Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending

Pull SCSI target fixes from Nicholas Bellinger:
 "The highlights this merge window include:

   - Allow target fabric drivers to function as built-in.  (Roland)
   - Fix tcm_loop multi-TPG endpoint nexus bug.  (Hannes)
   - Move per device config_item_type into se_subsystem_api, allowing
     configfs attributes to be defined at module_init time.  (Jerome +
     nab)
   - Convert existing IBLOCK/FILEIO/RAMDISK/PSCSI/TCMU drivers to use
     external configfs attributes.  (nab)
   - A number of iser-target fixes related to active session + network
     portal shutdown stability during extended stress testing.  (Sagi +
     Slava)
   - Dynamic allocation of T10-PI contexts for iser-target, fixing a
     potentially bogus iscsi_np->tpg_np pointer reference in >= v3.14
     code.  (Sagi)
   - iser-target performance + scalability improvements.  (Sagi)
   - Fixes for SPC-4 Persistent Reservation AllRegistrants spec
     compliance.  (Ilias + James + nab)
   - Avoid potential short kern_sendmsg() in iscsi-target for now until
     Al's conversion to use msghdr iteration is merged post -rc1.
     (Viro)

  Also, Sagi has requested a number of iser-target patches (9) that
  address stability issues he's encountered during extended stress
  testing be considered for v3.10.y + v3.14.y code.  Given the amount of
  LOC involved, it will certainly require extra backporting effort.

  Apologies in advance to Greg-KH & Co on this.  Sagi and I will be
  working post-merge to ensure they each get applied correctly"

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending: (53 commits)
  target: Allow AllRegistrants to re-RESERVE existing reservation
  uapi/linux/target_core_user.h: fix headers_install.sh badness
  iscsi-target: Fail connection on short sendmsg writes
  iscsi-target: nullify session in failed login sequence
  target: Avoid dropping AllRegistrants reservation during unregister
  target: Fix R_HOLDER bit usage for AllRegistrants
  iscsi-target: Drop left-over bogus iscsi_np->tpg_np
  iser-target: Fix wc->wr_id cast warning
  iser-target: Remove code duplication
  iser-target: Adjust log levels and prettify some prints
  iser-target: Use debug_level parameter to control logging level
  iser-target: Fix logout sequence
  iser-target: Don't wait for session commands from completion context
  iser-target: Reduce CQ lock contention by batch polling
  iser-target: Introduce isert_poll_budget
  iser-target: Remove an atomic operation from the IO path
  iser-target: Remove redundant call to isert_conn_terminate
  iser-target: Use single CQ for TX and RX
  iser-target: Centralize completion elements to a context
  iser-target: Cast wr_id with uintptr_t instead of unsinged long
  ...

2 files changed, 886 insertions, 793 deletions

diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 10641b7816f4..dafb3c531f96 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -22,7 +22,6 @@
 #include <linux/socket.h>
 #include <linux/in.h>
 #include <linux/in6.h>
-#include <linux/llist.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/rdma_cm.h>
 #include <target/target_core_base.h>
@@ -36,11 +35,17 @@
 #define	ISERT_MAX_CONN		8
 #define ISER_MAX_RX_CQ_LEN	(ISERT_QP_MAX_RECV_DTOS * ISERT_MAX_CONN)
 #define ISER_MAX_TX_CQ_LEN	(ISERT_QP_MAX_REQ_DTOS  * ISERT_MAX_CONN)
+#define ISER_MAX_CQ_LEN		(ISER_MAX_RX_CQ_LEN + ISER_MAX_TX_CQ_LEN + \
+				 ISERT_MAX_CONN)
+
+int isert_debug_level = 0;
+module_param_named(debug_level, isert_debug_level, int, 0644);
+MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0 (default:0)");
 
 static DEFINE_MUTEX(device_list_mutex);
 static LIST_HEAD(device_list);
-static struct workqueue_struct *isert_rx_wq;
 static struct workqueue_struct *isert_comp_wq;
+static struct workqueue_struct *isert_release_wq;
 
 static void
 isert_unmap_cmd(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn);
@@ -54,19 +59,32 @@ isert_reg_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	       struct isert_rdma_wr *wr);
 static int
 isert_put_response(struct iscsi_conn *conn, struct iscsi_cmd *cmd);
+static int
+isert_rdma_post_recvl(struct isert_conn *isert_conn);
+static int
+isert_rdma_accept(struct isert_conn *isert_conn);
+struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np);
+
+static inline bool
+isert_prot_cmd(struct isert_conn *conn, struct se_cmd *cmd)
+{
+	return (conn->pi_support &&
+		cmd->prot_op != TARGET_PROT_NORMAL);
+}
+
 
 static void
 isert_qp_event_callback(struct ib_event *e, void *context)
 {
 	struct isert_conn *isert_conn = (struct isert_conn *)context;
 
-	pr_err("isert_qp_event_callback event: %d\n", e->event);
+	isert_err("conn %p event: %d\n", isert_conn, e->event);
 	switch (e->event) {
 	case IB_EVENT_COMM_EST:
 		rdma_notify(isert_conn->conn_cm_id, IB_EVENT_COMM_EST);
 		break;
 	case IB_EVENT_QP_LAST_WQE_REACHED:
-		pr_warn("Reached TX IB_EVENT_QP_LAST_WQE_REACHED:\n");
+		isert_warn("Reached TX IB_EVENT_QP_LAST_WQE_REACHED\n");
 		break;
 	default:
 		break;
@@ -80,39 +98,41 @@ isert_query_device(struct ib_device *ib_dev, struct ib_device_attr *devattr)
 
 	ret = ib_query_device(ib_dev, devattr);
 	if (ret) {
-		pr_err("ib_query_device() failed: %d\n", ret);
+		isert_err("ib_query_device() failed: %d\n", ret);
 		return ret;
 	}
-	pr_debug("devattr->max_sge: %d\n", devattr->max_sge);
-	pr_debug("devattr->max_sge_rd: %d\n", devattr->max_sge_rd);
+	isert_dbg("devattr->max_sge: %d\n", devattr->max_sge);
+	isert_dbg("devattr->max_sge_rd: %d\n", devattr->max_sge_rd);
 
 	return 0;
 }
 
 static int
-isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id,
-		    u8 protection)
+isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id)
 {
 	struct isert_device *device = isert_conn->conn_device;
 	struct ib_qp_init_attr attr;
-	int ret, index, min_index = 0;
+	struct isert_comp *comp;
+	int ret, i, min = 0;
 
 	mutex_lock(&device_list_mutex);
-	for (index = 0; index < device->cqs_used; index++)
-		if (device->cq_active_qps[index] <
-		    device->cq_active_qps[min_index])
-			min_index = index;
-	device->cq_active_qps[min_index]++;
-	pr_debug("isert_conn_setup_qp: Using min_index: %d\n", min_index);
+	for (i = 0; i < device->comps_used; i++)
+		if (device->comps[i].active_qps <
+		    device->comps[min].active_qps)
+			min = i;
+	comp = &device->comps[min];
+	comp->active_qps++;
+	isert_info("conn %p, using comp %p min_index: %d\n",
+		   isert_conn, comp, min);
 	mutex_unlock(&device_list_mutex);
 
 	memset(&attr, 0, sizeof(struct ib_qp_init_attr));
 	attr.event_handler = isert_qp_event_callback;
 	attr.qp_context = isert_conn;
-	attr.send_cq = device->dev_tx_cq[min_index];
-	attr.recv_cq = device->dev_rx_cq[min_index];
+	attr.send_cq = comp->cq;
+	attr.recv_cq = comp->cq;
 	attr.cap.max_send_wr = ISERT_QP_MAX_REQ_DTOS;
-	attr.cap.max_recv_wr = ISERT_QP_MAX_RECV_DTOS;
+	attr.cap.max_recv_wr = ISERT_QP_MAX_RECV_DTOS + 1;
 	/*
 	 * FIXME: Use devattr.max_sge - 2 for max_send_sge as
 	 * work-around for RDMA_READs with ConnectX-2.
@@ -126,29 +146,29 @@ isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id,
 	attr.cap.max_recv_sge = 1;
 	attr.sq_sig_type = IB_SIGNAL_REQ_WR;
 	attr.qp_type = IB_QPT_RC;
-	if (protection)
+	if (device->pi_capable)
 		attr.create_flags |= IB_QP_CREATE_SIGNATURE_EN;
 
-	pr_debug("isert_conn_setup_qp cma_id->device: %p\n",
-		 cma_id->device);
-	pr_debug("isert_conn_setup_qp conn_pd->device: %p\n",
-		 isert_conn->conn_pd->device);
-
 	ret = rdma_create_qp(cma_id, isert_conn->conn_pd, &attr);
 	if (ret) {
-		pr_err("rdma_create_qp failed for cma_id %d\n", ret);
-		return ret;
+		isert_err("rdma_create_qp failed for cma_id %d\n", ret);
+		goto err;
 	}
 	isert_conn->conn_qp = cma_id->qp;
-	pr_debug("rdma_create_qp() returned success >>>>>>>>>>>>>>>>>>>>>>>>>.\n");
 
 	return 0;
+err:
+	mutex_lock(&device_list_mutex);
+	comp->active_qps--;
+	mutex_unlock(&device_list_mutex);
+
+	return ret;
 }
 
 static void
 isert_cq_event_callback(struct ib_event *e, void *context)
 {
-	pr_debug("isert_cq_event_callback event: %d\n", e->event);
+	isert_dbg("event: %d\n", e->event);
 }
 
 static int
@@ -182,6 +202,7 @@ isert_alloc_rx_descriptors(struct isert_conn *isert_conn)
 	}
 
 	isert_conn->conn_rx_desc_head = 0;
+
 	return 0;
 
 dma_map_fail:
@@ -193,6 +214,8 @@ dma_map_fail:
 	kfree(isert_conn->conn_rx_descs);
 	isert_conn->conn_rx_descs = NULL;
 fail:
+	isert_err("conn %p failed to allocate rx descriptors\n", isert_conn);
+
 	return -ENOMEM;
 }
 
@@ -216,27 +239,23 @@ isert_free_rx_descriptors(struct isert_conn *isert_conn)
 	isert_conn->conn_rx_descs = NULL;
 }
 
-static void isert_cq_tx_work(struct work_struct *);
-static void isert_cq_tx_callback(struct ib_cq *, void *);
-static void isert_cq_rx_work(struct work_struct *);
-static void isert_cq_rx_callback(struct ib_cq *, void *);
+static void isert_cq_work(struct work_struct *);
+static void isert_cq_callback(struct ib_cq *, void *);
 
 static int
 isert_create_device_ib_res(struct isert_device *device)
 {
 	struct ib_device *ib_dev = device->ib_device;
-	struct isert_cq_desc *cq_desc;
 	struct ib_device_attr *dev_attr;
-	int ret = 0, i, j;
-	int max_rx_cqe, max_tx_cqe;
+	int ret = 0, i;
+	int max_cqe;
 
 	dev_attr = &device->dev_attr;
 	ret = isert_query_device(ib_dev, dev_attr);
 	if (ret)
 		return ret;
 
-	max_rx_cqe = min(ISER_MAX_RX_CQ_LEN, dev_attr->max_cqe);
-	max_tx_cqe = min(ISER_MAX_TX_CQ_LEN, dev_attr->max_cqe);
+	max_cqe = min(ISER_MAX_CQ_LEN, dev_attr->max_cqe);
 
 	/* asign function handlers */
 	if (dev_attr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS &&
@@ -254,55 +273,38 @@ isert_create_device_ib_res(struct isert_device *device)
 	device->pi_capable = dev_attr->device_cap_flags &
 			     IB_DEVICE_SIGNATURE_HANDOVER ? true : false;
 
-	device->cqs_used = min_t(int, num_online_cpus(),
-				 device->ib_device->num_comp_vectors);
-	device->cqs_used = min(ISERT_MAX_CQ, device->cqs_used);
-	pr_debug("Using %d CQs, device %s supports %d vectors support "
-		 "Fast registration %d pi_capable %d\n",
-		 device->cqs_used, device->ib_device->name,
-		 device->ib_device->num_comp_vectors, device->use_fastreg,
-		 device->pi_capable);
-	device->cq_desc = kzalloc(sizeof(struct isert_cq_desc) *
-				device->cqs_used, GFP_KERNEL);
-	if (!device->cq_desc) {
-		pr_err("Unable to allocate device->cq_desc\n");
+	device->comps_used = min(ISERT_MAX_CQ, min_t(int, num_online_cpus(),
+					device->ib_device->num_comp_vectors));
+	isert_info("Using %d CQs, %s supports %d vectors support "
+		   "Fast registration %d pi_capable %d\n",
+		   device->comps_used, device->ib_device->name,
+		   device->ib_device->num_comp_vectors, device->use_fastreg,
+		   device->pi_capable);
+
+	device->comps = kcalloc(device->comps_used, sizeof(struct isert_comp),
+				GFP_KERNEL);
+	if (!device->comps) {
+		isert_err("Unable to allocate completion contexts\n");
 		return -ENOMEM;
 	}
-	cq_desc = device->cq_desc;
-
-	for (i = 0; i < device->cqs_used; i++) {
-		cq_desc[i].device = device;
-		cq_desc[i].cq_index = i;
-
-		INIT_WORK(&cq_desc[i].cq_rx_work, isert_cq_rx_work);
-		device->dev_rx_cq[i] = ib_create_cq(device->ib_device,
-						isert_cq_rx_callback,
-						isert_cq_event_callback,
-						(void *)&cq_desc[i],
-						max_rx_cqe, i);
-		if (IS_ERR(device->dev_rx_cq[i])) {
-			ret = PTR_ERR(device->dev_rx_cq[i]);
-			device->dev_rx_cq[i] = NULL;
-			goto out_cq;
-		}
 
-		INIT_WORK(&cq_desc[i].cq_tx_work, isert_cq_tx_work);
-		device->dev_tx_cq[i] = ib_create_cq(device->ib_device,
-						isert_cq_tx_callback,
-						isert_cq_event_callback,
-						(void *)&cq_desc[i],
-						max_tx_cqe, i);
-		if (IS_ERR(device->dev_tx_cq[i])) {
-			ret = PTR_ERR(device->dev_tx_cq[i]);
-			device->dev_tx_cq[i] = NULL;
-			goto out_cq;
-		}
+	for (i = 0; i < device->comps_used; i++) {
+		struct isert_comp *comp = &device->comps[i];
 
-		ret = ib_req_notify_cq(device->dev_rx_cq[i], IB_CQ_NEXT_COMP);
-		if (ret)
+		comp->device = device;
+		INIT_WORK(&comp->work, isert_cq_work);
+		comp->cq = ib_create_cq(device->ib_device,
+					isert_cq_callback,
+					isert_cq_event_callback,
+					(void *)comp,
+					max_cqe, i);
+		if (IS_ERR(comp->cq)) {
+			ret = PTR_ERR(comp->cq);
+			comp->cq = NULL;
 			goto out_cq;
+		}
 
-		ret = ib_req_notify_cq(device->dev_tx_cq[i], IB_CQ_NEXT_COMP);
+		ret = ib_req_notify_cq(comp->cq, IB_CQ_NEXT_COMP);
 		if (ret)
 			goto out_cq;
 	}
@@ -310,19 +312,15 @@ isert_create_device_ib_res(struct isert_device *device)
 	return 0;
 
 out_cq:
-	for (j = 0; j < i; j++) {
-		cq_desc = &device->cq_desc[j];
+	for (i = 0; i < device->comps_used; i++) {
+		struct isert_comp *comp = &device->comps[i];
 
-		if (device->dev_rx_cq[j]) {
-			cancel_work_sync(&cq_desc->cq_rx_work);
-			ib_destroy_cq(device->dev_rx_cq[j]);
-		}
-		if (device->dev_tx_cq[j]) {
-			cancel_work_sync(&cq_desc->cq_tx_work);
-			ib_destroy_cq(device->dev_tx_cq[j]);
+		if (comp->cq) {
+			cancel_work_sync(&comp->work);
+			ib_destroy_cq(comp->cq);
 		}
 	}
-	kfree(device->cq_desc);
+	kfree(device->comps);
 
 	return ret;
 }
@@ -330,21 +328,18 @@ out_cq:
 static void
 isert_free_device_ib_res(struct isert_device *device)
 {
-	struct isert_cq_desc *cq_desc;
 	int i;
 
-	for (i = 0; i < device->cqs_used; i++) {
-		cq_desc = &device->cq_desc[i];
+	isert_info("device %p\n", device);
 
-		cancel_work_sync(&cq_desc->cq_rx_work);
-		cancel_work_sync(&cq_desc->cq_tx_work);
-		ib_destroy_cq(device->dev_rx_cq[i]);
-		ib_destroy_cq(device->dev_tx_cq[i]);
-		device->dev_rx_cq[i] = NULL;
-		device->dev_tx_cq[i] = NULL;
-	}
+	for (i = 0; i < device->comps_used; i++) {
+		struct isert_comp *comp = &device->comps[i];
 
-	kfree(device->cq_desc);
+		cancel_work_sync(&comp->work);
+		ib_destroy_cq(comp->cq);
+		comp->cq = NULL;
+	}
+	kfree(device->comps);
 }
 
 static void
@@ -352,6 +347,7 @@ isert_device_try_release(struct isert_device *device)
 {
 	mutex_lock(&device_list_mutex);
 	device->refcount--;
+	isert_info("device %p refcount %d\n", device, device->refcount);
 	if (!device->refcount) {
 		isert_free_device_ib_res(device);
 		list_del(&device->dev_node);
@@ -370,6 +366,8 @@ isert_device_find_by_ib_dev(struct rdma_cm_id *cma_id)
 	list_for_each_entry(device, &device_list, dev_node) {
 		if (device->ib_device->node_guid == cma_id->device->node_guid) {
 			device->refcount++;
+			isert_info("Found iser device %p refcount %d\n",
+				   device, device->refcount);
 			mutex_unlock(&device_list_mutex);
 			return device;
 		}
@@ -393,6 +391,8 @@ isert_device_find_by_ib_dev(struct rdma_cm_id *cma_id)
 
 	device->refcount++;
 	list_add_tail(&device->dev_node, &device_list);
+	isert_info("Created a new iser device %p refcount %d\n",
+		   device, device->refcount);
 	mutex_unlock(&device_list_mutex);
 
 	return device;
@@ -407,7 +407,7 @@ isert_conn_free_fastreg_pool(struct isert_conn *isert_conn)
 	if (list_empty(&isert_conn->conn_fr_pool))
 		return;
 
-	pr_debug("Freeing conn %p fastreg pool", isert_conn);
+	isert_info("Freeing conn %p fastreg pool", isert_conn);
 
 	list_for_each_entry_safe(fr_desc, tmp,
 				 &isert_conn->conn_fr_pool, list) {
@@ -425,87 +425,97 @@ isert_conn_free_fastreg_pool(struct isert_conn *isert_conn)
 	}
 
 	if (i < isert_conn->conn_fr_pool_size)
-		pr_warn("Pool still has %d regions registered\n",
+		isert_warn("Pool still has %d regions registered\n",
 			isert_conn->conn_fr_pool_size - i);
 }
 
 static int
+isert_create_pi_ctx(struct fast_reg_descriptor *desc,
+		    struct ib_device *device,
+		    struct ib_pd *pd)
+{
+	struct ib_mr_init_attr mr_init_attr;
+	struct pi_context *pi_ctx;
+	int ret;
+
+	pi_ctx = kzalloc(sizeof(*desc->pi_ctx), GFP_KERNEL);
+	if (!pi_ctx) {
+		isert_err("Failed to allocate pi context\n");
+		return -ENOMEM;
+	}
+
+	pi_ctx->prot_frpl = ib_alloc_fast_reg_page_list(device,
+					    ISCSI_ISER_SG_TABLESIZE);
+	if (IS_ERR(pi_ctx->prot_frpl)) {
+		isert_err("Failed to allocate prot frpl err=%ld\n",
+			  PTR_ERR(pi_ctx->prot_frpl));
+		ret = PTR_ERR(pi_ctx->prot_frpl);
+		goto err_pi_ctx;
+	}
+
+	pi_ctx->prot_mr = ib_alloc_fast_reg_mr(pd, ISCSI_ISER_SG_TABLESIZE);
+	if (IS_ERR(pi_ctx->prot_mr)) {
+		isert_err("Failed to allocate prot frmr err=%ld\n",
+			  PTR_ERR(pi_ctx->prot_mr));
+		ret = PTR_ERR(pi_ctx->prot_mr);
+		goto err_prot_frpl;
+	}
+	desc->ind |= ISERT_PROT_KEY_VALID;
+
+	memset(&mr_init_attr, 0, sizeof(mr_init_attr));
+	mr_init_attr.max_reg_descriptors = 2;
+	mr_init_attr.flags |= IB_MR_SIGNATURE_EN;
+	pi_ctx->sig_mr = ib_create_mr(pd, &mr_init_attr);
+	if (IS_ERR(pi_ctx->sig_mr)) {
+		isert_err("Failed to allocate signature enabled mr err=%ld\n",
+			  PTR_ERR(pi_ctx->sig_mr));
+		ret = PTR_ERR(pi_ctx->sig_mr);
+		goto err_prot_mr;
+	}
+
+	desc->pi_ctx = pi_ctx;
+	desc->ind |= ISERT_SIG_KEY_VALID;
+	desc->ind &= ~ISERT_PROTECTED;
+
+	return 0;
+
+err_prot_mr:
+	ib_dereg_mr(desc->pi_ctx->prot_mr);
+err_prot_frpl:
+	ib_free_fast_reg_page_list(desc->pi_ctx->prot_frpl);
+err_pi_ctx:
+	kfree(desc->pi_ctx);
+
+	return ret;
+}
+
+static int
 isert_create_fr_desc(struct ib_device *ib_device, struct ib_pd *pd,
-		     struct fast_reg_descriptor *fr_desc, u8 protection)
+		     struct fast_reg_descriptor *fr_desc)
 {
 	int ret;
 
 	fr_desc->data_frpl = ib_alloc_fast_reg_page_list(ib_device,
 							 ISCSI_ISER_SG_TABLESIZE);
 	if (IS_ERR(fr_desc->data_frpl)) {
-		pr_err("Failed to allocate data frpl err=%ld\n",
-		       PTR_ERR(fr_desc->data_frpl));
+		isert_err("Failed to allocate data frpl err=%ld\n",
+			  PTR_ERR(fr_desc->data_frpl));
 		return PTR_ERR(fr_desc->data_frpl);
 	}
 
 	fr_desc->data_mr = ib_alloc_fast_reg_mr(pd, ISCSI_ISER_SG_TABLESIZE);
 	if (IS_ERR(fr_desc->data_mr)) {
-		pr_err("Failed to allocate data frmr err=%ld\n",
-		       PTR_ERR(fr_desc->data_mr));
+		isert_err("Failed to allocate data frmr err=%ld\n",
+			  PTR_ERR(fr_desc->data_mr));
 		ret = PTR_ERR(fr_desc->data_mr);
 		goto err_data_frpl;
 	}
-	pr_debug("Create fr_desc %p page_list %p\n",
-		 fr_desc, fr_desc->data_frpl->page_list);
 	fr_desc->ind |= ISERT_DATA_KEY_VALID;
 
-	if (protection) {
-		struct ib_mr_init_attr mr_init_attr = {0};
-		struct pi_context *pi_ctx;
-
-		fr_desc->pi_ctx = kzalloc(sizeof(*fr_desc->pi_ctx), GFP_KERNEL);
-		if (!fr_desc->pi_ctx) {
-			pr_err("Failed to allocate pi context\n");
-			ret = -ENOMEM;
-			goto err_data_mr;
-		}
-		pi_ctx = fr_desc->pi_ctx;
-
-		pi_ctx->prot_frpl = ib_alloc_fast_reg_page_list(ib_device,
-						    ISCSI_ISER_SG_TABLESIZE);
-		if (IS_ERR(pi_ctx->prot_frpl)) {
-			pr_err("Failed to allocate prot frpl err=%ld\n",
-			       PTR_ERR(pi_ctx->prot_frpl));
-			ret = PTR_ERR(pi_ctx->prot_frpl);
-			goto err_pi_ctx;
-		}
-
-		pi_ctx->prot_mr = ib_alloc_fast_reg_mr(pd, ISCSI_ISER_SG_TABLESIZE);
-		if (IS_ERR(pi_ctx->prot_mr)) {
-			pr_err("Failed to allocate prot frmr err=%ld\n",
-			       PTR_ERR(pi_ctx->prot_mr));
-			ret = PTR_ERR(pi_ctx->prot_mr);
-			goto err_prot_frpl;
-		}
-		fr_desc->ind |= ISERT_PROT_KEY_VALID;
-
-		mr_init_attr.max_reg_descriptors = 2;
-		mr_init_attr.flags |= IB_MR_SIGNATURE_EN;
-		pi_ctx->sig_mr = ib_create_mr(pd, &mr_init_attr);
-		if (IS_ERR(pi_ctx->sig_mr)) {
-			pr_err("Failed to allocate signature enabled mr err=%ld\n",
-			       PTR_ERR(pi_ctx->sig_mr));
-			ret = PTR_ERR(pi_ctx->sig_mr);
-			goto err_prot_mr;
-		}
-		fr_desc->ind |= ISERT_SIG_KEY_VALID;
-	}
-	fr_desc->ind &= ~ISERT_PROTECTED;
+	isert_dbg("Created fr_desc %p\n", fr_desc);
 
 	return 0;
-err_prot_mr:
-	ib_dereg_mr(fr_desc->pi_ctx->prot_mr);
-err_prot_frpl:
-	ib_free_fast_reg_page_list(fr_desc->pi_ctx->prot_frpl);
-err_pi_ctx:
-	kfree(fr_desc->pi_ctx);
-err_data_mr:
-	ib_dereg_mr(fr_desc->data_mr);
+
 err_data_frpl:
 	ib_free_fast_reg_page_list(fr_desc->data_frpl);
 
@@ -513,7 +523,7 @@ err_data_frpl:
 }
 
 static int
-isert_conn_create_fastreg_pool(struct isert_conn *isert_conn, u8 pi_support)
+isert_conn_create_fastreg_pool(struct isert_conn *isert_conn)
 {
 	struct fast_reg_descriptor *fr_desc;
 	struct isert_device *device = isert_conn->conn_device;
@@ -531,16 +541,15 @@ isert_conn_create_fastreg_pool(struct isert_conn *isert_conn, u8 pi_support)
 	for (i = 0; i < tag_num; i++) {
 		fr_desc = kzalloc(sizeof(*fr_desc), GFP_KERNEL);
 		if (!fr_desc) {
-			pr_err("Failed to allocate fast_reg descriptor\n");
+			isert_err("Failed to allocate fast_reg descriptor\n");
 			ret = -ENOMEM;
 			goto err;
 		}
 
 		ret = isert_create_fr_desc(device->ib_device,
-					   isert_conn->conn_pd, fr_desc,
-					   pi_support);
+					   isert_conn->conn_pd, fr_desc);
 		if (ret) {
-			pr_err("Failed to create fastreg descriptor err=%d\n",
+			isert_err("Failed to create fastreg descriptor err=%d\n",
 			       ret);
 			kfree(fr_desc);
 			goto err;
@@ -550,7 +559,7 @@ isert_conn_create_fastreg_pool(struct isert_conn *isert_conn, u8 pi_support)
 		isert_conn->conn_fr_pool_size++;
 	}
 
-	pr_debug("Creating conn %p fastreg pool size=%d",
+	isert_dbg("Creating conn %p fastreg pool size=%d",
 		 isert_conn, isert_conn->conn_fr_pool_size);
 
 	return 0;
@@ -563,47 +572,45 @@ err:
 static int
 isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
-	struct iscsi_np *np = cma_id->context;
-	struct isert_np *isert_np = np->np_context;
+	struct isert_np *isert_np = cma_id->context;
+	struct iscsi_np *np = isert_np->np;
 	struct isert_conn *isert_conn;
 	struct isert_device *device;
 	struct ib_device *ib_dev = cma_id->device;
 	int ret = 0;
-	u8 pi_support;
 
 	spin_lock_bh(&np->np_thread_lock);
 	if (!np->enabled) {
 		spin_unlock_bh(&np->np_thread_lock);
-		pr_debug("iscsi_np is not enabled, reject connect request\n");
+		isert_dbg("iscsi_np is not enabled, reject connect request\n");
 		return rdma_reject(cma_id, NULL, 0);
 	}
 	spin_unlock_bh(&np->np_thread_lock);
 
-	pr_debug("Entering isert_connect_request cma_id: %p, context: %p\n",
+	isert_dbg("cma_id: %p, portal: %p\n",
 		 cma_id, cma_id->context);
 
 	isert_conn = kzalloc(sizeof(struct isert_conn), GFP_KERNEL);
 	if (!isert_conn) {
-		pr_err("Unable to allocate isert_conn\n");
+		isert_err("Unable to allocate isert_conn\n");
 		return -ENOMEM;
 	}
 	isert_conn->state = ISER_CONN_INIT;
 	INIT_LIST_HEAD(&isert_conn->conn_accept_node);
 	init_completion(&isert_conn->conn_login_comp);
+	init_completion(&isert_conn->login_req_comp);
 	init_completion(&isert_conn->conn_wait);
-	init_completion(&isert_conn->conn_wait_comp_err);
 	kref_init(&isert_conn->conn_kref);
 	mutex_init(&isert_conn->conn_mutex);
 	spin_lock_init(&isert_conn->conn_lock);
 	INIT_LIST_HEAD(&isert_conn->conn_fr_pool);
 
-	cma_id->context = isert_conn;
 	isert_conn->conn_cm_id = cma_id;
 
 	isert_conn->login_buf = kzalloc(ISCSI_DEF_MAX_RECV_SEG_LEN +
 					ISER_RX_LOGIN_SIZE, GFP_KERNEL);
 	if (!isert_conn->login_buf) {
-		pr_err("Unable to allocate isert_conn->login_buf\n");
+		isert_err("Unable to allocate isert_conn->login_buf\n");
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -611,7 +618,7 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	isert_conn->login_req_buf = isert_conn->login_buf;
 	isert_conn->login_rsp_buf = isert_conn->login_buf +
 				    ISCSI_DEF_MAX_RECV_SEG_LEN;
-	pr_debug("Set login_buf: %p login_req_buf: %p login_rsp_buf: %p\n",
+	isert_dbg("Set login_buf: %p login_req_buf: %p login_rsp_buf: %p\n",
 		 isert_conn->login_buf, isert_conn->login_req_buf,
 		 isert_conn->login_rsp_buf);
 
@@ -621,7 +628,7 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 
 	ret = ib_dma_mapping_error(ib_dev, isert_conn->login_req_dma);
 	if (ret) {
-		pr_err("ib_dma_mapping_error failed for login_req_dma: %d\n",
+		isert_err("ib_dma_mapping_error failed for login_req_dma: %d\n",
 		       ret);
 		isert_conn->login_req_dma = 0;
 		goto out_login_buf;
@@ -633,7 +640,7 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 
 	ret = ib_dma_mapping_error(ib_dev, isert_conn->login_rsp_dma);
 	if (ret) {
-		pr_err("ib_dma_mapping_error failed for login_rsp_dma: %d\n",
+		isert_err("ib_dma_mapping_error failed for login_rsp_dma: %d\n",
 		       ret);
 		isert_conn->login_rsp_dma = 0;
 		goto out_req_dma_map;
@@ -649,13 +656,13 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	isert_conn->initiator_depth = min_t(u8,
 				event->param.conn.initiator_depth,
 				device->dev_attr.max_qp_init_rd_atom);
-	pr_debug("Using initiator_depth: %u\n", isert_conn->initiator_depth);
+	isert_dbg("Using initiator_depth: %u\n", isert_conn->initiator_depth);
 
 	isert_conn->conn_device = device;
 	isert_conn->conn_pd = ib_alloc_pd(isert_conn->conn_device->ib_device);
 	if (IS_ERR(isert_conn->conn_pd)) {
 		ret = PTR_ERR(isert_conn->conn_pd);
-		pr_err("ib_alloc_pd failed for conn %p: ret=%d\n",
+		isert_err("ib_alloc_pd failed for conn %p: ret=%d\n",
 		       isert_conn, ret);
 		goto out_pd;
 	}
@@ -664,20 +671,20 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 					   IB_ACCESS_LOCAL_WRITE);
 	if (IS_ERR(isert_conn->conn_mr)) {
 		ret = PTR_ERR(isert_conn->conn_mr);
-		pr_err("ib_get_dma_mr failed for conn %p: ret=%d\n",
+		isert_err("ib_get_dma_mr failed for conn %p: ret=%d\n",
 		       isert_conn, ret);
 		goto out_mr;
 	}
 
-	pi_support = np->tpg_np->tpg->tpg_attrib.t10_pi;
-	if (pi_support && !device->pi_capable) {
-		pr_err("Protection information requested but not supported, "
-		       "rejecting connect request\n");
-		ret = rdma_reject(cma_id, NULL, 0);
-		goto out_mr;
-	}
+	ret = isert_conn_setup_qp(isert_conn, cma_id);
+	if (ret)
+		goto out_conn_dev;
 
-	ret = isert_conn_setup_qp(isert_conn, cma_id, pi_support);
+	ret = isert_rdma_post_recvl(isert_conn);
+	if (ret)
+		goto out_conn_dev;
+
+	ret = isert_rdma_accept(isert_conn);
 	if (ret)
 		goto out_conn_dev;
 
@@ -685,7 +692,7 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	list_add_tail(&isert_conn->conn_accept_node, &isert_np->np_accept_list);
 	mutex_unlock(&isert_np->np_accept_mutex);
 
-	pr_debug("isert_connect_request() up np_sem np: %p\n", np);
+	isert_info("np %p: Allow accept_np to continue\n", np);
 	up(&isert_np->np_sem);
 	return 0;
 
@@ -705,6 +712,7 @@ out_login_buf:
 	kfree(isert_conn->login_buf);
 out:
 	kfree(isert_conn);
+	rdma_reject(cma_id, NULL, 0);
 	return ret;
 }
 
@@ -713,24 +721,25 @@ isert_connect_release(struct isert_conn *isert_conn)
 {
 	struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
 	struct isert_device *device = isert_conn->conn_device;
-	int cq_index;
 
-	pr_debug("Entering isert_connect_release(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
+	isert_dbg("conn %p\n", isert_conn);
 
 	if (device && device->use_fastreg)
 		isert_conn_free_fastreg_pool(isert_conn);
 
+	isert_free_rx_descriptors(isert_conn);
+	rdma_destroy_id(isert_conn->conn_cm_id);
+
 	if (isert_conn->conn_qp) {
-		cq_index = ((struct isert_cq_desc *)
-			isert_conn->conn_qp->recv_cq->cq_context)->cq_index;
-		pr_debug("isert_connect_release: cq_index: %d\n", cq_index);
-		isert_conn->conn_device->cq_active_qps[cq_index]--;
+		struct isert_comp *comp = isert_conn->conn_qp->recv_cq->cq_context;
 
-		rdma_destroy_qp(isert_conn->conn_cm_id);
-	}
+		isert_dbg("dec completion context %p active_qps\n", comp);
+		mutex_lock(&device_list_mutex);
+		comp->active_qps--;
+		mutex_unlock(&device_list_mutex);
 
-	isert_free_rx_descriptors(isert_conn);
-	rdma_destroy_id(isert_conn->conn_cm_id);
+		ib_destroy_qp(isert_conn->conn_qp);
+	}
 
 	ib_dereg_mr(isert_conn->conn_mr);
 	ib_dealloc_pd(isert_conn->conn_pd);
@@ -747,16 +756,24 @@ isert_connect_release(struct isert_conn *isert_conn)
 
 	if (device)
 		isert_device_try_release(device);
-
-	pr_debug("Leaving isert_connect_release >>>>>>>>>>>>\n");
 }
 
 static void
 isert_connected_handler(struct rdma_cm_id *cma_id)
 {
-	struct isert_conn *isert_conn = cma_id->context;
+	struct isert_conn *isert_conn = cma_id->qp->qp_context;
 
-	kref_get(&isert_conn->conn_kref);
+	isert_info("conn %p\n", isert_conn);
+
+	if (!kref_get_unless_zero(&isert_conn->conn_kref)) {
+		isert_warn("conn %p connect_release is running\n", isert_conn);
+		return;
+	}
+
+	mutex_lock(&isert_conn->conn_mutex);
+	if (isert_conn->state != ISER_CONN_FULL_FEATURE)
+		isert_conn->state = ISER_CONN_UP;
+	mutex_unlock(&isert_conn->conn_mutex);
 }
 
 static void
@@ -765,8 +782,8 @@ isert_release_conn_kref(struct kref *kref)
 	struct isert_conn *isert_conn = container_of(kref,
 				struct isert_conn, conn_kref);
 
-	pr_debug("Calling isert_connect_release for final kref %s/%d\n",
-		 current->comm, current->pid);
+	isert_info("conn %p final kref %s/%d\n", isert_conn, current->comm,
+		   current->pid);
 
 	isert_connect_release(isert_conn);
 }
@@ -777,75 +794,111 @@ isert_put_conn(struct isert_conn *isert_conn)
 	kref_put(&isert_conn->conn_kref, isert_release_conn_kref);
 }
 
+/**
+ * isert_conn_terminate() - Initiate connection termination
+ * @isert_conn: isert connection struct
+ *
+ * Notes:
+ * In case the connection state is FULL_FEATURE, move state
+ * to TEMINATING and start teardown sequence (rdma_disconnect).
+ * In case the connection state is UP, complete flush as well.
+ *
+ * This routine must be called with conn_mutex held. Thus it is
+ * safe to call multiple times.
+ */
 static void
-isert_disconnect_work(struct work_struct *work)
+isert_conn_terminate(struct isert_conn *isert_conn)
 {
-	struct isert_conn *isert_conn = container_of(work,
-				struct isert_conn, conn_logout_work);
+	int err;
 
-	pr_debug("isert_disconnect_work(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
-	mutex_lock(&isert_conn->conn_mutex);
-	if (isert_conn->state == ISER_CONN_UP)
+	switch (isert_conn->state) {
+	case ISER_CONN_TERMINATING:
+		break;
+	case ISER_CONN_UP:
+	case ISER_CONN_FULL_FEATURE: /* FALLTHRU */
+		isert_info("Terminating conn %p state %d\n",
+			   isert_conn, isert_conn->state);
 		isert_conn->state = ISER_CONN_TERMINATING;
-
-	if (isert_conn->post_recv_buf_count == 0 &&
-	    atomic_read(&isert_conn->post_send_buf_count) == 0) {
-		mutex_unlock(&isert_conn->conn_mutex);
-		goto wake_up;
-	}
-	if (!isert_conn->conn_cm_id) {
-		mutex_unlock(&isert_conn->conn_mutex);
-		isert_put_conn(isert_conn);
-		return;
+		err = rdma_disconnect(isert_conn->conn_cm_id);
+		if (err)
+			isert_warn("Failed rdma_disconnect isert_conn %p\n",
+				   isert_conn);
+		break;
+	default:
+		isert_warn("conn %p teminating in state %d\n",
+			   isert_conn, isert_conn->state);
 	}
+}
 
-	if (isert_conn->disconnect) {
-		/* Send DREQ/DREP towards our initiator */
-		rdma_disconnect(isert_conn->conn_cm_id);
-	}
+static int
+isert_np_cma_handler(struct isert_np *isert_np,
+		     enum rdma_cm_event_type event)
+{
+	isert_dbg("isert np %p, handling event %d\n", isert_np, event);
 
-	mutex_unlock(&isert_conn->conn_mutex);
+	switch (event) {
+	case RDMA_CM_EVENT_DEVICE_REMOVAL:
+		isert_np->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_err("isert np %p setup id failed: %ld\n",
+				  isert_np, PTR_ERR(isert_np->np_cm_id));
+			isert_np->np_cm_id = NULL;
+		}
+		break;
+	default:
+		isert_err("isert np %p Unexpected event %d\n",
+			  isert_np, event);
+	}
 
-wake_up:
-	complete(&isert_conn->conn_wait);
+	return -1;
 }
 
 static int
-isert_disconnected_handler(struct rdma_cm_id *cma_id, bool disconnect)
+isert_disconnected_handler(struct rdma_cm_id *cma_id,
+			   enum rdma_cm_event_type event)
 {
+	struct isert_np *isert_np = cma_id->context;
 	struct isert_conn *isert_conn;
 
-	if (!cma_id->qp) {
-		struct isert_np *isert_np = cma_id->context;
+	if (isert_np->np_cm_id == cma_id)
+		return isert_np_cma_handler(cma_id->context, event);
 
-		isert_np->np_cm_id = NULL;
-		return -1;
-	}
+	isert_conn = cma_id->qp->qp_context;
 
-	isert_conn = (struct isert_conn *)cma_id->context;
+	mutex_lock(&isert_conn->conn_mutex);
+	isert_conn_terminate(isert_conn);
+	mutex_unlock(&isert_conn->conn_mutex);
 
-	isert_conn->disconnect = disconnect;
-	INIT_WORK(&isert_conn->conn_logout_work, isert_disconnect_work);
-	schedule_work(&isert_conn->conn_logout_work);
+	isert_info("conn %p completing conn_wait\n", isert_conn);
+	complete(&isert_conn->conn_wait);
 
 	return 0;
 }
 
+static void
+isert_connect_error(struct rdma_cm_id *cma_id)
+{
+	struct isert_conn *isert_conn = cma_id->qp->qp_context;
+
+	isert_put_conn(isert_conn);
+}
+
 static int
 isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
 	int ret = 0;
-	bool disconnect = false;
 
-	pr_debug("isert_cma_handler: event %d status %d conn %p id %p\n",
-		 event->event, event->status, cma_id->context, cma_id);
+	isert_info("event %d status %d id %p np %p\n", event->event,
+		   event->status, cma_id, cma_id->context);
 
 	switch (event->event) {
 	case RDMA_CM_EVENT_CONNECT_REQUEST:
 		ret = isert_connect_request(cma_id, event);
 		if (ret)
-			pr_err("isert_cma_handler failed RDMA_CM_EVENT: 0x%08x %d\n",
-				event->event, ret);
+			isert_err("failed handle connect request %d\n", ret);
 		break;
 	case RDMA_CM_EVENT_ESTABLISHED:
 		isert_connected_handler(cma_id);
@@ -853,13 +906,16 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	case RDMA_CM_EVENT_ADDR_CHANGE:    /* FALLTHRU */
 	case RDMA_CM_EVENT_DISCONNECTED:   /* FALLTHRU */
 	case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */
-		disconnect = true;
 	case RDMA_CM_EVENT_TIMEWAIT_EXIT:  /* FALLTHRU */
-		ret = isert_disconnected_handler(cma_id, disconnect);
+		ret = isert_disconnected_handler(cma_id, event->event);
 		break;
+	case RDMA_CM_EVENT_REJECTED:       /* FALLTHRU */
+	case RDMA_CM_EVENT_UNREACHABLE:    /* FALLTHRU */
 	case RDMA_CM_EVENT_CONNECT_ERROR:
+		isert_connect_error(cma_id);
+		break;
 	default:
-		pr_err("Unhandled RDMA CMA event: %d\n", event->event);
+		isert_err("Unhandled RDMA CMA event: %d\n", event->event);
 		break;
 	}
 
@@ -876,7 +932,7 @@ isert_post_recv(struct isert_conn *isert_conn, u32 count)
 
 	for (rx_wr = isert_conn->conn_rx_wr, i = 0; i < count; i++, rx_wr++) {
 		rx_desc		= &isert_conn->conn_rx_descs[rx_head];
-		rx_wr->wr_id	= (unsigned long)rx_desc;
+		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;
@@ -890,10 +946,10 @@ isert_post_recv(struct isert_conn *isert_conn, u32 count)
 	ret = ib_post_recv(isert_conn->conn_qp, isert_conn->conn_rx_wr,