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

Pull networking fixes from David Miller:

 1) GTP fixes from Andreas Schultz (missing genl module alias, clear IP
    DF on transmit).

 2) Netfilter needs to reflect the fwmark when sending resets, from Pau
    Espin Pedrol.

 3) nftable dump OOPS fix from Liping Zhang.

 4) Fix erroneous setting of VIRTIO_NET_HDR_F_DATA_VALID on transmit,
    from Rolf Neugebauer.

 5) Fix build error of ipt_CLUSTERIP when procfs is disabled, from Arnd
    Bergmann.

 6) Fix regression in handling of NETIF_F_SG in harmonize_features(),
    from Eric Dumazet.

 7) Fix RTNL deadlock wrt. lwtunnel module loading, from David Ahern.

 8) tcp_fastopen_create_child() needs to setup tp->max_window, from
    Alexey Kodanev.

 9) Missing kmemdup() failure check in ipv6 segment routing code, from
    Eric Dumazet.

10) Don't execute unix_bind() under the bindlock, otherwise we deadlock
    with splice. From WANG Cong.

11) ip6_tnl_parse_tlv_enc_lim() potentially reallocates the skb buffer,
    therefore callers must reload cached header pointers into that skb.
    Fix from Eric Dumazet.

12) Fix various bugs in legacy IRQ fallback handling in alx driver, from
    Tobias Regnery.

13) Do not allow lwtunnel drivers to be unloaded while they are
    referenced by active instances, from Robert Shearman.

14) Fix truncated PHY LED trigger names, from Geert Uytterhoeven.

15) Fix a few regressions from virtio_net XDP support, from John
    Fastabend and Jakub Kicinski.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (102 commits)
  ISDN: eicon: silence misleading array-bounds warning
  net: phy: micrel: add support for KSZ8795
  gtp: fix cross netns recv on gtp socket
  gtp: clear DF bit on GTP packet tx
  gtp: add genl family modules alias
  tcp: don't annotate mark on control socket from tcp_v6_send_response()
  ravb: unmap descriptors when freeing rings
  virtio_net: reject XDP programs using header adjustment
  virtio_net: use dev_kfree_skb for small buffer XDP receive
  r8152: check rx after napi is enabled
  r8152: re-schedule napi for tx
  r8152: avoid start_xmit to schedule napi when napi is disabled
  r8152: avoid start_xmit to call napi_schedule during autosuspend
  net: dsa: Bring back device detaching in dsa_slave_suspend()
  net: phy: leds: Fix truncated LED trigger names
  net: phy: leds: Break dependency of phy.h on phy_led_triggers.h
  net: phy: leds: Clear phy_num_led_triggers on failure to avoid crash
  net-next: ethernet: mediatek: change the compatible string
  Documentation: devicetree: change the mediatek ethernet compatible string
  bnxt_en: Fix RTNL lock usage on bnxt_get_port_module_status().
  ...

9 files changed, 30 insertions, 16 deletions

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index eae0332b0e8c..7db2ad2e82d3 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -46,6 +46,7 @@
 #include <net/rtnetlink.h>
 #include <net/xfrm.h>
 #include <net/l3mdev.h>
+#include <net/lwtunnel.h>
 #include <trace/events/fib.h>
 
 #ifndef CONFIG_IP_MULTIPLE_TABLES
@@ -677,6 +678,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			cfg->fc_mx_len = nla_len(attr);
 			break;
 		case RTA_MULTIPATH:
+			err = lwtunnel_valid_encap_type_attr(nla_data(attr),
+							     nla_len(attr));
+			if (err < 0)
+				goto errout;
 			cfg->fc_mp = nla_data(attr);
 			cfg->fc_mp_len = nla_len(attr);
 			break;
@@ -691,6 +696,9 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			break;
 		case RTA_ENCAP_TYPE:
 			cfg->fc_encap_type = nla_get_u16(attr);
+			err = lwtunnel_valid_encap_type(cfg->fc_encap_type);
+			if (err < 0)
+				goto errout;
 			break;
 		}
 	}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index fac275c48108..b67719f45953 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1629,6 +1629,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
 	sk->sk_sndbuf = sysctl_wmem_default;
+	sk->sk_mark = fl4.flowi4_mark;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
 	if (unlikely(err)) {
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index fed3d29f9eb3..0fd1976ab63b 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -313,6 +313,7 @@ static const struct lwtunnel_encap_ops ip_tun_lwt_ops = {
 	.fill_encap = ip_tun_fill_encap_info,
 	.get_encap_size = ip_tun_encap_nlsize,
 	.cmp_encap = ip_tun_cmp_encap,
+	.owner = THIS_MODULE,
 };
 
 static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
@@ -403,6 +404,7 @@ static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = {
 	.fill_encap = ip6_tun_fill_encap_info,
 	.get_encap_size = ip6_tun_encap_nlsize,
 	.cmp_encap = ip_tun_cmp_encap,
+	.owner = THIS_MODULE,
 };
 
 void __init ip_tunnel_core_init(void)
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index a6b8c1a4102b..0a783cd73faf 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -144,7 +144,12 @@ clusterip_config_find_get(struct net *net, __be32 clusterip, int entry)
 	rcu_read_lock_bh();
 	c = __clusterip_config_find(net, clusterip);
 	if (c) {
-		if (!c->pde || unlikely(!atomic_inc_not_zero(&c->refcount)))
+#ifdef CONFIG_PROC_FS
+		if (!c->pde)
+			c = NULL;
+		else
+#endif
+		if (unlikely(!atomic_inc_not_zero(&c->refcount)))
 			c = NULL;
 		else if (entry)
 			atomic_inc(&c->entries);
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index f273098e48fd..37fb9552e858 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -63,10 +63,10 @@ static bool rpfilter_lookup_reverse(struct net *net, struct flowi4 *fl4,
 	return dev_match || flags & XT_RPFILTER_LOOSE;
 }
 
-static bool rpfilter_is_local(const struct sk_buff *skb)
+static bool
+rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in)
 {
-	const struct rtable *rt = skb_rtable(skb);
-	return rt && (rt->rt_flags & RTCF_LOCAL);
+	return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK;
 }
 
 static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
@@ -79,7 +79,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	info = par->matchinfo;
 	invert = info->flags & XT_RPFILTER_INVERT;
 
-	if (rpfilter_is_local(skb))
+	if (rpfilter_is_loopback(skb, xt_in(par)))
 		return true ^ invert;
 
 	iph = ip_hdr(skb);
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index fd8220213afc..146d86105183 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -126,6 +126,8 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 	/* ip_route_me_harder expects skb->dst to be set */
 	skb_dst_set_noref(nskb, skb_dst(oldskb));
 
+	nskb->mark = IP4_REPLY_MARK(net, oldskb->mark);
+
 	skb_reserve(nskb, LL_MAX_HEADER);
 	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
 				   ip4_dst_hoplimit(skb_dst(nskb)));
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index 965b1a161369..2981291910dd 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -26,13 +26,6 @@ static __be32 get_saddr(__be32 addr)
 	return addr;
 }
 
-static bool fib4_is_local(const struct sk_buff *skb)
-{
-	const struct rtable *rt = skb_rtable(skb);
-
-	return rt && (rt->rt_flags & RTCF_LOCAL);
-}
-
 #define DSCP_BITS     0xfc
 
 void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
@@ -95,8 +88,10 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	else
 		oif = NULL;
 
-	if (nft_hook(pkt) == NF_INET_PRE_ROUTING && fib4_is_local(pkt->skb)) {
-		nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX);
+	if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
+	    nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
+		nft_fib_store_result(dest, priv->result, pkt,
+				     nft_in(pkt)->ifindex);
 		return;
 	}
 
@@ -131,7 +126,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	switch (res.type) {
 	case RTN_UNICAST:
 		break;
-	case RTN_LOCAL:	/* should not appear here, see fib4_is_local() above */
+	case RTN_LOCAL: /* Should not see RTN_LOCAL here */
 		return;
 	default:
 		break;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index f51919535ca7..dd2560c83a85 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -205,6 +205,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	 * scaled. So correct it appropriately.
 	 */
 	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
+	tp->max_window = tp->snd_wnd;
 
 	/* Activate the retrans timer so that SYNACK can be retransmitted.
 	 * The request socket is not added to the ehash
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6c790754ae3e..41dcbd568cbe 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5078,7 +5078,7 @@ static void tcp_check_space(struct sock *sk)
 	if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) {
 		sock_reset_flag(sk, SOCK_QUEUE_SHRUNK);
 		/* pairs with tcp_poll() */
-		smp_mb__after_atomic();
+		smp_mb();
 		if (sk->sk_socket &&
 		    test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
 			tcp_new_space(sk);