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_ass