Merge tag 'v4.3-rc4' into locking/core, to pick up fixes before applying new changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

12 files changed, 263 insertions, 217 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 41d6911e244e..f1ccd40beae9 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -245,7 +245,6 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		props->device_cap_flags |= IB_DEVICE_BAD_QKEY_CNTR;
 	if (MLX5_CAP_GEN(mdev, apm))
 		props->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG;
-	props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY;
 	if (MLX5_CAP_GEN(mdev, xrc))
 		props->device_cap_flags |= IB_DEVICE_XRC;
 	props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
@@ -795,53 +794,6 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
 	return 0;
 }
 
-static int alloc_pa_mkey(struct mlx5_ib_dev *dev, u32 *key, u32 pdn)
-{
-	struct mlx5_create_mkey_mbox_in *in;
-	struct mlx5_mkey_seg *seg;
-	struct mlx5_core_mr mr;
-	int err;
-
-	in = kzalloc(sizeof(*in), GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
-
-	seg = &in->seg;
-	seg->flags = MLX5_PERM_LOCAL_READ | MLX5_ACCESS_MODE_PA;
-	seg->flags_pd = cpu_to_be32(pdn | MLX5_MKEY_LEN64);
-	seg->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
-	seg->start_addr = 0;
-
-	err = mlx5_core_create_mkey(dev->mdev, &mr, in, sizeof(*in),
-				    NULL, NULL, NULL);
-	if (err) {
-		mlx5_ib_warn(dev, "failed to create mkey, %d\n", err);
-		goto err_in;
-	}
-
-	kfree(in);
-	*key = mr.key;
-
-	return 0;
-
-err_in:
-	kfree(in);
-
-	return err;
-}
-
-static void free_pa_mkey(struct mlx5_ib_dev *dev, u32 key)
-{
-	struct mlx5_core_mr mr;
-	int err;
-
-	memset(&mr, 0, sizeof(mr));
-	mr.key = key;
-	err = mlx5_core_destroy_mkey(dev->mdev, &mr);
-	if (err)
-		mlx5_ib_warn(dev, "failed to destroy mkey 0x%x\n", key);
-}
-
 static struct ib_pd *mlx5_ib_alloc_pd(struct ib_device *ibdev,
 				      struct ib_ucontext *context,
 				      struct ib_udata *udata)
@@ -867,13 +819,6 @@ static struct ib_pd *mlx5_ib_alloc_pd(struct ib_device *ibdev,
 			kfree(pd);
 			return ERR_PTR(-EFAULT);
 		}
-	} else {
-		err = alloc_pa_mkey(to_mdev(ibdev), &pd->pa_lkey, pd->pdn);
-		if (err) {
-			mlx5_core_dealloc_pd(to_mdev(ibdev)->mdev, pd->pdn);
-			kfree(pd);
-			return ERR_PTR(err);
-		}
 	}
 
 	return &pd->ibpd;
@@ -884,9 +829,6 @@ static int mlx5_ib_dealloc_pd(struct ib_pd *pd)
 	struct mlx5_ib_dev *mdev = to_mdev(pd->device);
 	struct mlx5_ib_pd *mpd = to_mpd(pd);
 
-	if (!pd->uobject)
-		free_pa_mkey(mdev, mpd->pa_lkey);
-
 	mlx5_core_dealloc_pd(mdev->mdev, mpd->pdn);
 	kfree(mpd);
 
@@ -1245,18 +1187,10 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	struct ib_srq_init_attr attr;
 	struct mlx5_ib_dev *dev;
 	struct ib_cq_init_attr cq_attr = {.cqe = 1};
-	u32 rsvd_lkey;
 	int ret = 0;
 
 	dev = container_of(devr, struct mlx5_ib_dev, devr);
 
-	ret = mlx5_core_query_special_context(dev->mdev, &rsvd_lkey);
-	if (ret) {
-		pr_err("Failed to query special context %d\n", ret);
-		return ret;
-	}
-	dev->ib_dev.local_dma_lkey = rsvd_lkey;
-
 	devr->p0 = mlx5_ib_alloc_pd(&dev->ib_dev, NULL, NULL);
 	if (IS_ERR(devr->p0)) {
 		ret = PTR_ERR(devr->p0);
@@ -1418,6 +1352,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	strlcpy(dev->ib_dev.name, "mlx5_%d", IB_DEVICE_NAME_MAX);
 	dev->ib_dev.owner		= THIS_MODULE;
 	dev->ib_dev.node_type		= RDMA_NODE_IB_CA;
+	dev->ib_dev.local_dma_lkey	= 0 /* not supported for now */;
 	dev->num_ports		= MLX5_CAP_GEN(mdev, num_ports);
 	dev->ib_dev.phys_port_cnt     = dev->num_ports;
 	dev->ib_dev.num_comp_vectors    =
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index bb8cda79e881..22123b79d550 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -103,7 +103,6 @@ static inline struct mlx5_ib_ucontext *to_mucontext(struct ib_ucontext *ibuconte
 struct mlx5_ib_pd {
 	struct ib_pd		ibpd;
 	u32			pdn;
-	u32			pa_lkey;
 };
 
 /* Use macros here so that don't have to duplicate
@@ -213,7 +212,6 @@ struct mlx5_ib_qp {
 	int			uuarn;
 
 	int			create_type;
-	u32			pa_lkey;
 
 	/* Store signature errors */
 	bool			signature_en;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index c745c6c5e10d..6f521a3418e8 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -925,8 +925,6 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 			err = create_kernel_qp(dev, init_attr, qp, &in, &inlen);
 			if (err)
 				mlx5_ib_dbg(dev, "err %d\n", err);
-			else
-				qp->pa_lkey = to_mpd(pd)->pa_lkey;
 		}
 
 		if (err)
@@ -2045,7 +2043,7 @@ static void set_frwr_pages(struct mlx5_wqe_data_seg *dseg,
 		mfrpl->mapped_page_list[i] = cpu_to_be64(page_list[i] | perm);
 	dseg->addr = cpu_to_be64(mfrpl->map);
 	dseg->byte_count = cpu_to_be32(ALIGN(sizeof(u64) * wr->wr.fast_reg.page_list_len, 64));
-	dseg->lkey = cpu_to_be32(pd->pa_lkey);
+	dseg->lkey = cpu_to_be32(pd->ibpd.local_dma_lkey);
 }
 
 static __be32 send_ieth(struct ib_send_wr *wr)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index ca2873698d75..4cd5428a2399 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -80,7 +80,7 @@ enum {
 	IPOIB_NUM_WC		  = 4,
 
 	IPOIB_MAX_PATH_REC_QUEUE  = 3,
-	IPOIB_MAX_MCAST_QUEUE	  = 3,
+	IPOIB_MAX_MCAST_QUEUE	  = 64,
 
 	IPOIB_FLAG_OPER_UP	  = 0,
 	IPOIB_FLAG_INITIALIZED	  = 1,
@@ -548,6 +548,8 @@ void ipoib_path_iter_read(struct ipoib_path_iter *iter,
 
 int ipoib_mcast_attach(struct net_device *dev, u16 mlid,
 		       union ib_gid *mgid, int set_qkey);
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast);
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid);
 
 int ipoib_init_qp(struct net_device *dev);
 int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 36536ce5a3e2..f74316e679d2 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1149,6 +1149,9 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 	unsigned long dt;
 	unsigned long flags;
 	int i;
+	LIST_HEAD(remove_list);
+	struct ipoib_mcast *mcast, *tmcast;
+	struct net_device *dev = priv->dev;
 
 	if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
 		return;
@@ -1176,6 +1179,19 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 							  lockdep_is_held(&priv->lock))) != NULL) {
 			/* was the neigh idle for two GC periods */
 			if (time_after(neigh_obsolete, neigh->alive)) {
+				u8 *mgid = neigh->daddr + 4;
+
+				/* Is this multicast ? */
+				if (*mgid == 0xff) {
+					mcast = __ipoib_mcast_find(dev, mgid);
+
+					if (mcast && test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
+						list_del(&mcast->list);
+						rb_erase(&mcast->rb_node, &priv->multicast_tree);
+						list_add_tail(&mcast->list, &remove_list);
+					}
+				}
+
 				rcu_assign_pointer(*np,
 						   rcu_dereference_protected(neigh->hnext,
 									     lockdep_is_held(&priv->lock)));
@@ -1191,6 +1207,8 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 
 out_unlock:
 	spin_unlock_irqrestore(&priv->lock, flags);
+	list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
+		ipoib_mcast_leave(dev, mcast);
 }
 
 static void ipoib_reap_neigh(struct work_struct *work)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 09a1748f9d13..136cbefe00f8 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -153,7 +153,7 @@ static struct ipoib_mcast *ipoib_mcast_alloc(struct net_device *dev,
 	return mcast;
 }
 
-static struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct rb_node *n = priv->multicast_tree.rb_node;
@@ -508,17 +508,19 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 		rec.hop_limit	  = priv->broadcast->mcmember.hop_limit;
 
 		/*
-		 * Historically Linux IPoIB has never properly supported SEND
-		 * ONLY join. It emulated it by not providing all the required
-		 * attributes, which is enough to prevent group creation and
-		 * detect if there are full members or not. A major problem
-		 * with supporting SEND ONLY is detecting when the group is
-		 * auto-destroyed as IPoIB will cache the MLID..
+		 * Send-only IB Multicast joins do not work at the core
+		 * IB layer yet, so we can't use them here.  However,
+		 * we are emulating an Ethernet multicast send, which
+		 * does not require a multicast subscription and will
+		 * still send properly.  The most appropriate thing to
+		 * do is to create the group if it doesn't exist as that
+		 * most closely emulates the behavior, from a user space
+		 * application perspecitive, of Ethernet multicast
+		 * operation.  For now, we do a full join, maybe later
+		 * when the core IB layers support send only joins we
+		 * will use them.
 		 */
-#if 1
-		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
-			comp_mask &= ~IB_SA_MCMEMBER_REC_TRAFFIC_CLASS;
-#else
+#if 0
 		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
 			rec.join_state = 4;
 #endif
@@ -675,7 +677,7 @@ int ipoib_mcast_stop_thread(struct net_device *dev)
 	return 0;
 }
 
-static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	int ret = 0;
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 1ace5d83a4d7..f58ff96b6cbb 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -97,6 +97,11 @@ unsigned int iser_max_sectors = ISER_DEF_MAX_SECTORS;
 module_param_named(max_sectors, iser_max_sectors, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(max_sectors, "Max number of sectors in a single scsi command (default:1024");
 
+bool iser_always_reg = true;
+module_param_named(always_register, iser_always_reg, bool, S_IRUGO);
+MODULE_PARM_DESC(always_register,
+		 "Always register memory, even for continuous memory regions (default:true)");
+
 bool iser_pi_enable = false;
 module_param_named(pi_enable, iser_pi_enable, bool, S_IRUGO);
 MODULE_PARM_DESC(pi_enable, "Enable T10-PI offload support (default:disabled)");
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 86f6583485ef..a5edd6ede692 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -611,6 +611,7 @@ extern int iser_debug_level;
 extern bool iser_pi_enable;
 extern int iser_pi_guard;
 extern unsigned int iser_max_sectors;
+extern bool iser_always_reg;
 
 int iser_assign_reg_ops(struct iser_device *device);
 
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index 2493cc748db8..4c46d67d37a1 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -803,11 +803,12 @@ static int
 iser_reg_prot_sg(struct iscsi_iser_task *task,
 		 struct iser_data_buf *mem,
 		 struct iser_fr_desc *desc,
+		 bool use_dma_key,
 		 struct iser_mem_reg *reg)
 {
 	struct iser_device *device = task->iser_conn->ib_conn.device;
 
-	if (mem->dma_nents == 1)
+	if (use_dma_key)
 		return iser_reg_dma(device, mem, reg);
 
 	return device->reg_ops->reg_mem(task, mem, &desc->pi_ctx->rsc, reg);
@@ -817,11 +818,12 @@ static int
 iser_reg_data_sg(struct iscsi_iser_task *task,
 		 struct iser_data_buf *mem,
 		 struct iser_fr_desc *desc,
+		 bool use_dma_key,
 		 struct iser_mem_reg *reg)
 {
 	struct iser_device *device = task->iser_conn->ib_conn.device;
 
-	if (mem->dma_nents == 1)
+	if (use_dma_key)
 		return iser_reg_dma(device, mem, reg);
 
 	return device->reg_ops->reg_mem(task, mem, &desc->rsc, reg);
@@ -836,14 +838,17 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task,
 	struct iser_mem_reg *reg = &task->rdma_reg[dir];
 	struct iser_mem_reg *data_reg;
 	struct iser_fr_desc *desc = NULL;
+	bool use_dma_key;
 	int err;
 
 	err = iser_handle_unaligned_buf(task, mem, dir);
 	if (unlikely(err))
 		return err;
 
-	if (mem->dma_nents != 1 ||
-	    scsi_get_prot_op(task->sc) != SCSI_PROT_NORMAL) {
+	use_dma_key = (mem->dma_nents == 1 && !iser_always_reg &&
+		       scsi_get_prot_op(task->sc) == SCSI_PROT_NORMAL);
+
+	if (!use_dma_key) {
 		desc = device->reg_ops->reg_desc_get(ib_conn);
 		reg->mem_h = desc;
 	}
@@ -853,7 +858,7 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task,
 	else
 		data_reg = &task->desc.data_reg;
 
-	err = iser_reg_data_sg(task, mem, desc, data_reg);
+	err = iser_reg_data_sg(task, mem, desc, use_dma_key, data_reg);
 	if (unlikely(err))
 		goto err_reg;
 
@@ -866,7 +871,8 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task,
 			if (unlikely(err))
 				goto err_reg;
 
-			err = iser_reg_prot_sg(task, mem, desc, prot_reg);
+			err = iser_reg_prot_sg(task, mem, desc,
+					       use_dma_key, prot_reg);
 			if (unlikely(err))
 				goto err_reg;
 		}
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index ae70cc1463ac..85132d867bc8 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -133,11 +133,15 @@ static int iser_create_device_ib_res(struct iser_device *device)
 			     (unsigned long)comp);
 	}
 
-	device->mr = ib_get_dma_mr(device->pd, IB_ACCESS_LOCAL_WRITE |
-				   IB_ACCESS_REMOTE_WRITE |
-				   IB_ACCESS_REMOTE_READ);
-	if (IS_ERR(device->mr))
-		goto dma_mr_err;
+	if (!iser_always_reg) {
+		int access = IB_ACCESS_LOCAL_WRITE |
+			     IB_ACCESS_REMOTE_WRITE |
+			     IB_ACCESS_REMOTE_READ;
+
+		device->mr = ib_get_dma_mr(device->pd, access);
+		if (IS_ERR(device->mr))
+			goto dma_mr_err;
+	}
 
 	INIT_IB_EVENT_HANDLER(&device->event_handler, device->ib_device,
 				iser_event_handler);
@@ -147,7 +151,8 @@ static int iser_create_device_ib_res(struct iser_device *device)
 	return 0;
 
 handler_err:
-	ib_dereg_mr(device->mr);
+	if (device->mr)
+		ib_dereg_mr(device->mr);
 dma_mr_err:
 	for (i = 0; i < device->comps_used; i++)
 		tasklet_kill(&device->comps[i].tasklet);
@@ -173,7 +178,6 @@ comps_err:
 static void iser_free_device_ib_res(struct iser_device *device)
 {
 	int i;
-	BUG_ON(device->mr == NULL);
 
 	for (i = 0; i < device->comps_used; i++) {
 		struct iser_comp *comp = &device->comps[i];
@@ -184,7 +188,8 @@ static void iser_free_device_ib_res(struct iser_device *device)
 	}
 
 	(void)ib_unregister_event_handler(&device->event_handler);
-	(void)ib_dereg_mr(device->mr);
+	if (device->mr)
+		(void)ib_dereg_mr(device->mr);
 	ib_dealloc_pd(device->pd);
 
 	kfree(device->comps);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 403bd29443b8..aa59037d7504 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -238,8 +238,6 @@ isert_alloc_rx_descriptors(struct isert_conn *isert_conn)
 		rx_sg->lkey = device->pd->local_dma_lkey;
 	}
 
-	isert_conn->rx_desc_head = 0;
-
 	return 0;
 
 dma_map_fail:
@@ -634,7 +632,7 @@ static void
 isert_init_conn(struct isert_conn *isert_conn)
 {
 	isert_conn->state = ISER_CONN_INIT;
-	INIT_LIST_HEAD(&isert_conn->accept_node);
+	INIT_LIST_HEAD(&isert_conn->node);
 	init_completion(&isert_conn->login_comp);
 	init_completion(&isert_conn->login_req_comp);
 	init_completion(&isert_conn->wait);
@@ -762,28 +760,15 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	ret = isert_rdma_post_recvl(isert_conn);
 	if (ret)
 		goto out_conn_dev;
-	/*
-	 * Obtain the second reference now before isert_rdma_accept() to
-	 * ensure that any initiator generated REJECT CM event that occurs
-	 * asynchronously won't drop the last reference until the error path
-	 * in iscsi_target_login_sess_out() does it's ->iscsit_free_conn() ->
-	 * isert_free_conn() -> isert_put_conn() -> kref_put().
-	 */
-	if (!kref_get_unless_zero(&isert_conn->kref)) {
-		isert_warn("conn %p connect_release is running\n", isert_conn);
-		goto out_conn_dev;
-	}
 
 	ret = isert_rdma_accept(isert_conn);
 	if (ret)
 		goto out_conn_dev;
 
-	mutex_lock(&isert_np->np_accept_mutex);
-	list_add_tail(&isert_conn->accept_node, &isert_np->np_accept_list);
-	mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_lock(&isert_np->mutex);
+	list_add_tail(&isert_conn->node, &isert_np->accepted);
+	mutex_unlock(&isert_np->mutex);
 
-	isert_info("np %p: Allow accept_np to continue\n", np);
-	up(&isert_np->np_sem);
 	return 0;
 
 out_conn_dev:
@@ -831,13 +816,21 @@ static void
 isert_connected_handler(struct rdma_cm_id *cma_id)
 {
 	struct isert_conn *isert_conn = cma_id->qp->qp_context;
+	struct isert_np *isert_np = cma_id->context;
 
 	isert_info("conn %p\n", isert_conn);
 
 	mutex_lock(&isert_conn->mutex);
-	if (isert_conn->state != ISER_CONN_FULL_FEATURE)
-		isert_conn->state = ISER_CONN_UP;
+	isert_conn->state = ISER_CONN_UP;
+	kref_get(&isert_conn->kref);
 	mutex_unlock(&isert_conn->mutex);
+
+	mutex_lock(&isert_np->mutex);
+	list_move_tail(&isert_conn->node, &isert_np->pending);
+	mutex_unlock(&isert_np->mutex);
+
+	isert_info("np %p: Allow accept_np to continue\n", isert_np);
+	up(&isert_np->sem);
 }
 
 static void
@@ -903,14 +896,14 @@ isert_np_cma_handler(struct isert_np *isert_np,
 
 	switch (event) {
 	case RDMA_CM_EVENT_DEVICE_REMOVAL:
-		isert_np->np_cm_id = NULL;
+		isert_np->cm_id = NULL;
 		break;
 	case RDMA_CM_EVENT_ADDR_CHANGE:
-		isert_np->np_cm_id = isert_setup_id(isert_np);
-		if (IS_ERR(isert_np->np_cm_id)) {
+		isert_np->cm_id = isert_setup_id(isert_np);
+		if (IS_ERR(isert_np->cm_id)) {
 			isert_err("isert np %p setup id failed: %ld\n",
-				  isert_np, PTR_ERR(isert_np->np_cm_id));
-			isert_np->np_cm_id = NULL;
+				  isert_np, PTR_ERR(isert_np->cm_id));
+			isert_np->cm_id = NULL;
 		}
 		break;
 	default:
@@ -929,7 +922,7 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id,
 	struct isert_conn *isert_conn;
 	bool terminating = false;
 
-	if (isert_np->np_cm_id == cma_id)
+	if (isert_np->cm_id == cma_id)
 		return isert_np_cma_handler(cma_id->context, event);
 
 	isert_conn = cma_id->qp->qp_context;
@@ -945,13 +938,13 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id,
 	if (terminating)
 		goto out;
 
-	mutex_lock(&isert_np->np_accept_mutex);
-	if (!list_empty(&isert_conn->accept_node)) {
-		list_del_init(&isert_conn->accept_node);
+	mutex_lock(&isert_np->mutex);
+	if (!list_empty(&isert_conn->node)) {
+		list_del_init(&isert_conn->node);
 		isert_put_conn(isert_conn);
 		queue_work(isert_release_wq, &isert_conn->release_work);
 	}
-	mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_unlock(&isert_np->mutex);
 
 out:
 	return 0;
@@ -962,6 +955,7 @@ isert_connect_error(struct rdma_cm_id *cma_id)
 {
 	struct isert_conn *isert_conn = cma_id->qp->qp_context;
 
+	list_del_init(&isert_conn->node);
 	isert_conn->cm_id = NULL;
 	isert_put_conn(isert_conn);
 
@@ -1006,35 +1000,51 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 }
 
 static int
-isert_post_recv(struct isert_conn *isert_conn, u32 count)
+isert_post_recvm(struct isert_conn *isert_conn, u32 count)
 {
 	struct ib_recv_wr *rx_wr, *rx_wr_failed;
 	int i, ret;
-	unsigned int rx_head = isert_conn->rx_desc_head;
 	struct iser_rx_desc *rx_desc;
 
 	for (rx_wr = isert_conn->rx_wr, i = 0; i < count; i++, rx_wr++) {
-		rx_desc		= &isert_conn->rx_descs[rx_head];
-		rx_wr->wr_id	= (uintptr_t)rx_desc;
-		rx_wr->sg_list	= &rx_desc->rx_sg;
-		rx_wr->num_sge	= 1;
-		rx_wr->next	= rx_wr + 1;
-		rx_head = (rx_head + 1) & (ISERT_QP_MAX_RECV_DTOS - 1);
+		rx_desc = &isert_conn->rx_descs[i];
+		rx_wr->wr_id = (uintptr_t)rx_desc;
+		rx_wr->sg_list = &rx_desc->rx_sg;
+		rx_wr->num_sge = 1;
+		rx_wr->next = rx_wr + 1;
 	}
-
 	rx_wr--;
 	rx_wr->next = NULL; /* mark end of work requests list */
 
 	isert_conn->post_recv_buf_count += count;
 	ret = ib_post_recv(isert_conn->qp, isert_conn->rx_wr,
-				&rx_wr_failed);
+			   &rx_wr_failed);
 	if (ret) {
 		isert_err("ib_post_recv() failed with ret: %d\n", ret);
 		isert_conn->post_recv_buf_count -= count;
-	} else {
-		isert_dbg("Posted %d RX buffers\n", count);
-		isert_conn->rx_desc_head = rx_head;
 	}
+
+	return ret;
+}
+
+static int
+isert_post_recv(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc)
+{
+	struct ib_recv_wr *rx_wr_failed, rx_wr;
+	int ret;
+
+	rx_wr.wr_id = (uintptr_t)rx_desc;
+	rx_wr.sg_list = &rx_desc->rx_sg;
+	rx_wr.num_sge = 1;
+	rx_wr.next = NULL;
+
+	isert_conn->post_recv_buf_count++;
+	ret = ib_post_recv(isert_conn->qp, &rx_wr, &rx_wr_failed);
+	if (ret) {
+		isert_err("ib_post_recv() failed with ret: %d\n", ret);
+		isert_conn->post_recv_buf_count--;
+	}
+
 	return ret;
 }
 
@@ -1205,7 +1215,8 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login,
 			if (ret)
 				return ret;
 
-			ret = isert_post_recv(isert_conn, ISERT_MIN_POSTED_RX);
+			ret = isert_post_recvm(isert_conn,
+					       ISERT_QP_MAX_RECV_DTOS);
 			if (ret)
 				return ret;
 
@@ -1278,7 +1289,7 @@ isert_rx_login_req(struct isert_conn *isert_conn)
 }
 
 static struct iscsi_cmd
-*isert_allocate_cmd(struct iscsi_conn *conn)
+*isert_allocate_cmd(struct iscsi_conn *conn, struct iser_rx_desc *rx_desc)
 {
 	struct isert_conn *isert_conn = conn->context;
 	struct isert_cmd *isert_cmd;
@@ -1292,6 +1303,7 @@ static struct iscsi_cmd
 	isert_cmd = iscsit_priv_cmd(cmd);
 	isert_cmd->conn = isert_conn;
 	isert_cmd->iscsi_cmd = cmd;
+	isert_cmd->rx_desc = rx_desc;
 
 	return cmd;
 }
@@ -1303,9 +1315,9 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 {
 	struct iscsi_conn *conn = isert_conn->conn;
 	struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)buf;
-	struct scatterlist *sg;
 	int imm_data, imm_data_len, unsol_data, sg_nents, rc;
 	bool dump_payload = false;
+	unsigned int data_len;
 
 	rc = iscsit_setup_scsi_cmd(conn, cmd, buf);
 	if (rc < 0)
@@ -1314,7 +1326,10 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 	imm_data = cmd->immediate_data;
 	imm_data_len = cmd->first_burst_len;
 	unsol_data = cmd->unsolicited_data;
+	data_len = cmd->se_cmd.data_length;
 
+	if (imm_data && imm_data_len == data_len)
+		cmd->se_cmd.se_cmd_flags |= SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
 	rc = iscsit_process_scsi_cmd(conn, cmd, hdr);
 	if (rc < 0) {
 		return 0;
@@ -1326,13 +1341,20 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 	if (!imm_data)
 		return 0;
 
-	sg = &cmd->se_cmd.t_data_sg[0];
-	sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE));
-
-	isert_dbg("Copying Immediate SG: %p sg_nents: %u from %p imm_data_len: %d\n",
-		  sg, sg_nents, &rx_desc->data[0], imm_data_len);
-
-	sg_copy_from_buffer(sg, sg_nents, &rx_desc->data[0], imm_data_len);
+	if (imm_data_len != data_len) {
+		sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE));
+		sg_copy_from_buffer(cmd->se_cmd.t_data_sg, sg_nents,
+				    &rx_desc->data[0], imm_data_len);
+		isert_dbg("Copy Immediate sg_nents: %u imm_data_len: %d\n",
+			  sg_nents, imm_data_len);
+	} else {
+		sg_init_table(&isert_cmd->sg, 1);
+		cmd->se_cmd.t_data_sg = &isert_cmd->sg;
+		cmd->se_cmd.t_data_nents = 1;
+		sg_set_buf(&isert_cmd->sg, &rx_desc->data[0], imm_data_len);
+		isert_dbg("Transfer Immediate imm_data_len: %d\n",
+			  imm_data_len);
+	}
 
 	cmd->write_data_done += imm_data_len;
 
@@ -1407,6 +1429,15 @@ isert_handle_iscsi_dataout(struct isert_conn *isert_conn,
 	if (rc < 0)
 		return rc;
 
+	/*
+	 * multiple data-outs on the same command can arrive -
+	 * so post the buffer before hand
+	 */
+	rc = isert_post_recv(isert_conn, rx_desc);
+	if (rc) {
+		isert_err("ib_post_recv failed with %d\n", rc);
+		return rc;
+	}
 	return 0;
 }
 
@@ -1479,7 +1510,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 
 	switch (opcode) {
 	case ISCSI_OP_SCSI_CMD:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
@@ -1493,7 +1524,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 					rx_desc, (unsigned char *)hdr);
 		break;
 	case ISCSI_OP_NOOP_OUT:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
@@ -1506,7 +1537,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 						(unsigned char *)hdr);
 		break;
 	case ISCSI_OP_SCSI_TMFUNC:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
@@ -1514,22 +1545,20 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 						(unsigned char *)hdr);
 		break;
 	case ISCSI_OP_LOGOUT:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
 		ret = iscsit_handle_logout_cmd(conn, cmd, (unsigned char *)hdr);
 		break;
 	case ISCSI_OP_TEXT:
-		if (be32_to_cpu(hdr->ttt) != 0xFFFFFFFF) {
+		if (be32_to_cpu(hdr->ttt) != 0xFFFFFFFF)
 			cmd = iscsit_find_cmd_from_itt(conn, hdr->itt);
-			if (!cmd)
-				break;
-		} else {
-			cmd = isert_allocate_cmd(conn);
-			if (!cmd)
-				break;
-		}
+		else
+			cmd = isert_allocate_cmd(conn, rx_desc);
+
+		if (!cmd)
+			break;
 
 		isert_cmd = iscsit_priv_cmd(cmd);
 		ret = isert_handle_text_cmd(isert_conn, isert_cmd, cmd,
@@ -1589,7 +1618,7 @@ isert_rcv_completion(struct iser_rx_desc *desc,
 	struct ib_device *ib_dev = isert_conn->cm_id->device;
 	struct iscsi_hdr *hdr;
 	u64 rx_dma;
-	int rx_buflen, outstanding;
+	int rx_buflen;
 
 	if ((char *)desc == isert_conn->login_req_buf) {
 		rx_dma = isert_conn->login_req_dma;
@@ -1629,22 +1658,6 @@ isert_rcv_completion(struct iser_rx_desc *desc,
 				      DMA_FROM_DEVICE);
 
 	isert_conn->post_recv_buf_count--;
-	isert_dbg("Decremented post_recv_buf_count: %d\n",
-		  isert_conn->post_recv_buf_count);
-
-	if ((char *)desc == isert_conn->login_req_buf)
-		return;
-
-	outstanding = isert_conn->post_recv_buf_count;
-	if (outstanding + ISERT_MIN_POSTED_RX <= ISERT_QP_MAX_RECV_DTOS) {
-		int err, count = min(ISERT_QP_MAX_RECV_DTOS - outstanding,
-				ISERT_MIN_POSTED_RX);
-		err = isert_post_recv(isert_conn, count);
-		if (err) {
-			isert_err("isert_post_recv() count: %d failed, %d\n",
-			       count, err);
-		}
-	}
 }
 
 static int
@@ -2156,6 +2169,12 @@ isert_post_response(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd)
 	struct ib_send_wr *wr_failed;
 	int ret;
 
+	ret = isert_post_recv(isert_conn, isert_cmd->rx_desc);
+	if (ret) {
+		isert_err("ib_post_recv failed with %d\n", ret);
+		return ret;
+	}
+
 	ret = ib_post_send(isert_conn->qp, &isert_cmd->tx_desc.send_wr,
 			   &wr_failed);
 	if (ret) {
@@ -2950,6 +2969,12 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 				   &isert_cmd->tx_desc.send_wr);
 		isert_cmd->rdma_wr.s_send_wr.next = &isert_cmd->tx_desc.send_wr;
 		wr->send_wr_num += 1;
+
+		rc = isert_post_recv(isert_conn, isert_cmd->rx_desc);
+		if (rc) {
+			isert_err("ib_post_recv failed with %d\n", rc);
+			return rc;
+		}
 	}
 
 	rc = ib_post_send(isert_conn->qp, wr->send_wr, &wr_failed);
@@ -2999,9 +3024,16 @@ isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery)
 static int
 isert_immediate_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state)
 {
-	int ret;
+	struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+	int ret = 0;
 
 	switch (state) {
+	case ISTATE_REMOVE:
+		spin_lock_bh(&conn->cmd_lock);
+		list_del_init(&cmd->i_conn_node);
+		spin_unlock_bh(&conn->cmd_lock);
+		isert_put_cmd(isert_cmd, true);
+		break;
 	case ISTATE_SEND_NOPIN_WANT_RESPONSE:
 		ret = isert_put_nopin(cmd, conn, false);
 		break;
@@ -3106,10 +3138,10 @@ isert_setup_np(struct iscsi_np *np,
 		isert_err("Unable to allocate struct isert_np\n");
 		return -ENOMEM;
 	}
-	sema_init(&isert_np->np_sem, 0);
-	mutex_init(&isert_np->np_accept_mutex);
-	INIT_LIST_HEAD(&isert_np->np_accept_list);
-	init_completion(&isert_np->np_login_comp);
+	sema_init(&isert_np->sem, 0);
+	mutex_init(&isert_np->mutex);
+	INIT_LIST_HEAD(&isert_np->accepted);
+	INIT_LIST_HEAD(&isert_np->pending);
 	isert_np->np = np;
 
 	/*
@@ -3125,7 +3157,7 @@ isert_setup_np(struct iscsi_np *np,
 		goto out;
 	}
 
-	isert_np->np_cm_id = isert_lid;
+	isert_np->cm_id = isert_lid;
 	np->np_context = isert_np;
 
 	return 0;
@@ -3214,7 +3246,7 @@ isert_accept_np(struct iscsi_np *np, struct iscsi_conn *conn)
 	int ret;
 
 accept_wait:
-	ret = down_interruptible(&isert_np->np_sem);
+	ret = down_interruptible(&isert_np->sem);
 	if (ret)
 		return -ENODEV;
 
@@ -3231,15 +3263,15 @@ accept_wait:
 	}
 	spin_unlock_bh(&np->np_thread_lock);
 
-	mutex_lock(&isert_np->np_accept_mutex);
-	if (list_empty(&isert_np->np_accept_list)) {
-		mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_lock(&isert_np->mutex);
+	if (list_empty(&isert_np->pending)) {
+		mutex_unlock(&isert_np->mutex);
 		goto accept_wait;
 	}
-	isert_conn = list_first_entry(&isert_np->np_accept_list,
-			struct isert_conn, accept_node);
-	list_del_init(&isert_conn->accept_node);
-	mutex_unlock(&isert_np->np_accept_mutex);
+	isert_conn = list_first_entry(&isert_np->pending,
+			struct isert_conn, node);
+	list_del_init(&isert_conn->node);
+	mutex_unlock(&isert_np->mutex);
 
 	conn->context = isert_conn;
 	isert_conn->conn = conn;
@@ -3257,28 +3289,39 @@ isert_free_np(struct iscsi_np *np)
 	struct isert_np *isert_np = np->np_context;
 	struct isert_conn *isert_conn, *n;
 
-	if (isert_np->np_cm_id)
-		rdma_destroy_id(isert_np->np_cm_id);
+	if (isert_np->cm_id)
+		rdma_destroy_id(isert_np->cm_id);
 
 	/*
 	 * FIXME: At this point we don't have a good way to insure
 	 * that at this point we don't have hanging connections that
 	 * completed RDMA establishment but didn't start iscsi login
 	 * process. So work-around this by cleaning up what ever piled
-	 * up in np_accept_list.
+	 * up in accepted and pending lists.
 	 */
-	mutex_lock(&isert_np->np_accept_mutex);
-	if (!list_empty(&isert_np->np_accept_list)) {
-		isert_info("Still have isert connections, cleaning up...\n");
+	mutex_lock(&isert_np->mutex);
+	if (!list_empty(&isert_np->pending)) {
+		isert_info("Still have isert pending connections\n");
+		list_for_each_entry_safe(isert_conn, n,
+					 &isert_np->pending,
+					 node) {
+			isert_info("cleaning isert_conn %p state (%d)\n",
+				   isert_conn, isert_conn->state);
+			isert_connect_release(isert_conn);
+		}
+	}
+
+	if (!list_empty(&isert_np->accepted)) {
+		isert_info("Still have isert accepted connections\n");
 		list_for_each_entry_safe(isert_conn, n,
-					 &isert_np->np_accept_list,
-					 accept_node) {
+					 &isert_np->accepted,
+					 node) {
 			isert_info("cleaning isert_conn %p state (%d)\n",
 				   isert_conn, isert_conn->state);
 			isert_connect_release(isert_conn);
 		}
 	}
-	mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_unlock(&isert_np->mutex);
 
 	np->np_context = NULL;
 	kfree(isert_np);
@@ -3345,6 +3388,41 @@ isert_wait4flush(struct isert_conn *isert_conn)
 	wait_for_completion(&isert_conn->wait_comp_err);
 }
 
+/**
+ * isert_put_unsol_pending_cmds() - Drop commands waiting for
+ *     unsolicitate dataout
+ * @conn:    iscsi connection
+ *
+ * We might still have commands that are waiting for unsolicited
+ * dataouts messages. We must put the extra reference on those
+ * before blocking on the target_wait_for_session_cmds
+ */
+static void
+isert_put_unsol_pending_cmds(struct iscsi_conn *conn)
+{
+	struct iscsi_cmd *cmd, *tmp;
+	static LIST_HEAD(drop_cmd_list);
+
+	spin_lock_bh(&conn->cmd_lock);
+	list_for_each_entry_safe(cmd, tmp, &conn->conn_cmd_list, i_conn_node) {
+		if ((cmd->cmd_flags & ICF_NON_IMMEDIATE_UNSOLICITED_DATA) &&
+		    (cmd->write_data_done < conn->sess->sess_ops->FirstBurstLength) &&
+		    (cmd->write_data_done < cmd->se_cmd.data_length))
+			list_move_tail(&cmd->i_conn_node, &drop_cmd_list);
+	}
+	spin_unlock_bh(&conn->cmd_lock);
+
+	list_for_each_entry_safe(cmd, tmp, &drop_cmd_list, i_conn_node) {
+		list_del_init(&cmd->i_conn_node);
+		if (cmd->i_state != ISTATE_REMOVE) {
+			struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+
+			isert_info("conn %p dropping cmd %p\n", conn, cmd);
+			isert_put_cmd(isert_cmd, true);
+		}
+	}
+}
+
 static void isert_wait_conn(struct iscsi_conn *conn)
 {
 	struct isert_conn *isert_conn = conn->context;
@@ -3363,8 +3441,9 @@ static void isert_wait_conn(struct iscsi_conn *conn)
 	isert_conn_terminate(isert_conn);
 	mutex_unlock(&isert_conn->mutex);
 
-	isert_wait4cmds(conn);
 	isert_wait4flush(isert_conn);
+	isert_put_unsol_pending_cmds(conn);
+	isert_wait4cmds(conn);
 	isert_wait4logout(isert_conn);
 
 	queue_work(isert_release_wq, &isert_conn->release_work);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 6a04ba3c0f72..c5b99bcecbcf 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -113,7 +113,6 @@ enum {
 };
 
 struct isert_rdma_wr {
-	struct list_head	wr_list;
 	struct isert_cmd	*isert_cmd;
 	enum iser_ib_op_code	iser_ib_op;
 	struct ib_sge		*ib_sge;
@@ -134,14 +133,13 @@ struct isert_cmd {
 	uint64_t		write_va;
 	u64			pdu_buf_dma;
 	u32			pdu_buf_len;
-	u32			read_va_off;
-	u32			write_va_off;
-	u32			rdma_wr_num;
 	struct isert_conn	*conn;
 	struct iscsi_cmd	*iscsi_cmd;
 	struct iser_tx_desc	tx_desc;
+	struct iser_rx_desc	*rx_desc;
 	struct isert_rdma_wr	rdma_wr;
 	struct work_struct	comp_work;
+	struct scatterlist	sg;
 };
 
 struct isert_device;
@@ -159,11 +157,10 @@ struct isert_conn {
 	u64			login_req_dma;
 	int			login_req_len;
 	u64			login_rsp_dma;
-	unsigned int		rx_desc_head;
 	struct iser_rx_desc	*rx_descs;
-	struct ib_recv_wr	rx_wr[ISERT_MIN_POSTED_RX];
+	struct ib_recv_wr	rx_wr[ISERT_QP_MAX_RECV_DTOS];
 	struct iscsi_conn	*conn;
-	struct list_head	accept_node;
+	struct list_head	node;
 	struct completion	login_comp;
 	struct completion	login_req_comp;
 	struct iser_tx_desc	login_tx_desc;
@@ -222,9 +219,9 @@ struct isert_device {
 
 struct isert_np {
 	struct iscsi_np         *np;
-	struct semaphore	np_sem;
-	struct rdma_cm_id	*np_cm_id;
-	struct mutex		np_accept_mutex;
-	struct list_head	np_accept_list;
-	struct completion	np_login_comp;
+	struct semaphore	sem;
+	struct rdma_cm_id	*cm_id;
+	struct mutex		mutex;
+	struct list_head	accepted;
+	struct list_head	pending;
 };