Merge remote-tracking branch 'scsi/for-next'

76 files changed, 4090 insertions, 1933 deletions

diff --git a/drivers/block/cciss.h b/drivers/block/cciss.h
index 7fda30e4a241..428766d1ce80 100644
--- a/drivers/block/cciss.h
+++ b/drivers/block/cciss.h
@@ -402,27 +402,27 @@ static bool SA5_performant_intr_pending(ctlr_info_t *h)
 }
 
 static struct access_method SA5_access = {
-	SA5_submit_command,
-	SA5_intr_mask,
-	SA5_fifo_full,
-	SA5_intr_pending,
-	SA5_completed,
+	.submit_command = SA5_submit_command,
+	.set_intr_mask = SA5_intr_mask,
+	.fifo_full = SA5_fifo_full,
+	.intr_pending = SA5_intr_pending,
+	.command_completed = SA5_completed,
 };
 
 static struct access_method SA5B_access = {
-        SA5_submit_command,
-        SA5B_intr_mask,
-        SA5_fifo_full,
-        SA5B_intr_pending,
-        SA5_completed,
+	.submit_command = SA5_submit_command,
+	.set_intr_mask = SA5B_intr_mask,
+	.fifo_full = SA5_fifo_full,
+	.intr_pending = SA5B_intr_pending,
+	.command_completed = SA5_completed,
 };
 
 static struct access_method SA5_performant_access = {
-	SA5_submit_command,
-	SA5_performant_intr_mask,
-	SA5_fifo_full,
-	SA5_performant_intr_pending,
-	SA5_performant_completed,
+	.submit_command = SA5_submit_command,
+	.set_intr_mask = SA5_performant_intr_mask,
+	.fifo_full = SA5_fifo_full,
+	.intr_pending = SA5_performant_intr_pending,
+	.command_completed = SA5_performant_completed,
 };
 
 struct board_type {
diff --git a/drivers/message/fusion/mptlan.h b/drivers/message/fusion/mptlan.h
index 8946e19dbfc8..8a24494f8c4d 100644
--- a/drivers/message/fusion/mptlan.h
+++ b/drivers/message/fusion/mptlan.h
@@ -65,7 +65,6 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <linux/miscdevice.h>
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
 #include <linux/delay.h>
diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index 4f5ca794bb71..acc33440bca0 100644
--- a/drivers/scsi/NCR5380.c
+++ b/drivers/scsi/NCR5380.c
@@ -96,17 +96,6 @@
  * of chips.  To use it, you write an architecture specific functions
  * and macros and include this file in your driver.
  *
- * These macros control options :
- * AUTOSENSE - if defined, REQUEST SENSE will be performed automatically
- * for commands that return with a CHECK CONDITION status.
- *
- * DIFFERENTIAL - if defined, NCR53c81 chips will use external differential
- * transceivers.
- *
- * PSEUDO_DMA - if defined, PSEUDO DMA is used during the data transfer phases.
- *
- * REAL_DMA - if defined, REAL DMA is used during the data transfer phases.
- *
  * These macros MUST be defined :
  *
  * NCR5380_read(register)  - read from the specified register
@@ -347,7 +336,7 @@ static void NCR5380_print_phase(struct Scsi_Host *instance)
 #endif
 
 /**
- * NCR58380_info - report driver and host information
+ * NCR5380_info - report driver and host information
  * @instance: relevant scsi host instance
  *
  * For use as the host template info() handler.
@@ -360,33 +349,6 @@ static const char *NCR5380_info(struct Scsi_Host *instance)
 	return hostdata->info;
 }
 
-static void prepare_info(struct Scsi_Host *instance)
-{
-	struct NCR5380_hostdata *hostdata = shost_priv(instance);
-
-	snprintf(hostdata->info, sizeof(hostdata->info),
-	         "%s, irq %d, "
-		 "io_port 0x%lx, base 0x%lx, "
-	         "can_queue %d, cmd_per_lun %d, "
-	         "sg_tablesize %d, this_id %d, "
-	         "flags { %s%s%s}, "
-	         "options { %s} ",
-	         instance->hostt->name, instance->irq,
-		 hostdata->io_port, hostdata->base,
-	         instance->can_queue, instance->cmd_per_lun,
-	         instance->sg_tablesize, instance->this_id,
-	         hostdata->flags & FLAG_DMA_FIXUP     ? "DMA_FIXUP "     : "",
-	         hostdata->flags & FLAG_NO_PSEUDO_DMA ? "NO_PSEUDO_DMA " : "",
-	         hostdata->flags & FLAG_TOSHIBA_DELAY ? "TOSHIBA_DELAY "  : "",
-#ifdef DIFFERENTIAL
-	         "DIFFERENTIAL "
-#endif
-#ifdef PARITY
-	         "PARITY "
-#endif
-	         "");
-}
-
 /**
  * NCR5380_init - initialise an NCR5380
  * @instance: adapter to configure
@@ -436,7 +398,14 @@ static int NCR5380_init(struct Scsi_Host *instance, int flags)
 	if (!hostdata->work_q)
 		return -ENOMEM;
 
-	prepare_info(instance);
+	snprintf(hostdata->info, sizeof(hostdata->info),
+		"%s, irq %d, io_port 0x%lx, base 0x%lx, can_queue %d, cmd_per_lun %d, sg_tablesize %d, this_id %d, flags { %s%s%s}",
+		instance->hostt->name, instance->irq, hostdata->io_port,
+		hostdata->base, instance->can_queue, instance->cmd_per_lun,
+		instance->sg_tablesize, instance->this_id,
+		hostdata->flags & FLAG_DMA_FIXUP     ? "DMA_FIXUP "     : "",
+		hostdata->flags & FLAG_NO_PSEUDO_DMA ? "NO_PSEUDO_DMA " : "",
+		hostdata->flags & FLAG_TOSHIBA_DELAY ? "TOSHIBA_DELAY " : "");
 
 	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
 	NCR5380_write(MODE_REG, MR_BASE);
@@ -622,8 +591,9 @@ static inline void maybe_release_dma_irq(struct Scsi_Host *instance)
 	    list_empty(&hostdata->unissued) &&
 	    list_empty(&hostdata->autosense) &&
 	    !hostdata->connected &&
-	    !hostdata->selecting)
+	    !hostdata->selecting) {
 		NCR5380_release_dma_irq(instance);
+	}
 }
 
 /**
@@ -962,6 +932,7 @@ static irqreturn_t __maybe_unused NCR5380_intr(int irq, void *dev_id)
 
 static struct scsi_cmnd *NCR5380_select(struct Scsi_Host *instance,
                                         struct scsi_cmnd *cmd)
+	__releases(&hostdata->lock) __acquires(&hostdata->lock)
 {
 	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	unsigned char tmp[3], phase;
@@ -1194,8 +1165,16 @@ static struct scsi_cmnd *NCR5380_select(struct Scsi_Host *instance,
 	data = tmp;
 	phase = PHASE_MSGOUT;
 	NCR5380_transfer_pio(instance, &phase, &len, &data);
+	if (len) {
+		NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
+		cmd->result = DID_ERROR << 16;
+		complete_cmd(instance, cmd);
+		dsprintk(NDEBUG_SELECTION, instance, "IDENTIFY message transfer failed\n");
+		cmd = NULL;
+		goto out;
+	}
+
 	dsprintk(NDEBUG_SELECTION, instance, "nexus established.\n");
-	/* XXX need to handle errors here */
 
 	hostdata->connected = cmd;
 	hostdata->busy[cmd->device->id] |= 1 << cmd->device->lun;
@@ -1654,6 +1633,7 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance,
  */
 
 static void NCR5380_information_transfer(struct Scsi_Host *instance)
+	__releases(&hostdata->lock) __acquires(&hostdata->lock)
 {
 	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	unsigned char msgout = NOP;
diff --git a/drivers/scsi/NCR5380.h b/drivers/scsi/NCR5380.h
index 51a3567a6fb2..d78f0957d865 100644
--- a/drivers/scsi/NCR5380.h
+++ b/drivers/scsi/NCR5380.h
@@ -81,11 +81,7 @@
 #define ICR_ASSERT_ATN		0x02	/* rw Set to assert ATN */
 #define ICR_ASSERT_DATA		0x01	/* rw SCSI_DATA_REG is asserted */
 
-#ifdef DIFFERENTIAL
-#define ICR_BASE		ICR_DIFF_ENABLE
-#else
 #define ICR_BASE		0
-#endif
 
 #define MODE_REG		2
 /*
@@ -102,11 +98,7 @@
 #define MR_DMA_MODE		0x02	/* rw DMA / pseudo DMA mode */
 #define MR_ARBITRATE		0x01	/* rw start arbitration */
 
-#ifdef PARITY
-#define MR_BASE			MR_ENABLE_PAR_CHECK
-#else
 #define MR_BASE			0
-#endif
 
 #define TARGET_COMMAND_REG	3
 #define TCR_LAST_BYTE_SENT	0x80	/* ro DMA done */
@@ -174,11 +166,7 @@
 #define CSR_SCSI_BUF_RDY       0x02	/* ro  SCSI buffer read */
 #define CSR_GATED_53C80_IRQ    0x01	/* ro  Last block xferred */
 
-#if 0
-#define CSR_BASE CSR_SCSI_BUFF_INTR | CSR_53C80_INTR
-#else
 #define CSR_BASE CSR_53C80_INTR
-#endif
 
 /* Note : PHASE_* macros are based on the values of the STATUS register */
 #define PHASE_MASK 	(SR_MSG | SR_CD | SR_IO)
@@ -234,11 +222,9 @@ struct NCR5380_hostdata {
 	unsigned char id_higher_mask;		/* All bits above id_mask */
 	unsigned char last_message;		/* Last Message Out */
 	unsigned long region_size;		/* Size of address/port range */
-	char info[256];
+	char info[168];				/* Host banner message */
 };
 
-#ifdef __KERNEL__
-
 struct NCR5380_cmd {
 	struct list_head list;
 };
@@ -331,5 +317,4 @@ static inline int NCR5380_dma_residual_none(struct NCR5380_hostdata *hostdata)
 	return 0;
 }
 
-#endif				/* __KERNEL__ */
 #endif				/* NCR5380_H */
diff --git a/drivers/scsi/atari_scsi.c b/drivers/scsi/atari_scsi.c
index 105b35393ce9..f792420c533e 100644
--- a/drivers/scsi/atari_scsi.c
+++ b/drivers/scsi/atari_scsi.c
@@ -178,37 +178,6 @@ static int scsi_dma_is_ignored_buserr(unsigned char dma_stat)
 }
 
 
-#if 0
-/* Dead code... wasn't called anyway :-) and causes some trouble, because at
- * end-of-DMA, both SCSI ints are triggered simultaneously, so the NCR int has
- * to clear the DMA int pending bit before it allows other level 6 interrupts.
- */
-static void scsi_dma_buserr(int irq, void *dummy)
-{
-	unsigned char dma_stat = tt_scsi_dma.dma_ctrl;
-
-	/* Don't do anything if a NCR interrupt is pending. Probably it's just
-	 * masked... */
-	if (atari_irq_pending(IRQ_TT_MFP_SCSI))
-		return;
-
-	printk("Bad SCSI DMA interrupt! dma_addr=0x%08lx dma_stat=%02x dma_cnt=%08lx\n",
-	       SCSI_DMA_READ_P(dma_addr), dma_stat, SCSI_DMA_READ_P(dma_cnt));
-	if (dma_stat & 0x80) {
-		if (!scsi_dma_is_ignored_buserr(dma_stat))
-			printk("SCSI DMA bus error -- bad DMA programming!\n");
-	} else {
-		/* Under normal circumstances we never should get to this point,
-		 * since both interrupts are triggered simultaneously and the 5380
-		 * int has higher priority. When this irq is handled, that DMA
-		 * interrupt is cleared. So a warning message is printed here.
-		 */
-		printk("SCSI DMA intr ?? -- this shouldn't happen!\n");
-	}
-}
-#endif
-
-
 static irqreturn_t scsi_tt_intr(int irq, void *dev)
 {
 	struct Scsi_Host *instance = dev;
@@ -713,7 +682,8 @@ static int atari_scsi_bus_reset(struct scsi_cmnd *cmd)
 	if (IS_A_TT()) {
 		tt_scsi_dma.dma_ctrl = 0;
 	} else {
-		st_dma.dma_mode_status = 0x90;
+		if (stdma_is_locked_by(scsi_falcon_intr))
+			st_dma.dma_mode_status = 0x90;
 		atari_dma_active = 0;
 		atari_dma_orig_addr = NULL;
 	}
@@ -813,7 +783,7 @@ static int __init atari_scsi_probe(struct platform_device *pdev)
 			return -ENOMEM;
 		}
 		atari_dma_phys_buffer = atari_stram_to_phys(atari_dma_buffer);
-		atari_dma_orig_addr = 0;
+		atari_dma_orig_addr = NULL;
 	}
 
 	instance = scsi_host_alloc(&atari_scsi_template,
diff --git a/drivers/scsi/be2iscsi/be.h b/drivers/scsi/be2iscsi/be.h
index b1d0fdc5d5e1..ca9440fb2325 100644
--- a/drivers/scsi/be2iscsi/be.h
+++ b/drivers/scsi/be2iscsi/be.h
@@ -84,7 +84,6 @@ static inline void queue_tail_inc(struct be_queue_info *q)
 /*ISCSI */
 
 struct be_aic_obj {		/* Adaptive interrupt coalescing (AIC) info */
-	bool enable;
 	u32 min_eqd;		/* in usecs */
 	u32 max_eqd;		/* in usecs */
 	u32 prev_eqd;		/* in usecs */
@@ -94,8 +93,6 @@ struct be_aic_obj {		/* Adaptive interrupt coalescing (AIC) info */
 };
 
 struct be_eq_obj {
-	bool todo_mcc_cq;
-	bool todo_cq;
 	u32 cq_count;
 	struct be_queue_info q;
 	struct beiscsi_hba *phba;
diff --git a/drivers/scsi/be2iscsi/be_cmds.c b/drivers/scsi/be2iscsi/be_cmds.c
index be65da2988fb..5d59e2630ce6 100644
--- a/drivers/scsi/be2iscsi/be_cmds.c
+++ b/drivers/scsi/be2iscsi/be_cmds.c
@@ -676,10 +676,10 @@ void be_wrb_hdr_prepare(struct be_mcc_wrb *wrb, int payload_len,
 				bool embedded, u8 sge_cnt)
 {
 	if (embedded)
-		wrb->embedded |= MCC_WRB_EMBEDDED_MASK;
+		wrb->emb_sgecnt_special |= MCC_WRB_EMBEDDED_MASK;
 	else
-		wrb->embedded |= (sge_cnt & MCC_WRB_SGE_CNT_MASK) <<
-						MCC_WRB_SGE_CNT_SHIFT;
+		wrb->emb_sgecnt_special |= (sge_cnt & MCC_WRB_SGE_CNT_MASK) <<
+					   MCC_WRB_SGE_CNT_SHIFT;
 	wrb->payload_length = payload_len;
 	be_dws_cpu_to_le(wrb, 8);
 }
@@ -1599,7 +1599,7 @@ int beiscsi_cmd_function_reset(struct beiscsi_hba *phba)
 {
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 	struct be_mcc_wrb *wrb = wrb_from_mbox(&ctrl->mbox_mem);
-	struct be_post_sgl_pages_req *req = embedded_payload(wrb);
+	struct be_post_sgl_pages_req *req;
 	int status;
 
 	mutex_lock(&ctrl->mbox_lock);
@@ -1700,31 +1700,34 @@ int beiscsi_cmd_iscsi_cleanup(struct beiscsi_hba *phba, unsigned short ulp)
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 	struct iscsi_cleanup_req_v1 *req_v1;
 	struct iscsi_cleanup_req *req;
+	u16 hdr_ring_id, data_ring_id;
 	struct be_mcc_wrb *wrb;
 	int status;
 
 	mutex_lock(&ctrl->mbox_lock);
 	wrb = wrb_from_mbox(&ctrl->mbox_mem);
-	req = embedded_payload(wrb);
-	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
-	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
-			   OPCODE_COMMON_ISCSI_CLEANUP, sizeof(*req));
 
-       /**
-	* TODO: Check with FW folks the chute value to be set.
-	* For now, use the ULP_MASK as the chute value.
-	*/
+	hdr_ring_id = HWI_GET_DEF_HDRQ_ID(phba, ulp);
+	data_ring_id = HWI_GET_DEF_BUFQ_ID(phba, ulp);
 	if (is_chip_be2_be3r(phba)) {
+		req = embedded_payload(wrb);
+		be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
+		be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
+				   OPCODE_COMMON_ISCSI_CLEANUP, sizeof(*req));
 		req->chute = (1 << ulp);
-		req->hdr_ring_id = HWI_GET_DEF_HDRQ_ID(phba, ulp);
-		req->data_ring_id = HWI_GET_DEF_BUFQ_ID(phba, ulp);
+		/* BE2/BE3 FW creates 8-bit ring id */
+		req->hdr_ring_id = hdr_ring_id;
+		req->data_ring_id = data_ring_id;
 	} else {
-		req_v1 = (struct iscsi_cleanup_req_v1 *)req;
+		req_v1 = embedded_payload(wrb);
+		be_wrb_hdr_prepare(wrb, sizeof(*req_v1), true, 0);
+		be_cmd_hdr_prepare(&req_v1->hdr, CMD_SUBSYSTEM_ISCSI,
+				   OPCODE_COMMON_ISCSI_CLEANUP,
+				   sizeof(*req_v1));
 		req_v1->hdr.version = 1;
-		req_v1->hdr_ring_id = cpu_to_le16(HWI_GET_DEF_HDRQ_ID(phba,
-								      ulp));
-		req_v1->data_ring_id = cpu_to_le16(HWI_GET_DEF_BUFQ_ID(phba,
-								       ulp));
+		req_v1->chute = (1 << ulp);
+		req_v1->hdr_ring_id = cpu_to_le16(hdr_ring_id);
+		req_v1->data_ring_id = cpu_to_le16(data_ring_id);
 	}
 
 	status = be_mbox_notify(ctrl);
diff --git a/drivers/scsi/be2iscsi/be_cmds.h b/drivers/scsi/be2iscsi/be_cmds.h
index 328fb5b973cd..1d40e83b0790 100644
--- a/drivers/scsi/be2iscsi/be_cmds.h
+++ b/drivers/scsi/be2iscsi/be_cmds.h
@@ -31,10 +31,16 @@ struct be_sge {
 	__le32 len;
 };
 
-#define MCC_WRB_SGE_CNT_SHIFT 3	/* bits 3 - 7 of dword 0 */
-#define MCC_WRB_SGE_CNT_MASK 0x1F	/* bits 3 - 7 of dword 0 */
 struct be_mcc_wrb {
-	u32 embedded;		/* dword 0 */
+	u32 emb_sgecnt_special;	/* dword 0 */
+	/* bits 0 - embedded    */
+	/* bits 1 - 2 reserved	*/
+	/* bits 3 - 7 sge count	*/
+	/* bits 8 - 23 reserved	*/
+	/* bits 24 - 31 special	*/
+#define MCC_WRB_EMBEDDED_MASK 1
+#define MCC_WRB_SGE_CNT_SHIFT 3
+#define MCC_WRB_SGE_CNT_MASK 0x1F
 	u32 payload_length;	/* dword 1 */
 	u32 tag0;		/* dword 2 */
 	u32 tag1;		/* dword 3 */
@@ -1133,11 +1139,6 @@ struct tcp_connect_and_offload_out {
 
 } __packed;
 
-struct be_mcc_wrb_context {
-	struct MCC_WRB *wrb;
-	int *users_final_status;
-} __packed;
-
 #define DB_DEF_PDU_RING_ID_MASK	0x3FFF	/* bits 0 - 13 */
 #define DB_DEF_PDU_CQPROC_MASK		0x3FFF	/* bits 16 - 29 */
 #define DB_DEF_PDU_REARM_SHIFT		14
diff --git a/drivers/scsi/be2iscsi/be_iscsi.c b/drivers/scsi/be2iscsi/be_iscsi.c
index ba258217614e..a4844578e357 100644
--- a/drivers/scsi/be2iscsi/be_iscsi.c
+++ b/drivers/scsi/be2iscsi/be_iscsi.c
@@ -166,33 +166,6 @@ beiscsi_conn_create(struct iscsi_cls_session *cls_session, u32 cid)
 }
 
 /**
- * beiscsi_bindconn_cid - Bind the beiscsi_conn with phba connection table
- * @beiscsi_conn: The pointer to  beiscsi_conn structure
- * @phba: The phba instance
- * @cid: The cid to free
- */
-static int beiscsi_bindconn_cid(struct beiscsi_hba *phba,
-				struct beiscsi_conn *beiscsi_conn,
-				unsigned int cid)
-{
-	uint16_t cri_index = BE_GET_CRI_FROM_CID(cid);
-
-	if (phba->conn_table[cri_index]) {
-		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG,
-			    "BS_%d : Connection table already occupied. Detected clash\n");
-
-		return -EINVAL;
-	} else {
-		beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_CONFIG,
-			    "BS_%d : phba->conn_table[%d]=%p(beiscsi_conn)\n",
-			    cri_index, beiscsi_conn);
-
-		phba->conn_table[cri_index] = beiscsi_conn;
-	}
-	return 0;
-}
-
-/**
  * beiscsi_conn_bind - Binds iscsi session/connection with TCP connection
  * @cls_session: pointer to iscsi cls session
  * @cls_conn: pointer to iscsi cls conn
@@ -212,6 +185,7 @@ int beiscsi_conn_bind(struct iscsi_cls_session *cls_session,
 	struct hwi_wrb_context *pwrb_context;
 	struct beiscsi_endpoint *beiscsi_ep;
 	struct iscsi_endpoint *ep;
+	uint16_t cri_index;
 
 	ep = iscsi_lookup_endpoint(transport_fd);
 	if (!ep)
@@ -229,20 +203,34 @@ int beiscsi_conn_bind(struct iscsi_cls_session *cls_session,
 
 		return -EEXIST;
 	}
-
-	pwrb_context = &phwi_ctrlr->wrb_context[BE_GET_CRI_FROM_CID(
-						beiscsi_ep->ep_cid)];
+	cri_index = BE_GET_CRI_FROM_CID(beiscsi_ep->ep_cid);
+	if (phba->conn_table[cri_index]) {
+		if (beiscsi_conn != phba->conn_table[cri_index] ||
+		    beiscsi_ep != phba->conn_table[cri_index]->ep) {
+			__beiscsi_log(phba, KERN_ERR,
+				      "BS_%d : conn_table not empty at %u: cid %u conn %p:%p\n",
+				      cri_index,
+				      beiscsi_ep->ep_cid,
+				      beiscsi_conn,
+				      phba->conn_table[cri_index]);
+			return -EINVAL;
+		}
+	}
 
 	beiscsi_conn->beiscsi_conn_cid = beiscsi_ep->ep_cid;
 	beiscsi_conn->ep = beiscsi_ep;
 	beiscsi_ep->conn = beiscsi_conn;
+	/**
+	 * Each connection is associated with a WRBQ kept in wrb_context.
+	 * Store doorbell offset for transmit path.
+	 */
+	pwrb_context = &phwi_ctrlr->wrb_context[cri_index];
 	beiscsi_conn->doorbell_offset = pwrb_context->doorbell_offset;
-
 	beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_CONFIG,
-		    "BS_%d : beiscsi_conn=%p conn=%p ep_cid=%d\n",
-		    beiscsi_conn, conn, beiscsi_ep->ep_cid);
-
-	return beiscsi_bindconn_cid(phba, beiscsi_conn, beiscsi_ep->ep_cid);
+		    "BS_%d : cid %d phba->conn_table[%u]=%p\n",
+		    beiscsi_ep->ep_cid, cri_index, beiscsi_conn);
+	phba->conn_table[cri_index] = beiscsi_conn;
+	return 0;
 }
 
 static int beiscsi_iface_create_ipv4(struct beiscsi_hba *phba)
@@ -973,9 +961,9 @@ int beiscsi_conn_start(struct iscsi_cls_conn *cls_conn)
  */
 static int beiscsi_get_cid(struct beiscsi_hba *phba)
 {
-	unsigned short cid = 0xFFFF, cid_from_ulp;
-	struct ulp_cid_info *cid_info = NULL;
 	uint16_t cid_avlbl_ulp0, cid_avlbl_ulp1;
+	unsigned short cid, cid_from_ulp;
+	struct ulp_cid_info *cid_info;
 
 	/* Find the ULP which has more CID available */
 	cid_avlbl_ulp0 = (phba->cid_array_info[BEISCSI_ULP0]) ?
@@ -984,20 +972,27 @@ static int beiscsi_get_cid(struct beiscsi_hba *phba)
 			  BEISCSI_ULP1_AVLBL_CID(phba) : 0;
 	cid_from_ulp = (cid_avlbl_ulp0 > cid_avlbl_ulp1) ?
 			BEISCSI_ULP0 : BEISCSI_ULP1;
-
-	if (test_bit(cid_from_ulp, (void *)&phba->fw_config.ulp_supported)) {
-		cid_info = phba->cid_array_info[cid_from_ulp];
-		if (!cid_info->avlbl_cids)
-			return cid;
-
-		cid = cid_info->cid_array[cid_info->cid_alloc++];
-
-		if (cid_info->cid_alloc == BEISCSI_GET_CID_COUNT(
-					   phba, cid_from_ulp))
-			cid_info->cid_alloc = 0;
-
-		cid_info->avlbl_cids--;
+	/**
+	 * If iSCSI protocol is loaded only on ULP 0, and when cid_avlbl_ulp
+	 * is ZERO for both, ULP 1 is returned.
+	 * Check if ULP is loaded before getting new CID.
+	 */
+	if (!test_bit(cid_from_ulp, (void *)&phba->fw_config.ulp_supported))
+		return BE_INVALID_CID;
+
+	cid_info = phba->cid_array_info[cid_from_ulp];
+	cid = cid_info->cid_array[cid_info->cid_alloc];
+	if (!cid_info->avlbl_cids || cid == BE_INVALID_CID) {
+		__beiscsi_log(phba, KERN_ERR,
+				"BS_%d : failed to get cid: available %u:%u\n",
+				cid_info->avlbl_cids, cid_info->cid_free);
+		return BE_INVALID_CID;
 	}
+	/* empty the slot */
+	cid_info->cid_array[cid_info->cid_alloc++] = BE_INVALID_CID;
+	if (cid_info->cid_alloc == BEISCSI_GET_CID_COUNT(phba, cid_from_ulp))
+		cid_info->cid_alloc = 0;
+	cid_info->avlbl_cids--;
 	return cid;
 }
 
@@ -1008,22 +1003,28 @@ static int beiscsi_get_cid(struct beiscsi_hba *phba)
  */
 static void beiscsi_put_cid(struct beiscsi_hba *phba, unsigned short cid)
 {
-	uint16_t cid_post_ulp;
-	struct hwi_controller *phwi_ctrlr;
-	struct hwi_wrb_context *pwrb_context;
-	struct ulp_cid_info *cid_info = NULL;
 	uint16_t cri_index = BE_GET_CRI_FROM_CID(cid);
+	struct hwi_wrb_context *pwrb_context;
+	struct hwi_controller *phwi_ctrlr;
+	struct ulp_cid_info *cid_info;
+	uint16_t cid_post_ulp;
 
 	phwi_ctrlr = phba->phwi_ctrlr;
 	pwrb_context = &phwi_ctrlr->wrb_context[cri_index];
 	cid_post_ulp = pwrb_context->ulp_num;
 
 	cid_info = phba->cid_array_info[cid_post_ulp];
-	cid_info->avlbl_cids++;
-
+	/* fill only in empty slot */
+	if (cid_info->cid_array[cid_info->cid_free] != BE_INVALID_CID) {
+		__beiscsi_log(phba, KERN_ERR,
+			      "BS_%d : failed to put cid %u: available %u:%u\n",
+			      cid, cid_info->avlbl_cids, cid_info->cid_free);
+		return;
+	}
 	cid_info->cid_array[cid_info->cid_free++] = cid;
 	if (cid_info->cid_free == BEISCSI_GET_CID_COUNT(phba, cid_post_ulp))
 		cid_info->cid_free = 0;
+	cid_info->avlbl_cids++;
 }
 
 /**
@@ -1037,8 +1038,8 @@ static void beiscsi_free_ep(struct beiscsi_endpoint *beiscsi_ep)
 
 	beiscsi_put_cid(phba, beiscsi_ep->ep_cid);
 	beiscsi_ep->phba = NULL;
-	phba->ep_array[BE_GET_CRI_FROM_CID
-		       (beiscsi_ep->ep_cid)] = NULL;
+	/* clear this to track freeing in beiscsi_ep_disconnect */
+	phba->ep_array[BE_GET_CRI_FROM_CID(beiscsi_ep->ep_cid)] = NULL;
 
 	/**
 	 * Check if any connection resource allocated by driver
@@ -1049,6 +1050,11 @@ static void beiscsi_free_ep(struct beiscsi_endpoint *beiscsi_ep)
 		return;
 
 	beiscsi_conn = beiscsi_ep->conn;
+	/**
+	 * Break ep->conn link here so that completions after
+	 * this are ignored.
+	 */
+	beiscsi_ep->conn = NULL;
 	if (beiscsi_conn->login_in_progress) {
 		beiscsi_free_mgmt_task_handles(beiscsi_conn,
 					       beiscsi_conn->task);
@@ -1079,7 +1085,7 @@ static int beiscsi_open_conn(struct iscsi_endpoint *ep,
 		    "BS_%d : In beiscsi_open_conn\n");
 
 	beiscsi_ep->ep_cid = beiscsi_get_cid(phba);
-	if (beiscsi_ep->ep_cid == 0xFFFF) {
+	if (beiscsi_ep->ep_cid == BE_INVALID_CID) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG,
 			    "BS_%d : No free cid available\n");
 		return ret;
@@ -1114,7 +1120,7 @@ static int beiscsi_open_conn(struct iscsi_endpoint *ep,
 	nonemb_cmd.size = req_memsize;
 	memset(nonemb_cmd.va, 0, nonemb_cmd.size);
 	tag = mgmt_open_connection(phba, dst_addr, beiscsi_ep, &nonemb_cmd);
-	if (tag <= 0) {
+	if (!tag) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG,
 			    "BS_%d : mgmt_open_connection Failed for cid=%d\n",
 			    beiscsi_ep->ep_cid);
@@ -1285,26 +1291,6 @@ static int beiscsi_close_conn(struct  beiscsi_endpoint *beiscsi_ep, int flag)
 }
 
 /**
- * beiscsi_unbind_conn_to_cid - Unbind the beiscsi_conn from phba conn table
- * @phba: The phba instance
- * @cid: The cid to free
- */
-static int beiscsi_unbind_conn_to_cid(struct beiscsi_hba *phba,
-				      unsigned int cid)
-{
-	uint16_t cri_index = BE_GET_CRI_FROM_CID(cid);
-
-	if (phba->conn_table[cri_index])
-		phba->conn_table[cri_index] = NULL;
-	else {
-		beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_CONFIG,
-			    "BS_%d : Connection table Not occupied.\n");
-		return -EINVAL;
-	}
-	return 0;
-}
-
-/**
  * beiscsi_ep_disconnect - Tears down the TCP connection
  * @ep:	endpoint to be used
  *
@@ -1318,13 +1304,23 @@ void beiscsi_ep_disconnect(struct iscsi_endpoint *ep)
 	unsigned int tag;
 	uint8_t mgmt_invalidate_flag, tcp_upload_flag;
 	unsigned short savecfg_flag = CMD_ISCSI_SESSION_SAVE_CFG_ON_FLASH;
+	uint16_t cri_index;
 
 	beiscsi_ep = ep->dd_data;
 	phba = beiscsi_ep->phba;
 	beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_CONFIG,
-		    "BS_%d : In beiscsi_ep_disconnect for ep_cid = %d\n",
+		    "BS_%d : In beiscsi_ep_disconnect for ep_cid = %u\n",
 		    beiscsi_ep->ep_cid);
 
+	cri_index = BE_GET_CRI_FROM_CID(beiscsi_ep->ep_cid);
+	if (!phba->ep_array[cri_index]) {
+		__beiscsi_log(phba, KERN_ERR,
+			      "BS_%d : ep_array at %u cid %u empty\n",
+			      cri_index,
+			      beiscsi_ep->ep_cid);
+		return;
+	}
+
 	if (beiscsi_ep->conn) {
 		beiscsi_conn = beiscsi_ep->conn;
 		iscsi_suspend_queue(beiscsi_conn->conn);
@@ -1356,7 +1352,12 @@ void beiscsi_ep_disconnect(struct iscsi_endpoint *ep)
 free_ep:
 	msleep(BEISCSI_LOGOUT_SYNC_DELAY);
 	beiscsi_free_ep(beiscsi_ep);
-	beiscsi_unbind_conn_to_cid(phba, beiscsi_ep->ep_cid);
+	if (!phba->conn_table[cri_index])
+		__beiscsi_log(phba, KERN_ERR,
+				"BS_%d : conn_table empty at %u: cid %u\n",
+				cri_index,
+				beiscsi_ep->ep_cid);
+	phba->conn_table[cri_index] = NULL;
 	iscsi_destroy_endpoint(beiscsi_ep->openiscsi_ep);
 }
 
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index b5112d6d7e73..c9b9daa91091 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -67,8 +67,6 @@ beiscsi_##_name##_disp(struct device *dev,\
 {	\
 	struct Scsi_Host *shost = class_to_shost(dev);\
 	struct beiscsi_hba *phba = iscsi_host_priv(shost); \
-	uint32_t param_val = 0;	\
-	param_val = phba->attr_##_name;\
 	return snprintf(buf, PAGE_SIZE, "%d\n",\
 			phba->attr_##_name);\
 }
@@ -218,160 +216,156 @@ static int beiscsi_slave_configure(struct scsi_device *sdev)
 
 static int beiscsi_eh_abort(struct scsi_cmnd *sc)
 {
+	struct iscsi_task *abrt_task = (struct iscsi_task *)sc->SCp.ptr;
 	struct iscsi_cls_session *cls_session;
-	struct iscsi_task *aborted_task = (struct iscsi_task *)sc->SCp.ptr;
-	struct beiscsi_io_task *aborted_io_task;
-	struct iscsi_conn *conn;
+	struct beiscsi_io_task *abrt_io_task;
 	struct beiscsi_conn *beiscsi_conn;
-	struct beiscsi_hba *phba;
 	struct iscsi_session *session;
-	struct invalidate_command_table *inv_tbl;
-	struct be_dma_mem nonemb_cmd;
-	unsigned int cid, tag, num_invalidate;
+	struct invldt_cmd_tbl inv_tbl;
+	struct beiscsi_hba *phba;
+	struct iscsi_conn *conn;
 	int rc;
 
 	cls_session = starget_to_session(scsi_target(sc->device));
 	session = cls_session->dd_data;
 
-	spin_lock_bh(&session->frwd_lock);
-	if (!aborted_task || !aborted_task->sc) {
-		/* we raced */
-		spin_unlock_bh(&session->frwd_lock);
-		return SUCCESS;
-	}
-
-	aborted_io_task = aborted_task->dd_data;
-	if (!aborted_io_task->scsi_cmnd) {
-		/* raced or invalid command */
-		spin_unlock_bh(&session->frwd_lock);
+	/* check if we raced, task just got cleaned up under us */
+	spin_lock_bh(&session->back_lock);
+	if (!abrt_task || !abrt_task->sc) {
+		spin_unlock_bh(&session->back_lock);
 		return SUCCESS;
 	}
-	spin_unlock_bh(&session->frwd_lock);
-	/* Invalidate WRB Posted for this Task */
-	AMAP_SET_BITS(struct amap_iscsi_wrb, invld,
-		      aborted_io_task->pwrb_handle->pwrb,
-		      1);
-
-	conn = aborted_task->conn;
+	/* get a task ref till FW processes the req for the ICD used */
+	__iscsi_get_task(abrt_task);
+	abrt_io_task = abrt_task->dd_data;
+	conn = abrt_task->conn;
 	beiscsi_conn = conn->dd_data;
 	phba = beiscsi_conn->phba;
-
-	/* invalidate iocb */
-	cid = beiscsi_conn->beiscsi_conn_cid;
-	inv_tbl = phba->inv_tbl;
-	memset(inv_tbl, 0x0, sizeof(*inv_tbl));
-	inv_tbl->cid = cid;
-	inv_tbl->icd = aborted_io_task->psgl_handle->sgl_index;
-	num_invalidate = 1;
-	nonemb_cmd.va = pci_alloc_consistent(phba->ctrl.pdev,
-				sizeof(struct invalidate_commands_params_in),
-				&nonemb_cmd.dma);
-	if (nonemb_cmd.va == NULL) {
-		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_EH,
-			    "BM_%d : Failed to allocate memory for"
-			    "mgmt_invalidate_icds\n");
-		return FAILED;
+	/* mark WRB invalid which have been not processed by FW yet */
+	if (is_chip_be2_be3r(phba)) {
+		AMAP_SET_BITS(struct amap_iscsi_wrb, invld,
+			      abrt_io_task->pwrb_handle->pwrb, 1);
+	} else {
+		AMAP_SET_BITS(struct amap_iscsi_wrb_v2, invld,
+			      abrt_io_task->pwrb_handle->pwrb, 1);
 	}
-	nonemb_cmd.size = sizeof(struct invalidate_commands_params_in);
+	inv_tbl.cid = beiscsi_conn->beiscsi_conn_cid;
+	inv_tbl.icd = abrt_io_task->psgl_handle->sgl_index;
+	spin_unlock_bh(&session->back_lock);
 
-	tag = mgmt_invalidate_icds(phba, inv_tbl, num_invalidate,
-				   cid, &nonemb_cmd);
-	if (!tag) {
+	rc = beiscsi_mgmt_invalidate_icds(phba, &inv_tbl, 1);
+	iscsi_put_task(abrt_task);
+	if (rc) {
 		beiscsi_log(phba, KERN_WARNING, BEISCSI_LOG_EH,
-			    "BM_%d : mgmt_invalidate_icds could not be"
-			    "submitted\n");
-		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
-				    nonemb_cmd.va, nonemb_cmd.dma);
-
+			    "BM_%d : sc %p invalidation failed %d\n",
+			    sc, rc);
 		return FAILED;
 	}
 
-	rc = beiscsi_mccq_compl_wait(phba, tag, NULL, &nonemb_cmd);
-	if (rc != -EBUSY)
-		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
-				    nonemb_cmd.va, nonemb_cmd.dma);
-
 	return iscsi_eh_abort(sc);
 }
 
 static int beiscsi_eh_device_reset(struct scsi_cmnd *sc)
 {
-	struct iscsi_task *abrt_task;
-	struct beiscsi_io_task *abrt_io_task;
-	struct iscsi_conn *conn;
+	struct beiscsi_invldt_cmd_tbl {
+		struct invldt_cmd_tbl tbl[BE_INVLDT_CMD_TBL_SZ];
+		struct iscsi_task *task[BE_INVLDT_CMD_TBL_SZ];
+	} *inv_tbl;
+	struct iscsi_cls_session *cls_session;
 	struct beiscsi_conn *beiscsi_conn;
-	struct beiscsi_hba *phba;
+	struct beiscsi_io_task *io_task;
 	struct iscsi_session *session;
-	struct iscsi_cls_session *cls_session;
-	struct invalidate_command_table *inv_tbl;
-	struct be_dma_mem nonemb_cmd;
-	unsigned int cid, tag, i, num_invalidate;
-	int rc;
+	struct beiscsi_hba *phba;
+	struct iscsi_conn *conn;
+	struct iscsi_task *task;
+	unsigned int i, nents;
+	int rc, more = 0;
 
-	/* invalidate iocbs */
 	cls_session = starget_to_session(scsi_target(sc->device));
 	session = cls_session->dd_data;
+
 	spin_lock_bh(&session->frwd_lock);
 	if (!session->leadconn || session->state != ISCSI_STATE_LOGGED_IN) {
 		spin_unlock_bh(&session->frwd_lock);
 		return FAILED;
 	}
+
 	conn = session->leadconn;
 	beiscsi_conn = conn->dd_data;
 	phba = beiscsi_conn->phba;
-	cid = beiscsi_conn->beiscsi_conn_cid;
-	inv_tbl = phba->inv_tbl;
-	memset(inv_tbl, 0x0, sizeof(*inv_tbl) * BE2_CMDS_PER_CXN);
-	num_invalidate = 0;
+
+	inv_tbl = kzalloc(sizeof(*inv_tbl), GFP_ATOMIC);
+	if (!inv_tbl) {
+		spin_unlock_bh(&session->frwd_lock);
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_EH,
+			    "BM_%d : invldt_cmd_tbl alloc failed\n");
+		return FAILED;
+	}
+	nents = 0;
+	/* take back_lock to prevent task from getting cleaned up under us */
+	spin_lock(&session->back_lock);
 	for (i = 0; i < conn->session->cmds_max; i++) {
-		abrt_task = conn->session->cmds[i];
-		abrt_io_task = abrt_task->dd_data;
-		if (!abrt_task->sc || abrt_task->state == ISCSI_TASK_FREE)
+		task = conn->session->cmds[i];
+		if (!task->sc)
 			continue;
 
-		if (sc->device->lun != abrt_task->sc->device->lun)
+		if (sc->device->lun != task->sc->device->lun)
 			continue;
+		/**
+		 * Can't fit in more cmds? Normally this won't happen b'coz
+		 * BEISCSI_CMD_PER_LUN is same as BE_INVLDT_CMD_TBL_SZ.
+		 */
+		if (nents == BE_INVLDT_CMD_TBL_SZ) {
+			more = 1;
+			break;
+		}
 
-		/* Invalidate WRB Posted for this Task */
-		AMAP_SET_BITS(struct amap_iscsi_wrb, invld,
-			      abrt_io_task->pwrb_handle->pwrb,
-			      1);
+		/* get a task ref till FW processes the req for the ICD used */
+		__iscsi_get_task(task);
+		io_task = task->dd_data;
+		/* mark WRB invalid which have been not processed by FW yet */
+		if (is_chip_be2_be3r(phba)) {
+			AMAP_SET_BITS(struct amap_iscsi_wrb, invld,
+				      io_task->pwrb_handle->pwrb, 1);
+		} else {
+			AMAP_SET_BITS(struct amap_iscsi_wrb_v2, invld,
+				      io_task->pwrb_handle->pwrb, 1);
+		}
 
-		inv_tbl->cid = cid;
-		inv_tbl->icd = abrt_io_task->psgl_handle->sgl_index;
-		num_invalidate++;
-		inv_tbl++;
+		inv_tbl->tbl[nents].cid = beiscsi_conn->beiscsi_conn_cid;
+		inv_tbl->tbl[nents].icd = io_task->psgl_handle->sgl_index;
+		inv_tbl->task[nents] = task;
+		nents++;
 	}
+	spin_unlock_bh(&session->back_lock);
 	spin_unlock_bh(&session->frwd_lock);
-	inv_tbl = phba->inv_tbl;
 
-	nonemb_cmd.va = pci_alloc_consistent(phba->ctrl.pdev,
-				sizeof(struct invalidate_commands_params_in),
-				&nonemb_cmd.dma);
-	if (nonemb_cmd.va == NULL) {
+	rc = SUCCESS;
+	if (!nents)
+		goto end_reset;
+
+	if (more) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_EH,
-			    "BM_%d : Failed to allocate memory for"
-			    "mgmt_invalidate_icds\n");
-		return FAILED;
+			    "BM_%d : number of cmds exceeds size of invalidation table\n");
+		rc = FAILED;
+		goto end_reset;
 	}
-	nonemb_cmd.size = sizeof(struct invalidate_commands_params_in);
-	memset(nonemb_cmd.va, 0, nonemb_cmd.size);
-	tag = mgmt_invalidate_icds(phba, inv_tbl, num_invalidate,
-				   cid, &nonemb_cmd);
-	if (!tag) {
+
+	if (beiscsi_mgmt_invalidate_icds(phba, &inv_tbl->tbl[0], nents)) {
 		beiscsi_log(phba, KERN_WARNING, BEISCSI_LOG_EH,
-			    "BM_%d : mgmt_invalidate_icds could not be"
-			    " submitted\n");
-		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
-				    nonemb_cmd.va, nonemb_cmd.dma);
-		return FAILED;
+			    "BM_%d : cid %u scmds invalidation failed\n",
+			    beiscsi_conn->beiscsi_conn_cid);
+		rc = FAILED;
 	}
 
-	rc = beiscsi_mccq_compl_wait(phba, tag, NULL, &nonemb_cmd);
-	if (rc != -EBUSY)
-		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
-				    nonemb_cmd.va, nonemb_cmd.dma);
-	return iscsi_eh_device_reset(sc);
+end_reset:
+	for (i = 0; i < nents; i++)
+		iscsi_put_task(inv_tbl->task[i]);
+	kfree(inv_tbl);
+
+	if (rc == SUCCESS)
+		rc = iscsi_eh_device_reset(sc);
+	return rc;
 }
 
 /*------------------- PCI Driver operations and data ----------------- */
@@ -646,7 +640,6 @@ static void beiscsi_get_params(struct beiscsi_hba *phba)
 	phba->params.num_sge_per_io = BE2_SGE;
 	phba->params.defpdu_hdr_sz = BE2_DEFPDU_HDR_SZ;
 	phba->params.defpdu_data_sz = BE2_DEFPDU_DATA_SZ;
-	phba->params.eq_timer = 64;
 	phba->params.num_eq_entries = 1024;
 	phba->params.num_cq_entries = 1024;
 	phba->params.wrbs_per_cxn = 256;
@@ -964,6 +957,10 @@ beiscsi_get_wrb_handle(struct hwi_wrb_context *pwrb_context,
 	unsigned long flags;
 
 	spin_lock_irqsave(&pwrb_context->wrb_lock, flags);
+	if (!pwrb_context->wrb_handles_available) {
+		spin_unlock_irqrestore(&pwrb_context->wrb_lock, flags);
+		return NULL;
+	}
 	pwrb_handle = pwrb_context->pwrb_handle_base[pwrb_context->alloc_index];
 	pwrb_context->wrb_handles_available--;
 	if (pwrb_context->alloc_index == (wrbs_per_cxn - 1))
@@ -1014,6 +1011,7 @@ beiscsi_put_wrb_handle(struct hwi_wrb_context *pwrb_context,
 		pwrb_context->free_index = 0;
 	else
 		pwrb_context->free_index++;
+	pwrb_handle->pio_handle = NULL;
 	spin_unlock_irqrestore(&pwrb_context->wrb_lock, flags);
 }
 
@@ -1224,6 +1222,7 @@ hwi_complete_drvr_msgs(struct beiscsi_conn *beiscsi_conn,
 	uint16_t wrb_index, cid, cri_index;
 	struct hwi_controller *phwi_ctrlr;
 	struct wrb_handle *pwrb_handle;
+	struct iscsi_session *session;
 	struct iscsi_task *task;
 
 	phwi_ctrlr = phba->phwi_ctrlr;
@@ -1242,8 +1241,12 @@ hwi_complete_drvr_msgs(struct beiscsi_conn *beiscsi_conn,
 	cri_index = BE_GET_CRI_FROM_CID(cid);
 	pwrb_context = &phwi_ctrlr->wrb_context[cri_index];
 	pwrb_handle = pwrb_context->pwrb_handle_basestd[wrb_index];
+	session = beiscsi_conn->conn->session;
+	spin_lock_bh(&session->back_lock);
 	task = pwrb_handle->pio_handle;
-	iscsi_put_task(task);
+	if (task)
+		__iscsi_put_task(task);
+	spin_unlock_bh(&session->back_lock);
 }
 
 static void
@@ -1323,16 +1326,15 @@ static void adapter_get_sol_cqe(struct beiscsi_hba *phba,
 static void hwi_complete_cmd(struct beiscsi_conn *beiscsi_conn,
 			     struct beiscsi_hba *phba, struct sol_cqe *psol)
 {
-	struct hwi_wrb_context *pwrb_context;
-	struct wrb_handle *pwrb_handle;
-	struct iscsi_wrb *pwrb = NULL;
-	struct hwi_controller *phwi_ctrlr;
-	struct iscsi_task *task;
-	unsigned int type;
 	struct iscsi_conn *conn = beiscsi_conn->conn;
 	struct iscsi_session *session = conn->session;
 	struct common_sol_cqe csol_cqe = {0};
+	struct hwi_wrb_context *pwrb_context;
+	struct hwi_controller *phwi_ctrlr;
+	struct wrb_handle *pwrb_handle;
+	struct iscsi_task *task;
 	uint16_t cri_index = 0;
+	uint8_t type;
 
 	phwi_ctrlr = phba->phwi_ctrlr;
 
@@ -1345,11 +1347,14 @@ static void hwi_complete_cmd(struct beiscsi_conn *beiscsi_conn,
 	pwrb_handle = pwrb_context->pwrb_handle_basestd[
 		      csol_cqe.wrb_index];
 
+	spin_lock_bh(&session->back_lock);
 	task = pwrb_handle->pio_handle;
-	pwrb = pwrb_handle->pwrb;
+	if (!task) {
+		spin_unlock_bh(&session->back_lock);
+		return;
+	}
 	type = ((struct beiscsi_io_task *)task->dd_data)->wrb_type;
 
-	spin_lock_bh(&session->back_lock);
 	switch (type) {
 	case HWH_TYPE_IO:
 	case HWH_TYPE_IO_RD:
@@ -1711,13 +1716,12 @@ beiscsi_hdq_post_handles(struct beiscsi_hba *phba,
 	struct list_head *hfree_list;
 	struct phys_addr *pasync_sge;
 	u32 ring_id, doorbell = 0;
-	u16 index, num_entries;
 	u32 doorbell_offset;
 	u16 prod = 0, cons;
+	u16 index;
 
 	phwi_ctrlr = phba->phwi_ctrlr;
 	pasync_ctx = HWI_GET_ASYNC_PDU_CTX(phwi_ctrlr, ulp_num);
-	num_entries = pasync_ctx->num_entries;
 	if (header) {
 		cons = pasync_ctx->async_header.free_entries;
 		hfree_list = &pasync_ctx->async_header.free_list;
@@ -2374,13 +2378,10 @@ static int hwi_write_buffer(struct iscsi_wrb *pwrb, struct iscsi_task *task)
 static void beiscsi_find_mem_req(struct beiscsi_hba *phba)
 {
 	uint8_t mem_descr_index, ulp_num;
-	unsigned int num_cq_pages, num_async_pdu_buf_pages;
+	unsigned int num_async_pdu_buf_pages;
 	unsigned int num_async_pdu_data_pages, wrb_sz_per_cxn;
 	unsigned int num_async_pdu_buf_sgl_pages, num_async_pdu_data_sgl_pages;
 
-	num_cq_pages = PAGES_REQUIRED(phba->params.num_cq_entries * \
-				      sizeof(struct sol_cqe));
-
 	phba->params.hwi_ws_sz = sizeof(struct hwi_controller);
 
 	phba->mem_req[ISCSI_MEM_GLOBAL_HEADER] = 2 *
@@ -2737,7 +2738,7 @@ static int hwi_init_async_pdu_ctx(struct beiscsi_hba *phba)
 
 	for (ulp_num = 0; ulp_num < BEISCSI_ULP_COUNT; ulp_num++) {
 		if (test_bit(ulp_num, &phba->fw_config.ulp_supported)) {
-			 /* get async_ctx for each ULP */
+			/* get async_ctx for each ULP */
 			mem_descr = (struct be_mem_descriptor *)phba->init_mem;
 			mem_descr += (HWI_MEM_ASYNC_PDU_CONTEXT_ULP0 +
 				     (ulp_num * MEM_DESCR_OFFSET));
@@ -3367,7 +3368,7 @@ beiscsi_create_wrb_rings(struct beiscsi_hba *phba,
 			 struct hwi_context_memory *phwi_context,
 			 struct hwi_controller *phwi_ctrlr)
 {
-	unsigned int wrb_mem_index, offset, size, num_wrb_rings;
+	unsigned int num_wrb_rings;
 	u64 pa_addr_lo;
 	unsigned int idx, num, i, ulp_num;
 	struct mem_array *pwrb_arr;
@@ -3432,10 +3433,6 @@ beiscsi_create_wrb_rings(struct beiscsi_hba *phba,
 		}
 
 	for (i = 0; i < phba->params.cxns_per_ctrl; i++) {
-		wrb_mem_index = 0;
-		offset = 0;
-		size = 0;
-
 		if (ulp_count > 1) {
 			ulp_base_num = (ulp_base_num + 1) % BEISCSI_ULP_COUNT;
 
@@ -3663,7 +3660,6 @@ static void hwi_cleanup_port(struct beiscsi_hba *phba)
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 	struct hwi_controller *phwi_ctrlr;
 	struct hwi_context_memory *phwi_context;
-	struct hd_async_context *pasync_ctx;
 	int i, eq_for_mcc, ulp_num;
 
 	for (ulp_num = 0; ulp_num < BEISCSI_ULP_COUNT; ulp_num++)
@@ -3700,8 +3696,6 @@ static void hwi_cleanup_port(struct beiscsi_hba *phba)
 			q = &phwi_context->be_def_dataq[ulp_num];
 			if (q->created)
 				beiscsi_cmd_q_destroy(ctrl, q, QTYPE_DPDUQ);
-
-			pasync_ctx = phwi_ctrlr->phwi_ctxt->pasync_ctx[ulp_num];
 		}
 	}
 
@@ -3804,7 +3798,6 @@ static int hwi_init_port(struct beiscsi_hba *phba)
 			/**
 			 * Now that the default PDU rings have been created,
 			 * let EP know about it.
-			 * Call beiscsi_cmd_iscsi_cleanup before posting?
 			 */
 			beiscsi_hdq_post_handles(phba, BEISCSI_DEFQ_HDR,
 						 ulp_num);
@@ -3850,14 +3843,6 @@ static int hwi_init_port(struct beiscsi_hba *phba)
 					phwi_ctrlr->wrb_context[cri].cid] =
 					async_arr_idx++;
 			}
-			/**
-			 * Now that the default PDU rings have been created,
-			 * let EP know about it.
-			 */
-			beiscsi_hdq_post_handles(phba, BEISCSI_DEFQ_HDR,
-						 ulp_num);
-			beiscsi_hdq_post_handles(phba, BEISCSI_DEFQ_DATA,
-						 ulp_num);
 		}
 	}
 
@@ -3934,31 +3919,6 @@ static void beiscsi_free_mem(struct beiscsi_hba *phba)
 	kfree(phba->phwi_ctrlr);
 }
 
-static int beiscsi_init_controller(struct beiscsi_hba *phba)
-{
-	int ret = -ENOMEM;
-
-	ret = beiscsi_get_memory(phba);
-	if (ret < 0) {
-		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
-			    "BM_%d : beiscsi_dev_probe -"
-			    "Failed in beiscsi_alloc_memory\n");
-		return ret;
-	}
-
-	ret = hwi_init_controller(phba);
-	if (ret)
-		goto free_init;
-	beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_INIT,
-		    "BM_%d : Return success from beiscsi_init_controller");
-
-	return 0;
-
-free_init:
-	beiscsi_free_mem(phba);
-	return ret;
-}
-
 static int beiscsi_init_sgl_handle(struct beiscsi_hba *phba)
 {
 	struct be_mem_descriptor *mem_descr_sglh, *mem_descr_sg;
@@ -4089,9 +4049,10 @@ static int hba_setup_cid_tbls(struct beiscsi_hba *phba)
 			}
 
 			/* Allocate memory for CID array */
-			ptr_cid_info->cid_array = kzalloc(sizeof(void *) *
-						  BEISCSI_GET_CID_COUNT(phba,
-						  ulp_num), GFP_KERNEL);
+			ptr_cid_info->cid_array =
+				kcalloc(BEISCSI_GET_CID_COUNT(phba, ulp_num),
+					sizeof(*ptr_cid_info->cid_array),
+					GFP_KERNEL);
 			if (!ptr_cid_info->cid_array) {
 				beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
 					    "BM_%d : Failed to allocate memory"
@@ -4231,33 +4192,30 @@ static int beiscsi_init_port(struct beiscsi_hba *phba)
 {
 	int ret;
 
-	ret = beiscsi_init_controller(phba);
+	ret = hwi_init_controller(phba);
 	if (ret < 0) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
-			    "BM_%d : beiscsi_dev_probe - Failed in"
-			    "beiscsi_init_controller\n");
+			    "BM_%d : init controller failed\n");
 		return ret;
 	}
 	ret = beiscsi_init_sgl_handle(phba);
 	if (ret < 0) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
-			    "BM_%d : beiscsi_dev_probe - Failed in"
-			    "beiscsi_init_sgl_handle\n");
-		goto do_cleanup_ctrlr;
+			    "BM_%d : init sgl handles failed\n");
+		goto cleanup_port;
 	}
 
 	ret = hba_setup_cid_tbls(phba);
 	if (ret < 0) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
-			    "BM_%d : Failed in hba_setup_cid_tbls\n");
+			    "BM_%d : setup CID table failed\n");
 		kfree(phba->io_sgl_hndl_base);
 		kfree(phba->eh_sgl_hndl_base);
-		goto do_cleanup_ctrlr;
+		goto cleanup_port;
 	}
-
 	return ret;
 
-do_cleanup_ctrlr:
+cleanup_port:
 	hwi_cleanup_port(phba);
 	return ret;
 }
@@ -5417,10 +5375,10 @@ static int beiscsi_enable_port(struct beiscsi_hba *phba)
 
 	phba->shost->max_id = phba->params.cxns_per_ctrl;
 	phba->shost->can_queue = phba->params.ios_per_ctrl;
-	ret = hwi_init_controller(phba);
-	if (ret) {
+	ret = beiscsi_init_port(phba);
+	if (ret < 0) {
 		__beiscsi_log(phba, KERN_ERR,
-			      "BM_%d : init controller failed %d\n", ret);
+			      "BM_%d : init port failed\n");
 		goto disable_msix;
 	}
 
@@ -5526,6 +5484,7 @@ static void beiscsi_disable_port(struct beiscsi_hba *phba, int unload)
 		cancel_work_sync(&pbe_eq->mcc_work);
 	}
 	hwi_cleanup_port(phba);
+	beiscsi_cleanup_port(phba);
 }
 
 static void beiscsi_sess_work(struct work_struct *work)
@@ -5638,11 +5597,12 @@ static void beiscsi_eeh_resume(struct pci_dev *pdev)
 static int beiscsi_dev_probe(struct pci_dev *pcidev,
 			     const struct pci_device_id *id)
 {
-	struct beiscsi_hba *phba = NULL;
-	struct hwi_controller *phwi_ctrlr;
 	struct hwi_context_memory *phwi_context;
+	struct hwi_controller *phwi_ctrlr;
+	struct beiscsi_hba *phba = NULL;
 	struct be_eq_obj *pbe_eq;
 	unsigned int s_handle;
+	char wq_name[20];
 	int ret, i;
 
 	ret = beiscsi_enable_pci(pcidev);
@@ -5680,6 +5640,8 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 	case OC_DEVICE_ID2:
 		phba->generation = BE_GEN2;
 		phba->iotask_fn = beiscsi_iotask;
+		dev_warn(&pcidev->dev,
+			 "Obsolete/Unsupported BE2 Adapter Family\n");
 		break;
 	case BE_DEVICE_ID2:
 	case OC_DEVICE_ID3:
@@ -5735,11 +5697,18 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 
 	phba->shost->max_id = phba->params.cxns_per_ctrl;
 	phba->shost->can_queue = phba->params.ios_per_ctrl;
+	ret = beiscsi_get_memory(phba);
+	if (ret < 0) {
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
+			    "BM_%d : alloc host mem failed\n");
+		goto free_port;
+	}
+
 	ret = beiscsi_init_port(phba);
 	if (ret < 0) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
-			    "BM_%d : beiscsi_dev_probe-"
-			    "Failed in beiscsi_init_port\n");
+			    "BM_%d : init port failed\n");
+		beiscsi_free_mem(phba);
 		goto free_port;
 	}
 
@@ -5754,9 +5723,9 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 
 	phba->ctrl.mcc_alloc_index = phba->ctrl.mcc_free_index = 0;
 
-	snprintf(phba->wq_name, sizeof(phba->wq_name), "beiscsi_%02x_wq",
+	snprintf(wq_name, sizeof(wq_name), "beiscsi_%02x_wq",
 		 phba->shost->host_no);
-	phba->wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, phba->wq_name);
+	phba->wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, wq_name);
 	if (!phba->wq) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
 			    "BM_%d : beiscsi_dev_probe-"
@@ -5881,7 +5850,6 @@ static void beiscsi_remove(struct pci_dev *pcidev)
 
 	/* free all resources */
 	destroy_workqueue(phba->wq);
-	beiscsi_cleanup_port(phba);
 	beiscsi_free_mem(phba);
 
 	/* ctrl uninit */
diff --git a/drivers/scsi/be2iscsi/be_main.h b/drivers/scsi/be2iscsi/be_main.h
index 6376657e45f7..218857926566 100644
--- a/drivers/scsi/be2iscsi/be_main.h
+++ b/drivers/scsi/be2iscsi/be_main.h
@@ -36,7 +36,7 @@
 #include <scsi/scsi_transport_iscsi.h>
 
 #define DRV_NAME		"be2iscsi"
-#define BUILD_STR		"11.2.0.0"
+#define BUILD_STR		"11.2.1.0"
 #define BE_NAME			"Emulex OneConnect" \
 				"Open-iSCSI Driver version" BUILD_STR
 #define DRV_DESC		BE_NAME " " "Driver"
@@ -57,7 +57,6 @@
 
 #define BE2_IO_DEPTH		1024
 #define BE2_MAX_SESSIONS	256
-#define BE2_CMDS_PER_CXN	128
 #define BE2_TMFS		16
 #define BE2_NOPOUT_REQ		16
 #define BE2_SGE			32
@@ -72,8 +71,13 @@
 
 #define BEISCSI_SGLIST_ELEMENTS	30
 
-#define BEISCSI_CMD_PER_LUN	128 /* scsi_host->cmd_per_lun */
-#define BEISCSI_MAX_SECTORS	1024 /* scsi_host->max_sectors */
+/**
+ * BE_INVLDT_CMD_TBL_SZ is 128 which is total number commands that can
+ * be invalidated at a time, consider it before changing the value of
+ * BEISCSI_CMD_PER_LUN.
+ */
+#define BEISCSI_CMD_PER_LUN	128	/* scsi_host->cmd_per_lun */
+#define BEISCSI_MAX_SECTORS	1024	/* scsi_host->max_sectors */
 #define BEISCSI_TEMPLATE_HDR_PER_CXN_SIZE 128 /* Template size per cxn */
 
 #define BEISCSI_MAX_CMD_LEN	16	/* scsi_host->max_cmd_len */
@@ -239,19 +243,7 @@ struct hba_parameters {
 	unsigned int num_cq_entries;
 	unsigned int num_eq_entries;
 	unsigned int wrbs_per_cxn;
-	unsigned int crashmode;
-	unsigned int hba_num;
-
-	unsigned int mgmt_ws_sz;
 	unsigned int hwi_ws_sz;
-
-	unsigned int eto;
-	unsigned int ldto;
-
-	unsigned int dbg_flags;
-	unsigned int num_cxn;
-
-	unsigned int eq_timer;
 	/**
 	 * These are calculated from other params. They're here
 	 * for debug purposes
@@ -272,11 +264,6 @@ struct hba_parameters {
 	unsigned int num_sge;
 };
 
-struct invalidate_command_table {
-	unsigned short icd;
-	unsigned short cid;
-} __packed;
-
 #define BEISCSI_GET_ULP_FROM_CRI(phwi_ctrlr, cri) \
 	(phwi_ctrlr->wrb_context[cri].ulp_num)
 struct hwi_wrb_context {
@@ -334,7 +321,6 @@ struct beiscsi_hba {
 	struct be_bus_address pci_pa;	/* CSR */
 	/* PCI representation of our HBA */
 	struct pci_dev *pcidev;
-	unsigned short asic_revision;
 	unsigned int num_cpus;
 	unsigned int nxt_cqid;
 	struct msix_entry msix_entries[MAX_CPUS];
@@ -355,9 +341,9 @@ struct beiscsi_hba {
 	spinlock_t io_sgl_lock;
 	spinlock_t mgmt_sgl_lock;
 	spinlock_t async_pdu_lock;
-	unsigned int age;
 	struct list_head hba_queue;
 #define BE_MAX_SESSION 2048
+#define BE_INVALID_CID 0xffff
 #define BE_SET_CID_TO_CRI(cri_index, cid) \
 			  (phba->cid_to_cri_map[cid] = cri_index)
 #define BE_GET_CRI_FROM_CID(cid) (phba->cid_to_cri_map[cid])
@@ -425,12 +411,10 @@ struct beiscsi_hba {
 	u8 port_name;
 	u8 port_speed;
 	char fw_ver_str[BEISCSI_VER_STRLEN];
-	char wq_name[20];
 	struct workqueue_struct *wq;	/* The actuak work queue */
 	struct be_ctrl_info ctrl;
 	unsigned int generation;
 	unsigned int interface_handle;
-	struct invalidate_command_table inv_tbl[128];
 
 	struct be_aic_obj aic_obj[MAX_CPUS];
 	unsigned int attr_log_enable;
@@ -525,10 +509,6 @@ struct beiscsi_io_task {
 	struct scsi_cmnd *scsi_cmnd;
 	int num_sg;
 	struct hwi_wrb_context *pwrb_context;
-	unsigned int cmd_sn;
-	unsigned int flags;
-	unsigned short cid;
-	unsigned short header_len;
 	itt_t libiscsi_itt;
 	struct be_cmd_bhs *cmd_bhs;
 	struct be_bus_address bhs_pa;
@@ -842,7 +822,7 @@ struct amap_iscsi_wrb_v2 {
 	u8 diff_enbl;   /* DWORD 11 */
 	u8 u_run;       /* DWORD 11 */
 	u8 o_run;       /* DWORD 11 */
-	u8 invalid;     /* DWORD 11 */
+	u8 invld;     /* DWORD 11 */
 	u8 dsp;         /* DWORD 11 */
 	u8 dmsg;        /* DWORD 11 */
 	u8 rsvd4;       /* DWORD 11 */
@@ -1042,10 +1022,8 @@ struct hwi_controller {
 	struct list_head io_sgl_list;
 	struct list_head eh_sgl_list;
 	struct sgl_handle *psgl_handle_base;
-	unsigned int wrb_mem_index;
 
 	struct hwi_wrb_context *wrb_context;
-	struct mcc_wrb *pmcc_wrb_base;
 	struct be_ring default_pdu_hdr[BEISCSI_ULP_COUNT];
 	struct be_ring default_pdu_data[BEISCSI_ULP_COUNT];
 	struct hwi_context_memory *phwi_ctxt;
@@ -1062,9 +1040,7 @@ enum hwh_type_enum {
 };
 
 struct wrb_handle {
-	enum hwh_type_enum type;
 	unsigned short wrb_index;
-
 	struct iscsi_task *pio_handle;
 	struct iscsi_wrb *pwrb;
 };
diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c
index ac05317bba7f..2f6d5c2ac329 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.c
+++ b/drivers/scsi/be2iscsi/be_mgmt.c
@@ -66,7 +66,6 @@ unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 					 struct bsg_job *job,
 					 struct be_dma_mem *nonemb_cmd)
 {
-	struct be_cmd_resp_hdr *resp;
 	struct be_mcc_wrb *wrb;
 	struct be_sge *mcc_sge;
 	unsigned int tag = 0;
@@ -76,7 +75,6 @@ unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 
 	nonemb_cmd->size = job->request_payload.payload_len;
 	memset(nonemb_cmd->va, 0, nonemb_cmd->size);
-	resp = nonemb_cmd->va;
 	region =  bsg_req->rqst_data.h_vendor.vendor_cmd[1];
 	sector_size =  bsg_req->rqst_data.h_vendor.vendor_cmd[2];
 	sector =  bsg_req->rqst_data.h_vendor.vendor_cmd[3];
@@ -128,50 +126,6 @@ unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 	return tag;
 }
 
-unsigned int  mgmt_invalidate_icds(struct beiscsi_hba *phba,
-				struct invalidate_command_table *inv_tbl,
-				unsigned int num_invalidate, unsigned int cid,
-				struct be_dma_mem *nonemb_cmd)
-
-{
-	struct be_ctrl_info *ctrl = &phba->ctrl;
-	struct be_mcc_wrb *wrb;
-	struct be_sge *sge;
-	struct invalidate_commands_params_in *req;
-	unsigned int i, tag;
-
-	mutex_lock(&ctrl->mbox_lock);
-	wrb = alloc_mcc_wrb(phba, &tag);
-	if (!wrb) {
-		mutex_unlock(&ctrl->mbox_lock);
-		return 0;
-	}
-
-	req = nonemb_cmd->va;
-	memset(req, 0, sizeof(*req));
-	sge = nonembedded_sgl(wrb);
-
-	be_wrb_hdr_prepare(wrb, sizeof(*req), false, 1);
-	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
-			OPCODE_COMMON_ISCSI_ERROR_RECOVERY_INVALIDATE_COMMANDS,
-			sizeof(*req));
-	req->ref_handle = 0;
-	req->cleanup_type = CMD_ISCSI_COMMAND_INVALIDATE;
-	for (i = 0; i < num_invalidate; i++) {
-		req->table[i].icd = inv_tbl->icd;
-		req->table[i].cid = inv_tbl->cid;
-		req->icd_count++;
-		inv_tbl++;
-	}
-	sge->pa_hi = cpu_to_le32(upper_32_bits(nonemb_cmd->dma));
-	sge->pa_lo = cpu_to_le32(nonemb_cmd->dma & 0xFFFFFFFF);
-	sge->len = cpu_to_le32(nonemb_cmd->size);
-
-	be_mcc_notify(phba, tag);
-	mutex_unlock(&ctrl->mbox_lock);
-	return tag;
-}
-
 unsigned int mgmt_invalidate_connection(struct beiscsi_hba *phba,
 					 struct beiscsi_endpoint *beiscsi_ep,
 					 unsigned short cid,
@@ -1066,7 +1020,6 @@ unsigned int beiscsi_boot_reopen_sess(struct beiscsi_hba *phba)
 unsigned int beiscsi_boot_get_sinfo(struct beiscsi_hba *phba)
 {
 	struct be_ctrl_info *ctrl = &phba->ctrl;
-	struct be_cmd_get_session_resp *resp;
 	struct be_cmd_get_session_req *req;
 	struct be_dma_mem *nonemb_cmd;
 	struct be_mcc_wrb *wrb;
@@ -1081,7 +1034,7 @@ unsigned int beiscsi_boot_get_sinfo(struct beiscsi_hba *phba)
 	}
 
 	nonemb_cmd = &phba->boot_struct.nonemb_cmd;
-	nonemb_cmd->size = sizeof(*resp);
+	nonemb_cmd->size = sizeof(struct be_cmd_get_session_resp);
 	nonemb_cmd->va = pci_alloc_consistent(phba->ctrl.pdev,
 					      nonemb_cmd->size,
 					      &nonemb_cmd->dma);
@@ -1096,7 +1049,7 @@ unsigned int beiscsi_boot_get_sinfo(struct beiscsi_hba *phba)
 	be_wrb_hdr_prepare(wrb, sizeof(*req), false, 1);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI_INI,
 			   OPCODE_ISCSI_INI_SESSION_GET_A_SESSION,
-			   sizeof(*resp));
+			   sizeof(struct be_cmd_get_session_resp));
 	req->session_handle = phba->boot_struct.s_handle;
 	sge->pa_hi = cpu_to_le32(upper_32_bits(nonemb_cmd->dma));
 	sge->pa_lo = cpu_to_le32(nonemb_cmd->dma & 0xFFFFFFFF);
@@ -1309,7 +1262,8 @@ beiscsi_adap_family_disp(struct device *dev, struct device_attribute *attr,
 	case BE_DEVICE_ID1:
 	case OC_DEVICE_ID1:
 	case OC_DEVICE_ID2:
-		return snprintf(buf, PAGE_SIZE, "BE2 Adapter Family\n");
+		return snprintf(buf, PAGE_SIZE,
+				"Obsolete/Unsupported BE2 Adapter Family\n");
 		break;
 	case BE_DEVICE_ID2:
 	case OC_DEVICE_ID3:
@@ -1341,7 +1295,7 @@ beiscsi_phys_port_disp(struct device *dev, struct device_attribute *attr,
 	struct Scsi_Host *shost = class_to_shost(dev);
 	struct beiscsi_hba *phba = iscsi_host_priv(shost);
 
-	return snprintf(buf, PAGE_SIZE, "Port Identifier : %d\n",
+	return snprintf(buf, PAGE_SIZE, "Port Identifier : %u\n",
 			phba->fw_config.phys_port);
 }
 
@@ -1494,3 +1448,64 @@ void beiscsi_offload_cxn_v2(struct beiscsi_offload_params *params,
 		     (params->dw[offsetof(struct amap_beiscsi_offload_params,
 		      exp_statsn) / 32] + 1));
 }
+
+int beiscsi_mgmt_invalidate_icds(struct beiscsi_hba *phba,
+				 struct invldt_cmd_tbl *inv_tbl,
+				 unsigned int nents)
+{
+	struct be_ctrl_info *ctrl = &phba->ctrl;
+	struct invldt_cmds_params_in *req;
+	struct be_dma_mem nonemb_cmd;
+	struct be_mcc_wrb *wrb;
+	unsigned int i, tag;
+	struct be_sge *sge;
+	int rc;
+
+	if (!nents || nents > BE_INVLDT_CMD_TBL_SZ)
+		return -EINVAL;
+
+	nonemb_cmd.size = sizeof(union be_invldt_cmds_params);
+	nonemb_cmd.va = pci_zalloc_consistent(phba->ctrl.pdev,
+					      nonemb_cmd.size,
+					      &nonemb_cmd.dma);
+	if (!nonemb_cmd.va) {
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_EH,
+			    "BM_%d : invldt_cmds_params alloc failed\n");
+		return -ENOMEM;
+	}
+
+	mutex_lock(&ctrl->mbox_lock);
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
+				    nonemb_cmd.va, nonemb_cmd.dma);
+		return -ENOMEM;
+	}
+
+	req = nonemb_cmd.va;
+	be_wrb_hdr_prepare(wrb, nonemb_cmd.size, false, 1);
+	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
+			OPCODE_COMMON_ISCSI_ERROR_RECOVERY_INVALIDATE_COMMANDS,
+			sizeof(*req));
+	req->ref_handle = 0;
+	req->cleanup_type = CMD_ISCSI_COMMAND_INVALIDATE;
+	for (i = 0; i < nents; i++) {
+		req->table[i].icd = inv_tbl[i].icd;
+		req->table[i].cid = inv_tbl[i].cid;
+		req->icd_count++;
+	}
+	sge = nonembedded_sgl(wrb);
+	sge->pa_hi = cpu_to_le32(upper_32_bits(nonemb_cmd.dma));
+	sge->pa_lo = cpu_to_le32(lower_32_bits(nonemb_cmd.dma));
+	sge->len = cpu_to_le32(nonemb_cmd.size);
+
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
+
+	rc = beiscsi_mccq_compl_wait(phba, tag, NULL, &nonemb_cmd);
+	if (rc != -EBUSY)
+		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
+				    nonemb_cmd.va, nonemb_cmd.dma);
+	return rc;
+}
diff --git a/drivers/scsi/be2iscsi/be_mgmt.h b/drivers/scsi/be2iscsi/be_mgmt.h
index b897cfd57c72..308f1472f98a 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.h
+++ b/drivers/scsi/be2iscsi/be_mgmt.h
@@ -36,66 +36,6 @@
 #define PCICFG_UE_STATUS_MASK_LOW       0xA8
 #define PCICFG_UE_STATUS_MASK_HI        0xAC
 
-/**
- * Pseudo amap definition in which each bit of the actual structure is defined
- * as a byte: used to calculate offset/shift/mask of each field
- */
-struct amap_mcc_sge {
-	u8 pa_lo[32];		/* dword 0 */
-	u8 pa_hi[32];		/* dword 1 */
-	u8 length[32];		/* DWORD 2 */
-} __packed;
-
-/**
- * Pseudo amap definition in which each bit of the actual structure is defined
- * as a byte: used to calculate offset/shift/mask of each field
- */
-struct amap_mcc_wrb_payload {
-	union {
-		struct amap_mcc_sge sgl[19];
-		u8 embedded[59 * 32];	/* DWORDS 57 to 115 */
-	} u;
-} __packed;
-
-/**
- * Pseudo amap definition in which each bit of the actual structure is defined
- * as a byte: used to calculate offset/shift/mask of each field
- */
-struct amap_mcc_wrb {
-	u8 embedded;		/* DWORD 0 */
-	u8 rsvd0[2];		/* DWORD 0 */
-	u8 sge_count[5];	/* DWORD 0 */
-	u8 rsvd1[16];		/* DWORD 0 */
-	u8 special[8];		/* DWORD 0 */
-	u8 payload_length[32];
-	u8 tag[64];		/* DWORD 2 */
-	u8 rsvd2[32];		/* DWORD 4 */
-	struct amap_mcc_wrb_payload payload;
-};
-
-struct mcc_sge {
-	u32 pa_lo;		/* dword 0 */
-	u32 pa_hi;		/* dword 1 */
-	u32 length;		/* DWORD 2 */
-} __packed;
-
-struct mcc_wrb_payload {
-	union {
-		struct mcc_sge sgl[19];
-		u32 embedded[59];	/* DWORDS 57 to 115 */
-	} u;
-} __packed;
-
-#define MCC_WRB_EMBEDDED_MASK                0x00000001
-
-struct mcc_wrb {
-	u32 dw[0];		/* DWORD 0 */
-	u32 payload_length;
-	u32 tag[2];		/* DWORD 2 */
-	u32 rsvd2[1];		/* DWORD 4 */
-	struct mcc_wrb_payload payload;
-};
-
 int mgmt_open_connection(struct beiscsi_hba *phba,
 			 struct sockaddr *dst_addr,
 			 struct beiscsi_endpoint *beiscsi_ep,
@@ -104,10 +44,6 @@ int mgmt_open_connection(struct beiscsi_hba *phba,
 unsigned int mgmt_upload_connection(struct beiscsi_hba *phba,
 				     unsigned short cid,
 				     unsigned int upload_flag);
-unsigned int mgmt_invalidate_icds(struct beiscsi_hba *phba,
-				struct invalidate_command_table *inv_tbl,
-				unsigned int num_invalidate, unsigned int cid,
-				struct be_dma_mem *nonemb_cmd);
 unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 					 struct beiscsi_hba *phba,
 					 struct bsg_job *job,
@@ -134,24 +70,31 @@ union iscsi_invalidate_connection_params {
 	struct iscsi_invalidate_connection_params_out response;
 } __packed;
 
-struct invalidate_commands_params_in {
+#define BE_INVLDT_CMD_TBL_SZ	128
+struct invldt_cmd_tbl {
+	unsigned short icd;
+	unsigned short cid;
+} __packed;
+
+struct invldt_cmds_params_in {
 	struct be_cmd_req_hdr hdr;
 	unsigned int ref_handle;
 	unsigned int icd_count;
-	struct invalidate_command_table table[128];
+	struct invldt_cmd_tbl table[BE_INVLDT_CMD_TBL_SZ];
 	unsigned short cleanup_type;
 	unsigned short unused;
 } __packed;
 
-struct invalidate_commands_params_out {
+struct invldt_cmds_params_out {
+	struct be_cmd_resp_hdr hdr;
 	unsigned int ref_handle;
 	unsigned int icd_count;
-	unsigned int icd_status[128];
+	unsigned int icd_status[BE_INVLDT_CMD_TBL_SZ];
 } __packed;
 
-union invalidate_commands_params {
-	struct invalidate_commands_params_in request;
-	struct invalidate_commands_params_out response;
+union be_invldt_cmds_params {
+	struct invldt_cmds_params_in request;
+	struct invldt_cmds_params_out response;
 } __packed;
 
 struct mgmt_hba_attributes {
@@ -231,16 +174,6 @@ struct be_bsg_vendor_cmd {
 
 #define GET_MGMT_CONTROLLER_WS(phba)    (phba->pmgmt_ws)
 
-/* MGMT CMD flags */
-
-#define MGMT_CMDH_FREE                (1<<0)
-
-/*  --- MGMT_ERROR_CODES --- */
-/*  Error Codes returned in the status field of the CMD response header */
-#define MGMT_STATUS_SUCCESS 0	/* The CMD completed without errors */
-#define MGMT_STATUS_FAILED 1	/* Error status in the Status field of */
-				/* the CMD_RESPONSE_HEADER  */
-
 #define ISCSI_GET_PDU_TEMPLATE_ADDRESS(pc, pa) {\
 	pa->lo = phba->init_mem[ISCSI_MEM_GLOBAL_HEADER].mem_array[0].\
 					bus_address.u.a32.address_lo;  \
@@ -270,6 +203,9 @@ unsigned int mgmt_invalidate_connection(struct beiscsi_hba *phba,
 					 unsigned short cid,
 					 unsigned short issue_reset,
 					 unsigned short savecfg_flag);
+int beiscsi_mgmt_invalidate_icds(struct beiscsi_hba *phba,
+				 struct invldt_cmd_tbl *inv_tbl,
+				 unsigned int nents);
 
 int beiscsi_if_en_dhcp(struct beiscsi_hba *phba, u32 ip_type);
 
diff --git a/drivers/scsi/bfa/bfa_fcs.c b/drivers/scsi/bfa/bfa_fcs.c
index 1e7e139d71ea..4aa61e20e82d 100644
--- a/drivers/scsi/bfa/bfa_fcs.c
+++ b/drivers/scsi/bfa/bfa_fcs.c
@@ -28,24 +28,6 @@
 BFA_TRC_FILE(FCS, FCS);
 
 /*
- * FCS sub-modules
- */
-struct bfa_fcs_mod_s {
-	void		(*attach) (struct bfa_fcs_s *fcs);
-	void		(*modinit) (struct bfa_fcs_s *fcs);
-	void		(*modexit) (struct bfa_fcs_s *fcs);
-};
-
-#define BFA_FCS_MODULE(_mod) { _mod ## _modinit, _mod ## _modexit }
-
-static struct bfa_fcs_mod_s fcs_modules[] = {
-	{ bfa_fcs_port_attach, NULL, NULL },
-	{ bfa_fcs_uf_attach, NULL, NULL },
-	{ bfa_fcs_fabric_attach, bfa_fcs_fabric_modinit,
-	  bfa_fcs_fabric_modexit },
-};
-
-/*
  *  fcs_api BFA FCS API
  */
 
@@ -58,52 +40,19 @@ bfa_fcs_exit_comp(void *fcs_cbarg)
 	complete(&bfad->comp);
 }
 
-
-
 /*
- *  fcs_api BFA FCS API
- */
-
-/*
- * fcs attach -- called once to initialize data structures at driver attach time
+ * fcs initialization, called once after bfa initialization is complete
  */
 void
-bfa_fcs_attach(struct bfa_fcs_s *fcs, struct bfa_s *bfa, struct bfad_s *bfad,
-	       bfa_boolean_t min_cfg)
+bfa_fcs_init(struct bfa_fcs_s *fcs)
 {
-	int		i;
-	struct bfa_fcs_mod_s  *mod;
-
-	fcs->bfa = bfa;
-	fcs->bfad = bfad;
-	fcs->min_cfg = min_cfg;
-	fcs->num_rport_logins = 0;
-
-	bfa->fcs = BFA_TRUE;
-	fcbuild_init();
-
-	for (i = 0; i < ARRAY_SIZE(fcs_modules); i++) {
-		mod = &fcs_modules[i];
-		if (mod->attach)
-			mod->attach(fcs);
-	}
+	bfa_sm_send_event(&fcs->fabric, BFA_FCS_FABRIC_SM_CREATE);
+	bfa_trc(fcs, 0);
 }
 
 /*
- * fcs initialization, called once after bfa initialization is complete
+ *  fcs_api BFA FCS API
  */
-void
-bfa_fcs_init(struct bfa_fcs_s *fcs)
-{
-	int	i;
-	struct bfa_fcs_mod_s  *mod;
-
-	for (i = 0; i < ARRAY_SIZE(fcs_modules); i++) {
-		mod = &fcs_modules[i];
-		if (mod->modinit)
-			mod->modinit(fcs);
-	}
-}
 
 /*
  * FCS update cfg - reset the pwwn/nwwn of fabric base logical port
@@ -180,26 +129,14 @@ bfa_fcs_driver_info_init(struct bfa_fcs_s *fcs,
 void
 bfa_fcs_exit(struct bfa_fcs_s *fcs)
 {
-	struct bfa_fcs_mod_s  *mod;
-	int		nmods, i;
-
 	bfa_wc_init(&fcs->wc, bfa_fcs_exit_comp, fcs);
-
-	nmods = ARRAY_SIZE(fcs_modules);
-
-	for (i = 0; i < nmods; i++) {
-
-		mod = &fcs_modules[i];
-		if (mod->modexit) {
-			bfa_wc_up(&fcs->wc);
-			mod->modexit(fcs);
-		}
-	}
-
+	bfa_wc_up(&fcs->wc);
+	bfa_trc(fcs, 0);
+	bfa_lps_delete(fcs->fabric.lps);
+	bfa_sm_send_event(&fcs->fabric, BFA_FCS_FABRIC_SM_DELETE);
 	bfa_wc_wait(&fcs->wc);
 }
 
-
 /*
  * Fabric module implementation.
  */
@@ -1128,62 +1065,6 @@ bfa_fcs_fabric_stop_comp(void *cbarg)
  */
 
 /*
- * Attach time initialization.
- */
-void
-bfa_fcs_fabric_attach(struct bfa_fcs_s *fcs)
-{
-	struct bfa_fcs_fabric_s *fabric;
-
-	fabric = &fcs->fabric;
-	memset(fabric, 0, sizeof(struct bfa_fcs_fabric_s));
-
-	/*
-	 * Initialize base fabric.
-	 */
-	fabric->fcs = fcs;
-	INIT_LIST_HEAD(&fabric->vport_q);
-	INIT_LIST_HEAD(&fabric->vf_q);
-	fabric->lps = bfa_lps_alloc(fcs->bfa);
-	WARN_ON(!fabric->lps);
-
-	/*
-	 * Initialize fabric delete completion handler. Fabric deletion is
-	 * complete when the last vport delete is complete.
-	 */
-	bfa_wc_init(&fabric->wc, bfa_fcs_fabric_delete_comp, fabric);
-	bfa_wc_up(&fabric->wc); /* For the base port */
-
-	bfa_sm_set_state(fabric, bfa_fcs_fabric_sm_uninit);
-	bfa_fcs_lport_attach(&fabric->bport, fabric->fcs, FC_VF_ID_NULL, NULL);
-}
-
-void
-bfa_fcs_fabric_modinit(struct bfa_fcs_s *fcs)
-{
-	bfa_sm_send_event(&fcs->fabric, BFA_FCS_FABRIC_SM_CREATE);
-	bfa_trc(fcs, 0);
-}
-
-/*
- *   Module cleanup
- */
-void
-bfa_fcs_fabric_modexit(struct bfa_fcs_s *fcs)
-{
-	struct bfa_fcs_fabric_s *fabric;
-
-	bfa_trc(fcs, 0);
-
-	/*
-	 * Cleanup base fabric.
-	 */
-	fabric = &fcs->fabric;
-	bfa_lps_delete(fabric->lps);
-	bfa_sm_send_event(fabric, BFA_FCS_FABRIC_SM_DELETE);
-}
-
-/*
  * Fabric module stop -- stop FCS actions
  */
 void
@@ -1633,12 +1514,6 @@ bfa_fcs_port_event_handler(void *cbarg, enum bfa_port_linkstate event)
 	}
 }
 
-void
-bfa_fcs_port_attach(struct bfa_fcs_s *fcs)
-{
-	bfa_fcport_event_register(fcs->bfa, bfa_fcs_port_event_handler, fcs);
-}
-
 /*
  * BFA FCS UF ( Unsolicited Frames)
  */
@@ -1706,8 +1581,44 @@ bfa_fcs_uf_recv(void *cbarg, struct bfa_uf_s *uf)
 	bfa_uf_free(uf);
 }
 
+/*
+ * fcs attach -- called once to initialize data structures at driver attach time
+ */
 void
-bfa_fcs_uf_attach(struct bfa_fcs_s *fcs)
+bfa_fcs_attach(struct bfa_fcs_s *fcs, struct bfa_s *bfa, struct bfad_s *bfad,
+	       bfa_boolean_t min_cfg)
 {
+	struct bfa_fcs_fabric_s *fabric = &fcs->fabric;
+
+	fcs->bfa = bfa;
+	fcs->bfad = bfad;
+	fcs->min_cfg = min_cfg;
+	fcs->num_rport_logins = 0;
+
+	bfa->fcs = BFA_TRUE;
+	fcbuild_init();
+
+	bfa_fcport_event_register(fcs->bfa, bfa_fcs_port_event_handler, fcs);
 	bfa_uf_recv_register(fcs->bfa, bfa_fcs_uf_recv, fcs);
+
+	memset(fabric, 0, sizeof(struct bfa_fcs_fabric_s));
+
+	/*
+	 * Initialize base fabric.
+	 */
+	fabric->fcs = fcs;
+	INIT_LIST_HEAD(&fabric->vport_q);
+	INIT_LIST_HEAD(&fabric->vf_q);
+	fabric->lps = bfa_lps_alloc(fcs->bfa);
+	WARN_ON(!fabric->lps);
+
+	/*
+	 * Initialize fabric delete completion handler. Fabric deletion is
+	 * complete when the last vport delete is complete.
+	 */
+	bfa_wc_init(&fabric->wc, bfa_fcs_fabric_delete_comp, fabric);
+	bfa_wc_up(&fabric->wc); /* For the base port */
+
+	bfa_sm_set_state(fabric, bfa_fcs_fabric_sm_uninit);
+	bfa_fcs_lport_attach(&fabric->bport, fabric->fcs, FC_VF_ID_NULL, NULL);
 }
diff --git a/drivers/scsi/bfa/bfa_fcs.h b/drivers/scsi/bfa/bfa_fcs.h
index 0f797a55d504..e60f72b766ea 100644
--- a/drivers/scsi/bfa/bfa_fcs.h
+++ b/drivers/scsi/bfa/bfa_fcs.h
@@ -808,9 +808,7 @@ void bfa_fcs_vf_get_ports(bfa_fcs_vf_t *vf, wwn_t vpwwn[], int *nports);
 /*
  * fabric protected interface functions
  */
-void bfa_fcs_fabric_attach(struct bfa_fcs_s *fcs);
 void bfa_fcs_fabric_modinit(struct bfa_fcs_s *fcs);
-void bfa_fcs_fabric_modexit(struct bfa_fcs_s *fcs);
 void bfa_fcs_fabric_link_up(struct bfa_fcs_fabric_s *fabric);
 void bfa_fcs_fabric_link_down(struct bfa_fcs_fabric_s *fabric);
 void bfa_fcs_fabric_addvport(struct bfa_fcs_fabric_s *fabric,
@@ -827,8 +825,6 @@ void	bfa_fcs_fabric_nsymb_init(struct bfa_fcs_fabric_s *fabric);
 void bfa_fcs_fabric_set_fabric_name(struct bfa_fcs_fabric_s *fabric,
 	       wwn_t fabric_name);
 u16 bfa_fcs_fabric_get_switch_oui(struct bfa_fcs_fabric_s *fabric);
-void bfa_fcs_uf_attach(struct bfa_fcs_s *fcs);
-void bfa_fcs_port_attach(struct bfa_fcs_s *fcs);
 void bfa_fcs_fabric_modstop(struct bfa_fcs_s *fcs);
 void bfa_fcs_fabric_sm_online(struct bfa_fcs_fabric_s *fabric,
 			enum bfa_fcs_fabric_event event);
diff --git a/drivers/scsi/cxlflash/common.h b/drivers/scsi/cxlflash/common.h
index 0e9de5d62da2..d11dcc59ff46 100644
--- a/drivers/scsi/cxlflash/common.h
+++ b/drivers/scsi/cxlflash/common.h
@@ -54,6 +54,9 @@ extern const struct file_operations cxlflash_cxl_fops;
 /* RRQ for master issued cmds */
 #define NUM_RRQ_ENTRY                   CXLFLASH_MAX_CMDS
 
+/* SQ for master issued cmds */
+#define NUM_SQ_ENTRY			CXLFLASH_MAX_CMDS
+
 
 static inline void check_sizes(void)
 {
@@ -155,8 +158,8 @@ static inline struct afu_cmd *sc_to_afucz(struct scsi_cmnd *sc)
 
 struct afu {
 	/* Stuff requiring alignment go first. */
-
-	u64 rrq_entry[NUM_RRQ_ENTRY];	/* 2K RRQ */
+	struct sisl_ioarcb sq[NUM_SQ_ENTRY];		/* 16K SQ */
+	u64 rrq_entry[NUM_RRQ_ENTRY];			/* 2K RRQ */
 
 	/* Beware of alignment till here. Preferably introduce new
 	 * fields after this point
@@ -171,9 +174,13 @@ struct afu {
 	struct sisl_host_map __iomem *host_map;		/* MC host map */
 	struct sisl_ctrl_map __iomem *ctrl_map;		/* MC control map */
 
-	struct kref mapcount;
-
 	ctx_hndl_t ctx_hndl;	/* master's context handle */
+
+	atomic_t hsq_credits;
+	spinlock_t hsq_slock;
+	struct sisl_ioarcb *hsq_start;
+	struct sisl_ioarcb *hsq_end;
+	struct sisl_ioarcb *hsq_curr;
 	u64 *hrrq_start;
 	u64 *hrrq_end;
 	u64 *hrrq_curr;
@@ -191,6 +198,23 @@ struct afu {
 
 };
 
+static inline bool afu_is_cmd_mode(struct afu *afu, u64 cmd_mode)
+{
+	u64 afu_cap = afu->interface_version >> SISL_INTVER_CAP_SHIFT;
+
+	return afu_cap & cmd_mode;
+}
+
+static inline bool afu_is_sq_cmd_mode(struct afu *afu)
+{
+	return afu_is_cmd_mode(afu, SISL_INTVER_CAP_SQ_CMD_MODE);
+}
+
+static inline bool afu_is_ioarrin_cmd_mode(struct afu *afu)
+{
+	return afu_is_cmd_mode(afu, SISL_INTVER_CAP_IOARRIN_CMD_MODE);
+}
+
 static inline u64 lun_to_lunid(u64 lun)
 {
 	__be64 lun_id;
diff --git a/drivers/scsi/cxlflash/lunmgt.c b/drivers/scsi/cxlflash/lunmgt.c
index 6c318db90c85..0efed177cc8b 100644
--- a/drivers/scsi/cxlflash/lunmgt.c
+++ b/drivers/scsi/cxlflash/lunmgt.c
@@ -32,11 +32,13 @@
  */
 static struct llun_info *create_local(struct scsi_device *sdev, u8 *wwid)
 {
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = NULL;
 
 	lli = kzalloc(sizeof(*lli), GFP_KERNEL);
 	if (unlikely(!lli)) {
-		pr_err("%s: could not allocate lli\n", __func__);
+		dev_err(dev, "%s: could not allocate lli\n", __func__);
 		goto out;
 	}
 
@@ -58,11 +60,13 @@ out:
  */
 static struct glun_info *create_global(struct scsi_device *sdev, u8 *wwid)
 {
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct glun_info *gli = NULL;
 
 	gli = kzalloc(sizeof(*gli), GFP_KERNEL);
 	if (unlikely(!gli)) {
-		pr_err("%s: could not allocate gli\n", __func__);
+		dev_err(dev, "%s: could not allocate gli\n", __func__);
 		goto out;
 	}
 
@@ -129,10 +133,10 @@ static struct glun_info *lookup_global(u8 *wwid)
  */
 static struct llun_info *find_and_create_lun(struct scsi_device *sdev, u8 *wwid)
 {
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = NULL;
 	struct glun_info *gli = NULL;
-	struct Scsi_Host *shost = sdev->host;
-	struct cxlflash_cfg *cfg = shost_priv(shost);
 
 	if (unlikely(!wwid))
 		goto out;
@@ -165,7 +169,7 @@ static struct llun_info *find_and_create_lun(struct scsi_device *sdev, u8 *wwid)
 	list_add(&gli->list, &global.gluns);
 
 out:
-	pr_debug("%s: returning %p\n", __func__, lli);
+	dev_dbg(dev, "%s: returning lli=%p, gli=%p\n", __func__, lli, gli);
 	return lli;
 }
 
@@ -225,17 +229,18 @@ void cxlflash_term_global_luns(void)
 int cxlflash_manage_lun(struct scsi_device *sdev,
 			struct dk_cxlflash_manage_lun *manage)
 {
-	int rc = 0;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = NULL;
+	int rc = 0;
 	u64 flags = manage->hdr.flags;
 	u32 chan = sdev->channel;
 
 	mutex_lock(&global.mutex);
 	lli = find_and_create_lun(sdev, manage->wwid);
-	pr_debug("%s: ENTER: WWID = %016llX%016llX, flags = %016llX li = %p\n",
-		 __func__, get_unaligned_be64(&manage->wwid[0]),
-		 get_unaligned_be64(&manage->wwid[8]),
-		 manage->hdr.flags, lli);
+	dev_dbg(dev, "%s: WWID=%016llx%016llx, flags=%016llx lli=%p\n",
+		__func__, get_unaligned_be64(&manage->wwid[0]),
+		get_unaligned_be64(&manage->wwid[8]), manage->hdr.flags, lli);
 	if (unlikely(!lli)) {
 		rc = -ENOMEM;
 		goto out;
@@ -265,11 +270,11 @@ int cxlflash_manage_lun(struct scsi_device *sdev,
 		}
 	}
 
-	pr_debug("%s: port_sel = %08X chan = %u lun_id = %016llX\n", __func__,
-		 lli->port_sel, chan, lli->lun_id[chan]);
+	dev_dbg(dev, "%s: port_sel=%08x chan=%u lun_id=%016llx\n",
+		__func__, lli->port_sel, chan, lli->lun_id[chan]);
 
 out:
 	mutex_unlock(&global.mutex);
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index b17ebf6d0a7e..7069639e92bc 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -43,6 +43,9 @@ MODULE_LICENSE("GPL");
  */
 static void process_cmd_err(struct afu_cmd *cmd, struct scsi_cmnd *scp)
 {
+	struct afu *afu = cmd->parent;
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_ioarcb *ioarcb;
 	struct sisl_ioasa *ioasa;
 	u32 resid;
@@ -56,21 +59,20 @@ static void process_cmd_err(struct afu_cmd *cmd, struct scsi_cmnd *scp)
 	if (ioasa->rc.flags & SISL_RC_FLAGS_UNDERRUN) {
 		resid = ioasa->resid;
 		scsi_set_resid(scp, resid);
-		pr_debug("%s: cmd underrun cmd = %p scp = %p, resid = %d\n",
-			 __func__, cmd, scp, resid);
+		dev_dbg(dev, "%s: cmd underrun cmd = %p scp = %p, resid = %d\n",
+			__func__, cmd, scp, resid);
 	}
 
 	if (ioasa->rc.flags & SISL_RC_FLAGS_OVERRUN) {
-		pr_debug("%s: cmd underrun cmd = %p scp = %p\n",
-			 __func__, cmd, scp);
+		dev_dbg(dev, "%s: cmd underrun cmd = %p scp = %p\n",
+			__func__, cmd, scp);
 		scp->result = (DID_ERROR << 16);
 	}
 
-	pr_debug("%s: cmd failed afu_rc=%d scsi_rc=%d fc_rc=%d "
-		 "afu_extra=0x%X, scsi_extra=0x%X, fc_extra=0x%X\n",
-		 __func__, ioasa->rc.afu_rc, ioasa->rc.scsi_rc,
-		 ioasa->rc.fc_rc, ioasa->afu_extra, ioasa->scsi_extra,
-		 ioasa->fc_extra);
+	dev_dbg(dev, "%s: cmd failed afu_rc=%02x scsi_rc=%02x fc_rc=%02x "
+		"afu_extra=%02x scsi_extra=%02x fc_extra=%02x\n", __func__,
+		ioasa->rc.afu_rc, ioasa->rc.scsi_rc, ioasa->rc.fc_rc,
+		ioasa->afu_extra, ioasa->scsi_extra, ioasa->fc_extra);
 
 	if (ioasa->rc.scsi_rc) {
 		/* We have a SCSI status */
@@ -159,6 +161,7 @@ static void cmd_complete(struct afu_cmd *cmd)
 	ulong lock_flags;
 	struct afu *afu = cmd->parent;
 	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
 	bool cmd_is_tmf;
 
 	if (cmd->scp) {
@@ -170,9 +173,8 @@ static void cmd_complete(struct afu_cmd *cmd)
 
 		cmd_is_tmf = cmd->cmd_tmf;
 
-		pr_debug_ratelimited("%s: calling scsi_done scp=%p result=%X "
-				     "ioasc=%d\n", __func__, scp, scp->result,
-				     cmd->sa.ioasc);
+		dev_dbg_ratelimited(dev, "%s:scp=%p result=%08x ioasc=%08x\n",
+				    __func__, scp, scp->result, cmd->sa.ioasc);
 
 		scsi_dma_unmap(scp);
 		scp->scsi_done(scp);
@@ -188,10 +190,11 @@ static void cmd_complete(struct afu_cmd *cmd)
 }
 
 /**
- * context_reset_ioarrin() - reset command owner context via IOARRIN register
+ * context_reset() - reset command owner context via specified register
  * @cmd:	AFU command that timed out.
+ * @reset_reg:	MMIO register to perform reset.
  */
-static void context_reset_ioarrin(struct afu_cmd *cmd)
+static void context_reset(struct afu_cmd *cmd, __be64 __iomem *reset_reg)
 {
 	int nretry = 0;
 	u64 rrin = 0x1;
@@ -199,22 +202,44 @@ static void context_reset_ioarrin(struct afu_cmd *cmd)
 	struct cxlflash_cfg *cfg = afu->parent;
 	struct device *dev = &cfg->dev->dev;
 
-	pr_debug("%s: cmd=%p\n", __func__, cmd);
+	dev_dbg(dev, "%s: cmd=%p\n", __func__, cmd);
 
-	writeq_be(rrin, &afu->host_map->ioarrin);
+	writeq_be(rrin, reset_reg);
 	do {
-		rrin = readq_be(&afu->host_map->ioarrin);
+		rrin = readq_be(reset_reg);
 		if (rrin != 0x1)
 			break;
 		/* Double delay each time */
 		udelay(1 << nretry);
 	} while (nretry++ < MC_ROOM_RETRY_CNT);
 
-	dev_dbg(dev, "%s: returning rrin=0x%016llX nretry=%d\n",
+	dev_dbg(dev, "%s: returning rrin=%016llx nretry=%d\n",
 		__func__, rrin, nretry);
 }
 
 /**
+ * context_reset_ioarrin() - reset command owner context via IOARRIN register
+ * @cmd:	AFU command that timed out.
+ */
+static void context_reset_ioarrin(struct afu_cmd *cmd)
+{
+	struct afu *afu = cmd->parent;
+
+	context_reset(cmd, &afu->host_map->ioarrin);
+}
+
+/**
+ * context_reset_sq() - reset command owner context w/ SQ Context Reset register
+ * @cmd:	AFU command that timed out.
+ */
+static void context_reset_sq(struct afu_cmd *cmd)
+{
+	struct afu *afu = cmd->parent;
+
+	context_reset(cmd, &afu->host_map->sq_ctx_reset);
+}
+
+/**
  * send_cmd_ioarrin() - sends an AFU command via IOARRIN register
  * @afu:	AFU associated with the host.
  * @cmd:	AFU command to send.
@@ -251,8 +276,51 @@ static int send_cmd_ioarrin(struct afu *afu, struct afu_cmd *cmd)
 	writeq_be((u64)&cmd->rcb, &afu->host_map->ioarrin);
 out:
 	spin_unlock_irqrestore(&afu->rrin_slock, lock_flags);
-	pr_devel("%s: cmd=%p len=%d ea=%p rc=%d\n", __func__, cmd,
-		 cmd->rcb.data_len, (void *)cmd->rcb.data_ea, rc);
+	dev_dbg(dev, "%s: cmd=%p len=%u ea=%016llx rc=%d\n", __func__,
+		cmd, cmd->rcb.data_len, cmd->rcb.data_ea, rc);
+	return rc;
+}
+
+/**
+ * send_cmd_sq() - sends an AFU command via SQ ring
+ * @afu:	AFU associated with the host.
+ * @cmd:	AFU command to send.
+ *
+ * Return:
+ *	0 on success, SCSI_MLQUEUE_HOST_BUSY on failure
+ */
+static int send_cmd_sq(struct afu *afu, struct afu_cmd *cmd)
+{
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
+	int rc = 0;
+	int newval;
+	ulong lock_flags;
+
+	newval = atomic_dec_if_positive(&afu->hsq_credits);
+	if (newval <= 0) {
+		rc = SCSI_MLQUEUE_HOST_BUSY;
+		goto out;
+	}
+
+	cmd->rcb.ioasa = &cmd->sa;
+
+	spin_lock_irqsave(&afu->hsq_slock, lock_flags);
+
+	*afu->hsq_curr = cmd->rcb;
+	if (afu->hsq_curr < afu->hsq_end)
+		afu->hsq_curr++;
+	else
+		afu->hsq_curr = afu->hsq_start;
+	writeq_be((u64)afu->hsq_curr, &afu->host_map->sq_tail);
+
+	spin_unlock_irqrestore(&afu->hsq_slock, lock_flags);
+out:
+	dev_dbg(dev, "%s: cmd=%p len=%u ea=%016llx ioasa=%p rc=%d curr=%p "
+	       "head=%016llx tail=%016llx\n", __func__, cmd, cmd->rcb.data_len,
+	       cmd->rcb.data_ea, cmd->rcb.ioasa, rc, afu->hsq_curr,
+	       readq_be(&afu->host_map->sq_head),
+	       readq_be(&afu->host_map->sq_tail));
 	return rc;
 }
 
@@ -266,6 +334,8 @@ out:
  */
 static int wait_resp(struct afu *afu, struct afu_cmd *cmd)
 {
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
 	int rc = 0;
 	ulong timeout = msecs_to_jiffies(cmd->rcb.timeout * 2 * 1000);
 
@@ -276,10 +346,8 @@ static int wait_resp(struct afu *afu, struct afu_cmd *cmd)
 	}
 
 	if (unlikely(cmd->sa.ioasc != 0)) {
-		pr_err("%s: CMD 0x%X failed, IOASC: flags 0x%X, afu_rc 0x%X, "
-		       "scsi_rc 0x%X, fc_rc 0x%X\n", __func__, cmd->rcb.cdb[0],
-		       cmd->sa.rc.flags, cmd->sa.rc.afu_rc, cmd->sa.rc.scsi_rc,
-		       cmd->sa.rc.fc_rc);
+		dev_err(dev, "%s: cmd %02x failed, ioasc=%08x\n",
+			__func__, cmd->rcb.cdb[0], cmd->sa.ioasc);
 		rc = -1;
 	}
 
@@ -298,8 +366,7 @@ static int wait_resp(struct afu *afu, struct afu_cmd *cmd)
 static int send_tmf(struct afu *afu, struct scsi_cmnd *scp, u64 tmfcmd)
 {
 	u32 port_sel = scp->device->channel + 1;
-	struct Scsi_Host *host = scp->device->host;
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(scp->device->host);
 	struct afu_cmd *cmd = sc_to_afucz(scp);
 	struct device *dev = &cfg->dev->dev;
 	ulong lock_flags;
@@ -344,7 +411,7 @@ static int send_tmf(struct afu *afu, struct scsi_cmnd *scp, u64 tmfcmd)
 						       to);
 	if (!to) {
 		cfg->tmf_active = false;
-		dev_err(dev, "%s: TMF timed out!\n", __func__);
+		dev_err(dev, "%s: TMF timed out\n", __func__);
 		rc = -1;
 	}
 	spin_unlock_irqrestore(&cfg->tmf_slock, lock_flags);
@@ -352,16 +419,6 @@ out:
 	return rc;
 }
 
-static void afu_unmap(struct kref *ref)
-{
-	struct afu *afu = container_of(ref, struct afu, mapcount);
-
-	if (likely(afu->afu_map)) {
-		cxl_psa_unmap((void __iomem *)afu->afu_map);
-		afu->afu_map = NULL;
-	}
-}
-
 /**
  * cxlflash_driver_info() - information handler for this host driver
  * @host:	SCSI host associated with device.
@@ -382,7 +439,7 @@ static const char *cxlflash_driver_info(struct Scsi_Host *host)
  */
 static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(host);
 	struct afu *afu = cfg->afu;
 	struct device *dev = &cfg->dev->dev;
 	struct afu_cmd *cmd = sc_to_afucz(scp);
@@ -392,10 +449,9 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 	ulong lock_flags;
 	int nseg = 0;
 	int rc = 0;
-	int kref_got = 0;
 
 	dev_dbg_ratelimited(dev, "%s: (scp=%p) %d/%d/%d/%llu "
-			    "cdb=(%08X-%08X-%08X-%08X)\n",
+			    "cdb=(%08x-%08x-%08x-%08x)\n",
 			    __func__, scp, host->host_no, scp->device->channel,
 			    scp->device->id, scp->device->lun,
 			    get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
@@ -417,11 +473,11 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 
 	switch (cfg->state) {
 	case STATE_RESET:
-		dev_dbg_ratelimited(dev, "%s: device is in reset!\n", __func__);
+		dev_dbg_ratelimited(dev, "%s: device is in reset\n", __func__);
 		rc = SCSI_MLQUEUE_HOST_BUSY;
 		goto out;
 	case STATE_FAILTERM:
-		dev_dbg_ratelimited(dev, "%s: device has failed!\n", __func__);
+		dev_dbg_ratelimited(dev, "%s: device has failed\n", __func__);
 		scp->result = (DID_NO_CONNECT << 16);
 		scp->scsi_done(scp);
 		rc = 0;
@@ -430,13 +486,10 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 		break;
 	}
 
-	kref_get(&cfg->afu->mapcount);
-	kref_got = 1;
-
 	if (likely(sg)) {
 		nseg = scsi_dma_map(scp);
 		if (unlikely(nseg < 0)) {
-			dev_err(dev, "%s: Fail DMA map!\n", __func__);
+			dev_err(dev, "%s: Fail DMA map\n", __func__);
 			rc = SCSI_MLQUEUE_HOST_BUSY;
 			goto out;
 		}
@@ -463,9 +516,6 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 	if (unlikely(rc))
 		scsi_dma_unmap(scp);
 out:
-	if (kref_got)
-		kref_put(&afu->mapcount, afu_unmap);
-	pr_devel("%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -503,13 +553,15 @@ static void free_mem(struct cxlflash_cfg *cfg)
  *
  * Safe to call with AFU in a partially allocated/initialized state.
  *
- * Waits for any active internal AFU commands to timeout and then unmaps
- * the MMIO space.
+ * Cancels scheduled worker threads, waits for any active internal AFU
+ * commands to timeout and then unmaps the MMIO space.
  */
 static void stop_afu(struct cxlflash_cfg *cfg)
 {
 	struct afu *afu = cfg->afu;
 
+	cancel_work_sync(&cfg->work_q);
+
 	if (likely(afu)) {
 		while (atomic_read(&afu->cmds_active))
 			ssleep(1);
@@ -517,7 +569,6 @@ static void stop_afu(struct cxlflash_cfg *cfg)
 			cxl_psa_unmap((void __iomem *)afu->afu_map);
 			afu->afu_map = NULL;
 		}
-		kref_put(&afu->mapcount, afu_unmap);
 	}
 }
 
@@ -585,6 +636,8 @@ static void term_mc(struct cxlflash_cfg *cfg)
  */
 static void term_afu(struct cxlflash_cfg *cfg)
 {
+	struct device *dev = &cfg->dev->dev;
+
 	/*
 	 * Tear down is carefully orchestrated to ensure
 	 * no interrupts can come in when the problem state
@@ -600,7 +653,7 @@ static void term_afu(struct cxlflash_cfg *cfg)
 
 	term_mc(cfg);
 
-	pr_debug("%s: returning\n", __func__);
+	dev_dbg(dev, "%s: returning\n", __func__);
 }
 
 /**
@@ -627,8 +680,7 @@ static void notify_shutdown(struct cxlflash_cfg *cfg, bool wait)
 		return;
 
 	if (!afu || !afu->afu_map) {
-		dev_dbg(dev, "%s: The problem state area is not mapped\n",
-			__func__);
+		dev_dbg(dev, "%s: Problem state area not mapped\n", __func__);
 		return;
 	}
 
@@ -670,10 +722,11 @@ static void notify_shutdown(struct cxlflash_cfg *cfg, bool wait)
 static void cxlflash_remove(struct pci_dev *pdev)
 {
 	struct cxlflash_cfg *cfg = pci_get_drvdata(pdev);
+	struct device *dev = &pdev->dev;
 	ulong lock_flags;
 
 	if (!pci_is_enabled(pdev)) {
-		pr_debug("%s: Device is disabled\n", __func__);
+		dev_dbg(dev, "%s: Device is disabled\n", __func__);
 		return;
 	}
 
@@ -699,7 +752,6 @@ static void cxlflash_remove(struct pci_dev *pdev)
 		scsi_remove_host(cfg->host);
 		/* fall through */
 	case INIT_STATE_AFU:
-		cancel_work_sync(&cfg->work_q);
 		term_afu(cfg);
 	case INIT_STATE_PCI:
 		pci_disable_device(pdev);
@@ -709,7 +761,7 @@ static void cxlflash_remove(struct pci_dev *pdev)
 		break;
 	}
 
-	pr_debug("%s: returning\n", __func__);
+	dev_dbg(dev, "%s: returning\n", __func__);
 }
 
 /**
@@ -727,7 +779,7 @@ static int alloc_mem(struct cxlflash_cfg *cfg)
 	int rc = 0;
 	struct device *dev = &cfg->dev->dev;
 
-	/* AFU is ~12k, i.e. only one 64k page or up to four 4k pages */
+	/* AFU is ~28k, i.e. only one 64k page or up to seven 4k pages */
 	cfg->afu = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
 					    get_order(sizeof(struct afu)));
 	if (unlikely(!cfg->afu)) {
@@ -751,6 +803,7 @@ out:
 static int init_pci(struct cxlflash_cfg *cfg)
 {
 	struct pci_dev *pdev = cfg->dev;
+	struct device *dev = &cfg->dev->dev;
 	int rc = 0;
 
 	rc = pci_enable_device(pdev);
@@ -761,15 +814,14 @@ static int init_pci(struct cxlflash_cfg *cfg)
 		}
 
 		if (rc) {
-			dev_err(&pdev->dev, "%s: Cannot enable adapter\n",
-				__func__);
+			dev_err(dev, "%s: Cannot enable adapter\n", __func__);
 			cxlflash_wait_for_pci_err_recovery(cfg);
 			goto out;
 		}
 	}
 
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -782,19 +834,19 @@ out:
 static int init_scsi(struct cxlflash_cfg *cfg)
 {
 	struct pci_dev *pdev = cfg->dev;
+	struct device *dev = &cfg->dev->dev;
 	int rc = 0;
 
 	rc = scsi_add_host(cfg->host, &pdev->dev);
 	if (rc) {
-		dev_err(&pdev->dev, "%s: scsi_add_host failed (rc=%d)\n",
-			__func__, rc);
+		dev_err(dev, "%s: scsi_add_host failed rc=%d\n", __func__, rc);
 		goto out;
 	}
 
 	scsi_scan_host(cfg->host);
 
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -844,16 +896,12 @@ static void set_port_offline(__be64 __iomem *fc_regs)
  * Return:
  *	TRUE (1) when the specified port is online
  *	FALSE (0) when the specified port fails to come online after timeout
- *	-EINVAL when @delay_us is less than 1000
  */
-static int wait_port_online(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
+static bool wait_port_online(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
 {
 	u64 status;
 
-	if (delay_us < 1000) {
-		pr_err("%s: invalid delay specified %d\n", __func__, delay_us);
-		return -EINVAL;
-	}
+	WARN_ON(delay_us < 1000);
 
 	do {
 		msleep(delay_us / 1000);
@@ -877,16 +925,12 @@ static int wait_port_online(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
  * Return:
  *	TRUE (1) when the specified port is offline
  *	FALSE (0) when the specified port fails to go offline after timeout
- *	-EINVAL when @delay_us is less than 1000
  */
-static int wait_port_offline(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
+static bool wait_port_offline(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
 {
 	u64 status;
 
-	if (delay_us < 1000) {
-		pr_err("%s: invalid delay specified %d\n", __func__, delay_us);
-		return -EINVAL;
-	}
+	WARN_ON(delay_us < 1000);
 
 	do {
 		msleep(delay_us / 1000);
@@ -915,11 +959,14 @@ static int wait_port_offline(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
 static void afu_set_wwpn(struct afu *afu, int port, __be64 __iomem *fc_regs,
 			 u64 wwpn)
 {
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
+
 	set_port_offline(fc_regs);
 	if (!wait_port_offline(fc_regs, FC_PORT_STATUS_RETRY_INTERVAL_US,
 			       FC_PORT_STATUS_RETRY_CNT)) {
-		pr_debug("%s: wait on port %d to go offline timed out\n",
-			 __func__, port);
+		dev_dbg(dev, "%s: wait on port %d to go offline timed out\n",
+			__func__, port);
 	}
 
 	writeq_be(wwpn, &fc_regs[FC_PNAME / 8]);
@@ -927,8 +974,8 @@ static void afu_set_wwpn(struct afu *afu, int port, __be64 __iomem *fc_regs,
 	set_port_online(fc_regs);
 	if (!wait_port_online(fc_regs, FC_PORT_STATUS_RETRY_INTERVAL_US,
 			      FC_PORT_STATUS_RETRY_CNT)) {
-		pr_debug("%s: wait on port %d to go online timed out\n",
-			 __func__, port);
+		dev_dbg(dev, "%s: wait on port %d to go online timed out\n",
+			__func__, port);
 	}
 }
 
@@ -947,6 +994,8 @@ static void afu_set_wwpn(struct afu *afu, int port, __be64 __iomem *fc_regs,
  */
 static void afu_link_reset(struct afu *afu, int port, __be64 __iomem *fc_regs)
 {
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
 	u64 port_sel;
 
 	/* first switch the AFU to the other links, if any */
@@ -958,21 +1007,21 @@ static void afu_link_reset(struct afu *afu, int port, __be64 __iomem *fc_regs)
 	set_port_offline(fc_regs);
 	if (!wait_port_offline(fc_regs, FC_PORT_STATUS_RETRY_INTERVAL_US,
 			       FC_PORT_STATUS_RETRY_CNT))
-		pr_err("%s: wait on port %d to go offline timed out\n",
-		       __func__, port);
+		dev_err(dev, "%s: wait on port %d to go offline timed out\n",
+			__func__, port);
 
 	set_port_online(fc_regs);
 	if (!wait_port_online(fc_regs, FC_PORT_STATUS_RETRY_INTERVAL_US,
 			      FC_PORT_STATUS_RETRY_CNT))
-		pr_err("%s: wait on port %d to go online timed out\n",
-		       __func__, port);
+		dev_err(dev, "%s: wait on port %d to go online timed out\n",
+			__func__, port);
 
 	/* switch back to include this port */
 	port_sel |= (1ULL << port);
 	writeq_be(port_sel, &afu->afu_map->global.regs.afu_port_sel);
 	cxlflash_afu_sync(afu, 0, 0, AFU_GSYNC);
 
-	pr_debug("%s: returning port_sel=%lld\n", __func__, port_sel);
+	dev_dbg(dev, "%s: returning port_sel=%016llx\n", __func__, port_sel);
 }
 
 /*
@@ -1082,6 +1131,8 @@ static void afu_err_intr_init(struct afu *afu)
 static irqreturn_t cxlflash_sync_err_irq(int irq, void *data)
 {
 	struct afu *afu = (struct afu *)data;
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
 	u64 reg;
 	u64 reg_unmasked;
 
@@ -1089,18 +1140,17 @@ static irqreturn_t cxlflash_sync_err_irq(int irq, void *data)
 	reg_unmasked = (reg & SISL_ISTATUS_UNMASK);
 
 	if (reg_unmasked == 0UL) {
-		pr_err("%s: %llX: spurious interrupt, intr_status %016llX\n",
-		       __func__, (u64)afu, reg);
+		dev_err(dev, "%s: spurious interrupt, intr_status=%016llx\n",
+			__func__, reg);
 		goto cxlflash_sync_err_irq_exit;
 	}
 
-	pr_err("%s: %llX: unexpected interrupt, intr_status %016llX\n",
-	       __func__, (u64)afu, reg);
+	dev_err(dev, "%s: unexpected interrupt, intr_status=%016llx\n",
+		__func__, reg);
 
 	writeq_be(reg_unmasked, &afu->host_map->intr_clear);
 
 cxlflash_sync_err_irq_exit:
-	pr_debug("%s: returning rc=%d\n", __func__, IRQ_HANDLED);
 	return IRQ_HANDLED;
 }
 
@@ -1115,6 +1165,8 @@ static irqreturn_t cxlflash_rrq_irq(int irq, void *data)
 {
 	struct afu *afu = (struct afu *)data;
 	struct afu_cmd *cmd;
+	struct sisl_ioasa *ioasa;
+	struct sisl_ioarcb *ioarcb;
 	bool toggle = afu->toggle;
 	u64 entry,
 	    *hrrq_start = afu->hrrq_start,
@@ -1128,7 +1180,16 @@ static irqreturn_t cxlflash_rrq_irq(int irq, void *data)
 		if ((entry & SISL_RESP_HANDLE_T_BIT) != toggle)
 			break;
 
-		cmd = (struct afu_cmd *)(entry & ~SISL_RESP_HANDLE_T_BIT);
+		entry &= ~SISL_RESP_HANDLE_T_BIT;
+
+		if (afu_is_sq_cmd_mode(afu)) {
+			ioasa = (struct sisl_ioasa *)entry;
+			cmd = container_of(ioasa, struct afu_cmd, sa);
+		} else {
+			ioarcb = (struct sisl_ioarcb *)entry;
+			cmd = container_of(ioarcb, struct afu_cmd, rcb);
+		}
+
 		cmd_complete(cmd);
 
 		/* Advance to next entry or wrap and flip the toggle bit */
@@ -1138,6 +1199,8 @@ static irqreturn_t cxlflash_rrq_irq(int irq, void *data)
 			hrrq_curr = hrrq_start;
 			toggle ^= SISL_RESP_HANDLE_T_BIT;
 		}
+
+		atomic_inc(&afu->hsq_credits);
 	}
 
 	afu->hrrq_curr = hrrq_curr;
@@ -1169,7 +1232,7 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 	reg_unmasked = (reg & SISL_ASTATUS_UNMASK);
 
 	if (reg_unmasked == 0) {
-		dev_err(dev, "%s: spurious interrupt, aintr_status 0x%016llX\n",
+		dev_err(dev, "%s: spurious interrupt, aintr_status=%016llx\n",
 			__func__, reg);
 		goto out;
 	}
@@ -1185,7 +1248,7 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 
 		port = info->port;
 
-		dev_err(dev, "%s: FC Port %d -> %s, fc_status 0x%08llX\n",
+		dev_err(dev, "%s: FC Port %d -> %s, fc_status=%016llx\n",
 			__func__, port, info->desc,
 		       readq_be(&global->fc_regs[port][FC_STATUS / 8]));
 
@@ -1198,7 +1261,6 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 				__func__, port);
 			cfg->lr_state = LINK_RESET_REQUIRED;
 			cfg->lr_port = port;
-			kref_get(&cfg->afu->mapcount);
 			schedule_work(&cfg->work_q);
 		}
 
@@ -1210,7 +1272,7 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 			 * should be the same and tracing one is sufficient.
 			 */
 
-			dev_err(dev, "%s: fc %d: clearing fc_error 0x%08llX\n",
+			dev_err(dev, "%s: fc %d: clearing fc_error=%016llx\n",
 				__func__, port, reg);
 
 			writeq_be(reg, &global->fc_regs[port][FC_ERROR / 8]);
@@ -1219,13 +1281,11 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 
 		if (info->action & SCAN_HOST) {
 			atomic_inc(&cfg->scan_host_needed);
-			kref_get(&cfg->afu->mapcount);
 			schedule_work(&cfg->work_q);
 		}
 	}
 
 out:
-	dev_dbg(dev, "%s: returning IRQ_HANDLED, afu=%p\n", __func__, afu);
 	return IRQ_HANDLED;
 }
 
@@ -1237,13 +1297,14 @@ out:
  */
 static int start_context(struct cxlflash_cfg *cfg)
 {
+	struct device *dev = &cfg->dev->dev;
 	int rc = 0;
 
 	rc = cxl_start_context(cfg->mcctx,
 			       cfg->afu->work.work_element_descriptor,
 			       NULL);
 
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1256,7 +1317,8 @@ static int start_context(struct cxlflash_cfg *cfg)
  */
 static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 {
-	struct pci_dev *dev = cfg->dev;
+	struct device *dev = &cfg->dev->dev;
+	struct pci_dev *pdev = cfg->dev;
 	int rc = 0;
 	int ro_start, ro_size, i, j, k;
 	ssize_t vpd_size;
@@ -1265,10 +1327,10 @@ static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 	char *wwpn_vpd_tags[NUM_FC_PORTS] = { "V5", "V6" };
 
 	/* Get the VPD data from the device */
-	vpd_size = cxl_read_adapter_vpd(dev, vpd_data, sizeof(vpd_data));
+	vpd_size = cxl_read_adapter_vpd(pdev, vpd_data, sizeof(vpd_data));
 	if (unlikely(vpd_size <= 0)) {
-		dev_err(&dev->dev, "%s: Unable to read VPD (size = %ld)\n",
-		       __func__, vpd_size);
+		dev_err(dev, "%s: Unable to read VPD (size = %ld)\n",
+			__func__, vpd_size);
 		rc = -ENODEV;
 		goto out;
 	}
@@ -1277,8 +1339,7 @@ static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 	ro_start = pci_vpd_find_tag(vpd_data, 0, vpd_size,
 				    PCI_VPD_LRDT_RO_DATA);
 	if (unlikely(ro_start < 0)) {
-		dev_err(&dev->dev, "%s: VPD Read-only data not found\n",
-			__func__);
+		dev_err(dev, "%s: VPD Read-only data not found\n", __func__);
 		rc = -ENODEV;
 		goto out;
 	}
@@ -1288,8 +1349,8 @@ static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 	j = ro_size;
 	i = ro_start + PCI_VPD_LRDT_TAG_SIZE;
 	if (unlikely((i + j) > vpd_size)) {
-		pr_debug("%s: Might need to read more VPD (%d > %ld)\n",
-			 __func__, (i + j), vpd_size);
+		dev_dbg(dev, "%s: Might need to read more VPD (%d > %ld)\n",
+			__func__, (i + j), vpd_size);
 		ro_size = vpd_size - i;
 	}
 
@@ -1307,8 +1368,8 @@ static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 
 		i = pci_vpd_find_info_keyword(vpd_data, i, j, wwpn_vpd_tags[k]);
 		if (unlikely(i < 0)) {
-			dev_err(&dev->dev, "%s: Port %d WWPN not found "
-				"in VPD\n", __func__, k);
+			dev_err(dev, "%s: Port %d WWPN not found in VPD\n",
+				__func__, k);
 			rc = -ENODEV;
 			goto out;
 		}
@@ -1316,9 +1377,8 @@ static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 		j = pci_vpd_info_field_size(&vpd_data[i]);
 		i += PCI_VPD_INFO_FLD_HDR_SIZE;
 		if (unlikely((i + j > vpd_size) || (j != WWPN_LEN))) {
-			dev_err(&dev->dev, "%s: Port %d WWPN incomplete or "
-				"VPD corrupt\n",
-			       __func__, k);
+			dev_err(dev, "%s: Port %d WWPN incomplete or bad VPD\n",
+				__func__, k);
 			rc = -ENODEV;
 			goto out;
 		}
@@ -1326,15 +1386,15 @@ static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 		memcpy(tmp_buf, &vpd_data[i], WWPN_LEN);
 		rc = kstrtoul(tmp_buf, WWPN_LEN, (ulong *)&wwpn[k]);
 		if (unlikely(rc)) {
-			dev_err(&dev->dev, "%s: Fail to convert port %d WWPN "
-				"to integer\n", __func__, k);
+			dev_err(dev, "%s: WWPN conversion failed for port %d\n",
+				__func__, k);
 			rc = -ENODEV;
 			goto out;
 		}
 	}
 
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1388,12 +1448,18 @@ static int init_global(struct cxlflash_cfg *cfg)
 		goto out;
 	}
 
-	pr_debug("%s: wwpn0=0x%llX wwpn1=0x%llX\n", __func__, wwpn[0], wwpn[1]);
+	dev_dbg(dev, "%s: wwpn0=%016llx wwpn1=%016llx\n",
+		__func__, wwpn[0], wwpn[1]);
 
-	/* Set up RRQ in AFU for master issued cmds */
+	/* Set up RRQ and SQ in AFU for master issued cmds */
 	writeq_be((u64) afu->hrrq_start, &afu->host_map->rrq_start);
 	writeq_be((u64) afu->hrrq_end, &afu->host_map->rrq_end);
 
+	if (afu_is_sq_cmd_mode(afu)) {
+		writeq_be((u64)afu->hsq_start, &afu->host_map->sq_start);
+		writeq_be((u64)afu->hsq_end, &afu->host_map->sq_end);
+	}
+
 	/* AFU configuration */
 	reg = readq_be(&afu->afu_map->global.regs.afu_config);
 	reg |= SISL_AFUCONF_AR_ALL|SISL_AFUCONF_ENDIAN;
@@ -1443,7 +1509,6 @@ static int init_global(struct cxlflash_cfg *cfg)
 		  &afu->ctrl_map->ctx_cap);
 	/* Initialize heartbeat */
 	afu->hb = readq_be(&afu->afu_map->global.regs.afu_hb);
-
 out:
 	return rc;
 }
@@ -1455,6 +1520,7 @@ out:
 static int start_afu(struct cxlflash_cfg *cfg)
 {
 	struct afu *afu = cfg->afu;
+	struct device *dev = &cfg->dev->dev;
 	int rc = 0;
 
 	init_pcr(cfg);
@@ -1468,9 +1534,20 @@ static int start_afu(struct cxlflash_cfg *cfg)
 	afu->hrrq_curr = afu->hrrq_start;
 	afu->toggle = 1;
 
+	/* Initialize SQ */
+	if (afu_is_sq_cmd_mode(afu)) {
+		memset(&afu->sq, 0, sizeof(afu->sq));
+		afu->hsq_start = &afu->sq[0];
+		afu->hsq_end = &afu->sq[NUM_SQ_ENTRY - 1];
+		afu->hsq_curr = afu->hsq_start;
+
+		spin_lock_init(&afu->hsq_slock);
+		atomic_set(&afu->hsq_credits, NUM_SQ_ENTRY - 1);
+	}
+
 	rc = init_global(cfg);
 
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1490,7 +1567,7 @@ static enum undo_level init_intr(struct cxlflash_cfg *cfg,
 
 	rc = cxl_allocate_afu_irqs(ctx, 3);
 	if (unlikely(rc)) {
-		dev_err(dev, "%s: call to allocate_afu_irqs failed rc=%d!\n",
+		dev_err(dev, "%s: allocate_afu_irqs failed rc=%d\n",
 			__func__, rc);
 		level = UNDO_NOOP;
 		goto out;
@@ -1499,8 +1576,7 @@ static enum undo_level init_intr(struct cxlflash_cfg *cfg,
 	rc = cxl_map_afu_irq(ctx, 1, cxlflash_sync_err_irq, afu,
 			     "SISL_MSI_SYNC_ERROR");
 	if (unlikely(rc <= 0)) {
-		dev_err(dev, "%s: IRQ 1 (SISL_MSI_SYNC_ERROR) map failed!\n",
-			__func__);
+		dev_err(dev, "%s: SISL_MSI_SYNC_ERROR map failed\n", __func__);
 		level = FREE_IRQ;
 		goto out;
 	}
@@ -1508,8 +1584,7 @@ static enum undo_level init_intr(struct cxlflash_cfg *cfg,
 	rc = cxl_map_afu_irq(ctx, 2, cxlflash_rrq_irq, afu,
 			     "SISL_MSI_RRQ_UPDATED");
 	if (unlikely(rc <= 0)) {
-		dev_err(dev, "%s: IRQ 2 (SISL_MSI_RRQ_UPDATED) map failed!\n",
-			__func__);
+		dev_err(dev, "%s: SISL_MSI_RRQ_UPDATED map failed\n", __func__);
 		level = UNMAP_ONE;
 		goto out;
 	}
@@ -1517,8 +1592,7 @@ static enum undo_level init_intr(struct cxlflash_cfg *cfg,
 	rc = cxl_map_afu_irq(ctx, 3, cxlflash_async_err_irq, afu,
 			     "SISL_MSI_ASYNC_ERROR");
 	if (unlikely(rc <= 0)) {
-		dev_err(dev, "%s: IRQ 3 (SISL_MSI_ASYNC_ERROR) map failed!\n",
-			__func__);
+		dev_err(dev, "%s: SISL_MSI_ASYNC_ERROR map failed\n", __func__);
 		level = UNMAP_TWO;
 		goto out;
 	}
@@ -1552,15 +1626,13 @@ static int init_mc(struct cxlflash_cfg *cfg)
 	/* During initialization reset the AFU to start from a clean slate */
 	rc = cxl_afu_reset(cfg->mcctx);
 	if (unlikely(rc)) {
-		dev_err(dev, "%s: initial AFU reset failed rc=%d\n",
-			__func__, rc);
+		dev_err(dev, "%s: AFU reset failed rc=%d\n", __func__, rc);
 		goto ret;
 	}
 
 	level = init_intr(cfg, ctx);
 	if (unlikely(level)) {
-		dev_err(dev, "%s: setting up interrupts failed rc=%d\n",
-			__func__, rc);
+		dev_err(dev, "%s: interrupt init failed rc=%d\n", __func__, rc);
 		goto out;
 	}
 
@@ -1575,7 +1647,7 @@ static int init_mc(struct cxlflash_cfg *cfg)
 		goto out;
 	}
 ret:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 out:
 	term_intr(cfg, level);
@@ -1602,7 +1674,7 @@ static int init_afu(struct cxlflash_cfg *cfg)
 
 	rc = init_mc(cfg);
 	if (rc) {
-		dev_err(dev, "%s: call to init_mc failed, rc=%d!\n",
+		dev_err(dev, "%s: init_mc failed rc=%d\n",
 			__func__, rc);
 		goto out;
 	}
@@ -1610,11 +1682,10 @@ static int init_afu(struct cxlflash_cfg *cfg)
 	/* Map the entire MMIO space of the AFU */
 	afu->afu_map = cxl_psa_map(cfg->mcctx);
 	if (!afu->afu_map) {
-		dev_err(dev, "%s: call to cxl_psa_map failed!\n", __func__);
+		dev_err(dev, "%s: cxl_psa_map failed\n", __func__);
 		rc = -ENOMEM;
 		goto err1;
 	}
-	kref_init(&afu->mapcount);
 
 	/* No byte reverse on reading afu_version or string will be backwards */
 	reg = readq(&afu->afu_map->global.regs.afu_version);
@@ -1622,24 +1693,28 @@ static int init_afu(struct cxlflash_cfg *cfg)
 	afu->interface_version =
 	    readq_be(&afu->afu_map->global.regs.interface_version);
 	if ((afu->interface_version + 1) == 0) {
-		pr_err("Back level AFU, please upgrade. AFU version %s "
-		       "interface version 0x%llx\n", afu->version,
+		dev_err(dev, "Back level AFU, please upgrade. AFU version %s "
+			"interface version %016llx\n", afu->version,
 		       afu->interface_version);
 		rc = -EINVAL;
-		goto err2;
+		goto err1;
 	}
 
-	afu->send_cmd = send_cmd_ioarrin;
-	afu->context_reset = context_reset_ioarrin;
+	if (afu_is_sq_cmd_mode(afu)) {
+		afu->send_cmd = send_cmd_sq;
+		afu->context_reset = context_reset_sq;
+	} else {
+		afu->send_cmd = send_cmd_ioarrin;
+		afu->context_reset = context_reset_ioarrin;
+	}
 
-	pr_debug("%s: afu version %s, interface version 0x%llX\n", __func__,
-		 afu->version, afu->interface_version);
+	dev_dbg(dev, "%s: afu_ver=%s interface_ver=%016llx\n", __func__,
+		afu->version, afu->interface_version);
 
 	rc = start_afu(cfg);
 	if (rc) {
-		dev_err(dev, "%s: call to start_afu failed, rc=%d!\n",
-			__func__, rc);
-		goto err2;
+		dev_err(dev, "%s: start_afu failed, rc=%d\n", __func__, rc);
+		goto err1;
 	}
 
 	afu_err_intr_init(cfg->afu);
@@ -1649,11 +1724,9 @@ static int init_afu(struct cxlflash_cfg *cfg)
 	/* Restore the LUN mappings */
 	cxlflash_restore_luntable(cfg);
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 
-err2:
-	kref_put(&afu->mapcount, afu_unmap);
 err1:
 	term_intr(cfg, UNMAP_THREE);
 	term_mc(cfg);
@@ -1693,7 +1766,8 @@ int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t ctx_hndl_u,
 	static DEFINE_MUTEX(sync_active);
 
 	if (cfg->state != STATE_NORMAL) {
-		pr_debug("%s: Sync not required! (%u)\n", __func__, cfg->state);
+		dev_dbg(dev, "%s: Sync not required state=%u\n",
+			__func__, cfg->state);
 		return 0;
 	}
 
@@ -1710,7 +1784,7 @@ int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t ctx_hndl_u,
 	init_completion(&cmd->cevent);
 	cmd->parent = afu;
 
-	pr_debug("%s: afu=%p cmd=%p %d\n", __func__, afu, cmd, ctx_hndl_u);
+	dev_dbg(dev, "%s: afu=%p cmd=%p %d\n", __func__, afu, cmd, ctx_hndl_u);
 
 	cmd->rcb.req_flags = SISL_REQ_FLAGS_AFU_CMD;
 	cmd->rcb.ctx_id = afu->ctx_hndl;
@@ -1735,7 +1809,7 @@ out:
 	atomic_dec(&afu->cmds_active);
 	mutex_unlock(&sync_active);
 	kfree(buf);
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1747,16 +1821,17 @@ out:
  */
 static int afu_reset(struct cxlflash_cfg *cfg)
 {
+	struct device *dev = &cfg->dev->dev;
 	int rc = 0;
+
 	/* Stop the context before the reset. Since the context is
 	 * no longer available restart it after the reset is complete
 	 */
-
 	term_afu(cfg);
 
 	rc = init_afu(cfg);
 
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1785,18 +1860,18 @@ static int cxlflash_eh_device_reset_handler(struct scsi_cmnd *scp)
 {
 	int rc = SUCCESS;
 	struct Scsi_Host *host = scp->device->host;
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(host);
+	struct device *dev = &cfg->dev->dev;
 	struct afu *afu = cfg->afu;
 	int rcr = 0;
 
-	pr_debug("%s: (scp=%p) %d/%d/%d/%llu "
-		 "cdb=(%08X-%08X-%08X-%08X)\n", __func__, scp,
-		 host->host_no, scp->device->channel,
-		 scp->device->id, scp->device->lun,
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
+	dev_dbg(dev, "%s: (scp=%p) %d/%d/%d/%llu "
+		"cdb=(%08x-%08x-%08x-%08x)\n", __func__, scp, host->host_no,
+		scp->device->channel, scp->device->id, scp->device->lun,
+		get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
 
 retry:
 	switch (cfg->state) {
@@ -1813,7 +1888,7 @@ retry:
 		break;
 	}
 
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1835,16 +1910,16 @@ static int cxlflash_eh_host_reset_handler(struct scsi_cmnd *scp)
 	int rc = SUCCESS;
 	int rcr = 0;
 	struct Scsi_Host *host = scp->device->host;
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(host);
+	struct device *dev = &cfg->dev->dev;
 
-	pr_debug("%s: (scp=%p) %d/%d/%d/%llu "
-		 "cdb=(%08X-%08X-%08X-%08X)\n", __func__, scp,
-		 host->host_no, scp->device->channel,
-		 scp->device->id, scp->device->lun,
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
+	dev_dbg(dev, "%s: (scp=%p) %d/%d/%d/%llu "
+		"cdb=(%08x-%08x-%08x-%08x)\n", __func__, scp, host->host_no,
+		scp->device->channel, scp->device->id, scp->device->lun,
+		get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
 
 	switch (cfg->state) {
 	case STATE_NORMAL:
@@ -1870,7 +1945,7 @@ static int cxlflash_eh_host_reset_handler(struct scsi_cmnd *scp)
 		break;
 	}
 
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1936,8 +2011,7 @@ static ssize_t port0_show(struct device *dev,
 			  struct device_attribute *attr,
 			  char *buf)
 {
-	struct Scsi_Host *shost = class_to_shost(dev);
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(class_to_shost(dev));
 	struct afu *afu = cfg->afu;
 
 	return cxlflash_show_port_status(0, afu, buf);
@@ -1955,8 +2029,7 @@ static ssize_t port1_show(struct device *dev,
 			  struct device_attribute *attr,
 			  char *buf)
 {
-	struct Scsi_Host *shost = class_to_shost(dev);
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(class_to_shost(dev));
 	struct afu *afu = cfg->afu;
 
 	return cxlflash_show_port_status(1, afu, buf);
@@ -1973,8 +2046,7 @@ static ssize_t port1_show(struct device *dev,
 static ssize_t lun_mode_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
-	struct Scsi_Host *shost = class_to_shost(dev);
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(class_to_shost(dev));
 	struct afu *afu = cfg->afu;
 
 	return scnprintf(buf, PAGE_SIZE, "%u\n", afu->internal_lun);
@@ -2007,7 +2079,7 @@ static ssize_t lun_mode_store(struct device *dev,
 			      const char *buf, size_t count)
 {
 	struct Scsi_Host *shost = class_to_shost(dev);
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(shost);
 	struct afu *afu = cfg->afu;
 	int rc;
 	u32 lun_mode;
@@ -2069,7 +2141,7 @@ static ssize_t cxlflash_show_port_lun_table(u32 port,
 
 	for (i = 0; i < CXLFLASH_NUM_VLUNS; i++)
 		bytes += scnprintf(buf + bytes, PAGE_SIZE - bytes,
-				   "%03d: %016llX\n", i, readq_be(&fc_port[i]));
+				   "%03d: %016llx\n", i, readq_be(&fc_port[i]));
 	return bytes;
 }
 
@@ -2085,8 +2157,7 @@ static ssize_t port0_lun_table_show(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
 {
-	struct Scsi_Host *shost = class_to_shost(dev);
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(class_to_shost(dev));
 	struct afu *afu = cfg->afu;
 
 	return cxlflash_show_port_lun_table(0, afu, buf);
@@ -2104,8 +2175,7 @@ static ssize_t port1_lun_table_show(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
 {
-	struct Scsi_Host *shost = class_to_shost(dev);
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(class_to_shost(dev));
 	struct afu *afu = cfg->afu;
 
 	return cxlflash_show_port_lun_table(1, afu, buf);
@@ -2250,7 +2320,6 @@ static void cxlflash_worker_thread(struct work_struct *work)
 
 	if (atomic_dec_if_positive(&cfg->scan_host_needed) >= 0)
 		scsi_scan_host(cfg->host);
-	kref_put(&afu->mapcount, afu_unmap);
 }
 
 /**
@@ -2265,6 +2334,7 @@ static int cxlflash_probe(struct pci_dev *pdev,
 {
 	struct Scsi_Host *host;
 	struct cxlflash_cfg *cfg = NULL;
+	struct device *dev = &pdev->dev;
 	struct dev_dependent_vals *ddv;
 	int rc = 0;
 
@@ -2276,8 +2346,7 @@ static int cxlflash_probe(struct pci_dev *pdev,
 
 	host = scsi_host_alloc(&driver_template, sizeof(struct cxlflash_cfg));
 	if (!host) {
-		dev_err(&pdev->dev, "%s: call to scsi_host_alloc failed!\n",
-			__func__);
+		dev_err(dev, "%s: scsi_host_alloc failed\n", __func__);
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -2288,12 +2357,11 @@ static int cxlflash_probe(struct pci_dev *pdev,
 	host->unique_id = host->host_no;
 	host->max_cmd_len = CXLFLASH_MAX_CDB_LEN;
 
-	cfg = (struct cxlflash_cfg *)host->hostdata;
+	cfg = shost_priv(host);
 	cfg->host = host;
 	rc = alloc_mem(cfg);
 	if (rc) {
-		dev_err(&pdev->dev, "%s: call to alloc_mem failed!\n",
-			__func__);
+		dev_err(dev, "%s: alloc_mem failed\n", __func__);
 		rc = -ENOMEM;
 		scsi_host_put(cfg->host);
 		goto out;
@@ -2334,30 +2402,27 @@ static int cxlflash_probe(struct pci_dev *pdev,
 
 	rc = init_pci(cfg);
 	if (rc) {
-		dev_err(&pdev->dev, "%s: call to init_pci "
-			"failed rc=%d!\n", __func__, rc);
+		dev_err(dev, "%s: init_pci failed rc=%d\n", __func__, rc);
 		goto out_remove;
 	}
 	cfg->init_state = INIT_STATE_PCI;
 
 	rc = init_afu(cfg);
 	if (rc) {
-		dev_err(&pdev->dev, "%s: call to init_afu "
-			"failed rc=%d!\n", __func__, rc);
+		dev_err(dev, "%s: init_afu failed rc=%d\n", __func__, rc);
 		goto out_remove;
 	}
 	cfg->init_state = INIT_STATE_AFU;
 
 	rc = init_scsi(cfg);
 	if (rc) {
-		dev_err(&pdev->dev, "%s: call to init_scsi "
-			"failed rc=%d!\n", __func__, rc);
+		dev_err(dev, "%s: init_scsi failed rc=%d\n", __func__, rc);
 		goto out_remove;
 	}
 	cfg->init_state = INIT_STATE_SCSI;
 
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 
 out_remove:
@@ -2395,7 +2460,7 @@ static pci_ers_result_t cxlflash_pci_error_detected(struct pci_dev *pdev,
 		drain_ioctls(cfg);
 		rc = cxlflash_mark_contexts_error(cfg);
 		if (unlikely(rc))
-			dev_err(dev, "%s: Failed to mark user contexts!(%d)\n",
+			dev_err(dev, "%s: Failed to mark user contexts rc=%d\n",
 				__func__, rc);
 		term_afu(cfg);
 		return PCI_ERS_RESULT_NEED_RESET;
@@ -2429,7 +2494,7 @@ static pci_ers_result_t cxlflash_pci_slot_reset(struct pci_dev *pdev)
 
 	rc = init_afu(cfg);
 	if (unlikely(rc)) {
-		dev_err(dev, "%s: EEH recovery failed! (%d)\n", __func__, rc);
+		dev_err(dev, "%s: EEH recovery failed rc=%d\n", __func__, rc);
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
@@ -2477,8 +2542,6 @@ static struct pci_driver cxlflash_driver = {
  */
 static int __init init_cxlflash(void)
 {
-	pr_info("%s: %s\n", __func__, CXLFLASH_ADAPTER_NAME);
-
 	cxlflash_list_init();
 
 	return pci_register_driver(&cxlflash_driver);
diff --git a/drivers/scsi/cxlflash/sislite.h b/drivers/scsi/cxlflash/sislite.h
index 1a2d09c148b3..a6e48a893fef 100644
--- a/drivers/scsi/cxlflash/sislite.h
+++ b/drivers/scsi/cxlflash/sislite.h
@@ -72,7 +72,10 @@ struct sisl_ioarcb {
 	u16 timeout;		/* in units specified by req_flags */
 	u32 rsvd1;
 	u8 cdb[16];		/* must be in big endian */
-	u64 reserved;		/* Reserved area */
+	union {
+		u64 reserved;			/* Reserved for IOARRIN mode */
+		struct sisl_ioasa *ioasa;	/* IOASA EA for SQ Mode */
+	};
 } __packed;
 
 struct sisl_rc {
@@ -260,6 +263,11 @@ struct sisl_host_map {
 	__be64 cmd_room;
 	__be64 ctx_ctrl;	/* least significant byte or b56:63 is LISN# */
 	__be64 mbox_w;		/* restricted use */
+	__be64 sq_start;	/* Submission Queue (R/W): write sequence and */
+	__be64 sq_end;		/* inclusion semantics are the same as RRQ    */
+	__be64 sq_head;		/* Submission Queue Head (R): for debugging   */
+	__be64 sq_tail;		/* Submission Queue TAIL (R/W): next IOARCB   */
+	__be64 sq_ctx_reset;	/* Submission Queue Context Reset (R/W)	      */
 };
 
 /* per context provisioning & control MMIO */
@@ -348,6 +356,15 @@ struct sisl_global_regs {
 	__be64 rsvd[0xf8];
 	__le64 afu_version;
 	__be64 interface_version;
+#define SISL_INTVER_CAP_SHIFT			16
+#define SISL_INTVER_MAJ_SHIFT			8
+#define SISL_INTVER_CAP_MASK			0xFFFFFFFF00000000ULL
+#define SISL_INTVER_MAJ_MASK			0x00000000FFFF0000ULL
+#define SISL_INTVER_MIN_MASK			0x000000000000FFFFULL
+#define SISL_INTVER_CAP_IOARRIN_CMD_MODE	0x800000000000ULL
+#define SISL_INTVER_CAP_SQ_CMD_MODE		0x400000000000ULL
+#define SISL_INTVER_CAP_RESERVED_CMD_MODE_A	0x200000000000ULL
+#define SISL_INTVER_CAP_RESERVED_CMD_MODE_B	0x100000000000ULL
 };
 
 #define CXLFLASH_NUM_FC_PORTS   2
diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c
index 9636970d9611..90869cee2b20 100644
--- a/drivers/scsi/cxlflash/superpipe.c
+++ b/drivers/scsi/cxlflash/superpipe.c
@@ -212,7 +212,7 @@ struct ctx_info *get_context(struct cxlflash_cfg *cfg, u64 rctxid,
 	}
 
 out:
-	dev_dbg(dev, "%s: rctxid=%016llX ctxinfo=%p ctxpid=%u pid=%u "
+	dev_dbg(dev, "%s: rctxid=%016llx ctxinfo=%p ctxpid=%u pid=%u "
 		"ctx_ctrl=%u\n", __func__, rctxid, ctxi, ctxpid, pid,
 		ctx_ctrl);
 
@@ -260,7 +260,7 @@ static int afu_attach(struct cxlflash_cfg *cfg, struct ctx_info *ctxi)
 	writeq_be(val, &ctrl_map->ctx_cap);
 	val = readq_be(&ctrl_map->ctx_cap);
 	if (val != (SISL_CTX_CAP_READ_CMD | SISL_CTX_CAP_WRITE_CMD)) {
-		dev_err(dev, "%s: ctx may be closed val=%016llX\n",
+		dev_err(dev, "%s: ctx may be closed val=%016llx\n",
 			__func__, val);
 		rc = -EAGAIN;
 		goto out;
@@ -302,7 +302,7 @@ out:
  */
 static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct glun_info *gli = lli->parent;
 	u8 *cmd_buf = NULL;
@@ -326,7 +326,7 @@ retry:
 	scsi_cmd[1] = SAI_READ_CAPACITY_16;	/* service action */
 	put_unaligned_be32(CMD_BUFSIZE, &scsi_cmd[10]);
 
-	dev_dbg(dev, "%s: %ssending cmd(0x%x)\n", __func__,
+	dev_dbg(dev, "%s: %ssending cmd(%02x)\n", __func__,
 		retry_cnt ? "re" : "", scsi_cmd[0]);
 
 	/* Drop the ioctl read semahpore across lengthy call */
@@ -336,7 +336,7 @@ retry:
 	down_read(&cfg->ioctl_rwsem);
 	rc = check_state(cfg);
 	if (rc) {
-		dev_err(dev, "%s: Failed state! result=0x08%X\n",
+		dev_err(dev, "%s: Failed state result=%08x\n",
 			__func__, result);
 		rc = -ENODEV;
 		goto out;
@@ -378,7 +378,7 @@ retry:
 	}
 
 	if (result) {
-		dev_err(dev, "%s: command failed, result=0x%x\n",
+		dev_err(dev, "%s: command failed, result=%08x\n",
 			__func__, result);
 		rc = -EIO;
 		goto out;
@@ -415,29 +415,32 @@ out:
 struct sisl_rht_entry *get_rhte(struct ctx_info *ctxi, res_hndl_t rhndl,
 				struct llun_info *lli)
 {
+	struct cxlflash_cfg *cfg = ctxi->cfg;
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_rht_entry *rhte = NULL;
 
 	if (unlikely(!ctxi->rht_start)) {
-		pr_debug("%s: Context does not have allocated RHT!\n",
+		dev_dbg(dev, "%s: Context does not have allocated RHT\n",
 			 __func__);
 		goto out;
 	}
 
 	if (unlikely(rhndl >= MAX_RHT_PER_CONTEXT)) {
-		pr_debug("%s: Bad resource handle! (%d)\n", __func__, rhndl);
+		dev_dbg(dev, "%s: Bad resource handle rhndl=%d\n",
+			__func__, rhndl);
 		goto out;
 	}
 
 	if (unlikely(ctxi->rht_lun[rhndl] != lli)) {
-		pr_debug("%s: Bad resource handle LUN! (%d)\n",
-			 __func__, rhndl);
+		dev_dbg(dev, "%s: Bad resource handle LUN rhndl=%d\n",
+			__func__, rhndl);
 		goto out;
 	}
 
 	rhte = &ctxi->rht_start[rhndl];
 	if (unlikely(rhte->nmask == 0)) {
-		pr_debug("%s: Unopened resource handle! (%d)\n",
-			 __func__, rhndl);
+		dev_dbg(dev, "%s: Unopened resource handle rhndl=%d\n",
+			__func__, rhndl);
 		rhte = NULL;
 		goto out;
 	}
@@ -456,6 +459,8 @@ out:
 struct sisl_rht_entry *rhte_checkout(struct ctx_info *ctxi,
 				     struct llun_info *lli)
 {
+	struct cxlflash_cfg *cfg = ctxi->cfg;
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_rht_entry *rhte = NULL;
 	int i;
 
@@ -470,7 +475,7 @@ struct sisl_rht_entry *rhte_checkout(struct ctx_info *ctxi,
 	if (likely(rhte))
 		ctxi->rht_lun[i] = lli;
 
-	pr_debug("%s: returning rhte=%p (%d)\n", __func__, rhte, i);
+	dev_dbg(dev, "%s: returning rhte=%p index=%d\n", __func__, rhte, i);
 	return rhte;
 }
 
@@ -547,7 +552,7 @@ int cxlflash_lun_attach(struct glun_info *gli, enum lun_mode mode, bool locked)
 	if (gli->mode == MODE_NONE)
 		gli->mode = mode;
 	else if (gli->mode != mode) {
-		pr_debug("%s: LUN operating in mode %d, requested mode %d\n",
+		pr_debug("%s: gli_mode=%d requested_mode=%d\n",
 			 __func__, gli->mode, mode);
 		rc = -EINVAL;
 		goto out;
@@ -605,7 +610,7 @@ int _cxlflash_disk_release(struct scsi_device *sdev,
 			   struct ctx_info *ctxi,
 			   struct dk_cxlflash_release *release)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
@@ -622,13 +627,13 @@ int _cxlflash_disk_release(struct scsi_device *sdev,
 	struct sisl_rht_entry *rhte;
 	struct sisl_rht_entry_f1 *rhte_f1;
 
-	dev_dbg(dev, "%s: ctxid=%llu rhndl=0x%llx gli->mode=%u gli->users=%u\n",
+	dev_dbg(dev, "%s: ctxid=%llu rhndl=%llu gli->mode=%u gli->users=%u\n",
 		__func__, ctxid, release->rsrc_handle, gli->mode, gli->users);
 
 	if (!ctxi) {
 		ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
 		if (unlikely(!ctxi)) {
-			dev_dbg(dev, "%s: Bad context! (%llu)\n",
+			dev_dbg(dev, "%s: Bad context ctxid=%llu\n",
 				__func__, ctxid);
 			rc = -EINVAL;
 			goto out;
@@ -639,7 +644,7 @@ int _cxlflash_disk_release(struct scsi_device *sdev,
 
 	rhte = get_rhte(ctxi, rhndl, lli);
 	if (unlikely(!rhte)) {
-		dev_dbg(dev, "%s: Bad resource handle! (%d)\n",
+		dev_dbg(dev, "%s: Bad resource handle rhndl=%d\n",
 			__func__, rhndl);
 		rc = -EINVAL;
 		goto out;
@@ -758,13 +763,13 @@ static struct ctx_info *create_context(struct cxlflash_cfg *cfg)
 	lli = kzalloc((MAX_RHT_PER_CONTEXT * sizeof(*lli)), GFP_KERNEL);
 	ws = kzalloc((MAX_RHT_PER_CONTEXT * sizeof(*ws)), GFP_KERNEL);
 	if (unlikely(!ctxi || !lli || !ws)) {
-		dev_err(dev, "%s: Unable to allocate context!\n", __func__);
+		dev_err(dev, "%s: Unable to allocate context\n", __func__);
 		goto err;
 	}
 
 	rhte = (struct sisl_rht_entry *)get_zeroed_page(GFP_KERNEL);
 	if (unlikely(!rhte)) {
-		dev_err(dev, "%s: Unable to allocate RHT!\n", __func__);
+		dev_err(dev, "%s: Unable to allocate RHT\n", __func__);
 		goto err;
 	}
 
@@ -858,7 +863,7 @@ static int _cxlflash_disk_detach(struct scsi_device *sdev,
 				 struct ctx_info *ctxi,
 				 struct dk_cxlflash_detach *detach)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct lun_access *lun_access, *t;
@@ -875,7 +880,7 @@ static int _cxlflash_disk_detach(struct scsi_device *sdev,
 	if (!ctxi) {
 		ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
 		if (unlikely(!ctxi)) {
-			dev_dbg(dev, "%s: Bad context! (%llu)\n",
+			dev_dbg(dev, "%s: Bad context ctxid=%llu\n",
 				__func__, ctxid);
 			rc = -EINVAL;
 			goto out;
@@ -964,7 +969,7 @@ static int cxlflash_cxl_release(struct inode *inode, struct file *file)
 
 	ctxid = cxl_process_element(ctx);
 	if (unlikely(ctxid < 0)) {
-		dev_err(dev, "%s: Context %p was closed! (%d)\n",
+		dev_err(dev, "%s: Context %p was closed ctxid=%d\n",
 			__func__, ctx, ctxid);
 		goto out;
 	}
@@ -973,18 +978,18 @@ static int cxlflash_cxl_release(struct inode *inode, struct file *file)
 	if (unlikely(!ctxi)) {
 		ctxi = get_context(cfg, ctxid, file, ctrl | CTX_CTRL_CLONE);
 		if (!ctxi) {
-			dev_dbg(dev, "%s: Context %d already free!\n",
+			dev_dbg(dev, "%s: ctxid=%d already free\n",
 				__func__, ctxid);
 			goto out_release;
 		}
 
-		dev_dbg(dev, "%s: Another process owns context %d!\n",
+		dev_dbg(dev, "%s: Another process owns ctxid=%d\n",
 			__func__, ctxid);
 		put_context(ctxi);
 		goto out;
 	}
 
-	dev_dbg(dev, "%s: close for context %d\n", __func__, ctxid);
+	dev_dbg(dev, "%s: close for ctxid=%d\n", __func__, ctxid);
 
 	detach.context_id = ctxi->ctxid;
 	list_for_each_entry_safe(lun_access, t, &ctxi->luns, list)
@@ -1011,17 +1016,20 @@ static void unmap_context(struct ctx_info *ctxi)
 
 /**
  * get_err_page() - obtains and allocates the error notification page
+ * @cfg:	Internal structure associated with the host.
  *
  * Return: error notification page on success, NULL on failure
  */
-static struct page *get_err_page(void)
+static struct page *get_err_page(struct cxlflash_cfg *cfg)
 {
 	struct page *err_page = global.err_page;
+	struct device *dev = &cfg->dev->dev;
 
 	if (unlikely(!err_page)) {
 		err_page = alloc_page(GFP_KERNEL);
 		if (unlikely(!err_page)) {
-			pr_err("%s: Unable to allocate err_page!\n", __func__);
+			dev_err(dev, "%s: Unable to allocate err_page\n",
+				__func__);
 			goto out;
 		}
 
@@ -1039,7 +1047,7 @@ static struct page *get_err_page(void)
 	}
 
 out:
-	pr_debug("%s: returning err_page=%p\n", __func__, err_page);
+	dev_dbg(dev, "%s: returning err_page=%p\n", __func__, err_page);
 	return err_page;
 }
 
@@ -1074,14 +1082,14 @@ static int cxlflash_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	ctxid = cxl_process_element(ctx);
 	if (unlikely(ctxid < 0)) {
-		dev_err(dev, "%s: Context %p was closed! (%d)\n",
+		dev_err(dev, "%s: Context %p was closed ctxid=%d\n",
 			__func__, ctx, ctxid);
 		goto err;
 	}
 
 	ctxi = get_context(cfg, ctxid, file, ctrl);
 	if (unlikely(!ctxi)) {
-		dev_dbg(dev, "%s: Bad context! (%d)\n", __func__, ctxid);
+		dev_dbg(dev, "%s: Bad context ctxid=%d\n", __func__, ctxid);
 		goto err;
 	}
 
@@ -1091,13 +1099,12 @@ static int cxlflash_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 		rc = ctxi->cxl_mmap_vmops->fault(vma, vmf);
 	} else {
-		dev_dbg(dev, "%s: err recovery active, use err_page!\n",
+		dev_dbg(dev, "%s: err recovery active, use err_page\n",
 			__func__);
 
-		err_page = get_err_page();
+		err_page = get_err_page(cfg);
 		if (unlikely(!err_page)) {
-			dev_err(dev, "%s: Could not obtain error page!\n",
-				__func__);
+			dev_err(dev, "%s: Could not get err_page\n", __func__);
 			rc = VM_FAULT_RETRY;
 			goto out;
 		}
@@ -1147,7 +1154,7 @@ static int cxlflash_cxl_mmap(struct file *file, struct vm_area_struct *vma)
 
 	ctxid = cxl_process_element(ctx);
 	if (unlikely(ctxid < 0)) {
-		dev_err(dev, "%s: Context %p was closed! (%d)\n",
+		dev_err(dev, "%s: Context %p was closed ctxid=%d\n",
 			__func__, ctx, ctxid);
 		rc = -EIO;
 		goto out;
@@ -1155,7 +1162,7 @@ static int cxlflash_cxl_mmap(struct file *file, struct vm_area_struct *vma)
 
 	ctxi = get_context(cfg, ctxid, file, ctrl);
 	if (unlikely(!ctxi)) {
-		dev_dbg(dev, "%s: Bad context! (%d)\n", __func__, ctxid);
+		dev_dbg(dev, "%s: Bad context ctxid=%d\n", __func__, ctxid);
 		rc = -EIO;
 		goto out;
 	}
@@ -1251,7 +1258,7 @@ retry:
 			break;
 		goto retry;
 	case STATE_FAILTERM:
-		dev_dbg(dev, "%s: Failed/Terminating!\n", __func__);
+		dev_dbg(dev, "%s: Failed/Terminating\n", __func__);
 		rc = -ENODEV;
 		break;
 	default:
@@ -1276,7 +1283,7 @@ retry:
 static int cxlflash_disk_attach(struct scsi_device *sdev,
 				struct dk_cxlflash_attach *attach)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct afu *afu = cfg->afu;
 	struct llun_info *lli = sdev->hostdata;
@@ -1287,6 +1294,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 	int rc = 0;
 	u32 perms;
 	int ctxid = -1;
+	u64 flags = 0UL;
 	u64 rctxid = 0UL;
 	struct file *file = NULL;
 
@@ -1302,24 +1310,24 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 	}
 
 	if (gli->max_lba == 0) {
-		dev_dbg(dev, "%s: No capacity info for this LUN (%016llX)\n",
+		dev_dbg(dev, "%s: No capacity info for LUN=%016llx\n",
 			__func__, lli->lun_id[sdev->channel]);
 		rc = read_cap16(sdev, lli);
 		if (rc) {
-			dev_err(dev, "%s: Invalid device! (%d)\n",
+			dev_err(dev, "%s: Invalid device rc=%d\n",
 				__func__, rc);
 			rc = -ENODEV;
 			goto out;
 		}
-		dev_dbg(dev, "%s: LBA = %016llX\n", __func__, gli->max_lba);
-		dev_dbg(dev, "%s: BLK_LEN = %08X\n", __func__, gli->blk_len);
+		dev_dbg(dev, "%s: LBA = %016llx\n", __func__, gli->max_lba);
+		dev_dbg(dev, "%s: BLK_LEN = %08x\n", __func__, gli->blk_len);
 	}
 
 	if (attach->hdr.flags & DK_CXLFLASH_ATTACH_REUSE_CONTEXT) {
 		rctxid = attach->context_id;
 		ctxi = get_context(cfg, rctxid, NULL, 0);
 		if (!ctxi) {
-			dev_dbg(dev, "%s: Bad context! (%016llX)\n",
+			dev_dbg(dev, "%s: Bad context rctxid=%016llx\n",
 				__func__, rctxid);
 			rc = -EINVAL;
 			goto out;
@@ -1327,7 +1335,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 
 		list_for_each_entry(lun_access, &ctxi->luns, list)
 			if (lun_access->lli == lli) {
-				dev_dbg(dev, "%s: Already attached!\n",
+				dev_dbg(dev, "%s: Already attached\n",
 					__func__);
 				rc = -EINVAL;
 				goto out;
@@ -1336,13 +1344,13 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 
 	rc = scsi_device_get(sdev);
 	if (unlikely(rc)) {
-		dev_err(dev, "%s: Unable to get sdev reference!\n", __func__);
+		dev_err(dev, "%s: Unable to get sdev reference\n", __func__);
 		goto out;
 	}
 
 	lun_access = kzalloc(sizeof(*lun_access), GFP_KERNEL);
 	if (unlikely(!lun_access)) {
-		dev_err(dev, "%s: Unable to allocate lun_access!\n", __func__);
+		dev_err(dev, "%s: Unable to allocate lun_access\n", __func__);
 		rc = -ENOMEM;
 		goto err;
 	}
@@ -1352,7 +1360,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 
 	/* Non-NULL context indicates reuse (another context reference) */
 	if (ctxi) {
-		dev_dbg(dev, "%s: Reusing context for LUN! (%016llX)\n",
+		dev_dbg(dev, "%s: Reusing context for LUN rctxid=%016llx\n",
 			__func__, rctxid);
 		kref_get(&ctxi->kref);
 		list_add(&lun_access->list, &ctxi->luns);
@@ -1361,7 +1369,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 
 	ctxi = create_context(cfg);
 	if (unlikely(!ctxi)) {
-		dev_err(dev, "%s: Failed to create context! (%d)\n",
+		dev_err(dev, "%s: Failed to create context ctxid=%d\n",
 			__func__, ctxid);
 		goto err;
 	}
@@ -1387,7 +1395,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 
 	ctxid = cxl_process_element(ctx);
 	if (unlikely((ctxid >= MAX_CONTEXT) || (ctxid < 0))) {
-		dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
+		dev_err(dev, "%s: ctxid=%d invalid\n", __func__, ctxid);
 		rc = -EPERM;
 		goto err;
 	}
@@ -1426,10 +1434,11 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 
 out_attach:
 	if (fd != -1)
-		attach->hdr.return_flags = DK_CXLFLASH_APP_CLOSE_ADAP_FD;
-	else
-		attach->hdr.return_flags = 0;
+		flags |= DK_CXLFLASH_APP_CLOSE_ADAP_FD;
+	if (afu_is_sq_cmd_mode(afu))
+		flags |= DK_CXLFLASH_CONTEXT_SQ_CMD_MODE;
 
+	attach->hdr.return_flags = flags;
 	attach->context_id = ctxi->ctxid;
 	attach->block_size = gli->blk_len;
 	attach->mmio_size = sizeof(afu->afu_map->hosts[0].harea);
@@ -1520,7 +1529,7 @@ static int recover_context(struct cxlflash_cfg *cfg,
 
 	ctxid = cxl_process_element(ctx);
 	if (unlikely((ctxid >= MAX_CONTEXT) || (ctxid < 0))) {
-		dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
+		dev_err(dev, "%s: ctxid=%d invalid\n", __func__, ctxid);
 		rc = -EPERM;
 		goto err2;
 	}
@@ -1611,12 +1620,13 @@ err1:
 static int cxlflash_afu_recover(struct scsi_device *sdev,
 				struct dk_cxlflash_recover_afu *recover)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct afu *afu = cfg->afu;
 	struct ctx_info *ctxi = NULL;
 	struct mutex *mutex = &cfg->ctx_recovery_mutex;
+	u64 flags;
 	u64 ctxid = DECODE_CTXID(recover->context_id),
 	    rctxid = recover->context_id;
 	long reg;
@@ -1632,19 +1642,19 @@ static int cxlflash_afu_recover(struct scsi_device *sdev,
 		goto out;
 	rc = check_state(cfg);
 	if (rc) {
-		dev_err(dev, "%s: Failed state! rc=%d\n", __func__, rc);
+		dev_err(dev, "%s: Failed state rc=%d\n", __func__, rc);
 		rc = -ENODEV;
 		goto out;
 	}
 
-	dev_dbg(dev, "%s: reason 0x%016llX rctxid=%016llX\n",
+	dev_dbg(dev, "%s: reason=%016llx rctxid=%016llx\n",
 		__func__, recover->reason, rctxid);
 
 retry:
 	/* Ensure that this process is attached to the context */
 	ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
 	if (unlikely(!ctxi)) {
-		dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
+		dev_dbg(dev, "%s: Bad context ctxid=%llu\n", __func__, ctxid);
 		rc = -EINVAL;
 		goto out;
 	}
@@ -1653,12 +1663,12 @@ retry:
 retry_recover:
 		rc = recover_context(cfg, ctxi, &new_adap_fd);
 		if (unlikely(rc)) {
-			dev_err(dev, "%s: Recovery failed for context %llu (rc=%d)\n",
+			dev_err(dev, "%s: Recovery failed ctxid=%llu rc=%d\n",
 				__func__, ctxid, rc);
 			if ((rc == -ENODEV) &&
 			    ((atomic_read(&cfg->recovery_threads) > 1) ||
 			     (lretry--))) {
-				dev_dbg(dev, "%s: Going to try again!\n",
+				dev_dbg(dev, "%s: Going to try again\n",
 					__func__);
 				mutex_unlock(mutex);
 				msleep(100);
@@ -1672,11 +1682,16 @@ retry_recover:
 		}
 
 		ctxi->err_recovery_active = false;
+
+		flags = DK_CXLFLASH_APP_CLOSE_ADAP_FD |
+			DK_CXLFLASH_RECOVER_AFU_CONTEXT_RESET;
+		if (afu_is_sq_cmd_mode(afu))
+			flags |= DK_CXLFLASH_CONTEXT_SQ_CMD_MODE;
+
+		recover->hdr.return_flags = flags;
 		recover->context_id = ctxi->ctxid;
 		recover->adap_fd = new_adap_fd;
 		recover->mmio_size = sizeof(afu->afu_map->hosts[0].harea);
-		recover->hdr.return_flags = DK_CXLFLASH_APP_CLOSE_ADAP_FD |
-			DK_CXLFLASH_RECOVER_AFU_CONTEXT_RESET;
 		goto out;
 	}
 
@@ -1699,7 +1714,7 @@ retry_recover:
 		goto retry;
 	}
 
-	dev_dbg(dev, "%s: MMIO working, no recovery required!\n", __func__);
+	dev_dbg(dev, "%s: MMIO working, no recovery required\n", __func__);
 out:
 	if (likely(ctxi))
 		put_context(ctxi);
@@ -1718,7 +1733,7 @@ out:
 static int process_sense(struct scsi_device *sdev,
 			 struct dk_cxlflash_verify *verify)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
@@ -1729,7 +1744,7 @@ static int process_sense(struct scsi_device *sdev,
 	rc = scsi_normalize_sense((const u8 *)&verify->sense_data,
 				  DK_CXLFLASH_VERIFY_SENSE_LEN, &sshdr);
 	if (!rc) {
-		dev_err(dev, "%s: Failed to normalize sense data!\n", __func__);
+		dev_err(dev, "%s: Failed to normalize sense data\n", __func__);
 		rc = -EINVAL;
 		goto out;
 	}
@@ -1785,7 +1800,7 @@ static int cxlflash_disk_verify(struct scsi_device *sdev,
 {
 	int rc = 0;
 	struct ctx_info *ctxi = NULL;
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
@@ -1795,20 +1810,20 @@ static int cxlflash_disk_verify(struct scsi_device *sdev,
 	    rctxid = verify->context_id;
 	u64 last_lba = 0;
 
-	dev_dbg(dev, "%s: ctxid=%llu rhndl=%016llX, hint=%016llX, "
-		"flags=%016llX\n", __func__, ctxid, verify->rsrc_handle,
+	dev_dbg(dev, "%s: ctxid=%llu rhndl=%016llx, hint=%016llx, "
+		"flags=%016llx\n", __func__, ctxid, verify->rsrc_handle,
 		verify->hint, verify->hdr.flags);
 
 	ctxi = get_context(cfg, rctxid, lli, 0);
 	if (unlikely(!ctxi)) {
-		dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
+		dev_dbg(dev, "%s: Bad context ctxid=%llu\n", __func__, ctxid);
 		rc = -EINVAL;
 		goto out;
 	}
 
 	rhte = get_rhte(ctxi, rhndl, lli);
 	if (unlikely(!rhte)) {
-		dev_dbg(dev, "%s: Bad resource handle! (%d)\n",
+		dev_dbg(dev, "%s: Bad resource handle rhndl=%d\n",
 			__func__, rhndl);
 		rc = -EINVAL;
 		goto out;
@@ -1855,7 +1870,7 @@ static int cxlflash_disk_verify(struct scsi_device *sdev,
 out:
 	if (likely(ctxi))
 		put_context(ctxi);
-	dev_dbg(dev, "%s: returning rc=%d llba=%llX\n",
+	dev_dbg(dev, "%s: returning rc=%d llba=%llx\n",
 		__func__, rc, verify->last_lba);
 	return rc;
 }
@@ -1907,7 +1922,7 @@ static char *decode_ioctl(int cmd)
  */
 static int cxlflash_disk_direct_open(struct scsi_device *sdev, void *arg)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct afu *afu = cfg->afu;
 	struct llun_info *lli = sdev->hostdata;
@@ -1927,25 +1942,25 @@ static int cxlflash_disk_direct_open(struct scsi_device *sdev, void *arg)
 	struct ctx_info *ctxi = NULL;
 	struct sisl_rht_entry *rhte = NULL;
 
-	pr_debug("%s: ctxid=%llu ls=0x%llx\n", __func__, ctxid, lun_size);
+	dev_dbg(dev, "%s: ctxid=%llu ls=%llu\n", __func__, ctxid, lun_size);
 
 	rc = cxlflash_lun_attach(gli, MODE_PHYSICAL, false);
 	if (unlikely(rc)) {
-		dev_dbg(dev, "%s: Failed to attach to LUN! (PHYSICAL)\n",
-			__func__);
+		dev_dbg(dev, "%s: Failed attach to LUN (PHYSICAL)\n", __func__);
 		goto out;
 	}
 
 	ctxi = get_context(cfg, rctxid, lli, 0);
 	if (unlikely(!ctxi)) {
-		dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
+		dev_dbg(dev, "%s: Bad context ctxid=%llu\n", __func__, ctxid);
 		rc = -EINVAL;
 		goto err1;
 	}
 
 	rhte = rhte_checkout(ctxi, lli);
 	if (unlikely(!rhte)) {
-		dev_dbg(dev, "%s: too many opens for this context\n", __func__);
+		dev_dbg(dev, "%s: Too many opens ctxid=%lld\n",
+			__func__, ctxid);
 		rc = -EMFILE;	/* too many opens  */
 		goto err1;
 	}
@@ -1963,7 +1978,7 @@ static int cxlflash_disk_direct_open(struct scsi_device *sdev, void *arg)
 out:
 	if (likely(ctxi))
 		put_context(ctxi);
-	dev_dbg(dev, "%s: returning handle 0x%llx rc=%d llba %lld\n",
+	dev_dbg(dev, "%s: returning handle=%llu rc=%d llba=%llu\n",
 		__func__, rsrc_handle, rc, last_lba);
 	return rc;
 
@@ -1985,7 +2000,7 @@ err1:
  */
 static int ioctl_common(struct scsi_device *sdev, int cmd)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	int rc = 0;
@@ -2002,7 +2017,7 @@ static int ioctl_common(struct scsi_device *sdev, int cmd)
 		case DK_CXLFLASH_VLUN_RESIZE:
 		case DK_CXLFLASH_RELEASE:
 		case DK_CXLFLASH_DETACH:
-			dev_dbg(dev, "%s: Command override! (%d)\n",
+			dev_dbg(dev, "%s: Command override rc=%d\n",
 				__func__, rc);
 			rc = 0;
 			break;
@@ -2032,7 +2047,7 @@ int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 {
 	typedef int (*sioctl) (struct scsi_device *, void *);
 
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct afu *afu = cfg->afu;
 	struct dk_cxlflash_hdr *hdr;
@@ -2111,7 +2126,7 @@ int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 	}
 
 	if (unlikely(copy_from_user(&buf, arg, size))) {
-		dev_err(dev, "%s: copy_from_user() fail! "
+		dev_err(dev, "%s: copy_from_user() fail "
 			"size=%lu cmd=%d (%s) arg=%p\n",
 			__func__, size, cmd, decode_ioctl(cmd), arg);
 		rc = -EFAULT;
@@ -2127,7 +2142,7 @@ int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 	}
 
 	if (hdr->rsvd[0] || hdr->rsvd[1] || hdr->rsvd[2] || hdr->return_flags) {
-		dev_dbg(dev, "%s: Reserved/rflags populated!\n", __func__);
+		dev_dbg(dev, "%s: Reserved/rflags populated\n", __func__);
 		rc = -EINVAL;
 		goto cxlflash_ioctl_exit;
 	}
@@ -2135,7 +2150,7 @@ int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 	rc = do_ioctl(sdev, (void *)&buf);
 	if (likely(!rc))
 		if (unlikely(copy_to_user(arg, &buf, size))) {
-			dev_err(dev, "%s: copy_to_user() fail! "
+			dev_err(dev, "%s: copy_to_user() fail "
 				"size=%lu cmd=%d (%s) arg=%p\n",
 				__func__, size, cmd, decode_ioctl(cmd), arg);
 			rc = -EFAULT;
diff --git a/drivers/scsi/cxlflash/vlun.c b/drivers/scsi/cxlflash/vlun.c
index 90c5d7f5278e..8fcc804dbef9 100644
--- a/drivers/scsi/cxlflash/vlun.c
+++ b/drivers/scsi/cxlflash/vlun.c
@@ -66,8 +66,8 @@ static int ba_init(struct ba_lun *ba_lun)
 	int last_word_underflow = 0;
 	u64 *lam;
 
-	pr_debug("%s: Initializing LUN: lun_id = %llX, "
-		 "ba_lun->lsize = %lX, ba_lun->au_size = %lX\n",
+	pr_debug("%s: Initializing LUN: lun_id=%016llx "
+		 "ba_lun->lsize=%lx ba_lun->au_size=%lX\n",
 		__func__, ba_lun->lun_id, ba_lun->lsize, ba_lun->au_size);
 
 	/* Calculate bit map size */
@@ -80,7 +80,7 @@ static int ba_init(struct ba_lun *ba_lun)
 	/* Allocate lun information container */
 	bali = kzalloc(sizeof(struct ba_lun_info), GFP_KERNEL);
 	if (unlikely(!bali)) {
-		pr_err("%s: Failed to allocate lun_info for lun_id %llX\n",
+		pr_err("%s: Failed to allocate lun_info lun_id=%016llx\n",
 		       __func__, ba_lun->lun_id);
 		return -ENOMEM;
 	}
@@ -96,7 +96,7 @@ static int ba_init(struct ba_lun *ba_lun)
 				      GFP_KERNEL);
 	if (unlikely(!bali->lun_alloc_map)) {
 		pr_err("%s: Failed to allocate lun allocation map: "
-		       "lun_id = %llX\n", __func__, ba_lun->lun_id);
+		       "lun_id=%016llx\n", __func__, ba_lun->lun_id);
 		kfree(bali);
 		return -ENOMEM;
 	}
@@ -125,7 +125,7 @@ static int ba_init(struct ba_lun *ba_lun)
 	bali->aun_clone_map = kzalloc((bali->total_aus * sizeof(u8)),
 				      GFP_KERNEL);
 	if (unlikely(!bali->aun_clone_map)) {
-		pr_err("%s: Failed to allocate clone map: lun_id = %llX\n",
+		pr_err("%s: Failed to allocate clone map: lun_id=%016llx\n",
 		       __func__, ba_lun->lun_id);
 		kfree(bali->lun_alloc_map);
 		kfree(bali);
@@ -136,7 +136,7 @@ static int ba_init(struct ba_lun *ba_lun)
 	ba_lun->ba_lun_handle = bali;
 
 	pr_debug("%s: Successfully initialized the LUN: "
-		 "lun_id = %llX, bitmap size = %X, free_aun_cnt = %llX\n",
+		 "lun_id=%016llx bitmap size=%x, free_aun_cnt=%llx\n",
 		__func__, ba_lun->lun_id, bali->lun_bmap_size,
 		bali->free_aun_cnt);
 	return 0;
@@ -165,10 +165,9 @@ static int find_free_range(u32 low,
 			num_bits = (sizeof(*lam) * BITS_PER_BYTE);
 			bit_pos = find_first_bit(lam, num_bits);
 
-			pr_devel("%s: Found free bit %llX in LUN "
-				 "map entry %llX at bitmap index = %X\n",
-				 __func__, bit_pos, bali->lun_alloc_map[i],
-				 i);
+			pr_devel("%s: Found free bit %llu in LUN "
+				 "map entry %016llx at bitmap index = %d\n",
+				 __func__, bit_pos, bali->lun_alloc_map[i], i);
 
 			*bit_word = i;
 			bali->free_aun_cnt--;
@@ -194,11 +193,11 @@ static u64 ba_alloc(struct ba_lun *ba_lun)
 	bali = ba_lun->ba_lun_handle;
 
 	pr_debug("%s: Received block allocation request: "
-		 "lun_id = %llX, free_aun_cnt = %llX\n",
+		 "lun_id=%016llx free_aun_cnt=%llx\n",
 		 __func__, ba_lun->lun_id, bali->free_aun_cnt);
 
 	if (bali->free_aun_cnt == 0) {
-		pr_debug("%s: No space left on LUN: lun_id = %llX\n",
+		pr_debug("%s: No space left on LUN: lun_id=%016llx\n",
 			 __func__, ba_lun->lun_id);
 		return -1ULL;
 	}
@@ -212,7 +211,7 @@ static u64 ba_alloc(struct ba_lun *ba_lun)
 					  bali, &bit_word);
 		if (bit_pos == -1) {
 			pr_debug("%s: Could not find an allocation unit on LUN:"
-				 " lun_id = %llX\n", __func__, ba_lun->lun_id);
+				 " lun_id=%016llx\n", __func__, ba_lun->lun_id);
 			return -1ULL;
 		}
 	}
@@ -223,8 +222,8 @@ static u64 ba_alloc(struct ba_lun *ba_lun)
 	else
 		bali->free_curr_idx = bit_word;
 
-	pr_debug("%s: Allocating AU number %llX, on lun_id %llX, "
-		 "free_aun_cnt = %llX\n", __func__,
+	pr_debug("%s: Allocating AU number=%llx lun_id=%016llx "
+		 "free_aun_cnt=%llx\n", __func__,
 		 ((bit_word * BITS_PER_LONG) + bit_pos), ba_lun->lun_id,
 		 bali->free_aun_cnt);
 
@@ -266,18 +265,18 @@ static int ba_free(struct ba_lun *ba_lun, u64 to_free)
 	bali = ba_lun->ba_lun_handle;
 
 	if (validate_alloc(bali, to_free)) {
-		pr_debug("%s: The AUN %llX is not allocated on lun_id %llX\n",
+		pr_debug("%s: AUN %llx is not allocated on lun_id=%016llx\n",
 			 __func__, to_free, ba_lun->lun_id);
 		return -1;
 	}
 
-	pr_debug("%s: Received a request to free AU %llX on lun_id %llX, "
-		 "free_aun_cnt = %llX\n", __func__, to_free, ba_lun->lun_id,
+	pr_debug("%s: Received a request to free AU=%llx lun_id=%016llx "
+		 "free_aun_cnt=%llx\n", __func__, to_free, ba_lun->lun_id,
 		 bali->free_aun_cnt);
 
 	if (bali->aun_clone_map[to_free] > 0) {
-		pr_debug("%s: AUN %llX on lun_id %llX has been cloned. Clone "
-			 "count = %X\n", __func__, to_free, ba_lun->lun_id,
+		pr_debug("%s: AUN %llx lun_id=%016llx cloned. Clone count=%x\n",
+			 __func__, to_free, ba_lun->lun_id,
 			 bali->aun_clone_map[to_free]);
 		bali->aun_clone_map[to_free]--;
 		return 0;
@@ -294,8 +293,8 @@ static int ba_free(struct ba_lun *ba_lun, u64 to_free)
 	else if (idx > bali->free_high_idx)
 		bali->free_high_idx = idx;
 
-	pr_debug("%s: Successfully freed AU at bit_pos %X, bit map index %X on "
-		 "lun_id %llX, free_aun_cnt = %llX\n", __func__, bit_pos, idx,
+	pr_debug("%s: Successfully freed AU bit_pos=%x bit map index=%x "
+		 "lun_id=%016llx free_aun_cnt=%llx\n", __func__, bit_pos, idx,
 		 ba_lun->lun_id, bali->free_aun_cnt);
 
 	return 0;
@@ -313,16 +312,16 @@ static int ba_clone(struct ba_lun *ba_lun, u64 to_clone)
 	struct ba_lun_info *bali = ba_lun->ba_lun_handle;
 
 	if (validate_alloc(bali, to_clone)) {
-		pr_debug("%s: AUN %llX is not allocated on lun_id %llX\n",
+		pr_debug("%s: AUN=%llx not allocated on lun_id=%016llx\n",
 			 __func__, to_clone, ba_lun->lun_id);
 		return -1;
 	}
 
-	pr_debug("%s: Received a request to clone AUN %llX on lun_id %llX\n",
+	pr_debug("%s: Received a request to clone AUN %llx on lun_id=%016llx\n",
 		 __func__, to_clone, ba_lun->lun_id);
 
 	if (bali->aun_clone_map[to_clone] == MAX_AUN_CLONE_CNT) {
-		pr_debug("%s: AUN %llX on lun_id %llX hit max clones already\n",
+		pr_debug("%s: AUN %llx on lun_id=%016llx hit max clones already\n",
 			 __func__, to_clone, ba_lun->lun_id);
 		return -1;
 	}
@@ -433,7 +432,7 @@ static int write_same16(struct scsi_device *sdev,
 	u64 offset = lba;
 	int left = nblks;
 	u32 to = sdev->request_queue->rq_timeout;
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 
 	cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
@@ -459,7 +458,7 @@ static int write_same16(struct scsi_device *sdev,
 		down_read(&cfg->ioctl_rwsem);
 		rc = check_state(cfg);
 		if (rc) {
-			dev_err(dev, "%s: Failed state! result=0x08%X\n",
+			dev_err(dev, "%s: Failed state result=%08x\n",
 				__func__, result);
 			rc = -ENODEV;
 			goto out;
@@ -467,7 +466,7 @@ static int write_same16(struct scsi_device *sdev,
 
 		if (result) {
 			dev_err_ratelimited(dev, "%s: command failed for "
-					    "offset %lld result=0x%x\n",
+					    "offset=%lld result=%08x\n",
 					    __func__, offset, result);
 			rc = -EIO;
 			goto out;
@@ -480,7 +479,7 @@ out:
 	kfree(cmd_buf);
 	kfree(scsi_cmd);
 	kfree(sense_buf);
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -508,6 +507,8 @@ static int grow_lxt(struct afu *afu,
 		    struct sisl_rht_entry *rhte,
 		    u64 *new_size)
 {
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_lxt_entry *lxt = NULL, *lxt_old = NULL;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
@@ -527,7 +528,8 @@ static int grow_lxt(struct afu *afu,
 	mutex_lock(&blka->mutex);
 	av_size = ba_space(&blka->ba_lun);
 	if (unlikely(av_size <= 0)) {
-		pr_debug("%s: ba_space error: av_size %d\n", __func__, av_size);
+		dev_dbg(dev, "%s: ba_space error av_size=%d\n",
+			__func__, av_size);
 		mutex_unlock(&blka->mutex);
 		rc = -ENOSPC;
 		goto out;
@@ -568,8 +570,8 @@ static int grow_lxt(struct afu *afu,
 		 */
 		aun = ba_alloc(&blka->ba_lun);
 		if ((aun == -1ULL) || (aun >= blka->nchunk))
-			pr_debug("%s: ba_alloc error: allocated chunk# %llX, "
-				 "max %llX\n", __func__, aun, blka->nchunk - 1);
+			dev_dbg(dev, "%s: ba_alloc error allocated chunk=%llu "
+				"max=%llu\n", __func__, aun, blka->nchunk - 1);
 
 		/* select both ports, use r/w perms from RHT */
 		lxt[i].rlba_base = ((aun << MC_CHUNK_SHIFT) |
@@ -599,7 +601,7 @@ static int grow_lxt(struct afu *afu,
 		kfree(lxt_old);
 	*new_size = my_new_size;
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -621,6 +623,8 @@ static int shrink_lxt(struct afu *afu,
 		      struct ctx_info *ctxi,
 		      u64 *new_size)
 {
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_lxt_entry *lxt, *lxt_old;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
@@ -706,7 +710,7 @@ static int shrink_lxt(struct afu *afu,
 		kfree(lxt_old);
 	*new_size = my_new_size;
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -728,7 +732,8 @@ int _cxlflash_vlun_resize(struct scsi_device *sdev,
 			  struct ctx_info *ctxi,
 			  struct dk_cxlflash_resize *resize)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
 	struct afu *afu = cfg->afu;
@@ -751,13 +756,13 @@ int _cxlflash_vlun_resize(struct scsi_device *sdev,
 	nsectors = (resize->req_size * CXLFLASH_BLOCK_SIZE) / gli->blk_len;
 	new_size = DIV_ROUND_UP(nsectors, MC_CHUNK_SIZE);
 
-	pr_debug("%s: ctxid=%llu rhndl=0x%llx, req_size=0x%llx,"
-		 "new_size=%llx\n", __func__, ctxid, resize->rsrc_handle,
-		 resize->req_size, new_size);
+	dev_dbg(dev, "%s: ctxid=%llu rhndl=%llu req_size=%llu new_size=%llu\n",
+		__func__, ctxid, resize->rsrc_handle, resize->req_size,
+		new_size);
 
 	if (unlikely(gli->mode != MODE_VIRTUAL)) {
-		pr_debug("%s: LUN mode does not support resize! (%d)\n",
-			 __func__, gli->mode);
+		dev_dbg(dev, "%s: LUN mode does not support resize mode=%d\n",
+			__func__, gli->mode);
 		rc = -EINVAL;
 		goto out;
 
@@ -766,7 +771,8 @@ int _cxlflash_vlun_resize(struct scsi_device *sdev,
 	if (!ctxi) {
 		ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
 		if (unlikely(!ctxi)) {
-			pr_debug("%s: Bad context! (%llu)\n", __func__, ctxid);
+			dev_dbg(dev, "%s: Bad context ctxid=%llu\n",
+				__func__, ctxid);
 			rc = -EINVAL;
 			goto out;
 		}
@@ -776,7 +782,8 @@ int _cxlflash_vlun_resize(struct scsi_device *sdev,
 
 	rhte = get_rhte(ctxi, rhndl, lli);
 	if (unlikely(!rhte)) {
-		pr_debug("%s: Bad resource handle! (%u)\n", __func__, rhndl);
+		dev_dbg(dev, "%s: Bad resource handle rhndl=%u\n",
+			__func__, rhndl);
 		rc = -EINVAL;
 		goto out;
 	}
@@ -794,8 +801,8 @@ int _cxlflash_vlun_resize(struct scsi_device *sdev,
 out:
 	if (put_ctx)
 		put_context(ctxi);
-	pr_debug("%s: resized to %lld returning rc=%d\n",
-		 __func__, resize->last_lba, rc);
+	dev_dbg(dev, "%s: resized to %llu returning rc=%d\n",
+		__func__, resize->last_lba, rc);
 	return rc;
 }
 
@@ -815,6 +822,7 @@ void cxlflash_restore_luntable(struct cxlflash_cfg *cfg)
 	u32 chan;
 	u32 lind;
 	struct afu *afu = cfg->afu;
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_global_map __iomem *agm = &afu->afu_map->global;
 
 	mutex_lock(&global.mutex);
@@ -828,15 +836,15 @@ void cxlflash_restore_luntable(struct cxlflash_cfg *cfg)
 		if (lli->port_sel == BOTH_PORTS) {
 			writeq_be(lli->lun_id[0], &agm->fc_port[0][lind]);
 			writeq_be(lli->lun_id[1], &agm->fc_port[1][lind]);
-			pr_debug("%s: Virtual LUN on slot %d  id0=%llx, "
-				 "id1=%llx\n", __func__, lind,
-				 lli->lun_id[0], lli->lun_id[1]);
+			dev_dbg(dev, "%s: Virtual LUN on slot %d  id0=%llx "
+				"id1=%llx\n", __func__, lind,
+				lli->lun_id[0], lli->lun_id[1]);
 		} else {
 			chan = PORT2CHAN(lli->port_sel);
 			writeq_be(lli->lun_id[chan], &agm->fc_port[chan][lind]);
-			pr_debug("%s: Virtual LUN on slot %d chan=%d, "
-				 "id=%llx\n", __func__, lind, chan,
-				 lli->lun_id[chan]);
+			dev_dbg(dev, "%s: Virtual LUN on slot %d chan=%d "
+				"id=%llx\n", __func__, lind, chan,
+				lli->lun_id[chan]);
 		}
 	}
 
@@ -860,6 +868,7 @@ static int init_luntable(struct cxlflash_cfg *cfg, struct llun_info *lli)
 	u32 lind;
 	int rc = 0;
 	struct afu *afu = cfg->afu;
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_global_map __iomem *agm = &afu->afu_map->global;
 
 	mutex_lock(&global.mutex);
@@ -882,8 +891,8 @@ static int init_luntable(struct cxlflash_cfg *cfg, struct llun_info *lli)
 		writeq_be(lli->lun_id[0], &agm->fc_port[0][lind]);
 		writeq_be(lli->lun_id[1], &agm->fc_port[1][lind]);
 		cfg->promote_lun_index++;
-		pr_debug("%s: Virtual LUN on slot %d  id0=%llx, id1=%llx\n",
-			 __func__, lind, lli->lun_id[0], lli->lun_id[1]);
+		dev_dbg(dev, "%s: Virtual LUN on slot %d  id0=%llx id1=%llx\n",
+			__func__, lind, lli->lun_id[0], lli->lun_id[1]);
 	} else {
 		/*
 		 * If this LUN is visible only from one port, we will put
@@ -898,14 +907,14 @@ static int init_luntable(struct cxlflash_cfg *cfg, struct llun_info *lli)
 		lind = lli->lun_index = cfg->last_lun_index[chan];
 		writeq_be(lli->lun_id[chan], &agm->fc_port[chan][lind]);
 		cfg->last_lun_index[chan]--;
-		pr_debug("%s: Virtual LUN on slot %d  chan=%d, id=%llx\n",
-			 __func__, lind, chan, lli->lun_id[chan]);
+		dev_dbg(dev, "%s: Virtual LUN on slot %d  chan=%d id=%llx\n",
+			__func__, lind, chan, lli->lun_id[chan]);
 	}
 
 	lli->in_table = true;
 out:
 	mutex_unlock(&global.mutex);
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -923,7 +932,7 @@ out:
  */
 int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
@@ -942,14 +951,14 @@ int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)
 	struct ctx_info *ctxi = NULL;
 	struct sisl_rht_entry *rhte = NULL;
 
-	pr_debug("%s: ctxid=%llu ls=0x%llx\n", __func__, ctxid, lun_size);
+	dev_dbg(dev, "%s: ctxid=%llu ls=%llu\n", __func__, ctxid, lun_size);
 
 	/* Setup the LUNs block allocator on first call */
 	mutex_lock(&gli->mutex);
 	if (gli->mode == MODE_NONE) {
 		rc = init_vlun(lli);
 		if (rc) {
-			dev_err(dev, "%s: call to init_vlun failed rc=%d!\n",
+			dev_err(dev, "%s: init_vlun failed rc=%d\n",
 				__func__, rc);
 			rc = -ENOMEM;
 			goto err0;
@@ -958,29 +967,28 @@ int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)
 
 	rc = cxlflash_lun_attach(gli, MODE_VIRTUAL, true);
 	if (unlikely(rc)) {
-		dev_err(dev, "%s: Failed to attach to LUN! (VIRTUAL)\n",
-			__func__);
+		dev_err(dev, "%s: Failed attach to LUN (VIRTUAL)\n", __func__);
 		goto err0;
 	}
 	mutex_unlock(&gli->mutex);
 
 	rc = init_luntable(cfg, lli);
 	if (rc) {
-		dev_err(dev, "%s: call to init_luntable failed rc=%d!\n",
-			__func__, rc);
+		dev_err(dev, "%s: init_luntable failed rc=%d\n", __func__, rc);
 		goto err1;
 	}
 
 	ctxi = get_context(cfg, rctxid, lli, 0);
 	if (unlikely(!ctxi)) {
-		dev_err(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
+		dev_err(dev, "%s: Bad context ctxid=%llu\n", __func__, ctxid);
 		rc = -EINVAL;
 		goto err1;
 	}
 
 	rhte = rhte_checkout(ctxi, lli);
 	if (unlikely(!rhte)) {
-		dev_err(dev, "%s: too many opens for this context\n", __func__);
+		dev_err(dev, "%s: too many opens ctxid=%llu\n",
+			__func__, ctxid);
 		rc = -EMFILE;	/* too many opens  */
 		goto err1;
 	}
@@ -996,7 +1004,7 @@ int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)
 	resize.rsrc_handle = rsrc_handle;
 	rc = _cxlflash_vlun_resize(sdev, ctxi, &resize);
 	if (rc) {
-		dev_err(dev, "%s: resize failed rc %d\n", __func__, rc);
+		dev_err(dev, "%s: resize failed rc=%d\n", __func__, rc);
 		goto err2;
 	}
 	last_lba = resize.last_lba;
@@ -1013,8 +1021,8 @@ int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)
 out:
 	if (likely(ctxi))
 		put_context(ctxi);
-	pr_debug("%s: returning handle 0x%llx rc=%d llba %lld\n",
-		 __func__, rsrc_handle, rc, last_lba);
+	dev_dbg(dev, "%s: returning handle=%llu rc=%d llba=%llu\n",
+		__func__, rsrc_handle, rc, last_lba);
 	return rc;
 
 err2:
@@ -1047,6 +1055,8 @@ static int clone_lxt(struct afu *afu,
 		     struct sisl_rht_entry *rhte,
 		     struct sisl_rht_entry *rhte_src)
 {
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_lxt_entry *lxt;
 	u32 ngrps;
 	u64 aun;		/* chunk# allocated by block allocator */
@@ -1101,7 +1111,7 @@ static int clone_lxt(struct afu *afu,
 
 	cxlflash_afu_sync(afu, ctxid, rhndl, AFU_LW_SYNC);
 
-	pr_debug("%s: returning\n", __func__);
+	dev_dbg(dev, "%s: returning\n", __func__);
 	return 0;
 }
 
@@ -1120,7 +1130,8 @@ static int clone_lxt(struct afu *afu,
 int cxlflash_disk_clone(struct scsi_device *sdev,
 			struct dk_cxlflash_clone *clone)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
 	struct blka *blka = &gli->blka;
@@ -1140,8 +1151,8 @@ int cxlflash_disk_clone(struct scsi_device *sdev,
 	bool found;
 	LIST_HEAD(sidecar);
 
-	pr_debug("%s: ctxid_src=%llu ctxid_dst=%llu\n",
-		 __func__, ctxid_src, ctxid_dst);
+	dev_dbg(dev, "%s: ctxid_src=%llu ctxid_dst=%llu\n",
+		__func__, ctxid_src, ctxid_dst);
 
 	/* Do not clone yourself */
 	if (unlikely(rctxid_src == rctxid_dst)) {
@@ -1151,16 +1162,16 @@ int cxlflash_disk_clone(struct scsi_device *sdev,
 
 	if (unlikely(gli->mode != MODE_VIRTUAL)) {
 		rc = -EINVAL;
-		pr_debug("%s: Clone not supported on physical LUNs! (%d)\n",
-			 __func__, gli->mode);
+		dev_dbg(dev, "%s: Only supported on virtual LUNs mode=%u\n",
+			__func__, gli->mode);
 		goto out;
 	}
 
 	ctxi_src = get_context(cfg, rctxid_src, lli, CTX_CTRL_CLONE);
 	ctxi_dst = get_context(cfg, rctxid_dst, lli, 0);
 	if (unlikely(!ctxi_src || !ctxi_dst)) {
-		pr_debug("%s: Bad context! (%llu,%llu)\n", __func__,
-			 ctxid_src, ctxid_dst);
+		dev_dbg(dev, "%s: Bad context ctxid_src=%llu ctxid_dst=%llu\n",
+			__func__, ctxid_src, ctxid_dst);
 		rc = -EINVAL;
 		goto out;
 	}
@@ -1185,8 +1196,8 @@ int cxlflash_disk_clone(struct scsi_device *sdev,
 			lun_access_dst = kzalloc(sizeof(*lun_access_dst),
 						 GFP_KERNEL);
 			if (unlikely(!lun_access_dst)) {
-				pr_err("%s: Unable to allocate lun_access!\n",
-				       __func__);
+				dev_err(dev, "%s: lun_access allocation fail\n",
+					__func__);
 				rc = -ENOMEM;
 				goto out;
 			}
@@ -1197,7 +1208,7 @@ int cxlflash_disk_clone(struct scsi_device *sdev,
 	}
 
 	if (unlikely(!ctxi_src->rht_out)) {
-		pr_debug("%s: Nothing to clone!\n", __func__);
+		dev_dbg(dev, "%s: Nothing to clone\n", __func__);
 		goto out_success;
 	}
 
@@ -1256,7 +1267,7 @@ out:
 		put_context(ctxi_src);
 	if (ctxi_dst)
 		put_context(ctxi_dst);
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 
 err:
diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c
index 5f75e638ec95..256dd6791fcc 100644
--- a/drivers/scsi/dpt_i2o.c
+++ b/drivers/scsi/dpt_i2o.c
@@ -2768,16 +2768,12 @@ static int adpt_i2o_activate_hba(adpt_hba* pHba)
  
 static int adpt_i2o_online_hba(adpt_hba* pHba)
 {
-	if (adpt_i2o_systab_send(pHba) < 0) {
-		adpt_i2o_delete_hba(pHba);
+	if (adpt_i2o_systab_send(pHba) < 0)
 		return -1;
-	}
 	/* In READY state */
 
-	if (adpt_i2o_enable_hba(pHba) < 0) {
-		adpt_i2o_delete_hba(pHba);
+	if (adpt_i2o_enable_hba(pHba) < 0)
 		return -1;
-	}
 
 	/* In OPERATIONAL state  */
 	return 0;
diff --git a/drivers/scsi/esas2r/esas2r_init.c b/drivers/scsi/esas2r/esas2r_init.c
index d6e53aee2295..6432a50b26d8 100644
--- a/drivers/scsi/esas2r/esas2r_init.c
+++ b/drivers/scsi/esas2r/esas2r_init.c
@@ -237,7 +237,7 @@ static void esas2r_claim_interrupts(struct esas2r_adapter *a)
 		flags |= IRQF_SHARED;
 
 	esas2r_log(ESAS2R_LOG_INFO,
-		   "esas2r_claim_interrupts irq=%d (%p, %s, %x)",
+		   "esas2r_claim_interrupts irq=%d (%p, %s, %lx)",
 		   a->pcid->irq, a, a->name, flags);
 
 	if (request_irq(a->pcid->irq,
diff --git a/drivers/scsi/esas2r/esas2r_ioctl.c b/drivers/scsi/esas2r/esas2r_ioctl.c
index 3e8483410f61..b35ed3829421 100644
--- a/drivers/scsi/esas2r/esas2r_ioctl.c
+++ b/drivers/scsi/esas2r/esas2r_ioctl.c
@@ -1301,7 +1301,7 @@ int esas2r_ioctl_handler(void *hostdata, int cmd, void __user *arg)
 	ioctl = kzalloc(sizeof(struct atto_express_ioctl), GFP_KERNEL);
 	if (ioctl == NULL) {
 		esas2r_log(ESAS2R_LOG_WARN,
-			   "ioctl_handler kzalloc failed for %d bytes",
+			   "ioctl_handler kzalloc failed for %zu bytes",
 			   sizeof(struct atto_express_ioctl));
 		return -ENOMEM;
 	}
diff --git a/drivers/scsi/esas2r/esas2r_log.h b/drivers/scsi/esas2r/esas2r_log.h
index 7b6397bb5b94..75b9d23cd736 100644
--- a/drivers/scsi/esas2r/esas2r_log.h
+++ b/drivers/scsi/esas2r/esas2r_log.h
@@ -61,8 +61,8 @@ enum {
 #endif
 };
 
-int esas2r_log(const long level, const char *format, ...);
-int esas2r_log_dev(const long level,
+__printf(2, 3) int esas2r_log(const long level, const char *format, ...);
+__printf(3, 4) int esas2r_log_dev(const long level,
 		   const struct device *dev,
 		   const char *format,
 		   ...);
diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c
index 5092c821d088..f2e9d8aa979c 100644
--- a/drivers/scsi/esas2r/esas2r_main.c
+++ b/drivers/scsi/esas2r/esas2r_main.c
@@ -198,7 +198,7 @@ static ssize_t write_hw(struct file *file, struct kobject *kobj,
 					      GFP_KERNEL);
 		if (a->local_atto_ioctl == NULL) {
 			esas2r_log(ESAS2R_LOG_WARN,
-				   "write_hw kzalloc failed for %d bytes",
+				   "write_hw kzalloc failed for %zu bytes",
 				   sizeof(struct atto_ioctl));
 			return -ENOMEM;
 		}
@@ -1186,7 +1186,7 @@ retry:
 		} else {
 			esas2r_log(ESAS2R_LOG_CRIT,
 				   "unable to allocate a request for a "
-				   "device reset (%d:%d)!",
+				   "device reset (%d:%llu)!",
 				   cmd->device->id,
 				   cmd->device->lun);
 		}
diff --git a/drivers/scsi/g_NCR5380.c b/drivers/scsi/g_NCR5380.c
index 6f9665d50d84..67c8dac321ad 100644
--- a/drivers/scsi/g_NCR5380.c
+++ b/drivers/scsi/g_NCR5380.c
@@ -26,14 +26,55 @@
 #include <linux/blkdev.h>
 #include <linux/module.h>
 #include <scsi/scsi_host.h>
-#include "g_NCR5380.h"
-#include "NCR5380.h"
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/isa.h>
 #include <linux/pnp.h>
 #include <linux/interrupt.h>
 
+/* Definitions for the core NCR5380 driver. */
+
+#define NCR5380_read(reg) \
+	ioread8(hostdata->io + hostdata->offset + (reg))
+#define NCR5380_write(reg, value) \
+	iowrite8(value, hostdata->io + hostdata->offset + (reg))
+
+#define NCR5380_implementation_fields \
+	int offset; \
+	int c400_ctl_status; \
+	int c400_blk_cnt; \
+	int c400_host_buf; \
+	int io_width
+
+#define NCR5380_dma_xfer_len            generic_NCR5380_dma_xfer_len
+#define NCR5380_dma_recv_setup          generic_NCR5380_pread
+#define NCR5380_dma_send_setup          generic_NCR5380_pwrite
+#define NCR5380_dma_residual            NCR5380_dma_residual_none
+
+#define NCR5380_intr                    generic_NCR5380_intr
+#define NCR5380_queue_command           generic_NCR5380_queue_command
+#define NCR5380_abort                   generic_NCR5380_abort
+#define NCR5380_bus_reset               generic_NCR5380_bus_reset
+#define NCR5380_info                    generic_NCR5380_info
+
+#define NCR5380_io_delay(x)             udelay(x)
+
+#include "NCR5380.h"
+
+#define DRV_MODULE_NAME "g_NCR5380"
+
+#define NCR53C400_mem_base 0x3880
+#define NCR53C400_host_buffer 0x3900
+#define NCR53C400_region_size 0x3a00
+
+#define BOARD_NCR5380 0
+#define BOARD_NCR53C400 1
+#define BOARD_NCR53C400A 2
+#define BOARD_DTC3181E 3
+#define BOARD_HP_C2502 4
+
+#define IRQ_AUTO 254
+
 #define MAX_CARDS 8
 
 /* old-style parameters for compatibility */
diff --git a/drivers/scsi/g_NCR5380.h b/drivers/scsi/g_NCR5380.h
deleted file mode 100644
index 81b22d989648..000000000000
--- a/drivers/scsi/g_NCR5380.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- * Generic Generic NCR5380 driver defines
- *
- * Copyright 1993, Drew Eckhardt
- *	Visionary Computing
- *	(Unix and Linux consulting and custom programming)
- *	drew@colorado.edu
- *      +1 (303) 440-4894
- *
- * NCR53C400 extensions (c) 1994,1995,1996, Kevin Lentin
- *    K.Lentin@cs.monash.edu.au
- */
-
-#ifndef GENERIC_NCR5380_H
-#define GENERIC_NCR5380_H
-
-#define DRV_MODULE_NAME "g_NCR5380"
-
-#define NCR5380_read(reg) \
-	ioread8(hostdata->io + hostdata->offset + (reg))
-#define NCR5380_write(reg, value) \
-	iowrite8(value, hostdata->io + hostdata->offset + (reg))
-
-#define NCR5380_implementation_fields \
-	int offset; \
-	int c400_ctl_status; \
-	int c400_blk_cnt; \
-	int c400_host_buf; \
-	int io_width;
-
-#define NCR53C400_mem_base 0x3880
-#define NCR53C400_host_buffer 0x3900
-#define NCR53C400_region_size 0x3a00
-
-#define NCR5380_dma_xfer_len		generic_NCR5380_dma_xfer_len
-#define NCR5380_dma_recv_setup		generic_NCR5380_pread
-#define NCR5380_dma_send_setup		generic_NCR5380_pwrite
-#define NCR5380_dma_residual		NCR5380_dma_residual_none
-
-#define NCR5380_intr generic_NCR5380_intr
-#define NCR5380_queue_command generic_NCR5380_queue_command
-#define NCR5380_abort generic_NCR5380_abort
-#define NCR5380_bus_reset generic_NCR5380_bus_reset
-#define NCR5380_info generic_NCR5380_info
-
-#define NCR5380_io_delay(x)		udelay(x)
-
-#define BOARD_NCR5380	0
-#define BOARD_NCR53C400	1
-#define BOARD_NCR53C400A 2
-#define BOARD_DTC3181E	3
-#define BOARD_HP_C2502	4
-
-#define IRQ_AUTO	254
-
-#endif /* GENERIC_NCR5380_H */
diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index c0cd505a9ef7..9216deaa3ff5 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -95,6 +95,7 @@ struct hisi_sas_port {
 
 struct hisi_sas_cq {
 	struct hisi_hba *hisi_hba;
+	struct tasklet_struct tasklet;
 	int	rd_point;
 	int	id;
 };
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index d50e9cfefd24..53637a941b94 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -71,6 +71,8 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 			     struct hisi_sas_slot *slot)
 {
 	struct device *dev = &hisi_hba->pdev->dev;
+	struct domain_device *device = task->dev;
+	struct hisi_sas_device *sas_dev = device->lldd_dev;
 
 	if (!slot->task)
 		return;
@@ -97,6 +99,8 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 	slot->task = NULL;
 	slot->port = NULL;
 	hisi_sas_slot_index_free(hisi_hba, slot->idx);
+	if (sas_dev)
+		atomic64_dec(&sas_dev->running_req);
 	/* slot memory is fully zeroed when it is reused */
 }
 EXPORT_SYMBOL_GPL(hisi_sas_slot_task_free);
@@ -141,11 +145,10 @@ static void hisi_sas_slot_abort(struct work_struct *work)
 	struct hisi_hba *hisi_hba = dev_to_hisi_hba(task->dev);
 	struct scsi_cmnd *cmnd = task->uldd_task;
 	struct hisi_sas_tmf_task tmf_task;
-	struct domain_device *device = task->dev;
-	struct hisi_sas_device *sas_dev = device->lldd_dev;
 	struct scsi_lun lun;
 	struct device *dev = &hisi_hba->pdev->dev;
 	int tag = abort_slot->idx;
+	unsigned long flags;
 
 	if (!(task->task_proto & SAS_PROTOCOL_SSP)) {
 		dev_err(dev, "cannot abort slot for non-ssp task\n");
@@ -159,11 +162,11 @@ static void hisi_sas_slot_abort(struct work_struct *work)
 	hisi_sas_debug_issue_ssp_tmf(task->dev, lun.scsi_lun, &tmf_task);
 out:
 	/* Do cleanup for this task */
+	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_task_free(hisi_hba, task, abort_slot);
+	spin_unlock_irqrestore(&hisi_hba->lock, flags);
 	if (task->task_done)
 		task->task_done(task);
-	if (sas_dev)
-		atomic64_dec(&sas_dev->running_req);
 }
 
 static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
@@ -1118,7 +1121,7 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 	}
 
 exit:
-	dev_info(dev, "internal task abort: task to dev %016llx task=%p "
+	dev_dbg(dev, "internal task abort: task to dev %016llx task=%p "
 		"resp: 0x%x sts 0x%x\n",
 		SAS_ADDR(device->sas_addr),
 		task,
@@ -1450,7 +1453,7 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
 
 	refclk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(refclk))
-		dev_info(dev, "no ref clk property\n");
+		dev_dbg(dev, "no ref clk property\n");
 	else
 		hisi_hba->refclk_frequency_mhz = clk_get_rate(refclk) / 1000000;
 
@@ -1549,10 +1552,6 @@ int hisi_sas_probe(struct platform_device *pdev,
 
 	hisi_sas_init_add(hisi_hba);
 
-	rc = hisi_hba->hw->hw_init(hisi_hba);
-	if (rc)
-		goto err_out_ha;
-
 	rc = scsi_add_host(shost, &pdev->dev);
 	if (rc)
 		goto err_out_ha;
@@ -1561,6 +1560,10 @@ int hisi_sas_probe(struct platform_device *pdev,
 	if (rc)
 		goto err_out_register_ha;
 
+	rc = hisi_hba->hw->hw_init(hisi_hba);
+	if (rc)
+		goto err_out_register_ha;
+
 	scsi_scan_host(shost);
 
 	return 0;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 8a1be0ba8a22..854fbeaade3e 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1596,6 +1596,7 @@ static irqreturn_t cq_interrupt_v1_hw(int irq, void *p)
 			hisi_hba->complete_hdr[queue];
 	u32 irq_value, rd_point = cq->rd_point, wr_point;
 
+	spin_lock(&hisi_hba->lock);
 	irq_value = hisi_sas_read32(hisi_hba, OQ_INT_SRC);
 
 	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 1 << queue);
@@ -1628,6 +1629,7 @@ static irqreturn_t cq_interrupt_v1_hw(int irq, void *p)
 	/* update rd_point */
 	cq->rd_point = rd_point;
 	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
+	spin_unlock(&hisi_hba->lock);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index b934aec1eebb..1b214450dcb5 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -207,6 +207,8 @@
 #define TXID_AUTO			(PORT_BASE + 0xb8)
 #define TXID_AUTO_CT3_OFF		1
 #define TXID_AUTO_CT3_MSK		(0x1 << TXID_AUTO_CT3_OFF)
+#define TX_HARDRST_OFF          2
+#define TX_HARDRST_MSK          (0x1 << TX_HARDRST_OFF)
 #define RX_IDAF_DWORD0			(PORT_BASE + 0xc4)
 #define RX_IDAF_DWORD1			(PORT_BASE + 0xc8)
 #define RX_IDAF_DWORD2			(PORT_BASE + 0xcc)
@@ -215,6 +217,7 @@
 #define RX_IDAF_DWORD5			(PORT_BASE + 0xd8)
 #define RX_IDAF_DWORD6			(PORT_BASE + 0xdc)
 #define RXOP_CHECK_CFG_H		(PORT_BASE + 0xfc)
+#define CON_CONTROL			(PORT_BASE + 0x118)
 #define DONE_RECEIVED_TIME		(PORT_BASE + 0x11c)
 #define CHL_INT0			(PORT_BASE + 0x1b4)
 #define CHL_INT0_HOTPLUG_TOUT_OFF	0
@@ -333,6 +336,11 @@
 #define ITCT_HDR_MCR_MSK		(0xf << ITCT_HDR_MCR_OFF)
 #define ITCT_HDR_VLN_OFF		9
 #define ITCT_HDR_VLN_MSK		(0xf << ITCT_HDR_VLN_OFF)
+#define ITCT_HDR_SMP_TIMEOUT_OFF	16
+#define ITCT_HDR_SMP_TIMEOUT_8US	1
+#define ITCT_HDR_SMP_TIMEOUT		(ITCT_HDR_SMP_TIMEOUT_8US * \
+					 250) /* 2ms */
+#define ITCT_HDR_AWT_CONTINUE_OFF	25
 #define ITCT_HDR_PORT_ID_OFF		28
 #define ITCT_HDR_PORT_ID_MSK		(0xf << ITCT_HDR_PORT_ID_OFF)
 /* qw2 */
@@ -526,6 +534,8 @@ enum {
 #define SATA_PROTOCOL_FPDMA		0x8
 #define SATA_PROTOCOL_ATAPI		0x10
 
+static void hisi_sas_link_timeout_disable_link(unsigned long data);
+
 static u32 hisi_sas_read32(struct hisi_hba *hisi_hba, u32 off)
 {
 	void __iomem *regs = hisi_hba->regs + off;
@@ -693,6 +703,8 @@ static void setup_itct_v2_hw(struct hisi_hba *hisi_hba,
 	qw0 |= ((1 << ITCT_HDR_VALID_OFF) |
 		(device->linkrate << ITCT_HDR_MCR_OFF) |
 		(1 << ITCT_HDR_VLN_OFF) |
+		(ITCT_HDR_SMP_TIMEOUT << ITCT_HDR_SMP_TIMEOUT_OFF) |
+		(1 << ITCT_HDR_AWT_CONTINUE_OFF) |
 		(port->id << ITCT_HDR_PORT_ID_OFF));
 	itct->qw0 = cpu_to_le64(qw0);
 
@@ -702,7 +714,7 @@ static void setup_itct_v2_hw(struct hisi_hba *hisi_hba,
 
 	/* qw2 */
 	if (!dev_is_sata(device))
-		itct->qw2 = cpu_to_le64((500ULL << ITCT_HDR_INLT_OFF) |
+		itct->qw2 = cpu_to_le64((5000ULL << ITCT_HDR_INLT_OFF) |
 					(0x1ULL << ITCT_HDR_BITLT_OFF) |
 					(0x32ULL << ITCT_HDR_MCTLT_OFF) |
 					(0x1ULL << ITCT_HDR_RTOLT_OFF));
@@ -711,7 +723,7 @@ static void setup_itct_v2_hw(struct hisi_hba *hisi_hba,
 static void free_device_v2_hw(struct hisi_hba *hisi_hba,
 			      struct hisi_sas_device *sas_dev)
 {
-	u64 qw0, dev_id = sas_dev->device_id;
+	u64 dev_id = sas_dev->device_id;
 	struct device *dev = &hisi_hba->pdev->dev;
 	struct hisi_sas_itct *itct = &hisi_hba->itct[dev_id];
 	u32 reg_val = hisi_sas_read32(hisi_hba, ENT_INT_SRC3);
@@ -735,8 +747,7 @@ static void free_device_v2_hw(struct hisi_hba *hisi_hba,
 			dev_dbg(dev, "got clear ITCT done interrupt\n");
 
 			/* invalid the itct state*/
-			qw0 = cpu_to_le64(itct->qw0);
-			qw0 &= ~(1 << ITCT_HDR_VALID_OFF);
+			memset(itct, 0, sizeof(struct hisi_sas_itct));
 			hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
 					 ENT_INT_SRC3_ITC_INT_MSK);
 
@@ -978,6 +989,50 @@ static void init_reg_v2_hw(struct hisi_hba *hisi_hba)
 			 upper_32_bits(hisi_hba->initial_fis_dma));
 }
 
+static void hisi_sas_link_timeout_enable_link(unsigned long data)
+{
+	struct hisi_hba *hisi_hba = (struct hisi_hba *)data;
+	int i, reg_val;
+
+	for (i = 0; i < hisi_hba->n_phy; i++) {
+		reg_val = hisi_sas_phy_read32(hisi_hba, i, CON_CONTROL);
+		if (!(reg_val & BIT(0))) {
+			hisi_sas_phy_write32(hisi_hba, i,
+					CON_CONTROL, 0x7);
+			break;
+		}
+	}
+
+	hisi_hba->timer.function = hisi_sas_link_timeout_disable_link;
+	mod_timer(&hisi_hba->timer, jiffies + msecs_to_jiffies(900));
+}
+
+static void hisi_sas_link_timeout_disable_link(unsigned long data)
+{
+	struct hisi_hba *hisi_hba = (struct hisi_hba *)data;
+	int i, reg_val;
+
+	reg_val = hisi_sas_read32(hisi_hba, PHY_STATE);
+	for (i = 0; i < hisi_hba->n_phy && reg_val; i++) {
+		if (reg_val & BIT(i)) {
+			hisi_sas_phy_write32(hisi_hba, i,
+					CON_CONTROL, 0x6);
+			break;
+		}
+	}
+
+	hisi_hba->timer.function = hisi_sas_link_timeout_enable_link;
+	mod_timer(&hisi_hba->timer, jiffies + msecs_to_jiffies(100));
+}
+
+static void set_link_timer_quirk(struct hisi_hba *hisi_hba)
+{
+	hisi_hba->timer.data = (unsigned long)hisi_hba;
+	hisi_hba->timer.function = hisi_sas_link_timeout_disable_link;
+	hisi_hba->timer.expires = jiffies + msecs_to_jiffies(1000);
+	add_timer(&hisi_hba->timer);
+}
+
 static int hw_init_v2_hw(struct hisi_hba *hisi_hba)
 {
 	struct device *dev = &hisi_hba->pdev->dev;
@@ -1025,14 +1080,21 @@ static void stop_phy_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
 
 static void phy_hard_reset_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
 {
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+	u32 txid_auto;
+
 	stop_phy_v2_hw(hisi_hba, phy_no);
+	if (phy->identify.device_type == SAS_END_DEVICE) {
+		txid_auto = hisi_sas_phy_read32(hisi_hba, phy_no, TXID_AUTO);
+		hisi_sas_phy_write32(hisi_hba, phy_no, TXID_AUTO,
+					txid_auto | TX_HARDRST_MSK);
+	}
 	msleep(100);
 	start_phy_v2_hw(hisi_hba, phy_no);
 }
 
-static void start_phys_v2_hw(unsigned long data)
+static void start_phys_v2_hw(struct hisi_hba *hisi_hba)
 {
-	struct hisi_hba *hisi_hba = (struct hisi_hba *)data;
 	int i;
 
 	for (i = 0; i < hisi_hba->n_phy; i++)
@@ -1041,10 +1103,7 @@ static void start_phys_v2_hw(unsigned long data)
 
 static void phys_init_v2_hw(struct hisi_hba *hisi_hba)
 {
-	struct timer_list *timer = &hisi_hba->timer;
-
-	setup_timer(timer, start_phys_v2_hw, (unsigned long)hisi_hba);
-	mod_timer(timer, jiffies + HZ);
+	start_phys_v2_hw(hisi_hba);
 }
 
 static void sl_notify_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
@@ -1771,8 +1830,6 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot,
 	}
 
 out:
-	if (sas_dev)
-		atomic64_dec(&sas_dev->running_req);
 
 	hisi_sas_slot_task_free(hisi_hba, task, slot);
 	sts = ts->stat;
@@ -2020,9 +2077,12 @@ static int phy_up_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
 	if (phy->identify.device_type == SAS_END_DEVICE)
 		phy->identify.target_port_protocols =
 			SAS_PROTOCOL_SSP;
-	else if (phy->identify.device_type != SAS_PHY_UNUSED)
+	else if (phy->identify.device_type != SAS_PHY_UNUSED) {
 		phy->identify.target_port_protocols =
 			SAS_PROTOCOL_SMP;
+		if (!timer_pending(&hisi_hba->timer))
+			set_link_timer_quirk(hisi_hba);
+	}
 	queue_work(hisi_hba->wq, &phy->phyup_ws);
 
 end:
@@ -2033,10 +2093,23 @@ end:
 	return res;
 }
 
+static bool check_any_wideports_v2_hw(struct hisi_hba *hisi_hba)
+{
+	u32 port_state;
+
+	port_state = hisi_sas_read32(hisi_hba, PORT_STATE);
+	if (port_state & 0x1ff)
+		return true;
+
+	return false;
+}
+
 static int phy_down_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
 {
 	int res = 0;
 	u32 phy_state, sl_ctrl, txid_auto;
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+	struct hisi_sas_port *port = phy->port;
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, PHYCTRL_NOT_RDY_MSK, 1);
 
@@ -2046,6 +2119,10 @@ static int phy_down_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
 	sl_ctrl = hisi_sas_phy_read32(hisi_hba, phy_no, SL_CONTROL);
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_CONTROL,
 			     sl_ctrl & ~SL_CONTROL_CTA_MSK);
+	if (port && !get_wideport_bitmap_v2_hw(hisi_hba, port->id))
+		if (!check_any_wideports_v2_hw(hisi_hba) &&
+				timer_pending(&hisi_hba->timer))
+			del_timer(&hisi_hba->timer);
 
 	txid_auto = hisi_sas_phy_read32(hisi_hba, phy_no, TXID_AUTO);
 	hisi_sas_phy_write32(hisi_hba, phy_no, TXID_AUTO,
@@ -2481,21 +2558,19 @@ static irqreturn_t fatal_axi_int_v2_hw(int irq_no, void *p)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)
+static void cq_tasklet_v2_hw(unsigned long val)
 {
-	struct hisi_sas_cq *cq = p;
+	struct hisi_sas_cq *cq = (struct hisi_sas_cq *)val;
 	struct hisi_hba *hisi_hba = cq->hisi_hba;
 	struct hisi_sas_slot *slot;
 	struct hisi_sas_itct *itct;
 	struct hisi_sas_complete_v2_hdr *complete_queue;
-	u32 irq_value, rd_point = cq->rd_point, wr_point, dev_id;
+	u32 rd_point = cq->rd_point, wr_point, dev_id;
 	int queue = cq->id;
 
 	complete_queue = hisi_hba->complete_hdr[queue];
-	irq_value = hisi_sas_read32(hisi_hba, OQ_INT_SRC);
-
-	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 1 << queue);
 
+	spin_lock(&hisi_hba->lock);
 	wr_point = hisi_sas_read32(hisi_hba, COMPL_Q_0_WR_PTR +
 				   (0x14 * queue));
 
@@ -2545,6 +2620,19 @@ static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)
 	/* update rd_point */
 	cq->rd_point = rd_point;
 	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
+	spin_unlock(&hisi_hba->lock);
+}
+
+static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)
+{
+	struct hisi_sas_cq *cq = p;
+	struct hisi_hba *hisi_hba = cq->hisi_hba;
+	int queue = cq->id;
+
+	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 1 << queue);
+
+	tasklet_schedule(&cq->tasklet);
+
 	return IRQ_HANDLED;
 }
 
@@ -2726,6 +2814,8 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 
 	for (i = 0; i < hisi_hba->queue_count; i++) {
 		int idx = i + 96; /* First cq interrupt is irq96 */
+		struct hisi_sas_cq *cq = &hisi_hba->cq[i];
+		struct tasklet_struct *t = &cq->tasklet;
 
 		irq = irq_map[idx];
 		if (!irq) {
@@ -2742,6 +2832,7 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 				irq, rc);
 			return -ENOENT;
 		}
+		tasklet_init(t, cq_tasklet_v2_hw, (unsigned long)cq);
 	}
 
 	return 0;
@@ -2807,6 +2898,12 @@ static int hisi_sas_v2_probe(struct platform_device *pdev)
 
 static int hisi_sas_v2_remove(struct platform_device *pdev)
 {
+	struct sas_ha_struct *sha = platform_get_drvdata(pdev);
+	struct hisi_hba *hisi_hba = sha->lldd_ha;
+
+	if (timer_pending(&hisi_hba->timer))
+		del_timer(&hisi_hba->timer);
+
 	return hisi_sas_remove(pdev);
 }
 
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index c611412a8de9..524a0c755ed7 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -9263,13 +9263,9 @@ static int hpsa_enter_performant_mode(struct ctlr_info *h, u32 trans_support)
 		access = SA5_ioaccel_mode1_access;
 		writel(10, &h->cfgtable->HostWrite.CoalIntDelay);
 		writel(4, &h->cfgtable->HostWrite.CoalIntCount);
-	} else {
-		if (trans_support & CFGTBL_Trans_io_accel2) {
+	} else
+		if (trans_support & CFGTBL_Trans_io_accel2)
 			access = SA5_ioaccel_mode2_access;
-			writel(10, &h->cfgtable->HostWrite.CoalIntDelay);
-			writel(4, &h->cfgtable->HostWrite.CoalIntCount);
-		}
-	}
 	writel(CFGTBL_ChangeReq, h->vaddr + SA5_DOORBELL);
 	if (hpsa_wait_for_mode_change_ack(h)) {
 		dev_err(&h->pdev->dev,
diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h
index 64e98295b707..bf6cdc106654 100644
--- a/drivers/scsi/hpsa.h
+++ b/drivers/scsi/hpsa.h
@@ -578,38 +578,38 @@ static unsigned long SA5_ioaccel_mode1_completed(struct ctlr_info *h, u8 q)
 }
 
 static struct access_method SA5_access = {
-	SA5_submit_command,
-	SA5_intr_mask,
-	SA5_intr_pending,
-	SA5_completed,
+	.submit_command = SA5_submit_command,
+	.set_intr_mask = SA5_intr_mask,
+	.intr_pending = SA5_intr_pending,
+	.command_completed = SA5_completed,
 };
 
 static struct access_method SA5_ioaccel_mode1_access = {
-	SA5_submit_command,
-	SA5_performant_intr_mask,
-	SA5_ioaccel_mode1_intr_pending,
-	SA5_ioaccel_mode1_completed,
+	.submit_command = SA5_submit_command,
+	.set_intr_mask = SA5_performant_intr_mask,
+	.intr_pending = SA5_ioaccel_mode1_intr_pending,
+	.command_completed = SA5_ioaccel_mode1_completed,
 };
 
 static struct access_method SA5_ioaccel_mode2_access = {
-	SA5_submit_command_ioaccel2,
-	SA5_performant_intr_mask,
-	SA5_performant_intr_pending,
-	SA5_performant_completed,
+	.submit_command = SA5_submit_command_ioaccel2,
+	.set_intr_mask = SA5_performant_intr_mask,
+	.intr_pending = SA5_performant_intr_pending,
+	.command_completed = SA5_performant_completed,
 };
 
 static struct access_method SA5_performant_access = {
-	SA5_submit_command,
-	SA5_performant_intr_mask,
-	SA5_performant_intr_pending,
-	SA5_performant_completed,
+	.submit_command = SA5_submit_command,
+	.set_intr_mask = SA5_performant_intr_mask,
+	.intr_pending = SA5_performant_intr_pending,
+	.command_completed = SA5_performant_completed,
 };
 
 static struct access_method SA5_performant_access_no_read = {
-	SA5_submit_command_no_read,
-	SA5_performant_intr_mask,
-	SA5_performant_intr_pending,
-	SA5_performant_completed,
+	.submit_command = SA5_submit_command_no_read,
+	.set_intr_mask = SA5_performant_intr_mask,
+	.intr_pending = SA5_performant_intr_pending,
+	.command_completed = SA5_performant_completed,
 };
 
 struct board_type {
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 8a20b4e86224..6593b073c524 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -727,7 +727,6 @@ struct lpfc_hba {
 	uint32_t cfg_fcp_io_channel;
 	uint32_t cfg_total_seg_cnt;
 	uint32_t cfg_sg_seg_cnt;
-	uint32_t cfg_prot_sg_seg_cnt;
 	uint32_t cfg_sg_dma_buf_size;
 	uint64_t cfg_soft_wwnn;
 	uint64_t cfg_soft_wwpn;
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index c84775562c65..50cf402dea29 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -2073,6 +2073,13 @@ lpfc_soft_wwn_enable_store(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 
 	phba->soft_wwn_enable = 1;
+
+	dev_printk(KERN_WARNING, &phba->pcidev->dev,
+		   "lpfc%d: soft_wwpn assignment has been enabled.\n",
+		   phba->brd_no);
+	dev_printk(KERN_WARNING, &phba->pcidev->dev,
+		   "  The soft_wwpn feature is not supported by Broadcom.");
+
 	return count;
 }
 static DEVICE_ATTR(lpfc_soft_wwn_enable, S_IWUSR, NULL,
@@ -2143,7 +2150,7 @@ lpfc_soft_wwpn_store(struct device *dev, struct device_attribute *attr,
 	phba->soft_wwn_enable = 0;
 
 	rc = lpfc_wwn_set(buf, cnt, wwpn);
-	if (!rc) {
+	if (rc) {
 		/* not able to set wwpn, unlock it */
 		phba->soft_wwn_enable = 1;
 		return rc;
@@ -2224,7 +2231,7 @@ lpfc_soft_wwnn_store(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 
 	rc = lpfc_wwn_set(buf, cnt, wwnn);
-	if (!rc) {
+	if (rc) {
 		/* Allow wwnn to be set many times, as long as the enable
 		 * is set. However, once the wwpn is set, everything locks.
 		 */
@@ -2435,7 +2442,8 @@ lpfc_oas_vpt_store(struct device *dev, struct device_attribute *attr,
 	else
 		phba->cfg_oas_flags &= ~OAS_FIND_ANY_VPORT;
 	phba->cfg_oas_flags &= ~OAS_LUN_VALID;
-	phba->cfg_oas_priority = phba->cfg_XLanePriority;
+	if (phba->cfg_oas_priority == 0)
+		phba->cfg_oas_priority = phba->cfg_XLanePriority;
 	phba->sli4_hba.oas_next_lun = FIND_FIRST_OAS_LUN;
 	return count;
 }
@@ -2561,7 +2569,7 @@ lpfc_oas_lun_state_set(struct lpfc_hba *phba, uint8_t vpt_wwpn[],
 			rc = -ENOMEM;
 	} else {
 		lpfc_disable_oas_lun(phba, (struct lpfc_name *)vpt_wwpn,
-				     (struct lpfc_name *)tgt_wwpn, lun);
+				     (struct lpfc_name *)tgt_wwpn, lun, pri);
 	}
 	return rc;
 
@@ -2585,7 +2593,8 @@ lpfc_oas_lun_state_set(struct lpfc_hba *phba, uint8_t vpt_wwpn[],
  */
 static uint64_t
 lpfc_oas_lun_get_next(struct lpfc_hba *phba, uint8_t vpt_wwpn[],
-		      uint8_t tgt_wwpn[], uint32_t *lun_status)
+		      uint8_t tgt_wwpn[], uint32_t *lun_status,
+		      uint32_t *lun_pri)
 {
 	uint64_t found_lun;
 
@@ -2598,7 +2607,7 @@ lpfc_oas_lun_get_next(struct lpfc_hba *phba, uint8_t vpt_wwpn[],
 				   &phba->sli4_hba.oas_next_lun,
 				   (struct lpfc_name *)vpt_wwpn,
 				   (struct lpfc_name *)tgt_wwpn,
-				   &found_lun, lun_status))
+				   &found_lun, lun_status, lun_pri))
 		return found_lun;
 	else
 		return NOT_OAS_ENABLED_LUN;
@@ -2670,7 +2679,8 @@ lpfc_oas_lun_show(struct device *dev, struct device_attribute *attr,
 
 	oas_lun = lpfc_oas_lun_get_next(phba, phba->cfg_oas_vpt_wwpn,
 					phba->cfg_oas_tgt_wwpn,
-					&phba->cfg_oas_lun_status);
+					&phba->cfg_oas_lun_status,
+					&phba->cfg_oas_priority);
 	if (oas_lun != NOT_OAS_ENABLED_LUN)
 		phba->cfg_oas_flags |= OAS_LUN_VALID;
 
@@ -2701,6 +2711,7 @@ lpfc_oas_lun_store(struct device *dev, struct device_attribute *attr,
 	struct Scsi_Host *shost = class_to_shost(dev);
 	struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba;
 	uint64_t scsi_lun;
+	uint32_t pri;
 	ssize_t rc;
 
 	if (!phba->cfg_fof)
@@ -2718,17 +2729,20 @@ lpfc_oas_lun_store(struct device *dev, struct device_attribute *attr,
 	if (sscanf(buf, "0x%llx", &scsi_lun) != 1)
 		return -EINVAL;
 
+	pri = phba->cfg_oas_priority;
+	if (pri == 0)
+		pri = phba->cfg_XLanePriority;
+
 	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 			"3372 Try to set vport 0x%llx target 0x%llx lun:0x%llx "
 			"priority 0x%x with oas state %d\n",
 			wwn_to_u64(phba->cfg_oas_vpt_wwpn),
 			wwn_to_u64(phba->cfg_oas_tgt_wwpn), scsi_lun,
-			phba->cfg_oas_priority, phba->cfg_oas_lun_state);
+			pri, phba->cfg_oas_lun_state);
 
 	rc = lpfc_oas_lun_state_change(phba, phba->cfg_oas_vpt_wwpn,
 				       phba->cfg_oas_tgt_wwpn, scsi_lun,
-				       phba->cfg_oas_lun_state,
-				       phba->cfg_oas_priority);
+				       phba->cfg_oas_lun_state, pri);
 	if (rc)
 		return rc;
 
@@ -4670,14 +4684,6 @@ LPFC_ATTR_R(sg_seg_cnt, LPFC_DEFAULT_SG_SEG_CNT, LPFC_DEFAULT_SG_SEG_CNT,
 	    LPFC_MAX_SG_SEG_CNT, "Max Scatter Gather Segment Count");
 
 /*
- * This parameter will be depricated, the driver cannot limit the
- * protection data s/g list.
- */
-LPFC_ATTR_R(prot_sg_seg_cnt, LPFC_DEFAULT_SG_SEG_CNT,
-	    LPFC_DEFAULT_SG_SEG_CNT, LPFC_MAX_SG_SEG_CNT,
-	    "Max Protection Scatter Gather Segment Count");
-
-/*
  * lpfc_enable_mds_diags: Enable MDS Diagnostics
  *       0  = MDS Diagnostics disabled (default)
  *       1  = MDS Diagnostics enabled
@@ -4766,7 +4772,6 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_sg_seg_cnt,
 	&dev_attr_lpfc_max_scsicmpl_time,
 	&dev_attr_lpfc_stat_data_ctrl,
-	&dev_attr_lpfc_prot_sg_seg_cnt,
 	&dev_attr_lpfc_aer_support,
 	&dev_attr_lpfc_aer_state_cleanup,
 	&dev_attr_lpfc_sriov_nr_virtfn,
@@ -5061,6 +5066,19 @@ lpfc_free_sysfs_attr(struct lpfc_vport *vport)
  */
 
 /**
+ * lpfc_get_host_symbolic_name - Copy symbolic name into the scsi host
+ * @shost: kernel scsi host pointer.
+ **/
+static void
+lpfc_get_host_symbolic_name(struct Scsi_Host *shost)
+{
+	struct lpfc_vport *vport = (struct lpfc_vport *)shost->hostdata;
+
+	lpfc_vport_symbolic_node_name(vport, fc_host_symbolic_name(shost),
+				      sizeof fc_host_symbolic_name(shost));
+}
+
+/**
  * lpfc_get_host_port_id - Copy the vport DID into the scsi host port id
  * @shost: kernel scsi host pointer.
  **/
@@ -5597,6 +5615,8 @@ struct fc_function_template lpfc_transport_functions = {
 	.show_host_supported_fc4s = 1,
 	.show_host_supported_speeds = 1,
 	.show_host_maxframe_size = 1,
+
+	.get_host_symbolic_name = lpfc_get_host_symbolic_name,
 	.show_host_symbolic_name = 1,
 
 	/* dynamic attributes the driver supports */
@@ -5664,6 +5684,8 @@ struct fc_function_template lpfc_vport_transport_functions = {
 	.show_host_supported_fc4s = 1,
 	.show_host_supported_speeds = 1,
 	.show_host_maxframe_size = 1,
+
+	.get_host_symbolic_name = lpfc_get_host_symbolic_name,
 	.show_host_symbolic_name = 1,
 
 	/* dynamic attributes the driver supports */
@@ -5768,7 +5790,6 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	phba->cfg_soft_wwnn = 0L;
 	phba->cfg_soft_wwpn = 0L;
 	lpfc_sg_seg_cnt_init(phba, lpfc_sg_seg_cnt);
-	lpfc_prot_sg_seg_cnt_init(phba, lpfc_prot_sg_seg_cnt);
 	lpfc_hba_queue_depth_init(phba, lpfc_hba_queue_depth);
 	lpfc_hba_log_verbose_init(phba, lpfc_log_verbose);
 	lpfc_aer_support_init(phba, lpfc_aer_support);
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 15d2bfdf582d..309643a2c55c 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -480,7 +480,7 @@ void lpfc_sli4_offline_eratt(struct lpfc_hba *);
 struct lpfc_device_data *lpfc_create_device_data(struct lpfc_hba *,
 						struct lpfc_name *,
 						struct lpfc_name *,
-						uint64_t, bool);
+						uint64_t, uint32_t,  bool);
 void lpfc_delete_device_data(struct lpfc_hba *, struct lpfc_device_data*);
 struct lpfc_device_data *__lpfc_get_device_data(struct lpfc_hba *,
 					struct list_head *list,
@@ -489,9 +489,10 @@ struct lpfc_device_data *__lpfc_get_device_data(struct lpfc_hba *,
 bool lpfc_enable_oas_lun(struct lpfc_hba *, struct lpfc_name *,
 			 struct lpfc_name *, uint64_t, uint8_t);
 bool lpfc_disable_oas_lun(struct lpfc_hba *, struct lpfc_name *,
-			  struct lpfc_name *, uint64_t);
+			  struct lpfc_name *, uint64_t, uint8_t);
 bool lpfc_find_next_oas_lun(struct lpfc_hba *, struct lpfc_name *,
 			    struct lpfc_name *, uint64_t *, struct lpfc_name *,
-			    struct lpfc_name *, uint64_t *, uint32_t *);
+			    struct lpfc_name *, uint64_t *,
+			    uint32_t *, uint32_t *);
 int lpfc_sli4_dump_page_a0(struct lpfc_hba *phba, struct lpfcMboxq *mbox);
 void lpfc_mbx_cmpl_rdp_page_a0(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb);
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 63bef4566548..3a1f1a2a2b55 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1999,6 +1999,9 @@ lpfc_issue_els_plogi(struct lpfc_vport *vport, uint32_t did, uint8_t retry)
 	if (sp->cmn.fcphHigh < FC_PH3)
 		sp->cmn.fcphHigh = FC_PH3;
 
+	sp->cmn.valid_vendor_ver_level = 0;
+	memset(sp->vendorVersion, 0, sizeof(sp->vendorVersion));
+
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
 		"Issue PLOGI:     did:x%x",
 		did, 0, 0);
@@ -3990,6 +3993,9 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 		} else {
 			memcpy(pcmd, &vport->fc_sparam,
 			       sizeof(struct serv_parm));
+
+			sp->cmn.valid_vendor_ver_level = 0;
+			memset(sp->vendorVersion, 0, sizeof(sp->vendorVersion));
 		}
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
@@ -8851,8 +8857,7 @@ lpfc_cmpl_fabric_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 {
 	struct ls_rjt stat;
 
-	if ((cmdiocb->iocb_flag & LPFC_IO_FABRIC) != LPFC_IO_FABRIC)
-		BUG();
+	BUG_ON((cmdiocb->iocb_flag & LPFC_IO_FABRIC) != LPFC_IO_FABRIC);
 
 	switch (rspiocb->iocb.ulpStatus) {
 		case IOSTAT_NPORT_RJT:
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index 822654322e67..3b970d370600 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -360,6 +360,12 @@ struct csp {
  * Word 1 Bit 30 in PLOGI request is random offset
  */
 #define virtual_fabric_support randomOffset /* Word 1, bit 30 */
+/*
+ * Word 1 Bit 29 in common service parameter is overloaded.
+ * Word 1 Bit 29 in FLOGI response is multiple NPort assignment
+ * Word 1 Bit 29 in FLOGI/PLOGI request is Valid Vendor Version Level
+ */
+#define valid_vendor_ver_level response_multiple_NPort /* Word 1, bit 29 */
 #ifdef __BIG_ENDIAN_BITFIELD
 	uint16_t request_multiple_Nport:1;	/* FC Word 1, bit 31 */
 	uint16_t randomOffset:1;	/* FC Word 1, bit 30 */
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index ad350d969bdc..19d349fc889f 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -5452,7 +5452,9 @@ lpfc_slave_alloc(struct scsi_device *sdev)
 			device_data = lpfc_create_device_data(phba,
 							&vport->fc_portname,
 							&target_wwpn,
-							sdev->lun, true);
+							sdev->lun,
+							phba->cfg_XLanePriority,
+							true);
 			if (!device_data)
 				return -ENOMEM;
 			spin_lock_irqsave(&phba->devicelock, flags);
@@ -5587,7 +5589,7 @@ lpfc_slave_destroy(struct scsi_device *sdev)
 struct lpfc_device_data*
 lpfc_create_device_data(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 			struct lpfc_name *target_wwpn, uint64_t lun,
-			bool atomic_create)
+			uint32_t pri, bool atomic_create)
 {
 
 	struct lpfc_device_data *lun_info;
@@ -5614,7 +5616,7 @@ lpfc_create_device_data(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 	       sizeof(struct lpfc_name));
 	lun_info->device_id.lun = lun;
 	lun_info->oas_enabled = false;
-	lun_info->priority = phba->cfg_XLanePriority;
+	lun_info->priority = pri;
 	lun_info->available = false;
 	return lun_info;
 }
@@ -5716,7 +5718,8 @@ lpfc_find_next_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 		       struct lpfc_name *found_vport_wwpn,
 		       struct lpfc_name *found_target_wwpn,
 		       uint64_t *found_lun,
-		       uint32_t *found_lun_status)
+		       uint32_t *found_lun_status,
+		       uint32_t *found_lun_pri)
 {
 
 	unsigned long flags;
@@ -5763,6 +5766,7 @@ lpfc_find_next_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 						OAS_LUN_STATUS_EXISTS;
 				else
 					*found_lun_status = 0;
+				*found_lun_pri = lun_info->priority;
 				if (phba->cfg_oas_flags & OAS_FIND_ANY_VPORT)
 					memset(vport_wwpn, 0x0,
 					       sizeof(struct lpfc_name));
@@ -5824,13 +5828,14 @@ lpfc_enable_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 	if (lun_info) {
 		if (!lun_info->oas_enabled)
 			lun_info->oas_enabled = true;
+		lun_info->priority = pri;
 		spin_unlock_irqrestore(&phba->devicelock, flags);
 		return true;
 	}
 
 	/* Create an lun info structure and add to list of luns */
 	lun_info = lpfc_create_device_data(phba, vport_wwpn, target_wwpn, lun,
-					   false);
+					   pri, false);
 	if (lun_info) {
 		lun_info->oas_enabled = true;
 		lun_info->priority = pri;
@@ -5864,7 +5869,7 @@ lpfc_enable_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
  **/
 bool
 lpfc_disable_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
-		     struct lpfc_name *target_wwpn, uint64_t lun)
+		     struct lpfc_name *target_wwpn, uint64_t lun, uint8_t pri)
 {
 
 	struct lpfc_device_data *lun_info;
@@ -5882,6 +5887,7 @@ lpfc_disable_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 					  target_wwpn, lun);
 	if (lun_info) {
 		lun_info->oas_enabled = false;
+		lun_info->priority = pri;
 		if (!lun_info->available)
 			lpfc_delete_device_data(phba, lun_info);
 		spin_unlock_irqrestore(&phba->devicelock, flags);
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index a78a3df68f67..d977a472f89f 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -120,6 +120,8 @@ lpfc_sli4_wq_put(struct lpfc_queue *q, union lpfc_wqe *wqe)
 	if (q->phba->sli3_options & LPFC_SLI4_PHWQ_ENABLED)
 		bf_set(wqe_wqid, &wqe->generic.wqe_com, q->queue_id);
 	lpfc_sli_pcimem_bcopy(wqe, temp_wqe, q->entry_size);
+	/* ensure WQE bcopy flushed before doorbell write */
+	wmb();
 
 	/* Update the host index before invoking device */
 	host_index = q->host_index;
@@ -6313,7 +6315,8 @@ lpfc_set_host_data(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox)
 			 LPFC_SLI4_MBX_EMBED);
 
 	mbox->u.mqe.un.set_host_data.param_id = LPFC_SET_HOST_OS_DRIVER_VERSION;
-	mbox->u.mqe.un.set_host_data.param_len = 8;
+	mbox->u.mqe.un.set_host_data.param_len =
+					LPFC_HOST_OS_DRIVER_VERSION_SIZE;
 	snprintf(mbox->u.mqe.un.set_host_data.data,
 		 LPFC_HOST_OS_DRIVER_VERSION_SIZE,
 		 "Linux %s v"LPFC_DRIVER_VERSION,
@@ -10035,6 +10038,7 @@ lpfc_sli_abort_iotag_issue(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		iabt->ulpCommand = CMD_CLOSE_XRI_CN;
 
 	abtsiocbp->iocb_cmpl = lpfc_sli_abort_els_cmpl;
+	abtsiocbp->vport = vport;
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI,
 			 "0339 Abort xri x%x, original iotag x%x, "
@@ -17226,7 +17230,8 @@ lpfc_drain_txq(struct lpfc_hba *phba)
 	unsigned long iflags = 0;
 	char *fail_msg = NULL;
 	struct lpfc_sglq *sglq;
-	union lpfc_wqe wqe;
+	union lpfc_wqe128 wqe128;
+	union lpfc_wqe *wqe = (union lpfc_wqe *) &wqe128;
 	uint32_t txq_cnt = 0;
 
 	spin_lock_irqsave(&pring->ring_lock, iflags);
@@ -17265,9 +17270,9 @@ lpfc_drain_txq(struct lpfc_hba *phba)
 		piocbq->sli4_xritag = sglq->sli4_xritag;
 		if (NO_XRI == lpfc_sli4_bpl2sgl(phba, piocbq, sglq))
 			fail_msg = "to convert bpl to sgl";
-		else if (lpfc_sli4_iocb2wqe(phba, piocbq, &wqe))
+		else if (lpfc_sli4_iocb2wqe(phba, piocbq, wqe))
 			fail_msg = "to convert iocb to wqe";
-		else if (lpfc_sli4_wq_put(phba->sli4_hba.els_wq, &wqe))
+		else if (lpfc_sli4_wq_put(phba->sli4_hba.els_wq, wqe))
 			fail_msg = " - Wq is full";
 		else
 			lpfc_sli_ringtxcmpl_put(phba, pring, piocbq);
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 50bfc43ebcb0..0ee0623a354c 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -18,7 +18,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "11.2.0.2"
+#define LPFC_DRIVER_VERSION "11.2.0.4"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index c27f4b724547..e18bbc66e83b 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -537,6 +537,12 @@ enable_vport(struct fc_vport *fc_vport)
 
 	spin_lock_irq(shost->host_lock);
 	vport->load_flag |= FC_LOADING;
+	if (vport->fc_flag & FC_VPORT_NEEDS_INIT_VPI) {
+		spin_unlock_irq(shost->host_lock);
+		lpfc_issue_init_vpi(vport);
+		goto out;
+	}
+
 	vport->fc_flag |= FC_VPORT_NEEDS_REG_VPI;
 	spin_unlock_irq(shost->host_lock);
 
@@ -557,6 +563,8 @@ enable_vport(struct fc_vport *fc_vport)
 	} else {
 		lpfc_vport_set_state(vport, FC_VPORT_FAILED);
 	}
+
+out:
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_VPORT,
 			 "1827 Vport Enabled.\n");
 	return VPORT_OK;
diff --git a/drivers/scsi/mac_scsi.c b/drivers/scsi/mac_scsi.c
index ccb68d12692c..196acc79714b 100644
--- a/drivers/scsi/mac_scsi.c
+++ b/drivers/scsi/mac_scsi.c
@@ -154,7 +154,7 @@ __asm__ __volatile__					\
 static inline int macscsi_pread(struct NCR5380_hostdata *hostdata,
                                 unsigned char *dst, int len)
 {
-	unsigned char *s = hostdata->pdma_io + (INPUT_DATA_REG << 4);
+	u8 __iomem *s = hostdata->pdma_io + (INPUT_DATA_REG << 4);
 	unsigned char *d = dst;
 	int n = len;
 	int transferred;
@@ -257,7 +257,7 @@ static inline int macscsi_pwrite(struct NCR5380_hostdata *hostdata,
                                  unsigned char *src, int len)
 {
 	unsigned char *s = src;
-	unsigned char *d = hostdata->pdma_io + (OUTPUT_DATA_REG << 4);
+	u8 __iomem *d = hostdata->pdma_io + (OUTPUT_DATA_REG << 4);
 	int n = len;
 	int transferred;
 
@@ -381,10 +381,10 @@ static int __init mac_scsi_probe(struct platform_device *pdev)
 
 	hostdata = shost_priv(instance);
 	hostdata->base = pio_mem->start;
-	hostdata->io = (void *)pio_mem->start;
+	hostdata->io = (u8 __iomem *)pio_mem->start;
 
 	if (pdma_mem && setup_use_pdma)
-		hostdata->pdma_io = (void *)pdma_mem->start;
+		hostdata->pdma_io = (u8 __iomem *)pdma_mem->start;
 	else
 		host_flags |= FLAG_NO_PSEUDO_DMA;
 
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index fdd519c1dd57..ba9fbb71eb35 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -35,8 +35,8 @@
 /*
  * MegaRAID SAS Driver meta data
  */
-#define MEGASAS_VERSION				"06.812.07.00-rc1"
-#define MEGASAS_RELDATE				"August 22, 2016"
+#define MEGASAS_VERSION				"07.700.00.00-rc1"
+#define MEGASAS_RELDATE				"November 29, 2016"
 
 /*
  * Device IDs
@@ -56,6 +56,11 @@
 #define PCI_DEVICE_ID_LSI_INTRUDER_24		0x00cf
 #define PCI_DEVICE_ID_LSI_CUTLASS_52		0x0052
 #define PCI_DEVICE_ID_LSI_CUTLASS_53		0x0053
+#define PCI_DEVICE_ID_LSI_VENTURA		    0x0014
+#define PCI_DEVICE_ID_LSI_HARPOON		    0x0016
+#define PCI_DEVICE_ID_LSI_TOMCAT		    0x0017
+#define PCI_DEVICE_ID_LSI_VENTURA_4PORT		0x001B
+#define PCI_DEVICE_ID_LSI_CRUSADER_4PORT	0x001C
 
 /*
  * Intel HBA SSDIDs
@@ -100,7 +105,7 @@
  */
 
 /*
- * MFI stands for  MegaRAID SAS FW Interface. This is just a moniker for 
+ * MFI stands for  MegaRAID SAS FW Interface. This is just a moniker for
  * protocol between the software and firmware. Commands are issued using
  * "message frames"
  */
@@ -1312,7 +1317,55 @@ struct megasas_ctrl_info {
 #endif
 	} adapterOperations3;
 
-	u8          pad[0x800-0x7EC];
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u8 reserved:7;
+	/* Indicates whether the CPLD image is part of
+	 *  the package and stored in flash
+	 */
+	u8 cpld_in_flash:1;
+#else
+	u8 cpld_in_flash:1;
+	u8 reserved:7;
+#endif
+	u8 reserved1[3];
+	/* Null terminated string. Has the version
+	 *  information if cpld_in_flash = FALSE
+	 */
+	u8 userCodeDefinition[12];
+	} cpld;  /* Valid only if upgradableCPLD is TRUE */
+
+	struct {
+	#if defined(__BIG_ENDIAN_BITFIELD)
+		u16 reserved:8;
+		u16 fw_swaps_bbu_vpd_info:1;
+		u16 support_pd_map_target_id:1;
+		u16 support_ses_ctrl_in_multipathcfg:1;
+		u16 image_upload_supported:1;
+		u16 support_encrypted_mfc:1;
+		u16 supported_enc_algo:1;
+		u16 support_ibutton_less:1;
+		u16 ctrl_info_ext_supported:1;
+	#else
+
+		u16 ctrl_info_ext_supported:1;
+		u16 support_ibutton_less:1;
+		u16 supported_enc_algo:1;
+		u16 support_encrypted_mfc:1;
+		u16 image_upload_supported:1;
+		/* FW supports LUN based association and target port based */
+		u16 support_ses_ctrl_in_multipathcfg:1;
+		/* association for the SES device connected in multipath mode */
+		/* FW defines Jbod target Id within MR_PD_CFG_SEQ */
+		u16 support_pd_map_target_id:1;
+		/* FW swaps relevant fields in MR_BBU_VPD_INFO_FIXED to
+		 *  provide the data in little endian order
+		 */
+		u16 fw_swaps_bbu_vpd_info:1;
+		u16 reserved:8;
+	#endif
+		} adapter_operations4;
+	u8 pad[0x800-0x7FE]; /* 0x7FE pad to 2K for expansion */
 } __packed;
 
 /*
@@ -1424,18 +1477,26 @@ enum FW_BOOT_CONTEXT {
 #define MFI_1068_FW_HANDSHAKE_OFFSET		0x64
 #define MFI_1068_FW_READY			0xDDDD0000
 
+#define MEGASAS_RAID1_FAST_PATH_STATUS_CHECK_INTERVAL HZ
+
 #define MR_MAX_REPLY_QUEUES_OFFSET              0X0000001F
 #define MR_MAX_REPLY_QUEUES_EXT_OFFSET          0X003FC000
 #define MR_MAX_REPLY_QUEUES_EXT_OFFSET_SHIFT    14
 #define MR_MAX_MSIX_REG_ARRAY                   16
 #define MR_RDPQ_MODE_OFFSET			0X00800000
+
+#define MR_MAX_RAID_MAP_SIZE_OFFSET_SHIFT	16
+#define MR_MAX_RAID_MAP_SIZE_MASK		0x1FF
+#define MR_MIN_MAP_SIZE				0x10000
+/* 64k */
+
 #define MR_CAN_HANDLE_SYNC_CACHE_OFFSET		0X01000000
 
 /*
 * register set for both 1068 and 1078 controllers
 * structure extended for 1078 registers
 */
- 
+
 struct megasas_register_set {
 	u32	doorbell;                       /*0000h*/
 	u32	fusion_seq_offset;		/*0004h*/
@@ -1478,7 +1539,7 @@ struct megasas_register_set {
 
 	u32 	inbound_high_queue_port ;	/*00C4h*/
 
-	u32 	reserved_5;			/*00C8h*/
+	u32 inbound_single_queue_port;	/*00C8h*/
 	u32	res_6[11];			/*CCh*/
 	u32	host_diag;
 	u32	seq_offset;
@@ -1544,33 +1605,35 @@ union megasas_sgl_frame {
 typedef union _MFI_CAPABILITIES {
 	struct {
 #if   defined(__BIG_ENDIAN_BITFIELD)
-		u32     reserved:20;
-		u32     support_qd_throttling:1;
-		u32     support_fp_rlbypass:1;
-		u32     support_vfid_in_ioframe:1;
-		u32     support_ext_io_size:1;
-		u32	support_ext_queue_depth:1;
-		u32     security_protocol_cmds_fw:1;
-		u32     support_core_affinity:1;
-		u32     support_ndrive_r1_lb:1;
-		u32	support_max_255lds:1;
-		u32	support_fastpath_wb:1;
-		u32     support_additional_msix:1;
-		u32     support_fp_remote_lun:1;
+	u32     reserved:19;
+	u32 support_pd_map_target_id:1;
+	u32     support_qd_throttling:1;
+	u32     support_fp_rlbypass:1;
+	u32     support_vfid_in_ioframe:1;
+	u32     support_ext_io_size:1;
+	u32		support_ext_queue_depth:1;
+	u32     security_protocol_cmds_fw:1;
+	u32     support_core_affinity:1;
+	u32     support_ndrive_r1_lb:1;
+	u32		support_max_255lds:1;
+	u32		support_fastpath_wb:1;
+	u32     support_additional_msix:1;
+	u32     support_fp_remote_lun:1;
 #else
-		u32     support_fp_remote_lun:1;
-		u32     support_additional_msix:1;
-		u32	support_fastpath_wb:1;
-		u32	support_max_255lds:1;
-		u32     support_ndrive_r1_lb:1;
-		u32     support_core_affinity:1;
-		u32     security_protocol_cmds_fw:1;
-		u32	support_ext_queue_depth:1;
-		u32     support_ext_io_size:1;
-		u32     support_vfid_in_ioframe:1;
-		u32     support_fp_rlbypass:1;
-		u32     support_qd_throttling:1;
-		u32     reserved:20;
+	u32     support_fp_remote_lun:1;
+	u32     support_additional_msix:1;
+	u32		support_fastpath_wb:1;
+	u32		support_max_255lds:1;
+	u32     support_ndrive_r1_lb:1;
+	u32     support_core_affinity:1;
+	u32     security_protocol_cmds_fw:1;
+	u32		support_ext_queue_depth:1;
+	u32     support_ext_io_size:1;
+	u32     support_vfid_in_ioframe:1;
+	u32     support_fp_rlbypass:1;
+	u32     support_qd_throttling:1;
+	u32	support_pd_map_target_id:1;
+	u32     reserved:19;
 #endif
 	} mfi_capabilities;
 	__le32		reg;
@@ -2039,6 +2102,7 @@ struct megasas_instance {
 	u32 crash_dump_drv_support;
 	u32 crash_dump_app_support;
 	u32 secure_jbod_support;
+	u32 support_morethan256jbod; /* FW support for more than 256 PD/JBOD */
 	bool use_seqnum_jbod_fp;   /* Added for PD sequence */
 	spinlock_t crashdump_lock;
 
@@ -2051,6 +2115,7 @@ struct megasas_instance {
 
 	u16 max_num_sge;
 	u16 max_fw_cmds;
+	u16 max_mpt_cmds;
 	u16 max_mfi_cmds;
 	u16 max_scsi_cmds;
 	u16 ldio_threshold;
@@ -2065,6 +2130,7 @@ struct megasas_instance {
 	/* used to sync fire the cmd to fw */
 	spinlock_t hba_lock;
 	/* used to synch producer, consumer ptrs in dpc */
+	spinlock_t stream_lock;
 	spinlock_t completion_lock;
 	struct dma_pool *frame_dma_pool;
 	struct dma_pool *sense_dma_pool;
@@ -2088,6 +2154,10 @@ struct megasas_instance {
 	atomic_t ldio_outstanding;
 	atomic_t fw_reset_no_pci_access;
 
+	atomic64_t bytes_wrote; /* used for raid1 fast path enable or disable */
+	atomic_t r1_write_fp_capable;
+
+
 	struct megasas_instance_template *instancet;
 	struct tasklet_struct isr_tasklet;
 	struct work_struct work_init;
@@ -2129,6 +2199,7 @@ struct megasas_instance {
 	long reset_flags;
 	struct mutex reset_mutex;
 	struct timer_list sriov_heartbeat_timer;
+	struct timer_list r1_fp_hold_timer;
 	char skip_heartbeat_timer_del;
 	u8 requestorId;
 	char PlasmaFW111;
@@ -2142,6 +2213,10 @@ struct megasas_instance {
 	u8 is_rdpq;
 	bool dev_handle;
 	bool fw_sync_cache_support;
+	bool is_ventura;
+	bool msix_combined;
+	u16 max_raid_mapsize;
+	u64 pci_threshold_bandwidth; /* used to control the fp writes */
 };
 struct MR_LD_VF_MAP {
 	u32 size;
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index d5cf15eb8c5e..70891a76ca86 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -155,6 +155,12 @@ static struct pci_device_id megasas_pci_table[] = {
 	/* Intruder 24 port*/
 	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_CUTLASS_52)},
 	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_CUTLASS_53)},
+	/* VENTURA */
+	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_VENTURA)},
+	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_HARPOON)},
+	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_TOMCAT)},
+	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_VENTURA_4PORT)},
+	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_CRUSADER_4PORT)},
 	{}
 };
 
@@ -1934,6 +1940,9 @@ void megaraid_sas_kill_hba(struct megasas_instance *instance)
 	}
 	/* Complete outstanding ioctls when adapter is killed */
 	megasas_complete_outstanding_ioctls(instance);
+	if (instance->is_ventura)
+		del_timer_sync(&instance->r1_fp_hold_timer);
+
 }
 
  /**
@@ -2432,6 +2441,24 @@ void megasas_sriov_heartbeat_handler(unsigned long instance_addr)
 	}
 }
 
+/*Handler for disabling/enabling raid 1 fast paths*/
+void megasas_change_r1_fp_status(unsigned long instance_addr)
+{
+	struct megasas_instance *instance =
+			(struct megasas_instance *)instance_addr;
+	if (atomic64_read(&instance->bytes_wrote) >=
+					instance->pci_threshold_bandwidth) {
+
+		atomic64_set(&instance->bytes_wrote, 0);
+		atomic_set(&instance->r1_write_fp_capable, 0);
+	} else {
+		atomic64_set(&instance->bytes_wrote, 0);
+		atomic_set(&instance->r1_write_fp_capable, 1);
+	}
+	mod_timer(&instance->r1_fp_hold_timer,
+	 jiffies + MEGASAS_RAID1_FAST_PATH_STATUS_CHECK_INTERVAL);
+}
+
 /**
  * megasas_wait_for_outstanding -	Wait for all outstanding cmds
  * @instance:				Adapter soft state
@@ -4418,8 +4445,7 @@ megasas_ld_list_query(struct megasas_instance *instance, u8 query_type)
 static void megasas_update_ext_vd_details(struct megasas_instance *instance)
 {
 	struct fusion_context *fusion;
-	u32 old_map_sz;
-	u32 new_map_sz;
+	u32 ventura_map_sz = 0;
 
 	fusion = instance->ctrl_context;
 	/* For MFI based controllers return dummy success */
@@ -4449,21 +4475,38 @@ static void megasas_update_ext_vd_details(struct megasas_instance *instance)
 		instance->supportmax256vd ? "Extended VD(240 VD)firmware" :
 		"Legacy(64 VD) firmware");
 
-	old_map_sz = sizeof(struct MR_FW_RAID_MAP) +
-				(sizeof(struct MR_LD_SPAN_MAP) *
-				(instance->fw_supported_vd_count - 1));
-	new_map_sz = sizeof(struct MR_FW_RAID_MAP_EXT);
-	fusion->drv_map_sz = sizeof(struct MR_DRV_RAID_MAP) +
-				(sizeof(struct MR_LD_SPAN_MAP) *
-				(instance->drv_supported_vd_count - 1));
-
-	fusion->max_map_sz = max(old_map_sz, new_map_sz);
+	if (instance->max_raid_mapsize) {
+		ventura_map_sz = instance->max_raid_mapsize *
+						MR_MIN_MAP_SIZE; /* 64k */
+		fusion->current_map_sz = ventura_map_sz;
+		fusion->max_map_sz = ventura_map_sz;
+	} else {
+		fusion->old_map_sz =  sizeof(struct MR_FW_RAID_MAP) +
+					(sizeof(struct MR_LD_SPAN_MAP) *
+					(instance->fw_supported_vd_count - 1));
+		fusion->new_map_sz =  sizeof(struct MR_FW_RAID_MAP_EXT);
 
+		fusion->max_map_sz =
+			max(fusion->old_map_sz, fusion->new_map_sz);
 
-	if (instance->supportmax256vd)
-		fusion->current_map_sz = new_map_sz;
-	else
-		fusion->current_map_sz = old_map_sz;
+		if (instance->supportmax256vd)
+			fusion->current_map_sz = fusion->new_map_sz;
+		else
+			fusion->current_map_sz = fusion->old_map_sz;
+	}
+	/* irrespective of FW raid maps, driver raid map is constant */
+	fusion->drv_map_sz = sizeof(struct MR_DRV_RAID_MAP_ALL);
+
+#if VD_EXT_DEBUG
+	dev_info(&instance->pdev->dev, "instance->max_raid_mapsize 0x%x\n ",
+		instance->max_raid_mapsize);
+	dev_info(&instance->pdev->dev, "new_map_sz = 0x%x, old_map_sz = 0x%x\n",
+		fusion->new_map_sz, fusion->old_map_sz);
+	dev_info(&instance->pdev->dev, "ventura_map_sz = 0x%x, current_map_sz = 0x%x\n",
+		ventura_map_sz, fusion->current_map_sz);
+	dev_info(&instance->pdev->dev, "fusion->drv_map_sz =0x%x, size of driver raid map 0x%lx\n",
+		fusion->drv_map_sz, sizeof(struct MR_DRV_RAID_MAP_ALL));
+#endif
 }
 
 /**
@@ -4533,6 +4576,7 @@ megasas_get_ctrl_info(struct megasas_instance *instance)
 		le32_to_cpus((u32 *)&ctrl_info->properties.OnOffProperties);
 		le32_to_cpus((u32 *)&ctrl_info->adapterOperations2);
 		le32_to_cpus((u32 *)&ctrl_info->adapterOperations3);
+		le16_to_cpus((u16 *)&ctrl_info->adapter_operations4);
 
 		/* Update the latest Ext VD info.
 		 * From Init path, store current firmware details.
@@ -4542,6 +4586,8 @@ megasas_get_ctrl_info(struct megasas_instance *instance)
 		megasas_update_ext_vd_details(instance);
 		instance->use_seqnum_jbod_fp =
 			ctrl_info->adapterOperations3.useSeqNumJbodFP;
+		instance->support_morethan256jbod =
+			ctrl_info->adapter_operations4.support_pd_map_target_id;
 
 		/*Check whether controller is iMR or MR */
 		instance->is_imr = (ctrl_info->memory_size ? 0 : 1);
@@ -4990,12 +5036,12 @@ static int megasas_init_fw(struct megasas_instance *instance)
 {
 	u32 max_sectors_1;
 	u32 max_sectors_2;
-	u32 tmp_sectors, msix_enable, scratch_pad_2;
+	u32 tmp_sectors, msix_enable, scratch_pad_2, scratch_pad_3;
 	resource_size_t base_addr;
 	struct megasas_register_set __iomem *reg_set;
 	struct megasas_ctrl_info *ctrl_info = NULL;
 	unsigned long bar_list;
-	int i, loop, fw_msix_count = 0;
+	int i, j, loop, fw_msix_count = 0;
 	struct IOV_111 *iovPtr;
 	struct fusion_context *fusion;
 
@@ -5020,34 +5066,29 @@ static int megasas_init_fw(struct megasas_instance *instance)
 
 	reg_set = instance->reg_set;
 
-	switch (instance->pdev->device) {
-	case PCI_DEVICE_ID_LSI_FUSION:
-	case PCI_DEVICE_ID_LSI_PLASMA:
-	case PCI_DEVICE_ID_LSI_INVADER:
-	case PCI_DEVICE_ID_LSI_FURY:
-	case PCI_DEVICE_ID_LSI_INTRUDER:
-	case PCI_DEVICE_ID_LSI_INTRUDER_24:
-	case PCI_DEVICE_ID_LSI_CUTLASS_52:
-	case PCI_DEVICE_ID_LSI_CUTLASS_53:
+	if (fusion)
 		instance->instancet = &megasas_instance_template_fusion;
-		break;
-	case PCI_DEVICE_ID_LSI_SAS1078R:
-	case PCI_DEVICE_ID_LSI_SAS1078DE:
-		instance->instancet = &megasas_instance_template_ppc;
-		break;
-	case PCI_DEVICE_ID_LSI_SAS1078GEN2:
-	case PCI_DEVICE_ID_LSI_SAS0079GEN2:
-		instance->instancet = &megasas_instance_template_gen2;
-		break;
-	case PCI_DEVICE_ID_LSI_SAS0073SKINNY:
-	case PCI_DEVICE_ID_LSI_SAS0071SKINNY:
-		instance->instancet = &megasas_instance_template_skinny;
-		break;
-	case PCI_DEVICE_ID_LSI_SAS1064R:
-	case PCI_DEVICE_ID_DELL_PERC5:
-	default:
-		instance->instancet = &megasas_instance_template_xscale;
-		break;
+	else {
+		switch (instance->pdev->device) {
+		case PCI_DEVICE_ID_LSI_SAS1078R:
+		case PCI_DEVICE_ID_LSI_SAS1078DE:
+			instance->instancet = &megasas_instance_template_ppc;
+			break;
+		case PCI_DEVICE_ID_LSI_SAS1078GEN2:
+		case PCI_DEVICE_ID_LSI_SAS0079GEN2:
+			instance->instancet = &megasas_instance_template_gen2;
+			break;
+		case PCI_DEVICE_ID_LSI_SAS0073SKINNY:
+		case PCI_DEVICE_ID_LSI_SAS0071SKINNY:
+			instance->instancet = &megasas_instance_template_skinny;
+			break;
+		case PCI_DEVICE_ID_LSI_SAS1064R:
+		case PCI_DEVICE_ID_DELL_PERC5:
+		default:
+			instance->instancet = &megasas_instance_template_xscale;
+			instance->pd_list_not_supported = 1;
+			break;
+		}
 	}
 
 	if (megasas_transition_to_ready(instance, 0)) {
@@ -5066,13 +5107,17 @@ static int megasas_init_fw(struct megasas_instance *instance)
 			goto fail_ready_state;
 	}
 
-	/*
-	 * MSI-X host index 0 is common for all adapter.
-	 * It is used for all MPT based Adapters.
-	 */
-	instance->reply_post_host_index_addr[0] =
-		(u32 __iomem *)((u8 __iomem *)instance->reg_set +
-		MPI2_REPLY_POST_HOST_INDEX_OFFSET);
+	if (instance->is_ventura) {
+		scratch_pad_3 =
+			readl(&instance->reg_set->outbound_scratch_pad_3);
+#if VD_EXT_DEBUG
+		dev_info(&instance->pdev->dev, "scratch_pad3 0x%x\n",
+			scratch_pad_3);
+#endif
+		instance->max_raid_mapsize = ((scratch_pad_3 >>
+			MR_MAX_RAID_MAP_SIZE_OFFSET_SHIFT) &
+			MR_MAX_RAID_MAP_SIZE_MASK);
+	}
 
 	/* Check if MSI-X is supported while in ready state */
 	msix_enable = (instance->instancet->read_fw_status_reg(reg_set) &
@@ -5092,6 +5137,9 @@ static int megasas_init_fw(struct megasas_instance *instance)
 				instance->msix_vectors = ((scratch_pad_2
 					& MR_MAX_REPLY_QUEUES_EXT_OFFSET)
 					>> MR_MAX_REPLY_QUEUES_EXT_OFFSET_SHIFT) + 1;
+				if (instance->msix_vectors > 16)
+					instance->msix_combined = true;
+
 				if (rdpq_enable)
 					instance->is_rdpq = (scratch_pad_2 & MR_RDPQ_MODE_OFFSET) ?
 								1 : 0;
@@ -5125,6 +5173,20 @@ static int megasas_init_fw(struct megasas_instance *instance)
 		else
 			instance->msix_vectors = 0;
 	}
+	/*
+	 * MSI-X host index 0 is common for all adapter.
+	 * It is used for all MPT based Adapters.
+	 */
+	if (instance->msix_combined) {
+		instance->reply_post_host_index_addr[0] =
+				(u32 *)((u8 *)instance->reg_set +
+				MPI2_SUP_REPLY_POST_HOST_INDEX_OFFSET);
+	} else {
+		instance->reply_post_host_index_addr[0] =
+			(u32 *)((u8 *)instance->reg_set +
+			MPI2_REPLY_POST_HOST_INDEX_OFFSET);
+	}
+
 	i = pci_alloc_irq_vectors(instance->pdev, 1, 1, PCI_IRQ_LEGACY);
 	if (i < 0)
 		goto fail_setup_irqs;
@@ -5177,6 +5239,36 @@ static int megasas_init_fw(struct megasas_instance *instance)
 	}
 
 	memset(instance->ld_ids, 0xff, MEGASAS_MAX_LD_IDS);
+
+	/* stream detection initialization */
+	if (instance->is_ventura) {
+		fusion->stream_detect_by_ld =
+		kzalloc(sizeof(struct LD_STREAM_DETECT *)
+		* MAX_LOGICAL_DRIVES_EXT,
+		GFP_KERNEL);
+		if (!fusion->stream_detect_by_ld) {
+			dev_err(&instance->pdev->dev,
+					"unable to allocate stream detection for pool of LDs\n");
+			goto fail_get_ld_pd_list;
+		}
+		for (i = 0; i < MAX_LOGICAL_DRIVES_EXT; ++i) {
+			fusion->stream_detect_by_ld[i] =
+				kmalloc(sizeof(struct LD_STREAM_DETECT),
+				GFP_KERNEL);
+			if (!fusion->stream_detect_by_ld[i]) {
+				dev_err(&instance->pdev->dev,
+					"unable to allocate stream detect by LD\n ");
+				for (j = 0; j < i; ++j)
+					kfree(fusion->stream_detect_by_ld[j]);
+				kfree(fusion->stream_detect_by_ld);
+				fusion->stream_detect_by_ld = NULL;
+				goto fail_get_ld_pd_list;
+			}
+			fusion->stream_detect_by_ld[i]->mru_bit_map
+				= MR_STREAM_BITMAP;
+		}
+	}
+
 	if (megasas_ld_list_query(instance,
 				  MR_LD_QUERY_TYPE_EXPOSED_TO_HOST))
 		megasas_get_ld_list(instance);
@@ -5294,8 +5386,21 @@ static int megasas_init_fw(struct megasas_instance *instance)
 			instance->skip_heartbeat_timer_del = 1;
 	}
 
+	if (instance->is_ventura) {
+		atomic64_set(&instance->bytes_wrote, 0);
+		atomic_set(&instance->r1_write_fp_capable, 1);
+		megasas_start_timer(instance,
+			    &instance->r1_fp_hold_timer,
+			    megasas_change_r1_fp_status,
+			    MEGASAS_RAID1_FAST_PATH_STATUS_CHECK_INTERVAL);
+				dev_info(&instance->pdev->dev, "starting the raid 1 fp timer with interval %d\n",
+				MEGASAS_RAID1_FAST_PATH_STATUS_CHECK_INTERVAL);
+	}
+
 	return 0;
 
+fail_get_ld_pd_list:
+	instance->instancet->disable_intr(instance);
 fail_get_pd_list:
 	instance->instancet->disable_intr(instance);
 fail_init_adapter:
@@ -5714,6 +5819,12 @@ static int megasas_probe_one(struct pci_dev *pdev,
 	instance->pdev = pdev;
 
 	switch (instance->pdev->device) {
+	case PCI_DEVICE_ID_LSI_VENTURA:
+	case PCI_DEVICE_ID_LSI_HARPOON:
+	case PCI_DEVICE_ID_LSI_TOMCAT:
+	case PCI_DEVICE_ID_LSI_VENTURA_4PORT:
+	case PCI_DEVICE_ID_LSI_CRUSADER_4PORT:
+	     instance->is_ventura = true;
 	case PCI_DEVICE_ID_LSI_FUSION:
 	case PCI_DEVICE_ID_LSI_PLASMA:
 	case PCI_DEVICE_ID_LSI_INVADER:
@@ -5738,6 +5849,8 @@ static int megasas_probe_one(struct pci_dev *pdev,
 		if ((instance->pdev->device == PCI_DEVICE_ID_LSI_FUSION) ||
 			(instance->pdev->device == PCI_DEVICE_ID_LSI_PLASMA))
 			fusion->adapter_type = THUNDERBOLT_SERIES;
+		else if (instance->is_ventura)
+			fusion->adapter_type = VENTURA_SERIES;
 		else
 			fusion->adapter_type = INVADER_SERIES;
 	}
@@ -5823,6 +5936,7 @@ static int megasas_probe_one(struct pci_dev *pdev,
 
 	spin_lock_init(&instance->mfi_pool_lock);
 	spin_lock_init(&instance->hba_lock);
+	spin_lock_init(&instance->stream_lock);
 	spin_lock_init(&instance->completion_lock);
 
 	mutex_init(&instance->reset_mutex);
@@ -6073,6 +6187,9 @@ megasas_suspend(struct pci_dev *pdev, pm_message_t state)
 	if (instance->requestorId && !instance->skip_heartbeat_timer_del)
 		del_timer_sync(&instance->sriov_heartbeat_timer);
 
+	if (instance->is_ventura)
+		del_timer_sync(&instance->r1_fp_hold_timer);
+
 	megasas_flush_cache(instance);
 	megasas_shutdown_controller(instance, MR_DCMD_HIBERNATE_SHUTDOWN);
 
@@ -6199,6 +6316,16 @@ megasas_resume(struct pci_dev *pdev)
 	megasas_setup_jbod_map(instance);
 	instance->unload = 0;
 
+	if (instance->is_ventura) {
+		atomic64_set(&instance->bytes_wrote, 0);
+		atomic_set(&instance->r1_write_fp_capable, 1);
+		megasas_start_timer(instance,
+			    &instance->r1_fp_hold_timer,
+			    megasas_change_r1_fp_status,
+			    MEGASAS_RAID1_FAST_PATH_STATUS_CHECK_INTERVAL);
+	}
+
+
 	/*
 	 * Initiate AEN (Asynchronous Event Notification)
 	 */
@@ -6287,6 +6414,9 @@ static void megasas_detach_one(struct pci_dev *pdev)
 	if (instance->requestorId && !instance->skip_heartbeat_timer_del)
 		del_timer_sync(&instance->sriov_heartbeat_timer);
 
+	if (instance->is_ventura)
+		del_timer_sync(&instance->r1_fp_hold_timer);
+
 	if (instance->fw_crash_state != UNAVAILABLE)
 		megasas_free_host_crash_buffer(instance);
 	scsi_remove_host(instance->host);
@@ -6330,6 +6460,14 @@ skip_firing_dcmds:
 	if (instance->msix_vectors)
 		pci_free_irq_vectors(instance->pdev);
 
+	if (instance->is_ventura) {
+		for (i = 0; i < MAX_LOGICAL_DRIVES_EXT; ++i)
+			kfree(fusion->stream_detect_by_ld[i]);
+		kfree(fusion->stream_detect_by_ld);
+		fusion->stream_detect_by_ld = NULL;
+	}
+
+
 	if (instance->ctrl_context) {
 		megasas_release_fusion(instance);
 			pd_seq_map_sz = sizeof(struct MR_PD_CFG_SEQ_NUM_SYNC) +
diff --git a/drivers/scsi/megaraid/megaraid_sas_fp.c b/drivers/scsi/megaraid/megaraid_sas_fp.c
index f237d0003df3..322a72b593e3 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fp.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fp.c
@@ -179,18 +179,209 @@ void MR_PopulateDrvRaidMap(struct megasas_instance *instance)
 	struct fusion_context *fusion = instance->ctrl_context;
 	struct MR_FW_RAID_MAP_ALL     *fw_map_old    = NULL;
 	struct MR_FW_RAID_MAP         *pFwRaidMap    = NULL;
-	int i;
+	int i, j;
 	u16 ld_count;
+	struct MR_FW_RAID_MAP_DYNAMIC *fw_map_dyn;
+	struct MR_FW_RAID_MAP_EXT *fw_map_ext;
+	struct MR_RAID_MAP_DESC_TABLE *desc_table;
 
 
 	struct MR_DRV_RAID_MAP_ALL *drv_map =
 			fusion->ld_drv_map[(instance->map_id & 1)];
 	struct MR_DRV_RAID_MAP *pDrvRaidMap = &drv_map->raidMap;
+	void *raid_map_data = NULL;
+
+	memset(drv_map, 0, fusion->drv_map_sz);
+	memset(pDrvRaidMap->ldTgtIdToLd,
+		0xff, (sizeof(u16) * MAX_LOGICAL_DRIVES_DYN));
+
+	if (instance->max_raid_mapsize) {
+		fw_map_dyn = fusion->ld_map[(instance->map_id & 1)];
+		if (fw_map_dyn->pci_threshold_bandwidth)
+			instance->pci_threshold_bandwidth =
+			le64_to_cpu(fw_map_dyn->pci_threshold_bandwidth);
+#if VD_EXT_DEBUG
+		dev_dbg(&instance->pdev->dev, "raidMapSize 0x%x fw_map_dyn->descTableOffset 0x%x\n",
+			le32_to_cpu(fw_map_dyn->raid_map_size),
+			le32_to_cpu(fw_map_dyn->desc_table_offset));
+		dev_dbg(&instance->pdev->dev, "descTableSize 0x%x descTableNumElements 0x%x\n",
+			le32_to_cpu(fw_map_dyn->desc_table_size),
+			le32_to_cpu(fw_map_dyn->desc_table_num_elements));
+		dev_dbg(&instance->pdev->dev, "PCIThreasholdBandwidth %llu\n",
+			instance->pci_threshold_bandwidth);
+		dev_dbg(&instance->pdev->dev, "drv map %p ldCount %d\n",
+			drv_map, fw_map_dyn->ld_count);
+#endif
+		desc_table =
+		(struct MR_RAID_MAP_DESC_TABLE *)((void *)fw_map_dyn + le32_to_cpu(fw_map_dyn->desc_table_offset));
+		if (desc_table != fw_map_dyn->raid_map_desc_table)
+			dev_dbg(&instance->pdev->dev, "offsets of desc table are not matching desc %p original %p\n",
+				desc_table, fw_map_dyn->raid_map_desc_table);
+
+		ld_count = (u16)le16_to_cpu(fw_map_dyn->ld_count);
+		pDrvRaidMap->ldCount = (__le16)cpu_to_le16(ld_count);
+		pDrvRaidMap->fpPdIoTimeoutSec =
+			fw_map_dyn->fp_pd_io_timeout_sec;
+		pDrvRaidMap->totalSize = sizeof(struct MR_DRV_RAID_MAP_ALL);
+		/* point to actual data starting point*/
+		raid_map_data = (void *)fw_map_dyn +
+			le32_to_cpu(fw_map_dyn->desc_table_offset) +
+			le32_to_cpu(fw_map_dyn->desc_table_size);
+
+		for (i = 0; i < le32_to_cpu(fw_map_dyn->desc_table_num_elements); ++i) {
+
+#if VD_EXT_DEBUG
+			dev_dbg(&instance->pdev->dev, "desc table %p\n",
+				desc_table);
+			dev_dbg(&instance->pdev->dev, "raidmap type %d, raidmapOffset 0x%x\n",
+				desc_table->raid_map_desc_type,
+				desc_table->raid_map_desc_offset);
+			dev_dbg(&instance->pdev->dev, "raid map number of elements 0%x, raidmapsize 0x%x\n",
+				desc_table->raid_map_desc_elements,
+				desc_table->raid_map_desc_buffer_size);
+#endif
+			switch (le32_to_cpu(desc_table->raid_map_desc_type)) {
+			case RAID_MAP_DESC_TYPE_DEVHDL_INFO:
+				fw_map_dyn->dev_hndl_info =
+				(struct MR_DEV_HANDLE_INFO *)(raid_map_data + le32_to_cpu(desc_table->raid_map_desc_offset));
+#if VD_EXT_DEBUG
+				dev_dbg(&instance->pdev->dev, "devHndlInfo  address %p\n",
+					fw_map_dyn->dev_hndl_info);
+#endif
+				memcpy(pDrvRaidMap->devHndlInfo,
+				fw_map_dyn->dev_hndl_info,
+				sizeof(struct MR_DEV_HANDLE_INFO) *
+				le32_to_cpu(desc_table->raid_map_desc_elements));
+			break;
+			case RAID_MAP_DESC_TYPE_TGTID_INFO:
+				fw_map_dyn->ld_tgt_id_to_ld =
+				(u16 *) (raid_map_data +
+				le32_to_cpu(desc_table->raid_map_desc_offset));
+#if VD_EXT_DEBUG
+			dev_dbg(&instance->pdev->dev, "ldTgtIdToLd  address %p\n",
+				fw_map_dyn->ld_tgt_id_to_ld);
+#endif
+			for (j = 0; j < le32_to_cpu(desc_table->raid_map_desc_elements); j++) {
+				pDrvRaidMap->ldTgtIdToLd[j] =
+				fw_map_dyn->ld_tgt_id_to_ld[j];
+#if VD_EXT_DEBUG
+				dev_dbg(&instance->pdev->dev, " %d drv ldTgtIdToLd %d\n",
+					j, pDrvRaidMap->ldTgtIdToLd[j]);
+#endif
+			}
+			break;
+			case RAID_MAP_DESC_TYPE_ARRAY_INFO:
+				fw_map_dyn->ar_map_info =
+				(struct MR_ARRAY_INFO *)
+				(raid_map_data + le32_to_cpu(desc_table->raid_map_desc_offset));
+#if VD_EXT_DEBUG
+				dev_dbg(&instance->pdev->dev, "arMapInfo  address %p\n",
+					fw_map_dyn->ar_map_info);
+#endif
+
+				memcpy(pDrvRaidMap->arMapInfo,
+				fw_map_dyn->ar_map_info,
+				sizeof(struct MR_ARRAY_INFO) * le32_to_cpu(desc_table->raid_map_desc_elements));
+			break;
+			case RAID_MAP_DESC_TYPE_SPAN_INFO:
+				fw_map_dyn->ld_span_map =
+				(struct MR_LD_SPAN_MAP *)
+				(raid_map_data + le32_to_cpu(desc_table->raid_map_desc_offset));
+				memcpy(pDrvRaidMap->ldSpanMap,
+				fw_map_dyn->ld_span_map,
+				sizeof(struct MR_LD_SPAN_MAP) * le32_to_cpu(desc_table->raid_map_desc_elements));
+#if VD_EXT_DEBUG
+				dev_dbg(&instance->pdev->dev, "ldSpanMap  address %p\n",
+					fw_map_dyn->ld_span_map);
+				dev_dbg(&instance->pdev->dev, "MR_LD_SPAN_MAP size 0x%lx\n",
+					sizeof(struct MR_LD_SPAN_MAP));
+				for (j = 0; j < ld_count; j++) {
+					dev_dbg(&instance->pdev->dev, "megaraid_sas(%d) : fw_map_dyn->ldSpanMap[%d].ldRaid.targetId 0x%x\n",
+					j, j, fw_map_dyn->ld_span_map[j].ldRaid.targetId);
+					dev_dbg(&instance->pdev->dev, "fw_map_dyn->ldSpanMap[%d].ldRaid.seqNum 0x%x\n",
+					j, fw_map_dyn->ld_span_map[j].ldRaid.seqNum);
+					dev_dbg(&instance->pdev->dev, "fw_map_dyn->ld_span_map[%d].ldRaid.rowSize 0x%x\n",
+					j, (u32)fw_map_dyn->ld_span_map[j].ldRaid.rowSize);
+
+					dev_dbg(&instance->pdev->dev, "megaraid_sas(%d) :pDrvRaidMap->ldSpanMap[%d].ldRaid.targetId 0x%x\n",
+					j, j, pDrvRaidMap->ldSpanMap[j].ldRaid.targetId);
+					dev_dbg(&instance->pdev->dev, "DrvRaidMap->ldSpanMap[%d].ldRaid.seqNum 0x%x\n",
+					j, pDrvRaidMap->ldSpanMap[j].ldRaid.seqNum);
+					dev_dbg(&instance->pdev->dev, "pDrvRaidMap->ldSpanMap[%d].ldRaid.rowSize 0x%x\n",
+					j, (u32)pDrvRaidMap->ldSpanMap[j].ldRaid.rowSize);
+
+					dev_dbg(&instance->pdev->dev, "megaraid_sas(%d) : drv raid map all %p\n",
+					instance->unique_id, drv_map);
+					dev_dbg(&instance->pdev->dev, "raid map %p LD RAID MAP %p/%p\n",
+					pDrvRaidMap,
+					&fw_map_dyn->ld_span_map[j].ldRaid,
+					&pDrvRaidMap->ldSpanMap[j].ldRaid);
+				}
+#endif
+			break;
+			default:
+				dev_dbg(&instance->pdev->dev, "wrong number of desctableElements %d\n",
+					fw_map_dyn->desc_table_num_elements);
+			}
+			++desc_table;
+		}
+
+	} else if (instance->supportmax256vd) {
+		fw_map_ext =
+		(struct MR_FW_RAID_MAP_EXT *) fusion->ld_map[(instance->map_id & 1)];
+		ld_count = (u16)le16_to_cpu(fw_map_ext->ldCount);
+		if (ld_count > MAX_LOGICAL_DRIVES_EXT) {
+			dev_dbg(&instance->pdev->dev, "megaraid_sas: LD count exposed in RAID map in not valid\n");
+			return;
+		}
+#if VD_EXT_DEBUG
+		for (i = 0; i < ld_count; i++) {
+			dev_dbg(&instance->pdev->dev, "megaraid_sas(%d) :Index 0x%x\n",
+				instance->unique_id, i);
+			dev_dbg(&instance->pdev->dev, "Target Id 0x%x\n",
+				fw_map_ext->ldSpanMap[i].ldRaid.targetId);
+			dev_dbg(&instance->pdev->dev, "Seq Num 0x%x Size 0/%llx\n",
+				fw_map_ext->ldSpanMap[i].ldRaid.seqNum,
+				fw_map_ext->ldSpanMap[i].ldRaid.size);
+		}
+#endif
+
+		pDrvRaidMap->ldCount = (__le16)cpu_to_le16(ld_count);
+		pDrvRaidMap->fpPdIoTimeoutSec = fw_map_ext->fpPdIoTimeoutSec;
+		for (i = 0; i < (MAX_LOGICAL_DRIVES_EXT); i++)
+			pDrvRaidMap->ldTgtIdToLd[i] =
+				(u16)fw_map_ext->ldTgtIdToLd[i];
+		memcpy(pDrvRaidMap->ldSpanMap, fw_map_ext->ldSpanMap,
+				sizeof(struct MR_LD_SPAN_MAP) * ld_count);
+#if VD_EXT_DEBUG
+		for (i = 0; i < ld_count; i++) {
+			dev_dbg(&instance->pdev->dev, "megaraid_sas(%d) : fw_map_ext->ldSpanMap[%d].ldRaid.targetId 0x%x\n",
+			i, i, fw_map_ext->ldSpanMap[i].ldRaid.targetId);
+			dev_dbg(&instance->pdev->dev, "fw_map_ext->ldSpanMap[%d].ldRaid.seqNum 0x%x\n",
+			i, fw_map_ext->ldSpanMap[i].ldRaid.seqNum);
+			dev_dbg(&instance->pdev->dev, "fw_map_ext->ldSpanMap[%d].ldRaid.rowSize 0x%x\n",
+			i, (u32)fw_map_ext->ldSpanMap[i].ldRaid.rowSize);
+
+			dev_dbg(&instance->pdev->dev, "megaraid_sas(%d) : pDrvRaidMap->ldSpanMap[%d].ldRaid.targetId 0x%x\n",
+			i, i, pDrvRaidMap->ldSpanMap[i].ldRaid.targetId);
+			dev_dbg(&instance->pdev->dev, "pDrvRaidMap->ldSpanMap[%d].ldRaid.seqNum 0x%x\n",
+			i, pDrvRaidMap->ldSpanMap[i].ldRaid.seqNum);
+			dev_dbg(&instance->pdev->dev, "pDrvRaidMap->ldSpanMap[%d].ldRaid.rowSize 0x%x\n",
+			i, (u32)pDrvRaidMap->ldSpanMap[i].ldRaid.rowSize);
+
+			dev_dbg(&instance->pdev->dev, "megaraid_sas(%d) : drv raid map all %p\n",
+			instance->unique_id, drv_map);
+			dev_dbg(&instance->pdev->dev, "raid map %p LD RAID MAP %p %p\n",
+			pDrvRaidMap, &fw_map_ext->ldSpanMap[i].ldRaid,
+			&pDrvRaidMap->ldSpanMap[i].ldRaid);
+		}
+#endif
+		memcpy(pDrvRaidMap->arMapInfo, fw_map_ext->arMapInfo,
+			sizeof(struct MR_ARRAY_INFO) * MAX_API_ARRAYS_EXT);
+		memcpy(pDrvRaidMap->devHndlInfo, fw_map_ext->devHndlInfo,
+			sizeof(struct MR_DEV_HANDLE_INFO) *
+					MAX_RAIDMAP_PHYSICAL_DEVICES);
 
-	if (instance->supportmax256vd) {
-		memcpy(fusion->ld_drv_map[instance->map_id & 1],
-			fusion->ld_map[instance->map_id & 1],
-			fusion->current_map_sz);
 		/* New Raid map will not set totalSize, so keep expected value
 		 * for legacy code in ValidateMapInfo
 		 */
@@ -213,16 +404,12 @@ void MR_PopulateDrvRaidMap(struct megasas_instance *instance)
 		}
 #endif
 
-		memset(drv_map, 0, fusion->drv_map_sz);
 		pDrvRaidMap->totalSize = pFwRaidMap->totalSize;
 		pDrvRaidMap->ldCount = (__le16)cpu_to_le16(ld_count);
 		pDrvRaidMap->fpPdIoTimeoutSec = pFwRaidMap->fpPdIoTimeoutSec;
 		for (i = 0; i < MAX_RAIDMAP_LOGICAL_DRIVES + MAX_RAIDMAP_VIEWS; i++)
 			pDrvRaidMap->ldTgtIdToLd[i] =
 				(u8)pFwRaidMap->ldTgtIdToLd[i];
-		for (i = (MAX_RAIDMAP_LOGICAL_DRIVES + MAX_RAIDMAP_VIEWS);
-			i < MAX_LOGICAL_DRIVES_EXT; i++)
-			pDrvRaidMap->ldTgtIdToLd[i] = 0xff;
 		for (i = 0; i < ld_count; i++) {
 			pDrvRaidMap->ldSpanMap[i] = pFwRaidMap->ldSpanMap[i];
 #if VD_EXT_DEBUG
@@ -252,6 +439,8 @@ void MR_PopulateDrvRaidMap(struct megasas_instance *instance)
 			sizeof(struct MR_DEV_HANDLE_INFO) *
 			MAX_RAIDMAP_PHYSICAL_DEVICES);
 	}
+	if (instance->is_ventura && !instance->pci_threshold_bandwidth)
+		instance->pci_threshold_bandwidth = ULLONG_MAX;
 }
 
 /*
@@ -279,7 +468,9 @@ u8 MR_ValidateMapInfo(struct megasas_instance *instance)
 	lbInfo = fusion->load_balance_info;
 	ldSpanInfo = fusion->log_to_span;
 
-	if (instance->supportmax256vd)
+	if (instance->max_raid_mapsize)
+		expected_size = sizeof(struct MR_DRV_RAID_MAP_ALL);
+	else if (instance->supportmax256vd)
 		expected_size = sizeof(struct MR_FW_RAID_MAP_EXT);
 	else
 		expected_size =
@@ -287,8 +478,10 @@ u8 MR_ValidateMapInfo(struct megasas_instance *instance)
 			(sizeof(struct MR_LD_SPAN_MAP) * le16_to_cpu(pDrvRaidMap->ldCount)));
 
 	if (le32_to_cpu(pDrvRaidMap->totalSize) != expected_size) {
-		dev_err(&instance->pdev->dev, "map info structure size 0x%x is not matching with ld count\n",
-		       (unsigned int) expected_size);
+		dev_dbg(&instance->pdev->dev, "megasas: map info structure size 0x%x",
+			le32_to_cpu(pDrvRaidMap->totalSize));
+		dev_dbg(&instance->pdev->dev, "is not matching expected size 0x%x\n",
+			(unsigned int) expected_size);
 		dev_err(&instance->pdev->dev, "megasas: span map %x, pDrvRaidMap->totalSize : %x\n",
 			(unsigned int)sizeof(struct MR_LD_SPAN_MAP),
 			le32_to_cpu(pDrvRaidMap->totalSize));
@@ -737,7 +930,7 @@ static u8 mr_spanset_get_phy_params(struct megasas_instance *instance, u32 ld,
 		struct MR_DRV_RAID_MAP_ALL *map)
 {
 	struct MR_LD_RAID  *raid = MR_LdRaidGet(ld, map);
-	u32     pd, arRef;
+	u32     pd, arRef, r1_alt_pd;
 	u8      physArm, span;
 	u64     row;
 	u8	retval = TRUE;
@@ -772,15 +965,22 @@ static u8 mr_spanset_get_phy_params(struct megasas_instance *instance, u32 ld,
 	arRef       = MR_LdSpanArrayGet(ld, span, map);
 	pd          = MR_ArPdGet(arRef, physArm, map);
 
-	if (pd != MR_PD_INVALID)
+	if (pd != MR_PD_INVALID) {
 		*pDevHandle = MR_PdDevHandleGet(pd, map);
-	else {
+		/* get second pd also for raid 1/10 fast path writes*/
+		if (raid->level == 1) {
+			r1_alt_pd = MR_ArPdGet(arRef, physArm + 1, map);
+			if (r1_alt_pd != MR_PD_INVALID)
+				io_info->r1_alt_dev_handle =
+				MR_PdDevHandleGet(r1_alt_pd, map);
+		}
+	} else {
 		*pDevHandle = cpu_to_le16(MR_PD_INVALID);
 		if ((raid->level >= 5) &&
 			((fusion->adapter_type == THUNDERBOLT_SERIES)  ||
 			((fusion->adapter_type == INVADER_SERIES) &&
 			(raid->regTypeReqOnRead != REGION_TYPE_UNUSED))))
-			pRAID_Context->regLockFlags = REGION_TYPE_EXCLUSIVE;
+			pRAID_Context->reg_lock_flags = REGION_TYPE_EXCLUSIVE;
 		else if (raid->level == 1) {
 			physArm = physArm + 1;
 			pd = MR_ArPdGet(arRef, physArm, map);
@@ -790,9 +990,16 @@ static u8 mr_spanset_get_phy_params(struct megasas_instance *instance, u32 ld,
 	}
 
 	*pdBlock += stripRef + le64_to_cpu(MR_LdSpanPtrGet(ld, span, map)->startBlk);
-	pRAID_Context->spanArm = (span << RAID_CTX_SPANARM_SPAN_SHIFT) |
-					physArm;
-	io_info->span_arm = pRAID_Context->spanArm;
+	if (instance->is_ventura) {
+		((struct RAID_CONTEXT_G35 *) pRAID_Context)->span_arm =
+			(span << RAID_CTX_SPANARM_SPAN_SHIFT) | physArm;
+		io_info->span_arm =
+			(span << RAID_CTX_SPANARM_SPAN_SHIFT) | physArm;
+	} else {
+		pRAID_Context->span_arm =
+			(span << RAID_CTX_SPANARM_SPAN_SHIFT) | physArm;
+		io_info->span_arm = pRAID_Context->span_arm;
+	}
 	return retval;
 }
 
@@ -819,7 +1026,7 @@ u8 MR_GetPhyParams(struct megasas_instance *instance, u32 ld, u64 stripRow,
 		struct MR_DRV_RAID_MAP_ALL *map)
 {
 	struct MR_LD_RAID  *raid = MR_LdRaidGet(ld, map);
-	u32         pd, arRef;
+	u32         pd, arRef, r1_alt_pd;
 	u8          physArm, span;
 	u64         row;
 	u8	    retval = TRUE;
@@ -867,17 +1074,24 @@ u8 MR_GetPhyParams(struct megasas_instance *instance, u32 ld, u64 stripRow,
 	arRef       = MR_LdSpanArrayGet(ld, span, map);
 	pd          = MR_ArPdGet(arRef, physArm, map); /* Get the pd */
 
-	if (pd != MR_PD_INVALID)
+	if (pd != MR_PD_INVALID) {
 		/* Get dev handle from Pd. */
 		*pDevHandle = MR_PdDevHandleGet(pd, map);
-	else {
+		/* get second pd also for raid 1/10 fast path writes*/
+		if (raid->level == 1) {
+			r1_alt_pd = MR_ArPdGet(arRef, physArm + 1, map);
+			if (r1_alt_pd != MR_PD_INVALID)
+				io_info->r1_alt_dev_handle =
+				MR_PdDevHandleGet(r1_alt_pd, map);
+		}
+	} else {
 		/* set dev handle as invalid. */
 		*pDevHandle = cpu_to_le16(MR_PD_INVALID);
 		if ((raid->level >= 5) &&
 			((fusion->adapter_type == THUNDERBOLT_SERIES)  ||
 			((fusion->adapter_type == INVADER_SERIES) &&
 			(raid->regTypeReqOnRead != REGION_TYPE_UNUSED))))
-			pRAID_Context->regLockFlags = REGION_TYPE_EXCLUSIVE;
+			pRAID_Context->reg_lock_flags = REGION_TYPE_EXCLUSIVE;
 		else if (raid->level == 1) {
 			/* Get alternate Pd. */
 			physArm = physArm + 1;
@@ -889,9 +1103,16 @@ u8 MR_GetPhyParams(struct megasas_instance *instance, u32 ld, u64 stripRow,
 	}
 
 	*pdBlock += stripRef + le64_to_cpu(MR_LdSpanPtrGet(ld, span, map)->startBlk);
-	pRAID_Context->spanArm = (span << RAID_CTX_SPANARM_SPAN_SHIFT) |
-		physArm;
-	io_info->span_arm = pRAID_Context->spanArm;
+	if (instance->is_ventura) {
+		((struct RAID_CONTEXT_G35 *) pRAID_Context)->span_arm =
+				(span << RAID_CTX_SPANARM_SPAN_SHIFT) | physArm;
+		io_info->span_arm =
+				(span << RAID_CTX_SPANARM_SPAN_SHIFT) | physArm;
+	} else {
+		pRAID_Context->span_arm =
+			(span << RAID_CTX_SPANARM_SPAN_SHIFT) | physArm;
+		io_info->span_arm = pRAID_Context->span_arm;
+	}
 	return retval;
 }
 
@@ -935,6 +1156,8 @@ MR_BuildRaidContext(struct megasas_instance *instance,
 
 	ld = MR_TargetIdToLdGet(ldTgtId, map);
 	raid = MR_LdRaidGet(ld, map);
+	/*check read ahead bit*/
+	io_info->ra_capable = raid->capability.ra_capable;
 
 	/*
 	 * if rowDataSize @RAID map and spanRowDataSize @SPAN INFO are zero
@@ -1093,20 +1316,20 @@ MR_BuildRaidContext(struct megasas_instance *instance,
 			regSize += stripSize;
 	}
 
-	pRAID_Context->timeoutValue =
+	pRAID_Context->timeout_value =
 		cpu_to_le16(raid->fpIoTimeoutForLd ?
 			    raid->fpIoTimeoutForLd :
 			    map->raidMap.fpPdIoTimeoutSec);
 	if (fusion->adapter_type == INVADER_SERIES)
-		pRAID_Context->regLockFlags = (isRead) ?
+		pRAID_Context->reg_lock_flags = (isRead) ?
 			raid->regTypeReqOnRead : raid->regTypeReqOnWrite;
-	else
-		pRAID_Context->regLockFlags = (isRead) ?
+	else if (!instance->is_ventura)
+		pRAID_Context->reg_lock_flags = (isRead) ?
 			REGION_TYPE_SHARED_READ : raid->regTypeReqOnWrite;
-	pRAID_Context->VirtualDiskTgtId = raid->targetId;
-	pRAID_Context->regLockRowLBA    = cpu_to_le64(regStart);
-	pRAID_Context->regLockLength    = cpu_to_le32(regSize);
-	pRAID_Context->configSeqNum	= raid->seqNum;
+	pRAID_Context->virtual_disk_tgt_id = raid->targetId;
+	pRAID_Context->reg_lock_row_lba    = cpu_to_le64(regStart);
+	pRAID_Context->reg_lock_length    = cpu_to_le32(regSize);
+	pRAID_Context->config_seq_num	= raid->seqNum;
 	/* save pointer to raid->LUN array */
 	*raidLUN = raid->LUN;
 
@@ -1124,6 +1347,18 @@ MR_BuildRaidContext(struct megasas_instance *instance,
 		/* If IO on an invalid Pd, then FP is not possible.*/
 		if (io_info->devHandle == cpu_to_le16(MR_PD_INVALID))
 			io_info->fpOkForIo = FALSE;
+		/* if FP possible, set the SLUD bit in
+		 *  regLockFlags for ventura
+		 */
+		else if ((instance->is_ventura) && (!isRead) &&
+			(raid->writeMode == MR_RL_WRITE_BACK_MODE) &&
+			(raid->capability.fp_cache_bypass_capable))
+			((struct RAID_CONTEXT_G35 *) pRAID_Context)->routing_flags.bits.sld = 1;
+		/* set raid 1/10 fast path write capable bit in io_info */
+		if (io_info->fpOkForIo &&
+		    (io_info->r1_alt_dev_handle != MR_PD_INVALID) &&
+		    (raid->level == 1) && !isRead)
+			io_info->is_raid_1_fp_write = 1;
 		return retval;
 	} else if (isRead) {
 		uint stripIdx;
@@ -1298,6 +1533,7 @@ u8 megasas_get_best_arm_pd(struct megasas_instance *instance,
 	struct fusion_context *fusion;
 	struct MR_LD_RAID  *raid;
 	struct MR_DRV_RAID_MAP_ALL *drv_map;
+	u16	pd1_dev_handle;
 	u16     pend0, pend1, ld;
 	u64     diff0, diff1;
 	u8      bestArm, pd0, pd1, span, arm;
@@ -1323,23 +1559,36 @@ u8 megasas_get_best_arm_pd(struct megasas_instance *instance,
 	pd1 = MR_ArPdGet(arRef, (arm + 1) >= span_row_size ?
 		(arm + 1 - span_row_size) : arm + 1, drv_map);
 
-	/* get the pending cmds for the data and mirror arms */
-	pend0 = atomic_read(&lbInfo->scsi_pending_cmds[pd0]);
-	pend1 = atomic_read(&lbInfo->scsi_pending_cmds[pd1]);
+	/* Get PD1 Dev Handle */
+
+	pd1_dev_handle = MR_PdDevHandleGet(pd1, drv_map);
+
+	if (pd1_dev_handle == MR_PD_INVALID) {
+		bestArm = arm;
+	} else {
+		/* get the pending cmds for the data and mirror arms */
+		pend0 = atomic_read(&lbInfo->scsi_pending_cmds[pd0]);
+		pend1 = atomic_read(&lbInfo->scsi_pending_cmds[pd1]);
 
-	/* Determine the disk whose head is nearer to the req. block */
-	diff0 = ABS_DIFF(block, lbInfo->last_accessed_block[pd0]);
-	diff1 = ABS_DIFF(block, lbInfo->last_accessed_block[pd1]);
-	bestArm = (diff0 <= diff1 ? arm : arm ^ 1);
+		/* Determine the disk whose head is nearer to the req. block */
+		diff0 = ABS_DIFF(block, lbInfo->last_accessed_block[pd0]);
+		diff1 = ABS_DIFF(block, lbInfo->last_accessed_block[pd1]);
+		bestArm = (diff0 <= diff1 ? arm : arm ^ 1);
 
-	if ((bestArm == arm && pend0 > pend1 + lb_pending_cmds)  ||
+		/* Make balance count from 16 to 4 to
+		 *  keep driver in sync with Firmware
+		 */
+		if ((bestArm == arm && pend0 > pend1 + lb_pending_cmds)  ||
 			(bestArm != arm && pend1 > pend0 + lb_pending_cmds))
-		bestArm ^= 1;
+			bestArm ^= 1;
+
+		/* Update the last accessed block on the correct pd */
+		io_info->span_arm =
+			(span << RAID_CTX_SPANARM_SPAN_SHIFT) | bestArm;
+		io_info->pd_after_lb = (bestArm == arm) ? pd0 : pd1;
+	}
 
-	/* Update the last accessed block on the correct pd */
-	io_info->pd_after_lb = (bestArm == arm) ? pd0 : pd1;
 	lbInfo->last_accessed_block[io_info->pd_after_lb] = block + count - 1;
-	io_info->span_arm = (span << RAID_CTX_SPANARM_SPAN_SHIFT) | bestArm;
 #if SPAN_DEBUG
 	if (arm != bestArm)
 		dev_dbg(&instance->pdev->dev, "LSI Debug R1 Load balance "
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 24778ba4b6e8..9a9c84fb91b1 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -95,6 +95,7 @@ extern unsigned int resetwaittime;
 extern unsigned int dual_qdepth_disable;
 static void megasas_free_rdpq_fusion(struct megasas_instance *instance);
 static void megasas_free_reply_fusion(struct megasas_instance *instance);
+void megasas_change_r1_fp_status(unsigned long instance_addr);
 
 
 
@@ -189,15 +190,29 @@ inline void megasas_return_cmd_fusion(struct megasas_instance *instance,
  */
 static void
 megasas_fire_cmd_fusion(struct megasas_instance *instance,
-		union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc)
+	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc, bool is_32bit)
 {
+	struct megasas_register_set __iomem *regs = instance->reg_set;
+	unsigned long flags;
+
+	if (is_32bit)
+		writel(le32_to_cpu(req_desc->u.low),
+			&(regs)->inbound_single_queue_port);
+	else if (instance->is_ventura) {
+		spin_lock_irqsave(&instance->hba_lock, flags);
+		writel(le32_to_cpu(req_desc->u.low),
+			&(regs)->inbound_low_queue_port);
+		writel(le32_to_cpu(req_desc->u.high),
+			&(regs)->inbound_high_queue_port);
+		mmiowb();
+		spin_unlock_irqrestore(&instance->hba_lock, flags);
+	} 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));
 
 	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),
@@ -207,6 +222,7 @@ megasas_fire_cmd_fusion(struct megasas_instance *instance,
 	mmiowb();
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 #endif
+	}
 }
 
 /**
@@ -229,7 +245,10 @@ megasas_fusion_update_can_queue(struct megasas_instance *instance, int fw_boot_c
 
 	reg_set = instance->reg_set;
 
-	cur_max_fw_cmds = readl(&instance->reg_set->outbound_scratch_pad_3) & 0x00FFFF;
+	/* ventura FW does not fill outbound_scratch_pad_3 with queue depth */
+	if (!instance->is_ventura)
+		cur_max_fw_cmds =
+		readl(&instance->reg_set->outbound_scratch_pad_3) & 0x00FFFF;
 
 	if (dual_qdepth_disable || !cur_max_fw_cmds)
 		cur_max_fw_cmds = instance->instancet->read_fw_status_reg(reg_set) & 0x00FFFF;
@@ -255,7 +274,8 @@ megasas_fusion_update_can_queue(struct megasas_instance *instance, int fw_boot_c
 		instance->ldio_threshold = ldio_threshold;
 
 		if (!instance->is_rdpq)
-			instance->max_fw_cmds = min_t(u16, instance->max_fw_cmds, 1024);
+			instance->max_fw_cmds =
+				min_t(u16, instance->max_fw_cmds, 1024);
 
 		if (reset_devices)
 			instance->max_fw_cmds = min(instance->max_fw_cmds,
@@ -271,7 +291,14 @@ megasas_fusion_update_can_queue(struct megasas_instance *instance, int fw_boot_c
 				(MEGASAS_FUSION_INTERNAL_CMDS +
 				MEGASAS_FUSION_IOCTL_CMDS);
 		instance->cur_can_queue = instance->max_scsi_cmds;
+		instance->host->can_queue = instance->cur_can_queue;
 	}
+
+	if (instance->is_ventura)
+		instance->max_mpt_cmds =
+		instance->max_fw_cmds * RAID_1_10_RMW_CMDS;
+	else
+		instance->max_mpt_cmds = instance->max_fw_cmds;
 }
 /**
  * megasas_free_cmds_fusion -	Free all the cmds in the free cmd pool
@@ -285,7 +312,7 @@ megasas_free_cmds_fusion(struct megasas_instance *instance)
 	struct megasas_cmd_fusion *cmd;
 
 	/* SG, Sense */
-	for (i = 0; i < instance->max_fw_cmds; i++) {
+	for (i = 0; i < instance->max_mpt_cmds; i++) {
 		cmd = fusion->cmd_list[i];
 		if (cmd) {
 			if (cmd->sg_frame)
@@ -329,7 +356,7 @@ megasas_free_cmds_fusion(struct megasas_instance *instance)
 
 
 	/* cmd_list */
-	for (i = 0; i < instance->max_fw_cmds; i++)
+	for (i = 0; i < instance->max_mpt_cmds; i++)
 		kfree(fusion->cmd_list[i]);
 
 	kfree(fusion->cmd_list);
@@ -381,33 +408,49 @@ static int megasas_create_sg_sense_fusion(struct megasas_instance *instance)
 			return -ENOMEM;
 		}
 	}
+
+	/* create sense buffer for the raid 1/10 fp */
+	for (i = max_cmd; i < instance->max_mpt_cmds; i++) {
+		cmd = fusion->cmd_list[i];
+		cmd->sense = pci_pool_alloc(fusion->sense_dma_pool,
+			GFP_KERNEL, &cmd->sense_phys_addr);
+		if (!cmd->sense) {
+			dev_err(&instance->pdev->dev,
+				"Failed from %s %d\n",  __func__, __LINE__);
+			return -ENOMEM;
+		}
+	}
+
 	return 0;
 }
 
 int
 megasas_alloc_cmdlist_fusion(struct megasas_instance *instance)
 {
-	u32 max_cmd, i;
+	u32 max_mpt_cmd, i;
 	struct fusion_context *fusion;
 
 	fusion = instance->ctrl_context;
 
-	max_cmd = instance->max_fw_cmds;
+	max_mpt_cmd = instance->max_mpt_cmds;
 
 	/*
 	 * fusion->cmd_list is an array of struct megasas_cmd_fusion pointers.
 	 * Allocate the dynamic array first and then allocate individual
 	 * commands.
 	 */
-	fusion->cmd_list = kzalloc(sizeof(struct megasas_cmd_fusion *) * max_cmd,
-						GFP_KERNEL);
+	fusion->cmd_list =
+		kzalloc(sizeof(struct megasas_cmd_fusion *) * max_mpt_cmd,
+			GFP_KERNEL);
 	if (!fusion->cmd_list) {
 		dev_err(&instance->pdev->dev,
 			"Failed from %s %d\n",  __func__, __LINE__);
 		return -ENOMEM;
 	}
 
-	for (i = 0; i < max_cmd; i++) {
+
+
+	for (i = 0; i < max_mpt_cmd; i++) {
 		fusion->cmd_list[i] = kzalloc(sizeof(struct megasas_cmd_fusion),
 					      GFP_KERNEL);
 		if (!fusion->cmd_list[i]) {
@@ -642,13 +685,14 @@ megasas_alloc_cmds_fusion(struct megasas_instance *instance)
 	 */
 
 	/* SMID 0 is reserved. Set SMID/index from 1 */
-	for (i = 0; i < instance->max_fw_cmds; i++) {
+	for (i = 0; i < instance->max_mpt_cmds; i++) {
 		cmd = fusion->cmd_list[i];
 		offset = MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE * i;
 		memset(cmd, 0, sizeof(struct megasas_cmd_fusion));
 		cmd->index = i + 1;
 		cmd->scmd = NULL;
-		cmd->sync_cmd_idx = (i >= instance->max_scsi_cmds) ?
+		cmd->sync_cmd_idx =
+		(i >= instance->max_scsi_cmds && i < instance->max_fw_cmds) ?
 				(i - instance->max_scsi_cmds) :
 				(u32)ULONG_MAX; /* Set to Invalid */
 		cmd->instance = instance;
@@ -658,6 +702,7 @@ megasas_alloc_cmds_fusion(struct megasas_instance *instance)
 		memset(cmd->io_request, 0,
 		       sizeof(struct MPI2_RAID_SCSI_IO_REQUEST));
 		cmd->io_request_phys_addr = io_req_base_phys + offset;
+		cmd->is_raid_1_fp_write = 0;
 	}
 
 	if (megasas_create_sg_sense_fusion(instance))
@@ -796,7 +841,7 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 	drv_ops = (MFI_CAPABILITIES *) &(init_frame->driver_operations);
 
 	/* driver support Extended MSIX */
-	if (fusion->adapter_type == INVADER_SERIES)
+	if (fusion->adapter_type >= INVADER_SERIES)
 		drv_ops->mfi_capabilities.support_additional_msix = 1;
 	/* driver supports HA / Remote LUN over Fast Path interface */
 	drv_ops->mfi_capabilities.support_fp_remote_lun = 1;
@@ -813,6 +858,7 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 		drv_ops->mfi_capabilities.support_ext_queue_depth = 1;
 
 	drv_ops->mfi_capabilities.support_qd_throttling = 1;
+	drv_ops->mfi_capabilities.support_pd_map_target_id = 1;
 	/* Convert capability to LE32 */
 	cpu_to_le32s((u32 *)&init_frame->driver_operations.mfi_capabilities);
 
@@ -850,7 +896,7 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 			break;
 	}
 
-	megasas_fire_cmd_fusion(instance, &req_desc);
+	megasas_fire_cmd_fusion(instance, &req_desc, false);
 
 	wait_and_poll(instance, cmd, MFI_POLL_TIMEOUT_SECS);
 
@@ -1247,12 +1293,12 @@ megasas_init_adapter_fusion(struct megasas_instance *instance)
 	fusion->reply_q_depth = 2 * (((max_cmd + 1 + 15)/16)*16);
 
 	fusion->request_alloc_sz =
-		sizeof(union MEGASAS_REQUEST_DESCRIPTOR_UNION) *max_cmd;
+	sizeof(union MEGASAS_REQUEST_DESCRIPTOR_UNION) * instance->max_mpt_cmds;
 	fusion->reply_alloc_sz = sizeof(union MPI2_REPLY_DESCRIPTORS_UNION)
 		*(fusion->reply_q_depth);
 	fusion->io_frames_alloc_sz = MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE +
-		(MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE *
-		 (max_cmd + 1)); /* Extra 1 for SMID 0 */
+		(MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE
+		* (instance->max_mpt_cmds + 1)); /* Extra 1 for SMID 0 */
 
 	scratch_pad_2 = readl(&instance->reg_set->outbound_scratch_pad_2);
 	/* If scratch_pad_2 & MEGASAS_MAX_CHAIN_SIZE_UNITS_MASK is set,
@@ -1388,42 +1434,43 @@ fail_alloc_mfi_cmds:
  */
 
 void
-map_cmd_status(struct megasas_cmd_fusion *cmd, u8 status, u8 ext_status)
+map_cmd_status(struct fusion_context *fusion,
+	struct scsi_cmnd *scmd, u8 status, u8 ext_status,
+			u32 data_length, u8 *sense)
 {
 
 	switch (status) {
 
 	case MFI_STAT_OK:
-		cmd->scmd->result = DID_OK << 16;
+		scmd->result = DID_OK << 16;
 		break;
 
 	case MFI_STAT_SCSI_IO_FAILED:
 	case MFI_STAT_LD_INIT_IN_PROGRESS:
-		cmd->scmd->result = (DID_ERROR << 16) | ext_status;
+		scmd->result = (DID_ERROR << 16) | ext_status;
 		break;
 
 	case MFI_STAT_SCSI_DONE_WITH_ERROR:
 
-		cmd->scmd->result = (DID_OK << 16) | ext_status;
+		scmd->result = (DID_OK << 16) | ext_status;
 		if (ext_status == SAM_STAT_CHECK_CONDITION) {
-			memset(cmd->scmd->sense_buffer, 0,
+			memset(scmd->sense_buffer, 0,
 			       SCSI_SENSE_BUFFERSIZE);
-			memcpy(cmd->scmd->sense_buffer, cmd->sense,
+			memcpy(scmd->sense_buffer, sense,
 			       SCSI_SENSE_BUFFERSIZE);
-			cmd->scmd->result |= DRIVER_SENSE << 24;
+			scmd->result |= DRIVER_SENSE << 24;
 		}
 		break;
 
 	case MFI_STAT_LD_OFFLINE:
 	case MFI_STAT_DEVICE_NOT_FOUND:
-		cmd->scmd->result = DID_BAD_TARGET << 16;
+		scmd->result = DID_BAD_TARGET << 16;
 		break;
 	case MFI_STAT_CONFIG_SEQ_MISMATCH:
-		cmd->scmd->result = DID_IMM_RETRY << 16;
+		scmd->result = DID_IMM_RETRY << 16;
 		break;
 	default:
-		dev_printk(KERN_DEBUG, &cmd->instance->pdev->dev, "FW status %#x\n", status);
-		cmd->scmd->result = DID_ERROR << 16;
+		scmd->result = DID_ERROR << 16;
 		break;
 	}
 }
@@ -1449,7 +1496,7 @@ megasas_make_sgl_fusion(struct megasas_instance *instance,
 
 	fusion = instance->ctrl_context;
 
-	if (fusion->adapter_type == INVADER_SERIES) {
+	if (fusion->adapter_type >= INVADER_SERIES) {
 		struct MPI25_IEEE_SGE_CHAIN64 *sgl_ptr_end = sgl_ptr;
 		sgl_ptr_end += fusion->max_sge_in_main_msg - 1;
 		sgl_ptr_end->Flags = 0;
@@ -1466,7 +1513,7 @@ megasas_make_sgl_fusion(struct megasas_instance *instance,
 		sgl_ptr->Length = cpu_to_le32(sg_dma_len(os_sgl));
 		sgl_ptr->Address = cpu_to_le64(sg_dma_address(os_sgl));
 		sgl_ptr->Flags = 0;
-		if (fusion->adapter_type == INVADER_SERIES)
+		if (fusion->adapter_type >= INVADER_SERIES)
 			if (i == sge_count - 1)
 				sgl_ptr->Flags = IEEE_SGE_FLAGS_END_OF_LIST;
 		sgl_ptr++;
@@ -1477,7 +1524,7 @@ megasas_make_sgl_fusion(struct megasas_instance *instance,
 		    (sge_count > fusion->max_sge_in_main_msg)) {
 
 			struct MPI25_IEEE_SGE_CHAIN64 *sg_chain;
-			if (fusion->adapter_type == INVADER_SERIES) {
+			if (fusion->adapter_type >= INVADER_SERIES) {
 				if ((le16_to_cpu(cmd->io_request->IoFlags) &
 					MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH) !=
 					MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH)
@@ -1493,7 +1540,7 @@ megasas_make_sgl_fusion(struct megasas_instance *instance,
 			sg_chain = sgl_ptr;
 			/* Prepare chain element */
 			sg_chain->NextChainOffset = 0;
-			if (fusion->adapter_type == INVADER_SERIES)
+			if (fusion->adapter_type >= INVADER_SERIES)
 				sg_chain->Flags = IEEE_SGE_FLAGS_CHAIN_ELEMENT;
 			else
 				sg_chain->Flags =
@@ -1574,6 +1621,7 @@ megasas_set_pd_lba(struct MPI2_RAID_SCSI_IO_REQUEST *io_request, u8 cdb_len,
 				MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG |
 				MPI2_SCSIIO_EEDPFLAGS_CHECK_REMOVE_OP |
 				MPI2_SCSIIO_EEDPFLAGS_CHECK_APPTAG |
+				MPI25_SCSIIO_EEDPFLAGS_DO_NOT_DISABLE_MODE |
 				MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD);
 		} else {
 			io_request->EEDPFlags = cpu_to_le16(
@@ -1688,6 +1736,90 @@ megasas_set_pd_lba(struct MPI2_RAID_SCSI_IO_REQUEST *io_request, u8 cdb_len,
 }
 
 /**
+ * megasas_stream_detect -	stream detection on read and and write IOs
+ * @instance:		Adapter soft state
+ * @cmd:		    Command to be prepared
+ * @io_info:		IO Request info
+ *
+ */
+
+/** stream detection on read and and write IOs */
+static void megasas_stream_detect(struct megasas_instance *instance,
+				struct megasas_cmd_fusion *cmd,
+				struct IO_REQUEST_INFO *io_info)
+{
+	struct fusion_context *fusion = instance->ctrl_context;
+	u32 device_id = io_info->ldTgtId;
+	struct LD_STREAM_DETECT *current_ld_sd
+		= fusion->stream_detect_by_ld[device_id];
+	u32 *track_stream = &current_ld_sd->mru_bit_map, stream_num;
+	u32 shifted_values, unshifted_values;
+	u32 index_value_mask, shifted_values_mask;
+	int i;
+	bool is_read_ahead = false;
+	struct STREAM_DETECT *current_sd;
+	/* find possible stream */
+	for (i = 0; i < MAX_STREAMS_TRACKED; ++i) {
+		stream_num =
+		(*track_stream >> (i * BITS_PER_INDEX_STREAM)) &
+			STREAM_MASK;
+		current_sd = &current_ld_sd->stream_track[stream_num];
+	/* if we found a stream, update the raid
+	 *  context and also update the mruBitMap
+	 */
+	/*	boundary condition */
+	if ((current_sd->next_seq_lba) &&
+		(io_info->ldStartBlock >= current_sd->next_seq_lba) &&
+		(io_info->ldStartBlock <= (current_sd->next_seq_lba+32)) &&
+		(current_sd->is_read == io_info->isRead)) {
+
+		if ((io_info->ldStartBlock != current_sd->next_seq_lba)
+			&& ((!io_info->isRead) || (!is_read_ahead)))
+			/*
+			 * Once the API availible we need to change this.
+			 * At this point we are not allowing any gap
+			 */
+			continue;
+
+		cmd->io_request->RaidContext.raid_context_g35.stream_detected = true;
+		current_sd->next_seq_lba =
+		io_info->ldStartBlock + io_info->numBlocks;
+		/*
+		 *	update the mruBitMap LRU
+		 */
+		shifted_values_mask =
+			(1 <<  i * BITS_PER_INDEX_STREAM) - 1;
+		shifted_values = ((*track_stream & shifted_values_mask)
+					<< BITS_PER_INDEX_STREAM);
+		index_value_mask =
+			STREAM_MASK << i * BITS_PER_INDEX_STREAM;
+		unshifted_values =
+			*track_stream & ~(shifted_values_mask |
+			index_value_mask);
+		*track_stream =
+			unshifted_values | shifted_values | stream_num;
+		return;
+
+		}
+
+	}
+	/*
+	 * if we did not find any stream, create a new one
+	 * from the least recently used
+	 */
+	stream_num =
+	(*track_stream >> ((MAX_STREAMS_TRACKED - 1) * BITS_PER_INDEX_STREAM)) &
+			STREAM_MASK;
+	current_sd = &current_ld_sd->stream_track[stream_num];
+	current_sd->is_read = io_info->isRead;
+	current_sd->next_seq_lba = io_info->ldStartBlock + io_info->numBlocks;
+	*track_stream =
+	(((*track_stream & ZERO_LAST_STREAM) << 4) | stream_num);
+	return;
+
+}
+
+/**
  * megasas_build_ldio_fusion -	Prepares IOs to devices
  * @instance:		Adapter soft state
  * @scp:		SCSI command
@@ -1702,22 +1834,26 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 			  struct megasas_cmd_fusion *cmd)
 {
 	u8 fp_possible;
-	u32 start_lba_lo, start_lba_hi, device_id, datalength = 0;
+	u32 start_lba_lo, start_lba_hi, device_id, datalength = 0, ld;
 	struct MPI2_RAID_SCSI_IO_REQUEST *io_request;
 	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc;
 	struct IO_REQUEST_INFO io_info;
 	struct fusion_context *fusion;
 	struct MR_DRV_RAID_MAP_ALL *local_map_ptr;
 	u8 *raidLUN;
+	unsigned long spinlock_flags;
+	union RAID_CONTEXT_UNION *praid_context;
+	struct MR_LD_RAID *raid;
 
 	device_id = MEGASAS_DEV_INDEX(scp);
 
 	fusion = instance->ctrl_context;
 
 	io_request = cmd->io_request;
-	io_request->RaidContext.VirtualDiskTgtId = cpu_to_le16(device_id);
-	io_request->RaidContext.status = 0;
-	io_request->RaidContext.exStatus = 0;
+	io_request->RaidContext.raid_context.virtual_disk_tgt_id =
+		cpu_to_le16(device_id);
+	io_request->RaidContext.raid_context.status = 0;
+	io_request->RaidContext.raid_context.ex_status = 0;
 
 	req_desc = (union MEGASAS_REQUEST_DESCRIPTOR_UNION *)cmd->request_desc;
 
@@ -1779,20 +1915,23 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 	io_info.ldStartBlock = ((u64)start_lba_hi << 32) | start_lba_lo;
 	io_info.numBlocks = datalength;
 	io_info.ldTgtId = device_id;
+	io_info.r1_alt_dev_handle = MR_PD_INVALID;
 	io_request->DataLength = cpu_to_le32(scsi_bufflen(scp));
 
 	if (scp->sc_data_direction == PCI_DMA_FROMDEVICE)
 		io_info.isRead = 1;
 
 	local_map_ptr = fusion->ld_drv_map[(instance->map_id & 1)];
+	ld = MR_TargetIdToLdGet(device_id, local_map_ptr);
+	raid = MR_LdRaidGet(ld, local_map_ptr);
 
 	if ((MR_TargetIdToLdGet(device_id, local_map_ptr) >=
 		instance->fw_supported_vd_count) || (!fusion->fast_path_io)) {
-		io_request->RaidContext.regLockFlags  = 0;
+		io_request->RaidContext.raid_context.reg_lock_flags  = 0;
 		fp_possible = 0;
 	} else {
 		if (MR_BuildRaidContext(instance, &io_info,
-					&io_request->RaidContext,
+					&io_request->RaidContext.raid_context,
 					local_map_ptr, &raidLUN))
 			fp_possible = io_info.fpOkForIo;
 	}
@@ -1803,6 +1942,20 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 	cmd->request_desc->SCSIIO.MSIxIndex = instance->msix_vectors ?
 		raw_smp_processor_id() % instance->msix_vectors : 0;
 
+	if (instance->is_ventura) {
+		spin_lock_irqsave(&instance->stream_lock, spinlock_flags);
+		megasas_stream_detect(instance, cmd, &io_info);
+		spin_unlock_irqrestore(&instance->stream_lock, spinlock_flags);
+		/* In ventura if stream detected for a read and it is read ahead
+		 *  capable make this IO as LDIO
+		 */
+		if (io_request->RaidContext.raid_context_g35.stream_detected &&
+				io_info.isRead && io_info.ra_capable)
+			fp_possible = false;
+	}
+
+	praid_context = &io_request->RaidContext;
+
 	if (fp_possible) {
 		megasas_set_pd_lba(io_request, scp->cmd_len, &io_info, scp,
 				   local_map_ptr, start_lba_lo);
@@ -1811,17 +1964,25 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 			(MPI2_REQ_DESCRIPT_FLAGS_FP_IO
 			 << MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
 		if (fusion->adapter_type == INVADER_SERIES) {
-			if (io_request->RaidContext.regLockFlags ==
+			if (io_request->RaidContext.raid_context.reg_lock_flags ==
 			    REGION_TYPE_UNUSED)
 				cmd->request_desc->SCSIIO.RequestFlags =
 					(MEGASAS_REQ_DESCRIPT_FLAGS_NO_LOCK <<
 					MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
-			io_request->RaidContext.Type = MPI2_TYPE_CUDA;
-			io_request->RaidContext.nseg = 0x1;
+			io_request->RaidContext.raid_context.type
+				= MPI2_TYPE_CUDA;
+			io_request->RaidContext.raid_context.nseg = 0x1;
 			io_request->IoFlags |= cpu_to_le16(MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH);
-			io_request->RaidContext.regLockFlags |=
+			io_request->RaidContext.raid_context.reg_lock_flags |=
 			  (MR_RL_FLAGS_GRANT_DESTINATION_CUDA |
 			   MR_RL_FLAGS_SEQ_NUM_ENABLE);
+		} else if (instance->is_ventura) {
+			io_request->RaidContext.raid_context_g35.type
+				= MPI2_TYPE_CUDA;
+			io_request->RaidContext.raid_context_g35.nseg = 0x1;
+			io_request->RaidContext.raid_context_g35.routing_flags.bits.sqn = 1;
+			io_request->IoFlags |=
+			cpu_to_le16(MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH);
 		}
 		if ((fusion->load_balance_info[device_id].loadBalanceFlag) &&
 		    (io_info.isRead)) {
@@ -1831,9 +1992,20 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 					&io_info);
 			scp->SCp.Status |= MEGASAS_LOAD_BALANCE_FLAG;
 			cmd->pd_r1_lb = io_info.pd_after_lb;
+			if (instance->is_ventura)
+				io_request->RaidContext.raid_context_g35.span_arm
+					= io_info.span_arm;
+			else
+				io_request->RaidContext.raid_context.span_arm
+					= io_info.span_arm;
+
 		} else
 			scp->SCp.Status &= ~MEGASAS_LOAD_BALANCE_FLAG;
 
+		cmd->is_raid_1_fp_write = io_info.is_raid_1_fp_write;
+		if (io_info.is_raid_1_fp_write)
+			cmd->r1_alt_dev_handle = io_info.r1_alt_dev_handle;
+
 		if ((raidLUN[0] == 1) &&
 			(local_map_ptr->raidMap.devHndlInfo[io_info.pd_after_lb].validHandles > 1)) {
 			instance->dev_handle = !(instance->dev_handle);
@@ -1845,26 +2017,98 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 		io_request->DevHandle = io_info.devHandle;
 		/* populate the LUN field */
 		memcpy(io_request->LUN, raidLUN, 8);
+		if (instance->is_ventura) {
+			if (io_info.isRead) {
+				if ((raid->cpuAffinity.pdRead.cpu0) &&
+					(raid->cpuAffinity.pdRead.cpu1))
+					praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+					= MR_RAID_CTX_CPUSEL_FCFS;
+				else if (raid->cpuAffinity.pdRead.cpu1)
+					praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+					= MR_RAID_CTX_CPUSEL_1;
+				else
+					praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+					= MR_RAID_CTX_CPUSEL_0;
+			} else {
+			if ((raid->cpuAffinity.pdWrite.cpu0)
+			&& (raid->cpuAffinity.pdWrite.cpu1))
+				praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+					= MR_RAID_CTX_CPUSEL_FCFS;
+				else if (raid->cpuAffinity.pdWrite.cpu1)
+					praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+					= MR_RAID_CTX_CPUSEL_1;
+				else
+					praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+					= MR_RAID_CTX_CPUSEL_0;
+				if (praid_context->raid_context_g35.routing_flags.bits.sld) {
+					praid_context->raid_context_g35.raid_flags
+					= (MR_RAID_FLAGS_IO_SUB_TYPE_CACHE_BYPASS
+					<< MR_RAID_CTX_RAID_FLAGS_IO_SUB_TYPE_SHIFT);
+				}
+			}
+		}
 	} else {
-		io_request->RaidContext.timeoutValue =
+		io_request->RaidContext.raid_context.timeout_value =
 			cpu_to_le16(local_map_ptr->raidMap.fpPdIoTimeoutSec);
 		cmd->request_desc->SCSIIO.RequestFlags =
 			(MEGASAS_REQ_DESCRIPT_FLAGS_LD_IO
 			 << MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
 		if (fusion->adapter_type == INVADER_SERIES) {
 			if (io_info.do_fp_rlbypass ||
-				(io_request->RaidContext.regLockFlags == REGION_TYPE_UNUSED))
+			(io_request->RaidContext.raid_context.reg_lock_flags
+					== REGION_TYPE_UNUSED))
 				cmd->request_desc->SCSIIO.RequestFlags =
 					(MEGASAS_REQ_DESCRIPT_FLAGS_NO_LOCK <<
 					MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
-			io_request->RaidContext.Type = MPI2_TYPE_CUDA;
-			io_request->RaidContext.regLockFlags |=
+			io_request->RaidContext.raid_context.type
+				= MPI2_TYPE_CUDA;
+			io_request->RaidContext.raid_context.reg_lock_flags |=
 				(MR_RL_FLAGS_GRANT_DESTINATION_CPU0 |
 				 MR_RL_FLAGS_SEQ_NUM_ENABLE);
-			io_request->RaidContext.nseg = 0x1;
+			io_request->RaidContext.raid_context.nseg = 0x1;
+		} else if (instance->is_ventura) {
+			io_request->RaidContext.raid_context_g35.type
+				= MPI2_TYPE_CUDA;
+			io_request->RaidContext.raid_context_g35.routing_flags.bits.sqn = 1;
+			io_request->RaidContext.raid_context_g35.nseg = 0x1;
 		}
 		io_request->Function = MEGASAS_MPI2_FUNCTION_LD_IO_REQUEST;
 		io_request->DevHandle = cpu_to_le16(device_id);
+
+		if (instance->is_ventura) {
+			if (io_info.isRead) {
+				if ((raid->cpuAffinity.ldRead.cpu0)
+				&& (raid->cpuAffinity.ldRead.cpu1))
+					praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+					= MR_RAID_CTX_CPUSEL_FCFS;
+				else if (raid->cpuAffinity.ldRead.cpu1)
+					praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+						= MR_RAID_CTX_CPUSEL_1;
+				else
+					praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+						= MR_RAID_CTX_CPUSEL_0;
+			} else {
+				if ((raid->cpuAffinity.ldWrite.cpu0) &&
+					(raid->cpuAffinity.ldWrite.cpu1))
+					praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+						= MR_RAID_CTX_CPUSEL_FCFS;
+				else if (raid->cpuAffinity.ldWrite.cpu1)
+					praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+						= MR_RAID_CTX_CPUSEL_1;
+				else
+					praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+					= MR_RAID_CTX_CPUSEL_0;
+
+				if (io_request->RaidContext.raid_context_g35.stream_detected
+					&& (raid->level == 5) &&
+					(raid->writeMode == MR_RL_WRITE_THROUGH_MODE)) {
+					if (praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+						== MR_RAID_CTX_CPUSEL_FCFS)
+						praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+							= MR_RAID_CTX_CPUSEL_0;
+				}
+			}
+		}
 	} /* Not FP */
 }
 
@@ -1897,11 +2141,11 @@ static void megasas_build_ld_nonrw_fusion(struct megasas_instance *instance,
 	local_map_ptr = fusion->ld_drv_map[(instance->map_id & 1)];
 	io_request->DataLength = cpu_to_le32(scsi_bufflen(scmd));
 	/* get RAID_Context pointer */
-	pRAID_Context = &io_request->RaidContext;
+	pRAID_Context = &io_request->RaidContext.raid_context;
 	/* Check with FW team */
-	pRAID_Context->VirtualDiskTgtId = cpu_to_le16(device_id);
-	pRAID_Context->regLockRowLBA    = 0;
-	pRAID_Context->regLockLength    = 0;
+	pRAID_Context->virtual_disk_tgt_id = cpu_to_le16(device_id);
+	pRAID_Context->reg_lock_row_lba    = 0;
+	pRAID_Context->reg_lock_length    = 0;
 
 	if (fusion->fast_path_io && (
 		device_id < instance->fw_supported_vd_count)) {
@@ -1920,7 +2164,7 @@ static void megasas_build_ld_nonrw_fusion(struct megasas_instance *instance,
 		io_request->Function  = MEGASAS_MPI2_FUNCTION_LD_IO_REQUEST;
 		io_request->DevHandle = cpu_to_le16(device_id);
 		io_request->LUN[1] = scmd->device->lun;
-		pRAID_Context->timeoutValue =
+		pRAID_Context->timeout_value =
 			cpu_to_le16 (scmd->request->timeout / HZ);
 		cmd->request_desc->SCSIIO.RequestFlags =
 			(MPI2_REQ_DESCRIPT_FLAGS_SCSI_IO <<
@@ -1928,9 +2172,11 @@ static void megasas_build_ld_nonrw_fusion(struct megasas_instance *instance,
 	} else {
 
 		/* set RAID context values */
-		pRAID_Context->configSeqNum = raid->seqNum;
-		pRAID_Context->regLockFlags = REGION_TYPE_SHARED_READ;
-		pRAID_Context->timeoutValue = cpu_to_le16(raid->fpIoTimeoutForLd);
+		pRAID_Context->config_seq_num = raid->seqNum;
+		if (!instance->is_ventura)
+			pRAID_Context->reg_lock_flags = REGION_TYPE_SHARED_READ;
+		pRAID_Context->timeout_value =
+			cpu_to_le16(raid->fpIoTimeoutForLd);
 
 		/* get the DevHandle for the PD (since this is
 		   fpNonRWCapable, this is a single disk RAID0) */
@@ -1984,13 +2230,13 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 
 	io_request = cmd->io_request;
 	/* get RAID_Context pointer */
-	pRAID_Context = &io_request->RaidContext;
-	pRAID_Context->regLockFlags = 0;
-	pRAID_Context->regLockRowLBA = 0;
-	pRAID_Context->regLockLength = 0;
+	pRAID_Context = &io_request->RaidContext.raid_context;
+	pRAID_Context->reg_lock_flags = 0;
+	pRAID_Context->reg_lock_row_lba = 0;
+	pRAID_Context->reg_lock_length = 0;
 	io_request->DataLength = cpu_to_le32(scsi_bufflen(scmd));
 	io_request->LUN[1] = scmd->device->lun;
-	pRAID_Context->RAIDFlags = MR_RAID_FLAGS_IO_SUB_TYPE_SYSTEM_PD
+	pRAID_Context->raid_flags = MR_RAID_FLAGS_IO_SUB_TYPE_SYSTEM_PD
 		<< MR_RAID_CTX_RAID_FLAGS_IO_SUB_TYPE_SHIFT;
 
 	/* If FW supports PD sequence number */
@@ -1999,24 +2245,32 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 		/* TgtId must be incremented by 255 as jbod seq number is index
 		 * below raid map
 		 */
-		pRAID_Context->VirtualDiskTgtId =
+		 /* More than 256 PD/JBOD support for Ventura */
+		if (instance->support_morethan256jbod)
+			pRAID_Context->virtual_disk_tgt_id =
+				pd_sync->seq[pd_index].pd_target_id;
+		else
+		pRAID_Context->virtual_disk_tgt_id =
 			cpu_to_le16(device_id + (MAX_PHYSICAL_DEVICES - 1));
-		pRAID_Context->configSeqNum = pd_sync->seq[pd_index].seqNum;
+		pRAID_Context->config_seq_num = pd_sync->seq[pd_index].seqNum;
 		io_request->DevHandle = pd_sync->seq[pd_index].devHandle;
-		pRAID_Context->regLockFlags |=
+		if (instance->is_ventura)
+			io_request->RaidContext.raid_context_g35.routing_flags.bits.sqn = 1;
+		else
+		pRAID_Context->reg_lock_flags |=
 			(MR_RL_FLAGS_SEQ_NUM_ENABLE|MR_RL_FLAGS_GRANT_DESTINATION_CUDA);
-		pRAID_Context->Type = MPI2_TYPE_CUDA;
+		pRAID_Context->type = MPI2_TYPE_CUDA;
 		pRAID_Context->nseg = 0x1;
 	} else if (fusion->fast_path_io) {
-		pRAID_Context->VirtualDiskTgtId = cpu_to_le16(device_id);
-		pRAID_Context->configSeqNum = 0;
+		pRAID_Context->virtual_disk_tgt_id = cpu_to_le16(device_id);
+		pRAID_Context->config_seq_num = 0;
 		local_map_ptr = fusion->ld_drv_map[(instance->map_id & 1)];
 		io_request->DevHandle =
 			local_map_ptr->raidMap.devHndlInfo[device_id].curDevHdl;
 	} else {
 		/* Want to send all IO via FW path */
-		pRAID_Context->VirtualDiskTgtId = cpu_to_le16(device_id);
-		pRAID_Context->configSeqNum = 0;
+		pRAID_Context->virtual_disk_tgt_id = cpu_to_le16(device_id);
+		pRAID_Context->config_seq_num = 0;
 		io_request->DevHandle = cpu_to_le16(0xFFFF);
 	}
 
@@ -2032,17 +2286,17 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 		cmd->request_desc->SCSIIO.RequestFlags =
 			(MPI2_REQ_DESCRIPT_FLAGS_SCSI_IO <<
 				MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
-		pRAID_Context->timeoutValue = cpu_to_le16(os_timeout_value);
-		pRAID_Context->VirtualDiskTgtId = cpu_to_le16(device_id);
+		pRAID_Context->timeout_value = cpu_to_le16(os_timeout_value);
+		pRAID_Context->virtual_disk_tgt_id = cpu_to_le16(device_id);
 	} else {
 		/* system pd Fast Path */
 		io_request->Function = MPI2_FUNCTION_SCSI_IO_REQUEST;
 		timeout_limit = (scmd->device->type == TYPE_DISK) ?
 				255 : 0xFFFF;
-		pRAID_Context->timeoutValue =
+		pRAID_Context->timeout_value =
 			cpu_to_le16((os_timeout_value > timeout_limit) ?
 			timeout_limit : os_timeout_value);
-		if (fusion->adapter_type == INVADER_SERIES)
+		if (fusion->adapter_type >= INVADER_SERIES)
 			io_request->IoFlags |=
 				cpu_to_le16(MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH);
 
@@ -2078,9 +2332,9 @@ megasas_build_io_fusion(struct megasas_instance *instance,
 	io_request->Control = 0;
 	io_request->EEDPBlockSize = 0;
 	io_request->ChainOffset = 0;
-	io_request->RaidContext.RAIDFlags = 0;
-	io_request->RaidContext.Type = 0;
-	io_request->RaidContext.nseg = 0;
+	io_request->RaidContext.raid_context.raid_flags = 0;
+	io_request->RaidContext.raid_context.type = 0;
+	io_request->RaidContext.raid_context.nseg = 0;
 
 	memcpy(io_request->CDB.CDB32, scp->cmnd, scp->cmd_len);
 	/*
@@ -2124,11 +2378,16 @@ megasas_build_io_fusion(struct megasas_instance *instance,
 		return 1;
 	}
 
-	/* numSGE store lower 8 bit of sge_count.
-	 * numSGEExt store higher 8 bit of sge_count
-	 */
-	io_request->RaidContext.numSGE = sge_count;
-	io_request->RaidContext.numSGEExt = (u8)(sge_count >> 8);
+	if (instance->is_ventura)
+		io_request->RaidContext.raid_context_g35.num_sge = sge_count;
+	else {
+		/* numSGE store lower 8 bit of sge_count.
+		 * numSGEExt store higher 8 bit of sge_count
+		 */
+		io_request->RaidContext.raid_context.num_sge = sge_count;
+		io_request->RaidContext.raid_context.num_sge_ext =
+			(u8)(sge_count >> 8);
+	}
 
 	io_request->SGLFlags = cpu_to_le16(MPI2_SGE_FLAGS_64_BIT_ADDRESSING);
 
@@ -2155,19 +2414,151 @@ megasas_get_request_descriptor(struct megasas_instance *instance, u16 index)
 	u8 *p;
 	struct fusion_context *fusion;
 
-	if (index >= instance->max_fw_cmds) {
+	if (index >= instance->max_mpt_cmds) {
 		dev_err(&instance->pdev->dev, "Invalid SMID (0x%x)request for "
 		       "descriptor for scsi%d\n", index,
 			instance->host->host_no);
 		return NULL;
 	}
 	fusion = instance->ctrl_context;
-	p = fusion->req_frames_desc
-		+sizeof(union MEGASAS_REQUEST_DESCRIPTOR_UNION) *index;
+	p = fusion->req_frames_desc +
+		sizeof(union MEGASAS_REQUEST_DESCRIPTOR_UNION) * index;
 
 	return (union MEGASAS_REQUEST_DESCRIPTOR_UNION *)p;
 }
 
+/*
+ * megasas_fpio_to_ldio-
+ * This function converts an fp io to ldio
+ */
+
+void megasas_fpio_to_ldio(struct megasas_instance *instance,
+	struct megasas_cmd_fusion *cmd, struct scsi_cmnd *scmd)
+{
+	struct fusion_context *fusion;
+	union RAID_CONTEXT_UNION *praid_context;
+	struct MR_LD_RAID *raid;
+	struct MR_DRV_RAID_MAP_ALL *local_map_ptr;
+	u32 device_id, ld;
+
+	fusion = instance->ctrl_context;
+	cmd->request_desc->SCSIIO.RequestFlags =
+		(MEGASAS_REQ_DESCRIPT_FLAGS_LD_IO
+		<< MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
+	cmd->io_request->Function = MEGASAS_MPI2_FUNCTION_LD_IO_REQUEST;
+	cmd->io_request->DevHandle = cpu_to_le16(MEGASAS_DEV_INDEX(scmd));
+
+	/*remove FAST PATH ENABLE bit in IoFlags */
+	cmd->io_request->IoFlags &=
+	cpu_to_le16(~MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH);
+
+	/* if the numSGE > max_sge_in_main_sge set the chain offset*/
+	if (cmd->io_request->RaidContext.raid_context_g35.num_sge >
+		fusion->max_sge_in_main_msg)
+		cmd->io_request->ChainOffset = fusion->chain_offset_io_request;
+	memcpy(cmd->io_request->CDB.CDB32, scmd->cmnd, scmd->cmd_len);
+	cmd->io_request->CDB.EEDP32.PrimaryReferenceTag = 0;
+	cmd->io_request->CDB.EEDP32.PrimaryApplicationTagMask = 0;
+	cmd->io_request->EEDPFlags = 0;
+	cmd->io_request->Control = 0;
+	cmd->io_request->EEDPBlockSize = 0;
+	cmd->is_raid_1_fp_write = 0;
+
+	device_id = MEGASAS_DEV_INDEX(cmd->scmd);
+	local_map_ptr = fusion->ld_drv_map[(instance->map_id & 1)];
+	ld = MR_TargetIdToLdGet(device_id, local_map_ptr);
+	raid = MR_LdRaidGet(ld, local_map_ptr);
+	praid_context = &cmd->io_request->RaidContext;
+	if (cmd->scmd->sc_data_direction == PCI_DMA_FROMDEVICE) {
+		if ((raid->cpuAffinity.ldRead.cpu0)
+		&& (raid->cpuAffinity.ldRead.cpu1))
+			praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+			= MR_RAID_CTX_CPUSEL_FCFS;
+		else if (raid->cpuAffinity.ldRead.cpu1)
+			praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+			= MR_RAID_CTX_CPUSEL_1;
+		else
+			praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+			= MR_RAID_CTX_CPUSEL_0;
+	} else {
+	if ((raid->cpuAffinity.ldWrite.cpu0)
+		&& (raid->cpuAffinity.ldWrite.cpu1))
+		praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+			= MR_RAID_CTX_CPUSEL_FCFS;
+	else if (raid->cpuAffinity.ldWrite.cpu1)
+		praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+			= MR_RAID_CTX_CPUSEL_1;
+	else
+		praid_context->raid_context_g35.routing_flags.bits.cpu_sel
+		= MR_RAID_CTX_CPUSEL_0;
+	}
+}
+
+/* megasas_prepate_secondRaid1_IO
+ *  It prepares the raid 1 second IO
+ */
+void megasas_prepare_secondRaid1_IO(struct megasas_instance *instance,
+			    struct megasas_cmd_fusion *cmd,
+			    struct megasas_cmd_fusion *r1_cmd)
+{
+	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc, *req_desc2 = NULL;
+	struct fusion_context *fusion;
+
+	fusion = instance->ctrl_context;
+	req_desc = cmd->request_desc;
+	if (r1_cmd) {
+		/* copy the io request frame as well
+		 *  as 8 SGEs data for r1 command
+		 */
+		memcpy(r1_cmd->io_request, cmd->io_request,
+			sizeof(struct MPI2_RAID_SCSI_IO_REQUEST));
+		memcpy(&r1_cmd->io_request->SGL, &cmd->io_request->SGL,
+				(fusion->max_sge_in_main_msg *
+				sizeof(union MPI2_SGE_IO_UNION)));
+		/*sense buffer is different for r1 command*/
+		r1_cmd->io_request->SenseBufferLowAddress =
+				cpu_to_le32(r1_cmd->sense_phys_addr);
+		r1_cmd->scmd = cmd->scmd;
+		req_desc2 =
+		megasas_get_request_descriptor(instance, r1_cmd->index-1);
+		if (req_desc2) {
+			req_desc2->Words = 0;
+			r1_cmd->request_desc = req_desc2;
+			req_desc2->SCSIIO.SMID =
+				cpu_to_le16(r1_cmd->index);
+			req_desc2->SCSIIO.RequestFlags =
+				req_desc->SCSIIO.RequestFlags;
+			r1_cmd->is_raid_1_fp_write = 1;
+			r1_cmd->request_desc->SCSIIO.DevHandle =
+				cmd->r1_alt_dev_handle;
+			r1_cmd->io_request->DevHandle = cmd->r1_alt_dev_handle;
+			cmd->io_request->RaidContext.raid_context_g35.smid.peer_smid =
+				 cpu_to_le16(r1_cmd->index);
+			r1_cmd->io_request->RaidContext.raid_context_g35.smid.peer_smid =
+				cpu_to_le16(cmd->index);
+			/* MSIxIndex of both commands request
+			 * descriptors should be same
+			 */
+			r1_cmd->request_desc->SCSIIO.MSIxIndex =
+				cmd->request_desc->SCSIIO.MSIxIndex;
+			/*span arm is different for r1 cmd*/
+			r1_cmd->io_request->RaidContext.raid_context_g35.span_arm =
+			cmd->io_request->RaidContext.raid_context_g35.span_arm + 1;
+		} else {
+			megasas_return_cmd_fusion(instance, r1_cmd);
+			dev_info(&instance->pdev->dev,
+				"unable to get request descriptor, firing as normal IO\n");
+			atomic_dec(&instance->fw_outstanding);
+			megasas_fpio_to_ldio(instance, cmd, cmd->scmd);
+		}
+	} else {
+		dev_info(&instance->pdev->dev,
+			"unable to get command, firing as normal IO\n");
+		atomic_dec(&instance->fw_outstanding);
+		megasas_fpio_to_ldio(instance, cmd, cmd->scmd);
+	}
+}
+
 /**
  * megasas_build_and_issue_cmd_fusion -Main routine for building and
  *                                     issuing non IOCTL cmd
@@ -2178,7 +2569,7 @@ static u32
 megasas_build_and_issue_cmd_fusion(struct megasas_instance *instance,
 				   struct scsi_cmnd *scmd)
 {
-	struct megasas_cmd_fusion *cmd;
+	struct megasas_cmd_fusion *cmd, *r1_cmd = NULL;
 	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc;
 	u32 index;
 	struct fusion_context *fusion;
@@ -2193,13 +2584,26 @@ megasas_build_and_issue_cmd_fusion(struct megasas_instance *instance,
 		return SCSI_MLQUEUE_DEVICE_BUSY;
 	}
 
+	if (atomic_inc_return(&instance->fw_outstanding) >
+			instance->host->can_queue) {
+		atomic_dec(&instance->fw_outstanding);
+		return SCSI_MLQUEUE_HOST_BUSY;
+	}
+
 	cmd = megasas_get_cmd_fusion(instance, scmd->request->tag);
 
+	if (!cmd) {
+		atomic_dec(&instance->fw_outstanding);
+		return SCSI_MLQUEUE_HOST_BUSY;
+	}
+
 	index = cmd->index;
 
 	req_desc = megasas_get_request_descriptor(instance, index-1);
-	if (!req_desc)
+	if (!req_desc) {
+		atomic_dec(&instance->fw_outstanding);
 		return SCSI_MLQUEUE_HOST_BUSY;
+	}
 
 	req_desc->Words = 0;
 	cmd->request_desc = req_desc;
@@ -2208,6 +2612,7 @@ megasas_build_and_issue_cmd_fusion(struct megasas_instance *instance,
 		megasas_return_cmd_fusion(instance, cmd);
 		dev_err(&instance->pdev->dev, "Error building command\n");
 		cmd->request_desc = NULL;
+		atomic_dec(&instance->fw_outstanding);
 		return SCSI_MLQUEUE_HOST_BUSY;
 	}
 
@@ -2218,13 +2623,41 @@ megasas_build_and_issue_cmd_fusion(struct megasas_instance *instance,
 	    cmd->io_request->ChainOffset != 0xF)
 		dev_err(&instance->pdev->dev, "The chain offset value is not "
 		       "correct : %x\n", cmd->io_request->ChainOffset);
+	/*
+	 *	if it is raid 1/10 fp write capable.
+	 *	try to get second command from pool and construct it.
+	 *	From FW, it has confirmed that lba values of two PDs
+	 *	corresponds to single R1/10 LD are always same
+	 *
+	 */
+	/*	driver side count always should be less than max_fw_cmds
+	 *	to get new command
+	 */
+	if (cmd->is_raid_1_fp_write &&
+		(atomic_inc_return(&instance->fw_outstanding) >
+			(instance->host->can_queue) ||
+		(!atomic_read(&instance->r1_write_fp_capable)))) {
+		megasas_fpio_to_ldio(instance, cmd, cmd->scmd);
+		atomic_dec(&instance->fw_outstanding);
+	} else if (cmd->is_raid_1_fp_write) {
+		r1_cmd = megasas_get_cmd_fusion(instance,
+				(scmd->request->tag + instance->max_fw_cmds));
+		megasas_prepare_secondRaid1_IO(instance, cmd, r1_cmd);
+	}
 
 	/*
 	 * Issue the command to the FW
 	 */
-	atomic_inc(&instance->fw_outstanding);
+	if (scmd->sc_data_direction == PCI_DMA_TODEVICE && instance->is_ventura)
+		atomic64_add(scsi_bufflen(scmd), &instance->bytes_wrote);
 
-	megasas_fire_cmd_fusion(instance, req_desc);
+	megasas_fire_cmd_fusion(instance, req_desc, instance->is_ventura);
+
+	if (r1_cmd) {
+		atomic64_add(scsi_bufflen(scmd), &instance->bytes_wrote);
+		megasas_fire_cmd_fusion(instance, r1_cmd->request_desc,
+			instance->is_ventura);
+	}
 
 	return 0;
 }
@@ -2242,10 +2675,10 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 	struct MPI2_RAID_SCSI_IO_REQUEST *scsi_io_req;
 	struct fusion_context *fusion;
 	struct megasas_cmd *cmd_mfi;
-	struct megasas_cmd_fusion *cmd_fusion;
+	struct megasas_cmd_fusion *cmd_fusion, *r1_cmd = NULL;
 	u16 smid, num_completed;
-	u8 reply_descript_type;
-	u32 status, extStatus, device_id;
+	u8 reply_descript_type, *sense;
+	u32 status, extStatus, device_id, data_length;
 	union desc_value d_val;
 	struct LD_LOAD_BALANCE_INFO *lbinfo;
 	int threshold_reply_count = 0;
@@ -2275,6 +2708,15 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 
 	while (d_val.u.low != cpu_to_le32(UINT_MAX) &&
 	       d_val.u.high != cpu_to_le32(UINT_MAX)) {
+		   /*
+		    * Ensure that the peer command is NULL here in case a
+		    * command has completed but the R1 FP Write peer has
+		    * not completed yet.If not null, it's possible that
+		    * another thread will complete the peer
+		    * command and should not.
+		    */
+		r1_cmd = NULL;
+
 		smid = le16_to_cpu(reply_desc->SMID);
 
 		cmd_fusion = fusion->cmd_list[smid - 1];
@@ -2287,8 +2729,10 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 			cmd_fusion->scmd->SCp.ptr = NULL;
 
 		scmd_local = cmd_fusion->scmd;
-		status = scsi_io_req->RaidContext.status;
-		extStatus = scsi_io_req->RaidContext.exStatus;
+		status = scsi_io_req->RaidContext.raid_context.status;
+		extStatus = scsi_io_req->RaidContext.raid_context.ex_status;
+		sense = cmd_fusion->sense;
+		data_length = scsi_io_req->DataLength;
 
 		switch (scsi_io_req->Function) {
 		case MPI2_FUNCTION_SCSI_TASK_MGMT:
@@ -2305,12 +2749,28 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 			/* Update load balancing info */
 			device_id = MEGASAS_DEV_INDEX(scmd_local);
 			lbinfo = &fusion->load_balance_info[device_id];
-			if (cmd_fusion->scmd->SCp.Status &
-			    MEGASAS_LOAD_BALANCE_FLAG) {
+			/*
+			 * check for the raid 1/10 fast path writes
+			 */
+			if (!cmd_fusion->is_raid_1_fp_write &&
+				(cmd_fusion->scmd->SCp.Status &
+					MEGASAS_LOAD_BALANCE_FLAG)) {
 				atomic_dec(&lbinfo->scsi_pending_cmds[cmd_fusion->pd_r1_lb]);
 				cmd_fusion->scmd->SCp.Status &=
 					~MEGASAS_LOAD_BALANCE_FLAG;
+			} else if (cmd_fusion->is_raid_1_fp_write) {
+				/* get peer command */
+				if (cmd_fusion->index < instance->max_fw_cmds)
+					r1_cmd = fusion->cmd_list[(cmd_fusion->index +
+					instance->max_fw_cmds)-1];
+				else {
+					r1_cmd =
+					fusion->cmd_list[(cmd_fusion->index -
+						 instance->max_fw_cmds)-1];
+				}
+				cmd_fusion->cmd_completed = true;
 			}
+
 			if (reply_descript_type ==
 			    MPI2_RPY_DESCRIPT_FLAGS_SCSI_IO_SUCCESS) {
 				if (megasas_dbg_lvl == 5)
@@ -2320,14 +2780,49 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 			/* Fall thru and complete IO */
 		case MEGASAS_MPI2_FUNCTION_LD_IO_REQUEST: /* LD-IO Path */
 			/* Map the FW Cmd Status */
-			map_cmd_status(cmd_fusion, status, extStatus);
-			scsi_io_req->RaidContext.status = 0;
-			scsi_io_req->RaidContext.exStatus = 0;
-			if (megasas_cmd_type(scmd_local) == READ_WRITE_LDIO)
-				atomic_dec(&instance->ldio_outstanding);
-			megasas_return_cmd_fusion(instance, cmd_fusion);
-			scsi_dma_unmap(scmd_local);
-			scmd_local->scsi_done(scmd_local);
+			/*
+			 * check for the raid 1/10 fast path writes
+			 */
+			if (r1_cmd &&  r1_cmd->is_raid_1_fp_write
+				&& r1_cmd->cmd_completed) {
+				/*
+				 * if the peer  Raid  1/10 fast path failed,
+				 * mark IO as failed to the scsi layer.
+				 * over write the current status by the failed
+				 * status makes sure that if any one of
+				 * command fails,return fail status to
+				 * scsi layer
+				 */
+				if (r1_cmd->io_request->RaidContext.raid_context.status !=
+								MFI_STAT_OK) {
+					status =
+					r1_cmd->io_request->RaidContext.raid_context.status;
+					extStatus =
+					r1_cmd->io_request->RaidContext.raid_context.ex_status;
+					data_length =
+						r1_cmd->io_request->DataLength;
+					sense = r1_cmd->sense;
+				}
+				r1_cmd->io_request->RaidContext.raid_context.status = 0;
+				r1_cmd->io_request->RaidContext.raid_context.ex_status = 0;
+				cmd_fusion->is_raid_1_fp_write = 0;
+				r1_cmd->is_raid_1_fp_write = 0;
+				r1_cmd->cmd_completed = false;
+				cmd_fusion->cmd_completed = false;
+				megasas_return_cmd_fusion(instance, r1_cmd);
+			}
+			if (!cmd_fusion->is_raid_1_fp_write) {
+				map_cmd_status(fusion, scmd_local, status,
+					extStatus, data_length, sense);
+				scsi_io_req->RaidContext.raid_context.status = 0;
+				scsi_io_req->RaidContext.raid_context.ex_status = 0;
+				if (instance->ldio_threshold
+					&& megasas_cmd_type(scmd_local) == READ_WRITE_LDIO)
+					atomic_dec(&instance->ldio_outstanding);
+				megasas_return_cmd_fusion(instance, cmd_fusion);
+				scsi_dma_unmap(scmd_local);
+				scmd_local->scsi_done(scmd_local);
+			}
 			atomic_dec(&instance->fw_outstanding);
 
 			break;
@@ -2376,7 +2871,7 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 		 * pending to be completed
 		 */
 		if (threshold_reply_count >= THRESHOLD_REPLY_COUNT) {
-			if (fusion->adapter_type == INVADER_SERIES)
+			if (instance->msix_combined)
 				writel(((MSIxIndex & 0x7) << 24) |
 					fusion->last_reply_idx[MSIxIndex],
 					instance->reply_post_host_index_addr[MSIxIndex/8]);
@@ -2392,7 +2887,7 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 		return IRQ_NONE;
 
 	wmb();
-	if (fusion->adapter_type == INVADER_SERIES)
+	if (instance->msix_combined)
 		writel(((MSIxIndex & 0x7) << 24) |
 			fusion->last_reply_idx[MSIxIndex],
 			instance->reply_post_host_index_addr[MSIxIndex/8]);
@@ -2518,7 +3013,7 @@ build_mpt_mfi_pass_thru(struct megasas_instance *instance,
 
 	io_req = cmd->io_request;
 
-	if (fusion->adapter_type == INVADER_SERIES) {
+	if (fusion->adapter_type >= INVADER_SERIES) {
 		struct MPI25_IEEE_SGE_CHAIN64 *sgl_ptr_end =
 			(struct MPI25_IEEE_SGE_CHAIN64 *)&io_req->SGL;
 		sgl_ptr_end += fusion->max_sge_in_main_msg - 1;
@@ -2595,7 +3090,7 @@ megasas_issue_dcmd_fusion(struct megasas_instance *instance,
 		return DCMD_NOT_FIRED;
 	}
 
-	megasas_fire_cmd_fusion(instance, req_desc);
+	megasas_fire_cmd_fusion(instance, req_desc, instance->is_ventura);
 	return DCMD_SUCCESS;
 }
 
@@ -2888,7 +3383,8 @@ void megasas_refire_mgmt_cmd(struct megasas_instance *instance)
 				cpu_to_le32(MR_DCMD_SYSTEM_PD_MAP_GET_INFO)))
 				&& !(cmd_mfi->flags & DRV_DCMD_SKIP_REFIRE);
 		if (refire_cmd)
-			megasas_fire_cmd_fusion(instance, req_desc);
+			megasas_fire_cmd_fusion(instance, req_desc,
+				instance->is_ventura);
 		else
 			megasas_return_cmd(instance, cmd_mfi);
 	}
@@ -3067,7 +3563,7 @@ megasas_issue_tm(struct megasas_instance *instance, u16 device_handle,
 		mr_request->tmReqFlags.isTMForLD = 1;
 
 	init_completion(&cmd_fusion->done);
-	megasas_fire_cmd_fusion(instance, req_desc);
+	megasas_fire_cmd_fusion(instance, req_desc, instance->is_ventura);
 
 	timeleft = wait_for_completion_timeout(&cmd_fusion->done, 50 * HZ);
 
@@ -3377,9 +3873,9 @@ int megasas_check_mpio_paths(struct megasas_instance *instance,
 /* Core fusion reset function */
 int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 {
-	int retval = SUCCESS, i, convert = 0;
+	int retval = SUCCESS, i, j, convert = 0;
 	struct megasas_instance *instance;
-	struct megasas_cmd_fusion *cmd_fusion;
+	struct megasas_cmd_fusion *cmd_fusion, *mpt_cmd_fusion;
 	struct fusion_context *fusion;
 	u32 abs_state, status_reg, reset_adapter;
 	u32 io_timeout_in_crash_mode = 0;
@@ -3454,20 +3950,34 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 		/* Now return commands back to the OS */
 		for (i = 0 ; i < instance->max_scsi_cmds; i++) {
 			cmd_fusion = fusion->cmd_list[i];
+			/*check for extra commands issued by driver*/
+			if (instance->is_ventura) {
+				cmd_fusion->is_raid_1_fp_write = 0;
+				cmd_fusion->cmd_completed = false;
+				mpt_cmd_fusion =
+				fusion->cmd_list[i + instance->max_fw_cmds];
+				mpt_cmd_fusion->is_raid_1_fp_write = 0;
+				mpt_cmd_fusion->cmd_completed = false;
+				if (mpt_cmd_fusion->scmd)
+					megasas_return_cmd_fusion(instance,
+						mpt_cmd_fusion);
+			}
 			scmd_local = cmd_fusion->scmd;
 			if (cmd_fusion->scmd) {
 				scmd_local->result =
 					megasas_check_mpio_paths(instance,
 							scmd_local);
-				if (megasas_cmd_type(scmd_local) == READ_WRITE_LDIO)
+				if (instance->ldio_threshold &&
+					megasas_cmd_type(scmd_local) == READ_WRITE_LDIO)
 					atomic_dec(&instance->ldio_outstanding);
 				megasas_return_cmd_fusion(instance, cmd_fusion);
 				scsi_dma_unmap(scmd_local);
 				scmd_local->scsi_done(scmd_local);
-				atomic_dec(&instance->fw_outstanding);
 			}
 		}
 
+		atomic_set(&instance->fw_outstanding, 0);
+
 		status_reg = instance->instancet->read_fw_status_reg(
 			instance->reg_set);
 		abs_state = status_reg & MFI_STATE_MASK;
@@ -3542,6 +4052,16 @@ transition_to_ready:
 			shost_for_each_device(sdev, shost)
 				megasas_update_sdev_properties(sdev);
 
+			/* reset stream detection array */
+			if (instance->is_ventura) {
+				for (j = 0; j < MAX_LOGICAL_DRIVES_EXT; ++j) {
+					memset(fusion->stream_detect_by_ld[j],
+					0, sizeof(struct LD_STREAM_DETECT));
+				 fusion->stream_detect_by_ld[j]->mru_bit_map
+						= MR_STREAM_BITMAP;
+				}
+			}
+
 			clear_bit(MEGASAS_FUSION_IN_RESET,
 				  &instance->reset_flags);
 			instance->instancet->enable_intr(instance);
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.h b/drivers/scsi/megaraid/megaraid_sas_fusion.h
index e3bee04c1eb1..3addd0cb2e99 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.h
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.h
@@ -59,6 +59,8 @@
 #define	MR_RL_FLAGS_GRANT_DESTINATION_CPU1	    0x10
 #define	MR_RL_FLAGS_GRANT_DESTINATION_CUDA	    0x80
 #define MR_RL_FLAGS_SEQ_NUM_ENABLE		    0x8
+#define MR_RL_WRITE_THROUGH_MODE		    0x00
+#define MR_RL_WRITE_BACK_MODE			    0x01
 
 /* T10 PI defines */
 #define MR_PROT_INFO_TYPE_CONTROLLER                0x8
@@ -81,6 +83,11 @@
 enum MR_RAID_FLAGS_IO_SUB_TYPE {
 	MR_RAID_FLAGS_IO_SUB_TYPE_NONE = 0,
 	MR_RAID_FLAGS_IO_SUB_TYPE_SYSTEM_PD = 1,
+	MR_RAID_FLAGS_IO_SUB_TYPE_RMW_DATA     = 2,
+	MR_RAID_FLAGS_IO_SUB_TYPE_RMW_P        = 3,
+	MR_RAID_FLAGS_IO_SUB_TYPE_RMW_Q        = 4,
+	MR_RAID_FLAGS_IO_SUB_TYPE_CACHE_BYPASS = 6,
+	MR_RAID_FLAGS_IO_SUB_TYPE_LDIO_BW_LIMIT = 7
 };
 
 /*
@@ -94,11 +101,13 @@ enum MR_RAID_FLAGS_IO_SUB_TYPE {
 #define MEGASAS_FP_CMD_LEN	16
 #define MEGASAS_FUSION_IN_RESET 0
 #define THRESHOLD_REPLY_COUNT 50
+#define RAID_1_10_RMW_CMDS 3
 #define JBOD_MAPS_COUNT	2
 
 enum MR_FUSION_ADAPTER_TYPE {
 	THUNDERBOLT_SERIES = 0,
 	INVADER_SERIES = 1,
+	VENTURA_SERIES = 2,
 };
 
 /*
@@ -108,29 +117,104 @@ enum MR_FUSION_ADAPTER_TYPE {
 
 struct RAID_CONTEXT {
 #if   defined(__BIG_ENDIAN_BITFIELD)
-	u8	nseg:4;
-	u8	Type:4;
+	u8 nseg:4;
+	u8 type:4;
 #else
-	u8	Type:4;
-	u8	nseg:4;
+	u8 type:4;
+	u8 nseg:4;
 #endif
-	u8	resvd0;
-	__le16	timeoutValue;
-	u8      regLockFlags;
-	u8      resvd1;
-	__le16	VirtualDiskTgtId;
-	__le64	regLockRowLBA;
-	__le32	regLockLength;
-	__le16	nextLMId;
-	u8      exStatus;
-	u8      status;
-	u8      RAIDFlags;
-	u8      numSGE;
-	__le16	configSeqNum;
-	u8      spanArm;
-	u8      priority;
-	u8	numSGEExt;
-	u8      resvd2;
+	u8 resvd0;
+	__le16 timeout_value;
+	u8 reg_lock_flags;
+	u8 resvd1;
+	__le16 virtual_disk_tgt_id;
+	__le64 reg_lock_row_lba;
+	__le32 reg_lock_length;
+	__le16 next_lmid;
+	u8 ex_status;
+	u8 status;
+	u8 raid_flags;
+	u8 num_sge;
+	__le16 config_seq_num;
+	u8 span_arm;
+	u8 priority;
+	u8 num_sge_ext;
+	u8 resvd2;
+};
+
+/*
+ * Raid Context structure which describes ventura MegaRAID specific
+ * IO Paramenters ,This resides at offset 0x60 where the SGL normally
+ * starts in MPT IO Frames
+ */
+struct RAID_CONTEXT_G35 {
+#if   defined(__BIG_ENDIAN_BITFIELD)
+	u16	resvd0:8;
+	u16	nseg:4;
+	u16	type:4;
+#else
+	u16	type:4;		    /* 0x00 */
+	u16	nseg:4;		    /* 0x00 */
+	u16 resvd0:8;
+#endif
+	u16 timeout_value; /* 0x02 -0x03 */
+	union {
+		struct {
+#if	defined(__BIG_ENDIAN_BITFIELD)
+		u16	set_divert:4;
+		u16	cpu_sel:4;
+		u16	log:1;
+		u16	rw:1;
+		u16	sbs:1;
+		u16	sqn:1;
+		u16	fwn:1;
+		u16	c2f:1;
+		u16	sld:1;
+		u16	reserved:1;
+#else
+		u16	reserved:1;
+		u16	sld:1;
+		u16	c2f:1;
+		u16	fwn:1;
+		u16	sqn:1;
+		u16	sbs:1;
+		u16	rw:1;
+		u16	log:1;
+		u16	cpu_sel:4;
+		u16	set_divert:4;
+#endif
+			} bits;
+		u16 s;
+	} routing_flags;	/* 0x04 -0x05 routing flags */
+	u16 virtual_disk_tgt_id;   /* 0x06 -0x07 */
+	u64 reg_lock_row_lba;      /* 0x08 - 0x0F */
+	u32 reg_lock_length;      /* 0x10 - 0x13 */
+	union {
+		u16 next_lmid; /* 0x14 - 0x15 */
+		u16	peer_smid;	/* used for the raid 1/10 fp writes */
+	} smid;
+	u8 ex_status;       /* 0x16 : OUT */
+	u8 status;          /* 0x17 status */
+	u8 raid_flags;		/* 0x18 resvd[7:6], ioSubType[5:4],
+				 * resvd[3:1], preferredCpu[0]
+				 */
+	u8 span_arm;            /* 0x1C span[7:5], arm[4:0] */
+	u16	config_seq_num;           /* 0x1A -0x1B */
+#if   defined(__BIG_ENDIAN_BITFIELD) /* 0x1C - 0x1D */
+	u16 stream_detected:1;
+	u16 reserved:3;
+	u16 num_sge:12;
+#else
+	u16 num_sge:12;
+	u16 reserved:3;
+	u16 stream_detected:1;
+#endif
+	u8 resvd2[2];          /* 0x1E-0x1F */
+};
+
+union RAID_CONTEXT_UNION {
+	struct RAID_CONTEXT raid_context;
+	struct RAID_CONTEXT_G35 raid_context_g35;
 };
 
 #define RAID_CTX_SPANARM_ARM_SHIFT	(0)
@@ -139,6 +223,14 @@ struct RAID_CONTEXT {
 #define RAID_CTX_SPANARM_SPAN_SHIFT	(5)
 #define RAID_CTX_SPANARM_SPAN_MASK	(0xE0)
 
+/* number of bits per index in U32 TrackStream */
+#define BITS_PER_INDEX_STREAM		4
+#define INVALID_STREAM_NUM              16
+#define MR_STREAM_BITMAP		0x76543210
+#define STREAM_MASK			((1 << BITS_PER_INDEX_STREAM) - 1)
+#define ZERO_LAST_STREAM		0x0fffffff
+#define MAX_STREAMS_TRACKED		8
+
 /*
  * define region lock types
  */
@@ -175,6 +267,8 @@ enum REGION_TYPE {
 #define MPI2_SCSIIO_EEDPFLAGS_CHECK_APPTAG          (0x0200)
 #define MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD           (0x0100)
 #define MPI2_SCSIIO_EEDPFLAGS_INSERT_OP             (0x0004)
+/* EEDP escape mode */
+#define MPI25_SCSIIO_EEDPFLAGS_DO_NOT_DISABLE_MODE  (0x0040)
 #define MPI2_FUNCTION_SCSI_IO_REQUEST               (0x00) /* SCSI IO */
 #define MPI2_FUNCTION_SCSI_TASK_MGMT                (0x01)
 #define MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY       (0x03)
@@ -407,7 +501,7 @@ struct MPI2_RAID_SCSI_IO_REQUEST {
 	u8                      LUN[8];                         /* 0x34 */
 	__le32			Control;                        /* 0x3C */
 	union MPI2_SCSI_IO_CDB_UNION  CDB;			/* 0x40 */
-	struct RAID_CONTEXT	RaidContext;                    /* 0x60 */
+	union RAID_CONTEXT_UNION RaidContext;  /* 0x60 */
 	union MPI2_SGE_IO_UNION       SGL;			/* 0x80 */
 };
 
@@ -586,14 +680,17 @@ struct MPI2_IOC_INIT_REQUEST {
 #define MAX_RAIDMAP_ROW_SIZE (MAX_ROW_SIZE)
 #define MAX_LOGICAL_DRIVES 64
 #define MAX_LOGICAL_DRIVES_EXT 256
+#define MAX_LOGICAL_DRIVES_DYN 512
 #define MAX_RAIDMAP_LOGICAL_DRIVES (MAX_LOGICAL_DRIVES)
 #define MAX_RAIDMAP_VIEWS (MAX_LOGICAL_DRIVES)
 #define MAX_ARRAYS 128
 #define MAX_RAIDMAP_ARRAYS (MAX_ARRAYS)
 #define MAX_ARRAYS_EXT	256
 #define MAX_API_ARRAYS_EXT (MAX_ARRAYS_EXT)
+#define MAX_API_ARRAYS_DYN 512
 #define MAX_PHYSICAL_DEVICES 256
 #define MAX_RAIDMAP_PHYSICAL_DEVICES (MAX_PHYSICAL_DEVICES)
+#define MAX_RAIDMAP_PHYSICAL_DEVICES_DYN 512
 #define MR_DCMD_LD_MAP_GET_INFO             0x0300e101
 #define MR_DCMD_SYSTEM_PD_MAP_GET_INFO      0x0200e102
 #define MR_DCMD_CTRL_SHARED_HOST_MEM_ALLOC  0x010e8485   /* SR-IOV HB alloc*/
@@ -640,10 +737,56 @@ struct MR_SPAN_BLOCK_INFO {
 	struct MR_SPAN_INFO block_span_info;
 };
 
+#define MR_RAID_CTX_CPUSEL_0		0
+#define MR_RAID_CTX_CPUSEL_1		1
+#define MR_RAID_CTX_CPUSEL_2		2
+#define MR_RAID_CTX_CPUSEL_3		3
+#define MR_RAID_CTX_CPUSEL_FCFS		0xF
+
+struct MR_CPU_AFFINITY_MASK {
+	union {
+		struct {
+#ifndef MFI_BIG_ENDIAN
+		u8 hw_path:1;
+		u8 cpu0:1;
+		u8 cpu1:1;
+		u8 cpu2:1;
+		u8 cpu3:1;
+		u8 reserved:3;
+#else
+		u8 reserved:3;
+		u8 cpu3:1;
+		u8 cpu2:1;
+		u8 cpu1:1;
+		u8 cpu0:1;
+		u8 hw_path:1;
+#endif
+		};
+		u8 core_mask;
+	};
+};
+
+struct MR_IO_AFFINITY {
+	union {
+		struct {
+			struct MR_CPU_AFFINITY_MASK pdRead;
+			struct MR_CPU_AFFINITY_MASK pdWrite;
+			struct MR_CPU_AFFINITY_MASK ldRead;
+			struct MR_CPU_AFFINITY_MASK ldWrite;
+			};
+		u32 word;
+		};
+	u8 maxCores;    /* Total cores + HW Path in ROC */
+	u8 reserved[3];
+};
+
 struct MR_LD_RAID {
 	struct {
 #if   defined(__BIG_ENDIAN_BITFIELD)
-		u32     reserved4:5;
+		u32 reserved4:2;
+		u32 fp_cache_bypass_capable:1;
+		u32 fp_rmw_capable:1;
+		u32 disable_coalescing:1;
 		u32     fpBypassRegionLock:1;
 		u32     tmCapable:1;
 		u32	fpNonRWCapable:1;
@@ -654,11 +797,13 @@ struct MR_LD_RAID {
 		u32     encryptionType:8;
 		u32     pdPiMode:4;
 		u32     ldPiMode:4;
-		u32     reserved5:3;
+		u32 reserved5:2;
+		u32 ra_capable:1;
 		u32     fpCapable:1;
 #else
 		u32     fpCapable:1;
-		u32     reserved5:3;
+		u32 ra_capable:1;
+		u32 reserved5:2;
 		u32     ldPiMode:4;
 		u32     pdPiMode:4;
 		u32     encryptionType:8;
@@ -669,7 +814,10 @@ struct MR_LD_RAID {
 		u32	fpNonRWCapable:1;
 		u32     tmCapable:1;
 		u32     fpBypassRegionLock:1;
-		u32     reserved4:5;
+		u32 disable_coalescing:1;
+		u32 fp_rmw_capable:1;
+		u32 fp_cache_bypass_capable:1;
+		u32 reserved4:2;
 #endif
 	} capability;
 	__le32     reserved6;
@@ -696,7 +844,36 @@ struct MR_LD_RAID {
 
 	u8	LUN[8]; /* 0x24 8 byte LUN field used for SCSI IO's */
 	u8	fpIoTimeoutForLd;/*0x2C timeout value used by driver in FP IO*/
-	u8      reserved3[0x80-0x2D]; /* 0x2D */
+	/* Ox2D This LD accept priority boost of this type */
+	u8 ld_accept_priority_type;
+	u8 reserved2[2];	        /* 0x2E - 0x2F */
+	/* 0x30 - 0x33, Logical block size for the LD */
+	u32 logical_block_length;
+	struct {
+#ifndef MFI_BIG_ENDIAN
+	/* 0x34, P_I_EXPONENT from READ CAPACITY 16 */
+	u32 ld_pi_exp:4;
+	/* 0x34, LOGICAL BLOCKS PER PHYSICAL
+	 *  BLOCK EXPONENT from READ CAPACITY 16
+	 */
+	u32 ld_logical_block_exp:4;
+	u32 reserved1:24;           /* 0x34 */
+#else
+	u32 reserved1:24;           /* 0x34 */
+	/* 0x34, LOGICAL BLOCKS PER PHYSICAL
+	 *  BLOCK EXPONENT from READ CAPACITY 16
+	 */
+	u32 ld_logical_block_exp:4;
+	/* 0x34, P_I_EXPONENT from READ CAPACITY 16 */
+	u32 ld_pi_exp:4;
+#endif
+	};                               /* 0x34 - 0x37 */
+	 /* 0x38 - 0x3f, This will determine which
+	  *  core will process LD IO and PD IO.
+	  */
+	struct MR_IO_AFFINITY cpuAffinity;
+     /* Bit definiations are specified by MR_IO_AFFINITY */
+	u8 reserved3[0x80-0x40];    /* 0x40 - 0x7f */
 };
 
 struct MR_LD_SPAN_MAP {
@@ -743,6 +920,9 @@ struct IO_REQUEST_INFO {
 	u64 start_row;
 	u8  span_arm;	/* span[7:5], arm[4:0] */
 	u8  pd_after_lb;
+	u16 r1_alt_dev_handle; /* raid 1/10 only */
+	bool is_raid_1_fp_write;
+	bool ra_capable;
 };
 
 struct MR_LD_TARGET_SYNC {
@@ -751,6 +931,91 @@ struct MR_LD_TARGET_SYNC {
 	__le16 seqNum;
 };
 
+/*
+ * RAID Map descriptor Types.
+ * Each element should uniquely idetify one data structure in the RAID map
+ */
+enum MR_RAID_MAP_DESC_TYPE {
+	/* MR_DEV_HANDLE_INFO data */
+	RAID_MAP_DESC_TYPE_DEVHDL_INFO    = 0x0,
+	/* target to Ld num Index map */
+	RAID_MAP_DESC_TYPE_TGTID_INFO     = 0x1,
+	/* MR_ARRAY_INFO data */
+	RAID_MAP_DESC_TYPE_ARRAY_INFO     = 0x2,
+	/* MR_LD_SPAN_MAP data */
+	RAID_MAP_DESC_TYPE_SPAN_INFO      = 0x3,
+	RAID_MAP_DESC_TYPE_COUNT,
+};
+
+/*
+ * This table defines the offset, size and num elements  of each descriptor
+ * type in the RAID Map buffer
+ */
+struct MR_RAID_MAP_DESC_TABLE {
+	/* Raid map descriptor type */
+	u32 raid_map_desc_type;
+	/* Offset into the RAID map buffer where
+	 *  descriptor data is saved
+	 */
+	u32 raid_map_desc_offset;
+	/* total size of the
+	 * descriptor buffer
+	 */
+	u32 raid_map_desc_buffer_size;
+	/* Number of elements contained in the
+	 *  descriptor buffer
+	 */
+	u32 raid_map_desc_elements;
+};
+
+/*
+ * Dynamic Raid Map Structure.
+ */
+struct MR_FW_RAID_MAP_DYNAMIC {
+	u32 raid_map_size;   /* total size of RAID Map structure */
+	u32 desc_table_offset;/* Offset of desc table into RAID map*/
+	u32 desc_table_size;  /* Total Size of desc table */
+	/* Total Number of elements in the desc table */
+	u32 desc_table_num_elements;
+	u64	pci_threshold_bandwidth;
+	u32	reserved2[3];	/*future use */
+	/* timeout value used by driver in FP IOs */
+	u8 fp_pd_io_timeout_sec;
+	u8 reserved3[3];
+	/* when this seqNum increments, driver needs to
+	 *  release RMW buffers asap
+	 */
+	u32 rmw_fp_seq_num;
+	u16 ld_count;	/* count of lds. */
+	u16 ar_count;   /* count of arrays */
+	u16 span_count; /* count of spans */
+	u16 reserved4[3];
+/*
+ * The below structure of pointers is only to be used by the driver.
+ * This is added in the ,API to reduce the amount of code changes
+ * needed in the driver to support dynamic RAID map Firmware should
+ * not update these pointers while preparing the raid map
+ */
+	union {
+		struct {
+			struct MR_DEV_HANDLE_INFO  *dev_hndl_info;
+			u16 *ld_tgt_id_to_ld;
+			struct MR_ARRAY_INFO *ar_map_info;
+			struct MR_LD_SPAN_MAP *ld_span_map;
+			};
+		u64 ptr_structure_size[RAID_MAP_DESC_TYPE_COUNT];
+		};
+/*
+ * RAID Map descriptor table defines the layout of data in the RAID Map.
+ * The size of the descriptor table itself could change.
+ */
+	/* Variable Size descriptor Table. */
+	struct MR_RAID_MAP_DESC_TABLE
+			raid_map_desc_table[RAID_MAP_DESC_TYPE_COUNT];
+	/* Variable Size buffer containing all data */
+	u32 raid_map_desc_data[1];
+}; /* Dynamicaly sized RAID MAp structure */
+
 #define IEEE_SGE_FLAGS_ADDR_MASK            (0x03)
 #define IEEE_SGE_FLAGS_SYSTEM_ADDR          (0x00)
 #define IEEE_SGE_FLAGS_IOCDDR_ADDR          (0x01)
@@ -795,6 +1060,10 @@ struct megasas_cmd_fusion {
 	u32 index;
 	u8 pd_r1_lb;
 	struct completion done;
+	bool is_raid_1_fp_write;
+	u16 r1_alt_dev_handle; /* raid 1/10 only*/
+	bool cmd_completed;  /* raid 1/10 fp writes status holder */
+
 };
 
 struct LD_LOAD_BALANCE_INFO {
@@ -856,9 +1125,10 @@ struct MR_DRV_RAID_MAP {
 	__le16                 spanCount;
 	__le16                 reserve3;
 
-	struct MR_DEV_HANDLE_INFO  devHndlInfo[MAX_RAIDMAP_PHYSICAL_DEVICES];
-	u8                  ldTgtIdToLd[MAX_LOGICAL_DRIVES_EXT];
-	struct MR_ARRAY_INFO       arMapInfo[MAX_API_ARRAYS_EXT];
+	struct MR_DEV_HANDLE_INFO
+		devHndlInfo[MAX_RAIDMAP_PHYSICAL_DEVICES_DYN];
+	u16 ldTgtIdToLd[MAX_LOGICAL_DRIVES_DYN];
+	struct MR_ARRAY_INFO arMapInfo[MAX_API_ARRAYS_DYN];
 	struct MR_LD_SPAN_MAP      ldSpanMap[1];
 
 };
@@ -870,7 +1140,7 @@ struct MR_DRV_RAID_MAP {
 struct MR_DRV_RAID_MAP_ALL {
 
 	struct MR_DRV_RAID_MAP raidMap;
-	struct MR_LD_SPAN_MAP      ldSpanMap[MAX_LOGICAL_DRIVES_EXT - 1];
+	struct MR_LD_SPAN_MAP ldSpanMap[MAX_LOGICAL_DRIVES_DYN - 1];
 } __packed;
 
 
@@ -919,7 +1189,8 @@ struct MR_PD_CFG_SEQ {
 		u8     reserved:7;
 #endif
 	} capability;
-	u8  reserved[3];
+	u8  reserved;
+	u16 pd_target_id;
 } __packed;
 
 struct MR_PD_CFG_SEQ_NUM_SYNC {
@@ -928,6 +1199,30 @@ struct MR_PD_CFG_SEQ_NUM_SYNC {
 	struct MR_PD_CFG_SEQ seq[1];
 } __packed;
 
+/* stream detection */
+struct STREAM_DETECT {
+	u64 next_seq_lba; /* next LBA to match sequential access */
+	struct megasas_cmd_fusion *first_cmd_fusion; /* first cmd in group */
+	struct megasas_cmd_fusion *last_cmd_fusion; /* last cmd in group */
+	u32 count_cmds_in_stream; /* count of host commands in this stream */
+	u16 num_sges_in_group; /* total number of SGEs in grouped IOs */
+	u8 is_read; /* SCSI OpCode for this stream */
+	u8 group_depth; /* total number of host commands in group */
+	/* TRUE if cannot add any more commands to this group */
+	bool group_flush;
+	u8 reserved[7]; /* pad to 64-bit alignment */
+};
+
+struct LD_STREAM_DETECT {
+	bool write_back; /* TRUE if WB, FALSE if WT */
+	bool fp_write_enabled;
+	bool members_ssds;
+	bool fp_cache_bypass_capable;
+	u32 mru_bit_map; /* bitmap used to track MRU and LRU stream indicies */
+	/* this is the array of stream detect structures (one per stream) */
+	struct STREAM_DETECT stream_track[MAX_STREAMS_TRACKED];
+};
+
 struct MPI2_IOC_INIT_RDPQ_ARRAY_ENTRY {
 	u64 RDPQBaseAddress;
 	u32 Reserved1;
@@ -965,7 +1260,7 @@ struct fusion_context {
 	u8	chain_offset_io_request;
 	u8	chain_offset_mfi_pthru;
 
-	struct MR_FW_RAID_MAP_ALL *ld_map[2];
+	struct MR_FW_RAID_MAP_DYNAMIC *ld_map[2];
 	dma_addr_t ld_map_phys[2];
 
 	/*Non dma-able memory. Driver local copy.*/
@@ -973,6 +1268,8 @@ struct fusion_context {
 
 	u32 max_map_sz;
 	u32 current_map_sz;
+	u32 old_map_sz;
+	u32 new_map_sz;
 	u32 drv_map_sz;
 	u32 drv_map_pages;
 	struct MR_PD_CFG_SEQ_NUM_SYNC	*pd_seq_sync[JBOD_MAPS_COUNT];
@@ -981,6 +1278,7 @@ struct fusion_context {
 	struct LD_LOAD_BALANCE_INFO load_balance_info[MAX_LOGICAL_DRIVES_EXT];
 	LD_SPAN_INFO log_to_span[MAX_LOGICAL_DRIVES_EXT];
 	u8 adapter_type;
+	struct LD_STREAM_DETECT **stream_detect_by_ld;
 };
 
 union desc_value {
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h b/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
index 8bae305bc156..af4be403582e 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
@@ -624,6 +624,8 @@ typedef struct _MPI26_EVENT_DATA_ACTIVE_CABLE_EXCEPT {
 
 /* defines for ReasonCode field */
 #define MPI26_EVENT_ACTIVE_CABLE_INSUFFICIENT_POWER     (0x00)
+#define MPI26_EVENT_ACTIVE_CABLE_PRESENT                (0x01)
+#define MPI26_EVENT_ACTIVE_CABLE_DEGRADED               (0x02)
 
 /*Hard Reset Received Event data */
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index f00ef88a378a..a3fe1fb55c17 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -1040,6 +1040,25 @@ _base_interrupt(int irq, void *bus_id)
 		    reply_q->reply_post_free[reply_q->reply_post_host_index].
 		    Default.ReplyFlags & MPI2_RPY_DESCRIPT_FLAGS_TYPE_MASK;
 		completed_cmds++;
+		/* Update the reply post host index after continuously
+		 * processing the threshold number of Reply Descriptors.
+		 * So that FW can find enough entries to post the Reply
+		 * Descriptors in the reply descriptor post queue.
+		 */
+		if (completed_cmds > ioc->hba_queue_depth/3) {
+			if (ioc->combined_reply_queue) {
+				writel(reply_q->reply_post_host_index |
+						((msix_index  & 7) <<
+						 MPI2_RPHI_MSIX_INDEX_SHIFT),
+				    ioc->replyPostRegisterIndex[msix_index/8]);
+			} else {
+				writel(reply_q->reply_post_host_index |
+						(msix_index <<
+						 MPI2_RPHI_MSIX_INDEX_SHIFT),
+						&ioc->chip->ReplyPostHostIndex);
+			}
+			completed_cmds = 1;
+		}
 		if (request_desript_type == MPI2_RPY_DESCRIPT_FLAGS_UNUSED)
 			goto out;
 		if (!reply_q->reply_post_host_index)
@@ -5522,6 +5541,7 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 		goto out_free_resources;
 
 	ioc->non_operational_loop = 0;
+	ioc->got_task_abort_from_ioctl = 0;
 	return 0;
 
  out_free_resources:
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index dcb33f4fa687..4ab634fc27df 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -73,9 +73,9 @@
 #define MPT3SAS_DRIVER_NAME		"mpt3sas"
 #define MPT3SAS_AUTHOR "Avago Technologies <MPT-FusionLinux.pdl@avagotech.com>"
 #define MPT3SAS_DESCRIPTION	"LSI MPT Fusion SAS 3.0 Device Driver"
-#define MPT3SAS_DRIVER_VERSION		"14.101.00.00"
-#define MPT3SAS_MAJOR_VERSION		14
-#define MPT3SAS_MINOR_VERSION		101
+#define MPT3SAS_DRIVER_VERSION		"15.100.00.00"
+#define MPT3SAS_MAJOR_VERSION		15
+#define MPT3SAS_MINOR_VERSION		100
 #define MPT3SAS_BUILD_VERSION		0
 #define MPT3SAS_RELEASE_VERSION	00
 
@@ -1000,6 +1000,7 @@ struct MPT3SAS_ADAPTER {
 	u8		broadcast_aen_busy;
 	u16		broadcast_aen_pending;
 	u8		shost_recovery;
+	u8		got_task_abort_from_ioctl;
 
 	struct mutex	reset_in_progress_mutex;
 	spinlock_t	ioc_reset_in_progress_lock;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 95f0f24bac05..02fe1c4aae2f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -826,16 +826,18 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 			"TASK_MGMT: handle(0x%04x), task_type(0x%02x)\n",
 			ioc->name,
 		    le16_to_cpu(tm_request->DevHandle), tm_request->TaskType));
-
+		ioc->got_task_abort_from_ioctl = 1;
 		if (tm_request->TaskType ==
 		    MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK ||
 		    tm_request->TaskType ==
 		    MPI2_SCSITASKMGMT_TASKTYPE_QUERY_TASK) {
 			if (_ctl_set_task_mid(ioc, &karg, tm_request)) {
 				mpt3sas_base_free_smid(ioc, smid);
+				ioc->got_task_abort_from_ioctl = 0;
 				goto out;
 			}
 		}
+		ioc->got_task_abort_from_ioctl = 0;
 
 		if (test_bit(device_handle, ioc->device_remove_in_progress)) {
 			dtmprintk(ioc, pr_info(MPT3SAS_FMT
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 75f3fce1c867..81a64678390d 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -1074,6 +1074,26 @@ _scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 }
 
 /**
+ * __scsih_scsi_lookup_get_clear - returns scmd entry without
+ *						holding any lock.
+ * @ioc: per adapter object
+ * @smid: system request message index
+ *
+ * Returns the smid stored scmd pointer.
+ * Then will dereference the stored scmd pointer.
+ */
+static inline struct scsi_cmnd *
+__scsih_scsi_lookup_get_clear(struct MPT3SAS_ADAPTER *ioc,
+		u16 smid)
+{
+	struct scsi_cmnd *scmd = NULL;
+
+	swap(scmd, ioc->scsi_lookup[smid - 1].scmd);
+
+	return scmd;
+}
+
+/**
  * _scsih_scsi_lookup_get_clear - returns scmd entry
  * @ioc: per adapter object
  * @smid: system request message index
@@ -1088,8 +1108,7 @@ _scsih_scsi_lookup_get_clear(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 	struct scsi_cmnd *scmd;
 
 	spin_lock_irqsave(&ioc->scsi_lookup_lock, flags);
-	scmd = ioc->scsi_lookup[smid - 1].scmd;
-	ioc->scsi_lookup[smid - 1].scmd = NULL;
+	scmd = __scsih_scsi_lookup_get_clear(ioc, smid);
 	spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
 
 	return scmd;
@@ -4657,9 +4676,16 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	struct MPT3SAS_DEVICE *sas_device_priv_data;
 	u32 response_code = 0;
 	unsigned long flags;
+	unsigned int sector_sz;
 
 	mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply);
-	scmd = _scsih_scsi_lookup_get_clear(ioc, smid);
+
+	if (ioc->broadcast_aen_busy || ioc->pci_error_recovery ||
+			ioc->got_task_abort_from_ioctl)
+		scmd = _scsih_scsi_lookup_get_clear(ioc, smid);
+	else
+		scmd = __scsih_scsi_lookup_get_clear(ioc, smid);
+
 	if (scmd == NULL)
 		return 1;
 
@@ -4715,6 +4741,20 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	}
 
 	xfer_cnt = le32_to_cpu(mpi_reply->TransferCount);
+
+	/* In case of bogus fw or device, we could end up having
+	 * unaligned partial completion. We can force alignment here,
+	 * then scsi-ml does not need to handle this misbehavior.
+	 */
+	sector_sz = scmd->device->sector_size;
+	if (unlikely(!blk_rq_is_passthrough(scmd->request) && sector_sz &&
+		     xfer_cnt % sector_sz)) {
+		sdev_printk(KERN_INFO, scmd->device,
+		    "unaligned partial completion avoided (xfer_cnt=%u, sector_sz=%u)\n",
+			    xfer_cnt, sector_sz);
+		xfer_cnt = round_down(xfer_cnt, sector_sz);
+	}
+
 	scsi_set_resid(scmd, scsi_bufflen(scmd) - xfer_cnt);
 	if (ioc_status & MPI2_IOCSTATUS_FLAG_LOG_INFO_AVAILABLE)
 		log_info =  le32_to_cpu(mpi_reply->IOCLogInfo);
@@ -8028,15 +8068,24 @@ mpt3sas_scsih_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
 	case MPI2_EVENT_ACTIVE_CABLE_EXCEPTION:
 		ActiveCableEventData =
 		    (Mpi26EventDataActiveCableExcept_t *) mpi_reply->EventData;
-		if (ActiveCableEventData->ReasonCode ==
-				MPI26_EVENT_ACTIVE_CABLE_INSUFFICIENT_POWER) {
-			pr_info(MPT3SAS_FMT "Currently an active cable with ReceptacleID %d",
-			    ioc->name, ActiveCableEventData->ReceptacleID);
-			pr_info("cannot be powered and devices connected to this active cable");
-			pr_info("will not be seen. This active cable");
-			pr_info("requires %d mW of power",
-			    ActiveCableEventData->ActiveCablePowerRequirement);
+		switch (ActiveCableEventData->ReasonCode) {
+		case MPI26_EVENT_ACTIVE_CABLE_INSUFFICIENT_POWER:
+			pr_notice(MPT3SAS_FMT "Receptacle ID %d: This active cable"
+				  " requires %d mW of power\n", ioc->name,
+			     ActiveCableEventData->ReceptacleID,
+			     ActiveCableEventData->ActiveCablePowerRequirement);
+			pr_notice(MPT3SAS_FMT "Receptacle ID %d: Devices connected"
+				  " to this active cable will not be seen\n",
+			     ioc->name, ActiveCableEventData->ReceptacleID);
+			break;
+
+		case MPI26_EVENT_ACTIVE_CABLE_DEGRADED:
+			pr_notice(MPT3SAS_FMT "ReceptacleID %d: This cable",
+				ioc->name, ActiveCableEventData->ReceptacleID);
+			pr_notice(" is not running at an optimal speed(12 Gb/s)\n");
+			break;
 		}
+
 		break;
 
 	default: /* ignore the rest */
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index 337982cf3d63..49e70a383afa 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -4587,16 +4587,14 @@ static void pmcraid_tasklet_function(unsigned long instance)
 static
 void pmcraid_unregister_interrupt_handler(struct pmcraid_instance *pinstance)
 {
+	struct pci_dev *pdev = pinstance->pdev;
 	int i;
 
 	for (i = 0; i < pinstance->num_hrrq; i++)
-		free_irq(pinstance->hrrq_vector[i].vector,
-			 &(pinstance->hrrq_vector[i]));
+		free_irq(pci_irq_vector(pdev, i), &pinstance->hrrq_vector[i]);
 
-	if (pinstance->interrupt_mode) {
-		pci_disable_msix(pinstance->pdev);
-		pinstance->interrupt_mode = 0;
-	}
+	pinstance->interrupt_mode = 0;
+	pci_free_irq_vectors(pdev);
 }
 
 /**
@@ -4609,60 +4607,52 @@ void pmcraid_unregister_interrupt_handler(struct pmcraid_instance *pinstance)
 static int
 pmcraid_register_interrupt_handler(struct pmcraid_instance *pinstance)
 {
-	int rc;
 	struct pci_dev *pdev = pinstance->pdev;
+	unsigned int irq_flag = PCI_IRQ_LEGACY, flag;
+	int num_hrrq, rc, i;
+	irq_handler_t isr;
 
-	if ((pmcraid_enable_msix) &&
-		(pci_find_capability(pdev, PCI_CAP_ID_MSIX))) {
-		int num_hrrq = PMCRAID_NUM_MSIX_VECTORS;
-		struct msix_entry entries[PMCRAID_NUM_MSIX_VECTORS];
-		int i;
-		for (i = 0; i < PMCRAID_NUM_MSIX_VECTORS; i++)
-			entries[i].entry = i;
-
-		num_hrrq = pci_enable_msix_range(pdev, entries, 1, num_hrrq);
-		if (num_hrrq < 0)
-			goto pmcraid_isr_legacy;
-
-		for (i = 0; i < num_hrrq; i++) {
-			pinstance->hrrq_vector[i].hrrq_id = i;
-			pinstance->hrrq_vector[i].drv_inst = pinstance;
-			pinstance->hrrq_vector[i].vector = entries[i].vector;
-			rc = request_irq(pinstance->hrrq_vector[i].vector,
-					pmcraid_isr_msix, 0,
-					PMCRAID_DRIVER_NAME,
-					&(pinstance->hrrq_vector[i]));
-
-			if (rc) {
-				int j;
-				for (j = 0; j < i; j++)
-					free_irq(entries[j].vector,
-						 &(pinstance->hrrq_vector[j]));
-				pci_disable_msix(pdev);
-				goto pmcraid_isr_legacy;
-			}
-		}
+	if (pmcraid_enable_msix)
+		irq_flag |= PCI_IRQ_MSIX;
 
-		pinstance->num_hrrq = num_hrrq;
+	num_hrrq = pci_alloc_irq_vectors(pdev, 1, PMCRAID_NUM_MSIX_VECTORS,
+			irq_flag);
+	if (num_hrrq < 0)
+		return num_hrrq;
+
+	if (pdev->msix_enabled) {
+		flag = 0;
+		isr = pmcraid_isr_msix;
+	} else {
+		flag = IRQF_SHARED;
+		isr = pmcraid_isr;
+	}
+
+	for (i = 0; i < num_hrrq; i++) {
+		struct pmcraid_isr_param *vec = &pinstance->hrrq_vector[i];
+
+		vec->hrrq_id = i;
+		vec->drv_inst = pinstance;
+		rc = request_irq(pci_irq_vector(pdev, i), isr, flag,
+				PMCRAID_DRIVER_NAME, vec);
+		if (rc)
+			goto out_unwind;
+	}
+
+	pinstance->num_hrrq = num_hrrq;
+	if (pdev->msix_enabled) {
 		pinstance->interrupt_mode = 1;
 		iowrite32(DOORBELL_INTR_MODE_MSIX,
 			  pinstance->int_regs.host_ioa_interrupt_reg);
 		ioread32(pinstance->int_regs.host_ioa_interrupt_reg);
-		goto pmcraid_isr_out;
 	}
 
-pmcraid_isr_legacy:
-	/* If MSI-X registration failed fallback to legacy mode, where
-	 * only one hrrq entry will be used
-	 */
-	pinstance->hrrq_vector[0].hrrq_id = 0;
-	pinstance->hrrq_vector[0].drv_inst = pinstance;
-	pinstance->hrrq_vector[0].vector = pdev->irq;
-	pinstance->num_hrrq = 1;
-
-	rc = request_irq(pdev->irq, pmcraid_isr, IRQF_SHARED,
-			 PMCRAID_DRIVER_NAME, &pinstance->hrrq_vector[0]);
-pmcraid_isr_out:
+	return 0;
+
+out_unwind:
+	while (--i > 0)
+		free_irq(pci_irq_vector(pdev, i), &pinstance->hrrq_vector[i]);
+	pci_free_irq_vectors(pdev);
 	return rc;
 }
 
diff --git a/drivers/scsi/pmcraid.h b/drivers/scsi/pmcraid.h
index e1d150f3fd4d..568b18a2f47d 100644
--- a/drivers/scsi/pmcraid.h
+++ b/drivers/scsi/pmcraid.h
@@ -628,7 +628,6 @@ struct pmcraid_interrupts {
 /* ISR parameters LLD allocates (one for each MSI-X if enabled) vectors */
 struct pmcraid_isr_param {
 	struct pmcraid_instance *drv_inst;
-	u16 vector;			/* allocated msi-x vector */
 	u8 hrrq_id;			/* hrrq entry index */
 };
 
diff --git a/drivers/scsi/qedi/qedi_dbg.c b/drivers/scsi/qedi/qedi_dbg.c
index 2bdedb9c39bc..8fd28b056f73 100644
--- a/drivers/scsi/qedi/qedi_dbg.c
+++ b/drivers/scsi/qedi/qedi_dbg.c
@@ -52,7 +52,7 @@ qedi_dbg_warn(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
 	vaf.va = &va;
 
 	if (!(qedi_dbg_log & QEDI_LOG_WARN))
-		return;
+		goto ret;
 
 	if (likely(qedi) && likely(qedi->pdev))
 		pr_warn("[%s]:[%s:%d]:%d: %pV", dev_name(&qedi->pdev->dev),
@@ -60,6 +60,7 @@ qedi_dbg_warn(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
 	else
 		pr_warn("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
 
+ret:
 	va_end(va);
 }
 
@@ -80,7 +81,7 @@ qedi_dbg_notice(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
 	vaf.va = &va;
 
 	if (!(qedi_dbg_log & QEDI_LOG_NOTICE))
-		return;
+		goto ret;
 
 	if (likely(qedi) && likely(qedi->pdev))
 		pr_notice("[%s]:[%s:%d]:%d: %pV",
@@ -89,6 +90,7 @@ qedi_dbg_notice(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
 	else
 		pr_notice("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
 
+ret:
 	va_end(va);
 }
 
@@ -109,7 +111,7 @@ qedi_dbg_info(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
 	vaf.va = &va;
 
 	if (!(qedi_dbg_log & level))
-		return;
+		goto ret;
 
 	if (likely(qedi) && likely(qedi->pdev))
 		pr_info("[%s]:[%s:%d]:%d: %pV", dev_name(&qedi->pdev->dev),
@@ -117,6 +119,7 @@ qedi_dbg_info(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
 	else
 		pr_info("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
 
+ret:
 	va_end(va);
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 5b1287a63c49..2f14adfab018 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2248,7 +2248,7 @@ struct ct_fdmiv2_hba_attr {
 		uint32_t num_ports;
 		uint8_t fabric_name[WWN_SIZE];
 		uint8_t bios_name[32];
-		uint8_t vendor_indentifer[8];
+		uint8_t vendor_identifier[8];
 	} a;
 };
 
@@ -2423,7 +2423,7 @@ struct ct_sns_req {
 		} rsnn_nn;
 
 		struct {
-			uint8_t hba_indentifier[8];
+			uint8_t hba_identifier[8];
 		} ghat;
 
 		struct {
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index 94e8a8592f69..ee3df8794806 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -1939,15 +1939,15 @@ qla2x00_fdmiv2_rhba(scsi_qla_host_t *vha)
 	/* Vendor Identifier */
 	eiter = entries + size;
 	eiter->type = cpu_to_be16(FDMI_HBA_TYPE_VENDOR_IDENTIFIER);
-	snprintf(eiter->a.vendor_indentifer, sizeof(eiter->a.vendor_indentifer),
+	snprintf(eiter->a.vendor_identifier, sizeof(eiter->a.vendor_identifier),
 	    "%s", "QLGC");
-	alen = strlen(eiter->a.vendor_indentifer);
+	alen = strlen(eiter->a.vendor_identifier);
 	alen += 4 - (alen & 3);
 	eiter->len = cpu_to_be16(4 + alen);
 	size += 4 + alen;
 
 	ql_dbg(ql_dbg_disc, vha, 0x20b1,
-	    "Vendor Identifier = %s.\n", eiter->a.vendor_indentifer);
+	    "Vendor Identifier = %s.\n", eiter->a.vendor_identifier);
 
 	/* Update MS request size. */
 	qla2x00_update_ms_fdmi_iocb(vha, size + 16);
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 67e157d81da8..edc2264db45b 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -2997,14 +2997,14 @@ struct qla_init_msix_entry {
 	irq_handler_t handler;
 };
 
-static struct qla_init_msix_entry msix_entries[] = {
+static const struct qla_init_msix_entry msix_entries[] = {
 	{ "qla2xxx (default)", qla24xx_msix_default },
 	{ "qla2xxx (rsp_q)", qla24xx_msix_rsp_q },
 	{ "qla2xxx (atio_q)", qla83xx_msix_atio_q },
 	{ "qla2xxx (qpair_multiq)", qla2xxx_msix_rsp_q },
 };
 
-static struct qla_init_msix_entry qla82xx_msix_entries[] = {
+static const struct qla_init_msix_entry qla82xx_msix_entries[] = {
 	{ "qla2xxx (default)", qla82xx_msix_default },
 	{ "qla2xxx (rsp_q)", qla82xx_msix_rsp_q },
 };
@@ -3078,7 +3078,7 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 		qentry->handle = rsp;
 		rsp->msix = qentry;
 		scnprintf(qentry->name, sizeof(qentry->name),
-		    msix_entries[i].name);
+		    "%s", msix_entries[i].name);
 		if (IS_P3P_TYPE(ha))
 			ret = request_irq(qentry->vector,
 				qla82xx_msix_entries[i].handler,
@@ -3102,7 +3102,7 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 		rsp->msix = qentry;
 		qentry->handle = rsp;
 		scnprintf(qentry->name, sizeof(qentry->name),
-		    msix_entries[QLA_ATIO_VECTOR].name);
+		    "%s", msix_entries[QLA_ATIO_VECTOR].name);
 		qentry->in_use = 1;
 		ret = request_irq(qentry->vector,
 			msix_entries[QLA_ATIO_VECTOR].handler,
@@ -3244,7 +3244,7 @@ qla2x00_free_irqs(scsi_qla_host_t *vha)
 	 * from a probe failure context.
 	 */
 	if (!ha->rsp_q_map || !ha->rsp_q_map[0])
-		return;
+		goto free_irqs;
 	rsp = ha->rsp_q_map[0];
 
 	if (ha->flags.msix_enabled) {
@@ -3264,13 +3264,14 @@ qla2x00_free_irqs(scsi_qla_host_t *vha)
 		free_irq(pci_irq_vector(ha->pdev, 0), rsp);
 	}
 
+free_irqs:
 	pci_free_irq_vectors(ha->pdev);
 }
 
 int qla25xx_request_irq(struct qla_hw_data *ha, struct qla_qpair *qpair,
 	struct qla_msix_entry *msix, int vector_type)
 {
-	struct qla_init_msix_entry *intr = &msix_entries[vector_type];
+	const struct qla_init_msix_entry *intr = &msix_entries[vector_type];
 	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
 	int ret;
 
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 0a000ecf0881..40660461a4b5 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1616,7 +1616,7 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res)
 				/* Don't abort commands in adapter during EEH
 				 * recovery as it's not accessible/responding.
 				 */
-				if (!ha->flags.eeh_busy) {
+				if (GET_CMD_SP(sp) && !ha->flags.eeh_busy) {
 					/* Get a reference to the sp and drop the lock.
 					 * The reference ensures this sp->done() call
 					 * - and not the call in qla2xxx_eh_abort() -
diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h
index aeebefb1e9f8..fc233717355f 100644
--- a/drivers/scsi/qla4xxx/ql4_def.h
+++ b/drivers/scsi/qla4xxx/ql4_def.h
@@ -408,9 +408,6 @@ struct qla4_8xxx_legacy_intr_set {
 };
 
 /* MSI-X Support */
-
-#define QLA_MSIX_DEFAULT	0
-#define QLA_MSIX_RSP_Q		1
 #define QLA_MSIX_ENTRIES	2
 
 /*
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 9fbb33fc90c7..ac52150d1569 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -9539,15 +9539,15 @@ exit_host_reset:
  * driver calls the following device driver's callbacks
  *
  * - Fatal Errors - link_reset
- * - Non-Fatal Errors - driver's pci_error_detected() which
+ * - Non-Fatal Errors - driver's error_detected() which
  * returns CAN_RECOVER, NEED_RESET or DISCONNECT.
  *
  * PCI AER driver calls
- * CAN_RECOVER - driver's pci_mmio_enabled(), mmio_enabled
+ * CAN_RECOVER - driver's mmio_enabled(), mmio_enabled()
  *               returns RECOVERED or NEED_RESET if fw_hung
  * NEED_RESET - driver's slot_reset()
  * DISCONNECT - device is dead & cannot recover
- * RECOVERED - driver's pci_resume()
+ * RECOVERED - driver's resume()
  */
 static pci_ers_result_t
 qla4xxx_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 03051e12a072..17249c3650fe 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -125,6 +125,7 @@ static const char *sdebug_version_date = "20160430";
 #define DEF_OPTS   0
 #define DEF_OPT_BLKS 1024
 #define DEF_PHYSBLK_EXP 0
+#define DEF_OPT_XFERLEN_EXP 0
 #define DEF_PTYPE   TYPE_DISK
 #define DEF_REMOVABLE false
 #define DEF_SCSI_LEVEL   7    /* INQUIRY, byte2 [6->SPC-4; 7->SPC-5] */
@@ -590,6 +591,7 @@ static int sdebug_num_tgts = DEF_NUM_TGTS; /* targets per host */
 static int sdebug_opt_blks = DEF_OPT_BLKS;
 static int sdebug_opts = DEF_OPTS;
 static int sdebug_physblk_exp = DEF_PHYSBLK_EXP;
+static int sdebug_opt_xferlen_exp = DEF_OPT_XFERLEN_EXP;
 static int sdebug_ptype = DEF_PTYPE; /* SCSI peripheral device type */
 static int sdebug_scsi_level = DEF_SCSI_LEVEL;
 static int sdebug_sector_size = DEF_SECTOR_SIZE;
@@ -1205,7 +1207,11 @@ static int inquiry_vpd_b0(unsigned char *arr)
 	memcpy(arr, vpdb0_data, sizeof(vpdb0_data));
 
 	/* Optimal transfer length granularity */
-	gran = 1 << sdebug_physblk_exp;
+	if (sdebug_opt_xferlen_exp != 0 &&
+	    sdebug_physblk_exp < sdebug_opt_xferlen_exp)
+		gran = 1 << sdebug_opt_xferlen_exp;
+	else
+		gran = 1 << sdebug_physblk_exp;
 	put_unaligned_be16(gran, arr + 2);
 
 	/* Maximum Transfer Length */
@@ -4161,6 +4167,7 @@ module_param_named(num_tgts, sdebug_num_tgts, int, S_IRUGO | S_IWUSR);
 module_param_named(opt_blks, sdebug_opt_blks, int, S_IRUGO);
 module_param_named(opts, sdebug_opts, int, S_IRUGO | S_IWUSR);
 module_param_named(physblk_exp, sdebug_physblk_exp, int, S_IRUGO);
+module_param_named(opt_xferlen_exp, sdebug_opt_xferlen_exp, int, S_IRUGO);
 module_param_named(ptype, sdebug_ptype, int, S_IRUGO | S_IWUSR);
 module_param_named(removable, sdebug_removable, bool, S_IRUGO | S_IWUSR);
 module_param_named(scsi_level, sdebug_scsi_level, int, S_IRUGO);
@@ -4212,6 +4219,7 @@ MODULE_PARM_DESC(num_tgts, "number of targets per host to simulate(def=1)");
 MODULE_PARM_DESC(opt_blks, "optimal transfer length in blocks (def=1024)");
 MODULE_PARM_DESC(opts, "1->noise, 2->medium_err, 4->timeout, 8->recovered_err... (def=0)");
 MODULE_PARM_DESC(physblk_exp, "physical block exponent (def=0)");
+MODULE_PARM_DESC(opt_xferlen_exp, "optimal transfer length granularity exponent (def=physblk_exp)");
 MODULE_PARM_DESC(ptype, "SCSI peripheral type(def=0[disk])");
 MODULE_PARM_DESC(removable, "claim to have removable media (def=0)");
 MODULE_PARM_DESC(scsi_level, "SCSI level to simulate(def=7[SPC-5])");
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 40b4038c019e..cb6e68dd6df0 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -703,7 +703,7 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 
 /**
  * sd_setup_discard_cmnd - unmap blocks on thinly provisioned device
- * @sdp: scsi device to operate one
+ * @sdp: scsi device to operate on
  * @rq: Request to prepare
  *
  * Will issue either UNMAP or WRITE SAME(16) depending on preference
@@ -3226,7 +3226,7 @@ static int sd_probe(struct device *dev)
  *	sd_remove - called whenever a scsi disk (previously recognized by
  *	sd_probe) is detached from the system. It is called (potentially
  *	multiple times) during sd module unload.
- *	@sdp: pointer to mid level scsi device object
+ *	@dev: pointer to device object
  *
  *	Note: this function is invoked from the scsi mid-level.
  *	This function potentially frees up a device name (e.g. /dev/sdc)
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 05526b71541b..ceadf6b4ebc1 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -136,6 +136,8 @@ struct hv_fc_wwn_packet {
 #define SRB_FLAGS_PORT_DRIVER_RESERVED		0x0F000000
 #define SRB_FLAGS_CLASS_DRIVER_RESERVED		0xF0000000
 
+#define SP_UNTAGGED			((unsigned char) ~0)
+#define SRB_SIMPLE_TAG_REQUEST		0x20
 
 /*
  * Platform neutral description of a scsi request -
@@ -375,6 +377,7 @@ enum storvsc_request_type {
 #define SRB_STATUS_SUCCESS	0x01
 #define SRB_STATUS_ABORTED	0x02
 #define SRB_STATUS_ERROR	0x04
+#define SRB_STATUS_DATA_OVERRUN	0x12
 
 #define SRB_STATUS(status) \
 	(status & ~(SRB_STATUS_AUTOSENSE_VALID | SRB_STATUS_QUEUE_FROZEN))
@@ -458,6 +461,15 @@ struct storvsc_device {
 	 * Max I/O, the device can support.
 	 */
 	u32   max_transfer_bytes;
+	/*
+	 * Number of sub-channels we will open.
+	 */
+	u16 num_sc;
+	struct vmbus_channel **stor_chns;
+	/*
+	 * Mask of CPUs bound to subchannels.
+	 */
+	struct cpumask alloced_cpus;
 	/* Used for vsc/vsp channel reset process */
 	struct storvsc_cmd_request init_request;
 	struct storvsc_cmd_request reset_request;
@@ -635,6 +647,11 @@ static void handle_sc_creation(struct vmbus_channel *new_sc)
 		   (void *)&props,
 		   sizeof(struct vmstorage_channel_properties),
 		   storvsc_on_channel_callback, new_sc);
+
+	if (new_sc->state == CHANNEL_OPENED_STATE) {
+		stor_device->stor_chns[new_sc->target_cpu] = new_sc;
+		cpumask_set_cpu(new_sc->target_cpu, &stor_device->alloced_cpus);
+	}
 }
 
 static void  handle_multichannel_storage(struct hv_device *device, int max_chns)
@@ -651,6 +668,7 @@ static void  handle_multichannel_storage(struct hv_device *device, int max_chns)
 	if (!stor_device)
 		return;
 
+	stor_device->num_sc = num_sc;
 	request = &stor_device->init_request;
 	vstor_packet = &request->vstor_packet;
 
@@ -838,6 +856,25 @@ static int storvsc_channel_init(struct hv_device *device, bool is_fc)
 	 * support multi-channel.
 	 */
 	max_chns = vstor_packet->storage_channel_properties.max_channel_cnt;
+
+	/*
+	 * Allocate state to manage the sub-channels.
+	 * We allocate an array based on the numbers of possible CPUs
+	 * (Hyper-V does not support cpu online/offline).
+	 * This Array will be sparseley populated with unique
+	 * channels - primary + sub-channels.
+	 * We will however populate all the slots to evenly distribute
+	 * the load.
+	 */
+	stor_device->stor_chns = kzalloc(sizeof(void *) * num_possible_cpus(),
+					 GFP_KERNEL);
+	if (stor_device->stor_chns == NULL)
+		return -ENOMEM;
+
+	stor_device->stor_chns[device->channel->target_cpu] = device->channel;
+	cpumask_set_cpu(device->channel->target_cpu,
+			&stor_device->alloced_cpus);
+
 	if (vmstor_proto_version >= VMSTOR_PROTO_VERSION_WIN8) {
 		if (vstor_packet->storage_channel_properties.flags &
 		    STORAGE_CHANNEL_SUPPORTS_MULTI_CHANNEL)
@@ -889,6 +926,13 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb,
 	switch (SRB_STATUS(vm_srb->srb_status)) {
 	case SRB_STATUS_ERROR:
 		/*
+		 * Let upper layer deal with error when
+		 * sense message is present.
+		 */
+
+		if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID)
+			break;
+		/*
 		 * If there is an error; offline the device since all
 		 * error recovery strategies would have already been
 		 * deployed on the host side. However, if the command
@@ -953,6 +997,7 @@ static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request,
 	struct scsi_cmnd *scmnd = cmd_request->cmd;
 	struct scsi_sense_hdr sense_hdr;
 	struct vmscsi_request *vm_srb;
+	u32 data_transfer_length;
 	struct Scsi_Host *host;
 	u32 payload_sz = cmd_request->payload_sz;
 	void *payload = cmd_request->payload;
@@ -960,6 +1005,7 @@ static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request,
 	host = stor_dev->host;
 
 	vm_srb = &cmd_request->vstor_packet.vm_srb;
+	data_transfer_length = vm_srb->data_transfer_length;
 
 	scmnd->result = vm_srb->scsi_status;
 
@@ -973,13 +1019,20 @@ static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request,
 					     &sense_hdr);
 	}
 
-	if (vm_srb->srb_status != SRB_STATUS_SUCCESS)
+	if (vm_srb->srb_status != SRB_STATUS_SUCCESS) {
 		storvsc_handle_error(vm_srb, scmnd, host, sense_hdr.asc,
 					 sense_hdr.ascq);
+		/*
+		 * The Windows driver set data_transfer_length on
+		 * SRB_STATUS_DATA_OVERRUN. On other errors, this value
+		 * is untouched.  In these cases we set it to 0.
+		 */
+		if (vm_srb->srb_status != SRB_STATUS_DATA_OVERRUN)
+			data_transfer_length = 0;
+	}
 
 	scsi_set_resid(scmnd,
-		cmd_request->payload->range.len -
-		vm_srb->data_transfer_length);
+		cmd_request->payload->range.len - data_transfer_length);
 
 	scmnd->scsi_done(scmnd);
 
@@ -1198,17 +1251,64 @@ static int storvsc_dev_remove(struct hv_device *device)
 	/* Close the channel */
 	vmbus_close(device->channel);
 
+	kfree(stor_device->stor_chns);
 	kfree(stor_device);
 	return 0;
 }
 
+static struct vmbus_channel *get_og_chn(struct storvsc_device *stor_device,
+					u16 q_num)
+{
+	u16 slot = 0;
+	u16 hash_qnum;
+	struct cpumask alloced_mask;
+	int num_channels, tgt_cpu;
+
+	if (stor_device->num_sc == 0)
+		return stor_device->device->channel;
+
+	/*
+	 * Our channel array is sparsley populated and we
+	 * initiated I/O on a processor/hw-q that does not
+	 * currently have a designated channel. Fix this.
+	 * The strategy is simple:
+	 * I. Ensure NUMA locality
+	 * II. Distribute evenly (best effort)
+	 * III. Mapping is persistent.
+	 */
+
+	cpumask_and(&alloced_mask, &stor_device->alloced_cpus,
+		    cpumask_of_node(cpu_to_node(q_num)));
+
+	num_channels = cpumask_weight(&alloced_mask);
+	if (num_channels == 0)
+		return stor_device->device->channel;
+
+	hash_qnum = q_num;
+	while (hash_qnum >= num_channels)
+		hash_qnum -= num_channels;
+
+	for_each_cpu(tgt_cpu, &alloced_mask) {
+		if (slot == hash_qnum)
+			break;
+		slot++;
+	}
+
+	stor_device->stor_chns[q_num] = stor_device->stor_chns[tgt_cpu];
+
+	return stor_device->stor_chns[q_num];
+}
+
+
 static int storvsc_do_io(struct hv_device *device,
-			 struct storvsc_cmd_request *request)
+			 struct storvsc_cmd_request *request, u16 q_num)
 {
 	struct storvsc_device *stor_device;
 	struct vstor_packet *vstor_packet;
 	struct vmbus_channel *outgoing_channel;
 	int ret = 0;
+	struct cpumask alloced_mask;
+	int tgt_cpu;
 
 	vstor_packet = &request->vstor_packet;
 	stor_device = get_out_stor_device(device);
@@ -1222,7 +1322,26 @@ static int storvsc_do_io(struct hv_device *device,
 	 * Select an an appropriate channel to send the request out.
 	 */
 
-	outgoing_channel = vmbus_get_outgoing_channel(device->channel);
+	if (stor_device->stor_chns[q_num] != NULL) {
+		outgoing_channel = stor_device->stor_chns[q_num];
+		if (outgoing_channel->target_cpu == smp_processor_id()) {
+			/*
+			 * Ideally, we want to pick a different channel if
+			 * available on the same NUMA node.
+			 */
+			cpumask_and(&alloced_mask, &stor_device->alloced_cpus,
+				    cpumask_of_node(cpu_to_node(q_num)));
+			for_each_cpu(tgt_cpu, &alloced_mask) {
+				if (tgt_cpu != outgoing_channel->target_cpu) {
+					outgoing_channel =
+					stor_device->stor_chns[tgt_cpu];
+					break;
+				}
+			}
+		}
+	} else {
+		outgoing_channel = get_og_chn(stor_device, q_num);
+	}
 
 
 	vstor_packet->flags |= REQUEST_COMPLETION_FLAG;
@@ -1267,8 +1386,6 @@ static int storvsc_do_io(struct hv_device *device,
 static int storvsc_device_configure(struct scsi_device *sdevice)
 {
 
-	blk_queue_max_segment_size(sdevice->request_queue, PAGE_SIZE);
-
 	blk_queue_bounce_limit(sdevice->request_queue, BLK_BOUNCE_ANY);
 
 	blk_queue_rq_timeout(sdevice->request_queue, (storvsc_timeout * HZ));
@@ -1451,6 +1568,13 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	vm_srb->win8_extension.srb_flags |=
 		SRB_FLAGS_DISABLE_SYNCH_TRANSFER;
 
+	if (scmnd->device->tagged_supported) {
+		vm_srb->win8_extension.srb_flags |=
+		(SRB_FLAGS_QUEUE_ACTION_ENABLE | SRB_FLAGS_NO_QUEUE_FREEZE);
+		vm_srb->win8_extension.queue_tag = SP_UNTAGGED;
+		vm_srb->win8_extension.queue_action = SRB_SIMPLE_TAG_REQUEST;
+	}
+
 	/* Build the SRB */
 	switch (scmnd->sc_data_direction) {
 	case DMA_TO_DEVICE:
@@ -1511,20 +1635,14 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 				page_to_pfn(sg_page((cur_sgl)));
 			cur_sgl = sg_next(cur_sgl);
 		}
-
-	} else if (scsi_sglist(scmnd)) {
-		payload->range.len = length;
-		payload->range.offset =
-			virt_to_phys(scsi_sglist(scmnd)) & (PAGE_SIZE-1);
-		payload->range.pfn_array[0] =
-			virt_to_phys(scsi_sglist(scmnd)) >> PAGE_SHIFT;
 	}
 
 	cmd_request->payload = payload;
 	cmd_request->payload_sz = payload_sz;
 
 	/* Invokes the vsc to start an IO */
-	ret = storvsc_do_io(dev, cmd_request);
+	ret = storvsc_do_io(dev, cmd_request, get_cpu());
+	put_cpu();
 
 	if (ret == -EAGAIN) {
 		/* no more space */
@@ -1550,6 +1668,7 @@ static struct scsi_host_template scsi_driver = {
 	/* Make sure we dont get a sg segment crosses a page boundary */
 	.dma_boundary =		PAGE_SIZE-1,
 	.no_write_same =	1,
+	.track_queue_depth =	1,
 };
 
 enum {
@@ -1680,6 +1799,11 @@ static int storvsc_probe(struct hv_device *device,
 	 * from the host.
 	 */
 	host->sg_tablesize = (stor_device->max_transfer_bytes >> PAGE_SHIFT);
+	/*
+	 * Set the number of HW queues we are supporting.
+	 */
+	if (stor_device->num_sc != 0)
+		host->nr_hw_queues = stor_device->num_sc + 1;
 
 	/* Register the HBA and start the scsi bus scan */
 	ret = scsi_add_host(host, &device->device);
@@ -1716,6 +1840,7 @@ err_out2:
 	goto err_out0;
 
 err_out1:
+	kfree(stor_device->stor_chns);
 	kfree(stor_device);
 
 err_out0:
diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c
index bcf7d05d1aab..e64b0c542f95 100644
--- a/drivers/scsi/sun3_scsi.c
+++ b/drivers/scsi/sun3_scsi.c
@@ -34,7 +34,6 @@
 #include <asm/dvma.h>
 
 #include <scsi/scsi_host.h>
-#include "sun3_scsi.h"
 
 /* minimum number of bytes to do dma on */
 #define DMA_MIN_SIZE                    129
@@ -56,11 +55,87 @@
 #define NCR5380_dma_send_setup          sun3scsi_dma_count
 #define NCR5380_dma_residual            sun3scsi_dma_residual
 
-#define NCR5380_acquire_dma_irq(instance)    (1)
-#define NCR5380_release_dma_irq(instance)
-
 #include "NCR5380.h"
 
+/* dma regs start at regbase + 8, directly after the NCR regs */
+struct sun3_dma_regs {
+	unsigned short dma_addr_hi; /* vme only */
+	unsigned short dma_addr_lo; /* vme only */
+	unsigned short dma_count_hi; /* vme only */
+	unsigned short dma_count_lo; /* vme only */
+	unsigned short udc_data; /* udc dma data reg (obio only) */
+	unsigned short udc_addr; /* uda dma addr reg (obio only) */
+	unsigned short fifo_data; /* fifo data reg,
+	                           * holds extra byte on odd dma reads
+	                           */
+	unsigned short fifo_count;
+	unsigned short csr; /* control/status reg */
+	unsigned short bpack_hi; /* vme only */
+	unsigned short bpack_lo; /* vme only */
+	unsigned short ivect; /* vme only */
+	unsigned short fifo_count_hi; /* vme only */
+};
+
+/* ucd chip specific regs - live in dvma space */
+struct sun3_udc_regs {
+	unsigned short rsel; /* select regs to load */
+	unsigned short addr_hi; /* high word of addr */
+	unsigned short addr_lo; /* low word */
+	unsigned short count; /* words to be xfer'd */
+	unsigned short mode_hi; /* high word of channel mode */
+	unsigned short mode_lo; /* low word of channel mode */
+};
+
+/* addresses of the udc registers */
+#define UDC_MODE 0x38
+#define UDC_CSR 0x2e /* command/status */
+#define UDC_CHN_HI 0x26 /* chain high word */
+#define UDC_CHN_LO 0x22 /* chain lo word */
+#define UDC_CURA_HI 0x1a /* cur reg A high */
+#define UDC_CURA_LO 0x0a /* cur reg A low */
+#define UDC_CURB_HI 0x12 /* cur reg B high */
+#define UDC_CURB_LO 0x02 /* cur reg B low */
+#define UDC_MODE_HI 0x56 /* mode reg high */
+#define UDC_MODE_LO 0x52 /* mode reg low */
+#define UDC_COUNT 0x32 /* words to xfer */
+
+/* some udc commands */
+#define UDC_RESET 0
+#define UDC_CHN_START 0xa0 /* start chain */
+#define UDC_INT_ENABLE 0x32 /* channel 1 int on */
+
+/* udc mode words */
+#define UDC_MODE_HIWORD 0x40
+#define UDC_MODE_LSEND 0xc2
+#define UDC_MODE_LRECV 0xd2
+
+/* udc reg selections */
+#define UDC_RSEL_SEND 0x282
+#define UDC_RSEL_RECV 0x182
+
+/* bits in csr reg */
+#define CSR_DMA_ACTIVE 0x8000
+#define CSR_DMA_CONFLICT 0x4000
+#define CSR_DMA_BUSERR 0x2000
+
+#define CSR_FIFO_EMPTY 0x400 /* fifo flushed? */
+#define CSR_SDB_INT 0x200 /* sbc interrupt pending */
+#define CSR_DMA_INT 0x100 /* dma interrupt pending */
+
+#define CSR_LEFT 0xc0
+#define CSR_LEFT_3 0xc0
+#define CSR_LEFT_2 0x80
+#define CSR_LEFT_1 0x40
+#define CSR_PACK_ENABLE 0x20
+
+#define CSR_DMA_ENABLE 0x10
+
+#define CSR_SEND 0x8 /* 1 = send  0 = recv */
+#define CSR_FIFO 0x2 /* reset fifo */
+#define CSR_INTR 0x4 /* interrupt enable */
+#define CSR_SCSI 0x1
+
+#define VME_DATA24 0x3d00
 
 extern int sun3_map_test(unsigned long, char *);
 
diff --git a/drivers/scsi/sun3_scsi.h b/drivers/scsi/sun3_scsi.h
deleted file mode 100644
index d22745fae328..000000000000
--- a/drivers/scsi/sun3_scsi.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/*
- * Sun3 SCSI stuff by Erik Verbruggen (erik@bigmama.xtdnet.nl)
- *
- * Sun3 DMA additions by Sam Creasey (sammy@sammy.net)
- *
- * Adapted from mac_scsinew.h:
- */
-/*
- * Cumana Generic NCR5380 driver defines
- *
- * Copyright 1993, Drew Eckhardt
- *	Visionary Computing
- *	(Unix and Linux consulting and custom programming)
- *	drew@colorado.edu
- *      +1 (303) 440-4894
- */
-
-#ifndef SUN3_SCSI_H
-#define SUN3_SCSI_H
-
-/* additional registers - mainly DMA control regs */
-/* these start at regbase + 8 -- directly after the NCR regs */
-struct sun3_dma_regs {
-	unsigned short dma_addr_hi; /* vme only */
-	unsigned short dma_addr_lo; /* vme only */
-	unsigned short dma_count_hi; /* vme only */
-	unsigned short dma_count_lo; /* vme only */
-	unsigned short udc_data; /* udc dma data reg (obio only) */
-	unsigned short udc_addr; /* uda dma addr reg (obio only) */
-	unsigned short fifo_data; /* fifo data reg, holds extra byte on
-				     odd dma reads */
-	unsigned short fifo_count; 
-	unsigned short csr; /* control/status reg */
-	unsigned short bpack_hi; /* vme only */
-	unsigned short bpack_lo; /* vme only */
-	unsigned short ivect; /* vme only */
-	unsigned short fifo_count_hi; /* vme only */
-};
-
-/* ucd chip specific regs - live in dvma space */
-struct sun3_udc_regs {
-     unsigned short rsel; /* select regs to load */
-     unsigned short addr_hi; /* high word of addr */
-     unsigned short addr_lo; /* low word */
-     unsigned short count; /* words to be xfer'd */
-     unsigned short mode_hi; /* high word of channel mode */
-     unsigned short mode_lo; /* low word of channel mode */
-};
-
-/* addresses of the udc registers */
-#define UDC_MODE 0x38 
-#define UDC_CSR 0x2e /* command/status */
-#define UDC_CHN_HI 0x26 /* chain high word */
-#define UDC_CHN_LO 0x22 /* chain lo word */
-#define UDC_CURA_HI 0x1a /* cur reg A high */
-#define UDC_CURA_LO 0x0a /* cur reg A low */
-#define UDC_CURB_HI 0x12 /* cur reg B high */
-#define UDC_CURB_LO 0x02 /* cur reg B low */
-#define UDC_MODE_HI 0x56 /* mode reg high */
-#define UDC_MODE_LO 0x52 /* mode reg low */
-#define UDC_COUNT 0x32 /* words to xfer */
-
-/* some udc commands */
-#define UDC_RESET 0
-#define UDC_CHN_START 0xa0 /* start chain */
-#define UDC_INT_ENABLE 0x32 /* channel 1 int on */
-
-/* udc mode words */
-#define UDC_MODE_HIWORD 0x40
-#define UDC_MODE_LSEND 0xc2
-#define UDC_MODE_LRECV 0xd2
-
-/* udc reg selections */
-#define UDC_RSEL_SEND 0x282
-#define UDC_RSEL_RECV 0x182
-
-/* bits in csr reg */
-#define CSR_DMA_ACTIVE 0x8000
-#define CSR_DMA_CONFLICT 0x4000
-#define CSR_DMA_BUSERR 0x2000
-
-#define CSR_FIFO_EMPTY 0x400 /* fifo flushed? */
-#define CSR_SDB_INT 0x200 /* sbc interrupt pending */
-#define CSR_DMA_INT 0x100 /* dma interrupt pending */
-
-#define CSR_LEFT 0xc0
-#define CSR_LEFT_3 0xc0
-#define CSR_LEFT_2 0x80
-#define CSR_LEFT_1 0x40
-#define CSR_PACK_ENABLE 0x20
-
-#define CSR_DMA_ENABLE 0x10
-
-#define CSR_SEND 0x8 /* 1 = send  0 = recv */
-#define CSR_FIFO 0x2 /* reset fifo */
-#define CSR_INTR 0x4 /* interrupt enable */
-#define CSR_SCSI 0x1 
-
-#define VME_DATA24 0x3d00
-
-#endif /* SUN3_SCSI_H */
-
diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c
index abe617372661..5ff8a6bf6fd3 100644
--- a/drivers/scsi/ufs/ufs-qcom.c
+++ b/drivers/scsi/ufs/ufs-qcom.c
@@ -1692,6 +1692,7 @@ static const struct of_device_id ufs_qcom_of_match[] = {
 	{ .compatible = "qcom,ufshc"},
 	{},
 };
+MODULE_DEVICE_TABLE(of, ufs_qcom_of_match);
 
 static const struct dev_pm_ops ufs_qcom_pm_ops = {
 	.suspend	= ufshcd_pltfrm_suspend,
diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h
index 8e6709a3fb6b..318e4a1f76c9 100644
--- a/drivers/scsi/ufs/ufs.h
+++ b/drivers/scsi/ufs/ufs.h
@@ -523,4 +523,16 @@ struct ufs_dev_info {
 	bool is_lu_power_on_wp;
 };
 
+#define MAX_MODEL_LEN 16
+/**
+ * ufs_dev_desc - ufs device details from the device descriptor
+ *
+ * @wmanufacturerid: card details
+ * @model: card model
+ */
+struct ufs_dev_desc {
+	u16 wmanufacturerid;
+	char model[MAX_MODEL_LEN + 1];
+};
+
 #endif /* End of Header */
diff --git a/drivers/scsi/ufs/ufs_quirks.h b/drivers/scsi/ufs/ufs_quirks.h
index 08b799d4efcc..71f73d1d1ad1 100644
--- a/drivers/scsi/ufs/ufs_quirks.h
+++ b/drivers/scsi/ufs/ufs_quirks.h
@@ -21,41 +21,28 @@
 #define UFS_ANY_VENDOR 0xFFFF
 #define UFS_ANY_MODEL  "ANY_MODEL"
 
-#define MAX_MODEL_LEN 16
-
 #define UFS_VENDOR_TOSHIBA     0x198
 #define UFS_VENDOR_SAMSUNG     0x1CE
 #define UFS_VENDOR_SKHYNIX     0x1AD
 
 /**
- * ufs_device_info - ufs device details
- * @wmanufacturerid: card details
- * @model: card model
- */
-struct ufs_device_info {
-	u16 wmanufacturerid;
-	char model[MAX_MODEL_LEN + 1];
-};
-
-/**
  * ufs_dev_fix - ufs device quirk info
  * @card: ufs card details
  * @quirk: device quirk
  */
 struct ufs_dev_fix {
-	struct ufs_device_info card;
+	struct ufs_dev_desc card;
 	unsigned int quirk;
 };
 
 #define END_FIX { { 0 }, 0 }
 
 /* add specific device quirk */
-#define UFS_FIX(_vendor, _model, _quirk) \
-		{					  \
-			.card.wmanufacturerid = (_vendor),\
-			.card.model = (_model),		  \
-			.quirk = (_quirk),		  \
-		}
+#define UFS_FIX(_vendor, _model, _quirk) { \
+	.card.wmanufacturerid = (_vendor),\
+	.card.model = (_model),		   \
+	.quirk = (_quirk),		   \
+}
 
 /*
  * If UFS device is having issue in processing LCC (Line Control
@@ -144,7 +131,4 @@ struct ufs_dev_fix {
  */
 #define UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME	(1 << 8)
 
-struct ufs_hba;
-void ufs_advertise_fixup_device(struct ufs_hba *hba);
-
 #endif /* UFS_QUIRKS_H_ */
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 20e5e5fb048c..a70bf066f277 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -45,6 +45,9 @@
 #include "ufs_quirks.h"
 #include "unipro.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/ufs.h>
+
 #define UFSHCD_REQ_SENSE_SIZE	18
 
 #define UFSHCD_ENABLE_INTRS	(UTP_TRANSFER_REQ_COMPL |\
@@ -94,6 +97,9 @@
 		_ret;                                                   \
 	})
 
+#define ufshcd_hex_dump(prefix_str, buf, len) \
+print_hex_dump(KERN_ERR, prefix_str, DUMP_PREFIX_OFFSET, 16, 4, buf, len, false)
+
 static u32 ufs_query_desc_max_size[] = {
 	QUERY_DESC_DEVICE_MAX_SIZE,
 	QUERY_DESC_CONFIGURAION_MAX_SIZE,
@@ -185,6 +191,22 @@ ufs_get_pm_lvl_to_link_pwr_state(enum ufs_pm_level lvl)
 	return ufs_pm_lvl_states[lvl].link_state;
 }
 
+static inline enum ufs_pm_level
+ufs_get_desired_pm_lvl_for_dev_link_state(enum ufs_dev_pwr_mode dev_state,
+					enum uic_link_state link_state)
+{
+	enum ufs_pm_level lvl;
+
+	for (lvl = UFS_PM_LVL_0; lvl < UFS_PM_LVL_MAX; lvl++) {
+		if ((ufs_pm_lvl_states[lvl].dev_state == dev_state) &&
+			(ufs_pm_lvl_states[lvl].link_state == link_state))
+			return lvl;
+	}
+
+	/* if no match found, return the level 0 */
+	return UFS_PM_LVL_0;
+}
+
 static struct ufs_dev_fix ufs_fixups[] = {
 	/* UFS cards deviations table */
 	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
@@ -212,6 +234,7 @@ static struct ufs_dev_fix ufs_fixups[] = {
 static void ufshcd_tmc_handler(struct ufs_hba *hba);
 static void ufshcd_async_scan(void *data, async_cookie_t cookie);
 static int ufshcd_reset_and_restore(struct ufs_hba *hba);
+static int ufshcd_eh_host_reset_handler(struct scsi_cmnd *cmd);
 static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag);
 static void ufshcd_hba_exit(struct ufs_hba *hba);
 static int ufshcd_probe_hba(struct ufs_hba *hba);
@@ -223,6 +246,9 @@ static int ufshcd_uic_hibern8_exit(struct ufs_hba *hba);
 static int ufshcd_uic_hibern8_enter(struct ufs_hba *hba);
 static inline void ufshcd_add_delay_before_dme_cmd(struct ufs_hba *hba);
 static int ufshcd_host_reset_and_restore(struct ufs_hba *hba);
+static void ufshcd_resume_clkscaling(struct ufs_hba *hba);
+static void ufshcd_suspend_clkscaling(struct ufs_hba *hba);
+static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up);
 static irqreturn_t ufshcd_intr(int irq, void *__hba);
 static int ufshcd_config_pwr_mode(struct ufs_hba *hba,
 		struct ufs_pa_layer_attr *desired_pwr_mode);
@@ -267,6 +293,192 @@ static inline void ufshcd_remove_non_printable(char *val)
 		*val = ' ';
 }
 
+static void ufshcd_add_command_trace(struct ufs_hba *hba,
+		unsigned int tag, const char *str)
+{
+	sector_t lba = -1;
+	u8 opcode = 0;
+	u32 intr, doorbell;
+	struct ufshcd_lrb *lrbp;
+	int transfer_len = -1;
+
+	if (!trace_ufshcd_command_enabled())
+		return;
+
+	lrbp = &hba->lrb[tag];
+
+	if (lrbp->cmd) { /* data phase exists */
+		opcode = (u8)(*lrbp->cmd->cmnd);
+		if ((opcode == READ_10) || (opcode == WRITE_10)) {
+			/*
+			 * Currently we only fully trace read(10) and write(10)
+			 * commands
+			 */
+			if (lrbp->cmd->request && lrbp->cmd->request->bio)
+				lba =
+				  lrbp->cmd->request->bio->bi_iter.bi_sector;
+			transfer_len = be32_to_cpu(
+				lrbp->ucd_req_ptr->sc.exp_data_transfer_len);
+		}
+	}
+
+	intr = ufshcd_readl(hba, REG_INTERRUPT_STATUS);
+	doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
+	trace_ufshcd_command(dev_name(hba->dev), str, tag,
+				doorbell, transfer_len, intr, lba, opcode);
+}
+
+static void ufshcd_print_clk_freqs(struct ufs_hba *hba)
+{
+	struct ufs_clk_info *clki;
+	struct list_head *head = &hba->clk_list_head;
+
+	if (!head || list_empty(head))
+		return;
+
+	list_for_each_entry(clki, head, list) {
+		if (!IS_ERR_OR_NULL(clki->clk) && clki->min_freq &&
+				clki->max_freq)
+			dev_err(hba->dev, "clk: %s, rate: %u\n",
+					clki->name, clki->curr_freq);
+	}
+}
+
+static void ufshcd_print_uic_err_hist(struct ufs_hba *hba,
+		struct ufs_uic_err_reg_hist *err_hist, char *err_name)
+{
+	int i;
+
+	for (i = 0; i < UIC_ERR_REG_HIST_LENGTH; i++) {
+		int p = (i + err_hist->pos - 1) % UIC_ERR_REG_HIST_LENGTH;
+
+		if (err_hist->reg[p] == 0)
+			continue;
+		dev_err(hba->dev, "%s[%d] = 0x%x at %lld us\n", err_name, i,
+			err_hist->reg[p], ktime_to_us(err_hist->tstamp[p]));
+	}
+}
+
+static void ufshcd_print_host_regs(struct ufs_hba *hba)
+{
+	/*
+	 * hex_dump reads its data without the readl macro. This might
+	 * cause inconsistency issues on some platform, as the printed
+	 * values may be from cache and not the most recent value.
+	 * To know whether you are looking at an un-cached version verify
+	 * that IORESOURCE_MEM flag is on when xxx_get_resource() is invoked
+	 * during platform/pci probe function.
+	 */
+	ufshcd_hex_dump("host regs: ", hba->mmio_base, UFSHCI_REG_SPACE_SIZE);
+	dev_err(hba->dev, "hba->ufs_version = 0x%x, hba->capabilities = 0x%x\n",
+		hba->ufs_version, hba->capabilities);
+	dev_err(hba->dev,
+		"hba->outstanding_reqs = 0x%x, hba->outstanding_tasks = 0x%x\n",
+		(u32)hba->outstanding_reqs, (u32)hba->outstanding_tasks);
+	dev_err(hba->dev,
+		"last_hibern8_exit_tstamp at %lld us, hibern8_exit_cnt = %d\n",
+		ktime_to_us(hba->ufs_stats.last_hibern8_exit_tstamp),
+		hba->ufs_stats.hibern8_exit_cnt);
+
+	ufshcd_print_uic_err_hist(hba, &hba->ufs_stats.pa_err, "pa_err");
+	ufshcd_print_uic_err_hist(hba, &hba->ufs_stats.dl_err, "dl_err");
+	ufshcd_print_uic_err_hist(hba, &hba->ufs_stats.nl_err, "nl_err");
+	ufshcd_print_uic_err_hist(hba, &hba->ufs_stats.tl_err, "tl_err");
+	ufshcd_print_uic_err_hist(hba, &hba->ufs_stats.dme_err, "dme_err");
+
+	ufshcd_print_clk_freqs(hba);
+
+	if (hba->vops && hba->vops->dbg_register_dump)
+		hba->vops->dbg_register_dump(hba);
+}
+
+static
+void ufshcd_print_trs(struct ufs_hba *hba, unsigned long bitmap, bool pr_prdt)
+{
+	struct ufshcd_lrb *lrbp;
+	int tag;
+
+	for_each_set_bit(tag, &bitmap, hba->nutrs) {
+		lrbp = &hba->lrb[tag];
+
+		dev_err(hba->dev, "UPIU[%d] - issue time %lld us\n",
+				tag, ktime_to_us(lrbp->issue_time_stamp));
+		dev_err(hba->dev,
+			"UPIU[%d] - Transfer Request Descriptor phys@0x%llx\n",
+			tag, (u64)lrbp->utrd_dma_addr);
+
+		ufshcd_hex_dump("UPIU TRD: ", lrbp->utr_descriptor_ptr,
+				sizeof(struct utp_transfer_req_desc));
+		dev_err(hba->dev, "UPIU[%d] - Request UPIU phys@0x%llx\n", tag,
+			(u64)lrbp->ucd_req_dma_addr);
+		ufshcd_hex_dump("UPIU REQ: ", lrbp->ucd_req_ptr,
+				sizeof(struct utp_upiu_req));
+		dev_err(hba->dev, "UPIU[%d] - Response UPIU phys@0x%llx\n", tag,
+			(u64)lrbp->ucd_rsp_dma_addr);
+		ufshcd_hex_dump("UPIU RSP: ", lrbp->ucd_rsp_ptr,
+				sizeof(struct utp_upiu_rsp));
+		if (pr_prdt) {
+			int prdt_length = le16_to_cpu(
+				lrbp->utr_descriptor_ptr->prd_table_length);
+
+			dev_err(hba->dev,
+				"UPIU[%d] - PRDT - %d entries  phys@0x%llx\n",
+				tag, prdt_length,
+				(u64)lrbp->ucd_prdt_dma_addr);
+			ufshcd_hex_dump("UPIU PRDT: ", lrbp->ucd_prdt_ptr,
+					sizeof(struct ufshcd_sg_entry) *
+					prdt_length);
+		}
+	}
+}
+
+static void ufshcd_print_tmrs(struct ufs_hba *hba, unsigned long bitmap)
+{
+	struct utp_task_req_desc *tmrdp;
+	int tag;
+
+	for_each_set_bit(tag, &bitmap, hba->nutmrs) {
+		tmrdp = &hba->utmrdl_base_addr[tag];
+		dev_err(hba->dev, "TM[%d] - Task Management Header\n", tag);
+		ufshcd_hex_dump("TM TRD: ", &tmrdp->header,
+				sizeof(struct request_desc_header));
+		dev_err(hba->dev, "TM[%d] - Task Management Request UPIU\n",
+				tag);
+		ufshcd_hex_dump("TM REQ: ", tmrdp->task_req_upiu,
+				sizeof(struct utp_upiu_req));
+		dev_err(hba->dev, "TM[%d] - Task Management Response UPIU\n",
+				tag);
+		ufshcd_hex_dump("TM RSP: ", tmrdp->task_rsp_upiu,
+				sizeof(struct utp_task_req_desc));
+	}
+}
+
+/**
+ * ufshcd_print_pwr_info - print power params as saved in hba
+ * power info
+ * @hba: per-adapter instance
+ */
+static void ufshcd_print_pwr_info(struct ufs_hba *hba)
+{
+	static const char * const names[] = {
+		"INVALID MODE",
+		"FAST MODE",
+		"SLOW_MODE",
+		"INVALID MODE",
+		"FASTAUTO_MODE",
+		"SLOWAUTO_MODE",
+		"INVALID MODE",
+	};
+
+	dev_err(hba->dev, "%s:[RX, TX]: gear=[%d, %d], lane[%d, %d], pwr[%s, %s], rate = %d\n",
+		 __func__,
+		 hba->pwr_info.gear_rx, hba->pwr_info.gear_tx,
+		 hba->pwr_info.lane_rx, hba->pwr_info.lane_tx,
+		 names[hba->pwr_info.pwr_rx],
+		 names[hba->pwr_info.pwr_tx],
+		 hba->pwr_info.hs_rate);
+}
+
 /*
  * ufshcd_wait_for_register - wait for register value to change
  * @hba - per-adapter interface
@@ -605,6 +817,28 @@ static inline int ufshcd_is_hba_active(struct ufs_hba *hba)
 	return (ufshcd_readl(hba, REG_CONTROLLER_ENABLE) & 0x1) ? 0 : 1;
 }
 
+static const char *ufschd_uic_link_state_to_string(
+			enum uic_link_state state)
+{
+	switch (state) {
+	case UIC_LINK_OFF_STATE:	return "OFF";
+	case UIC_LINK_ACTIVE_STATE:	return "ACTIVE";
+	case UIC_LINK_HIBERN8_STATE:	return "HIBERN8";
+	default:			return "UNKNOWN";
+	}
+}
+
+static const char *ufschd_ufs_dev_pwr_mode_to_string(
+			enum ufs_dev_pwr_mode state)
+{
+	switch (state) {
+	case UFS_ACTIVE_PWR_MODE:	return "ACTIVE";
+	case UFS_SLEEP_PWR_MODE:	return "SLEEP";
+	case UFS_POWERDOWN_PWR_MODE:	return "POWERDOWN";
+	default:			return "UNKNOWN";
+	}
+}
+
 u32 ufshcd_get_local_unipro_ver(struct ufs_hba *hba)
 {
 	/* HCI version 1.0 and 1.1 supports UniPro 1.41 */
@@ -635,16 +869,58 @@ static bool ufshcd_is_unipro_pa_params_tuning_req(struct ufs_hba *hba)
 
 static void ufshcd_suspend_clkscaling(struct ufs_hba *hba)
 {
-	if (ufshcd_is_clkscaling_enabled(hba)) {
-		devfreq_suspend_device(hba->devfreq);
-		hba->clk_scaling.window_start_t = 0;
-	}
+	if (!ufshcd_is_clkscaling_supported(hba))
+		return;
+
+	devfreq_suspend_device(hba->devfreq);
+	hba->clk_scaling.window_start_t = 0;
 }
 
 static void ufshcd_resume_clkscaling(struct ufs_hba *hba)
 {
-	if (ufshcd_is_clkscaling_enabled(hba))
-		devfreq_resume_device(hba->devfreq);
+	devfreq_resume_device(hba->devfreq);
+}
+
+static ssize_t ufshcd_clkscale_enable_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", hba->clk_scaling.is_allowed);
+}
+
+static ssize_t ufshcd_clkscale_enable_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	u32 value;
+	int err;
+
+	if (kstrtou32(buf, 0, &value))
+		return -EINVAL;
+
+	value = !!value;
+	if (value == hba->clk_scaling.is_allowed)
+		goto out;
+
+	pm_runtime_get_sync(hba->dev);
+	ufshcd_hold(hba, false);
+
+	if (value) {
+		ufshcd_resume_clkscaling(hba);
+	} else {
+		ufshcd_suspend_clkscaling(hba);
+		err = ufshcd_scale_clks(hba, true);
+		if (err)
+			dev_err(hba->dev, "%s: failed to scale clocks up %d\n",
+					__func__, err);
+	}
+	hba->clk_scaling.is_allowed = value;
+
+	ufshcd_release(hba);
+	pm_runtime_put_sync(hba->dev);
+out:
+	return count;
 }
 
 static void ufshcd_ungate_work(struct work_struct *work)
@@ -680,7 +956,8 @@ static void ufshcd_ungate_work(struct work_struct *work)
 		hba->clk_gating.is_suspended = false;
 	}
 unblock_reqs:
-	ufshcd_resume_clkscaling(hba);
+	if (hba->clk_scaling.is_allowed)
+		ufshcd_resume_clkscaling(hba);
 	scsi_unblock_requests(hba->host);
 }
 
@@ -727,6 +1004,8 @@ start:
 	case REQ_CLKS_OFF:
 		if (cancel_delayed_work(&hba->clk_gating.gate_work)) {
 			hba->clk_gating.state = CLKS_ON;
+			trace_ufshcd_clk_gating(dev_name(hba->dev),
+						hba->clk_gating.state);
 			break;
 		}
 		/*
@@ -737,6 +1016,8 @@ start:
 	case CLKS_OFF:
 		scsi_block_requests(hba->host);
 		hba->clk_gating.state = REQ_CLKS_ON;
+		trace_ufshcd_clk_gating(dev_name(hba->dev),
+					hba->clk_gating.state);
 		schedule_work(&hba->clk_gating.ungate_work);
 		/*
 		 * fall through to check if we should wait for this
@@ -781,6 +1062,8 @@ static void ufshcd_gate_work(struct work_struct *work)
 	if (hba->clk_gating.is_suspended ||
 		(hba->clk_gating.state == REQ_CLKS_ON)) {
 		hba->clk_gating.state = CLKS_ON;
+		trace_ufshcd_clk_gating(dev_name(hba->dev),
+					hba->clk_gating.state);
 		goto rel_lock;
 	}
 
@@ -796,6 +1079,8 @@ static void ufshcd_gate_work(struct work_struct *work)
 	if (ufshcd_can_hibern8_during_gating(hba)) {
 		if (ufshcd_uic_hibern8_enter(hba)) {
 			hba->clk_gating.state = CLKS_ON;
+			trace_ufshcd_clk_gating(dev_name(hba->dev),
+						hba->clk_gating.state);
 			goto out;
 		}
 		ufshcd_set_link_hibern8(hba);
@@ -819,9 +1104,11 @@ static void ufshcd_gate_work(struct work_struct *work)
 	 * new requests arriving before the current cancel work is done.
 	 */
 	spin_lock_irqsave(hba->host->host_lock, flags);
-	if (hba->clk_gating.state == REQ_CLKS_OFF)
+	if (hba->clk_gating.state == REQ_CLKS_OFF) {
 		hba->clk_gating.state = CLKS_OFF;
-
+		trace_ufshcd_clk_gating(dev_name(hba->dev),
+					hba->clk_gating.state);
+	}
 rel_lock:
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 out:
@@ -844,6 +1131,7 @@ static void __ufshcd_release(struct ufs_hba *hba)
 		return;
 
 	hba->clk_gating.state = REQ_CLKS_OFF;
+	trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state);
 	schedule_delayed_work(&hba->clk_gating.gate_work,
 			msecs_to_jiffies(hba->clk_gating.delay_ms));
 }
@@ -881,6 +1169,41 @@ static ssize_t ufshcd_clkgate_delay_store(struct device *dev,
 	return count;
 }
 
+static ssize_t ufshcd_clkgate_enable_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", hba->clk_gating.is_enabled);
+}
+
+static ssize_t ufshcd_clkgate_enable_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	unsigned long flags;
+	u32 value;
+
+	if (kstrtou32(buf, 0, &value))
+		return -EINVAL;
+
+	value = !!value;
+	if (value == hba->clk_gating.is_enabled)
+		goto out;
+
+	if (value) {
+		ufshcd_release(hba);
+	} else {
+		spin_lock_irqsave(hba->host->host_lock, flags);
+		hba->clk_gating.active_reqs++;
+		spin_unlock_irqrestore(hba->host->host_lock, flags);
+	}
+
+	hba->clk_gating.is_enabled = value;
+out:
+	return count;
+}
+
 static void ufshcd_init_clk_gating(struct ufs_hba *hba)
 {
 	if (!ufshcd_is_clkgating_allowed(hba))
@@ -890,13 +1213,23 @@ static void ufshcd_init_clk_gating(struct ufs_hba *hba)
 	INIT_DELAYED_WORK(&hba->clk_gating.gate_work, ufshcd_gate_work);
 	INIT_WORK(&hba->clk_gating.ungate_work, ufshcd_ungate_work);
 
+	hba->clk_gating.is_enabled = true;
+
 	hba->clk_gating.delay_attr.show = ufshcd_clkgate_delay_show;
 	hba->clk_gating.delay_attr.store = ufshcd_clkgate_delay_store;
 	sysfs_attr_init(&hba->clk_gating.delay_attr.attr);
 	hba->clk_gating.delay_attr.attr.name = "clkgate_delay_ms";
-	hba->clk_gating.delay_attr.attr.mode = S_IRUGO | S_IWUSR;
+	hba->clk_gating.delay_attr.attr.mode = 0644;
 	if (device_create_file(hba->dev, &hba->clk_gating.delay_attr))
 		dev_err(hba->dev, "Failed to create sysfs for clkgate_delay\n");
+
+	hba->clk_gating.enable_attr.show = ufshcd_clkgate_enable_show;
+	hba->clk_gating.enable_attr.store = ufshcd_clkgate_enable_store;
+	sysfs_attr_init(&hba->clk_gating.enable_attr.attr);
+	hba->clk_gating.enable_attr.attr.name = "clkgate_enable";
+	hba->clk_gating.enable_attr.attr.mode = 0644;
+	if (device_create_file(hba->dev, &hba->clk_gating.enable_attr))
+		dev_err(hba->dev, "Failed to create sysfs for clkgate_enable\n");
 }
 
 static void ufshcd_exit_clk_gating(struct ufs_hba *hba)
@@ -904,6 +1237,7 @@ static void ufshcd_exit_clk_gating(struct ufs_hba *hba)
 	if (!ufshcd_is_clkgating_allowed(hba))
 		return;
 	device_remove_file(hba->dev, &hba->clk_gating.delay_attr);
+	device_remove_file(hba->dev, &hba->clk_gating.enable_attr);
 	cancel_work_sync(&hba->clk_gating.ungate_work);
 	cancel_delayed_work_sync(&hba->clk_gating.gate_work);
 }
@@ -911,7 +1245,7 @@ static void ufshcd_exit_clk_gating(struct ufs_hba *hba)
 /* Must be called with host lock acquired */
 static void ufshcd_clk_scaling_start_busy(struct ufs_hba *hba)
 {
-	if (!ufshcd_is_clkscaling_enabled(hba))
+	if (!ufshcd_is_clkscaling_supported(hba))
 		return;
 
 	if (!hba->clk_scaling.is_busy_started) {
@@ -924,7 +1258,7 @@ static void ufshcd_clk_scaling_update_busy(struct ufs_hba *hba)
 {
 	struct ufs_clk_scaling *scaling = &hba->clk_scaling;
 
-	if (!ufshcd_is_clkscaling_enabled(hba))
+	if (!ufshcd_is_clkscaling_supported(hba))
 		return;
 
 	if (!hba->outstanding_reqs && scaling->is_busy_started) {
@@ -942,11 +1276,13 @@ static void ufshcd_clk_scaling_update_busy(struct ufs_hba *hba)
 static inline
 void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag)
 {
+	hba->lrb[task_tag].issue_time_stamp = ktime_get();
 	ufshcd_clk_scaling_start_busy(hba);
 	__set_bit(task_tag, &hba->outstanding_reqs);
 	ufshcd_writel(hba, 1 << task_tag, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 	/* Make sure that doorbell is committed immediately */
 	wmb();
+	ufshcd_add_command_trace(hba, task_tag, "send");
 }
 
 /**
@@ -1622,6 +1958,7 @@ ufshcd_dev_cmd_completion(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 	int resp;
 	int err = 0;
 
+	hba->ufs_stats.last_hibern8_exit_tstamp = ktime_set(0, 0);
 	resp = ufshcd_get_req_rsp(lrbp->ucd_rsp_ptr);
 
 	switch (resp) {
@@ -2073,9 +2410,11 @@ out:
  * The buf_len parameter will contain, on return, the length parameter
  * received on the response.
  */
-int ufshcd_query_descriptor_retry(struct ufs_hba *hba,
-			enum query_opcode opcode, enum desc_idn idn, u8 index,
-			u8 selector, u8 *desc_buf, int *buf_len)
+static int ufshcd_query_descriptor_retry(struct ufs_hba *hba,
+					 enum query_opcode opcode,
+					 enum desc_idn idn, u8 index,
+					 u8 selector,
+					 u8 *desc_buf, int *buf_len)
 {
 	int err;
 	int retries;
@@ -2089,7 +2428,6 @@ int ufshcd_query_descriptor_retry(struct ufs_hba *hba,
 
 	return err;
 }
-EXPORT_SYMBOL(ufshcd_query_descriptor_retry);
 
 /**
  * ufshcd_read_desc_param - read the specified descriptor parameter
@@ -2207,11 +2545,10 @@ static inline int ufshcd_read_power_desc(struct ufs_hba *hba,
 	return err;
 }
 
-int ufshcd_read_device_desc(struct ufs_hba *hba, u8 *buf, u32 size)
+static int ufshcd_read_device_desc(struct ufs_hba *hba, u8 *buf, u32 size)
 {
 	return ufshcd_read_desc(hba, QUERY_DESC_IDN_DEVICE, 0, buf, size);
 }
-EXPORT_SYMBOL(ufshcd_read_device_desc);
 
 /**
  * ufshcd_read_string_desc - read string descriptor
@@ -2223,8 +2560,9 @@ EXPORT_SYMBOL(ufshcd_read_device_desc);
  *
  * Return 0 in case of success, non-zero otherwise
  */
-int ufshcd_read_string_desc(struct ufs_hba *hba, int desc_index, u8 *buf,
-				u32 size, bool ascii)
+#define ASCII_STD true
+static int ufshcd_read_string_desc(struct ufs_hba *hba, int desc_index,
+				   u8 *buf, u32 size, bool ascii)
 {
 	int err = 0;
 
@@ -2280,7 +2618,6 @@ int ufshcd_read_string_desc(struct ufs_hba *hba, int desc_index, u8 *buf,
 out:
 	return err;
 }
-EXPORT_SYMBOL(ufshcd_read_string_desc);
 
 /**
  * ufshcd_read_unit_desc_param - read the specified unit descriptor parameter
@@ -2453,12 +2790,19 @@ static void ufshcd_host_memory_configure(struct ufs_hba *hba)
 		}
 
 		hba->lrb[i].utr_descriptor_ptr = (utrdlp + i);
+		hba->lrb[i].utrd_dma_addr = hba->utrdl_dma_addr +
+				(i * sizeof(struct utp_transfer_req_desc));
 		hba->lrb[i].ucd_req_ptr =
 			(struct utp_upiu_req *)(cmd_descp + i);
+		hba->lrb[i].ucd_req_dma_addr = cmd_desc_element_addr;
 		hba->lrb[i].ucd_rsp_ptr =
 			(struct utp_upiu_rsp *)cmd_descp[i].response_upiu;
+		hba->lrb[i].ucd_rsp_dma_addr = cmd_desc_element_addr +
+				response_offset;
 		hba->lrb[i].ucd_prdt_ptr =
 			(struct ufshcd_sg_entry *)cmd_descp[i].prd_table;
+		hba->lrb[i].ucd_prdt_dma_addr = cmd_desc_element_addr +
+				prdt_offset;
 	}
 }
 
@@ -2482,7 +2826,7 @@ static int ufshcd_dme_link_startup(struct ufs_hba *hba)
 
 	ret = ufshcd_send_uic_cmd(hba, &uic_cmd);
 	if (ret)
-		dev_err(hba->dev,
+		dev_dbg(hba->dev,
 			"dme-link-startup: error code %d\n", ret);
 	return ret;
 }
@@ -2776,11 +3120,14 @@ static int __ufshcd_uic_hibern8_enter(struct ufs_hba *hba)
 {
 	int ret;
 	struct uic_command uic_cmd = {0};
+	ktime_t start = ktime_get();
 
 	ufshcd_vops_hibern8_notify(hba, UIC_CMD_DME_HIBER_ENTER, PRE_CHANGE);
 
 	uic_cmd.command = UIC_CMD_DME_HIBER_ENTER;
 	ret = ufshcd_uic_pwr_ctrl(hba, &uic_cmd);
+	trace_ufshcd_profile_hibern8(dev_name(hba->dev), "enter",
+			     ktime_to_us(ktime_sub(ktime_get(), start)), ret);
 
 	if (ret) {
 		dev_err(hba->dev, "%s: hibern8 enter failed. ret = %d\n",
@@ -2816,18 +3163,25 @@ static int ufshcd_uic_hibern8_exit(struct ufs_hba *hba)
 {
 	struct uic_command uic_cmd = {0};
 	int ret;
+	ktime_t start = ktime_get();
 
 	ufshcd_vops_hibern8_notify(hba, UIC_CMD_DME_HIBER_EXIT, PRE_CHANGE);
 
 	uic_cmd.command = UIC_CMD_DME_HIBER_EXIT;
 	ret = ufshcd_uic_pwr_ctrl(hba, &uic_cmd);
+	trace_ufshcd_profile_hibern8(dev_name(hba->dev), "exit",
+			     ktime_to_us(ktime_sub(ktime_get(), start)), ret);
+
 	if (ret) {
 		dev_err(hba->dev, "%s: hibern8 exit failed. ret = %d\n",
 			__func__, ret);
 		ret = ufshcd_link_recovery(hba);
-	} else
+	} else {
 		ufshcd_vops_hibern8_notify(hba, UIC_CMD_DME_HIBER_EXIT,
 								POST_CHANGE);
+		hba->ufs_stats.last_hibern8_exit_tstamp = ktime_get();
+		hba->ufs_stats.hibern8_exit_cnt++;
+	}
 
 	return ret;
 }
@@ -2973,6 +3327,8 @@ static int ufshcd_change_power_mode(struct ufs_hba *hba,
 			sizeof(struct ufs_pa_layer_attr));
 	}
 
+	ufshcd_print_pwr_info(hba);
+
 	return ret;
 }
 
@@ -3265,6 +3621,10 @@ link_startup:
 		goto link_startup;
 	}
 
+	/* Mark that link is up in PWM-G1, 1-lane, SLOW-AUTO mode */
+	ufshcd_init_pwr_info(hba);
+	ufshcd_print_pwr_info(hba);
+
 	if (hba->quirks & UFSHCD_QUIRK_BROKEN_LCC) {
 		ret = ufshcd_disable_device_tx_lcc(hba);
 		if (ret)
@@ -3591,7 +3951,7 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 	switch (ocs) {
 	case OCS_SUCCESS:
 		result = ufshcd_get_req_rsp(lrbp->ucd_rsp_ptr);
-
+		hba->ufs_stats.last_hibern8_exit_tstamp = ktime_set(0, 0);
 		switch (result) {
 		case UPIU_TRANSACTION_RESPONSE:
 			/*
@@ -3652,10 +4012,14 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 	default:
 		result |= DID_ERROR << 16;
 		dev_err(hba->dev,
-		"OCS error from controller = %x\n", ocs);
+				"OCS error from controller = %x for tag %d\n",
+				ocs, lrbp->task_tag);
+		ufshcd_print_host_regs(hba);
 		break;
 	} /* end of switch */
 
+	if (host_byte(result) != DID_OK)
+		ufshcd_print_trs(hba, 1 << lrbp->task_tag, true);
 	return result;
 }
 
@@ -3695,6 +4059,7 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
 		lrbp = &hba->lrb[index];
 		cmd = lrbp->cmd;
 		if (cmd) {
+			ufshcd_add_command_trace(hba, index, "complete");
 			result = ufshcd_transfer_rsp_status(hba, lrbp);
 			scsi_dma_unmap(cmd);
 			cmd->result = result;
@@ -3706,8 +4071,11 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
 			__ufshcd_release(hba);
 		} else if (lrbp->command_type == UTP_CMD_TYPE_DEV_MANAGE ||
 			lrbp->command_type == UTP_CMD_TYPE_UFS_STORAGE) {
-			if (hba->dev_cmd.complete)
+			if (hba->dev_cmd.complete) {
+				ufshcd_add_command_trace(hba, index,
+						"dev_complete");
 				complete(hba->dev_cmd.complete);
+			}
 		}
 	}
 
@@ -3828,6 +4196,7 @@ static int ufshcd_enable_auto_bkops(struct ufs_hba *hba)
 	}
 
 	hba->auto_bkops_enabled = true;
+	trace_ufshcd_auto_bkops_state(dev_name(hba->dev), "Enabled");
 
 	/* No need of URGENT_BKOPS exception from the device */
 	err = ufshcd_disable_ee(hba, MASK_EE_URGENT_BKOPS);
@@ -3878,23 +4247,31 @@ static int ufshcd_disable_auto_bkops(struct ufs_hba *hba)
 	}
 
 	hba->auto_bkops_enabled = false;
+	trace_ufshcd_auto_bkops_state(dev_name(hba->dev), "Disabled");
 out:
 	return err;
 }
 
 /**
- * ufshcd_force_reset_auto_bkops - force enable of auto bkops
+ * ufshcd_force_reset_auto_bkops - force reset auto bkops state
  * @hba: per adapter instance
  *
  * After a device reset the device may toggle the BKOPS_EN flag
  * to default value. The s/w tracking variables should be updated
- * as well. Do this by forcing enable of auto bkops.
+ * as well. This function would change the auto-bkops state based on
+ * UFSHCD_CAP_KEEP_AUTO_BKOPS_ENABLED_EXCEPT_SUSPEND.
  */
-static void  ufshcd_force_reset_auto_bkops(struct ufs_hba *hba)
+static void ufshcd_force_reset_auto_bkops(struct ufs_hba *hba)
 {
-	hba->auto_bkops_enabled = false;
-	hba->ee_ctrl_mask |= MASK_EE_URGENT_BKOPS;
-	ufshcd_enable_auto_bkops(hba);
+	if (ufshcd_keep_autobkops_enabled_except_suspend(hba)) {
+		hba->auto_bkops_enabled = false;
+		hba->ee_ctrl_mask |= MASK_EE_URGENT_BKOPS;
+		ufshcd_enable_auto_bkops(hba);
+	} else {
+		hba->auto_bkops_enabled = true;
+		hba->ee_ctrl_mask &= ~MASK_EE_URGENT_BKOPS;
+		ufshcd_disable_auto_bkops(hba);
+	}
 }
 
 static inline int ufshcd_get_bkops_status(struct ufs_hba *hba, u32 *status)
@@ -4246,6 +4623,14 @@ out:
 	pm_runtime_put_sync(hba->dev);
 }
 
+static void ufshcd_update_uic_reg_hist(struct ufs_uic_err_reg_hist *reg_hist,
+		u32 reg)
+{
+	reg_hist->reg[reg_hist->pos] = reg;
+	reg_hist->tstamp[reg_hist->pos] = ktime_get();
+	reg_hist->pos = (reg_hist->pos + 1) % UIC_ERR_REG_HIST_LENGTH;
+}
+
 /**
  * ufshcd_update_uic_error - check and set fatal UIC error flags.
  * @hba: per-adapter instance
@@ -4258,15 +4643,20 @@ static void ufshcd_update_uic_error(struct ufs_hba *hba)
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_PHY_ADAPTER_LAYER);
 	/* Ignore LINERESET indication, as this is not an error */
 	if ((reg & UIC_PHY_ADAPTER_LAYER_ERROR) &&
-			(reg & UIC_PHY_ADAPTER_LAYER_LANE_ERR_MASK))
+			(reg & UIC_PHY_ADAPTER_LAYER_LANE_ERR_MASK)) {
 		/*
 		 * To know whether this error is fatal or not, DB timeout
 		 * must be checked but this error is handled separately.
 		 */
 		dev_dbg(hba->dev, "%s: UIC Lane error reported\n", __func__);
+		ufshcd_update_uic_reg_hist(&hba->ufs_stats.pa_err, reg);
+	}
 
 	/* PA_INIT_ERROR is fatal and needs UIC reset */
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_DATA_LINK_LAYER);
+	if (reg)
+		ufshcd_update_uic_reg_hist(&hba->ufs_stats.dl_err, reg);
+
 	if (reg & UIC_DATA_LINK_LAYER_ERROR_PA_INIT)
 		hba->uic_error |= UFSHCD_UIC_DL_PA_INIT_ERROR;
 	else if (hba->dev_quirks &
@@ -4280,16 +4670,22 @@ static void ufshcd_update_uic_error(struct ufs_hba *hba)
 
 	/* UIC NL/TL/DME errors needs software retry */
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_NETWORK_LAYER);
-	if (reg)
+	if (reg) {
+		ufshcd_update_uic_reg_hist(&hba->ufs_stats.nl_err, reg);
 		hba->uic_error |= UFSHCD_UIC_NL_ERROR;
+	}
 
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_TRANSPORT_LAYER);
-	if (reg)
+	if (reg) {
+		ufshcd_update_uic_reg_hist(&hba->ufs_stats.tl_err, reg);
 		hba->uic_error |= UFSHCD_UIC_TL_ERROR;
+	}
 
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_DME);
-	if (reg)
+	if (reg) {
+		ufshcd_update_uic_reg_hist(&hba->ufs_stats.dme_err, reg);
 		hba->uic_error |= UFSHCD_UIC_DME_ERROR;
+	}
 
 	dev_dbg(hba->dev, "%s: UIC error flags = 0x%08x\n",
 			__func__, hba->uic_error);
@@ -4327,6 +4723,22 @@ static void ufshcd_check_errors(struct ufs_hba *hba)
 			scsi_block_requests(hba->host);
 
 			hba->ufshcd_state = UFSHCD_STATE_EH_SCHEDULED;
+
+			/* dump controller state before resetting */
+			if (hba->saved_err & (INT_FATAL_ERRORS | UIC_ERROR)) {
+				bool pr_prdt = !!(hba->saved_err &
+						SYSTEM_BUS_FATAL_ERROR);
+
+				dev_err(hba->dev, "%s: saved_err 0x%x saved_uic_err 0x%x\n",
+					__func__, hba->saved_err,
+					hba->saved_uic_err);
+
+				ufshcd_print_host_regs(hba);
+				ufshcd_print_pwr_info(hba);
+				ufshcd_print_tmrs(hba, hba->outstanding_tasks);
+				ufshcd_print_trs(hba, hba->outstanding_reqs,
+							pr_prdt);
+			}
 			schedule_work(&hba->eh_work);
 		}
 	}
@@ -4594,6 +5006,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 	host = cmd->device->host;
 	hba = shost_priv(host);
 	tag = cmd->request->tag;
+	lrbp = &hba->lrb[tag];
 	if (!ufshcd_valid_tag(hba, tag)) {
 		dev_err(hba->dev,
 			"%s: invalid command tag %d: cmd=0x%p, cmd->request=0x%p",
@@ -4601,6 +5014,16 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 		BUG();
 	}
 
+	/*
+	 * Task abort to the device W-LUN is illegal. When this command
+	 * will fail, due to spec violation, scsi err handling next step
+	 * will be to send LU reset which, again, is a spec violation.
+	 * To avoid these unnecessary/illegal step we skip to the last error
+	 * handling stage: reset and restore.
+	 */
+	if (lrbp->lun == UFS_UPIU_UFS_DEVICE_WLUN)
+		return ufshcd_eh_host_reset_handler(cmd);
+
 	ufshcd_hold(hba, false);
 	reg = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 	/* If command is already aborted/completed, return SUCCESS */
@@ -4617,18 +5040,28 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 		__func__, tag);
 	}
 
-	lrbp = &hba->lrb[tag];
+	/* Print Transfer Request of aborted task */
+	dev_err(hba->dev, "%s: Device abort task at tag %d\n", __func__, tag);
+	scsi_print_command(hba->lrb[tag].cmd);
+	ufshcd_print_host_regs(hba);
+	ufshcd_print_pwr_info(hba);
+	ufshcd_print_trs(hba, 1 << tag, true);
+
 	for (poll_cnt = 100; poll_cnt; poll_cnt--) {
 		err = ufshcd_issue_tm_cmd(hba, lrbp->lun, lrbp->task_tag,
 				UFS_QUERY_TASK, &resp);
 		if (!err && resp == UPIU_TASK_MANAGEMENT_FUNC_SUCCEEDED) {
 			/* cmd pending in the device */
+			dev_err(hba->dev, "%s: cmd pending in the device. tag = %d\n",
+				__func__, tag);
 			break;
 		} else if (!err && resp == UPIU_TASK_MANAGEMENT_FUNC_COMPL) {
 			/*
 			 * cmd not pending in the device, check if it is
 			 * in transition.
 			 */
+			dev_err(hba->dev, "%s: cmd at tag %d not pending in the device.\n",
+				__func__, tag);
 			reg = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 			if (reg & (1 << tag)) {
 				/* sleep for max. 200us to stabilize */
@@ -4636,8 +5069,13 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 				continue;
 			}
 			/* command completed already */
+			dev_err(hba->dev, "%s: cmd at tag %d successfully cleared from DB.\n",
+				__func__, tag);
 			goto out;
 		} else {
+			dev_err(hba->dev,
+				"%s: no response from device. tag = %d, err %d\n",
+				__func__, tag, err);
 			if (!err)
 				err = resp; /* service response error */
 			goto out;
@@ -4652,14 +5090,20 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 	err = ufshcd_issue_tm_cmd(hba, lrbp->lun, lrbp->task_tag,
 			UFS_ABORT_TASK, &resp);
 	if (err || resp != UPIU_TASK_MANAGEMENT_FUNC_COMPL) {
-		if (!err)
+		if (!err) {
 			err = resp; /* service response error */
+			dev_err(hba->dev, "%s: issued. tag = %d, err %d\n",
+				__func__, tag, err);
+		}
 		goto out;
 	}
 
 	err = ufshcd_clear_cmd(hba, tag);
-	if (err)
+	if (err) {
+		dev_err(hba->dev, "%s: Failed clearing cmd at tag %d, err %d\n",
+			__func__, tag, err);
 		goto out;
+	}
 
 	scsi_dma_unmap(cmd);
 
@@ -4822,7 +5266,7 @@ static u32 ufshcd_get_max_icc_level(int sup_curr_uA, u32 start_scan, char *buff)
 	u16 unit;
 
 	for (i = start_scan; i >= 0; i--) {
-		data = be16_to_cpu(*((u16 *)(buff + 2*i)));
+		data = be16_to_cpup((__be16 *)&buff[2 * i]);
 		unit = (data & ATTR_ICC_LVL_UNIT_MASK) >>
 						ATTR_ICC_LVL_UNIT_OFFSET;
 		curr_uA = data & ATTR_ICC_LVL_VALUE_MASK;
@@ -5008,8 +5452,8 @@ out:
 	return ret;
 }
 
-static int ufs_get_device_info(struct ufs_hba *hba,
-				struct ufs_device_info *card_data)
+static int ufs_get_device_desc(struct ufs_hba *hba,
+			       struct ufs_dev_desc *dev_desc)
 {
 	int err;
 	u8 model_index;
@@ -5028,7 +5472,7 @@ static int ufs_get_device_info(struct ufs_hba *hba,
 	 * getting vendor (manufacturerID) and Bank Index in big endian
 	 * format
 	 */
-	card_data->wmanufacturerid = desc_buf[DEVICE_DESC_PARAM_MANF_ID] << 8 |
+	dev_desc->wmanufacturerid = desc_buf[DEVICE_DESC_PARAM_MANF_ID] << 8 |
 				     desc_buf[DEVICE_DESC_PARAM_MANF_ID + 1];
 
 	model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME];
@@ -5042,36 +5486,26 @@ static int ufs_get_device_info(struct ufs_hba *hba,
 	}
 
 	str_desc_buf[QUERY_DESC_STRING_MAX_SIZE] = '\0';
-	strlcpy(card_data->model, (str_desc_buf + QUERY_DESC_HDR_SIZE),
+	strlcpy(dev_desc->model, (str_desc_buf + QUERY_DESC_HDR_SIZE),
 		min_t(u8, str_desc_buf[QUERY_DESC_LENGTH_OFFSET],
 		      MAX_MODEL_LEN));
 
 	/* Null terminate the model string */
-	card_data->model[MAX_MODEL_LEN] = '\0';
+	dev_desc->model[MAX_MODEL_LEN] = '\0';
 
 out:
 	return err;
 }
 
-void ufs_advertise_fixup_device(struct ufs_hba *hba)
+static void ufs_fixup_device_setup(struct ufs_hba *hba,
+				   struct ufs_dev_desc *dev_desc)
 {
-	int err;
 	struct ufs_dev_fix *f;
-	struct ufs_device_info card_data;
-
-	card_data.wmanufacturerid = 0;
-
-	err = ufs_get_device_info(hba, &card_data);
-	if (err) {
-		dev_err(hba->dev, "%s: Failed getting device info. err = %d\n",
-			__func__, err);
-		return;
-	}
 
 	for (f = ufs_fixups; f->quirk; f++) {
-		if (((f->card.wmanufacturerid == card_data.wmanufacturerid) ||
-		    (f->card.wmanufacturerid == UFS_ANY_VENDOR)) &&
-		    (STR_PRFX_EQUAL(f->card.model, card_data.model) ||
+		if ((f->card.wmanufacturerid == dev_desc->wmanufacturerid ||
+		     f->card.wmanufacturerid == UFS_ANY_VENDOR) &&
+		    (STR_PRFX_EQUAL(f->card.model, dev_desc->model) ||
 		     !strcmp(f->card.model, UFS_ANY_MODEL)))
 			hba->dev_quirks |= f->quirk;
 	}
@@ -5241,6 +5675,20 @@ static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
 	ufshcd_vops_apply_dev_quirks(hba);
 }
 
+static void ufshcd_clear_dbg_ufs_stats(struct ufs_hba *hba)
+{
+	int err_reg_hist_size = sizeof(struct ufs_uic_err_reg_hist);
+
+	hba->ufs_stats.hibern8_exit_cnt = 0;
+	hba->ufs_stats.last_hibern8_exit_tstamp = ktime_set(0, 0);
+
+	memset(&hba->ufs_stats.pa_err, 0, err_reg_hist_size);
+	memset(&hba->ufs_stats.dl_err, 0, err_reg_hist_size);
+	memset(&hba->ufs_stats.nl_err, 0, err_reg_hist_size);
+	memset(&hba->ufs_stats.tl_err, 0, err_reg_hist_size);
+	memset(&hba->ufs_stats.dme_err, 0, err_reg_hist_size);
+}
+
 /**
  * ufshcd_probe_hba - probe hba to detect device and initialize
  * @hba: per-adapter instance
@@ -5249,18 +5697,21 @@ static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
  */
 static int ufshcd_probe_hba(struct ufs_hba *hba)
 {
+	struct ufs_dev_desc card = {0};
 	int ret;
+	ktime_t start = ktime_get();
 
 	ret = ufshcd_link_startup(hba);
 	if (ret)
 		goto out;
 
-	ufshcd_init_pwr_info(hba);
-
 	/* set the default level for urgent bkops */
 	hba->urgent_bkops_lvl = BKOPS_STATUS_PERF_IMPACT;
 	hba->is_urgent_bkops_lvl_checked = false;
 
+	/* Debug counters initialization */
+	ufshcd_clear_dbg_ufs_stats(hba);
+
 	/* UniPro link is active now */
 	ufshcd_set_link_active(hba);
 
@@ -5272,7 +5723,14 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 	if (ret)
 		goto out;
 
-	ufs_advertise_fixup_device(hba);
+	ret = ufs_get_device_desc(hba, &card);
+	if (ret) {
+		dev_err(hba->dev, "%s: Failed getting device info. err = %d\n",
+			__func__, ret);
+		goto out;
+	}
+
+	ufs_fixup_device_setup(hba, &card);
 	ufshcd_tune_unipro_params(hba);
 
 	ret = ufshcd_set_vccq_rail_unused(hba,
@@ -5324,12 +5782,15 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 		pm_runtime_put_sync(hba->dev);
 	}
 
+	/* Resume devfreq after UFS device is detected */
+	if (ufshcd_is_clkscaling_supported(hba)) {
+		ufshcd_resume_clkscaling(hba);
+		hba->clk_scaling.is_allowed = true;
+	}
+
 	if (!hba->is_init_prefetch)
 		hba->is_init_prefetch = true;
 
-	/* Resume devfreq after UFS device is detected */
-	ufshcd_resume_clkscaling(hba);
-
 out:
 	/*
 	 * If we failed to initialize the device or the device is not
@@ -5340,6 +5801,9 @@ out:
 		ufshcd_hba_exit(hba);
 	}
 
+	trace_ufshcd_init(dev_name(hba->dev), ret,
+		ktime_to_us(ktime_sub(ktime_get(), start)),
+		hba->curr_dev_pwr_mode, hba->uic_link_state);
 	return ret;
 }
 
@@ -5650,6 +6114,8 @@ static int __ufshcd_setup_clocks(struct ufs_hba *hba, bool on,
 	struct ufs_clk_info *clki;
 	struct list_head *head = &hba->clk_list_head;
 	unsigned long flags;
+	ktime_t start = ktime_get();
+	bool clk_state_changed = false;
 
 	if (!head || list_empty(head))
 		goto out;
@@ -5663,6 +6129,7 @@ static int __ufshcd_setup_clocks(struct ufs_hba *hba, bool on,
 			if (skip_ref_clk && !strcmp(clki->name, "ref_clk"))
 				continue;
 
+			clk_state_changed = on ^ clki->enabled;
 			if (on && !clki->enabled) {
 				ret = clk_prepare_enable(clki->clk);
 				if (ret) {
@@ -5689,11 +6156,18 @@ out:
 			if (!IS_ERR_OR_NULL(clki->clk) && clki->enabled)
 				clk_disable_unprepare(clki->clk);
 		}
-	} else if (on) {
+	} else if (!ret && on) {
 		spin_lock_irqsave(hba->host->host_lock, flags);
 		hba->clk_gating.state = CLKS_ON;
+		trace_ufshcd_clk_gating(dev_name(hba->dev),
+					hba->clk_gating.state);
 		spin_unlock_irqrestore(hba->host->host_lock, flags);
 	}
+
+	if (clk_state_changed)
+		trace_ufshcd_profile_clk_gating(dev_name(hba->dev),
+			(on ? "on" : "off"),
+			ktime_to_us(ktime_sub(ktime_get(), start)), ret);
 	return ret;
 }
 
@@ -6176,6 +6650,7 @@ disable_clks:
 		__ufshcd_setup_clocks(hba, false, true);
 
 	hba->clk_gating.state = CLKS_OFF;
+	trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state);
 	/*
 	 * Disable the host irq as host controller as there won't be any
 	 * host controller transaction expected till resume.
@@ -6268,14 +6743,19 @@ static int ufshcd_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 			goto set_old_link_state;
 	}
 
-	/*
-	 * If BKOPs operations are urgently needed at this moment then
-	 * keep auto-bkops enabled or else disable it.
-	 */
-	ufshcd_urgent_bkops(hba);
+	if (ufshcd_keep_autobkops_enabled_except_suspend(hba))
+		ufshcd_enable_auto_bkops(hba);
+	else
+		/*
+		 * If BKOPs operations are urgently needed at this moment then
+		 * keep auto-bkops enabled or else disable it.
+		 */
+		ufshcd_urgent_bkops(hba);
+
 	hba->clk_gating.is_suspended = false;
 
-	ufshcd_resume_clkscaling(hba);
+	if (hba->clk_scaling.is_allowed)
+		ufshcd_resume_clkscaling(hba);
 
 	/* Schedule clock gating in case of no access to UFS device yet */
 	ufshcd_release(hba);
@@ -6308,6 +6788,7 @@ out:
 int ufshcd_system_suspend(struct ufs_hba *hba)
 {
 	int ret = 0;
+	ktime_t start = ktime_get();
 
 	if (!hba || !hba->is_powered)
 		return 0;
@@ -6334,6 +6815,9 @@ int ufshcd_system_suspend(struct ufs_hba *hba)
 
 	ret = ufshcd_suspend(hba, UFS_SYSTEM_PM);
 out:
+	trace_ufshcd_system_suspend(dev_name(hba->dev), ret,
+		ktime_to_us(ktime_sub(ktime_get(), start)),
+		hba->curr_dev_pwr_mode, hba->uic_link_state);
 	if (!ret)
 		hba->is_sys_suspended = true;
 	return ret;
@@ -6349,6 +6833,9 @@ EXPORT_SYMBOL(ufshcd_system_suspend);
 
 int ufshcd_system_resume(struct ufs_hba *hba)
 {
+	int ret = 0;
+	ktime_t start = ktime_get();
+
 	if (!hba)
 		return -EINVAL;
 
@@ -6357,9 +6844,14 @@ int ufshcd_system_resume(struct ufs_hba *hba)
 		 * Let the runtime resume take care of resuming
 		 * if runtime suspended.
 		 */
-		return 0;
-
-	return ufshcd_resume(hba, UFS_SYSTEM_PM);
+		goto out;
+	else
+		ret = ufshcd_resume(hba, UFS_SYSTEM_PM);
+out:
+	trace_ufshcd_system_resume(dev_name(hba->dev), ret,
+		ktime_to_us(ktime_sub(ktime_get(), start)),
+		hba->curr_dev_pwr_mode, hba->uic_link_state);
+	return ret;
 }
 EXPORT_SYMBOL(ufshcd_system_resume);
 
@@ -6373,13 +6865,21 @@ EXPORT_SYMBOL(ufshcd_system_resume);
  */
 int ufshcd_runtime_suspend(struct ufs_hba *hba)
 {
+	int ret = 0;
+	ktime_t start = ktime_get();
+
 	if (!hba)
 		return -EINVAL;
 
 	if (!hba->is_powered)
-		return 0;
-
-	return ufshcd_suspend(hba, UFS_RUNTIME_PM);
+		goto out;
+	else
+		ret = ufshcd_suspend(hba, UFS_RUNTIME_PM);
+out:
+	trace_ufshcd_runtime_suspend(dev_name(hba->dev), ret,
+		ktime_to_us(ktime_sub(ktime_get(), start)),
+		hba->curr_dev_pwr_mode, hba->uic_link_state);
+	return ret;
 }
 EXPORT_SYMBOL(ufshcd_runtime_suspend);
 
@@ -6406,13 +6906,21 @@ EXPORT_SYMBOL(ufshcd_runtime_suspend);
  */
 int ufshcd_runtime_resume(struct ufs_hba *hba)
 {
+	int ret = 0;
+	ktime_t start = ktime_get();
+
 	if (!hba)
 		return -EINVAL;
 
 	if (!hba->is_powered)
-		return 0;
-
-	return ufshcd_resume(hba, UFS_RUNTIME_PM);
+		goto out;
+	else
+		ret = ufshcd_resume(hba, UFS_RUNTIME_PM);
+out:
+	trace_ufshcd_runtime_resume(dev_name(hba->dev), ret,
+		ktime_to_us(ktime_sub(ktime_get(), start)),
+		hba->curr_dev_pwr_mode, hba->uic_link_state);
+	return ret;
 }
 EXPORT_SYMBOL(ufshcd_runtime_resume);
 
@@ -6422,6 +6930,127 @@ int ufshcd_runtime_idle(struct ufs_hba *hba)
 }
 EXPORT_SYMBOL(ufshcd_runtime_idle);
 
+static inline ssize_t ufshcd_pm_lvl_store(struct device *dev,
+					   struct device_attribute *attr,
+					   const char *buf, size_t count,
+					   bool rpm)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	unsigned long flags, value;
+
+	if (kstrtoul(buf, 0, &value))
+		return -EINVAL;
+
+	if ((value < UFS_PM_LVL_0) || (value >= UFS_PM_LVL_MAX))
+		return -EINVAL;
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (rpm)
+		hba->rpm_lvl = value;
+	else
+		hba->spm_lvl = value;
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	return count;
+}
+
+static ssize_t ufshcd_rpm_lvl_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	int curr_len;
+	u8 lvl;
+
+	curr_len = snprintf(buf, PAGE_SIZE,
+			    "\nCurrent Runtime PM level [%d] => dev_state [%s] link_state [%s]\n",
+			    hba->rpm_lvl,
+			    ufschd_ufs_dev_pwr_mode_to_string(
+				ufs_pm_lvl_states[hba->rpm_lvl].dev_state),
+			    ufschd_uic_link_state_to_string(
+				ufs_pm_lvl_states[hba->rpm_lvl].link_state));
+
+	curr_len += snprintf((buf + curr_len), (PAGE_SIZE - curr_len),
+			     "\nAll available Runtime PM levels info:\n");
+	for (lvl = UFS_PM_LVL_0; lvl < UFS_PM_LVL_MAX; lvl++)
+		curr_len += snprintf((buf + curr_len), (PAGE_SIZE - curr_len),
+				     "\tRuntime PM level [%d] => dev_state [%s] link_state [%s]\n",
+				    lvl,
+				    ufschd_ufs_dev_pwr_mode_to_string(
+					ufs_pm_lvl_states[lvl].dev_state),
+				    ufschd_uic_link_state_to_string(
+					ufs_pm_lvl_states[lvl].link_state));
+
+	return curr_len;
+}
+
+static ssize_t ufshcd_rpm_lvl_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	return ufshcd_pm_lvl_store(dev, attr, buf, count, true);
+}
+
+static void ufshcd_add_rpm_lvl_sysfs_nodes(struct ufs_hba *hba)
+{
+	hba->rpm_lvl_attr.show = ufshcd_rpm_lvl_show;
+	hba->rpm_lvl_attr.store = ufshcd_rpm_lvl_store;
+	sysfs_attr_init(&hba->rpm_lvl_attr.attr);
+	hba->rpm_lvl_attr.attr.name = "rpm_lvl";
+	hba->rpm_lvl_attr.attr.mode = 0644;
+	if (device_create_file(hba->dev, &hba->rpm_lvl_attr))
+		dev_err(hba->dev, "Failed to create sysfs for rpm_lvl\n");
+}
+
+static ssize_t ufshcd_spm_lvl_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	int curr_len;
+	u8 lvl;
+
+	curr_len = snprintf(buf, PAGE_SIZE,
+			    "\nCurrent System PM level [%d] => dev_state [%s] link_state [%s]\n",
+			    hba->spm_lvl,
+			    ufschd_ufs_dev_pwr_mode_to_string(
+				ufs_pm_lvl_states[hba->spm_lvl].dev_state),
+			    ufschd_uic_link_state_to_string(
+				ufs_pm_lvl_states[hba->spm_lvl].link_state));
+
+	curr_len += snprintf((buf + curr_len), (PAGE_SIZE - curr_len),
+			     "\nAll available System PM levels info:\n");
+	for (lvl = UFS_PM_LVL_0; lvl < UFS_PM_LVL_MAX; lvl++)
+		curr_len += snprintf((buf + curr_len), (PAGE_SIZE - curr_len),
+				     "\tSystem PM level [%d] => dev_state [%s] link_state [%s]\n",
+				    lvl,
+				    ufschd_ufs_dev_pwr_mode_to_string(
+					ufs_pm_lvl_states[lvl].dev_state),
+				    ufschd_uic_link_state_to_string(
+					ufs_pm_lvl_states[lvl].link_state));
+
+	return curr_len;
+}
+
+static ssize_t ufshcd_spm_lvl_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	return ufshcd_pm_lvl_store(dev, attr, buf, count, false);
+}
+
+static void ufshcd_add_spm_lvl_sysfs_nodes(struct ufs_hba *hba)
+{
+	hba->spm_lvl_attr.show = ufshcd_spm_lvl_show;
+	hba->spm_lvl_attr.store = ufshcd_spm_lvl_store;
+	sysfs_attr_init(&hba->spm_lvl_attr.attr);
+	hba->spm_lvl_attr.attr.name = "spm_lvl";
+	hba->spm_lvl_attr.attr.mode = 0644;
+	if (device_create_file(hba->dev, &hba->spm_lvl_attr))
+		dev_err(hba->dev, "Failed to create sysfs for spm_lvl\n");
+}
+
+static inline void ufshcd_add_sysfs_nodes(struct ufs_hba *hba)
+{
+	ufshcd_add_rpm_lvl_sysfs_nodes(hba);
+	ufshcd_add_spm_lvl_sysfs_nodes(hba);
+}
+
 /**
  * ufshcd_shutdown - shutdown routine
  * @hba: per adapter instance
@@ -6465,6 +7094,8 @@ void ufshcd_remove(struct ufs_hba *hba)
 	ufshcd_hba_stop(hba, true);
 
 	ufshcd_exit_clk_gating(hba);
+	if (ufshcd_is_clkscaling_supported(hba))
+		device_remove_file(hba->dev, &hba->clk_scaling.enable_attr);
 	ufshcd_hba_exit(hba);
 }
 EXPORT_SYMBOL_GPL(ufshcd_remove);
@@ -6536,6 +7167,8 @@ static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up)
 	int ret = 0;
 	struct ufs_clk_info *clki;
 	struct list_head *head = &hba->clk_list_head;
+	ktime_t start = ktime_get();
+	bool clk_state_changed = false;
 
 	if (!head || list_empty(head))
 		goto out;
@@ -6549,6 +7182,8 @@ static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up)
 			if (scale_up && clki->max_freq) {
 				if (clki->curr_freq == clki->max_freq)
 					continue;
+
+				clk_state_changed = true;
 				ret = clk_set_rate(clki->clk, clki->max_freq);
 				if (ret) {
 					dev_err(hba->dev, "%s: %s clk set rate(%dHz) failed, %d\n",
@@ -6556,11 +7191,18 @@ static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up)
 						clki->max_freq, ret);
 					break;
 				}
+				trace_ufshcd_clk_scaling(dev_name(hba->dev),
+						"scaled up", clki->name,
+						clki->curr_freq,
+						clki->max_freq);
+
 				clki->curr_freq = clki->max_freq;
 
 			} else if (!scale_up && clki->min_freq) {
 				if (clki->curr_freq == clki->min_freq)
 					continue;
+
+				clk_state_changed = true;
 				ret = clk_set_rate(clki->clk, clki->min_freq);
 				if (ret) {
 					dev_err(hba->dev, "%s: %s clk set rate(%dHz) failed, %d\n",
@@ -6568,6 +7210,10 @@ static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up)
 						clki->min_freq, ret);
 					break;
 				}
+				trace_ufshcd_clk_scaling(dev_name(hba->dev),
+						"scaled down", clki->name,
+						clki->curr_freq,
+						clki->min_freq);
 				clki->curr_freq = clki->min_freq;
 			}
 		}
@@ -6578,6 +7224,10 @@ static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up)
 	ret = ufshcd_vops_clk_scale_notify(hba, scale_up, POST_CHANGE);
 
 out:
+	if (clk_state_changed)
+		trace_ufshcd_profile_clk_scaling(dev_name(hba->dev),
+			(scale_up ? "up" : "down"),
+			ktime_to_us(ktime_sub(ktime_get(), start)), ret);
 	return ret;
 }
 
@@ -6589,7 +7239,7 @@ static int ufshcd_devfreq_target(struct device *dev,
 	bool release_clk_hold = false;
 	unsigned long irq_flags;
 
-	if (!ufshcd_is_clkscaling_enabled(hba))
+	if (!ufshcd_is_clkscaling_supported(hba))
 		return -EINVAL;
 
 	spin_lock_irqsave(hba->host->host_lock, irq_flags);
@@ -6637,7 +7287,7 @@ static int ufshcd_devfreq_get_dev_status(struct device *dev,
 	struct ufs_clk_scaling *scaling = &hba->clk_scaling;
 	unsigned long flags;
 
-	if (!ufshcd_is_clkscaling_enabled(hba))
+	if (!ufshcd_is_clkscaling_supported(hba))
 		return -EINVAL;
 
 	memset(stat, 0, sizeof(*stat));
@@ -6673,6 +7323,16 @@ static struct devfreq_dev_profile ufs_devfreq_profile = {
 	.target		= ufshcd_devfreq_target,
 	.get_dev_status	= ufshcd_devfreq_get_dev_status,
 };
+static void ufshcd_clkscaling_init_sysfs(struct ufs_hba *hba)
+{
+	hba->clk_scaling.enable_attr.show = ufshcd_clkscale_enable_show;
+	hba->clk_scaling.enable_attr.store = ufshcd_clkscale_enable_store;
+	sysfs_attr_init(&hba->clk_scaling.enable_attr.attr);
+	hba->clk_scaling.enable_attr.attr.name = "clkscale_enable";
+	hba->clk_scaling.enable_attr.attr.mode = 0644;
+	if (device_create_file(hba->dev, &hba->clk_scaling.enable_attr))
+		dev_err(hba->dev, "Failed to create sysfs for clkscale_enable\n");
+}
 
 /**
  * ufshcd_init - Driver initialization routine
@@ -6795,10 +7455,11 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	err = ufshcd_hba_enable(hba);
 	if (err) {
 		dev_err(hba->dev, "Host controller enable failed\n");
+		ufshcd_print_host_regs(hba);
 		goto out_remove_scsi_host;
 	}
 
-	if (ufshcd_is_clkscaling_enabled(hba)) {
+	if (ufshcd_is_clkscaling_supported(hba)) {
 		hba->devfreq = devm_devfreq_add_device(dev, &ufs_devfreq_profile,
 						   "simple_ondemand", NULL);
 		if (IS_ERR(hba->devfreq)) {
@@ -6809,8 +7470,21 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 		}
 		/* Suspend devfreq until the UFS device is detected */
 		ufshcd_suspend_clkscaling(hba);
+		ufshcd_clkscaling_init_sysfs(hba);
 	}
 
+	/*
+	 * Set the default power management level for runtime and system PM.
+	 * Default power saving mode is to keep UFS link in Hibern8 state
+	 * and UFS device in sleep state.
+	 */
+	hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
+						UFS_SLEEP_PWR_MODE,
+						UIC_LINK_HIBERN8_STATE);
+	hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
+						UFS_SLEEP_PWR_MODE,
+						UIC_LINK_HIBERN8_STATE);
+
 	/* Hold auto suspend until async scan completes */
 	pm_runtime_get_sync(dev);
 
@@ -6823,6 +7497,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	ufshcd_set_ufs_dev_active(hba);
 
 	async_schedule(ufshcd_async_scan, hba);
+	ufshcd_add_sysfs_nodes(hba);
 
 	return 0;
 
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 08cd26ed2382..7ffcde21975b 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -152,6 +152,10 @@ struct ufs_pm_lvl_states {
  * @ucd_req_ptr: UCD address of the command
  * @ucd_rsp_ptr: Response UPIU address for this command
  * @ucd_prdt_ptr: PRDT address of the command
+ * @utrd_dma_addr: UTRD dma address for debug
+ * @ucd_prdt_dma_addr: PRDT dma address for debug
+ * @ucd_rsp_dma_addr: UPIU response dma address for debug
+ * @ucd_req_dma_addr: UPIU request dma address for debug
  * @cmd: pointer to SCSI command
  * @sense_buffer: pointer to sense buffer address of the SCSI command
  * @sense_bufflen: Length of the sense buffer
@@ -160,6 +164,7 @@ struct ufs_pm_lvl_states {
  * @task_tag: Task tag of the command
  * @lun: LUN of the command
  * @intr_cmd: Interrupt command (doesn't participate in interrupt aggregation)
+ * @issue_time_stamp: time stamp for debug purposes
  */
 struct ufshcd_lrb {
 	struct utp_transfer_req_desc *utr_descriptor_ptr;
@@ -167,6 +172,11 @@ struct ufshcd_lrb {
 	struct utp_upiu_rsp *ucd_rsp_ptr;
 	struct ufshcd_sg_entry *ucd_prdt_ptr;
 
+	dma_addr_t utrd_dma_addr;
+	dma_addr_t ucd_req_dma_addr;
+	dma_addr_t ucd_rsp_dma_addr;
+	dma_addr_t ucd_prdt_dma_addr;
+
 	struct scsi_cmnd *cmd;
 	u8 *sense_buffer;
 	unsigned int sense_bufflen;
@@ -176,6 +186,7 @@ struct ufshcd_lrb {
 	int task_tag;
 	u8 lun; /* UPIU LUN id field is only 8-bit wide */
 	bool intr_cmd;
+	ktime_t issue_time_stamp;
 };
 
 /**
@@ -320,6 +331,8 @@ enum clk_gating_state {
  * @is_suspended: clk gating is suspended when set to 1 which can be used
  * during suspend/resume
  * @delay_attr: sysfs attribute to control delay_attr
+ * @enable_attr: sysfs attribute to enable/disable clock gating
+ * @is_enabled: Indicates the current status of clock gating
  * @active_reqs: number of requests that are pending and should be waited for
  * completion before gating clocks.
  */
@@ -330,6 +343,8 @@ struct ufs_clk_gating {
 	unsigned long delay_ms;
 	bool is_suspended;
 	struct device_attribute delay_attr;
+	struct device_attribute enable_attr;
+	bool is_enabled;
 	int active_reqs;
 };
 
@@ -338,6 +353,8 @@ struct ufs_clk_scaling {
 	bool is_busy_started;
 	unsigned long  tot_busy_t;
 	unsigned long window_start_t;
+	struct device_attribute enable_attr;
+	bool is_allowed;
 };
 
 /**
@@ -349,6 +366,41 @@ struct ufs_init_prefetch {
 	u32 icc_level;
 };
 
+#define UIC_ERR_REG_HIST_LENGTH 8
+/**
+ * struct ufs_uic_err_reg_hist - keeps history of uic errors
+ * @pos: index to indicate cyclic buffer position
+ * @reg: cyclic buffer for registers value
+ * @tstamp: cyclic buffer for time stamp
+ */
+struct ufs_uic_err_reg_hist {
+	int pos;
+	u32 reg[UIC_ERR_REG_HIST_LENGTH];
+	ktime_t tstamp[UIC_ERR_REG_HIST_LENGTH];
+};
+
+/**
+ * struct ufs_stats - keeps usage/err statistics
+ * @hibern8_exit_cnt: Counter to keep track of number of exits,
+ *		reset this after link-startup.
+ * @last_hibern8_exit_tstamp: Set time after the hibern8 exit.
+ *		Clear after the first successful command completion.
+ * @pa_err: tracks pa-uic errors
+ * @dl_err: tracks dl-uic errors
+ * @nl_err: tracks nl-uic errors
+ * @tl_err: tracks tl-uic errors
+ * @dme_err: tracks dme errors
+ */
+struct ufs_stats {
+	u32 hibern8_exit_cnt;
+	ktime_t last_hibern8_exit_tstamp;
+	struct ufs_uic_err_reg_hist pa_err;
+	struct ufs_uic_err_reg_hist dl_err;
+	struct ufs_uic_err_reg_hist nl_err;
+	struct ufs_uic_err_reg_hist tl_err;
+	struct ufs_uic_err_reg_hist dme_err;
+};
+
 /**
  * struct ufs_hba - per adapter private structure
  * @mmio_base: UFSHCI base register address
@@ -429,6 +481,8 @@ struct ufs_hba {
 	enum ufs_pm_level rpm_lvl;
 	/* Desired UFS power management level during system PM */
 	enum ufs_pm_level spm_lvl;
+	struct device_attribute rpm_lvl_attr;
+	struct device_attribute spm_lvl_attr;
 	int pm_op_in_progress;
 
 	struct ufshcd_lrb *lrb;
@@ -523,6 +577,7 @@ struct ufs_hba {
 	u32 uic_error;
 	u32 saved_err;
 	u32 saved_uic_err;
+	struct ufs_stats ufs_stats;
 
 	/* Device management request data */
 	struct ufs_dev_cmd dev_cmd;
@@ -558,6 +613,14 @@ struct ufs_hba {
 	 * CAUTION: Enabling this might reduce overall UFS throughput.
 	 */
 #define UFSHCD_CAP_INTR_AGGR (1 << 4)
+	/*
+	 * This capability allows the device auto-bkops to be always enabled
+	 * except during suspend (both runtime and suspend).
+	 * Enabling this capability means that device will always be allowed
+	 * to do background operation when it's active but it might degrade
+	 * the performance of ongoing read/write operations.
+	 */
+#define UFSHCD_CAP_KEEP_AUTO_BKOPS_ENABLED_EXCEPT_SUSPEND (1 << 5)
 
 	struct devfreq *devfreq;
 	struct ufs_clk_scaling clk_scaling;
@@ -576,7 +639,7 @@ static inline bool ufshcd_can_hibern8_during_gating(struct ufs_hba *hba)
 {
 	return hba->caps & UFSHCD_CAP_HIBERN8_WITH_CLK_GATING;
 }
-static inline int ufshcd_is_clkscaling_enabled(struct ufs_hba *hba)
+static inline int ufshcd_is_clkscaling_supported(struct ufs_hba *hba)
 {
 	return hba->caps & UFSHCD_CAP_CLK_SCALING;
 }
@@ -655,6 +718,11 @@ static inline void *ufshcd_get_variant(struct ufs_hba *hba)
 	BUG_ON(!hba);
 	return hba->priv;
 }
+static inline bool ufshcd_keep_autobkops_enabled_except_suspend(
+							struct ufs_hba *hba)
+{
+	return hba->caps & UFSHCD_CAP_KEEP_AUTO_BKOPS_ENABLED_EXCEPT_SUSPEND;
+}
 
 extern int ufshcd_runtime_suspend(struct ufs_hba *hba);
 extern int ufshcd_runtime_resume(struct ufs_hba *hba);
@@ -713,8 +781,6 @@ static inline int ufshcd_dme_peer_get(struct ufs_hba *hba,
 	return ufshcd_dme_get_attr(hba, attr_sel, mib_val, DME_PEER);
 }
 
-int ufshcd_read_device_desc(struct ufs_hba *hba, u8 *buf, u32 size);
-
 static inline bool ufshcd_is_hs_mode(struct ufs_pa_layer_attr *pwr_info)
 {
 	return (pwr_info->pwr_rx == FAST_MODE ||
@@ -723,11 +789,6 @@ static inline bool ufshcd_is_hs_mode(struct ufs_pa_layer_attr *pwr_info)
 		pwr_info->pwr_tx == FASTAUTO_MODE);
 }
 
-#define ASCII_STD true
-
-int ufshcd_read_string_desc(struct ufs_hba *hba, int desc_index, u8 *buf,
-				u32 size, bool ascii);
-
 /* Expose Query-Request API */
 int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
 	enum flag_idn idn, bool *flag_res);
diff --git a/drivers/scsi/ufs/ufshci.h b/drivers/scsi/ufs/ufshci.h
index 8c5190e2e1c9..d14e9b965d1e 100644
--- a/drivers/scsi/ufs/ufshci.h
+++ b/drivers/scsi/ufs/ufshci.h
@@ -72,6 +72,9 @@ enum {
 	REG_UIC_COMMAND_ARG_1			= 0x94,
 	REG_UIC_COMMAND_ARG_2			= 0x98,
 	REG_UIC_COMMAND_ARG_3			= 0x9C,
+
+	UFSHCI_REG_SPACE_SIZE			= 0xA0,
+
 	REG_UFS_CCAP				= 0x100,
 	REG_UFS_CRYPTOCAP			= 0x104,
 
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 15ca09cd16f3..ef474a748744 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -68,10 +68,7 @@ struct pvscsi_ctx {
 
 struct pvscsi_adapter {
 	char				*mmioBase;
-	unsigned int			irq;
 	u8				rev;
-	bool				use_msi;
-	bool				use_msix;
 	bool				use_msg;
 	bool				use_req_threshold;
 
@@ -1161,30 +1158,26 @@ static bool pvscsi_setup_req_threshold(struct pvscsi_adapter *adapter,
 static irqreturn_t pvscsi_isr(int irq, void *devp)
 {
 	struct pvscsi_adapter *adapter = devp;
-	int handled;
-
-	if (adapter->use_msi || adapter->use_msix)
-		handled = true;
-	else {
-		u32 val = pvscsi_read_intr_status(adapter);
-		handled = (val & PVSCSI_INTR_ALL_SUPPORTED) != 0;
-		if (handled)
-			pvscsi_write_intr_status(devp, val);
-	}
-
-	if (handled) {
-		unsigned long flags;
+	unsigned long flags;
 
-		spin_lock_irqsave(&adapter->hw_lock, flags);
+	spin_lock_irqsave(&adapter->hw_lock, flags);
+	pvscsi_process_completion_ring(adapter);
+	if (adapter->use_msg && pvscsi_msg_pending(adapter))
+		queue_work(adapter->workqueue, &adapter->work);
+	spin_unlock_irqrestore(&adapter->hw_lock, flags);
 
-		pvscsi_process_completion_ring(adapter);
-		if (adapter->use_msg && pvscsi_msg_pending(adapter))
-			queue_work(adapter->workqueue, &adapter->work);
+	return IRQ_HANDLED;
+}
 
-		spin_unlock_irqrestore(&adapter->hw_lock, flags);
-	}
+static irqreturn_t pvscsi_shared_isr(int irq, void *devp)
+{
+	struct pvscsi_adapter *adapter = devp;
+	u32 val = pvscsi_read_intr_status(adapter);
 
-	return IRQ_RETVAL(handled);
+	if (!(val & PVSCSI_INTR_ALL_SUPPORTED))
+		return IRQ_NONE;
+	pvscsi_write_intr_status(devp, val);
+	return pvscsi_isr(irq, devp);
 }
 
 static void pvscsi_free_sgls(const struct pvscsi_adapter *adapter)
@@ -1196,34 +1189,10 @@ static void pvscsi_free_sgls(const struct pvscsi_adapter *adapter)
 		free_pages((unsigned long)ctx->sgl, get_order(SGL_SIZE));
 }
 
-static int pvscsi_setup_msix(const struct pvscsi_adapter *adapter,
-			     unsigned int *irq)
-{
-	struct msix_entry entry = { 0, PVSCSI_VECTOR_COMPLETION };
-	int ret;
-
-	ret = pci_enable_msix_exact(adapter->dev, &entry, 1);
-	if (ret)
-		return ret;
-
-	*irq = entry.vector;
-
-	return 0;
-}
-
 static void pvscsi_shutdown_intr(struct pvscsi_adapter *adapter)
 {
-	if (adapter->irq) {
-		free_irq(adapter->irq, adapter);
-		adapter->irq = 0;
-	}
-	if (adapter->use_msi) {
-		pci_disable_msi(adapter->dev);
-		adapter->use_msi = 0;
-	} else if (adapter->use_msix) {
-		pci_disable_msix(adapter->dev);
-		adapter->use_msix = 0;
-	}
+	free_irq(pci_irq_vector(adapter->dev, 0), adapter);
+	pci_free_irq_vectors(adapter->dev);
 }
 
 static void pvscsi_release_resources(struct pvscsi_adapter *adapter)
@@ -1359,11 +1328,11 @@ exit:
 
 static int pvscsi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	unsigned int irq_flag = PCI_IRQ_MSIX | PCI_IRQ_MSI | PCI_IRQ_LEGACY;
 	struct pvscsi_adapter *adapter;
 	struct pvscsi_adapter adapter_temp;
 	struct Scsi_Host *host = NULL;
 	unsigned int i;
-	unsigned long flags = 0;
 	int error;
 	u32 max_id;
 
@@ -1512,30 +1481,33 @@ static int pvscsi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto out_reset_adapter;
 	}
 
-	if (!pvscsi_disable_msix &&
-	    pvscsi_setup_msix(adapter, &adapter->irq) == 0) {
-		printk(KERN_INFO "vmw_pvscsi: using MSI-X\n");
-		adapter->use_msix = 1;
-	} else if (!pvscsi_disable_msi && pci_enable_msi(pdev) == 0) {
-		printk(KERN_INFO "vmw_pvscsi: using MSI\n");
-		adapter->use_msi = 1;
-		adapter->irq = pdev->irq;
-	} else {
-		printk(KERN_INFO "vmw_pvscsi: using INTx\n");
-		adapter->irq = pdev->irq;
-		flags = IRQF_SHARED;
-	}
+	if (pvscsi_disable_msix)
+		irq_flag &= ~PCI_IRQ_MSIX;
+	if (pvscsi_disable_msi)
+		irq_flag &= ~PCI_IRQ_MSI;
+
+	error = pci_alloc_irq_vectors(adapter->dev, 1, 1, irq_flag);
+	if (error)
+		goto out_reset_adapter;
 
 	adapter->use_req_threshold = pvscsi_setup_req_threshold(adapter, true);
 	printk(KERN_DEBUG "vmw_pvscsi: driver-based request coalescing %sabled\n",
 	       adapter->use_req_threshold ? "en" : "dis");
 
-	error = request_irq(adapter->irq, pvscsi_isr, flags,
-			    "vmw_pvscsi", adapter);
+	if (adapter->dev->msix_enabled || adapter->dev->msi_enabled) {
+		printk(KERN_INFO "vmw_pvscsi: using MSI%s\n",
+			adapter->dev->msix_enabled ? "-X" : "");
+		error = request_irq(pci_irq_vector(pdev, 0), pvscsi_isr,
+				0, "vmw_pvscsi", adapter);
+	} else {
+		printk(KERN_INFO "vmw_pvscsi: using INTx\n");
+		error = request_irq(pci_irq_vector(pdev, 0), pvscsi_shared_isr,
+				IRQF_SHARED, "vmw_pvscsi", adapter);
+	}
+
 	if (error) {
 		printk(KERN_ERR
 		       "vmw_pvscsi: unable to request IRQ: %d\n", error);
-		adapter->irq = 0;
 		goto out_reset_adapter;
 	}
 
diff --git a/drivers/scsi/vmw_pvscsi.h b/drivers/scsi/vmw_pvscsi.h
index d41292ef85f2..75966d3f326e 100644
--- a/drivers/scsi/vmw_pvscsi.h
+++ b/drivers/scsi/vmw_pvscsi.h
@@ -423,11 +423,6 @@ struct PVSCSIConfigPageController {
 #define PVSCSI_MAX_INTRS        24
 
 /*
- * Enumeration of supported MSI-X vectors
- */
-#define PVSCSI_VECTOR_COMPLETION   0
-
-/*
  * Misc constants for the rings.
  */