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

Pull networking fixes from David Miller:

 1) Fix ppp_mppe crypto soft dependencies, from Takashi Iawi.

 2) Fix TX completion to be finite, from Sergej Benilov.

 3) Use register_pernet_device to avoid a dst leak in tipc, from Xin
    Long.

 4) Double free of TX cleanup in Dirk van der Merwe.

 5) Memory leak in packet_set_ring(), from Eric Dumazet.

 6) Out of bounds read in qmi_wwan, from Bjørn Mork.

 7) Fix iif used in mcast/bcast looped back packets, from Stephen
    Suryaputra.

 8) Fix neighbour resolution on raw ipv6 sockets, from Nicolas Dichtel.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (25 commits)
  af_packet: Block execution of tasks waiting for transmit to complete in AF_PACKET
  sctp: change to hold sk after auth shkey is created successfully
  ipv6: fix neighbour resolution with raw socket
  ipv6: constify rt6_nexthop()
  net: dsa: microchip: Use gpiod_set_value_cansleep()
  net: aquantia: fix vlans not working over bridged network
  ipv4: reset rt_iif for recirculated mcast/bcast out pkts
  team: Always enable vlan tx offload
  net/smc: Fix error path in smc_init
  net/smc: hold conns_lock before calling smc_lgr_register_conn()
  bonding: Always enable vlan tx offload
  net/ipv6: Fix misuse of proc_dointvec "skip_notify_on_dev_down"
  ipv4: Use return value of inet_iif() for __raw_v4_lookup in the while loop
  qmi_wwan: Fix out-of-bounds read
  tipc: check msg->req data len in tipc_nl_compat_bearer_disable
  net: macb: do not copy the mac address if NULL
  net/packet: fix memory leak in packet_set_ring()
  net/tls: fix page double free on TX cleanup
  net/sched: cbs: Fix error path of cbs_module_init
  tipc: change to use register_pernet_device
  ...

16 files changed, 114 insertions, 28 deletions

diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 19d27bee285e..1555b0c6f7ec 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -160,10 +160,10 @@ static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_btle_dev *dev,
 						  struct in6_addr *daddr,
 						  struct sk_buff *skb)
 {
-	struct lowpan_peer *peer;
-	struct in6_addr *nexthop;
 	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
 	int count = atomic_read(&dev->peer_count);
+	const struct in6_addr *nexthop;
+	struct lowpan_peer *peer;
 
 	BT_DBG("peers %d addr %pI6c rt %p", count, daddr, rt);
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 16f9159234a2..8c2ec35b6512 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -318,6 +318,7 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk
 static int ip_mc_finish_output(struct net *net, struct sock *sk,
 			       struct sk_buff *skb)
 {
+	struct rtable *new_rt;
 	int ret;
 
 	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
@@ -326,6 +327,17 @@ static int ip_mc_finish_output(struct net *net, struct sock *sk,
 		return ret;
 	}
 
+	/* Reset rt_iif so that inet_iif() will return skb->skb_iif. Setting
+	 * this to non-zero causes ipi_ifindex in in_pktinfo to be overwritten,
+	 * see ipv4_pktinfo_prepare().
+	 */
+	new_rt = rt_dst_clone(net->loopback_dev, skb_rtable(skb));
+	if (new_rt) {
+		new_rt->rt_iif = 0;
+		skb_dst_drop(skb);
+		skb_dst_set(skb, &new_rt->dst);
+	}
+
 	return dev_loopback_xmit(net, sk, skb);
 }
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 0b8e06ca75d6..40a6abbc9cf6 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -197,7 +197,7 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
 		}
 		sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol,
 				     iph->saddr, iph->daddr,
-				     skb->dev->ifindex, sdif);
+				     dif, sdif);
 	}
 out:
 	read_unlock(&raw_v4_hashinfo.lock);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6cb7cff22db9..8ea0735a6754 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1647,6 +1647,39 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
 }
 EXPORT_SYMBOL(rt_dst_alloc);
 
+struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt)
+{
+	struct rtable *new_rt;
+
+	new_rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK,
+			   rt->dst.flags);
+
+	if (new_rt) {
+		new_rt->rt_genid = rt_genid_ipv4(dev_net(dev));
+		new_rt->rt_flags = rt->rt_flags;
+		new_rt->rt_type = rt->rt_type;
+		new_rt->rt_is_input = rt->rt_is_input;
+		new_rt->rt_iif = rt->rt_iif;
+		new_rt->rt_pmtu = rt->rt_pmtu;
+		new_rt->rt_mtu_locked = rt->rt_mtu_locked;
+		new_rt->rt_gw_family = rt->rt_gw_family;
+		if (rt->rt_gw_family == AF_INET)
+			new_rt->rt_gw4 = rt->rt_gw4;
+		else if (rt->rt_gw_family == AF_INET6)
+			new_rt->rt_gw6 = rt->rt_gw6;
+		INIT_LIST_HEAD(&new_rt->rt_uncached);
+
+		new_rt->dst.flags |= DST_HOST;
+		new_rt->dst.input = rt->dst.input;
+		new_rt->dst.output = rt->dst.output;
+		new_rt->dst.error = rt->dst.error;
+		new_rt->dst.lastuse = jiffies;
+		new_rt->dst.lwtstate = lwtstate_get(rt->dst.lwtstate);
+	}
+	return new_rt;
+}
+EXPORT_SYMBOL(rt_dst_clone);
+
 /* called in rcu_read_lock() section */
 int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 			  u8 tos, struct net_device *dev,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 834475717110..21efcd02f337 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -59,8 +59,8 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
+	const struct in6_addr *nexthop;
 	struct neighbour *neigh;
-	struct in6_addr *nexthop;
 	int ret;
 
 	if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 11ad62effd56..97a843cf164c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -218,7 +218,8 @@ static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst,
 {
 	const struct rt6_info *rt = container_of(dst, struct rt6_info, dst);
 
-	return ip6_neigh_lookup(&rt->rt6i_gateway, dst->dev, skb, daddr);
+	return ip6_neigh_lookup(rt6_nexthop(rt, &in6addr_any),
+				dst->dev, skb, daddr);
 }
 
 static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr)
@@ -5281,7 +5282,7 @@ static struct ctl_table ipv6_route_table_template[] = {
 		.data		=	&init_net.ipv6.sysctl.skip_notify_on_dev_down,
 		.maxlen		=	sizeof(int),
 		.mode		=	0644,
-		.proc_handler	=	proc_dointvec,
+		.proc_handler	=	proc_dointvec_minmax,
 		.extra1		=	&zero,
 		.extra2		=	&one,
 	},
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 241317473114..cdfc33517e85 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -439,9 +439,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	struct nf_flowtable *flow_table = priv;
 	struct flow_offload_tuple tuple = {};
 	enum flow_offload_tuple_dir dir;
+	const struct in6_addr *nexthop;
 	struct flow_offload *flow;
 	struct net_device *outdev;
-	struct in6_addr *nexthop;
 	struct ipv6hdr *ip6h;
 	struct rt6_info *rt;
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a29d66da7394..5f78df080573 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2401,6 +2401,9 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 
 		ts = __packet_set_timestamp(po, ph, skb);
 		__packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts);
+
+		if (!packet_read_pending(&po->tx_ring))
+			complete(&po->skb_completion);
 	}
 
 	sock_wfree(skb);
@@ -2585,7 +2588,7 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame,
 
 static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 {
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	struct net_device *dev;
 	struct virtio_net_hdr *vnet_hdr = NULL;
 	struct sockcm_cookie sockc;
@@ -2600,6 +2603,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	int len_sum = 0;
 	int status = TP_STATUS_AVAILABLE;
 	int hlen, tlen, copylen = 0;
+	long timeo = 0;
 
 	mutex_lock(&po->pg_vec_lock);
 
@@ -2646,12 +2650,21 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !po->has_vnet_hdr)
 		size_max = dev->mtu + reserve + VLAN_HLEN;
 
+	reinit_completion(&po->skb_completion);
+
 	do {
 		ph = packet_current_frame(po, &po->tx_ring,
 					  TP_STATUS_SEND_REQUEST);
 		if (unlikely(ph == NULL)) {
-			if (need_wait && need_resched())
-				schedule();
+			if (need_wait && skb) {
+				timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT);
+				timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo);
+				if (timeo <= 0) {
+					err = !timeo ? -ETIMEDOUT : -ERESTARTSYS;
+					goto out_put;
+				}
+			}
+			/* check for additional frames */
 			continue;
 		}
 
@@ -3207,6 +3220,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	sock_init_data(sock, sk);
 
 	po = pkt_sk(sk);
+	init_completion(&po->skb_completion);
 	sk->sk_family = PF_PACKET;
 	po->num = proto;
 	po->xmit = dev_queue_xmit;
@@ -4314,7 +4328,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 				    req3->tp_sizeof_priv ||
 				    req3->tp_feature_req_word) {
 					err = -EINVAL;
-					goto out;
+					goto out_free_pg_vec;
 				}
 			}
 			break;
@@ -4378,6 +4392,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			prb_shutdown_retire_blk_timer(po, rb_queue);
 	}
 
+out_free_pg_vec:
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 3bb7c5fb3bff..c70a2794456f 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -128,6 +128,7 @@ struct packet_sock {
 	unsigned int		tp_hdrlen;
 	unsigned int		tp_reserve;
 	unsigned int		tp_tstamp;
+	struct completion	skb_completion;
 	struct net_device __rcu	*cached_dev;
 	int			(*xmit)(struct sk_buff *skb);
 	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index e16a3d37d2bc..732e109c3055 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -549,12 +549,17 @@ static struct notifier_block cbs_device_notifier = {
 
 static int __init cbs_module_init(void)
 {
-	int err = register_netdevice_notifier(&cbs_device_notifier);
+	int err;
 
+	err = register_netdevice_notifier(&cbs_device_notifier);
 	if (err)
 		return err;
 
-	return register_qdisc(&cbs_qdisc_ops);
+	err = register_qdisc(&cbs_qdisc_ops);
+	if (err)
+		unregister_netdevice_notifier(&cbs_device_notifier);
+
+	return err;
 }
 
 static void __exit cbs_module_exit(void)
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index e358437ba29b..69cebb2c998b 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -118,10 +118,6 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 	/* Initialize the bind addr area */
 	sctp_bind_addr_init(&ep->base.bind_addr, 0);
 
-	/* Remember who we are attached to.  */
-	ep->base.sk = sk;
-	sock_hold(ep->base.sk);
-
 	/* Create the lists of associations.  */
 	INIT_LIST_HEAD(&ep->asocs);
 
@@ -154,6 +150,10 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 	ep->prsctp_enable = net->sctp.prsctp_enable;
 	ep->reconf_enable = net->sctp.reconf_enable;
 
+	/* Remember who we are attached to.  */
+	ep->base.sk = sk;
+	sock_hold(ep->base.sk);
+
 	return ep;
 
 nomem_shkey:
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 0c874e996f85..7621ec2f539c 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -2029,7 +2029,7 @@ static int __init smc_init(void)
 
 	rc = smc_pnet_init();
 	if (rc)
-		return rc;
+		goto out_pernet_subsys;
 
 	rc = smc_llc_init();
 	if (rc) {
@@ -2080,6 +2080,9 @@ out_proto:
 	proto_unregister(&smc_proto);
 out_pnet:
 	smc_pnet_exit();
+out_pernet_subsys:
+	unregister_pernet_subsys(&smc_net_ops);
+
 	return rc;
 }
 
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 2d2850adc2a3..4ca50ddf8d16 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -652,7 +652,10 @@ create:
 		rc = smc_lgr_create(smc, ini);
 		if (rc)
 			goto out;
+		lgr = conn->lgr;
+		write_lock_bh(&lgr->conns_lock);
 		smc_lgr_register_conn(conn); /* add smc conn to lgr */
+		write_unlock_bh(&lgr->conns_lock);
 	}
 	conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
 	conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
diff --git a/net/tipc/core.c b/net/tipc/core.c
index ed536c05252a..c8370722f0bb 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -134,7 +134,7 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_sysctl;
 
-	err = register_pernet_subsys(&tipc_net_ops);
+	err = register_pernet_device(&tipc_net_ops);
 	if (err)
 		goto out_pernet;
 
@@ -142,7 +142,7 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_socket;
 
-	err = register_pernet_subsys(&tipc_topsrv_net_ops);
+	err = register_pernet_device(&tipc_topsrv_net_ops);
 	if (err)
 		goto out_pernet_topsrv;
 
@@ -153,11 +153,11 @@ static int __init tipc_init(void)
 	pr_info("Started in single node mode\n");
 	return 0;
 out_bearer:
-	unregister_pernet_subsys(&tipc_topsrv_net_ops);
+	unregister_pernet_device(&tipc_topsrv_net_ops);
 out_pernet_topsrv:
 	tipc_socket_stop();
 out_socket:
-	unregister_pernet_subsys(&tipc_net_ops);
+	unregister_pernet_device(&tipc_net_ops);
 out_pernet:
 	tipc_unregister_sysctl();
 out_sysctl:
@@ -172,9 +172,9 @@ out_netlink:
 static void __exit tipc_exit(void)
 {
 	tipc_bearer_cleanup();
-	unregister_pernet_subsys(&tipc_topsrv_net_ops);
+	unregister_pernet_device(&tipc_topsrv_net_ops);
 	tipc_socket_stop();
-	unregister_pernet_subsys(&tipc_net_ops);
+	unregister_pernet_device(&tipc_net_ops);
 	tipc_netlink_stop();
 	tipc_netlink_compat_stop();
 	tipc_unregister_sysctl();
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index c6a04c09d075..cf155061c472 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -445,7 +445,11 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd,
 	if (!bearer)
 		return -EMSGSIZE;
 
-	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME);
+	len = TLV_GET_DATA_LEN(msg->req);
+	if (len <= 0)
+		return -EINVAL;
+
+	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
 	if (!string_is_valid(name, len))
 		return -EINVAL;
 
@@ -539,7 +543,11 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
 
 	name = (char *)TLV_DATA(msg->req);
 
-	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+	len = TLV_GET_DATA_LEN(msg->req);
+	if (len <= 0)
+		return -EINVAL;
+
+	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
 	if (!string_is_valid(name, len))
 		return -EINVAL;
 
@@ -817,7 +825,11 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd,
 	if (!link)
 		return -EMSGSIZE;
 
-	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+	len = TLV_GET_DATA_LEN(msg->req);
+	if (len <= 0)
+		return -EINVAL;
+
+	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
 	if (!string_is_valid(name, len))
 		return -EINVAL;
 
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index fc81ae18cc44..e2b69e805d46 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -279,7 +279,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 		goto skip_tx_cleanup;
 	}
 
-	if (!tls_complete_pending_work(sk, ctx, 0, &timeo))
+	if (unlikely(sk->sk_write_pending) &&
+	    !wait_on_pending_writer(sk, &timeo))
 		tls_handle_open_record(sk, 0);
 
 	/* We need these for tls_sw_fallback handling of other packets */