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

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

25 files changed, 288 insertions, 123 deletions

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 15bbfaf943fd..8b644113715e 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -284,9 +284,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
 	return 0;
 
 out_free_newdev:
-	if (new_dev->reg_state == NETREG_UNINITIALIZED ||
-	    new_dev->reg_state == NETREG_UNREGISTERED)
-		free_netdev(new_dev);
+	free_netdev(new_dev);
 	return err;
 }
 
diff --git a/net/can/isotp.c b/net/can/isotp.c
index 7839c3b9e5be..3ef7f78e553b 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1155,6 +1155,7 @@ static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
 	if (peer)
 		return -EOPNOTSUPP;
 
+	memset(addr, 0, sizeof(*addr));
 	addr->can_family = AF_CAN;
 	addr->can_ifindex = so->ifindex;
 	addr->can_addr.tp.rx_id = so->rxid;
diff --git a/net/core/dev.c b/net/core/dev.c
index 267c4a8daa55..0a31d4ea6f4d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9648,9 +9648,15 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
 		}
 	}
 
-	if ((features & NETIF_F_HW_TLS_TX) && !(features & NETIF_F_HW_CSUM)) {
-		netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
-		features &= ~NETIF_F_HW_TLS_TX;
+	if (features & NETIF_F_HW_TLS_TX) {
+		bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) ==
+			(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
+		bool hw_csum = features & NETIF_F_HW_CSUM;
+
+		if (!ip_csum && !hw_csum) {
+			netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
+			features &= ~NETIF_F_HW_TLS_TX;
+		}
 	}
 
 	return features;
@@ -10064,17 +10070,11 @@ int register_netdevice(struct net_device *dev)
 	ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
 	ret = notifier_to_errno(ret);
 	if (ret) {
+		/* Expect explicit free_netdev() on failure */
+		dev->needs_free_netdev = false;
 		rollback_registered(dev);
-		rcu_barrier();
-
-		dev->reg_state = NETREG_UNREGISTERED;
-		/* We should put the kobject that hold in
-		 * netdev_unregister_kobject(), otherwise
-		 * the net device cannot be freed when
-		 * driver calls free_netdev(), because the
-		 * kobject is being hold.
-		 */
-		kobject_put(&dev->dev.kobj);
+		net_set_todo(dev);
+		goto out;
 	}
 	/*
 	 *	Prevent userspace races by waiting until the network
@@ -10618,6 +10618,17 @@ void free_netdev(struct net_device *dev)
 	struct napi_struct *p, *n;
 
 	might_sleep();
+
+	/* When called immediately after register_netdevice() failed the unwind
+	 * handling may still be dismantling the device. Handle that case by
+	 * deferring the free.
+	 */
+	if (dev->reg_state == NETREG_UNREGISTERING) {
+		ASSERT_RTNL();
+		dev->needs_free_netdev = true;
+		return;
+	}
+
 	netif_free_tx_queues(dev);
 	netif_free_rx_queues(dev);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index bb0596c41b3e..3d6ab194d0f5 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3439,26 +3439,15 @@ replay:
 
 	dev->ifindex = ifm->ifi_index;
 
-	if (ops->newlink) {
+	if (ops->newlink)
 		err = ops->newlink(link_net ? : net, dev, tb, data, extack);
-		/* Drivers should call free_netdev() in ->destructor
-		 * and unregister it on failure after registration
-		 * so that device could be finally freed in rtnl_unlock.
-		 */
-		if (err < 0) {
-			/* If device is not registered at all, free it now */
-			if (dev->reg_state == NETREG_UNINITIALIZED ||
-			    dev->reg_state == NETREG_UNREGISTERED)
-				free_netdev(dev);
-			goto out;
-		}
-	} else {
+	else
 		err = register_netdevice(dev);
-		if (err < 0) {
-			free_netdev(dev);
-			goto out;
-		}
+	if (err < 0) {
+		free_netdev(dev);
+		goto out;
 	}
+
 	err = rtnl_configure_link(dev, ifm);
 	if (err < 0)
 		goto out_unregister;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7626a33cce59..60390696e184 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -501,13 +501,17 @@ EXPORT_SYMBOL(__netdev_alloc_skb);
 struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
 				 gfp_t gfp_mask)
 {
-	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+	struct napi_alloc_cache *nc;
 	struct sk_buff *skb;
 	void *data;
 
 	len += NET_SKB_PAD + NET_IP_ALIGN;
 
-	if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) ||
+	/* If requested length is either too small or too big,
+	 * we use kmalloc() for skb->head allocation.
+	 */
+	if (len <= SKB_WITH_OVERHEAD(1024) ||
+	    len > SKB_WITH_OVERHEAD(PAGE_SIZE) ||
 	    (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
 		skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE);
 		if (!skb)
@@ -515,6 +519,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
 		goto skb_success;
 	}
 
+	nc = this_cpu_ptr(&napi_alloc_cache);
 	len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	len = SKB_DATA_ALIGN(len);
 
@@ -3439,6 +3444,7 @@ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
 	st->root_skb = st->cur_skb = skb;
 	st->frag_idx = st->stepped_offset = 0;
 	st->frag_data = NULL;
+	st->frag_off = 0;
 }
 EXPORT_SYMBOL(skb_prepare_seq_read);
 
@@ -3493,14 +3499,27 @@ next_skb:
 		st->stepped_offset += skb_headlen(st->cur_skb);
 
 	while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) {
+		unsigned int pg_idx, pg_off, pg_sz;
+
 		frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx];
-		block_limit = skb_frag_size(frag) + st->stepped_offset;
 
+		pg_idx = 0;
+		pg_off = skb_frag_off(frag);
+		pg_sz = skb_frag_size(frag);
+
+		if (skb_frag_must_loop(skb_frag_page(frag))) {
+			pg_idx = (pg_off + st->frag_off) >> PAGE_SHIFT;
+			pg_off = offset_in_page(pg_off + st->frag_off);
+			pg_sz = min_t(unsigned int, pg_sz - st->frag_off,
+						    PAGE_SIZE - pg_off);
+		}
+
+		block_limit = pg_sz + st->stepped_offset;
 		if (abs_offset < block_limit) {
 			if (!st->frag_data)
-				st->frag_data = kmap_atomic(skb_frag_page(frag));
+				st->frag_data = kmap_atomic(skb_frag_page(frag) + pg_idx);
 
-			*data = (u8 *) st->frag_data + skb_frag_off(frag) +
+			*data = (u8 *)st->frag_data + pg_off +
 				(abs_offset - st->stepped_offset);
 
 			return block_limit - abs_offset;
@@ -3511,8 +3530,12 @@ next_skb:
 			st->frag_data = NULL;
 		}
 
-		st->frag_idx++;
-		st->stepped_offset += skb_frag_size(frag);
+		st->stepped_offset += pg_sz;
+		st->frag_off += pg_sz;
+		if (st->frag_off == skb_frag_size(frag)) {
+			st->frag_off = 0;
+			st->frag_idx++;
+		}
 	}
 
 	if (st->frag_data) {
@@ -3652,7 +3675,8 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
 	unsigned int delta_truesize = 0;
 	unsigned int delta_len = 0;
 	struct sk_buff *tail = NULL;
-	struct sk_buff *nskb;
+	struct sk_buff *nskb, *tmp;
+	int err;
 
 	skb_push(skb, -skb_network_offset(skb) + offset);
 
@@ -3662,11 +3686,28 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
 		nskb = list_skb;
 		list_skb = list_skb->next;
 
+		err = 0;
+		if (skb_shared(nskb)) {
+			tmp = skb_clone(nskb, GFP_ATOMIC);
+			if (tmp) {
+				consume_skb(nskb);
+				nskb = tmp;
+				err = skb_unclone(nskb, GFP_ATOMIC);
+			} else {
+				err = -ENOMEM;
+			}
+		}
+
 		if (!tail)
 			skb->next = nskb;
 		else
 			tail->next = nskb;
 
+		if (unlikely(err)) {
+			nskb->next = list_skb;
+			goto err_linearize;
+		}
+
 		tail = nskb;
 
 		delta_len += nskb->len;
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index bbdd3c7b6cb5..b065f0a103ed 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -293,7 +293,7 @@ select_by_hash:
 			i = j = reciprocal_scale(hash, socks);
 			while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) {
 				i++;
-				if (i >= reuse->num_socks)
+				if (i >= socks)
 					i = 0;
 				if (i == j)
 					goto out;
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 7d49b6fd6cef..653e3bc9c87b 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1765,7 +1765,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	fn = &reply_funcs[dcb->cmd];
 	if (!fn->cb)
 		return -EOPNOTSUPP;
-	if (fn->type != nlh->nlmsg_type)
+	if (fn->type == RTM_SETDCB && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!tb[DCB_ATTR_IFNAME])
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index fd343466df27..6f65ea0eef9f 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -412,9 +412,13 @@ static int dsa_port_devlink_setup(struct dsa_port *dp)
 
 static void dsa_port_teardown(struct dsa_port *dp)
 {
+	struct devlink_port *dlp = &dp->devlink_port;
+
 	if (!dp->setup)
 		return;
 
+	devlink_port_type_clear(dlp);
+
 	switch (dp->type) {
 	case DSA_PORT_TYPE_UNUSED:
 		break;
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 5a0f6fec4271..cb3a5cf99b25 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -309,8 +309,18 @@ static struct lock_class_key dsa_master_addr_list_lock_key;
 int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 {
 	int mtu = ETH_DATA_LEN + cpu_dp->tag_ops->overhead;
+	struct dsa_switch *ds = cpu_dp->ds;
+	struct device_link *consumer_link;
 	int ret;
 
+	/* The DSA master must use SET_NETDEV_DEV for this to work. */
+	consumer_link = device_link_add(ds->dev, dev->dev.parent,
+					DL_FLAG_AUTOREMOVE_CONSUMER);
+	if (!consumer_link)
+		netdev_err(dev,
+			   "Failed to create a device link to DSA switch %s\n",
+			   dev_name(ds->dev));
+
 	rtnl_lock();
 	ret = dev_set_mtu(dev, mtu);
 	rtnl_unlock();
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 8b07f3a4f2db..a3271ec3e162 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -443,7 +443,6 @@ static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb,
 int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
 {
 	u8 *tail;
-	u8 *vaddr;
 	int nfrags;
 	int esph_offset;
 	struct page *page;
@@ -485,14 +484,10 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			page = pfrag->page;
 			get_page(page);
 
-			vaddr = kmap_atomic(page);
-
-			tail = vaddr + pfrag->offset;
+			tail = page_address(page) + pfrag->offset;
 
 			esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
 
-			kunmap_atomic(vaddr);
-
 			nfrags = skb_shinfo(skb)->nr_frags;
 
 			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 52c2f063529f..2b804fcebcc6 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -478,7 +478,6 @@ static int esp6_output_encap(struct xfrm_state *x, struct sk_buff *skb,
 int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
 {
 	u8 *tail;
-	u8 *vaddr;
 	int nfrags;
 	int esph_offset;
 	struct page *page;
@@ -519,14 +518,10 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 			page = pfrag->page;
 			get_page(page);
 
-			vaddr = kmap_atomic(page);
-
-			tail = vaddr + pfrag->offset;
+			tail = page_address(page) + pfrag->offset;
 
 			esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
 
-			kunmap_atomic(vaddr);
-
 			nfrags = skb_shinfo(skb)->nr_frags;
 
 			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 072ce9678616..117cd95df213 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -125,8 +125,43 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 	return -EINVAL;
 }
 
+static int
+ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
+				    struct sk_buff *skb, unsigned int mtu)
+{
+	struct sk_buff *segs, *nskb;
+	netdev_features_t features;
+	int ret = 0;
+
+	/* Please see corresponding comment in ip_finish_output_gso
+	 * describing the cases where GSO segment length exceeds the
+	 * egress MTU.
+	 */
+	features = netif_skb_features(skb);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR_OR_NULL(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	skb_list_walk_safe(segs, segs, nskb) {
+		int err;
+
+		skb_mark_not_on_list(segs);
+		err = ip6_fragment(net, sk, segs, ip6_finish_output2);
+		if (err && ret == 0)
+			ret = err;
+	}
+
+	return ret;
+}
+
 static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	unsigned int mtu;
+
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
 	if (skb_dst(skb)->xfrm) {
@@ -135,7 +170,11 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
 	}
 #endif
 
-	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
+	mtu = ip6_skb_dst_mtu(skb);
+	if (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))
+		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
+
+	if ((skb->len > mtu && !skb_is_gso(skb)) ||
 	    dst_allfrag(skb_dst(skb)) ||
 	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
 		return ip6_fragment(net, sk, skb, ip6_finish_output2);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 2da0ee703779..93636867aee2 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1645,8 +1645,11 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
 	}
 
 #ifdef CONFIG_IPV6_SIT_6RD
-	if (ipip6_netlink_6rd_parms(data, &ip6rd))
+	if (ipip6_netlink_6rd_parms(data, &ip6rd)) {
 		err = ipip6_tunnel_update_6rd(nt, &ip6rd);
+		if (err < 0)
+			unregister_netdevice_queue(dev, NULL);
+	}
 #endif
 
 	return err;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 6628d8d74203..f998a077c7dd 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -427,7 +427,7 @@ static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 static bool tcp_can_send_ack(const struct sock *ssk)
 {
 	return !((1 << inet_sk_state_load(ssk)) &
-	       (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE));
+	       (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN));
 }
 
 static void mptcp_send_ack(struct mptcp_sock *msk)
@@ -2642,11 +2642,17 @@ static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
 
 static int mptcp_disconnect(struct sock *sk, int flags)
 {
-	/* Should never be called.
-	 * inet_stream_connect() calls ->disconnect, but that
-	 * refers to the subflow socket, not the mptcp one.
-	 */
-	WARN_ON_ONCE(1);
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	__mptcp_flush_join_list(msk);
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		lock_sock(ssk);
+		tcp_disconnect(ssk, flags);
+		release_sock(ssk);
+	}
 	return 0;
 }
 
@@ -3089,6 +3095,14 @@ bool mptcp_finish_join(struct sock *ssk)
 	return true;
 }
 
+static void mptcp_shutdown(struct sock *sk, int how)
+{
+	pr_debug("sk=%p, how=%d", sk, how);
+
+	if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
+		__mptcp_wr_shutdown(sk);
+}
+
 static struct proto mptcp_prot = {
 	.name		= "MPTCP",
 	.owner		= THIS_MODULE,
@@ -3098,7 +3112,7 @@ static struct proto mptcp_prot = {
 	.accept		= mptcp_accept,
 	.setsockopt	= mptcp_setsockopt,
 	.getsockopt	= mptcp_getsockopt,
-	.shutdown	= tcp_shutdown,
+	.shutdown	= mptcp_shutdown,
 	.destroy	= mptcp_destroy,
 	.sendmsg	= mptcp_sendmsg,
 	.recvmsg	= mptcp_recvmsg,
@@ -3344,43 +3358,6 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	return mask;
 }
 
-static int mptcp_shutdown(struct socket *sock, int how)
-{
-	struct mptcp_sock *msk = mptcp_sk(sock->sk);
-	struct sock *sk = sock->sk;
-	int ret = 0;
-
-	pr_debug("sk=%p, how=%d", msk, how);
-
-	lock_sock(sk);
-
-	how++;
-	if ((how & ~SHUTDOWN_MASK) || !how) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
-
-	if (sock->state == SS_CONNECTING) {
-		if ((1 << sk->sk_state) &
-		    (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
-			sock->state = SS_DISCONNECTING;
-		else
-			sock->state = SS_CONNECTED;
-	}
-
-	sk->sk_shutdown |= how;
-	if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
-		__mptcp_wr_shutdown(sk);
-
-	/* Wake up anyone sleeping in poll. */
-	sk->sk_state_change(sk);
-
-out_unlock:
-	release_sock(sk);
-
-	return ret;
-}
-
 static const struct proto_ops mptcp_stream_ops = {
 	.family		   = PF_INET,
 	.owner		   = THIS_MODULE,
@@ -3394,7 +3371,7 @@ static const struct proto_ops mptcp_stream_ops = {
 	.ioctl		   = inet_ioctl,
 	.gettstamp	   = sock_gettstamp,
 	.listen		   = mptcp_listen,
-	.shutdown	   = mptcp_shutdown,
+	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
 	.getsockopt	   = sock_common_getsockopt,
 	.sendmsg	   = inet_sendmsg,
@@ -3444,7 +3421,7 @@ static const struct proto_ops mptcp_v6_stream_ops = {
 	.ioctl		   = inet6_ioctl,
 	.gettstamp	   = sock_gettstamp,
 	.listen		   = mptcp_listen,
-	.shutdown	   = mptcp_shutdown,
+	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
 	.getsockopt	   = sock_common_getsockopt,
 	.sendmsg	   = inet6_sendmsg,
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 46c5557c1fec..0ee702d374b0 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -523,6 +523,9 @@ nf_conntrack_hash_sysctl(struct ctl_table *table, int write,
 {
 	int ret;
 
+	/* module_param hashsize could have changed value */
+	nf_conntrack_htable_size_user = nf_conntrack_htable_size;
+
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 	if (ret < 0 || !write)
 		return ret;
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index ea923f8cf9c4..b7c3c902290f 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -1174,6 +1174,7 @@ static int __init nf_nat_init(void)
 	ret = register_pernet_subsys(&nat_net_ops);
 	if (ret < 0) {
 		nf_ct_extend_unregister(&nat_extend);
+		kvfree(nf_nat_bysource);
 		return ret;
 	}
 
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 667c44aa5a63..dc201363f2c4 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -430,7 +430,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 		return;
 	}
 
-	if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST) {
+	if (state == RXRPC_CALL_SERVER_RECV_REQUEST) {
 		unsigned long timo = READ_ONCE(call->next_req_timo);
 		unsigned long now, expect_req_by;
 
diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index 9631aa8543b5..8d2073e0e3da 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -598,7 +598,7 @@ static long rxrpc_read(const struct key *key,
 		default: /* we have a ticket we can't encode */
 			pr_err("Unsupported key token type (%u)\n",
 			       token->security_index);
-			continue;
+			return -ENOPKG;
 		}
 
 		_debug("token[%u]: toksize=%u", ntoks, toksize);
@@ -674,7 +674,9 @@ static long rxrpc_read(const struct key *key,
 			break;
 
 		default:
-			break;
+			pr_err("Unsupported key token type (%u)\n",
+			       token->security_index);
+			return -ENOPKG;
 		}
 
 		ASSERTCMP((unsigned long)xdr - (unsigned long)oldxdr, ==,
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 59342b519e34..0df85a12651e 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -246,7 +246,8 @@ int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb)
 		goto errattr;
 	smc_clc_get_hostname(&host);
 	if (host) {
-		snprintf(hostname, sizeof(hostname), "%s", host);
+		memcpy(hostname, host, SMC_MAX_HOSTNAME_LEN);
+		hostname[SMC_MAX_HOSTNAME_LEN] = 0;
 		if (nla_put_string(skb, SMC_NLA_SYS_LOCAL_HOST, hostname))
 			goto errattr;
 	}
@@ -257,7 +258,8 @@ int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb)
 		smc_ism_get_system_eid(smcd_dev, &seid);
 	mutex_unlock(&smcd_dev_list.mutex);
 	if (seid && smc_ism_is_v2_capable()) {
-		snprintf(smc_seid, sizeof(smc_seid), "%s", seid);
+		memcpy(smc_seid, seid, SMC_MAX_EID_LEN);
+		smc_seid[SMC_MAX_EID_LEN] = 0;
 		if (nla_put_string(skb, SMC_NLA_SYS_SEID, smc_seid))
 			goto errattr;
 	}
@@ -295,7 +297,8 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr,
 		goto errattr;
 	if (nla_put_u8(skb, SMC_NLA_LGR_R_VLAN_ID, lgr->vlan_id))
 		goto errattr;
-	snprintf(smc_target, sizeof(smc_target), "%s", lgr->pnet_id);
+	memcpy(smc_target, lgr->pnet_id, SMC_MAX_PNETID_LEN);
+	smc_target[SMC_MAX_PNETID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target))
 		goto errattr;
 
@@ -312,7 +315,7 @@ static int smc_nl_fill_lgr_link(struct smc_link_group *lgr,
 				struct sk_buff *skb,
 				struct netlink_callback *cb)
 {
-	char smc_ibname[IB_DEVICE_NAME_MAX + 1];
+	char smc_ibname[IB_DEVICE_NAME_MAX];
 	u8 smc_gid_target[41];
 	struct nlattr *attrs;
 	u32 link_uid = 0;
@@ -461,7 +464,8 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr,
 		goto errattr;
 	if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd)))
 		goto errattr;
-	snprintf(smc_pnet, sizeof(smc_pnet), "%s", lgr->smcd->pnetid);
+	memcpy(smc_pnet, lgr->smcd->pnetid, SMC_MAX_PNETID_LEN);
+	smc_pnet[SMC_MAX_PNETID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet))
 		goto errattr;
 
@@ -474,10 +478,12 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr,
 		goto errv2attr;
 	if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os))
 		goto errv2attr;
-	snprintf(smc_host, sizeof(smc_host), "%s", lgr->peer_hostname);
+	memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN);
+	smc_host[SMC_MAX_HOSTNAME_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host))
 		goto errv2attr;
-	snprintf(smc_eid, sizeof(smc_eid), "%s", lgr->negotiated_eid);
+	memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN);
+	smc_eid[SMC_MAX_EID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid))
 		goto errv2attr;
 
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index ddd7fac98b1d..7d7ba0320d5a 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -371,8 +371,8 @@ static int smc_nl_handle_dev_port(struct sk_buff *skb,
 	if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR,
 		       smcibdev->pnetid_by_user[port]))
 		goto errattr;
-	snprintf(smc_pnet, sizeof(smc_pnet), "%s",
-		 (char *)&smcibdev->pnetid[port]);
+	memcpy(smc_pnet, &smcibdev->pnetid[port], SMC_MAX_PNETID_LEN);
+	smc_pnet[SMC_MAX_PNETID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet))
 		goto errattr;
 	if (nla_put_u32(skb, SMC_NLA_DEV_PORT_NETDEV,
@@ -414,7 +414,7 @@ static int smc_nl_handle_smcr_dev(struct smc_ib_device *smcibdev,
 				  struct sk_buff *skb,
 				  struct netlink_callback *cb)
 {
-	char smc_ibname[IB_DEVICE_NAME_MAX + 1];
+	char smc_ibname[IB_DEVICE_NAME_MAX];
 	struct smc_pci_dev smc_pci_dev;
 	struct pci_dev *pci_dev;
 	unsigned char is_crit;
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index 524ef64a191a..9c6e95882553 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -250,7 +250,8 @@ static int smc_nl_handle_smcd_dev(struct smcd_dev *smcd,
 		goto errattr;
 	if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR, smcd->pnetid_by_user))
 		goto errportattr;
-	snprintf(smc_pnet, sizeof(smc_pnet), "%s", smcd->pnetid);
+	memcpy(smc_pnet, smcd->pnetid, SMC_MAX_PNETID_LEN);
+	smc_pnet[SMC_MAX_PNETID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet))
 		goto errportattr;
 
diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c
index 010dcb876f9d..6e4dbd577a39 100644
--- a/net/sunrpc/addr.c
+++ b/net/sunrpc/addr.c
@@ -185,7 +185,7 @@ static int rpc_parse_scope_id(struct net *net, const char *buf,
 			scope_id = dev->ifindex;
 			dev_put(dev);
 		} else {
-			if (kstrtou32(p, 10, &scope_id) == 0) {
+			if (kstrtou32(p, 10, &scope_id) != 0) {
 				kfree(p);
 				return 0;
 			}
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index b248f2349437..c9766d07eb81 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1062,6 +1062,90 @@ err_noclose:
 	return 0;	/* record not complete */
 }
 
+static int svc_tcp_send_kvec(struct socket *sock, const struct kvec *vec,
+			      int flags)
+{
+	return kernel_sendpage(sock, virt_to_page(vec->iov_base),
+			       offset_in_page(vec->iov_base),
+			       vec->iov_len, flags);
+}
+
+/*
+ * kernel_sendpage() is used exclusively to reduce the number of
+ * copy operations in this path. Therefore the caller must ensure
+ * that the pages backing @xdr are unchanging.
+ *
+ * In addition, the logic assumes that * .bv_len is never larger
+ * than PAGE_SIZE.
+ */
+static int svc_tcp_sendmsg(struct socket *sock, struct msghdr *msg,
+			   struct xdr_buf *xdr, rpc_fraghdr marker,
+			   unsigned int *sentp)
+{
+	const struct kvec *head = xdr->head;
+	const struct kvec *tail = xdr->tail;
+	struct kvec rm = {
+		.iov_base	= &marker,
+		.iov_len	= sizeof(marker),
+	};
+	int flags, ret;
+
+	*sentp = 0;
+	xdr_alloc_bvec(xdr, GFP_KERNEL);
+
+	msg->msg_flags = MSG_MORE;
+	ret = kernel_sendmsg(sock, msg, &rm, 1, rm.iov_len);
+	if (ret < 0)
+		return ret;
+	*sentp += ret;
+	if (ret != rm.iov_len)
+		return -EAGAIN;
+
+	flags = head->iov_len < xdr->len ? MSG_MORE | MSG_SENDPAGE_NOTLAST : 0;
+	ret = svc_tcp_send_kvec(sock, head, flags);
+	if (ret < 0)
+		return ret;
+	*sentp += ret;
+	if (ret != head->iov_len)
+		goto out;
+
+	if (xdr->page_len) {
+		unsigned int offset, len, remaining;
+		struct bio_vec *bvec;
+
+		bvec = xdr->bvec;
+		offset = xdr->page_base;
+		remaining = xdr->page_len;
+		flags = MSG_MORE | MSG_SENDPAGE_NOTLAST;
+		while (remaining > 0) {
+			if (remaining <= PAGE_SIZE && tail->iov_len == 0)
+				flags = 0;
+			len = min(remaining, bvec->bv_len);
+			ret = kernel_sendpage(sock, bvec->bv_page,
+					      bvec->bv_offset + offset,
+					      len, flags);
+			if (ret < 0)
+				return ret;
+			*sentp += ret;
+			if (ret != len)
+				goto out;
+			remaining -= len;
+			offset = 0;
+			bvec++;
+		}
+	}
+
+	if (tail->iov_len) {
+		ret = svc_tcp_send_kvec(sock, tail, 0);
+		if (ret < 0)
+			return ret;
+		*sentp += ret;
+	}
+
+out:
+	return 0;
+}
+
 /**
  * svc_tcp_sendto - Send out a reply on a TCP socket
  * @rqstp: completed svc_rqst
@@ -1089,7 +1173,7 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
 	mutex_lock(&xprt->xpt_mutex);
 	if (svc_xprt_is_dead(xprt))
 		goto out_notconn;
-	err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, marker, &sent);
+	err = svc_tcp_sendmsg(svsk->sk_sock, &msg, xdr, marker, &sent);
 	xdr_free_bvec(xdr);
 	trace_svcsock_tcp_send(xprt, err < 0 ? err : sent);
 	if (err < 0 || sent != (xdr->len + sizeof(marker)))
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 6ae2140eb4f7..115109259430 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1030,7 +1030,6 @@ void tipc_link_reset(struct tipc_link *l)
 int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 		   struct sk_buff_head *xmitq)
 {
-	struct tipc_msg *hdr = buf_msg(skb_peek(list));
 	struct sk_buff_head *backlogq = &l->backlogq;
 	struct sk_buff_head *transmq = &l->transmq;
 	struct sk_buff *skb, *_skb;
@@ -1038,13 +1037,18 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 	u16 ack = l->rcv_nxt - 1;
 	u16 seqno = l->snd_nxt;
 	int pkt_cnt = skb_queue_len(list);
-	int imp = msg_importance(hdr);
 	unsigned int mss = tipc_link_mss(l);
 	unsigned int cwin = l->window;
 	unsigned int mtu = l->mtu;
+	struct tipc_msg *hdr;
 	bool new_bundle;
 	int rc = 0;
+	int imp;
+
+	if (pkt_cnt <= 0)
+		return 0;
 
+	hdr = buf_msg(skb_peek(list));
 	if (unlikely(msg_size(hdr) > mtu)) {
 		pr_warn("Too large msg, purging xmit list %d %d %d %d %d!\n",
 			skb_queue_len(list), msg_user(hdr),
@@ -1053,6 +1057,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 		return -EMSGSIZE;
 	}
 
+	imp = msg_importance(hdr);
 	/* Allow oversubscription of one data msg per source at congestion */
 	if (unlikely(l->backlog[imp].len >= l->backlog[imp].limit)) {
 		if (imp == TIPC_SYSTEM_IMPORTANCE) {
@@ -2539,7 +2544,7 @@ void tipc_link_set_queue_limits(struct tipc_link *l, u32 min_win, u32 max_win)
 }
 
 /**
- * link_reset_stats - reset link statistics
+ * tipc_link_reset_stats - reset link statistics
  * @l: pointer to link
  */
 void tipc_link_reset_stats(struct tipc_link *l)
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 83d9eb830592..008670d1f43e 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1665,7 +1665,7 @@ static void tipc_lxc_xmit(struct net *peer_net, struct sk_buff_head *list)
 }
 
 /**
- * tipc_node_xmit() is the general link level function for message sending
+ * tipc_node_xmit() - general link level function for message sending
  * @net: the applicable net namespace
  * @list: chain of buffers containing message
  * @dnode: address of destination node