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

Pull networking fixes from David Miller:

 1) Verify netlink attributes properly in nf_queue, from Eric Dumazet.

 2) Need to bump memory lock rlimit for test_sockmap bpf test, from
    Yonghong Song.

 3) Fix VLAN handling in lan78xx driver, from Dave Stevenson.

 4) Fix uninitialized read in nf_log, from Jann Horn.

 5) Fix raw command length parsing in mlx5, from Alex Vesker.

 6) Cleanup loopback RDS connections upon netns deletion, from Sowmini
    Varadhan.

 7) Fix regressions in FIB rule matching during create, from Jason A.
    Donenfeld and Roopa Prabhu.

 8) Fix mpls ether type detection in nfp, from Pieter Jansen van Vuuren.

 9) More bpfilter build fixes/adjustments from Masahiro Yamada.

10) Fix XDP_{TX,REDIRECT} flushing in various drivers, from Jesper
    Dangaard Brouer.

11) fib_tests.sh file permissions were broken, from Shuah Khan.

12) Make sure BH/preemption is disabled in data path of mac80211, from
    Denis Kenzior.

13) Don't ignore nla_parse_nested() return values in nl80211, from
    Johannes berg.

14) Properly account sock objects ot kmemcg, from Shakeel Butt.

15) Adjustments to setting bpf program permissions to read-only, from
    Daniel Borkmann.

16) TCP Fast Open key endianness was broken, it always took on the host
    endiannness. Whoops. Explicitly make it little endian. From Yuching
    Cheng.

17) Fix prefix route setting for link local addresses in ipv6, from
    David Ahern.

18) Potential Spectre v1 in zatm driver, from Gustavo A. R. Silva.

19) Various bpf sockmap fixes, from John Fastabend.

20) Use after free for GRO with ESP, from Sabrina Dubroca.

21) Passing bogus flags to crypto_alloc_shash() in ipv6 SR code, from
    Eric Biggers.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (87 commits)
  qede: Adverstise software timestamp caps when PHC is not available.
  qed: Fix use of incorrect size in memcpy call.
  qed: Fix setting of incorrect eswitch mode.
  qed: Limit msix vectors in kdump kernel to the minimum required count.
  ipvlan: call dev_change_flags when ipvlan mode is reset
  ipv6: sr: fix passing wrong flags to crypto_alloc_shash()
  net: fix use-after-free in GRO with ESP
  tcp: prevent bogus FRTO undos with non-SACK flows
  bpf: sockhash, add release routine
  bpf: sockhash fix omitted bucket lock in sock_close
  bpf: sockmap, fix smap_list_map_remove when psock is in many maps
  bpf: sockmap, fix crash when ipv6 sock is added
  net: fib_rules: bring back rule_exists to match rule during add
  hv_netvsc: split sub-channel setup into async and sync
  net: use dev_change_tx_queue_len() for SIOCSIFTXQLEN
  atm: zatm: Fix potential Spectre v1
  s390/qeth: consistently re-enable device features
  s390/qeth: don't clobber buffer on async TX completion
  s390/qeth: avoid using is_multicast_ether_addr_64bits on (u8 *)[6]
  s390/qeth: fix race when setting MAC address
  ...

2 files changed, 71 insertions, 33 deletions

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 973b4471b532..e017b6a4452b 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -45,6 +45,7 @@ static DEFINE_MUTEX(smc_create_lgr_pending);	/* serialize link group
 						 */
 
 static void smc_tcp_listen_work(struct work_struct *);
+static void smc_connect_work(struct work_struct *);
 
 static void smc_set_keepalive(struct sock *sk, int val)
 {
@@ -122,6 +123,12 @@ static int smc_release(struct socket *sock)
 		goto out;
 
 	smc = smc_sk(sk);
+
+	/* cleanup for a dangling non-blocking connect */
+	flush_work(&smc->connect_work);
+	kfree(smc->connect_info);
+	smc->connect_info = NULL;
+
 	if (sk->sk_state == SMC_LISTEN)
 		/* smc_close_non_accepted() is called and acquires
 		 * sock lock for child sockets again
@@ -186,6 +193,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
 	sk->sk_protocol = protocol;
 	smc = smc_sk(sk);
 	INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
+	INIT_WORK(&smc->connect_work, smc_connect_work);
 	INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
 	INIT_LIST_HEAD(&smc->accept_q);
 	spin_lock_init(&smc->accept_q_lock);
@@ -576,6 +584,35 @@ static int __smc_connect(struct smc_sock *smc)
 	return 0;
 }
 
+static void smc_connect_work(struct work_struct *work)
+{
+	struct smc_sock *smc = container_of(work, struct smc_sock,
+					    connect_work);
+	int rc;
+
+	lock_sock(&smc->sk);
+	rc = kernel_connect(smc->clcsock, &smc->connect_info->addr,
+			    smc->connect_info->alen, smc->connect_info->flags);
+	if (smc->clcsock->sk->sk_err) {
+		smc->sk.sk_err = smc->clcsock->sk->sk_err;
+		goto out;
+	}
+	if (rc < 0) {
+		smc->sk.sk_err = -rc;
+		goto out;
+	}
+
+	rc = __smc_connect(smc);
+	if (rc < 0)
+		smc->sk.sk_err = -rc;
+
+out:
+	smc->sk.sk_state_change(&smc->sk);
+	kfree(smc->connect_info);
+	smc->connect_info = NULL;
+	release_sock(&smc->sk);
+}
+
 static int smc_connect(struct socket *sock, struct sockaddr *addr,
 		       int alen, int flags)
 {
@@ -605,15 +642,32 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr,
 
 	smc_copy_sock_settings_to_clc(smc);
 	tcp_sk(smc->clcsock->sk)->syn_smc = 1;
-	rc = kernel_connect(smc->clcsock, addr, alen, flags);
-	if (rc)
-		goto out;
+	if (flags & O_NONBLOCK) {
+		if (smc->connect_info) {
+			rc = -EALREADY;
+			goto out;
+		}
+		smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL);
+		if (!smc->connect_info) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		smc->connect_info->alen = alen;
+		smc->connect_info->flags = flags ^ O_NONBLOCK;
+		memcpy(&smc->connect_info->addr, addr, alen);
+		schedule_work(&smc->connect_work);
+		rc = -EINPROGRESS;
+	} else {
+		rc = kernel_connect(smc->clcsock, addr, alen, flags);
+		if (rc)
+			goto out;
 
-	rc = __smc_connect(smc);
-	if (rc < 0)
-		goto out;
-	else
-		rc = 0; /* success cases including fallback */
+		rc = __smc_connect(smc);
+		if (rc < 0)
+			goto out;
+		else
+			rc = 0; /* success cases including fallback */
+	}
 
 out:
 	release_sock(sk);
@@ -1279,40 +1333,18 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 	struct smc_sock *smc;
-	int rc;
 
 	if (!sk)
 		return EPOLLNVAL;
 
 	smc = smc_sk(sock->sk);
-	sock_hold(sk);
-	lock_sock(sk);
 	if ((sk->sk_state == SMC_INIT) || smc->use_fallback) {
 		/* delegate to CLC child sock */
-		release_sock(sk);
 		mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
-		lock_sock(sk);
 		sk->sk_err = smc->clcsock->sk->sk_err;
-		if (sk->sk_err) {
+		if (sk->sk_err)
 			mask |= EPOLLERR;
-		} else {
-			/* if non-blocking connect finished ... */
-			if (sk->sk_state == SMC_INIT &&
-			    mask & EPOLLOUT &&
-			    smc->clcsock->sk->sk_state != TCP_CLOSE) {
-				rc = __smc_connect(smc);
-				if (rc < 0)
-					mask |= EPOLLERR;
-				/* success cases including fallback */
-				mask |= EPOLLOUT | EPOLLWRNORM;
-			}
-		}
 	} else {
-		if (sk->sk_state != SMC_CLOSED) {
-			release_sock(sk);
-			sock_poll_wait(file, sk_sleep(sk), wait);
-			lock_sock(sk);
-		}
 		if (sk->sk_err)
 			mask |= EPOLLERR;
 		if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
@@ -1340,8 +1372,6 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
 			mask |= EPOLLPRI;
 
 	}
-	release_sock(sk);
-	sock_put(sk);
 
 	return mask;
 }
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 51ae1f10d81a..d7ca26570482 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -187,11 +187,19 @@ struct smc_connection {
 	struct work_struct	close_work;	/* peer sent some closing */
 };
 
+struct smc_connect_info {
+	int			flags;
+	int			alen;
+	struct sockaddr		addr;
+};
+
 struct smc_sock {				/* smc sock container */
 	struct sock		sk;
 	struct socket		*clcsock;	/* internal tcp socket */
 	struct smc_connection	conn;		/* smc connection */
 	struct smc_sock		*listen_smc;	/* listen parent */
+	struct smc_connect_info *connect_info;	/* connect address & flags */
+	struct work_struct	connect_work;	/* handle non-blocking connect*/
 	struct work_struct	tcp_listen_work;/* handle tcp socket accepts */
 	struct work_struct	smc_listen_work;/* prepare new accept socket */
 	struct list_head	accept_q;	/* sockets to be accepted */