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

Pull networking fixes from David Miller:

 1) Several nf_flow_table_offload fixes from Pablo Neira Ayuso,
    including adding a missing ipv6 match description.

 2) Several heap overflow fixes in mwifiex from qize wang and Ganapathi
    Bhat.

 3) Fix uninit value in bond_neigh_init(), from Eric Dumazet.

 4) Fix non-ACPI probing of nxp-nci, from Stephan Gerhold.

 5) Fix use after free in tipc_disc_rcv(), from Tuong Lien.

 6) Enforce limit of 33 tail calls in mips and riscv JIT, from Paul
    Chaignon.

 7) Multicast MAC limit test is off by one in qede, from Manish Chopra.

 8) Fix established socket lookup race when socket goes from
    TCP_ESTABLISHED to TCP_LISTEN, because there lacks an intervening
    RCU grace period. From Eric Dumazet.

 9) Don't send empty SKBs from tcp_write_xmit(), also from Eric Dumazet.

10) Fix active backup transition after link failure in bonding, from
    Mahesh Bandewar.

11) Avoid zero sized hash table in gtp driver, from Taehee Yoo.

12) Fix wrong interface passed to ->mac_link_up(), from Russell King.

13) Fix DSA egress flooding settings in b53, from Florian Fainelli.

14) Memory leak in gmac_setup_txqs(), from Navid Emamdoost.

15) Fix double free in dpaa2-ptp code, from Ioana Ciornei.

16) Reject invalid MTU values in stmmac, from Jose Abreu.

17) Fix refcount leak in error path of u32 classifier, from Davide
    Caratti.

18) Fix regression causing iwlwifi firmware crashes on boot, from Anders
    Kaseorg.

19) Fix inverted return value logic in llc2 code, from Chan Shu Tak.

20) Disable hardware GRO when XDP is attached to qede, frm Manish
    Chopra.

21) Since we encode state in the low pointer bits, dst metrics must be
    at least 4 byte aligned, which is not necessarily true on m68k. Add
    annotations to fix this, from Geert Uytterhoeven.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (160 commits)
  sfc: Include XDP packet headroom in buffer step size.
  sfc: fix channel allocation with brute force
  net: dst: Force 4-byte alignment of dst_metrics
  selftests: pmtu: fix init mtu value in description
  hv_netvsc: Fix unwanted rx_table reset
  net: phy: ensure that phy IDs are correctly typed
  mod_devicetable: fix PHY module format
  qede: Disable hardware gro when xdp prog is installed
  net: ena: fix issues in setting interrupt moderation params in ethtool
  net: ena: fix default tx interrupt moderation interval
  net/smc: unregister ib devices in reboot_event
  net: stmmac: platform: Fix MDIO init for platforms without PHY
  llc2: Fix return statement of llc_stat_ev_rx_null_dsap_xid_c (and _test_c)
  net: hisilicon: Fix a BUG trigered by wrong bytes_compl
  net: dsa: ksz: use common define for tag len
  s390/qeth: don't return -ENOTSUPP to userspace
  s390/qeth: fix promiscuous mode after reset
  s390/qeth: handle error due to unsupported transport mode
  cxgb4: fix refcount init for TC-MQPRIO offload
  tc-testing: initial tdc selftests for cls_u32
  ...

6 files changed, 31 insertions, 21 deletions

diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index af154977904c..f11e997e517b 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -911,11 +911,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
 
 		for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
 			struct inet_listen_hashbucket *ilb;
+			struct hlist_nulls_node *node;
 
 			num = 0;
 			ilb = &hashinfo->listening_hash[i];
 			spin_lock(&ilb->lock);
-			sk_for_each(sk, &ilb->head) {
+			sk_nulls_for_each(sk, node, &ilb->nulls_head) {
 				struct inet_sock *inet = inet_sk(sk);
 
 				if (!net_eq(sock_net(sk), net))
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 83fb00153018..2bbaaf0c7176 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -516,10 +516,11 @@ static int inet_reuseport_add_sock(struct sock *sk,
 				   struct inet_listen_hashbucket *ilb)
 {
 	struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash;
+	const struct hlist_nulls_node *node;
 	struct sock *sk2;
 	kuid_t uid = sock_i_uid(sk);
 
-	sk_for_each_rcu(sk2, &ilb->head) {
+	sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) {
 		if (sk2 != sk &&
 		    sk2->sk_family == sk->sk_family &&
 		    ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&
@@ -555,9 +556,9 @@ int __inet_hash(struct sock *sk, struct sock *osk)
 	}
 	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
 		sk->sk_family == AF_INET6)
-		hlist_add_tail_rcu(&sk->sk_node, &ilb->head);
+		__sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head);
 	else
-		hlist_add_head_rcu(&sk->sk_node, &ilb->head);
+		__sk_nulls_add_node_rcu(sk, &ilb->nulls_head);
 	inet_hash2(hashinfo, sk);
 	ilb->count++;
 	sock_set_flag(sk, SOCK_RCU_FREE);
@@ -606,11 +607,9 @@ void inet_unhash(struct sock *sk)
 		reuseport_detach_sock(sk);
 	if (ilb) {
 		inet_unhash2(hashinfo, sk);
-		 __sk_del_node_init(sk);
-		 ilb->count--;
-	} else {
-		__sk_nulls_del_node_init_rcu(sk);
+		ilb->count--;
 	}
+	__sk_nulls_del_node_init_rcu(sk);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 unlock:
 	spin_unlock_bh(lock);
@@ -750,7 +749,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h)
 
 	for (i = 0; i < INET_LHTABLE_SIZE; i++) {
 		spin_lock_init(&h->listening_hash[i].lock);
-		INIT_HLIST_HEAD(&h->listening_hash[i].head);
+		INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head,
+				      i + LISTENING_NULLS_BASE);
 		h->listening_hash[i].count = 0;
 	}
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3e50ac24fe41..d885ba868822 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1087,8 +1087,7 @@ do_error:
 		goto out;
 out_err:
 	/* make sure we wake any epoll edge trigger waiter */
-	if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 &&
-		     err == -EAGAIN)) {
+	if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
 		sk->sk_write_space(sk);
 		tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
 	}
@@ -1419,8 +1418,7 @@ out_err:
 	sock_zerocopy_put_abort(uarg, true);
 	err = sk_stream_error(sk, flags, err);
 	/* make sure we wake any epoll edge trigger waiter */
-	if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 &&
-		     err == -EAGAIN)) {
+	if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
 		sk->sk_write_space(sk);
 		tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
 	}
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 32772d6ded4e..a6545ef0d27b 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -306,7 +306,8 @@ static u32 bbr_tso_segs_goal(struct sock *sk)
 	/* Sort of tcp_tso_autosize() but ignoring
 	 * driver provided sk_gso_max_size.
 	 */
-	bytes = min_t(unsigned long, sk->sk_pacing_rate >> sk->sk_pacing_shift,
+	bytes = min_t(unsigned long,
+		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift),
 		      GSO_MAX_SIZE - 1 - MAX_TCP_HEADER);
 	segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk));
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 92282f98dc82..1c7326e04f9b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2147,13 +2147,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
 	struct inet_listen_hashbucket *ilb;
+	struct hlist_nulls_node *node;
 	struct sock *sk = cur;
 
 	if (!sk) {
 get_head:
 		ilb = &tcp_hashinfo.listening_hash[st->bucket];
 		spin_lock(&ilb->lock);
-		sk = sk_head(&ilb->head);
+		sk = sk_nulls_head(&ilb->nulls_head);
 		st->offset = 0;
 		goto get_sk;
 	}
@@ -2161,9 +2162,9 @@ get_head:
 	++st->num;
 	++st->offset;
 
-	sk = sk_next(sk);
+	sk = sk_nulls_next(sk);
 get_sk:
-	sk_for_each_from(sk) {
+	sk_nulls_for_each_from(sk, node) {
 		if (!net_eq(sock_net(sk), net))
 			continue;
 		if (sk->sk_family == afinfo->family)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b184f03d7437..1f7735ca8f22 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1725,7 +1725,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
 	u32 bytes, segs;
 
 	bytes = min_t(unsigned long,
-		      sk->sk_pacing_rate >> sk->sk_pacing_shift,
+		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift),
 		      sk->sk_gso_max_size - 1 - MAX_TCP_HEADER);
 
 	/* Goal is to send at least one packet per ms,
@@ -2260,7 +2260,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 
 	limit = max_t(unsigned long,
 		      2 * skb->truesize,
-		      sk->sk_pacing_rate >> sk->sk_pacing_shift);
+		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
 	if (sk->sk_pacing_status == SK_PACING_NONE)
 		limit = min_t(unsigned long, limit,
 			      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
@@ -2438,6 +2438,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		if (tcp_small_queue_check(sk, skb, 0))
 			break;
 
+		/* Argh, we hit an empty skb(), presumably a thread
+		 * is sleeping in sendmsg()/sk_stream_wait_memory().
+		 * We do not want to send a pure-ack packet and have
+		 * a strange looking rtx queue with empty packet(s).
+		 */
+		if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq)
+			break;
+
 		if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
 			break;
 
@@ -3121,7 +3129,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size)
  */
 void tcp_send_fin(struct sock *sk)
 {
-	struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
+	struct sk_buff *skb, *tskb, *tail = tcp_write_queue_tail(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	/* Optimization, tack on the FIN if we have one skb in write queue and
@@ -3129,6 +3137,7 @@ void tcp_send_fin(struct sock *sk)
 	 * Note: in the latter case, FIN packet will be sent after a timeout,
 	 * as TCP stack thinks it has already been transmitted.
 	 */
+	tskb = tail;
 	if (!tskb && tcp_under_memory_pressure(sk))
 		tskb = skb_rb_last(&sk->tcp_rtx_queue);
 
@@ -3136,7 +3145,7 @@ void tcp_send_fin(struct sock *sk)
 		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
 		TCP_SKB_CB(tskb)->end_seq++;
 		tp->write_seq++;
-		if (tcp_write_queue_empty(sk)) {
+		if (!tail) {
 			/* This means tskb was already sent.
 			 * Pretend we included the FIN on previous transmit.
 			 * We need to set tp->snd_nxt to the value it would have