag_off |= htons(IP_MF);
 			offset += (skb->len - skb->mac_len - iph->ihl * 4);
-		} else
-			iph->id = htons(id++);
+		} else  {
+			if (!(iph->frag_off & htons(IP_DF)))
+				iph->id = htons(id++);
+		}
 		iph->tot_len = htons(skb->len - skb->mac_len);
 		iph->check = 0;
 		iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl);
@@ -1572,7 +1579,7 @@ static const struct net_offload udp_offload = {
 
 static const struct net_protocol icmp_protocol = {
 	.handler =	icmp_rcv,
-	.err_handler =	ping_err,
+	.err_handler =	icmp_err,
 	.no_policy =	1,
 	.netns_ok =	1,
 };
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 17ff9fd..3ac5dff 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -934,6 +934,29 @@ error:
 	goto drop;
 }
 
+void icmp_err(struct sk_buff *skb, u32 info)
+{
+	struct iphdr *iph = (struct iphdr *)skb->data;
+	struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2));
+	int type = icmp_hdr(skb)->type;
+	int code = icmp_hdr(skb)->code;
+	struct net *net = dev_net(skb->dev);
+
+	/*
+	 * Use ping_err to handle all icmp errors except those
+	 * triggered by ICMP_ECHOREPLY which sent from kernel.
+	 */
+	if (icmph->type != ICMP_ECHOREPLY) {
+		ping_err(skb, info);
+		return;
+	}
+
+	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
+		ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ICMP, 0);
+	else if (type == ICMP_REDIRECT)
+		ipv4_redirect(skb, net, 0, 0, IPPROTO_ICMP, 0);
+}
+
 /*
  *	This table is the definition of how we handle ICMP.
  */
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 5ef4da7..d0ef0e6 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -735,7 +735,7 @@ drop:
 	return 0;
 }
 
-static struct sk_buff *handle_offloads(struct sk_buff *skb)
+static struct sk_buff *handle_offloads(struct ip_tunnel *tunnel, struct sk_buff *skb)
 {
 	int err;
 
@@ -745,8 +745,12 @@ static struct sk_buff *handle_offloads(struct sk_buff *skb)
 			goto error;
 		skb_shinfo(skb)->gso_type |= SKB_GSO_GRE;
 		return skb;
-	}
-	if (skb->ip_summed != CHECKSUM_PARTIAL)
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL &&
+		   tunnel->parms.o_flags&GRE_CSUM) {
+		err = skb_checksum_help(skb);
+		if (unlikely(err))
+			goto error;
+	} else if (skb->ip_summed != CHECKSUM_PARTIAL)
 		skb->ip_summed = CHECKSUM_NONE;
 
 	return skb;
@@ -776,7 +780,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 	int    err;
 	int    pkt_len;
 
-	skb = handle_offloads(skb);
+	skb = handle_offloads(tunnel, skb);
 	if (IS_ERR(skb)) {
 		dev->stats.tx_dropped++;
 		return NETDEV_TX_OK;
@@ -970,7 +974,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 	iph->daddr		=	fl4.daddr;
 	iph->saddr		=	fl4.saddr;
 	iph->ttl		=	ttl;
-	iph->id			=	0;
+
+	tunnel_ip_select_ident(skb, old_iph, &rt->dst);
 
 	if (ttl == 0) {
 		if (skb->protocol == htons(ETH_P_IP))
@@ -1101,14 +1106,8 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev)
 	tunnel->hlen = addend;
 	/* TCP offload with GRE SEQ is not supported. */
 	if (!(tunnel->parms.o_flags & GRE_SEQ)) {
-		/* device supports enc gso offload*/
-		if (tdev->hw_enc_features & NETIF_F_GRE_GSO) {
-			dev->features		|= NETIF_F_TSO;
-			dev->hw_features	|= NETIF_F_TSO;
-		} else {
-			dev->features		|= NETIF_F_GSO_SOFTWARE;
-			dev->hw_features	|= NETIF_F_GSO_SOFTWARE;
-		}
+		dev->features		|= NETIF_F_GSO_SOFTWARE;
+		dev->hw_features	|= NETIF_F_GSO_SOFTWARE;
 	}
 
 	return mtu;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 55c4ee1..2e91006 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -322,8 +322,8 @@ void ping_err(struct sk_buff *skb, u32 info)
 	struct iphdr *iph = (struct iphdr *)skb->data;
 	struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2));
 	struct inet_sock *inet_sock;
-	int type = icmph->type;
-	int code = icmph->code;
+	int type = icmp_hdr(skb)->type;
+	int code = icmp_hdr(skb)->code;
 	struct net *net = dev_net(skb->dev);
 	struct sock *sk;
 	int harderr;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index fd0cea1..e2b4461 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1351,8 +1351,8 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 	return 0;
 }
 
-/* Calculate MSS. Not accounting for SACKs here.  */
-int tcp_mtu_to_mss(struct sock *sk, int pmtu)
+/* Calculate MSS not accounting any TCP options.  */
+static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1381,13 +1381,17 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu)
 	/* Then reserve room for full set of TCP options and 8 bytes of data */
 	if (mss_now < 48)
 		mss_now = 48;
-
-	/* Now subtract TCP options size, not including SACKs */
-	mss_now -= tp->tcp_header_len - sizeof(struct tcphdr);
-
 	return mss_now;
 }
 
+/* Calculate MSS. Not accounting for SACKs here.  */
+int tcp_mtu_to_mss(struct sock *sk, int pmtu)
+{
+	/* Subtract TCP options size, not including SACKs */
+	return __tcp_mtu_to_mss(sk, pmtu) -
+	       (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr));
+}
+
 /* Inverse of above */
 int tcp_mss_to_mtu(struct sock *sk, int mss)
 {
@@ -2930,7 +2934,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	 */
 	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->rx_opt.mss_clamp)
 		tp->rx_opt.mss_clamp = tp->rx_opt.user_mss;
-	space = tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
+	space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
 		MAX_TCP_OPTION_SPACE;
 
 	syn_data = skb_copy_expand(syn, skb_headroom(syn), space,