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

Pull SCSI target updates from Nicholas Bellinger:
 "The highlights this round include:

  - add support for SCSI Referrals (Hannes)
  - add support for T10 DIF into target core (nab + mkp)
  - add support for T10 DIF emulation in FILEIO + RAMDISK backends (Sagi + nab)
  - add support for T10 DIF -> bio_integrity passthrough in IBLOCK backend (nab)
  - prep changes to iser-target for >= v3.15 T10 DIF support (Sagi)
  - add support for qla2xxx N_Port ID Virtualization - NPIV (Saurav + Quinn)
  - allow percpu_ida_alloc() to receive task state bitmask (Kent)
  - fix >= v3.12 iscsi-target session reset hung task regression (nab)
  - fix >= v3.13 percpu_ref se_lun->lun_ref_active race (nab)
  - fix a long-standing network portal creation race (Andy)"

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending: (51 commits)
  target: Fix percpu_ref_put race in transport_lun_remove_cmd
  target/iscsi: Fix network portal creation race
  target: Report bad sector in sense data for DIF errors
  iscsi-target: Convert gfp_t parameter to task state bitmask
  iscsi-target: Fix connection reset hang with percpu_ida_alloc
  percpu_ida: Make percpu_ida_alloc + callers accept task state bitmask
  iscsi-target: Pre-allocate more tags to avoid ack starvation
  qla2xxx: Configure NPIV fc_vport via tcm_qla2xxx_npiv_make_lport
  qla2xxx: Enhancements to enable NPIV support for QLOGIC ISPs with TCM/LIO.
  qla2xxx: Fix scsi_host leak on qlt_lport_register callback failure
  IB/isert: pass scatterlist instead of cmd to fast_reg_mr routine
  IB/isert: Move fastreg descriptor creation to a function
  IB/isert: Avoid frwr notation, user fastreg
  IB/isert: seperate connection protection domains and dma MRs
  tcm_loop: Enable DIF/DIX modes in SCSI host LLD
  target/rd: Add DIF protection into rd_execute_rw
  target/rd: Add support for protection SGL setup + release
  target/rd: Refactor rd_build_device_space + rd_release_device_space
  target/file: Add DIF protection support to fd_execute_rw
  target/file: Add DIF protection init/format support
  ...

43 files changed, 2300 insertions, 505 deletions

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index d64a02fb1f7..5d70edc9855 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -36,7 +36,8 @@ static unsigned int __blk_mq_get_tag(struct blk_mq_tags *tags, gfp_t gfp)
 {
 	int tag;
 
-	tag = percpu_ida_alloc(&tags->free_tags, gfp);
+	tag = percpu_ida_alloc(&tags->free_tags, (gfp & __GFP_WAIT) ?
+			       TASK_UNINTERRUPTIBLE : TASK_RUNNING);
 	if (tag < 0)
 		return BLK_MQ_TAG_FAIL;
 	return tag + tags->nr_reserved_tags;
@@ -52,7 +53,8 @@ static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_tags *tags,
 		return BLK_MQ_TAG_FAIL;
 	}
 
-	tag = percpu_ida_alloc(&tags->reserved_tags, gfp);
+	tag = percpu_ida_alloc(&tags->reserved_tags, (gfp & __GFP_WAIT) ?
+			       TASK_UNINTERRUPTIBLE : TASK_RUNNING);
 	if (tag < 0)
 		return BLK_MQ_TAG_FAIL;
 	return tag;
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 9804fca6bf0..2b161be3c1a 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -47,10 +47,10 @@ static int
 isert_map_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	       struct isert_rdma_wr *wr);
 static void
-isert_unreg_rdma_frwr(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn);
+isert_unreg_rdma(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn);
 static int
-isert_reg_rdma_frwr(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
-		    struct isert_rdma_wr *wr);
+isert_reg_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+	       struct isert_rdma_wr *wr);
 
 static void
 isert_qp_event_callback(struct ib_event *e, void *context)
@@ -227,11 +227,11 @@ isert_create_device_ib_res(struct isert_device *device)
 
 	/* asign function handlers */
 	if (dev_attr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) {
-		device->use_frwr = 1;
-		device->reg_rdma_mem = isert_reg_rdma_frwr;
-		device->unreg_rdma_mem = isert_unreg_rdma_frwr;
+		device->use_fastreg = 1;
+		device->reg_rdma_mem = isert_reg_rdma;
+		device->unreg_rdma_mem = isert_unreg_rdma;
 	} else {
-		device->use_frwr = 0;
+		device->use_fastreg = 0;
 		device->reg_rdma_mem = isert_map_rdma;
 		device->unreg_rdma_mem = isert_unmap_cmd;
 	}
@@ -239,9 +239,10 @@ isert_create_device_ib_res(struct isert_device *device)
 	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 FRWR %d\n",
+	pr_debug("Using %d CQs, device %s supports %d vectors support "
+		 "Fast registration %d\n",
 		 device->cqs_used, device->ib_device->name,
-		 device->ib_device->num_comp_vectors, device->use_frwr);
+		 device->ib_device->num_comp_vectors, device->use_fastreg);
 	device->cq_desc = kzalloc(sizeof(struct isert_cq_desc) *
 				device->cqs_used, GFP_KERNEL);
 	if (!device->cq_desc) {
@@ -250,13 +251,6 @@ isert_create_device_ib_res(struct isert_device *device)
 	}
 	cq_desc = device->cq_desc;
 
-	device->dev_pd = ib_alloc_pd(ib_dev);
-	if (IS_ERR(device->dev_pd)) {
-		ret = PTR_ERR(device->dev_pd);
-		pr_err("ib_alloc_pd failed for dev_pd: %d\n", ret);
-		goto out_cq_desc;
-	}
-
 	for (i = 0; i < device->cqs_used; i++) {
 		cq_desc[i].device = device;
 		cq_desc[i].cq_index = i;
@@ -294,13 +288,6 @@ isert_create_device_ib_res(struct isert_device *device)
 			goto out_cq;
 	}
 
-	device->dev_mr = ib_get_dma_mr(device->dev_pd, IB_ACCESS_LOCAL_WRITE);
-	if (IS_ERR(device->dev_mr)) {
-		ret = PTR_ERR(device->dev_mr);
-		pr_err("ib_get_dma_mr failed for dev_mr: %d\n", ret);
-		goto out_cq;
-	}
-
 	return 0;
 
 out_cq:
@@ -316,9 +303,6 @@ out_cq:
 			ib_destroy_cq(device->dev_tx_cq[j]);
 		}
 	}
-	ib_dealloc_pd(device->dev_pd);
-
-out_cq_desc:
 	kfree(device->cq_desc);
 
 	return ret;
@@ -341,8 +325,6 @@ isert_free_device_ib_res(struct isert_device *device)
 		device->dev_tx_cq[i] = NULL;
 	}
 
-	ib_dereg_mr(device->dev_mr);
-	ib_dealloc_pd(device->dev_pd);
 	kfree(device->cq_desc);
 }
 
@@ -398,18 +380,18 @@ isert_device_find_by_ib_dev(struct rdma_cm_id *cma_id)
 }
 
 static void
-isert_conn_free_frwr_pool(struct isert_conn *isert_conn)
+isert_conn_free_fastreg_pool(struct isert_conn *isert_conn)
 {
 	struct fast_reg_descriptor *fr_desc, *tmp;
 	int i = 0;
 
-	if (list_empty(&isert_conn->conn_frwr_pool))
+	if (list_empty(&isert_conn->conn_fr_pool))
 		return;
 
-	pr_debug("Freeing conn %p frwr pool", isert_conn);
+	pr_debug("Freeing conn %p fastreg pool", isert_conn);
 
 	list_for_each_entry_safe(fr_desc, tmp,
-				 &isert_conn->conn_frwr_pool, list) {
+				 &isert_conn->conn_fr_pool, list) {
 		list_del(&fr_desc->list);
 		ib_free_fast_reg_page_list(fr_desc->data_frpl);
 		ib_dereg_mr(fr_desc->data_mr);
@@ -417,20 +399,47 @@ isert_conn_free_frwr_pool(struct isert_conn *isert_conn)
 		++i;
 	}
 
-	if (i < isert_conn->conn_frwr_pool_size)
+	if (i < isert_conn->conn_fr_pool_size)
 		pr_warn("Pool still has %d regions registered\n",
-			isert_conn->conn_frwr_pool_size - i);
+			isert_conn->conn_fr_pool_size - i);
+}
+
+static int
+isert_create_fr_desc(struct ib_device *ib_device, struct ib_pd *pd,
+		     struct fast_reg_descriptor *fr_desc)
+{
+	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));
+		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));
+		ib_free_fast_reg_page_list(fr_desc->data_frpl);
+		return PTR_ERR(fr_desc->data_mr);
+	}
+	pr_debug("Create fr_desc %p page_list %p\n",
+		 fr_desc, fr_desc->data_frpl->page_list);
+
+	fr_desc->valid = true;
+
+	return 0;
 }
 
 static int
-isert_conn_create_frwr_pool(struct isert_conn *isert_conn)
+isert_conn_create_fastreg_pool(struct isert_conn *isert_conn)
 {
 	struct fast_reg_descriptor *fr_desc;
 	struct isert_device *device = isert_conn->conn_device;
 	int i, ret;
 
-	INIT_LIST_HEAD(&isert_conn->conn_frwr_pool);
-	isert_conn->conn_frwr_pool_size = 0;
+	INIT_LIST_HEAD(&isert_conn->conn_fr_pool);
+	isert_conn->conn_fr_pool_size = 0;
 	for (i = 0; i < ISCSI_DEF_XMIT_CMDS_MAX; i++) {
 		fr_desc = kzalloc(sizeof(*fr_desc), GFP_KERNEL);
 		if (!fr_desc) {
@@ -439,40 +448,25 @@ isert_conn_create_frwr_pool(struct isert_conn *isert_conn)
 			goto err;
 		}
 
-		fr_desc->data_frpl =
-			ib_alloc_fast_reg_page_list(device->ib_device,
-						    ISCSI_ISER_SG_TABLESIZE);
-		if (IS_ERR(fr_desc->data_frpl)) {
-			pr_err("Failed to allocate fr_pg_list err=%ld\n",
-			       PTR_ERR(fr_desc->data_frpl));
-			ret = PTR_ERR(fr_desc->data_frpl);
-			goto err;
-		}
-
-		fr_desc->data_mr = ib_alloc_fast_reg_mr(device->dev_pd,
-					ISCSI_ISER_SG_TABLESIZE);
-		if (IS_ERR(fr_desc->data_mr)) {
-			pr_err("Failed to allocate frmr err=%ld\n",
-			       PTR_ERR(fr_desc->data_mr));
-			ret = PTR_ERR(fr_desc->data_mr);
-			ib_free_fast_reg_page_list(fr_desc->data_frpl);
+		ret = isert_create_fr_desc(device->ib_device,
+					   isert_conn->conn_pd, fr_desc);
+		if (ret) {
+			pr_err("Failed to create fastreg descriptor err=%d\n",
+			       ret);
 			goto err;
 		}
-		pr_debug("Create fr_desc %p page_list %p\n",
-			 fr_desc, fr_desc->data_frpl->page_list);
 
-		fr_desc->valid = true;
-		list_add_tail(&fr_desc->list, &isert_conn->conn_frwr_pool);
-		isert_conn->conn_frwr_pool_size++;
+		list_add_tail(&fr_desc->list, &isert_conn->conn_fr_pool);
+		isert_conn->conn_fr_pool_size++;
 	}
 
-	pr_debug("Creating conn %p frwr pool size=%d",
-		 isert_conn, isert_conn->conn_frwr_pool_size);
+	pr_debug("Creating conn %p fastreg pool size=%d",
+		 isert_conn, isert_conn->conn_fr_pool_size);
 
 	return 0;
 
 err:
-	isert_conn_free_frwr_pool(isert_conn);
+	isert_conn_free_fastreg_pool(isert_conn);
 	return ret;
 }
 
@@ -558,14 +552,29 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	}
 
 	isert_conn->conn_device = device;
-	isert_conn->conn_pd = device->dev_pd;
-	isert_conn->conn_mr = device->dev_mr;
+	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_conn, ret);
+		goto out_pd;
+	}
 
-	if (device->use_frwr) {
-		ret = isert_conn_create_frwr_pool(isert_conn);
+	isert_conn->conn_mr = ib_get_dma_mr(isert_conn->conn_pd,
+					   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_conn, ret);
+		goto out_mr;
+	}
+
+	if (device->use_fastreg) {
+		ret = isert_conn_create_fastreg_pool(isert_conn);
 		if (ret) {
-			pr_err("Conn: %p failed to create frwr_pool\n", isert_conn);
-			goto out_frwr;
+			pr_err("Conn: %p failed to create fastreg pool\n",
+			       isert_conn);
+			goto out_fastreg;
 		}
 	}
 
@@ -582,9 +591,13 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	return 0;
 
 out_conn_dev:
-	if (device->use_frwr)
-		isert_conn_free_frwr_pool(isert_conn);
-out_frwr:
+	if (device->use_fastreg)
+		isert_conn_free_fastreg_pool(isert_conn);
+out_fastreg:
+	ib_dereg_mr(isert_conn->conn_mr);
+out_mr:
+	ib_dealloc_pd(isert_conn->conn_pd);
+out_pd:
 	isert_device_try_release(device);
 out_rsp_dma_map:
 	ib_dma_unmap_single(ib_dev, isert_conn->login_rsp_dma,
@@ -608,8 +621,8 @@ isert_connect_release(struct isert_conn *isert_conn)
 
 	pr_debug("Entering isert_connect_release(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
 
-	if (device && device->use_frwr)
-		isert_conn_free_frwr_pool(isert_conn);
+	if (device && device->use_fastreg)
+		isert_conn_free_fastreg_pool(isert_conn);
 
 	if (isert_conn->conn_qp) {
 		cq_index = ((struct isert_cq_desc *)
@@ -623,6 +636,9 @@ isert_connect_release(struct isert_conn *isert_conn)
 	isert_free_rx_descriptors(isert_conn);
 	rdma_destroy_id(isert_conn->conn_cm_id);
 
+	ib_dereg_mr(isert_conn->conn_mr);
+	ib_dealloc_pd(isert_conn->conn_pd);
+
 	if (isert_conn->login_buf) {
 		ib_dma_unmap_single(ib_dev, isert_conn->login_rsp_dma,
 				    ISER_RX_LOGIN_SIZE, DMA_TO_DEVICE);
@@ -1024,13 +1040,13 @@ isert_rx_login_req(struct iser_rx_desc *rx_desc, int rx_buflen,
 }
 
 static struct iscsi_cmd
-*isert_allocate_cmd(struct iscsi_conn *conn, gfp_t gfp)
+*isert_allocate_cmd(struct iscsi_conn *conn)
 {
 	struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
 	struct isert_cmd *isert_cmd;
 	struct iscsi_cmd *cmd;
 
-	cmd = iscsit_allocate_cmd(conn, gfp);
+	cmd = iscsit_allocate_cmd(conn, TASK_INTERRUPTIBLE);
 	if (!cmd) {
 		pr_err("Unable to allocate iscsi_cmd + isert_cmd\n");
 		return NULL;
@@ -1219,7 +1235,7 @@ 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, GFP_KERNEL);
+		cmd = isert_allocate_cmd(conn);
 		if (!cmd)
 			break;
 
@@ -1233,7 +1249,7 @@ 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, GFP_KERNEL);
+		cmd = isert_allocate_cmd(conn);
 		if (!cmd)
 			break;
 
@@ -1246,7 +1262,7 @@ 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, GFP_KERNEL);
+		cmd = isert_allocate_cmd(conn);
 		if (!cmd)
 			break;
 
@@ -1254,7 +1270,7 @@ 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, GFP_KERNEL);
+		cmd = isert_allocate_cmd(conn);
 		if (!cmd)
 			break;
 
@@ -1265,7 +1281,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 						    HZ);
 		break;
 	case ISCSI_OP_TEXT:
-		cmd = isert_allocate_cmd(conn, GFP_KERNEL);
+		cmd = isert_allocate_cmd(conn);
 		if (!cmd)
 			break;
 
@@ -1404,25 +1420,25 @@ isert_unmap_cmd(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn)
 }
 
 static void
-isert_unreg_rdma_frwr(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn)
+isert_unreg_rdma(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn)
 {
 	struct isert_rdma_wr *wr = &isert_cmd->rdma_wr;
 	struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
 	LIST_HEAD(unmap_list);
 
-	pr_debug("unreg_frwr_cmd: %p\n", isert_cmd);
+	pr_debug("unreg_fastreg_cmd: %p\n", isert_cmd);
 
 	if (wr->fr_desc) {
-		pr_debug("unreg_frwr_cmd: %p free fr_desc %p\n",
+		pr_debug("unreg_fastreg_cmd: %p free fr_desc %p\n",
 			 isert_cmd, wr->fr_desc);
 		spin_lock_bh(&isert_conn->conn_lock);
-		list_add_tail(&wr->fr_desc->list, &isert_conn->conn_frwr_pool);
+		list_add_tail(&wr->fr_desc->list, &isert_conn->conn_fr_pool);
 		spin_unlock_bh(&isert_conn->conn_lock);
 		wr->fr_desc = NULL;
 	}
 
 	if (wr->sge) {
-		pr_debug("unreg_frwr_cmd: %p unmap_sg op\n", isert_cmd);
+		pr_debug("unreg_fastreg_cmd: %p unmap_sg op\n", isert_cmd);
 		ib_dma_unmap_sg(ib_dev, wr->sge, wr->num_sge,
 				(wr->iser_ib_op == ISER_IB_RDMA_WRITE) ?
 				DMA_TO_DEVICE : DMA_FROM_DEVICE);
@@ -2163,26 +2179,22 @@ isert_map_fr_pagelist(struct ib_device *ib_dev,
 
 static int
 isert_fast_reg_mr(struct fast_reg_descriptor *fr_desc,
-		  struct isert_cmd *isert_cmd, struct isert_conn *isert_conn,
-		  struct ib_sge *ib_sge, u32 offset, unsigned int data_len)
+		  struct isert_conn *isert_conn, struct scatterlist *sg_start,
+		  struct ib_sge *ib_sge, u32 sg_nents, u32 offset,
+		  unsigned int data_len)
 {
-	struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd;
 	struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
-	struct scatterlist *sg_start;
-	u32 sg_off, page_off;
 	struct ib_send_wr fr_wr, inv_wr;
 	struct ib_send_wr *bad_wr, *wr = NULL;
+	int ret, pagelist_len;
+	u32 page_off;
 	u8 key;
-	int ret, sg_nents, pagelist_len;
 
-	sg_off = offset / PAGE_SIZE;
-	sg_start = &cmd->se_cmd.t_data_sg[sg_off];
-	sg_nents = min_t(unsigned int, cmd->se_cmd.t_data_nents - sg_off,
-			 ISCSI_ISER_SG_TABLESIZE);
+	sg_nents = min_t(unsigned int, sg_nents, ISCSI_ISER_SG_TABLESIZE);
 	page_off = offset % PAGE_SIZE;
 
-	pr_debug("Cmd: %p use fr_desc %p sg_nents %d sg_off %d offset %u\n",
-		 isert_cmd, fr_desc, sg_nents, sg_off, offset);
+	pr_debug("Use fr_desc %p sg_nents %d offset %u\n",
+		 fr_desc, sg_nents, offset);
 
 	pagelist_len = isert_map_fr_pagelist(ib_dev, sg_start, sg_nents,
 					     &fr_desc->data_frpl->page_list[0]);
@@ -2232,8 +2244,8 @@ isert_fast_reg_mr(struct fast_reg_descriptor *fr_desc,
 }
 
 static int
-isert_reg_rdma_frwr(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
-		    struct isert_rdma_wr *wr)
+isert_reg_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+	       struct isert_rdma_wr *wr)
 {
 	struct se_cmd *se_cmd = &cmd->se_cmd;
 	struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
@@ -2251,9 +2263,9 @@ isert_reg_rdma_frwr(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	if (wr->iser_ib_op == ISER_IB_RDMA_WRITE) {
 		data_left = se_cmd->data_length;
 	} else {
-		sg_off = cmd->write_data_done / PAGE_SIZE;
-		data_left = se_cmd->data_length - cmd->write_data_done;
 		offset = cmd->write_data_done;
+		sg_off = offset / PAGE_SIZE;
+		data_left = se_cmd->data_length - cmd->write_data_done;
 		isert_cmd->tx_desc.isert_cmd = isert_cmd;
 	}
 
@@ -2311,16 +2323,16 @@ isert_reg_rdma_frwr(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 		wr->fr_desc = NULL;
 	} else {
 		spin_lock_irqsave(&isert_conn->conn_lock, flags);
-		fr_desc = list_first_entry(&isert_conn->conn_frwr_pool,
+		fr_desc = list_first_entry(&isert_conn->conn_fr_pool,
 					   struct fast_reg_descriptor, list);
 		list_del(&fr_desc->list);
 		spin_unlock_irqrestore(&isert_conn->conn_lock, flags);
 		wr->fr_desc = fr_desc;
 
-		ret = isert_fast_reg_mr(fr_desc, isert_cmd, isert_conn,
-				  ib_sge, offset, data_len);
+		ret = isert_fast_reg_mr(fr_desc, isert_conn, sg_start,
+					ib_sge, sg_nents, offset, data_len);
 		if (ret) {
-			list_add_tail(&fr_desc->list, &isert_conn->conn_frwr_pool);
+			list_add_tail(&fr_desc->list, &isert_conn->conn_fr_pool);
 			goto unmap_sg;
 		}
 	}
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 691f90ff2d8..708a069002f 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -119,9 +119,9 @@ struct isert_conn {
 	wait_queue_head_t	conn_wait;
 	wait_queue_head_t	conn_wait_comp_err;
 	struct kref		conn_kref;
-	struct list_head	conn_frwr_pool;
-	int			conn_frwr_pool_size;
-	/* lock to protect frwr_pool */
+	struct list_head	conn_fr_pool;
+	int			conn_fr_pool_size;
+	/* lock to protect fastreg pool */
 	spinlock_t		conn_lock;
 #define ISERT_COMP_BATCH_COUNT	8
 	int			conn_comp_batch;
@@ -139,13 +139,11 @@ struct isert_cq_desc {
 };
 
 struct isert_device {
-	int			use_frwr;
+	int			use_fastreg;
 	int			cqs_used;
 	int			refcount;
 	int			cq_active_qps[ISERT_MAX_CQ];
 	struct ib_device	*ib_device;
-	struct ib_pd		*dev_pd;
-	struct ib_mr		*dev_mr;
 	struct ib_cq		*dev_rx_cq[ISERT_MAX_CQ];
 	struct ib_cq		*dev_tx_cq[ISERT_MAX_CQ];
 	struct isert_cq_desc	*cq_desc;
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 570c7fcc0c4..4a0d7c92181 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -1990,6 +1990,8 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)
 
 	vha->flags.delete_progress = 1;
 
+	qlt_remove_target(ha, vha);
+
 	fc_remove_host(vha->host);
 
 	scsi_remove_host(vha->host);
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 41d6491d7bd..e1fe95ef23e 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2750,6 +2750,13 @@ struct qlfc_fw {
 	uint32_t len;
 };
 
+struct scsi_qlt_host {
+	void *target_lport_ptr;
+	struct mutex tgt_mutex;
+	struct mutex tgt_host_action_mutex;
+	struct qla_tgt *qla_tgt;
+};
+
 struct qlt_hw_data {
 	/* Protected by hw lock */
 	uint32_t enable_class_2:1;
@@ -2765,15 +2772,11 @@ struct qlt_hw_data {
 	uint32_t __iomem *atio_q_in;
 	uint32_t __iomem *atio_q_out;
 
-	void *target_lport_ptr;
 	struct qla_tgt_func_tmpl *tgt_ops;
-	struct qla_tgt *qla_tgt;
 	struct qla_tgt_cmd *cmds[DEFAULT_OUTSTANDING_COMMANDS];
 	uint16_t current_handle;
 
 	struct qla_tgt_vp_map *tgt_vp_map;
-	struct mutex tgt_mutex;
-	struct mutex tgt_host_action_mutex;
 
 	int saved_set;
 	uint16_t saved_exchange_count;
@@ -3435,6 +3438,7 @@ typedef struct scsi_qla_host {
 #define VP_ERR_FAB_LOGOUT	4
 #define VP_ERR_ADAP_NORESOURCES	5
 	struct qla_hw_data *hw;
+	struct scsi_qlt_host vha_tgt;
 	struct req_que *req;
 	int		fw_heartbeat_counter;
 	int		seconds_since_last_heartbeat;
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 38a1257e76e..9e80d61e5a3 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -590,7 +590,7 @@ static struct qla_tgt_sess *qlt_create_sess(
 
 	/* Check to avoid double sessions */
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	list_for_each_entry(sess, &ha->tgt.qla_tgt->sess_list,
+	list_for_each_entry(sess, &vha->vha_tgt.qla_tgt->sess_list,
 				sess_list_entry) {
 		if (!memcmp(sess->port_name, fcport->port_name, WWN_SIZE)) {
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf005,
@@ -627,7 +627,7 @@ static struct qla_tgt_sess *qlt_create_sess(
 
 		return NULL;
 	}
-	sess->tgt = ha->tgt.qla_tgt;
+	sess->tgt = vha->vha_tgt.qla_tgt;
 	sess->vha = vha;
 	sess->s_id = fcport->d_id;
 	sess->loop_id = fcport->loop_id;
@@ -635,7 +635,7 @@ static struct qla_tgt_sess *qlt_create_sess(
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf006,
 	    "Adding sess %p to tgt %p via ->check_initiator_node_acl()\n",
-	    sess, ha->tgt.qla_tgt);
+	    sess, vha->vha_tgt.qla_tgt);
 
 	be_sid[0] = sess->s_id.b.domain;
 	be_sid[1] = sess->s_id.b.area;
@@ -662,8 +662,8 @@ static struct qla_tgt_sess *qlt_create_sess(
 	memcpy(sess->port_name, fcport->port_name, sizeof(sess->port_name));
 
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	list_add_tail(&sess->sess_list_entry, &ha->tgt.qla_tgt->sess_list);
-	ha->tgt.qla_tgt->sess_count++;
+	list_add_tail(&sess->sess_list_entry, &vha->vha_tgt.qla_tgt->sess_list);
+	vha->vha_tgt.qla_tgt->sess_count++;
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04b,
@@ -682,7 +682,7 @@ static struct qla_tgt_sess *qlt_create_sess(
 void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt *tgt = ha->tgt.qla_tgt;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	struct qla_tgt_sess *sess;
 	unsigned long flags;
 
@@ -692,6 +692,9 @@ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport)
 	if (!tgt || (fcport->port_type != FCT_INITIATOR))
 		return;
 
+	if (qla_ini_mode_enabled(vha))
+		return;
+
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	if (tgt->tgt_stop) {
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
@@ -701,9 +704,9 @@ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport)
 	if (!sess) {
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
-		mutex_lock(&ha->tgt.tgt_mutex);
+		mutex_lock(&vha->vha_tgt.tgt_mutex);
 		sess = qlt_create_sess(vha, fcport, false);
-		mutex_unlock(&ha->tgt.tgt_mutex);
+		mutex_unlock(&vha->vha_tgt.tgt_mutex);
 
 		spin_lock_irqsave(&ha->hardware_lock, flags);
 	} else {
@@ -739,7 +742,7 @@ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport)
 void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt *tgt = ha->tgt.qla_tgt;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	struct qla_tgt_sess *sess;
 	unsigned long flags;
 
@@ -806,12 +809,12 @@ void qlt_stop_phase1(struct qla_tgt *tgt)
 	 * Mutex needed to sync with qla_tgt_fc_port_[added,deleted].
 	 * Lock is needed, because we still can get an incoming packet.
 	 */
-	mutex_lock(&ha->tgt.tgt_mutex);
+	mutex_lock(&vha->vha_tgt.tgt_mutex);
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	tgt->tgt_stop = 1;
 	qlt_clear_tgt_db(tgt, true);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
-	mutex_unlock(&ha->tgt.tgt_mutex);
+	mutex_unlock(&vha->vha_tgt.tgt_mutex);
 
 	flush_delayed_work(&tgt->sess_del_work);
 
@@ -845,20 +848,21 @@ EXPORT_SYMBOL(qlt_stop_phase1);
 void qlt_stop_phase2(struct qla_tgt *tgt)
 {
 	struct qla_hw_data *ha = tgt->ha;
+	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
 	unsigned long flags;
 
 	if (tgt->tgt_stopped) {
-		ql_dbg(ql_dbg_tgt_mgt, tgt->vha, 0xf04f,
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04f,
 		    "Already in tgt->tgt_stopped state\n");
 		dump_stack();
 		return;
 	}
 
-	ql_dbg(ql_dbg_tgt_mgt, tgt->vha, 0xf00b,
+	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf00b,
 	    "Waiting for %d IRQ commands to complete (tgt %p)",
 	    tgt->irq_cmd_count, tgt);
 
-	mutex_lock(&ha->tgt.tgt_mutex);
+	mutex_lock(&vha->vha_tgt.tgt_mutex);
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	while (tgt->irq_cmd_count != 0) {
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
@@ -868,9 +872,9 @@ void qlt_stop_phase2(struct qla_tgt *tgt)
 	tgt->tgt_stop = 0;
 	tgt->tgt_stopped = 1;
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
-	mutex_unlock(&ha->tgt.tgt_mutex);
+	mutex_unlock(&vha->vha_tgt.tgt_mutex);
 
-	ql_dbg(ql_dbg_tgt_mgt, tgt->vha, 0xf00c, "Stop of tgt %p finished",
+	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf00c, "Stop of tgt %p finished",
 	    tgt);
 }
 EXPORT_SYMBOL(qlt_stop_phase2);
@@ -878,14 +882,14 @@ EXPORT_SYMBOL(qlt_stop_phase2);
 /* Called from qlt_remove_target() -> qla2x00_remove_one() */
 static void qlt_release(struct qla_tgt *tgt)
 {
-	struct qla_hw_data *ha = tgt->ha;
+	scsi_qla_host_t *vha = tgt->vha;
 
-	if ((ha->tgt.qla_tgt != NULL) && !tgt->tgt_stopped)
+	if ((vha->vha_tgt.qla_tgt != NULL) && !tgt->tgt_stopped)
 		qlt_stop_phase2(tgt);
 
-	ha->tgt.qla_tgt = NULL;
+	vha->vha_tgt.qla_tgt = NULL;
 
-	ql_dbg(ql_dbg_tgt_mgt, tgt->vha, 0xf00d,
+	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf00d,
 	    "Release of tgt %p finished\n", tgt);
 
 	kfree(tgt);
@@ -949,8 +953,8 @@ static void qlt_send_notify_ack(struct scsi_qla_host *vha,
 		return;
 	}
 
-	if (ha->tgt.qla_tgt != NULL)
-		ha->tgt.qla_tgt->notify_ack_expected++;
+	if (vha->vha_tgt.qla_tgt != NULL)
+		vha->vha_tgt.qla_tgt->notify_ack_expected++;
 
 	pkt->entry_type = NOTIFY_ACK_TYPE;
 	pkt->entry_count = 1;
@@ -1054,7 +1058,7 @@ static void qlt_24xx_send_abts_resp(struct scsi_qla_host *vha,
 		/* Other bytes are zero */
 	}
 
-	ha->tgt.qla_tgt->abts_resp_expected++;
+	vha->vha_tgt.qla_tgt->abts_resp_expected++;
 
 	qla2x00_start_iocbs(vha, vha->req);
 }
@@ -1206,7 +1210,7 @@ static void qlt_24xx_handle_abts(struct scsi_qla_host *vha,
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf012,
 		    "qla_target(%d): task abort for non-existant session\n",
 		    vha->vp_idx);
-		rc = qlt_sched_sess_work(ha->tgt.qla_tgt,
+		rc = qlt_sched_sess_work(vha->vha_tgt.qla_tgt,
 		    QLA_TGT_SESS_WORK_ABORT, abts, sizeof(*abts));
 		if (rc != 0) {
 			qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_REJECTED,
@@ -2157,8 +2161,7 @@ static int qlt_prepare_srr_ctio(struct scsi_qla_host *vha,
 	struct qla_tgt_cmd *cmd, void *ctio)
 {
 	struct qla_tgt_srr_ctio *sc;
-	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt *tgt = ha->tgt.qla_tgt;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	struct qla_tgt_srr_imm *imm;
 
 	tgt->ctio_srr_id++;
@@ -2474,7 +2477,7 @@ static void qlt_do_work(struct work_struct *work)
 	struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
 	scsi_qla_host_t *vha = cmd->vha;
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt *tgt = ha->tgt.qla_tgt;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	struct qla_tgt_sess *sess = NULL;
 	struct atio_from_isp *atio = &cmd->atio;
 	unsigned char *cdb;
@@ -2507,10 +2510,10 @@ static void qlt_do_work(struct work_struct *work)
 			goto out_term;
 		}
 
-		mutex_lock(&ha->tgt.tgt_mutex);
+		mutex_lock(&vha->vha_tgt.tgt_mutex);
 		sess = qlt_make_local_sess(vha, s_id);
 		/* sess has an extra creation ref. */
-		mutex_unlock(&ha->tgt.tgt_mutex);
+		mutex_unlock(&vha->vha_tgt.tgt_mutex);
 
 		if (!sess)
 			goto out_term;
@@ -2576,8 +2579,7 @@ out_term:
 static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 	struct atio_from_isp *atio)
 {
-	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt *tgt = ha->tgt.qla_tgt;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	struct qla_tgt_cmd *cmd;
 
 	if (unlikely(tgt->tgt_stop)) {
@@ -2597,7 +2599,7 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 
 	memcpy(&cmd->atio, atio, sizeof(*atio));
 	cmd->state = QLA_TGT_STATE_NEW;
-	cmd->tgt = ha->tgt.qla_tgt;
+	cmd->tgt = vha->vha_tgt.qla_tgt;
 	cmd->vha = vha;
 
 	INIT_WORK(&cmd->work, qlt_do_work);
@@ -2723,7 +2725,7 @@ static int qlt_handle_task_mgmt(struct scsi_qla_host *vha, void *iocb)
 	uint32_t lun, unpacked_lun;
 	int lun_size, fn;
 
-	tgt = ha->tgt.qla_tgt;
+	tgt = vha->vha_tgt.qla_tgt;
 
 	lun = a->u.isp24.fcp_cmnd.lun;
 	lun_size = sizeof(a->u.isp24.fcp_cmnd.lun);
@@ -2797,7 +2799,7 @@ static int qlt_abort_task(struct scsi_qla_host *vha,
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf025,
 		    "qla_target(%d): task abort for unexisting "
 		    "session\n", vha->vp_idx);
-		return qlt_sched_sess_work(ha->tgt.qla_tgt,
+		return qlt_sched_sess_work(vha->vha_tgt.qla_tgt,
 		    QLA_TGT_SESS_WORK_ABORT, iocb, sizeof(*iocb));
 	}
 
@@ -2810,7 +2812,6 @@ static int qlt_abort_task(struct scsi_qla_host *vha,
 static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 	struct imm_ntfy_from_isp *iocb)
 {
-	struct qla_hw_data *ha = vha->hw;
 	int res = 0;
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf026,
@@ -2828,7 +2829,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 	case ELS_PDISC:
 	case ELS_ADISC:
 	{
-		struct qla_tgt *tgt = ha->tgt.qla_tgt;
+		struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 		if (tgt->link_reinit_iocb_pending) {
 			qlt_send_notify_ack(vha, &tgt->link_reinit_iocb,
 			    0, 0, 0, 0, 0, 0);
@@ -3202,8 +3203,7 @@ static void qlt_prepare_srr_imm(struct scsi_qla_host *vha,
 	struct imm_ntfy_from_isp *iocb)
 {
 	struct qla_tgt_srr_imm *imm;
-	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt *tgt = ha->tgt.qla_tgt;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	struct qla_tgt_srr_ctio *sctio;
 
 	tgt->imm_srr_id++;
@@ -3313,7 +3313,7 @@ static void qlt_handle_imm_notify(struct scsi_qla_host *vha,
 
 	case IMM_NTFY_LIP_LINK_REINIT:
 	{
-		struct qla_tgt *tgt = ha->tgt.qla_tgt;
+		struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf033,
 		    "qla_target(%d): LINK REINIT (loop %#x, "
 		    "subcode %x)\n", vha->vp_idx,
@@ -3489,7 +3489,7 @@ static void qlt_24xx_atio_pkt(struct scsi_qla_host *vha,
 	struct atio_from_isp *atio)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt *tgt = ha->tgt.qla_tgt;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	int rc;
 
 	if (unlikely(tgt == NULL)) {
@@ -3591,7 +3591,7 @@ static void qlt_24xx_atio_pkt(struct scsi_qla_host *vha,
 static void qlt_response_pkt(struct scsi_qla_host *vha, response_t *pkt)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt *tgt = ha->tgt.qla_tgt;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 
 	if (unlikely(tgt == NULL)) {
 		ql_dbg(ql_dbg_tgt, vha, 0xe05d,
@@ -3794,7 +3794,7 @@ void qlt_async_event(uint16_t code, struct scsi_qla_host *vha,
 	uint16_t *mailbox)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt *tgt = ha->tgt.qla_tgt;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	int login_code;
 
 	ql_dbg(ql_dbg_tgt, vha, 0xe039,
@@ -3924,14 +3924,14 @@ static fc_port_t *qlt_get_port_database(struct scsi_qla_host *vha,
 static struct qla_tgt_sess *qlt_make_local_sess(struct scsi_qla_host *vha,
 	uint8_t *s_id)
 {
-	struct qla_hw_data *ha = vha->hw;
 	struct qla_tgt_sess *sess = NULL;
 	fc_port_t *fcport = NULL;
 	int rc, global_resets;
 	uint16_t loop_id = 0;
 
 retry:
-	global_resets = atomic_read(&ha->tgt.qla_tgt->tgt_global_resets_count);
+	global_resets =
+	    atomic_read(&vha->vha_tgt.qla_tgt->tgt_global_resets_count);
 
 	rc = qla24xx_get_loop_id(vha, s_id, &loop_id);
 	if (rc != 0) {
@@ -3958,12 +3958,13 @@ retry:
 		return NULL;
 
 	if (global_resets !=
-	    atomic_read(&ha->tgt.qla_tgt->tgt_global_resets_count)) {
+	    atomic_read(&vha->vha_tgt.qla_tgt->tgt_global_resets_count)) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf043,
 		    "qla_target(%d): global reset during session discovery "
 		    "(counter was %d, new %d), retrying", vha->vp_idx,
 		    global_resets,
-		    atomic_read(&ha->tgt.qla_tgt->tgt_global_resets_count));
+		    atomic_read(&vha->vha_tgt.
+			qla_tgt->tgt_global_resets_count));
 		goto retry;
 	}
 
@@ -3998,10 +3999,10 @@ static void qlt_abort_work(struct qla_tgt *tgt,
 	if (!sess) {
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
-		mutex_lock(&ha->tgt.tgt_mutex);
+		mutex_lock(&vha->vha_tgt.tgt_mutex);
 		sess = qlt_make_local_sess(vha, s_id);
 		/* sess has got an extra creation ref */
-		mutex_unlock(&ha->tgt.tgt_mutex);
+		mutex_unlock(&vha->vha_tgt.tgt_mutex);
 
 		spin_lock_irqsave(&ha->hardware_lock, flags);
 		if (!sess)
@@ -4052,10 +4053,10 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
 	if (!sess) {
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
-		mutex_lock(&ha->tgt.tgt_mutex);
+		mutex_lock(&vha->vha_tgt.tgt_mutex);
 		sess = qlt_make_local_sess(vha, s_id);
 		/* sess has got an extra creation ref */
-		mutex_unlock(&ha->tgt.tgt_mutex);
+		mutex_unlock(&vha->vha_tgt.tgt_mutex);
 
 		spin_lock_irqsave(&ha->hardware_lock, flags);
 		if (!sess)
@@ -4141,9 +4142,9 @@ int qlt_add_target(struct qla_hw_data *ha, struct scsi_qla_host *base_vha)
 	}
 
 	ql_dbg(ql_dbg_tgt, base_vha, 0xe03b,
-	    "Registering target for host %ld(%p)", base_vha->host_no, ha);
+	    "Registering target for host %ld(%p).\n", base_vha->host_no, ha);
 
-	BUG_ON((ha->tgt.qla_tgt != NULL) || (ha->tgt.tgt_ops != NULL));
+	BUG_ON(base_vha->vha_tgt.qla_tgt != NULL);
 
 	tgt = kzalloc(sizeof(struct qla_tgt), GFP_KERNEL);
 	if (!tgt) {
@@ -4171,7 +4172,7 @@ int qlt_add_target(struct qla_hw_data *ha, struct scsi_qla_host *base_vha)
 	INIT_WORK(&tgt->srr_work, qlt_handle_srr_work);
 	atomic_set(&tgt->tgt_global_resets_count, 0);
 
-	ha->tgt.qla_tgt = tgt;
+	base_vha->vha_tgt.qla_tgt = tgt;
 
 	ql_dbg(ql_dbg_tgt, base_vha, 0xe067,
 		"qla_target(%d): using 64 Bit PCI addressing",
@@ -4192,16 +4193,16 @@ int qlt_add_target(struct qla_hw_data *ha, struct scsi_qla_host *base_vha)
 /* Must be called under tgt_host_action_mutex */
 int qlt_remove_target(struct qla_hw_data *ha, struct scsi_qla_host *vha)
 {
-	if (!ha->tgt.qla_tgt)
+	if (!vha->vha_tgt.qla_tgt)
 		return 0;
 
 	mutex_lock(&qla_tgt_mutex);
-	list_del(&ha->tgt.qla_tgt->tgt_list_entry);
+	list_del(&vha->vha_tgt.qla_tgt->tgt_list_entry);
 	mutex_unlock(&qla_tgt_mutex);
 
 	ql_dbg(ql_dbg_tgt, vha, 0xe03c, "Unregistering target for host %ld(%p)",
 	    vha->host_no, ha);
-	qlt_release(ha->tgt.qla_tgt);
+	qlt_release(vha->vha_tgt.qla_tgt);
 
 	return 0;
 }
@@ -4235,8 +4236,9 @@ static void qlt_lport_dump(struct scsi_qla_host *vha, u64 wwpn,
  * @callback:  lport initialization callback for tcm_qla2xxx code
  * @target_lport_ptr: pointer for tcm_qla2xxx specific lport data
  */
-int qlt_lport_register(struct qla_tgt_func_tmpl *qla_tgt_ops, u64 wwpn,
-	int (*callback)(struct scsi_qla_host *), void *target_lport_ptr)
+int qlt_lport_register(void *target_lport_ptr, u64 phys_wwpn,
+		       u64 npiv_wwpn, u64 npiv_wwnn,
+		       int (*callback)(struct scsi_qla_host *, void *, u64, u64))
 {
 	struct qla_tgt *tgt;
 	struct scsi_qla_host *vha;
@@ -4255,14 +4257,11 @@ int qlt_lport_register(struct qla_tgt_func_tmpl *qla_tgt_ops, u64 wwpn,
 		if (!host)
 			continue;
 
-		if (ha->tgt.tgt_ops != NULL)
-			continue;
-
 		if (!(host->hostt->supported_mode & MODE_TARGET))
 			continue;
 
 		spin_lock_irqsave(&ha->hardware_lock, flags);
-		if (host->active_mode & MODE_TARGET) {
+		if ((!npiv_wwpn || !npiv_wwnn) && host->active_mode & MODE_TARGET) {
 			pr_debug("MODE_TARGET already active on qla2xxx(%d)\n",
 			    host->host_no);
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
@@ -4276,24 +4275,18 @@ int qlt_lport_register(struct qla_tgt_func_tmpl *qla_tgt_ops, u64 wwpn,
 			    " qla2xxx scsi_host\n");
 			continue;
 		}
-		qlt_lport_dump(vha, wwpn, b);
+		qlt_lport_dump(vha, phys_wwpn, b);
 
 		if (memcmp(vha->port_name, b, WWN_SIZE)) {
 			scsi_host_put(host);
 			continue;
 		}
-		/*
-		 * Setup passed parameters ahead of invoking callback
-		 */
-		ha->tgt.tgt_ops = qla_tgt_ops;
-		ha->tgt.target_lport_ptr = target_lport_ptr;
-		rc = (*callback)(vha);
-		if (rc != 0) {
-			ha->tgt.tgt_ops = NULL;
-			ha->tgt.target_lport_ptr = NULL;
-			scsi_host_put(host);
-		}
 		mutex_unlock(&qla_tgt_mutex);
+
+		rc = (*callback)(vha, target_lport_ptr, npiv_wwpn, npiv_wwnn);
+		if (rc != 0)
+			scsi_host_put(host);
+
 		return rc;
 	}
 	mutex_unlock(&qla_tgt_mutex);
@@ -4314,7 +4307,7 @@ void qlt_lport_deregister(struct scsi_qla_host *vha)
 	/*
 	 * Clear the target_lport_ptr qla_target_template pointer in qla_hw_data
 	 */
-	ha->tgt.target_lport_ptr = NULL;
+	vha->vha_tgt.target_lport_ptr = NULL;
 	ha->tgt.tgt_ops = NULL;
 	/*
 	 * Release the Scsi_Host reference for the underlying qla2xxx host
@@ -4376,8 +4369,9 @@ void
 qlt_enable_vha(struct scsi_qla_host *vha)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt *tgt = ha->tgt.qla_tgt;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	unsigned long flags;
+	scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev);
 
 	if (!tgt) {
 		ql_dbg(ql_dbg_tgt, vha, 0xe069,
@@ -4392,9 +4386,14 @@ qlt_enable_vha(struct scsi_qla_host *vha)
 	qlt_set_mode(vha);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
-	set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags);
-	qla2xxx_wake_dpc(vha);
-	qla2x00_wait_for_hba_online(vha);
+	if (vha->vp_idx) {
+		qla24xx_disable_vp(vha);
+		qla24xx_enable_vp(vha);
+	} else {
+		set_bit(ISP_ABORT_NEEDED, &base_vha->dpc_flags);
+		qla2xxx_wake_dpc(base_vha);
+		qla2x00_wait_for_hba_online(base_vha);
+	}
 }
 EXPORT_SYMBOL(qlt_enable_vha);
 
@@ -4407,7 +4406,7 @@ void
 qlt_disable_vha(struct scsi_qla_host *vha)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_tgt *tgt = ha->tgt.qla_tgt;
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	unsigned long flags;
 
 	if (!tgt) {
@@ -4438,8 +4437,10 @@ qlt_vport_create(struct scsi_qla_host *vha, struct qla_hw_data *ha)
 	if (!qla_tgt_mode_enabled(vha))
 		return;
 
-	mutex_init(&ha->tgt.tgt_mutex);
-	mutex_init(&ha->tgt.tgt_host_action_mutex);
+	vha->vha_tgt.qla_tgt = NULL;
+
+	mutex_init(&vha->vha_tgt.tgt_mutex);
+	mutex_init(&vha->vha_tgt.tgt_host_action_mutex);
 
 	qlt_clear_mode(vha);
 
@@ -4450,6 +4451,8 @@ qlt_vport_create(struct scsi_qla_host *vha, struct qla_hw_data *ha)
 	 * assigning the value appropriately.
 	 */
 	ha->tgt.atio_q_length = ATIO_ENTRY_CNT_24XX;
+
+	qlt_add_target(ha, vha);
 }
 
 void
@@ -4768,8 +4771,8 @@ qlt_probe_one_stage1(struct scsi_qla_host *base_vha, struct qla_hw_data *ha)
 		ISP_ATIO_Q_OUT(base_vha) = &ha->iobase->isp24.atio_q_out;
 	}
 
-	mutex_init(&ha->tgt.tgt_mutex);
-	mutex_init(&ha->tgt.tgt_host_action_mutex);
+	mutex_init(&base_vha->vha_tgt.tgt_mutex);
+	mutex_init(&base_vha->vha_tgt.tgt_host_action_mutex);
 	qlt_clear_mode(base_vha);
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index b33e411f28a..1d10eecad49 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -932,8 +932,8 @@ void qlt_disable_vha(struct scsi_qla_host *);
  */
 extern int qlt_add_target(struct qla_hw_data *, struct scsi_qla_host *);
 extern int qlt_remove_target(struct qla_hw_data *, struct scsi_qla_host *);
-extern int qlt_lport_register(struct qla_tgt_func_tmpl *, u64,
-			int (*callback)(struct scsi_qla_host *), void *);
+extern int qlt_lport_register(void *, u64, u64, u64,
+			int (*callback)(struct scsi_qla_host *, void *, u64, u64));
 extern void qlt_lport_deregister(struct scsi_qla_host *);
 extern void qlt_unreg_sess(struct qla_tgt_sess *);
 extern void qlt_fc_port_added(struct scsi_qla_host *, fc_port_t *);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 7eb19be35d4..75a141bbe74 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -53,16 +53,6 @@
 struct workqueue_struct *tcm_qla2xxx_free_wq;
 struct workqueue_struct *tcm_qla2xxx_cmd_wq;
 
-static int tcm_qla2xxx_check_true(struct se_portal_group *se_tpg)
-{
-	return 1;
-}
-
-static int tcm_qla2xxx_check_false(struct se_portal_group *se_tpg)
-{
-	return 0;
-}
-
 /*
  * Parse WWN.
  * If strict, we require lower-case hex and colon separators to be sure
@@ -174,7 +164,7 @@ static int tcm_qla2xxx_npiv_parse_wwn(
 	*wwnn = 0;
 
 	/* count may include a LF at end of string */
-	if (name[cnt-1] == '\n')
+	if (name[cnt-1] == '\n' || name[cnt-1] == 0)
 		cnt--;
 
 	/* validate we have enough characters for WWPN */
@@ -777,6 +767,9 @@ static void tcm_qla2xxx_put_session(struct se_session *se_sess)
 
 static void tcm_qla2xxx_put_sess(struct qla_tgt_sess *sess)
 {
+	if (!sess)
+		return;
+
 	assert_spin_locked(&sess->vha->hw->hardware_lock);
 	kref_put(&sess->se_sess->sess_kref, tcm_qla2xxx_release_session);
 }
@@ -957,7 +950,6 @@ static ssize_t tcm_qla2xxx_tpg_store_enable(
 	struct tcm_qla2xxx_lport *lport = container_of(se_wwn,
 			struct tcm_qla2xxx_lport, lport_wwn);
 	struct scsi_qla_host *vha = lport->qla_vha;
-	struct qla_hw_data *ha = vha->hw;
 	struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
 			struct tcm_qla2xxx_tpg, se_tpg);
 	unsigned long op;
@@ -977,12 +969,12 @@ static ssize_t tcm_qla2xxx_tpg_store_enable(
 		atomic_set(&tpg->lport_tpg_enabled, 1);
 		qlt_enable_vha(vha);
 	} else {
-		if (!ha->tgt.qla_tgt) {
-			pr_err("truct qla_hw_data *ha->tgt.qla_tgt is NULL\n");
+		if (!vha->vha_tgt.qla_tgt) {
+			pr_err("struct qla_hw_data *vha->vha_tgt.qla_tgt is NULL\n");
 			return -ENODEV;
 		}
 		atomic_set(&tpg->lport_tpg_enabled, 0);
-		qlt_stop_phase1(ha->tgt.qla_tgt);
+		qlt_stop_phase1(vha->vha_tgt.qla_tgt);
 	}
 
 	return count;
@@ -1011,7 +1003,7 @@ static struct se_portal_group *tcm_qla2xxx_make_tpg(
 	if (kstrtoul(name + 5, 10, &tpgt) || tpgt > USHRT_MAX)
 		return ERR_PTR(-EINVAL);
 
-	if (!lport->qla_npiv_vp && (tpgt != 1)) {
+	if ((tpgt != 1)) {
 		pr_err("In non NPIV mode, a single TPG=1 is used for HW port mappings\n");
 		return ERR_PTR(-ENOSYS);
 	}
@@ -1038,11 +1030,8 @@ static struct se_portal_group *tcm_qla2xxx_make_tpg(
 		kfree(tpg);
 		return NULL;
 	}
-	/*
-	 * Setup local TPG=1 pointer for non NPIV mode.
-	 */
-	if (lport->qla_npiv_vp == NULL)
-		lport->tpg_1 = tpg;
+
+	lport->tpg_1 = tpg;
 
 	return &tpg->se_tpg;
 }
@@ -1053,19 +1042,17 @@ static void tcm_qla2xxx_drop_tpg(struct se_portal_group *se_tpg)
 			struct tcm_qla2xxx_tpg, se_tpg);
 	struct tcm_qla2xxx_lport *lport = tpg->lport;
 	struct scsi_qla_host *vha = lport->qla_vha;
-	struct qla_hw_data *ha = vha->hw;
 	/*
 	 * Call into qla2x_target.c LLD logic to shutdown the active
 	 * FC Nexuses and disable target mode operation for this qla_hw_data
 	 */
-	if (ha->tgt.qla_tgt && !ha->tgt.qla_tgt->tgt_stop)
-		qlt_stop_phase1(ha->tgt.qla_tgt);
+	if (vha->vha_tgt.qla_tgt && !vha->vha_tgt.qla_tgt->tgt_stop)
+		qlt_stop_phase1(vha->vha_tgt.qla_tgt);
 
 	core_tpg_deregister(se_tpg);
 	/*
 	 * Clear local TPG=1 pointer for non NPIV mode.
 	 */
-	if (lport->qla_npiv_vp == NULL)
 		lport->tpg_1 = NULL;
 
 	kfree(tpg);
@@ -1095,12 +1082,22 @@ static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg(
 	tpg->lport = lport;
 	tpg->lport_tpgt = tpgt;
 
+	/*
+	 * By default allow READ-ONLY TPG demo-mode access w/ cached dynamic
+	 * NodeACLs
+	 */
+	tpg->tpg_attrib.generate_node_acls = 1;
+	tpg->tpg_attrib.demo_mode_write_protect = 1;
+	tpg->tpg_attrib.cache_dynamic_acls = 1;
+	tpg->tpg_attrib.demo_mode_login_only = 1;
+
 	ret = core_tpg_register(&tcm_qla2xxx_npiv_fabric_configfs->tf_ops, wwn,
 				&tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL);
 	if (ret < 0) {
 		kfree(tpg);
 		return NULL;
 	}
+	lport->tpg_1 = tpg;
 	return &tpg->se_tpg;
 }
 
@@ -1111,13 +1108,12 @@ static struct qla_tgt_sess *tcm_qla2xxx_find_sess_by_s_id(
 	scsi_qla_host_t *vha,
 	const uint8_t *s_id)
 {
-	struct qla_hw_data *ha = vha->hw;
 	struct tcm_qla2xxx_lport *lport;
 	struct se_node_acl *se_nacl;
 	struct tcm_qla2xxx_nacl *nacl;
 	u32 key;
 
-	lport = ha->tgt.target_lport_ptr;
+	lport = vha->vha_tgt.target_lport_ptr;
 	if (!lport) {
 		pr_err("Unable to locate struct tcm_qla2xxx_lport\n");
 		dump_stack();
@@ -1221,13 +1217,12 @@ static struct qla_tgt_sess *tcm_qla2xxx_find_sess_by_loop_id(
 	scsi_qla_host_t *vha,
 	const uint16_t loop_id)
 {
-	struct qla_hw_data *ha = vha->hw;
 	struct tcm_qla2xxx_lport *lport;
 	struct se_node_acl *se_nacl;
 	struct tcm_qla2xxx_nacl *nacl;
 	struct tcm_qla2xxx_fc_loopid *fc_loopid;
 
-	lport = ha->tgt.target_lport_ptr;
+	lport = vha->vha_tgt.target_lport_ptr;
 	if (!lport) {
 		pr_err("Unable to locate struct tcm_qla2xxx_lport\n");
 		dump_stack();
@@ -1341,6 +1336,7 @@ static void tcm_qla2xxx_free_session(struct qla_tgt_sess *sess)
 {
 	struct qla_tgt *tgt = sess->tgt;
 	struct qla_hw_data *ha = tgt->ha;
+	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
 	struct se_session *se_sess;
 	struct se_node_acl *se_nacl;
 	struct tcm_qla2xxx_lport *lport;
@@ -1357,7 +1353,7 @@ static void tcm_qla2xxx_free_session(struct qla_tgt_sess *sess)
 	se_nacl = se_sess->se_node_acl;
 	nacl = container_of(se_nacl, struct tcm_qla2xxx_nacl, se_node_acl);
 
-	lport = ha->tgt.target_lport_ptr;
+	lport = vha->vha_tgt.target_lport_ptr;
 	if (!lport) {
 		pr_err("Unable to locate struct tcm_qla2xxx_lport\n");
 		dump_stack();
@@ -1391,7 +1387,7 @@ static int tcm_qla2xxx_check_initiator_node_acl(
 	unsigned char port_name[36];
 	unsigned long flags;
 
-	lport = ha->tgt.target_lport_ptr;
+	lport = vha->vha_tgt.target_lport_ptr;
 	if (!lport) {
 		pr_err("Unable to locate struct tcm_qla2xxx_lport\n");
 		dump_stack();
@@ -1455,7 +1451,8 @@ static void tcm_qla2xxx_update_sess(struct qla_tgt_sess *sess, port_id_t s_id,
 {
 	struct qla_tgt *tgt = sess->tgt;
 	struct qla_hw_data *ha = tgt->ha;
-	struct tcm_qla2xxx_lport *lport = ha->tgt.target_lport_ptr;
+	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
+	struct tcm_qla2xxx_lport *lport = vha->vha_tgt.target_lport_ptr;
 	struct se_node_acl *se_nacl = sess->se_sess->se_node_acl;
 	struct tcm_qla2xxx_nacl *nacl = container_of(se_nacl,
 			struct tcm_qla2xxx_nacl, se_node_acl);
@@ -1562,15 +1559,18 @@ static int tcm_qla2xxx_init_lport(struct tcm_qla2xxx_lport *lport)
 	return 0;
 }
 
-static int tcm_qla2xxx_lport_register_cb(struct scsi_qla_host *vha)
+static int tcm_qla2xxx_lport_register_cb(struct scsi_qla_host *vha,
+					 void *target_lport_ptr,
+					 u64 npiv_wwpn, u64 npiv_wwnn)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct tcm_qla2xxx_lport *lport;
+	struct tcm_qla2xxx_lport *lport =
+			(struct tcm_qla2xxx_lport *)target_lport_ptr;
 	/*
-	 * Setup local pointer to vha, NPIV VP pointer (if present) and
-	 * vha->tcm_lport pointer
+	 * Setup tgt_ops, local pointer to vha and target_lport_ptr
 	 */
-	lport = (struct tcm_qla2xxx_lport *)ha->tgt.target_lport_ptr;
+	ha->tgt.tgt_ops = &tcm_qla2xxx_template;
+	vha->vha_tgt.target_lport_ptr = target_lport_ptr;
 	lport->qla_vha = vha;
 
 	return 0;
@@ -1602,8 +1602,8 @@ static struct se_wwn *tcm_qla2xxx_make_lport(
 	if (ret != 0)
 		goto out;
 
-	ret = qlt_lport_register(&tcm_qla2xxx_template, wwpn,
-				tcm_qla2xxx_lport_register_cb, lport);
+	ret = qlt_lport_register(lport, wwpn, 0, 0,
+				 tcm_qla2xxx_lport_register_cb);
 	if (ret != 0)
 		goto out_lport;
 
@@ -1621,7 +1621,6 @@ static void tcm_qla2xxx_drop_lport(struct se_wwn *wwn)
 	struct tcm_qla2xxx_lport *lport = container_of(wwn,
 			struct tcm_qla2xxx_lport, lport_wwn);
 	struct scsi_qla_host *vha = lport->qla_vha;
-	struct qla_hw_data *ha = vha->hw;
 	struct se_node_acl *node;
 	u32 key = 0;
 
@@ -1630,8 +1629,8 @@ static void tcm_qla2xxx_drop_lport(struct se_wwn *wwn)
 	 * shutdown of struct qla_tgt after the call to
 	 * qlt_stop_phase1() from tcm_qla2xxx_drop_tpg() above..
 	 */
-	if (ha->tgt.qla_tgt && !ha->tgt.qla_tgt->tgt_stopped)
-		qlt_stop_phase2(ha->tgt.qla_tgt);
+	if (vha->vha_tgt.qla_tgt && !vha->vha_tgt.qla_tgt->tgt_stopped)
+		qlt_stop_phase2(vha->vha_tgt.qla_tgt);
 
 	qlt_lport_deregister(vha);
 
@@ -1642,17 +1641,70 @@ static void tcm_qla2xxx_drop_lport(struct se_wwn *wwn)
 	kfree(lport);
 }
 
+static int tcm_qla2xxx_lport_register_npiv_cb(struct scsi_qla_host *base_vha,
+					      void *target_lport_ptr,
+					      u64 npiv_wwpn, u64 npiv_wwnn)
+{
+	struct fc_vport *vport;
+	struct Scsi_Host *sh = base_vha->host;
+	struct scsi_qla_host *npiv_vha;
+	struct tcm_qla2xxx_lport *lport =
+			(struct tcm_qla2xxx_lport *)target_lport_ptr;
+	struct fc_vport_identifiers vport_id;
+
+	if (!qla_tgt_mode_enabled(base_vha)) {
+		pr_err("qla2xxx base_vha not enabled for target mode\n");
+		return -EPERM;
+	}
+
+	memset(&vport_id, 0, sizeof(vport_id));
+	vport_id.port_name = npiv_wwpn;
+	vport_id.node_name = npiv_wwnn;
+	vport_id.roles = FC_PORT_ROLE_FCP_INITIATOR;
+	vport_id.vport_type = FC_PORTTYPE_NPIV;
+	vport_id.disable = false;
+
+	vport = fc_vport_create(sh, 0, &vport_id);
+	if (!vport) {
+		pr_err("fc_vport_create failed for qla2xxx_npiv\n");
+		return -ENODEV;
+	}
+	/*
+	 * Setup local pointer to NPIV vhba + target_lport_ptr
+	 */
+	npiv_vha = (struct scsi_qla_host *)vport->dd_data;
+	npiv_vha->vha_tgt.target_lport_ptr = target_lport_ptr;
+	lport->qla_vha = npiv_vha;
+
+	scsi_host_get(npiv_vha->host);
+	return 0;
+}
+
+
 static struct se_wwn *tcm_qla2xxx_npiv_make_lport(
 	struct target_fabric_configfs *tf,
 	struct config_group *group,
 	const char *name)
 {
 	struct tcm_qla2xxx_lport *lport;
-	u64 npiv_wwpn, npiv_wwnn;
+	u64 phys_wwpn, npiv_wwpn, npiv_wwnn;
+	char *p, tmp[128];
 	int ret;
 
-	if (tcm_qla2xxx_npiv_parse_wwn(name, strlen(name)+1,
-				&npiv_wwpn, &npiv_wwnn) < 0)
+	snprintf(tmp, 128, "%s", name);
+
+	p = strchr(tmp, '@');
+	if (!p) {
+		pr_err("Unable to locate NPIV '@' seperator\n");
+		return ERR_PTR(-EINVAL);
+	}
+	*p++ = '\0';
+
+	if (tcm_qla2xxx_parse_wwn(tmp, &phys_wwpn, 1) < 0)
+		return ERR_PTR(-EINVAL);
+
+	if (tcm_qla2xxx_npiv_parse_wwn(p, strlen(p)+1,
+				       &npiv_wwpn, &npiv_wwnn) < 0)
 		return ERR_PTR(-EINVAL);
 
 	lport = kzalloc(sizeof(struct tcm_qla2xxx_lport), GFP_KERNEL);
@@ -1666,12 +1718,19 @@ static struct se_wwn *tcm_qla2xxx_npiv_make_lport(
 			TCM_QLA2XXX_NAMELEN, npiv_wwpn, npiv_wwnn);
 	sprintf(lport->lport_naa_name, "naa.%016llx", (unsigned long long) npiv_wwpn);
 
-/* FIXME: tcm_qla2xxx_npiv_make_lport */
-	ret = -ENOSYS;
+	ret = tcm_qla2xxx_init_lport(lport);
 	if (ret != 0)
 		goto out;
 
+	ret = qlt_lport_register(lport, phys_wwpn, npiv_wwpn, npiv_wwnn,
+				 tcm_qla2xxx_lport_register_npiv_cb);
+	if (ret != 0)
+		goto out_lport;
+
 	return &lport->lport_wwn;
+out_lport:
+	vfree(lport->lport_loopid_map);
+	btree_destroy32(&lport->lport_fcport_map);
 out:
 	kfree(lport);
 	return ERR_PTR(ret);
@@ -1681,14 +1740,16 @@ static void tcm_qla2xxx_npiv_drop_lport(struct se_wwn *wwn)
 {
 	struct tcm_qla2xxx_lport *lport = container_of(wwn,
 			struct tcm_qla2xxx_lport, lport_wwn);
-	struct scsi_qla_host *vha = lport->qla_vha;
-	struct Scsi_Host *sh = vha->host;
+	struct scsi_qla_host *npiv_vha = lport->qla_vha;
+	struct qla_hw_data *ha = npiv_vha->hw;
+	scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev);
+
+	scsi_host_put(npiv_vha->host);
 	/*
-	 * Notify libfc that we want to release the lport->npiv_vport
+	 * Notify libfc that we want to release the vha->fc_vport
 	 */
-	fc_vport_terminate(lport->npiv_vport);
-
-	scsi_host_put(sh);
+	fc_vport_terminate(npiv_vha->fc_vport);
+	scsi_host_put(base_vha->host);
 	kfree(lport);
 }
 
@@ -1769,14 +1830,16 @@ static struct target_core_fabric_ops tcm_qla2xxx_npiv_ops = {
 	.tpg_get_pr_transport_id	= tcm_qla2xxx_get_pr_transport_id,
 	.tpg_get_pr_transport_id_len	= tcm_qla2xxx_get_pr_transport_id_len,
 	.tpg_parse_pr_out_transport_id	= tcm_qla2xxx_parse_pr_out_transport_id,
-	.tpg_check_demo_mode		= tcm_qla2xxx_check_false,
-	.tpg_check_demo_mode_cache	= tcm_qla2xxx_check_true,
-	.tpg_check_demo_mode_write_protect = tcm_qla2xxx_check_true,
-	.tpg_check_prod_mode_write_protect = tcm_qla2xxx_check_false,
+	.tpg_check_demo_mode		= tcm_qla2xxx_check_demo_mode,
+	.tpg_check_demo_mode_cache	= tcm_qla2xxx_check_demo_mode_cache,
+	.tpg_check_demo_mode_write_protect = tcm_qla2xxx_check_demo_mode,
+	.tpg_check_prod_mode_write_protect =
+	    tcm_qla2xxx_check_prod_write_protect,
 	.tpg_check_demo_mode_login_only	= tcm_qla2xxx_check_demo_mode_login_only,
 	.tpg_alloc_fabric_acl		= tcm_qla2xxx_alloc_fabric_acl,
 	.tpg_release_fabric_acl		= tcm_qla2xxx_release_fabric_acl,
 	.tpg_get_inst_index		= tcm_qla2xxx_tpg_get_inst_index,
+	.check_stop_free                = tcm_qla2xxx_check_stop_free,
 	.release_cmd			= tcm_qla2xxx_release_cmd,
 	.put_session			= tcm_qla2xxx_put_session,
 	.shutdown_session		= tcm_qla2xxx_shutdown_session,
@@ -1871,7 +1934,8 @@ static int tcm_qla2xxx_register_configfs(void)
 	 * Setup default attribute lists for various npiv_fabric->tf_cit_tmpl
 	 */
 	npiv_fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs;
-	npiv_fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = NULL;
+	npiv_fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs =
+	    tcm_qla2xxx_tpg_attrs;
 	npiv_fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
 	npiv_fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
 	npiv_fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.h b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
index 771f7b81644..275d8b9a7a3 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.h
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
@@ -70,12 +70,8 @@ struct tcm_qla2xxx_lport {
 	struct tcm_qla2xxx_fc_loopid *lport_loopid_map;
 	/* Pointer to struct scsi_qla_host from qla2xxx LLD */
 	struct scsi_qla_host *qla_vha;
-	/* Pointer to struct scsi_qla_host for NPIV VP from qla2xxx LLD */
-	struct scsi_qla_host *qla_npiv_vp;
 	/* Pointer to struct qla_tgt pointer */
 	struct qla_tgt lport_qla_tgt;
-	/* Pointer to struct fc_vport for NPIV vport from libfc */
-	struct fc_vport *npiv_vport;
 	/* Pointer to TPG=1 for non NPIV mode */
 	struct tcm_qla2xxx_tpg *tpg_1;
 	/* Returned by tcm_qla2xxx_make_lport() */
diff --git a/drivers/target/Kconfig b/drivers/target/Kconfig
index 18303686eb5..dc2d84ac5a0 100644
--- a/drivers/target/Kconfig
+++ b/drivers/target/Kconfig
@@ -3,6 +3,7 @@ menuconfig TARGET_CORE
 	tristate "Generic Target Core Mod (TCM) and ConfigFS Infrastructure"
 	depends on SCSI && BLOCK
 	select CONFIGFS_FS
+	select CRC_T10DIF
 	default n
 	help
 	Say Y or M here to enable the TCM Storage Engine and ConfigFS enabled
@@ -13,6 +14,7 @@ if TARGET_CORE
 
 config TCM_IBLOCK
 	tristate "TCM/IBLOCK Subsystem Plugin for Linux/BLOCK"
+	select BLK_DEV_INTEGRITY
 	help
 	Say Y here to enable the TCM/IBLOCK subsystem plugin for non-buffered
 	access to Linux/Block devices using BIO
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 00867190413..7f1a7ce4b77 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -52,7 +52,7 @@
 static LIST_HEAD(g_tiqn_list);
 static LIST_HEAD(g_np_list);
 static DEFINE_SPINLOCK(tiqn_lock);
-static DEFINE_SPINLOCK(np_lock);
+static DEFINE_MUTEX(np_lock);
 
 static struct idr tiqn_idr;
 struct idr sess_idr;
@@ -307,6 +307,9 @@ bool iscsit_check_np_match(
 	return false;
 }
 
+/*
+ * Called with mutex np_lock held
+ */
 static struct iscsi_np *iscsit_get_np(
 	struct __kernel_sockaddr_storage *sockaddr,
 	int network_transport)
@@ -314,11 +317,10 @@ static struct iscsi_np *iscsit_get_np(
 	struct iscsi_np *np;
 	bool match;
 
-	spin_lock_bh(&np_lock);
 	list_for_each_entry(np, &g_np_list, np_list) {
-		spin_lock(&np->np_thread_lock);
+		spin_lock_bh(&np->np_thread_lock);
 		if (np->np_thread_state != ISCSI_NP_THREAD_ACTIVE) {
-			spin_unlock(&np->np_thread_lock);
+			spin_unlock_bh(&np->np_thread_lock);
 			continue;
 		}
 
@@ -330,13 +332,11 @@ static struct iscsi_np *iscsit_get_np(
 			 * while iscsi_tpg_add_network_portal() is called.
 			 */
 			np->np_exports++;
-			spin_unlock(&np->np_thread_lock);
-			spin_unlock_bh(&np_lock);
+			spin_unlock_bh(&np->np_thread_lock);
 			return np;
 		}
-		spin_unlock(&np->np_thread_lock);
+		spin_unlock_bh(&np->np_thread_lock);
 	}
-	spin_unlock_bh(&np_lock);
 
 	return NULL;
 }
@@ -350,16 +350,22 @@ struct iscsi_np *iscsit_add_np(
 	struct sockaddr_in6 *sock_in6;
 	struct iscsi_np *np;
 	int ret;
+
+	mutex_lock(&np_lock);
+
 	/*
 	 * Locate the existing struct iscsi_np if already active..
 	 */
 	np = iscsit_get_np(sockaddr, network_transport);
-	if (np)
+	if (np) {
+		mutex_unlock(&np_lock);
 		return np;
+	}
 
 	np = kzalloc(sizeof(struct iscsi_np), GFP_KERNEL);
 	if (!np) {
 		pr_err("Unable to allocate memory for struct iscsi_np\n");
+		mutex_unlock(&np_lock);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -382,6 +388,7 @@ struct iscsi_np *iscsit_add_np(
 	ret = iscsi_target_setup_login_socket(np, sockaddr);
 	if (ret != 0) {
 		kfree(np);
+		mutex_unlock(&np_lock);
 		return ERR_PTR(ret);
 	}
 
@@ -390,6 +397,7 @@ struct iscsi_np *iscsit_add_np(
 		pr_err("Unable to create kthread: iscsi_np\n");
 		ret = PTR_ERR(np->np_thread);
 		kfree(np);
+		mutex_unlock(&np_lock);
 		return ERR_PTR(ret);
 	}
 	/*
@@ -400,10 +408,10 @@ struct iscsi_np *iscsit_add_np(
 	 * point because iscsi_np has not been added to g_np_list yet.
 	 */
 	np->np_exports = 1;
+	np->np_thread_state = ISCSI_NP_THREAD_ACTIVE;
 
-	spin_lock_bh(&np_lock);
 	list_add_tail(&np->np_list, &g_np_list);
-	spin_unlock_bh(&np_lock);
+	mutex_unlock(&np_lock);
 
 	pr_debug("CORE[0] - Added Network Portal: %s:%hu on %s\n",
 		np->np_ip, np->np_port, np->np_transport->name);
@@ -470,9 +478,9 @@ int iscsit_del_np(struct iscsi_np *np)
 
 	np->np_transport->iscsit_free_np(np);
 
-	spin_lock_bh(&np_lock);
+	mutex_lock(&np_lock);
 	list_del(&np->np_list);
-	spin_unlock_bh(&np_lock);
+	mutex_unlock(&np_lock);
 
 	pr_debug("CORE[0] - Removed Network Portal: %s:%hu on %s\n",
 		np->np_ip, np->np_port, np->np_transport->name);
@@ -622,7 +630,7 @@ static int iscsit_add_reject(
 {
 	struct iscsi_cmd *cmd;
 
-	cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
+	cmd = iscsit_allocate_cmd(conn, TASK_INTERRUPTIBLE);
 	if (!cmd)
 		return -1;
 
@@ -2475,7 +2483,7 @@ static void iscsit_build_conn_drop_async_message(struct iscsi_conn *conn)
 	if (!conn_p)
 		return;
 
-	cmd = iscsit_allocate_cmd(conn_p, GFP_ATOMIC);
+	cmd = iscsit_allocate_cmd(conn_p, TASK_RUNNING);
 	if (!cmd) {
 		iscsit_dec_conn_usage_count(conn_p);
 		return;
@@ -3951,7 +3959,7 @@ static int iscsi_target_rx_opcode(struct iscsi_conn *conn, unsigned char *buf)
 
 	switch (hdr->opcode & ISCSI_OPCODE_MASK) {
 	case ISCSI_OP_SCSI_CMD:
-		cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
+		cmd = iscsit_allocate_cmd(conn, TASK_INTERRUPTIBLE);
 		if (!cmd)
 			goto reject;
 
@@ -3963,28 +3971,28 @@ static int iscsi_target_rx_opcode(struct iscsi_conn *conn, unsigned char *buf)
 	case ISCSI_OP_NOOP_OUT:
 		cmd = NULL;
 		if (hdr->ttt == cpu_to_be32(0xFFFFFFFF)) {
-			cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
+			cmd = iscsit_allocate_cmd(conn, TASK_INTERRUPTIBLE);
 			if (!cmd)
 				goto reject;
 		}
 		ret = iscsit_handle_nop_out(conn, cmd, buf);
 		break;
 	case ISCSI_OP_SCSI_TMFUNC:
-		cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
+		cmd = iscsit_allocate_cmd(conn, TASK_INTERRUPTIBLE);
 		if (!cmd)
 			goto reject;
 
 		ret = iscsit_handle_task_mgt_cmd(conn, cmd, buf);
 		break;
 	case ISCSI_OP_TEXT:
-		cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
+		cmd = iscsit_allocate_cmd(conn, TASK_INTERRUPTIBLE);
 		if (!cmd)
 			goto reject;
 
 		ret = iscsit_handle_text_cmd(conn, cmd, buf);
 		break;
 	case ISCSI_OP_LOGOUT:
-		cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
+		cmd = iscsit_allocate_cmd(conn, TASK_INTERRUPTIBLE);
 		if (!cmd)
 			goto reject;
 
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 83c965c6538..582ba84075e 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -1192,7 +1192,7 @@ get_target:
 	 */
 alloc_tags:
 	tag_num = max_t(u32, ISCSIT_MIN_TAGS, queue_depth);
-	tag_num += (tag_num / 2) + ISCSIT_EXTRA_TAGS;
+	tag_num = (tag_num * 2) + ISCSIT_EXTRA_TAGS;
 	tag_size = sizeof(struct iscsi_cmd) + conn->conn_transport->priv_size;
 
 	ret = transport_alloc_session_tags(sess->se_sess, tag_num, tag_size);
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 0819e688a39..e655b042ed1 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -152,13 +152,16 @@ void iscsit_free_r2ts_from_list(struct iscsi_cmd *cmd)
  * May be called from software interrupt (timer) context for allocating
  * iSCSI NopINs.
  */
-struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *conn, gfp_t gfp_mask)
+struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *conn, int state)
 {
 	struct iscsi_cmd *cmd;
 	struct se_session *se_sess = conn->sess->se_sess;
 	int size, tag;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, gfp_mask);
+	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, state);
+	if (tag < 0)
+		return NULL;
+
 	size = sizeof(struct iscsi_cmd) + conn->conn_transport->priv_size;
 	cmd = (struct iscsi_cmd *)(se_sess->sess_cmd_map + (tag * size));
 	memset(cmd, 0, size);
@@ -926,7 +929,7 @@ static int iscsit_add_nopin(struct iscsi_conn *conn, int want_response)
 	u8 state;
 	struct iscsi_cmd *cmd;
 
-	cmd = iscsit_allocate_cmd(conn, GFP_ATOMIC);
+	cmd = iscsit_allocate_cmd(conn, TASK_RUNNING);
 	if (!cmd)
 		return -1;
 
diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h
index e4fc34a02f5..561a424d198 100644
--- a/drivers/target/iscsi/iscsi_target_util.h
+++ b/drivers/target/iscsi/iscsi_target_util.h
@@ -9,7 +9,7 @@ extern struct iscsi_r2t *iscsit_get_r2t_from_list(struct iscsi_cmd *);
 extern void iscsit_free_r2t(struct iscsi_r2t *, struct iscsi_cmd *);
 extern void iscsit_free_r2ts_from_list(struct iscsi_cmd *);
 extern struct iscsi_cmd *iscsit_alloc_cmd(struct iscsi_conn *, gfp_t);
-extern struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *, gfp_t);
+extern struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *, int);
 extern struct iscsi_seq *iscsit_get_seq_holder_for_datain(struct iscsi_cmd *, u32);
 extern struct iscsi_seq *iscsit_get_seq_holder_for_r2t(struct iscsi_cmd *);
 extern struct iscsi_r2t *iscsit_get_holder_for_r2tsn(struct iscsi_cmd *, u32);
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 1b41e677615..fadad7c5f63 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -217,7 +217,8 @@ static void tcm_loop_submission_work(struct work_struct *work)
 			scsi_bufflen(sc), tcm_loop_sam_attr(sc),
 			sc->sc_data_direction, 0,
 			scsi_sglist(sc), scsi_sg_count(sc),
-			sgl_bidi, sgl_bidi_count);
+			sgl_bidi, sgl_bidi_count,
+			scsi_prot_sglist(sc), scsi_prot_sg_count(sc));
 	if (rc < 0) {
 		set_host_byte(sc, DID_NO_CONNECT);
 		goto out_done;
@@ -462,7 +463,7 @@ static int tcm_loop_driver_probe(struct device *dev)
 {
 	struct tcm_loop_hba *tl_hba;
 	struct Scsi_Host *sh;
-	int error;
+	int error, host_prot;
 
 	tl_hba = to_tcm_loop_hba(dev);
 
@@ -486,6 +487,13 @@ static int tcm_loop_driver_probe(struct device *dev)
 	sh->max_channel = 0;
 	sh->max_cmd_len = TL_SCSI_MAX_CMD_LEN;
 
+	host_prot = SHOST_DIF_TYPE1_PROTECTION | SHOST_DIF_TYPE2_PROTECTION |
+		    SHOST_DIF_TYPE3_PROTECTION | SHOST_DIX_TYPE1_PROTECTION |
+		    SHOST_DIX_TYPE2_PROTECTION | SHOST_DIX_TYPE3_PROTECTION;
+
+	scsi_host_set_prot(sh, host_prot);
+	scsi_host_set_guard(sh, SHOST_DIX_GUARD_CRC);
+
 	error = scsi_add_host(sh, &tl_hba->dev);
 	if (error) {
 		pr_err("%s: scsi_add_host failed\n", __func__);
@@ -1228,7 +1236,7 @@ static struct configfs_attribute *tcm_loop_tpg_attrs[] = {
 
 /* Start items for tcm_loop_naa_cit */
 
-struct se_portal_group *tcm_loop_make_naa_tpg(
+static struct se_portal_group *tcm_loop_make_naa_tpg(
 	struct se_wwn *wwn,
 	struct config_group *group,
 	const char *name)
@@ -1273,7 +1281,7 @@ struct se_portal_group *tcm_loop_make_naa_tpg(
 	return &tl_tpg->tl_se_tpg;
 }
 
-void tcm_loop_drop_naa_tpg(
+static void tcm_loop_drop_naa_tpg(
 	struct se_portal_group *se_tpg)
 {
 	struct se_wwn *wwn = se_tpg->se_tpg_wwn;
@@ -1305,7 +1313,7 @@ void tcm_loop_drop_naa_tpg(
 
 /* Start items for tcm_loop_cit */
 
-struct se_wwn *tcm_loop_make_scsi_hba(
+static struct se_wwn *tcm_loop_make_scsi_hba(
 	struct target_fabric_configfs *tf,
 	struct config_group *group,
 	const char *name)
@@ -1375,7 +1383,7 @@ out:
 	return ERR_PTR(ret);
 }
 
-void tcm_loop_drop_scsi_hba(
+static void tcm_loop_drop_scsi_hba(
 	struct se_wwn *wwn)
 {
 	struct tcm_loop_hba *tl_hba = container_of(wwn,
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index fdcee326bfb..12da9b38616 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -41,11 +41,14 @@
 #include "target_core_alua.h"
 #include "target_core_ua.h"
 
-static sense_reason_t core_alua_check_transition(int state, int *primary);
+static sense_reason_t core_alua_check_transition(int state, int valid,
+						 int *primary);
 static int core_alua_set_tg_pt_secondary_state(
 		struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem,
 		struct se_port *port, int explicit, int offline);
 
+static char *core_alua_dump_state(int state);
+
 static u16 alua_lu_gps_counter;
 static u32 alua_lu_gps_count;
 
@@ -55,6 +58,86 @@ static LIST_HEAD(lu_gps_list);
 struct t10_alua_lu_gp *default_lu_gp;
 
 /*
+ * REPORT REFERRALS
+ *
+ * See sbc3r35 section 5.23
+ */
+sense_reason_t
+target_emulate_report_referrals(struct se_cmd *cmd)
+{
+	struct se_device *dev = cmd->se_dev;
+	struct t10_alua_lba_map *map;
+	struct t10_alua_lba_map_member *map_mem;
+	unsigned char *buf;
+	u32 rd_len = 0, off;
+
+	if (cmd->data_length < 4) {
+		pr_warn("REPORT REFERRALS allocation length %u too"
+			" small\n", cmd->data_length);
+		return TCM_INVALID_CDB_FIELD;
+	}
+
+	buf = transport_kmap_data_sg(cmd);
+	if (!buf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
+	off = 4;
+	spin_lock(&dev->t10_alua.lba_map_lock);
+	if (list_empty(&dev->t10_alua.lba_map_list)) {
+		spin_unlock(&dev->t10_alua.lba_map_lock);
+		transport_kunmap_data_sg(cmd);
+
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
+	}
+
+	list_for_each_entry(map, &dev->t10_alua.lba_map_list,
+			    lba_map_list) {
+		int desc_num = off + 3;
+		int pg_num;
+
+		off += 4;
+		if (cmd->data_length > off)
+			put_unaligned_be64(map->lba_map_first_lba, &buf[off]);
+		off += 8;
+		if (cmd->data_length > off)
+			put_unaligned_be64(map->lba_map_last_lba, &buf[off]);
+		off += 8;
+		rd_len += 20;
+		pg_num = 0;
+		list_for_each_entry(map_mem, &map->lba_map_mem_list,
+				    lba_map_mem_list) {
+			int alua_state = map_mem->lba_map_mem_alua_state;
+			int alua_pg_id = map_mem->lba_map_mem_alua_pg_id;
+
+			if (cmd->data_length > off)
+				buf[off] = alua_state & 0x0f;
+			off += 2;
+			if (cmd->data_length > off)
+				buf[off] = (alua_pg_id >> 8) & 0xff;
+			off++;
+			if (cmd->data_length > off)
+				buf[off] = (alua_pg_id & 0xff);
+			off++;
+			rd_len += 4;
+			pg_num++;
+		}
+		if (cmd->data_length > desc_num)
+			buf[desc_num] = pg_num;
+	}
+	spin_unlock(&dev->t10_alua.lba_map_lock);
+
+	/*
+	 * Set the RETURN DATA LENGTH set in the header of the DataIN Payload
+	 */
+	put_unaligned_be16(rd_len, &buf[2]);
+
+	transport_kunmap_data_sg(cmd);
+
+	target_complete_cmd(cmd, GOOD);
+	return 0;
+}
+
+/*
  * REPORT_TARGET_PORT_GROUPS
  *
  * See spc4r17 section 6.27
@@ -210,7 +293,7 @@ target_emulate_set_target_port_groups(struct se_cmd *cmd)
 	unsigned char *ptr;
 	sense_reason_t rc = TCM_NO_SENSE;
 	u32 len = 4; /* Skip over RESERVED area in header */
-	int alua_access_state, primary = 0;
+	int alua_access_state, primary = 0, valid_states;
 	u16 tg_pt_id, rtpi;
 
 	if (!l_port)
@@ -252,6 +335,7 @@ target_emulate_set_target_port_groups(struct se_cmd *cmd)
 		rc = TCM_UNSUPPORTED_SCSI_OPCODE;
 		goto out;
 	}
+	valid_states = l_tg_pt_gp->tg_pt_gp_alua_supported_states;
 
 	ptr = &buf[4]; /* Skip over RESERVED area in header */
 
@@ -263,7 +347,8 @@ target_emulate_set_target_port_groups(struct se_cmd *cmd)
 		 * the state is a primary or secondary target port asymmetric
 		 * access state.
 		 */
-		rc = core_alua_check_transition(alua_access_state, &primary);
+		rc = core_alua_check_transition(alua_access_state,
+						valid_states, &primary);
 		if (rc) {
 			/*
 			 * If the SET TARGET PORT GROUPS attempts to establish
@@ -386,6 +471,81 @@ static inline int core_alua_state_nonoptimized(
 	return 0;
 }
 
+static inline int core_alua_state_lba_dependent(
+	struct se_cmd *cmd,
+	struct t10_alua_tg_pt_gp *tg_pt_gp,
+	u8 *alua_ascq)
+{
+	struct se_device *dev = cmd->se_dev;
+	u64 segment_size, segment_mult, sectors, lba;
+
+	/* Only need to check for cdb actually containing LBAs */
+	if (!(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB))
+		return 0;
+
+	spin_lock(&dev->t10_alua.lba_map_lock);
+	segment_size = dev->t10_alua.lba_map_segment_size;
+	segment_mult = dev->t10_alua.lba_map_segment_multiplier;
+	sectors = cmd->data_length / dev->dev_attrib.block_size;
+
+	lba = cmd->t_task_lba;
+	while (lba < cmd->t_task_lba + sectors) {
+		struct t10_alua_lba_map *cur_map = NULL, *map;
+		struct t10_alua_lba_map_member *map_mem;
+
+		list_for_each_entry(map, &dev->t10_alua.lba_map_list,
+				    lba_map_list) {
+			u64 start_lba, last_lba;
+			u64 first_lba = map->lba_map_first_lba;
+
+			if (segment_mult) {
+				u64 tmp = lba;
+				start_lba = sector_div(tmp, segment_size * segment_mult);
+
+				last_lba = first_lba + segment_size - 1;
+				if (start_lba >= first_lba &&
+				    start_lba <= last_lba) {
+					lba += segment_size;
+					cur_map = map;
+					break;
+				}
+			} else {
+				last_lba = map->lba_map_last_lba;
+				if (lba >= first_lba && lba <= last_lba) {
+					lba = last_lba + 1;
+					cur_map = map;
+					break;
+				}
+			}
+		}
+		if (!cur_map) {
+			spin_unlock(&dev->t10_alua.lba_map_lock);
+			*alua_ascq = ASCQ_04H_ALUA_TG_PT_UNAVAILABLE;
+			return 1;
+		}
+		list_for_each_entry(map_mem, &cur_map->lba_map_mem_list,
+				    lba_map_mem_list) {
+			if (map_mem->lba_map_mem_alua_pg_id !=
+			    tg_pt_gp->tg_pt_gp_id)
+				continue;
+			switch(map_mem->lba_map_mem_alua_state) {
+			case ALUA_ACCESS_STATE_STANDBY:
+				spin_unlock(&dev->t10_alua.lba_map_lock);
+				*alua_ascq = ASCQ_04H_ALUA_TG_PT_STANDBY;
+				return 1;
+			case ALUA_ACCESS_STATE_UNAVAILABLE:
+				spin_unlock(&dev->t10_alua.lba_map_lock);
+				*alua_ascq = ASCQ_04H_ALUA_TG_PT_UNAVAILABLE;
+				return 1;
+			default:
+				break;
+			}
+		}
+	}
+	spin_unlock(&dev->t10_alua.lba_map_lock);
+	return 0;
+}
+
 static inline int core_alua_state_standby(
 	struct se_cmd *cmd,
 	unsigned char *cdb,
@@ -583,6 +743,9 @@ target_alua_state_check(struct se_cmd *cmd)
 	case ALUA_ACCESS_STATE_TRANSITION:
 		ret = core_alua_state_transition(cmd, cdb, &alua_ascq);
 		break;
+	case ALUA_ACCESS_STATE_LBA_DEPENDENT:
+		ret = core_alua_state_lba_dependent(cmd, tg_pt_gp, &alua_ascq);
+		break;
 	/*
 	 * OFFLINE is a secondary ALUA target port group access state, that is
 	 * handled above with struct se_port->sep_tg_pt_secondary_offline=1
@@ -618,17 +781,36 @@ out:
  * Check implicit and explicit ALUA state change request.
  */
 static sense_reason_t
-core_alua_check_transition(int state, int *primary)
+core_alua_check_transition(int state, int valid, int *primary)
 {
+	/*
+	 * OPTIMIZED, NON-OPTIMIZED, STANDBY and UNAVAILABLE are
+	 * defined as primary target port asymmetric access states.
+	 */
 	switch (state) {
 	case ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED:
+		if (!(valid & ALUA_AO_SUP))
+			goto not_supported;
+		*primary = 1;
+		break;
 	case ALUA_ACCESS_STATE_ACTIVE_NON_OPTIMIZED:
+		if (!(valid & ALUA_AN_SUP))
+			goto not_supported;
+		*primary = 1;
+		break;
 	case ALUA_ACCESS_STATE_STANDBY:
+		if (!(valid & ALUA_S_SUP))
+			goto not_supported;
+		*primary = 1;
+		break;
 	case ALUA_ACCESS_STATE_UNAVAILABLE:
-		/*
-		 * OPTIMIZED, NON-OPTIMIZED, STANDBY and UNAVAILABLE are
-		 * defined as primary target port asymmetric access states.
-		 */
+		if (!(valid & ALUA_U_SUP))
+			goto not_supported;
+		*primary = 1;
+		break;
+	case ALUA_ACCESS_STATE_LBA_DEPENDENT:
+		if (!(valid & ALUA_LBD_SUP))
+			goto not_supported;
 		*primary = 1;
 		break;
 	case ALUA_ACCESS_STATE_OFFLINE:
@@ -636,14 +818,27 @@ core_alua_check_transition(int state, int *primary)
 		 * OFFLINE state is defined as a secondary target port
 		 * asymmetric access state.
 		 */
+		if (!(valid & ALUA_O_SUP))
+			goto not_supported;
 		*primary = 0;
 		break;
+	case ALUA_ACCESS_STATE_TRANSITION:
+		/*
+		 * Transitioning is set internally, and
+		 * cannot be selected manually.
+		 */
+		goto not_supported;
 	default:
 		pr_err("Unknown ALUA access state: 0x%02x\n", state);
 		return TCM_INVALID_PARAMETER_LIST;
 	}
 
 	return 0;
+
+not_supported:
+	pr_err("ALUA access state %s not supported",
+	       core_alua_dump_state(state));
+	return TCM_INVALID_PARAMETER_LIST;
 }
 
 static char *core_alua_dump_state(int state)
@@ -653,12 +848,16 @@ static char *core_alua_dump_state(int state)
 		return "Active/Optimized";
 	case ALUA_ACCESS_STATE_ACTIVE_NON_OPTIMIZED:
 		return "Active/NonOptimized";
+	case ALUA_ACCESS_STATE_LBA_DEPENDENT:
+		return "LBA Dependent";
 	case ALUA_ACCESS_STATE_STANDBY:
 		return "Standby";
 	case ALUA_ACCESS_STATE_UNAVAILABLE:
 		return "Unavailable";
 	case ALUA_ACCESS_STATE_OFFLINE:
 		return "Offline";
+	case ALUA_ACCESS_STATE_TRANSITION:
+		return "Transitioning";
 	default:
 		return "Unknown";
 	}
@@ -735,58 +934,49 @@ static int core_alua_write_tpg_metadata(
  * Called with tg_pt_gp->tg_pt_gp_md_mutex held
  */
 static int core_alua_update_tpg_primary_metadata(
-	struct t10_alua_tg_pt_gp *tg_pt_gp,
-	int primary_state,
-	unsigned char *md_buf)
+	struct t10_alua_tg_pt_gp *tg_pt_gp)
 {
+	unsigned char *md_buf;
 	struct t10_wwn *wwn = &tg_pt_gp->tg_pt_gp_dev->t10_wwn;
 	char path[ALUA_METADATA_PATH_LEN];
-	int len;
+	int len, rc;
+
+	md_buf = kzalloc(ALUA_MD_BUF_LEN, GFP_KERNEL);
+	if (!md_buf) {
+		pr_err("Unable to allocate buf for ALUA metadata\n");
+		return -ENOMEM;
+	}
 
 	memset(path, 0, ALUA_METADATA_PATH_LEN);
 
-	len = snprintf(md_buf, tg_pt_gp->tg_pt_gp_md_buf_len,
+	len = snprintf(md_buf, ALUA_MD_BUF_LEN,
 			"tg_pt_gp_id=%hu\n"
 			"alua_access_state=0x%02x\n"
 			"alua_access_status=0x%02x\n",
-			tg_pt_gp->tg_pt_gp_id, primary_state,
+			tg_pt_gp->tg_pt_gp_id,
+			tg_pt_gp->tg_pt_gp_alua_pending_state,
 			tg_pt_gp->tg_pt_gp_alua_access_status);
 
 	snprintf(path, ALUA_METADATA_PATH_LEN,
 		"/var/target/alua/tpgs_%s/%s", &wwn->unit_serial[0],
 		config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item));
 
-	return core_alua_write_tpg_metadata(path, md_buf, len);
+	rc = core_alua_write_tpg_metadata(path, md_buf, len);
+	kfree(md_buf);
+	return rc;
 }
 
-static int core_alua_do_transition_tg_pt(
-	struct t10_alua_tg_pt_gp *tg_pt_gp,
-	struct se_port *l_port,
-	struct se_node_acl *nacl,
-	unsigned char *md_buf,
-	int new_state,
-	int explicit)
+static void core_alua_do_transition_tg_pt_work(struct work_struct *work)
 {
+	struct t10_alua_tg_pt_gp *tg_pt_gp = container_of(work,
+		struct t10_alua_tg_pt_gp, tg_pt_gp_transition_work.work);
+	struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
 	struct se_dev_entry *se_deve;
 	struct se_lun_acl *lacl;
 	struct se_port *port;
 	struct t10_alua_tg_pt_gp_member *mem;
-	int old_state = 0;
-	/*
-	 * Save the old primary ALUA access state, and set the current state
-	 * to ALUA_ACCESS_STATE_TRANSITION.
-	 */
-	old_state = atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
-	atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
-			ALUA_ACCESS_STATE_TRANSITION);
-	tg_pt_gp->tg_pt_gp_alua_access_status = (explicit) ?
-				ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG :
-				ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA;
-	/*
-	 * Check for the optional ALUA primary state transition delay
-	 */
-	if (tg_pt_gp->tg_pt_gp_trans_delay_msecs != 0)
-		msleep_interruptible(tg_pt_gp->tg_pt_gp_trans_delay_msecs);
+	bool explicit = (tg_pt_gp->tg_pt_gp_alua_access_status ==
+			 ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG);
 
 	spin_lock(&tg_pt_gp->tg_pt_gp_lock);
 	list_for_each_entry(mem, &tg_pt_gp->tg_pt_gp_mem_list,
@@ -821,9 +1011,12 @@ static int core_alua_do_transition_tg_pt(
 			if (!lacl)
 				continue;
 
-			if (explicit &&
-			   (nacl != NULL) && (nacl == lacl->se_lun_nacl) &&
-			   (l_port != NULL) && (l_port == port))
+			if ((tg_pt_gp->tg_pt_gp_alua_access_status ==
+			     ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG) &&
+			   (tg_pt_gp->tg_pt_gp_alua_nacl != NULL) &&
+			    (tg_pt_gp->tg_pt_gp_alua_nacl == lacl->se_lun_nacl) &&
+			   (tg_pt_gp->tg_pt_gp_alua_port != NULL) &&
+			    (tg_pt_gp->tg_pt_gp_alua_port == port))
 				continue;
 
 			core_scsi3_ua_allocate(lacl->se_lun_nacl,
@@ -851,20 +1044,102 @@ static int core_alua_do_transition_tg_pt(
 	 */
 	if (tg_pt_gp->tg_pt_gp_write_metadata) {
 		mutex_lock(&tg_pt_gp->tg_pt_gp_md_mutex);
-		core_alua_update_tpg_primary_metadata(tg_pt_gp,
-					new_state, md_buf);
+		core_alua_update_tpg_primary_metadata(tg_pt_gp);
 		mutex_unlock(&tg_pt_gp->tg_pt_gp_md_mutex);
 	}
 	/*
 	 * Set the current primary ALUA access state to the requested new state
 	 */
-	atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state, new_state);
+	atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
+		   tg_pt_gp->tg_pt_gp_alua_pending_state);
 
 	pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu"
 		" from primary access state %s to %s\n", (explicit) ? "explicit" :
 		"implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
-		tg_pt_gp->tg_pt_gp_id, core_alua_dump_state(old_state),
-		core_alua_dump_state(new_state));
+		tg_pt_gp->tg_pt_gp_id,
+		core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_previous_state),
+		core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_pending_state));
+	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
+	atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
+	smp_mb__after_atomic_dec();
+	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
+
+	if (tg_pt_gp->tg_pt_gp_transition_complete)
+		complete(tg_pt_gp->tg_pt_gp_transition_complete);
+}
+
+static int core_alua_do_transition_tg_pt(
+	struct t10_alua_tg_pt_gp *tg_pt_gp,
+	int new_state,
+	int explicit)
+{
+	struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	/* Nothing to be done here */
+	if (atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state) == new_state)
+		return 0;
+
+	if (new_state == ALUA_ACCESS_STATE_TRANSITION)
+		return -EAGAIN;
+
+	/*
+	 * Flush any pending transitions
+	 */
+	if (!explicit && tg_pt_gp->tg_pt_gp_implicit_trans_secs &&
+	    atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state) ==
+	    ALUA_ACCESS_STATE_TRANSITION) {
+		/* Just in case */
+		tg_pt_gp->tg_pt_gp_alua_pending_state = new_state;
+		tg_pt_gp->tg_pt_gp_transition_complete = &wait;
+		flush_delayed_work(&tg_pt_gp->tg_pt_gp_transition_work);
+		wait_for_completion(&wait);
+		tg_pt_gp->tg_pt_gp_transition_complete = NULL;
+		return 0;
+	}
+
+	/*
+	 * Save the old primary ALUA access state, and set the current state
+	 * to ALUA_ACCESS_STATE_TRANSITION.
+	 */
+	tg_pt_gp->tg_pt_gp_alua_previous_state =
+		atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
+	tg_pt_gp->tg_pt_gp_alua_pending_state = new_state;
+
+	atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
+			ALUA_ACCESS_STATE_TRANSITION);
+	tg_pt_gp->tg_pt_gp_alua_access_status = (explicit) ?
+				ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG :
+				ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA;
+
+	/*
+	 * Check for the optional ALUA primary state transition delay
+	 */
+	if (tg_pt_gp->tg_pt_gp_trans_delay_msecs != 0)
+		msleep_interruptible(tg_pt_gp->tg_pt_gp_trans_delay_msecs);
+
+	/*
+	 * Take a reference for workqueue item
+	 */
+	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
+	atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
+	smp_mb__after_atomic_inc();
+	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
+
+	if (!explicit && tg_pt_gp->tg_pt_gp_implicit_trans_secs) {
+		unsigned long transition_tmo;
+
+		transition_tmo = tg_pt_gp->tg_pt_gp_implicit_trans_secs * HZ;
+		queue_delayed_work(tg_pt_gp->tg_pt_gp_dev->tmr_wq,
+				   &tg_pt_gp->tg_pt_gp_transition_work,
+				   transition_tmo);
+	} else {
+		tg_pt_gp->tg_pt_gp_transition_complete = &wait;
+		queue_delayed_work(tg_pt_gp->tg_pt_gp_dev->tmr_wq,
+				   &tg_pt_gp->tg_pt_gp_transition_work, 0);
+		wait_for_completion(&wait);
+		tg_pt_gp->tg_pt_gp_transition_complete = NULL;
+	}
 
 	return 0;
 }
@@ -878,23 +1153,15 @@ int core_alua_do_port_transition(
 	int explicit)
 {
 	struct se_device *dev;
-	struct se_port *port;
-	struct se_node_acl *nacl;
 	struct t10_alua_lu_gp *lu_gp;
 	struct t10_alua_lu_gp_member *lu_gp_mem, *local_lu_gp_mem;
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
-	unsigned char *md_buf;
-	int primary;
+	int primary, valid_states, rc = 0;
 
-	if (core_alua_check_transition(new_state, &primary) != 0)
+	valid_states = l_tg_pt_gp->tg_pt_gp_alua_supported_states;
+	if (core_alua_check_transition(new_state, valid_states, &primary) != 0)
 		return -EINVAL;
 
-	md_buf = kzalloc(l_tg_pt_gp->tg_pt_gp_md_buf_len, GFP_KERNEL);
-	if (!md_buf) {
-		pr_err("Unable to allocate buf for ALUA metadata\n");
-		return -ENOMEM;
-	}
-
 	local_lu_gp_mem = l_dev->dev_alua_lu_gp_mem;
 	spin_lock(&local_lu_gp_mem->lu_gp_mem_lock);
 	lu_gp = local_lu_gp_mem->lu_gp;
@@ -911,12 +1178,13 @@ int core_alua_do_port_transition(
 		 * core_alua_do_transition_tg_pt() will always return
 		 * success.
 		 */
-		core_alua_do_transition_tg_pt(l_tg_pt_gp, l_port, l_nacl,
-					md_buf, new_state, explicit);
+		l_tg_pt_gp->tg_pt_gp_alua_port = l_port;
+		l_tg_pt_gp->tg_pt_gp_alua_nacl = l_nacl;
+		rc = core_alua_do_transition_tg_pt(l_tg_pt_gp,
+						   new_state, explicit);
 		atomic_dec(&lu_gp->lu_gp_ref_cnt);
 		smp_mb__after_atomic_dec();
-		kfree(md_buf);
-		return 0;
+		return rc;
 	}
 	/*
 	 * For all other LU groups aside from 'default_lu_gp', walk all of
@@ -951,11 +1219,11 @@ int core_alua_do_port_transition(
 				continue;
 
 			if (l_tg_pt_gp == tg_pt_gp) {
-				port = l_port;
-				nacl = l_nacl;
+				tg_pt_gp->tg_pt_gp_alua_port = l_port;
+				tg_pt_gp->tg_pt_gp_alua_nacl = l_nacl;
 			} else {
-				port = NULL;
-				nacl = NULL;
+				tg_pt_gp->tg_pt_gp_alua_port = NULL;
+				tg_pt_gp->tg_pt_gp_alua_nacl = NULL;
 			}
 			atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
 			smp_mb__after_atomic_inc();
@@ -964,12 +1232,14 @@ int core_alua_do_port_transition(
 			 * core_alua_do_transition_tg_pt() will always return
 			 * success.
 			 */
-			core_alua_do_transition_tg_pt(tg_pt_gp, port,
-					nacl, md_buf, new_state, explicit);
+			rc = core_alua_do_transition_tg_pt(tg_pt_gp,
+					new_state, explicit);
 
 			spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 			atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
 			smp_mb__after_atomic_dec();
+			if (rc)
+				break;
 		}
 		spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 
@@ -979,16 +1249,18 @@ int core_alua_do_port_transition(
 	}
 	spin_unlock(&lu_gp->lu_gp_lock);
 
-	pr_debug("Successfully processed LU Group: %s all ALUA TG PT"
-		" Group IDs: %hu %s transition to primary state: %s\n",
-		config_item_name(&lu_gp->lu_gp_group.cg_item),
-		l_tg_pt_gp->tg_pt_gp_id, (explicit) ? "explicit" : "implicit",
-		core_alua_dump_state(new_state));
+	if (!rc) {
+		pr_debug("Successfully processed LU Group: %s all ALUA TG PT"
+			 " Group IDs: %hu %s transition to primary state: %s\n",
+			 config_item_name(&lu_gp->lu_gp_group.cg_item),
+			 l_tg_pt_gp->tg_pt_gp_id,
+			 (explicit) ? "explicit" : "implicit",
+			 core_alua_dump_state(new_state));
+	}
 
 	atomic_dec(&lu_gp->lu_gp_ref_cnt);
 	smp_mb__after_atomic_dec();
-	kfree(md_buf);
-	return 0;
+	return rc;
 }
 
 /*
@@ -996,13 +1268,18 @@ int core_alua_do_port_transition(
  */
 static int core_alua_update_tpg_secondary_metadata(
 	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem,
-	struct se_port *port,
-	unsigned char *md_buf,
-	u32 md_buf_len)
+	struct se_port *port)
 {
+	unsigned char *md_buf;
 	struct se_portal_group *se_tpg = port->sep_tpg;
 	char path[ALUA_METADATA_PATH_LEN], wwn[ALUA_SECONDARY_METADATA_WWN_LEN];
-	int len;
+	int len, rc;
+
+	md_buf = kzalloc(ALUA_MD_BUF_LEN, GFP_KERNEL);
+	if (!md_buf) {
+		pr_err("Unable to allocate buf for ALUA metadata\n");
+		return -ENOMEM;
+	}
 
 	memset(path, 0, ALUA_METADATA_PATH_LEN);
 	memset(wwn, 0, ALUA_SECONDARY_METADATA_WWN_LEN);
@@ -1014,7 +1291,7 @@ static int core_alua_update_tpg_secondary_metadata(
 		snprintf(wwn+len, ALUA_SECONDARY_METADATA_WWN_LEN-len, "+%hu",
 				se_tpg->se_tpg_tfo->tpg_get_tag(se_tpg));
 
-	len = snprintf(md_buf, md_buf_len, "alua_tg_pt_offline=%d\n"
+	len = snprintf(md_buf, ALUA_MD_BUF_LEN, "alua_tg_pt_offline=%d\n"
 			"alua_tg_pt_status=0x%02x\n",
 			atomic_read(&port->sep_tg_pt_secondary_offline),
 			port->sep_tg_pt_secondary_stat);
@@ -1023,7 +1300,10 @@ static int core_alua_update_tpg_secondary_metadata(
 			se_tpg->se_tpg_tfo->get_fabric_name(), wwn,
 			port->sep_lun->unpacked_lun);
 
-	return core_alua_write_tpg_metadata(path, md_buf, len);
+	rc = core_alua_write_tpg_metadata(path, md_buf, len);
+	kfree(md_buf);
+
+	return rc;
 }
 
 static int core_alua_set_tg_pt_secondary_state(
@@ -1033,8 +1313,6 @@ static int core_alua_set_tg_pt_secondary_state(
 	int offline)
 {
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
-	unsigned char *md_buf;
-	u32 md_buf_len;
 	int trans_delay_msecs;
 
 	spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
@@ -1055,7 +1333,6 @@ static int core_alua_set_tg_pt_secondary_state(
 	else
 		atomic_set(&port->sep_tg_pt_secondary_offline, 0);
 
-	md_buf_len = tg_pt_gp->tg_pt_gp_md_buf_len;
 	port->sep_tg_pt_secondary_stat = (explicit) ?
 			ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG :
 			ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA;
@@ -1077,23 +1354,115 @@ static int core_alua_set_tg_pt_secondary_state(
 	 * secondary state and status
 	 */
 	if (port->sep_tg_pt_secondary_write_md) {
-		md_buf = kzalloc(md_buf_len, GFP_KERNEL);
-		if (!md_buf) {
-			pr_err("Unable to allocate md_buf for"
-				" secondary ALUA access metadata\n");
-			return -ENOMEM;
-		}
 		mutex_lock(&port->sep_tg_pt_md_mutex);
-		core_alua_update_tpg_secondary_metadata(tg_pt_gp_mem, port,
-				md_buf, md_buf_len);
+		core_alua_update_tpg_secondary_metadata(tg_pt_gp_mem, port);
 		mutex_unlock(&port->sep_tg_pt_md_mutex);
+	}
+
+	return 0;
+}
+
+struct t10_alua_lba_map *
+core_alua_allocate_lba_map(struct list_head *list,
+			   u64 first_lba, u64 last_lba)
+{
+	struct t10_alua_lba_map *lba_map;
+
+	lba_map = kmem_cache_zalloc(t10_alua_lba_map_cache, GFP_KERNEL);
+	if (!lba_map) {
+		pr_err("Unable to allocate struct t10_alua_lba_map\n");
+		return ERR_PTR(-ENOMEM);
+	}
+	INIT_LIST_HEAD(&lba_map->lba_map_mem_list);
+	lba_map->lba_map_first_lba = first_lba;
+	lba_map->lba_map_last_lba = last_lba;
 
-		kfree(md_buf);
+	list_add_tail(&lba_map->lba_map_list, list);
+	return lba_map;
+}
+
+int
+core_alua_allocate_lba_map_mem(struct t10_alua_lba_map *lba_map,
+			       int pg_id, int state)
+{
+	struct t10_alua_lba_map_member *lba_map_mem;
+
+	list_for_each_entry(lba_map_mem, &lba_map->lba_map_mem_list,
+			    lba_map_mem_list) {
+		if (lba_map_mem->lba_map_mem_alua_pg_id == pg_id) {
+			pr_err("Duplicate pg_id %d in lba_map\n", pg_id);
+			return -EINVAL;
+		}
+	}
+
+	lba_map_mem = kmem_cache_zalloc(t10_alua_lba_map_mem_cache, GFP_KERNEL);
+	if (!lba_map_mem) {
+		pr_err("Unable to allocate struct t10_alua_lba_map_mem\n");
+		return -ENOMEM;
 	}
+	lba_map_mem->lba_map_mem_alua_state = state;
+	lba_map_mem->lba_map_mem_alua_pg_id = pg_id;
 
+	list_add_tail(&lba_map_mem->lba_map_mem_list,
+		      &lba_map->lba_map_mem_list);
 	return 0;
 }
 
+void
+core_alua_free_lba_map(struct list_head *lba_list)
+{
+	struct t10_alua_lba_map *lba_map, *lba_map_tmp;
+	struct t10_alua_lba_map_member *lba_map_mem, *lba_map_mem_tmp;
+
+	list_for_each_entry_safe(lba_map, lba_map_tmp, lba_list,
+				 lba_map_list) {
+		list_for_each_entry_safe(lba_map_mem, lba_map_mem_tmp,
+					 &lba_map->lba_map_mem_list,
+					 lba_map_mem_list) {
+			list_del(&lba_map_mem->lba_map_mem_list);
+			kmem_cache_free(t10_alua_lba_map_mem_cache,
+					lba_map_mem);
+		}
+		list_del(&lba_map->lba_map_list);
+		kmem_cache_free(t10_alua_lba_map_cache, lba_map);
+	}
+}
+
+void
+core_alua_set_lba_map(struct se_device *dev, struct list_head *lba_map_list,
+		      int segment_size, int segment_mult)
+{
+	struct list_head old_lba_map_list;
+	struct t10_alua_tg_pt_gp *tg_pt_gp;
+	int activate = 0, supported;
+
+	INIT_LIST_HEAD(&old_lba_map_list);
+	spin_lock(&dev->t10_alua.lba_map_lock);
+	dev->t10_alua.lba_map_segment_size = segment_size;
+	dev->t10_alua.lba_map_segment_multiplier = segment_mult;
+	list_splice_init(&dev->t10_alua.lba_map_list, &old_lba_map_list);
+	if (lba_map_list) {
+		list_splice_init(lba_map_list, &dev->t10_alua.lba_map_list);
+		activate = 1;
+	}
+	spin_unlock(&dev->t10_alua.lba_map_lock);
+	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
+	list_for_each_entry(tg_pt_gp, &dev->t10_alua.tg_pt_gps_list,
+			    tg_pt_gp_list) {
+
+		if (!tg_pt_gp->tg_pt_gp_valid_id)
+			continue;
+		supported = tg_pt_gp->tg_pt_gp_alua_supported_states;
+		if (activate)
+			supported |= ALUA_LBD_SUP;
+		else
+			supported &= ~ALUA_LBD_SUP;
+		tg_pt_gp->tg_pt_gp_alua_supported_states = supported;
+	}
+	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
+	core_alua_free_lba_map(&old_lba_map_list);
+}
+
 struct t10_alua_lu_gp *
 core_alua_allocate_lu_gp(const char *name, int def_group)
 {
@@ -1346,8 +1715,9 @@ struct t10_alua_tg_pt_gp *core_alua_allocate_tg_pt_gp(struct se_device *dev,
 	mutex_init(&tg_pt_gp->tg_pt_gp_md_mutex);
 	spin_lock_init(&tg_pt_gp->tg_pt_gp_lock);
 	atomic_set(&tg_pt_gp->tg_pt_gp_ref_cnt, 0);
+	INIT_DELAYED_WORK(&tg_pt_gp->tg_pt_gp_transition_work,
+			  core_alua_do_transition_tg_pt_work);
 	tg_pt_gp->tg_pt_gp_dev = dev;
-	tg_pt_gp->tg_pt_gp_md_buf_len = ALUA_MD_BUF_LEN;
 	atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
 		ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED);
 	/*
@@ -1475,6 +1845,8 @@ void core_alua_free_tg_pt_gp(
 	dev->t10_alua.alua_tg_pt_gps_counter--;
 	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 
+	flush_delayed_work(&tg_pt_gp->tg_pt_gp_transition_work);
+
 	/*
 	 * Allow a struct t10_alua_tg_pt_gp_member * referenced by
 	 * core_alua_get_tg_pt_gp_by_name() in
diff --git a/drivers/target/target_core_alua.h b/drivers/target/target_core_alua.h
index 88e2e835f14..0a7d65e8040 100644
--- a/drivers/target/target_core_alua.h
+++ b/drivers/target/target_core_alua.h
@@ -13,12 +13,13 @@
 /*
  * ASYMMETRIC ACCESS STATE field
  *
- * from spc4r17 section 6.27 Table 245
+ * from spc4r36j section 6.37 Table 307
  */
 #define ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED	0x0
 #define ALUA_ACCESS_STATE_ACTIVE_NON_OPTIMIZED	0x1
 #define ALUA_ACCESS_STATE_STANDBY		0x2
 #define ALUA_ACCESS_STATE_UNAVAILABLE		0x3
+#define ALUA_ACCESS_STATE_LBA_DEPENDENT		0x4
 #define ALUA_ACCESS_STATE_OFFLINE		0xe
 #define ALUA_ACCESS_STATE_TRANSITION		0xf
 
@@ -78,18 +79,30 @@
  */
 #define ALUA_SECONDARY_METADATA_WWN_LEN			256
 
+/* Used by core_alua_update_tpg_(primary,secondary)_metadata */
+#define ALUA_MD_BUF_LEN					1024
+
 extern struct kmem_cache *t10_alua_lu_gp_cache;
 extern struct kmem_cache *t10_alua_lu_gp_mem_cache;
 extern struct kmem_cache *t10_alua_tg_pt_gp_cache;
 extern struct kmem_cache *t10_alua_tg_pt_gp_mem_cache;
+extern struct kmem_cache *t10_alua_lba_map_cache;
+extern struct kmem_cache *t10_alua_lba_map_mem_cache;
 
 extern sense_reason_t target_emulate_report_target_port_groups(struct se_cmd *);
 extern sense_reason_t target_emulate_set_target_port_groups(struct se_cmd *);
+extern sense_reason_t target_emulate_report_referrals(struct se_cmd *);
 extern int core_alua_check_nonop_delay(struct se_cmd *);
 extern int core_alua_do_port_transition(struct t10_alua_tg_pt_gp *,
 				struct se_device *, struct se_port *,
 				struct se_node_acl *, int, int);
 extern char *core_alua_dump_status(int);
+extern struct t10_alua_lba_map *core_alua_allocate_lba_map(
+				struct list_head *, u64, u64);
+extern int core_alua_allocate_lba_map_mem(struct t10_alua_lba_map *, int, int);
+extern void core_alua_free_lba_map(struct list_head *);
+extern void core_alua_set_lba_map(struct se_device *, struct list_head *,
+				int, int);
 extern struct t10_alua_lu_gp *core_alua_allocate_lu_gp(const char *, int);
 extern int core_alua_set_lu_gp_id(struct t10_alua_lu_gp *, u16);
 extern void core_alua_free_lu_gp(struct t10_alua_lu_gp *);
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 272755d03e5..f0e85b11969 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -643,6 +643,15 @@ SE_DEV_ATTR(emulate_caw, S_IRUGO | S_IWUSR);
 DEF_DEV_ATTRIB(emulate_3pc);
 SE_DEV_ATTR(emulate_3pc, S_IRUGO | S_IWUSR);
 
+DEF_DEV_ATTRIB(pi_prot_type);
+SE_DEV_ATTR(pi_prot_type, S_IRUGO | S_IWUSR);
+
+DEF_DEV_ATTRIB_RO(hw_pi_prot_type);
+SE_DEV_ATTR_RO(hw_pi_prot_type);
+
+DEF_DEV_ATTRIB(pi_prot_format);
+SE_DEV_ATTR(pi_prot_format, S_IRUGO | S_IWUSR);
+
 DEF_DEV_ATTRIB(enforce_pr_isids);
 SE_DEV_ATTR(enforce_pr_isids, S_IRUGO | S_IWUSR);
 
@@ -702,6 +711,9 @@ static struct configfs_attribute *target_core_dev_attrib_attrs[] = {
 	&target_core_dev_attrib_emulate_tpws.attr,
 	&target_core_dev_attrib_emulate_caw.attr,
 	&target_core_dev_attrib_emulate_3pc.attr,
+	&target_core_dev_attrib_pi_prot_type.attr,
+	&target_core_dev_attrib_hw_pi_prot_type.attr,
+	&target_core_dev_attrib_pi_prot_format.attr,
 	&target_core_dev_attrib_enforce_pr_isids.attr,
 	&target_core_dev_attrib_is_nonrot.attr,
 	&target_core_dev_attrib_emulate_rest_reord.attr,
@@ -1741,6 +1753,176 @@ static struct target_core_configfs_attribute target_core_attr_dev_alua_lu_gp = {
 	.store	= target_core_store_alua_lu_gp,
 };
 
+static ssize_t target_core_show_dev_lba_map(void *p, char *page)
+{
+	struct se_device *dev = p;
+	struct t10_alua_lba_map *map;
+	struct t10_alua_lba_map_member *mem;
+	char *b = page;
+	int bl = 0;
+	char state;
+
+	spin_lock(&dev->t10_alua.lba_map_lock);
+	if (!list_empty(&dev->t10_alua.lba_map_list))
+	    bl += sprintf(b + bl, "%u %u\n",
+			  dev->t10_alua.lba_map_segment_size,
+			  dev->t10_alua.lba_map_segment_multiplier);
+	list_for_each_entry(map, &dev->t10_alua.lba_map_list, lba_map_list) {
+		bl += sprintf(b + bl, "%llu %llu",
+			      map->lba_map_first_lba, map->lba_map_last_lba);
+		list_for_each_entry(mem, &map->lba_map_mem_list,
+				    lba_map_mem_list) {
+			switch (mem->lba_map_mem_alua_state) {
+			case ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED:
+				state = 'O';
+				break;
+			case ALUA_ACCESS_STATE_ACTIVE_NON_OPTIMIZED:
+				state = 'A';
+				break;
+			case ALUA_ACCESS_STATE_STANDBY:
+				state = 'S';
+				break;
+			case ALUA_ACCESS_STATE_UNAVAILABLE:
+				state = 'U';
+				break;
+			default:
+				state = '.';
+				break;
+			}
+			bl += sprintf(b + bl, " %d:%c",
+				      mem->lba_map_mem_alua_pg_id, state);
+		}
+		bl += sprintf(b + bl, "\n");
+	}
+	spin_unlock(&dev->t10_alua.lba_map_lock);
+	return bl;
+}
+
+static ssize_t target_core_store_dev_lba_map(
+	void *p,
+	const char *page,
+	size_t count)
+{
+	struct se_device *dev = p;
+	struct t10_alua_lba_map *lba_map = NULL;
+	struct list_head lba_list;
+	char *map_entries, *ptr;
+	char state;
+	int pg_num = -1, pg;
+	int ret = 0, num = 0, pg_id, alua_state;
+	unsigned long start_lba = -1, end_lba = -1;
+	unsigned long segment_size = -1, segment_mult = -1;
+
+	map_entries = kstrdup(page, GFP_KERNEL);
+	if (!map_entries)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&lba_list);
+	while ((ptr = strsep(&map_entries, "\n")) != NULL) {
+		if (!*ptr)
+			continue;
+
+		if (num == 0) {
+			if (sscanf(ptr, "%lu %lu\n",
+				   &segment_size, &segment_mult) != 2) {
+				pr_err("Invalid line %d\n", num);
+				ret = -EINVAL;
+				break;
+			}
+			num++;
+			continue;
+		}
+		if (sscanf(ptr, "%lu %lu", &start_lba, &end_lba) != 2) {
+			pr_err("Invalid line %d\n", num);
+			ret = -EINVAL;
+			break;
+		}
+		ptr = strchr(ptr, ' ');
+		if (!ptr) {
+			pr_err("Invalid line %d, missing end lba\n", num);
+			ret = -EINVAL;
+			break;
+		}
+		ptr++;
+		ptr = strchr(ptr, ' ');
+		if (!ptr) {
+			pr_err("Invalid line %d, missing state definitions\n",
+			       num);
+			ret = -EINVAL;
+			break;
+		}
+		ptr++;
+		lba_map = core_alua_allocate_lba_map(&lba_list,
+						     start_lba, end_lba);
+		if (IS_ERR(lba_map)) {
+			ret = PTR_ERR(lba_map);
+			break;
+		}
+		pg = 0;
+		while (sscanf(ptr, "%d:%c", &pg_id, &state) == 2) {
+			switch (state) {
+			case 'O':
+				alua_state = ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED;
+				break;
+			case 'A':
+				alua_state = ALUA_ACCESS_STATE_ACTIVE_NON_OPTIMIZED;
+				break;
+			case 'S':
+				alua_state = ALUA_ACCESS_STATE_STANDBY;
+				break;
+			case 'U':
+				alua_state = ALUA_ACCESS_STATE_UNAVAILABLE;
+				break;
+			default:
+				pr_err("Invalid ALUA state '%c'\n", state);
+				ret = -EINVAL;
+				goto out;
+			}
+
+			ret = core_alua_allocate_lba_map_mem(lba_map,
+							     pg_id, alua_state);
+			if (ret) {
+				pr_err("Invalid target descriptor %d:%c "
+				       "at line %d\n",
+				       pg_id, state, num);
+				break;
+			}
+			pg++;
+			ptr = strchr(ptr, ' ');
+			if (ptr)
+				ptr++;
+			else
+				break;
+		}
+		if (pg_num == -1)
+		    pg_num = pg;
+		else if (pg != pg_num) {
+			pr_err("Only %d from %d port groups definitions "
+			       "at line %d\n", pg, pg_num, num);
+			ret = -EINVAL;
+			break;
+		}
+		num++;
+	}
+out:
+	if (ret) {
+		core_alua_free_lba_map(&lba_list);
+		count = ret;
+	} else
+		core_alua_set_lba_map(dev, &lba_list,
+				      segment_size, segment_mult);
+	kfree(map_entries);
+	return count;
+}
+
+static struct target_core_configfs_attribute target_core_attr_dev_lba_map = {
+	.attr	= { .ca_owner = THIS_MODULE,
+		    .ca_name = "lba_map",
+		    .ca_mode = S_IRUGO | S_IWUSR },
+	.show	= target_core_show_dev_lba_map,
+	.store	= target_core_store_dev_lba_map,
+};
+
 static struct configfs_attribute *lio_core_dev_attrs[] = {
 	&target_core_attr_dev_info.attr,
 	&target_core_attr_dev_control.attr,
@@ -1748,6 +1930,7 @@ static struct configfs_attribute *lio_core_dev_attrs[] = {
 	&target_core_attr_dev_udev_path.attr,
 	&target_core_attr_dev_enable.attr,
 	&target_core_attr_dev_alua_lu_gp.attr,
+	&target_core_attr_dev_lba_map.attr,
 	NULL,
 };
 
@@ -2054,6 +2237,13 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_access_state(
 			" transition while TPGS_IMPLICIT_ALUA is disabled\n");
 		return -EINVAL;
 	}
+	if (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICIT_ALUA &&
+	    new_state == ALUA_ACCESS_STATE_LBA_DEPENDENT) {
+		/* LBA DEPENDENT is only allowed with implicit ALUA */
+		pr_err("Unable to process implicit configfs ALUA transition"
+		       " while explicit ALUA management is enabled\n");
+		return -EINVAL;
+	}
 
 	ret = core_alua_do_port_transition(tg_pt_gp, dev,
 					NULL, NULL, new_state, 0);
@@ -2188,7 +2378,7 @@ SE_DEV_ALUA_SUPPORT_STATE_SHOW(lba_dependent,
 			       tg_pt_gp_alua_supported_states, ALUA_LBD_SUP);
 SE_DEV_ALUA_SUPPORT_STATE_STORE(lba_dependent,
 				tg_pt_gp_alua_supported_states, ALUA_LBD_SUP);
-SE_DEV_ALUA_TG_PT_ATTR(alua_support_lba_dependent, S_IRUGO | S_IWUSR);
+SE_DEV_ALUA_TG_PT_ATTR(alua_support_lba_dependent, S_IRUGO);
 
 SE_DEV_ALUA_SUPPORT_STATE_SHOW(unavailable,
 			       tg_pt_gp_alua_supported_states, ALUA_U_SUP);
@@ -2937,7 +3127,7 @@ static int __init target_core_init_configfs(void)
 	 * and ALUA Logical Unit Group and Target Port Group infrastructure.
 	 */
 	target_cg = &subsys->su_group;
-	target_cg->default_groups = kmalloc(sizeof(struct config_group) * 2,
+	target_cg->default_groups = kmalloc(sizeof(struct config_group *) * 2,
 				GFP_KERNEL);
 	if (!target_cg->default_groups) {
 		pr_err("Unable to allocate target_cg->default_groups\n");
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index d06de84b069..65001e13367 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -918,6 +918,90 @@ int se_dev_set_emulate_3pc(struct se_device *dev, int flag)
 	return 0;
 }
 
+int se_dev_set_pi_prot_type(struct se_device *dev, int flag)
+{
+	int rc, old_prot = dev->dev_attrib.pi_prot_type;
+
+	if (flag != 0 && flag != 1 && flag != 2 && flag != 3) {
+		pr_err("Illegal value %d for pi_prot_type\n", flag);
+		return -EINVAL;
+	}
+	if (flag == 2) {
+		pr_err("DIF TYPE2 protection currently not supported\n");
+		return -ENOSYS;
+	}
+	if (dev->dev_attrib.hw_pi_prot_type) {
+		pr_warn("DIF protection enabled on underlying hardware,"
+			" ignoring\n");
+		return 0;
+	}
+	if (!dev->transport->init_prot || !dev->transport->free_prot) {
+		pr_err("DIF protection not supported by backend: %s\n",
+		       dev->transport->name);
+		return -ENOSYS;
+	}
+	if (!(dev->dev_flags & DF_CONFIGURED)) {
+		pr_err("DIF protection requires device to be configured\n");
+		return -ENODEV;
+	}
+	if (dev->export_count) {
+		pr_err("dev[%p]: Unable to change SE Device PROT type while"
+		       " export_count is %d\n", dev, dev->export_count);
+		return -EINVAL;
+	}
+
+	dev->dev_attrib.pi_prot_type = flag;
+
+	if (flag && !old_prot) {
+		rc = dev->transport->init_prot(dev);
+		if (rc) {
+			dev->dev_attrib.pi_prot_type = old_prot;
+			return rc;
+		}
+
+	} else if (!flag && old_prot) {
+		dev->transport->free_prot(dev);
+	}
+	pr_debug("dev[%p]: SE Device Protection Type: %d\n", dev, flag);
+
+	return 0;
+}
+
+int se_dev_set_pi_prot_format(struct se_device *dev, int flag)
+{
+	int rc;
+
+	if (!flag)
+		return 0;
+
+	if (flag != 1) {
+		pr_err("Illegal value %d for pi_prot_format\n", flag);
+		return -EINVAL;
+	}
+	if (!dev->transport->format_prot) {
+		pr_err("DIF protection format not supported by backend %s\n",
+		       dev->transport->name);
+		return -ENOSYS;
+	}
+	if (!(dev->dev_flags & DF_CONFIGURED)) {
+		pr_err("DIF protection format requires device to be configured\n");
+		return -ENODEV;
+	}
+	if (dev->export_count) {
+		pr_err("dev[%p]: Unable to format SE Device PROT type while"
+		       " export_count is %d\n", dev, dev->export_count);
+		return -EINVAL;
+	}
+
+	rc = dev->transport->format_prot(dev);
+	if (rc)
+		return rc;
+
+	pr_debug("dev[%p]: SE Device Protection Format complete\n", dev);
+
+	return 0;
+}
+
 int se_dev_set_enforce_pr_isids(struct se_device *dev, int flag)
 {
 	if ((flag != 0) && (flag != 1)) {
@@ -1117,23 +1201,23 @@ int se_dev_set_block_size(struct se_device *dev, u32 block_size)
 struct se_lun *core_dev_add_lun(
 	struct se_portal_group *tpg,
 	struct se_device *dev,
-	u32 lun)
+	u32 unpacked_lun)
 {
-	struct se_lun *lun_p;
+	struct se_lun *lun;
 	int rc;
 
-	lun_p = core_tpg_pre_addlun(tpg, lun);
-	if (IS_ERR(lun_p))
-		return lun_p;
+	lun = core_tpg_alloc_lun(tpg, unpacked_lun);
+	if (IS_ERR(lun))
+		return lun;
 
-	rc = core_tpg_post_addlun(tpg, lun_p,
+	rc = core_tpg_add_lun(tpg, lun,
 				TRANSPORT_LUNFLAGS_READ_WRITE, dev);
 	if (rc < 0)
 		return ERR_PTR(rc);
 
 	pr_debug("%s_TPG[%u]_LUN[%u] - Activated %s Logical Unit from"
 		" CORE HBA: %u\n", tpg->se_tpg_tfo->get_fabric_name(),
-		tpg->se_tpg_tfo->tpg_get_tag(tpg), lun_p->unpacked_lun,
+		tpg->se_tpg_tfo->tpg_get_tag(tpg), lun->unpacked_lun,
 		tpg->se_tpg_tfo->get_fabric_name(), dev->se_hba->hba_id);
 	/*
 	 * Update LUN maps for dynamically added initiators when
@@ -1154,7 +1238,7 @@ struct se_lun *core_dev_add_lun(
 		spin_unlock_irq(&tpg->acl_node_lock);
 	}
 
-	return lun_p;
+	return lun;
 }
 
 /*      core_dev_del_lun():
@@ -1420,6 +1504,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	dev->dev_link_magic = SE_DEV_LINK_MAGIC;
 	dev->se_hba = hba;
 	dev->transport = hba->transport;
+	dev->prot_length = sizeof(struct se_dif_v1_tuple);
 
 	INIT_LIST_HEAD(&dev->dev_list);
 	INIT_LIST_HEAD(&dev->dev_sep_list);
@@ -1444,6 +1529,8 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	spin_lock_init(&dev->t10_pr.aptpl_reg_lock);
 	INIT_LIST_HEAD(&dev->t10_alua.tg_pt_gps_list);
 	spin_lock_init(&dev->t10_alua.tg_pt_gps_lock);
+	INIT_LIST_HEAD(&dev->t10_alua.lba_map_list);
+	spin_lock_init(&dev->t10_alua.lba_map_lock);
 
 	dev->t10_wwn.t10_dev = dev;
 	dev->t10_alua.t10_dev = dev;
@@ -1460,6 +1547,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	dev->dev_attrib.emulate_tpws = DA_EMULATE_TPWS;
 	dev->dev_attrib.emulate_caw = DA_EMULATE_CAW;
 	dev->dev_attrib.emulate_3pc = DA_EMULATE_3PC;
+	dev->dev_attrib.pi_prot_type = TARGET_DIF_TYPE0_PROT;
 	dev->dev_attrib.enforce_pr_isids = DA_ENFORCE_PR_ISIDS;
 	dev->dev_attrib.is_nonrot = DA_IS_NONROT;
 	dev->dev_attrib.emulate_rest_reord = DA_EMULATE_REST_REORD;
@@ -1588,9 +1676,13 @@ void target_free_device(struct se_device *dev)
 	}
 
 	core_alua_free_lu_gp_mem(dev);
+	core_alua_set_lba_map(dev, NULL, 0, 0);
 	core_scsi3_free_all_registrations(dev);
 	se_release_vpd_for_dev(dev);
 
+	if (dev->transport->free_prot)
+		dev->transport->free_prot(dev);
+
 	dev->transport->free_device(dev);
 }
 
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index dae2ad6a669..7de9f0475d0 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -906,7 +906,7 @@ static struct config_group *target_fabric_make_lun(
 	lun_cg->default_groups[1] = NULL;
 
 	port_stat_grp = &lun->port_stat_grps.stat_group;
-	port_stat_grp->default_groups =  kzalloc(sizeof(struct config_group) * 3,
+	port_stat_grp->default_groups =  kzalloc(sizeof(struct config_group *) * 4,
 				GFP_KERNEL);
 	if (!port_stat_grp->default_groups) {
 		pr_err("Unable to allocate port_stat_grp->default_groups\n");
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 78241a53b55..cf991a91a8a 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -257,6 +257,72 @@ static void fd_free_device(struct se_device *dev)
 	kfree(fd_dev);
 }
 
+static int fd_do_prot_rw(struct se_cmd *cmd, struct fd_prot *fd_prot,
+			 int is_write)
+{
+	struct se_device *se_dev = cmd->se_dev;
+	struct fd_dev *dev = FD_DEV(se_dev);
+	struct file *prot_fd = dev->fd_prot_file;
+	struct scatterlist *sg;
+	loff_t pos = (cmd->t_task_lba * se_dev->prot_length);
+	unsigned char *buf;
+	u32 prot_size, len, size;
+	int rc, ret = 1, i;
+
+	prot_size = (cmd->data_length / se_dev->dev_attrib.block_size) *
+		     se_dev->prot_length;
+
+	if (!is_write) {
+		fd_prot->prot_buf = vzalloc(prot_size);
+		if (!fd_prot->prot_buf) {
+			pr_err("Unable to allocate fd_prot->prot_buf\n");
+			return -ENOMEM;
+		}
+		buf = fd_prot->prot_buf;
+
+		fd_prot->prot_sg_nents = cmd->t_prot_nents;
+		fd_prot->prot_sg = kzalloc(sizeof(struct scatterlist) *
+					   fd_prot->prot_sg_nents, GFP_KERNEL);
+		if (!fd_prot->prot_sg) {
+			pr_err("Unable to allocate fd_prot->prot_sg\n");
+			vfree(fd_prot->prot_buf);
+			return -ENOMEM;
+		}
+		size = prot_size;
+
+		for_each_sg(fd_prot->prot_sg, sg, fd_prot->prot_sg_nents, i) {
+
+			len = min_t(u32, PAGE_SIZE, size);
+			sg_set_buf(sg, buf, len);
+			size -= len;
+			buf += len;
+		}
+	}
+
+	if (is_write) {
+		rc = kernel_write(prot_fd, fd_prot->prot_buf, prot_size, pos);
+		if (rc < 0 || prot_size != rc) {
+			pr_err("kernel_write() for fd_do_prot_rw failed:"
+			       " %d\n", rc);
+			ret = -EINVAL;
+		}
+	} else {
+		rc = kernel_read(prot_fd, pos, fd_prot->prot_buf, prot_size);
+		if (rc < 0) {
+			pr_err("kernel_read() for fd_do_prot_rw failed:"
+			       " %d\n", rc);
+			ret = -EINVAL;
+		}
+	}
+
+	if (is_write || ret < 0) {
+		kfree(fd_prot->prot_sg);
+		vfree(fd_prot->prot_buf);
+	}
+
+	return ret;
+}
+
 static int fd_do_rw(struct se_cmd *cmd, struct scatterlist *sgl,
 		u32 sgl_nents, int is_write)
 {
@@ -551,6 +617,8 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	      enum dma_data_direction data_direction)
 {
 	struct se_device *dev = cmd->se_dev;
+	struct fd_prot fd_prot;
+	sense_reason_t rc;
 	int ret = 0;
 
 	/*
@@ -558,8 +626,48 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	 * physical memory addresses to struct iovec virtual memory.
 	 */
 	if (data_direction == DMA_FROM_DEVICE) {
+		memset(&fd_prot, 0, sizeof(struct fd_prot));
+
+		if (cmd->prot_type) {
+			ret = fd_do_prot_rw(cmd, &fd_prot, false);
+			if (ret < 0)
+				return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+		}
+
 		ret = fd_do_rw(cmd, sgl, sgl_nents, 0);
+
+		if (ret > 0 && cmd->prot_type) {
+			u32 sectors = cmd->data_length / dev->dev_attrib.block_size;
+
+			rc = sbc_dif_verify_read(cmd, cmd->t_task_lba, sectors,
+						 0, fd_prot.prot_sg, 0);
+			if (rc) {
+				kfree(fd_prot.prot_sg);
+				vfree(fd_prot.prot_buf);
+				return rc;
+			}
+			kfree(fd_prot.prot_sg);
+			vfree(fd_prot.prot_buf);
+		}
 	} else {
+		memset(&fd_prot, 0, sizeof(struct fd_prot));
+
+		if (cmd->prot_type) {
+			u32 sectors = cmd->data_length / dev->dev_attrib.block_size;
+
+			ret = fd_do_prot_rw(cmd, &fd_prot, false);
+			if (ret < 0)
+				return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
+			rc = sbc_dif_verify_write(cmd, cmd->t_task_lba, sectors,
+						  0, fd_prot.prot_sg, 0);
+			if (rc) {
+				kfree(fd_prot.prot_sg);
+				vfree(fd_prot.prot_buf);
+				return rc;
+			}
+		}
+
 		ret = fd_do_rw(cmd, sgl, sgl_nents, 1);
 		/*
 		 * Perform implicit vfs_fsync_range() for fd_do_writev() ops
@@ -576,10 +684,19 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 
 			vfs_fsync_range(fd_dev->fd_file, start, end, 1);
 		}
+
+		if (ret > 0 && cmd->prot_type) {
+			ret = fd_do_prot_rw(cmd, &fd_prot, true);
+			if (ret < 0)
+				return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+		}
 	}
 
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(fd_prot.prot_sg);
+		vfree(fd_prot.prot_buf);
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+	}
 
 	if (ret)
 		target_complete_cmd(cmd, SAM_STAT_GOOD);
@@ -700,6 +817,140 @@ static sector_t fd_get_blocks(struct se_device *dev)
 		       dev->dev_attrib.block_size);
 }
 
+static int fd_init_prot(struct se_device *dev)
+{
+	struct fd_dev *fd_dev = FD_DEV(dev);
+	struct file *prot_file, *file = fd_dev->fd_file;
+	struct inode *inode;
+	int ret, flags = O_RDWR | O_CREAT | O_LARGEFILE | O_DSYNC;
+	char buf[FD_MAX_DEV_PROT_NAME];
+
+	if (!file) {
+		pr_err("Unable to locate fd_dev->fd_file\n");
+		return -ENODEV;
+	}
+
+	inode = file->f_mapping->host;
+	if (S_ISBLK(inode->i_mode)) {
+		pr_err("FILEIO Protection emulation only supported on"
+		       " !S_ISBLK\n");
+		return -ENOSYS;
+	}
+
+	if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE)
+		flags &= ~O_DSYNC;
+
+	snprintf(buf, FD_MAX_DEV_PROT_NAME, "%s.protection",
+		 fd_dev->fd_dev_name);
+
+	prot_file = filp_open(buf, flags, 0600);
+	if (IS_ERR(prot_file)) {
+		pr_err("filp_open(%s) failed\n", buf);
+		ret = PTR_ERR(prot_file);
+		return ret;
+	}
+	fd_dev->fd_prot_file = prot_file;
+
+	return 0;
+}
+
+static void fd_init_format_buf(struct se_device *dev, unsigned char *buf,
+			       u32 unit_size, u32 *ref_tag, u16 app_tag,
+			       bool inc_reftag)
+{
+	unsigned char *p = buf;
+	int i;
+
+	for (i = 0; i < unit_size; i += dev->prot_length) {
+		*((u16 *)&p[0]) = 0xffff;
+		*((__be16 *)&p[2]) = cpu_to_be16(app_tag);
+		*((__be32 *)&p[4]) = cpu_to_be32(*ref_tag);
+
+		if (inc_reftag)
+			(*ref_tag)++;
+
+		p += dev->prot_length;
+	}
+}
+
+static int fd_format_prot(struct se_device *dev)
+{
+	struct fd_dev *fd_dev = FD_DEV(dev);
+	struct file *prot_fd = fd_dev->fd_prot_file;
+	sector_t prot_length, prot;
+	unsigned char *buf;
+	loff_t pos = 0;
+	u32 ref_tag = 0;
+	int unit_size = FDBD_FORMAT_UNIT_SIZE * dev->dev_attrib.block_size;
+	int rc, ret = 0, size, len;
+	bool inc_reftag = false;
+
+	if (!dev->dev_attrib.pi_prot_type) {
+		pr_err("Unable to format_prot while pi_prot_type == 0\n");
+		return -ENODEV;
+	}
+	if (!prot_fd) {
+		pr_err("Unable to locate fd_dev->fd_prot_file\n");
+		return -ENODEV;
+	}
+
+	switch (dev->dev_attrib.pi_prot_type) {
+	case TARGET_DIF_TYPE3_PROT:
+		ref_tag = 0xffffffff;
+		break;
+	case TARGET_DIF_TYPE2_PROT:
+	case TARGET_DIF_TYPE1_PROT:
+		inc_reftag = true;
+		break;
+	default:
+		break;
+	}
+
+	buf = vzalloc(unit_size);
+	if (!buf) {
+		pr_err("Unable to allocate FILEIO prot buf\n");
+		return -ENOMEM;
+	}
+
+	prot_length = (dev->transport->get_blocks(dev) + 1) * dev->prot_length;
+	size = prot_length;
+
+	pr_debug("Using FILEIO prot_length: %llu\n",
+		 (unsigned long long)prot_length);
+
+	for (prot = 0; prot < prot_length; prot += unit_size) {
+
+		fd_init_format_buf(dev, buf, unit_size, &ref_tag, 0xffff,
+				   inc_reftag);
+
+		len = min(unit_size, size);
+
+		rc = kernel_write(prot_fd, buf, len, pos);
+		if (rc != len) {
+			pr_err("vfs_write to prot file failed: %d\n", rc);
+			ret = -ENODEV;
+			goto out;
+		}
+		pos += len;
+		size -= len;
+	}
+
+out:
+	vfree(buf);
+	return ret;
+}
+
+static void fd_free_prot(struct se_device *dev)
+{
+	struct fd_dev *fd_dev = FD_DEV(dev);
+
+	if (!fd_dev->fd_prot_file)
+		return;
+
+	filp_close(fd_dev->fd_prot_file, NULL);
+	fd_dev->fd_prot_file = NULL;
+}
+
 static struct sbc_ops fd_sbc_ops = {
 	.execute_rw		= fd_execute_rw,
 	.execute_sync_cache	= fd_execute_sync_cache,
@@ -730,6 +981,9 @@ static struct se_subsystem_api fileio_template = {
 	.show_configfs_dev_params = fd_show_configfs_dev_params,
 	.get_device_type	= sbc_get_device_type,
 	.get_blocks		= fd_get_blocks,
+	.init_prot		= fd_init_prot,
+	.format_prot		= fd_format_prot,
+	.free_prot		= fd_free_prot,
 };
 
 static int __init fileio_module_init(void)
diff --git a/drivers/target/target_core_file.h b/drivers/target/target_core_file.h
index d7772c16768..182cbb29503 100644
--- a/drivers/target/target_core_file.h
+++ b/drivers/target/target_core_file.h
@@ -4,6 +4,7 @@
 #define FD_VERSION		"4.0"
 
 #define FD_MAX_DEV_NAME		256
+#define FD_MAX_DEV_PROT_NAME	FD_MAX_DEV_NAME + 16
 #define FD_DEVICE_QUEUE_DEPTH	32
 #define FD_MAX_DEVICE_QUEUE_DEPTH 128
 #define FD_BLOCKSIZE		512
@@ -18,6 +19,13 @@
 #define FBDF_HAS_PATH		0x01
 #define FBDF_HAS_SIZE		0x02
 #define FDBD_HAS_BUFFERED_IO_WCE 0x04
+#define FDBD_FORMAT_UNIT_SIZE	2048
+
+struct fd_prot {
+	unsigned char	*prot_buf;
+	struct scatterlist *prot_sg;
+	u32 prot_sg_nents;
+};
 
 struct fd_dev {
 	struct se_device dev;
@@ -32,6 +40,7 @@ struct fd_dev {
 	u32		fd_block_size;
 	unsigned long long fd_dev_size;
 	struct file	*fd_file;
+	struct file	*fd_prot_file;
 	/* FILEIO HBA device is connected to */
 	struct fd_host *fd_host;
 } ____cacheline_aligned;
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 2d29356d0c8..554d4f75a75 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -91,6 +91,7 @@ static int iblock_configure_device(struct se_device *dev)
 	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
 	struct request_queue *q;
 	struct block_device *bd = NULL;
+	struct blk_integrity *bi;
 	fmode_t mode;
 	int ret = -ENOMEM;
 
@@ -155,8 +156,40 @@ static int iblock_configure_device(struct se_device *dev)
 	if (blk_queue_nonrot(q))
 		dev->dev_attrib.is_nonrot = 1;
 
+	bi = bdev_get_integrity(bd);
+	if (bi) {
+		struct bio_set *bs = ib_dev->ibd_bio_set;
+
+		if (!strcmp(bi->name, "T10-DIF-TYPE3-IP") ||
+		    !strcmp(bi->name, "T10-DIF-TYPE1-IP")) {
+			pr_err("IBLOCK export of blk_integrity: %s not"
+			       " supported\n", bi->name);
+			ret = -ENOSYS;
+			goto out_blkdev_put;
+		}
+
+		if (!strcmp(bi->name, "T10-DIF-TYPE3-CRC")) {
+			dev->dev_attrib.pi_prot_type = TARGET_DIF_TYPE3_PROT;
+		} else if (!strcmp(bi->name, "T10-DIF-TYPE1-CRC")) {
+			dev->dev_attrib.pi_prot_type = TARGET_DIF_TYPE1_PROT;
+		}
+
+		if (dev->dev_attrib.pi_prot_type) {
+			if (bioset_integrity_create(bs, IBLOCK_BIO_POOL_SIZE) < 0) {
+				pr_err("Unable to allocate bioset for PI\n");
+				ret = -ENOMEM;
+				goto out_blkdev_put;
+			}
+			pr_debug("IBLOCK setup BIP bs->bio_integrity_pool: %p\n",
+				 bs->bio_integrity_pool);
+		}
+		dev->dev_attrib.hw_pi_prot_type = dev->dev_attrib.pi_prot_type;
+	}
+
 	return 0;
 
+out_blkdev_put:
+	blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
 out_free_bioset:
 	bioset_free(ib_dev->ibd_bio_set);
 	ib_dev->ibd_bio_set = NULL;
@@ -170,8 +203,10 @@ static void iblock_free_device(struct se_device *dev)
 
 	if (ib_dev->ibd_bd != NULL)
 		blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
-	if (ib_dev->ibd_bio_set != NULL)
+	if (ib_dev->ibd_bio_set != NULL) {
+		bioset_integrity_free(ib_dev->ibd_bio_set);
 		bioset_free(ib_dev->ibd_bio_set);
+	}
 	kfree(ib_dev);
 }
 
@@ -586,13 +621,58 @@ static ssize_t iblock_show_configfs_dev_params(struct se_device *dev, char *b)
 	return bl;
 }
 
+static int
+iblock_alloc_bip(struct se_cmd *cmd, struct bio *bio)
+{
+	struct se_device *dev = cmd->se_dev;
+	struct blk_integrity *bi;
+	struct bio_integrity_payload *bip;
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+	struct scatterlist *sg;
+	int i, rc;
+
+	bi = bdev_get_integrity(ib_dev->ibd_bd);
+	if (!bi) {
+		pr_err("Unable to locate bio_integrity\n");
+		return -ENODEV;
+	}
+
+	bip = bio_integrity_alloc(bio, GFP_NOIO, cmd->t_prot_nents);
+	if (!bip) {
+		pr_err("Unable to allocate bio_integrity_payload\n");
+		return -ENOMEM;
+	}
+
+	bip->bip_iter.bi_size = (cmd->data_length / dev->dev_attrib.block_size) *
+			 dev->prot_length;
+	bip->bip_iter.bi_sector = bio->bi_iter.bi_sector;
+
+	pr_debug("IBLOCK BIP Size: %u Sector: %llu\n", bip->bip_iter.bi_size,
+		 (unsigned long long)bip->bip_iter.bi_sector);
+
+	for_each_sg(cmd->t_prot_sg, sg, cmd->t_prot_nents, i) {
+
+		rc = bio_integrity_add_page(bio, sg_page(sg), sg->length,
+					    sg->offset);
+		if (rc != sg->length) {
+			pr_err("bio_integrity_add_page() failed; %d\n", rc);
+			return -ENOMEM;
+		}
+
+		pr_debug("Added bio integrity page: %p length: %d offset; %d\n",
+			 sg_page(sg), sg->length, sg->offset);
+	}
+
+	return 0;
+}
+
 static sense_reason_t
 iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 		  enum dma_data_direction data_direction)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct iblock_req *ibr;
-	struct bio *bio;
+	struct bio *bio, *bio_start;
 	struct bio_list list;
 	struct scatterlist *sg;
 	u32 sg_num = sgl_nents;
@@ -655,6 +735,7 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	if (!bio)
 		goto fail_free_ibr;
 
+	bio_start = bio;
 	bio_list_init(&list);
 	bio_list_add(&list, bio);
 
@@ -688,6 +769,12 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 		sg_num--;
 	}
 
+	if (cmd->prot_type) {
+		int rc = iblock_alloc_bip(cmd, bio_start);
+		if (rc)
+			goto fail_put_bios;
+	}
+
 	iblock_submit_bios(&list, rw);
 	iblock_complete_cmd(cmd);
 	return 0;
@@ -763,7 +850,7 @@ iblock_parse_cdb(struct se_cmd *cmd)
 	return sbc_parse_cdb(cmd, &iblock_sbc_ops);
 }
 
-bool iblock_get_write_cache(struct se_device *dev)
+static bool iblock_get_write_cache(struct se_device *dev)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
 	struct block_device *bd = ib_dev->ibd_bd;
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 47b63b094cd..de9cab708f4 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -35,6 +35,8 @@ int	se_dev_set_emulate_tpu(struct se_device *, int);
 int	se_dev_set_emulate_tpws(struct se_device *, int);
 int	se_dev_set_emulate_caw(struct se_device *, int);
 int	se_dev_set_emulate_3pc(struct se_device *, int);
+int	se_dev_set_pi_prot_type(struct se_device *, int);
+int	se_dev_set_pi_prot_format(struct se_device *, int);
 int	se_dev_set_enforce_pr_isids(struct se_device *, int);
 int	se_dev_set_is_nonrot(struct se_device *, int);
 int	se_dev_set_emulate_rest_reord(struct se_device *dev, int);
@@ -77,9 +79,9 @@ struct se_node_acl *__core_tpg_get_initiator_node_acl(struct se_portal_group *tp
 		const char *);
 void	core_tpg_add_node_to_devs(struct se_node_acl *, struct se_portal_group *);
 void	core_tpg_wait_for_nacl_pr_ref(struct se_node_acl *);
-struct se_lun *core_tpg_pre_addlun(struct se_portal_group *, u32);
-int	core_tpg_post_addlun(struct se_portal_group *, struct se_lun *,
-		u32, void *);
+struct se_lun *core_tpg_alloc_lun(struct se_portal_group *, u32);
+int	core_tpg_add_lun(struct se_portal_group *, struct se_lun *,
+		u32, struct se_device *);
 struct se_lun *core_tpg_pre_dellun(struct se_portal_group *, u32 unpacked_lun);
 int	core_tpg_post_dellun(struct se_portal_group *, struct se_lun *);
 
diff --git a/drivers/target/target_core_pr.h b/drivers/target/target_core_pr.h
index ed75cdd32cb..2ee2936fa0b 100644
--- a/drivers/target/target_core_pr.h
+++ b/drivers/target/target_core_pr.h
@@ -43,6 +43,11 @@
 #define PR_APTPL_MAX_IPORT_LEN			256
 #define PR_APTPL_MAX_TPORT_LEN			256
 
+/*
+ *  Function defined in target_core_spc.c
+ */
+void spc_parse_naa_6h_vendor_specific(struct se_device *, unsigned char *);
+
 extern struct kmem_cache *t10_pr_reg_cache;
 
 extern void core_pr_dump_initiator_port(struct t10_pr_registration *,
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 4ffe5f2ec0e..66a5aba5a0d 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -78,23 +78,14 @@ static void rd_detach_hba(struct se_hba *hba)
 	hba->hba_ptr = NULL;
 }
 
-/*	rd_release_device_space():
- *
- *
- */
-static void rd_release_device_space(struct rd_dev *rd_dev)
+static u32 rd_release_sgl_table(struct rd_dev *rd_dev, struct rd_dev_sg_table *sg_table,
+				 u32 sg_table_count)
 {
-	u32 i, j, page_count = 0, sg_per_table;
-	struct rd_dev_sg_table *sg_table;
 	struct page *pg;
 	struct scatterlist *sg;
+	u32 i, j, page_count = 0, sg_per_table;
 
-	if (!rd_dev->sg_table_array || !rd_dev->sg_table_count)
-		return;
-
-	sg_table = rd_dev->sg_table_array;
-
-	for (i = 0; i < rd_dev->sg_table_count; i++) {
+	for (i = 0; i < sg_table_count; i++) {
 		sg = sg_table[i].sg_table;
 		sg_per_table = sg_table[i].rd_sg_count;
 
@@ -105,16 +96,28 @@ static void rd_release_device_space(struct rd_dev *rd_dev)
 				page_count++;
 			}
 		}
-
 		kfree(sg);
 	}
 
+	kfree(sg_table);
+	return page_count;
+}
+
+static void rd_release_device_space(struct rd_dev *rd_dev)
+{
+	u32 page_count;
+
+	if (!rd_dev->sg_table_array || !rd_dev->sg_table_count)
+		return;
+
+	page_count = rd_release_sgl_table(rd_dev, rd_dev->sg_table_array,
+					  rd_dev->sg_table_count);
+
 	pr_debug("CORE_RD[%u] - Released device space for Ramdisk"
 		" Device ID: %u, pages %u in %u tables total bytes %lu\n",
 		rd_dev->rd_host->rd_host_id, rd_dev->rd_dev_id, page_count,
 		rd_dev->sg_table_count, (unsigned long)page_count * PAGE_SIZE);
 
-	kfree(sg_table);
 	rd_dev->sg_table_array = NULL;
 	rd_dev->sg_table_count = 0;
 }
@@ -124,38 +127,15 @@ static void rd_release_device_space(struct rd_dev *rd_dev)
  *
  *
  */
-static int rd_build_device_space(struct rd_dev *rd_dev)
+static int rd_allocate_sgl_table(struct rd_dev *rd_dev, struct rd_dev_sg_table *sg_table,
+				 u32 total_sg_needed, unsigned char init_payload)
 {
-	u32 i = 0, j, page_offset = 0, sg_per_table, sg_tables, total_sg_needed;
+	u32 i = 0, j, page_offset = 0, sg_per_table;
 	u32 max_sg_per_table = (RD_MAX_ALLOCATION_SIZE /
 				sizeof(struct scatterlist));
-	struct rd_dev_sg_table *sg_table;
 	struct page *pg;
 	struct scatterlist *sg;
-
-	if (rd_dev->rd_page_count <= 0) {
-		pr_err("Illegal page count: %u for Ramdisk device\n",
-			rd_dev->rd_page_count);
-		return -EINVAL;
-	}
-
-	/* Don't need backing pages for NULLIO */
-	if (rd_dev->rd_flags & RDF_NULLIO)
-		return 0;
-
-	total_sg_needed = rd_dev->rd_page_count;
-
-	sg_tables = (total_sg_needed / max_sg_per_table) + 1;
-
-	sg_table = kzalloc(sg_tables * sizeof(struct rd_dev_sg_table), GFP_KERNEL);
-	if (!sg_table) {
-		pr_err("Unable to allocate memory for Ramdisk"
-			" scatterlist tables\n");
-		return -ENOMEM;
-	}
-
-	rd_dev->sg_table_array = sg_table;
-	rd_dev->sg_table_count = sg_tables;
+	unsigned char *p;
 
 	while (total_sg_needed) {
 		sg_per_table = (total_sg_needed > max_sg_per_table) ?
@@ -186,16 +166,114 @@ static int rd_build_device_space(struct rd_dev *rd_dev)
 			}
 			sg_assign_page(&sg[j], pg);
 			sg[j].length = PAGE_SIZE;
+
+			p = kmap(pg);
+			memset(p, init_payload, PAGE_SIZE);
+			kunmap(pg);
 		}
 
 		page_offset += sg_per_table;
 		total_sg_needed -= sg_per_table;
 	}
 
+	return 0;
+}
+
+static int rd_build_device_space(struct rd_dev *rd_dev)
+{
+	struct rd_dev_sg_table *sg_table;
+	u32 sg_tables, total_sg_needed;
+	u32 max_sg_per_table = (RD_MAX_ALLOCATION_SIZE /
+				sizeof(struct scatterlist));
+	int rc;
+
+	if (rd_dev->rd_page_count <= 0) {
+		pr_err("Illegal page count: %u for Ramdisk device\n",
+		       rd_dev->rd_page_count);
+		return -EINVAL;
+	}
+
+	/* Don't need backing pages for NULLIO */
+	if (rd_dev->rd_flags & RDF_NULLIO)
+		return 0;
+
+	total_sg_needed = rd_dev->rd_page_count;
+
+	sg_tables = (total_sg_needed / max_sg_per_table) + 1;
+
+	sg_table = kzalloc(sg_tables * sizeof(struct rd_dev_sg_table), GFP_KERNEL);
+	if (!sg_table) {
+		pr_err("Unable to allocate memory for Ramdisk"
+		       " scatterlist tables\n");
+		return -ENOMEM;
+	}
+
+	rd_dev->sg_table_array = sg_table;
+	rd_dev->sg_table_count = sg_tables;
+
+	rc = rd_allocate_sgl_table(rd_dev, sg_table, total_sg_needed, 0x00);
+	if (rc)
+		return rc;
+
 	pr_debug("CORE_RD[%u] - Built Ramdisk Device ID: %u space of"
-		" %u pages in %u tables\n", rd_dev->rd_host->rd_host_id,
-		rd_dev->rd_dev_id, rd_dev->rd_page_count,
-		rd_dev->sg_table_count);
+		 " %u pages in %u tables\n", rd_dev->rd_host->rd_host_id,
+		 rd_dev->rd_dev_id, rd_dev->rd_page_count,
+		 rd_dev->sg_table_count);
+
+	return 0;
+}
+
+static void rd_release_prot_space(struct rd_dev *rd_dev)
+{
+	u32 page_count;
+
+	if (!rd_dev->sg_prot_array || !rd_dev->sg_prot_count)
+		return;
+
+	page_count = rd_release_sgl_table(rd_dev, rd_dev->sg_prot_array,
+					  rd_dev->sg_prot_count);
+
+	pr_debug("CORE_RD[%u] - Released protection space for Ramdisk"
+		 " Device ID: %u, pages %u in %u tables total bytes %lu\n",
+		 rd_dev->rd_host->rd_host_id, rd_dev->rd_dev_id, page_count,
+		 rd_dev->sg_table_count, (unsigned long)page_count * PAGE_SIZE);
+
+	rd_dev->sg_prot_array = NULL;
+	rd_dev->sg_prot_count = 0;
+}
+
+static int rd_build_prot_space(struct rd_dev *rd_dev, int prot_length)
+{
+	struct rd_dev_sg_table *sg_table;
+	u32 total_sg_needed, sg_tables;
+	u32 max_sg_per_table = (RD_MAX_ALLOCATION_SIZE /
+				sizeof(struct scatterlist));
+	int rc;
+
+	if (rd_dev->rd_flags & RDF_NULLIO)
+		return 0;
+
+	total_sg_needed = rd_dev->rd_page_count / prot_length;
+
+	sg_tables = (total_sg_needed / max_sg_per_table) + 1;
+
+	sg_table = kzalloc(sg_tables * sizeof(struct rd_dev_sg_table), GFP_KERNEL);
+	if (!sg_table) {
+		pr_err("Unable to allocate memory for Ramdisk protection"
+		       " scatterlist tables\n");
+		return -ENOMEM;
+	}
+
+	rd_dev->sg_prot_array = sg_table;
+	rd_dev->sg_prot_count = sg_tables;
+
+	rc = rd_allocate_sgl_table(rd_dev, sg_table, total_sg_needed, 0xff);
+	if (rc)
+		return rc;
+
+	pr_debug("CORE_RD[%u] - Built Ramdisk Device ID: %u prot space of"
+		 " %u pages in %u tables\n", rd_dev->rd_host->rd_host_id,
+		 rd_dev->rd_dev_id, total_sg_needed, rd_dev->sg_prot_count);
 
 	return 0;
 }
@@ -278,6 +356,26 @@ static struct rd_dev_sg_table *rd_get_sg_table(struct rd_dev *rd_dev, u32 page)
 	return NULL;
 }
 
+static struct rd_dev_sg_table *rd_get_prot_table(struct rd_dev *rd_dev, u32 page)
+{
+	struct rd_dev_sg_table *sg_table;
+	u32 i, sg_per_table = (RD_MAX_ALLOCATION_SIZE /
+				sizeof(struct scatterlist));
+
+	i = page / sg_per_table;
+	if (i < rd_dev->sg_prot_count) {
+		sg_table = &rd_dev->sg_prot_array[i];
+		if ((sg_table->page_start_offset <= page) &&
+		     (sg_table->page_end_offset >= page))
+			return sg_table;
+	}
+
+	pr_err("Unable to locate struct prot rd_dev_sg_table for page: %u\n",
+			page);
+
+	return NULL;
+}
+
 static sense_reason_t
 rd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	      enum dma_data_direction data_direction)
@@ -292,6 +390,7 @@ rd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	u32 rd_page;
 	u32 src_len;
 	u64 tmp;
+	sense_reason_t rc;
 
 	if (dev->rd_flags & RDF_NULLIO) {
 		target_complete_cmd(cmd, SAM_STAT_GOOD);
@@ -314,6 +413,28 @@ rd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 			data_direction == DMA_FROM_DEVICE ? "Read" : "Write",
 			cmd->t_task_lba, rd_size, rd_page, rd_offset);
 
+	if (cmd->prot_type && data_direction == DMA_TO_DEVICE) {
+		struct rd_dev_sg_table *prot_table;
+		struct scatterlist *prot_sg;
+		u32 sectors = cmd->data_length / se_dev->dev_attrib.block_size;
+		u32 prot_offset, prot_page;
+
+		tmp = cmd->t_task_lba * se_dev->prot_length;
+		prot_offset = do_div(tmp, PAGE_SIZE);
+		prot_page = tmp;
+
+		prot_table = rd_get_prot_table(dev, prot_page);
+		if (!prot_table)
+			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
+		prot_sg = &prot_table->sg_table[prot_page - prot_table->page_start_offset];
+
+		rc = sbc_dif_verify_write(cmd, cmd->t_task_lba, sectors, 0,
+					  prot_sg, prot_offset);
+		if (rc)
+			return rc;
+	}
+
 	src_len = PAGE_SIZE - rd_offset;
 	sg_miter_start(&m, sgl, sgl_nents,
 			data_direction == DMA_FROM_DEVICE ?
@@ -375,6 +496,28 @@ rd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	}
 	sg_miter_stop(&m);
 
+	if (cmd->prot_type && data_direction == DMA_FROM_DEVICE) {
+		struct rd_dev_sg_table *prot_table;
+		struct scatterlist *prot_sg;
+		u32 sectors = cmd->data_length / se_dev->dev_attrib.block_size;
+		u32 prot_offset, prot_page;
+
+		tmp = cmd->t_task_lba * se_dev->prot_length;
+		prot_offset = do_div(tmp, PAGE_SIZE);
+		prot_page = tmp;
+
+		prot_table = rd_get_prot_table(dev, prot_page);
+		if (!prot_table)
+			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
+		prot_sg = &prot_table->sg_table[prot_page - prot_table->page_start_offset];
+
+		rc = sbc_dif_verify_read(cmd, cmd->t_task_lba, sectors, 0,
+					 prot_sg, prot_offset);
+		if (rc)
+			return rc;
+	}
+
 	target_complete_cmd(cmd, SAM_STAT_GOOD);
 	return 0;
 }
@@ -456,6 +599,23 @@ static sector_t rd_get_blocks(struct se_device *dev)
 	return blocks_long;
 }
 
+static int rd_init_prot(struct se_device *dev)
+{
+	struct rd_dev *rd_dev = RD_DEV(dev);
+
+        if (!dev->dev_attrib.pi_prot_type)
+		return 0;
+
+	return rd_build_prot_space(rd_dev, dev->prot_length);
+}
+
+static void rd_free_prot(struct se_device *dev)
+{
+	struct rd_dev *rd_dev = RD_DEV(dev);
+
+	rd_release_prot_space(rd_dev);
+}
+
 static struct sbc_ops rd_sbc_ops = {
 	.execute_rw		= rd_execute_rw,
 };
@@ -481,6 +641,8 @@ static struct se_subsystem_api rd_mcp_template = {
 	.show_configfs_dev_params = rd_show_configfs_dev_params,
 	.get_device_type	= sbc_get_device_type,
 	.get_blocks		= rd_get_blocks,
+	.init_prot		= rd_init_prot,
+	.free_prot		= rd_free_prot,
 };
 
 int __init rd_module_init(void)
diff --git a/drivers/target/target_core_rd.h b/drivers/target/target_core_rd.h
index 1789d1e1439..cc46a6a89b3 100644
--- a/drivers/target/target_core_rd.h
+++ b/drivers/target/target_core_rd.h
@@ -33,8 +33,12 @@ struct rd_dev {
 	u32		rd_page_count;
 	/* Number of SG tables in sg_table_array */
 	u32		sg_table_count;
+	/* Number of SG tables in sg_prot_array */
+	u32		sg_prot_count;
 	/* Array of rd_dev_sg_table_t containing scatterlists */
 	struct rd_dev_sg_table *sg_table_array;
+	/* Array of rd_dev_sg_table containing protection scatterlists */
+	struct rd_dev_sg_table *sg_prot_array;
 	/* Ramdisk HBA device is connected to */
 	struct rd_host *rd_host;
 } ____cacheline_aligned;
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 52ae54e6010..fa3cae393e1 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/ratelimit.h>
+#include <linux/crc-t10dif.h>
 #include <asm/unaligned.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_tcq.h>
@@ -33,7 +34,7 @@
 
 #include "target_core_internal.h"
 #include "target_core_ua.h"
-
+#include "target_core_alua.h"
 
 static sense_reason_t
 sbc_emulate_readcapacity(struct se_cmd *cmd)
@@ -105,6 +106,11 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd)
 	buf[9] = (dev->dev_attrib.block_size >> 16) & 0xff;
 	buf[10] = (dev->dev_attrib.block_size >> 8) & 0xff;
 	buf[11] = dev->dev_attrib.block_size & 0xff;
+	/*
+	 * Set P_TYPE and PROT_EN bits for DIF support
+	 */
+	if (dev->dev_attrib.pi_prot_type)
+		buf[12] = (dev->dev_attrib.pi_prot_type - 1) << 1 | 0x1;
 
 	if (dev->transport->get_lbppbe)
 		buf[13] = dev->transport->get_lbppbe(dev) & 0x0f;
@@ -563,6 +569,44 @@ sbc_compare_and_write(struct se_cmd *cmd)
 	return TCM_NO_SENSE;
 }
 
+static bool
+sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb,
+	       u32 sectors)
+{
+	if (!cmd->t_prot_sg || !cmd->t_prot_nents)
+		return true;
+
+	switch (dev->dev_attrib.pi_prot_type) {
+	case TARGET_DIF_TYPE3_PROT:
+		if (!(cdb[1] & 0xe0))
+			return true;
+
+		cmd->reftag_seed = 0xffffffff;
+		break;
+	case TARGET_DIF_TYPE2_PROT:
+		if (cdb[1] & 0xe0)
+			return false;
+
+		cmd->reftag_seed = cmd->t_task_lba;
+		break;
+	case TARGET_DIF_TYPE1_PROT:
+		if (!(cdb[1] & 0xe0))
+			return true;
+
+		cmd->reftag_seed = cmd->t_task_lba;
+		break;
+	case TARGET_DIF_TYPE0_PROT:
+	default:
+		return true;
+	}
+
+	cmd->prot_type = dev->dev_attrib.pi_prot_type;
+	cmd->prot_length = dev->prot_length * sectors;
+	cmd->prot_handover = PROT_SEPERATED;
+
+	return true;
+}
+
 sense_reason_t
 sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 {
@@ -583,6 +627,10 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 	case READ_10:
 		sectors = transport_get_sectors_10(cdb);
 		cmd->t_task_lba = transport_lba_32(cdb);
+
+		if (!sbc_check_prot(dev, cmd, cdb, sectors))
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
+
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
 		cmd->execute_rw = ops->execute_rw;
 		cmd->execute_cmd = sbc_execute_rw;
@@ -590,6 +638,10 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 	case READ_12:
 		sectors = transport_get_sectors_12(cdb);
 		cmd->t_task_lba = transport_lba_32(cdb);
+
+		if (!sbc_check_prot(dev, cmd, cdb, sectors))
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
+
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
 		cmd->execute_rw = ops->execute_rw;
 		cmd->execute_cmd = sbc_execute_rw;
@@ -597,6 +649,10 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 	case READ_16:
 		sectors = transport_get_sectors_16(cdb);
 		cmd->t_task_lba = transport_lba_64(cdb);
+
+		if (!sbc_check_prot(dev, cmd, cdb, sectors))
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
+
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
 		cmd->execute_rw = ops->execute_rw;
 		cmd->execute_cmd = sbc_execute_rw;
@@ -612,6 +668,10 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 	case WRITE_VERIFY:
 		sectors = transport_get_sectors_10(cdb);
 		cmd->t_task_lba = transport_lba_32(cdb);
+
+		if (!sbc_check_prot(dev, cmd, cdb, sectors))
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
+
 		if (cdb[1] & 0x8)
 			cmd->se_cmd_flags |= SCF_FUA;
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
@@ -621,6 +681,10 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 	case WRITE_12:
 		sectors = transport_get_sectors_12(cdb);
 		cmd->t_task_lba = transport_lba_32(cdb);
+
+		if (!sbc_check_prot(dev, cmd, cdb, sectors))
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
+
 		if (cdb[1] & 0x8)
 			cmd->se_cmd_flags |= SCF_FUA;
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
@@ -630,6 +694,10 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 	case WRITE_16:
 		sectors = transport_get_sectors_16(cdb);
 		cmd->t_task_lba = transport_lba_64(cdb);
+
+		if (!sbc_check_prot(dev, cmd, cdb, sectors))
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
+
 		if (cdb[1] & 0x8)
 			cmd->se_cmd_flags |= SCF_FUA;
 		cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
@@ -731,6 +799,9 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 		case SAI_READ_CAPACITY_16:
 			cmd->execute_cmd = sbc_emulate_readcapacity_16;
 			break;
+		case SAI_REPORT_REFERRALS:
+			cmd->execute_cmd = target_emulate_report_referrals;
+			break;
 		default:
 			pr_err("Unsupported SA: 0x%02x\n",
 				cmd->t_task_cdb[1] & 0x1f);
@@ -959,3 +1030,182 @@ err:
 	return ret;
 }
 EXPORT_SYMBOL(sbc_execute_unmap);
+
+static sense_reason_t
+sbc_dif_v1_verify(struct se_device *dev, struct se_dif_v1_tuple *sdt,
+		  const void *p, sector_t sector, unsigned int ei_lba)
+{
+	int block_size = dev->dev_attrib.block_size;
+	__be16 csum;
+
+	csum = cpu_to_be16(crc_t10dif(p, block_size));
+
+	if (sdt->guard_tag != csum) {
+		pr_err("DIFv1 checksum failed on sector %llu guard tag 0x%04x"
+			" csum 0x%04x\n", (unsigned long long)sector,
+			be16_to_cpu(sdt->guard_tag), be16_to_cpu(csum));
+		return TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED;
+	}
+
+	if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE1_PROT &&
+	    be32_to_cpu(sdt->ref_tag) != (sector & 0xffffffff)) {
+		pr_err("DIFv1 Type 1 reference failed on sector: %llu tag: 0x%08x"
+		       " sector MSB: 0x%08x\n", (unsigned long long)sector,
+		       be32_to_cpu(sdt->ref_tag), (u32)(sector & 0xffffffff));
+		return TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED;
+	}
+
+	if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE2_PROT &&
+	    be32_to_cpu(sdt->ref_tag) != ei_lba) {
+		pr_err("DIFv1 Type 2 reference failed on sector: %llu tag: 0x%08x"
+		       " ei_lba: 0x%08x\n", (unsigned long long)sector,
+			be32_to_cpu(sdt->ref_tag), ei_lba);
+		return TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED;
+	}
+
+	return 0;
+}
+
+static void
+sbc_dif_copy_prot(struct se_cmd *cmd, unsigned int sectors, bool read,
+		  struct scatterlist *sg, int sg_off)
+{
+	struct se_device *dev = cmd->se_dev;
+	struct scatterlist *psg;
+	void *paddr, *addr;
+	unsigned int i, len, left;
+
+	left = sectors * dev->prot_length;
+
+	for_each_sg(cmd->t_prot_sg, psg, cmd->t_prot_nents, i) {
+
+		len = min(psg->length, left);
+		paddr = kmap_atomic(sg_page(psg)) + psg->offset;
+		addr = kmap_atomic(sg_page(sg)) + sg_off;
+
+		if (read)
+			memcpy(paddr, addr, len);
+		else
+			memcpy(addr, paddr, len);
+
+		left -= len;
+		kunmap_atomic(paddr);
+		kunmap_atomic(addr);
+	}
+}
+
+sense_reason_t
+sbc_dif_verify_write(struct se_cmd *cmd, sector_t start, unsigned int sectors,
+		     unsigned int ei_lba, struct scatterlist *sg, int sg_off)
+{
+	struct se_device *dev = cmd->se_dev;
+	struct se_dif_v1_tuple *sdt;
+	struct scatterlist *dsg, *psg = cmd->t_prot_sg;
+	sector_t sector = start;
+	void *daddr, *paddr;
+	int i, j, offset = 0;
+	sense_reason_t rc;
+
+	for_each_sg(cmd->t_data_sg, dsg, cmd->t_data_nents, i) {
+		daddr = kmap_atomic(sg_page(dsg)) + dsg->offset;
+		paddr = kmap_atomic(sg_page(psg)) + psg->offset;
+
+		for (j = 0; j < dsg->length; j += dev->dev_attrib.block_size) {
+
+			if (offset >= psg->length) {
+				kunmap_atomic(paddr);
+				psg = sg_next(psg);
+				paddr = kmap_atomic(sg_page(psg)) + psg->offset;
+				offset = 0;
+			}
+
+			sdt = paddr + offset;
+
+			pr_debug("DIF WRITE sector: %llu guard_tag: 0x%04x"
+				 " app_tag: 0x%04x ref_tag: %u\n",
+				 (unsigned long long)sector, sdt->guard_tag,
+				 sdt->app_tag, be32_to_cpu(sdt->ref_tag));
+
+			rc = sbc_dif_v1_verify(dev, sdt, daddr + j, sector,
+					       ei_lba);
+			if (rc) {
+				kunmap_atomic(paddr);
+				kunmap_atomic(daddr);
+				cmd->bad_sector = sector;
+				return rc;
+			}
+
+			sector++;
+			ei_lba++;
+			offset += sizeof(struct se_dif_v1_tuple);
+		}
+
+		kunmap_atomic(paddr);
+		kunmap_atomic(daddr);
+	}
+	sbc_dif_copy_prot(cmd, sectors, false, sg, sg_off);
+
+	return 0;
+}
+EXPORT_SYMBOL(sbc_dif_verify_write);
+
+sense_reason_t
+sbc_dif_verify_read(struct se_cmd *cmd, sector_t start, unsigned int sectors,
+		    unsigned int ei_lba, struct scatterlist *sg, int sg_off)
+{
+	struct se_device *dev = cmd->se_dev;
+	struct se_dif_v1_tuple *sdt;
+	struct scatterlist *dsg;
+	sector_t sector = start;
+	void *daddr, *paddr;
+	int i, j, offset = sg_off;
+	sense_reason_t rc;
+
+	for_each_sg(cmd->t_data_sg, dsg, cmd->t_data_nents, i) {
+		daddr = kmap_atomic(sg_page(dsg)) + dsg->offset;
+		paddr = kmap_atomic(sg_page(sg)) + sg->offset;
+
+		for (j = 0; j < dsg->length; j += dev->dev_attrib.block_size) {
+
+			if (offset >= sg->length) {
+				kunmap_atomic(paddr);
+				sg = sg_next(sg);
+				paddr = kmap_atomic(sg_page(sg)) + sg->offset;
+				offset = 0;
+			}
+
+			sdt = paddr + offset;
+
+			pr_debug("DIF READ sector: %llu guard_tag: 0x%04x"
+				 " app_tag: 0x%04x ref_tag: %u\n",
+				 (unsigned long long)sector, sdt->guard_tag,
+				 sdt->app_tag, be32_to_cpu(sdt->ref_tag));
+
+			if (sdt->app_tag == cpu_to_be16(0xffff)) {
+				sector++;
+				offset += sizeof(struct se_dif_v1_tuple);
+				continue;
+			}
+
+			rc = sbc_dif_v1_verify(dev, sdt, daddr + j, sector,
+					       ei_lba);
+			if (rc) {
+				kunmap_atomic(paddr);
+				kunmap_atomic(daddr);
+				cmd->bad_sector = sector;
+				return rc;
+			}
+
+			sector++;
+			ei_lba++;
+			offset += sizeof(struct se_dif_v1_tuple);
+		}
+
+		kunmap_atomic(paddr);
+		kunmap_atomic(daddr);
+	}
+	sbc_dif_copy_prot(cmd, sectors, true, sg, sg_off);
+
+	return 0;
+}
+EXPORT_SYMBOL(sbc_dif_verify_read);
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 021c3f4a4f0..43c5ca9878b 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -100,6 +100,11 @@ spc_emulate_inquiry_std(struct se_cmd *cmd, unsigned char *buf)
 	 */
 	if (dev->dev_attrib.emulate_3pc)
 		buf[5] |= 0x8;
+	/*
+	 * Set Protection (PROTECT) bit when DIF has been enabled.
+	 */
+	if (dev->dev_attrib.pi_prot_type)
+		buf[5] |= 0x1;
 
 	buf[7] = 0x2; /* CmdQue=1 */
 
@@ -267,7 +272,7 @@ check_t10_vend_desc:
 	port = lun->lun_sep;
 	if (port) {
 		struct t10_alua_lu_gp *lu_gp;
-		u32 padding, scsi_name_len;
+		u32 padding, scsi_name_len, scsi_target_len;
 		u16 lu_gp_id = 0;
 		u16 tg_pt_gp_id = 0;
 		u16 tpgt;
@@ -365,16 +370,6 @@ check_lu_gp:
 		 * section 7.5.1 Table 362
 		 */
 check_scsi_name:
-		scsi_name_len = strlen(tpg->se_tpg_tfo->tpg_get_wwn(tpg));
-		/* UTF-8 ",t,0x<16-bit TPGT>" + NULL Terminator */
-		scsi_name_len += 10;
-		/* Check for 4-byte padding */
-		padding = ((-scsi_name_len) & 3);
-		if (padding != 0)
-			scsi_name_len += padding;
-		/* Header size + Designation descriptor */
-		scsi_name_len += 4;
-
 		buf[off] =
 			(tpg->se_tpg_tfo->get_fabric_proto_ident(tpg) << 4);
 		buf[off++] |= 0x3; /* CODE SET == UTF-8 */
@@ -402,13 +397,57 @@ check_scsi_name:
 		 * shall be no larger than 256 and shall be a multiple
 		 * of four.
 		 */
+		padding = ((-scsi_name_len) & 3);
 		if (padding)
 			scsi_name_len += padding;
+		if (scsi_name_len > 256)
+			scsi_name_len = 256;
 
 		buf[off-1] = scsi_name_len;
 		off += scsi_name_len;
 		/* Header size + Designation descriptor */
 		len += (scsi_name_len + 4);
+
+		/*
+		 * Target device designator
+		 */
+		buf[off] =
+			(tpg->se_tpg_tfo->get_fabric_proto_ident(tpg) << 4);
+		buf[off++] |= 0x3; /* CODE SET == UTF-8 */
+		buf[off] = 0x80; /* Set PIV=1 */
+		/* Set ASSOCIATION == target device: 10b */
+		buf[off] |= 0x20;
+		/* DESIGNATOR TYPE == SCSI name string */
+		buf[off++] |= 0x8;
+		off += 2; /* Skip over Reserved and length */
+		/*
+		 * SCSI name string identifer containing, $FABRIC_MOD
+		 * dependent information.  For LIO-Target and iSCSI
+		 * Target Port, this means "<iSCSI name>" in
+		 * UTF-8 encoding.
+		 */
+		scsi_target_len = sprintf(&buf[off], "%s",
+					  tpg->se_tpg_tfo->tpg_get_wwn(tpg));
+		scsi_target_len += 1 /* Include  NULL terminator */;
+		/*
+		 * The null-terminated, null-padded (see 4.4.2) SCSI
+		 * NAME STRING field contains a UTF-8 format string.
+		 * The number of bytes in the SCSI NAME STRING field
+		 * (i.e., the value in the DESIGNATOR LENGTH field)
+		 * shall be no larger than 256 and shall be a multiple
+		 * of four.
+		 */
+		padding = ((-scsi_target_len) & 3);
+		if (padding)
+			scsi_target_len += padding;
+		if (scsi_name_len > 256)
+			scsi_name_len = 256;
+
+		buf[off-1] = scsi_target_len;
+		off += scsi_target_len;
+
+		/* Header size + Designation descriptor */
+		len += (scsi_target_len + 4);
 	}
 	buf[2] = ((len >> 8) & 0xff);
 	buf[3] = (len & 0xff); /* Page Length for VPD 0x83 */
@@ -436,12 +475,26 @@ spc_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf)
 	struct se_device *dev = cmd->se_dev;
 
 	buf[3] = 0x3c;
+	/*
+	 * Set GRD_CHK + REF_CHK for TYPE1 protection, or GRD_CHK
+	 * only for TYPE3 protection.
+	 */
+	if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE1_PROT)
+		buf[4] = 0x5;
+	else if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE3_PROT)
+		buf[4] = 0x4;
+
 	/* Set HEADSUP, ORDSUP, SIMPSUP */
 	buf[5] = 0x07;
 
 	/* If WriteCache emulation is enabled, set V_SUP */
 	if (spc_check_dev_wce(dev))
 		buf[6] = 0x01;
+	/* If an LBA map is present set R_SUP */
+	spin_lock(&cmd->se_dev->t10_alua.lba_map_lock);
+	if (!list_empty(&dev->t10_alua.lba_map_list))
+		buf[8] = 0x10;
+	spin_unlock(&cmd->se_dev->t10_alua.lba_map_lock);
 	return 0;
 }
 
@@ -600,6 +653,20 @@ spc_emulate_evpd_b2(struct se_cmd *cmd, unsigned char *buf)
 	return 0;
 }
 
+/* Referrals VPD page */
+static sense_reason_t
+spc_emulate_evpd_b3(struct se_cmd *cmd, unsigned char *buf)
+{
+	struct se_device *dev = cmd->se_dev;
+
+	buf[0] = dev->transport->get_device_type(dev);
+	buf[3] = 0x0c;
+	put_unaligned_be32(dev->t10_alua.lba_map_segment_size, &buf[8]);
+	put_unaligned_be32(dev->t10_alua.lba_map_segment_size, &buf[12]);
+
+	return 0;
+}
+
 static sense_reason_t
 spc_emulate_evpd_00(struct se_cmd *cmd, unsigned char *buf);
 
@@ -614,6 +681,7 @@ static struct {
 	{ .page = 0xb0, .emulate = spc_emulate_evpd_b0 },
 	{ .page = 0xb1, .emulate = spc_emulate_evpd_b1 },
 	{ .page = 0xb2, .emulate = spc_emulate_evpd_b2 },
+	{ .page = 0xb3, .emulate = spc_emulate_evpd_b3 },
 };
 
 /* supported vital product data pages */
@@ -643,11 +711,15 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 	struct se_portal_group *tpg = cmd->se_lun->lun_sep->sep_tpg;
 	unsigned char *rbuf;
 	unsigned char *cdb = cmd->t_task_cdb;
-	unsigned char buf[SE_INQUIRY_BUF];
+	unsigned char *buf;
 	sense_reason_t ret;
 	int p;
 
-	memset(buf, 0, SE_INQUIRY_BUF);
+	buf = kzalloc(SE_INQUIRY_BUF, GFP_KERNEL);
+	if (!buf) {
+		pr_err("Unable to allocate response buffer for INQUIRY\n");
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+	}
 
 	if (dev == tpg->tpg_virt_lun0.lun_se_dev)
 		buf[0] = 0x3f; /* Not connected */
@@ -680,9 +752,10 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 out:
 	rbuf = transport_kmap_data_sg(cmd);
 	if (rbuf) {
-		memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
+		memcpy(rbuf, buf, min_t(u32, SE_INQUIRY_BUF, cmd->data_length));
 		transport_kunmap_data_sg(cmd);
 	}
+	kfree(buf);
 
 	if (!ret)
 		target_complete_cmd(cmd, GOOD);
@@ -785,6 +858,19 @@ static int spc_modesense_control(struct se_device *dev, u8 pc, u8 *p)
 	 * status (see SAM-4).
 	 */
 	p[5] = (dev->dev_attrib.emulate_tas) ? 0x40 : 0x00;
+	/*
+	 * From spc4r30, section 7.5.7 Control mode page
+	 *
+	 * Application Tag Owner (ATO) bit set to one.
+	 *
+	 * If the ATO bit is set to one the device server shall not modify the
+	 * LOGICAL BLOCK APPLICATION TAG field and, depending on the protection
+	 * type, shall not modify the contents of the LOGICAL BLOCK REFERENCE
+	 * TAG field.
+	 */
+	if (dev->dev_attrib.pi_prot_type)
+		p[5] |= 0x80;
+
 	p[8] = 0xff;
 	p[9] = 0xff;
 	p[11] = 30;
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index 2a573de19a9..c036595b17c 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -656,7 +656,7 @@ static int core_tpg_setup_virtual_lun0(struct se_portal_group *se_tpg)
 	spin_lock_init(&lun->lun_sep_lock);
 	init_completion(&lun->lun_ref_comp);
 
-	ret = core_tpg_post_addlun(se_tpg, lun, lun_access, dev);
+	ret = core_tpg_add_lun(se_tpg, lun, lun_access, dev);
 	if (ret < 0)
 		return ret;
 
@@ -781,7 +781,7 @@ int core_tpg_deregister(struct se_portal_group *se_tpg)
 }
 EXPORT_SYMBOL(core_tpg_deregister);
 
-struct se_lun *core_tpg_pre_addlun(
+struct se_lun *core_tpg_alloc_lun(
 	struct se_portal_group *tpg,
 	u32 unpacked_lun)
 {
@@ -811,11 +811,11 @@ struct se_lun *core_tpg_pre_addlun(
 	return lun;
 }
 
-int core_tpg_post_addlun(
+int core_tpg_add_lun(
 	struct se_portal_group *tpg,
 	struct se_lun *lun,
 	u32 lun_access,
-	void *lun_ptr)
+	struct se_device *dev)
 {
 	int ret;
 
@@ -823,7 +823,7 @@ int core_tpg_post_addlun(
 	if (ret < 0)
 		return ret;
 
-	ret = core_dev_export(lun_ptr, tpg, lun);
+	ret = core_dev_export(dev, tpg, lun);
 	if (ret < 0) {
 		percpu_ref_cancel_init(&lun->lun_ref);
 		return ret;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 91953da0f62..c50fd9f11aa 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -62,6 +62,8 @@ struct kmem_cache *t10_alua_lu_gp_cache;
 struct kmem_cache *t10_alua_lu_gp_mem_cache;
 struct kmem_cache *t10_alua_tg_pt_gp_cache;
 struct kmem_cache *t10_alua_tg_pt_gp_mem_cache;
+struct kmem_cache *t10_alua_lba_map_cache;
+struct kmem_cache *t10_alua_lba_map_mem_cache;
 
 static void transport_complete_task_attr(struct se_cmd *cmd);
 static void transport_handle_queue_full(struct se_cmd *cmd,
@@ -128,14 +130,36 @@ int init_se_kmem_caches(void)
 				"mem_t failed\n");
 		goto out_free_tg_pt_gp_cache;
 	}
+	t10_alua_lba_map_cache = kmem_cache_create(
+			"t10_alua_lba_map_cache",
+			sizeof(struct t10_alua_lba_map),
+			__alignof__(struct t10_alua_lba_map), 0, NULL);
+	if (!t10_alua_lba_map_cache) {
+		pr_err("kmem_cache_create() for t10_alua_lba_map_"
+				"cache failed\n");
+		goto out_free_tg_pt_gp_mem_cache;
+	}
+	t10_alua_lba_map_mem_cache = kmem_cache_create(
+			"t10_alua_lba_map_mem_cache",
+			sizeof(struct t10_alua_lba_map_member),
+			__alignof__(struct t10_alua_lba_map_member), 0, NULL);
+	if (!t10_alua_lba_map_mem_cache) {
+		pr_err("kmem_cache_create() for t10_alua_lba_map_mem_"
+				"cache failed\n");
+		goto out_free_lba_map_cache;
+	}
 
 	target_completion_wq = alloc_workqueue("target_completion",
 					       WQ_MEM_RECLAIM, 0);
 	if (!target_completion_wq)
-		goto out_free_tg_pt_gp_mem_cache;
+		goto out_free_lba_map_mem_cache;
 
 	return 0;
 
+out_free_lba_map_mem_cache:
+	kmem_cache_destroy(t10_alua_lba_map_mem_cache);
+out_free_lba_map_cache:
+	kmem_cache_destroy(t10_alua_lba_map_cache);
 out_free_tg_pt_gp_mem_cache:
 	kmem_cache_destroy(t10_alua_tg_pt_gp_mem_cache);
 out_free_tg_pt_gp_cache:
@@ -164,6 +188,8 @@ void release_se_kmem_caches(void)
 	kmem_cache_destroy(t10_alua_lu_gp_mem_cache);
 	kmem_cache_destroy(t10_alua_tg_pt_gp_cache);
 	kmem_cache_destroy(t10_alua_tg_pt_gp_mem_cache);
+	kmem_cache_destroy(t10_alua_lba_map_cache);
+	kmem_cache_destroy(t10_alua_lba_map_mem_cache);
 }
 
 /* This code ensures unique mib indexes are handed out. */
@@ -568,10 +594,11 @@ static void transport_lun_remove_cmd(struct se_cmd *cmd)
 {
 	struct se_lun *lun = cmd->se_lun;
 
-	if (!lun || !cmd->lun_ref_active)
+	if (!lun)
 		return;
 
-	percpu_ref_put(&lun->lun_ref);
+	if (cmpxchg(&cmd->lun_ref_active, true, false))
+		percpu_ref_put(&lun->lun_ref);
 }
 
 void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
@@ -1284,6 +1311,8 @@ transport_generic_map_mem_to_cmd(struct se_cmd *cmd, struct scatterlist *sgl,
  * @sgl_count: scatterlist count for unidirectional mapping
  * @sgl_bidi: struct scatterlist memory for bidirectional READ mapping
  * @sgl_bidi_count: scatterlist count for bidirectional READ mapping
+ * @sgl_prot: struct scatterlist memory protection information
+ * @sgl_prot_count: scatterlist count for protection information
  *
  * Returns non zero to signal active I/O shutdown failure.  All other
  * setup exceptions will be returned as a SCSI CHECK_CONDITION response,
@@ -1296,7 +1325,8 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess
 		unsigned char *cdb, unsigned char *sense, u32 unpacked_lun,
 		u32 data_length, int task_attr, int data_dir, int flags,
 		struct scatterlist *sgl, u32 sgl_count,
-		struct scatterlist *sgl_bidi, u32 sgl_bidi_count)
+		struct scatterlist *sgl_bidi, u32 sgl_bidi_count,
+		struct scatterlist *sgl_prot, u32 sgl_prot_count)
 {
 	struct se_portal_group *se_tpg;
 	sense_reason_t rc;
@@ -1338,6 +1368,14 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess
 		target_put_sess_cmd(se_sess, se_cmd);
 		return 0;
 	}
+	/*
+	 * Save pointers for SGLs containing protection information,
+	 * if present.
+	 */
+	if (sgl_prot_count) {
+		se_cmd->t_prot_sg = sgl_prot;
+		se_cmd->t_prot_nents = sgl_prot_count;
+	}
 
 	rc = target_setup_cmd_from_cdb(se_cmd, cdb);
 	if (rc != 0) {
@@ -1380,6 +1418,7 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess
 			return 0;
 		}
 	}
+
 	/*
 	 * Check if we need to delay processing because of ALUA
 	 * Active/NonOptimized primary access state..
@@ -1419,7 +1458,7 @@ int target_submit_cmd(struct se_cmd *se_cmd, struct se_session *se_sess,
 {
 	return target_submit_cmd_map_sgls(se_cmd, se_sess, cdb, sense,
 			unpacked_lun, data_length, task_attr, data_dir,
-			flags, NULL, 0, NULL, 0);
+			flags, NULL, 0, NULL, 0, NULL, 0);
 }
 EXPORT_SYMBOL(target_submit_cmd);
 
@@ -2455,6 +2494,19 @@ static int transport_get_sense_codes(
 	return 0;
 }
 
+static
+void transport_err_sector_info(unsigned char *buffer, sector_t bad_sector)
+{
+	/* Place failed LBA in sense data information descriptor 0. */
+	buffer[SPC_ADD_SENSE_LEN_OFFSET] = 0xc;
+	buffer[SPC_DESC_TYPE_OFFSET] = 0; /* Information */
+	buffer[SPC_ADDITIONAL_DESC_LEN_OFFSET] = 0xa;
+	buffer[SPC_VALIDITY_OFFSET] = 0x80;
+
+	/* Descriptor Information: failing sector */
+	put_unaligned_be64(bad_sector, &buffer[12]);
+}
+
 int
 transport_send_check_condition_and_sense(struct se_cmd *cmd,
 		sense_reason_t reason, int from_transport)
@@ -2648,6 +2700,39 @@ transport_send_check_condition_and_sense(struct se_cmd *cmd,
 		buffer[SPC_ASC_KEY_OFFSET] = 0x1d;
 		buffer[SPC_ASCQ_KEY_OFFSET] = 0x00;
 		break;
+	case TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED:
+		/* CURRENT ERROR */
+		buffer[0] = 0x70;
+		buffer[SPC_ADD_SENSE_LEN_OFFSET] = 10;
+		/* ILLEGAL REQUEST */
+		buffer[SPC_SENSE_KEY_OFFSET] = ILLEGAL_REQUEST;
+		/* LOGICAL BLOCK GUARD CHECK FAILED */
+		buffer[SPC_ASC_KEY_OFFSET] = 0x10;
+		buffer[SPC_ASCQ_KEY_OFFSET] = 0x01;
+		transport_err_sector_info(buffer, cmd->bad_sector);
+		break;
+	case TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED:
+		/* CURRENT ERROR */
+		buffer[0] = 0x70;
+		buffer[SPC_ADD_SENSE_LEN_OFFSET] = 10;
+		/* ILLEGAL REQUEST */
+		buffer[SPC_SENSE_KEY_OFFSET] = ILLEGAL_REQUEST;
+		/* LOGICAL BLOCK APPLICATION TAG CHECK FAILED */
+		buffer[SPC_ASC_KEY_OFFSET] = 0x10;
+		buffer[SPC_ASCQ_KEY_OFFSET] = 0x02;
+		transport_err_sector_info(buffer, cmd->bad_sector);
+		break;
+	case TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED:
+		/* CURRENT ERROR */
+		buffer[0] = 0x70;
+		buffer[SPC_ADD_SENSE_LEN_OFFSET] = 10;
+		/* ILLEGAL REQUEST */
+		buffer[SPC_SENSE_KEY_OFFSET] = ILLEGAL_REQUEST;
+		/* LOGICAL BLOCK REFERENCE TAG CHECK FAILED */
+		buffer[SPC_ASC_KEY_OFFSET] = 0x10;
+		buffer[SPC_ASCQ_KEY_OFFSET] = 0x03;
+		transport_err_sector_info(buffer, cmd->bad_sector);
+		break;
 	case TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE:
 	default:
 		/* CURRENT ERROR */
diff --git a/drivers/target/target_core_ua.c b/drivers/target/target_core_ua.c
index b04467e7547..505519b10cb 100644
--- a/drivers/target/target_core_ua.c
+++ b/drivers/target/target_core_ua.c
@@ -98,7 +98,6 @@ int core_scsi3_ua_allocate(
 		pr_err("Unable to allocate struct se_ua\n");
 		return -ENOMEM;
 	}
-	INIT_LIST_HEAD(&ua->ua_dev_list);
 	INIT_LIST_HEAD(&ua->ua_nacl_list);
 
 	ua->ua_nacl = nacl;
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 6b88a9958f6..669c536fd95 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -40,10 +40,6 @@
 
 static struct workqueue_struct *xcopy_wq = NULL;
 /*
- * From target_core_spc.c
- */
-extern void spc_parse_naa_6h_vendor_specific(struct se_device *, unsigned char *);
-/*
  * From target_core_device.c
  */
 extern struct mutex g_device_mutex;
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index 479ec5621a4..8b2c1aaf81d 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -438,7 +438,7 @@ static void ft_recv_cmd(struct ft_sess *sess, struct fc_frame *fp)
 	struct se_session *se_sess = sess->se_sess;
 	int tag;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_ATOMIC);
+	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
 	if (tag < 0)
 		goto busy;
 
diff --git a/drivers/target/tcm_fc/tfc_conf.c b/drivers/target/tcm_fc/tfc_conf.c
index c6932fb53a8..e879da81ad9 100644
--- a/drivers/target/tcm_fc/tfc_conf.c
+++ b/drivers/target/tcm_fc/tfc_conf.c
@@ -267,7 +267,7 @@ struct ft_node_acl *ft_acl_get(struct ft_tpg *tpg, struct fc_rport_priv *rdata)
 	return found;
 }
 
-struct se_node_acl *ft_tpg_alloc_fabric_acl(struct se_portal_group *se_tpg)
+static struct se_node_acl *ft_tpg_alloc_fabric_acl(struct se_portal_group *se_tpg)
 {
 	struct ft_node_acl *acl;
 
@@ -552,7 +552,7 @@ static struct target_core_fabric_ops ft_fabric_ops = {
 	.fabric_drop_nodeacl =		&ft_del_acl,
 };
 
-int ft_register_configfs(void)
+static int ft_register_configfs(void)
 {
 	struct target_fabric_configfs *fabric;
 	int ret;
@@ -599,7 +599,7 @@ int ft_register_configfs(void)
 	return 0;
 }
 
-void ft_deregister_configfs(void)
+static void ft_deregister_configfs(void)
 {
 	if (!ft_configfs)
 		return;
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 1e4c75c5b36..0a025b8e2a1 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -728,7 +728,7 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq,
 	}
 	se_sess = tv_nexus->tvn_se_sess;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_ATOMIC);
+	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
 	if (tag < 0) {
 		pr_err("Unable to obtain tag for tcm_vhost_cmd\n");
 		return ERR_PTR(-ENOMEM);
@@ -889,7 +889,7 @@ static void tcm_vhost_submission_work(struct work_struct *work)
 			cmd->tvc_lun, cmd->tvc_exp_data_len,
 			cmd->tvc_task_attr, cmd->tvc_data_direction,
 			TARGET_SCF_ACK_KREF, sg_ptr, cmd->tvc_sgl_count,
-			sg_bidi_ptr, sg_no_bidi);
+			sg_bidi_ptr, sg_no_bidi, NULL, 0);
 	if (rc < 0) {
 		transport_send_check_condition_and_sense(se_cmd,
 				TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE, 0);
diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h
index 1900bd0fa63..f5cfdd6a553 100644
--- a/include/linux/percpu_ida.h
+++ b/include/linux/percpu_ida.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 #include <linux/spinlock_types.h>
 #include <linux/wait.h>
 #include <linux/cpumask.h>
@@ -61,7 +62,7 @@ struct percpu_ida {
 /* Max size of percpu freelist, */
 #define IDA_DEFAULT_PCPU_SIZE	((IDA_DEFAULT_PCPU_BATCH_MOVE * 3) / 2)
 
-int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp);
+int percpu_ida_alloc(struct percpu_ida *pool, int state);
 void percpu_ida_free(struct percpu_ida *pool, unsigned tag);
 
 void percpu_ida_destroy(struct percpu_ida *pool);
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index 66d42edfb3f..0a4edfe8af5 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -155,6 +155,7 @@ enum scsi_timeouts {
 /* values for service action in */
 #define	SAI_READ_CAPACITY_16  0x10
 #define SAI_GET_LBA_STATUS    0x12
+#define SAI_REPORT_REFERRALS  0x13
 /* values for VARIABLE_LENGTH_CMD service action codes
  * see spc4r17 Section D.3.5, table D.7 and D.8 */
 #define VLC_SA_RECEIVE_CREDENTIAL 0x1800
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index a12589c4ee9..ae5a1711196 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -94,7 +94,7 @@ extern int iscsit_tmr_post_handler(struct iscsi_cmd *, struct iscsi_conn *);
 /*
  * From iscsi_target_util.c
  */
-extern struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *, gfp_t);
+extern struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *, int);
 extern int iscsit_sequence_cmd(struct iscsi_conn *, struct iscsi_cmd *,
 			       unsigned char *, __be32);
 extern void iscsit_release_cmd(struct iscsi_cmd *);
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 39e0114d70c..7020e33e742 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -41,6 +41,9 @@ struct se_subsystem_api {
 	unsigned int (*get_io_opt)(struct se_device *);
 	unsigned char *(*get_sense_buffer)(struct se_cmd *);
 	bool (*get_write_cache)(struct se_device *);
+	int (*init_prot)(struct se_device *);
+	int (*format_prot)(struct se_device *);
+	void (*free_prot)(struct se_device *);
 };
 
 struct sbc_ops {
@@ -70,6 +73,10 @@ sense_reason_t sbc_execute_unmap(struct se_cmd *cmd,
 	sense_reason_t (*do_unmap_fn)(struct se_cmd *cmd, void *priv,
 				      sector_t lba, sector_t nolb),
 	void *priv);
+sense_reason_t	sbc_dif_verify_write(struct se_cmd *, sector_t, unsigned int,
+				     unsigned int, struct scatterlist *, int);
+sense_reason_t	sbc_dif_verify_read(struct se_cmd *, sector_t, unsigned int,
+				    unsigned int, struct scatterlist *, int);
 
 void	transport_set_vpd_proto_id(struct t10_vpd *, unsigned char *);
 int	transport_set_vpd_assoc(struct t10_vpd *, unsigned char *);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 321301c0a64..c9c791209cd 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -37,6 +37,9 @@
 /* Used by transport_send_check_condition_and_sense() */
 #define SPC_SENSE_KEY_OFFSET			2
 #define SPC_ADD_SENSE_LEN_OFFSET		7
+#define SPC_DESC_TYPE_OFFSET			8
+#define SPC_ADDITIONAL_DESC_LEN_OFFSET		9
+#define SPC_VALIDITY_OFFSET			10
 #define SPC_ASC_KEY_OFFSET			12
 #define SPC_ASCQ_KEY_OFFSET			13
 #define TRANSPORT_IQN_LEN			224
@@ -112,7 +115,7 @@
 /* Queue Algorithm Modifier default for restricted reordering in control mode page */
 #define DA_EMULATE_REST_REORD			0
 
-#define SE_INQUIRY_BUF				512
+#define SE_INQUIRY_BUF				1024
 #define SE_MODE_PAGE_BUF			512
 #define SE_SENSE_BUF				96
 
@@ -205,6 +208,9 @@ enum tcm_sense_reason_table {
 	TCM_OUT_OF_RESOURCES			= R(0x12),
 	TCM_PARAMETER_LIST_LENGTH_ERROR		= R(0x13),
 	TCM_MISCOMPARE_VERIFY			= R(0x14),
+	TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED	= R(0x15),
+	TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED	= R(0x16),
+	TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED	= R(0x17),
 #undef R
 };
 
@@ -247,10 +253,28 @@ typedef enum {
 
 struct se_cmd;
 
+struct t10_alua_lba_map_member {
+	struct list_head lba_map_mem_list;
+	int lba_map_mem_alua_state;
+	int lba_map_mem_alua_pg_id;
+};
+
+struct t10_alua_lba_map {
+	u64 lba_map_first_lba;
+	u64 lba_map_last_lba;
+	struct list_head lba_map_list;
+	struct list_head lba_map_mem_list;
+};
+
 struct t10_alua {
 	/* ALUA Target Port Group ID */
 	u16	alua_tg_pt_gps_counter;
 	u32	alua_tg_pt_gps_count;
+	/* Referrals support */
+	spinlock_t lba_map_lock;
+	u32     lba_map_segment_size;
+	u32     lba_map_segment_multiplier;
+	struct list_head lba_map_list;
 	spinlock_t tg_pt_gps_lock;
 	struct se_device *t10_dev;
 	/* Used for default ALUA Target Port Group */
@@ -284,6 +308,8 @@ struct t10_alua_tg_pt_gp {
 	u16	tg_pt_gp_id;
 	int	tg_pt_gp_valid_id;
 	int	tg_pt_gp_alua_supported_states;
+	int	tg_pt_gp_alua_pending_state;
+	int	tg_pt_gp_alua_previous_state;
 	int	tg_pt_gp_alua_access_status;
 	int	tg_pt_gp_alua_access_type;
 	int	tg_pt_gp_nonop_delay_msecs;
@@ -291,9 +317,6 @@ struct t10_alua_tg_pt_gp {
 	int	tg_pt_gp_implicit_trans_secs;
 	int	tg_pt_gp_pref;
 	int	tg_pt_gp_write_metadata;
-	/* Used by struct t10_alua_tg_pt_gp->tg_pt_gp_md_buf_len */
-#define ALUA_MD_BUF_LEN				1024
-	u32	tg_pt_gp_md_buf_len;
 	u32	tg_pt_gp_members;
 	atomic_t tg_pt_gp_alua_access_state;
 	atomic_t tg_pt_gp_ref_cnt;
@@ -303,6 +326,10 @@ struct t10_alua_tg_pt_gp {
 	struct config_group tg_pt_gp_group;
 	struct list_head tg_pt_gp_list;
 	struct list_head tg_pt_gp_mem_list;
+	struct se_port *tg_pt_gp_alua_port;
+	struct se_node_acl *tg_pt_gp_alua_nacl;
+	struct delayed_work tg_pt_gp_transition_work;
+	struct completion *tg_pt_gp_transition_complete;
 };
 
 struct t10_alua_tg_pt_gp_member {
@@ -414,6 +441,34 @@ struct se_tmr_req {
 	struct list_head	tmr_list;
 };
 
+enum target_prot_op {
+	TARGET_PROT_NORMAL = 0,
+	TARGET_PROT_DIN_INSERT,
+	TARGET_PROT_DOUT_INSERT,
+	TARGET_PROT_DIN_STRIP,
+	TARGET_PROT_DOUT_STRIP,
+	TARGET_PROT_DIN_PASS,
+	TARGET_PROT_DOUT_PASS,
+};
+
+enum target_prot_ho {
+	PROT_SEPERATED,
+	PROT_INTERLEAVED,
+};
+
+enum target_prot_type {
+	TARGET_DIF_TYPE0_PROT,
+	TARGET_DIF_TYPE1_PROT,
+	TARGET_DIF_TYPE2_PROT,
+	TARGET_DIF_TYPE3_PROT,
+};
+
+struct se_dif_v1_tuple {
+	__be16			guard_tag;
+	__be16			app_tag;
+	__be32			ref_tag;
+};
+
 struct se_cmd {
 	/* SAM response code being sent to initiator */
 	u8			scsi_status;
@@ -497,14 +552,24 @@ struct se_cmd {
 	void			*priv;
 
 	/* Used for lun->lun_ref counting */
-	bool			lun_ref_active;
+	int			lun_ref_active;
+
+	/* DIF related members */
+	enum target_prot_op	prot_op;
+	enum target_prot_type	prot_type;
+	u32			prot_length;
+	u32			reftag_seed;
+	struct scatterlist	*t_prot_sg;
+	unsigned int		t_prot_nents;
+	enum target_prot_ho	prot_handover;
+	sense_reason_t		pi_err;
+	sector_t		bad_sector;
 };
 
 struct se_ua {
 	u8			ua_asc;
 	u8			ua_ascq;
 	struct se_node_acl	*ua_nacl;
-	struct list_head	ua_dev_list;
 	struct list_head	ua_nacl_list;
 };
 
@@ -605,6 +670,9 @@ struct se_dev_attrib {
 	int		emulate_tpws;
 	int		emulate_caw;
 	int		emulate_3pc;
+	int		pi_prot_format;
+	enum target_prot_type pi_prot_type;
+	enum target_prot_type hw_pi_prot_type;
 	int		enforce_pr_isids;
 	int		is_nonrot;
 	int		emulate_rest_reord;
@@ -736,6 +804,8 @@ struct se_device {
 	/* Linked list for struct se_hba struct se_device list */
 	struct list_head	dev_list;
 	struct se_lun		xcopy_lun;
+	/* Protection Information */
+	int			prot_length;
 };
 
 struct se_hba {
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 4cf4fda404a..0218d689b3d 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -105,7 +105,8 @@ sense_reason_t transport_lookup_cmd_lun(struct se_cmd *, u32);
 sense_reason_t target_setup_cmd_from_cdb(struct se_cmd *, unsigned char *);
 int	target_submit_cmd_map_sgls(struct se_cmd *, struct se_session *,
 		unsigned char *, unsigned char *, u32, u32, int, int, int,
-		struct scatterlist *, u32, struct scatterlist *, u32);
+		struct scatterlist *, u32, struct scatterlist *, u32,
+		struct scatterlist *, u32);
 int	target_submit_cmd(struct se_cmd *, struct se_session *, unsigned char *,
 		unsigned char *, u32, u32, int, int, int);
 int	target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess,
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index 9d054bf91d0..7be235f1a70 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -132,22 +132,22 @@ static inline unsigned alloc_local_tag(struct percpu_ida_cpu *tags)
 /**
  * percpu_ida_alloc - allocate a tag
  * @pool: pool to allocate from
- * @gfp: gfp flags
+ * @state: task state for prepare_to_wait
  *
  * Returns a tag - an integer in the range [0..nr_tags) (passed to
  * tag_pool_init()), or otherwise -ENOSPC on allocation failure.
  *
  * Safe to be called from interrupt context (assuming it isn't passed
- * __GFP_WAIT, of course).
+ * TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, of course).
  *
  * @gfp indicates whether or not to wait until a free id is available (it's not
  * used for internal memory allocations); thus if passed __GFP_WAIT we may sleep
  * however long it takes until another thread frees an id (same semantics as a
  * mempool).
  *
- * Will not fail if passed __GFP_WAIT.
+ * Will not fail if passed TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE.
  */
-int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp)
+int percpu_ida_alloc(struct percpu_ida *pool, int state)
 {
 	DEFINE_WAIT(wait);
 	struct percpu_ida_cpu *tags;
@@ -174,7 +174,8 @@ int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp)
 		 *
 		 * global lock held and irqs disabled, don't need percpu lock
 		 */
-		prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
+		if (state != TASK_RUNNING)
+			prepare_to_wait(&pool->wait, &wait, state);
 
 		if (!tags->nr_free)
 			alloc_global_tags(pool, tags);
@@ -191,16 +192,22 @@ int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp)
 		spin_unlock(&pool->lock);
 		local_irq_restore(flags);
 
-		if (tag >= 0 || !(gfp & __GFP_WAIT))
+		if (tag >= 0 || state == TASK_RUNNING)
 			break;
 
+		if (signal_pending_state(state, current)) {
+			tag = -ERESTARTSYS;
+			break;
+		}
+
 		schedule();
 
 		local_irq_save(flags);
 		tags = this_cpu_ptr(pool->tag_cpu);
 	}
+	if (state != TASK_RUNNING)
+		finish_wait(&pool->wait, &wait);
 
-	finish_wait(&pool->wait, &wait);
 	return tag;
 }
 EXPORT_SYMBOL_GPL(percpu_ida_alloc);