9 files changed, 113 insertions, 50 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index ff50a7bd66d8..7ac25059c40f 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -336,6 +336,7 @@ struct ipoib_dev_priv {
 	unsigned long flags;
 
 	struct rw_semaphore vlan_rwsem;
+	struct mutex mcast_mutex;
 
 	struct rb_root  path_tree;
 	struct list_head path_list;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 7cbcfdac6529..d69410c2ed97 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -39,6 +39,7 @@
 #include <linux/vmalloc.h>
 #include <linux/moduleparam.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 
 #include "ipoib.h"
 
@@ -510,7 +511,6 @@ static int ipoib_cm_rx_handler(struct ib_cm_id *cm_id,
 	case IB_CM_REQ_RECEIVED:
 		return ipoib_cm_req_handler(cm_id, event);
 	case IB_CM_DREQ_RECEIVED:
-		p = cm_id->context;
 		ib_send_cm_drep(cm_id, NULL, 0);
 		/* Fall through */
 	case IB_CM_REJ_RECEIVED:
@@ -954,7 +954,7 @@ void ipoib_cm_dev_stop(struct net_device *dev)
 			break;
 		}
 		spin_unlock_irq(&priv->lock);
-		msleep(1);
+		usleep_range(1000, 2000);
 		ipoib_drain_cq(dev);
 		spin_lock_irq(&priv->lock);
 	}
@@ -1047,9 +1047,8 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_
 		.sq_sig_type		= IB_SIGNAL_ALL_WR,
 		.qp_type		= IB_QPT_RC,
 		.qp_context		= tx,
-		.create_flags		= IB_QP_CREATE_USE_GFP_NOIO
+		.create_flags		= 0
 	};
-
 	struct ib_qp *tx_qp;
 
 	if (dev->features & NETIF_F_SG)
@@ -1057,10 +1056,6 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_
 			min_t(u32, priv->ca->attrs.max_sge, MAX_SKB_FRAGS + 1);
 
 	tx_qp = ib_create_qp(priv->pd, &attr);
-	if (PTR_ERR(tx_qp) == -EINVAL) {
-		attr.create_flags &= ~IB_QP_CREATE_USE_GFP_NOIO;
-		tx_qp = ib_create_qp(priv->pd, &attr);
-	}
 	tx->max_send_sge = attr.cap.max_send_sge;
 	return tx_qp;
 }
@@ -1131,10 +1126,11 @@ static int ipoib_cm_tx_init(struct ipoib_cm_tx *p, u32 qpn,
 			    struct sa_path_rec *pathrec)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(p->dev);
+	unsigned int noio_flag;
 	int ret;
 
-	p->tx_ring = __vmalloc(ipoib_sendq_size * sizeof *p->tx_ring,
-			       GFP_NOIO, PAGE_KERNEL);
+	noio_flag = memalloc_noio_save();
+	p->tx_ring = vzalloc(ipoib_sendq_size * sizeof(*p->tx_ring));
 	if (!p->tx_ring) {
 		ret = -ENOMEM;
 		goto err_tx;
@@ -1142,9 +1138,10 @@ static int ipoib_cm_tx_init(struct ipoib_cm_tx *p, u32 qpn,
 	memset(p->tx_ring, 0, ipoib_sendq_size * sizeof *p->tx_ring);
 
 	p->qp = ipoib_cm_create_tx_qp(p->dev, p);
+	memalloc_noio_restore(noio_flag);
 	if (IS_ERR(p->qp)) {
 		ret = PTR_ERR(p->qp);
-		ipoib_warn(priv, "failed to allocate tx qp: %d\n", ret);
+		ipoib_warn(priv, "failed to create tx qp: %d\n", ret);
 		goto err_qp;
 	}
 
@@ -1206,7 +1203,7 @@ static void ipoib_cm_tx_destroy(struct ipoib_cm_tx *p)
 				goto timeout;
 			}
 
-			msleep(1);
+			usleep_range(1000, 2000);
 		}
 	}
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
index 7871379342f4..184a22f48027 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
@@ -52,7 +52,8 @@ static const struct ipoib_stats ipoib_gstrings_stats[] = {
 	IPOIB_NETDEV_STAT(tx_bytes),
 	IPOIB_NETDEV_STAT(tx_errors),
 	IPOIB_NETDEV_STAT(rx_dropped),
-	IPOIB_NETDEV_STAT(tx_dropped)
+	IPOIB_NETDEV_STAT(tx_dropped),
+	IPOIB_NETDEV_STAT(multicast),
 };
 
 #define IPOIB_GLOBAL_STATS_LEN	ARRAY_SIZE(ipoib_gstrings_stats)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index efe7402f4885..2e075377242e 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -256,6 +256,8 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
+	if (skb->pkt_type == PACKET_MULTICAST)
+		dev->stats.multicast++;
 
 	skb->dev = dev;
 	if ((dev->features & NETIF_F_RXCSUM) &&
@@ -709,6 +711,27 @@ static int recvs_pending(struct net_device *dev)
 	return pending;
 }
 
+static void check_qp_movement_and_print(struct ipoib_dev_priv *priv,
+					struct ib_qp *qp,
+					enum ib_qp_state new_state)
+{
+	struct ib_qp_attr qp_attr;
+	struct ib_qp_init_attr query_init_attr;
+	int ret;
+
+	ret = ib_query_qp(qp, &qp_attr, IB_QP_STATE, &query_init_attr);
+	if (ret) {
+		ipoib_warn(priv, "%s: Failed to query QP\n", __func__);
+		return;
+	}
+	/* print according to the new-state and the previous state.*/
+	if (new_state == IB_QPS_ERR && qp_attr.qp_state == IB_QPS_RESET)
+		ipoib_dbg(priv, "Failed modify QP, IB_QPS_RESET to IB_QPS_ERR, acceptable\n");
+	else
+		ipoib_warn(priv, "Failed to modify QP to state: %d from state: %d\n",
+			   new_state, qp_attr.qp_state);
+}
+
 int ipoib_ib_dev_stop_default(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
@@ -728,7 +751,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev)
 	 */
 	qp_attr.qp_state = IB_QPS_ERR;
 	if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
-		ipoib_warn(priv, "Failed to modify QP to ERROR state\n");
+		check_qp_movement_and_print(priv, priv->qp, IB_QPS_ERR);
 
 	/* Wait for all sends and receives to complete */
 	begin = jiffies;
@@ -770,7 +793,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev)
 
 		ipoib_drain_cq(dev);
 
-		msleep(1);
+		usleep_range(1000, 2000);
 	}
 
 	ipoib_dbg(priv, "All sends and receives done.\n");
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 6e86eeee370e..6c77df34869d 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -233,6 +233,7 @@ static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_featu
 static int ipoib_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
+	int ret = 0;
 
 	/* dev->mtu > 2K ==> connected mode */
 	if (ipoib_cm_admin_enabled(dev)) {
@@ -256,9 +257,34 @@ static int ipoib_change_mtu(struct net_device *dev, int new_mtu)
 		ipoib_dbg(priv, "MTU must be smaller than the underlying "
 				"link layer MTU - 4 (%u)\n", priv->mcast_mtu);
 
-	dev->mtu = min(priv->mcast_mtu, priv->admin_mtu);
+	new_mtu = min(priv->mcast_mtu, priv->admin_mtu);
 
-	return 0;
+	if (priv->rn_ops->ndo_change_mtu) {
+		bool carrier_status = netif_carrier_ok(dev);
+
+		netif_carrier_off(dev);
+
+		/* notify lower level on the real mtu */
+		ret = priv->rn_ops->ndo_change_mtu(dev, new_mtu);
+
+		if (carrier_status)
+			netif_carrier_on(dev);
+	} else {
+		dev->mtu = new_mtu;
+	}
+
+	return ret;
+}
+
+static void ipoib_get_stats(struct net_device *dev,
+			    struct rtnl_link_stats64 *stats)
+{
+	struct ipoib_dev_priv *priv = ipoib_priv(dev);
+
+	if (priv->rn_ops->ndo_get_stats64)
+		priv->rn_ops->ndo_get_stats64(dev, stats);
+	else
+		netdev_stats_to_stats64(stats, &dev->stats);
 }
 
 /* Called with an RCU read lock taken */
@@ -1534,6 +1560,7 @@ static void ipoib_flush_neighs(struct ipoib_dev_priv *priv)
 	int i, wait_flushed = 0;
 
 	init_completion(&priv->ntbl.flushed);
+	set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
 
 	spin_lock_irqsave(&priv->lock, flags);
 
@@ -1578,7 +1605,6 @@ static void ipoib_neigh_hash_uninit(struct net_device *dev)
 
 	ipoib_dbg(priv, "ipoib_neigh_hash_uninit\n");
 	init_completion(&priv->ntbl.deleted);
-	set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
 
 	/* Stop GC if called at init fail need to cancel work */
 	stopped = test_and_set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
@@ -1808,6 +1834,7 @@ static const struct net_device_ops ipoib_netdev_ops_pf = {
 	.ndo_get_vf_stats	 = ipoib_get_vf_stats,
 	.ndo_set_vf_guid	 = ipoib_set_vf_guid,
 	.ndo_set_mac_address	 = ipoib_set_mac,
+	.ndo_get_stats64	 = ipoib_get_stats,
 };
 
 static const struct net_device_ops ipoib_netdev_ops_vf = {
@@ -1820,6 +1847,7 @@ static const struct net_device_ops ipoib_netdev_ops_vf = {
 	.ndo_tx_timeout		 = ipoib_timeout,
 	.ndo_set_rx_mode	 = ipoib_set_mcast_list,
 	.ndo_get_iflink		 = ipoib_get_iflink,
+	.ndo_get_stats64	 = ipoib_get_stats,
 };
 
 void ipoib_setup_common(struct net_device *dev)
@@ -1850,6 +1878,7 @@ static void ipoib_build_priv(struct net_device *dev)
 	priv->dev = dev;
 	spin_lock_init(&priv->lock);
 	init_rwsem(&priv->vlan_rwsem);
+	mutex_init(&priv->mcast_mutex);
 
 	INIT_LIST_HEAD(&priv->path_list);
 	INIT_LIST_HEAD(&priv->child_intfs);
@@ -2146,14 +2175,14 @@ static struct net_device *ipoib_add_port(const char *format,
 	priv->dev->dev_id = port - 1;
 
 	result = ib_query_port(hca, port, &attr);
-	if (!result)
-		priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
-	else {
+	if (result) {
 		printk(KERN_WARNING "%s: ib_query_port %d failed\n",
 		       hca->name, port);
 		goto device_init_failed;
 	}
 
+	priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
+
 	/* MTU will be reset when mcast join happens */
 	priv->dev->mtu  = IPOIB_UD_MTU(priv->max_ib_mtu);
 	priv->mcast_mtu  = priv->admin_mtu = priv->dev->mtu;
@@ -2184,12 +2213,14 @@ static struct net_device *ipoib_add_port(const char *format,
 		printk(KERN_WARNING "%s: ib_query_gid port %d failed (ret = %d)\n",
 		       hca->name, port, result);
 		goto device_init_failed;
-	} else
-		memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));
+	}
+
+	memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw,
+	       sizeof(union ib_gid));
 	set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
 
 	result = ipoib_dev_init(priv->dev, hca, port);
-	if (result < 0) {
+	if (result) {
 		printk(KERN_WARNING "%s: failed to initialize port %d (ret = %d)\n",
 		       hca->name, port, result);
 		goto device_init_failed;
@@ -2212,6 +2243,7 @@ static struct net_device *ipoib_add_port(const char *format,
 		goto register_failed;
 	}
 
+	result = -ENOMEM;
 	if (ipoib_cm_add_mode_attr(priv->dev))
 		goto sysfs_failed;
 	if (ipoib_add_pkey_attr(priv->dev))
@@ -2337,6 +2369,7 @@ static int __init ipoib_init_module(void)
 	ipoib_sendq_size = max3(ipoib_sendq_size, 2 * MAX_SEND_CQE, IPOIB_MIN_QUEUE_SIZE);
 #ifdef CONFIG_INFINIBAND_IPOIB_CM
 	ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP);
+	ipoib_max_conn_qp = max(ipoib_max_conn_qp, 0);
 #endif
 
 	/*
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 057f58e6afca..93e149efc1f5 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -684,15 +684,10 @@ void ipoib_mcast_start_thread(struct net_device *dev)
 int ipoib_mcast_stop_thread(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
-	unsigned long flags;
 
 	ipoib_dbg_mcast(priv, "stopping multicast thread\n");
 
-	spin_lock_irqsave(&priv->lock, flags);
-	cancel_delayed_work(&priv->mcast_task);
-	spin_unlock_irqrestore(&priv->lock, flags);
-
-	flush_workqueue(priv->wq);
+	cancel_delayed_work_sync(&priv->mcast_task);
 
 	return 0;
 }
@@ -748,6 +743,14 @@ void ipoib_mcast_remove_list(struct list_head *remove_list)
 {
 	struct ipoib_mcast *mcast, *tmcast;
 
+	/*
+	 * make sure the in-flight joins have finished before we attempt
+	 * to leave
+	 */
+	list_for_each_entry_safe(mcast, tmcast, remove_list, list)
+		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
+			wait_for_completion(&mcast->done);
+
 	list_for_each_entry_safe(mcast, tmcast, remove_list, list) {
 		ipoib_mcast_leave(mcast->dev, mcast);
 		ipoib_mcast_free(mcast);
@@ -838,6 +841,7 @@ void ipoib_mcast_dev_flush(struct net_device *dev)
 	struct ipoib_mcast *mcast, *tmcast;
 	unsigned long flags;
 
+	mutex_lock(&priv->mcast_mutex);
 	ipoib_dbg_mcast(priv, "flushing multicast list\n");
 
 	spin_lock_irqsave(&priv->lock, flags);
@@ -856,15 +860,8 @@ void ipoib_mcast_dev_flush(struct net_device *dev)
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 
-	/*
-	 * make sure the in-flight joins have finished before we attempt
-	 * to leave
-	 */
-	list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
-		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
-			wait_for_completion(&mcast->done);
-
 	ipoib_mcast_remove_list(&remove_list);
+	mutex_unlock(&priv->mcast_mutex);
 }
 
 static int ipoib_mcast_addr_is_valid(const u8 *addr, const u8 *broadcast)
@@ -982,14 +979,6 @@ void ipoib_mcast_restart_task(struct work_struct *work)
 	netif_addr_unlock(dev);
 	local_irq_restore(flags);
 
-	/*
-	 * make sure the in-flight joins have finished before we attempt
-	 * to leave
-	 */
-	list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
-		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
-			wait_for_completion(&mcast->done);
-
 	ipoib_mcast_remove_list(&remove_list);
 
 	/*
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 5a887efb4bdf..37b33d708c2d 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -83,6 +83,7 @@ static struct scsi_host_template iscsi_iser_sht;
 static struct iscsi_transport iscsi_iser_transport;
 static struct scsi_transport_template *iscsi_iser_scsi_transport;
 static struct workqueue_struct *release_wq;
+static DEFINE_MUTEX(unbind_iser_conn_mutex);
 struct iser_global ig;
 
 int iser_debug_level = 0;
@@ -550,12 +551,14 @@ iscsi_iser_conn_stop(struct iscsi_cls_conn *cls_conn, int flag)
 	 */
 	if (iser_conn) {
 		mutex_lock(&iser_conn->state_mutex);
+		mutex_lock(&unbind_iser_conn_mutex);
 		iser_conn_terminate(iser_conn);
 		iscsi_conn_stop(cls_conn, flag);
 
 		/* unbind */
 		iser_conn->iscsi_conn = NULL;
 		conn->dd_data = NULL;
+		mutex_unlock(&unbind_iser_conn_mutex);
 
 		complete(&iser_conn->stop_completion);
 		mutex_unlock(&iser_conn->state_mutex);
@@ -977,13 +980,21 @@ static int iscsi_iser_slave_alloc(struct scsi_device *sdev)
 	struct iser_conn *iser_conn;
 	struct ib_device *ib_dev;
 
+	mutex_lock(&unbind_iser_conn_mutex);
+
 	session = starget_to_session(scsi_target(sdev))->dd_data;
 	iser_conn = session->leadconn->dd_data;
+	if (!iser_conn) {
+		mutex_unlock(&unbind_iser_conn_mutex);
+		return -ENOTCONN;
+	}
 	ib_dev = iser_conn->ib_conn.device->ib_device;
 
 	if (!(ib_dev->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG))
 		blk_queue_virt_boundary(sdev->request_queue, ~MASK_4K);
 
+	mutex_unlock(&unbind_iser_conn_mutex);
+
 	return 0;
 }
 
diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c
index 12ed62ce9ff7..2a07692007bd 100644
--- a/drivers/infiniband/ulp/iser/iser_initiator.c
+++ b/drivers/infiniband/ulp/iser/iser_initiator.c
@@ -137,8 +137,10 @@ iser_prepare_write_cmd(struct iscsi_task *task,
 
 	if (unsol_sz < edtl) {
 		hdr->flags     |= ISER_WSV;
-		hdr->write_stag = cpu_to_be32(mem_reg->rkey);
-		hdr->write_va   = cpu_to_be64(mem_reg->sge.addr + unsol_sz);
+		if (buf_out->data_len > imm_sz) {
+			hdr->write_stag = cpu_to_be32(mem_reg->rkey);
+			hdr->write_va = cpu_to_be64(mem_reg->sge.addr + unsol_sz);
+		}
 
 		iser_dbg("Cmd itt:%d, WRITE tags, RKEY:%#.4X "
 			 "VA:%#llX + unsol:%d\n",
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index c538a38c91ce..26a004e97ae0 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -708,8 +708,14 @@ iser_calc_scsi_params(struct iser_conn *iser_conn,
 	unsigned short sg_tablesize, sup_sg_tablesize;
 
 	sg_tablesize = DIV_ROUND_UP(max_sectors * 512, SIZE_4K);
-	sup_sg_tablesize = min_t(unsigned, ISCSI_ISER_MAX_SG_TABLESIZE,
-				 device->ib_device->attrs.max_fast_reg_page_list_len);
+	if (device->ib_device->attrs.device_cap_flags &
+			IB_DEVICE_MEM_MGT_EXTENSIONS)
+		sup_sg_tablesize =
+			min_t(
+			 uint, ISCSI_ISER_MAX_SG_TABLESIZE,
+			 device->ib_device->attrs.max_fast_reg_page_list_len);
+	else
+		sup_sg_tablesize = ISCSI_ISER_MAX_SG_TABLESIZE;
 
 	iser_conn->scsi_sg_tablesize = min(sg_tablesize, sup_sg_tablesize);
 }