Merge tag 'v4.18' into rdma.git for-next

Resolve merge conflicts from the -rc cycle against the rdma.git tree:

Conflicts:
 drivers/infiniband/core/uverbs_cmd.c
  - New ifs added to ib_uverbs_ex_create_flow in -rc and for-next
  - Merge removal of file->ucontext in for-next with new code in -rc
 drivers/infiniband/core/uverbs_main.c
  - for-next removed code from ib_uverbs_write() that was modified
    in for-rc

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

6 files changed, 129 insertions, 50 deletions

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index da7f02edcd37..e7de5f282722 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
@@ -140,7 +147,8 @@ static int smc_release(struct socket *sock)
 		smc->clcsock = NULL;
 	}
 	if (smc->use_fallback) {
-		sock_put(sk); /* passive closing */
+		if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT)
+			sock_put(sk); /* passive closing */
 		sk->sk_state = SMC_CLOSED;
 		sk->sk_state_change(sk);
 	}
@@ -186,6 +194,7 @@ 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);
@@ -409,12 +418,18 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
 {
 	int rc;
 
-	if (reason_code < 0) /* error, fallback is not possible */
+	if (reason_code < 0) { /* error, fallback is not possible */
+		if (smc->sk.sk_state == SMC_INIT)
+			sock_put(&smc->sk); /* passive closing */
 		return reason_code;
+	}
 	if (reason_code != SMC_CLC_DECL_REPLY) {
 		rc = smc_clc_send_decline(smc, reason_code);
-		if (rc < 0)
+		if (rc < 0) {
+			if (smc->sk.sk_state == SMC_INIT)
+				sock_put(&smc->sk); /* passive closing */
 			return rc;
+		}
 	}
 	return smc_connect_fallback(smc);
 }
@@ -427,8 +442,6 @@ static int smc_connect_abort(struct smc_sock *smc, int reason_code,
 		smc_lgr_forget(smc->conn.lgr);
 	mutex_unlock(&smc_create_lgr_pending);
 	smc_conn_free(&smc->conn);
-	if (reason_code < 0 && smc->sk.sk_state == SMC_INIT)
-		sock_put(&smc->sk); /* passive closing */
 	return reason_code;
 }
 
@@ -576,6 +589,35 @@ 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 +647,32 @@ 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);
@@ -1063,6 +1122,8 @@ static void smc_tcp_listen_work(struct work_struct *work)
 		sock_hold(lsk); /* sock_put in smc_listen_work */
 		INIT_WORK(&new_smc->smc_listen_work, smc_listen_work);
 		smc_copy_sock_settings_to_smc(new_smc);
+		new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf;
+		new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf;
 		sock_hold(&new_smc->sk); /* sock_put in passive closing */
 		if (!schedule_work(&new_smc->smc_listen_work))
 			sock_put(&new_smc->sk);
@@ -1273,40 +1334,26 @@ static __poll_t smc_accept_poll(struct sock *parent)
 	return mask;
 }
 
-static __poll_t smc_poll_mask(struct socket *sock, __poll_t events)
+static __poll_t smc_poll(struct file *file, struct socket *sock,
+			     poll_table *wait)
 {
 	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_mask(smc->clcsock, events);
-		lock_sock(sk);
+		mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
 		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)
+			sock_poll_wait(file, sk_sleep(sk), wait);
 		if (sk->sk_err)
 			mask |= EPOLLERR;
 		if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
@@ -1332,10 +1379,7 @@ static __poll_t smc_poll_mask(struct socket *sock, __poll_t events)
 		}
 		if (smc->conn.urg_state == SMC_URG_VALID)
 			mask |= EPOLLPRI;
-
 	}
-	release_sock(sk);
-	sock_put(sk);
 
 	return mask;
 }
@@ -1355,8 +1399,7 @@ static int smc_shutdown(struct socket *sock, int how)
 	lock_sock(sk);
 
 	rc = -ENOTCONN;
-	if ((sk->sk_state != SMC_LISTEN) &&
-	    (sk->sk_state != SMC_ACTIVE) &&
+	if ((sk->sk_state != SMC_ACTIVE) &&
 	    (sk->sk_state != SMC_PEERCLOSEWAIT1) &&
 	    (sk->sk_state != SMC_PEERCLOSEWAIT2) &&
 	    (sk->sk_state != SMC_APPCLOSEWAIT1) &&
@@ -1415,7 +1458,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 
 	if (optlen < sizeof(int))
 		return -EINVAL;
-	get_user(val, (int __user *)optval);
+	if (get_user(val, (int __user *)optval))
+		return -EFAULT;
 
 	lock_sock(sk);
 	switch (optname) {
@@ -1478,15 +1522,22 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 
 	smc = smc_sk(sock->sk);
 	conn = &smc->conn;
+	lock_sock(&smc->sk);
 	if (smc->use_fallback) {
-		if (!smc->clcsock)
+		if (!smc->clcsock) {
+			release_sock(&smc->sk);
 			return -EBADF;
-		return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
+		}
+		answ = smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
+		release_sock(&smc->sk);
+		return answ;
 	}
 	switch (cmd) {
 	case SIOCINQ: /* same as FIONREAD */
-		if (smc->sk.sk_state == SMC_LISTEN)
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
 			return -EINVAL;
+		}
 		if (smc->sk.sk_state == SMC_INIT ||
 		    smc->sk.sk_state == SMC_CLOSED)
 			answ = 0;
@@ -1495,8 +1546,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 		break;
 	case SIOCOUTQ:
 		/* output queue size (not send + not acked) */
-		if (smc->sk.sk_state == SMC_LISTEN)
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
 			return -EINVAL;
+		}
 		if (smc->sk.sk_state == SMC_INIT ||
 		    smc->sk.sk_state == SMC_CLOSED)
 			answ = 0;
@@ -1506,8 +1559,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 		break;
 	case SIOCOUTQNSD:
 		/* output queue size (not send only) */
-		if (smc->sk.sk_state == SMC_LISTEN)
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
 			return -EINVAL;
+		}
 		if (smc->sk.sk_state == SMC_INIT ||
 		    smc->sk.sk_state == SMC_CLOSED)
 			answ = 0;
@@ -1515,8 +1570,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 			answ = smc_tx_prepared_sends(&smc->conn);
 		break;
 	case SIOCATMARK:
-		if (smc->sk.sk_state == SMC_LISTEN)
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
 			return -EINVAL;
+		}
 		if (smc->sk.sk_state == SMC_INIT ||
 		    smc->sk.sk_state == SMC_CLOSED) {
 			answ = 0;
@@ -1532,8 +1589,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 		}
 		break;
 	default:
+		release_sock(&smc->sk);
 		return -ENOIOCTLCMD;
 	}
+	release_sock(&smc->sk);
 
 	return put_user(answ, (int __user *)arg);
 }
@@ -1619,7 +1678,7 @@ static const struct proto_ops smc_sock_ops = {
 	.socketpair	= sock_no_socketpair,
 	.accept		= smc_accept,
 	.getname	= smc_getname,
-	.poll_mask	= smc_poll_mask,
+	.poll		= smc_poll,
 	.ioctl		= smc_ioctl,
 	.listen		= smc_listen,
 	.shutdown	= smc_shutdown,
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 */
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index a7e8d63fc8ae..9bde1e4ca288 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -233,7 +233,8 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 			/* force immediate tx of current consumer cursor, but
 			 * under send_lock to guarantee arrival in seqno-order
 			 */
-			smc_tx_sndbuf_nonempty(conn);
+			if (smc->sk.sk_state != SMC_INIT)
+				smc_tx_sndbuf_nonempty(conn);
 		}
 	}
 
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 717449b1da0b..ae5d168653ce 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -250,6 +250,7 @@ out:
 int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		     u8 expected_type)
 {
+	long rcvtimeo = smc->clcsock->sk->sk_rcvtimeo;
 	struct sock *clc_sk = smc->clcsock->sk;
 	struct smc_clc_msg_hdr *clcm = buf;
 	struct msghdr msg = {NULL, 0};
@@ -306,7 +307,6 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	memset(&msg, 0, sizeof(struct msghdr));
 	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen);
 	krflags = MSG_WAITALL;
-	smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
 	len = sock_recvmsg(smc->clcsock, &msg, krflags);
 	if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) {
 		smc->sk.sk_err = EPROTO;
@@ -322,6 +322,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	}
 
 out:
+	smc->clcsock->sk->sk_rcvtimeo = rcvtimeo;
 	return reason_code;
 }
 
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index fa41d9881741..ac961dfb1ea1 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -107,6 +107,8 @@ static void smc_close_active_abort(struct smc_sock *smc)
 	}
 	switch (sk->sk_state) {
 	case SMC_INIT:
+		sk->sk_state = SMC_PEERABORTWAIT;
+		break;
 	case SMC_ACTIVE:
 		sk->sk_state = SMC_PEERABORTWAIT;
 		release_sock(sk);
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index a171c168f98e..72e1a2782fe8 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -494,7 +494,8 @@ out:
 
 void smc_tx_consumer_update(struct smc_connection *conn, bool force)
 {
-	union smc_host_cursor cfed, cons;
+	union smc_host_cursor cfed, cons, prod;
+	int sender_free = conn->rmb_desc->len;
 	int to_confirm;
 
 	smc_curs_write(&cons,
@@ -504,11 +505,18 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force)
 		       smc_curs_read(&conn->rx_curs_confirmed, conn),
 		       conn);
 	to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons);
+	if (to_confirm > conn->rmbe_update_limit) {
+		smc_curs_write(&prod,
+			       smc_curs_read(&conn->local_rx_ctrl.prod, conn),
+			       conn);
+		sender_free = conn->rmb_desc->len -
+			      smc_curs_diff(conn->rmb_desc->len, &prod, &cfed);
+	}
 
 	if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
 	    force ||
 	    ((to_confirm > conn->rmbe_update_limit) &&
-	     ((to_confirm > (conn->rmb_desc->len / 2)) ||
+	     ((sender_free <= (conn->rmb_desc->len / 2)) ||
 	      conn->local_rx_ctrl.prod_flags.write_blocked))) {
 		if ((smc_cdc_get_slot_and_msg_send(conn) < 0) &&
 		    conn->alert_token_local) { /* connection healthy */