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

Three cases of simple overlapping changes.

Signed-off-by: David S. Miller <davem@davemloft.net>

58 files changed, 362 insertions, 247 deletions

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 861ae2a165f4..5a7be3bddfa9 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -53,6 +53,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	brstats->tx_bytes += skb->len;
 	u64_stats_update_end(&brstats->syncp);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	skb->offload_fwd_mark = 0;
+#endif
 	BR_INPUT_SKB_CB(skb)->brdev = dev;
 
 	skb_reset_mac_header(skb);
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index 181a44d0f1da..f6b1c7de059d 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -115,7 +115,7 @@ br_switchdev_fdb_call_notifiers(bool adding, const unsigned char *mac,
 void
 br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type)
 {
-	if (!fdb->added_by_user)
+	if (!fdb->added_by_user || !fdb->dst)
 		return;
 
 	switch (type) {
diff --git a/net/core/datagram.c b/net/core/datagram.c
index a4d5f10d83a1..f7fb7e3f2acf 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -362,7 +362,7 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue,
 	if (flags & MSG_PEEK) {
 		err = -ENOENT;
 		spin_lock_bh(&sk_queue->lock);
-		if (skb == skb_peek(sk_queue)) {
+		if (skb->next) {
 			__skb_unlink(skb, sk_queue);
 			refcount_dec(&skb->users);
 			if (destructor)
diff --git a/net/core/dev.c b/net/core/dev.c
index 270b54754821..6f845e4fec17 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5319,6 +5319,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
 	 * Ideally, a new ndo_busy_poll_stop() could avoid another round.
 	 */
 	rc = napi->poll(napi, BUSY_POLL_BUDGET);
+	trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
 	netpoll_poll_unlock(have_poll_lock);
 	if (rc == BUSY_POLL_BUDGET)
 		__napi_schedule(napi);
@@ -5697,12 +5698,13 @@ EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu);
  * Find out if a device is linked to an upper device and return true in case
  * it is. The caller must hold the RTNL lock.
  */
-static bool netdev_has_any_upper_dev(struct net_device *dev)
+bool netdev_has_any_upper_dev(struct net_device *dev)
 {
 	ASSERT_RTNL();
 
 	return !list_empty(&dev->adj_list.upper);
 }
+EXPORT_SYMBOL(netdev_has_any_upper_dev);
 
 /**
  * netdev_master_upper_dev_get - Get master upper device
diff --git a/net/core/filter.c b/net/core/filter.c
index f9add024d92f..5912c738a7b2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3066,15 +3066,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 		   sk->sk_prot->setsockopt == tcp_setsockopt) {
 		if (optname == TCP_CONGESTION) {
 			char name[TCP_CA_NAME_MAX];
+			bool reinit = bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN;
 
 			strncpy(name, optval, min_t(long, optlen,
 						    TCP_CA_NAME_MAX-1));
 			name[TCP_CA_NAME_MAX-1] = 0;
-			ret = tcp_set_congestion_control(sk, name, false);
-			if (!ret && bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN)
-				/* replacing an existing ca */
-				tcp_reinit_congestion_control(sk,
-					inet_csk(sk)->icsk_ca_ops);
+			ret = tcp_set_congestion_control(sk, name, false, reinit);
 		} else {
 			struct tcp_sock *tp = tcp_sk(sk);
 
@@ -3102,7 +3099,6 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 				ret = -EINVAL;
 			}
 		}
-		ret = -EINVAL;
 #endif
 	} else {
 		ret = -EINVAL;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 917da73d3ab3..246ca1c81715 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1615,18 +1615,20 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
 EXPORT_SYMBOL(skb_copy_expand);
 
 /**
- *	skb_pad			-	zero pad the tail of an skb
+ *	__skb_pad		-	zero pad the tail of an skb
  *	@skb: buffer to pad
  *	@pad: space to pad
+ *	@free_on_error: free buffer on error
  *
  *	Ensure that a buffer is followed by a padding area that is zero
  *	filled. Used by network drivers which may DMA or transfer data
  *	beyond the buffer end onto the wire.
  *
- *	May return error in out of memory cases. The skb is freed on error.
+ *	May return error in out of memory cases. The skb is freed on error
+ *	if @free_on_error is true.
  */
 
-int skb_pad(struct sk_buff *skb, int pad)
+int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error)
 {
 	int err;
 	int ntail;
@@ -1655,10 +1657,11 @@ int skb_pad(struct sk_buff *skb, int pad)
 	return 0;
 
 free_skb:
-	kfree_skb(skb);
+	if (free_on_error)
+		kfree_skb(skb);
 	return err;
 }
-EXPORT_SYMBOL(skb_pad);
+EXPORT_SYMBOL(__skb_pad);
 
 /**
  *	pskb_put - add data to the tail of a potentially fragmented buffer
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index cceaa4dd9f53..873af0108e24 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -577,7 +577,7 @@ static int dsa_dst_parse(struct dsa_switch_tree *dst)
 			return err;
 	}
 
-	if (!dst->cpu_dp->netdev) {
+	if (!dst->cpu_dp) {
 		pr_warn("Tree has no master device\n");
 		return -EINVAL;
 	}
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 17f30675c15c..010ca0a336c4 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -42,7 +42,8 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev)
 	padlen = (skb->len >= ETH_ZLEN) ? 0 : ETH_ZLEN - skb->len;
 
 	if (skb_tailroom(skb) >= padlen + KSZ_INGRESS_TAG_LEN) {
-		if (skb_put_padto(skb, skb->len + padlen))
+		/* Let dsa_slave_xmit() free skb */
+		if (__skb_put_padto(skb, skb->len + padlen, false))
 			return NULL;
 
 		nskb = skb;
@@ -60,12 +61,13 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev)
 					 skb_transport_header(skb) - skb->head);
 		skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len));
 
-		if (skb_put_padto(nskb, nskb->len + padlen)) {
-			kfree_skb(nskb);
+		/* Let skb_put_padto() free nskb, and let dsa_slave_xmit() free
+		 * skb
+		 */
+		if (skb_put_padto(nskb, nskb->len + padlen))
 			return NULL;
-		}
 
-		kfree_skb(skb);
+		consume_skb(skb);
 	}
 
 	tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN);
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 8707157dea32..d2fd4923aa3e 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -40,7 +40,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_set_network_header(nskb, skb_network_header(skb) - skb->head);
 	skb_set_transport_header(nskb, skb_transport_header(skb) - skb->head);
 	skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len));
-	kfree_skb(skb);
+	consume_skb(skb);
 
 	if (padlen) {
 		skb_put_zero(nskb, padlen);
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 4e7bdb213cd0..172d8309f89e 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -314,7 +314,8 @@ static void send_hsr_supervision_frame(struct hsr_port *master,
 	hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload));
 	ether_addr_copy(hsr_sp->MacAddressA, master->dev->dev_addr);
 
-	skb_put_padto(skb, ETH_ZLEN + HSR_HLEN);
+	if (skb_put_padto(skb, ETH_ZLEN + HSR_HLEN))
+		return;
 
 	hsr_forward_skb(skb, master);
 	return;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 319000573bc7..b00e4a43b4dc 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -258,7 +258,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 		esp_output_udp_encap(x, skb, esp);
 
 	if (!skb_cloned(skb)) {
-		if (tailen <= skb_availroom(skb)) {
+		if (tailen <= skb_tailroom(skb)) {
 			nfrags = 1;
 			trailer = skb;
 			tail = skb_tail_pointer(trailer);
@@ -292,8 +292,6 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 
 			kunmap_atomic(vaddr);
 
-			spin_unlock_bh(&x->lock);
-
 			nfrags = skb_shinfo(skb)->nr_frags;
 
 			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
@@ -301,6 +299,9 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			skb_shinfo(skb)->nr_frags = ++nfrags;
 
 			pfrag->offset = pfrag->offset + allocsize;
+
+			spin_unlock_bh(&x->lock);
+
 			nfrags++;
 
 			skb->len += tailen;
@@ -381,7 +382,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 		           (unsigned char *)esph - skb->data,
 		           assoclen + ivlen + esp->clen + alen);
 	if (unlikely(err < 0))
-		goto error;
+		goto error_free;
 
 	if (!esp->inplace) {
 		int allocsize;
@@ -392,7 +393,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 		spin_lock_bh(&x->lock);
 		if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
 			spin_unlock_bh(&x->lock);
-			goto error;
+			goto error_free;
 		}
 
 		skb_shinfo(skb)->nr_frags = 1;
@@ -409,7 +410,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			           (unsigned char *)esph - skb->data,
 			           assoclen + ivlen + esp->clen + alen);
 		if (unlikely(err < 0))
-			goto error;
+			goto error_free;
 	}
 
 	if ((x->props.flags & XFRM_STATE_ESN))
@@ -442,8 +443,9 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 
 	if (sg != dsg)
 		esp_ssg_unref(x, tmp);
-	kfree(tmp);
 
+error_free:
+	kfree(tmp);
 error:
 	return err;
 }
@@ -727,8 +729,10 @@ skip_cow:
 
 	sg_init_table(sg, nfrags);
 	err = skb_to_sgvec(skb, sg, 0, skb->len);
-	if (unlikely(err < 0))
+	if (unlikely(err < 0)) {
+		kfree(tmp);
 		goto out;
+	}
 
 	skb->ip_summed = CHECKSUM_NONE;
 
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index aca1c85f0795..f8b918c766b0 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -259,7 +259,7 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_
 	esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32));
 
 	err = esp_output_tail(x, skb, &esp);
-	if (err < 0)
+	if (err)
 		return err;
 
 	secpath_reset(skb);
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 0bc3c3d73e61..9e9d9afd18f7 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -268,14 +268,14 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 		acpar.targinfo = t->data;
 		verdict = t->u.kernel.target->target(skb, &acpar);
 
-		/* Target might have changed stuff. */
-		arp = arp_hdr(skb);
-
-		if (verdict == XT_CONTINUE)
+		if (verdict == XT_CONTINUE) {
+			/* Target might have changed stuff. */
+			arp = arp_hdr(skb);
 			e = arpt_next_entry(e);
-		else
+		} else {
 			/* Verdict */
 			break;
+		}
 	} while (!acpar.hotdrop);
 	xt_write_recseq_end(addend);
 	local_bh_enable();
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 2a55a40211cb..622ed2887cd5 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -352,13 +352,14 @@ ipt_do_table(struct sk_buff *skb,
 		acpar.targinfo = t->data;
 
 		verdict = t->u.kernel.target->target(skb, &acpar);
-		/* Target might have changed stuff. */
-		ip = ip_hdr(skb);
-		if (verdict == XT_CONTINUE)
+		if (verdict == XT_CONTINUE) {
+			/* Target might have changed stuff. */
+			ip = ip_hdr(skb);
 			e = ipt_next_entry(e);
-		else
+		} else {
 			/* Verdict */
 			break;
+		}
 	} while (!acpar.hotdrop);
 
 	xt_write_recseq_end(addend);
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 7d72decb80f9..efaa04dcc80e 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -117,7 +117,8 @@ clusterip_config_entry_put(struct net *net, struct clusterip_config *c)
 		 * functions are also incrementing the refcount on their own,
 		 * so it's safe to remove the entry even if it's in use. */
 #ifdef CONFIG_PROC_FS
-		proc_remove(c->pde);
+		if (cn->procdir)
+			proc_remove(c->pde);
 #endif
 		return;
 	}
@@ -815,6 +816,7 @@ static void clusterip_net_exit(struct net *net)
 #ifdef CONFIG_PROC_FS
 	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
 	proc_remove(cn->procdir);
+	cn->procdir = NULL;
 #endif
 	nf_unregister_net_hook(net, &cip_arp_ops);
 }
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 21ca2df274c5..7a3d84375836 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2498,7 +2498,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		name[val] = 0;
 
 		lock_sock(sk);
-		err = tcp_set_congestion_control(sk, name, true);
+		err = tcp_set_congestion_control(sk, name, true, true);
 		release_sock(sk);
 		return err;
 	}
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index c2b174469645..2f26124fd160 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -189,8 +189,8 @@ void tcp_init_congestion_control(struct sock *sk)
 		INET_ECN_dontxmit(sk);
 }
 
-void tcp_reinit_congestion_control(struct sock *sk,
-				   const struct tcp_congestion_ops *ca)
+static void tcp_reinit_congestion_control(struct sock *sk,
+					  const struct tcp_congestion_ops *ca)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -338,7 +338,7 @@ out:
  * tcp_reinit_congestion_control (if the current congestion control was
  * already initialized.
  */
-int tcp_set_congestion_control(struct sock *sk, const char *name, bool load)
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_congestion_ops *ca;
@@ -360,9 +360,18 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load)
 	if (!ca) {
 		err = -ENOENT;
 	} else if (!load) {
-		icsk->icsk_ca_ops = ca;
-		if (!try_module_get(ca->owner))
+		const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops;
+
+		if (try_module_get(ca->owner)) {
+			if (reinit) {
+				tcp_reinit_congestion_control(sk, ca);
+			} else {
+				icsk->icsk_ca_ops = ca;
+				module_put(old_ca->owner);
+			}
+		} else {
 			err = -EBUSY;
+		}
 	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
 		     ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) {
 		err = -EPERM;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index bf6c406bf5e7..f900cdd0fbfb 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1933,14 +1933,16 @@ drop:
 /* For TCP sockets, sk_rx_dst is protected by socket lock
  * For UDP, we use xchg() to guard against concurrent changes.
  */
-void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
+bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 {
 	struct dst_entry *old;
 
 	if (dst_hold_safe(dst)) {
 		old = xchg(&sk->sk_rx_dst, dst);
 		dst_release(old);
+		return old != dst;
 	}
+	return false;
 }
 EXPORT_SYMBOL(udp_sk_rx_dst_set);
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 45d0a24644de..c2e2a78787ec 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5514,7 +5514,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 		 * our DAD process, so we don't need
 		 * to do it again
 		 */
-		if (!(ifp->rt->rt6i_node))
+		if (!rcu_access_pointer(ifp->rt->rt6i_node))
 			ip6_ins_rt(ifp->rt);
 		if (ifp->idev->cnf.forwarding)
 			addrconf_join_anycast(ifp);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 7fb41b0ad437..89910e2c10f4 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -226,7 +226,7 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 	int tailen = esp->tailen;
 
 	if (!skb_cloned(skb)) {
-		if (tailen <= skb_availroom(skb)) {
+		if (tailen <= skb_tailroom(skb)) {
 			nfrags = 1;
 			trailer = skb;
 			tail = skb_tail_pointer(trailer);
@@ -260,8 +260,6 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 
 			kunmap_atomic(vaddr);
 
-			spin_unlock_bh(&x->lock);
-
 			nfrags = skb_shinfo(skb)->nr_frags;
 
 			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
@@ -269,6 +267,9 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 			skb_shinfo(skb)->nr_frags = ++nfrags;
 
 			pfrag->offset = pfrag->offset + allocsize;
+
+			spin_unlock_bh(&x->lock);
+
 			nfrags++;
 
 			skb->len += tailen;
@@ -345,7 +346,7 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 		           (unsigned char *)esph - skb->data,
 		           assoclen + ivlen + esp->clen + alen);
 	if (unlikely(err < 0))
-		goto error;
+		goto error_free;
 
 	if (!esp->inplace) {
 		int allocsize;
@@ -356,7 +357,7 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 		spin_lock_bh(&x->lock);
 		if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
 			spin_unlock_bh(&x->lock);
-			goto error;
+			goto error_free;
 		}
 
 		skb_shinfo(skb)->nr_frags = 1;
@@ -373,7 +374,7 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 			           (unsigned char *)esph - skb->data,
 			           assoclen + ivlen + esp->clen + alen);
 		if (unlikely(err < 0))
-			goto error;
+			goto error_free;
 	}
 
 	if ((x->props.flags & XFRM_STATE_ESN))
@@ -406,8 +407,9 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 
 	if (sg != dsg)
 		esp_ssg_unref(x, tmp);
-	kfree(tmp);
 
+error_free:
+	kfree(tmp);
 error:
 	return err;
 }
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 8d4e2ba9163d..333a478aa161 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -288,7 +288,7 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features
 	esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32));
 
 	err = esp6_output_tail(x, skb, &esp);
-	if (err < 0)
+	if (err)
 		return err;
 
 	secpath_reset(skb);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 549aacc3cb2c..a3b5c163325f 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -149,11 +149,23 @@ static struct fib6_node *node_alloc(void)
 	return fn;
 }
 
-static void node_free(struct fib6_node *fn)
+static void node_free_immediate(struct fib6_node *fn)
+{
+	kmem_cache_free(fib6_node_kmem, fn);
+}
+
+static void node_free_rcu(struct rcu_head *head)
 {
+	struct fib6_node *fn = container_of(head, struct fib6_node, rcu);
+
 	kmem_cache_free(fib6_node_kmem, fn);
 }
 
+static void node_free(struct fib6_node *fn)
+{
+	call_rcu(&fn->rcu, node_free_rcu);
+}
+
 void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
 {
 	int cpu;
@@ -697,9 +709,9 @@ insert_above:
 
 		if (!in || !ln) {
 			if (in)
-				node_free(in);
+				node_free_immediate(in);
 			if (ln)
-				node_free(ln);
+				node_free_immediate(ln);
 			return ERR_PTR(-ENOMEM);
 		}
 
@@ -971,7 +983,7 @@ add:
 
 		rt->dst.rt6_next = iter;
 		*ins = rt;
-		rt->rt6i_node = fn;
+		rcu_assign_pointer(rt->rt6i_node, fn);
 		atomic_inc(&rt->rt6i_ref);
 		call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_ADD,
 					  rt);
@@ -999,7 +1011,7 @@ add:
 			return err;
 
 		*ins = rt;
-		rt->rt6i_node = fn;
+		rcu_assign_pointer(rt->rt6i_node, fn);
 		rt->dst.rt6_next = iter->dst.rt6_next;
 		atomic_inc(&rt->rt6i_ref);
 		call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE,
@@ -1138,7 +1150,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 				   root, and then (in failure) stale node
 				   in main tree.
 				 */
-				node_free(sfn);
+				node_free_immediate(sfn);
 				err = PTR_ERR(sn);
 				goto failure;
 			}
@@ -1569,8 +1581,9 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 
 int fib6_del(struc