Merge tag 'net-5.11-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Networking fixes for 5.11-rc7, including fixes from bpf and mac80211
  trees.

  Current release - regressions:

   - ip_tunnel: fix mtu calculation

   - mlx5: fix function calculation for page trees

  Previous releases - regressions:

   - vsock: fix the race conditions in multi-transport support

   - neighbour: prevent a dead entry from updating gc_list

   - dsa: mv88e6xxx: override existent unicast portvec in port_fdb_add

  Previous releases - always broken:

   - bpf, cgroup: two copy_{from,to}_user() warn_on_once splats for BPF
     cgroup getsockopt infra when user space is trying to race against
     optlen, from Loris Reiff.

   - bpf: add missing fput() in BPF inode storage map update helper

   - udp: ipv4: manipulate network header of NATed UDP GRO fraglist

   - mac80211: fix station rate table updates on assoc

   - r8169: work around RTL8125 UDP HW bug

   - igc: report speed and duplex as unknown when device is runtime
     suspended

   - rxrpc: fix deadlock around release of dst cached on udp tunnel"

* tag 'net-5.11-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (36 commits)
  net: hsr: align sup_multicast_addr in struct hsr_priv to u16 boundary
  net: ipa: fix two format specifier errors
  net: ipa: use the right accessor in ipa_endpoint_status_skip()
  net: ipa: be explicit about endianness
  net: ipa: add a missing __iomem attribute
  net: ipa: pass correct dma_handle to dma_free_coherent()
  r8169: fix WoL on shutdown if CONFIG_DEBUG_SHIRQ is set
  net/rds: restrict iovecs length for RDS_CMSG_RDMA_ARGS
  net: mvpp2: TCAM entry enable should be written after SRAM data
  net: lapb: Copy the skb before sending a packet
  net/mlx5e: Release skb in case of failure in tc update skb
  net/mlx5e: Update max_opened_tc also when channels are closed
  net/mlx5: Fix leak upon failure of rule creation
  net/mlx5: Fix function calculation for page trees
  docs: networking: swap words in icmp_errors_use_inbound_ifaddr doc
  udp: ipv4: manipulate network header of NATed UDP GRO fraglist
  net: ip_tunnel: fix mtu calculation
  vsock: fix the race conditions in multi-transport support
  net: sched: replaced invalid qdisc tree flush helper in qdisc_replace
  ibmvnic: device remove has higher precedence over reset
  ...

11 files changed, 106 insertions, 30 deletions

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 277ed854aef1..6d2d557442dc 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1245,13 +1245,14 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
 	old    = neigh->nud_state;
 	err    = -EPERM;
 
-	if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
-	    (old & (NUD_NOARP | NUD_PERMANENT)))
-		goto out;
 	if (neigh->dead) {
 		NL_SET_ERR_MSG(extack, "Neighbor entry is now dead");
+		new = old;
 		goto out;
 	}
+	if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
+	    (old & (NUD_NOARP | NUD_PERMANENT)))
+		goto out;
 
 	ext_learn_change = neigh_update_ext_learned(neigh, flags, &notify);
 
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index 7dc92ce5a134..a9c30a608e35 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -217,7 +217,10 @@ struct hsr_priv {
 	u8 net_id;		/* for PRP, it occupies most significant 3 bits
 				 * of lan_id
 				 */
-	unsigned char		sup_multicast_addr[ETH_ALEN];
+	unsigned char		sup_multicast_addr[ETH_ALEN] __aligned(sizeof(u16));
+				/* Align to u16 boundary to avoid unaligned access
+				 * in ether_addr_equal
+				 */
 #ifdef	CONFIG_DEBUG_FS
 	struct dentry *node_tbl_root;
 #endif
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 64594aa755f0..76a420c76f16 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -317,7 +317,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 	}
 
 	dev->needed_headroom = t_hlen + hlen;
-	mtu -= (dev->hard_header_len + t_hlen);
+	mtu -= t_hlen;
 
 	if (mtu < IPV4_MIN_MTU)
 		mtu = IPV4_MIN_MTU;
@@ -347,7 +347,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 	nt = netdev_priv(dev);
 	t_hlen = nt->hlen + sizeof(struct iphdr);
 	dev->min_mtu = ETH_MIN_MTU;
-	dev->max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
+	dev->max_mtu = IP_MAX_MTU - t_hlen;
 	ip_tunnel_add(itn, nt);
 	return nt;
 
@@ -488,11 +488,10 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	int mtu;
 
 	tunnel_hlen = md ? tunnel_hlen : tunnel->hlen;
-	pkt_size = skb->len - tunnel_hlen - dev->hard_header_len;
+	pkt_size = skb->len - tunnel_hlen;
 
 	if (df)
-		mtu = dst_mtu(&rt->dst) - dev->hard_header_len
-					- sizeof(struct iphdr) - tunnel_hlen;
+		mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen);
 	else
 		mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
 
@@ -972,7 +971,7 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
-	int max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
+	int max_mtu = IP_MAX_MTU - t_hlen;
 
 	if (new_mtu < ETH_MIN_MTU)
 		return -EINVAL;
@@ -1149,10 +1148,9 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 
 	mtu = ip_tunnel_bind_dev(dev);
 	if (tb[IFLA_MTU]) {
-		unsigned int max = IP_MAX_MTU - dev->hard_header_len - nt->hlen;
+		unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr));
 
-		mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU,
-			    (unsigned int)(max - sizeof(struct iphdr)));
+		mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max);
 	}
 
 	err = dev_set_mtu(dev, mtu);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index ff39e94781bf..cfc872689b99 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -187,8 +187,67 @@ out_unlock:
 }
 EXPORT_SYMBOL(skb_udp_tunnel_segment);
 
+static void __udpv4_gso_segment_csum(struct sk_buff *seg,
+				     __be32 *oldip, __be32 *newip,
+				     __be16 *oldport, __be16 *newport)
+{
+	struct udphdr *uh;
+	struct iphdr *iph;
+
+	if (*oldip == *newip && *oldport == *newport)
+		return;
+
+	uh = udp_hdr(seg);
+	iph = ip_hdr(seg);
+
+	if (uh->check) {
+		inet_proto_csum_replace4(&uh->check, seg, *oldip, *newip,
+					 true);
+		inet_proto_csum_replace2(&uh->check, seg, *oldport, *newport,
+					 false);
+		if (!uh->check)
+			uh->check = CSUM_MANGLED_0;
+	}
+	*oldport = *newport;
+
+	csum_replace4(&iph->check, *oldip, *newip);
+	*oldip = *newip;
+}
+
+static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs)
+{
+	struct sk_buff *seg;
+	struct udphdr *uh, *uh2;
+	struct iphdr *iph, *iph2;
+
+	seg = segs;
+	uh = udp_hdr(seg);
+	iph = ip_hdr(seg);
+
+	if ((udp_hdr(seg)->dest == udp_hdr(seg->next)->dest) &&
+	    (udp_hdr(seg)->source == udp_hdr(seg->next)->source) &&
+	    (ip_hdr(seg)->daddr == ip_hdr(seg->next)->daddr) &&
+	    (ip_hdr(seg)->saddr == ip_hdr(seg->next)->saddr))
+		return segs;
+
+	while ((seg = seg->next)) {
+		uh2 = udp_hdr(seg);
+		iph2 = ip_hdr(seg);
+
+		__udpv4_gso_segment_csum(seg,
+					 &iph2->saddr, &iph->saddr,
+					 &uh2->source, &uh->source);
+		__udpv4_gso_segment_csum(seg,
+					 &iph2->daddr, &iph->daddr,
+					 &uh2->dest, &uh->dest);
+	}
+
+	return segs;
+}
+
 static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
-					      netdev_features_t features)
+					      netdev_features_t features,
+					      bool is_ipv6)
 {
 	unsigned int mss = skb_shinfo(skb)->gso_size;
 
@@ -198,11 +257,11 @@ static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
 
 	udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss);
 
-	return skb;
+	return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb);
 }
 
 struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
-				  netdev_features_t features)
+				  netdev_features_t features, bool is_ipv6)
 {
 	struct sock *sk = gso_skb->sk;
 	unsigned int sum_truesize = 0;
@@ -214,7 +273,7 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 	__be16 newlen;
 
 	if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST)
-		return __udp_gso_segment_list(gso_skb, features);
+		return __udp_gso_segment_list(gso_skb, features, is_ipv6);
 
 	mss = skb_shinfo(gso_skb)->gso_size;
 	if (gso_skb->len <= sizeof(*uh) + mss)
@@ -328,7 +387,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 		goto out;
 
 	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
-		return __udp_gso_segment(skb, features);
+		return __udp_gso_segment(skb, features, false);
 
 	mss = skb_shinfo(skb)->gso_size;
 	if (unlikely(skb->len <= mss))
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index c7bd7b1a04c1..faa823c24292 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -42,7 +42,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 			goto out;
 
 		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
-			return __udp_gso_segment(skb, features);
+			return __udp_gso_segment(skb, features, true);
 
 		mss = skb_shinfo(skb)->gso_size;
 		if (unlikely(skb->len <= mss))
diff --git a/net/lapb/lapb_out.c b/net/lapb/lapb_out.c
index 7a4d0715d1c3..a966d29c772d 100644
--- a/net/lapb/lapb_out.c
+++ b/net/lapb/lapb_out.c
@@ -82,7 +82,8 @@ void lapb_kick(struct lapb_cb *lapb)
 		skb = skb_dequeue(&lapb->write_queue);
 
 		do {
-			if ((skbn = skb_clone(skb, GFP_ATOMIC)) == NULL) {
+			skbn = skb_copy(skb, GFP_ATOMIC);
+			if (!skbn) {
 				skb_queue_head(&lapb->write_queue, skb);
 				break;
 			}
diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index c9a8a2433e8a..48322e45e7dd 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -125,8 +125,11 @@ int drv_sta_state(struct ieee80211_local *local,
 	} else if (old_state == IEEE80211_STA_AUTH &&
 		   new_state == IEEE80211_STA_ASSOC) {
 		ret = drv_sta_add(local, sdata, &sta->sta);
-		if (ret == 0)
+		if (ret == 0) {
 			sta->uploaded = true;
+			if (rcu_access_pointer(sta->sta.rates))
+				drv_sta_rate_tbl_update(local, sdata, &sta->sta);
+		}
 	} else if (old_state == IEEE80211_STA_ASSOC &&
 		   new_state == IEEE80211_STA_AUTH) {
 		drv_sta_remove(local, sdata, &sta->sta);
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 45927202c71c..63652c39c8e0 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -960,7 +960,8 @@ int rate_control_set_rates(struct ieee80211_hw *hw,
 	if (old)
 		kfree_rcu(old, rcu_head);
 
-	drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta);
+	if (sta->uploaded)
+		drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta);
 
 	ieee80211_sta_set_expected_throughput(pubsta, sta_get_expected_throughput(sta));
 
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 1d0afb1dd77b..6f1a50d50d06 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -565,6 +565,9 @@ int rds_rdma_extra_size(struct rds_rdma_args *args,
 	if (args->nr_local == 0)
 		return -EINVAL;
 
+	if (args->nr_local > UIO_MAXIOV)
+		return -EMSGSIZE;
+
 	iov->iov = kcalloc(args->nr_local,
 			   sizeof(struct rds_iovec),
 			   GFP_KERNEL);
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 0a2f4817ec6c..41671af6b33f 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -990,7 +990,7 @@ static int __init af_rxrpc_init(void)
 		goto error_security;
 	}
 
-	ret = register_pernet_subsys(&rxrpc_net_ops);
+	ret = register_pernet_device(&rxrpc_net_ops);
 	if (ret)
 		goto error_pernet;
 
@@ -1035,7 +1035,7 @@ error_key_type:
 error_sock:
 	proto_unregister(&rxrpc_proto);
 error_proto:
-	unregister_pernet_subsys(&rxrpc_net_ops);
+	unregister_pernet_device(&rxrpc_net_ops);
 error_pernet:
 	rxrpc_exit_security();
 error_security:
@@ -1057,7 +1057,7 @@ static void __exit af_rxrpc_exit(void)
 	unregister_key_type(&key_type_rxrpc);
 	sock_unregister(PF_RXRPC);
 	proto_unregister(&rxrpc_proto);
-	unregister_pernet_subsys(&rxrpc_net_ops);
+	unregister_pernet_device(&rxrpc_net_ops);
 	ASSERTCMP(atomic_read(&rxrpc_n_tx_skbs), ==, 0);
 	ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0);
 
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index b12d3a322242..6894f21dc147 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1014,9 +1014,12 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock,
 			mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
 
 	} else if (sock->type == SOCK_STREAM) {
-		const struct vsock_transport *transport = vsk->transport;
+		const struct vsock_transport *transport;
+
 		lock_sock(sk);
 
+		transport = vsk->transport;
+
 		/* Listening sockets that have connections in their accept
 		 * queue can be read.
 		 */
@@ -1099,10 +1102,11 @@ static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	err = 0;
 	sk = sock->sk;
 	vsk = vsock_sk(sk);
-	transport = vsk->transport;
 
 	lock_sock(sk);
 
+	transport = vsk->transport;
+
 	err = vsock_auto_bind(vsk);
 	if (err)
 		goto out;
@@ -1561,10 +1565,11 @@ static int vsock_stream_setsockopt(struct socket *sock,
 	err = 0;
 	sk = sock->sk;
 	vsk = vsock_sk(sk);
-	transport = vsk->transport;
 
 	lock_sock(sk);
 
+	transport = vsk->transport;
+
 	switch (optname) {
 	case SO_VM_SOCKETS_BUFFER_SIZE:
 		COPY_IN(val);
@@ -1697,7 +1702,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	sk = sock->sk;
 	vsk = vsock_sk(sk);
-	transport = vsk->transport;
 	total_written = 0;
 	err = 0;
 
@@ -1706,6 +1710,8 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	lock_sock(sk);
 
+	transport = vsk->transport;
+
 	/* Callers should not provide a destination with stream sockets. */
 	if (msg->msg_namelen) {
 		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
@@ -1840,11 +1846,12 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	sk = sock->sk;
 	vsk = vsock_sk(sk);
-	transport = vsk->transport;
 	err = 0;
 
 	lock_sock(sk);
 
+	transport = vsk->transport;
+
 	if (!transport || sk->sk_state != TCP_ESTABLISHED) {
 		/* Recvmsg is supposed to return 0 if a peer performs an
 		 * orderly shutdown. Differentiate between that case and when a