Merge tag 'net-6.4-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Happy Wear a Dress Day.

  Fairly standard-sized batch of fixes, accounting for the lack of
  sub-tree submissions this week. The mlx5 IRQ fixes are notable, people
  were complaining about that. No fires burning.

  Current release - regressions:

   - eth: mlx5e:
      - multiple fixes for dynamic IRQ allocation
      - prevent encap offload when neigh update is running

   - eth: mana: fix perf regression: remove rx_cqes, tx_cqes counters

  Current release - new code bugs:

   - eth: mlx5e: DR, add missing mutex init/destroy in pattern manager

  Previous releases - always broken:

   - tcp: deny tcp_disconnect() when threads are waiting

   - sched: prevent ingress Qdiscs from getting installed in random
     locations in the hierarchy and moving around

   - sched: flower: fix possible OOB write in fl_set_geneve_opt()

   - netlink: fix NETLINK_LIST_MEMBERSHIPS length report

   - udp6: fix race condition in udp6_sendmsg & connect

   - tcp: fix mishandling when the sack compression is deferred

   - rtnetlink: validate link attributes set at creation time

   - mptcp: fix connect timeout handling

   - eth: stmmac: fix call trace when stmmac_xdp_xmit() is invoked

   - eth: amd-xgbe: fix the false linkup in xgbe_phy_status

   - eth: mlx5e:
      - fix corner cases in internal buffer configuration
      - drain health before unregistering devlink

   - usb: qmi_wwan: set DTR quirk for BroadMobi BM818

  Misc:

   - tcp: return user_mss for TCP_MAXSEG in CLOSE/LISTEN state if
     user_mss set"

* tag 'net-6.4-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (71 commits)
  mptcp: fix active subflow finalization
  mptcp: add annotations around sk->sk_shutdown accesses
  mptcp: fix data race around msk->first access
  mptcp: consolidate passive msk socket initialization
  mptcp: add annotations around msk->subflow accesses
  mptcp: fix connect timeout handling
  rtnetlink: add the missing IFLA_GRO_ tb check in validate_linkmsg
  rtnetlink: move IFLA_GSO_ tb check to validate_linkmsg
  rtnetlink: call validate_linkmsg in rtnl_create_link
  ice: recycle/free all of the fragments from multi-buffer frame
  net: phy: mxl-gpy: extend interrupt fix to all impacted variants
  net: renesas: rswitch: Fix return value in error path of xmit
  net: dsa: mv88e6xxx: Increase wait after reset deactivation
  net: ipa: Use correct value for IPA_STATUS_SIZE
  tcp: fix mishandling when the sack compression is deferred.
  net/sched: flower: fix possible OOB write in fl_set_geneve_opt()
  sfc: fix error unwinds in TC offload
  net/mlx5: Read embedded cpu after init bit cleared
  net/mlx5e: Fix error handling in mlx5e_refresh_tirs
  net/mlx5: Ensure af_desc.mask is properly initialized
  ...

23 files changed, 219 insertions, 134 deletions

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 653901a1bf75..41de3a2f29e1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2385,6 +2385,37 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[],
 		if (tb[IFLA_BROADCAST] &&
 		    nla_len(tb[IFLA_BROADCAST]) < dev->addr_len)
 			return -EINVAL;
+
+		if (tb[IFLA_GSO_MAX_SIZE] &&
+		    nla_get_u32(tb[IFLA_GSO_MAX_SIZE]) > dev->tso_max_size) {
+			NL_SET_ERR_MSG(extack, "too big gso_max_size");
+			return -EINVAL;
+		}
+
+		if (tb[IFLA_GSO_MAX_SEGS] &&
+		    (nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > GSO_MAX_SEGS ||
+		     nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > dev->tso_max_segs)) {
+			NL_SET_ERR_MSG(extack, "too big gso_max_segs");
+			return -EINVAL;
+		}
+
+		if (tb[IFLA_GRO_MAX_SIZE] &&
+		    nla_get_u32(tb[IFLA_GRO_MAX_SIZE]) > GRO_MAX_SIZE) {
+			NL_SET_ERR_MSG(extack, "too big gro_max_size");
+			return -EINVAL;
+		}
+
+		if (tb[IFLA_GSO_IPV4_MAX_SIZE] &&
+		    nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]) > dev->tso_max_size) {
+			NL_SET_ERR_MSG(extack, "too big gso_ipv4_max_size");
+			return -EINVAL;
+		}
+
+		if (tb[IFLA_GRO_IPV4_MAX_SIZE] &&
+		    nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]) > GRO_MAX_SIZE) {
+			NL_SET_ERR_MSG(extack, "too big gro_ipv4_max_size");
+			return -EINVAL;
+		}
 	}
 
 	if (tb[IFLA_AF_SPEC]) {
@@ -2858,11 +2889,6 @@ static int do_setlink(const struct sk_buff *skb,
 	if (tb[IFLA_GSO_MAX_SIZE]) {
 		u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]);
 
-		if (max_size > dev->tso_max_size) {
-			err = -EINVAL;
-			goto errout;
-		}
-
 		if (dev->gso_max_size ^ max_size) {
 			netif_set_gso_max_size(dev, max_size);
 			status |= DO_SETLINK_MODIFIED;
@@ -2872,11 +2898,6 @@ static int do_setlink(const struct sk_buff *skb,
 	if (tb[IFLA_GSO_MAX_SEGS]) {
 		u32 max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]);
 
-		if (max_segs > GSO_MAX_SEGS || max_segs > dev->tso_max_segs) {
-			err = -EINVAL;
-			goto errout;
-		}
-
 		if (dev->gso_max_segs ^ max_segs) {
 			netif_set_gso_max_segs(dev, max_segs);
 			status |= DO_SETLINK_MODIFIED;
@@ -2895,11 +2916,6 @@ static int do_setlink(const struct sk_buff *skb,
 	if (tb[IFLA_GSO_IPV4_MAX_SIZE]) {
 		u32 max_size = nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]);
 
-		if (max_size > dev->tso_max_size) {
-			err = -EINVAL;
-			goto errout;
-		}
-
 		if (dev->gso_ipv4_max_size ^ max_size) {
 			netif_set_gso_ipv4_max_size(dev, max_size);
 			status |= DO_SETLINK_MODIFIED;
@@ -3285,6 +3301,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 	struct net_device *dev;
 	unsigned int num_tx_queues = 1;
 	unsigned int num_rx_queues = 1;
+	int err;
 
 	if (tb[IFLA_NUM_TX_QUEUES])
 		num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]);
@@ -3320,13 +3337,18 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
+	err = validate_linkmsg(dev, tb, extack);
+	if (err < 0) {
+		free_netdev(dev);
+		return ERR_PTR(err);
+	}
+
 	dev_net_set(dev, net);
 	dev->rtnl_link_ops = ops;
 	dev->rtnl_link_state = RTNL_LINK_INITIALIZING;
 
 	if (tb[IFLA_MTU]) {
 		u32 mtu = nla_get_u32(tb[IFLA_MTU]);
-		int err;
 
 		err = dev_validate_mtu(dev, mtu, extack);
 		if (err) {
diff --git a/net/core/sock.c b/net/core/sock.c
index 5440e67bcfe3..24f2761bdb1d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2381,7 +2381,6 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 {
 	u32 max_segs = 1;
 
-	sk_dst_set(sk, dst);
 	sk->sk_route_caps = dst->dev->features;
 	if (sk_is_tcp(sk))
 		sk->sk_route_caps |= NETIF_F_GSO;
@@ -2400,6 +2399,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 		}
 	}
 	sk->sk_gso_max_segs = max_segs;
+	sk_dst_set(sk, dst);
 }
 EXPORT_SYMBOL_GPL(sk_setup_caps);
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index c4aab3aacbd8..4a76ebf793b8 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -586,6 +586,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
 
 	add_wait_queue(sk_sleep(sk), &wait);
 	sk->sk_write_pending += writebias;
+	sk->sk_wait_pending++;
 
 	/* Basic assumption: if someone sets sk->sk_err, he _must_
 	 * change state of the socket from TCP_SYN_*.
@@ -601,6 +602,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
 	}
 	remove_wait_queue(sk_sleep(sk), &wait);
 	sk->sk_write_pending -= writebias;
+	sk->sk_wait_pending--;
 	return timeo;
 }
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 65ad4251f6fd..1386787eaf1a 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1142,6 +1142,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 	if (newsk) {
 		struct inet_connection_sock *newicsk = inet_csk(newsk);
 
+		newsk->sk_wait_pending = 0;
 		inet_sk_set_state(newsk, TCP_SYN_RECV);
 		newicsk->icsk_bind_hash = NULL;
 		newicsk->icsk_bind2_hash = NULL;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a60f6f4e7cd9..8d20d9221238 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3081,6 +3081,12 @@ int tcp_disconnect(struct sock *sk, int flags)
 	int old_state = sk->sk_state;
 	u32 seq;
 
+	/* Deny disconnect if other threads are blocked in sk_wait_event()
+	 * or inet_wait_for_connect().
+	 */
+	if (sk->sk_wait_pending)
+		return -EBUSY;
+
 	if (old_state != TCP_CLOSE)
 		tcp_set_state(sk, TCP_CLOSE);
 
@@ -4072,7 +4078,8 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 	switch (optname) {
 	case TCP_MAXSEG:
 		val = tp->mss_cache;
-		if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
+		if (tp->rx_opt.user_mss &&
+		    ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 			val = tp->rx_opt.user_mss;
 		if (tp->repair)
 			val = tp->rx_opt.mss_clamp;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 61b6710f337a..bf8b22218dd4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4530,7 +4530,7 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
 	}
 }
 
-static void tcp_sack_compress_send_ack(struct sock *sk)
+void tcp_sack_compress_send_ack(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b839c2f91292..39eb947fe392 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -290,9 +290,19 @@ static int tcp_write_timeout(struct sock *sk)
 void tcp_delack_timer_handler(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
-	    !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+	if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
+		return;
+
+	/* Handling the sack compression case */
+	if (tp->compressed_ack) {
+		tcp_mstamp_refresh(tp);
+		tcp_sack_compress_send_ack(sk);
+		return;
+	}
+
+	if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
 		return;
 
 	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -312,7 +322,7 @@ void tcp_delack_timer_handler(struct sock *sk)
 			inet_csk_exit_pingpong_mode(sk);
 			icsk->icsk_ack.ato      = TCP_ATO_MIN;
 		}
-		tcp_mstamp_refresh(tcp_sk(sk));
+		tcp_mstamp_refresh(tp);
 		tcp_send_ack(sk);
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS);
 	}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 08dc53f56bc2..67311e7d5b21 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -90,8 +90,8 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	if (err)
 		return err;
 
-	msk->first = ssock->sk;
-	msk->subflow = ssock;
+	WRITE_ONCE(msk->first, ssock->sk);
+	WRITE_ONCE(msk->subflow, ssock);
 	subflow = mptcp_subflow_ctx(ssock->sk);
 	list_add(&subflow->node, &msk->conn_list);
 	sock_hold(ssock->sk);
@@ -603,7 +603,7 @@ static bool mptcp_check_data_fin(struct sock *sk)
 		WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1);
 		WRITE_ONCE(msk->rcv_data_fin, 0);
 
-		sk->sk_shutdown |= RCV_SHUTDOWN;
+		WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
 		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
 
 		switch (sk->sk_state) {
@@ -825,6 +825,13 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 	mptcp_data_unlock(sk);
 }
 
+static void mptcp_subflow_joined(struct mptcp_sock *msk, struct sock *ssk)
+{
+	mptcp_subflow_ctx(ssk)->map_seq = READ_ONCE(msk->ack_seq);
+	WRITE_ONCE(msk->allow_infinite_fallback, false);
+	mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC);
+}
+
 static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct sock *sk = (struct sock *)msk;
@@ -839,6 +846,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
 		mptcp_sock_graft(ssk, sk->sk_socket);
 
 	mptcp_sockopt_sync_locked(msk, ssk);
+	mptcp_subflow_joined(msk, ssk);
 	return true;
 }
 
@@ -910,7 +918,7 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk)
 		/* hopefully temporary hack: propagate shutdown status
 		 * to msk, when all subflows agree on it
 		 */
-		sk->sk_shutdown |= RCV_SHUTDOWN;
+		WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
 
 		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
 		sk->sk_data_ready(sk);
@@ -1702,7 +1710,6 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 
 	lock_sock(ssk);
 	msg->msg_flags |= MSG_DONTWAIT;
-	msk->connect_flags = O_NONBLOCK;
 	msk->fastopening = 1;
 	ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL);
 	msk->fastopening = 0;
@@ -2283,7 +2290,7 @@ static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk)
 {
 	if (msk->subflow) {
 		iput(SOCK_INODE(msk->subflow));
-		msk->subflow = NULL;
+		WRITE_ONCE(msk->subflow, NULL);
 	}
 }
 
@@ -2420,7 +2427,7 @@ out_release:
 	sock_put(ssk);
 
 	if (ssk == msk->first)
-		msk->first = NULL;
+		WRITE_ONCE(msk->first, NULL);
 
 out:
 	if (ssk == msk->last_snd)
@@ -2527,7 +2534,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 	}
 
 	inet_sk_state_store(sk, TCP_CLOSE);
-	sk->sk_shutdown = SHUTDOWN_MASK;
+	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 	smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
 	set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);
 
@@ -2721,7 +2728,7 @@ static int __mptcp_init_sock(struct sock *sk)
 	WRITE_ONCE(msk->rmem_released, 0);
 	msk->timer_ival = TCP_RTO_MIN;
 
-	msk->first = NULL;
+	WRITE_ONCE(msk->first, NULL);
 	inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
 	WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
 	WRITE_ONCE(msk->allow_infinite_fallback, true);
@@ -2959,7 +2966,7 @@ bool __mptcp_close(struct sock *sk, long timeout)
 	bool do_cancel_work = false;
 	int subflows_alive = 0;
 
-	sk->sk_shutdown = SHUTDOWN_MASK;
+	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 
 	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
 		mptcp_listen_inuse_dec(sk);
@@ -3039,7 +3046,7 @@ static void mptcp_close(struct sock *sk, long timeout)
 	sock_put(sk);
 }
 
-void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
+static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
 {
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	const struct ipv6_pinfo *ssk6 = inet6_sk(ssk);
@@ -3102,7 +3109,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	mptcp_pm_data_reset(msk);
 	mptcp_ca_reset(sk);
 
-	sk->sk_shutdown = 0;
+	WRITE_ONCE(sk->sk_shutdown, 0);
 	sk_error_report(sk);
 	return 0;
 }
@@ -3116,9 +3123,10 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk)
 }
 #endif
 
-struct sock *mptcp_sk_clone(const struct sock *sk,
-			    const struct mptcp_options_received *mp_opt,
-			    struct request_sock *req)
+struct sock *mptcp_sk_clone_init(const struct sock *sk,
+				 const struct mptcp_options_received *mp_opt,
+				 struct sock *ssk,
+				 struct request_sock *req)
 {
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
 	struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);
@@ -3137,7 +3145,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 	msk = mptcp_sk(nsk);
 	msk->local_key = subflow_req->local_key;
 	msk->token = subflow_req->token;
-	msk->subflow = NULL;
+	WRITE_ONCE(msk->subflow, NULL);
 	msk->in_accept_queue = 1;
 	WRITE_ONCE(msk->fully_established, false);
 	if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD)
@@ -3150,10 +3158,30 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
 
 	sock_reset_flag(nsk, SOCK_RCU_FREE);
-	/* will be fully established after successful MPC subflow creation */
-	inet_sk_state_store(nsk, TCP_SYN_RECV);
-
 	security_inet_csk_clone(nsk, req);
+
+	/* this can't race with mptcp_close(), as the msk is
+	 * not yet exposted to user-space
+	 */
+	inet_sk_state_store(nsk, TCP_ESTABLISHED);
+
+	/* The msk maintain a ref to each subflow in the connections list */
+	WRITE_ONCE(msk->first, ssk);
+	list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list);
+	sock_hold(ssk);
+
+	/* new mpc subflow takes ownership of the newly
+	 * created mptcp socket
+	 */
+	mptcp_token_accept(subflow_req, msk);
+
+	/* set msk addresses early to ensure mptcp_pm_get_local_id()
+	 * uses the correct data
+	 */
+	mptcp_copy_inaddrs(nsk, ssk);
+	mptcp_propagate_sndbuf(nsk, ssk);
+
+	mptcp_rcv_space_init(msk, ssk);
 	bh_unlock_sock(nsk);
 
 	/* note: the newly allocated socket refcount is 2 now */
@@ -3185,7 +3213,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 	struct socket *listener;
 	struct sock *newsk;
 
-	listener = msk->subflow;
+	listener = READ_ONCE(msk->subflow);
 	if (WARN_ON_ONCE(!listener)) {
 		*err = -EINVAL;
 		return NULL;
@@ -3465,14 +3493,16 @@ bool mptcp_finish_join(struct sock *ssk)
 		return false;
 	}
 
-	if (!list_empty(&subflow->node))
-		goto out;
+	/* active subflow, already present inside the conn_list */
+	if (!list_empty(&subflow->node)) {
+		mptcp_subflow_joined(msk, ssk);
+		return true;
+	}
 
 	if (!mptcp_pm_allow_new_subflow(msk))
 		goto err_prohibited;
 
-	/* active connections are already on conn_list.
-	 * If we can't acquire msk socket lock here, let the release callback
+	/* If we can't acquire msk socket lock here, let the release callback
 	 * handle it
 	 */
 	mptcp_data_lock(parent);
@@ -3495,11 +3525,6 @@ err_prohibited:
 		return false;
 	}
 
-	subflow->map_seq = READ_ONCE(msk->ack_seq);
-	WRITE_ONCE(msk->allow_infinite_fallback, false);
-
-out:
-	mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC);
 	return true;
 }
 
@@ -3617,9 +3642,9 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	 * acquired the subflow socket lock, too.
 	 */
 	if (msk->fastopening)
-		err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1);
+		err = __inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK, 1);
 	else
-		err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags);
+		err = inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK);
 	inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect;
 
 	/* on successful connect, the msk state will be moved to established by
@@ -3632,12 +3657,10 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	mptcp_copy_inaddrs(sk, ssock->sk);
 
-	/* unblocking connect, mptcp-level inet_stream_connect will error out
-	 * without changing the socket state, update it here.
+	/* silence EINPROGRESS and let the caller inet_stream_connect
+	 * handle the connection in progress
 	 */
-	if (err == -EINPROGRESS)
-		sk->sk_socket->state = ssock->state;
-	return err;
+	return 0;
 }
 
 static struct proto mptcp_prot = {
@@ -3696,18 +3719,6 @@ unlock:
 	return err;
 }
 
-static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr,
-				int addr_len, int flags)
-{
-	int ret;
-
-	lock_sock(sock->sk);
-	mptcp_sk(sock->sk)->connect_flags = flags;
-	ret = __inet_stream_connect(sock, uaddr, addr_len, flags, 0);
-	release_sock(sock->sk);
-	return ret;
-}
-
 static int mptcp_listen(struct socket *sock, int backlog)
 {
 	struct mptcp_sock *msk = mptcp_sk(sock->sk);
@@ -3751,10 +3762,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 
 	pr_debug("msk=%p", msk);
 
-	/* buggy applications can call accept on socket states other then LISTEN
+	/* Buggy applications can call accept on socket states other then LISTEN
 	 * but no need to allocate the first subflow just to error out.
 	 */
-	ssock = msk->subflow;
+	ssock = READ_ONCE(msk->subflow);
 	if (!ssock)
 		return -EINVAL;
 
@@ -3800,9 +3811,6 @@ static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
 {
 	struct sock *sk = (struct sock *)msk;
 
-	if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN))
-		return EPOLLOUT | EPOLLWRNORM;
-
 	if (sk_stream_is_writeable(sk))
 		return EPOLLOUT | EPOLLWRNORM;
 
@@ -3820,6 +3828,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk;
 	struct mptcp_sock *msk;
 	__poll_t mask = 0;
+	u8 shutdown;
 	int state;
 
 	msk = mptcp_sk(sk);
@@ -3828,23 +3837,30 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	state = inet_sk_state_load(sk);
 	pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags);
 	if (state == TCP_LISTEN) {
-		if (WARN_ON_ONCE(!msk->subflow || !msk->subflow->sk))
+		struct socket *ssock = READ_ONCE(msk->subflow);
+
+		if (WARN_ON_ONCE(!ssock || !ssock->sk))
 			return 0;
 
-		return inet_csk_listen_poll(msk->subflow->sk);
+		return inet_csk_listen_poll(ssock->sk);
 	}
 
+	shutdown = READ_ONCE(sk->sk_shutdown);
+	if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
+		mask |= EPOLLHUP;
+	if (shutdown & RCV_SHUTDOWN)
+		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
+
 	if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
 		mask |= mptcp_check_readable(msk);
-		mask |= mptcp_check_writeable(msk);
+		if (shutdown & SEND_SHUTDOWN)
+			mask |= EPOLLOUT | EPOLLWRNORM;
+		else
+			mask |= mptcp_check_writeable(msk);
 	} else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
 		/* cf tcp_poll() note about TFO */
 		mask |= EPOLLOUT | EPOLLWRNORM;
 	}
-	if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
-		mask |= EPOLLHUP;
-	if (sk->sk_shutdown & RCV_SHUTDOWN)
-		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
 
 	/* This barrier is coupled with smp_wmb() in __mptcp_error_report() */
 	smp_rmb();
@@ -3859,7 +3875,7 @@ static const struct proto_ops mptcp_stream_ops = {
 	.owner		   = THIS_MODULE,
 	.release	   = inet_release,
 	.bind		   = mptcp_bind,
-	.connect	   = mptcp_stream_connect,
+	.connect	   = inet_stream_connect,
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = mptcp_stream_accept,
 	.getname	   = inet_getname,
@@ -3954,7 +3970,7 @@ static const struct proto_ops mptcp_v6_stream_ops = {
 	.owner		   = THIS_MODULE,
 	.release	   = inet6_release,
 	.bind		   = mptcp_bind,
-	.connect	   = mptcp_stream_connect,
+	.connect	   = inet_stream_connect,
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = mptcp_stream_accept,
 	.getname	   = inet6_getname,
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 2d7b2c80a164..c5255258bfb3 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -297,7 +297,6 @@ struct mptcp_sock {
 			nodelay:1,
 			fastopening:1,
 			in_accept_queue:1;
-	int		connect_flags;
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
@@ -306,7 +305,11 @@ struct mptcp_sock {
 	struct list_head rtx_queue;
 	struct mptcp_data_frag *first_pending;
 	struct list_head join_list;
-	struct socket	*subflow; /* outgoing connect/listener/!mp_capable */
+	struct socket	*subflow; /* outgoing connect/listener/!mp_capable
+				   * The mptcp ops can safely dereference, using suitable
+				   * ONCE annotation, the subflow outside the socket
+				   * lock as such sock is freed after close().
+				   */
 	struct sock	*first;
 	struct mptcp_pm_data	pm;
 	struct {
@@ -613,7 +616,6 @@ int mptcp_is_checksum_enabled(const struct net *net);
 int mptcp_allow_join_id0(const struct net *net);
 unsigned int mptcp_stale_loss_cnt(const struct net *net);
 int mptcp_get_pm_type(const struct net *net);
-void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 				     const struct mptcp_options_received *mp_opt);
 bool __mptcp_retransmit_pending_data(struct sock *sk);
@@ -683,9 +685,10 @@ void __init mptcp_proto_init(void);
 int __init mptcp_proto_v6_init(void);
 #endif
 
-struct sock *mptcp_sk_clone(const struct sock *sk,
-			    const struct mptcp_options_received *mp_opt,
-			    struct request_sock *req);
+struct sock *mptcp_sk_clone_init(const struct sock *sk,
+				 const struct mptcp_options_received *mp_opt,
+				 struct sock *ssk,
+				 struct request_sock *req);
 void mptcp_get_options(const struct sk_buff *skb,
 		       struct mptcp_options_received *mp_opt);
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index ba065b66551a..4688daa6b38b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -815,38 +815,12 @@ create_child:
 		ctx->setsockopt_seq = listener->setsockopt_seq;
 
 		if (ctx->mp_capable) {
-			ctx->conn = mptcp_sk_clone(listener->conn, &mp_opt, req);
+			ctx->conn = mptcp_sk_clone_init(listener->conn, &mp_opt, child, req);
 			if (!ctx->conn)
 				goto fallback;
 
 			owner = mptcp_sk(ctx->conn);
-
-			/* this can't race with mptcp_close(), as the msk is
-			 * not yet exposted to user-space
-			 */
-			inet_sk_state_store(ctx->conn, TCP_ESTABLISHED);
-
-			/* record the newly created socket as the first msk
-			 * subflow, but don't link it yet into conn_list
-			 */
-			WRITE_ONCE(owner->first, child);
-
-			/* new mpc subflow takes ownership of the newly
-			 * created mptcp socket
-			 */
-			owner->setsockopt_seq = ctx->setsockopt_seq;
 			mptcp_pm_new_connection(owner, child, 1);
-			mptcp_token_accept(subflow_req, owner);
-
-			/* set msk addresses early to ensure mptcp_pm_get_local_id()
-			 * uses the correct data
-			 */
-			mptcp_copy_inaddrs(ctx->conn, child);
-			mptcp_propagate_sndbuf(ctx->conn, child);
-
-			mptcp_rcv_space_init(owner, child);
-			list_add(&ctx->node, &owner->conn_list);
-			sock_hold(child);
 
 			/* with OoO packets we can reach here without ingress
 			 * mpc option
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index c87804112d0c..3a1e0fd5bf14 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1779,7 +1779,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 				break;
 			}
 		}
-		if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen))
+		if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen))
 			err = -EFAULT;
 		netlink_unlock_table();
 		return err;
diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c
index 3f99b432ea70..e2d2af924cff 100644
--- a/net/netrom/nr_subr.c
+++ b/net/netrom/nr_subr.c
@@ -123,7 +123,7 @@ void nr_write_internal(struct sock *sk, int frametype)
 	unsigned char  *dptr;
 	int len, timeout;
 
-	len = NR_NETWORK_LEN + NR_TRANSPORT_LEN;
+	len = NR_TRANSPORT_LEN;
 
 	switch (frametype & 0x0F) {
 	case NR_CONNREQ:
@@ -141,7 +141,8 @@ void nr_write_internal(struct sock *sk, int frametype)
 		return;
 	}
 
-	if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL)
+	skb = alloc_skb(NR_NETWORK_LEN + len, GFP_ATOMIC);
+	if (!skb)
 		return;
 
 	/*
@@ -149,7 +150,7 @@ void nr_write_internal(struct sock *sk, int frametype)
 	 */
 	skb_reserve(skb, NR_NETWORK_LEN);
 
-	dptr = skb_put(skb, skb_tailroom(skb));
+	dptr = skb_put(skb, len);
 
 	switch (frametype & 0x0F) {
 	case NR_CONNREQ:
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 94c6a1ffa459..a2dbeb264f26 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3201,6 +3201,9 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 
 	lock_sock(sk);
 	spin_lock(&po->bind_lock);
+	if (!proto)
+		proto = po->num;
+
 	rcu_read_lock();
 
 	if (po->fanout) {
@@ -3299,7 +3302,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 	memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min));
 	name[sizeof(uaddr->sa_data_min)] = 0;
 
-	return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
+	return packet_do_bind(sk, name, 0, 0);
 }
 
 static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
@@ -3316,8 +3319,7 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len
 	if (sll->sll_family != AF_PACKET)
 		return -EINVAL;
 
-	return packet_do_bind(sk, NULL, sll->sll_ifindex,
-			      sll->sll_protocol ? : pkt_sk(sk)->num);
+	return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol);
 }
 
 static struct proto packet_proto = {
diff --git a/net/packet/diag.c b/net/packet/diag.c
index d0c4eda4cdc6..f6b200cb3c06 100644
--- a/net/packet/diag.c
+++ b/net/packet/diag.c
@@ -143,7 +143,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 	rp = nlmsg_data(nlh);
 	rp->pdiag_family = AF_PACKET;
 	rp->pdiag_type = sk->sk_type;
-	rp->pdiag_num = ntohs(po->num);
+	rp->pdiag_num = ntohs(READ_ONCE(po->num));
 	rp->pdiag_ino = sk_ino;
 	sock_diag_save_cookie(sk, rp->pdiag_cookie);
 
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 31f738d65f1c..da0b3b5157d5 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -980,6 +980,7 @@ static int __init af_rxrpc_init(void)
 	BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb));
 
 	ret = -ENOMEM;
+	rxrpc_gen_version_string();
 	rxrpc_call_jar = kmem_cache_create(
 		"rxrpc_call_jar", sizeof(struct rxrpc_call), 0,
 		SLAB_HWCACHE_ALIGN, NULL);
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5d44dc08f66d..e8e14c6f904d 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -1068,6 +1068,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time64_t,
 /*
  * local_event.c
  */
+void rxrpc_gen_version_string(void);
 void rxrpc_send_version_request(struct rxrpc_local *local,
 				struct rxrpc_host_header *hdr,
 				struct sk_buff *skb);
diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c
index 5e69ea6b233d..993c69f97488 100644
--- a/net/rxrpc/local_event.c
+++ b/net/rxrpc/local_event.c
@@ -16,7 +16,16 @@
 #include <generated/utsrelease.h>
 #include "ar-internal.h"
 
-static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC";
+static char rxrpc_version_string[65]; // "linux-" UTS_RELEASE " AF_RXRPC";
+
+/*
+ * Generate the VERSION packet string.
+ */
+void rxrpc_gen_version_string(void)
+{
+	snprintf(rxrpc_version_string, sizeof(rxrpc_version_string),
+		 "linux-%.49s AF_RXRPC", UTS_RELEASE);
+}
 
 /*
  * Reply to a version request
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 9dbc43388e57..815c3e416bc5 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1153,6 +1153,9 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key,
 	if (option_len > sizeof(struct geneve_opt))
 		data_len = option_len - sizeof(struct geneve_opt);
 
+	if (key->enc_opts.len > FLOW_DIS_TUN_OPTS_MAX - 4)
+		return -ERANGE;
+
 	opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len];
 	memset(opt, 0xff, option_len);
 	opt->length = data_len / 4;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index fdb8f429333d..014209b1dd58 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1252,7 +1252,12 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
 	sch->parent = parent;
 
 	if (handle == TC_H_INGRESS) {
-		sch->flags |= TCQ_F_INGRESS;
+		if (!(sch->flags & TCQ_F_INGRESS)) {
+			NL_SET_ERR_MSG(extack,
+				       "Specified parent ID is reserved for ingress and clsact Qdiscs");
+			err = -EINVAL;
+			goto err_out3;
+		}
 		handle = TC_H_MAKE(TC_H_INGRESS, 0);
 	} else {
 		if (handle == 0) {
@@ -1591,11 +1596,20 @@ replay:
 					NL_SET_ERR_MSG(extack, "Invalid qdisc name");
 					return -EINVAL;
 				}
+				if (q->flags & TCQ_F_INGRESS) {
+					NL_SET_ERR_MSG(extack,
+						       "Cannot regraft ingress or clsact Qdiscs");
+					return -EINVAL;
+				}
 				if (q == p ||
 				    (p && check_loop(q, p, 0))) {
 					NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected");
 					return -ELOOP;
 				}
+				if (clid == TC_H_INGRESS) {
+					NL_SET_ERR_MSG(extack, "Ingress cannot graft directly");
+					return -EINVAL;
+				}
 				qdisc_refcount_inc(q);
 				goto graft;
 			} else {
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 84838128b9c5..e43a45499372 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -80,6 +80,9 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
 	struct net_device *dev = qdisc_dev(sch);
 	int err;
 
+	if (sch->parent != TC_H_INGRESS)
+		return -EOPNOTSUPP;
+
 	net_inc_ingress_queue();
 
 	mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress);
@@ -101,6 +104,9 @@ static void ingress_destroy(struct Qdisc *sch)
 {
 	struct ingress_sched_data *q = qdisc_priv(sch);
 
+	if (sch->parent != TC_H_INGRESS)
+		return;
+
 	tcf_block_put_ext(q->block, sch, &q->block_info);
 	net_dec_ingress_queue();
 }
@@ -134,7 +140,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = {
 	.cl_ops			=	&ingress_class_ops,
 	.id			=	"ingress",
 	.priv_size		=	sizeof(struct ingress_sched_data),
-	.static_flags		=	TCQ_F_CPUSTATS,
+	.static_flags		=	TCQ_F_INGRESS | TCQ_F_CPUSTATS,
 	.init			=	ingress_init,
 	.destroy		=	ingress_destroy,
 	.dump			=	ingress_dump,
@@ -219,6 +225,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 	struct net_device *dev = qdisc_dev(sch);
 	int err;
 
+	if (sch->parent != TC_H_CLSACT)
+		return -EOPNOTSUPP;
+
 	net_inc_ingress_queue();
 	net_inc_egress_queue();
 
@@ -248,6 +257,9 @@ static void clsact_destroy(struct Qdisc *sch)
 {
 	struct clsact_sched_data *q = qdisc_priv(sch);
 
+	if (sch->parent != TC_H_CLSACT)
+		return;
+
 	tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info);
 	tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info);
 
@@ -269,7 +281,7 @@ static struct Qdisc_ops clsact_qdisc_ops __read_mostly = {
 	.cl_ops			=	&clsact_class_ops,
 	.id			=	"clsact",
 	.priv_size		=	sizeof(struct clsact_sched_data),
-	.static_flags		=	TCQ_F_CPUSTATS,
+	.static_flags		=	TCQ_F_INGRESS | TCQ_F_CPUSTATS,
 	.init			=	clsact_init,
 	.destroy		=	clsact_destroy,
 	.dump			=	ingress_dump,
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index a0840b8c935b..7a8d9163d186 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -578,7 +578,10 @@ static struct smc_buf_desc *smc_llc_get_next_rmb(struct smc_link_group *lgr,
 {
 	struct smc_buf_desc *buf_next;
 
-	if (!buf_pos || list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) {
+	if (!buf_pos)
+		return _smc_llc_get_next_rmb(lgr, buf_lst);
+
+	if (list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) {
 		(*buf_lst)++;
 		return _smc_llc_get_next_rmb(lgr, buf_lst);
 	}
@@ -614,6 +617,8 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext,
 		goto out;
 	buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst);
 	for (i = 0; i < ext->num_rkeys; i++) {
+		while (buf_pos && !(buf_pos)->used)
+			buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos);
 		if (!buf_pos)
 			break;
 		rmb = buf_pos;
@@ -623,8 +628,6 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext,
 			cpu_to_be64((uintptr_t)rmb->cpu_addr) :
 			cpu_to_be64((u64)sg_dma_address(rmb->sgt[lnk_idx].sgl));
 		buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos);
-		while (buf_pos && !(buf_pos)->used)
-			buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos);
 	}
 	len += i * sizeof(ext->rt[0]);
 out:
diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c
index da95abbb7ea3..f37f4a0fcd3c 100644
--- a/net/tls/tls_strp.c
+++ b/net/tls/tls_strp.c
@@ -20,7 +20,9 @@ static void tls_strp_abort_strp(struct tls_strparser *strp, int err)
 	strp->stopped = 1;
 
 	/* Report an error on the lower socket */
-	strp->sk->sk_err = -err;
+	WRITE_ONCE(strp->sk->sk_err, -err);
+	/* Paired with smp_rmb() in tcp_poll() */
+	smp_wmb();
 	sk_error_report(strp->sk);
 }
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 6e6a7c37d685..1a53c8f481e9 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -70,7 +70,9 @@ noinline void tls_err_abort(struct sock *sk, int err)
 {
 	WARN_ON_ONCE(err >= 0);
 	/* sk->sk_err should contain a positive error code. */
-	sk->sk_err = -err;
+	WRITE_ONCE(sk->sk_err, -err);
+	/* Paired with smp_rmb() in tcp_poll() */
+	smp_wmb();
 	sk_error_report(sk);
 }