Merge tag 'net-5.18-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bluetooth, bpf and netfilter.

  Current release - new code bugs:

   - bridge: switchdev: check br_vlan_group() return value

   - use this_cpu_inc() to increment net->core_stats, fix preempt-rt

  Previous releases - regressions:

   - eth: stmmac: fix write to sgmii_adapter_base

  Previous releases - always broken:

   - netfilter: nf_conntrack_tcp: re-init for syn packets only,
     resolving issues with TCP fastopen

   - tcp: md5: fix incorrect tcp_header_len for incoming connections

   - tcp: fix F-RTO may not work correctly when receiving DSACK

   - tcp: ensure use of most recently sent skb when filling rate samples

   - tcp: fix potential xmit stalls caused by TCP_NOTSENT_LOWAT

   - virtio_net: fix wrong buf address calculation when using xdp

   - xsk: fix forwarding when combining copy mode with busy poll

   - xsk: fix possible crash when multiple sockets are created

   - bpf: lwt: fix crash when using bpf_skb_set_tunnel_key() from
     bpf_xmit lwt hook

   - sctp: null-check asoc strreset_chunk in sctp_generate_reconf_event

   - wireguard: device: check for metadata_dst with skb_valid_dst()

   - netfilter: update ip6_route_me_harder to consider L3 domain

   - gre: make o_seqno start from 0 in native mode

   - gre: switch o_seqno to atomic to prevent races in collect_md mode

  Misc:

   - add Eric Dumazet to networking maintainers

   - dt: dsa: realtek: remove realtek,rtl8367s string

   - netfilter: flowtable: Remove the empty file"

* tag 'net-5.18-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (65 commits)
  tcp: fix F-RTO may not work correctly when receiving DSACK
  Revert "ibmvnic: Add ethtool private flag for driver-defined queue limits"
  net: enetc: allow tc-etf offload even with NETIF_F_CSUM_MASK
  ixgbe: ensure IPsec VF<->PF compatibility
  MAINTAINERS: Update BNXT entry with firmware files
  netfilter: nft_socket: only do sk lookups when indev is available
  net: fec: add missing of_node_put() in fec_enet_init_stop_mode()
  bnx2x: fix napi API usage sequence
  tls: Skip tls_append_frag on zero copy size
  Add Eric Dumazet to networking maintainers
  netfilter: conntrack: fix udp offload timeout sysctl
  netfilter: nf_conntrack_tcp: re-init for syn packets only
  net: dsa: lantiq_gswip: Don't set GSWIP_MII_CFG_RMII_CLK
  net: Use this_cpu_inc() to increment net->core_stats
  Bluetooth: hci_sync: Cleanup hci_conn if it cannot be aborted
  Bluetooth: hci_event: Fix creating hci_conn object on error status
  Bluetooth: hci_event: Fix checking for invalid handle on error status
  ice: fix use-after-free when deinitializing mailbox snapshot
  ice: wait 5 s for EMP reset after firmware flash
  ice: Protect vf_state check by cfg_lock in ice_vc_process_vf_msg()
  ...

1 files changed, 95 insertions, 42 deletions

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index fc7b6eb22143..fce16b9d6e1a 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -243,11 +243,27 @@ struct proto smc_proto6 = {
 };
 EXPORT_SYMBOL_GPL(smc_proto6);
 
+static void smc_fback_restore_callbacks(struct smc_sock *smc)
+{
+	struct sock *clcsk = smc->clcsock->sk;
+
+	write_lock_bh(&clcsk->sk_callback_lock);
+	clcsk->sk_user_data = NULL;
+
+	smc_clcsock_restore_cb(&clcsk->sk_state_change, &smc->clcsk_state_change);
+	smc_clcsock_restore_cb(&clcsk->sk_data_ready, &smc->clcsk_data_ready);
+	smc_clcsock_restore_cb(&clcsk->sk_write_space, &smc->clcsk_write_space);
+	smc_clcsock_restore_cb(&clcsk->sk_error_report, &smc->clcsk_error_report);
+
+	write_unlock_bh(&clcsk->sk_callback_lock);
+}
+
 static void smc_restore_fallback_changes(struct smc_sock *smc)
 {
 	if (smc->clcsock->file) { /* non-accepted sockets have no file yet */
 		smc->clcsock->file->private_data = smc->sk.sk_socket;
 		smc->clcsock->file = NULL;
+		smc_fback_restore_callbacks(smc);
 	}
 }
 
@@ -373,6 +389,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
 	sk->sk_prot->hash(sk);
 	sk_refcnt_debug_inc(sk);
 	mutex_init(&smc->clcsock_release_lock);
+	smc_init_saved_callbacks(smc);
 
 	return sk;
 }
@@ -744,47 +761,73 @@ out:
 
 static void smc_fback_state_change(struct sock *clcsk)
 {
-	struct smc_sock *smc =
-		smc_clcsock_user_data(clcsk);
+	struct smc_sock *smc;
 
-	if (!smc)
-		return;
-	smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_state_change);
+	read_lock_bh(&clcsk->sk_callback_lock);
+	smc = smc_clcsock_user_data(clcsk);
+	if (smc)
+		smc_fback_forward_wakeup(smc, clcsk,
+					 smc->clcsk_state_change);
+	read_unlock_bh(&clcsk->sk_callback_lock);
 }
 
 static void smc_fback_data_ready(struct sock *clcsk)
 {
-	struct smc_sock *smc =
-		smc_clcsock_user_data(clcsk);
+	struct smc_sock *smc;
 
-	if (!smc)
-		return;
-	smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_data_ready);
+	read_lock_bh(&clcsk->sk_callback_lock);
+	smc = smc_clcsock_user_data(clcsk);
+	if (smc)
+		smc_fback_forward_wakeup(smc, clcsk,
+					 smc->clcsk_data_ready);
+	read_unlock_bh(&clcsk->sk_callback_lock);
 }
 
 static void smc_fback_write_space(struct sock *clcsk)
 {
-	struct smc_sock *smc =
-		smc_clcsock_user_data(clcsk);
+	struct smc_sock *smc;
 
-	if (!smc)
-		return;
-	smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_write_space);
+	read_lock_bh(&clcsk->sk_callback_lock);
+	smc = smc_clcsock_user_data(clcsk);
+	if (smc)
+		smc_fback_forward_wakeup(smc, clcsk,
+					 smc->clcsk_write_space);
+	read_unlock_bh(&clcsk->sk_callback_lock);
 }
 
 static void smc_fback_error_report(struct sock *clcsk)
 {
-	struct smc_sock *smc =
-		smc_clcsock_user_data(clcsk);
+	struct smc_sock *smc;
 
-	if (!smc)
-		return;
-	smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_error_report);
+	read_lock_bh(&clcsk->sk_callback_lock);
+	smc = smc_clcsock_user_data(clcsk);
+	if (smc)
+		smc_fback_forward_wakeup(smc, clcsk,
+					 smc->clcsk_error_report);
+	read_unlock_bh(&clcsk->sk_callback_lock);
+}
+
+static void smc_fback_replace_callbacks(struct smc_sock *smc)
+{
+	struct sock *clcsk = smc->clcsock->sk;
+
+	write_lock_bh(&clcsk->sk_callback_lock);
+	clcsk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY);
+
+	smc_clcsock_replace_cb(&clcsk->sk_state_change, smc_fback_state_change,
+			       &smc->clcsk_state_change);
+	smc_clcsock_replace_cb(&clcsk->sk_data_ready, smc_fback_data_ready,
+			       &smc->clcsk_data_ready);
+	smc_clcsock_replace_cb(&clcsk->sk_write_space, smc_fback_write_space,
+			       &smc->clcsk_write_space);
+	smc_clcsock_replace_cb(&clcsk->sk_error_report, smc_fback_error_report,
+			       &smc->clcsk_error_report);
+
+	write_unlock_bh(&clcsk->sk_callback_lock);
 }
 
 static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 {
-	struct sock *clcsk;
 	int rc = 0;
 
 	mutex_lock(&smc->clcsock_release_lock);
@@ -792,10 +835,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 		rc = -EBADF;
 		goto out;
 	}
-	clcsk = smc->clcsock->sk;
 
-	if (smc->use_fallback)
-		goto out;
 	smc->use_fallback = true;
 	smc->fallback_rsn = reason_code;
 	smc_stat_fallback(smc);
@@ -810,18 +850,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 		 * in smc sk->sk_wq and they should be woken up
 		 * as clcsock's wait queue is woken up.
 		 */
-		smc->clcsk_state_change = clcsk->sk_state_change;
-		smc->clcsk_data_ready = clcsk->sk_data_ready;
-		smc->clcsk_write_space = clcsk->sk_write_space;
-		smc->clcsk_error_report = clcsk->sk_error_report;
-
-		clcsk->sk_state_change = smc_fback_state_change;
-		clcsk->sk_data_ready = smc_fback_data_ready;
-		clcsk->sk_write_space = smc_fback_write_space;
-		clcsk->sk_error_report = smc_fback_error_report;
-
-		smc->clcsock->sk->sk_user_data =
-			(void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY);
+		smc_fback_replace_callbacks(smc);
 	}
 out:
 	mutex_unlock(&smc->clcsock_release_lock);
@@ -1475,6 +1504,8 @@ static void smc_connect_work(struct work_struct *work)
 		smc->sk.sk_state = SMC_CLOSED;
 		if (rc == -EPIPE || rc == -EAGAIN)
 			smc->sk.sk_err = EPIPE;
+		else if (rc == -ECONNREFUSED)
+			smc->sk.sk_err = ECONNREFUSED;
 		else if (signal_pending(current))
 			smc->sk.sk_err = -sock_intr_errno(timeo);
 		sock_put(&smc->sk); /* passive closing */
@@ -1594,6 +1625,19 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc)
 	 * function; switch it back to the original sk_data_ready function
 	 */
 	new_clcsock->sk->sk_data_ready = lsmc->clcsk_data_ready;
+
+	/* if new clcsock has also inherited the fallback-specific callback
+	 * functions, switch them back to the original ones.
+	 */
+	if (lsmc->use_fallback) {
+		if (lsmc->clcsk_state_change)
+			new_clcsock->sk->sk_state_change = lsmc->clcsk_state_change;
+		if (lsmc->clcsk_write_space)
+			new_clcsock->sk->sk_write_space = lsmc->clcsk_write_space;
+		if (lsmc->clcsk_error_report)
+			new_clcsock->sk->sk_error_report = lsmc->clcsk_error_report;
+	}
+
 	(*new_smc)->clcsock = new_clcsock;
 out:
 	return rc;
@@ -2353,17 +2397,20 @@ out:
 
 static void smc_clcsock_data_ready(struct sock *listen_clcsock)
 {
-	struct smc_sock *lsmc =
-		smc_clcsock_user_data(listen_clcsock);
+	struct smc_sock *lsmc;
 
+	read_lock_bh(&listen_clcsock->sk_callback_lock);
+	lsmc = smc_clcsock_user_data(listen_clcsock);
 	if (!lsmc)
-		return;
+		goto out;
 	lsmc->clcsk_data_ready(listen_clcsock);
 	if (lsmc->sk.sk_state == SMC_LISTEN) {
 		sock_hold(&lsmc->sk); /* sock_put in smc_tcp_listen_work() */
 		if (!queue_work(smc_tcp_ls_wq, &lsmc->tcp_listen_work))
 			sock_put(&lsmc->sk);
 	}
+out:
+	read_unlock_bh(&listen_clcsock->sk_callback_lock);
 }
 
 static int smc_listen(struct socket *sock, int backlog)
@@ -2395,10 +2442,12 @@ static int smc_listen(struct socket *sock, int backlog)
 	/* save original sk_data_ready function and establish
 	 * smc-specific sk_data_ready function
 	 */
-	smc->clcsk_data_ready = smc->clcsock->sk->sk_data_ready;
-	smc->clcsock->sk->sk_data_ready = smc_clcsock_data_ready;
+	write_lock_bh(&smc->clcsock->sk->sk_callback_lock);
 	smc->clcsock->sk->sk_user_data =
 		(void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY);
+	smc_clcsock_replace_cb(&smc->clcsock->sk->sk_data_ready,
+			       smc_clcsock_data_ready, &smc->clcsk_data_ready);
+	write_unlock_bh(&smc->clcsock->sk->sk_callback_lock);
 
 	/* save original ops */
 	smc->ori_af_ops = inet_csk(smc->clcsock->sk)->icsk_af_ops;
@@ -2413,7 +2462,11 @@ static int smc_listen(struct socket *sock, int backlog)
 
 	rc = kernel_listen(smc->clcsock, backlog);
 	if (rc) {
-		smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready;
+		write_lock_bh(&smc->clcsock->sk->sk_callback_lock);
+		smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready,
+				       &smc->clcsk_data_ready);
+		smc->clcsock->sk->sk_user_data = NULL;
+		write_unlock_bh(&smc->clcsock->sk->sk_callback_lock);
 		goto out;
 	}
 	sk->sk_max_ack_backlog = backlog;