Merge branch 'smc-bug-fixes'

Ursula Braun says:

====================
net/smc: bug fixes 2017-09-20

here is a collection of small smc-patches built for net fixing
smc problems in different areas.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

net/smc/af_smc.c

@@ -282,6 +282,7 @@ int smc_netinfo_by_tcpsk(struct socket *clcsock,
 			 __be32 *subnet, u8 *prefix_len)
 {
 	struct dst_entry *dst = sk_dst_get(clcsock->sk);
+	struct in_device *in_dev;
 	struct sockaddr_in addr;
 	int rc = -ENOENT;
 	int len;
@@ -298,14 +299,17 @@ int smc_netinfo_by_tcpsk(struct socket *clcsock,
 	/* get address to which the internal TCP socket is bound */
 	kernel_getsockname(clcsock, (struct sockaddr *)&addr, &len);
 	/* analyze IPv4 specific data of net_device belonging to TCP socket */
-	for_ifa(dst->dev->ip_ptr) {
-		if (ifa->ifa_address != addr.sin_addr.s_addr)
+	rcu_read_lock();
+	in_dev = __in_dev_get_rcu(dst->dev);
+	for_ifa(in_dev) {
+		if (!inet_ifa_match(addr.sin_addr.s_addr, ifa))
 			continue;
 		*prefix_len = inet_mask_len(ifa->ifa_mask);
 		*subnet = ifa->ifa_address & ifa->ifa_mask;
 		rc = 0;
 		break;
-	} endfor_ifa(dst->dev->ip_ptr);
+	} endfor_ifa(in_dev);
+	rcu_read_unlock();
 
 out_rel:
 	dst_release(dst);
@@ -509,7 +513,7 @@ decline_rdma:
 	/* RDMA setup failed, switch back to TCP */
 	smc->use_fallback = true;
 	if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) {
-		rc = smc_clc_send_decline(smc, reason_code, 0);
+		rc = smc_clc_send_decline(smc, reason_code);
 		if (rc < sizeof(struct smc_clc_msg_decline))
 			goto out_err;
 	}
@@ -804,8 +808,6 @@ static void smc_listen_work(struct work_struct *work)
 		rc = local_contact;
 		if (rc == -ENOMEM)
 			reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
-		else if (rc == -ENOLINK)
-			reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */
 		goto decline_rdma;
 	}
 	link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
@@ -899,7 +901,7 @@ decline_rdma:
 	smc_conn_free(&new_smc->conn);
 	new_smc->use_fallback = true;
 	if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) {
-		rc = smc_clc_send_decline(new_smc, reason_code, 0);
+		rc = smc_clc_send_decline(new_smc, reason_code);
 		if (rc < sizeof(struct smc_clc_msg_decline))
 			goto out_err;
 	}

net/smc/smc.h

@@ -149,7 +149,7 @@ struct smc_connection {
 	atomic_t		sndbuf_space;	/* remaining space in sndbuf */
 	u16			tx_cdc_seq;	/* sequence # for CDC send */
 	spinlock_t		send_lock;	/* protect wr_sends */
-	struct work_struct	tx_work;	/* retry of smc_cdc_msg_send */
+	struct delayed_work	tx_work;	/* retry of smc_cdc_msg_send */
 
 	struct smc_host_cdc_msg	local_rx_ctrl;	/* filled during event_handl.
 						 * .prod cf. TCP rcv_nxt

net/smc/smc_clc.c

@@ -95,9 +95,10 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	}
 	if (clcm->type == SMC_CLC_DECLINE) {
 		reason_code = SMC_CLC_DECL_REPLY;
-		if (ntohl(((struct smc_clc_msg_decline *)buf)->peer_diagnosis)
-			== SMC_CLC_DECL_SYNCERR)
+		if (((struct smc_clc_msg_decline *)buf)->hdr.flag) {
 			smc->conn.lgr->sync_err = true;
+			smc_lgr_terminate(smc->conn.lgr);
+		}
 	}
 
 out:
@@ -105,8 +106,7 @@ out:
 }
 
 /* send CLC DECLINE message across internal TCP socket */
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
-			 u8 out_of_sync)
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
 {
 	struct smc_clc_msg_decline dclc;
 	struct msghdr msg;
@@ -118,7 +118,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
 	dclc.hdr.type = SMC_CLC_DECLINE;
 	dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline));
 	dclc.hdr.version = SMC_CLC_V1;
-	dclc.hdr.flag = out_of_sync ? 1 : 0;
+	dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0;
 	memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid));
 	dclc.peer_diagnosis = htonl(peer_diag_info);
 	memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));

net/smc/smc_clc.h

@@ -106,8 +106,7 @@ struct smc_ib_device;
 
 int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		     u8 expected_type);
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
-			 u8 out_of_sync);
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
 int smc_clc_send_proposal(struct smc_sock *smc, struct smc_ib_device *smcibdev,
 			  u8 ibport);
 int smc_clc_send_confirm(struct smc_sock *smc);

net/smc/smc_close.c

@@ -174,15 +174,15 @@ int smc_close_active(struct smc_sock *smc)
 {
 	struct smc_cdc_conn_state_flags *txflags =
 		&smc->conn.local_tx_ctrl.conn_state_flags;
-	long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT;
 	struct smc_connection *conn = &smc->conn;
 	struct sock *sk = &smc->sk;
 	int old_state;
+	long timeout;
 	int rc = 0;
 
-	if (sock_flag(sk, SOCK_LINGER) &&
-	    !(current->flags & PF_EXITING))
-		timeout = sk->sk_lingertime;
+	timeout = current->flags & PF_EXITING ?
+		  0 : sock_flag(sk, SOCK_LINGER) ?
+		      sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
 
 again:
 	old_state = sk->sk_state;
@@ -208,7 +208,7 @@ again:
 	case SMC_ACTIVE:
 		smc_close_stream_wait(smc, timeout);
 		release_sock(sk);
-		cancel_work_sync(&conn->tx_work);
+		cancel_delayed_work_sync(&conn->tx_work);
 		lock_sock(sk);
 		if (sk->sk_state == SMC_ACTIVE) {
 			/* send close request */
@@ -234,7 +234,7 @@ again:
 		if (!smc_cdc_rxed_any_close(conn))
 			smc_close_stream_wait(smc, timeout);
 		release_sock(sk);
-		cancel_work_sync(&conn->tx_work);
+		cancel_delayed_work_sync(&conn->tx_work);
 		lock_sock(sk);
 		if (sk->sk_err != ECONNABORTED) {
 			/* confirm close from peer */
@@ -263,7 +263,9 @@ again:
 		/* peer sending PeerConnectionClosed will cause transition */
 		break;
 	case SMC_PROCESSABORT:
-		cancel_work_sync(&conn->tx_work);
+		release_sock(sk);
+		cancel_delayed_work_sync(&conn->tx_work);
+		lock_sock(sk);
 		smc_close_abort(conn);
 		sk->sk_state = SMC_CLOSED;
 		smc_close_wait_tx_pends(smc);
@@ -411,13 +413,14 @@ void smc_close_sock_put_work(struct work_struct *work)
 int smc_close_shutdown_write(struct smc_sock *smc)
 {
 	struct smc_connection *conn = &smc->conn;
-	long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT;
 	struct sock *sk = &smc->sk;
 	int old_state;
+	long timeout;
 	int rc = 0;
 
-	if (sock_flag(sk, SOCK_LINGER))
-		timeout = sk->sk_lingertime;
+	timeout = current->flags & PF_EXITING ?
+		  0 : sock_flag(sk, SOCK_LINGER) ?
+		      sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
 
 again:
 	old_state = sk->sk_state;
@@ -425,7 +428,7 @@ again:
 	case SMC_ACTIVE:
 		smc_close_stream_wait(smc, timeout);
 		release_sock(sk);
-		cancel_work_sync(&conn->tx_work);
+		cancel_delayed_work_sync(&conn->tx_work);
 		lock_sock(sk);
 		/* send close wr request */
 		rc = smc_close_wr(conn);
@@ -439,7 +442,7 @@ again:
 		if (!smc_cdc_rxed_any_close(conn))
 			smc_close_stream_wait(smc, timeout);
 		release_sock(sk);
-		cancel_work_sync(&conn->tx_work);
+		cancel_delayed_work_sync(&conn->tx_work);
 		lock_sock(sk);
 		/* confirm close from peer */
 		rc = smc_close_wr(conn);

net/smc/smc_core.c

@@ -25,8 +25,9 @@
 #include "smc_cdc.h"
 #include "smc_close.h"
 
-#define SMC_LGR_NUM_INCR	256
-#define SMC_LGR_FREE_DELAY	(600 * HZ)
+#define SMC_LGR_NUM_INCR		256
+#define SMC_LGR_FREE_DELAY_SERV		(600 * HZ)
+#define SMC_LGR_FREE_DELAY_CLNT		(SMC_LGR_FREE_DELAY_SERV + 10)
 
 static u32 smc_lgr_num;			/* unique link group number */
 
@@ -107,8 +108,15 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn)
 		__smc_lgr_unregister_conn(conn);
 	}
 	write_unlock_bh(&lgr->conns_lock);
-	if (reduced && !lgr->conns_num)
-		schedule_delayed_work(&lgr->free_work, SMC_LGR_FREE_DELAY);
+	if (!reduced || lgr->conns_num)
+		return;
+	/* client link group creation always follows the server link group
+	 * creation. For client use a somewhat higher removal delay time,
+	 * otherwise there is a risk of out-of-sync link groups.
+	 */
+	mod_delayed_work(system_wq, &lgr->free_work,
+			 lgr->role == SMC_CLNT ? SMC_LGR_FREE_DELAY_CLNT :
+						 SMC_LGR_FREE_DELAY_SERV);
 }
 
 static void smc_lgr_free_work(struct work_struct *work)

net/smc/smc_ib.c

@@ -380,6 +380,7 @@ static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport)
 	ndev = smcibdev->ibdev->get_netdev(smcibdev->ibdev, ibport);
 	if (ndev) {
 		memcpy(&smcibdev->mac, ndev->dev_addr, ETH_ALEN);
+		dev_put(ndev);
 	} else if (!rc) {
 		memcpy(&smcibdev->mac[ibport - 1][0],
 		       &smcibdev->gid[ibport - 1].raw[8], 3);

net/smc/smc_pnet.c

@@ -181,8 +181,10 @@ static int smc_pnet_enter(struct smc_pnetentry *new_pnetelem)
 			     sizeof(new_pnetelem->ndev->name)) ||
 		    smc_pnet_same_ibname(pnetelem,
 					 new_pnetelem->smcibdev->ibdev->name,
-					 new_pnetelem->ib_port))
+					 new_pnetelem->ib_port)) {
+			dev_put(pnetelem->ndev);
 			goto found;
+		}
 	}
 	list_add_tail(&new_pnetelem->list, &smc_pnettable.pnetlist);
 	rc = 0;

net/smc/smc_rx.c

@@ -148,6 +148,8 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len,
 				read_done = sock_intr_errno(timeo);
 				break;
 			}
+			if (!timeo)
+				return -EAGAIN;
 		}
 
 		if (!atomic_read(&conn->bytes_to_rcv)) {

net/smc/smc_tx.c

@@ -24,6 +24,8 @@
 #include "smc_cdc.h"
 #include "smc_tx.h"
 
+#define SMC_TX_WORK_DELAY	HZ
+
 /***************************** sndbuf producer *******************************/
 
 /* callback implementation for sk.sk_write_space()
@@ -406,7 +408,8 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
 				goto out_unlock;
 			}
 			rc = 0;
-			schedule_work(&conn->tx_work);
+			schedule_delayed_work(&conn->tx_work,
+					      SMC_TX_WORK_DELAY);
 		}
 		goto out_unlock;
 	}
@@ -430,7 +433,7 @@ out_unlock:
  */
 static void smc_tx_work(struct work_struct *work)
 {
-	struct smc_connection *conn = container_of(work,
+	struct smc_connection *conn = container_of(to_delayed_work(work),
 						   struct smc_connection,
 						   tx_work);
 	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
@@ -468,7 +471,8 @@ void smc_tx_consumer_update(struct smc_connection *conn)
 		if (!rc)
 			rc = smc_cdc_msg_send(conn, wr_buf, pend);
 		if (rc < 0) {
-			schedule_work(&conn->tx_work);
+			schedule_delayed_work(&conn->tx_work,
+					      SMC_TX_WORK_DELAY);
 			return;
 		}
 		smc_curs_write(&conn->rx_curs_confirmed,
@@ -487,6 +491,6 @@ void smc_tx_consumer_update(struct smc_connection *conn)
 void smc_tx_init(struct smc_sock *smc)
 {
 	smc->sk.sk_write_space = smc_tx_write_space;
-	INIT_WORK(&smc->conn.tx_work, smc_tx_work);
+	INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
 	spin_lock_init(&smc->conn.send_lock);
 }

net/smc/smc_wr.c

@@ -244,7 +244,7 @@ int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv)
 	int rc;
 
 	ib_req_notify_cq(link->smcibdev->roce_cq_send,
-			 IB_CQ_SOLICITED_MASK | IB_CQ_REPORT_MISSED_EVENTS);
+			 IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
 	pend = container_of(priv, struct smc_wr_tx_pend, priv);
 	rc = ib_post_send(link->roce_qp, &link->wr_tx_ibs[pend->idx],
 			  &failed_wr);