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

Pull networking fixes from David Miller:

 1) Stretch ACKs can kill performance with Reno and CUBIC congestion
    control, largely due to LRO and GRO.  Fix from Neal Cardwell.

 2) Fix userland breakage because we accidently emit zero length netlink
    messages from the bridging code.  From Roopa Prabhu.

 3) Carry handling in generic csum_tcpudp_nofold is broken, fix from
    Karl Beldan.

 4) Remove bogus dev_set_net() calls from CAIF driver, from Nicolas
    Dichtel.

 5) Make sure PPP deflation never returns a length greater then the
    output buffer, otherwise we overflow and trigger skb_over_panic().
    Fix from Florian Westphal.

 6) COSA driver needs VIRT_TO_BUS Kconfig dependencies, from Arnd
    Bergmann.

 7) Don't increase route cached MTU on datagram too big ICMPs.  From Li
    Wei.

 8) Fix error path leaks in nf_tables, from Pablo Neira Ayuso.

 9) Fix bitmask handling regression in netlink that broke things like
    acpi userland tools.  From Pablo Neira Ayuso.

10) Wrong header pointer passed to param_type2af() in SCTP code, from
    Saran Maruti Ramanara.

11) Stacked vlans not handled correctly by vlan_get_protocol(), from
    Toshiaki Makita.

12) Add missing DMA memory barrier to xgene driver, from Iyappan
    Subramanian.

13) Fix crash in rate estimators, from Eric Dumazet.

14) We've been adding various workarounds, one after another, for the
    change which added the per-net tcp_sock.  It was meant to reduce
    socket contention but added lots of problems.

    Reduce this instead to a proper per-cpu socket and that rids us of
    all the daemons.

    From Eric Dumazet.

15) Fix memory corruption and OOPS in mlx4 driver, from Jack
    Morgenstein.

16) When we disabled UFO in the virtio_net device, it introduces some
    serious performance regressions.  The orignal problem was IPV6
    fragment ID generation, so fix that properly instead.  From Vlad
    Yasevich.

17) sr9700 driver build breaks on xtensa because it defines macros with
    the same name as those used by the arch code.  Use more unique
    names.  From Chen Gang.

18) Fix endianness in new virio 1.0 mode of the vhost net driver, from
    Michael S Tsirkin.

19) Several sysctls were setting the maxlen attribute incorrectly, from
    Sasha Levin.

20) Don't accept an FQ scheduler quantum of zero, that leads to crashes.
    From Kenneth Klette Jonassen.

21) Fix dumping of non-existing actions in the packet scheduler
    classifier.  From Ignacy Gawędzki.

22) Return the write work_done value when doing TX work in the qlcnic
    driver.

23) ip6gre_err accesses the info field with the wrong endianness, from
    Sabrina Dubroca.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (54 commits)
  sit: fix some __be16/u16 mismatches
  ipv6: fix sparse errors in ip6_make_flowlabel()
  net: remove some sparse warnings
  flow_keys: n_proto type should be __be16
  ip6_gre: fix endianness errors in ip6gre_err
  qlcnic: Fix NAPI poll routine for Tx completion
  amd-xgbe: Set RSS enablement based on hardware features
  amd-xgbe: Adjust for zero-based traffic class count
  cls_api.c: Fix dumping of non-existing actions' stats.
  pkt_sched: fq: avoid hang when quantum 0
  net: rds: use correct size for max unacked packets and bytes
  vhost/net: fix up num_buffers endian-ness
  gianfar: correct the bad expression while writing bit-pattern
  net: usb: sr9700: Use 'SR_' prefix for the common register macros
  Revert "drivers/net: Disable UFO through virtio"
  Revert "drivers/net, ipv6: Select IPv6 fragment idents for virtio UFO packets"
  ipv6: Select fragment id during UFO segmentation if not set.
  xen-netback: stop the guest rx thread after a fatal error
  net/mlx4_core: Fix kernel Oops (mem corruption) when working with more than 80 VFs
  isdn: off by one in connect_res()
  ...

9 files changed, 66 insertions, 31 deletions

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 515a35e2a48..960e666c51e 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -472,27 +472,59 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
 /**
  * vlan_get_protocol - get protocol EtherType.
  * @skb: skbuff to query
+ * @type: first vlan protocol
+ * @depth: buffer to store length of eth and vlan tags in bytes
  *
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
+static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
+					 int *depth)
 {
-	__be16 protocol = 0;
-
-	if (vlan_tx_tag_present(skb) ||
-	     skb->protocol != cpu_to_be16(ETH_P_8021Q))
-		protocol = skb->protocol;
-	else {
-		__be16 proto, *protop;
-		protop = skb_header_pointer(skb, offsetof(struct vlan_ethhdr,
-						h_vlan_encapsulated_proto),
-						sizeof(proto), &proto);
-		if (likely(protop))
-			protocol = *protop;
+	unsigned int vlan_depth = skb->mac_len;
+
+	/* if type 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 (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));
 	}
 
-	return protocol;
+	if (depth)
+		*depth = vlan_depth;
+
+	return type;
+}
+
+/**
+ * vlan_get_protocol - get protocol EtherType.
+ * @skb: skbuff to query
+ *
+ * Returns the EtherType of the packet, regardless of whether it is
+ * vlan encapsulated (normal or hardware accelerated) or not.
+ */
+static inline __be16 vlan_get_protocol(struct sk_buff *skb)
+{
+	return __vlan_get_protocol(skb, skb->protocol, NULL);
 }
 
 static inline void vlan_set_encap_proto(struct sk_buff *skb,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 25c791e295f..5f3a9aa7225 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -97,7 +97,7 @@ enum {
 	MLX4_MAX_NUM_PF		= 16,
 	MLX4_MAX_NUM_VF		= 126,
 	MLX4_MAX_NUM_VF_P_PORT  = 64,
-	MLX4_MFUNC_MAX		= 80,
+	MLX4_MFUNC_MAX		= 128,
 	MLX4_MAX_EQ_NUM		= 1024,
 	MLX4_MFUNC_EQ_NUM	= 4,
 	MLX4_MFUNC_MAX_EQES     = 8,
diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h
index 7ee2df08354..dc8fd81412b 100644
--- a/include/net/flow_keys.h
+++ b/include/net/flow_keys.h
@@ -22,9 +22,9 @@ struct flow_keys {
 		__be32 ports;
 		__be16 port16[2];
 	};
-	u16 thoff;
-	u16 n_proto;
-	u8 ip_proto;
+	u16	thoff;
+	__be16	n_proto;
+	u8	ip_proto;
 };
 
 bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
diff --git a/include/net/ip.h b/include/net/ip.h
index f7cbd703d15..09cf5aebb28 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -181,7 +181,7 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg)
 	return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;
 }
 
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   const struct ip_options *sopt,
 			   __be32 daddr, __be32 saddr,
 			   const struct ip_reply_arg *arg,
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4292929392b..6e416f6d3e3 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -671,6 +671,9 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 	return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
 }
 
+u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst,
+			struct in6_addr *src);
+void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
 void ipv6_proxy_select_ident(struct sk_buff *skb);
 
 int ip6_dst_hoplimit(struct dst_entry *dst);
@@ -708,7 +711,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 					__be32 flowlabel, bool autolabel)
 {
 	if (!flowlabel && (autolabel || net->ipv6.sysctl.auto_flowlabels)) {
-		__be32 hash;
+		u32 hash;
 
 		hash = skb_get_hash(skb);
 
@@ -718,7 +721,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 		 */
 		hash ^= hash >> 12;
 
-		flowlabel = hash & IPV6_FLOWLABEL_MASK;
+		flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
 	}
 
 	return flowlabel;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 3ae969e3acf..9eaaa788458 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -530,6 +530,8 @@ enum nft_chain_type {
 
 int nft_chain_validate_dependency(const struct nft_chain *chain,
 				  enum nft_chain_type type);
+int nft_chain_validate_hooks(const struct nft_chain *chain,
+                             unsigned int hook_flags);
 
 struct nft_stats {
 	u64			bytes;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 24945cefc4f..0ffef1a38ef 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -52,6 +52,7 @@ struct netns_ipv4 {
 	struct inet_peer_base	*peers;
 	struct tcpm_hash_bucket	*tcp_metrics_hash;
 	unsigned int		tcp_metrics_hash_log;
+	struct sock  * __percpu	*tcp_sk;
 	struct netns_frags	frags;
 #ifdef CONFIG_NETFILTER
 	struct xt_table		*iptable_filter;
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 3d282cbb66b..c605d305c57 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -79,6 +79,9 @@ struct Qdisc {
 	struct netdev_queue	*dev_queue;
 
 	struct gnet_stats_rate_est64	rate_est;
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct gnet_stats_queue	__percpu *cpu_qstats;
+
 	struct Qdisc		*next_sched;
 	struct sk_buff		*gso_skb;
 	/*
@@ -86,15 +89,9 @@ struct Qdisc {
 	 */
 	unsigned long		state;
 	struct sk_buff_head	q;
-	union {
-		struct gnet_stats_basic_packed bstats;
-		struct gnet_stats_basic_cpu __percpu *cpu_bstats;
-	} __packed;
+	struct gnet_stats_basic_packed bstats;
 	unsigned int		__state;
-	union {
-		struct gnet_stats_queue	qstats;
-		struct gnet_stats_queue	__percpu *cpu_qstats;
-	} __packed;
+	struct gnet_stats_queue	qstats;
 	struct rcu_head		rcu_head;
 	int			padded;
 	atomic_t		refcnt;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f50f29faf76..9d9111ef43a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -834,8 +834,8 @@ void tcp_get_available_congestion_control(char *buf, size_t len);
 void tcp_get_allowed_congestion_control(char *buf, size_t len);
 int tcp_set_allowed_congestion_control(char *allowed);
 int tcp_set_congestion_control(struct sock *sk, const char *name);
-void tcp_slow_start(struct tcp_sock *tp, u32 acked);
-void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
+u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
+void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);
 
 u32 tcp_reno_ssthresh(struct sock *sk);
 void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);