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

Pull networking fixes from David Miller:

 1) Fix off by one wrt. indexing when dumping /proc/net/route entries,
    from Alexander Duyck.

 2) Fix lockdep splats in iwlwifi, from Johannes Berg.

 3) Cure panic when inserting certain netfilter rules when NFT_SET_HASH
    is disabled, from Liping Zhang.

 4) Memory leak when nft_expr_clone() fails, also from Liping Zhang.

 5) Disable UFO when path will apply IPSEC tranformations, from Jakub
    Sitnicki.

 6) Don't bogusly double cwnd in dctcp module, from Florian Westphal.

 7) skb_checksum_help() should never actually use the value "0" for the
    resulting checksum, that has a special meaning, use CSUM_MANGLED_0
    instead. From Eric Dumazet.

 8) Per-tx/rx queue statistic strings are wrong in qed driver, fix from
    Yuval MIntz.

 9) Fix SCTP reference counting of associations and transports in
    sctp_diag. From Xin Long.

10) When we hit ip6tunnel_xmit() we could have come from an ipv4 path in
    a previous layer or similar, so explicitly clear the ipv6 control
    block in the skb. From Eli Cooper.

11) Fix bogus sleeping inside of inet_wait_for_connect(), from WANG
    Cong.

12) Correct deivce ID of T6 adapter in cxgb4 driver, from Hariprasad
    Shenai.

13) Fix potential access past the end of the skb page frag array in
    tcp_sendmsg(). From Eric Dumazet.

14) 'skb' can legitimately be NULL in inet{,6}_exact_dif_match(). Fix
    from David Ahern.

15) Don't return an error in tcp_sendmsg() if we wronte any bytes
    successfully, from Eric Dumazet.

16) Extraneous unlocks in netlink_diag_dump(), we removed the locking
    but forgot to purge these unlock calls. From Eric Dumazet.

17) Fix memory leak in error path of __genl_register_family(). We leak
    the attrbuf, from WANG Cong.

18) cgroupstats netlink policy table is mis-sized, from WANG Cong.

19) Several XDP bug fixes in mlx5, from Saeed Mahameed.

20) Fix several device refcount leaks in network drivers, from Johan
    Hovold.

21) icmp6_send() should use skb dst device not skb->dev to determine L3
    routing domain. From David Ahern.

22) ip_vs_genl_family sets maxattr incorrectly, from WANG Cong.

23) We leak new macvlan port in some cases of maclan_common_netlink()
    errors. Fix from Gao Feng.

24) Similar to the icmp6_send() fix, icmp_route_lookup() should
    determine L3 routing domain using skb_dst(skb)->dev not skb->dev.
    Also from David Ahern.

25) Several fixes for route offloading and FIB notification handling in
    mlxsw driver, from Jiri Pirko.

26) Properly cap __skb_flow_dissect()'s return value, from Eric Dumazet.

27) Fix long standing regression in ipv4 redirect handling, wrt.
    validating the new neighbour's reachability. From Stephen Suryaputra
    Lin.

28) If sk_filter() trims the packet excessively, handle it reasonably in
    tcp input instead of exploding. From Eric Dumazet.

29) Fix handling of napi hash state when copying channels in sfc driver,
    from Bert Kenward.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (121 commits)
  mlxsw: spectrum_router: Flush FIB tables during fini
  net: stmmac: Fix lack of link transition for fixed PHYs
  sctp: change sk state only when it has assocs in sctp_shutdown
  bnx2: Wait for in-flight DMA to complete at probe stage
  Revert "bnx2: Reset device during driver initialization"
  ps3_gelic: fix spelling mistake in debug message
  net: ethernet: ixp4xx_eth: fix spelling mistake in debug message
  ibmvnic: Fix size of debugfs name buffer
  ibmvnic: Unmap ibmvnic_statistics structure
  sfc: clear napi_hash state when copying channels
  mlxsw: spectrum_router: Correctly dump neighbour activity
  mlxsw: spectrum: Fix refcount bug on span entries
  bnxt_en: Fix VF virtual link state.
  bnxt_en: Fix ring arithmetic in bnxt_setup_tc().
  Revert "include/uapi/linux/atm_zatm.h: include linux/time.h"
  tcp: take care of truncations done by sk_filter()
  ipv4: use new_gw for redirect neigh lookup
  r8152: Fix error path in open function
  net: bpqether.h: remove if_ether.h guard
  net: __skb_flow_dissect() must cap its return value
  ...

5 files changed, 80 insertions, 25 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 820bac239738..6666b28b6815 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1766,19 +1766,14 @@ EXPORT_SYMBOL_GPL(is_skb_forwardable);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 {
-	if (skb_orphan_frags(skb, GFP_ATOMIC) ||
-	    unlikely(!is_skb_forwardable(dev, skb))) {
-		atomic_long_inc(&dev->rx_dropped);
-		kfree_skb(skb);
-		return NET_RX_DROP;
-	}
+	int ret = ____dev_forward_skb(dev, skb);
 
-	skb_scrub_packet(skb, true);
-	skb->priority = 0;
-	skb->protocol = eth_type_trans(skb, dev);
-	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+	if (likely(!ret)) {
+		skb->protocol = eth_type_trans(skb, dev);
+		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+	}
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(__dev_forward_skb);
 
@@ -2484,7 +2479,7 @@ int skb_checksum_help(struct sk_buff *skb)
 			goto out;
 	}
 
-	*(__sum16 *)(skb->data + offset) = csum_fold(csum);
+	*(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0;
 out_set_summed:
 	skb->ip_summed = CHECKSUM_NONE;
 out:
diff --git a/net/core/filter.c b/net/core/filter.c
index 00351cdf7d0c..b391209838ef 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1628,6 +1628,19 @@ static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
 	return dev_forward_skb(dev, skb);
 }
 
+static inline int __bpf_rx_skb_no_mac(struct net_device *dev,
+				      struct sk_buff *skb)
+{
+	int ret = ____dev_forward_skb(dev, skb);
+
+	if (likely(!ret)) {
+		skb->dev = dev;
+		ret = netif_rx(skb);
+	}
+
+	return ret;
+}
+
 static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
 {
 	int ret;
@@ -1647,6 +1660,51 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
 	return ret;
 }
 
+static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev,
+				 u32 flags)
+{
+	/* skb->mac_len is not set on normal egress */
+	unsigned int mlen = skb->network_header - skb->mac_header;
+
+	__skb_pull(skb, mlen);
+
+	/* At ingress, the mac header has already been pulled once.
+	 * At egress, skb_pospull_rcsum has to be done in case that
+	 * the skb is originated from ingress (i.e. a forwarded skb)
+	 * to ensure that rcsum starts at net header.
+	 */
+	if (!skb_at_tc_ingress(skb))
+		skb_postpull_rcsum(skb, skb_mac_header(skb), mlen);
+	skb_pop_mac_header(skb);
+	skb_reset_mac_len(skb);
+	return flags & BPF_F_INGRESS ?
+	       __bpf_rx_skb_no_mac(dev, skb) : __bpf_tx_skb(dev, skb);
+}
+
+static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev,
+				 u32 flags)
+{
+	bpf_push_mac_rcsum(skb);
+	return flags & BPF_F_INGRESS ?
+	       __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
+}
+
+static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
+			  u32 flags)
+{
+	switch (dev->type) {
+	case ARPHRD_TUNNEL:
+	case ARPHRD_TUNNEL6:
+	case ARPHRD_SIT:
+	case ARPHRD_IPGRE:
+	case ARPHRD_VOID:
+	case ARPHRD_NONE:
+		return __bpf_redirect_no_mac(skb, dev, flags);
+	default:
+		return __bpf_redirect_common(skb, dev, flags);
+	}
+}
+
 BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
 {
 	struct net_device *dev;
@@ -1675,10 +1733,7 @@ BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
 		return -ENOMEM;
 	}
 
-	bpf_push_mac_rcsum(clone);
-
-	return flags & BPF_F_INGRESS ?
-	       __bpf_rx_skb(dev, clone) : __bpf_tx_skb(dev, clone);
+	return __bpf_redirect(clone, dev, flags);
 }
 
 static const struct bpf_func_proto bpf_clone_redirect_proto = {
@@ -1722,10 +1777,7 @@ int skb_do_redirect(struct sk_buff *skb)
 		return -EINVAL;
 	}
 
-	bpf_push_mac_rcsum(skb);
-
-	return ri->flags & BPF_F_INGRESS ?
-	       __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
+	return __bpf_redirect(skb, dev, ri->flags);
 }
 
 static const struct bpf_func_proto bpf_redirect_proto = {
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index ab193e5def07..69e4463a4b1b 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -122,7 +122,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 	struct flow_dissector_key_keyid *key_keyid;
 	bool skip_vlan = false;
 	u8 ip_proto = 0;
-	bool ret = false;
+	bool ret;
 
 	if (!data) {
 		data = skb->data;
@@ -549,12 +549,17 @@ ip_proto_again:
 out_good:
 	ret = true;
 
-out_bad:
+	key_control->thoff = (u16)nhoff;
+out:
 	key_basic->n_proto = proto;
 	key_basic->ip_proto = ip_proto;
-	key_control->thoff = (u16)nhoff;
 
 	return ret;
+
+out_bad:
+	ret = false;
+	key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen);
+	goto out;
 }
 EXPORT_SYMBOL(__skb_flow_dissect);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index fb7348f13501..db313ec7af32 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -275,6 +275,7 @@ int rtnl_unregister(int protocol, int msgtype)
 
 	rtnl_msg_handlers[protocol][msgindex].doit = NULL;
 	rtnl_msg_handlers[protocol][msgindex].dumpit = NULL;
+	rtnl_msg_handlers[protocol][msgindex].calcit = NULL;
 
 	return 0;
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index c73e28fc9c2a..5e3ca414357e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -453,7 +453,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 EXPORT_SYMBOL(sock_queue_rcv_skb);
 
 int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
-		     const int nested, unsigned int trim_cap)
+		     const int nested, unsigned int trim_cap, bool refcounted)
 {
 	int rc = NET_RX_SUCCESS;
 
@@ -487,7 +487,8 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
 
 	bh_unlock_sock(sk);
 out:
-	sock_put(sk);
+	if (refcounted)
+		sock_put(sk);
 	return rc;
 discard_and_relse:
 	kfree_skb(skb);
@@ -1543,6 +1544,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL);
 
 		newsk->sk_err	   = 0;
+		newsk->sk_err_soft = 0;
 		newsk->sk_priority = 0;
 		newsk->sk_incoming_cpu = raw_smp_processor_id();
 		atomic64_set(&newsk->sk_cookie, 0);