Merge branch 'fixes' into misc

Somewhat nasty merge due to conflicts between "33b28357dd00 scsi:
qla2xxx: Fix Async GPN_FT for FCP and FC-NVMe scan" and "2b5b96473efc
scsi: qla2xxx: Fix FC-NVMe LUN discovery"

Merge is non-trivial and has been verified by Qlogic (Cavium)

Signed-off-by: James E.J. Bottomley <jejb@linux.vnet.ibm.com>

43 files changed, 424 insertions, 391 deletions

diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c
index 8d12017b9893..4470630dd545 100644
--- a/drivers/message/fusion/mptctl.c
+++ b/drivers/message/fusion/mptctl.c
@@ -2687,6 +2687,8 @@ mptctl_hp_targetinfo(unsigned long arg)
 				__FILE__, __LINE__, iocnum);
 		return -ENODEV;
 	}
+	if (karg.hdr.id >= MPT_MAX_FC_DEVICES)
+		return -EINVAL;
 	dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_hp_targetinfo called.\n",
 	    ioc->name));
 
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index d5135efbf9cd..e29f9b8fd66d 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -180,7 +180,6 @@ ncr53c8xx-flags-$(CONFIG_SCSI_ZALON) \
 CFLAGS_ncr53c8xx.o	:= $(ncr53c8xx-flags-y) $(ncr53c8xx-flags-m)
 zalon7xx-objs	:= zalon.o ncr53c8xx.o
 NCR_Q720_mod-objs	:= NCR_Q720.o ncr53c8xx.o
-oktagon_esp_mod-objs	:= oktagon_esp.o oktagon_io.o
 
 # Files generated that shall be removed upon make clean
 clean-files :=	53c700_d.h 53c700_u.h
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index b3b931ab77eb..2664ea0df35f 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -1693,8 +1693,10 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	 *	Map in the registers from the adapter.
 	 */
 	aac->base_size = AAC_MIN_FOOTPRINT_SIZE;
-	if ((*aac_drivers[index].init)(aac))
+	if ((*aac_drivers[index].init)(aac)) {
+		error = -ENODEV;
 		goto out_unmap;
+	}
 
 	if (aac->sync_mode) {
 		if (aac_sync_mode)
diff --git a/drivers/scsi/aic7xxx/aiclib.c b/drivers/scsi/aic7xxx/aiclib.c
deleted file mode 100644
index 828ae3d9a510..000000000000
--- a/drivers/scsi/aic7xxx/aiclib.c
+++ /dev/null
@@ -1,34 +0,0 @@
-/*
- * Implementation of Utility functions for all SCSI device types.
- *
- * Copyright (c) 1997, 1998, 1999 Justin T. Gibbs.
- * Copyright (c) 1997, 1998 Kenneth D. Merry.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions, and the following disclaimer,
- *    without modification, immediately at the beginning of the file.
- * 2. The name of the author may not be used to endorse or promote products
- *    derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR
- * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- *
- * $FreeBSD: src/sys/cam/scsi/scsi_all.c,v 1.38 2002/09/23 04:56:35 mjacob Exp $
- * $Id$
- */
-
-#include "aiclib.h"
-
diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c
index 8e2f767147cb..5a645b8b9af1 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_io.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_io.c
@@ -1889,6 +1889,7 @@ void bnx2fc_process_scsi_cmd_compl(struct bnx2fc_cmd *io_req,
 		/* we will not receive ABTS response for this IO */
 		BNX2FC_IO_DBG(io_req, "Timer context finished processing "
 			   "this scsi cmd\n");
+		return;
 	}
 
 	/* Cancel the timeout_work, as we received IO completion */
diff --git a/drivers/scsi/csiostor/csio_lnode.c b/drivers/scsi/csiostor/csio_lnode.c
index 1c53179523b8..cc5611efc7a9 100644
--- a/drivers/scsi/csiostor/csio_lnode.c
+++ b/drivers/scsi/csiostor/csio_lnode.c
@@ -114,7 +114,7 @@ static enum csio_ln_ev fwevt_to_lnevt[] = {
 static struct csio_lnode *
 csio_ln_lookup_by_portid(struct csio_hw *hw, uint8_t portid)
 {
-	struct csio_lnode *ln = hw->rln;
+	struct csio_lnode *ln;
 	struct list_head *tmp;
 
 	/* Match siblings lnode with portid */
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index acd7fb356f01..12dc7100bb4c 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -876,6 +876,11 @@ static void alua_rtpg_work(struct work_struct *work)
 
 /**
  * alua_rtpg_queue() - cause RTPG to be submitted asynchronously
+ * @pg: ALUA port group associated with @sdev.
+ * @sdev: SCSI device for which to submit an RTPG.
+ * @qdata: Information about the callback to invoke after the RTPG.
+ * @force: Whether or not to submit an RTPG if a work item that will submit an
+ *         RTPG already has been scheduled.
  *
  * Returns true if and only if alua_rtpg_work() will be called asynchronously.
  * That function is responsible for calling @qdata->fn().
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index ffd1030b6c91..7649d63a1b8d 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -333,8 +333,6 @@ static void scsi_host_dev_release(struct device *dev)
 	if (shost->work_q)
 		destroy_workqueue(shost->work_q);
 
-	destroy_rcu_head(&shost->rcu);
-
 	if (shost->shost_state == SHOST_CREATED) {
 		/*
 		 * Free the shost_dev device name here if scsi_host_alloc()
@@ -403,7 +401,6 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	INIT_LIST_HEAD(&shost->starved_list);
 	init_waitqueue_head(&shost->host_wait);
 	mutex_init(&shost->scan_mutex);
-	init_rcu_head(&shost->rcu);
 
 	index = ida_simple_get(&host_index_ida, 0, 0, GFP_KERNEL);
 	if (index < 0)
@@ -476,6 +473,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 		shost->dma_boundary = 0xffffffff;
 
 	shost->use_blk_mq = scsi_use_blk_mq;
+	shost->use_blk_mq = scsi_use_blk_mq || shost->hostt->force_blk_mq;
 
 	device_initialize(&shost->shost_gendev);
 	dev_set_name(&shost->shost_gendev, "host%d", shost->host_no);
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 5293e6827ce5..3a9eca163db8 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -1045,11 +1045,7 @@ static void set_performant_mode(struct ctlr_info *h, struct CommandList *c,
 		c->busaddr |= 1 | (h->blockFetchTable[c->Header.SGList] << 1);
 		if (unlikely(!h->msix_vectors))
 			return;
-		if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
-			c->Header.ReplyQueue =
-				raw_smp_processor_id() % h->nreply_queues;
-		else
-			c->Header.ReplyQueue = reply_queue % h->nreply_queues;
+		c->Header.ReplyQueue = reply_queue;
 	}
 }
 
@@ -1063,10 +1059,7 @@ static void set_ioaccel1_performant_mode(struct ctlr_info *h,
 	 * Tell the controller to post the reply to the queue for this
 	 * processor.  This seems to give the best I/O throughput.
 	 */
-	if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
-		cp->ReplyQueue = smp_processor_id() % h->nreply_queues;
-	else
-		cp->ReplyQueue = reply_queue % h->nreply_queues;
+	cp->ReplyQueue = reply_queue;
 	/*
 	 * Set the bits in the address sent down to include:
 	 *  - performant mode bit (bit 0)
@@ -1087,10 +1080,7 @@ static void set_ioaccel2_tmf_performant_mode(struct ctlr_info *h,
 	/* Tell the controller to post the reply to the queue for this
 	 * processor.  This seems to give the best I/O throughput.
 	 */
-	if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
-		cp->reply_queue = smp_processor_id() % h->nreply_queues;
-	else
-		cp->reply_queue = reply_queue % h->nreply_queues;
+	cp->reply_queue = reply_queue;
 	/* Set the bits in the address sent down to include:
 	 *  - performant mode bit not used in ioaccel mode 2
 	 *  - pull count (bits 0-3)
@@ -1109,10 +1099,7 @@ static void set_ioaccel2_performant_mode(struct ctlr_info *h,
 	 * Tell the controller to post the reply to the queue for this
 	 * processor.  This seems to give the best I/O throughput.
 	 */
-	if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
-		cp->reply_queue = smp_processor_id() % h->nreply_queues;
-	else
-		cp->reply_queue = reply_queue % h->nreply_queues;
+	cp->reply_queue = reply_queue;
 	/*
 	 * Set the bits in the address sent down to include:
 	 *  - performant mode bit not used in ioaccel mode 2
@@ -1157,6 +1144,8 @@ static void __enqueue_cmd_and_start_io(struct ctlr_info *h,
 {
 	dial_down_lockup_detection_during_fw_flash(h, c);
 	atomic_inc(&h->commands_outstanding);
+
+	reply_queue = h->reply_map[raw_smp_processor_id()];
 	switch (c->cmd_type) {
 	case CMD_IOACCEL1:
 		set_ioaccel1_performant_mode(h, c, reply_queue);
@@ -7376,6 +7365,26 @@ static void hpsa_disable_interrupt_mode(struct ctlr_info *h)
 	h->msix_vectors = 0;
 }
 
+static void hpsa_setup_reply_map(struct ctlr_info *h)
+{
+	const struct cpumask *mask;
+	unsigned int queue, cpu;
+
+	for (queue = 0; queue < h->msix_vectors; queue++) {
+		mask = pci_irq_get_affinity(h->pdev, queue);
+		if (!mask)
+			goto fallback;
+
+		for_each_cpu(cpu, mask)
+			h->reply_map[cpu] = queue;
+	}
+	return;
+
+fallback:
+	for_each_possible_cpu(cpu)
+		h->reply_map[cpu] = 0;
+}
+
 /* If MSI/MSI-X is supported by the kernel we will try to enable it on
  * controllers that are capable. If not, we use legacy INTx mode.
  */
@@ -7771,6 +7780,10 @@ static int hpsa_pci_init(struct ctlr_info *h)
 	err = hpsa_interrupt_mode(h);
 	if (err)
 		goto clean1;
+
+	/* setup mapping between CPU and reply queue */
+	hpsa_setup_reply_map(h);
+
 	err = hpsa_pci_find_memory_BAR(h->pdev, &h->paddr);
 	if (err)
 		goto clean2;	/* intmode+region, pci */
@@ -8480,6 +8493,28 @@ static struct workqueue_struct *hpsa_create_controller_wq(struct ctlr_info *h,
 	return wq;
 }
 
+static void hpda_free_ctlr_info(struct ctlr_info *h)
+{
+	kfree(h->reply_map);
+	kfree(h);
+}
+
+static struct ctlr_info *hpda_alloc_ctlr_info(void)
+{
+	struct ctlr_info *h;
+
+	h = kzalloc(sizeof(*h), GFP_KERNEL);
+	if (!h)
+		return NULL;
+
+	h->reply_map = kzalloc(sizeof(*h->reply_map) * nr_cpu_ids, GFP_KERNEL);
+	if (!h->reply_map) {
+		kfree(h);
+		return NULL;
+	}
+	return h;
+}
+
 static int hpsa_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int dac, rc;
@@ -8517,7 +8552,7 @@ reinit_after_soft_reset:
 	 * the driver.  See comments in hpsa.h for more info.
 	 */
 	BUILD_BUG_ON(sizeof(struct CommandList) % COMMANDLIST_ALIGNMENT);
-	h = kzalloc(sizeof(*h), GFP_KERNEL);
+	h = hpda_alloc_ctlr_info();
 	if (!h) {
 		dev_err(&pdev->dev, "Failed to allocate controller head\n");
 		return -ENOMEM;
@@ -8916,7 +8951,7 @@ static void hpsa_remove_one(struct pci_dev *pdev)
 	h->lockup_detected = NULL;			/* init_one 2 */
 	/* (void) pci_disable_pcie_error_reporting(pdev); */	/* init_one 1 */
 
-	kfree(h);					/* init_one 1 */
+	hpda_free_ctlr_info(h);				/* init_one 1 */
 }
 
 static int hpsa_suspend(__attribute__((unused)) struct pci_dev *pdev,
diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h
index 018f980a701c..fb9f5e7f8209 100644
--- a/drivers/scsi/hpsa.h
+++ b/drivers/scsi/hpsa.h
@@ -158,6 +158,7 @@ struct bmic_controller_parameters {
 #pragma pack()
 
 struct ctlr_info {
+	unsigned int *reply_map;
 	int	ctlr;
 	char	devname[8];
 	char    *product_name;
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index b1b1d3a3b173..daefe8172b04 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -3579,11 +3579,9 @@ static void ibmvfc_tgt_implicit_logout(struct ibmvfc_target *tgt)
 static int ibmvfc_adisc_needs_plogi(struct ibmvfc_passthru_mad *mad,
 				    struct ibmvfc_target *tgt)
 {
-	if (memcmp(&mad->fc_iu.response[2], &tgt->ids.port_name,
-		   sizeof(tgt->ids.port_name)))
+	if (wwn_to_u64((u8 *)&mad->fc_iu.response[2]) != tgt->ids.port_name)
 		return 1;
-	if (memcmp(&mad->fc_iu.response[4], &tgt->ids.node_name,
-		   sizeof(tgt->ids.node_name)))
+	if (wwn_to_u64((u8 *)&mad->fc_iu.response[4]) != tgt->ids.node_name)
 		return 1;
 	if (be32_to_cpu(mad->fc_iu.response[6]) != tgt->scsi_id)
 		return 1;
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.h b/drivers/scsi/ibmvscsi/ibmvfc.h
index 9a0696f68f37..b81a53c4a9a8 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.h
+++ b/drivers/scsi/ibmvscsi/ibmvfc.h
@@ -367,7 +367,7 @@ enum ibmvfc_fcp_rsp_info_codes {
 };
 
 struct ibmvfc_fcp_rsp_info {
-	__be16 reserved;
+	u8 reserved[3];
 	u8 rsp_code;
 	u8 reserved2[4];
 }__attribute__((packed, aligned (2)));
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 6198559abbd8..dd66c11399a2 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -37,6 +37,7 @@
 #include <linux/kfifo.h>
 #include <linux/scatterlist.h>
 #include <linux/module.h>
+#include <linux/backing-dev.h>
 #include <net/tcp.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
@@ -954,6 +955,13 @@ static int iscsi_sw_tcp_slave_alloc(struct scsi_device *sdev)
 
 static int iscsi_sw_tcp_slave_configure(struct scsi_device *sdev)
 {
+	struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(sdev->host);
+	struct iscsi_session *session = tcp_sw_host->session;
+	struct iscsi_conn *conn = session->leadconn;
+
+	if (conn->datadgst_en)
+		sdev->request_queue->backing_dev_info->capabilities
+			|= BDI_CAP_STABLE_WRITES;
 	blk_queue_bounce_limit(sdev->request_queue, BLK_BOUNCE_ANY);
 	blk_queue_dma_alignment(sdev->request_queue, 0);
 	return 0;
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 6de9681ace82..ceab5e5c41c2 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -223,6 +223,7 @@ out_done:
 static void sas_eh_finish_cmd(struct scsi_cmnd *cmd)
 {
 	struct sas_ha_struct *sas_ha = SHOST_TO_SAS_HA(cmd->device->host);
+	struct domain_device *dev = cmd_to_domain_dev(cmd);
 	struct sas_task *task = TO_SAS_TASK(cmd);
 
 	/* At this point, we only get called following an actual abort
@@ -231,6 +232,14 @@ static void sas_eh_finish_cmd(struct scsi_cmnd *cmd)
 	 */
 	sas_end_task(cmd, task);
 
+	if (dev_is_sata(dev)) {
+		/* defer commands to libata so that libata EH can
+		 * handle ata qcs correctly
+		 */
+		list_move_tail(&cmd->eh_entry, &sas_ha->eh_ata_q);
+		return;
+	}
+
 	/* now finish the command and move it on to the error
 	 * handler done list, this also takes it off the
 	 * error handler pending list.
@@ -238,22 +247,6 @@ static void sas_eh_finish_cmd(struct scsi_cmnd *cmd)
 	scsi_eh_finish_cmd(cmd, &sas_ha->eh_done_q);
 }
 
-static void sas_eh_defer_cmd(struct scsi_cmnd *cmd)
-{
-	struct domain_device *dev = cmd_to_domain_dev(cmd);
-	struct sas_ha_struct *ha = dev->port->ha;
-	struct sas_task *task = TO_SAS_TASK(cmd);
-
-	if (!dev_is_sata(dev)) {
-		sas_eh_finish_cmd(cmd);
-		return;
-	}
-
-	/* report the timeout to libata */
-	sas_end_task(cmd, task);
-	list_move_tail(&cmd->eh_entry, &ha->eh_ata_q);
-}
-
 static void sas_scsi_clear_queue_lu(struct list_head *error_q, struct scsi_cmnd *my_cmd)
 {
 	struct scsi_cmnd *cmd, *n;
@@ -261,7 +254,7 @@ static void sas_scsi_clear_queue_lu(struct list_head *error_q, struct scsi_cmnd
 	list_for_each_entry_safe(cmd, n, error_q, eh_entry) {
 		if (cmd->device->sdev_target == my_cmd->device->sdev_target &&
 		    cmd->device->lun == my_cmd->device->lun)
-			sas_eh_defer_cmd(cmd);
+			sas_eh_finish_cmd(cmd);
 	}
 }
 
@@ -631,12 +624,12 @@ static void sas_eh_handle_sas_errors(struct Scsi_Host *shost, struct list_head *
 		case TASK_IS_DONE:
 			SAS_DPRINTK("%s: task 0x%p is done\n", __func__,
 				    task);
-			sas_eh_defer_cmd(cmd);
+			sas_eh_finish_cmd(cmd);
 			continue;
 		case TASK_IS_ABORTED:
 			SAS_DPRINTK("%s: task 0x%p is aborted\n",
 				    __func__, task);
-			sas_eh_defer_cmd(cmd);
+			sas_eh_finish_cmd(cmd);
 			continue;
 		case TASK_IS_AT_LU:
 			SAS_DPRINTK("task 0x%p is at LU: lu recover\n", task);
@@ -647,7 +640,7 @@ static void sas_eh_handle_sas_errors(struct Scsi_Host *shost, struct list_head *
 					    "recovered\n",
 					    SAS_ADDR(task->dev),
 					    cmd->device->lun);
-				sas_eh_defer_cmd(cmd);
+				sas_eh_finish_cmd(cmd);
 				sas_scsi_clear_queue_lu(work_q, cmd);
 				goto Again;
 			}
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index ba6503f37756..27fab8235ea5 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -2128,6 +2128,7 @@ enum MR_PD_TYPE {
 
 struct megasas_instance {
 
+	unsigned int *reply_map;
 	__le32 *producer;
 	dma_addr_t producer_h;
 	__le32 *consumer;
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 905ea36da646..2ca9b25095da 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -5164,6 +5164,26 @@ skip_alloc:
 		instance->use_seqnum_jbod_fp = false;
 }
 
+static void megasas_setup_reply_map(struct megasas_instance *instance)
+{
+	const struct cpumask *mask;
+	unsigned int queue, cpu;
+
+	for (queue = 0; queue < instance->msix_vectors; queue++) {
+		mask = pci_irq_get_affinity(instance->pdev, queue);
+		if (!mask)
+			goto fallback;
+
+		for_each_cpu(cpu, mask)
+			instance->reply_map[cpu] = queue;
+	}
+	return;
+
+fallback:
+	for_each_possible_cpu(cpu)
+		instance->reply_map[cpu] = cpu % instance->msix_vectors;
+}
+
 /**
  * megasas_init_fw -	Initializes the FW
  * @instance:		Adapter soft state
@@ -5342,6 +5362,8 @@ static int megasas_init_fw(struct megasas_instance *instance)
 			goto fail_setup_irqs;
 	}
 
+	megasas_setup_reply_map(instance);
+
 	dev_info(&instance->pdev->dev,
 		"firmware supports msix\t: (%d)", fw_msix_count);
 	dev_info(&instance->pdev->dev,
@@ -6122,20 +6144,29 @@ static inline int megasas_alloc_mfi_ctrl_mem(struct megasas_instance *instance)
  */
 static int megasas_alloc_ctrl_mem(struct megasas_instance *instance)
 {
+	instance->reply_map = kzalloc(sizeof(unsigned int) * nr_cpu_ids,
+				      GFP_KERNEL);
+	if (!instance->reply_map)
+		return -ENOMEM;
+
 	switch (instance->adapter_type) {
 	case MFI_SERIES:
 		if (megasas_alloc_mfi_ctrl_mem(instance))
-			return -ENOMEM;
+			goto fail;
 		break;
 	case VENTURA_SERIES:
 	case THUNDERBOLT_SERIES:
 	case INVADER_SERIES:
 		if (megasas_alloc_fusion_context(instance))
-			return -ENOMEM;
+			goto fail;
 		break;
 	}
 
 	return 0;
+ fail:
+	kfree(instance->reply_map);
+	instance->reply_map = NULL;
+	return -ENOMEM;
 }
 
 /*
@@ -6147,6 +6178,7 @@ static int megasas_alloc_ctrl_mem(struct megasas_instance *instance)
  */
 static inline void megasas_free_ctrl_mem(struct megasas_instance *instance)
 {
+	kfree(instance->reply_map);
 	if (instance->adapter_type == MFI_SERIES) {
 		if (instance->producer)
 			pci_free_consistent(instance->pdev, sizeof(u32),
@@ -6539,7 +6571,6 @@ fail_io_attach:
 		pci_free_irq_vectors(instance->pdev);
 fail_init_mfi:
 	scsi_host_put(host);
-
 fail_alloc_instance:
 	pci_disable_device(pdev);
 
@@ -6745,6 +6776,8 @@ megasas_resume(struct pci_dev *pdev)
 	if (rval < 0)
 		goto fail_reenable_msix;
 
+	megasas_setup_reply_map(instance);
+
 	if (instance->adapter_type != MFI_SERIES) {
 		megasas_reset_reply_desc(instance);
 		if (megasas_ioc_init_fusion(instance)) {
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 073ced07e662..5ec3b74e8aed 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -216,36 +216,30 @@ inline void megasas_return_cmd_fusion(struct megasas_instance *instance,
 /**
  * megasas_fire_cmd_fusion -	Sends command to the FW
  * @instance:			Adapter soft state
- * @req_desc:			32bit or 64bit Request descriptor
+ * @req_desc:			64bit Request descriptor
  *
- * Perform PCI Write. Ventura supports 32 bit Descriptor.
- * Prior to Ventura (12G) MR controller supports 64 bit Descriptor.
+ * Perform PCI Write.
  */
 
 static void
 megasas_fire_cmd_fusion(struct megasas_instance *instance,
 		union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc)
 {
-	if (instance->adapter_type == VENTURA_SERIES)
-		writel(le32_to_cpu(req_desc->u.low),
-			&instance->reg_set->inbound_single_queue_port);
-	else {
 #if defined(writeq) && defined(CONFIG_64BIT)
-		u64 req_data = (((u64)le32_to_cpu(req_desc->u.high) << 32) |
-				le32_to_cpu(req_desc->u.low));
+	u64 req_data = (((u64)le32_to_cpu(req_desc->u.high) << 32) |
+		le32_to_cpu(req_desc->u.low));
 
-		writeq(req_data, &instance->reg_set->inbound_low_queue_port);
+	writeq(req_data, &instance->reg_set->inbound_low_queue_port);
 #else
-		unsigned long flags;
-		spin_lock_irqsave(&instance->hba_lock, flags);
-		writel(le32_to_cpu(req_desc->u.low),
-			&instance->reg_set->inbound_low_queue_port);
-		writel(le32_to_cpu(req_desc->u.high),
-			&instance->reg_set->inbound_high_queue_port);
-		mmiowb();
-		spin_unlock_irqrestore(&instance->hba_lock, flags);
+	unsigned long flags;
+	spin_lock_irqsave(&instance->hba_lock, flags);
+	writel(le32_to_cpu(req_desc->u.low),
+		&instance->reg_set->inbound_low_queue_port);
+	writel(le32_to_cpu(req_desc->u.high),
+		&instance->reg_set->inbound_high_queue_port);
+	mmiowb();
+	spin_unlock_irqrestore(&instance->hba_lock, flags);
 #endif
-	}
 }
 
 /**
@@ -982,7 +976,6 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 	const char *sys_info;
 	MFI_CAPABILITIES *drv_ops;
 	u32 scratch_pad_2;
-	unsigned long flags;
 	ktime_t time;
 	bool cur_fw_64bit_dma_capable;
 
@@ -1121,14 +1114,7 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 			break;
 	}
 
-	/* For Ventura also IOC INIT required 64 bit Descriptor write. */
-	spin_lock_irqsave(&instance->hba_lock, flags);
-	writel(le32_to_cpu(req_desc.u.low),
-	       &instance->reg_set->inbound_low_queue_port);
-	writel(le32_to_cpu(req_desc.u.high),
-	       &instance->reg_set->inbound_high_queue_port);
-	mmiowb();
-	spin_unlock_irqrestore(&instance->hba_lock, flags);
+	megasas_fire_cmd_fusion(instance, &req_desc);
 
 	wait_and_poll(instance, cmd, MFI_POLL_TIMEOUT_SECS);
 
@@ -2655,11 +2641,8 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 			fp_possible = (io_info.fpOkForIo > 0) ? true : false;
 	}
 
-	/* Use raw_smp_processor_id() for now until cmd->request->cpu is CPU
-	   id by default, not CPU group id, otherwise all MSI-X queues won't
-	   be utilized */
-	cmd->request_desc->SCSIIO.MSIxIndex = instance->msix_vectors ?
-		raw_smp_processor_id() % instance->msix_vectors : 0;
+	cmd->request_desc->SCSIIO.MSIxIndex =
+		instance->reply_map[raw_smp_processor_id()];
 
 	praid_context = &io_request->RaidContext;
 
@@ -2985,10 +2968,9 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 	}
 
 	cmd->request_desc->SCSIIO.DevHandle = io_request->DevHandle;
-	cmd->request_desc->SCSIIO.MSIxIndex =
-		instance->msix_vectors ?
-		(raw_smp_processor_id() % instance->msix_vectors) : 0;
 
+	cmd->request_desc->SCSIIO.MSIxIndex =
+		instance->reply_map[raw_smp_processor_id()];
 
 	if (!fp_possible) {
 		/* system pd firmware path */
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 0a0e7aad0ca4..61f93a134956 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -2774,8 +2774,11 @@ _base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc)
 				continue;
 			}
 
-			for_each_cpu(cpu, mask)
+			for_each_cpu_and(cpu, mask, cpu_online_mask) {
+				if (cpu >= ioc->cpu_msix_table_sz)
+					break;
 				ioc->cpu_msix_table[cpu] = reply_q->msix_index;
+			}
 		}
 		return;
 	}
@@ -6637,14 +6640,14 @@ _base_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase)
 }
 
 /**
- * _wait_for_commands_to_complete - reset controller
+ * mpt3sas_wait_for_commands_to_complete - reset controller
  * @ioc: Pointer to MPT_ADAPTER structure
  *
  * This function is waiting 10s for all pending commands to complete
  * prior to putting controller in reset.
  */
-static void
-_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc)
+void
+mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc)
 {
 	u32 ioc_state;
 
@@ -6717,7 +6720,7 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
 			is_fault = 1;
 	}
 	_base_reset_handler(ioc, MPT3_IOC_PRE_RESET);
-	_wait_for_commands_to_complete(ioc);
+	mpt3sas_wait_for_commands_to_complete(ioc);
 	_base_mask_interrupts(ioc);
 	r = _base_make_ioc_ready(ioc, type);
 	if (r)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 4de0251e158e..ae36d8fb2f2b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -1440,6 +1440,9 @@ void mpt3sas_base_update_missing_delay(struct MPT3SAS_ADAPTER *ioc,
 
 int mpt3sas_port_enable(struct MPT3SAS_ADAPTER *ioc);
 
+void
+mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc);
+
 
 /* scsih shared API */
 struct scsi_cmnd *mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 50efccd73cb1..89be0170aef6 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -2835,7 +2835,8 @@ scsih_abort(struct scsi_cmnd *scmd)
 	_scsih_tm_display_info(ioc, scmd);
 
 	sas_device_priv_data = scmd->device->hostdata;
-	if (!sas_device_priv_data || !sas_device_priv_data->sas_target) {
+	if (!sas_device_priv_data || !sas_device_priv_data->sas_target ||
+	    ioc->remove_host) {
 		sdev_printk(KERN_INFO, scmd->device,
 			"device been deleted! scmd(%p)\n", scmd);
 		scmd->result = DID_NO_CONNECT << 16;
@@ -2898,7 +2899,8 @@ scsih_dev_reset(struct scsi_cmnd *scmd)
 	_scsih_tm_display_info(ioc, scmd);
 
 	sas_device_priv_data = scmd->device->hostdata;
-	if (!sas_device_priv_data || !sas_device_priv_data->sas_target) {
+	if (!sas_device_priv_data || !sas_device_priv_data->sas_target ||
+	    ioc->remove_host) {
 		sdev_printk(KERN_INFO, scmd->device,
 			"device been deleted! scmd(%p)\n", scmd);
 		scmd->result = DID_NO_CONNECT << 16;
@@ -2961,7 +2963,8 @@ scsih_target_reset(struct scsi_cmnd *scmd)
 	_scsih_tm_display_info(ioc, scmd);
 
 	sas_device_priv_data = scmd->device->hostdata;
-	if (!sas_device_priv_data || !sas_device_priv_data->sas_target) {
+	if (!sas_device_priv_data || !sas_device_priv_data->sas_target ||
+	    ioc->remove_host) {
 		starget_printk(KERN_INFO, starget, "target been deleted! scmd(%p)\n",
 			scmd);
 		scmd->result = DID_NO_CONNECT << 16;
@@ -3019,7 +3022,7 @@ scsih_host_reset(struct scsi_cmnd *scmd)
 	    ioc->name, scmd);
 	scsi_print_command(scmd);
 
-	if (ioc->is_driver_loading) {
+	if (ioc->is_driver_loading || ioc->remove_host) {
 		pr_info(MPT3SAS_FMT "Blocking the host reset\n",
 		    ioc->name);
 		r = FAILED;
@@ -4453,7 +4456,7 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc)
 		st = scsi_cmd_priv(scmd);
 		mpt3sas_base_clear_st(ioc, st);
 		scsi_dma_unmap(scmd);
-		if (ioc->pci_error_recovery)
+		if (ioc->pci_error_recovery || ioc->remove_host)
 			scmd->result = DID_NO_CONNECT << 16;
 		else
 			scmd->result = DID_RESET << 16;
@@ -9739,6 +9742,10 @@ static void scsih_remove(struct pci_dev *pdev)
 	unsigned long flags;
 
 	ioc->remove_host = 1;
+
+	mpt3sas_wait_for_commands_to_complete(ioc);
+	_scsih_flush_running_cmds(ioc);
+
 	_scsih_fw_event_cleanup_queue(ioc);
 
 	spin_lock_irqsave(&ioc->fw_event_lock, flags);
@@ -9815,6 +9822,10 @@ scsih_shutdown(struct pci_dev *pdev)
 	unsigned long flags;
 
 	ioc->remove_host = 1;
+
+	mpt3sas_wait_for_commands_to_complete(ioc);
+	_scsih_flush_running_cmds(ioc);
+
 	_scsih_fw_event_cleanup_queue(ioc);
 
 	spin_lock_irqsave(&ioc->fw_event_lock, flags);
@@ -10563,7 +10574,7 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	snprintf(ioc->firmware_event_name, sizeof(ioc->firmware_event_name),
 	    "fw_event_%s%d", ioc->driver_name, ioc->id);
 	ioc->firmware_event_thread = alloc_ordered_workqueue(
-	    ioc->firmware_event_name, WQ_MEM_RECLAIM);
+	    ioc->firmware_event_name, 0);
 	if (!ioc->firmware_event_thread) {
 		pr_err(MPT3SAS_FMT "failure at %s:%d/%s()!\n",
 		    ioc->name, __FILE__, __LINE__, __func__);
diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c
index 667d7697ba01..d09afe1b567d 100644
--- a/drivers/scsi/qedi/qedi_fw.c
+++ b/drivers/scsi/qedi/qedi_fw.c
@@ -762,6 +762,11 @@ static void qedi_process_cmd_cleanup_resp(struct qedi_ctx *qedi,
 
 	iscsi_cid = cqe->conn_id;
 	qedi_conn = qedi->cid_que.conn_cid_tbl[iscsi_cid];
+	if (!qedi_conn) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "icid not found 0x%x\n", cqe->conn_id);
+		return;
+	}
 
 	/* Based on this itt get the corresponding qedi_cmd */
 	spin_lock_bh(&qedi_conn->tmf_work_lock);
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index e992f9d3ef00..4da3592aec0f 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -1724,7 +1724,6 @@ static ssize_t qedi_show_boot_eth_info(void *data, int type, char *buf)
 {
 	struct qedi_ctx *qedi = data;
 	struct nvm_iscsi_initiator *initiator;
-	char *str = buf;
 	int rc = 1;
 	u32 ipv6_en, dhcp_en, ip_len;
 	struct nvm_iscsi_block *block;
@@ -1758,32 +1757,32 @@ static ssize_t qedi_show_boot_eth_info(void *data, int type, char *buf)
 
 	switch (type) {
 	case ISCSI_BOOT_ETH_IP_ADDR:
-		rc = snprintf(str, ip_len, fmt, ip);
+		rc = snprintf(buf, ip_len, fmt, ip);
 		break;
 	case ISCSI_BOOT_ETH_SUBNET_MASK:
-		rc = snprintf(str, ip_len, fmt, sub);
+		rc = snprintf(buf, ip_len, fmt, sub);
 		break;
 	case ISCSI_BOOT_ETH_GATEWAY:
-		rc = snprintf(str, ip_len, fmt, gw);
+		rc = snprintf(buf, ip_len, fmt, gw);
 		break;
 	case ISCSI_BOOT_ETH_FLAGS:
-		rc = snprintf(str, 3, "%hhd\n",
+		rc = snprintf(buf, 3, "%hhd\n",
 			      SYSFS_FLAG_FW_SEL_BOOT);
 		break;
 	case ISCSI_BOOT_ETH_INDEX:
-		rc = snprintf(str, 3, "0\n");
+		rc = snprintf(buf, 3, "0\n");
 		break;
 	case ISCSI_BOOT_ETH_MAC:
-		rc = sysfs_format_mac(str, qedi->mac, ETH_ALEN);
+		rc = sysfs_format_mac(buf, qedi->mac, ETH_ALEN);
 		break;
 	case ISCSI_BOOT_ETH_VLAN:
-		rc = snprintf(str, 12, "%d\n",
+		rc = snprintf(buf, 12, "%d\n",
 			      GET_FIELD2(initiator->generic_cont0,
 					 NVM_ISCSI_CFG_INITIATOR_VLAN));
 		break;
 	case ISCSI_BOOT_ETH_ORIGIN:
 		if (dhcp_en)
-			rc = snprintf(str, 3, "3\n");
+			rc = snprintf(buf, 3, "3\n");
 		break;
 	default:
 		rc = 0;
@@ -1819,7 +1818,6 @@ static ssize_t qedi_show_boot_ini_info(void *data, int type, char *buf)
 {
 	struct qedi_ctx *qedi = data;
 	struct nvm_iscsi_initiator *initiator;
-	char *str = buf;
 	int rc;
 	struct nvm_iscsi_block *block;
 
@@ -1831,8 +1829,8 @@ static ssize_t qedi_show_boot_ini_info(void *data, int type, char *buf)
 
 	switch (type) {
 	case ISCSI_BOOT_INI_INITIATOR_NAME:
-		rc = snprintf(str, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n",
-			      initiator->initiator_name.byte);
+		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN,
+			     initiator->initiator_name.byte);
 		break;
 	default:
 		rc = 0;
@@ -1860,7 +1858,6 @@ static ssize_t
 qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type,
 			char *buf, enum qedi_nvm_tgts idx)
 {
-	char *str = buf;
 	int rc = 1;
 	u32 ctrl_flags, ipv6_en, chap_en, mchap_en, ip_len;
 	struct nvm_iscsi_block *block;
@@ -1899,48 +1896,48 @@ qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type,
 
 	switch (type) {
 	case ISCSI_BOOT_TGT_NAME:
-		rc = snprintf(str, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n",
-			      block->target[idx].target_name.byte);
+		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN,
+			     block->target[idx].target_name.byte);
 		break;
 	case ISCSI_BOOT_TGT_IP_ADDR:
 		if (ipv6_en)
-			rc = snprintf(str, ip_len, "%pI6\n",
+			rc = snprintf(buf, ip_len, "%pI6\n",
 				      block->target[idx].ipv6_addr.byte);
 		else
-			rc = snprintf(str, ip_len, "%pI4\n",
+			rc = snprintf(buf, ip_len, "%pI4\n",
 				      block->target[idx].ipv4_addr.byte);
 		break;
 	case ISCSI_BOOT_TGT_PORT:
-		rc = snprintf(str, 12, "%d\n",
+		rc = snprintf(buf, 12, "%d\n",
 			      GET_FIELD2(block->target[idx].generic_cont0,
 					 NVM_ISCSI_CFG_TARGET_TCP_PORT));
 		break;
 	case ISCSI_BOOT_TGT_LUN:
-		rc = snprintf(str, 22, "%.*d\n",
+		rc = snprintf(buf, 22, "%.*d\n",
 			      block->target[idx].lun.value[1],
 			      block->target[idx].lun.value[0]);
 		break;
 	case ISCSI_BOOT_TGT_CHAP_NAME:
-		rc = snprintf(str, NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, "%s\n",
-			      chap_name);
+		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN,
+			     chap_name);
 		break;
 	case ISCSI_BOOT_TGT_CHAP_SECRET:
-		rc = snprintf(str, NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, "%s\n",
-			      chap_secret);
+		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN,
+			     chap_secret);
 		break;
 	case ISCSI_BOOT_TGT_REV_CHAP_NAME:
-		rc = snprintf(str, NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, "%s\n",
-			      mchap_name);
+		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN,
+			     mchap_name);
 		break;
 	case ISCSI_BOOT_TGT_REV_CHAP_SECRET:
-		rc = snprintf(str, NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, "%s\n",
-			      mchap_secret);
+		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN,
+			     mchap_secret);
 		break;
 	case ISCSI_BOOT_TGT_FLAGS:
-		rc = snprintf(str, 3, "%hhd\n", SYSFS_FLAG_FW_SEL_BOOT);
+		rc = snprintf(buf, 3, "%hhd\n", SYSFS_FLAG_FW_SEL_BOOT);
 		break;
 	case ISCSI_BOOT_TGT_NIC_ASSOC:
-		rc = snprintf(str, 3, "0\n");
+		rc = snprintf(buf, 3, "0\n");
 		break;
 	default:
 		rc = 0;
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 1abc8a9064b3..5fd44c50bbac 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -14,7 +14,7 @@
  * | Module Init and Probe        |       0x0193       | 0x0146         |
  * |                              |                    | 0x015b-0x0160	|
  * |                              |                    | 0x016e		|
- * | Mailbox commands             |       0x1205       | 0x11a2-0x11ff	|
+ * | Mailbox commands             |       0x1206       | 0x11a2-0x11ff	|
  * | Device Discovery             |       0x2134       | 0x210e-0x2116  |
  * |				  | 		       | 0x211a         |
  * |                              |                    | 0x211c-0x2128  |
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 54625eb2904f..eb2ec1fb07cb 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -261,9 +261,9 @@
 struct name_list_extended {
 	struct get_name_list_extended *l;
 	dma_addr_t		ldma;
-	struct list_head 	fcports;	/* protect by sess_list */
+	struct list_head	fcports;
+	spinlock_t		fcports_lock;
 	u32			size;
-	u8			sent;
 };
 /*
  * Timeout timer counts in seconds
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index 39dd62b8c649..2288757b5c9e 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -3177,6 +3177,7 @@ done_free_sp:
 	sp->free(sp);
 	fcport->flags &= ~FCF_ASYNC_SENT;
 done:
+	fcport->flags &= ~FCF_ASYNC_ACTIVE;
 	return rval;
 }
 
@@ -3368,6 +3369,7 @@ done_free_sp:
 	sp->free(sp);
 	fcport->flags &= ~FCF_ASYNC_SENT;
 done:
+	fcport->flags &= ~FCF_ASYNC_ACTIVE;
 	return rval;
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 77c9177d0c25..8aeb0ed524a1 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -59,8 +59,6 @@ qla2x00_sp_timeout(struct timer_list *t)
 	req->outstanding_cmds[sp->handle] = NULL;
 	iocb = &sp->u.iocb_cmd;
 	iocb->timeout(sp);
-	if (sp->type != SRB_ELS_DCMD)
-		sp->free(sp);
 	spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
 }
 
@@ -102,7 +100,6 @@ qla2x00_async_iocb_timeout(void *data)
 	srb_t *sp = data;
 	fc_port_t *fcport = sp->fcport;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
-	struct event_arg ea;
 
 	if (fcport) {
 		ql_dbg(ql_dbg_disc, fcport->vha, 0x2071,
@@ -117,25 +114,13 @@ qla2x00_async_iocb_timeout(void *data)
 
 	switch (sp->type) {
 	case SRB_LOGIN_CMD:
-		if (!fcport)
-			break;
 		/* Retry as needed. */
 		lio->u.logio.data[0] = MBS_COMMAND_ERROR;
 		lio->u.logio.data[1] = lio->u.logio.flags & SRB_LOGIN_RETRIED ?
 			QLA_LOGIO_LOGIN_RETRIED : 0;
-		memset(&ea, 0, sizeof(ea));
-		ea.event = FCME_PLOGI_DONE;
-		ea.fcport = sp->fcport;
-		ea.data[0] = lio->u.logio.data[0];
-		ea.data[1] = lio->u.logio.data[1];
-		ea.sp = sp;
-		qla24xx_handle_plogi_done_event(fcport->vha, &ea);
+		sp->done(sp, QLA_FUNCTION_TIMEOUT);
 		break;
 	case SRB_LOGOUT_CMD:
-		if (!fcport)
-			break;
-		qlt_logo_completion_handler(fcport, QLA_FUNCTION_TIMEOUT);
-		break;
 	case SRB_CT_PTHRU_CMD:
 	case SRB_MB_IOCB:
 	case SRB_NACK_PLOGI:
@@ -228,6 +213,7 @@ done_free_sp:
 	sp->free(sp);
 	fcport->flags &= ~FCF_ASYNC_SENT;
 done:
+	fcport->flags &= ~FCF_ASYNC_ACTIVE;
 	return rval;
 }
 
@@ -235,12 +221,10 @@ static void
 qla2x00_async_logout_sp_done(void *ptr, int res)
 {
 	srb_t *sp = ptr;
-	struct srb_iocb *lio = &sp->u.iocb_cmd;
 
 	sp->fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
-	if (!test_bit(UNLOADING, &sp->vha->dpc_flags))
-		qla2x00_post_async_logout_done_work(sp->vha, sp->fcport,
-		    lio->u.logio.data);
+	sp->fcport->login_gen++;
+	qlt_logo_completion_handler(sp->fcport, res);
 	sp->free(sp);
 }
 
@@ -280,7 +264,7 @@ qla2x00_async_logout(struct scsi_qla_host *vha, fc_port_t *fcport)
 done_free_sp:
 	sp->free(sp);
 done:
-	fcport->flags &= ~FCF_ASYNC_SENT;
+	fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
 	return rval;
 }
 
@@ -288,6 +272,7 @@ void
 qla2x00_async_prlo_done(struct scsi_qla_host *vha, fc_port_t *fcport,
     uint16_t *data)
 {
+	fcport->flags &= ~FCF_ASYNC_ACTIVE;
 	/* Don't re-login in target mode */
 	if (!fcport->tgt_session)
 		qla2x00_mark_device_lost(vha, fcport, 1, 0);
@@ -301,6 +286,7 @@ qla2x00_async_prlo_sp_done(void *s, int res)
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
 	struct scsi_qla_host *vha = sp->vha;
 
+	sp->fcport->flags &= ~FCF_ASYNC_ACTIVE;
 	if (!test_bit(UNLOADING, &vha->dpc_flags))
 		qla2x00_post_async_prlo_done_work(sp->fcport->vha, sp->fcport,
 		    lio->u.logio.data);
@@ -339,6 +325,7 @@ qla2x00_async_prlo(struct scsi_qla_host *vha, fc_port_t *fcport)
 done_free_sp:
 	sp->free(sp);
 done:
+	fcport->flags &= ~FCF_ASYNC_ACTIVE;
 	return rval;
 }
 
@@ -392,6 +379,8 @@ qla2x00_async_adisc_sp_done(void *ptr, int res)
 	    "Async done-%s res %x %8phC\n",
 	    sp->name, res, sp->fcport->port_name);
 
+	sp->fcport->flags &= ~FCF_ASYNC_SENT;
+
 	memset(&ea, 0, sizeof(ea));
 	ea.event = FCME_ADISC_DONE;
 	ea.rc = res;
@@ -442,7 +431,7 @@ qla2x00_async_adisc(struct scsi_qla_host *vha, fc_port_t *fcport,
 done_free_sp:
 	sp->free(sp);
 done:
-	fcport->flags &= ~FCF_ASYNC_SENT;
+	fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
 	qla2x00_post_async_adisc_work(vha, fcport, data);
 	return rval;
 }
@@ -660,8 +649,7 @@ qla24xx_async_gnl_sp_done(void *s, int res)
 		    (loop_id & 0x7fff));
 	}
 
-	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
-	vha->gnl.sent = 0;
+	spin_lock_irqsave(&vha->gnl.fcports_lock, flags);
 
 	INIT_LIST_HEAD(&h);
 	fcport = tf = NULL;
@@ -670,12 +658,16 @@ qla24xx_async_gnl_sp_done(void *s, int res)
 
 	list_for_each_entry_safe(fcport, tf, &h, gnl_entry) {
 		list_del_init(&fcport->gnl_entry);
+		spin_lock(&vha->hw->tgt.sess_lock);
 		fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
+		spin_unlock(&vha->hw->tgt.sess_lock);
 		ea.fcport = fcport;
 
 		qla2x00_fcport_event_handler(vha, &ea);
 	}
+	spin_unlock_irqrestore(&vha->gnl.fcports_lock, flags);
 
+	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
 	/* create new fcport if fw has knowledge of new sessions */
 	for (i = 0; i < n; i++) {
 		port_id_t id;
@@ -727,18 +719,21 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport)
 	ql_dbg(ql_dbg_disc, vha, 0x20d9,
 	    "Async-gnlist WWPN %8phC \n", fcport->port_name);
 
-	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
+	spin_lock_irqsave(&vha->gnl.fcports_lock, flags);
+	if (!list_empty(&fcport->gnl_entry)) {
+		spin_unlock_irqrestore(&vha->gnl.fcports_lock, flags);
+		rval = QLA_SUCCESS;
+		goto done;
+	}
+
+	spin_lock(&vha->hw->tgt.sess_lock);
 	fcport->disc_state = DSC_GNL;
 	fcport->last_rscn_gen = fcport->rscn_gen;
 	fcport->last_login_gen = fcport->login_gen;
+	spin_unlock(&vha->hw->tgt.sess_lock);
 
 	list_add_tail(&fcport->gnl_entry, &vha->gnl.fcports);
-	if (vha->gnl.sent) {
-		spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
-		return QLA_SUCCESS;
-	}
-	vha->gnl.sent = 1;
-	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+	spin_unlock_irqrestore(&vha->gnl.fcports_lock, flags);
 
 	sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL);
 	if (!sp)
@@ -1065,6 +1060,7 @@ void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea)
 	fc_port_t *fcport = ea->fcport;
 	struct port_database_24xx *pd;
 	struct srb *sp = ea->sp;
+	uint8_t	ls;
 
 	pd = (struct port_database_24xx *)sp->u.iocb_cmd.u.mbx.in;
 
@@ -1077,7 +1073,12 @@ void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea)
 	if (fcport->disc_state == DSC_DELETE_PEND)
 		return;
 
-	switch (pd->current_login_state) {
+	if (fcport->fc4f_nvme)
+		ls = pd->current_login_state >> 4;
+	else
+		ls = pd->current_login_state & 0xf;
+
+	switch (ls) {
 	case PDS_PRLI_COMPLETE:
 		__qla24xx_parse_gpdb(vha, fcport, pd);
 		break;
@@ -1167,8 +1168,9 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 	if (fcport->scan_state != QLA_FCPORT_FOUND)
 		return 0;
 
-	if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) ||
-	    (fcport->fw_login_state == DSC_LS_PRLI_PEND))
+	if ((fcport->loop_id != FC_NO_LOOP_ID) &&
+	    ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) ||
+	     (fcport->fw_login_state == DSC_LS_PRLI_PEND)))
 		return 0;
 
 	if (fcport->fw_login_state == DSC_LS_PLOGI_COMP) {
@@ -1548,6 +1550,7 @@ qla24xx_abort_sp_done(void *ptr, int res)
 	srb_t *sp = ptr;
 	struct srb_iocb *abt = &sp->u.iocb_cmd;
 
+	del_timer(&sp->u.iocb_cmd.timer);
 	complete(&abt->u.abt.comp);
 }
 
@@ -1727,7 +1730,6 @@ qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea)
 
 			set_bit(ea->fcport->loop_id, vha->hw->loop_id_map);
 			spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
-			ea->fcport->loop_id = FC_NO_LOOP_ID;
 			ea->fcport->chip_reset = vha->hw->base_qpair->chip_reset;
 			ea->fcport->logout_on_delete = 1;
 			ea->fcport->send_els_logo = 0;
@@ -1819,6 +1821,7 @@ qla2x00_async_logout_done(struct scsi_qla_host *vha, fc_port_t *fcport,
 	qla2x00_mark_device_lost(vha, fcport, 1, 0);
 	qlt_logo_completion_handler(fcport, data[0]);
 	fcport->login_gen++;
+	fcport->flags &= ~FCF_ASYNC_ACTIVE;
 	return;
 }
 
@@ -1826,6 +1829,7 @@ void
 qla2x00_async_adisc_done(struct scsi_qla_host *vha, fc_port_t *fcport,
     uint16_t *data)
 {
+	fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
 	if (data[0] == MBS_COMMAND_COMPLETE) {
 		qla2x00_update_fcport(vha, fcport);
 
@@ -1833,7 +1837,6 @@ qla2x00_async_adisc_done(struct scsi_qla_host *vha, fc_port_t *fcport,
 	}
 
 	/* Retry login. */
-	fcport->flags &= ~FCF_ASYNC_SENT;
 	if (data[1] & QLA_LOGIO_LOGIN_RETRIED)
 		set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
 	else
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index a4edbecfaf96..f74ff7b550b6 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -3276,12 +3276,11 @@ qla24xx_abort_iocb(srb_t *sp, struct abort_entry_24xx *abt_iocb)
 	memset(abt_iocb, 0, sizeof(struct abort_entry_24xx));
 	abt_iocb->entry_type = ABORT_IOCB_TYPE;
 	abt_iocb->entry_count = 1;
-	abt_iocb->handle =
-	     cpu_to_le32(MAKE_HANDLE(aio->u.abt.req_que_no,
-		 aio->u.abt.cmd_hndl));
+	abt_iocb->handle = cpu_to_le32(MAKE_HANDLE(req->id, sp->handle));
 	abt_iocb->nport_handle = cpu_to_le16(sp->fcport->loop_id);
 	abt_iocb->handle_to_abort =
-	    cpu_to_le32(MAKE_HANDLE(req->id, aio->u.abt.cmd_hndl));
+	    cpu_to_le32(MAKE_HANDLE(aio->u.abt.req_que_no,
+				    aio->u.abt.cmd_hndl));
 	abt_iocb->port_id[0] = sp->fcport->d_id.b.al_pa;
 	abt_iocb->port_id[1] = sp->fcport->d_id.b.area;
 	abt_iocb->port_id[2] = sp->fcport->d_id.b.domain;
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 5fbb8f4b4dc7..7cacdc3408fa 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -272,7 +272,8 @@ qla2x00_mbx_completion(scsi_qla_host_t *vha, uint16_t mb0)
 	struct device_reg_2xxx __iomem *reg = &ha->iobase->isp;
 
 	/* Read all mbox registers? */
-	mboxes = (1 << ha->mbx_count) - 1;
+	WARN_ON_ONCE(ha->mbx_count > 32);
+	mboxes = (1ULL << ha->mbx_count) - 1;
 	if (!ha->mcp)
 		ql_dbg(ql_dbg_async, vha, 0x5001, "MBX pointer ERROR.\n");
 	else
@@ -2862,7 +2863,8 @@ qla24xx_mbx_completion(scsi_qla_host_t *vha, uint16_t mb0)
 	struct device_reg_24xx __iomem *reg = &ha->iobase->isp24;
 
 	/* Read all mbox registers? */
-	mboxes = (1 << ha->mbx_count) - 1;
+	WARN_ON_ONCE(ha->mbx_count > 32);
+	mboxes = (1ULL << ha->mbx_count) - 1;
 	if (!ha->mcp)
 		ql_dbg(ql_dbg_async, vha, 0x504e, "MBX pointer ERROR.\n");
 	else
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index c9a134ae0d2b..5db0262d5c94 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -503,11 +503,19 @@ mbx_done:
 				}
 			pr_warn(" cmd=%x ****\n", command);
 		}
-		ql_dbg(ql_dbg_mbx, vha, 0x1198,
-		    "host_status=%#x intr_ctrl=%#x intr_status=%#x\n",
-		    RD_REG_DWORD(&reg->isp24.host_status),
-		    RD_REG_DWORD(&reg->isp24.ictrl),
-		    RD_REG_DWORD(&reg->isp24.istatus));
+		if (IS_FWI2_CAPABLE(ha) && !(IS_P3P_TYPE(ha))) {
+			ql_dbg(ql_dbg_mbx, vha, 0x1198,
+			    "host_status=%#x intr_ctrl=%#x intr_status=%#x\n",
+			    RD_REG_DWORD(&reg->isp24.host_status),
+			    RD_REG_DWORD(&reg->isp24.ictrl),
+			    RD_REG_DWORD(&reg->isp24.istatus));
+		} else {
+			ql_dbg(ql_dbg_mbx, vha, 0x1206,
+			    "ctrl_status=%#x ictrl=%#x istatus=%#x\n",
+			    RD_REG_WORD(&reg->isp.ctrl_status),
+			    RD_REG_WORD(&reg->isp.ictrl),
+			    RD_REG_WORD(&reg->isp.istatus));
+		}
 	} else {
 		ql_dbg(ql_dbg_mbx, base_vha, 0x1021, "Done %s.\n", __func__);
 	}
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 6fa2467e2a16..fb35d9e94912 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -453,7 +453,7 @@ static int qla2x00_alloc_queues(struct qla_hw_data *ha, struct req_que *req,
 	ha->req_q_map[0] = req;
 	set_bit(0, ha->rsp_qid_map);
 	set_bit(0, ha->req_qid_map);
-	return 1;
+	return 0;
 
 fail_qpair_map:
 	kfree(ha->base_qpair);
@@ -470,6 +470,9 @@ fail_req_map:
 
 static void qla2x00_free_req_que(struct qla_hw_data *ha, struct req_que *req)
 {
+	if (!ha->req_q_map)
+		return;
+
 	if (IS_QLAFX00(ha)) {
 		if (req && req->ring_fx00)
 			dma_free_coherent(&ha->pdev->dev,
@@ -480,16 +483,19 @@ static void qla2x00_free_req_que(struct qla_hw_data *ha, struct req_que *req)
 		(req->length + 1) * sizeof(request_t),
 		req->ring, req->dma);
 
-	if (req)
+	if (req) {
 		kfree(req->outstanding_cmds);
-
-	kfree(req);
+		kfree(req);
+	}
 }
 
 static void qla2x00_free_rsp_que(struct qla_hw_data *ha, struct rsp_que *rsp)
 {
+	if (!ha->rsp_q_map)
+		return;
+
 	if (IS_QLAFX00(ha)) {
-		if (rsp && rsp->ring)
+		if (rsp && rsp->ring_fx00)
 			dma_free_coherent(&ha->pdev->dev,
 			    (rsp->length_fx00 + 1) * sizeof(request_t),
 			    rsp->ring_fx00, rsp->dma_fx00);
@@ -498,7 +504,8 @@ static void qla2x00_free_rsp_que(struct qla_hw_data *ha, struct rsp_que *rsp)
 		(rsp->length + 1) * sizeof(response_t),
 		rsp->ring, rsp->dma);
 	}
-	kfree(rsp);
+	if (rsp)
+		kfree(rsp);
 }
 
 static void qla2x00_free_queues(struct qla_hw_data *ha)
@@ -1722,6 +1729,8 @@ __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res)
 	struct qla_tgt_cmd *cmd;
 	uint8_t trace = 0;
 
+	if (!ha->req_q_map)
+		return;
 	spin_lock_irqsave(qp->qp_lock_ptr, flags);
 	req = qp->req;
 	for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) {
@@ -3094,14 +3103,14 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* Set up the irqs */
 	ret = qla2x00_request_irqs(ha, rsp);
 	if (ret)
-		goto probe_hw_failed;
+		goto probe_failed;
 
 	/* Alloc arrays of request and response ring ptrs */
-	if (!qla2x00_alloc_queues(ha, req, rsp)) {
+	if (qla2x00_alloc_queues(ha, req, rsp)) {
 		ql_log(ql_log_fatal, base_vha, 0x003d,
 		    "Failed to allocate memory for queue pointers..."
 		    "aborting.\n");
-		goto probe_init_failed;
+		goto probe_failed;
 	}
 
 	if (ha->mqenable && shost_use_blk_mq(host)) {
@@ -3386,15 +3395,6 @@ skip_dpc:
 
 	return 0;
 
-probe_init_failed:
-	qla2x00_free_req_que(ha, req);
-	ha->req_q_map[0] = NULL;
-	clear_bit(0, ha->req_qid_map);
-	qla2x00_free_rsp_que(ha, rsp);
-	ha->rsp_q_map[0] = NULL;
-	clear_bit(0, ha->rsp_qid_map);
-	ha->max_req_queues = ha->max_rsp_queues = 0;
-
 probe_failed:
 	if (base_vha->timer_active)
 		qla2x00_stop_timer(base_vha);
@@ -3624,6 +3624,8 @@ qla2x00_remove_one(struct pci_dev *pdev)
 	}
 	qla2x00_wait_for_hba_ready(base_vha);
 
+	qla2x00_wait_for_sess_deletion(base_vha);
+
 	/*
 	 * if UNLOAD flag is already set, then continue unload,
 	 * where it was set first.
@@ -4505,11 +4507,17 @@ qla2x00_mem_free(struct qla_hw_data *ha)
 	if (ha->init_cb)
 		dma_free_coherent(&ha->pdev->dev, ha->init_cb_size,
 			ha->init_cb, ha->init_cb_dma);
-	vfree(ha->optrom_buffer);
-	kfree(ha->nvram);
-	kfree(ha->npiv_info);
-	kfree(ha->swl);
-	kfree(ha->loop_id_map);
+
+	if (ha->optrom_buffer)
+		vfree(ha->optrom_buffer);
+	if (ha->nvram)
+		kfree(ha->nvram);
+	if (ha->npiv_info)
+		kfree(ha->npiv_info);
+	if (ha->swl)
+		kfree(ha->swl);
+	if (ha->loop_id_map)
+		kfree(ha->loop_id_map);
 
 	ha->srb_mempool = NULL;
 	ha->ctx_mempool = NULL;
@@ -4525,6 +4533,15 @@ qla2x00_mem_free(struct qla_hw_data *ha)
 	ha->ex_init_cb_dma = 0;
 	ha->async_pd = NULL;
 	ha->async_pd_dma = 0;
+	ha->loop_id_map = NULL;
+	ha->npiv_info = NULL;
+	ha->optrom_buffer = NULL;
+	ha->swl = NULL;
+	ha->nvram = NULL;
+	ha->mctp_dump = NULL;
+	ha->dcbx_tlv = NULL;
+	ha->xgmac_data = NULL;
+	ha->sfp_data = NULL;
 
 	ha->s_dma_pool = NULL;
 	ha->dl_dma_pool = NULL;
@@ -4574,6 +4591,7 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht,
 
 	spin_lock_init(&vha->work_lock);
 	spin_lock_init(&vha->cmd_list_lock);
+	spin_lock_init(&vha->gnl.fcports_lock);
 	init_waitqueue_head(&vha->fcport_waitQ);
 	init_waitqueue_head(&vha->vref_waitq);
 
@@ -4879,6 +4897,8 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 			}
 			qlt_plogi_ack_unref(vha, pla);
 		} else {
+			fc_port_t *dfcp = NULL;
+
 			spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
 			tfcp = qla2x00_find_fcport_by_nportid(vha,
 			    &e->u.new_sess.id, 1);
@@ -4901,11 +4921,13 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 				default:
 					fcport->login_pause = 1;
 					tfcp->conflict = fcport;
-					qlt_schedule_sess_for_deletion(tfcp);
+					dfcp = tfcp;
 					break;
 				}
 			}
 			spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+			if (dfcp)
+				qlt_schedule_sess_for_deletion(tfcp);
 
 			wwn = wwn_to_u64(fcport->node_name);
 
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index ead6813ea9b3..5546ac9c3d9d 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1227,10 +1227,10 @@ static void qla24xx_chk_fcp_state(struct fc_port *sess)
 	}
 }
 
-/* ha->tgt.sess_lock supposed to be held on entry */
 void qlt_schedule_sess_for_deletion(struct fc_port *sess)
 {
 	struct qla_tgt *tgt = sess->tgt;
+	struct qla_hw_data *ha = sess->vha->hw;
 	unsigned long flags;
 
 	if (sess->disc_state == DSC_DELETE_PEND)
@@ -1247,16 +1247,16 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess)
 			return;
 	}
 
+	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
 	if (sess->deleted == QLA_SESS_DELETED)
 		sess->logout_on_delete = 0;
 
-	spin_lock_irqsave(&sess->vha->work_lock, flags);
 	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
-		spin_unlock_irqrestore(&sess->vha->work_lock, flags);
+		spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 		return;
 	}
 	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
-	spin_unlock_irqrestore(&sess->vha->work_lock, flags);
+	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 
 	sess->disc_state = DSC_DELETE_PEND;
 
@@ -1265,13 +1265,10 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess)
 	ql_dbg(ql_dbg_tgt, sess->vha, 0xe001,
 	    "Scheduling sess %p for deletion\n", sess);
 
-	/* use cancel to push work element through before re-queue */
-	cancel_work_sync(&sess->del_work);
 	INIT_WORK(&sess->del_work, qla24xx_delete_sess_fn);
-	queue_work(sess->vha->hw->wq, &sess->del_work);
+	WARN_ON(!queue_work(sess->vha->hw->wq, &sess->del_work));
 }
 
-/* ha->tgt.sess_lock supposed to be held on entry */
 static void qlt_clear_tgt_db(struct qla_tgt *tgt)
 {
 	struct fc_port *sess;
@@ -1454,8 +1451,8 @@ qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport, int max_gen)
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf008, "qla_tgt_fc_port_deleted %p", sess);
 
 	sess->local = 1;
-	qlt_schedule_sess_for_deletion(sess);
 	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+	qlt_schedule_sess_for_deletion(sess);
 }
 
 static inline int test_tgt_sess_count(struct qla_tgt *tgt)
@@ -1515,10 +1512,8 @@ int qlt_stop_phase1(struct qla_tgt *tgt)
 	 * Lock is needed, because we still can get an incoming packet.
 	 */
 	mutex_lock(&vha->vha_tgt.tgt_mutex);
-	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
 	tgt->tgt_stop = 1;
 	qlt_clear_tgt_db(tgt);
-	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 	mutex_unlock(&vha->vha_tgt.tgt_mutex);
 	mutex_unlock(&qla_tgt_mutex);
 
@@ -4869,8 +4864,6 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 				    sess);
 				qlt_send_term_imm_notif(vha, iocb, 1);
 				res = 0;
-				spin_lock_irqsave(&tgt->ha->tgt.sess_lock,
-				    flags);
 				break;
 			}
 
diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h
index fc233717355f..817f312023a9 100644
--- a/drivers/scsi/qla4xxx/ql4_def.h
+++ b/drivers/scsi/qla4xxx/ql4_def.h
@@ -168,6 +168,8 @@
 #define DEV_DB_NON_PERSISTENT	0
 #define DEV_DB_PERSISTENT	1
 
+#define QL4_ISP_REG_DISCONNECT 0xffffffffU
+
 #define COPY_ISID(dst_isid, src_isid) {			\
 	int i, j;					\
 	for (i = 0, j = ISID_SIZE - 1; i < ISID_SIZE;)	\
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 589634358c83..94c14ce94da2 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -262,6 +262,24 @@ static struct iscsi_transport qla4xxx_iscsi_transport = {
 
 static struct scsi_transport_template *qla4xxx_scsi_transport;
 
+static int qla4xxx_isp_check_reg(struct scsi_qla_host *ha)
+{
+	u32 reg_val = 0;
+	int rval = QLA_SUCCESS;
+
+	if (is_qla8022(ha))
+		reg_val = readl(&ha->qla4_82xx_reg->host_status);
+	else if (is_qla8032(ha) || is_qla8042(ha))
+		reg_val = qla4_8xxx_rd_direct(ha, QLA8XXX_PEG_ALIVE_COUNTER);
+	else
+		reg_val = readw(&ha->reg->ctrl_status);
+
+	if (reg_val == QL4_ISP_REG_DISCONNECT)
+		rval = QLA_ERROR;
+
+	return rval;
+}
+
 static int qla4xxx_send_ping(struct Scsi_Host *shost, uint32_t iface_num,
 			     uint32_t iface_type, uint32_t payload_size,
 			     uint32_t pid, struct sockaddr *dst_addr)
@@ -9184,10 +9202,17 @@ static int qla4xxx_eh_abort(struct scsi_cmnd *cmd)
 	struct srb *srb = NULL;
 	int ret = SUCCESS;
 	int wait = 0;
+	int rval;
 
 	ql4_printk(KERN_INFO, ha, "scsi%ld:%d:%llu: Abort command issued cmd=%p, cdb=0x%x\n",
 		   ha->host_no, id, lun, cmd, cmd->cmnd[0]);
 
+	rval = qla4xxx_isp_check_reg(ha);
+	if (rval != QLA_SUCCESS) {
+		ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, exiting.\n");
+		return FAILED;
+	}
+
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	srb = (struct srb *) CMD_SP(cmd);
 	if (!srb) {
@@ -9239,6 +9264,7 @@ static int qla4xxx_eh_device_reset(struct scsi_cmnd *cmd)
 	struct scsi_qla_host *ha = to_qla_host(cmd->device->host);
 	struct ddb_entry *ddb_entry = cmd->device->hostdata;
 	int ret = FAILED, stat;
+	int rval;
 
 	if (!ddb_entry)
 		return ret;
@@ -9258,6 +9284,12 @@ static int qla4xxx_eh_device_reset(struct scsi_cmnd *cmd)
 		      cmd, jiffies, cmd->request->timeout / HZ,
 		      ha->dpc_flags, cmd->result, cmd->allowed));
 
+	rval = qla4xxx_isp_check_reg(ha);
+	if (rval != QLA_SUCCESS) {
+		ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, exiting.\n");
+		return FAILED;
+	}
+
 	/* FIXME: wait for hba to go online */
 	stat = qla4xxx_reset_lun(ha, ddb_entry, cmd->device->lun);
 	if (stat != QLA_SUCCESS) {
@@ -9301,6 +9333,7 @@ static int qla4xxx_eh_target_reset(struct scsi_cmnd *cmd)
 	struct scsi_qla_host *ha = to_qla_host(cmd->device->host);
 	struct ddb_entry *ddb_entry = cmd->device->hostdata;
 	int stat, ret;
+	int rval;
 
 	if (!ddb_entry)
 		return FAILED;
@@ -9318,6 +9351,12 @@ static int qla4xxx_eh_target_reset(struct scsi_cmnd *cmd)
 		      ha->host_no, cmd, jiffies, cmd->request->timeout / HZ,
 		      ha->dpc_flags, cmd->result, cmd->allowed));
 
+	rval = qla4xxx_isp_check_reg(ha);
+	if (rval != QLA_SUCCESS) {
+		ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, exiting.\n");
+		return FAILED;
+	}
+
 	stat = qla4xxx_reset_target(ha, ddb_entry);
 	if (stat != QLA_SUCCESS) {
 		starget_printk(KERN_INFO, scsi_target(cmd->device),
@@ -9372,9 +9411,16 @@ static int qla4xxx_eh_host_reset(struct scsi_cmnd *cmd)
 {
 	int return_status = FAILED;
 	struct scsi_qla_host *ha;
+	int rval;
 
 	ha = to_qla_host(cmd->device->host);
 
+	rval = qla4xxx_isp_check_reg(ha);
+	if (rval != QLA_SUCCESS) {
+		ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, exiting.\n");
+		return FAILED;
+	}
+
 	if ((is_qla8032(ha) || is_qla8042(ha)) && ql4xdontresethba)
 		qla4_83xx_set_idc_dontreset(ha);
 
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index ac3b1c36c478..946039117bf4 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -229,7 +229,8 @@ static void scsi_eh_reset(struct scsi_cmnd *scmd)
 
 static void scsi_eh_inc_host_failed(struct rcu_head *head)
 {
-	struct Scsi_Host *shost = container_of(head, typeof(*shost), rcu);
+	struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu);
+	struct Scsi_Host *shost = scmd->device->host;
 	unsigned long flags;
 
 	spin_lock_irqsave(shost->host_lock, flags);
@@ -265,7 +266,7 @@ void scsi_eh_scmd_add(struct scsi_cmnd *scmd)
 	 * Ensure that all tasks observe the host state change before the
 	 * host_failed change.
 	 */
-	call_rcu(&shost->rcu, scsi_eh_inc_host_failed);
+	call_rcu(&scmd->rcu, scsi_eh_inc_host_failed);
 }
 
 /**
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 393f9db8f41b..1d83f29aee74 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -683,6 +683,7 @@ static bool scsi_end_request(struct request *req, blk_status_t error,
 	if (!blk_rq_is_scsi(req)) {
 		WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED));
 		cmd->flags &= ~SCMD_INITIALIZED;
+		destroy_rcu_head(&cmd->rcu);
 	}
 
 	if (req->mq_ctx) {
@@ -732,6 +733,8 @@ static blk_status_t __scsi_error_from_host_byte(struct scsi_cmnd *cmd,
 		int result)
 {
 	switch (host_byte(result)) {
+	case DID_OK:
+		return BLK_STS_OK;
 	case DID_TRANSPORT_FAILFAST:
 		return BLK_STS_TRANSPORT;
 	case DID_TARGET_FAILURE:
@@ -1174,6 +1177,7 @@ static void scsi_initialize_rq(struct request *rq)
 	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
 
 	scsi_req_init(&cmd->req);
+	init_rcu_head(&cmd->rcu);
 	cmd->jiffies_at_alloc = jiffies;
 	cmd->retries = 0;
 }
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index bff21e636ddd..1fa84d6a0f8b 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2484,6 +2484,8 @@ sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer)
 				sector_size = old_sector_size;
 				goto got_data;
 			}
+			/* Remember that READ CAPACITY(16) succeeded */
+			sdp->try_rc_10_first = 0;
 		}
 	}
 
@@ -2595,6 +2597,7 @@ sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer)
 	int res;
 	struct scsi_device *sdp = sdkp->device;
 	struct scsi_mode_data data;
+	int disk_ro = get_disk_ro(sdkp->disk);
 	int old_wp = sdkp->write_prot;
 
 	set_disk_ro(sdkp->disk, 0);
@@ -2635,7 +2638,7 @@ sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer)
 			  "Test WP failed, assume Write Enabled\n");
 	} else {
 		sdkp->write_prot = ((data.device_specific & 0x80) != 0);
-		set_disk_ro(sdkp->disk, sdkp->write_prot);
+		set_disk_ro(sdkp->disk, sdkp->write_prot || disk_ro);
 		if (sdkp->first_scan || old_wp != sdkp->write_prot) {
 			sd_printk(KERN_NOTICE, sdkp, "Write Protect is %s\n",
 				  sdkp->write_prot ? "on" : "off");
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 8f3669fd490d..41df75eea57b 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -403,7 +403,7 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf)
  */
 static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 {
-	u64 zone_blocks;
+	u64 zone_blocks = 0;
 	sector_t block = 0;
 	unsigned char *buf;
 	unsigned char *rec;
@@ -421,10 +421,8 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 
 	/* Do a report zone to get the same field */
 	ret = sd_zbc_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, 0);
-	if (ret) {
-		zone_blocks = 0;
-		goto out;
-	}
+	if (ret)
+		goto out_free;
 
 	same = buf[4] & 0x0f;
 	if (same > 0) {
@@ -464,7 +462,7 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 			ret = sd_zbc_report_zones(sdkp, buf,
 						  SD_ZBC_BUF_SIZE, block);
 			if (ret)
-				return ret;
+				goto out_free;
 		}
 
 	} while (block < sdkp->capacity);
@@ -472,35 +470,32 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 	zone_blocks = sdkp->zone_blocks;
 
 out:
-	kfree(buf);
-
 	if (!zone_blocks) {
 		if (sdkp->first_scan)
 			sd_printk(KERN_NOTICE, sdkp,
 				  "Devices with non constant zone "
 				  "size are not supported\n");
-		return -ENODEV;
-	}
-
-	if (!is_power_of_2(zone_blocks)) {
+		ret = -ENODEV;
+	} else if (!is_power_of_2(zone_blocks)) {
 		if (sdkp->first_scan)
 			sd_printk(KERN_NOTICE, sdkp,
 				  "Devices with non power of 2 zone "
 				  "size are not supported\n");
-		return -ENODEV;
-	}
-
-	if (logical_to_sectors(sdkp->device, zone_blocks) > UINT_MAX) {
+		ret = -ENODEV;
+	} else if (logical_to_sectors(sdkp->device, zone_blocks) > UINT_MAX) {
 		if (sdkp->first_scan)
 			sd_printk(KERN_NOTICE, sdkp,
 				  "Zone size too large\n");
-		return -ENODEV;
+		ret = -ENODEV;
+	} else {
+		sdkp->zone_blocks = zone_blocks;
+		sdkp->zone_shift = ilog2(zone_blocks);
 	}
 
-	sdkp->zone_blocks = zone_blocks;
-	sdkp->zone_shift = ilog2(zone_blocks);
+out_free:
+	kfree(buf);
 
-	return 0;
+	return ret;
 }
 
 /**
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 40fc7a590e81..8c51d628b52e 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1311,7 +1311,8 @@ static int storvsc_do_io(struct hv_device *device,
 			 */
 			cpumask_and(&alloced_mask, &stor_device->alloced_cpus,
 				    cpumask_of_node(cpu_to_node(q_num)));
-			for_each_cpu(tgt_cpu, &alloced_mask) {
+			for_each_cpu_wrap(tgt_cpu, &alloced_mask,
+					outgoing_channel->target_cpu + 1) {
 				if (tgt_cpu != outgoing_channel->target_cpu) {
 					outgoing_channel =
 					stor_device->stor_chns[tgt_cpu];
@@ -1657,7 +1658,7 @@ static struct scsi_host_template scsi_driver = {
 	.eh_timed_out =		storvsc_eh_timed_out,
 	.slave_alloc =		storvsc_device_alloc,
 	.slave_configure =	storvsc_device_configure,
-	.cmd_per_lun =		255,
+	.cmd_per_lun =		2048,
 	.this_id =		-1,
 	.use_clustering =	ENABLE_CLUSTERING,
 	/* Make sure we dont get a sg segment crosses a page boundary */
diff --git a/drivers/scsi/sym53c8xx_2/sym_hipd.c b/drivers/scsi/sym53c8xx_2/sym_hipd.c
index ca360daa6a25..378af306fda1 100644
--- a/drivers/scsi/sym53c8xx_2/sym_hipd.c
+++ b/drivers/scsi/sym53c8xx_2/sym_hipd.c
@@ -536,7 +536,7 @@ sym_getsync(struct sym_hcb *np, u_char dt, u_char sfac, u_char *divp, u_char *fa
 	 *  Look for the greatest clock divisor that allows an 
 	 *  input speed faster than the period.
 	 */
-	while (div-- > 0)
+	while (--div > 0)
 		if (kpc >= (div_10M[div] << 2)) break;
 
 	/*
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index facee2b97926..c5b1bf1cadcb 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -4331,6 +4331,8 @@ static int ufshcd_slave_alloc(struct scsi_device *sdev)
 	/* REPORT SUPPORTED OPERATION CODES is not supported */
 	sdev->no_report_opcodes = 1;
 
+	/* WRITE_SAME command is not supported */
+	sdev->no_write_same = 1;
 
 	ufshcd_set_queue_depth(sdev);
 
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 7c28e8d4955a..45d04631888a 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -91,9 +91,6 @@ struct virtio_scsi_vq {
 struct virtio_scsi_target_state {
 	seqcount_t tgt_seq;
 
-	/* Count of outstanding requests. */
-	atomic_t reqs;
-
 	/* Currently active virtqueue for requests sent to this target. */
 	struct virtio_scsi_vq *req_vq;
 };
@@ -152,8 +149,6 @@ static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf)
 	struct virtio_scsi_cmd *cmd = buf;
 	struct scsi_cmnd *sc = cmd->sc;
 	struct virtio_scsi_cmd_resp *resp = &cmd->resp.cmd;
-	struct virtio_scsi_target_state *tgt =
-				scsi_target(sc->device)->hostdata;
 
 	dev_dbg(&sc->device->sdev_gendev,
 		"cmd %p response %u status %#02x sense_len %u\n",
@@ -210,8 +205,6 @@ static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf)
 	}
 
 	sc->scsi_done(sc);
-
-	atomic_dec(&tgt->reqs);
 }
 
 static void virtscsi_vq_done(struct virtio_scsi *vscsi,
@@ -529,11 +522,20 @@ static void virtio_scsi_init_hdr_pi(struct virtio_device *vdev,
 }
 #endif
 
-static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
-				 struct virtio_scsi_vq *req_vq,
+static struct virtio_scsi_vq *virtscsi_pick_vq_mq(struct virtio_scsi *vscsi,
+						  struct scsi_cmnd *sc)
+{
+	u32 tag = blk_mq_unique_tag(sc->request);
+	u16 hwq = blk_mq_unique_tag_to_hwq(tag);
+
+	return &vscsi->req_vqs[hwq];
+}
+
+static int virtscsi_queuecommand(struct Scsi_Host *shost,
 				 struct scsi_cmnd *sc)
 {
-	struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
+	struct virtio_scsi *vscsi = shost_priv(shost);
+	struct virtio_scsi_vq *req_vq = virtscsi_pick_vq_mq(vscsi, sc);
 	struct virtio_scsi_cmd *cmd = scsi_cmd_priv(sc);
 	unsigned long flags;
 	int req_size;
@@ -576,79 +578,6 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
 	return 0;
 }
 
-static int virtscsi_queuecommand_single(struct Scsi_Host *sh,
-					struct scsi_cmnd *sc)
-{
-	struct virtio_scsi *vscsi = shost_priv(sh);
-	struct virtio_scsi_target_state *tgt =
-				scsi_target(sc->device)->hostdata;
-
-	atomic_inc(&tgt->reqs);
-	return virtscsi_queuecommand(vscsi, &vscsi->req_vqs[0], sc);
-}
-
-static struct virtio_scsi_vq *virtscsi_pick_vq_mq(struct virtio_scsi *vscsi,
-						  struct scsi_cmnd *sc)
-{
-	u32 tag = blk_mq_unique_tag(sc->request);
-	u16 hwq = blk_mq_unique_tag_to_hwq(tag);
-
-	return &vscsi->req_vqs[hwq];
-}
-
-static struct virtio_scsi_vq *virtscsi_pick_vq(struct virtio_scsi *vscsi,
-					       struct virtio_scsi_target_state *tgt)
-{
-	struct virtio_scsi_vq *vq;
-	unsigned long flags;
-	u32 queue_num;
-
-	local_irq_save(flags);
-	if (atomic_inc_return(&tgt->reqs) > 1) {
-		unsigned long seq;
-
-		do {
-			seq = read_seqcount_begin(&tgt->tgt_seq);
-			vq = tgt->req_vq;
-		} while (read_seqcount_retry(&tgt->tgt_seq, seq));
-	} else {
-		/* no writes can be concurrent because of atomic_t */
-		write_seqcount_begin(&tgt->tgt_seq);
-
-		/* keep previous req_vq if a reader just arrived */
-		if (unlikely(atomic_read(&tgt->reqs) > 1)) {
-			vq = tgt->req_vq;
-			goto unlock;
-		}
-
-		queue_num = smp_processor_id();
-		while (unlikely(queue_num >= vscsi->num_queues))
-			queue_num -= vscsi->num_queues;
-		tgt->req_vq = vq = &vscsi->req_vqs[queue_num];
- unlock:
-		write_seqcount_end(&tgt->tgt_seq);
-	}
-	local_irq_restore(flags);
-
-	return vq;
-}
-
-static int virtscsi_queuecommand_multi(struct Scsi_Host *sh,
-				       struct scsi_cmnd *sc)
-{
-	struct virtio_scsi *vscsi = shost_priv(sh);
-	struct virtio_scsi_target_state *tgt =
-				scsi_target(sc->device)->hostdata;
-	struct virtio_scsi_vq *req_vq;
-
-	if (shost_use_blk_mq(sh))
-		req_vq = virtscsi_pick_vq_mq(vscsi, sc);
-	else
-		req_vq = virtscsi_pick_vq(vscsi, tgt);
-
-	return virtscsi_queuecommand(vscsi, req_vq, sc);
-}
-
 static int virtscsi_tmf(struct virtio_scsi *vscsi, struct virtio_scsi_cmd *cmd)
 {
 	DECLARE_COMPLETION_ONSTACK(comp);
@@ -775,7 +704,6 @@ static int virtscsi_target_alloc(struct scsi_target *starget)
 		return -ENOMEM;
 
 	seqcount_init(&tgt->tgt_seq);
-	atomic_set(&tgt->reqs, 0);
 	tgt->req_vq = &vscsi->req_vqs[0];
 
 	starget->hostdata = tgt;
@@ -805,33 +733,13 @@ static enum blk_eh_timer_return virtscsi_eh_timed_out(struct scsi_cmnd *scmnd)
 	return BLK_EH_RESET_TIMER;
 }
 
-static struct scsi_host_template virtscsi_host_template_single = {
-	.module = THIS_MODULE,
-	.name = "Virtio SCSI HBA",
-	.proc_name = "virtio_scsi",
-	.this_id = -1,
-	.cmd_size = sizeof(struct virtio_scsi_cmd),
-	.queuecommand = virtscsi_queuecommand_single,
-	.change_queue_depth = virtscsi_change_queue_depth,
-	.eh_abort_handler = virtscsi_abort,
-	.eh_device_reset_handler = virtscsi_device_reset,
-	.eh_timed_out = virtscsi_eh_timed_out,
-	.slave_alloc = virtscsi_device_alloc,
-
-	.dma_boundary = UINT_MAX,
-	.use_clustering = ENABLE_CLUSTERING,
-	.target_alloc = virtscsi_target_alloc,
-	.target_destroy = virtscsi_target_destroy,
-	.track_queue_depth = 1,
-};
-
-static struct scsi_host_template virtscsi_host_template_multi = {
+static struct scsi_host_template virtscsi_host_template = {
 	.module = THIS_MODULE,
 	.name = "Virtio SCSI HBA",
 	.proc_name = "virtio_scsi",
 	.this_id = -1,
 	.cmd_size = sizeof(struct virtio_scsi_cmd),
-	.queuecommand = virtscsi_queuecommand_multi,
+	.queuecommand = virtscsi_queuecommand,
 	.change_queue_depth = virtscsi_change_queue_depth,
 	.eh_abort_handler = virtscsi_abort,
 	.eh_device_reset_handler = virtscsi_device_reset,
@@ -844,6 +752,7 @@ static struct scsi_host_template virtscsi_host_template_multi = {
 	.target_destroy = virtscsi_target_destroy,
 	.map_queues = virtscsi_map_queues,
 	.track_queue_depth = 1,
+	.force_blk_mq = 1,
 };
 
 #define virtscsi_config_get(vdev, fld) \
@@ -936,7 +845,6 @@ static int virtscsi_probe(struct virtio_device *vdev)
 	u32 sg_elems, num_targets;
 	u32 cmd_per_lun;
 	u32 num_queues;
-	struct scsi_host_template *hostt;
 
 	if (!vdev->config->get) {
 		dev_err(&vdev->dev, "%s failure: config access disabled\n",
@@ -949,12 +857,7 @@ static int virtscsi_probe(struct virtio_device *vdev)
 
 	num_targets = virtscsi_config_get(vdev, max_target) + 1;
 
-	if (num_queues == 1)
-		hostt = &virtscsi_host_template_single;
-	else
-		hostt = &virtscsi_host_template_multi;
-
-	shost = scsi_host_alloc(hostt,
+	shost = scsi_host_alloc(&virtscsi_host_template,
 		sizeof(*vscsi) + sizeof(vscsi->req_vqs[0]) * num_queues);
 	if (!shost)
 		return -ENOMEM;
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index d8d4a902a88d..2280b2351739 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -68,6 +68,9 @@ struct scsi_cmnd {
 	struct list_head list;  /* scsi_cmnd participates in queue lists */
 	struct list_head eh_entry; /* entry for the host eh_cmd_q */
 	struct delayed_work abort_work;
+
+	struct rcu_head rcu;
+
 	int eh_eflags;		/* Used by error handlr */
 
 	/*
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 4e418fb539f8..12f454cb6f61 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -437,6 +437,9 @@ struct scsi_host_template {
 	/* True if the controller does not support WRITE SAME */
 	unsigned no_write_same:1;
 
+	/* True if the low-level driver supports blk-mq only */
+	unsigned force_blk_mq:1;
+
 	/*
 	 * Countdown for host blocking with no commands outstanding.
 	 */
@@ -553,8 +556,6 @@ struct Scsi_Host {
 		struct blk_mq_tag_set	tag_set;
 	};
 
-	struct rcu_head rcu;
-
 	atomic_t host_busy;		   /* commands actually active on low-level */
 	atomic_t host_blocked;