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

Pull networking fixes from David Miller:

 1) Handle init flow failures properly in iwlwifi driver, from Shahar S
    Matityahu.

 2) mac80211 TXQs need to be unscheduled on powersave start, from Felix
    Fietkau.

 3) SKB memory accounting fix in A-MDSU aggregation, from Felix Fietkau.

 4) Increase RCU lock hold time in mlx5 FPGA code, from Saeed Mahameed.

 5) Avoid checksum complete with XDP in mlx5, also from Saeed.

 6) Fix netdev feature clobbering in ibmvnic driver, from Thomas Falcon.

 7) Partial sent TLS record leak fix from Jakub Kicinski.

 8) Reject zero size iova range in vhost, from Jason Wang.

 9) Allow pending work to complete before clcsock release from Karsten
    Graul.

10) Fix XDP handling max MTU in thunderx, from Matteo Croce.

11) A lot of protocols look at the sa_family field of a sockaddr before
    validating it's length is large enough, from Tetsuo Handa.

12) Don't write to free'd pointer in qede ptp error path, from Colin Ian
    King.

13) Have to recompile IP options in ipv4_link_failure because it can be
    invoked from ARP, from Stephen Suryaputra.

14) Doorbell handling fixes in qed from Denis Bolotin.

15) Revert net-sysfs kobject register leak fix, it causes new problems.
    From Wang Hai.

16) Spectre v1 fix in ATM code, from Gustavo A. R. Silva.

17) Fix put of BROPT_VLAN_STATS_PER_PORT in bridging code, from Nikolay
    Aleksandrov.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (111 commits)
  socket: fix compat SO_RCVTIMEO_NEW/SO_SNDTIMEO_NEW
  tcp: tcp_grow_window() needs to respect tcp_space()
  ocelot: Clean up stats update deferred work
  ocelot: Don't sleep in atomic context (irqs_disabled())
  net: bridge: fix netlink export of vlan_stats_per_port option
  qed: fix spelling mistake "faspath" -> "fastpath"
  tipc: set sysctl_tipc_rmem and named_timeout right range
  tipc: fix link established but not in session
  net: Fix missing meta data in skb with vlan packet
  net: atm: Fix potential Spectre v1 vulnerabilities
  net/core: work around section mismatch warning for ptp_classifier
  net: bridge: fix per-port af_packet sockets
  bnx2x: fix spelling mistake "dicline" -> "decline"
  route: Avoid crash from dereferencing NULL rt->from
  MAINTAINERS: normalize Woojung Huh's email address
  bonding: fix event handling for stacked bonds
  Revert "net-sysfs: Fix memory leak in netdev_register_kobject"
  rtnetlink: fix rtnl_valid_stats_req() nlmsg_len check
  qed: Fix the DORQ's attentions handling
  qed: Fix missing DORQ attentions
  ...

5 files changed, 68 insertions, 24 deletions

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 77ef53596d18..6f869ef49b32 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -167,10 +167,9 @@ static int smc_release(struct socket *sock)
 
 	if (sk->sk_state == SMC_CLOSED) {
 		if (smc->clcsock) {
-			mutex_lock(&smc->clcsock_release_lock);
-			sock_release(smc->clcsock);
-			smc->clcsock = NULL;
-			mutex_unlock(&smc->clcsock_release_lock);
+			release_sock(sk);
+			smc_clcsock_release(smc);
+			lock_sock(sk);
 		}
 		if (!smc->use_fallback)
 			smc_conn_free(&smc->conn);
@@ -446,10 +445,19 @@ static void smc_link_save_peer_info(struct smc_link *link,
 	link->peer_mtu = clc->qp_mtu;
 }
 
+static void smc_switch_to_fallback(struct smc_sock *smc)
+{
+	smc->use_fallback = true;
+	if (smc->sk.sk_socket && smc->sk.sk_socket->file) {
+		smc->clcsock->file = smc->sk.sk_socket->file;
+		smc->clcsock->file->private_data = smc->clcsock;
+	}
+}
+
 /* fall back during connect */
 static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
 {
-	smc->use_fallback = true;
+	smc_switch_to_fallback(smc);
 	smc->fallback_rsn = reason_code;
 	smc_copy_sock_settings_to_clc(smc);
 	if (smc->sk.sk_state == SMC_INIT)
@@ -775,10 +783,14 @@ static void smc_connect_work(struct work_struct *work)
 		smc->sk.sk_err = -rc;
 
 out:
-	if (smc->sk.sk_err)
-		smc->sk.sk_state_change(&smc->sk);
-	else
-		smc->sk.sk_write_space(&smc->sk);
+	if (!sock_flag(&smc->sk, SOCK_DEAD)) {
+		if (smc->sk.sk_err) {
+			smc->sk.sk_state_change(&smc->sk);
+		} else { /* allow polling before and after fallback decision */
+			smc->clcsock->sk->sk_write_space(smc->clcsock->sk);
+			smc->sk.sk_write_space(&smc->sk);
+		}
+	}
 	kfree(smc->connect_info);
 	smc->connect_info = NULL;
 	release_sock(&smc->sk);
@@ -872,11 +884,11 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc)
 	if  (rc < 0)
 		lsk->sk_err = -rc;
 	if (rc < 0 || lsk->sk_state == SMC_CLOSED) {
+		new_sk->sk_prot->unhash(new_sk);
 		if (new_clcsock)
 			sock_release(new_clcsock);
 		new_sk->sk_state = SMC_CLOSED;
 		sock_set_flag(new_sk, SOCK_DEAD);
-		new_sk->sk_prot->unhash(new_sk);
 		sock_put(new_sk); /* final */
 		*new_smc = NULL;
 		goto out;
@@ -927,16 +939,21 @@ struct sock *smc_accept_dequeue(struct sock *parent,
 
 		smc_accept_unlink(new_sk);
 		if (new_sk->sk_state == SMC_CLOSED) {
+			new_sk->sk_prot->unhash(new_sk);
 			if (isk->clcsock) {
 				sock_release(isk->clcsock);
 				isk->clcsock = NULL;
 			}
-			new_sk->sk_prot->unhash(new_sk);
 			sock_put(new_sk); /* final */
 			continue;
 		}
-		if (new_sock)
+		if (new_sock) {
 			sock_graft(new_sk, new_sock);
+			if (isk->use_fallback) {
+				smc_sk(new_sk)->clcsock->file = new_sock->file;
+				isk->clcsock->file->private_data = isk->clcsock;
+			}
+		}
 		return new_sk;
 	}
 	return NULL;
@@ -956,6 +973,7 @@ void smc_close_non_accepted(struct sock *sk)
 		sock_set_flag(sk, SOCK_DEAD);
 		sk->sk_shutdown |= SHUTDOWN_MASK;
 	}
+	sk->sk_prot->unhash(sk);
 	if (smc->clcsock) {
 		struct socket *tcp;
 
@@ -971,7 +989,6 @@ void smc_close_non_accepted(struct sock *sk)
 			smc_conn_free(&smc->conn);
 	}
 	release_sock(sk);
-	sk->sk_prot->unhash(sk);
 	sock_put(sk); /* final sock_put */
 }
 
@@ -1037,13 +1054,13 @@ static void smc_listen_out(struct smc_sock *new_smc)
 	struct smc_sock *lsmc = new_smc->listen_smc;
 	struct sock *newsmcsk = &new_smc->sk;
 
-	lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
 	if (lsmc->sk.sk_state == SMC_LISTEN) {
+		lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
 		smc_accept_enqueue(&lsmc->sk, newsmcsk);
+		release_sock(&lsmc->sk);
 	} else { /* no longer listening */
 		smc_close_non_accepted(newsmcsk);
 	}
-	release_sock(&lsmc->sk);
 
 	/* Wake up accept */
 	lsmc->sk.sk_data_ready(&lsmc->sk);
@@ -1087,7 +1104,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
 		return;
 	}
 	smc_conn_free(&new_smc->conn);
-	new_smc->use_fallback = true;
+	smc_switch_to_fallback(new_smc);
 	new_smc->fallback_rsn = reason_code;
 	if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) {
 		if (smc_clc_send_decline(new_smc, reason_code) < 0) {
@@ -1237,6 +1254,9 @@ static void smc_listen_work(struct work_struct *work)
 	int rc = 0;
 	u8 ibport;
 
+	if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN)
+		return smc_listen_out_err(new_smc);
+
 	if (new_smc->use_fallback) {
 		smc_listen_out_connected(new_smc);
 		return;
@@ -1244,7 +1264,7 @@ static void smc_listen_work(struct work_struct *work)
 
 	/* check if peer is smc capable */
 	if (!tcp_sk(newclcsock->sk)->syn_smc) {
-		new_smc->use_fallback = true;
+		smc_switch_to_fallback(new_smc);
 		new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC;
 		smc_listen_out_connected(new_smc);
 		return;
@@ -1501,7 +1521,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 
 	if (msg->msg_flags & MSG_FASTOPEN) {
 		if (sk->sk_state == SMC_INIT) {
-			smc->use_fallback = true;
+			smc_switch_to_fallback(smc);
 			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
 		} else {
 			rc = -EINVAL;
@@ -1703,7 +1723,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 	case TCP_FASTOPEN_NO_COOKIE:
 		/* option not supported by SMC */
 		if (sk->sk_state == SMC_INIT) {
-			smc->use_fallback = true;
+			smc_switch_to_fallback(smc);
 			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
 		} else {
 			if (!smc->use_fallback)
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 2ad37e998509..fc06720b53c1 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -21,6 +21,22 @@
 
 #define SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME	(5 * HZ)
 
+/* release the clcsock that is assigned to the smc_sock */
+void smc_clcsock_release(struct smc_sock *smc)
+{
+	struct socket *tcp;
+
+	if (smc->listen_smc && current_work() != &smc->smc_listen_work)
+		cancel_work_sync(&smc->smc_listen_work);
+	mutex_lock(&smc->clcsock_release_lock);
+	if (smc->clcsock) {
+		tcp = smc->clcsock;
+		smc->clcsock = NULL;
+		sock_release(tcp);
+	}
+	mutex_unlock(&smc->clcsock_release_lock);
+}
+
 static void smc_close_cleanup_listen(struct sock *parent)
 {
 	struct sock *sk;
@@ -321,6 +337,7 @@ static void smc_close_passive_work(struct work_struct *work)
 						   close_work);
 	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
 	struct smc_cdc_conn_state_flags *rxflags;
+	bool release_clcsock = false;
 	struct sock *sk = &smc->sk;
 	int old_state;
 
@@ -400,13 +417,13 @@ wakeup:
 		if ((sk->sk_state == SMC_CLOSED) &&
 		    (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) {
 			smc_conn_free(conn);
-			if (smc->clcsock) {
-				sock_release(smc->clcsock);
-				smc->clcsock = NULL;
-			}
+			if (smc->clcsock)
+				release_clcsock = true;
 		}
 	}
 	release_sock(sk);
+	if (release_clcsock)
+		smc_clcsock_release(smc);
 	sock_put(sk); /* sock_hold done by schedulers of close_work */
 }
 
diff --git a/net/smc/smc_close.h b/net/smc/smc_close.h
index 19eb6a211c23..e0e3b5df25d2 100644
--- a/net/smc/smc_close.h
+++ b/net/smc/smc_close.h
@@ -23,5 +23,6 @@ void smc_close_wake_tx_prepared(struct smc_sock *smc);
 int smc_close_active(struct smc_sock *smc);
 int smc_close_shutdown_write(struct smc_sock *smc);
 void smc_close_init(struct smc_sock *smc);
+void smc_clcsock_release(struct smc_sock *smc);
 
 #endif /* SMC_CLOSE_H */
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index 2fff79db1a59..e89e918b88e0 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -289,6 +289,11 @@ struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
 	INIT_LIST_HEAD(&smcd->vlan);
 	smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)",
 						 WQ_MEM_RECLAIM, name);
+	if (!smcd->event_wq) {
+		kfree(smcd->conn);
+		kfree(smcd);
+		return NULL;
+	}
 	return smcd;
 }
 EXPORT_SYMBOL_GPL(smcd_alloc_dev);
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 8d2f6296279c..0285c7f9e79b 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -603,7 +603,8 @@ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net *net = genl_info_net(info);
 
-	return smc_pnet_remove_by_pnetid(net, NULL);
+	smc_pnet_remove_by_pnetid(net, NULL);
+	return 0;
 }
 
 /* SMC_PNETID generic netlink operation definition */