Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi

Pull SCSI updates from James Bottomley:
 "This is mostly update of the usual drivers: aacraid, ufs, zfcp,
  NCR5380, lpfc, qla2xxx, smartpqi, hisi_sas, target, mpt3sas, pm80xx
  plus a whole load of minor updates and fixes.

  The major core changes are Al Viro's reworking of sg's handling of
  copy to/from user, Ming Lei's removal of the host busy counter to
  avoid contention in the multiqueue case and Damien Le Moal's fixing of
  residual tracking across error handling"

* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (251 commits)
  scsi: bnx2fc: timeout calculation invalid for bnx2fc_eh_abort()
  scsi: target: core: Fix a pr_debug() argument
  scsi: iscsi: Don't send data to unbound connection
  scsi: target: iscsi: Wait for all commands to finish before freeing a session
  scsi: target: core: Release SPC-2 reservations when closing a session
  scsi: target: core: Document target_cmd_size_check()
  scsi: bnx2i: fix potential use after free
  Revert "scsi: qla2xxx: Fix memory leak when sending I/O fails"
  scsi: NCR5380: Add disconnect_mask module parameter
  scsi: NCR5380: Unconditionally clear ICR after do_abort()
  scsi: NCR5380: Call scsi_set_resid() on command completion
  scsi: scsi_debug: num_tgts must be >= 0
  scsi: lpfc: use hdwq assigned cpu for allocation
  scsi: arcmsr: fix indentation issues
  scsi: qla4xxx: fix double free bug
  scsi: pm80xx: Modified the logic to collect fatal dump
  scsi: pm80xx: Tie the interrupt name to the module instance
  scsi: pm80xx: Controller fatal error through sysfs
  scsi: pm80xx: Do not request 12G sas speeds
  scsi: pm80xx: Cleanup command when a reset times out
  ...

128 files changed, 4677 insertions, 1812 deletions

diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index 536426f25e86..f2f7e6e76c07 100644
--- a/drivers/scsi/NCR5380.c
+++ b/drivers/scsi/NCR5380.c
@@ -129,6 +129,9 @@
 #define NCR5380_release_dma_irq(x)
 #endif
 
+static unsigned int disconnect_mask = ~0;
+module_param(disconnect_mask, int, 0444);
+
 static int do_abort(struct Scsi_Host *);
 static void do_reset(struct Scsi_Host *);
 static void bus_reset_cleanup(struct Scsi_Host *);
@@ -172,6 +175,19 @@ static inline void advance_sg_buffer(struct scsi_cmnd *cmd)
 	}
 }
 
+static inline void set_resid_from_SCp(struct scsi_cmnd *cmd)
+{
+	int resid = cmd->SCp.this_residual;
+	struct scatterlist *s = cmd->SCp.buffer;
+
+	if (s)
+		while (!sg_is_last(s)) {
+			s = sg_next(s);
+			resid += s->length;
+		}
+	scsi_set_resid(cmd, resid);
+}
+
 /**
  * NCR5380_poll_politely2 - wait for two chip register values
  * @hostdata: host private data
@@ -954,7 +970,8 @@ static bool NCR5380_select(struct Scsi_Host *instance, struct scsi_cmnd *cmd)
 	int err;
 	bool ret = true;
 	bool can_disconnect = instance->irq != NO_IRQ &&
-			      cmd->cmnd[0] != REQUEST_SENSE;
+			      cmd->cmnd[0] != REQUEST_SENSE &&
+			      (disconnect_mask & BIT(scmd_id(cmd)));
 
 	NCR5380_dprint(NDEBUG_ARBITRATION, instance);
 	dsprintk(NDEBUG_ARBITRATION, instance, "starting arbitration, id = %d\n",
@@ -1379,7 +1396,7 @@ static void do_reset(struct Scsi_Host *instance)
  * MESSAGE OUT phase and sending an ABORT message.
  * @instance: relevant scsi host instance
  *
- * Returns 0 on success, -1 on failure.
+ * Returns 0 on success, negative error code on failure.
  */
 
 static int do_abort(struct Scsi_Host *instance)
@@ -1404,7 +1421,7 @@ static int do_abort(struct Scsi_Host *instance)
 
 	rc = NCR5380_poll_politely(hostdata, STATUS_REG, SR_REQ, SR_REQ, 10 * HZ);
 	if (rc < 0)
-		goto timeout;
+		goto out;
 
 	tmp = NCR5380_read(STATUS_REG) & PHASE_MASK;
 
@@ -1415,7 +1432,7 @@ static int do_abort(struct Scsi_Host *instance)
 		              ICR_BASE | ICR_ASSERT_ATN | ICR_ASSERT_ACK);
 		rc = NCR5380_poll_politely(hostdata, STATUS_REG, SR_REQ, 0, 3 * HZ);
 		if (rc < 0)
-			goto timeout;
+			goto out;
 		NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE | ICR_ASSERT_ATN);
 	}
 
@@ -1424,17 +1441,17 @@ static int do_abort(struct Scsi_Host *instance)
 	len = 1;
 	phase = PHASE_MSGOUT;
 	NCR5380_transfer_pio(instance, &phase, &len, &msgptr);
+	if (len)
+		rc = -ENXIO;
 
 	/*
 	 * If we got here, and the command completed successfully,
 	 * we're about to go into bus free state.
 	 */
 
-	return len ? -1 : 0;
-
-timeout:
+out:
 	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
-	return -1;
+	return rc;
 }
 
 /*
@@ -1803,6 +1820,8 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 					cmd->result |= cmd->SCp.Status;
 					cmd->result |= cmd->SCp.Message << 8;
 
+					set_resid_from_SCp(cmd);
+
 					if (cmd->cmnd[0] == REQUEST_SENSE)
 						complete_cmd(instance, cmd);
 					else {
@@ -2264,7 +2283,7 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 		dsprintk(NDEBUG_ABORT, instance, "abort: cmd %p is connected\n", cmd);
 		hostdata->connected = NULL;
 		hostdata->dma_len = 0;
-		if (do_abort(instance)) {
+		if (do_abort(instance) < 0) {
 			set_host_byte(cmd, DID_ERROR);
 			complete_cmd(instance, cmd);
 			result = FAILED;
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index 0ed3f806ace5..e36608ce937a 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -1477,6 +1477,7 @@ static struct aac_srb * aac_scsi_common(struct fib * fib, struct scsi_cmnd * cmd
 	struct aac_srb * srbcmd;
 	u32 flag;
 	u32 timeout;
+	struct aac_dev *dev = fib->dev;
 
 	aac_fib_init(fib);
 	switch(cmd->sc_data_direction){
@@ -1503,7 +1504,7 @@ static struct aac_srb * aac_scsi_common(struct fib * fib, struct scsi_cmnd * cmd
 	srbcmd->flags    = cpu_to_le32(flag);
 	timeout = cmd->request->timeout/HZ;
 	if (timeout == 0)
-		timeout = 1;
+		timeout = (dev->sa_firmware ? AAC_SA_TIMEOUT : AAC_ARC_TIMEOUT);
 	srbcmd->timeout  = cpu_to_le32(timeout);  // timeout in seconds
 	srbcmd->retry_limit = 0; /* Obsolete parameter */
 	srbcmd->cdb_size = cpu_to_le32(cmd->cmd_len);
@@ -2467,13 +2468,13 @@ static int aac_read(struct scsi_cmnd * scsicmd)
 		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
 			SAM_STAT_CHECK_CONDITION;
 		set_sense(&dev->fsa_dev[cid].sense_data,
-			  HARDWARE_ERROR, SENCODE_INTERNAL_TARGET_FAILURE,
+			  ILLEGAL_REQUEST, SENCODE_LBA_OUT_OF_RANGE,
 			  ASENCODE_INTERNAL_TARGET_FAILURE, 0, 0);
 		memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data,
 		       min_t(size_t, sizeof(dev->fsa_dev[cid].sense_data),
 			     SCSI_SENSE_BUFFERSIZE));
 		scsicmd->scsi_done(scsicmd);
-		return 1;
+		return 0;
 	}
 
 	dprintk((KERN_DEBUG "aac_read[cpu %d]: lba = %llu, t = %ld.\n",
@@ -2559,13 +2560,13 @@ static int aac_write(struct scsi_cmnd * scsicmd)
 		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
 			SAM_STAT_CHECK_CONDITION;
 		set_sense(&dev->fsa_dev[cid].sense_data,
-			  HARDWARE_ERROR, SENCODE_INTERNAL_TARGET_FAILURE,
+			  ILLEGAL_REQUEST, SENCODE_LBA_OUT_OF_RANGE,
 			  ASENCODE_INTERNAL_TARGET_FAILURE, 0, 0);
 		memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data,
 		       min_t(size_t, sizeof(dev->fsa_dev[cid].sense_data),
 			     SCSI_SENSE_BUFFERSIZE));
 		scsicmd->scsi_done(scsicmd);
-		return 1;
+		return 0;
 	}
 
 	dprintk((KERN_DEBUG "aac_write[cpu %d]: lba = %llu, t = %ld.\n",
diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index 3fa03230f6ba..e3e4ecbea726 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -85,7 +85,7 @@ enum {
 #define	PMC_GLOBAL_INT_BIT0		0x00000001
 
 #ifndef AAC_DRIVER_BUILD
-# define AAC_DRIVER_BUILD 50877
+# define AAC_DRIVER_BUILD 50983
 # define AAC_DRIVER_BRANCH "-custom"
 #endif
 #define MAXIMUM_NUM_CONTAINERS	32
@@ -108,6 +108,8 @@ enum {
 #define AAC_BUS_TARGET_LOOP		(AAC_MAX_BUSES * AAC_MAX_TARGETS)
 #define AAC_MAX_NATIVE_SIZE		2048
 #define FW_ERROR_BUFFER_SIZE		512
+#define AAC_SA_TIMEOUT			180
+#define AAC_ARC_TIMEOUT			60
 
 #define get_bus_number(x)	(x/AAC_MAX_TARGETS)
 #define get_target_number(x)	(x%AAC_MAX_TARGETS)
@@ -1328,7 +1330,7 @@ struct fib {
 #define AAC_DEVTYPE_ARC_RAW		2
 #define AAC_DEVTYPE_NATIVE_RAW		3
 
-#define AAC_SAFW_RESCAN_DELAY		(10 * HZ)
+#define AAC_RESCAN_DELAY		(10 * HZ)
 
 struct aac_hba_map_info {
 	__le32	rmw_nexus;		/* nexus for native HBA devices */
@@ -1601,6 +1603,7 @@ struct aac_dev
 	struct fsa_dev_info	*fsa_dev;
 	struct task_struct	*thread;
 	struct delayed_work	safw_rescan_work;
+	struct delayed_work	src_reinit_aif_worker;
 	int			cardtype;
 	/*
 	 *This lock will protect the two 32-bit
@@ -1673,6 +1676,7 @@ struct aac_dev
 	u8			adapter_shutdown;
 	u32			handle_pci_error;
 	bool			init_reset;
+	u8			soft_reset_support;
 };
 
 #define aac_adapter_interrupt(dev) \
@@ -2644,7 +2648,12 @@ int aac_scan_host(struct aac_dev *dev);
 
 static inline void aac_schedule_safw_scan_worker(struct aac_dev *dev)
 {
-	schedule_delayed_work(&dev->safw_rescan_work, AAC_SAFW_RESCAN_DELAY);
+	schedule_delayed_work(&dev->safw_rescan_work, AAC_RESCAN_DELAY);
+}
+
+static inline void aac_schedule_src_reinit_aif_worker(struct aac_dev *dev)
+{
+	schedule_delayed_work(&dev->src_reinit_aif_worker, AAC_RESCAN_DELAY);
 }
 
 static inline void aac_safw_rescan_worker(struct work_struct *work)
@@ -2658,10 +2667,10 @@ static inline void aac_safw_rescan_worker(struct work_struct *work)
 	aac_scan_host(dev);
 }
 
-static inline void aac_cancel_safw_rescan_worker(struct aac_dev *dev)
+static inline void aac_cancel_rescan_worker(struct aac_dev *dev)
 {
-	if (dev->sa_firmware)
-		cancel_delayed_work_sync(&dev->safw_rescan_work);
+	cancel_delayed_work_sync(&dev->safw_rescan_work);
+	cancel_delayed_work_sync(&dev->src_reinit_aif_worker);
 }
 
 /* SCp.phase values */
@@ -2671,6 +2680,7 @@ static inline void aac_cancel_safw_rescan_worker(struct aac_dev *dev)
 #define AAC_OWNER_FIRMWARE	0x106
 
 void aac_safw_rescan_worker(struct work_struct *work);
+void aac_src_reinit_aif_worker(struct work_struct *work);
 int aac_acquire_irq(struct aac_dev *dev);
 void aac_free_irq(struct aac_dev *dev);
 int aac_setup_safw_adapter(struct aac_dev *dev);
@@ -2728,6 +2738,7 @@ int aac_probe_container(struct aac_dev *dev, int cid);
 int _aac_rx_init(struct aac_dev *dev);
 int aac_rx_select_comm(struct aac_dev *dev, int comm);
 int aac_rx_deliver_producer(struct fib * fib);
+void aac_reinit_aif(struct aac_dev *aac, unsigned int index);
 
 static inline int aac_is_src(struct aac_dev *dev)
 {
diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c
index d4fcfa1e54e0..f75878d773cf 100644
--- a/drivers/scsi/aacraid/comminit.c
+++ b/drivers/scsi/aacraid/comminit.c
@@ -571,6 +571,11 @@ struct aac_dev *aac_init_adapter(struct aac_dev *dev)
 		else
 			dev->sa_firmware = 0;
 
+		if (status[4] & le32_to_cpu(AAC_EXTOPT_SOFT_RESET))
+			dev->soft_reset_support = 1;
+		else
+			dev->soft_reset_support = 0;
+
 		if ((dev->comm_interface == AAC_COMM_MESSAGE) &&
 		    (status[2] > dev->base_size)) {
 			aac_adapter_ioremap(dev, 0);
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 2142a649e865..5a8a999606ea 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -232,6 +232,7 @@ struct fib *aac_fib_alloc_tag(struct aac_dev *dev, struct scsi_cmnd *scmd)
 	fibptr->type = FSAFS_NTC_FIB_CONTEXT;
 	fibptr->callback_data = NULL;
 	fibptr->callback = NULL;
+	fibptr->flags = 0;
 
 	return fibptr;
 }
@@ -1463,6 +1464,14 @@ retry_next:
 	}
 }
 
+static void aac_schedule_bus_scan(struct aac_dev *aac)
+{
+	if (aac->sa_firmware)
+		aac_schedule_safw_scan_worker(aac);
+	else
+		aac_schedule_src_reinit_aif_worker(aac);
+}
+
 static int _aac_reset_adapter(struct aac_dev *aac, int forced, u8 reset_type)
 {
 	int index, quirks;
@@ -1638,7 +1647,7 @@ out:
 	 */
 	if (!retval && !is_kdump_kernel()) {
 		dev_info(&aac->pdev->dev, "Scheduling bus rescan\n");
-		aac_schedule_safw_scan_worker(aac);
+		aac_schedule_bus_scan(aac);
 	}
 
 	if (jafo) {
@@ -1959,6 +1968,16 @@ int aac_scan_host(struct aac_dev *dev)
 	return rcode;
 }
 
+void aac_src_reinit_aif_worker(struct work_struct *work)
+{
+	struct aac_dev *dev = container_of(to_delayed_work(work),
+				struct aac_dev, src_reinit_aif_worker);
+
+	wait_event(dev->scsi_host_ptr->host_wait,
+			!scsi_host_in_recovery(dev->scsi_host_ptr));
+	aac_reinit_aif(dev, dev->cardtype);
+}
+
 /**
  *	aac_handle_sa_aif	Handle a message from the firmware
  *	@dev: Which adapter this fib is from
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 4a858789e6c5..ee6bc2f9b80a 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -391,6 +391,7 @@ static int aac_slave_configure(struct scsi_device *sdev)
 	int chn, tid;
 	unsigned int depth = 0;
 	unsigned int set_timeout = 0;
+	int timeout = 0;
 	bool set_qd_dev_type = false;
 	u8 devtype = 0;
 
@@ -483,10 +484,13 @@ common_config:
 
 	/*
 	 * Firmware has an individual device recovery time typically
-	 * of 35 seconds, give us a margin.
+	 * of 35 seconds, give us a margin. Thor devices can take longer in
+	 * error recovery, hence different value.
 	 */
-	if (set_timeout && sdev->request_queue->rq_timeout < (45 * HZ))
-		blk_queue_rq_timeout(sdev->request_queue, 45*HZ);
+	if (set_timeout) {
+		timeout = aac->sa_firmware ? AAC_SA_TIMEOUT : AAC_ARC_TIMEOUT;
+		blk_queue_rq_timeout(sdev->request_queue, timeout * HZ);
+	}
 
 	if (depth > 256)
 		depth = 256;
@@ -608,9 +612,13 @@ static struct device_attribute *aac_dev_attrs[] = {
 static int aac_ioctl(struct scsi_device *sdev, unsigned int cmd,
 		     void __user *arg)
 {
+	int retval;
 	struct aac_dev *dev = (struct aac_dev *)sdev->host->hostdata;
 	if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
+	retval = aac_adapter_check_health(dev);
+	if (retval)
+		return -EBUSY;
 	return aac_do_ioctl(dev, cmd, arg);
 }
 
@@ -1585,6 +1593,19 @@ static void aac_init_char(void)
 	}
 }
 
+void aac_reinit_aif(struct aac_dev *aac, unsigned int index)
+{
+	/*
+	 * Firmware may send a AIF messages very early and the Driver may have
+	 * ignored as it is not fully ready to process the messages. Send
+	 * AIF to firmware so that if there are any unprocessed events they
+	 * can be processed now.
+	 */
+	if (aac_drivers[index].quirks & AAC_QUIRK_SRC)
+		aac_intr_normal(aac, 0, 2, 0, NULL);
+
+}
+
 static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	unsigned index = id->driver_data;
@@ -1682,6 +1703,8 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	mutex_init(&aac->scan_mutex);
 
 	INIT_DELAYED_WORK(&aac->safw_rescan_work, aac_safw_rescan_worker);
+	INIT_DELAYED_WORK(&aac->src_reinit_aif_worker,
+				aac_src_reinit_aif_worker);
 	/*
 	 *	Map in the registers from the adapter.
 	 */
@@ -1872,7 +1895,7 @@ static int aac_suspend(struct pci_dev *pdev, pm_message_t state)
 	struct aac_dev *aac = (struct aac_dev *)shost->hostdata;
 
 	scsi_block_requests(shost);
-	aac_cancel_safw_rescan_worker(aac);
+	aac_cancel_rescan_worker(aac);
 	aac_send_shutdown(aac);
 
 	aac_release_resources(aac);
@@ -1931,7 +1954,7 @@ static void aac_remove_one(struct pci_dev *pdev)
 	struct Scsi_Host *shost = pci_get_drvdata(pdev);
 	struct aac_dev *aac = (struct aac_dev *)shost->hostdata;
 
-	aac_cancel_safw_rescan_worker(aac);
+	aac_cancel_rescan_worker(aac);
 	scsi_remove_host(shost);
 
 	__aac_shutdown(aac);
@@ -1989,7 +2012,7 @@ static pci_ers_result_t aac_pci_error_detected(struct pci_dev *pdev,
 		aac->handle_pci_error = 1;
 
 		scsi_block_requests(aac->scsi_host_ptr);
-		aac_cancel_safw_rescan_worker(aac);
+		aac_cancel_rescan_worker(aac);
 		aac_flush_ios(aac);
 		aac_release_resources(aac);
 
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 3b66e06726c8..787ec9baebb0 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -733,10 +733,20 @@ static bool aac_is_ctrl_up_and_running(struct aac_dev *dev)
 	return ctrl_up;
 }
 
+static void aac_src_drop_io(struct aac_dev *dev)
+{
+	if (!dev->soft_reset_support)
+		return;
+
+	aac_adapter_sync_cmd(dev, DROP_IO,
+			0, 0, 0, 0, 0, 0, NULL, NULL, NULL, NULL, NULL);
+}
+
 static void aac_notify_fw_of_iop_reset(struct aac_dev *dev)
 {
 	aac_adapter_sync_cmd(dev, IOP_RESET_ALWAYS, 0, 0, 0, 0, 0, 0, NULL,
 						NULL, NULL, NULL, NULL);
+	aac_src_drop_io(dev);
 }
 
 static void aac_send_iop_reset(struct aac_dev *dev)
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 88053b15c363..db687ef8a99e 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -1400,7 +1400,7 @@ static void arcmsr_drain_donequeue(struct AdapterControlBlock *acb, struct Comma
 				, pCCB->acb
 				, pCCB->startdone
 				, atomic_read(&acb->ccboutstandingcount));
-		  return;
+		return;
 	}
 	arcmsr_report_ccb_state(acb, pCCB, error);
 }
@@ -3476,8 +3476,8 @@ polling_hbc_ccb_retry:
 					, pCCB->pcmd->device->id
 					, (u32)pCCB->pcmd->device->lun
 					, pCCB);
-					pCCB->pcmd->result = DID_ABORT << 16;
-					arcmsr_ccb_complete(pCCB);
+				pCCB->pcmd->result = DID_ABORT << 16;
+				arcmsr_ccb_complete(pCCB);
 				continue;
 			}
 			printk(KERN_NOTICE "arcmsr%d: polling get an illegal ccb"
diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c
index d12dd89538df..ddb52e7ba622 100644
--- a/drivers/scsi/arm/acornscsi.c
+++ b/drivers/scsi/arm/acornscsi.c
@@ -1067,7 +1067,7 @@ void acornscsi_dma_setup(AS_Host *host, dmadir_t direction)
  * Purpose : ensure that all DMA transfers are up-to-date & host->scsi.SCp is correct
  * Params  : host - host to finish
  * Notes   : This is called when a command is:
- *		terminating, RESTORE_POINTERS, SAVE_POINTERS, DISCONECT
+ *		terminating, RESTORE_POINTERS, SAVE_POINTERS, DISCONNECT
  *	   : This must not return until all transfers are completed.
  */
 static
@@ -1816,7 +1816,7 @@ int acornscsi_reconnect(AS_Host *host)
 }
 
 /*
- * Function: int acornscsi_reconect_finish(AS_Host *host)
+ * Function: int acornscsi_reconnect_finish(AS_Host *host)
  * Purpose : finish reconnecting a command
  * Params  : host - host to complete
  * Returns : 0 if failed
diff --git a/drivers/scsi/atari_scsi.c b/drivers/scsi/atari_scsi.c
index e809493d0d06..a82b63a66635 100644
--- a/drivers/scsi/atari_scsi.c
+++ b/drivers/scsi/atari_scsi.c
@@ -742,7 +742,7 @@ static int __init atari_scsi_probe(struct platform_device *pdev)
 		atari_scsi_template.sg_tablesize = SG_ALL;
 	} else {
 		atari_scsi_template.can_queue    = 1;
-		atari_scsi_template.sg_tablesize = SG_NONE;
+		atari_scsi_template.sg_tablesize = 1;
 	}
 
 	if (setup_can_queue > 0)
@@ -751,8 +751,8 @@ static int __init atari_scsi_probe(struct platform_device *pdev)
 	if (setup_cmd_per_lun > 0)
 		atari_scsi_template.cmd_per_lun = setup_cmd_per_lun;
 
-	/* Leave sg_tablesize at 0 on a Falcon! */
-	if (ATARIHW_PRESENT(TT_SCSI) && setup_sg_tablesize >= 0)
+	/* Don't increase sg_tablesize on Falcon! */
+	if (ATARIHW_PRESENT(TT_SCSI) && setup_sg_tablesize > 0)
 		atari_scsi_template.sg_tablesize = setup_sg_tablesize;
 
 	if (setup_hostid >= 0) {
diff --git a/drivers/scsi/atp870u.c b/drivers/scsi/atp870u.c
index e41f0bbdc9fd..c6a752309dda 100644
--- a/drivers/scsi/atp870u.c
+++ b/drivers/scsi/atp870u.c
@@ -1680,7 +1680,7 @@ static struct scsi_host_template atp870u_template = {
      .bios_param        	= atp870u_biosparam	/* biosparm */,
      .can_queue         	= qcnt			/* can_queue */,
      .this_id           	= 7			/* SCSI ID */,
-     .sg_tablesize      	= ATP870U_SCATTER	/*SG_ALL*/ /*SG_NONE*/,
+     .sg_tablesize      	= ATP870U_SCATTER	/*SG_ALL*/,
      .max_sectors		= ATP870U_MAX_SECTORS,
 };
 
diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c
index 2f9213b257a4..eb0c76338295 100644
--- a/drivers/scsi/bfa/bfad.c
+++ b/drivers/scsi/bfa/bfad.c
@@ -1487,8 +1487,7 @@ bfad_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
 	return ret;
 }
 
-int
-restart_bfa(struct bfad_s *bfad)
+static int restart_bfa(struct bfad_s *bfad)
 {
 	unsigned long flags;
 	struct pci_dev *pdev = bfad->pcidev;
diff --git a/drivers/scsi/bfa/bfad_attr.c b/drivers/scsi/bfa/bfad_attr.c
index 29ab81df75c0..fbfce02e5b93 100644
--- a/drivers/scsi/bfa/bfad_attr.c
+++ b/drivers/scsi/bfa/bfad_attr.c
@@ -275,8 +275,10 @@ bfad_im_get_stats(struct Scsi_Host *shost)
 	rc = bfa_port_get_stats(BFA_FCPORT(&bfad->bfa),
 				fcstats, bfad_hcb_comp, &fcomp);
 	spin_unlock_irqrestore(&bfad->bfad_lock, flags);
-	if (rc != BFA_STATUS_OK)
+	if (rc != BFA_STATUS_OK) {
+		kfree(fcstats);
 		return NULL;
+	}
 
 	wait_for_completion(&fcomp.comp);
 
diff --git a/drivers/scsi/bnx2fc/57xx_hsi_bnx2fc.h b/drivers/scsi/bnx2fc/57xx_hsi_bnx2fc.h
index e4469df9c469..698f5ebaa0c2 100644
--- a/drivers/scsi/bnx2fc/57xx_hsi_bnx2fc.h
+++ b/drivers/scsi/bnx2fc/57xx_hsi_bnx2fc.h
@@ -813,7 +813,7 @@ struct fcoe_confqe {
 
 
 /*
- * FCoE conection data base
+ * FCoE connection data base
  */
 struct fcoe_conn_db {
 #if defined(__BIG_ENDIAN)
diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c
index 401743e2b429..4c8122a82322 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_io.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_io.c
@@ -1242,7 +1242,7 @@ int bnx2fc_eh_abort(struct scsi_cmnd *sc_cmd)
 
 	/* Wait 2 * RA_TOV + 1 to be sure timeout function hasn't fired */
 	time_left = wait_for_completion_timeout(&io_req->abts_done,
-						(2 * rp->r_a_tov + 1) * HZ);
+					msecs_to_jiffies(2 * rp->r_a_tov + 1));
 	if (time_left)
 		BNX2FC_IO_DBG(io_req,
 			      "Timed out in eh_abort waiting for abts_done");
diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c
index c5fa5f3b00e9..0b28d44d3573 100644
--- a/drivers/scsi/bnx2i/bnx2i_iscsi.c
+++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c
@@ -915,12 +915,12 @@ void bnx2i_free_hba(struct bnx2i_hba *hba)
 	INIT_LIST_HEAD(&hba->ep_ofld_list);
 	INIT_LIST_HEAD(&hba->ep_active_list);
 	INIT_LIST_HEAD(&hba->ep_destroy_list);
-	pci_dev_put(hba->pcidev);
 
 	if (hba->regview) {
 		pci_iounmap(hba->pcidev, hba->regview);
 		hba->regview = NULL;
 	}
+	pci_dev_put(hba->pcidev);
 	bnx2i_free_mp_bdt(hba);
 	bnx2i_release_free_cid_que(hba);
 	iscsi_host_free(shost);
diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c
index e51923886475..950f9cdf0577 100644
--- a/drivers/scsi/csiostor/csio_hw.c
+++ b/drivers/scsi/csiostor/csio_hw.c
@@ -793,10 +793,10 @@ csio_hw_get_flash_params(struct csio_hw *hw)
 			goto found;
 		}
 
-	/* Decode Flash part size.  The code below looks repetative with
+	/* Decode Flash part size.  The code below looks repetitive with
 	 * common encodings, but that's not guaranteed in the JEDEC
-	 * specification for the Read JADEC ID command.  The only thing that
-	 * we're guaranteed by the JADEC specification is where the
+	 * specification for the Read JEDEC ID command.  The only thing that
+	 * we're guaranteed by the JEDEC specification is where the
 	 * Manufacturer ID is in the returned result.  After that each
 	 * Manufacturer ~could~ encode things completely differently.
 	 * Note, all Flash parts must have 64KB sectors.
@@ -983,8 +983,8 @@ retry:
 			waiting -= 50;
 
 			/*
-			 * If neither Error nor Initialialized are indicated
-			 * by the firmware keep waiting till we exaust our
+			 * If neither Error nor Initialized are indicated
+			 * by the firmware keep waiting till we exhaust our
 			 * timeout ... and then retry if we haven't exhausted
 			 * our retries ...
 			 */
@@ -1738,7 +1738,7 @@ static void csio_link_l1cfg(struct link_config *lc, uint16_t fw_caps,
 	 * Convert Common Code Forward Error Control settings into the
 	 * Firmware's API.  If the current Requested FEC has "Automatic"
 	 * (IEEE 802.3) specified, then we use whatever the Firmware
-	 * sent us as part of it's IEEE 802.3-based interpratation of
+	 * sent us as part of it's IEEE 802.3-based interpretation of
 	 * the Transceiver Module EPROM FEC parameters.  Otherwise we
 	 * use whatever is in the current Requested FEC settings.
 	 */
@@ -2834,7 +2834,7 @@ csio_hws_configuring(struct csio_hw *hw, enum csio_hw_ev evt)
 }
 
 /*
- * csio_hws_initializing - Initialiazing state
+ * csio_hws_initializing - Initializing state
  * @hw - HW module
  * @evt - Event
  *
@@ -3049,7 +3049,7 @@ csio_hws_removing(struct csio_hw *hw, enum csio_hw_ev evt)
 		if (!csio_is_hw_master(hw))
 			break;
 		/*
-		 * The BYE should have alerady been issued, so we cant
+		 * The BYE should have already been issued, so we can't
 		 * use the mailbox interface. Hence we use the PL_RST
 		 * register directly.
 		 */
@@ -3104,7 +3104,7 @@ csio_hws_pcierr(struct csio_hw *hw, enum csio_hw_ev evt)
  *
  *	A table driven interrupt handler that applies a set of masks to an
  *	interrupt status word and performs the corresponding actions if the
- *	interrupts described by the mask have occured.  The actions include
+ *	interrupts described by the mask have occurred.  The actions include
  *	optionally emitting a warning or alert message. The table is terminated
  *	by an entry specifying mask 0.  Returns the number of fatal interrupt
  *	conditions.
@@ -4219,7 +4219,7 @@ csio_mgmtm_exit(struct csio_mgmtm *mgmtm)
  * @hw:		Pointer to HW module.
  *
  * It is assumed that the initialization is a synchronous operation.
- * So when we return afer posting the event, the HW SM should be in
+ * So when we return after posting the event, the HW SM should be in
  * the ready state, if there were no errors during init.
  */
 int
diff --git a/drivers/scsi/csiostor/csio_init.c b/drivers/scsi/csiostor/csio_init.c
index a6dd704d7f2d..2e8a3ac575cb 100644
--- a/drivers/scsi/csiostor/csio_init.c
+++ b/drivers/scsi/csiostor/csio_init.c
@@ -154,13 +154,10 @@ csio_dfs_create(struct csio_hw *hw)
 /*
  * csio_dfs_destroy - Destroys per-hw debugfs.
  */
-static int
+static void
 csio_dfs_destroy(struct csio_hw *hw)
 {
-	if (hw->debugfs_root)
-		debugfs_remove_recursive(hw->debugfs_root);
-
-	return 0;
+	debugfs_remove_recursive(hw->debugfs_root);
 }
 
 /*
diff --git a/drivers/scsi/csiostor/csio_lnode.c b/drivers/scsi/csiostor/csio_lnode.c
index 66e58f0a75dc..74ff8adc41f7 100644
--- a/drivers/scsi/csiostor/csio_lnode.c
+++ b/drivers/scsi/csiostor/csio_lnode.c
@@ -301,6 +301,7 @@ csio_ln_fdmi_rhba_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req)
 	struct fc_fdmi_port_name *port_name;
 	uint8_t buf[64];
 	uint8_t *fc4_type;
+	unsigned long flags;
 
 	if (fdmi_req->wr_status != FW_SUCCESS) {
 		csio_ln_dbg(ln, "WR error:%x in processing fdmi rhba cmd\n",
@@ -385,13 +386,13 @@ csio_ln_fdmi_rhba_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req)
 	len = (uint32_t)(pld - (uint8_t *)cmd);
 
 	/* Submit FDMI RPA request */
-	spin_lock_irq(&hw->lock);
+	spin_lock_irqsave(&hw->lock, flags);
 	if (csio_ln_mgmt_submit_req(fdmi_req, csio_ln_fdmi_done,
 				FCOE_CT, &fdmi_req->dma_buf, len)) {
 		CSIO_INC_STATS(ln, n_fdmi_err);
 		csio_ln_dbg(ln, "Failed to issue fdmi rpa req\n");
 	}
-	spin_unlock_irq(&hw->lock);
+	spin_unlock_irqrestore(&hw->lock, flags);
 }
 
 /*
@@ -412,6 +413,7 @@ csio_ln_fdmi_dprt_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req)
 	struct fc_fdmi_rpl *reg_pl;
 	struct fs_fdmi_attrs *attrib_blk;
 	uint8_t buf[64];
+	unsigned long flags;
 
 	if (fdmi_req->wr_status != FW_SUCCESS) {
 		csio_ln_dbg(ln, "WR error:%x in processing fdmi dprt cmd\n",
@@ -491,13 +493,13 @@ csio_ln_fdmi_dprt_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req)
 	attrib_blk->numattrs = htonl(numattrs);
 
 	/* Submit FDMI RHBA request */
-	spin_lock_irq(&hw->lock);
+	spin_lock_irqsave(&hw->lock, flags);
 	if (csio_ln_mgmt_submit_req(fdmi_req, csio_ln_fdmi_rhba_cbfn,
 				FCOE_CT, &fdmi_req->dma_buf, len)) {
 		CSIO_INC_STATS(ln, n_fdmi_err);
 		csio_ln_dbg(ln, "Failed to issue fdmi rhba req\n");
 	}
-	spin_unlock_irq(&hw->lock);
+	spin_unlock_irqrestore(&hw->lock, flags);
 }
 
 /*
@@ -512,6 +514,7 @@ csio_ln_fdmi_dhba_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req)
 	void *cmd;
 	struct fc_fdmi_port_name *port_name;
 	uint32_t len;
+	unsigned long flags;
 
 	if (fdmi_req->wr_status != FW_SUCCESS) {
 		csio_ln_dbg(ln, "WR error:%x in processing fdmi dhba cmd\n",
@@ -542,13 +545,13 @@ csio_ln_fdmi_dhba_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req)
 	len += sizeof(*port_name);
 
 	/* Submit FDMI request */
-	spin_lock_irq(&hw->lock);
+	spin_lock_irqsave(&hw->lock, flags);
 	if (csio_ln_mgmt_submit_req(fdmi_req, csio_ln_fdmi_dprt_cbfn,
 				FCOE_CT, &fdmi_req->dma_buf, len)) {
 		CSIO_INC_STATS(ln, n_fdmi_err);
 		csio_ln_dbg(ln, "Failed to issue fdmi dprt req\n");
 	}
-	spin_unlock_irq(&hw->lock);
+	spin_unlock_irqrestore(&hw->lock, flags);
 }
 
 /**
@@ -1989,7 +1992,7 @@ static int
 csio_ln_init(struct csio_lnode *ln)
 {
 	int rv = -EINVAL;
-	struct csio_lnode *rln, *pln;
+	struct csio_lnode *pln;
 	struct csio_hw *hw = csio_lnode_to_hw(ln);
 
 	csio_init_state(&ln->sm, csio_lns_uninit);
@@ -2019,7 +2022,6 @@ csio_ln_init(struct csio_lnode *ln)
 		 * THe rest is common for non-root physical and NPIV lnodes.
 		 * Just get references to all other modules
 		 */
-		rln = csio_root_lnode(ln);
 
 		if (csio_is_npiv_ln(ln)) {
 			/* NPIV */
diff --git a/drivers/scsi/csiostor/csio_mb.c b/drivers/scsi/csiostor/csio_mb.c
index 6f13673d6aa0..94810b19e747 100644
--- a/drivers/scsi/csiostor/csio_mb.c
+++ b/drivers/scsi/csiostor/csio_mb.c
@@ -1210,7 +1210,7 @@ csio_mb_issue(struct csio_hw *hw, struct csio_mb *mbp)
 		   !csio_is_hw_intr_enabled(hw)) {
 		csio_err(hw, "Cannot issue mailbox in interrupt mode 0x%x\n",
 			 *((uint8_t *)mbp->mb));
-			goto error_out;
+		goto error_out;
 	}
 
 	if (mbm->mcurrent != NULL) {
diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index da50e87921bc..bc1086ae6835 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -2073,7 +2073,6 @@ static int cxgb4i_ddp_init(struct cxgbi_device *cdev)
 	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
 	struct net_device *ndev = cdev->ports[0];
 	struct cxgbi_tag_format tformat;
-	unsigned int ppmax;
 	int i, err;
 
 	if (!lldi->vr->iscsi.size) {
@@ -2082,7 +2081,6 @@ static int cxgb4i_ddp_init(struct cxgbi_device *cdev)
 	}
 
 	cdev->flags |= CXGBI_FLAG_USE_PPOD_OFLDQ;
-	ppmax = lldi->vr->iscsi.size >> PPOD_SIZE_SHIFT;
 
 	memset(&tformat, 0, sizeof(struct cxgbi_tag_format));
 	for (i = 0; i < 4; i++)
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index 3e17af8aedeb..0d044c165960 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -2284,34 +2284,6 @@ int cxgbi_set_conn_param(struct iscsi_cls_conn *cls_conn,
 }
 EXPORT_SYMBOL_GPL(cxgbi_set_conn_param);
 
-static inline int csk_print_port(struct cxgbi_sock *csk, char *buf)
-{
-	int len;
-
-	cxgbi_sock_get(csk);
-	len = sprintf(buf, "%hu\n", ntohs(csk->daddr.sin_port));
-	cxgbi_sock_put(csk);
-
-	return len;
-}
-
-static inline int csk_print_ip(struct cxgbi_sock *csk, char *buf)
-{
-	int len;
-
-	cxgbi_sock_get(csk);
-	if (csk->csk_family == AF_INET)
-		len = sprintf(buf, "%pI4",
-			      &csk->daddr.sin_addr.s_addr);
-	else
-		len = sprintf(buf, "%pI6",
-			      &csk->daddr6.sin6_addr);
-
-	cxgbi_sock_put(csk);
-
-	return len;
-}
-
 int cxgbi_get_ep_param(struct iscsi_endpoint *ep, enum iscsi_param param,
 		       char *buf)
 {
diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index 2dbf35f82787..fbd2ae40dab4 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -44,14 +44,12 @@ 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;
 
 	if (unlikely(!cmd))
 		return;
 
-	ioarcb = &(cmd->rcb);
 	ioasa = &(cmd->sa);
 
 	if (ioasa->rc.flags & SISL_RC_FLAGS_UNDERRUN) {
diff --git a/drivers/scsi/esas2r/esas2r_flash.c b/drivers/scsi/esas2r/esas2r_flash.c
index 7bd376d95ed5..b02ac389e6c6 100644
--- a/drivers/scsi/esas2r/esas2r_flash.c
+++ b/drivers/scsi/esas2r/esas2r_flash.c
@@ -1197,6 +1197,7 @@ bool esas2r_nvram_read_direct(struct esas2r_adapter *a)
 	if (!esas2r_read_flash_block(a, a->nvram, FLS_OFFSET_NVR,
 				     sizeof(struct esas2r_sas_nvram))) {
 		esas2r_hdebug("NVRAM read failed, using defaults");
+		up(&a->nvram_semaphore);
 		return false;
 	}
 
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 80608b53897b..8ef150dfb6f7 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -1024,7 +1024,8 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic,
 		atomic64_inc(&fnic_stats->io_stats.io_completions);
 
 
-	io_duration_time = jiffies_to_msecs(jiffies) - jiffies_to_msecs(io_req->start_time);
+	io_duration_time = jiffies_to_msecs(jiffies) -
+						jiffies_to_msecs(start_time);
 
 	if(io_duration_time <= 10)
 		atomic64_inc(&fnic_stats->io_stats.io_btw_0_to_10_msec);
diff --git a/drivers/scsi/fnic/vnic_dev.c b/drivers/scsi/fnic/vnic_dev.c
index 78af9cc2009b..1f55b9e4e74a 100644
--- a/drivers/scsi/fnic/vnic_dev.c
+++ b/drivers/scsi/fnic/vnic_dev.c
@@ -259,7 +259,7 @@ int vnic_dev_cmd1(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd, int wait)
 	struct vnic_devcmd __iomem *devcmd = vdev->devcmd;
 	int delay;
 	u32 status;
-	int dev_cmd_err[] = {
+	static const int dev_cmd_err[] = {
 		/* convert from fw's version of error.h to host's version */
 		0,	/* ERR_SUCCESS */
 		EINVAL,	/* ERR_EINVAL */
diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 720c4d6be939..233c73e01246 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -21,6 +21,7 @@
 #include <linux/platform_device.h>
 #include <linux/property.h>
 #include <linux/regmap.h>
+#include <linux/timer.h>
 #include <scsi/sas_ata.h>
 #include <scsi/libsas.h>
 
@@ -84,6 +85,7 @@
 #define HISI_SAS_PROT_MASK (HISI_SAS_DIF_PROT_MASK | HISI_SAS_DIX_PROT_MASK)
 
 #define HISI_SAS_WAIT_PHYUP_TIMEOUT 20
+#define CLEAR_ITCT_TIMEOUT	20
 
 struct hisi_hba;
 
@@ -167,6 +169,7 @@ struct hisi_sas_phy {
 	enum sas_linkrate	minimum_linkrate;
 	enum sas_linkrate	maximum_linkrate;
 	int enable;
+	atomic_t down_cnt;
 };
 
 struct hisi_sas_port {
@@ -296,8 +299,8 @@ struct hisi_sas_hw {
 	void (*phy_set_linkrate)(struct hisi_hba *hisi_hba, int phy_no,
 			struct sas_phy_linkrates *linkrates);
 	enum sas_linkrate (*phy_get_max_linkrate)(void);
-	void (*clear_itct)(struct hisi_hba *hisi_hba,
-			    struct hisi_sas_device *dev);
+	int (*clear_itct)(struct hisi_hba *hisi_hba,
+			  struct hisi_sas_device *dev);
 	void (*free_device)(struct hisi_sas_device *sas_dev);
 	int (*get_wideport_bitmap)(struct hisi_hba *hisi_hba, int port_id);
 	void (*dereg_device)(struct hisi_hba *hisi_hba,
@@ -321,6 +324,44 @@ struct hisi_sas_hw {
 	const struct hisi_sas_debugfs_reg *debugfs_reg_port;
 };
 
+#define HISI_SAS_MAX_DEBUGFS_DUMP (50)
+
+struct hisi_sas_debugfs_cq {
+	struct hisi_sas_cq *cq;
+	void *complete_hdr;
+};
+
+struct hisi_sas_debugfs_dq {
+	struct hisi_sas_dq *dq;
+	struct hisi_sas_cmd_hdr *hdr;
+};
+
+struct hisi_sas_debugfs_regs {
+	struct hisi_hba *hisi_hba;
+	u32 *data;
+};
+
+struct hisi_sas_debugfs_port {
+	struct hisi_sas_phy *phy;
+	u32 *data;
+};
+
+struct hisi_sas_debugfs_iost {
+	struct hisi_sas_iost *iost;
+};
+
+struct hisi_sas_debugfs_itct {
+	struct hisi_sas_itct *itct;
+};
+
+struct hisi_sas_debugfs_iost_cache {
+	struct hisi_sas_iost_itct_cache *cache;
+};
+
+struct hisi_sas_debugfs_itct_cache {
+	struct hisi_sas_iost_itct_cache *cache;
+};
+
 struct hisi_hba {
 	/* This must be the first element, used by SHOST_TO_SAS_HA */
 	struct sas_ha_struct *p;
@@ -402,19 +443,20 @@ struct hisi_hba {
 
 	/* debugfs memories */
 	/* Put Global AXI and RAS Register into register array */
-	u32 *debugfs_regs[DEBUGFS_REGS_NUM];
-	u32 *debugfs_port_reg[HISI_SAS_MAX_PHYS];
-	void *debugfs_complete_hdr[HISI_SAS_MAX_QUEUES];
-	struct hisi_sas_cmd_hdr	*debugfs_cmd_hdr[HISI_SAS_MAX_QUEUES];
-	struct hisi_sas_iost *debugfs_iost;
-	struct hisi_sas_itct *debugfs_itct;
-	u64 *debugfs_iost_cache;
-	u64 *debugfs_itct_cache;
-
+	struct hisi_sas_debugfs_regs debugfs_regs[HISI_SAS_MAX_DEBUGFS_DUMP][DEBUGFS_REGS_NUM];
+	struct hisi_sas_debugfs_port debugfs_port_reg[HISI_SAS_MAX_DEBUGFS_DUMP][HISI_SAS_MAX_PHYS];
+	struct hisi_sas_debugfs_cq debugfs_cq[HISI_SAS_MAX_DEBUGFS_DUMP][HISI_SAS_MAX_QUEUES];
+	struct hisi_sas_debugfs_dq debugfs_dq[HISI_SAS_MAX_DEBUGFS_DUMP][HISI_SAS_MAX_QUEUES];
+	struct hisi_sas_debugfs_iost debugfs_iost[HISI_SAS_MAX_DEBUGFS_DUMP];
+	struct hisi_sas_debugfs_itct debugfs_itct[HISI_SAS_MAX_DEBUGFS_DUMP];
+	struct hisi_sas_debugfs_iost_cache debugfs_iost_cache[HISI_SAS_MAX_DEBUGFS_DUMP];
+	struct hisi_sas_debugfs_itct_cache debugfs_itct_cache[HISI_SAS_MAX_DEBUGFS_DUMP];
+
+	u64 debugfs_timestamp[HISI_SAS_MAX_DEBUGFS_DUMP];
+	int debugfs_dump_index;
 	struct dentry *debugfs_dir;
 	struct dentry *debugfs_dump_dentry;
 	struct dentry *debugfs_bist_dentry;
-	bool debugfs_snapshot;
 };
 
 /* Generic HW DMA host memory structures */
@@ -556,6 +598,7 @@ struct hisi_sas_slot_dif_buf_table {
 extern struct scsi_transport_template *hisi_sas_stt;
 
 extern bool hisi_sas_debugfs_enable;
+extern u32 hisi_sas_debugfs_dump_count;
 extern struct dentry *hisi_sas_debugfs_dir;
 
 extern void hisi_sas_stop_phys(struct hisi_hba *hisi_hba);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 0847e682797b..03588ec3c394 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -587,7 +587,13 @@ static int hisi_sas_task_exec(struct sas_task *task, gfp_t gfp_flags,
 	dev = hisi_hba->dev;
 
 	if (unlikely(test_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags))) {
-		if (in_softirq())
+		/*
+		 * For IOs from upper layer, it may already disable preempt
+		 * in the IO path, if disable preempt again in down(),
+		 * function schedule() will report schedule_bug(), so check
+		 * preemptible() before goto down().
+		 */
+		if (!preemptible())
 			return -EINVAL;
 
 		down(&hisi_hba->sem);
@@ -968,12 +974,13 @@ static void hisi_sas_port_notify_formed(struct asd_sas_phy *sas_phy)
 	struct hisi_hba *hisi_hba = sas_ha->lldd_ha;
 	struct hisi_sas_phy *phy = sas_phy->lldd_phy;
 	struct asd_sas_port *sas_port = sas_phy->port;
-	struct hisi_sas_port *port = to_hisi_sas_port(sas_port);
+	struct hisi_sas_port *port;
 	unsigned long flags;
 
 	if (!sas_port)
 		return;
 
+	port = to_hisi_sas_port(sas_port);
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	port->port_attached = 1;
 	port->id = phy->port_id;
@@ -1045,6 +1052,7 @@ static void hisi_sas_dev_gone(struct domain_device *device)
 	struct hisi_sas_device *sas_dev = device->lldd_dev;
 	struct hisi_hba *hisi_hba = dev_to_hisi_hba(device);
 	struct device *dev = hisi_hba->dev;
+	int ret = 0;
 
 	dev_info(dev, "dev[%d:%x] is gone\n",
 		 sas_dev->device_id, sas_dev->dev_type);
@@ -1056,13 +1064,16 @@ static void hisi_sas_dev_gone(struct domain_device *device)
 
 		hisi_sas_dereg_device(hisi_hba, device);
 
-		hisi_hba->hw->clear_itct(hisi_hba, sas_dev);
+		ret = hisi_hba->hw->clear_itct(hisi_hba, sas_dev);
 		device->lldd_dev = NULL;
 	}
 
 	if (hisi_hba->hw->free_device)
 		hisi_hba->hw->free_device(sas_dev);
-	sas_dev->dev_type = SAS_PHY_UNUSED;
+
+	/* Don't mark it as SAS_PHY_UNUSED if failed to clear ITCT */
+	if (!ret)
+		sas_dev->dev_type = SAS_PHY_UNUSED;
 	sas_dev->sas_device = NULL;
 	up(&hisi_hba->sem);
 }
@@ -1402,7 +1413,7 @@ static void hisi_sas_rescan_topology(struct hisi_hba *hisi_hba, u32 state)
 		struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 		struct asd_sas_phy *sas_phy = &phy->sas_phy;
 		struct asd_sas_port *sas_port = sas_phy->port;
-		bool do_port_check = !!(_sas_port != sas_port);
+		bool do_port_check = _sas_port != sas_port;
 
 		if (!sas_phy->phy->enabled)
 			continue;
@@ -1563,7 +1574,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 	struct Scsi_Host *shost = hisi_hba->shost;
 	int rc;
 
-	if (hisi_sas_debugfs_enable && hisi_hba->debugfs_itct)
+	if (hisi_sas_debugfs_enable && hisi_hba->debugfs_itct[0].itct)
 		queue_work(hisi_hba->wq, &hisi_hba->debugfs_work);
 
 	if (!hisi_hba->hw->soft_reset)
@@ -2055,7 +2066,7 @@ _hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 
 	/* Internal abort timed out */
 	if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) {
-		if (hisi_sas_debugfs_enable && hisi_hba->debugfs_itct)
+		if (hisi_sas_debugfs_enable && hisi_hba->debugfs_itct[0].itct)
 			queue_work(hisi_hba->wq, &hisi_hba->debugfs_work);
 
 		if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
@@ -2676,6 +2687,7 @@ int hisi_sas_probe(struct platform_device *pdev,
 err_out_register_ha:
 	scsi_remove_host(shost);
 err_out_ha:
+	hisi_sas_debugfs_exit(hisi_hba);
 	hisi_sas_free(hisi_hba);
 	scsi_host_put(shost);
 	return rc;
@@ -2687,10 +2699,11 @@ struct dentry *hisi_sas_debugfs_dir;
 static void hisi_sas_debugfs_snapshot_cq_reg(struct hisi_hba *hisi_hba)
 {
 	int queue_entry_size = hisi_hba->hw->complete_hdr_size;
+	int dump_index = hisi_hba->debugfs_dump_index;
 	int i;
 
 	for (i = 0; i < hisi_hba->queue_count; i++)
-		memcpy(hisi_hba->debugfs_complete_hdr[i],
+		memcpy(hisi_hba->debugfs_cq[dump_index][i].complete_hdr,
 		       hisi_hba->complete_hdr[i],
 		       HISI_SAS_QUEUE_SLOTS * queue_entry_size);
 }
@@ -2698,13 +2711,14 @@ static void hisi_sas_debugfs_snapshot_cq_reg(struct hisi_hba *hisi_hba)
 static void hisi_sas_debugfs_snapshot_dq_reg(struct hisi_hba *hisi_hba)
 {
 	int queue_entry_size = sizeof(struct hisi_sas_cmd_hdr);
+	int dump_index = hisi_hba->debugfs_dump_index;
 	int i;
 
 	for (i = 0; i < hisi_hba->queue_count; i++) {
-		struct hisi_sas_cmd_hdr	*debugfs_cmd_hdr, *cmd_hdr;
+		struct hisi_sas_cmd_hdr *debugfs_cmd_hdr, *cmd_hdr;
 		int j;
 
-		debugfs_cmd_hdr = hisi_hba->debugfs_cmd_hdr[i];
+		debugfs_cmd_hdr = hisi_hba->debugfs_dq[dump_index][i].hdr;
 		cmd_hdr = hisi_hba->cmd_hdr[i];
 
 		for (j = 0; j < HISI_SAS_QUEUE_SLOTS; j++)
@@ -2715,6 +2729,7 @@ static void hisi_sas_debugfs_snapshot_dq_reg(struct hisi_hba *hisi_hba)
 
 static void hisi_sas_debugfs_snapshot_port_reg(struct hisi_hba *hisi_hba)
 {
+	int dump_index = hisi_hba->debugfs_dump_index;
 	const struct hisi_sas_debugfs_reg *port =
 		hisi_hba->hw->debugfs_reg_port;
 	int i, phy_cnt;
@@ -2722,7 +2737,7 @@ static void hisi_sas_debugfs_snapshot_port_reg(struct hisi_hba *hisi_hba)
 	u32 *databuf;
 
 	for (phy_cnt = 0; phy_cnt < hisi_hba->n_phy; phy_cnt++) {
-		databuf = (u32 *)hisi_hba->debugfs_port_reg[phy_cnt];
+		databuf = hisi_hba->debugfs_port_reg[dump_index][phy_cnt].data;
 		for (i = 0; i < port->count; i++, databuf++) {
 			offset = port->base_off + 4 * i;
 			*databuf = port->read_port_reg(hisi_hba, phy_cnt,
@@ -2733,7 +2748,8 @@ static void hisi_sas_debugfs_snapshot_port_reg(struct hisi_hba *hisi_hba)
 
 static void hisi_sas_debugfs_snapshot_global_reg(struct hisi_hba *hisi_hba)
 {
-	u32 *databuf = hisi_hba->debugfs_regs[DEBUGFS_GLOBAL];
+	int dump_index = hisi_hba->debugfs_dump_index;
+	u32 *databuf = hisi_hba->debugfs_regs[dump_index][DEBUGFS_GLOBAL].data;
 	const struct hisi_sas_hw *hw = hisi_hba->hw;
 	const struct hisi_sas_debugfs_reg *global =
 			hw->debugfs_reg_array[DEBUGFS_GLOBAL];
@@ -2745,7 +2761,8 @@ static void hisi_sas_debugfs_snapshot_global_reg(struct hisi_hba *hisi_hba)
 
 static void hisi_sas_debugfs_snapshot_axi_reg(struct hisi_hba *hisi_hba)
 {
-	u32 *databuf = hisi_hba->debugfs_regs[DEBUGFS_AXI];
+	int dump_index = hisi_hba->debugfs_dump_index;
+	u32 *databuf = hisi_hba->debugfs_regs[dump_index][DEBUGFS_AXI].data;
 	const struct hisi_sas_hw *hw = hisi_hba->hw;
 	const struct hisi_sas_debugfs_reg *axi =
 			hw->debugfs_reg_array[DEBUGFS_AXI];
@@ -2758,7 +2775,8 @@ static void hisi_sas_debugfs_snapshot_axi_reg(struct hisi_hba *hisi_hba)
 
 static void hisi_sas_debugfs_snapshot_ras_reg(struct hisi_hba *hisi_hba)
 {
-	u32 *databuf = hisi_hba->debugfs_regs[DEBUGFS_RAS];
+	int dump_index = hisi_hba->debugfs_dump_index;
+	u32 *databuf = hisi_hba->debugfs_regs[dump_index][DEBUGFS_RAS].data;
 	const struct hisi_sas_hw *hw = hisi_hba->hw;
 	const struct hisi_sas_debugfs_reg *ras =
 			hw->debugfs_reg_array[DEBUGFS_RAS];
@@ -2771,8 +2789,9 @@ static void hisi_sas_debugfs_snapshot_ras_reg(struct hisi_hba *hisi_hba)
 
 static void hisi_sas_debugfs_snapshot_itct_reg(struct hisi_hba *hisi_hba)
 {
-	void *cachebuf = hisi_hba->debugfs_itct_cache;
-	void *databuf = hisi_hba->debugfs_itct;
+	int dump_index = hisi_hba->debugfs_dump_index;
+	void *cachebuf = hisi_hba->debugfs_itct_cache[dump_index].cache;
+	void *databuf = hisi_hba->debugfs_itct[dump_index].itct;
 	struct hisi_sas_itct *itct;
 	int i;
 
@@ -2789,9 +2808,10 @@ static void hisi_sas_debugfs_snapshot_itct_reg(struct hisi_hba *hisi_hba)
 
 static void hisi_sas_debugfs_snapshot_iost_reg(struct hisi_hba *hisi_hba)
 {
+	int dump_index = hisi_hba->debugfs_dump_index;
 	int max_command_entries = HISI_SAS_MAX_COMMANDS;
-	void *cachebuf = hisi_hba->debugfs_iost_cache;
-	void *databuf = hisi_hba->debugfs_iost;
+	void *cachebuf = hisi_hba->debugfs_iost_cache[dump_index].cache;
+	void *databuf = hisi_hba->debugfs_iost[dump_index].iost;
 	struct hisi_sas_iost *iost;
 	int i;
 
@@ -2842,11 +2862,12 @@ static void hisi_sas_debugfs_print_reg(u32 *regs_val, const void *ptr,
 
 static int hisi_sas_debugfs_global_show(struct seq_file *s, void *p)
 {
-	struct hisi_hba *hisi_hba = s->private;
+	struct hisi_sas_debugfs_regs *global = s->private;
+	struct hisi_hba *hisi_hba = global->hisi_hba;
 	const struct hisi_sas_hw *hw = hisi_hba->hw;
 	const void *reg_global = hw->debugfs_reg_array[DEBUGFS_GLOBAL];
 
-	hisi_sas_debugfs_print_reg(hisi_hba->debugfs_regs[DEBUGFS_GLOBAL],
+	hisi_sas_debugfs_print_reg(global->data,
 				   reg_global, s);
 
 	return 0;
@@ -2868,11 +2889,12 @@ static const struct file_operations hisi_sas_debugfs_global_fops = {
 
 static int hisi_sas_debugfs_axi_show(struct seq_file *s, void *p)
 {
-	struct hisi_hba *hisi_hba = s->private;
+	struct hisi_sas_debugfs_regs *axi = s->private;
+	struct hisi_hba *hisi_hba = axi->hisi_hba;
 	const struct hisi_sas_hw *hw = hisi_hba->hw;
 	const void *reg_axi = hw->debugfs_reg_array[DEBUGFS_AXI];
 
-	hisi_sas_debugfs_print_reg(hisi_hba->debugfs_regs[DEBUGFS_AXI],
+	hisi_sas_debugfs_print_reg(axi->data,
 				   reg_axi, s);
 
 	return 0;
@@ -2894,11 +2916,12 @@ static const struct file_operations hisi_sas_debugfs_axi_fops = {
 
 static int hisi_sas_debugfs_ras_show(struct seq_file *s, void *p)
 {
-	struct hisi_hba *hisi_hba = s->private;
+	struct hisi_sas_debugfs_regs *ras = s->private;
+	struct hisi_hba *hisi_hba = ras->hisi_hba;
 	const struct hisi_sas_hw *hw = hisi_hba->hw;
 	const void *reg_ras = hw->debugfs_reg_array[DEBUGFS_RAS];
 
-	hisi_sas_debugfs_print_reg(hisi_hba->debugfs_regs[DEBUGFS_RAS],
+	hisi_sas_debugfs_print_reg(ras->data,
 				   reg_ras, s);
 
 	return 0;
@@ -2920,13 +2943,13 @@ static const struct file_operations hisi_sas_debugfs_ras_fops = {
 
 static int hisi_sas_debugfs_port_show(struct seq_file *s, void *p)
 {
-	struct hisi_sas_phy *phy = s->private;
+	struct hisi_sas_debugfs_port *port = s->private;
+	struct hisi_sas_phy *phy = port->phy;
 	struct hisi_hba *hisi_hba = phy->hisi_hba;
 	const struct hisi_sas_hw *hw = hisi_hba->hw;
 	const struct hisi_sas_debugfs_reg *reg_port = hw->debugfs_reg_port;
-	u32 *databuf = hisi_hba->debugfs_port_reg[phy->sas_phy.id];
 
-	hisi_sas_debugfs_print_reg(databuf, reg_port, s);
+	hisi_sas_debugfs_print_reg(port->data, reg_port, s);
 
 	return 0;
 }
@@ -2975,13 +2998,13 @@ static void hisi_sas_show_row_32(struct seq_file *s, int index,
 	seq_puts(s, "\n");
 }
 
-static void hisi_sas_cq_show_slot(struct seq_file *s, int slot, void *cq_ptr)
+static void hisi_sas_cq_show_slot(struct seq_file *s, int slot,
+				  struct hisi_sas_debugfs_cq *debugfs_cq)
 {
-	struct hisi_sas_cq *cq = cq_ptr;
+	struct hisi_sas_cq *cq = debugfs_cq->cq;
 	struct hisi_hba *hisi_hba = cq->hisi_hba;
-	void *complete_queue = hisi_hba->debugfs_complete_hdr[cq->id];
-	__le32 *complete_hdr = complete_queue +
-			(hisi_hba->hw->complete_hdr_size * slot);
+	__le32 *complete_hdr = debugfs_cq->complete_hdr +
+			       (hisi_hba->hw->complete_hdr_size * slot);
 
 	hisi_sas_show_row_32(s, slot,
 			     hisi_hba->hw->complete_hdr_size,
@@ -2990,11 +3013,11 @@ static void hisi_sas_cq_show_slot(struct seq_file *s, int slot, void *cq_ptr)
 
 static int hisi_sas_debugfs_cq_show(struct seq_file *s, void *p)
 {
-	struct hisi_sas_cq *cq = s->private;
+	struct hisi_sas_debugfs_cq *debugfs_cq = s->private;
 	int slot;
 
 	for (slot = 0; slot < HISI_SAS_QUEUE_SLOTS; slot++) {
-		hisi_sas_cq_show_slot(s, slot, cq);
+		hisi_sas_cq_show_slot(s, slot, debugfs_cq);
 	}
 	return 0;
 }
@@ -3014,9 +3037,8 @@ static const struct file_operations hisi_sas_debugfs_cq_fops = {
 
 static void hisi_sas_dq_show_slot(struct seq_file *s, int slot, void *dq_ptr)
 {
-	struct hisi_sas_dq *dq = dq_ptr;
-	struct hisi_hba *hisi_hba = dq->hisi_hba;
-	void *cmd_queue = hisi_hba->debugfs_cmd_hdr[dq->id];
+	struct hisi_sas_debugfs_dq *debugfs_dq = dq_ptr;
+	void *cmd_queue = debugfs_dq->hdr;
 	__le32 *cmd_hdr = cmd_queue +
 		sizeof(struct hisi_sas_cmd_hdr) * slot;
 
@@ -3048,14 +3070,14 @@ static const struct file_operations hisi_sas_debugfs_dq_fops = {
 
 static int hisi_sas_debugfs_iost_show(struct seq_file *s, void *p)
 {
-	struct hisi_hba *hisi_hba = s->private;
-	struct hisi_sas_iost *debugfs_iost = hisi_hba->debugfs_iost;
+	struct hisi_sas_debugfs_iost *debugfs_iost = s->private;
+	struct hisi_sas_iost *iost = debugfs_iost->iost;
 	int i, max_command_entries = HISI_SAS_MAX_COMMANDS;
 
-	for (i = 0; i < max_command_entries; i++, debugfs_iost++) {
-		__le64 *iost = &debugfs_iost->qw0;
+	for (i = 0; i < max_command_entries; i++, iost++) {
+		__le64 *data = &iost->qw0;
 
-		hisi_sas_show_row_64(s, i, sizeof(*debugfs_iost), iost);
+		hisi_sas_show_row_64(s, i, sizeof(*iost), data);
 	}
 
 	return 0;
@@ -3076,9 +3098,8 @@ static const struct file_operations hisi_sas_debugfs_iost_fops = {
 
 static int hisi_sas_debugfs_iost_cache_show(struct seq_file *s, void *p)
 {
-	struct hisi_hba *hisi_hba = s->private;
-	struct hisi_sas_iost_itct_cache *iost_cache =
-		(struct hisi_sas_iost_itct_cache *)hisi_hba->debugfs_iost_cache;
+	struct hisi_sas_debugfs_iost_cache *debugfs_iost_cache = s->private;
+	struct hisi_sas_iost_itct_cache *iost_cache = debugfs_iost_cache->cache;
 	u32 cache_size = HISI_SAS_IOST_ITCT_CACHE_DW_SZ * 4;
 	int i, tab_idx;
 	__le64 *iost;
@@ -3117,13 +3138,13 @@ static const struct file_operations hisi_sas_debugfs_iost_cache_fops = {
 static int hisi_sas_debugfs_itct_show(struct seq_file *s, void *p)
 {
 	int i;
-	struct hisi_hba *hisi_hba = s->private;
-	struct hisi_sas_itct *debugfs_itct = hisi_hba->debugfs_itct;
+	struct hisi_sas_debugfs_itct *debugfs_itct = s->private;
+	struct hisi_sas_itct *itct = debugfs_itct->itct;
 
-	for (i = 0; i < HISI_SAS_MAX_ITCT_ENTRIES; i++, debugfs_itct++) {
-		__le64 *itct = &debugfs_itct->qw0;
+	for (i = 0; i < HISI_SAS_MAX_ITCT_ENTRIES; i++, itct++) {
+		__le64 *data = &itct->qw0;
 
-		hisi_sas_show_row_64(s, i, sizeof(*debugfs_itct), itct);
+		hisi_sas_show_row_64(s, i, sizeof(*itct), data);
 	}
 
 	return 0;
@@ -3144,9 +3165,8 @@ static const struct file_operations hisi_sas_debugfs_itct_fops = {
 
 static int hisi_sas_debugfs_itct_cache_show(struct seq_file *s, void *p)
 {
-	struct hisi_hba *hisi_hba = s->private;
-	struct hisi_sas_iost_itct_cache *itct_cache =
-		(struct hisi_sas_iost_itct_cache *)hisi_hba->debugfs_itct_cache;
+	struct hisi_sas_debugfs_itct_cache *debugfs_itct_cache = s->private;
+	struct hisi_sas_iost_itct_cache *itct_cache = debugfs_itct_cache->cache;
 	u32 cache_size = HISI_SAS_IOST_ITCT_CACHE_DW_SZ * 4;
 	int i, tab_idx;
 	__le64 *itct;
@@ -3184,6 +3204,8 @@ static const struct file_operations hisi_sas_debugfs_itct_cache_fops = {
 
 static void hisi_sas_debugfs_create_files(struct hisi_hba *hisi_hba)
 {
+	u64 *debugfs_timestamp;
+	int dump_index = hisi_hba->debugfs_dump_index;
 	struct dentry *dump_dentry;
 	struct dentry *dentry;
 	char name[256];
@@ -3191,19 +3213,26 @@ static void hisi_sas_debugfs_create_files(struct hisi_hba *hisi_hba)
 	int c;
 	int d;
 
-	/* Create dump dir inside device dir */
-	dump_dentry = debugfs_create_dir("dump", hisi_hba->debugfs_dir);
-	hisi_hba->debugfs_dump_dentry = dump_dentry;
+	snprintf(name, 256, "%d", dump_index);
+
+	dump_dentry = debugfs_create_dir(name, hisi_hba->debugfs_dump_dentry);
 
-	debugfs_create_file("global", 0400, dump_dentry, hisi_hba,
-			    &hisi_sas_debugfs_global_fops);
+	debugfs_timestamp = &hisi_hba->debugfs_timestamp[dump_index];
+
+	debugfs_create_u64("timestamp", 0400, dump_dentry,
+			   debugfs_timestamp);
+
+	debugfs_create_file("global", 0400, dump_dentry,
+			   &hisi_hba->debugfs_regs[dump_index][DEBUGFS_GLOBAL],
+			   &hisi_sas_debugfs_global_fops);
 
 	/* Create port dir and files */
 	dentry = debugfs_create_dir("port", dump_dentry);
 	for (p = 0; p < hisi_hba->n_phy; p++) {
 		snprintf(name, 256, "%d", p);
 
-		debugfs_create_file(name, 0400, dentry, &hisi_hba->phy[p],
+		debugfs_create_file(name, 0400, dentry,
+				    &hisi_hba->debugfs_port_reg[dump_index][p],
 				    &hisi_sas_debugfs_port_fops);
 	}
 
@@ -3212,7 +3241,8 @@ static void hisi_sas_debugfs_create_files(struct hisi_hba *hisi_hba)
 	for (c = 0; c < hisi_hba->queue_count; c++) {
 		snprintf(name, 256, "%d", c);
 
-		debugfs_create_file(name, 0400, dentry, &hisi_hba->cq[c],
+		debugfs_create_file(name, 0400, dentry,
+				    &hisi_hba->debugfs_cq[dump_index][c],
 				    &hisi_sas_debugfs_cq_fops);
 	}
 
@@ -3221,26 +3251,33 @@ static void hisi_sas_debugfs_create_files(struct hisi_hba *hisi_hba)
 	for (d = 0; d < hisi_hba->queue_count; d++) {
 		snprintf(name, 256, "%d", d);
 
-		debugfs_create_file(name, 0400, dentry, &hisi_hba->dq[d],
+		debugfs_create_file(name, 0400, dentry,
+				    &hisi_hba->debugfs_dq[dump_index][d],
 				    &hisi_sas_debugfs_dq_fops);
 	}
 
-	debugfs_create_file("iost", 0400, dump_dentry, hisi_hba,
+	debugfs_create_file("iost", 0400, dump_dentry,
+			    &hisi_hba->debugfs_iost[dump_index],
 			    &hisi_sas_debugfs_iost_fops);
 
-	debugfs_create_file("iost_cache", 0400, dump_dentry, hisi_hba,
+	debugfs_create_file("iost_cache", 0400, dump_dentry,
+			    &hisi_hba->debugfs_iost_cache[dump_index],
 			    &hisi_sas_debugfs_iost_cache_fops);
 
-	debugfs_create_file("itct", 0400, dump_dentry, hisi_hba,
+	debugfs_create_file("itct", 0400, dump_dentry,
+			    &hisi_hba->debugfs_itct[dump_index],
 			    &hisi_sas_debugfs_itct_fops);
 
-	debugfs_create_file("itct_cache", 0400, dump_dentry, hisi_hba,
+	debugfs_create_file("itct_cache", 0400, dump_dentry,
+			    &hisi_hba->debugfs_itct_cache[dump_index],
 			    &hisi_sas_debugfs_itct_cache_fops);
 
-	debugfs_create_file("axi", 0400, dump_dentry, hisi_hba,
+	debugfs_create_file("axi", 0400, dump_dentry,
+			    &hisi_hba->debugfs_regs[dump_index][DEBUGFS_AXI],
 			    &hisi_sas_debugfs_axi_fops);
 
-	debugfs_create_file("ras", 0400, dump_dentry, hisi_hba,
+	debugfs_create_file("ras", 0400, dump_dentry,
+			    &hisi_hba->debugfs_regs[dump_index][DEBUGFS_RAS],
 			    &hisi_sas_debugfs_ras_fops);
 
 	return;
@@ -3271,8 +3308,7 @@ static ssize_t hisi_sas_debugfs_trigger_dump_write(struct file *file,
 	struct hisi_hba *hisi_hba = file->f_inode->i_private;
 	char buf[8];
 
-	/* A bit racy, but don't care too much since it's only debugfs */
-	if (hisi_hba->debugfs_snapshot)
+	if (hisi_hba->debugfs_dump_index >= hisi_sas_debugfs_dump_count)
 		return -EFAULT;
 
 	if (count > 8)
@@ -3539,7 +3575,7 @@ static const struct {
 	int		value;
 	char		*name;
 } hisi_sas_debugfs_loop_modes[] = {
-	{ HISI_SAS_BIST_LOOPBACK_MODE_DIGITAL, "digial" },
+	{ HISI_SAS_BIST_LOOPBACK_MODE_DIGITAL, "digital" },
 	{ HISI_SAS_BIST_LOOPBACK_MODE_SERDES, "serdes" },
 	{ HISI_SAS_BIST_LOOPBACK_MODE_REMOTE, "remote" },
 };
@@ -3670,132 +3706,201 @@ static const struct file_operations hisi_sas_debugfs_bist_enable_ops = {
 	.owner = THIS_MODULE,
 };
 
+static ssize_t hisi_sas_debugfs_phy_down_cnt_write(struct file *filp,
+						   const char __user *buf,
+						   size_t count, loff_t *ppos)
+{
+	struct seq_file *s = filp->private_data;
+	struct hisi_sas_phy *phy = s->private;
+	unsigned int set_val;
+	int res;
+
+	res = kstrtouint_from_user(buf, count, 0, &set_val);
+	if (res)
+		return res;
+
+	if (set_val > 0)
+		return -EINVAL;
+
+	atomic_set(&phy->down_cnt, 0);
+
+	return count;
+}
+
+static int hisi_sas_debugfs_phy_down_cnt_show(struct seq_file *s, void *p)
+{
+	struct hisi_sas_phy *phy = s->private;
+
+	seq_printf(s, "%d\n", atomic_read(&phy->down_cnt));
+
+	return 0;
+}
+
+static int hisi_sas_debugfs_phy_down_cnt_open(struct inode *inode,
+					      struct file *filp)
+{
+	return single_open(filp, hisi_sas_debugfs_phy_down_cnt_show,
+			   inode->i_private);
+}
+
+static const struct file_operations hisi_sas_debugfs_phy_down_cnt_ops = {
+	.open = hisi_sas_debugfs_phy_down_cnt_open,
+	.read = seq_read,
+	.write = hisi_sas_debugfs_phy_down_cnt_write,
+	.llseek = seq_lseek,
+	.release = single_release,
+	.owner = THIS_MODULE,
+};
+
 void hisi_sas_debugfs_work_handler(struct work_struct *work)
 {
 	struct hisi_hba *hisi_hba =
 		container_of(work, struct hisi_hba, debugfs_work);
+	int debugfs_dump_index = hisi_hba->debugfs_dump_index;
+	struct device *dev = hisi_hba->dev;
+	u64 timestamp = local_clock();
 
-	if (hisi_hba->debugfs_snapshot)
+	if (debugfs_dump_index >= hisi_sas_debugfs_dump_count) {
+		dev_warn(dev, "dump count exceeded!\n");
 		return;
-	hisi_hba->debugfs_snapshot = true;
+	}
+
+	do_div(timestamp, NSEC_PER_MSEC);
+	hisi_hba->debugfs_timestamp[debugfs_dump_index] = timestamp;
 
 	hisi_sas_debugfs_snapshot_regs(hisi_hba);
+	hisi_hba->debugfs_dump_index++;
 }
 EXPORT_SYMBOL_GPL(hisi_sas_debugfs_work_handler);
 
-static void hisi_sas_debugfs_release(struct hisi_hba *hisi_hba)
+static void hisi_sas_debugfs_release(struct hisi_hba *hisi_hba, int dump_index)
 {
 	struct device *dev = hisi_hba->dev;
 	int i;
 
-	devm_kfree(dev, hisi_hba->debugfs_iost_cache);
-	devm_kfree(dev, hisi_hba->debugfs_itct_cache);
-	devm_kfree(dev, hisi_hba->debugfs_iost);
+	devm_kfree(dev, hisi_hba->debugfs_iost_cache[dump_index].cache);
+	devm_kfree(dev, hisi_hba->debugfs_itct_cache[dump_index].cache);
+	devm_kfree(dev, hisi_hba->debugfs_iost[dump_index].iost);
+	devm_kfree(dev, hisi_hba->debugfs_itct[dump_index].itct);
 
 	for (i = 0; i < hisi_hba->queue_count; i++)
-		devm_kfree(dev, hisi_hba->debugfs_cmd_hdr[i]);
+		devm_kfree(dev, hisi_hba->debugfs_dq[dump_index][i].hdr);
 
 	for (i = 0; i < hisi_hba->queue_count; i++)
-		devm_kfree(dev, hisi_hba->debugfs_complete_hdr[i]);
+		devm_kfree(dev,
+			   hisi_hba->debugfs_cq[dump_index][i].complete_hdr);
 
 	for (i = 0; i < DEBUGFS_REGS_NUM; i++)
-		devm_kfree(dev, hisi_hba->debugfs_regs[i]);
+		devm_kfree(dev, hisi_hba->debugfs_regs[dump_index][i].data);
 
 	for (i = 0; i < hisi_hba->n_phy; i++)
-		devm_kfree(dev, hisi_hba->debugfs_port_reg[i]);
+		devm_kfree(dev, hisi_hba->debugfs_port_reg[dump_index][i].data);
 }
 
-static int hisi_sas_debugfs_alloc(struct hisi_hba *hisi_hba)
+static int hisi_sas_debugfs_alloc(struct hisi_hba *hisi_hba, int dump_index)
 {
 	const struct hisi_sas_hw *hw = hisi_hba->hw;
 	struct device *dev = hisi_hba->dev;
-	int p, c, d;
+	int p, c, d, r, i;
 	size_t sz;
 
-	hisi_hba->debugfs_dump_dentry =
-			debugfs_create_dir("dump", hisi_hba->debugfs_dir);
+	for (r = 0; r < DEBUGFS_REGS_NUM; r++) {
+		struct hisi_sas_debugfs_regs *regs =
+				&hisi_hba->debugfs_regs[dump_index][r];
 
-	sz = hw->debugfs_reg_array[DEBUGFS_GLOBAL]->count * 4;
-	hisi_hba->debugfs_regs[DEBUGFS_GLOBAL] =
-				devm_kmalloc(dev, sz, GFP_KERNEL);
-
-	if (!hisi_hba->debugfs_regs[DEBUGFS_GLOBAL])
-		goto fail;
+		sz = hw->debugfs_reg_array[r]->count * 4;
+		regs->data = devm_kmalloc(dev, sz, GFP_KERNEL);
+		if (!regs->data)
+			goto fail;
+		regs->hisi_hba = hisi_hba;
+	}
 
 	sz = hw->debugfs_reg_port->count * 4;
 	for (p = 0; p < hisi_hba->n_phy; p++) {
-		hisi_hba->debugfs_port_reg[p] =
-			devm_kmalloc(dev, sz, GFP_KERNEL);
+		struct hisi_sas_debugfs_port *port =
+				&hisi_hba->debugfs_port_reg[dump_index][p];
 
-		if (!hisi_hba->debugfs_port_reg[p])
+		port->data = devm_kmalloc(dev, sz, GFP_KERNEL);
+		if (!port->data)
 			goto fail;
+		port->phy = &hisi_hba->phy[p];
 	}
 
-	sz = hw->debugfs_reg_array[DEBUGFS_AXI]->count * 4;
-	hisi_hba->debugfs_regs[DEBUGFS_AXI] =
-		devm_kmalloc(dev, sz, GFP_KERNEL);
-
-	if (!hisi_hba->debugfs_regs[DEBUGFS_AXI])
-		goto fail;
-
-	sz = hw->debugfs_reg_array[DEBUGFS_RAS]->count * 4;
-	hisi_hba->debugfs_regs[DEBUGFS_RAS] =
-		devm_kmalloc(dev, sz, GFP_KERNEL);
-
-	if (!hisi_hba->debugfs_regs[DEBUGFS_RAS])
-		goto fail;
-
 	sz = hw->complete_hdr_size * HISI_SAS_QUEUE_SLOTS;
 	for (c = 0; c < hisi_hba->queue_count; c++) {
-		hisi_hba->debugfs_complete_hdr[c] =
-			devm_kmalloc(dev, sz, GFP_KERNEL);
+		struct hisi_sas_debugfs_cq *cq =
+				&hisi_hba->debugfs_cq[dump_index][c];
 
-		if (!hisi_hba->debugfs_complete_hdr[c])
+		cq->complete_hdr = devm_kmalloc(dev, sz, GFP_KERNEL);
+		if (!cq->complete_hdr)
 			goto fail;
+		cq->cq = &hisi_hba->cq[c];
 	}
 
 	sz = sizeof(struct hisi_sas_cmd_hdr) * HISI_SAS_QUEUE_SLOTS;
 	for (d = 0; d < hisi_hba->queue_count; d++) {
-		hisi_hba->debugfs_cmd_hdr[d] =
-			devm_kmalloc(dev, sz, GFP_KERNEL);
+		struct hisi_sas_debugfs_dq *dq =
+				&hisi_hba->debugfs_dq[dump_index][d];
 
-		if (!hisi_hba->debugfs_cmd_hdr[d])
+		dq->hdr = devm_kmalloc(dev, sz, GFP_KERNEL);
+		if (!dq->hdr)
 			goto fail;
+		dq->dq = &hisi_hba->dq[d];
 	}
 
 	sz = HISI_SAS_MAX_COMMANDS * sizeof(struct hisi_sas_iost);
 
-	hisi_hba->debugfs_iost = devm_kmalloc(dev, sz, GFP_KERNEL);
-	if (!hisi_hba->debugfs_iost)
+	hisi_hba->debugfs_iost[dump_index].iost =
+				devm_kmalloc(dev, sz, GFP_KERNEL);
+	if (!hisi_hba->debugfs_iost[dump_index].iost)
 		goto fail;
 
 	sz = HISI_SAS_IOST_ITCT_CACHE_NUM *
 	     sizeof(struct hisi_sas_iost_itct_cache);
 
-	hisi_hba->debugfs_iost_cache = devm_kmalloc(dev, sz, GFP_KERNEL);
-	if (!hisi_hba->debugfs_iost_cache)
+	hisi_hba->debugfs_iost_cache[dump_index].cache =
+				devm_kmalloc(dev, sz, GFP_KERNEL);
+	if (!hisi_hba->debugfs_iost_cache[dump_index].cache)
 		goto fail;
 
 	sz = HISI_SAS_IOST_ITCT_CACHE_NUM *
 	     sizeof(struct hisi_sas_iost_itct_cache);
 
-	hisi_hba->debugfs_itct_cache = devm_kmalloc(dev, sz, GFP_KERNEL);
-	if (!hisi_hba->debugfs_itct_cache)
+	hisi_hba->debugfs_itct_cache[dump_index].cache =
+				devm_kmalloc(dev, sz, GFP_KERNEL);
+	if (!hisi_hba->debugfs_itct_cache[dump_index].cache)
 		goto fail;
 
 	/* New memory allocation must be locate before itct */
 	sz = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
 
-	hisi_hba->debugfs_itct = devm_kmalloc(dev, sz, GFP_KERNEL);
-	if (!hisi_hba->debugfs_itct)
+	hisi_hba->debugfs_itct[dump_index].itct =
+				devm_kmalloc(dev, sz, GFP_KERNEL);
+	if (!hisi_hba->debugfs_itct[dump_index].itct)
 		goto fail;
 
 	return 0;
 fail:
-	hisi_sas_debugfs_release(hisi_hba);
+	for (i = 0; i < hisi_sas_debugfs_dump_count; i++)
+		hisi_sas_debugfs_release(hisi_hba, i);
 	return -ENOMEM;
 }
 
+static void hisi_sas_debugfs_phy_down_cnt_init(struct hisi_hba *hisi_hba)
+{
+	struct dentry *dir = debugfs_create_dir("phy_down_cnt",
+						hisi_hba->debugfs_dir);
+	char name[16];
+	int phy_no;
+
+	for (phy_no = 0; phy_no < hisi_hba->n_phy; phy_no++) {
+		snprintf(name, 16, "%d", phy_no);
+		debugfs_create_file(name, 0600, dir,
+				    &hisi_hba->phy[phy_no],
+				    &hisi_sas_debugfs_phy_down_cnt_ops);
+	}
+}
+
 static void hisi_sas_debugfs_bist_init(struct hisi_hba *hisi_hba)
 {
 	hisi_hba->debugfs_bist_dentry =
@@ -3827,6 +3932,7 @@ static void hisi_sas_debugfs_bist_init(struct hisi_hba *hisi_hba)
 void hisi_sas_debugfs_init(struct hisi_hba *hisi_hba)
 {
 	struct device *dev = hisi_hba->dev;
+	int i;
 
 	hisi_hba->debugfs_dir = debugfs_create_dir(dev_name(dev),
 						   hisi_sas_debugfs_dir);
@@ -3838,9 +3944,17 @@ void hisi_sas_debugfs_init(struct hisi_hba *hisi_hba)
 	/* create bist structures */
 	hisi_sas_debugfs_bist_init(hisi_hba);
 
-	if (hisi_sas_debugfs_alloc(hisi_hba)) {
-		debugfs_remove_recursive(hisi_hba->debugfs_dir);
-		dev_dbg(dev, "failed to init debugfs!\n");
+	hisi_hba->debugfs_dump_dentry =
+			debugfs_create_dir("dump", hisi_hba->debugfs_dir);
+
+	hisi_sas_debugfs_phy_down_cnt_init(hisi_hba);
+
+	for (i = 0; i < hisi_sas_debugfs_dump_count; i++) {
+		if (hisi_sas_debugfs_alloc(hisi_hba, i)) {
+			debugfs_remove_recursive(hisi_hba->debugfs_dir);
+			dev_dbg(dev, "failed to init debugfs!\n");
+			break;
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(hisi_sas_debugfs_init);
@@ -3874,14 +3988,24 @@ EXPORT_SYMBOL_GPL(hisi_sas_debugfs_enable);
 module_param_named(debugfs_enable, hisi_sas_debugfs_enable, bool, 0444);
 MODULE_PARM_DESC(hisi_sas_debugfs_enable, "Enable driver debugfs (default disabled)");
 
+u32 hisi_sas_debugfs_dump_count = 1;
+EXPORT_SYMBOL_GPL(hisi_sas_debugfs_dump_count);
+module_param_named(debugfs_dump_count, hisi_sas_debugfs_dump_count, uint, 0444);
+MODULE_PARM_DESC(hisi_sas_debugfs_dump_count, "Number of debugfs dumps to allow");
+
 static __init int hisi_sas_init(void)
 {
 	hisi_sas_stt = sas_domain_attach_transport(&hisi_sas_transport_ops);
 	if (!hisi_sas_stt)
 		return -ENOMEM;
 
-	if (hisi_sas_debugfs_enable)
+	if (hisi_sas_debugfs_enable) {
 		hisi_sas_debugfs_dir = debugfs_create_dir("hisi_sas", NULL);
+		if (hisi_sas_debugfs_dump_count > HISI_SAS_MAX_DEBUGFS_DUMP) {
+			pr_info("hisi_sas: Limiting debugfs dump count\n");
+			hisi_sas_debugfs_dump_count = HISI_SAS_MAX_DEBUGFS_DUMP;
+		}
+	}
 
 	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 b861a0f14c9d..3af53cc42bd6 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -531,8 +531,8 @@ static void setup_itct_v1_hw(struct hisi_hba *hisi_hba,
 				(0xff00ULL << ITCT_HDR_REJ_OPEN_TL_OFF));
 }
 
-static void clear_itct_v1_hw(struct hisi_hba *hisi_hba,
-			      struct hisi_sas_device *sas_dev)
+static int clear_itct_v1_hw(struct hisi_hba *hisi_hba,
+			    struct hisi_sas_device *sas_dev)
 {
 	u64 dev_id = sas_dev->device_id;
 	struct hisi_sas_itct *itct = &hisi_hba->itct[dev_id];
@@ -551,6 +551,8 @@ static void clear_itct_v1_hw(struct hisi_hba *hisi_hba,
 	qw0 = le64_to_cpu(itct->qw0);
 	qw0 &= ~ITCT_HDR_VALID_MSK;
 	itct->qw0 = cpu_to_le64(qw0);
+
+	return 0;
 }
 
 static int reset_hw_v1_hw(struct hisi_hba *hisi_hba)
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 8e96a257e439..61b1e2693b08 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -974,13 +974,14 @@ static void setup_itct_v2_hw(struct hisi_hba *hisi_hba,
 					(0x1ULL << ITCT_HDR_RTOLT_OFF));
 }
 
-static void clear_itct_v2_hw(struct hisi_hba *hisi_hba,
-			      struct hisi_sas_device *sas_dev)
+static int clear_itct_v2_hw(struct hisi_hba *hisi_hba,
+			    struct hisi_sas_device *sas_dev)
 {
 	DECLARE_COMPLETION_ONSTACK(completion);
 	u64 dev_id = sas_dev->device_id;
 	struct hisi_sas_itct *itct = &hisi_hba->itct[dev_id];
 	u32 reg_val = hisi_sas_read32(hisi_hba, ENT_INT_SRC3);
+	struct device *dev = hisi_hba->dev;
 	int i;
 
 	sas_dev->completion = &completion;
@@ -990,13 +991,19 @@ static void clear_itct_v2_hw(struct hisi_hba *hisi_hba,
 		hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
 				 ENT_INT_SRC3_ITC_INT_MSK);
 
+	/* need to set register twice to clear ITCT for v2 hw */
 	for (i = 0; i < 2; i++) {
 		reg_val = ITCT_CLR_EN_MSK | (dev_id & ITCT_DEV_MSK);
 		hisi_sas_write32(hisi_hba, ITCT_CLR, reg_val);
-		wait_for_completion(sas_dev->completion);
+		if (!wait_for_completion_timeout(sas_dev->completion,
+						 CLEAR_ITCT_TIMEOUT * HZ)) {
+			dev_warn(dev, "failed to clear ITCT\n");
+			return -ETIMEDOUT;
+		}
 
 		memset(itct, 0, sizeof(struct hisi_sas_itct));
 	}
+	return 0;
 }
 
 static void free_device_v2_hw(struct hisi_sas_device *sas_dev)
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index cb8d087762db..bf5d5f138437 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -795,13 +795,14 @@ static void setup_itct_v3_hw(struct hisi_hba *hisi_hba,
 					(0x1ULL << ITCT_HDR_RTOLT_OFF));
 }
 
-static void clear_itct_v3_hw(struct hisi_hba *hisi_hba,
-			      struct hisi_sas_device *sas_dev)
+static int clear_itct_v3_hw(struct hisi_hba *hisi_hba,
+			    struct hisi_sas_device *sas_dev)
 {
 	DECLARE_COMPLETION_ONSTACK(completion);
 	u64 dev_id = sas_dev->device_id;
 	struct hisi_sas_itct *itct = &hisi_hba->itct[dev_id];
 	u32 reg_val = hisi_sas_read32(hisi_hba, ENT_INT_SRC3);
+	struct device *dev = hisi_hba->dev;
 
 	sas_dev->completion = &completion;
 
@@ -814,8 +815,14 @@ static void clear_itct_v3_hw(struct hisi_hba *hisi_hba,
 	reg_val = ITCT_CLR_EN_MSK | (dev_id & ITCT_DEV_MSK);
 	hisi_sas_write32(hisi_hba, ITCT_CLR, reg_val);
 
-	wait_for_completion(sas_dev->completion);
+	if (!wait_for_completion_timeout(sas_dev->completion,
+					 CLEAR_ITCT_TIMEOUT * HZ)) {
+		dev_warn(dev, "failed to clear ITCT\n");
+		return -ETIMEDOUT;
+	}
+
 	memset(itct, 0, sizeof(struct hisi_sas_itct));
+	return 0;
 }
 
 static void dereg_device_v3_hw(struct hisi_hba *hisi_hba,
@@ -1542,6 +1549,8 @@ static irqreturn_t phy_down_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 	u32 phy_state, sl_ctrl, txid_auto;
 	struct device *dev = hisi_hba->dev;
 
+	atomic_inc(&phy->down_cnt);
+
 	del_timer(&phy->timer);
 	hisi_sas_phy_write32(hisi_hba, phy_no, PHYCTRL_NOT_RDY_MSK, 1);
 
@@ -3022,11 +3031,6 @@ static int debugfs_set_bist_v3_hw(struct hisi_hba *hisi_hba, bool enable)
 		hisi_sas_phy_write32(hisi_hba, phy_id,
 				     SAS_PHY_BIST_CTRL, reg_val);
 
-		mdelay(100);
-		reg_val |= (CFG_RX_BIST_EN_MSK | CFG_TX_BIST_EN_MSK);
-		hisi_sas_phy_write32(hisi_hba, phy_id,
-				     SAS_PHY_BIST_CTRL, reg_val);
-
 		/* set the bist init value */
 		hisi_sas_phy_write32(hisi_hba, phy_id,
 				     SAS_PHY_BIST_CODE,
@@ -3035,6 +3039,11 @@ static int debugfs_set_bist_v3_hw(struct hisi_hba *hisi_hba, bool enable)
 				     SAS_PHY_BIST_CODE1,
 				     SAS_PHY_BIST_CODE1_INIT);
 
+		mdelay(100);
+		reg_val |= (CFG_RX_BIST_EN_MSK | CFG_TX_BIST_EN_MSK);
+		hisi_sas_phy_write32(hisi_hba, phy_id,
+				     SAS_PHY_BIST_CTRL, reg_val);
+
 		/* clear error bit */
 		mdelay(100);
 		hisi_sas_phy_read32(hisi_hba, phy_id, SAS_BIST_ERR_CNT);
@@ -3259,6 +3268,7 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 err_out_register_ha:
 	scsi_remove_host(shost);
 err_out_ha:
+	hisi_sas_debugfs_exit(hisi_hba);
 	scsi_host_put(shost);
 err_out_regions:
 	pci_release_regions(pdev);
@@ -3292,8 +3302,6 @@ static void hisi_sas_v3_remove(struct pci_dev *pdev)
 	struct hisi_hba *hisi_hba = sha->lldd_ha;
 	struct Scsi_Host *shost = sha->core.shost;
 
-	hisi_sas_debugfs_exit(hisi_hba);
-
 	if (timer_pending(&hisi_hba->timer))
 		del_timer(&hisi_hba->timer);
 
@@ -3305,6 +3313,7 @@ static void hisi_sas_v3_remove(struct pci_dev *pdev)
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
 	hisi_sas_free(hisi_hba);
+	hisi_sas_debugfs_exit(hisi_hba);
 	scsi_host_put(shost);
 }
 
@@ -3422,6 +3431,7 @@ static int hisi_sas_v3_resume(struct pci_dev *pdev)
 	if (rc) {
 		scsi_remove_host(shost);
 		pci_disable_device(pdev);
+		return rc;
 	}
 	hisi_hba->hw->phys_init(hisi_hba);
 	sas_resume_ha(sha);
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 55522b7162d3..1d669e47b692 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -38,6 +38,7 @@
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport.h>
+#include <scsi/scsi_cmnd.h>
 
 #include "scsi_priv.h"
 #include "scsi_logging.h"
@@ -554,13 +555,29 @@ struct Scsi_Host *scsi_host_get(struct Scsi_Host *shost)
 }
 EXPORT_SYMBOL(scsi_host_get);
 
+static bool scsi_host_check_in_flight(struct request *rq, void *data,
+				      bool reserved)
+{
+	int *count = data;
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+
+	if (test_bit(SCMD_STATE_INFLIGHT, &cmd->state))
+		(*count)++;
+
+	return true;
+}
+
 /**
  * scsi_host_busy - Return the host busy counter
  * @shost:	Pointer to Scsi_Host to inc.
  **/
 int scsi_host_busy(struct Scsi_Host *shost)
 {
-	return atomic_read(&shost->host_busy);
+	int cnt = 0;
+
+	blk_mq_tagset_busy_iter(&shost->tag_set,
+				scsi_host_check_in_flight, &cnt);
+	return cnt;
 }
 EXPORT_SYMBOL(scsi_host_busy);
 
diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c
index e8bc8d328bab..f25672982c5f 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -498,7 +498,7 @@ ips_setup(char *ips_str)
 	int i;
 	char *key;
 	char *value;
-	IPS_OPTION options[] = {
+	static const IPS_OPTION options[] = {
 		{"noi2o", &ips_force_i2o, 0},
 		{"nommap", &ips_force_memio, 0},
 		{"ioctlsize", &ips_ioctlsize, IPS_IOCTL_SIZE},
diff --git a/drivers/scsi/isci/port_config.c b/drivers/scsi/isci/port_config.c
index 9e8de1462593..b1c197505579 100644
--- a/drivers/scsi/isci/port_config.c
+++ b/drivers/scsi/isci/port_config.c
@@ -147,7 +147,7 @@ static struct isci_port *sci_port_configuration_agent_find_port(
 /**
  *
  * @controller: This is the controller object that contains the port agent
- * @port_agent: This is the port configruation agent for the controller.
+ * @port_agent: This is the port configuration agent for the controller.
  *
  * This routine will validate the port configuration is correct for the SCU
  * hardware.  The SCU hardware allows for port configurations as follows. LP0
diff --git a/drivers/scsi/isci/remote_device.c b/drivers/scsi/isci/remote_device.c
index 49aa4e657c44..cd1e4b4d95bb 100644
--- a/drivers/scsi/isci/remote_device.c
+++ b/drivers/scsi/isci/remote_device.c
@@ -1504,7 +1504,7 @@ static enum sci_status isci_remote_device_construct(struct isci_port *iport,
  * This function builds the isci_remote_device when a libsas dev_found message
  *    is received.
  * @isci_host: This parameter specifies the isci host object.
- * @port: This parameter specifies the isci_port conected to this device.
+ * @port: This parameter specifies the isci_port connected to this device.
  *
  * pointer to new isci_remote_device.
  */
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 7bedbe877704..0bc63a7ab41c 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -369,8 +369,16 @@ static int iscsi_sw_tcp_pdu_xmit(struct iscsi_task *task)
 {
 	struct iscsi_conn *conn = task->conn;
 	unsigned int noreclaim_flag;
+	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
 	int rc = 0;
 
+	if (!tcp_sw_conn->sock) {
+		iscsi_conn_printk(KERN_ERR, conn,
+				  "Transport not bound to socket!\n");
+		return -EINVAL;
+	}
+
 	noreclaim_flag = memalloc_noreclaim_save();
 
 	while (iscsi_sw_tcp_xmit_qlen(conn)) {
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 691acbdcc46d..935f98804198 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -605,6 +605,12 @@ struct lpfc_epd_pool {
 	spinlock_t lock;	/* lock for expedite pool */
 };
 
+enum ras_state {
+	INACTIVE,
+	REG_INPROGRESS,
+	ACTIVE
+};
+
 struct lpfc_ras_fwlog {
 	uint8_t *fwlog_buff;
 	uint32_t fw_buffcount; /* Buffer size posted to FW */
@@ -621,7 +627,7 @@ struct lpfc_ras_fwlog {
 	bool ras_enabled;   /* Ras Enabled for the function */
 #define LPFC_RAS_DISABLE_LOGGING 0x00
 #define LPFC_RAS_ENABLE_LOGGING 0x01
-	bool ras_active;    /* RAS logging running state */
+	enum ras_state state;    /* RAS logging running state */
 };
 
 struct lpfc_hba {
@@ -725,6 +731,7 @@ struct lpfc_hba {
 #define HBA_FCOE_MODE		0x4 /* HBA function in FCoE Mode */
 #define HBA_SP_QUEUE_EVT	0x8 /* Slow-path qevt posted to worker thread*/
 #define HBA_POST_RECEIVE_BUFFER 0x10 /* Rcv buffers need to be posted */
+#define HBA_PERSISTENT_TOPO	0x20 /* Persistent topology support in hba */
 #define ELS_XRI_ABORT_EVENT	0x40
 #define ASYNC_EVENT		0x80
 #define LINK_DISABLED		0x100 /* Link disabled by user */
@@ -830,6 +837,7 @@ struct lpfc_hba {
 	uint32_t cfg_fcp_mq_threshold;
 	uint32_t cfg_hdw_queue;
 	uint32_t cfg_irq_chann;
+	uint32_t cfg_irq_numa;
 	uint32_t cfg_suppress_rsp;
 	uint32_t cfg_nvme_oas;
 	uint32_t cfg_nvme_embed_cmd;
@@ -872,7 +880,6 @@ struct lpfc_hba {
 	uint32_t cfg_aer_support;
 	uint32_t cfg_sriov_nr_virtfn;
 	uint32_t cfg_request_firmware_upgrade;
-	uint32_t cfg_iocb_cnt;
 	uint32_t cfg_suppress_link_up;
 	uint32_t cfg_rrq_xri_bitmap_sz;
 	uint32_t cfg_delay_discovery;
@@ -990,7 +997,6 @@ struct lpfc_hba {
 	struct dma_pool *lpfc_drb_pool; /* data receive buffer pool */
 	struct dma_pool *lpfc_nvmet_drb_pool; /* data receive buffer pool */
 	struct dma_pool *lpfc_hbq_pool;	/* SLI3 hbq buffer pool */
-	struct dma_pool *txrdy_payload_pool;
 	struct dma_pool *lpfc_cmd_rsp_buf_pool;
 	struct lpfc_dma_pool lpfc_mbuf_safety_pool;
 
@@ -1055,6 +1061,7 @@ struct lpfc_hba {
 #ifdef LPFC_HDWQ_LOCK_STAT
 	struct dentry *debug_lockstat;
 #endif
+	struct dentry *debug_ras_log;
 	atomic_t nvmeio_trc_cnt;
 	uint32_t nvmeio_trc_size;
 	uint32_t nvmeio_trc_output_idx;
@@ -1209,6 +1216,13 @@ struct lpfc_hba {
 	uint64_t ktime_seg10_min;
 	uint64_t ktime_seg10_max;
 #endif
+
+	struct hlist_node cpuhp;	/* used for cpuhp per hba callback */
+	struct timer_list cpuhp_poll_timer;
+	struct list_head poll_list;	/* slowpath eq polling list */
+#define LPFC_POLL_HB	1		/* slowpath heartbeat */
+#define LPFC_POLL_FASTPATH	0	/* called from fastpath */
+#define LPFC_POLL_SLOWPATH	1	/* called from slowpath */
 };
 
 static inline struct Scsi_Host *
@@ -1299,6 +1313,26 @@ lpfc_phba_elsring(struct lpfc_hba *phba)
 }
 
 /**
+ * lpfc_next_online_numa_cpu - Finds next online CPU on NUMA node
+ * @numa_mask: Pointer to phba's numa_mask member.
+ * @start: starting cpu index
+ *
+ * Note: If no valid cpu found, then nr_cpu_ids is returned.
+ *
+ **/
+static inline unsigned int
+lpfc_next_online_numa_cpu(const struct cpumask *numa_mask, unsigned int start)
+{
+	unsigned int cpu_it;
+
+	for_each_cpu_wrap(cpu_it, numa_mask, start) {
+		if (cpu_online(cpu_it))
+			break;
+	}
+
+	return cpu_it;
+}
+/**
  * lpfc_sli4_mod_hba_eq_delay - update EQ delay
  * @phba: Pointer to HBA context object.
  * @q: The Event Queue to update.
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 25aa7a53d255..4ff82b36a37a 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -176,7 +176,6 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 	int i;
 	int len = 0;
 	char tmp[LPFC_MAX_NVME_INFO_TMP_LEN] = {0};
-	unsigned long iflags = 0;
 
 	if (!(vport->cfg_enable_fc4_type & LPFC_ENABLE_NVME)) {
 		len = scnprintf(buf, PAGE_SIZE, "NVME Disabled\n");
@@ -347,7 +346,6 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 	if (strlcat(buf, "\nNVME Initiator Enabled\n", PAGE_SIZE) >= PAGE_SIZE)
 		goto buffer_done;
 
-	rcu_read_lock();
 	scnprintf(tmp, sizeof(tmp),
 		  "XRI Dist lpfc%d Total %d IO %d ELS %d\n",
 		  phba->brd_no,
@@ -355,7 +353,7 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 		  phba->sli4_hba.io_xri_max,
 		  lpfc_sli4_get_els_iocb_cnt(phba));
 	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
-		goto rcu_unlock_buf_done;
+		goto buffer_done;
 
 	/* Port state is only one of two values for now. */
 	if (localport->port_id)
@@ -371,15 +369,17 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 		  wwn_to_u64(vport->fc_nodename.u.wwn),
 		  localport->port_id, statep);
 	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
-		goto rcu_unlock_buf_done;
+		goto buffer_done;
+
+	spin_lock_irq(shost->host_lock);
 
 	list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
 		nrport = NULL;
-		spin_lock_irqsave(&vport->phba->hbalock, iflags);
+		spin_lock(&vport->phba->hbalock);
 		rport = lpfc_ndlp_get_nrport(ndlp);
 		if (rport)
 			nrport = rport->remoteport;
-		spin_unlock_irqrestore(&vport->phba->hbalock, iflags);
+		spin_unlock(&vport->phba->hbalock);
 		if (!nrport)
 			continue;
 
@@ -398,39 +398,39 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 
 		/* Tab in to show lport ownership. */
 		if (strlcat(buf, "NVME RPORT       ", PAGE_SIZE) >= PAGE_SIZE)
-			goto rcu_unlock_buf_done;
+			goto unlock_buf_done;
 		if (phba->brd_no >= 10) {
 			if (strlcat(buf, " ", PAGE_SIZE) >= PAGE_SIZE)
-				goto rcu_unlock_buf_done;
+				goto unlock_buf_done;
 		}
 
 		scnprintf(tmp, sizeof(tmp), "WWPN x%llx ",
 			  nrport->port_name);
 		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
-			goto rcu_unlock_buf_done;
+			goto unlock_buf_done;
 
 		scnprintf(tmp, sizeof(tmp), "WWNN x%llx ",
 			  nrport->node_name);
 		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
-			goto rcu_unlock_buf_done;
+			goto unlock_buf_done;
 
 		scnprintf(tmp, sizeof(tmp), "DID x%06x ",
 			  nrport->port_id);
 		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
-			goto rcu_unlock_buf_done;
+			goto unlock_buf_done;
 
 		/* An NVME rport can have multiple roles. */
 		if (nrport->port_role & FC_PORT_ROLE_NVME_INITIATOR) {
 			if (strlcat(buf, "INITIATOR ", PAGE_SIZE) >= PAGE_SIZE)
-				goto rcu_unlock_buf_done;
+				goto unlock_buf_done;
 		}
 		if (nrport->port_role & FC_PORT_ROLE_NVME_TARGET) {
 			if (strlcat(buf, "TARGET ", PAGE_SIZE) >= PAGE_SIZE)
-				goto rcu_unlock_buf_done;
+				goto unlock_buf_done;
 		}
 		if (nrport->port_role & FC_PORT_ROLE_NVME_DISCOVERY) {
 			if (strlcat(buf, "DISCSRVC ", PAGE_SIZE) >= PAGE_SIZE)
-				goto rcu_unlock_buf_done;
+				goto unlock_buf_done;
 		}
 		if (nrport->port_role & ~(FC_PORT_ROLE_NVME_INITIATOR |
 					  FC_PORT_ROLE_NVME_TARGET |
@@ -438,14 +438,14 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 			scnprintf(tmp, sizeof(tmp), "UNKNOWN ROLE x%x",
 				  nrport->port_role);
 			if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
-				goto rcu_unlock_buf_done;
+				goto unlock_buf_done;
 		}
 
 		scnprintf(tmp, sizeof(tmp), "%s\n", statep);
 		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
-			goto rcu_unlock_buf_done;
+			goto unlock_buf_done;
 	}
-	rcu_read_unlock();
+	spin_unlock_irq(shost->host_lock);
 
 	if (!lport)
 		goto buffer_done;
@@ -505,11 +505,11 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 		  atomic_read(&lport->cmpl_fcp_err));
 	strlcat(buf, tmp, PAGE_SIZE);
 
-	/* RCU is already unlocked. */
+	/* host_lock is already unlocked. */
 	goto buffer_done;
 
- rcu_unlock_buf_done:
-	rcu_read_unlock();
+ unlock_buf_done:
+	spin_unlock_irq(shost->host_lock);
 
  buffer_done:
 	len = strnlen(buf, PAGE_SIZE);
@@ -1475,8 +1475,9 @@ lpfc_sli4_pdev_status_reg_wait(struct lpfc_hba *phba)
 	int i;
 
 	msleep(100);
-	lpfc_readl(phba->sli4_hba.u.if_type2.STATUSregaddr,
-		   &portstat_reg.word0);
+	if (lpfc_readl(phba->sli4_hba.u.if_type2.STATUSregaddr,
+		       &portstat_reg.word0))
+		return -EIO;
 
 	/* verify if privileged for the request operation */
 	if (!bf_get(lpfc_sliport_status_rn, &portstat_reg) &&
@@ -1486,8 +1487,9 @@ lpfc_sli4_pdev_status_reg_wait(struct lpfc_hba *phba)
 	/* wait for the SLI port firmware ready after firmware reset */
 	for (i = 0; i < LPFC_FW_RESET_MAXIMUM_WAIT_10MS_CNT; i++) {
 		msleep(10);
-		lpfc_readl(phba->sli4_hba.u.if_type2.STATUSregaddr,
-			   &portstat_reg.word0);
+		if (lpfc_readl(phba->sli4_hba.u.if_type2.STATUSregaddr,
+			       &portstat_reg.word0))
+			continue;
 		if (!bf_get(lpfc_sliport_status_err, &portstat_reg))
 			continue;
 		if (!bf_get(lpfc_sliport_status_rn, &portstat_reg))
@@ -1642,7 +1644,7 @@ lpfc_set_trunking(struct lpfc_hba *phba, char *buff_out)
 {
 	LPFC_MBOXQ_t *mbox = NULL;
 	unsigned long val = 0;
-	char *pval = 0;
+	char *pval = NULL;
 	int rc = 0;
 
 	if (!strncmp("enable", buff_out,
@@ -3533,6 +3535,31 @@ LPFC_ATTR_R(enable_rrq, 2, 0, 2,
 LPFC_ATTR_R(suppress_link_up, LPFC_INITIALIZE_LINK, LPFC_INITIALIZE_LINK,
 		LPFC_DELAY_INIT_LINK_INDEFINITELY,
 		"Suppress Link Up at initialization");
+
+static ssize_t
+lpfc_pls_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct Scsi_Host  *shost = class_to_shost(dev);
+	struct lpfc_hba   *phba = ((struct lpfc_vport *)shost->hostdata)->phba;
+
+	return scnprintf(buf, PAGE_SIZE, "%d\n",
+			 phba->sli4_hba.pc_sli4_params.pls);
+}
+static DEVICE_ATTR(pls, 0444,
+			 lpfc_pls_show, NULL);
+
+static ssize_t
+lpfc_pt_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct Scsi_Host  *shost = class_to_shost(dev);
+	struct lpfc_hba   *phba = ((struct lpfc_vport *)shost->hostdata)->phba;
+
+	return scnprintf(buf, PAGE_SIZE, "%d\n",
+			 (phba->hba_flag & HBA_PERSISTENT_TOPO) ? 1 : 0);
+}
+static DEVICE_ATTR(pt, 0444,
+			 lpfc_pt_show, NULL);
+
 /*
 # lpfc_cnt: Number of IOCBs allocated for ELS, CT, and ABTS
 #       1 - (1024)
@@ -3580,9 +3607,6 @@ lpfc_txcmplq_hw_show(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(txcmplq_hw, S_IRUGO,
 			 lpfc_txcmplq_hw_show, NULL);
 
-LPFC_ATTR_R(iocb_cnt, 2, 1, 5,
-	"Number of IOCBs alloc for ELS, CT, and ABTS: 1k to 5k IOCBs");
-
 /*
 # lpfc_nodev_tmo: If set, it will hold all I/O errors on devices that disappear
 # until the timer expires. Value range is [0,255]. Default value is 30.
@@ -4096,7 +4120,16 @@ lpfc_topology_store(struct device *dev, struct device_attribute *attr,
 				val);
 			return -EINVAL;
 		}
-		if ((phba->pcidev->device == PCI_DEVICE_ID_LANCER_G6_FC ||
+		/*
+		 * The 'topology' is not a configurable parameter if :
+		 *   - persistent topology enabled
+		 *   - G7 adapters
+		 *   - G6 with no private loop support
+		 */
+
+		if (((phba->hba_flag & HBA_PERSISTENT_TOPO) ||
+		     (!phba->sli4_hba.pc_sli4_params.pls &&
+		     phba->pcidev->device == PCI_DEVICE_ID_LANCER_G6_FC) ||
 		     phba->pcidev->device == PCI_DEVICE_ID_LANCER_G7_FC) &&
 		    val == 4) {
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
@@ -5298,7 +5331,7 @@ lpfc_fcp_cpu_map_show(struct device *dev, struct device_attribute *attr,
 			len += scnprintf(buf + len, PAGE_SIZE - len,
 					"CPU %02d not present\n",
 					phba->sli4_hba.curr_disp_cpu);
-		else if (cpup->irq == LPFC_VECTOR_MAP_EMPTY) {
+		else if (cpup->eq == LPFC_VECTOR_MAP_EMPTY) {
 			if (cpup->hdwq == LPFC_VECTOR_MAP_EMPTY)
 				len += scnprintf(
 					buf + len, PAGE_SIZE - len,
@@ -5311,10 +5344,10 @@ lpfc_fcp_cpu_map_show(struct device *dev, struct device_attribute *attr,
 			else
 				len += scnprintf(
 					buf + len, PAGE_SIZE - len,
-					"CPU %02d EQ %04d hdwq %04d "
+					"CPU %02d EQ None hdwq %04d "
 					"physid %d coreid %d ht %d ua %d\n",
 					phba->sli4_hba.curr_disp_cpu,
-					cpup->eq, cpup->hdwq, cpup->phys_id,
+					cpup->hdwq, cpup->phys_id,
 					cpup->core_id,
 					(cpup->flag & LPFC_CPU_MAP_HYPER),
 					(cpup->flag & LPFC_CPU_MAP_UNASSIGN));
@@ -5329,7 +5362,7 @@ lpfc_fcp_cpu_map_show(struct device *dev, struct device_attribute *attr,
 					cpup->core_id,
 					(cpup->flag & LPFC_CPU_MAP_HYPER),
 					(cpup->flag & LPFC_CPU_MAP_UNASSIGN),
-					cpup->irq);
+					lpfc_get_irq(cpup->eq));
 			else
 				len += scnprintf(
 					buf + len, PAGE_SIZE - len,
@@ -5340,7 +5373,7 @@ lpfc_fcp_cpu_map_show(struct device *dev, struct device_attribute *attr,
 					cpup->core_id,
 					(cpup->flag & LPFC_CPU_MAP_HYPER),
 					(cpup->flag & LPFC_CPU_MAP_UNASSIGN),
-					cpup->irq);
+					lpfc_get_irq(cpup->eq));
 		}
 
 		phba->sli4_hba.curr_disp_cpu++;
@@ -5711,7 +5744,7 @@ LPFC_ATTR_RW(nvme_embed_cmd, 1, 0, 2,
  * the driver will advertise it supports to the SCSI layer.
  *
  *      0    = Set nr_hw_queues by the number of CPUs or HW queues.
- *      1,128 = Manually specify the maximum nr_hw_queue value to be set,
+ *      1,256 = Manually specify nr_hw_queue value to be advertised,
  *
  * Value range is [0,256]. Default value is 8.
  */
@@ -5729,30 +5762,130 @@ LPFC_ATTR_R(fcp_mq_threshold, LPFC_FCP_MQ_THRESHOLD_DEF,
  * A hardware IO queue maps (qidx) to a specific driver CQ/WQ.
  *
  *      0    = Configure the number of hdw queues to the number of active CPUs.
- *      1,128 = Manually specify how many hdw queues to use.
+ *      1,256 = Manually specify how many hdw queues to use.
  *
- * Value range is [0,128]. Default value is 0.
+ * Value range is [0,256]. Default value is 0.
  */
 LPFC_ATTR_R(hdw_queue,
 	    LPFC_HBA_HDWQ_DEF,
 	    LPFC_HBA_HDWQ_MIN, LPFC_HBA_HDWQ_MAX,
 	    "Set the number of I/O Hardware Queues");
 
+static inline void
+lpfc_assign_default_irq_numa(struct lpfc_hba *phba)
+{
+#if IS_ENABLED(CONFIG_X86)
+	/* If AMD architecture, then default is LPFC_IRQ_CHANN_NUMA */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		phba->cfg_irq_numa = 1;
+	else
+		phba->cfg_irq_numa = 0;
+#else
+	phba->cfg_irq_numa = 0;
+#endif
+}
+
 /*
  * lpfc_irq_chann: Set the number of IRQ vectors that are available
  * for Hardware Queues to utilize.  This also will map to the number
  * of EQ / MSI-X vectors the driver will create. This should never be
  * more than the number of Hardware Queues
  *
- *      0     = Configure number of IRQ Channels to the number of active CPUs.
- *      1,128 = Manually specify how many IRQ Channels to use.
+ *	0		= Configure number of IRQ Channels to:
+ *			  if AMD architecture, number of CPUs on HBA's NUMA node
+ *			  otherwise, number of active CPUs.
+ *	[1,256]		= Manually specify how many IRQ Channels to use.
  *
- * Value range is [0,128]. Default value is 0.
+ * Value range is [0,256]. Default value is [0].
  */
-LPFC_ATTR_R(irq_chann,
-	    LPFC_HBA_HDWQ_DEF,
-	    LPFC_HBA_HDWQ_MIN, LPFC_HBA_HDWQ_MAX,
-	    "Set the number of I/O IRQ Channels");
+static uint lpfc_irq_chann = LPFC_IRQ_CHANN_DEF;
+module_param(lpfc_irq_chann, uint, 0444);
+MODULE_PARM_DESC(lpfc_irq_chann, "Set number of interrupt vectors to allocate");
+
+/* lpfc_irq_chann_init - Set the hba irq_chann initial value
+ * @phba: lpfc_hba pointer.
+ * @val: contains the initial value
+ *
+ * Description:
+ * Validates the initial value is within range and assigns it to the
+ * adapter. If not in range, an error message is posted and the
+ * default value is assigned.
+ *
+ * Returns:
+ * zero if value is in range and is set
+ * -EINVAL if value was out of range
+ **/
+static int
+lpfc_irq_chann_init(struct lpfc_hba *phba, uint32_t val)
+{
+	const struct cpumask *numa_mask;
+
+	if (phba->cfg_use_msi != 2) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+				"8532 use_msi = %u ignoring cfg_irq_numa\n",
+				phba->cfg_use_msi);
+		phba->cfg_irq_numa = 0;
+		phba->cfg_irq_chann = LPFC_IRQ_CHANN_MIN;
+		return 0;
+	}
+
+	/* Check if default setting was passed */
+	if (val == LPFC_IRQ_CHANN_DEF)
+		lpfc_assign_default_irq_numa(phba);
+
+	if (phba->cfg_irq_numa) {
+		numa_mask = &phba->sli4_hba.numa_mask;
+
+		if (cpumask_empty(numa_mask)) {
+			lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+					"8533 Could not identify NUMA node, "
+					"ignoring cfg_irq_numa\n");
+			phba->cfg_irq_numa = 0;
+			phba->cfg_irq_chann = LPFC_IRQ_CHANN_MIN;
+		} else {
+			phba->cfg_irq_chann = cpumask_weight(numa_mask);
+			lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+					"8543 lpfc_irq_chann set to %u "
+					"(numa)\n", phba->cfg_irq_chann);
+		}
+	} else {
+		if (val > LPFC_IRQ_CHANN_MAX) {
+			lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+					"8545 lpfc_irq_chann attribute cannot "
+					"be set to %u, allowed range is "
+					"[%u,%u]\n",
+					val,
+					LPFC_IRQ_CHANN_MIN,
+					LPFC_IRQ_CHANN_MAX);
+			phba->cfg_irq_chann = LPFC_IRQ_CHANN_MIN;
+			return -EINVAL;
+		}
+		phba->cfg_irq_chann = val;
+	}
+
+	return 0;
+}
+
+/**
+ * lpfc_irq_chann_show - Display value of irq_chann
+ * @dev: class converted to a Scsi_host structure.
+ * @attr: device attribute, not used.
+ * @buf: on return contains a string with the list sizes
+ *
+ * Returns: size of formatted string.
+ **/
+static ssize_t
+lpfc_irq_chann_show(struct device *dev, struct device_attribute *attr,
+		    char *buf)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+	struct lpfc_vport *vport = (struct lpfc_vport *)shost->hostdata;
+	struct lpfc_hba *phba = vport->phba;
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", phba->cfg_irq_chann);
+}
+
+static DEVICE_ATTR_RO(lpfc_irq_chann);
 
 /*
 # lpfc_enable_hba_reset: Allow or prevent HBA resets to the hardware.
@@ -5933,7 +6066,53 @@ LPFC_ATTR_RW(enable_mds_diags, 0, 0, 1, "Enable MDS Diagnostics");
  *	[1-4] = Multiple of 1/4th Mb of host memory for FW logging
  * Value range [0..4]. Default value is 0
  */
-LPFC_ATTR_RW(ras_fwlog_buffsize, 0, 0, 4, "Host memory for FW logging");
+LPFC_ATTR(ras_fwlog_buffsize, 0, 0, 4, "Host memory for FW logging");
+lpfc_param_show(ras_fwlog_buffsize);
+
+static ssize_t
+lpfc_ras_fwlog_buffsize_set(struct lpfc_hba  *phba, uint val)
+{
+	int ret = 0;
+	enum ras_state state;
+
+	if (!lpfc_rangecheck(val, 0, 4))
+		return -EINVAL;
+
+	if (phba->cfg_ras_fwlog_buffsize == val)
+		return 0;
+
+	if (phba->cfg_ras_fwlog_func != PCI_FUNC(phba->pcidev->devfn))
+		return -EINVAL;
+
+	spin_lock_irq(&phba->hbalock);
+	state = phba->ras_fwlog.state;
+	spin_unlock_irq(&phba->hbalock);
+
+	if (state == REG_INPROGRESS) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_SLI, "6147 RAS Logging "
+				"registration is in progress\n");
+		return -EBUSY;
+	}
+
+	/* For disable logging: stop the logs and free the DMA.
+	 * For ras_fwlog_buffsize size change we still need to free and
+	 * reallocate the DMA in lpfc_sli4_ras_fwlog_init.
+	 */
+	phba->cfg_ras_fwlog_buffsize = val;
+	if (state == ACTIVE) {
+		lpfc_ras_stop_fwlog(phba);
+		lpfc_sli4_ras_dma_free(phba);
+	}
+
+	lpfc_sli4_ras_init(phba);
+	if (phba->ras_fwlog.ras_enabled)
+		ret = lpfc_sli4_ras_fwlog_init(phba, phba->cfg_ras_fwlog_level,
+					       LPFC_RAS_ENABLE_LOGGING);
+	return ret;
+}
+
+lpfc_param_store(ras_fwlog_buffsize);
+static DEVICE_ATTR_RW(lpfc_ras_fwlog_buffsize);
 
 /*
  * lpfc_ras_fwlog_level: Firmware logging verbosity level
@@ -6071,8 +6250,9 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_sriov_nr_virtfn,
 	&dev_attr_lpfc_req_fw_upgrade,
 	&dev_attr_lpfc_suppress_link_up,
-	&dev_attr_lpfc_iocb_cnt,
 	&dev_attr_iocb_hw,
+	&dev_attr_pls,
+	&dev_attr_pt,
 	&dev_attr_txq_hw,
 	&dev_attr_txcmplq_hw,
 	&dev_attr_lpfc_fips_level,
@@ -7085,11 +7265,22 @@ struct fc_function_template lpfc_vport_transport_functions = {
 static void
 lpfc_get_hba_function_mode(struct lpfc_hba *phba)
 {
-	/* If it's a SkyHawk FCoE adapter */
-	if (phba->pcidev->device == PCI_DEVICE_ID_SKYHAWK)
+	/* If the adapter supports FCoE mode */
+	switch (phba->pcidev->device) {
+	case PCI_DEVICE_ID_SKYHAWK:
+	case PCI_DEVICE_ID_SKYHAWK_VF:
+	case PCI_DEVICE_ID_LANCER_FCOE:
+	case PCI_DEVICE_ID_LANCER_FCOE_VF:
+	case PCI_DEVICE_ID_ZEPHYR_DCSP:
+	case PCI_DEVICE_ID_HORNET:
+	case PCI_DEVICE_ID_TIGERSHARK:
+	case PCI_DEVICE_ID_TOMCAT:
 		phba->hba_flag |= HBA_FCOE_MODE;
-	else
+		break;
+	default:
+	/* for others, clear the flag */
 		phba->hba_flag &= ~HBA_FCOE_MODE;
+	}
 }
 
 /**
@@ -7099,6 +7290,7 @@ lpfc_get_hba_function_mode(struct lpfc_hba *phba)
 void
 lpfc_get_cfgparam(struct lpfc_hba *phba)
 {
+	lpfc_hba_log_verbose_init(phba, lpfc_log_verbose);
 	lpfc_fcp_io_sched_init(phba, lpfc_fcp_io_sched);
 	lpfc_ns_query_init(phba, lpfc_ns_query);
 	lpfc_fcp2_no_tgt_reset_init(phba, lpfc_fcp2_no_tgt_reset);
@@ -7205,12 +7397,10 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	phba->cfg_soft_wwpn = 0L;
 	lpfc_sg_seg_cnt_init(phba, lpfc_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);
 	lpfc_sriov_nr_virtfn_init(phba, lpfc_sriov_nr_virtfn);
 	lpfc_request_firmware_upgrade_init(phba, lpfc_req_fw_upgrade);
 	lpfc_suppress_link_up_init(phba, lpfc_suppress_link_up);
-	lpfc_iocb_cnt_init(phba, lpfc_iocb_cnt);
 	lpfc_delay_discovery_init(phba, lpfc_delay_discovery);
 	lpfc_sli_mode_init(phba, lpfc_sli_mode);
 	phba->cfg_enable_dss = 1;
@@ -7256,11 +7446,11 @@ lpfc_nvme_mod_param_dep(struct lpfc_hba *phba)
 		}
 
 		if (!phba->cfg_nvmet_mrq)
-			phba->cfg_nvmet_mrq = phba->cfg_irq_chann;
+			phba->cfg_nvmet_mrq = phba->cfg_hdw_queue;
 
 		/* Adjust lpfc_nvmet_mrq to avoid running out of WQE slots */
-		if (phba->cfg_nvmet_mrq > phba->cfg_irq_chann) {
-			phba->cfg_nvmet_mrq = phba->cfg_irq_chann;
+		if (phba->cfg_nvmet_mrq > phba->cfg_hdw_queue) {
+			phba->cfg_nvmet_mrq = phba->cfg_hdw_queue;
 			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
 					"6018 Adjust lpfc_nvmet_mrq to %d\n",
 					phba->cfg_nvmet_mrq);
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index 39a736b887b1..d4e1b120cc9e 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -5435,10 +5435,12 @@ lpfc_bsg_get_ras_config(struct bsg_job *job)
 		bsg_reply->reply_data.vendor_reply.vendor_rsp;
 
 	/* Current logging state */
-	if (ras_fwlog->ras_active == true)
+	spin_lock_irq(&phba->hbalock);
+	if (ras_fwlog->state == ACTIVE)
 		ras_reply->state = LPFC_RASLOG_STATE_RUNNING;
 	else
 		ras_reply->state = LPFC_RASLOG_STATE_STOPPED;
+	spin_unlock_irq(&phba->hbalock);
 
 	ras_reply->log_level = phba->ras_fwlog.fw_loglevel;
 	ras_reply->log_buff_sz = phba->cfg_ras_fwlog_buffsize;
@@ -5495,10 +5497,13 @@ lpfc_bsg_set_ras_config(struct bsg_job *job)
 
 	if (action == LPFC_RASACTION_STOP_LOGGING) {
 		/* Check if already disabled */
-		if (ras_fwlog->ras_active == false) {
+		spin_lock_irq(&phba->hbalock);
+		if (ras_fwlog->state != ACTIVE) {
+			spin_unlock_irq(&phba->hbalock);
 			rc = -ESRCH;
 			goto ras_job_error;
 		}
+		spin_unlock_irq(&phba->hbalock);
 
 		/* Disable logging */
 		lpfc_ras_stop_fwlog(phba);
@@ -5509,8 +5514,10 @@ lpfc_bsg_set_ras_config(struct bsg_job *job)
 		 * FW-logging with new log-level. Return status
 		 * "Logging already Running" to caller.
 		 **/
-		if (ras_fwlog->ras_active)
+		spin_lock_irq(&phba->hbalock);
+		if (ras_fwlog->state != INACTIVE)
 			action_status = -EINPROGRESS;
+		spin_unlock_irq(&phba->hbalock);
 
 		/* Enable logging */
 		rc = lpfc_sli4_ras_fwlog_init(phba, log_level,
@@ -5626,10 +5633,13 @@ lpfc_bsg_get_ras_fwlog(struct bsg_job *job)
 		goto ras_job_error;
 
 	/* Logging to be stopped before reading */
-	if (ras_fwlog->ras_active == true) {
+	spin_lock_irq(&phba->hbalock);
+	if (ras_fwlog->state == ACTIVE) {
+		spin_unlock_irq(&phba->hbalock);
 		rc = -EINPROGRESS;
 		goto ras_job_error;
 	}
+	spin_unlock_irq(&phba->hbalock);
 
 	if (job->request_len <
 	    sizeof(struct fc_bsg_request) +
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index b2ad8c750486..ee353c84a097 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -215,6 +215,12 @@ irqreturn_t lpfc_sli_fp_intr_handler(int, void *);
 irqreturn_t lpfc_sli4_intr_handler(int, void *);
 irqreturn_t lpfc_sli4_hba_intr_handler(int, void *);
 
+void lpfc_sli4_cleanup_poll_list(struct lpfc_hba *phba);
+int lpfc_sli4_poll_eq(struct lpfc_queue *q, uint8_t path);
+void lpfc_sli4_poll_hbtimer(struct timer_list *t);
+void lpfc_sli4_start_polling(struct lpfc_queue *q);
+void lpfc_sli4_stop_polling(struct lpfc_queue *q);
+
 void lpfc_read_rev(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_sli4_swap_str(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_config_ring(struct lpfc_hba *, int, LPFC_MBOXQ_t *);
@@ -586,6 +592,7 @@ void lpfc_release_io_buf(struct lpfc_hba *phba, struct lpfc_io_buf *ncmd,
 void lpfc_nvme_cmd_template(void);
 void lpfc_nvmet_cmd_template(void);
 void lpfc_nvme_cancel_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn);
+void lpfc_nvme_prep_abort_wqe(struct lpfc_iocbq *pwqeq, u16 xritag, u8 opt);
 extern int lpfc_enable_nvmet_cnt;
 extern unsigned long long lpfc_enable_nvmet[];
 extern int lpfc_no_hba_reset_cnt;
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 25e86706e207..99c9bb249758 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -763,9 +763,11 @@ lpfc_cmpl_ct_cmd_gid_ft(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		    cpu_to_be16(SLI_CT_RESPONSE_FS_ACC)) {
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
 					 "0208 NameServer Rsp Data: x%x x%x "
-					 "sz x%x\n",
+					 "x%x x%x sz x%x\n",
 					 vport->fc_flag,
 					 CTreq->un.gid.Fc4Type,
+					 vport->num_disc_nodes,
+					 vport->gidft_inp,
 					 irsp->un.genreq64.bdl.bdeSize);
 
 			lpfc_ns_rsp(vport,
@@ -961,9 +963,13 @@ lpfc_cmpl_ct_cmd_gid_pt(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		if (CTrsp->CommandResponse.bits.CmdRsp ==
 		    cpu_to_be16(SLI_CT_RESPONSE_FS_ACC)) {
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
-					 "4105 NameServer Rsp Data: x%x x%x\n",
+					 "4105 NameServer Rsp Data: x%x x%x "
+					 "x%x x%x sz x%x\n",
 					 vport->fc_flag,
-					 CTreq->un.gid.Fc4Type);
+					 CTreq->un.gid.Fc4Type,
+					 vport->num_disc_nodes,
+					 vport->gidft_inp,
+					 irsp->un.genreq64.bdl.bdeSize);
 
 			lpfc_ns_rsp(vport,
 				    outp,
@@ -1025,6 +1031,11 @@ lpfc_cmpl_ct_cmd_gid_pt(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		}
 		vport->gidft_inp--;
 	}
+
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+			 "6450 GID_PT cmpl inp %d disc %d\n",
+			 vport->gidft_inp, vport->num_disc_nodes);
+
 	/* Link up / RSCN discovery */
 	if ((vport->num_disc_nodes == 0) &&
 	    (vport->gidft_inp == 0)) {
@@ -1159,6 +1170,11 @@ out:
 	/* Link up / RSCN discovery */
 	if (vport->num_disc_nodes)
 		vport->num_disc_nodes--;
+
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+			 "6451 GFF_ID cmpl inp %d disc %d\n",
+			 vport->gidft_inp, vport->num_disc_nodes);
+
 	if (vport->num_disc_nodes == 0) {
 		/*
 		 * The driver has cycled through all Nports in the RSCN payload.
@@ -1868,6 +1884,12 @@ lpfc_cmpl_ct_disc_fdmi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		if (irsp->ulpStatus == IOSTAT_LOCAL_REJECT) {
 			switch ((irsp->un.ulpWord[4] & IOERR_PARAM_MASK)) {
 			case IOERR_SLI_ABORTED:
+			case IOERR_SLI_DOWN:
+				/* Driver aborted this IO.  No retry as error
+				 * is likely Offline->Online or some adapter
+				 * error.  Recovery will try again.
+				 */
+				break;
 			case IOERR_ABORT_IN_PROGRESS:
 			case IOERR_SEQUENCE_TIMEOUT:
 			case IOERR_ILLEGAL_FRAME:
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 8d34be60d379..2e6a68d9ea4f 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -31,6 +31,7 @@
 #include <linux/pci.h>
 #include <linux/spinlock.h>
 #include <linux/ctype.h>
+#include <linux/vmalloc.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_device.h>
@@ -2078,6 +2079,96 @@ lpfc_debugfs_lockstat_write(struct file *file, const char __user *buf,
 }
 #endif
 
+static int lpfc_debugfs_ras_log_data(struct lpfc_hba *phba,
+				     char *buffer, int size)
+{
+	int copied = 0;
+	struct lpfc_dmabuf *dmabuf, *next;
+
+	spin_lock_irq(&phba->hbalock);
+	if (phba->ras_fwlog.state != ACTIVE) {
+		spin_unlock_irq(&phba->hbalock);
+		return -EINVAL;
+	}
+	spin_unlock_irq(&phba->hbalock);
+
+	list_for_each_entry_safe(dmabuf, next,
+				 &phba->ras_fwlog.fwlog_buff_list, list) {
+		memcpy(buffer + copied, dmabuf->virt, LPFC_RAS_MAX_ENTRY_SIZE);
+		copied += LPFC_RAS_MAX_ENTRY_SIZE;
+		if (size > copied)
+			break;
+	}
+	return copied;
+}
+
+static int
+lpfc_debugfs_ras_log_release(struct inode *inode, struct file *file)
+{
+	struct lpfc_debug *debug = file->private_data;
+
+	vfree(debug->buffer);
+	kfree(debug);
+
+	return 0;
+}
+
+/**
+ * lpfc_debugfs_ras_log_open - Open the RAS log debugfs buffer
+ * @inode: The inode pointer that contains a vport pointer.
+ * @file: The file pointer to attach the log output.
+ *
+ * Description:
+ * This routine is the entry point for the debugfs open file operation. It gets
+ * the vport from the i_private field in @inode, allocates the necessary buffer
+ * for the log, fills the buffer from the in-memory log for this vport, and then
+ * returns a pointer to that log in the private_data field in @file.
+ *
+ * Returns:
+ * This function returns zero if successful. On error it will return a negative
+ * error value.
+ **/
+static int
+lpfc_debugfs_ras_log_open(struct inode *inode, struct file *file)
+{
+	struct lpfc_hba *phba = inode->i_private;
+	struct lpfc_debug *debug;
+	int size;
+	int rc = -ENOMEM;
+
+	spin_lock_irq(&phba->hbalock);
+	if (phba->ras_fwlog.state != ACTIVE) {
+		spin_unlock_irq(&phba->hbalock);
+		rc = -EINVAL;
+		goto out;
+	}
+	spin_unlock_irq(&phba->hbalock);
+	debug = kmalloc(sizeof(*debug), GFP_KERNEL);
+	if (!debug)
+		goto out;
+
+	size = LPFC_RAS_MIN_BUFF_POST_SIZE * phba->cfg_ras_fwlog_buffsize;
+	debug->buffer = vmalloc(size);
+	if (!debug->buffer)
+		goto free_debug;
+
+	debug->len = lpfc_debugfs_ras_log_data(phba, debug->buffer, size);
+	if (debug->len < 0) {
+		rc = -EINVAL;
+		goto free_buffer;
+	}
+	file->private_data = debug;
+
+	return 0;
+
+free_buffer:
+	vfree(debug->buffer);
+free_debug:
+	kfree(debug);
+out:
+	return rc;
+}
+
 /**
  * lpfc_debugfs_dumpHBASlim_open - Open the Dump HBA SLIM debugfs buffer
  * @inode: The inode pointer that contains a vport pointer.
@@ -5286,6 +5377,16 @@ static const struct file_operations lpfc_debugfs_op_lockstat = {
 };
 #endif
 
+#undef lpfc_debugfs_ras_log
+static const struct file_operations lpfc_debugfs_ras_log = {
+	.owner =        THIS_MODULE,
+	.open =         lpfc_debugfs_ras_log_open,
+	.llseek =       lpfc_debugfs_lseek,
+	.read =         lpfc_debugfs_read,
+	.release =      lpfc_debugfs_ras_log_release,
+};
+#endif
+
 #undef lpfc_debugfs_op_dumpHBASlim
 static const struct file_operations lpfc_debugfs_op_dumpHBASlim = {
 	.owner =        THIS_MODULE,
@@ -5457,7 +5558,6 @@ static const struct file_operations lpfc_idiag_op_extAcc = {
 	.release =      lpfc_idiag_cmd_release,
 };
 
-#endif
 
 /* lpfc_idiag_mbxacc_dump_bsg_mbox - idiag debugfs dump bsg mailbox command
  * @phba: Pointer to HBA context object.
@@ -5707,6 +5807,19 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 			goto debug_failed;
 		}
 
+		/* RAS log */
+		snprintf(name, sizeof(name), "ras_log");
+		phba->debug_ras_log =
+			debugfs_create_file(name, 0644,
+					    phba->hba_debugfs_root,
+					    phba, &lpfc_debugfs_ras_log);
+		if (!phba->debug_ras_log) {
+			lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
+					 "6148 Cannot create debugfs"
+					 " ras_log\n");
+			goto debug_failed;
+		}
+
 		/* Setup hbqinfo */
 		snprintf(name, sizeof(name), "hbqinfo");
 		phba->debug_hbqinfo =
@@ -6117,6 +6230,9 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport)
 		debugfs_remove(phba->debug_hbqinfo); /* hbqinfo */
 		phba->debug_hbqinfo = NULL;
 
+		debugfs_remove(phba->debug_ras_log);
+		phba->debug_ras_log = NULL;
+
 #ifdef LPFC_HDWQ_LOCK_STAT
 		debugfs_remove(phba->debug_lockstat); /* lockstat */
 		phba->debug_lockstat = NULL;
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index d5303994bfd6..42a2bf38eaea 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -2236,6 +2236,7 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	struct Scsi_Host  *shost = lpfc_shost_from_vport(vport);
 	IOCB_t *irsp;
 	struct lpfc_nodelist *ndlp;
+	char *mode;
 
 	/* we pass cmdiocb to state machine which needs rspiocb as well */
 	cmdiocb->context_un.rsp_iocb = rspiocb;
@@ -2273,8 +2274,17 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			goto out;
 		}
 
+		/* If we don't send GFT_ID to Fabric, a PRLI error
+		 * could be expected.
+		 */
+		if ((vport->fc_flag & FC_FABRIC) ||
+		    (vport->cfg_enable_fc4_type != LPFC_ENABLE_BOTH))
+			mode = KERN_ERR;
+		else
+			mode = KERN_INFO;
+
 		/* PRLI failed */
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
+		lpfc_printf_vlog(vport, mode, LOG_ELS,
 				 "2754 PRLI failure DID:%06X Status:x%x/x%x, "
 				 "data: x%x\n",
 				 ndlp->nlp_DID, irsp->ulpStatus,
@@ -4291,6 +4301,11 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 	irsp = &rspiocb->iocb;
 
+	if (!vport) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_ELS,
+				"3177 ELS response failed\n");
+		goto out;
+	}
 	if (cmdiocb->context_un.mbox)
 		mbox = cmdiocb->context_un.mbox;
 
@@ -4430,7 +4445,7 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		mempool_free(mbox, phba->mbox_mem_pool);
 	}
 out:
-	if (ndlp && NLP_CHK_NODE_ACT(ndlp)) {
+	if (ndlp && NLP_CHK_NODE_ACT(ndlp) && shost) {
 		spin_lock_irq(shost->host_lock);
 		ndlp->nlp_flag &= ~(NLP_ACC_REGLOGIN | NLP_RM_DFLT_RPI);
 		spin_unlock_irq(shost->host_lock);
@@ -5260,6 +5275,11 @@ lpfc_els_disc_plogi(struct lpfc_vport *vport)
 			}
 		}
 	}
+
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+			 "6452 Discover PLOGI %d flag x%x\n",
+			 sentplogi, vport->fc_flag);
+
 	if (sentplogi) {
 		lpfc_set_disctmo(vport);
 	}
@@ -6455,7 +6475,7 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 	uint32_t payload_len, length, nportid, *cmd;
 	int rscn_cnt;
 	int rscn_id = 0, hba_id = 0;
-	int i;
+	int i, tmo;
 
 	pcmd = (struct lpfc_dmabuf *) cmdiocb->context2;
 	lp = (uint32_t *) pcmd->virt;
@@ -6561,6 +6581,13 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 
 		spin_lock_irq(shost->host_lock);
 		vport->fc_flag |= FC_RSCN_DEFERRED;
+
+		/* Restart disctmo if its already running */
+		if (vport->fc_flag & FC_DISC_TMO) {
+			tmo = ((phba->fc_ratov * 3) + 3);
+			mod_timer(&vport->fc_disctmo,
+				  jiffies + msecs_to_jiffies(1000 * tmo));
+		}
 		if ((rscn_cnt < FC_MAX_HOLD_RSCN) &&
 		    !(vport->fc_flag & FC_RSCN_DISCOVERY)) {
 			vport->fc_flag |= FC_RSCN_MODE;
@@ -6663,9 +6690,10 @@ lpfc_els_handle_rscn(struct lpfc_vport *vport)
 
 	/* RSCN processed */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
-			 "0215 RSCN processed Data: x%x x%x x%x x%x\n",
+			 "0215 RSCN processed Data: x%x x%x x%x x%x x%x x%x\n",
 			 vport->fc_flag, 0, vport->fc_rscn_id_cnt,
-			 vport->port_state);
+			 vport->port_state, vport->num_disc_nodes,
+			 vport->gidft_inp);
 
 	/* To process RSCN, first compare RSCN data with NameServer */
 	vport->fc_ns_retry = 0;
@@ -7986,20 +8014,22 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport)
 	struct lpfc_sli_ring *pring;
 	struct lpfc_iocbq *tmp_iocb, *piocb;
 	IOCB_t *cmd = NULL;
+	unsigned long iflags = 0;
 
 	lpfc_fabric_abort_vport(vport);
+
 	/*
 	 * For SLI3, only the hbalock is required.  But SLI4 needs to coordinate
 	 * with the ring insert operation.  Because lpfc_sli_issue_abort_iotag
 	 * ultimately grabs the ring_lock, the driver must splice the list into
 	 * a working list and release the locks before calling the abort.
 	 */
-	spin_lock_irq(&phba->hbalock);
+	spin_lock_irqsave(&phba->hbalock, iflags);
 	pring = lpfc_phba_elsring(phba);
 
 	/* Bail out if we've no ELS wq, like in PCI error recovery case. */
 	if (unlikely(!pring)) {
-		spin_unlock_irq(&phba->hbalock);
+		spin_unlock_irqrestore(&phba->hbalock, iflags);
 		return;
 	}
 
@@ -8014,6 +8044,9 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport)
 		if (piocb->vport != vport)
 			continue;
 
+		if (piocb->iocb_flag & LPFC_DRIVER_ABORTED)
+			continue;
+
 		/* On the ELS ring we can have ELS_REQUESTs or
 		 * GEN_REQUESTs waiting for a response.
 		 */
@@ -8037,21 +8070,21 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport)
 
 	if (phba->sli_rev == LPFC_SLI_REV4)
 		spin_unlock(&pring->ring_lock);
-	spin_unlock_irq(&phba->hbalock);
+	spin_unlock_irqrestore(&phba->hbalock, iflags);
 
 	/* Abort each txcmpl iocb on aborted list and remove the dlist links. */
 	list_for_each_entry_safe(piocb, tmp_iocb, &abort_list, dlist) {
-		spin_lock_irq(&phba->hbalock);
+		spin_lock_irqsave(&phba->hbalock, iflags);
 		list_del_init(&piocb->dlist);
 		lpfc_sli_issue_abort_iotag(phba, pring, piocb);
-		spin_unlock_irq(&phba->hbalock);
+		spin_unlock_irqrestore(&phba->hbalock, iflags);
 	}
 	if (!list_empty(&abort_list))
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
 				 "3387 abort list for txq not empty\n");
 	INIT_LIST_HEAD(&abort_list);
 
-	spin_lock_irq(&phba->hbalock);
+	spin_lock_irqsave(&phba->hbalock, iflags);
 	if (phba->sli_rev == LPFC_SLI_REV4)
 		spin_lock(&pring->ring_lock);
 
@@ -8091,7 +8124,7 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport)
 
 	if (phba->sli_rev == LPFC_SLI_REV4)
 		spin_unlock(&pring->ring_lock);
-	spin_unlock_irq(&phba->hbalock);
+	spin_unlock_irqrestore(&phba->hbalock, iflags);
 
 	/* Cancel all the IOCBs from the completions list */
 	lpfc_sli_cancel_iocbs(phba, &abort_list,
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 749286acdc17..85ada3deb47d 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -700,7 +700,10 @@ lpfc_work_done(struct lpfc_hba *phba)
 			if (!(phba->hba_flag & HBA_SP_QUEUE_EVT))
 				set_bit(LPFC_DATA_READY, &phba->data_flags);
 		} else {
-			if (phba->link_state >= LPFC_LINK_UP ||
+			/* Driver could have abort request completed in queue
+			 * when link goes down.  Allow for this transition.
+			 */
+			if (phba->link_state >= LPFC_LINK_DOWN ||
 			    phba->link_flag & LS_MDS_LOOPBACK) {
 				pring->flag &= ~LPFC_DEFERRED_RING_EVENT;
 				lpfc_sli_handle_slow_ring_event(phba, pring,
@@ -1135,7 +1138,6 @@ void
 lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 {
 	struct lpfc_vport *vport = pmb->vport;
-	uint8_t bbscn = 0;
 
 	if (pmb->u.mb.mbxStatus)
 		goto out;
@@ -1162,17 +1164,11 @@ lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	/* Start discovery by sending a FLOGI. port_state is identically
 	 * LPFC_FLOGI while waiting for FLOGI cmpl
 	 */
-	if (vport->port_state != LPFC_FLOGI) {
-		if (phba->bbcredit_support && phba->cfg_enable_bbcr) {
-			bbscn = bf_get(lpfc_bbscn_def,
-				       &phba->sli4_hba.bbscn_params);
-			vport->fc_sparam.cmn.bbRcvSizeMsb &= 0xf;
-			vport->fc_sparam.cmn.bbRcvSizeMsb |= (bbscn << 4);
-		}
+	if (vport->port_state != LPFC_FLOGI)
 		lpfc_initial_flogi(vport);
-	} else if (vport->fc_flag & FC_PT2PT) {
+	else if (vport->fc_flag & FC_PT2PT)
 		lpfc_disc_start(vport);
-	}
+
 	return;
 
 out:
@@ -3456,8 +3452,8 @@ lpfc_mbx_cmpl_read_topology(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 				phba->pport->port_state, vport->fc_flag);
 		else if (attn_type == LPFC_ATT_UNEXP_WWPN)
 			lpfc_printf_log(phba, KERN_ERR, LOG_LINK_EVENT,
-				"1313 Link Down UNEXP WWPN Event x%x received "
-				"Data: x%x x%x x%x x%x x%x\n",
+				"1313 Link Down Unexpected FA WWPN Event x%x "
+				"received Data: x%x x%x x%x x%x x%x\n",
 				la->eventTag, phba->fc_eventTag,
 				phba->pport->port_state, vport->fc_flag,
 				bf_get(lpfc_mbx_read_top_mm, la),
@@ -4046,7 +4042,7 @@ out:
 	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
-	lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI,
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_DISCOVERY,
 			 "0003 rpi:%x DID:%x flg:%x %d map%x x%px\n",
 			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
 			 kref_read(&ndlp->kref),
@@ -4575,8 +4571,10 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	return ndlp;
 
 free_rpi:
-	if (phba->sli_rev == LPFC_SLI_REV4)
+	if (phba->sli_rev == LPFC_SLI_REV4) {
 		lpfc_sli4_free_rpi(vport->phba, rpi);
+		ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
+	}
 	return NULL;
 }
 
@@ -4835,12 +4833,51 @@ lpfc_nlp_logo_unreg(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		if (ndlp->nlp_flag & NLP_RELEASE_RPI) {
 			lpfc_sli4_free_rpi(vport->phba, ndlp->nlp_rpi);
 			ndlp->nlp_flag &= ~NLP_RELEASE_RPI;
+			ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
 		}
 		ndlp->nlp_flag &= ~NLP_UNREG_INP;
 	}
 }
 
 /*
+ * Sets the mailbox completion handler to be used for the
+ * unreg_rpi command. The handler varies based on the state of
+ * the port and what will be happening to the rpi next.
+ */
+static void
+lpfc_set_unreg_login_mbx_cmpl(struct lpfc_hba *phba, struct lpfc_vport *vport,
+	struct lpfc_nodelist *ndlp, LPFC_MBOXQ_t *mbox)
+{
+	unsigned long iflags;
+
+	if (ndlp->nlp_flag & NLP_ISSUE_LOGO) {
+		mbox->ctx_ndlp = ndlp;
+		mbox->mbox_cmpl = lpfc_nlp_logo_unreg;
+
+	} else if (phba->sli_rev == LPFC_SLI_REV4 &&
+		   (!(vport->load_flag & FC_UNLOADING)) &&
+		    (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) >=
+				      LPFC_SLI_INTF_IF_TYPE_2) &&
+		    (kref_read(&ndlp->kref) > 0)) {
+		mbox->ctx_ndlp = lpfc_nlp_get(ndlp);
+		mbox->mbox_cmpl = lpfc_sli4_unreg_rpi_cmpl_clr;
+	} else {
+		if (vport->load_flag & FC_UNLOADING) {
+			if (phba->sli_rev == LPFC_SLI_REV4) {
+				spin_lock_irqsave(&vport->phba->ndlp_lock,
+						  iflags);
+				ndlp->nlp_flag |= NLP_RELEASE_RPI;
+				spin_unlock_irqrestore(&vport->phba->ndlp_lock,
+						       iflags);
+			}
+			lpfc_nlp_get(ndlp);
+		}
+		mbox->ctx_ndlp = ndlp;
+		mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
+	}
+}
+
+/*
  * Free rpi associated with LPFC_NODELIST entry.
  * This routine is called from lpfc_freenode(), when we are removing
  * a LPFC_NODELIST entry. It is also called if the driver initiates a
@@ -4860,7 +4897,8 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	if (ndlp->nlp_flag & NLP_RPI_REGISTERED ||
 	    ndlp->nlp_flag & NLP_REG_LOGIN_SEND) {
 		if (ndlp->nlp_flag & NLP_REG_LOGIN_SEND)
-			lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI,
+			lpfc_printf_vlog(vport, KERN_INFO,
+					 LOG_NODE | LOG_DISCOVERY,
 					 "3366 RPI x%x needs to be "
 					 "unregistered nlp_flag x%x "
 					 "did x%x\n",
@@ -4871,7 +4909,8 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		 * no need to queue up another one.
 		 */
 		if (ndlp->nlp_flag & NLP_UNREG_INP) {
-			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+			lpfc_printf_vlog(vport, KERN_INFO,
+					 LOG_NODE | LOG_DISCOVERY,
 					 "1436 unreg_rpi SKIP UNREG x%x on "
 					 "NPort x%x deferred x%x  flg x%x "
 					 "Data: x%px\n",
@@ -4890,39 +4929,19 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 
 			lpfc_unreg_login(phba, vport->vpi, rpi, mbox);
 			mbox->vport = vport;
-			if (ndlp->nlp_flag & NLP_ISSUE_LOGO) {
-				mbox->ctx_ndlp = ndlp;
-				mbox->mbox_cmpl = lpfc_nlp_logo_unreg;
-			} else {
-				if (phba->sli_rev == LPFC_SLI_REV4 &&
-				    (!(vport->load_flag & FC_UNLOADING)) &&
-				    (bf_get(lpfc_sli_intf_if_type,
-				     &phba->sli4_hba.sli_intf) >=
-				      LPFC_SLI_INTF_IF_TYPE_2) &&
-				    (kref_read(&ndlp->kref) > 0)) {
-					mbox->ctx_ndlp = lpfc_nlp_get(ndlp);
-					mbox->mbox_cmpl =
-						lpfc_sli4_unreg_rpi_cmpl_clr;
-					/*
-					 * accept PLOGIs after unreg_rpi_cmpl
-					 */
-					acc_plogi = 0;
-				} else if (vport->load_flag & FC_UNLOADING) {
-					mbox->ctx_ndlp = NULL;
-					mbox->mbox_cmpl =
-						lpfc_sli_def_mbox_cmpl;
-				} else {
-					mbox->ctx_ndlp = ndlp;
-					mbox->mbox_cmpl =
-						lpfc_sli_def_mbox_cmpl;
-				}
-			}
+			lpfc_set_unreg_login_mbx_cmpl(phba, vport, ndlp, mbox);
+			if (mbox->mbox_cmpl == lpfc_sli4_unreg_rpi_cmpl_clr)
+				/*
+				 * accept PLOGIs after unreg_rpi_cmpl
+				 */
+				acc_plogi = 0;
 			if (((ndlp->nlp_DID & Fabric_DID_MASK) !=
 			    Fabric_DID_MASK) &&
 			    (!(vport->fc_flag & FC_OFFLINE_MODE)))
 				ndlp->nlp_flag |= NLP_UNREG_INP;
 
-			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+			lpfc_printf_vlog(vport, KERN_INFO,
+					 LOG_NODE | LOG_DISCOVERY,
 					 "1433 unreg_rpi UNREG x%x on "
 					 "NPort x%x deferred flg x%x "
 					 "Data:x%px\n",
@@ -5057,6 +5076,7 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	struct lpfc_hba  *phba = vport->phba;
 	LPFC_MBOXQ_t *mb, *nextmb;
 	struct lpfc_dmabuf *mp;
+	unsigned long iflags;
 
 	/* Cleanup node for NPort <nlp_DID> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
@@ -5138,8 +5158,20 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	lpfc_cleanup_vports_rrqs(vport, ndlp);
 	if (phba->sli_rev == LPFC_SLI_REV4)
 		ndlp->nlp_flag |= NLP_RELEASE_RPI;
-	lpfc_unreg_rpi(vport, ndlp);
-
+	if (!lpfc_unreg_rpi(vport, ndlp)) {
+		/* Clean up unregistered and non freed rpis */
+		if ((ndlp->nlp_flag & NLP_RELEASE_RPI) &&
+		    !(ndlp->nlp_rpi == LPFC_RPI_ALLOC_ERROR)) {
+			lpfc_sli4_free_rpi(vport->phba,
+					   ndlp->nlp_rpi);
+			spin_lock_irqsave(&vport->phba->ndlp_lock,
+					  iflags);
+			ndlp->nlp_flag &= ~NLP_RELEASE_RPI;
+			ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
+			spin_unlock_irqrestore(&vport->phba->ndlp_lock,
+					       iflags);
+		}
+	}
 	return 0;
 }
 
@@ -5165,8 +5197,10 @@ lpfc_nlp_remove(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		/* For this case we need to cleanup the default rpi
 		 * allocated by the firmware.
 		 */
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
-				 "0005 rpi:%x DID:%x flg:%x %d map:%x x%px\n",
+		lpfc_printf_vlog(vport, KERN_INFO,
+				 LOG_NODE | LOG_DISCOVERY,
+				 "0005 Cleanup Default rpi:x%x DID:x%x flg:x%x "
+				 "ref %d map:x%x ndlp x%px\n",
 				 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
 				 kref_read(&ndlp->kref),
 				 ndlp->nlp_usg_map, ndlp);
@@ -5203,8 +5237,9 @@ lpfc_nlp_remove(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		 */
 		lpfc_printf_vlog(vport, KERN_WARNING, LOG_NODE,
 				"0940 removed node x%px DID x%x "
-				" rport not null x%px\n",
-				ndlp, ndlp->nlp_DID, ndlp->rport);
+				"rpi %d rport not null x%px\n",
+				 ndlp, ndlp->nlp_DID, ndlp->nlp_rpi,
+				 ndlp->rport);
 		rport = ndlp->rport;
 		rdata = rport->dd_data;
 		rdata->pnode = NULL;
@@ -5362,6 +5397,13 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 		if (!ndlp)
 			return NULL;
 		lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
+
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+				 "6453 Setup New Node 2B_DISC x%x "
+				 "Data:x%x x%x x%x\n",
+				 ndlp->nlp_DID, ndlp->nlp_flag,
+				 ndlp->nlp_state, vport->fc_flag);
+
 		spin_lock_irq(shost->host_lock);
 		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
 		spin_unlock_irq(shost->host_lock);
@@ -5375,6 +5417,12 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 					 "0014 Could not enable ndlp\n");
 			return NULL;
 		}
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+				 "6454 Setup Enabled Node 2B_DISC x%x "
+				 "Data:x%x x%x x%x\n",
+				 ndlp->nlp_DID, ndlp->nlp_flag,
+				 ndlp->nlp_state, vport->fc_flag);
+
 		spin_lock_irq(shost->host_lock);
 		ndlp->nlp_flag |= NLP_NPR_2B_DISC;
 		spin_unlock_irq(shost->host_lock);
@@ -5394,6 +5442,12 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 			 */
 			lpfc_cancel_retry_delay_tmo(vport, ndlp);
 
+			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+					 "6455 Setup RSCN Node 2B_DISC x%x "
+					 "Data:x%x x%x x%x\n",
+					 ndlp->nlp_DID, ndlp->nlp_flag,
+					 ndlp->nlp_state, vport->fc_flag);
+
 			/* NVME Target mode waits until rport is known to be
 			 * impacted by the RSCN before it transitions.  No
 			 * active management - just go to NPR provided the
@@ -5405,15 +5459,32 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
 			/* If we've already received a PLOGI from this NPort
 			 * we don't need to try to discover it again.
 			 */
-			if (ndlp->nlp_flag & NLP_RCV_PLOGI)
+			if (ndlp->nlp_flag & NLP_RCV_PLOGI &&
+			    !(ndlp->nlp_type &
+			     (NLP_FCP_TARGET | NLP_NVME_TARGET)))
 				return NULL;
 
+			ndlp->nlp_prev_state = ndlp->nlp_state;
+			lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
+
 			spin_lock_irq(shost->host_lock);
 			ndlp->nlp_flag |= NLP_NPR_2B_DISC;
 			spin_unlock_irq(shost->host_lock);
-		} else
+		} else {
+			lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+					 "6456 Skip Setup RSCN Node x%x "
+					 "Data:x%x x%x x%x\n",
+					 ndlp->nlp_DID, ndlp->nlp_flag,
+					 ndlp->nlp_state, vport->fc_flag);
 			ndlp = NULL;
+		}
 	} else {
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+				 "6457 Setup Active Node 2B_DISC x%x "
+				 "Data:x%x x%x x%x\n",
+				 ndlp->nlp_DID, ndlp->nlp_flag,
+				 ndlp->nlp_state, vport->fc_flag);
+
 		/* If the initiator received a PLOGI from this NPort or if the
 		 * initiator is already in the process of discovery on it,
 		 * there's no need to try to discover it again.
@@ -5565,10 +5636,10 @@ lpfc_disc_start(struct lpfc_vport *vport)
 
 	/* Start Discovery state <hba_state> */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
-			 "0202 Start Discovery hba state x%x "
-			 "Data: x%x x%x x%x\n",
+			 "0202 Start Discovery port state x%x "
+			 "flg x%x Data: x%x x%x x%x\n",
 			 vport->port_state, vport->fc_flag, vport->fc_plogi_cnt,
-			 vport->fc_adisc_cnt);
+			 vport->fc_adisc_cnt, vport->fc_npr_cnt);
 
 	/* First do ADISCs - if any */
 	num_sent = lpfc_els_disc_adisc(vport);
@@ -5996,7 +6067,7 @@ lpfc_mbx_cmpl_fdmi_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	ndlp->nlp_flag |= NLP_RPI_REGISTERED;
 	ndlp->nlp_type |= NLP_FABRIC;
 	lpfc_nlp_set_state(vport, ndlp, NLP_STE_UNMAPPED_NODE);
-	lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI,
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_DISCOVERY,
 			 "0004 rpi:%x DID:%x flg:%x %d map:%x x%px\n",
 			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
 			 kref_read(&ndlp->kref),
@@ -6185,12 +6256,12 @@ lpfc_nlp_init(struct lpfc_vport *vport, uint32_t did)
 	INIT_LIST_HEAD(&ndlp->nlp_listp);
 	if (vport->phba->sli_rev == LPFC_SLI_REV4) {
 		ndlp->nlp_rpi = rpi;
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
-				 "0007 rpi:%x DID:%x flg:%x refcnt:%d "
-				 "map:%x x%px\n", ndlp->nlp_rpi, ndlp->nlp_DID,
-				 ndlp->nlp_flag,
-				 kref_read(&ndlp->kref),
-				 ndlp->nlp_usg_map, ndlp);
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE | LOG_DISCOVERY,
+				 "0007 Init New ndlp x%px, rpi:x%x DID:%x "
+				 "flg:x%x refcnt:%d map:x%x\n",
+				 ndlp, ndlp->nlp_rpi, ndlp->nlp_DID,
+				 ndlp->nlp_flag, kref_read(&ndlp->kref),
+				 ndlp->nlp_usg_map);
 
 		ndlp->active_rrqs_xri_bitmap =
 				mempool_alloc(vport->phba->active_rrq_pool,
@@ -6419,7 +6490,8 @@ lpfc_fcf_inuse(struct lpfc_hba *phba)
 				goto out;
 			} else if (ndlp->nlp_flag & NLP_RPI_REGISTERED) {
 				ret = 1;
-				lpfc_printf_log(phba, KERN_INFO, LOG_ELS,
+				lpfc_printf_log(phba, KERN_INFO,
+						LOG_NODE | LOG_DISCOVERY,
 						"2624 RPI %x DID %x flag %x "
 						"still logged in\n",
 						ndlp->nlp_rpi, ndlp->nlp_DID,
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index bd533475c86a..25cdcbc2b02f 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -210,7 +210,6 @@ struct lpfc_sli_intf {
 #define LPFC_MAX_IMAX          5000000
 #define LPFC_DEF_IMAX          0
 
-#define LPFC_IMAX_THRESHOLD    1000
 #define LPFC_MAX_AUTO_EQ_DELAY 120
 #define LPFC_EQ_DELAY_STEP     15
 #define LPFC_EQD_ISR_TRIGGER   20000
@@ -2320,6 +2319,7 @@ struct lpfc_mbx_redisc_fcf_tbl {
 #define ADD_STATUS_OPERATION_ALREADY_ACTIVE		0x67
 #define ADD_STATUS_FW_NOT_SUPPORTED			0xEB
 #define ADD_STATUS_INVALID_REQUEST			0x4B
+#define ADD_STATUS_FW_DOWNLOAD_HW_DISABLED              0x58
 
 struct lpfc_mbx_sli4_config {
 	struct mbox_header header;
@@ -2809,6 +2809,15 @@ struct lpfc_mbx_read_config {
 #define lpfc_mbx_rd_conf_trunk_SHIFT		12
 #define lpfc_mbx_rd_conf_trunk_MASK		0x0000000F
 #define lpfc_mbx_rd_conf_trunk_WORD		word2
+#define lpfc_mbx_rd_conf_pt_SHIFT		20
+#define lpfc_mbx_rd_conf_pt_MASK		0x00000003
+#define lpfc_mbx_rd_conf_pt_WORD		word2
+#define lpfc_mbx_rd_conf_tf_SHIFT		22
+#define lpfc_mbx_rd_conf_tf_MASK		0x00000001
+#define lpfc_mbx_rd_conf_tf_WORD		word2
+#define lpfc_mbx_rd_conf_ptv_SHIFT		23
+#define lpfc_mbx_rd_conf_ptv_MASK		0x00000001
+#define lpfc_mbx_rd_conf_ptv_WORD		word2
 #define lpfc_mbx_rd_conf_topology_SHIFT		24
 #define lpfc_mbx_rd_conf_topology_MASK		0x000000FF
 #define lpfc_mbx_rd_conf_topology_WORD		word2
@@ -3479,6 +3488,9 @@ struct lpfc_sli4_parameters {
 #define cfg_bv1s_SHIFT                          10
 #define cfg_bv1s_MASK                           0x00000001
 #define cfg_bv1s_WORD                           word19
+#define cfg_pvl_SHIFT				13
+#define cfg_pvl_MASK				0x00000001
+#define cfg_pvl_WORD				word19
 
 #define cfg_nsler_SHIFT                         12
 #define cfg_nsler_MASK                          0x00000001
@@ -3518,6 +3530,7 @@ struct lpfc_sli4_parameters {
 
 #define LPFC_SET_UE_RECOVERY		0x10
 #define LPFC_SET_MDS_DIAGS		0x11
+#define LPFC_SET_DUAL_DUMP		0x1e
 struct lpfc_mbx_set_feature {
 	struct mbox_header header;
 	uint32_t feature;
@@ -3532,6 +3545,15 @@ struct lpfc_mbx_set_feature {
 #define lpfc_mbx_set_feature_mds_deep_loopbk_SHIFT  1
 #define lpfc_mbx_set_feature_mds_deep_loopbk_MASK   0x00000001
 #define lpfc_mbx_set_feature_mds_deep_loopbk_WORD   word6
+#define lpfc_mbx_set_feature_dd_SHIFT		0
+#define lpfc_mbx_set_feature_dd_MASK		0x00000001
+#define lpfc_mbx_set_feature_dd_WORD		word6
+#define lpfc_mbx_set_feature_ddquery_SHIFT	1
+#define lpfc_mbx_set_feature_ddquery_MASK	0x00000001
+#define lpfc_mbx_set_feature_ddquery_WORD	word6
+#define LPFC_DISABLE_DUAL_DUMP		0
+#define LPFC_ENABLE_DUAL_DUMP		1
+#define LPFC_QUERY_OP_DUAL_DUMP		2
 	uint32_t word7;
 #define lpfc_mbx_set_feature_UERP_SHIFT 0
 #define lpfc_mbx_set_feature_UERP_MASK  0x0000ffff
@@ -4261,6 +4283,8 @@ struct lpfc_acqe_sli {
 #define LPFC_SLI_EVENT_TYPE_DIAG_DUMP		0x5
 #define LPFC_SLI_EVENT_TYPE_MISCONFIGURED	0x9
 #define LPFC_SLI_EVENT_TYPE_REMOTE_DPORT	0xA
+#define LPFC_SLI_EVENT_TYPE_MISCONF_FAWWN	0xF
+#define LPFC_SLI_EVENT_TYPE_EEPROM_FAILURE	0x10
 };
 
 /*
@@ -4659,6 +4683,7 @@ struct create_xri_wqe {
 	uint32_t rsvd_12_15[4];         /* word 12-15 */
 };
 
+#define INHIBIT_ABORT 1
 #define T_REQUEST_TAG 3
 #define T_XRI_TAG 1
 
@@ -4807,8 +4832,8 @@ union lpfc_wqe128 {
 	struct send_frame_wqe send_frame;
 };
 
-#define MAGIC_NUMER_G6 0xFEAA0003
-#define MAGIC_NUMER_G7 0xFEAA0005
+#define MAGIC_NUMBER_G6 0xFEAA0003
+#define MAGIC_NUMBER_G7 0xFEAA0005
 
 struct lpfc_grp_hdr {
 	uint32_t size;
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index e8813d26e594..dc6f7c4b54c6 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -40,6 +40,8 @@
 #include <linux/irq.h>
 #include <linux/bitops.h>
 #include <linux/crash_dump.h>
+#include <linux/cpu.h>
+#include <linux/cpuhotplug.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_device.h>
@@ -66,9 +68,13 @@
 #include "lpfc_version.h"
 #include "lpfc_ids.h"
 
+static enum cpuhp_state lpfc_cpuhp_state;
 /* Used when mapping IRQ vectors in a driver centric manner */
 static uint32_t lpfc_present_cpu;
 
+static void __lpfc_cpuhp_remove(struct lpfc_hba *phba);
+static void lpfc_cpuhp_remove(struct lpfc_hba *phba);
+static void lpfc_cpuhp_add(struct lpfc_hba *phba);
 static void lpfc_get_hba_model_desc(struct lpfc_hba *, uint8_t *, uint8_t *);
 static int lpfc_post_rcv_buf(struct lpfc_hba *);
 static int lpfc_sli4_queue_verify(struct lpfc_hba *);
@@ -1235,10 +1241,9 @@ lpfc_hb_eq_delay_work(struct work_struct *work)
 					     struct lpfc_hba, eq_delay_work);
 	struct lpfc_eq_intr_info *eqi, *eqi_new;
 	struct lpfc_queue *eq, *eq_next;
-	unsigned char *eqcnt = NULL;
+	unsigned char *ena_delay = NULL;
 	uint32_t usdelay;
 	int i;
-	bool update = false;
 
 	if (!phba->cfg_auto_imax || phba->pport->load_flag & FC_UNLOADING)
 		return;
@@ -1247,44 +1252,36 @@ lpfc_hb_eq_delay_work(struct work_struct *work)
 	    phba->pport->fc_flag & FC_OFFLINE_MODE)
 		goto requeue;
 
-	eqcnt = kcalloc(num_possible_cpus(), sizeof(unsigned char),
-			GFP_KERNEL);
-	if (!eqcnt)
+	ena_delay = kcalloc(phba->sli4_hba.num_possible_cpu, sizeof(*ena_delay),
+			    GFP_KERNEL);
+	if (!ena_delay)
 		goto requeue;
 
-	if (phba->cfg_irq_chann > 1) {
-		/* Loop thru all IRQ vectors */
-		for (i = 0; i < phba->cfg_irq_chann; i++) {
-			/* Get the EQ corresponding to the IRQ vector */
-			eq = phba->sli4_hba.hba_eq_hdl[i].eq;
-			if (!eq)
-				continue;
-			if (eq->q_mode) {
-				update = true;
-				break;
-			}
-			if (eqcnt[eq->last_cpu] < 2)
-				eqcnt[eq->last_cpu]++;
+	for (i = 0; i < phba->cfg_irq_chann; i++) {
+		/* Get the EQ corresponding to the IRQ vector */
+		eq = phba->sli4_hba.hba_eq_hdl[i].eq;
+		if (!eq)
+			continue;
+		if (eq->q_mode || eq->q_flag & HBA_EQ_DELAY_CHK) {
+			eq->q_flag &= ~HBA_EQ_DELAY_CHK;
+			ena_delay[eq->last_cpu] = 1;
 		}
-	} else
-		update = true;
+	}
 
 	for_each_present_cpu(i) {
 		eqi = per_cpu_ptr(phba->sli4_hba.eq_info, i);
-		if (!update && eqcnt[i] < 2) {
-			eqi->icnt = 0;
-			continue;
+		if (ena_delay[i]) {
+			usdelay = (eqi->icnt >> 10) * LPFC_EQ_DELAY_STEP;
+			if (usdelay > LPFC_MAX_AUTO_EQ_DELAY)
+				usdelay = LPFC_MAX_AUTO_EQ_DELAY;
+		} else {
+			usdelay = 0;
 		}
 
-		usdelay = (eqi->icnt / LPFC_IMAX_THRESHOLD) *
-			   LPFC_EQ_DELAY_STEP;
-		if (usdelay > LPFC_MAX_AUTO_EQ_DELAY)
-			usdelay = LPFC_MAX_AUTO_EQ_DELAY;
-
 		eqi->icnt = 0;
 
 		list_for_each_entry_safe(eq, eq_next, &eqi->list, cpu_list) {
-			if (eq->last_cpu != i) {
+			if (unlikely(eq->last_cpu != i)) {
 				eqi_new = per_cpu_ptr(phba->sli4_hba.eq_info,
 						      eq->last_cpu);
 				list_move_tail(&eq->cpu_list, &eqi_new->list);
@@ -1296,7 +1293,7 @@ lpfc_hb_eq_delay_work(struct work_struct *work)
 		}
 	}
 
-	kfree(eqcnt);
+	kfree(ena_delay);
 
 requeue:
 	queue_delayed_work(phba->wq, &phba->eq_delay_work,
@@ -3053,11 +3050,12 @@ lpfc_sli4_node_prep(struct lpfc_hba *phba)
 				continue;
 			}
 			ndlp->nlp_rpi = rpi;
-			lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
-					 "0009 rpi:%x DID:%x "
-					 "flg:%x map:%x x%px\n", ndlp->nlp_rpi,
-					 ndlp->nlp_DID, ndlp->nlp_flag,
-					 ndlp->nlp_usg_map, ndlp);
+			lpfc_printf_vlog(ndlp->vport, KERN_INFO,
+					 LOG_NODE | LOG_DISCOVERY,
+					 "0009 Assign RPI x%x to ndlp x%px "
+					 "DID:x%06x flg:x%x map:x%x\n",
+					 ndlp->nlp_rpi, ndlp, ndlp->nlp_DID,
+					 ndlp->nlp_flag, ndlp->nlp_usg_map);
 		}
 	}
 	lpfc_destroy_vport_work_array(phba, vports);
@@ -3387,6 +3385,8 @@ lpfc_online(struct lpfc_hba *phba)
 	if (phba->cfg_xri_rebalancing)
 		lpfc_create_multixri_pools(phba);
 
+	lpfc_cpuhp_add(phba);
+
 	lpfc_unblock_mgmt_io(phba);
 	return 0;
 }
@@ -3453,10 +3453,15 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action)
 			list_for_each_entry_safe(ndlp, next_ndlp,
 						 &vports[i]->fc_nodes,
 						 nlp_listp) {
-				if (!NLP_CHK_NODE_ACT(ndlp))
-					continue;
-				if (ndlp->nlp_state == NLP_STE_UNUSED_NODE)
+				if ((!NLP_CHK_NODE_ACT(ndlp)) ||
+				    ndlp->nlp_state == NLP_STE_UNUSED_NODE) {
+					/* Driver must assume RPI is invalid for
+					 * any unused or inactive node.
+					 */
+					ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
 					continue;
+				}
+
 				if (ndlp->nlp_type & NLP_FABRIC) {
 					lpfc_disc_state_machine(vports[i], ndlp,
 						NULL, NLP_EVT_DEVICE_RECOVERY);
@@ -3472,16 +3477,16 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action)
 				 * comes back online.
 				 */
 				if (phba->sli_rev == LPFC_SLI_REV4) {
-					lpfc_printf_vlog(ndlp->vport,
-							 KERN_INFO, LOG_NODE,
-							 "0011 lpfc_offline: "
-							 "ndlp:x%px did %x "
-							 "usgmap:x%x rpi:%x\n",
-							 ndlp, ndlp->nlp_DID,
-							 ndlp->nlp_usg_map,
-							 ndlp->nlp_rpi);
-
+					lpfc_printf_vlog(ndlp->vport, KERN_INFO,
+						 LOG_NODE | LOG_DISCOVERY,
+						 "0011 Free RPI x%x on "
+						 "ndlp:x%px did x%x "
+						 "usgmap:x%x\n",
+						 ndlp->nlp_rpi, ndlp,
+						 ndlp->nlp_DID,
+						 ndlp->nlp_usg_map);
 					lpfc_sli4_free_rpi(phba, ndlp->nlp_rpi);
+					ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR;
 				}
 				lpfc_unreg_rpi(vports[i], ndlp);
 			}
@@ -3545,6 +3550,7 @@ lpfc_offline(struct lpfc_hba *phba)
 			spin_unlock_irq(shost->host_lock);
 		}
 	lpfc_destroy_vport_work_array(phba, vports);
+	__lpfc_cpuhp_remove(phba);
 
 	if (phba->cfg_xri_rebalancing)
 		lpfc_destroy_multixri_pools(phba);
@@ -5283,10 +5289,10 @@ lpfc_sli4_async_sli_evt(struct lpfc_hba *phba, struct lpfc_acqe_sli *acqe_sli)
 	evt_type = bf_get(lpfc_trailer_type, acqe_sli);
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
-			"2901 Async SLI event - Event Data1:x%08x Event Data2:"
-			"x%08x SLI Event Type:%d\n",
+			"2901 Async SLI event - Type:%d, Event Data: x%08x "
+			"x%08x x%08x x%08x\n", evt_type,
 			acqe_sli->event_data1, acqe_sli->event_data2,
-			evt_type);
+			acqe_sli->reserved, acqe_sli->trailer);
 
 	port_name = phba->Port[0];
 	if (port_name == 0x00)
@@ -5433,11 +5439,26 @@ lpfc_sli4_async_sli_evt(struct lpfc_hba *phba, struct lpfc_acqe_sli *acqe_sli)
 				"Event Data1:x%08x Event Data2: x%08x\n",
 				acqe_sli->event_data1, acqe_sli->event_data2);
 		break;
+	case LPFC_SLI_EVENT_TYPE_MISCONF_FAWWN:
+		/* Misconfigured WWN. Reports that the SLI Port is configured
+		 * to use FA-WWN, but the attached device doesn’t support it.
+		 * No driver action is required.
+		 * Event Data1 - N.A, Event Data2 - N.A
+		 */
+		lpfc_log_msg(phba, KERN_WARNING, LOG_SLI,
+			     "2699 Misconfigured FA-WWN - Attached device does "
+			     "not support FA-WWN\n");
+		break;
+	case LPFC_SLI_EVENT_TYPE_EEPROM_FAILURE:
+		/* EEPROM failure. No driver action is required */
+		lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
+			     "2518 EEPROM failure - "
+			     "Event Data1: x%08x Event Data2: x%08x\n",
+			     acqe_sli->event_data1, acqe_sli->event_data2);
+		break;
 	default:
 		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
-				"3193 Async SLI event - Event Data1:x%08x Event Data2:"
-				"x%08x SLI Event Type:%d\n",
-				acqe_sli->event_data1, acqe_sli->event_data2,
+				"3193 Unrecognized SLI event, type: 0x%x",
 				evt_type);
 		break;
 	}
@@ -5976,6 +5997,29 @@ static void lpfc_log_intr_mode(struct lpfc_hba *phba, uint32_t intr_mode)
 }
 
 /**
+ * lpfc_cpumask_of_node_init - initalizes cpumask of phba's NUMA node
+ * @phba: Pointer to HBA context object.
+ *
+ **/
+static void
+lpfc_cpumask_of_node_init(struct lpfc_hba *phba)
+{
+	unsigned int cpu, numa_node;
+	struct cpumask *numa_mask = &phba->sli4_hba.numa_mask;
+
+	cpumask_clear(numa_mask);
+
+	/* Check if we're a NUMA architecture */
+	numa_node = dev_to_node(&phba->pcidev->dev);
+	if (numa_node == NUMA_NO_NODE)
+		return;
+
+	for_each_possible_cpu(cpu)
+		if (cpu_to_node(cpu) == numa_node)
+			cpumask_set_cpu(cpu, numa_mask);
+}
+
+/**
  * lpfc_enable_pci_dev - Enable a generic PCI device.
  * @phba: pointer to lpfc hba data structure.
  *
@@ -6418,6 +6462,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	phba->sli4_hba.num_present_cpu = lpfc_present_cpu;
 	phba->sli4_hba.num_possible_cpu = num_possible_cpus();
 	phba->sli4_hba.curr_disp_cpu = 0;
+	lpfc_cpumask_of_node_init(phba);
 
 	/* Get all the module params for configuring this host */
 	lpfc_get_cfgparam(phba);
@@ -6953,6 +6998,7 @@ lpfc_sli4_driver_resource_unset(struct lpfc_hba *phba)
 	phba->sli4_hba.num_possible_cpu = 0;
 	phba->sli4_hba.num_present_cpu = 0;
 	phba->sli4_hba.curr_disp_cpu = 0;
+	cpumask_clear(&phba->sli4_hba.numa_mask);
 
 	/* Free memory allocated for fast-path work queue handles */
 	kfree(phba->sli4_hba.hba_eq_hdl);
@@ -7126,7 +7172,7 @@ lpfc_init_iocb_list(struct lpfc_hba *phba, int iocb_count)
 		if (iocbq_entry == NULL) {
 			printk(KERN_ERR "%s: only allocated %d iocbs of "
 				"expected %d count. Unloading driver.\n",
-				__func__, i, LPFC_IOCB_LIST_CNT);
+				__func__, i, iocb_count);
 			goto out_free_iocbq;
 		}
 
@@ -7545,18 +7591,10 @@ lpfc_create_shost(struct lpfc_hba *phba)
 
 	if (phba->nvmet_support) {
 		/* Only 1 vport (pport) will support NVME target */
-		if (phba->txrdy_payload_pool == NULL) {
-			phba->txrdy_payload_pool = dma_pool_create(
-				"txrdy_pool", &phba->pcidev->dev,
-				TXRDY_PAYLOAD_LEN, 16, 0);
-			if (phba->txrdy_payload_pool) {
-				phba->targetport = NULL;
-				phba->cfg_enable_fc4_type = LPFC_ENABLE_NVME;
-				lpfc_printf_log(phba, KERN_INFO,
-						LOG_INIT | LOG_NVME_DISC,
-						"6076 NVME Target Found\n");
-			}
-		}
+		phba->targetport = NULL;
+		phba->cfg_enable_fc4_type = LPFC_ENABLE_NVME;
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT | LOG_NVME_DISC,
+				"6076 NVME Target Found\n");
 	}
 
 	lpfc_debugfs_initialize(vport);
@@ -8235,6 +8273,94 @@ lpfc_destroy_bootstrap_mbox(struct lpfc_hba *phba)
 	memset(&phba->sli4_hba.bmbx, 0, sizeof(struct lpfc_bmbx));
 }
 
+static const char * const lpfc_topo_to_str[] = {
+	"Loop then P2P",
+	"Loopback",
+	"P2P Only",
+	"Unsupported",
+	"Loop Only",
+	"Unsupported",
+	"P2P then Loop",
+};
+
+/**
+ * lpfc_map_topology - Map the topology read from READ_CONFIG
+ * @phba: pointer to lpfc hba data structure.
+ * @rdconf: pointer to read config data
+ *
+ * This routine is invoked to map the topology values as read
+ * from the read config mailbox command. If the persistent
+ * topology feature is supported, the firmware will provide the
+ * saved topology information to be used in INIT_LINK
+ *
+ **/
+#define	LINK_FLAGS_DEF	0x0
+#define	LINK_FLAGS_P2P	0x1
+#define	LINK_FLAGS_LOOP	0x2
+static void
+lpfc_map_topology(struct lpfc_hba *phba, struct lpfc_mbx_read_config *rd_config)
+{
+	u8 ptv, tf, pt;
+
+	ptv = bf_get(lpfc_mbx_rd_conf_ptv, rd_config);
+	tf = bf_get(lpfc_mbx_rd_conf_tf, rd_config);
+	pt = bf_get(lpfc_mbx_rd_conf_pt, rd_config);
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
+			"2027 Read Config Data : ptv:0x%x, tf:0x%x pt:0x%x",
+			 ptv, tf, pt);
+	if (!ptv) {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
+				"2019 FW does not support persistent topology "
+				"Using driver parameter defined value [%s]",
+				lpfc_topo_to_str[phba->cfg_topology]);
+		return;
+	}
+	/* FW supports persistent topology - override module parameter value */
+	phba->hba_flag |= HBA_PERSISTENT_TOPO;
+	switch (phba->pcidev->device) {
+	case PCI_DEVICE_ID_LANCER_G7_FC:
+		if (tf || (pt == LINK_FLAGS_LOOP)) {
+			/* Invalid values from FW - use driver params */
+			phba->hba_flag &= ~HBA_PERSISTENT_TOPO;
+		} else {
+			/* Prism only supports PT2PT topology */
+			phba->cfg_topology = FLAGS_TOPOLOGY_MODE_PT_PT;
+		}
+		break;
+	case PCI_DEVICE_ID_LANCER_G6_FC:
+		if (!tf) {
+			phba->cfg_topology = ((pt == LINK_FLAGS_LOOP)
+					? FLAGS_TOPOLOGY_MODE_LOOP
+					: FLAGS_TOPOLOGY_MODE_PT_PT);
+		} else {
+			phba->hba_flag &= ~HBA_PERSISTENT_TOPO;
+		}
+		break;
+	default:	/* G5 */
+		if (tf) {
+			/* If topology failover set - pt is '0' or '1' */
+			phba->cfg_topology = (pt ? FLAGS_TOPOLOGY_MODE_PT_LOOP :
+					      FLAGS_TOPOLOGY_MODE_LOOP_PT);
+		} else {
+			phba->cfg_topology = ((pt == LINK_FLAGS_P2P)
+					? FLAGS_TOPOLOGY_MODE_PT_PT
+					: FLAGS_TOPOLOGY_MODE_LOOP);
+		}
+		break;
+	}
+	if (phba->hba_flag & HBA_PERSISTENT_TOPO) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
+				"2020 Using persistent topology value [%s]",
+				lpfc_topo_to_str[phba->cfg_topology]);
+	} else {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
+				"2021 Invalid topology values from FW "
+				"Using driver parameter defined value [%s]",
+				lpfc_topo_to_str[phba->cfg_topology]);
+	}
+}
+
 /**
  * lpfc_sli4_read_config - Get the config parameters.
  * @phba: pointer to lpfc hba data structure.
@@ -8346,6 +8472,7 @@ lpfc_sli4_read_config(struct lpfc_hba *phba)
 		phba->max_vpi = (phba->sli4_hba.max_cfg_param.max_vpi > 0) ?
 				(phba->sli4_hba.max_cfg_param.max_vpi - 1) : 0;
 		phba->max_vports = phba->max_vpi;
+		lpfc_map_topology(phba, rd_config);
 		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
 				"2003 cfg params Extents? %d "
 				"XRI(B:%d M:%d), "
@@ -8619,8 +8746,8 @@ lpfc_sli4_queue_verify(struct lpfc_hba *phba)
 	 */
 
 	if (phba->nvmet_support) {
-		if (phba->cfg_irq_chann < phba->cfg_nvmet_mrq)
-			phba->cfg_nvmet_mrq = phba->cfg_irq_chann;
+		if (phba->cfg_hdw_queue < phba->cfg_nvmet_mrq)
+			phba->cfg_nvmet_mrq = phba->cfg_hdw_queue;
 		if (phba->cfg_nvmet_mrq > LPFC_NVMET_MRQ_MAX)
 			phba->cfg_nvmet_mrq = LPFC_NVMET_MRQ_MAX;
 	}
@@ -9160,6 +9287,8 @@ lpfc_sli4_queue_destroy(struct lpfc_hba *phba)
 	}
 	spin_unlock_irq(&phba->hbalock);
 
+	lpfc_sli4_cleanup_poll_list(phba);
+
 	/* Release HBA eqs */
 	if (phba->sli4_hba.hdwq)
 		lpfc_sli4_release_hdwq(phba);
@@ -10581,7 +10710,6 @@ lpfc_find_cpu_handle(struct lpfc_hba *phba, uint16_t id, int match)
 		 */
 		if ((match == LPFC_FIND_BY_EQ) &&
 		    (cpup->flag & LPFC_CPU_FIRST_IRQ) &&
-		    (cpup->irq != LPFC_VECTOR_MAP_EMPTY) &&
 		    (cpup->eq == id))
 			return cpu;
 
@@ -10619,6 +10747,75 @@ lpfc_find_hyper(struct lpfc_hba *phba, int cpu,
 }
 #endif
 
+/*
+ * lpfc_assign_eq_map_info - Assigns eq for vector_map structure
+ * @phba: pointer to lpfc hba data structure.
+ * @eqidx: index for eq and irq vector
+ * @flag: flags to set for vector_map structure
+ * @cpu: cpu used to index vector_map structure
+ *
+ * The routine assigns eq info into vector_map structure
+ */
+static inline void
+lpfc_assign_eq_map_info(struct lpfc_hba *phba, uint16_t eqidx, uint16_t flag,
+			unsigned int cpu)
+{
+	struct lpfc_vector_map_info *cpup = &phba->sli4_hba.cpu_map[cpu];
+	struct lpfc_hba_eq_hdl *eqhdl = lpfc_get_eq_hdl(eqidx);
+
+	cpup->eq = eqidx;
+	cpup->flag |= flag;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+			"3336 Set Affinity: CPU %d irq %d eq %d flag x%x\n",
+			cpu, eqhdl->irq, cpup->eq, cpup->flag);
+}
+
+/**
+ * lpfc_cpu_map_array_init - Initialize cpu_map structure
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * The routine initializes the cpu_map array structure
+ */
+static void
+lpfc_cpu_map_array_init(struct lpfc_hba *phba)
+{
+	struct lpfc_vector_map_info *cpup;
+	struct lpfc_eq_intr_info *eqi;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		cpup = &phba->sli4_hba.cpu_map[cpu];
+		cpup->phys_id = LPFC_VECTOR_MAP_EMPTY;
+		cpup->core_id = LPFC_VECTOR_MAP_EMPTY;
+		cpup->hdwq = LPFC_VECTOR_MAP_EMPTY;
+		cpup->eq = LPFC_VECTOR_MAP_EMPTY;
+		cpup->flag = 0;
+		eqi = per_cpu_ptr(phba->sli4_hba.eq_info, cpu);
+		INIT_LIST_HEAD(&eqi->list);
+		eqi->icnt = 0;
+	}
+}
+
+/**
+ * lpfc_hba_eq_hdl_array_init - Initialize hba_eq_hdl structure
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * The routine initializes the hba_eq_hdl array structure
+ */
+static void
+lpfc_hba_eq_hdl_array_init(struct lpfc_hba *phba)
+{
+	struct lpfc_hba_eq_hdl *eqhdl;
+	int i;
+
+	for (i = 0; i < phba->cfg_irq_chann; i++) {
+		eqhdl = lpfc_get_eq_hdl(i);
+		eqhdl->irq = LPFC_VECTOR_MAP_EMPTY;
+		eqhdl->phba = phba;
+	}
+}
+
 /**
  * lpfc_cpu_affinity_check - Check vector CPU affinity mappings
  * @phba: pointer to lpfc hba data structure.
@@ -10637,22 +10834,10 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors)
 	int max_core_id, min_core_id;
 	struct lpfc_vector_map_info *cpup;
 	struct lpfc_vector_map_info *new_cpup;
-	const struct cpumask *maskp;
 #ifdef CONFIG_X86
 	struct cpuinfo_x86 *cpuinfo;
 #endif
 
-	/* Init cpu_map array */
-	for_each_possible_cpu(cpu) {
-		cpup = &phba->sli4_hba.cpu_map[cpu];
-		cpup->phys_id = LPFC_VECTOR_MAP_EMPTY;
-		cpup->core_id = LPFC_VECTOR_MAP_EMPTY;
-		cpup->hdwq = LPFC_VECTOR_MAP_EMPTY;
-		cpup->eq = LPFC_VECTOR_MAP_EMPTY;
-		cpup->irq = LPFC_VECTOR_MAP_EMPTY;
-		cpup->flag = 0;
-	}
-
 	max_phys_id = 0;
 	min_phys_id = LPFC_VECTOR_MAP_EMPTY;
 	max_core_id = 0;
@@ -10688,65 +10873,6 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors)
 			min_core_id = cpup->core_id;
 	}
 
-	for_each_possible_cpu(i) {
-		struct lpfc_eq_intr_info *eqi =
-			per_cpu_ptr(phba->sli4_hba.eq_info, i);
-
-		INIT_LIST_HEAD(&eqi->list);
-		eqi->icnt = 0;
-	}
-
-	/* This loop sets up all CPUs that are affinitized with a
-	 * irq vector assigned to the driver. All affinitized CPUs
-	 * will get a link to that vectors IRQ and EQ.
-	 *
-	 * NULL affinity mask handling:
-	 * If irq count is greater than one, log an error message.
-	 * If the null mask is received for the first irq, find the
-	 * first present cpu, and assign the eq index to ensure at
-	 * least one EQ is assigned.
-	 */
-	for (idx = 0; idx <  phba->cfg_irq_chann; idx++) {
-		/* Get a CPU mask for all CPUs affinitized to this vector */
-		maskp = pci_irq_get_affinity(phba->pcidev, idx);
-		if (!maskp) {
-			if (phba->cfg_irq_chann > 1)
-				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-						"3329 No affinity mask found "
-						"for vector %d (%d)\n",
-						idx, phba->cfg_irq_chann);
-			if (!idx) {
-				cpu = cpumask_first(cpu_present_mask);
-				cpup = &phba->sli4_hba.cpu_map[cpu];
-				cpup->eq = idx;
-				cpup->irq = pci_irq_vector(phba->pcidev, idx);
-				cpup->flag |= LPFC_CPU_FIRST_IRQ;
-			}
-			break;
-		}
-
-		i = 0;
-		/* Loop through all CPUs associated with vector idx */
-		for_each_cpu_and(cpu, maskp, cpu_present_mask) {
-			/* Set the EQ index and IRQ for that vector */
-			cpup = &phba->sli4_hba.cpu_map[cpu];
-			cpup->eq = idx;
-			cpup->irq = pci_irq_vector(phba->pcidev, idx);
-
-			/* If this is the first CPU thats assigned to this
-			 * vector, set LPFC_CPU_FIRST_IRQ.
-			 */
-			if (!i)
-				cpup->flag |= LPFC_CPU_FIRST_IRQ;
-			i++;
-
-			lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-					"3336 Set Affinity: CPU %d "
-					"irq %d eq %d flag x%x\n",
-					cpu, cpup->irq, cpup->eq, cpup->flag);
-		}
-	}
-
 	/* After looking at each irq vector assigned to this pcidev, its
 	 * possible to see that not ALL CPUs have been accounted for.
 	 * Next we will set any unassigned (unaffinitized) cpu map
@@ -10772,7 +10898,7 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors)
 			for (i = 0; i < phba->sli4_hba.num_present_cpu; i++) {
 				new_cpup = &phba->sli4_hba.cpu_map[new_cpu];
 				if (!(new_cpup->flag & LPFC_CPU_MAP_UNASSIGN) &&
-				    (new_cpup->irq != LPFC_VECTOR_MAP_EMPTY) &&
+				    (new_cpup->eq != LPFC_VECTOR_MAP_EMPTY) &&
 				    (new_cpup->phys_id == cpup->phys_id))
 					goto found_same;
 				new_cpu = cpumask_next(
@@ -10785,7 +10911,6 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors)
 found_same:
 			/* We found a matching phys_id, so copy the IRQ info */
 			cpup->eq = new_cpup->eq;
-			cpup->irq = new_cpup->irq;
 
 			/* Bump start_cpu to the next slot to minmize the
 			 * chance of having multiple unassigned CPU entries
@@ -10797,9 +10922,10 @@ found_same:
 
 			lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 					"3337 Set Affinity: CPU %d "
-					"irq %d from id %d same "
+					"eq %d from peer cpu %d same "
 					"phys_id (%d)\n",
-					cpu, cpup->irq, new_cpu, cpup->phys_id);
+					cpu, cpup->eq, new_cpu,
+					cpup->phys_id);
 		}
 	}
 
@@ -10823,7 +10949,7 @@ found_same:
 			for (i = 0; i < phba->sli4_hba.num_present_cpu; i++) {
 				new_cpup = &phba->sli4_hba.cpu_map[new_cpu];
 				if (!(new_cpup->flag & LPFC_CPU_MAP_UNASSIGN) &&
-				    (new_cpup->irq != LPFC_VECTOR_MAP_EMPTY))
+				    (new_cpup->eq != LPFC_VECTOR_MAP_EMPTY))
 					goto found_any;
 				new_cpu = cpumask_next(
 					new_cpu, cpu_present_mask);
@@ -10833,13 +10959,12 @@ found_same:
 			/* We should never leave an entry unassigned */
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 					"3339 Set Affinity: CPU %d "
-					"irq %d UNASSIGNED\n",
-					cpup->hdwq, cpup->irq);
+					"eq %d UNASSIGNED\n",
+					cpup->hdwq, cpup->eq);
 			continue;
 found_any:
 			/* We found an available entry, copy the IRQ info */
 			cpup->eq = new_cpup->eq;
-			cpup->irq = new_cpup->irq;
 
 			/* Bump start_cpu to the next slot to minmize the
 			 * chance of having multiple unassigned CPU entries
@@ -10851,8 +10976,8 @@ found_any:
 
 			lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 					"3338 Set Affinity: CPU %d "
-					"irq %d from id %d (%d/%d)\n",
-					cpu, cpup->irq, new_cpu,
+					"eq %d from peer cpu %d (%d/%d)\n",
+					cpu, cpup->eq, new_cpu,
 					new_cpup->phys_id, new_cpup->core_id);
 		}
 	}
@@ -10873,11 +10998,11 @@ found_any:
 		idx++;
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"3333 Set Affinity: CPU %d (phys %d core %d): "
-				"hdwq %d eq %d irq %d flg x%x\n",
+				"hdwq %d eq %d flg x%x\n",
 				cpu, cpup->phys_id, cpup->core_id,
-				cpup->hdwq, cpup->eq, cpup->irq, cpup->flag);
+				cpup->hdwq, cpup->eq, cpup->flag);
 	}
-	/* Finally we need to associate a hdwq with each cpu_map entry
+	/* Associate a hdwq with each cpu_map entry
 	 * This will be 1 to 1 - hdwq to cpu, unless there are less
 	 * hardware queues then CPUs. For that case we will just round-robin
 	 * the available hardware queues as they get assigned to CPUs.
@@ -10951,9 +11076,26 @@ found_any:
  logit:
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"3335 Set Affinity: CPU %d (phys %d core %d): "
-				"hdwq %d eq %d irq %d flg x%x\n",
+				"hdwq %d eq %d flg x%x\n",
 				cpu, cpup->phys_id, cpup->core_id,
-				cpup->hdwq, cpup->eq, cpup->irq, cpup->flag);
+				cpup->hdwq, cpup->eq, cpup->flag);
+	}
+
+	/*
+	 * Initialize the cpu_map slots for not-present cpus in case
+	 * a cpu is hot-added. Perform a simple hdwq round robin assignment.
+	 */
+	idx = 0;
+	for_each_possible_cpu(cpu) {
+		cpup = &phba->sli4_hba.cpu_map[cpu];
+		if (cpup->hdwq != LPFC_VECTOR_MAP_EMPTY)
+			continue;
+
+		cpup->hdwq = idx++ % phba->cfg_hdw_queue;
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+				"3340 Set Affinity: not present "
+				"CPU %d hdwq %d\n",
+				cpu, cpup->hdwq);
 	}
 
 	/* The cpu_map array will be used later during initialization
@@ -10963,11 +11105,280 @@ found_any:
 }
 
 /**
+ * lpfc_cpuhp_get_eq
+ *
+ * @phba:   pointer to lpfc hba data structure.
+ * @cpu:    cpu going offline
+ * @eqlist:
+ */
+static void
+lpfc_cpuhp_get_eq(struct lpfc_hba *phba, unsigned int cpu,
+		  struct list_head *eqlist)
+{
+	const struct cpumask *maskp;
+	struct lpfc_queue *eq;
+	cpumask_t tmp;
+	u16 idx;
+
+	for (idx = 0; idx < phba->cfg_irq_chann; idx++) {
+		maskp = pci_irq_get_affinity(phba->pcidev, idx);
+		if (!maskp)
+			continue;
+		/*
+		 * if irq is not affinitized to the cpu going
+		 * then we don't need to poll the eq attached
+		 * to it.
+		 */
+		if (!cpumask_and(&tmp, maskp, cpumask_of(cpu)))
+			continue;
+		/* get the cpus that are online and are affini-
+		 * tized to this irq vector.  If the count is
+		 * more than 1 then cpuhp is not going to shut-
+		 * down this vector.  Since this cpu has not
+		 * gone offline yet, we need >1.
+		 */
+		cpumask_and(&tmp, maskp, cpu_online_mask);
+		if (cpumask_weight(&tmp) > 1)
+			continue;
+
+		/* Now that we have an irq to shutdown, get the eq
+		 * mapped to this irq.  Note: multiple hdwq's in
+		 * the software can share an eq, but eventually
+		 * only eq will be mapped to this vector
+		 */
+		eq = phba->sli4_hba.hba_eq_hdl[idx].eq;
+		list_add(&eq->_poll_list, eqlist);
+	}
+}
+
+static void __lpfc_cpuhp_remove(struct lpfc_hba *phba)
+{
+	if (phba->sli_rev != LPFC_SLI_REV4)
+		return;
+
+	cpuhp_state_remove_instance_nocalls(lpfc_cpuhp_state,
+					    &phba->cpuhp);
+	/*
+	 * unregistering the instance doesn't stop the polling
+	 * timer. Wait for the poll timer to retire.
+	 */
+	synchronize_rcu();
+	del_timer_sync(&phba->cpuhp_poll_timer);
+}
+
+static void lpfc_cpuhp_remove(struct lpfc_hba *phba)
+{
+	if (phba->pport->fc_flag & FC_OFFLINE_MODE)
+		return;
+
+	__lpfc_cpuhp_remove(phba);
+}
+
+static void lpfc_cpuhp_add(struct lpfc_hba *phba)
+{
+	if (phba->sli_rev != LPFC_SLI_REV4)
+		return;
+
+	rcu_read_lock();
+
+	if (!list_empty(&phba->poll_list)) {
+		timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0);
+		mod_timer(&phba->cpuhp_poll_timer,
+			  jiffies + msecs_to_jiffies(LPFC_POLL_HB));
+	}
+
+	rcu_read_unlock();
+
+	cpuhp_state_add_instance_nocalls(lpfc_cpuhp_state,
+					 &phba->cpuhp);
+}
+
+static int __lpfc_cpuhp_checks(struct lpfc_hba *phba, int *retval)
+{
+	if (phba->pport->load_flag & FC_UNLOADING) {
+		*retval = -EAGAIN;
+		return true;
+	}
+
+	if (phba->sli_rev != LPFC_SLI_REV4) {
+		*retval = 0;
+		return true;
+	}
+
+	/* proceed with the hotplug */
+	return false;
+}
+
+/**
+ * lpfc_irq_set_aff - set IRQ affinity
+ * @eqhdl: EQ handle
+ * @cpu: cpu to set affinity
+ *
+ **/
+static inline void
+lpfc_irq_set_aff(struct lpfc_hba_eq_hdl *eqhdl, unsigned int cpu)
+{
+	cpumask_clear(&eqhdl->aff_mask);
+	cpumask_set_cpu(cpu, &eqhdl->aff_mask);
+	irq_set_status_flags(eqhdl->irq, IRQ_NO_BALANCING);
+	irq_set_affinity_hint(eqhdl->irq, &eqhdl->aff_mask);
+}
+
+/**
+ * lpfc_irq_clear_aff - clear IRQ affinity
+ * @eqhdl: EQ handle
+ *
+ **/
+static inline void
+lpfc_irq_clear_aff(struct lpfc_hba_eq_hdl *eqhdl)
+{
+	cpumask_clear(&eqhdl->aff_mask);
+	irq_clear_status_flags(eqhdl->irq, IRQ_NO_BALANCING);
+	irq_set_affinity_hint(eqhdl->irq, &eqhdl->aff_mask);
+}
+
+/**
+ * lpfc_irq_rebalance - rebalances IRQ affinity according to cpuhp event
+ * @phba: pointer to HBA context object.
+ * @cpu: cpu going offline/online
+ * @offline: true, cpu is going offline. false, cpu is coming online.
+ *
+ * If cpu is going offline, we'll try our best effort to find the next
+ * online cpu on the phba's NUMA node and migrate all offlining IRQ affinities.
+ *
+ * If cpu is coming online, reaffinitize the IRQ back to the onlineng cpu.
+ *
+ * Note: Call only if cfg_irq_numa is enabled, otherwise rely on
+ *	 PCI_IRQ_AFFINITY to auto-manage IRQ affinity.
+ *
+ **/
+static void
+lpfc_irq_rebalance(struct lpfc_hba *phba, unsigned int cpu, bool offline)
+{
+	struct lpfc_vector_map_info *cpup;
+	struct cpumask *aff_mask;
+	unsigned int cpu_select, cpu_next, idx;
+	const struct cpumask *numa_mask;
+
+	if (!phba->cfg_irq_numa)
+		return;
+
+	numa_mask = &phba->sli4_hba.numa_mask;
+
+	if (!cpumask_test_cpu(cpu, numa_mask))
+		return;
+
+	cpup = &phba->sli4_hba.cpu_map[cpu];
+
+	if (!(cpup->flag & LPFC_CPU_FIRST_IRQ))
+		return;
+
+	if (offline) {
+		/* Find next online CPU on NUMA node */
+		cpu_next = cpumask_next_wrap(cpu, numa_mask, cpu, true);
+		cpu_select = lpfc_next_online_numa_cpu(numa_mask, cpu_next);
+
+		/* Found a valid CPU */
+		if ((cpu_select < nr_cpu_ids) && (cpu_select != cpu)) {
+			/* Go through each eqhdl and ensure offlining
+			 * cpu aff_mask is migrated
+			 */
+			for (idx = 0; idx < phba->cfg_irq_chann; idx++) {
+				aff_mask = lpfc_get_aff_mask(idx);
+
+				/* Migrate affinity */
+				if (cpumask_test_cpu(cpu, aff_mask))
+					lpfc_irq_set_aff(lpfc_get_eq_hdl(idx),
+							 cpu_select);
+			}
+		} else {
+			/* Rely on irqbalance if no online CPUs left on NUMA */
+			for (idx = 0; idx < phba->cfg_irq_chann; idx++)
+				lpfc_irq_clear_aff(lpfc_get_eq_hdl(idx));
+		}
+	} else {
+		/* Migrate affinity back to this CPU */
+		lpfc_irq_set_aff(lpfc_get_eq_hdl(cpup->eq), cpu);
+	}
+}
+
+static int lpfc_cpu_offline(unsigned int cpu, struct hlist_node *node)
+{
+	struct lpfc_hba *phba = hlist_entry_safe(node, struct lpfc_hba, cpuhp);
+	struct lpfc_queue *eq, *next;
+	LIST_HEAD(eqlist);
+	int retval;
+
+	if (!phba) {
+		WARN_ONCE(!phba, "cpu: %u. phba:NULL", raw_smp_processor_id());
+		return 0;
+	}
+
+	if (__lpfc_cpuhp_checks(phba, &retval))
+		return retval;
+
+	lpfc_irq_rebalance(phba, cpu, true);
+
+	lpfc_cpuhp_get_eq(phba, cpu, &eqlist);
+
+	/* start polling on these eq's */
+	list_for_each_entry_safe(eq, next, &eqlist, _poll_list) {
+		list_del_init(&eq->_poll_list);
+		lpfc_sli4_start_polling(eq);
+	}
+
+	return 0;
+}
+
+static int lpfc_cpu_online(unsigned int cpu, struct hlist_node *node)
+{
+	struct lpfc_hba *phba = hlist_entry_safe(node, struct lpfc_hba, cpuhp);
+	struct lpfc_queue *eq, *next;
+	unsigned int n;
+	int retval;
+
+	if (!phba) {
+		WARN_ONCE(!phba, "cpu: %u. phba:NULL", raw_smp_processor_id());
+		return 0;
+	}
+
+	if (__lpfc_cpuhp_checks(phba, &retval))
+		return retval;
+
+	lpfc_irq_rebalance(phba, cpu, false);
+
+	list_for_each_entry_safe(eq, next, &phba->poll_list, _poll_list) {
+		n = lpfc_find_cpu_handle(phba, eq->hdwq, LPFC_FIND_BY_HDWQ);
+		if (n == cpu)
+			lpfc_sli4_stop_polling(eq);
+	}
+
+	return 0;
+}
+
+/**
  * lpfc_sli4_enable_msix - Enable MSI-X interrupt mode to SLI-4 device
  * @phba: pointer to lpfc hba data structure.
  *
  * This routine is invoked to enable the MSI-X interrupt vectors to device
- * with SLI-4 interface spec.
+ * with SLI-4 interface spec.  It also allocates MSI-X vectors and maps them
+ * to cpus on the system.
+ *
+ * When cfg_irq_numa is enabled, the adapter will only allocate vectors for
+ * the number of cpus on the same numa node as this adapter.  The vectors are
+ * allocated without requesting OS affinity mapping.  A vector will be
+ * allocated and assigned to each online and offline cpu.  If the cpu is
+ * online, then affinity will be set to that cpu.  If the cpu is offline, then
+ * affinity will be set to the nearest peer cpu within the numa node that is
+ * online.  If there are no online cpus within the numa node, affinity is not
+ * assigned and the OS may do as it pleases. Note: cpu vector affinity mapping
+ * is consistent with the way cpu online/offline is handled when cfg_irq_numa is
+ * configured.
+ *
+ * If numa mode is not enabled and there is more than 1 vector allocated, then
+ * the driver relies on the managed irq interface where the OS assigns vector to
+ * cpu affinity.  The driver will then use that affinity mapping to setup its
+ * cpu mapping table.
  *
  * Return codes
  * 0 - successful
@@ -10978,13 +11389,31 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 {
 	int vectors, rc, index;
 	char *name;
+	const struct cpumask *numa_mask = NULL;
+	unsigned int cpu = 0, cpu_cnt = 0, cpu_select = nr_cpu_ids;
+	struct lpfc_hba_eq_hdl *eqhdl;
+	const struct cpumask *maskp;
+	bool first;
+	unsigned int flags = PCI_IRQ_MSIX;
 
 	/* Set up MSI-X multi-message vectors */
 	vectors = phba->cfg_irq_chann;
 
-	rc = pci_alloc_irq_vectors(phba->pcidev,
-				1,
-				vectors, PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
+	if (phba->cfg_irq_numa) {
+		numa_mask = &phba->sli4_hba.numa_mask;
+		cpu_cnt = cpumask_weight(numa_mask);
+		vectors = min(phba->cfg_irq_chann, cpu_cnt);
+
+		/* cpu: iterates over numa_mask including offline or online
+		 * cpu_select: iterates over online numa_mask to set affinity
+		 */
+		cpu = cpumask_first(numa_mask);
+		cpu_select = lpfc_next_online_numa_cpu(numa_mask, cpu);
+	} else {
+		flags |= PCI_IRQ_AFFINITY;
+	}
+
+	rc = pci_alloc_irq_vectors(phba->pcidev, 1, vectors, flags);
 	if (rc < 0) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"0484 PCI enable MSI-X failed (%d)\n", rc);
@@ -10994,23 +11423,61 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 
 	/* Assign MSI-X vectors to interrupt handlers */
 	for (index = 0; index < vectors; index++) {
-		name = phba->sli4_hba.hba_eq_hdl[index].handler_name;
+		eqhdl = lpfc_get_eq_hdl(index);
+		name = eqhdl->handler_name;
 		memset(name, 0, LPFC_SLI4_HANDLER_NAME_SZ);
 		snprintf(name, LPFC_SLI4_HANDLER_NAME_SZ,
 			 LPFC_DRIVER_HANDLER_NAME"%d", index);
 
-		phba->sli4_hba.hba_eq_hdl[index].idx = index;
-		phba->sli4_hba.hba_eq_hdl[index].phba = phba;
+		eqhdl->idx = index;
 		rc = request_irq(pci_irq_vector(phba->pcidev, index),
 			 &lpfc_sli4_hba_intr_handler, 0,
-			 name,
-			 &phba->sli4_hba.hba_eq_hdl[index]);
+			 name, eqhdl);
 		if (rc) {
 			lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
 					"0486 MSI-X fast-path (%d) "
 					"request_irq failed (%d)\n", index, rc);
 			goto cfg_fail_out;
 		}
+
+		eqhdl->irq = pci_irq_vector(phba->pcidev, index);
+
+		if (phba->cfg_irq_numa) {
+			/* If found a neighboring online cpu, set affinity */
+			if (cpu_select < nr_cpu_ids)
+				lpfc_irq_set_aff(eqhdl, cpu_select);
+
+			/* Assign EQ to cpu_map */
+			lpfc_assign_eq_map_info(phba, index,
+						LPFC_CPU_FIRST_IRQ,
+						cpu);
+
+			/* Iterate to next offline or online cpu in numa_mask */
+			cpu = cpumask_next(cpu, numa_mask);
+
+			/* Find next online cpu in numa_mask to set affinity */
+			cpu_select = lpfc_next_online_numa_cpu(numa_mask, cpu);
+		} else if (vectors == 1) {
+			cpu = cpumask_first(cpu_present_mask);
+			lpfc_assign_eq_map_info(phba, index, LPFC_CPU_FIRST_IRQ,
+						cpu);
+		} else {
+			maskp = pci_irq_get_affinity(phba->pcidev, index);
+
+			first = true;
+			/* Loop through all CPUs associated with vector index */
+			for_each_cpu_and(cpu, maskp, cpu_present_mask) {
+				/* If this is the first CPU thats assigned to
+				 * this vector, set LPFC_CPU_FIRST_IRQ.
+				 */
+				lpfc_assign_eq_map_info(phba, index,
+							first ?
+							LPFC_CPU_FIRST_IRQ : 0,
+							cpu);
+				if (first)
+					first = false;
+			}
+		}
 	}
 
 	if (vectors != phba->cfg_irq_chann) {
@@ -11020,17 +11487,18 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 				phba->cfg_irq_chann, vectors);
 		if (phba->cfg_irq_chann > vectors)
 			phba->cfg_irq_chann = vectors;
-		if (phba->nvmet_support && (phba->cfg_nvmet_mrq > vectors))
-			phba->cfg_nvmet_mrq = vectors;
 	}
 
 	return rc;
 
 cfg_fail_out:
 	/* free the irq already requested */
-	for (--index; index >= 0; index--)
-		free_irq(pci_irq_vector(phba->pcidev, index),
-				&phba->sli4_hba.hba_eq_hdl[index]);
+	for (--index; index >= 0; index--) {
+		eqhdl = lpfc_get_eq_hdl(index);
+		lpfc_irq_clear_aff(eqhdl);
+		irq_set_affinity_hint(eqhdl->irq, NULL);
+		free_irq(eqhdl->irq, eqhdl);
+	}
 
 	/* Unconfigure MSI-X capability structure */
 	pci_free_irq_vectors(phba->pcidev);
@@ -11057,6 +11525,8 @@ static int
 lpfc_sli4_enable_msi(struct lpfc_hba *phba)
 {
 	int rc, index;
+	unsigned int cpu;
+	struct lpfc_hba_eq_hdl *eqhdl;
 
 	rc = pci_alloc_irq_vectors(phba->pcidev, 1, 1,
 				   PCI_IRQ_MSI | PCI_IRQ_AFFINITY);
@@ -11078,9 +11548,15 @@ lpfc_sli4_enable_msi(struct lpfc_hba *phba)
 		return rc;
 	}
 
+	eqhdl = lpfc_get_eq_hdl(0);
+	eqhdl->irq = pci_irq_vector(phba->pcidev, 0);
+
+	cpu = cpumask_first(cpu_present_mask);
+	lpfc_assign_eq_map_info(phba, 0, LPFC_CPU_FIRST_IRQ, cpu);
+
 	for (index = 0; index < phba->cfg_irq_chann; index++) {
-		phba->sli4_hba.hba_eq_hdl[index].idx = index;
-		phba->sli4_hba.hba_eq_hdl[index].phba = phba;
+		eqhdl = lpfc_get_eq_hdl(index);
+		eqhdl->idx = index;
 	}
 
 	return 0;
@@ -11138,15 +11614,21 @@ lpfc_sli4_enable_intr(struct lpfc_hba *phba, uint32_t cfg_mode)
 				     IRQF_SHARED, LPFC_DRIVER_NAME, phba);
 		if (!retval) {
 			struct lpfc_hba_eq_hdl *eqhdl;
+			unsigned int cpu;
 
 			/* Indicate initialization to INTx mode */
 			phba->intr_type = INTx;
 			intr_mode = 0;
 
+			eqhdl = lpfc_get_eq_hdl(0);
+			eqhdl->irq = pci_irq_vector(phba->pcidev, 0);
+
+			cpu = cpumask_first(cpu_present_mask);
+			lpfc_assign_eq_map_info(phba, 0, LPFC_CPU_FIRST_IRQ,
+						cpu);
 			for (idx = 0; idx < phba->cfg_irq_chann; idx++) {
-				eqhdl = &phba->sli4_hba.hba_eq_hdl[idx];
+				eqhdl = lpfc_get_eq_hdl(idx);
 				eqhdl->idx = idx;
-				eqhdl->phba = phba;
 			}
 		}
 	}
@@ -11168,14 +11650,14 @@ lpfc_sli4_disable_intr(struct lpfc_hba *phba)
 	/* Disable the currently initialized interrupt mode */
 	if (phba->intr_type == MSIX) {
 		int index;
+		struct lpfc_hba_eq_hdl *eqhdl;
 
 		/* Free up MSI-X multi-message vectors */
 		for (index = 0; index < phba->cfg_irq_chann; index++) {
-			irq_set_affinity_hint(
-				pci_irq_vector(phba->pcidev, index),
-				NULL);
-			free_irq(pci_irq_vector(phba->pcidev, index),
-					&phba->sli4_hba.hba_eq_hdl[index]);
+			eqhdl = lpfc_get_eq_hdl(index);
+			lpfc_irq_clear_aff(eqhdl);
+			irq_set_affinity_hint(eqhdl->irq, NULL);
+			free_irq(eqhdl->irq, eqhdl);
 		}
 	} else {
 		free_irq(phba->pcidev->irq, phba);
@@ -11367,6 +11849,9 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba)
 	/* Wait for completion of device XRI exchange busy */
 	lpfc_sli4_xri_exchange_busy_wait(phba);
 
+	/* per-phba callback de-registration for hotplug event */
+	lpfc_cpuhp_remove(phba);
+
 	/* Disable PCI subsystem interrupt */
 	lpfc_sli4_disable_intr(phba);
 
@@ -11538,6 +12023,7 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 	sli4_params->cqav = bf_get(cfg_cqav, mbx_sli4_parameters);
 	sli4_params->wqsize = bf_get(cfg_wqsize, mbx_sli4_parameters);
 	sli4_params->bv1s = bf_get(cfg_bv1s, mbx_sli4_parameters);
+	sli4_params->pls = bf_get(cfg_pvl, mbx_sli4_parameters);
 	sli4_params->sgl_pages_max = bf_get(cfg_sgl_page_cnt,
 					    mbx_sli4_parameters);
 	sli4_params->wqpcnt = bf_get(cfg_wqpcnt, mbx_sli4_parameters);
@@ -11589,13 +12075,10 @@ fcponly:
 	}
 
 	/* If the NVME FC4 type is enabled, scale the sg_seg_cnt to
-	 * accommodate 512K and 1M IOs in a single nvme buf and supply
-	 * enough NVME LS iocb buffers for larger connectivity counts.
+	 * accommodate 512K and 1M IOs in a single nvme buf.
 	 */
-	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
+	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)
 		phba->cfg_sg_seg_cnt = LPFC_MAX_NVME_SEG_CNT;
-		phba->cfg_iocb_cnt = 5;
-	}
 
 	/* Only embed PBDE for if_type 6, PBDE support requires xib be set */
 	if ((bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
@@ -12312,35 +12795,57 @@ lpfc_sli4_get_iocb_cnt(struct lpfc_hba *phba)
 }
 
 
-static void
+static int
 lpfc_log_write_firmware_error(struct lpfc_hba *phba, uint32_t offset,
 	uint32_t magic_number, uint32_t ftype, uint32_t fid, uint32_t fsize,
 	const struct firmware *fw)
 {
-	if ((offset == ADD_STATUS_FW_NOT_SUPPORTED) ||
+	int rc;
+
+	/* Three cases:  (1) FW was not supported on the detected adapter.
+	 * (2) FW update has been locked out administratively.
+	 * (3) Some other error during FW update.
+	 * In each case, an unmaskable message is written to the console
+	 * for admin diagnosis.
+	 */
+	if (offset == ADD_STATUS_FW_NOT_SUPPORTED ||
 	    (phba->pcidev->device == PCI_DEVICE_ID_LANCER_G6_FC &&
-	     magic_number != MAGIC_NUMER_G6) ||
+	     magic_number != MAGIC_NUMBER_G6) ||
 	    (phba->pcidev->device == PCI_DEVICE_ID_LANCER_G7_FC &&
-	     magic_number != MAGIC_NUMER_G7))
+	     magic_number != MAGIC_NUMBER_G7)) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-			"3030 This firmware version is not supported on "
-			"this HBA model. Device:%x Magic:%x Type:%x "
-			"ID:%x Size %d %zd\n",
-			phba->pcidev->device, magic_number, ftype, fid,
-			fsize, fw->size);
-	else
+				"3030 This firmware version is not supported on"
+				" this HBA model. Device:%x Magic:%x Type:%x "
+				"ID:%x Size %d %zd\n",
+				phba->pcidev->device, magic_number, ftype, fid,
+				fsize, fw->size);
+		rc = -EINVAL;
+	} else if (offset == ADD_STATUS_FW_DOWNLOAD_HW_DISABLED) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-			"3022 FW Download failed. Device:%x Magic:%x Type:%x "
-			"ID:%x Size %d %zd\n",
-			phba->pcidev->device, magic_number, ftype, fid,
-			fsize, fw->size);
+				"3021 Firmware downloads have been prohibited "
+				"by a system configuration setting on "
+				"Device:%x Magic:%x Type:%x ID:%x Size %d "
+				"%zd\n",
+				phba->pcidev->device, magic_number, ftype, fid,
+				fsize, fw->size);
+		rc = -EACCES;
+	} else {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"3022 FW Download failed. Add Status x%x "
+				"Device:%x Magic:%x Type:%x ID:%x Size %d "
+				"%zd\n",
+				offset, phba->pcidev->device, magic_number,
+				ftype, fid, fsize, fw->size);
+		rc = -EIO;
+	}
+	return rc;
 }
 
-
 /**
  * lpfc_write_firmware - attempt to write a firmware image to the port
  * @fw: pointer to firmware image returned from request_firmware.
- * @phba: pointer to lpfc hba data structure.
+ * @context: pointer to firmware image returned from request_firmware.
+ * @ret: return value this routine provides to the caller.
  *
  **/
 static void
@@ -12409,8 +12914,12 @@ lpfc_write_firmware(const struct firmware *fw, void *context)
 			rc = lpfc_wr_object(phba, &dma_buffer_list,
 				    (fw->size - offset), &offset);
 			if (rc) {
-				lpfc_log_write_firmware_error(phba, offset,
-					magic_number, ftype, fid, fsize, fw);
+				rc = lpfc_log_write_firmware_error(phba, offset,
+								   magic_number,
+								   ftype,
+								   fid,
+								   fsize,
+								   fw);
 				goto release_out;
 			}
 		}
@@ -12430,9 +12939,12 @@ release_out:
 	}
 	release_firmware(fw);
 out:
-	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-			"3024 Firmware update done: %d.\n", rc);
-	return;
+	if (rc < 0)
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"3062 Firmware update error, status %d.\n", rc);
+	else
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"3024 Firmware update success: size %d.\n", rc);
 }
 
 /**
@@ -12551,6 +13063,12 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	phba->pport = NULL;
 	lpfc_stop_port(phba);
 
+	/* Init cpu_map array */
+	lpfc_cpu_map_array_init(phba);
+
+	/* Init hba_eq_hdl array */
+	lpfc_hba_eq_hdl_array_init(phba);
+
 	/* Configure and enable interrupt */
 	intr_mode = lpfc_sli4_enable_intr(phba, cfg_mode);
 	if (intr_mode == LPFC_INTR_ERROR) {
@@ -12632,6 +13150,9 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	/* Enable RAS FW log support */
 	lpfc_sli4_ras_setup(phba);
 
+	INIT_LIST_HEAD(&phba->poll_list);
+	cpuhp_state_add_instance_nocalls(lpfc_cpuhp_state, &phba->cpuhp);
+
 	return 0;
 
 out_free_sysfs_attr:
@@ -13344,8 +13865,7 @@ lpfc_sli4_oas_verify(struct lpfc_hba *phba)
 		phba->cfg_fof = 1;
 	} else {
 		phba->cfg_fof = 0;
-		if (phba->device_data_mem_pool)
-			mempool_destroy(phba->device_data_mem_pool);
+		mempool_destroy(phba->device_data_mem_pool);
 		phba->device_data_mem_pool = NULL;
 	}
 
@@ -13450,11 +13970,24 @@ lpfc_init(void)
 	/* Initialize in case vector mapping is needed */
 	lpfc_present_cpu = num_present_cpus();
 
+	error = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+					"lpfc/sli4:online",
+					lpfc_cpu_online, lpfc_cpu_offline);
+	if (error < 0)
+		goto cpuhp_failure;
+	lpfc_cpuhp_state = error;
+
 	error = pci_register_driver(&lpfc_driver);
-	if (error) {
-		fc_release_transport(lpfc_transport_template);
-		fc_release_transport(lpfc_vport_transport_template);
-	}
+	if (error)
+		goto unwind;
+
+	return error;
+
+unwind:
+	cpuhp_remove_multi_state(lpfc_cpuhp_state);
+cpuhp_failure:
+	fc_release_transport(lpfc_transport_template);
+	fc_release_transport(lpfc_vport_transport_template);
 
 	return error;
 }
@@ -13471,6 +14004,7 @@ lpfc_exit(void)
 {
 	misc_deregister(&lpfc_mgmt_dev);
 	pci_unregister_driver(&lpfc_driver);
+	cpuhp_remove_multi_state(lpfc_cpuhp_state);
 	fc_release_transport(lpfc_transport_template);
 	fc_release_transport(lpfc_vport_transport_template);
 	idr_destroy(&lpfc_hba_index);
diff --git a/drivers/scsi/lpfc/lpfc_logmsg.h b/drivers/scsi/lpfc/lpfc_logmsg.h
index ea10f03437f5..148d02a27b58 100644
--- a/drivers/scsi/lpfc/lpfc_logmsg.h
+++ b/drivers/scsi/lpfc/lpfc_logmsg.h
@@ -46,6 +46,23 @@
 #define LOG_NVME_IOERR  0x00800000      /* NVME IO Error events. */
 #define LOG_ALL_MSG	0xffffffff	/* LOG all messages */
 
+/* generate message by verbose log setting or severity */
+#define lpfc_vlog_msg(vport, level, mask, fmt, arg...) \
+{ if (((mask) & (vport)->cfg_log_verbose) || (level[1] <= '4')) \
+	dev_printk(level, &((vport)->phba->pcidev)->dev, "%d:(%d):" \
+		   fmt, (vport)->phba->brd_no, vport->vpi, ##arg); }
+
+#define lpfc_log_msg(phba, level, mask, fmt, arg...) \
+do { \
+	{ uint32_t log_verbose = (phba)->pport ? \
+				 (phba)->pport->cfg_log_verbose : \
+				 (phba)->cfg_log_verbose; \
+	if (((mask) & log_verbose) || (level[1] <= '4')) \
+		dev_printk(level, &((phba)->pcidev)->dev, "%d:" \
+			   fmt, phba->brd_no, ##arg); \
+	} \
+} while (0)
+
 #define lpfc_printf_vlog(vport, level, mask, fmt, arg...) \
 do { \
 	{ if (((mask) & (vport)->cfg_log_verbose) || (level[1] <= '3')) \
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index 8abe933bad09..d1773c01d2b3 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -515,6 +515,7 @@ lpfc_init_link(struct lpfc_hba * phba,
 
 	if ((phba->pcidev->device == PCI_DEVICE_ID_LANCER_G6_FC ||
 	     phba->pcidev->device == PCI_DEVICE_ID_LANCER_G7_FC) &&
+	    !(phba->sli4_hba.pc_sli4_params.pls) &&
 	    mb->un.varInitLnk.link_flags & FLAGS_TOPOLOGY_MODE_LOOP) {
 		mb->un.varInitLnk.link_flags = FLAGS_TOPOLOGY_MODE_PT_PT;
 		phba->cfg_topology = FLAGS_TOPOLOGY_MODE_PT_PT;
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index ae09bb863497..7082279e4c01 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -230,9 +230,6 @@ lpfc_mem_free(struct lpfc_hba *phba)
 	dma_pool_destroy(phba->lpfc_hrb_pool);
 	phba->lpfc_hrb_pool = NULL;
 
-	dma_pool_destroy(phba->txrdy_payload_pool);
-	phba->txrdy_payload_pool = NULL;
-
 	dma_pool_destroy(phba->lpfc_hbq_pool);
 	phba->lpfc_hbq_pool = NULL;
 
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index fc6e4546d738..ae4359013846 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -279,6 +279,55 @@ lpfc_els_abort(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 	lpfc_cancel_retry_delay_tmo(phba->pport, ndlp);
 }
 
+/* lpfc_defer_pt2pt_acc - Complete SLI3 pt2pt processing on link up
+ * @phba: pointer to lpfc hba data structure.
+ * @link_mbox: pointer to CONFIG_LINK mailbox object
+ *
+ * This routine is only called if we are SLI3, direct connect pt2pt
+ * mode and the remote NPort issues the PLOGI after link up.
+ */
+static void
+lpfc_defer_pt2pt_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *link_mbox)
+{
+	LPFC_MBOXQ_t *login_mbox;
+	MAILBOX_t *mb = &link_mbox->u.mb;
+	struct lpfc_iocbq *save_iocb;
+	struct lpfc_nodelist *ndlp;
+	int rc;
+
+	ndlp = link_mbox->ctx_ndlp;
+	login_mbox = link_mbox->context3;
+	save_iocb = login_mbox->context3;
+	link_mbox->context3 = NULL;
+	login_mbox->context3 = NULL;
+
+	/* Check for CONFIG_LINK error */
+	if (mb->mbxStatus) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_DISCOVERY,
+				"4575 CONFIG_LINK fails pt2pt discovery: %x\n",
+				mb->mbxStatus);
+		mempool_free(login_mbox, phba->mbox_mem_pool);
+		mempool_free(link_mbox, phba->mbox_mem_pool);
+		lpfc_sli_release_iocbq(phba, save_iocb);
+		return;
+	}
+
+	/* Now that CONFIG_LINK completed, and our SID is configured,
+	 * we can now proceed with sending the PLOGI ACC.
+	 */
+	rc = lpfc_els_rsp_acc(link_mbox->vport, ELS_CMD_PLOGI,
+			      save_iocb, ndlp, login_mbox);
+	if (rc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_DISCOVERY,
+				"4576 PLOGI ACC fails pt2pt discovery: %x\n",
+				rc);
+		mempool_free(login_mbox, phba->mbox_mem_pool);
+	}
+
+	mempool_free(link_mbox, phba->mbox_mem_pool);
+	lpfc_sli_release_iocbq(phba, save_iocb);
+}
+
 static int
 lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	       struct lpfc_iocbq *cmdiocb)
@@ -291,10 +340,12 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	IOCB_t *icmd;
 	struct serv_parm *sp;
 	uint32_t ed_tov;
-	LPFC_MBOXQ_t *mbox;
+	LPFC_MBOXQ_t *link_mbox;
+	LPFC_MBOXQ_t *login_mbox;
+	struct lpfc_iocbq *save_iocb;
 	struct ls_rjt stat;
 	uint32_t vid, flag;
-	int rc;
+	int rc, defer_acc;
 
 	memset(&stat, 0, sizeof (struct ls_rjt));
 	pcmd = (struct lpfc_dmabuf *) cmdiocb->context2;
@@ -343,6 +394,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	else
 		ndlp->nlp_fcp_info |= CLASS3;
 
+	defer_acc = 0;
 	ndlp->nlp_class_sup = 0;
 	if (sp->cls1.classValid)
 		ndlp->nlp_class_sup |= FC_COS_CLASS1;
@@ -354,7 +406,6 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		ndlp->nlp_class_sup |= FC_COS_CLASS4;
 	ndlp->nlp_maxframe =
 		((sp->cmn.bbRcvSizeMsb & 0x0F) << 8) | sp->cmn.bbRcvSizeLsb;
-
 	/* if already logged in, do implicit logout */
 	switch (ndlp->nlp_state) {
 	case  NLP_STE_NPR_NODE:
@@ -396,6 +447,10 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
 	ndlp->nlp_flag &= ~NLP_FIRSTBURST;
 
+	login_mbox = NULL;
+	link_mbox = NULL;
+	save_iocb = NULL;
+
 	/* Check for Nport to NPort pt2pt protocol */
 	if ((vport->fc_flag & FC_PT2PT) &&
 	    !(vport->fc_flag & FC_PT2PT_PLOGI)) {
@@ -423,17 +478,22 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		if (phba->sli_rev == LPFC_SLI_REV4)
 			lpfc_issue_reg_vfi(vport);
 		else {
-			mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-			if (mbox == NULL)
+			defer_acc = 1;
+			link_mbox = mempool_alloc(phba->mbox_mem_pool,
+						  GFP_KERNEL);
+			if (!link_mbox)
 				goto out;
-			lpfc_config_link(phba, mbox);
-			mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
-			mbox->vport = vport;
-			rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
-			if (rc == MBX_NOT_FINISHED) {
-				mempool_free(mbox, phba->mbox_mem_pool);
+			lpfc_config_link(phba, link_mbox);
+			link_mbox->mbox_cmpl = lpfc_defer_pt2pt_acc;
+			link_mbox->vport = vport;
+			link_mbox->ctx_ndlp = ndlp;
+
+			save_iocb = lpfc_sli_get_iocbq(phba);
+			if (!save_iocb)
 				goto out;
-			}
+			/* Save info from cmd IOCB used in rsp */
+			memcpy((uint8_t *)save_iocb, (uint8_t *)cmdiocb,
+			       sizeof(struct lpfc_iocbq));
 		}
 
 		lpfc_can_disctmo(vport);
@@ -448,8 +508,8 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			ndlp->nlp_flag |= NLP_SUPPRESS_RSP;
 	}
 
-	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-	if (!mbox)
+	login_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!login_mbox)
 		goto out;
 
 	/* Registering an existing RPI behaves differently for SLI3 vs SLI4 */
@@ -457,21 +517,19 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		lpfc_unreg_rpi(vport, ndlp);
 
 	rc = lpfc_reg_rpi(phba, vport->vpi, icmd->un.rcvels.remoteID,
-			    (uint8_t *) sp, mbox, ndlp->nlp_rpi);
-	if (rc) {
-		mempool_free(mbox, phba->mbox_mem_pool);
+			    (uint8_t *)sp, login_mbox, ndlp->nlp_rpi);
+	if (rc)
 		goto out;
-	}
 
 	/* ACC PLOGI rsp command needs to execute first,
-	 * queue this mbox command to be processed later.
+	 * queue this login_mbox command to be processed later.
 	 */
-	mbox->mbox_cmpl = lpfc_mbx_cmpl_reg_login;
+	login_mbox->mbox_cmpl = lpfc_mbx_cmpl_reg_login;
 	/*
-	 * mbox->ctx_ndlp = lpfc_nlp_get(ndlp) deferred until mailbox
+	 * login_mbox->ctx_ndlp = lpfc_nlp_get(ndlp) deferred until mailbox
 	 * command issued in lpfc_cmpl_els_acc().
 	 */
-	mbox->vport = vport;
+	login_mbox->vport = vport;
 	spin_lock_irq(shost->host_lock);
 	ndlp->nlp_flag |= (NLP_ACC_REGLOGIN | NLP_RCV_PLOGI);
 	spin_unlock_irq(shost->host_lock);
@@ -484,8 +542,10 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	 * single discovery thread, this will cause a huge delay in
 	 * discovery. Also this will cause multiple state machines
 	 * running in parallel for this node.
+	 * This only applies to a fabric environment.
 	 */
-	if (ndlp->nlp_state == NLP_STE_PLOGI_ISSUE) {
+	if ((ndlp->nlp_state == NLP_STE_PLOGI_ISSUE) &&
+	    (vport->fc_flag & FC_FABRIC)) {
 		/* software abort outstanding PLOGI */
 		lpfc_els_abort(phba, ndlp);
 	}
@@ -504,16 +564,47 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		stat.un.b.lsRjtRsnCode = LSRJT_INVALID_CMD;
 		stat.un.b.lsRjtRsnCodeExp = LSEXP_NOTHING_MORE;
 		rc = lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb,
-			ndlp, mbox);
+			ndlp, login_mbox);
 		if (rc)
-			mempool_free(mbox, phba->mbox_mem_pool);
+			mempool_free(login_mbox, phba->mbox_mem_pool);
+		return 1;
+	}
+	if (defer_acc) {
+		/* So the order here should be:
+		 * Issue CONFIG_LINK mbox
+		 * CONFIG_LINK cmpl
+		 * Issue PLOGI ACC
+		 * PLOGI ACC cmpl
+		 * Issue REG_LOGIN mbox
+		 */
+
+		/* Save the REG_LOGIN mbox for and rcv IOCB copy later */
+		link_mbox->context3 = login_mbox;
+		login_mbox->context3 = save_iocb;
+
+		/* Start the ball rolling by issuing CONFIG_LINK here */
+		rc = lpfc_sli_issue_mbox(phba, link_mbox, MBX_NOWAIT);
+		if (rc == MBX_NOT_FINISHED)
+			goto out;
 		return 1;
 	}
-	rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, mbox);
+
+	rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, login_mbox);
 	if (rc)
-		mempool_free(mbox, phba->mbox_mem_pool);
+		mempool_free(login_mbox, phba->mbox_mem_pool);
 	return 1;
 out:
+	if (defer_acc)
+		lpfc_printf_log(phba, KERN_ERR, LOG_DISCOVERY,
+				"4577 pt2pt discovery failure: %p %p %p\n",
+				save_iocb, link_mbox, login_mbox);
+	if (save_iocb)
+		lpfc_sli_release_iocbq(phba, save_iocb);
+	if (link_mbox)
+		mempool_free(link_mbox, phba->mbox_mem_pool);
+	if (login_mbox)
+		mempool_free(login_mbox, phba->mbox_mem_pool);
+
 	stat.un.b.lsRjtRsnCode = LSRJT_UNABLE_TPC;
 	stat.un.b.lsRjtRsnCodeExp = LSEXP_OUT_OF_RESOURCE;
 	lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb, ndlp, NULL);
@@ -2030,7 +2121,9 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		if (bf_get_be32(prli_init, nvpr))
 			ndlp->nlp_type |= NLP_NVME_INITIATOR;
 
-		if (phba->nsler && bf_get_be32(prli_nsler, nvpr))
+		if (phba->nsler && bf_get_be32(prli_nsler, nvpr) &&
+		    bf_get_be32(prli_conf, nvpr))
+
 			ndlp->nlp_nvme_info |= NLP_NVME_NSLER;
 		else
 			ndlp->nlp_nvme_info &= ~NLP_NVME_NSLER;
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index a227e36cbdc2..db4a04a207ec 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -196,6 +196,46 @@ lpfc_nvme_cmd_template(void)
 }
 
 /**
+ * lpfc_nvme_prep_abort_wqe - set up 'abort' work queue entry.
+ * @pwqeq: Pointer to command iocb.
+ * @xritag: Tag that  uniqely identifies the local exchange resource.
+ * @opt: Option bits -
+ *		bit 0 = inhibit sending abts on the link
+ *
+ * This function is called with hbalock held.
+ **/
+void
+lpfc_nvme_prep_abort_wqe(struct lpfc_iocbq *pwqeq, u16 xritag, u8 opt)
+{
+	union lpfc_wqe128 *wqe = &pwqeq->wqe;
+
+	/* WQEs are reused.  Clear stale data and set key fields to
+	 * zero like ia, iaab, iaar, xri_tag, and ctxt_tag.
+	 */
+	memset(wqe, 0, sizeof(*wqe));
+
+	if (opt & INHIBIT_ABORT)
+		bf_set(abort_cmd_ia, &wqe->abort_cmd, 1);
+	/* Abort specified xri tag, with the mask deliberately zeroed */
+	bf_set(abort_cmd_criteria, &wqe->abort_cmd, T_XRI_TAG);
+
+	bf_set(wqe_cmnd, &wqe->abort_cmd.wqe_com, CMD_ABORT_XRI_CX);
+
+	/* Abort the IO associated with this outstanding exchange ID. */
+	wqe->abort_cmd.wqe_com.abort_tag = xritag;
+
+	/* iotag for the wqe completion. */
+	bf_set(wqe_reqtag, &wqe->abort_cmd.wqe_com, pwqeq->iotag);
+
+	bf_set(wqe_qosd, &wqe->abort_cmd.wqe_com, 1);
+	bf_set(wqe_lenloc, &wqe->abort_cmd.wqe_com, LPFC_WQE_LENLOC_NONE);
+
+	bf_set(wqe_cmd_type, &wqe->abort_cmd.wqe_com, OTHER_COMMAND);
+	bf_set(wqe_wqec, &wqe->abort_cmd.wqe_com, 1);
+	bf_set(wqe_cqid, &wqe->abort_cmd.wqe_com, LPFC_WQE_CQ_ID_DEFAULT);
+}
+
+/**
  * lpfc_nvme_create_queue -
  * @lpfc_pnvme: Pointer to the driver's nvme instance data
  * @qidx: An cpu index used to affinitize IO queues and MSIX vectors.
@@ -1791,7 +1831,6 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 	struct lpfc_iocbq *abts_buf;
 	struct lpfc_iocbq *nvmereq_wqe;
 	struct lpfc_nvme_fcpreq_priv *freqpriv;
-	union lpfc_wqe128 *abts_wqe;
 	unsigned long flags;
 	int ret_val;
 
@@ -1912,37 +1951,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 	/* Ready - mark outstanding as aborted by driver. */
 	nvmereq_wqe->iocb_flag |= LPFC_DRIVER_ABORTED;
 
-	/* Complete prepping the abort wqe and issue to the FW. */
-	abts_wqe = &abts_buf->wqe;
-
-	/* WQEs are reused.  Clear stale data and set key fields to
-	 * zero like ia, iaab, iaar, xri_tag, and ctxt_tag.
-	 */
-	memset(abts_wqe, 0, sizeof(*abts_wqe));
-	bf_set(abort_cmd_criteria, &abts_wqe->abort_cmd, T_XRI_TAG);
-
-	/* word 7 */
-	bf_set(wqe_cmnd, &abts_wqe->abort_cmd.wqe_com, CMD_ABORT_XRI_CX);
-	bf_set(wqe_class, &abts_wqe->abort_cmd.wqe_com,
-	       nvmereq_wqe->iocb.ulpClass);
-
-	/* word 8 - tell the FW to abort the IO associated with this
-	 * outstanding exchange ID.
-	 */
-	abts_wqe->abort_cmd.wqe_com.abort_tag = nvmereq_wqe->sli4_xritag;
-
-	/* word 9 - this is the iotag for the abts_wqe completion. */
-	bf_set(wqe_reqtag, &abts_wqe->abort_cmd.wqe_com,
-	       abts_buf->iotag);
-
-	/* word 10 */
-	bf_set(wqe_qosd, &abts_wqe->abort_cmd.wqe_com, 1);
-	bf_set(wqe_lenloc, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_LENLOC_NONE);
-
-	/* word 11 */
-	bf_set(wqe_cmd_type, &abts_wqe->abort_cmd.wqe_com, OTHER_COMMAND);
-	bf_set(wqe_wqec, &abts_wqe->abort_cmd.wqe_com, 1);
-	bf_set(wqe_cqid, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_CQ_ID_DEFAULT);
+	lpfc_nvme_prep_abort_wqe(abts_buf, nvmereq_wqe->sli4_xritag, 0);
 
 	/* ABTS WQE must go to the same WQ as the WQE to be aborted */
 	abts_buf->iocb_flag |= LPFC_IO_NVME;
@@ -2084,7 +2093,7 @@ lpfc_release_nvme_buf(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_ncmd)
 	lpfc_ncmd->flags &= ~LPFC_SBUF_BUMP_QDEPTH;
 
 	qp = lpfc_ncmd->hdwq;
-	if (lpfc_ncmd->flags & LPFC_SBUF_XBUSY) {
+	if (unlikely(lpfc_ncmd->flags & LPFC_SBUF_XBUSY)) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
 				"6310 XB release deferred for "
 				"ox_id x%x on reqtag x%x\n",
@@ -2139,12 +2148,10 @@ lpfc_nvme_create_localport(struct lpfc_vport *vport)
 	 */
 	lpfc_nvme_template.max_sgl_segments = phba->cfg_nvme_seg_cnt + 1;
 
-	/* Advertise how many hw queues we support based on fcp_io_sched */
-	if (phba->cfg_fcp_io_sched == LPFC_FCP_SCHED_BY_HDWQ)
-		lpfc_nvme_template.max_hw_queues = phba->cfg_hdw_queue;
-	else
-		lpfc_nvme_template.max_hw_queues =
-			phba->sli4_hba.num_present_cpu;
+	/* Advertise how many hw queues we support based on cfg_hdw_queue,
+	 * which will not exceed cpu count.
+	 */
+	lpfc_nvme_template.max_hw_queues = phba->cfg_hdw_queue;
 
 	if (!IS_ENABLED(CONFIG_NVME_FC))
 		return ret;
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 9884228800a5..9dc9afe1c255 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -378,13 +378,6 @@ lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba, struct lpfc_nvmet_ctxbuf *ctx_buf)
 	int cpu;
 	unsigned long iflag;
 
-	if (ctxp->txrdy) {
-		dma_pool_free(phba->txrdy_payload_pool, ctxp->txrdy,
-			      ctxp->txrdy_phys);
-		ctxp->txrdy = NULL;
-		ctxp->txrdy_phys = 0;
-	}
-
 	if (ctxp->state == LPFC_NVMET_STE_FREE) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
 				"6411 NVMET free, already free IO x%x: %d %d\n",
@@ -430,7 +423,6 @@ lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba, struct lpfc_nvmet_ctxbuf *ctx_buf)
 
 		ctxp = (struct lpfc_nvmet_rcv_ctx *)ctx_buf->context;
 		ctxp->wqeq = NULL;
-		ctxp->txrdy = NULL;
 		ctxp->offset = 0;
 		ctxp->phba = phba;
 		ctxp->size = size;
@@ -1958,12 +1950,10 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	uint32_t *payload;
 	uint32_t size, oxid, sid, rc;
 
-	fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
-	oxid = be16_to_cpu(fc_hdr->fh_ox_id);
 
-	if (!phba->targetport) {
+	if (!nvmebuf || !phba->targetport) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-				"6154 LS Drop IO x%x\n", oxid);
+				"6154 LS Drop IO\n");
 		oxid = 0;
 		size = 0;
 		sid = 0;
@@ -1971,6 +1961,9 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		goto dropit;
 	}
 
+	fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
+	oxid = be16_to_cpu(fc_hdr->fh_ox_id);
+
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
 	payload = (uint32_t *)(nvmebuf->dbuf.virt);
 	size = bf_get(lpfc_rcqe_length,  &nvmebuf->cq_event.cqe.rcqe_cmpl);
@@ -2326,7 +2319,6 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 				ctxp->state, ctxp->entry_cnt, ctxp->oxid);
 	}
 	ctxp->wqeq = NULL;
-	ctxp->txrdy = NULL;
 	ctxp->offset = 0;
 	ctxp->phba = phba;
 	ctxp->size = size;
@@ -2401,6 +2393,11 @@ lpfc_nvmet_unsol_ls_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	d_buf = piocb->context2;
 	nvmebuf = container_of(d_buf, struct hbq_dmabuf, dbuf);
 
+	if (!nvmebuf) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"3015 LS Drop IO\n");
+		return;
+	}
 	if (phba->nvmet_support == 0) {
 		lpfc_in_buf_free(phba, &nvmebuf->dbuf);
 		return;
@@ -2429,6 +2426,11 @@ lpfc_nvmet_unsol_fcp_event(struct lpfc_hba *phba,
 			   uint64_t isr_timestamp,
 			   uint8_t cqflag)
 {
+	if (!nvmebuf) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"3167 NVMET FCP Drop IO\n");
+		return;
+	}
 	if (phba->nvmet_support == 0) {
 		lpfc_rq_buf_free(phba, &nvmebuf->hbuf);
 		return;
@@ -2595,7 +2597,6 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 	struct scatterlist *sgel;
 	union lpfc_wqe128 *wqe;
 	struct ulp_bde64 *bde;
-	uint32_t *txrdy;
 	dma_addr_t physaddr;
 	int i, cnt;
 	int do_pbde;
@@ -2757,23 +2758,11 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 		       &lpfc_treceive_cmd_template.words[3],
 		       sizeof(uint32_t) * 9);
 
-		/* Words 0 - 2 : The first sg segment */
-		txrdy = dma_pool_alloc(phba->txrdy_payload_pool,
-				       GFP_KERNEL, &physaddr);
-		if (!txrdy) {
-			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-					"6041 Bad txrdy buffer: oxid x%x\n",
-					ctxp->oxid);
-			return NULL;
-		}
-		ctxp->txrdy = txrdy;
-		ctxp->txrdy_phys = physaddr;
-		wqe->fcp_treceive.bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
-		wqe->fcp_treceive.bde.tus.f.bdeSize = TXRDY_PAYLOAD_LEN;
-		wqe->fcp_treceive.bde.addrLow =
-			cpu_to_le32(putPaddrLow(physaddr));
-		wqe->fcp_treceive.bde.addrHigh =
-			cpu_to_le32(putPaddrHigh(physaddr));
+		/* Words 0 - 2 : First SGE is skipped, set invalid BDE type */
+		wqe->fcp_treceive.bde.tus.f.bdeFlags = LPFC_SGE_TYPE_SKIP;
+		wqe->fcp_treceive.bde.tus.f.bdeSize = 0;
+		wqe->fcp_treceive.bde.addrLow = 0;
+		wqe->fcp_treceive.bde.addrHigh = 0;
 
 		/* Word 4 */
 		wqe->fcp_treceive.relative_offset = ctxp->offset;
@@ -2808,17 +2797,13 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 		/* Word 12 */
 		wqe->fcp_tsend.fcp_data_len = rsp->transfer_length;
 
-		/* Setup 1 TXRDY and 1 SKIP SGE */
-		txrdy[0] = 0;
-		txrdy[1] = cpu_to_be32(rsp->transfer_length);
-		txrdy[2] = 0;
-
-		sgl->addr_hi = putPaddrHigh(physaddr);
-		sgl->addr_lo = putPaddrLow(physaddr);
+		/* Setup 2 SKIP SGEs */
+		sgl->addr_hi = 0;
+		sgl->addr_lo = 0;
 		sgl->word2 = 0;
-		bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_DATA);
+		bf_set(lpfc_sli4_sge_type, sgl, LPFC_SGE_TYPE_SKIP);
 		sgl->word2 = cpu_to_le32(sgl->word2);
-		sgl->sge_len = cpu_to_le32(TXRDY_PAYLOAD_LEN);
+		sgl->sge_len = 0;
 		sgl++;
 		sgl->addr_hi = 0;
 		sgl->addr_lo = 0;
@@ -3239,9 +3224,9 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 {
 	struct lpfc_nvmet_tgtport *tgtp;
 	struct lpfc_iocbq *abts_wqeq;
-	union lpfc_wqe128 *abts_wqe;
 	struct lpfc_nodelist *ndlp;
 	unsigned long flags;
+	u8 opt;
 	int rc;
 
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
@@ -3280,8 +3265,8 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 		return 0;
 	}
 	abts_wqeq = ctxp->abort_wqeq;
-	abts_wqe = &abts_wqeq->wqe;
 	ctxp->state = LPFC_NVMET_STE_ABORT;
+	opt = (ctxp->flag & LPFC_NVMET_ABTS_RCV) ? INHIBIT_ABORT : 0;
 	spin_unlock_irqrestore(&ctxp->ctxlock, flags);
 
 	/* Announce entry to new IO submit field. */
@@ -3327,40 +3312,12 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	/* Ready - mark outstanding as aborted by driver. */
 	abts_wqeq->iocb_flag |= LPFC_DRIVER_ABORTED;
 
-	/* WQEs are reused.  Clear stale data and set key fields to
-	 * zero like ia, iaab, iaar, xri_tag, and ctxt_tag.
-	 */
-	memset(abts_wqe, 0, sizeof(*abts_wqe));
-
-	/* word 3 */
-	bf_set(abort_cmd_criteria, &abts_wqe->abort_cmd, T_XRI_TAG);
-
-	/* word 7 */
-	bf_set(wqe_ct, &abts_wqe->abort_cmd.wqe_com, 0);
-	bf_set(wqe_cmnd, &abts_wqe->abort_cmd.wqe_com, CMD_ABORT_XRI_CX);
-
-	/* word 8 - tell the FW to abort the IO associated with this
-	 * outstanding exchange ID.
-	 */
-	abts_wqe->abort_cmd.wqe_com.abort_tag = ctxp->wqeq->sli4_xritag;
-
-	/* word 9 - this is the iotag for the abts_wqe completion. */
-	bf_set(wqe_reqtag, &abts_wqe->abort_cmd.wqe_com,
-	       abts_wqeq->iotag);
-
-	/* word 10 */
-	bf_set(wqe_qosd, &abts_wqe->abort_cmd.wqe_com, 1);
-	bf_set(wqe_lenloc, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_LENLOC_NONE);
-
-	/* word 11 */
-	bf_set(wqe_cmd_type, &abts_wqe->abort_cmd.wqe_com, OTHER_COMMAND);
-	bf_set(wqe_wqec, &abts_wqe->abort_cmd.wqe_com, 1);
-	bf_set(wqe_cqid, &abts_wqe->abort_cmd.wqe_com, LPFC_WQE_CQ_ID_DEFAULT);
+	lpfc_nvme_prep_abort_wqe(abts_wqeq, ctxp->wqeq->sli4_xritag, opt);
 
 	/* ABTS WQE must go to the same WQ as the WQE to be aborted */
 	abts_wqeq->hba_wqidx = ctxp->wqeq->hba_wqidx;
 	abts_wqeq->wqe_cmpl = lpfc_nvmet_sol_fcp_abort_cmp;
-	abts_wqeq->iocb_cmpl = 0;
+	abts_wqeq->iocb_cmpl = NULL;
 	abts_wqeq->iocb_flag |= LPFC_IO_NVME;
 	abts_wqeq->context2 = ctxp;
 	abts_wqeq->vport = phba->pport;
@@ -3495,7 +3452,7 @@ lpfc_nvmet_unsol_ls_issue_abort(struct lpfc_hba *phba,
 
 	spin_lock_irqsave(&phba->hbalock, flags);
 	abts_wqeq->wqe_cmpl = lpfc_nvmet_xmt_ls_abort_cmp;
-	abts_wqeq->iocb_cmpl = 0;
+	abts_wqeq->iocb_cmpl = NULL;
 	abts_wqeq->iocb_flag |=  LPFC_IO_NVME_LS;
 	rc = lpfc_sli4_issue_wqe(phba, ctxp->hdwq, abts_wqeq);
 	spin_unlock_irqrestore(&phba->hbalock, flags);
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.h b/drivers/scsi/lpfc/lpfc_nvmet.h
index 8ff67deac10a..b80b1639b9a7 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.h
+++ b/drivers/scsi/lpfc/lpfc_nvmet.h
@@ -112,9 +112,7 @@ struct lpfc_nvmet_rcv_ctx {
 	struct lpfc_hba *phba;
 	struct lpfc_iocbq *wqeq;
 	struct lpfc_iocbq *abort_wqeq;
-	dma_addr_t txrdy_phys;
 	spinlock_t ctxlock; /* protect flag access */
-	uint32_t *txrdy;
 	uint32_t sid;
 	uint32_t offset;
 	uint16_t oxid;
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 6822cd9ff8f1..b138d9fee675 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -134,21 +134,21 @@ lpfc_sli4_set_rsp_sgl_last(struct lpfc_hba *phba,
 
 /**
  * lpfc_update_stats - Update statistical data for the command completion
- * @phba: Pointer to HBA object.
+ * @vport: The virtual port on which this call is executing.
  * @lpfc_cmd: lpfc scsi command object pointer.
  *
  * This function is called when there is a command completion and this
  * function updates the statistical data for the command completion.
  **/
 static void
-lpfc_update_stats(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd)
+lpfc_update_stats(struct lpfc_vport *vport, struct lpfc_io_buf *lpfc_cmd)
 {
+	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_rport_data *rdata;
 	struct lpfc_nodelist *pnode;
 	struct scsi_cmnd *cmd = lpfc_cmd->pCmd;
 	unsigned long flags;
-	struct Scsi_Host  *shost = cmd->device->host;
-	struct lpfc_vport *vport = (struct lpfc_vport *) shost->hostdata;
+	struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
 	unsigned long latency;
 	int i;
 
@@ -526,7 +526,7 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba,
 		&qp->lpfc_abts_io_buf_list, list) {
 		if (psb->cur_iocbq.sli4_xritag == xri) {
 			list_del_init(&psb->list);
-			psb->exch_busy = 0;
+			psb->flags &= ~LPFC_SBUF_XBUSY;
 			psb->status = IOSTAT_SUCCESS;
 			if (psb->cur_iocbq.iocb_flag == LPFC_IO_NVME) {
 				qp->abts_nvme_io_bufs--;
@@ -566,7 +566,7 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba,
 		if (iocbq->sli4_xritag != xri)
 			continue;
 		psb = container_of(iocbq, struct lpfc_io_buf, cur_iocbq);
-		psb->exch_busy = 0;
+		psb->flags &= ~LPFC_SBUF_XBUSY;
 		spin_unlock_irqrestore(&phba->hbalock, iflag);
 		if (!list_empty(&pring->txq))
 			lpfc_worker_wake_up(phba);
@@ -786,7 +786,7 @@ lpfc_release_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *psb)
 	psb->prot_seg_cnt = 0;
 
 	qp = psb->hdwq;
-	if (psb->exch_busy) {
+	if (psb->flags & LPFC_SBUF_XBUSY) {
 		spin_lock_irqsave(&qp->abts_io_buf_list_lock, iflag);
 		psb->pCmd = NULL;
 		list_add_tail(&psb->list, &qp->lpfc_abts_io_buf_list);
@@ -3812,7 +3812,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 
 	/* Sanity check on return of outstanding command */
 	cmd = lpfc_cmd->pCmd;
-	if (!cmd) {
+	if (!cmd || !phba) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
 				 "2621 IO completion: Not an active IO\n");
 		spin_unlock(&lpfc_cmd->buf_lock);
@@ -3824,7 +3824,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 		phba->sli4_hba.hdwq[idx].scsi_cstat.io_cmpls++;
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	if (phba->cpucheck_on & LPFC_CHECK_SCSI_IO) {
+	if (unlikely(phba->cpucheck_on & LPFC_CHECK_SCSI_IO)) {
 		cpu = raw_smp_processor_id();
 		if (cpu < LPFC_CHECK_CPU_CNT && phba->sli4_hba.hdwq)
 			phba->sli4_hba.hdwq[idx].cpucheck_cmpl_io[cpu]++;
@@ -3835,7 +3835,10 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 	lpfc_cmd->result = (pIocbOut->iocb.un.ulpWord[4] & IOERR_PARAM_MASK);
 	lpfc_cmd->status = pIocbOut->iocb.ulpStatus;
 	/* pick up SLI4 exhange busy status from HBA */
-	lpfc_cmd->exch_busy = pIocbOut->iocb_flag & LPFC_EXCHANGE_BUSY;
+	if (pIocbOut->iocb_flag & LPFC_EXCHANGE_BUSY)
+		lpfc_cmd->flags |= LPFC_SBUF_XBUSY;
+	else
+		lpfc_cmd->flags &= ~LPFC_SBUF_XBUSY;
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	if (lpfc_cmd->prot_data_type) {
@@ -3869,7 +3872,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 	}
 #endif
 
-	if (lpfc_cmd->status) {
+	if (unlikely(lpfc_cmd->status)) {
 		if (lpfc_cmd->status == IOSTAT_LOCAL_REJECT &&
 		    (lpfc_cmd->result & IOERR_DRVR_MASK))
 			lpfc_cmd->status = IOSTAT_DRIVER_REJECT;
@@ -4002,7 +4005,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 				 scsi_get_resid(cmd));
 	}
 
-	lpfc_update_stats(phba, lpfc_cmd);
+	lpfc_update_stats(vport, lpfc_cmd);
 	if (vport->cfg_max_scsicmpl_time &&
 	   time_after(jiffies, lpfc_cmd->start_time +
 		msecs_to_jiffies(vport->cfg_max_scsicmpl_time))) {
@@ -4610,17 +4613,18 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 		err = lpfc_scsi_prep_dma_buf(phba, lpfc_cmd);
 	}
 
-	if (err == 2) {
-		cmnd->result = DID_ERROR << 16;
-		goto out_fail_command_release_buf;
-	} else if (err) {
+	if (unlikely(err)) {
+		if (err == 2) {
+			cmnd->result = DID_ERROR << 16;
+			goto out_fail_command_release_buf;
+		}
 		goto out_host_busy_free_buf;
 	}
 
 	lpfc_scsi_prep_cmnd(vport, lpfc_cmd, ndlp);
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	if (phba->cpucheck_on & LPFC_CHECK_SCSI_IO) {
+	if (unlikely(phba->cpucheck_on & LPFC_CHECK_SCSI_IO)) {
 		cpu = raw_smp_processor_id();
 		if (cpu < LPFC_CHECK_CPU_CNT) {
 			struct lpfc_sli4_hdw_queue *hdwq =
@@ -4843,20 +4847,21 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 		ret_val = __lpfc_sli_issue_iocb(phba, LPFC_FCP_RING,
 						abtsiocb, 0);
 	}
-	/* no longer need the lock after this point */
-	spin_unlock_irqrestore(&phba->hbalock, flags);
 
 	if (ret_val == IOCB_ERROR) {
 		/* Indicate the IO is not being aborted by the driver. */
 		iocb->iocb_flag &= ~LPFC_DRIVER_ABORTED;
 		lpfc_cmd->waitq = NULL;
 		spin_unlock(&lpfc_cmd->buf_lock);
+		spin_unlock_irqrestore(&phba->hbalock, flags);
 		lpfc_sli_release_iocbq(phba, abtsiocb);
 		ret = FAILED;
 		goto out;
 	}
 
+	/* no longer need the lock after this point */
 	spin_unlock(&lpfc_cmd->buf_lock);
+	spin_unlock_irqrestore(&phba->hbalock, flags);
 
 	if (phba->cfg_poll & DISABLE_FCP_RING_INT)
 		lpfc_sli_handle_fast_ring_event(phba,
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 614f78dddafe..c82b5792da98 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -87,6 +87,10 @@ static void lpfc_sli4_hba_handle_eqe(struct lpfc_hba *phba,
 				     struct lpfc_eqe *eqe);
 static bool lpfc_sli4_mbox_completions_pending(struct lpfc_hba *phba);
 static bool lpfc_sli4_process_missed_mbox_completions(struct lpfc_hba *phba);
+static struct lpfc_cqe *lpfc_sli4_cq_get(struct lpfc_queue *q);
+static void __lpfc_sli4_consume_cqe(struct lpfc_hba *phba,
+				    struct lpfc_queue *cq,
+				    struct lpfc_cqe *cqe);
 
 static IOCB_t *
 lpfc_get_iocb_from_iocbq(struct lpfc_iocbq *iocbq)
@@ -467,25 +471,52 @@ __lpfc_sli4_consume_eqe(struct lpfc_hba *phba, struct lpfc_queue *eq,
 }
 
 static void
-lpfc_sli4_eq_flush(struct lpfc_hba *phba, struct lpfc_queue *eq)
+lpfc_sli4_eqcq_flush(struct lpfc_hba *phba, struct lpfc_queue *eq)
 {
-	struct lpfc_eqe *eqe;
-	uint32_t count = 0;
+	struct lpfc_eqe *eqe = NULL;
+	u32 eq_count = 0, cq_count = 0;
+	struct lpfc_cqe *cqe = NULL;
+	struct lpfc_queue *cq = NULL, *childq = NULL;
+	int cqid = 0;
 
 	/* walk all the EQ entries and drop on the floor */
 	eqe = lpfc_sli4_eq_get(eq);
 	while (eqe) {
+		/* Get the reference to the corresponding CQ */
+		cqid = bf_get_le32(lpfc_eqe_resource_id, eqe);
+		cq = NULL;
+
+		list_for_each_entry(childq, &eq->child_list, list) {
+			if (childq->queue_id == cqid) {
+				cq = childq;
+				break;
+			}
+		}
+		/* If CQ is valid, iterate through it and drop all the CQEs */
+		if (cq) {
+			cqe = lpfc_sli4_cq_get(cq);
+			while (cqe) {
+				__lpfc_sli4_consume_cqe(phba, cq, cqe);
+				cq_count++;
+				cqe = lpfc_sli4_cq_get(cq);
+			}
+			/* Clear and re-arm the CQ */
+			phba->sli4_hba.sli4_write_cq_db(phba, cq, cq_count,
+			    LPFC_QUEUE_REARM);
+			cq_count = 0;
+		}
 		__lpfc_sli4_consume_eqe(phba, eq, eqe);
-		count++;
+		eq_count++;
 		eqe = lpfc_sli4_eq_get(eq);
 	}
 
 	/* Clear and re-arm the EQ */
-	phba->sli4_hba.sli4_write_eq_db(phba, eq, count, LPFC_QUEUE_REARM);
+	phba->sli4_hba.sli4_write_eq_db(phba, eq, eq_count, LPFC_QUEUE_REARM);
 }
 
 static int
-lpfc_sli4_process_eq(struct lpfc_hba *phba, struct lpfc_queue *eq)
+lpfc_sli4_process_eq(struct lpfc_hba *phba, struct lpfc_queue *eq,
+		     uint8_t rearm)
 {
 	struct lpfc_eqe *eqe;
 	int count = 0, consumed = 0;
@@ -519,8 +550,8 @@ lpfc_sli4_process_eq(struct lpfc_hba *phba, struct lpfc_queue *eq)
 	eq->queue_claimed = 0;
 
 rearm_and_exit:
-	/* Always clear and re-arm the EQ */
-	phba->sli4_hba.sli4_write_eq_db(phba, eq, consumed, LPFC_QUEUE_REARM);
+	/* Always clear the EQ. */
+	phba->sli4_hba.sli4_write_eq_db(phba, eq, consumed, rearm);
 
 	return count;
 }
@@ -2526,6 +2557,8 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 			} else {
 				__lpfc_sli_rpi_release(vport, ndlp);
 			}
+			if (vport->load_flag & FC_UNLOADING)
+				lpfc_nlp_put(ndlp);
 			pmb->ctx_ndlp = NULL;
 		}
 	}
@@ -2672,7 +2705,8 @@ lpfc_sli_handle_mb_event(struct lpfc_hba *phba)
 			lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
 					"(%d):0323 Unknown Mailbox command "
 					"x%x (x%x/x%x) Cmpl\n",
-					pmb->vport ? pmb->vport->vpi : 0,
+					pmb->vport ? pmb->vport->vpi :
+					LPFC_VPORT_UNKNOWN,
 					pmbox->mbxCommand,
 					lpfc_sli_config_mbox_subsys_get(phba,
 									pmb),
@@ -2693,7 +2727,8 @@ lpfc_sli_handle_mb_event(struct lpfc_hba *phba)
 					"(%d):0305 Mbox cmd cmpl "
 					"error - RETRYing Data: x%x "
 					"(x%x/x%x) x%x x%x x%x\n",
-					pmb->vport ? pmb->vport->vpi : 0,
+					pmb->vport ? pmb->vport->vpi :
+					LPFC_VPORT_UNKNOWN,
 					pmbox->mbxCommand,
 					lpfc_sli_config_mbox_subsys_get(phba,
 									pmb),
@@ -2701,7 +2736,8 @@ lpfc_sli_handle_mb_event(struct lpfc_hba *phba)
 									pmb),
 					pmbox->mbxStatus,
 					pmbox->un.varWords[0],
-					pmb->vport->port_state);
+					pmb->vport ? pmb->vport->port_state :
+					LPFC_VPORT_UNKNOWN);
 				pmbox->mbxStatus = 0;
 				pmbox->mbxOwner = OWN_HOST;
 				rc = lpfc_sli_issue_mbox(phba, pmb, MBX_NOWAIT);
@@ -6167,6 +6203,14 @@ lpfc_set_features(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox,
 		mbox->u.mqe.un.set_feature.feature = LPFC_SET_MDS_DIAGS;
 		mbox->u.mqe.un.set_feature.param_len = 8;
 		break;
+	case LPFC_SET_DUAL_DUMP:
+		bf_set(lpfc_mbx_set_feature_dd,
+		       &mbox->u.mqe.un.set_feature, LPFC_ENABLE_DUAL_DUMP);
+		bf_set(lpfc_mbx_set_feature_ddquery,
+		       &mbox->u.mqe.un.set_feature, 0);
+		mbox->u.mqe.un.set_feature.feature = LPFC_SET_DUAL_DUMP;
+		mbox->u.mqe.un.set_feature.param_len = 4;
+		break;
 	}
 
 	return;
@@ -6184,11 +6228,16 @@ lpfc_ras_stop_fwlog(struct lpfc_hba *phba)
 {
 	struct lpfc_ras_fwlog *ras_fwlog = &phba->ras_fwlog;
 
-	ras_fwlog->ras_active = false;
+	spin_lock_irq(&phba->hbalock);
+	ras_fwlog->state = INACTIVE;
+	spin_unlock_irq(&phba->hbalock);
 
 	/* Disable FW logging to host memory */
 	writel(LPFC_CTL_PDEV_CTL_DDL_RAS,
 	       phba->sli4_hba.conf_regs_memmap_p + LPFC_CTL_PDEV_CTL_OFFSET);
+
+	/* Wait 10ms for firmware to stop using DMA buffer */
+	usleep_range(10 * 1000, 20 * 1000);
 }
 
 /**
@@ -6224,7 +6273,9 @@ lpfc_sli4_ras_dma_free(struct lpfc_hba *phba)
 		ras_fwlog->lwpd.virt = NULL;
 	}
 
-	ras_fwlog->ras_active = false;
+	spin_lock_irq(&phba->hbalock);
+	ras_fwlog->state = INACTIVE;
+	spin_unlock_irq(&phba->hbalock);
 }
 
 /**
@@ -6326,7 +6377,9 @@ lpfc_sli4_ras_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		goto disable_ras;
 	}
 
-	ras_fwlog->ras_active = true;
+	spin_lock_irq(&phba->hbalock);
+	ras_fwlog->state = ACTIVE;
+	spin_unlock_irq(&phba->hbalock);
 	mempool_free(pmb, phba->mbox_mem_pool);
 
 	return;
@@ -6358,6 +6411,10 @@ lpfc_sli4_ras_fwlog_init(struct lpfc_hba *phba,
 	uint32_t len = 0, fwlog_buffsize, fwlog_entry_count;
 	int rc = 0;
 
+	spin_lock_irq(&phba->hbalock);
+	ras_fwlog->state = INACTIVE;
+	spin_unlock_irq(&phba->hbalock);
+
 	fwlog_buffsize = (LPFC_RAS_MIN_BUFF_POST_SIZE *
 			  phba->cfg_ras_fwlog_buffsize);
 	fwlog_entry_count = (fwlog_buffsize/LPFC_RAS_MAX_ENTRY_SIZE);
@@ -6417,6 +6474,9 @@ lpfc_sli4_ras_fwlog_init(struct lpfc_hba *phba,
 	mbx_fwlog->u.request.lwpd.addr_lo = putPaddrLow(ras_fwlog->lwpd.phys);
 	mbx_fwlog->u.request.lwpd.addr_hi = putPaddrHigh(ras_fwlog->lwpd.phys);
 
+	spin_lock_irq(&phba->hbalock);
+	ras_fwlog->state = REG_INPROGRESS;
+	spin_unlock_irq(&phba->hbalock);
 	mbox->vport = phba->pport;
 	mbox->mbox_cmpl = lpfc_sli4_ras_mbox_cmpl;
 
@@ -7148,7 +7208,7 @@ lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 int
 lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 {
-	int rc, i, cnt, len;
+	int rc, i, cnt, len, dd;
 	LPFC_MBOXQ_t *mboxq;
 	struct lpfc_mqe *mqe;
 	uint8_t *vpd;
@@ -7399,6 +7459,23 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 	phba->sli3_options |= (LPFC_SLI3_NPIV_ENABLED | LPFC_SLI3_HBQ_ENABLED);
 	spin_unlock_irq(&phba->hbalock);
 
+	/* Always try to enable dual dump feature if we can */
+	lpfc_set_features(phba, mboxq, LPFC_SET_DUAL_DUMP);
+	rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
+	dd = bf_get(lpfc_mbx_set_feature_dd, &mboxq->u.mqe.un.set_feature);
+	if ((rc == MBX_SUCCESS) && (dd == LPFC_ENABLE_DUAL_DUMP))
+		lpfc_printf_log(phba, KERN_ERR, LOG_SLI | LOG_INIT,
+				"6448 Dual Dump is enabled\n");
+	else
+		lpfc_printf_log(phba, KERN_INFO, LOG_SLI | LOG_INIT,
+				"6447 Dual Dump Mailbox x%x (x%x/x%x) failed, "
+				"rc:x%x dd:x%x\n",
+				bf_get(lpfc_mqe_command, &mboxq->u.mqe),
+				lpfc_sli_config_mbox_subsys_get(
+					phba, mboxq),
+				lpfc_sli_config_mbox_opcode_get(
+					phba, mboxq),
+				rc, dd);
 	/*
 	 * Allocate all resources (xri,rpi,vpi,vfi) now.  Subsequent
 	 * calls depends on these resources to complete port setup.
@@ -7523,9 +7600,11 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 		}
 		phba->sli4_hba.nvmet_xri_cnt = rc;
 
-		cnt = phba->cfg_iocb_cnt * 1024;
-		/* We need 1 iocbq for every SGL, for IO processing */
-		cnt += phba->sli4_hba.nvmet_xri_cnt;
+		/* We allocate an iocbq for every receive context SGL.
+		 * The additional allocation is for abort and ls handling.
+		 */
+		cnt = phba->sli4_hba.nvmet_xri_cnt +
+			phba->sli4_hba.max_cfg_param.max_xri;
 	} else {
 		/* update host common xri-sgl sizes and mappings */
 		rc = lpfc_sli4_io_sgl_update(phba);
@@ -7547,14 +7626,17 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 			rc = -ENODEV;
 			goto out_destroy_queue;
 		}
-		cnt = phba->cfg_iocb_cnt * 1024;
+		/* Each lpfc_io_buf job structure has an iocbq element.
+		 * This cnt provides for abort, els, ct and ls requests.
+		 */
+		cnt = phba->sli4_hba.max_cfg_param.max_xri;
 	}
 
 	if (!phba->sli.iocbq_lookup) {
 		/* Initialize and populate the iocb list per host */
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-				"2821 initialize iocb list %d total %d\n",
-				phba->cfg_iocb_cnt, cnt);
+				"2821 initialize iocb list with %d entries\n",
+				cnt);
 		rc = lpfc_init_iocb_list(phba, cnt);
 		if (rc) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
@@ -7892,7 +7974,7 @@ lpfc_sli4_process_missed_mbox_completions(struct lpfc_hba *phba)
 
 	if (mbox_pending)
 		/* process and rearm the EQ */
-		lpfc_sli4_process_eq(phba, fpeq);
+		lpfc_sli4_process_eq(phba, fpeq, LPFC_QUEUE_REARM);
 	else
 		/* Always clear and re-arm the EQ */
 		sli4_hba->sli4_write_eq_db(phba, fpeq, 0, LPFC_QUEUE_REARM);
@@ -8964,7 +9046,8 @@ lpfc_mbox_api_table_setup(struct lpfc_hba *phba, uint8_t dev_grp)
  * @pring: Pointer to driver SLI ring object.
  * @piocb: Pointer to address of newly added command iocb.
  *
- * This function is called with hbalock held to add a command
+ * This function is called with hbalock held for SLI3 ports or
+ * the ring lock held for SLI4 ports to add a command
  * iocb to the txq when SLI layer cannot submit the command iocb
  * to the ring.
  **/
@@ -8972,7 +9055,10 @@ void
 __lpfc_sli_ringtx_put(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		    struct lpfc_iocbq *piocb)
 {
-	lockdep_assert_held(&phba->hbalock);
+	if (phba->sli_rev == LPFC_SLI_REV4)
+		lockdep_assert_held(&pring->ring_lock);
+	else
+		lockdep_assert_held(&phba->hbalock);
 	/* Insert the caller's iocb in the txq tail for later processing. */
 	list_add_tail(&piocb->list, &pring->txq);
 }
@@ -9863,7 +9949,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
  * __lpfc_sli_issue_iocb_s4 is used by other functions in the driver to issue
  * an iocb command to an HBA with SLI-4 interface spec.
  *
- * This function is called with hbalock held. The function will return success
+ * This function is called with ringlock held. The function will return success
  * after it successfully submit the iocb to firmware or after adding to the
  * txq.
  **/
@@ -10053,10 +10139,13 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number,
 		    struct lpfc_iocbq *piocb, uint32_t flag)
 {
 	struct lpfc_sli_ring *pring;
+	struct lpfc_queue *eq;
 	unsigned long iflags;
 	int rc;
 
 	if (phba->sli_rev == LPFC_SLI_REV4) {
+		eq = phba->sli4_hba.hdwq[piocb->hba_wqidx].hba_eq;
+
 		pring = lpfc_sli4_calc_ring(phba, piocb);
 		if (unlikely(pring == NULL))
 			return IOCB_ERROR;
@@ -10064,6 +10153,8 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number,
 		spin_lock_irqsave(&pring->ring_lock, iflags);
 		rc = __lpfc_sli_issue_iocb(phba, ring_number, piocb, flag);
 		spin_unlock_irqrestore(&pring->ring_lock, iflags);
+
+		lpfc_sli4_poll_eq(eq, LPFC_POLL_FASTPATH);
 	} else {
 		/* For now, SLI2/3 will still use hbalock */
 		spin_lock_irqsave(&phba->hbalock, iflags);
@@ -10678,14 +10769,14 @@ lpfc_sli_host_down(struct lpfc_vport *vport)
 				set_bit(LPFC_DATA_READY, &phba->data_flags);
 			}
 			prev_pring_flag = pring->flag;
-			spin_lock_irq(&pring->ring_lock);
+			spin_lock(&pring->ring_lock);
 			list_for_each_entry_safe(iocb, next_iocb,
 						 &pring->txq, list) {
 				if (iocb->vport != vport)
 					continue;
 				list_move_tail(&iocb->list, &completions);
 			}
-			spin_unlock_irq(&pring->ring_lock);
+			spin_unlock(&pring->ring_lock);
 			list_for_each_entry_safe(iocb, next_iocb,
 						 &pring->txcmplq, list) {
 				if (iocb->vport != vport)
@@ -11050,9 +11141,6 @@ lpfc_sli_abort_els_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 				irsp->ulpStatus, irsp->un.ulpWord[4]);
 
 		spin_unlock_irq(&phba->hbalock);
-		if (irsp->ulpStatus == IOSTAT_LOCAL_REJECT &&
-		    irsp->un.ulpWord[4] == IOERR_SLI_ABORTED)
-			lpfc_sli_release_iocbq(phba, abort_iocb);
 	}
 release_iocb:
 	lpfc_sli_release_iocbq(phba, cmdiocb);
@@ -11736,7 +11824,10 @@ lpfc_sli_wake_iocb_wait(struct lpfc_hba *phba,
 		!(cmdiocbq->iocb_flag & LPFC_IO_LIBDFC)) {
 		lpfc_cmd = container_of(cmdiocbq, struct lpfc_io_buf,
 			cur_iocbq);
-		lpfc_cmd->exch_busy = rspiocbq->iocb_flag & LPFC_EXCHANGE_BUSY;
+		if (rspiocbq && (rspiocbq->iocb_flag & LPFC_EXCHANGE_BUSY))
+			lpfc_cmd->flags |= LPFC_SBUF_XBUSY;
+		else
+			lpfc_cmd->flags &= ~LPFC_SBUF_XBUSY;
 	}
 
 	pdone_q = cmdiocbq->context_un.wait_queue;
@@ -13158,13 +13249,19 @@ send_current_mbox:
 	phba->sli.sli_flag &= ~LPFC_SLI_MBOX_ACTIVE;
 	/* Setting active mailbox pointer need to be in sync to flag clear */
 	phba->sli.mbox_active = NULL;
+	if (bf_get(lpfc_trailer_consumed, mcqe))
+		lpfc_sli4_mq_release(phba->sli4_hba.mbx_wq);
 	spin_unlock_irqrestore(&phba->hbalock, iflags);
 	/* Wake up worker thread to post the next pending mailbox command */
 	lpfc_worker_wake_up(phba);
+	return workposted;
+
 out_no_mqe_complete:
+	spin_lock_irqsave(&phba->hbalock, iflags);
 	if (bf_get(lpfc_trailer_consumed, mcqe))
 		lpfc_sli4_mq_release(phba->sli4_hba.mbx_wq);
-	return workposted;
+	spin_unlock_irqrestore(&phba->hbalock, iflags);
+	return false;
 }
 
 /**
@@ -13217,7 +13314,6 @@ lpfc_sli4_sp_handle_els_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	struct lpfc_sli_ring *pring = cq->pring;
 	int txq_cnt = 0;
 	int txcmplq_cnt = 0;
-	int fcp_txcmplq_cnt = 0;
 
 	/* Check for response status */
 	if (unlikely(bf_get(lpfc_wcqe_c_status, wcqe))) {
@@ -13239,9 +13335,8 @@ lpfc_sli4_sp_handle_els_wcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 			txcmplq_cnt++;
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
 			"0387 NO IOCBQ data: txq_cnt=%d iocb_cnt=%d "
-			"fcp_txcmplq_cnt=%d, els_txcmplq_cnt=%d\n",
+			"els_txcmplq_cnt=%d\n",
 			txq_cnt, phba->iocb_cnt,
-			fcp_txcmplq_cnt,
 			txcmplq_cnt);
 		return false;
 	}
@@ -13592,6 +13687,7 @@ __lpfc_sli4_process_cq(struct lpfc_hba *phba, struct lpfc_queue *cq,
 			phba->sli4_hba.sli4_write_cq_db(phba, cq, consumed,
 						LPFC_QUEUE_NOARM);
 			consumed = 0;
+			cq->assoc_qp->q_flag |= HBA_EQ_DELAY_CHK;
 		}
 
 		if (count == LPFC_NVMET_CQ_NOTIFY)
@@ -14220,7 +14316,7 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 		spin_lock_irqsave(&phba->hbalock, iflag);
 		if (phba->link_state < LPFC_LINK_DOWN)
 			/* Flush, clear interrupt, and rearm the EQ */
-			lpfc_sli4_eq_flush(phba, fpeq);
+			lpfc_sli4_eqcq_flush(phba, fpeq);
 		spin_unlock_irqrestore(&phba->hbalock, iflag);
 		return IRQ_NONE;
 	}
@@ -14230,14 +14326,14 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 	fpeq->last_cpu = raw_smp_processor_id();
 
 	if (icnt > LPFC_EQD_ISR_TRIGGER &&
-	    phba->cfg_irq_chann == 1 &&
+	    fpeq->q_flag & HBA_EQ_DELAY_CHK &&
 	    phba->cfg_auto_imax &&
 	    fpeq->q_mode != LPFC_MAX_AUTO_EQ_DELAY &&
 	    phba->sli.sli_flag & LPFC_SLI_USE_EQDR)
 		lpfc_sli4_mod_hba_eq_delay(phba, fpeq, LPFC_MAX_AUTO_EQ_DELAY);
 
 	/* process and rearm the EQ */
-	ecount = lpfc_sli4_process_eq(phba, fpeq);
+	ecount = lpfc_sli4_process_eq(phba, fpeq, LPFC_QUEUE_REARM);
 
 	if (unlikely(ecount == 0)) {
 		fpeq->EQ_no_entry++;
@@ -14297,6 +14393,147 @@ lpfc_sli4_intr_handler(int irq, void *dev_id)
 	return (hba_handled == true) ? IRQ_HANDLED : IRQ_NONE;
 } /* lpfc_sli4_intr_handler */
 
+void lpfc_sli4_poll_hbtimer(struct timer_list *t)
+{
+	struct lpfc_hba *phba = from_timer(phba, t, cpuhp_poll_timer);
+	struct lpfc_queue *eq;
+	int i = 0;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(eq, &phba->poll_list, _poll_list)
+		i += lpfc_sli4_poll_eq(eq, LPFC_POLL_SLOWPATH);
+	if (!list_empty(&phba->poll_list))
+		mod_timer(&phba->cpuhp_poll_timer,
+			  jiffies + msecs_to_jiffies(LPFC_POLL_HB));
+
+	rcu_read_unlock();
+}
+
+inline int lpfc_sli4_poll_eq(struct lpfc_queue *eq, uint8_t path)
+{
+	struct lpfc_hba *phba = eq->phba;
+	int i = 0;
+
+	/*
+	 * Unlocking an irq is one of the entry point to check
+	 * for re-schedule, but we are good for io submission
+	 * path as midlayer does a get_cpu to glue us in. Flush
+	 * out the invalidate queue so we can see the updated
+	 * value for flag.
+	 */
+	smp_rmb();
+
+	if (READ_ONCE(eq->mode) == LPFC_EQ_POLL)
+		/* We will not likely get the completion for the caller
+		 * during this iteration but i guess that's fine.
+		 * Future io's coming on this eq should be able to
+		 * pick it up.  As for the case of single io's, they
+		 * will be handled through a sched from polling timer
+		 * function which is currently triggered every 1msec.
+		 */
+		i = lpfc_sli4_process_eq(phba, eq, LPFC_QUEUE_NOARM);
+
+	return i;
+}
+
+static inline void lpfc_sli4_add_to_poll_list(struct lpfc_queue *eq)
+{
+	struct lpfc_hba *phba = eq->phba;
+
+	if (list_empty(&phba->poll_list)) {
+		timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0);
+		/* kickstart slowpath processing for this eq */
+		mod_timer(&phba->cpuhp_poll_timer,
+			  jiffies + msecs_to_jiffies(LPFC_POLL_HB));
+	}
+
+	list_add_rcu(&eq->_poll_list, &phba->poll_list);
+	synchronize_rcu();
+}
+
+static inline void lpfc_sli4_remove_from_poll_list(struct lpfc_queue *eq)
+{
+	struct lpfc_hba *phba = eq->phba;
+
+	/* Disable slowpath processing for this eq.  Kick start the eq
+	 * by RE-ARMING the eq's ASAP
+	 */
+	list_del_rcu(&eq->_poll_list);
+	synchronize_rcu();
+
+	if (list_empty(&phba->poll_list))
+		del_timer_sync(&phba->cpuhp_poll_timer);
+}
+
+void lpfc_sli4_cleanup_poll_list(struct lpfc_hba *phba)
+{
+	struct lpfc_queue *eq, *next;
+
+	list_for_each_entry_safe(eq, next, &phba->poll_list, _poll_list)
+		list_del(&eq->_poll_list);
+
+	INIT_LIST_HEAD(&phba->poll_list);
+	synchronize_rcu();
+}
+
+static inline void
+__lpfc_sli4_switch_eqmode(struct lpfc_queue *eq, uint8_t mode)
+{
+	if (mode == eq->mode)
+		return;
+	/*
+	 * currently this function is only called during a hotplug
+	 * event and the cpu on which this function is executing
+	 * is going offline.  By now the hotplug has instructed
+	 * the scheduler to remove this cpu from cpu active mask.
+	 * So we don't need to work about being put aside by the
+	 * scheduler for a high priority process.  Yes, the inte-
+	 * rrupts could come but they are known to retire ASAP.
+	 */
+
+	/* Disable polling in the fastpath */
+	WRITE_ONCE(eq->mode, mode);
+	/* flush out the store buffer */
+	smp_wmb();
+
+	/*
+	 * Add this eq to the polling list and start polling. For
+	 * a grace period both interrupt handler and poller will
+	 * try to process the eq _but_ that's fine.  We have a
+	 * synchronization mechanism in place (queue_claimed) to
+	 * deal with it.  This is just a draining phase for int-
+	 * errupt handler (not eq's) as we have guranteed through
+	 * barrier that all the CPUs have seen the new CQ_POLLED
+	 * state. which will effectively disable the REARMING of
+	 * the EQ.  The whole idea is eq's die off eventually as
+	 * we are not rearming EQ's anymore.
+	 */
+	mode ? lpfc_sli4_add_to_poll_list(eq) :
+	       lpfc_sli4_remove_from_poll_list(eq);
+}
+
+void lpfc_sli4_start_polling(struct lpfc_queue *eq)
+{
+	__lpfc_sli4_switch_eqmode(eq, LPFC_EQ_POLL);
+}
+
+void lpfc_sli4_stop_polling(struct lpfc_queue *eq)
+{
+	struct lpfc_hba *phba = eq->phba;
+
+	__lpfc_sli4_switch_eqmode(eq, LPFC_EQ_INTERRUPT);
+
+	/* Kick start for the pending io's in h/w.
+	 * Once we switch back to interrupt processing on a eq
+	 * the io path completion will only arm eq's when it
+	 * receives a completion.  But since eq's are in disa-
+	 * rmed state it doesn't receive a completion.  This
+	 * creates a deadlock scenaro.
+	 */
+	phba->sli4_hba.sli4_write_eq_db(phba, eq, 0, LPFC_QUEUE_REARM);
+}
+
 /**
  * lpfc_sli4_queue_free - free a queue structure and associated memory
  * @queue: The queue structure to free.
@@ -14371,6 +14608,7 @@ lpfc_sli4_queue_alloc(struct lpfc_hba *phba, uint32_t page_size,
 		return NULL;
 
 	INIT_LIST_HEAD(&queue->list);
+	INIT_LIST_HEAD(&queue->_poll_list);
 	INIT_LIST_HEAD(&queue->wq_list);
 	INIT_LIST_HEAD(&queue->wqfull_list);
 	INIT_LIST_HEAD(&queue->page_list);
@@ -18124,8 +18362,9 @@ lpfc_sli4_alloc_rpi(struct lpfc_hba *phba)
 		phba->sli4_hba.max_cfg_param.rpi_used++;
 		phba->sli4_hba.rpi_count++;
 	}
-	lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
-			"0001 rpi:%x max:%x lim:%x\n",
+	lpfc_printf_log(phba, KERN_INFO,
+			LOG_NODE | LOG_DISCOVERY,
+			"0001 Allocated rpi:x%x max:x%x lim:x%x\n",
 			(int) rpi, max_rpi, rpi_limit);
 
 	/*
@@ -18181,11 +18420,19 @@ lpfc_sli4_alloc_rpi(struct lpfc_hba *phba)
 static void
 __lpfc_sli4_free_rpi(struct lpfc_hba *phba, int rpi)
 {
+	/*
+	 * if the rpi value indicates a prior unreg has already
+	 * been done, skip the unreg.
+	 */
+	if (rpi == LPFC_RPI_ALLOC_ERROR)
+		return;
+
 	if (test_and_clear_bit(rpi, phba->sli4_hba.rpi_bmask)) {
 		phba->sli4_hba.rpi_count--;
 		phba->sli4_hba.max_cfg_param.rpi_used--;
 	} else {
-		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
+		lpfc_printf_log(phba, KERN_INFO,
+				LOG_NODE | LOG_DISCOVERY,
 				"2016 rpi %x not inuse\n",
 				rpi);
 	}
@@ -19683,6 +19930,8 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, struct lpfc_sli4_hdw_queue *qp,
 
 		lpfc_sli_ringtxcmpl_put(phba, pring, pwqe);
 		spin_unlock_irqrestore(&pring->ring_lock, iflags);
+
+		lpfc_sli4_poll_eq(qp->hba_eq, LPFC_POLL_FASTPATH);
 		return 0;
 	}
 
@@ -19703,6 +19952,8 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, struct lpfc_sli4_hdw_queue *qp,
 		}
 		lpfc_sli_ringtxcmpl_put(phba, pring, pwqe);
 		spin_unlock_irqrestore(&pring->ring_lock, iflags);
+
+		lpfc_sli4_poll_eq(qp->hba_eq, LPFC_POLL_FASTPATH);
 		return 0;
 	}
 
@@ -19731,6 +19982,8 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, struct lpfc_sli4_hdw_queue *qp,
 		}
 		lpfc_sli_ringtxcmpl_put(phba, pring, pwqe);
 		spin_unlock_irqrestore(&pring->ring_lock, iflags);
+
+		lpfc_sli4_poll_eq(qp->hba_eq, LPFC_POLL_FASTPATH);
 		return 0;
 	}
 	return WQE_ERROR;
@@ -20093,6 +20346,13 @@ void lpfc_release_io_buf(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_ncmd,
 	lpfc_ncmd->cur_iocbq.wqe_cmpl = NULL;
 	lpfc_ncmd->cur_iocbq.iocb_cmpl = NULL;
 
+	if (phba->cfg_xpsgl && !phba->nvmet_support &&
+	    !list_empty(&lpfc_ncmd->dma_sgl_xtra_list))
+		lpfc_put_sgl_per_hdwq(phba, lpfc_ncmd);
+
+	if (!list_empty(&lpfc_ncmd->dma_cmd_rsp_list))
+		lpfc_put_cmd_rsp_buf_per_hdwq(phba, lpfc_ncmd);
+
 	if (phba->cfg_xri_rebalancing) {
 		if (lpfc_ncmd->expedite) {
 			/* Return to expedite pool */
@@ -20157,13 +20417,6 @@ void lpfc_release_io_buf(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_ncmd,
 		spin_unlock_irqrestore(&qp->io_buf_list_put_lock,
 				       iflag);
 	}
-
-	if (phba->cfg_xpsgl && !phba->nvmet_support &&
-	    !list_empty(&lpfc_ncmd->dma_sgl_xtra_list))
-		lpfc_put_sgl_per_hdwq(phba, lpfc_ncmd);
-
-	if (!list_empty(&lpfc_ncmd->dma_cmd_rsp_list))
-		lpfc_put_cmd_rsp_buf_per_hdwq(phba, lpfc_ncmd);
 }
 
 /**
@@ -20399,8 +20652,9 @@ lpfc_get_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf)
 	struct sli4_hybrid_sgl *allocated_sgl = NULL;
 	struct lpfc_sli4_hdw_queue *hdwq = lpfc_buf->hdwq;
 	struct list_head *buf_list = &hdwq->sgl_list;
+	unsigned long iflags;
 
-	spin_lock_irq(&hdwq->hdwq_lock);
+	spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
 
 	if (likely(!list_empty(buf_list))) {
 		/* break off 1 chunk from the sgl_list */
@@ -20412,9 +20666,9 @@ lpfc_get_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf)
 		}
 	} else {
 		/* allocate more */
-		spin_unlock_irq(&hdwq->hdwq_lock);
+		spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
 		tmp = kmalloc_node(sizeof(*tmp), GFP_ATOMIC,
-				   cpu_to_node(smp_processor_id()));
+				   cpu_to_node(hdwq->io_wq->chann));
 		if (!tmp) {
 			lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
 					"8353 error kmalloc memory for HDWQ "
@@ -20434,7 +20688,7 @@ lpfc_get_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf)
 			return NULL;
 		}
 
-		spin_lock_irq(&hdwq->hdwq_lock);
+		spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
 		list_add_tail(&tmp->list_node, &lpfc_buf->dma_sgl_xtra_list);
 	}
 
@@ -20442,7 +20696,7 @@ lpfc_get_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf)
 					struct sli4_hybrid_sgl,
 					list_node);
 
-	spin_unlock_irq(&hdwq->hdwq_lock);
+	spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
 
 	return allocated_sgl;
 }
@@ -20466,8 +20720,9 @@ lpfc_put_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf)
 	struct sli4_hybrid_sgl *tmp = NULL;
 	struct lpfc_sli4_hdw_queue *hdwq = lpfc_buf->hdwq;
 	struct list_head *buf_list = &hdwq->sgl_list;
+	unsigned long iflags;
 
-	spin_lock_irq(&hdwq->hdwq_lock);
+	spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
 
 	if (likely(!list_empty(&lpfc_buf->dma_sgl_xtra_list))) {
 		list_for_each_entry_safe(list_entry, tmp,
@@ -20480,7 +20735,7 @@ lpfc_put_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf)
 		rc = -EINVAL;
 	}
 
-	spin_unlock_irq(&hdwq->hdwq_lock);
+	spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
 	return rc;
 }
 
@@ -20501,8 +20756,9 @@ lpfc_free_sgl_per_hdwq(struct lpfc_hba *phba,
 	struct list_head *buf_list = &hdwq->sgl_list;
 	struct sli4_hybrid_sgl *list_entry = NULL;
 	struct sli4_hybrid_sgl *tmp = NULL;
+	unsigned long iflags;
 
-	spin_lock_irq(&hdwq->hdwq_lock);
+	spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
 
 	/* Free sgl pool */
 	list_for_each_entry_safe(list_entry, tmp,
@@ -20514,7 +20770,7 @@ lpfc_free_sgl_per_hdwq(struct lpfc_hba *phba,
 		kfree(list_entry);
 	}
 
-	spin_unlock_irq(&hdwq->hdwq_lock);
+	spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
 }
 
 /**
@@ -20538,8 +20794,9 @@ lpfc_get_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
 	struct fcp_cmd_rsp_buf *allocated_buf = NULL;
 	struct lpfc_sli4_hdw_queue *hdwq = lpfc_buf->hdwq;
 	struct list_head *buf_list = &hdwq->cmd_rsp_buf_list;
+	unsigned long iflags;
 
-	spin_lock_irq(&hdwq->hdwq_lock);
+	spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
 
 	if (likely(!list_empty(buf_list))) {
 		/* break off 1 chunk from the list */
@@ -20552,9 +20809,9 @@ lpfc_get_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
 		}
 	} else {
 		/* allocate more */
-		spin_unlock_irq(&hdwq->hdwq_lock);
+		spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
 		tmp = kmalloc_node(sizeof(*tmp), GFP_ATOMIC,
-				   cpu_to_node(smp_processor_id()));
+				   cpu_to_node(hdwq->io_wq->chann));
 		if (!tmp) {
 			lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
 					"8355 error kmalloc memory for HDWQ "
@@ -20579,7 +20836,7 @@ lpfc_get_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
 		tmp->fcp_rsp = (struct fcp_rsp *)((uint8_t *)tmp->fcp_cmnd +
 				sizeof(struct fcp_cmnd));
 
-		spin_lock_irq(&hdwq->hdwq_lock);
+		spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
 		list_add_tail(&tmp->list_node, &lpfc_buf->dma_cmd_rsp_list);
 	}
 
@@ -20587,7 +20844,7 @@ lpfc_get_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
 					struct fcp_cmd_rsp_buf,
 					list_node);
 
-	spin_unlock_irq(&hdwq->hdwq_lock);
+	spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
 
 	return allocated_buf;
 }
@@ -20612,8 +20869,9 @@ lpfc_put_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
 	struct fcp_cmd_rsp_buf *tmp = NULL;
 	struct lpfc_sli4_hdw_queue *hdwq = lpfc_buf->hdwq;
 	struct list_head *buf_list = &hdwq->cmd_rsp_buf_list;
+	unsigned long iflags;
 
-	spin_lock_irq(&hdwq->hdwq_lock);
+	spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
 
 	if (likely(!list_empty(&lpfc_buf->dma_cmd_rsp_list))) {
 		list_for_each_entry_safe(list_entry, tmp,
@@ -20626,7 +20884,7 @@ lpfc_put_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
 		rc = -EINVAL;
 	}
 
-	spin_unlock_irq(&hdwq->hdwq_lock);
+	spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
 	return rc;
 }
 
@@ -20647,8 +20905,9 @@ lpfc_free_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
 	struct list_head *buf_list = &hdwq->cmd_rsp_buf_list;
 	struct fcp_cmd_rsp_buf *list_entry = NULL;
 	struct fcp_cmd_rsp_buf *tmp = NULL;
+	unsigned long iflags;
 
-	spin_lock_irq(&hdwq->hdwq_lock);
+	spin_lock_irqsave(&hdwq->hdwq_lock, iflags);
 
 	/* Free cmd_rsp buf pool */
 	list_for_each_entry_safe(list_entry, tmp,
@@ -20661,5 +20920,5 @@ lpfc_free_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
 		kfree(list_entry);
 	}
 
-	spin_unlock_irq(&hdwq->hdwq_lock);
+	spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
 }
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 37fbcb46387e..7bcf922a8be2 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -384,14 +384,13 @@ struct lpfc_io_buf {
 
 	struct lpfc_nodelist *ndlp;
 	uint32_t timeout;
-	uint16_t flags;  /* TBD convert exch_busy to flags */
+	uint16_t flags;
 #define LPFC_SBUF_XBUSY		0x1	/* SLI4 hba reported XB on WCQE cmpl */
 #define LPFC_SBUF_BUMP_QDEPTH	0x2	/* bumped queue depth counter */
 					/* External DIF device IO conversions */
 #define LPFC_SBUF_NORMAL_DIF	0x4	/* normal mode to insert/strip */
 #define LPFC_SBUF_PASS_DIF	0x8	/* insert/strip mode to passthru */
 #define LPFC_SBUF_NOT_POSTED    0x10    /* SGL failed post to FW. */
-	uint16_t exch_busy;     /* SLI4 hba reported XB on complete WCQE */
 	uint16_t status;	/* From IOCB Word 7- ulpStatus */
 	uint32_t result;	/* From IOCB Word 4. */
 
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 0d4882a9e634..d963ca871383 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -41,8 +41,13 @@
 
 /* Multi-queue arrangement for FCP EQ/CQ/WQ tuples */
 #define LPFC_HBA_HDWQ_MIN	0
-#define LPFC_HBA_HDWQ_MAX	128
-#define LPFC_HBA_HDWQ_DEF	0
+#define LPFC_HBA_HDWQ_MAX	256
+#define LPFC_HBA_HDWQ_DEF	LPFC_HBA_HDWQ_MIN
+
+/* irq_chann range, values */
+#define LPFC_IRQ_CHANN_MIN	0
+#define LPFC_IRQ_CHANN_MAX	256
+#define LPFC_IRQ_CHANN_DEF	LPFC_IRQ_CHANN_MIN
 
 /* FCP MQ queue count limiting */
 #define LPFC_FCP_MQ_THRESHOLD_MIN	0
@@ -133,6 +138,23 @@ struct lpfc_rqb {
 struct lpfc_queue {
 	struct list_head list;
 	struct list_head wq_list;
+
+	/*
+	 * If interrupts are in effect on _all_ the eq's the footprint
+	 * of polling code is zero (except mode). This memory is chec-
+	 * ked for every io to see if the io needs to be polled and
+	 * while completion to check if the eq's needs to be rearmed.
+	 * Keep in same cacheline as the queue ptr to avoid cpu fetch
+	 * stalls. Using 1B memory will leave us with 7B hole. Fill
+	 * it with other frequently used members.
+	 */
+	uint16_t last_cpu;	/* most recent cpu */
+	uint16_t hdwq;
+	uint8_t	 qe_valid;
+	uint8_t  mode;	/* interrupt or polling */
+#define LPFC_EQ_INTERRUPT	0
+#define LPFC_EQ_POLL		1
+
 	struct list_head wqfull_list;
 	enum lpfc_sli4_queue_type type;
 	enum lpfc_sli4_queue_subtype subtype;
@@ -199,6 +221,7 @@ struct lpfc_queue {
 	uint8_t q_flag;
 #define HBA_NVMET_WQFULL	0x1 /* We hit WQ Full condition for NVMET */
 #define HBA_NVMET_CQ_NOTIFY	0x1 /* LPFC_NVMET_CQ_NOTIFY CQEs this EQE */
+#define HBA_EQ_DELAY_CHK	0x2 /* EQ is a candidate for coalescing */
 #define LPFC_NVMET_CQ_NOTIFY	4
 	void __iomem *db_regaddr;
 	uint16_t dpp_enable;
@@ -239,10 +262,8 @@ struct lpfc_queue {
 	struct delayed_work	sched_spwork;
 
 	uint64_t isr_timestamp;
-	uint16_t hdwq;
-	uint16_t last_cpu;	/* most recent cpu */
-	uint8_t	qe_valid;
 	struct lpfc_queue *assoc_qp;
+	struct list_head _poll_list;
 	void **q_pgs;	/* array to index entries per page */
 };
 
@@ -451,11 +472,17 @@ struct lpfc_hba;
 #define LPFC_SLI4_HANDLER_NAME_SZ	16
 struct lpfc_hba_eq_hdl {
 	uint32_t idx;
+	uint16_t irq;
 	char handler_name[LPFC_SLI4_HANDLER_NAME_SZ];
 	struct lpfc_hba *phba;
 	struct lpfc_queue *eq;
+	struct cpumask aff_mask;
 };
 
+#define lpfc_get_eq_hdl(eqidx) (&phba->sli4_hba.hba_eq_hdl[eqidx])
+#define lpfc_get_aff_mask(eqidx) (&phba->sli4_hba.hba_eq_hdl[eqidx].aff_mask)
+#define lpfc_get_irq(eqidx) (phba->sli4_hba.hba_eq_hdl[eqidx].irq)
+
 /*BB Credit recovery value*/
 struct lpfc_bbscn_params {
 	uint32_t word0;
@@ -513,6 +540,7 @@ struct lpfc_pc_sli4_params {
 	uint8_t cqav;
 	uint8_t wqsize;
 	uint8_t bv1s;
+	uint8_t pls;
 #define LPFC_WQ_SZ64_SUPPORT	1
 #define LPFC_WQ_SZ128_SUPPORT	2
 	uint8_t wqpcnt;
@@ -544,11 +572,10 @@ struct lpfc_sli4_lnk_info {
 #define LPFC_SLI4_HANDLER_CNT		(LPFC_HBA_IO_CHAN_MAX+ \
 					 LPFC_FOF_IO_CHAN_NUM)
 
-/* Used for IRQ vector to CPU mapping */
+/* Used for tracking CPU mapping attributes */
 struct lpfc_vector_map_info {
 	uint16_t	phys_id;
 	uint16_t	core_id;
-	uint16_t	irq;
 	uint16_t	eq;
 	uint16_t	hdwq;
 	uint16_t	flag;
@@ -891,6 +918,7 @@ struct lpfc_sli4_hba {
 	struct lpfc_vector_map_info *cpu_map;
 	uint16_t num_possible_cpu;
 	uint16_t num_present_cpu;
+	struct cpumask numa_mask;
 	uint16_t curr_disp_cpu;
 	struct lpfc_eq_intr_info __percpu *eq_info;
 	uint32_t conf_trunk;
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index b8aae31ffda3..9e5ff58edaca 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "12.4.0.0"
+#define LPFC_DRIVER_VERSION "12.6.0.2"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
diff --git a/drivers/scsi/mac_scsi.c b/drivers/scsi/mac_scsi.c
index 9c5566217ef6..b5dde9d0d054 100644
--- a/drivers/scsi/mac_scsi.c
+++ b/drivers/scsi/mac_scsi.c
@@ -464,7 +464,7 @@ static int __init mac_scsi_probe(struct platform_device *pdev)
 		mac_scsi_template.can_queue = setup_can_queue;
 	if (setup_cmd_per_lun > 0)
 		mac_scsi_template.cmd_per_lun = setup_cmd_per_lun;
-	if (setup_sg_tablesize >= 0)
+	if (setup_sg_tablesize > 0)
 		mac_scsi_template.sg_tablesize = setup_sg_tablesize;
 	if (setup_hostid >= 0)
 		mac_scsi_template.this_id = setup_hostid & 7;
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index a6e788c02ff4..bd8184072bed 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -24,6 +24,8 @@
 #define MEGASAS_VERSION				"07.710.50.00-rc1"
 #define MEGASAS_RELDATE				"June 28, 2019"
 
+#define MEGASAS_MSIX_NAME_LEN			32
+
 /*
  * Device IDs
  */
@@ -2203,6 +2205,7 @@ struct megasas_aen_event {
 };
 
 struct megasas_irq_context {
+	char name[MEGASAS_MSIX_NAME_LEN];
 	struct megasas_instance *instance;
 	u32 MSIxIndex;
 	u32 os_irq;
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 42cf38c1ea99..c40fbea06cc5 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -5546,9 +5546,11 @@ megasas_setup_irqs_ioapic(struct megasas_instance *instance)
 	pdev = instance->pdev;
 	instance->irq_context[0].instance = instance;
 	instance->irq_context[0].MSIxIndex = 0;
+	snprintf(instance->irq_context->name, MEGASAS_MSIX_NAME_LEN, "%s%u",
+		"megasas", instance->host->host_no);
 	if (request_irq(pci_irq_vector(pdev, 0),
 			instance->instancet->service_isr, IRQF_SHARED,
-			"megasas", &instance->irq_context[0])) {
+			instance->irq_context->name, &instance->irq_context[0])) {
 		dev_err(&instance->pdev->dev,
 				"Failed to register IRQ from %s %d\n",
 				__func__, __LINE__);
@@ -5580,8 +5582,10 @@ megasas_setup_irqs_msix(struct megasas_instance *instance, u8 is_probe)
 	for (i = 0; i < instance->msix_vectors; i++) {
 		instance->irq_context[i].instance = instance;
 		instance->irq_context[i].MSIxIndex = i;
+		snprintf(instance->irq_context[i].name, MEGASAS_MSIX_NAME_LEN, "%s%u-msix%u",
+			"megasas", instance->host->host_no, i);
 		if (request_irq(pci_irq_vector(pdev, i),
-			instance->instancet->service_isr, 0, "megasas",
+			instance->instancet->service_isr, 0, instance->irq_context[i].name,
 			&instance->irq_context[i])) {
 			dev_err(&instance->pdev->dev,
 				"Failed to register IRQ for vector %d.\n", i);
diff --git a/drivers/scsi/megaraid/megaraid_sas_fp.c b/drivers/scsi/megaraid/megaraid_sas_fp.c
index 50b8c1b12767..89c3685f5163 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fp.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fp.c
@@ -386,9 +386,8 @@ u32 MR_GetSpanBlock(u32 ld, u64 row, u64 *span_blk,
 				le64_to_cpu(quad->logEnd) && (mega_mod64(row - le64_to_cpu(quad->logStart),
 				le32_to_cpu(quad->diff))) == 0) {
 				if (span_blk != NULL) {
-					u64  blk, debugBlk;
+					u64  blk;
 					blk =  mega_div64_32((row-le64_to_cpu(quad->logStart)), le32_to_cpu(quad->diff));
-					debugBlk = blk;
 
 					blk = (blk + le64_to_cpu(quad->offsetInSpan)) << raid->stripeShift;
 					*span_blk = blk;
@@ -699,9 +698,7 @@ static u8 mr_spanset_get_phy_params(struct megasas_instance *instance, u32 ld,
 	__le16	*pDevHandle = &io_info->devHandle;
 	u8	*pPdInterface = &io_info->pd_interface;
 	u32	logArm, rowMod, armQ, arm;
-	struct fusion_context *fusion;
 
-	fusion = instance->ctrl_context;
 	*pDevHandle = cpu_to_le16(MR_DEVHANDLE_INVALID);
 
 	/*Get row and span from io_info for Uneven Span IO.*/
@@ -801,9 +798,7 @@ u8 MR_GetPhyParams(struct megasas_instance *instance, u32 ld, u64 stripRow,
 	u64	    *pdBlock = &io_info->pdBlock;
 	__le16	    *pDevHandle = &io_info->devHandle;
 	u8	    *pPdInterface = &io_info->pd_interface;
-	struct fusion_context *fusion;
 
-	fusion = instance->ctrl_context;
 	*pDevHandle = cpu_to_le16(MR_DEVHANDLE_INVALID);
 
 	row =  mega_div64_32(stripRow, raid->rowDataSize);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index fea3cb6a090b..848fbec7bda6 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -3044,11 +3044,11 @@ _base_alloc_irq_vectors(struct MPT3SAS_ADAPTER *ioc)
 		descp = NULL;
 
 	ioc_info(ioc, " %d %d\n", ioc->high_iops_queues,
-	    ioc->msix_vector_count);
+	    ioc->reply_queue_count);
 
 	i = pci_alloc_irq_vectors_affinity(ioc->pdev,
 	    ioc->high_iops_queues,
-	    ioc->msix_vector_count, irq_flags, descp);
+	    ioc->reply_queue_count, irq_flags, descp);
 
 	return i;
 }
@@ -4242,10 +4242,12 @@ _base_display_OEMs_branding(struct MPT3SAS_ADAPTER *ioc)
 	static int
 _base_display_fwpkg_version(struct MPT3SAS_ADAPTER *ioc)
 {
-	Mpi2FWImageHeader_t *FWImgHdr;
+	Mpi2FWImageHeader_t *fw_img_hdr;
+	Mpi26ComponentImageHeader_t *cmp_img_hdr;
 	Mpi25FWUploadRequest_t *mpi_request;
 	Mpi2FWUploadReply_t mpi_reply;
 	int r = 0;
+	u32  package_version = 0;
 	void *fwpkg_data = NULL;
 	dma_addr_t fwpkg_data_dma;
 	u16 smid, ioc_status;
@@ -4302,14 +4304,26 @@ _base_display_fwpkg_version(struct MPT3SAS_ADAPTER *ioc)
 			ioc_status = le16_to_cpu(mpi_reply.IOCStatus) &
 						MPI2_IOCSTATUS_MASK;
 			if (ioc_status == MPI2_IOCSTATUS_SUCCESS) {
-				FWImgHdr = (Mpi2FWImageHeader_t *)fwpkg_data;
-				if (FWImgHdr->PackageVersion.Word) {
-					ioc_info(ioc, "FW Package Version (%02d.%02d.%02d.%02d)\n",
-						 FWImgHdr->PackageVersion.Struct.Major,
-						 FWImgHdr->PackageVersion.Struct.Minor,
-						 FWImgHdr->PackageVersion.Struct.Unit,
-						 FWImgHdr->PackageVersion.Struct.Dev);
-				}
+				fw_img_hdr = (Mpi2FWImageHeader_t *)fwpkg_data;
+				if (le32_to_cpu(fw_img_hdr->Signature) ==
+				    MPI26_IMAGE_HEADER_SIGNATURE0_MPI26) {
+					cmp_img_hdr =
+					    (Mpi26ComponentImageHeader_t *)
+					    (fwpkg_data);
+					package_version =
+					    le32_to_cpu(
+					    cmp_img_hdr->ApplicationSpecific);
+				} else
+					package_version =
+					    le32_to_cpu(
+					    fw_img_hdr->PackageVersion.Word);
+				if (package_version)
+					ioc_info(ioc,
+					"FW Package Ver(%02d.%02d.%02d.%02d)\n",
+					((package_version) & 0xFF000000) >> 24,
+					((package_version) & 0x00FF0000) >> 16,
+					((package_version) & 0x0000FF00) >> 8,
+					(package_version) & 0x000000FF);
 			} else {
 				_debug_dump_mf(&mpi_reply,
 						sizeof(Mpi2FWUploadReply_t)/4);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index faca0a5e71f8..4ebf81ea4d2f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -76,8 +76,8 @@
 #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		"31.100.00.00"
-#define MPT3SAS_MAJOR_VERSION		31
+#define MPT3SAS_DRIVER_VERSION		"32.100.00.00"
+#define MPT3SAS_MAJOR_VERSION		32
 #define MPT3SAS_MINOR_VERSION		100
 #define MPT3SAS_BUILD_VERSION		0
 #define MPT3SAS_RELEASE_VERSION	00
@@ -303,6 +303,8 @@ struct mpt3sas_nvme_cmd {
 #define MPT3_DIAG_BUFFER_IS_REGISTERED	(0x01)
 #define MPT3_DIAG_BUFFER_IS_RELEASED	(0x02)
 #define MPT3_DIAG_BUFFER_IS_DIAG_RESET	(0x04)
+#define MPT3_DIAG_BUFFER_IS_DRIVER_ALLOCATED (0x08)
+#define MPT3_DIAG_BUFFER_IS_APP_OWNED (0x10)
 
 /*
  * HP HBA branding
@@ -391,9 +393,12 @@ struct Mpi2ManufacturingPage11_t {
 	u8	Reserved6;			/* 2Fh */
 	__le32	Reserved7[7];			/* 30h - 4Bh */
 	u8	NVMeAbortTO;			/* 4Ch */
-	u8	Reserved8;			/* 4Dh */
-	u16	Reserved9;			/* 4Eh */
-	__le32	Reserved10[4];			/* 50h - 60h */
+	u8	NumPerDevEvents;		/* 4Dh */
+	u8	HostTraceBufferDecrementSizeKB;	/* 4Eh */
+	u8	HostTraceBufferFlags;		/* 4Fh */
+	u16	HostTraceBufferMaxSizeKB;	/* 50h */
+	u16	HostTraceBufferMinSizeKB;	/* 52h */
+	__le32	Reserved10[2];			/* 54h - 5Bh */
 };
 
 /**
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 7d696952b376..6874cf017739 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -466,6 +466,13 @@ void mpt3sas_ctl_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc)
 		if ((ioc->diag_buffer_status[i] &
 		     MPT3_DIAG_BUFFER_IS_RELEASED))
 			continue;
+
+		/*
+		 * add a log message to indicate the release
+		 */
+		ioc_info(ioc,
+		    "%s: Releasing the trace buffer due to adapter reset.",
+		    __func__);
 		mpt3sas_send_diag_release(ioc, i, &issue_reset);
 	}
 }
@@ -778,6 +785,18 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 	case MPI2_FUNCTION_NVME_ENCAPSULATED:
 	{
 		nvme_encap_request = (Mpi26NVMeEncapsulatedRequest_t *)request;
+		if (!ioc->pcie_sg_lookup) {
+			dtmprintk(ioc, ioc_info(ioc,
+			    "HBA doesn't support NVMe. Rejecting NVMe Encapsulated request.\n"
+			    ));
+
+			if (ioc->logging_level & MPT_DEBUG_TM)
+				_debug_dump_mf(nvme_encap_request,
+				    ioc->request_sz/4);
+			mpt3sas_base_free_smid(ioc, smid);
+			ret = -EINVAL;
+			goto out;
+		}
 		/*
 		 * Get the Physical Address of the sense buffer.
 		 * Use Error Response buffer address field to hold the sense
@@ -1484,6 +1503,26 @@ _ctl_diag_capability(struct MPT3SAS_ADAPTER *ioc, u8 buffer_type)
 	return rc;
 }
 
+/**
+ * _ctl_diag_get_bufftype - return diag buffer type
+ *              either TRACE, SNAPSHOT, or EXTENDED
+ * @ioc: per adapter object
+ * @unique_id: specifies the unique_id for the buffer
+ *
+ * returns MPT3_DIAG_UID_NOT_FOUND if the id not found
+ */
+static u8
+_ctl_diag_get_bufftype(struct MPT3SAS_ADAPTER *ioc, u32 unique_id)
+{
+	u8  index;
+
+	for (index = 0; index < MPI2_DIAG_BUF_TYPE_COUNT; index++) {
+		if (ioc->unique_id[index] == unique_id)
+			return index;
+	}
+
+	return MPT3_DIAG_UID_NOT_FOUND;
+}
 
 /**
  * _ctl_diag_register_2 - wrapper for registering diag buffer support
@@ -1531,11 +1570,88 @@ _ctl_diag_register_2(struct MPT3SAS_ADAPTER *ioc,
 		return -EPERM;
 	}
 
+	if (diag_register->unique_id == 0) {
+		ioc_err(ioc,
+		    "%s: Invalid UID(0x%08x), buffer_type(0x%02x)\n", __func__,
+		    diag_register->unique_id, buffer_type);
+		return -EINVAL;
+	}
+
+	if ((ioc->diag_buffer_status[buffer_type] &
+	    MPT3_DIAG_BUFFER_IS_APP_OWNED) &&
+	    !(ioc->diag_buffer_status[buffer_type] &
+	    MPT3_DIAG_BUFFER_IS_RELEASED)) {
+		ioc_err(ioc,
+		    "%s: buffer_type(0x%02x) is already registered by application with UID(0x%08x)\n",
+		    __func__, buffer_type, ioc->unique_id[buffer_type]);
+		return -EINVAL;
+	}
+
 	if (ioc->diag_buffer_status[buffer_type] &
 	    MPT3_DIAG_BUFFER_IS_REGISTERED) {
-		ioc_err(ioc, "%s: already has a registered buffer for buffer_type(0x%02x)\n",
-			__func__, buffer_type);
-		return -EINVAL;
+		/*
+		 * If driver posts buffer initially, then an application wants
+		 * to Register that buffer (own it) without Releasing first,
+		 * the application Register command MUST have the same buffer
+		 * type and size in the Register command (obtained from the
+		 * Query command). Otherwise that Register command will be
+		 * failed. If the application has released the buffer but wants
+		 * to re-register it, it should be allowed as long as the
+		 * Unique-Id/Size match.
+		 */
+
+		if (ioc->unique_id[buffer_type] == MPT3DIAGBUFFUNIQUEID &&
+		    ioc->diag_buffer_sz[buffer_type] ==
+		    diag_register->requested_buffer_size) {
+
+			if (!(ioc->diag_buffer_status[buffer_type] &
+			     MPT3_DIAG_BUFFER_IS_RELEASED)) {
+				dctlprintk(ioc, ioc_info(ioc,
+				    "%s: diag_buffer (%d) ownership changed. old-ID(0x%08x), new-ID(0x%08x)\n",
+				    __func__, buffer_type,
+				    ioc->unique_id[buffer_type],
+				    diag_register->unique_id));
+
+				/*
+				 * Application wants to own the buffer with
+				 * the same size.
+				 */
+				ioc->unique_id[buffer_type] =
+				    diag_register->unique_id;
+				rc = 0; /* success */
+				goto out;
+			}
+		} else if (ioc->unique_id[buffer_type] !=
+		    MPT3DIAGBUFFUNIQUEID) {
+			if (ioc->unique_id[buffer_type] !=
+			    diag_register->unique_id ||
+			    ioc->diag_buffer_sz[buffer_type] !=
+			    diag_register->requested_buffer_size ||
+			    !(ioc->diag_buffer_status[buffer_type] &
+			    MPT3_DIAG_BUFFER_IS_RELEASED)) {
+				ioc_err(ioc,
+				    "%s: already has a registered buffer for buffer_type(0x%02x)\n",
+				    __func__, buffer_type);
+				return -EINVAL;
+			}
+		} else {
+			ioc_err(ioc, "%s: already has a registered buffer for buffer_type(0x%02x)\n",
+			    __func__, buffer_type);
+			return -EINVAL;
+		}
+	} else if (ioc->diag_buffer_status[buffer_type] &
+	    MPT3_DIAG_BUFFER_IS_DRIVER_ALLOCATED) {
+
+		if (ioc->unique_id[buffer_type] != MPT3DIAGBUFFUNIQUEID ||
+		    ioc->diag_buffer_sz[buffer_type] !=
+		    diag_register->requested_buffer_size) {
+
+			ioc_err(ioc,
+			    "%s: already a buffer is allocated for buffer_type(0x%02x) of size %d bytes, so please try registering again with same size\n",
+			     __func__, buffer_type,
+			    ioc->diag_buffer_sz[buffer_type]);
+			return -EINVAL;
+		}
 	}
 
 	if (diag_register->requested_buffer_size % 4)  {
@@ -1560,7 +1676,8 @@ _ctl_diag_register_2(struct MPT3SAS_ADAPTER *ioc,
 	request_data = ioc->diag_buffer[buffer_type];
 	request_data_sz = diag_register->requested_buffer_size;
 	ioc->unique_id[buffer_type] = diag_register->unique_id;
-	ioc->diag_buffer_status[buffer_type] = 0;
+	ioc->diag_buffer_status[buffer_type] &=
+	    MPT3_DIAG_BUFFER_IS_DRIVER_ALLOCATED;
 	memcpy(ioc->product_specific[buffer_type],
 	    diag_register->product_specific, MPT3_PRODUCT_SPECIFIC_DWORDS);
 	ioc->diagnostic_flags[buffer_type] = diag_register->diagnostic_flags;
@@ -1584,7 +1701,8 @@ _ctl_diag_register_2(struct MPT3SAS_ADAPTER *ioc,
 			ioc_err(ioc, "%s: failed allocating memory for diag buffers, requested size(%d)\n",
 				__func__, request_data_sz);
 			mpt3sas_base_free_smid(ioc, smid);
-			return -ENOMEM;
+			rc = -ENOMEM;
+			goto out;
 		}
 		ioc->diag_buffer[buffer_type] = request_data;
 		ioc->diag_buffer_sz[buffer_type] = request_data_sz;
@@ -1649,9 +1767,12 @@ _ctl_diag_register_2(struct MPT3SAS_ADAPTER *ioc,
 
  out:
 
-	if (rc && request_data)
+	if (rc && request_data) {
 		dma_free_coherent(&ioc->pdev->dev, request_data_sz,
 		    request_data, request_data_dma);
+		ioc->diag_buffer_status[buffer_type] &=
+		    ~MPT3_DIAG_BUFFER_IS_DRIVER_ALLOCATED;
+	}
 
 	ioc->ctl_cmds.status = MPT3_CMD_NOT_USED;
 	return rc;
@@ -1669,6 +1790,10 @@ void
 mpt3sas_enable_diag_buffer(struct MPT3SAS_ADAPTER *ioc, u8 bits_to_register)
 {
 	struct mpt3_diag_register diag_register;
+	u32 ret_val;
+	u32 trace_buff_size = ioc->manu_pg11.HostTraceBufferMaxSizeKB<<10;
+	u32 min_trace_buff_size = 0;
+	u32 decr_trace_buff_size = 0;
 
 	memset(&diag_register, 0, sizeof(struct mpt3_diag_register));
 
@@ -1677,10 +1802,68 @@ mpt3sas_enable_diag_buffer(struct MPT3SAS_ADAPTER *ioc, u8 bits_to_register)
 		ioc->diag_trigger_master.MasterData =
 		    (MASTER_TRIGGER_FW_FAULT + MASTER_TRIGGER_ADAPTER_RESET);
 		diag_register.buffer_type = MPI2_DIAG_BUF_TYPE_TRACE;
-		/* register for 2MB buffers  */
-		diag_register.requested_buffer_size = 2 * (1024 * 1024);
-		diag_register.unique_id = 0x7075900;
-		_ctl_diag_register_2(ioc,  &diag_register);
+		diag_register.unique_id =
+		    (ioc->hba_mpi_version_belonged == MPI2_VERSION) ?
+		    (MPT2DIAGBUFFUNIQUEID):(MPT3DIAGBUFFUNIQUEID);
+
+		if (trace_buff_size != 0) {
+			diag_register.requested_buffer_size = trace_buff_size;
+			min_trace_buff_size =
+			    ioc->manu_pg11.HostTraceBufferMinSizeKB<<10;
+			decr_trace_buff_size =
+			    ioc->manu_pg11.HostTraceBufferDecrementSizeKB<<10;
+
+			if (min_trace_buff_size > trace_buff_size) {
+				/* The buff size is not set correctly */
+				ioc_err(ioc,
+				    "Min Trace Buff size (%d KB) greater than Max Trace Buff size (%d KB)\n",
+				     min_trace_buff_size>>10,
+				     trace_buff_size>>10);
+				ioc_err(ioc,
+				    "Using zero Min Trace Buff Size\n");
+				min_trace_buff_size = 0;
+			}
+
+			if (decr_trace_buff_size == 0) {
+				/*
+				 * retry the min size if decrement
+				 * is not available.
+				 */
+				decr_trace_buff_size =
+				    trace_buff_size - min_trace_buff_size;
+			}
+		} else {
+			/* register for 2MB buffers  */
+			diag_register.requested_buffer_size = 2 * (1024 * 1024);
+		}
+
+		do {
+			ret_val = _ctl_diag_register_2(ioc,  &diag_register);
+
+			if (ret_val == -ENOMEM && min_trace_buff_size &&
+			    (trace_buff_size - decr_trace_buff_size) >=
+			    min_trace_buff_size) {
+				/* adjust the buffer size */
+				trace_buff_size -= decr_trace_buff_size;
+				diag_register.requested_buffer_size =
+				    trace_buff_size;
+			} else
+				break;
+		} while (true);
+
+		if (ret_val == -ENOMEM)
+			ioc_err(ioc,
+			    "Cannot allocate trace buffer memory. Last memory tried = %d KB\n",
+			    diag_register.requested_buffer_size>>10);
+		else if (ioc->diag_buffer_status[MPI2_DIAG_BUF_TYPE_TRACE]
+		    & MPT3_DIAG_BUFFER_IS_REGISTERED) {
+			ioc_err(ioc, "Trace buffer memory %d KB allocated\n",
+			    diag_register.requested_buffer_size>>10);
+			if (ioc->hba_mpi_version_belonged != MPI2_VERSION)
+				ioc->diag_buffer_status[
+				    MPI2_DIAG_BUF_TYPE_TRACE] |=
+				    MPT3_DIAG_BUFFER_IS_DRIVER_ALLOCATED;
+		}
 	}
 
 	if (bits_to_register & 2) {
@@ -1723,6 +1906,12 @@ _ctl_diag_register(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 	}
 
 	rc = _ctl_diag_register_2(ioc, &karg);
+
+	if (!rc && (ioc->diag_buffer_status[karg.buffer_type] &
+	    MPT3_DIAG_BUFFER_IS_REGISTERED))
+		ioc->diag_buffer_status[karg.buffer_type] |=
+		    MPT3_DIAG_BUFFER_IS_APP_OWNED;
+
 	return rc;
 }
 
@@ -1752,7 +1941,13 @@ _ctl_diag_unregister(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 	dctlprintk(ioc, ioc_info(ioc, "%s\n",
 				 __func__));
 
-	buffer_type = karg.unique_id & 0x000000ff;
+	buffer_type = _ctl_diag_get_bufftype(ioc, karg.unique_id);
+	if (buffer_type == MPT3_DIAG_UID_NOT_FOUND) {
+		ioc_err(ioc, "%s: buffer with unique_id(0x%08x) not found\n",
+		    __func__, karg.unique_id);
+		return -EINVAL;
+	}
+
 	if (!_ctl_diag_capability(ioc, buffer_type)) {
 		ioc_err(ioc, "%s: doesn't have capability for buffer_type(0x%02x)\n",
 			__func__, buffer_type);
@@ -1785,12 +1980,21 @@ _ctl_diag_unregister(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 		return -ENOMEM;
 	}
 
-	request_data_sz = ioc->diag_buffer_sz[buffer_type];
-	request_data_dma = ioc->diag_buffer_dma[buffer_type];
-	dma_free_coherent(&ioc->pdev->dev, request_data_sz,
-			request_data, request_data_dma);
-	ioc->diag_buffer[buffer_type] = NULL;
-	ioc->diag_buffer_status[buffer_type] = 0;
+	if (ioc->diag_buffer_status[buffer_type] &
+	    MPT3_DIAG_BUFFER_IS_DRIVER_ALLOCATED) {
+		ioc->unique_id[buffer_type] = MPT3DIAGBUFFUNIQUEID;
+		ioc->diag_buffer_status[buffer_type] &=
+		    ~MPT3_DIAG_BUFFER_IS_APP_OWNED;
+		ioc->diag_buffer_status[buffer_type] &=
+		    ~MPT3_DIAG_BUFFER_IS_REGISTERED;
+	} else {
+		request_data_sz = ioc->diag_buffer_sz[buffer_type];
+		request_data_dma = ioc->diag_buffer_dma[buffer_type];
+		dma_free_coherent(&ioc->pdev->dev, request_data_sz,
+				request_data, request_data_dma);
+		ioc->diag_buffer[buffer_type] = NULL;
+		ioc->diag_buffer_status[buffer_type] = 0;
+	}
 	return 0;
 }
 
@@ -1829,14 +2033,17 @@ _ctl_diag_query(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 		return -EPERM;
 	}
 
-	if ((ioc->diag_buffer_status[buffer_type] &
-	    MPT3_DIAG_BUFFER_IS_REGISTERED) == 0) {
-		ioc_err(ioc, "%s: buffer_type(0x%02x) is not registered\n",
-			__func__, buffer_type);
-		return -EINVAL;
+	if (!(ioc->diag_buffer_status[buffer_type] &
+	    MPT3_DIAG_BUFFER_IS_DRIVER_ALLOCATED)) {
+		if ((ioc->diag_buffer_status[buffer_type] &
+		    MPT3_DIAG_BUFFER_IS_REGISTERED) == 0) {
+			ioc_err(ioc, "%s: buffer_type(0x%02x) is not registered\n",
+				__func__, buffer_type);
+			return -EINVAL;
+		}
 	}
 
-	if (karg.unique_id & 0xffffff00) {
+	if (karg.unique_id) {
 		if (karg.unique_id != ioc->unique_id[buffer_type]) {
 			ioc_err(ioc, "%s: unique_id(0x%08x) is not registered\n",
 				__func__, karg.unique_id);
@@ -1851,13 +2058,21 @@ _ctl_diag_query(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 		return -ENOMEM;
 	}
 
-	if (ioc->diag_buffer_status[buffer_type] & MPT3_DIAG_BUFFER_IS_RELEASED)
-		karg.application_flags = (MPT3_APP_FLAGS_APP_OWNED |
-		    MPT3_APP_FLAGS_BUFFER_VALID);
-	else
-		karg.application_flags = (MPT3_APP_FLAGS_APP_OWNED |
-		    MPT3_APP_FLAGS_BUFFER_VALID |
-		    MPT3_APP_FLAGS_FW_BUFFER_ACCESS);
+	if ((ioc->diag_buffer_status[buffer_type] &
+	    MPT3_DIAG_BUFFER_IS_REGISTERED))
+		karg.application_flags |= MPT3_APP_FLAGS_BUFFER_VALID;
+
+	if (!(ioc->diag_buffer_status[buffer_type] &
+	     MPT3_DIAG_BUFFER_IS_RELEASED))
+		karg.application_flags |= MPT3_APP_FLAGS_FW_BUFFER_ACCESS;
+
+	if (!(ioc->diag_buffer_status[buffer_type] &
+	    MPT3_DIAG_BUFFER_IS_DRIVER_ALLOCATED))
+		karg.application_flags |= MPT3_APP_FLAGS_DYNAMIC_BUFFER_ALLOC;
+
+	if ((ioc->diag_buffer_status[buffer_type] &
+	    MPT3_DIAG_BUFFER_IS_APP_OWNED))
+		karg.application_flags |= MPT3_APP_FLAGS_APP_OWNED;
 
 	for (i = 0; i < MPT3_PRODUCT_SPECIFIC_DWORDS; i++)
 		karg.product_specific[i] =
@@ -2002,7 +2217,13 @@ _ctl_diag_release(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 	dctlprintk(ioc, ioc_info(ioc, "%s\n",
 				 __func__));
 
-	buffer_type = karg.unique_id & 0x000000ff;
+	buffer_type = _ctl_diag_get_bufftype(ioc, karg.unique_id);
+	if (buffer_type == MPT3_DIAG_UID_NOT_FOUND) {
+		ioc_err(ioc, "%s: buffer with unique_id(0x%08x) not found\n",
+		    __func__, karg.unique_id);
+		return -EINVAL;
+	}
+
 	if (!_ctl_diag_capability(ioc, buffer_type)) {
 		ioc_err(ioc, "%s: doesn't have capability for buffer_type(0x%02x)\n",
 			__func__, buffer_type);
@@ -2026,7 +2247,7 @@ _ctl_diag_release(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 	    MPT3_DIAG_BUFFER_IS_RELEASED) {
 		ioc_err(ioc, "%s: buffer_type(0x%02x) is already released\n",
 			__func__, buffer_type);
-		return 0;
+		return -EINVAL;
 	}
 
 	request_data = ioc->diag_buffer[buffer_type];
@@ -2086,7 +2307,13 @@ _ctl_diag_read_buffer(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 	dctlprintk(ioc, ioc_info(ioc, "%s\n",
 				 __func__));
 
-	buffer_type = karg.unique_id & 0x000000ff;
+	buffer_type = _ctl_diag_get_bufftype(ioc, karg.unique_id);
+	if (buffer_type == MPT3_DIAG_UID_NOT_FOUND) {
+		ioc_err(ioc, "%s: buffer with unique_id(0x%08x) not found\n",
+		    __func__, karg.unique_id);
+		return -EINVAL;
+	}
+
 	if (!_ctl_diag_capability(ioc, buffer_type)) {
 		ioc_err(ioc, "%s: doesn't have capability for buffer_type(0x%02x)\n",
 			__func__, buffer_type);
@@ -2210,6 +2437,8 @@ _ctl_diag_read_buffer(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 	if (ioc_status == MPI2_IOCSTATUS_SUCCESS) {
 		ioc->diag_buffer_status[buffer_type] |=
 		    MPT3_DIAG_BUFFER_IS_REGISTERED;
+		ioc->diag_buffer_status[buffer_type] &=
+		    ~MPT3_DIAG_BUFFER_IS_RELEASED;
 		dctlprintk(ioc, ioc_info(ioc, "%s: success\n", __func__));
 	} else {
 		ioc_info(ioc, "%s: ioc_status(0x%04x) log_info(0x%08x)\n",
@@ -3130,10 +3359,49 @@ host_trace_buffer_enable_store(struct device *cdev,
 		memset(&diag_register, 0, sizeof(struct mpt3_diag_register));
 		ioc_info(ioc, "posting host trace buffers\n");
 		diag_register.buffer_type = MPI2_DIAG_BUF_TYPE_TRACE;
-		diag_register.requested_buffer_size = (1024 * 1024);
-		diag_register.unique_id = 0x7075900;
+
+		if (ioc->manu_pg11.HostTraceBufferMaxSizeKB != 0 &&
+		    ioc->diag_buffer_sz[MPI2_DIAG_BUF_TYPE_TRACE] != 0) {
+			/* post the same buffer allocated previously */
+			diag_register.requested_buffer_size =
+			    ioc->diag_buffer_sz[MPI2_DIAG_BUF_TYPE_TRACE];
+		} else {
+			/*
+			 * Free the diag buffer memory which was previously
+			 * allocated by an application.
+			 */
+			if ((ioc->diag_buffer_sz[MPI2_DIAG_BUF_TYPE_TRACE] != 0)
+			    &&
+			    (ioc->diag_buffer_status[MPI2_DIAG_BUF_TYPE_TRACE] &
+			    MPT3_DIAG_BUFFER_IS_APP_OWNED)) {
+				pci_free_consistent(ioc->pdev,
+				    ioc->diag_buffer_sz[
+				    MPI2_DIAG_BUF_TYPE_TRACE],
+				    ioc->diag_buffer[MPI2_DIAG_BUF_TYPE_TRACE],
+				    ioc->diag_buffer_dma[
+				    MPI2_DIAG_BUF_TYPE_TRACE]);
+				ioc->diag_buffer[MPI2_DIAG_BUF_TYPE_TRACE] =
+				    NULL;
+			}
+
+			diag_register.requested_buffer_size = (1024 * 1024);
+		}
+
+		diag_register.unique_id =
+		    (ioc->hba_mpi_version_belonged == MPI2_VERSION) ?
+		    (MPT2DIAGBUFFUNIQUEID):(MPT3DIAGBUFFUNIQUEID);
 		ioc->diag_buffer_status[MPI2_DIAG_BUF_TYPE_TRACE] = 0;
 		_ctl_diag_register_2(ioc,  &diag_register);
+		if (ioc->diag_buffer_status[MPI2_DIAG_BUF_TYPE_TRACE] &
+		    MPT3_DIAG_BUFFER_IS_REGISTERED) {
+			ioc_info(ioc,
+			    "Trace buffer %d KB allocated through sysfs\n",
+			    diag_register.requested_buffer_size>>10);
+			if (ioc->hba_mpi_version_belonged != MPI2_VERSION)
+				ioc->diag_buffer_status[
+				    MPI2_DIAG_BUF_TYPE_TRACE] |=
+				    MPT3_DIAG_BUFFER_IS_DRIVER_ALLOCATED;
+		}
 	} else if (!strcmp(str, "release")) {
 		/* exit out if host buffers are already released */
 		if (!ioc->diag_buffer[MPI2_DIAG_BUF_TYPE_TRACE])
@@ -3702,12 +3970,6 @@ mpt3sas_ctl_exit(ushort hbas_to_enumerate)
 		for (i = 0; i < MPI2_DIAG_BUF_TYPE_COUNT; i++) {
 			if (!ioc->diag_buffer[i])
 				continue;
-			if (!(ioc->diag_buffer_status[i] &
-			    MPT3_DIAG_BUFFER_IS_REGISTERED))
-				continue;
-			if ((ioc->diag_buffer_status[i] &
-			    MPT3_DIAG_BUFFER_IS_RELEASED))
-				continue;
 			dma_free_coherent(&ioc->pdev->dev,
 					  ioc->diag_buffer_sz[i],
 					  ioc->diag_buffer[i],
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.h b/drivers/scsi/mpt3sas/mpt3sas_ctl.h
index 18b46faef6f1..0f7aa4ddade0 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.h
@@ -95,6 +95,14 @@
 #define MPT3DIAGREADBUFFER _IOWR(MPT3_MAGIC_NUMBER, 30, \
 	struct mpt3_diag_read_buffer)
 
+/* Trace Buffer default UniqueId */
+#define MPT2DIAGBUFFUNIQUEID (0x07075900)
+#define MPT3DIAGBUFFUNIQUEID (0x4252434D)
+
+/* UID not found */
+#define MPT3_DIAG_UID_NOT_FOUND (0xFF)
+
+
 /**
  * struct mpt3_ioctl_header - main header structure
  * @ioc_number -  IOC unit number
@@ -310,6 +318,7 @@ struct mpt3_ioctl_btdh_mapping {
 #define MPT3_APP_FLAGS_APP_OWNED	(0x0001)
 #define MPT3_APP_FLAGS_BUFFER_VALID	(0x0002)
 #define MPT3_APP_FLAGS_FW_BUFFER_ACCESS	(0x0004)
+#define MPT3_APP_FLAGS_DYNAMIC_BUFFER_ALLOC (0x0008)
 
 /* flags for mpt3_diag_read_buffer */
 #define MPT3_FLAGS_REREGISTER		(0x0001)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index c8e512ba6d39..a038be8a0e90 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -5161,7 +5161,7 @@ _scsih_smart_predicted_fault(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	/* insert into event log */
 	sz = offsetof(Mpi2EventNotificationReply_t, EventData) +
 	     sizeof(Mpi2EventDataSasDeviceStatusChange_t);
-	event_reply = kzalloc(sz, GFP_KERNEL);
+	event_reply = kzalloc(sz, GFP_ATOMIC);
 	if (!event_reply) {
 		ioc_err(ioc, "failure at %s:%d/%s()!\n",
 			__FILE__, __LINE__, __func__);
@@ -10193,6 +10193,8 @@ scsih_scan_start(struct Scsi_Host *shost)
 	int rc;
 	if (diag_buffer_enable != -1 && diag_buffer_enable != 0)
 		mpt3sas_enable_diag_buffer(ioc, diag_buffer_enable);
+	else if (ioc->manu_pg11.HostTraceBufferMaxSizeKB != 0)
+		mpt3sas_enable_diag_buffer(ioc, 1);
 
 	if (disable_discovery > 0)
 		return;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_trigger_diag.c b/drivers/scsi/mpt3sas/mpt3sas_trigger_diag.c
index 6ac453fd5937..8ec9bab20ec4 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_trigger_diag.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_trigger_diag.c
@@ -113,15 +113,21 @@ mpt3sas_process_trigger_data(struct MPT3SAS_ADAPTER *ioc,
 	struct SL_WH_TRIGGERS_EVENT_DATA_T *event_data)
 {
 	u8 issue_reset = 0;
+	u32 *trig_data = (u32 *)&event_data->u.master;
 
 	dTriggerDiagPrintk(ioc, ioc_info(ioc, "%s: enter\n", __func__));
 
 	/* release the diag buffer trace */
 	if ((ioc->diag_buffer_status[MPI2_DIAG_BUF_TYPE_TRACE] &
 	    MPT3_DIAG_BUFFER_IS_RELEASED) == 0) {
-		dTriggerDiagPrintk(ioc,
-				   ioc_info(ioc, "%s: release trace diag buffer\n",
-					    __func__));
+		/*
+		 * add a log message so that user knows which event caused
+		 * the release
+		 */
+		ioc_info(ioc,
+		    "%s: Releasing the trace buffer. Trigger_Type 0x%08x, Data[0] 0x%08x, Data[1] 0x%08x\n",
+		    __func__, event_data->trigger_type,
+		    trig_data[0], trig_data[1]);
 		mpt3sas_send_diag_release(ioc, MPI2_DIAG_BUF_TYPE_TRACE,
 		    &issue_reset);
 	}
diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c
index 3e0b8ebe257f..a920eced92ec 100644
--- a/drivers/scsi/mvsas/mv_sas.c
+++ b/drivers/scsi/mvsas/mv_sas.c
@@ -1541,7 +1541,7 @@ out:
 
 int mvs_abort_task_set(struct domain_device *dev, u8 *lun)
 {
-	int rc = TMF_RESP_FUNC_FAILED;
+	int rc;
 	struct mvs_tmf_task tmf_task;
 
 	tmf_task.tmf = TMF_ABORT_TASK_SET;
diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c
index e0b427fdf818..11a2cb844ecb 100644
--- a/drivers/scsi/ncr53c8xx.c
+++ b/drivers/scsi/ncr53c8xx.c
@@ -1722,7 +1722,7 @@ struct ncb {
 	**	Miscellaneous configuration and status parameters.
 	**----------------------------------------------------------------
 	*/
-	u_char		disc;		/* Diconnection allowed		*/
+	u_char		disc;		/* Disconnection allowed	*/
 	u_char		scsi_mode;	/* Current SCSI BUS mode	*/
 	u_char		order;		/* Tag order to use		*/
 	u_char		verbose;	/* Verbosity for this controller*/
diff --git a/drivers/scsi/nsp32.c b/drivers/scsi/nsp32.c
index 70db79254155..b6e04d14292d 100644
--- a/drivers/scsi/nsp32.c
+++ b/drivers/scsi/nsp32.c
@@ -1542,7 +1542,7 @@ static void nsp32_scsi_done(struct scsi_cmnd *SCpnt)
  * with ACK reply when below condition is matched:
  *	MsgIn 00: Command Complete.
  *	MsgIn 02: Save Data Pointer.
- *	MsgIn 04: Diconnect.
+ *	MsgIn 04: Disconnect.
  * In other case, unexpected BUSFREE is detected.
  */
 static int nsp32_busfree_occur(struct scsi_cmnd *SCpnt, unsigned short execph)
diff --git a/drivers/scsi/pcmcia/Kconfig b/drivers/scsi/pcmcia/Kconfig
index 2368f34efba3..dc9b74c9348a 100644
--- a/drivers/scsi/pcmcia/Kconfig
+++ b/drivers/scsi/pcmcia/Kconfig
@@ -32,7 +32,7 @@ config PCMCIA_FDOMAIN
 
 config PCMCIA_NINJA_SCSI
 	tristate "NinjaSCSI-3 / NinjaSCSI-32Bi (16bit) PCMCIA support"
-	depends on !64BIT
+	depends on !64BIT || COMPILE_TEST
 	help
 	  If you intend to attach this type of PCMCIA SCSI host adapter to
 	  your computer, say Y here and read
diff --git a/drivers/scsi/pcmcia/nsp_cs.c b/drivers/scsi/pcmcia/nsp_cs.c
index 97416e1dcc5b..93616f9fd6d7 100644
--- a/drivers/scsi/pcmcia/nsp_cs.c
+++ b/drivers/scsi/pcmcia/nsp_cs.c
@@ -56,9 +56,7 @@
 MODULE_AUTHOR("YOKOTA Hiroshi <yokota@netlab.is.tsukuba.ac.jp>");
 MODULE_DESCRIPTION("WorkBit NinjaSCSI-3 / NinjaSCSI-32Bi(16bit) PCMCIA SCSI host adapter module");
 MODULE_SUPPORTED_DEVICE("sd,sr,sg,st");
-#ifdef MODULE_LICENSE
 MODULE_LICENSE("GPL");
-#endif
 
 #include "nsp_io.h"
 
diff --git a/drivers/scsi/pm8001/pm8001_ctl.c b/drivers/scsi/pm8001/pm8001_ctl.c
index 6b85016b4db3..7c6be2ec110d 100644
--- a/drivers/scsi/pm8001/pm8001_ctl.c
+++ b/drivers/scsi/pm8001/pm8001_ctl.c
@@ -70,6 +70,25 @@ static
 DEVICE_ATTR(interface_rev, S_IRUGO, pm8001_ctl_mpi_interface_rev_show, NULL);
 
 /**
+ * controller_fatal_error_show - check controller is under fatal err
+ * @cdev: pointer to embedded class device
+ * @buf: the buffer returned
+ *
+ * A sysfs 'read only' shost attribute.
+ */
+static ssize_t controller_fatal_error_show(struct device *cdev,
+		struct device_attribute *attr, char *buf)
+{
+	struct Scsi_Host *shost = class_to_shost(cdev);
+	struct sas_ha_struct *sha = SHOST_TO_SAS_HA(shost);
+	struct pm8001_hba_info *pm8001_ha = sha->lldd_ha;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			pm8001_ha->controller_fatal_error);
+}
+static DEVICE_ATTR_RO(controller_fatal_error);
+
+/**
  * pm8001_ctl_fw_version_show - firmware version
  * @cdev: pointer to embedded class device
  * @buf: the buffer returned
@@ -804,6 +823,7 @@ static DEVICE_ATTR(update_fw, S_IRUGO|S_IWUSR|S_IWGRP,
 	pm8001_show_update_fw, pm8001_store_update_fw);
 struct device_attribute *pm8001_host_attrs[] = {
 	&dev_attr_interface_rev,
+	&dev_attr_controller_fatal_error,
 	&dev_attr_fw_version,
 	&dev_attr_update_fw,
 	&dev_attr_aap_log,
diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c
index 68a8217032d0..1cbcade747fe 100644
--- a/drivers/scsi/pm8001/pm8001_hwi.c
+++ b/drivers/scsi/pm8001/pm8001_hwi.c
@@ -1336,10 +1336,13 @@ int pm8001_mpi_msg_free_get(struct inbound_queue_table *circularQ,
  * @circularQ: the inbound queue we want to transfer to HBA.
  * @opCode: the operation code represents commands which LLDD and fw recognized.
  * @payload: the command payload of each operation command.
+ * @nb: size in bytes of the command payload
+ * @responseQueue: queue to interrupt on w/ command response (if any)
  */
 int pm8001_mpi_build_cmd(struct pm8001_hba_info *pm8001_ha,
 			 struct inbound_queue_table *circularQ,
-			 u32 opCode, void *payload, u32 responseQueue)
+			 u32 opCode, void *payload, size_t nb,
+			 u32 responseQueue)
 {
 	u32 Header = 0, hpriority = 0, bc = 1, category = 0x02;
 	void *pMessage;
@@ -1350,10 +1353,13 @@ int pm8001_mpi_build_cmd(struct pm8001_hba_info *pm8001_ha,
 			pm8001_printk("No free mpi buffer\n"));
 		return -ENOMEM;
 	}
-	BUG_ON(!payload);
-	/*Copy to the payload*/
-	memcpy(pMessage, payload, (pm8001_ha->iomb_size -
-				sizeof(struct mpi_msg_hdr)));
+
+	if (nb > (pm8001_ha->iomb_size - sizeof(struct mpi_msg_hdr)))
+		nb = pm8001_ha->iomb_size - sizeof(struct mpi_msg_hdr);
+	memcpy(pMessage, payload, nb);
+	if (nb + sizeof(struct mpi_msg_hdr) < pm8001_ha->iomb_size)
+		memset(pMessage + nb, 0, pm8001_ha->iomb_size -
+				(nb + sizeof(struct mpi_msg_hdr)));
 
 	/*Build the header*/
 	Header = ((1 << 31) | (hpriority << 30) | ((bc & 0x1f) << 24)
@@ -1364,7 +1370,7 @@ int pm8001_mpi_build_cmd(struct pm8001_hba_info *pm8001_ha,
 	/*Update the PI to the firmware*/
 	pm8001_cw32(pm8001_ha, circularQ->pi_pci_bar,
 		circularQ->pi_offset, circularQ->producer_idx);
-	PM8001_IO_DBG(pm8001_ha,
+	PM8001_DEVIO_DBG(pm8001_ha,
 		pm8001_printk("INB Q %x OPCODE:%x , UPDATED PI=%d CI=%d\n",
 			responseQueue, opCode, circularQ->producer_idx,
 			circularQ->consumer_index));
@@ -1436,6 +1442,10 @@ u32 pm8001_mpi_msg_consume(struct pm8001_hba_info *pm8001_ha,
 			/* read header */
 			header_tmp = pm8001_read_32(msgHeader);
 			msgHeader_tmp = cpu_to_le32(header_tmp);
+			PM8001_DEVIO_DBG(pm8001_ha, pm8001_printk(
+				"outbound opcode msgheader:%x ci=%d pi=%d\n",
+				msgHeader_tmp, circularQ->consumer_idx,
+				circularQ->producer_index));
 			if (0 != (le32_to_cpu(msgHeader_tmp) & 0x80000000)) {
 				if (OPC_OUB_SKIP_ENTRY !=
 					(le32_to_cpu(msgHeader_tmp) & 0xfff)) {
@@ -1604,7 +1614,8 @@ void pm8001_work_fn(struct work_struct *work)
 				break;
 
 			default:
-				pm8001_printk("...query task failed!!!\n");
+				PM8001_DEVIO_DBG(pm8001_ha, pm8001_printk(
+					"...query task failed!!!\n"));
 				break;
 			});
 
@@ -1758,7 +1769,8 @@ static void pm8001_send_abort_all(struct pm8001_hba_info *pm8001_ha,
 	task_abort.device_id = cpu_to_le32(pm8001_ha_dev->device_id);
 	task_abort.tag = cpu_to_le32(ccb_tag);
 
-	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &task_abort, 0);
+	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &task_abort,
+			sizeof(task_abort), 0);
 	if (ret)
 		pm8001_tag_free(pm8001_ha, ccb_tag);
 
@@ -1831,7 +1843,8 @@ static void pm8001_send_read_log(struct pm8001_hba_info *pm8001_ha,
 	sata_cmd.ncqtag_atap_dir_m |= ((0x1 << 7) | (0x5 << 9));
 	memcpy(&sata_cmd.sata_fis, &fis, sizeof(struct host_to_dev_fis));
 
-	res = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &sata_cmd, 0);
+	res = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &sata_cmd,
+			sizeof(sata_cmd), 0);
 	if (res) {
 		sas_free_task(task);
 		pm8001_tag_free(pm8001_ha, ccb_tag);
@@ -1890,6 +1903,11 @@ mpi_ssp_completion(struct pm8001_hba_info *pm8001_ha , void *piomb)
 			pm8001_printk("SAS Address of IO Failure Drive:"
 			"%016llx", SAS_ADDR(t->dev->sas_addr)));
 
+	if (status)
+		PM8001_IOERR_DBG(pm8001_ha, pm8001_printk(
+			"status:0x%x, tag:0x%x, task:0x%p\n",
+			status, tag, t));
+
 	switch (status) {
 	case IO_SUCCESS:
 		PM8001_IO_DBG(pm8001_ha, pm8001_printk("IO_SUCCESS"
@@ -2072,7 +2090,7 @@ mpi_ssp_completion(struct pm8001_hba_info *pm8001_ha , void *piomb)
 		ts->open_rej_reason = SAS_OREJ_RSVD_RETRY;
 		break;
 	default:
-		PM8001_IO_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("Unknown status 0x%x\n", status));
 		/* not allowed case. Therefore, return failed status */
 		ts->resp = SAS_TASK_COMPLETE;
@@ -2125,7 +2143,7 @@ static void mpi_ssp_event(struct pm8001_hba_info *pm8001_ha , void *piomb)
 	if (unlikely(!t || !t->lldd_task || !t->dev))
 		return;
 	ts = &t->task_status;
-	PM8001_IO_DBG(pm8001_ha,
+	PM8001_DEVIO_DBG(pm8001_ha,
 		pm8001_printk("port_id = %x,device_id = %x\n",
 		port_id, dev_id));
 	switch (event) {
@@ -2263,7 +2281,7 @@ static void mpi_ssp_event(struct pm8001_hba_info *pm8001_ha , void *piomb)
 			pm8001_printk("  IO_XFER_CMD_FRAME_ISSUED\n"));
 		return;
 	default:
-		PM8001_IO_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("Unknown status 0x%x\n", event));
 		/* not allowed case. Therefore, return failed status */
 		ts->resp = SAS_TASK_COMPLETE;
@@ -2352,6 +2370,12 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
 			pm8001_printk("ts null\n"));
 		return;
 	}
+
+	if (status)
+		PM8001_IOERR_DBG(pm8001_ha, pm8001_printk(
+			"status:0x%x, tag:0x%x, task::0x%p\n",
+			status, tag, t));
+
 	/* Print sas address of IO failed device */
 	if ((status != IO_SUCCESS) && (status != IO_OVERFLOW) &&
 		(status != IO_UNDERFLOW)) {
@@ -2652,7 +2676,7 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
 		ts->open_rej_reason = SAS_OREJ_RSVD_RETRY;
 		break;
 	default:
-		PM8001_IO_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("Unknown status 0x%x\n", status));
 		/* not allowed case. Therefore, return failed status */
 		ts->resp = SAS_TASK_COMPLETE;
@@ -2723,7 +2747,7 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha , void *piomb)
 	if (unlikely(!t || !t->lldd_task || !t->dev))
 		return;
 	ts = &t->task_status;
-	PM8001_IO_DBG(pm8001_ha, pm8001_printk(
+	PM8001_DEVIO_DBG(pm8001_ha, pm8001_printk(
 		"port_id:0x%x, device_id:0x%x, tag:0x%x, event:0x%x\n",
 		port_id, dev_id, tag, event));
 	switch (event) {
@@ -2872,7 +2896,7 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha , void *piomb)
 		ts->stat = SAS_OPEN_TO;
 		break;
 	default:
-		PM8001_IO_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("Unknown status 0x%x\n", event));
 		/* not allowed case. Therefore, return failed status */
 		ts->resp = SAS_TASK_COMPLETE;
@@ -2917,9 +2941,13 @@ mpi_smp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
 	t = ccb->task;
 	ts = &t->task_status;
 	pm8001_dev = ccb->device;
-	if (status)
+	if (status) {
 		PM8001_FAIL_DBG(pm8001_ha,
 			pm8001_printk("smp IO status 0x%x\n", status));
+		PM8001_IOERR_DBG(pm8001_ha,
+			pm8001_printk("status:0x%x, tag:0x%x, task:0x%p\n",
+			status, tag, t));
+	}
 	if (unlikely(!t || !t->lldd_task || !t->dev))
 		return;
 
@@ -3070,7 +3098,7 @@ mpi_smp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
 		ts->open_rej_reason = SAS_OREJ_RSVD_RETRY;
 		break;
 	default:
-		PM8001_IO_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("Unknown status 0x%x\n", status));
 		ts->resp = SAS_TASK_COMPLETE;
 		ts->stat = SAS_DEV_NO_RESPONSE;
@@ -3355,7 +3383,8 @@ static void pm8001_hw_event_ack_req(struct pm8001_hba_info *pm8001_ha,
 		((phyId & 0x0F) << 4) | (port_id & 0x0F));
 	payload.param0 = cpu_to_le32(param0);
 	payload.param1 = cpu_to_le32(param1);
-	pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 }
 
 static int pm8001_chip_phy_ctl_req(struct pm8001_hba_info *pm8001_ha,
@@ -3416,7 +3445,7 @@ hw_event_sas_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb)
 		pm8001_get_lrate_mode(phy, link_rate);
 		break;
 	default:
-		PM8001_MSG_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("unknown device type(%x)\n", deviceType));
 		break;
 	}
@@ -3463,7 +3492,7 @@ hw_event_sata_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb)
 	struct sas_ha_struct *sas_ha = pm8001_ha->sas;
 	struct pm8001_phy *phy = &pm8001_ha->phy[phy_id];
 	unsigned long flags;
-	PM8001_MSG_DBG(pm8001_ha,
+	PM8001_DEVIO_DBG(pm8001_ha,
 		pm8001_printk("HW_EVENT_SATA_PHY_UP port id = %d,"
 		" phy id = %d\n", port_id, phy_id));
 	port->port_state =  portstate;
@@ -3541,7 +3570,7 @@ hw_event_phy_down(struct pm8001_hba_info *pm8001_ha, void *piomb)
 		break;
 	default:
 		port->port_attached = 0;
-		PM8001_MSG_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk(" phy Down and(default) = %x\n",
 			portstate));
 		break;
@@ -3689,7 +3718,7 @@ int pm8001_mpi_fw_flash_update_resp(struct pm8001_hba_info *pm8001_ha,
 			pm8001_printk(": FLASH_UPDATE_DISABLED\n"));
 		break;
 	default:
-		PM8001_MSG_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("No matched status = %d\n", status));
 		break;
 	}
@@ -3805,8 +3834,9 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void* piomb)
 	struct sas_ha_struct *sas_ha = pm8001_ha->sas;
 	struct pm8001_phy *phy = &pm8001_ha->phy[phy_id];
 	struct asd_sas_phy *sas_phy = sas_ha->sas_phy[phy_id];
-	PM8001_MSG_DBG(pm8001_ha,
-		pm8001_printk("outbound queue HW event & event type : "));
+	PM8001_DEVIO_DBG(pm8001_ha, pm8001_printk(
+		"SPC HW event for portid:%d, phyid:%d, event:%x, status:%x\n",
+		port_id, phy_id, eventType, status));
 	switch (eventType) {
 	case HW_EVENT_PHY_START_STATUS:
 		PM8001_MSG_DBG(pm8001_ha,
@@ -3990,7 +4020,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void* piomb)
 			pm8001_printk("EVENT_BROADCAST_ASYNCH_EVENT\n"));
 		break;
 	default:
-		PM8001_MSG_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("Unknown event type = %x\n", eventType));
 		break;
 	}
@@ -4161,7 +4191,7 @@ static void process_one_iomb(struct pm8001_hba_info *pm8001_ha, void *piomb)
 			pm8001_printk("OPC_OUB_SAS_RE_INITIALIZE\n"));
 		break;
 	default:
-		PM8001_MSG_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("Unknown outbound Queue IOMB OPC = %x\n",
 			opc));
 		break;
@@ -4284,7 +4314,7 @@ static int pm8001_chip_smp_req(struct pm8001_hba_info *pm8001_ha,
 		cpu_to_le32((u32)sg_dma_len(&task->smp_task.smp_resp)-4);
 	build_smp_cmd(pm8001_dev->device_id, smp_cmd.tag, &smp_cmd);
 	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc,
-					(u32 *)&smp_cmd, 0);
+			&smp_cmd, sizeof(smp_cmd), 0);
 	if (rc)
 		goto err_out_2;
 
@@ -4352,7 +4382,8 @@ static int pm8001_chip_ssp_io_req(struct pm8001_hba_info *pm8001_ha,
 		ssp_cmd.len = cpu_to_le32(task->total_xfer_len);
 		ssp_cmd.esgl = 0;
 	}
-	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &ssp_cmd, 0);
+	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &ssp_cmd,
+			sizeof(ssp_cmd), 0);
 	return ret;
 }
 
@@ -4461,7 +4492,8 @@ static int pm8001_chip_sata_req(struct pm8001_hba_info *pm8001_ha,
 		}
 	}
 
-	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &sata_cmd, 0);
+	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &sata_cmd,
+			sizeof(sata_cmd), 0);
 	return ret;
 }
 
@@ -4496,7 +4528,8 @@ pm8001_chip_phy_start_req(struct pm8001_hba_info *pm8001_ha, u8 phy_id)
 	memcpy(payload.sas_identify.sas_addr,
 		pm8001_ha->sas_addr, SAS_ADDR_SIZE);
 	payload.sas_identify.phy_id = phy_id;
-	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opcode, &payload, 0);
+	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opcode, &payload,
+			sizeof(payload), 0);
 	return ret;
 }
 
@@ -4518,7 +4551,8 @@ static int pm8001_chip_phy_stop_req(struct pm8001_hba_info *pm8001_ha,
 	memset(&payload, 0, sizeof(payload));
 	payload.tag = cpu_to_le32(tag);
 	payload.phy_id = cpu_to_le32(phy_id);
-	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opcode, &payload, 0);
+	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opcode, &payload,
+			sizeof(payload), 0);
 	return ret;
 }
 
@@ -4577,7 +4611,8 @@ static int pm8001_chip_reg_dev_req(struct pm8001_hba_info *pm8001_ha,
 		cpu_to_le32(ITNT | (firstBurstSize * 0x10000));
 	memcpy(payload.sas_addr, pm8001_dev->sas_device->sas_addr,
 		SAS_ADDR_SIZE);
-	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 	return rc;
 }
 
@@ -4598,7 +4633,8 @@ int pm8001_chip_dereg_dev_req(struct pm8001_hba_info *pm8001_ha,
 	payload.device_id = cpu_to_le32(device_id);
 	PM8001_MSG_DBG(pm8001_ha,
 		pm8001_printk("unregister device device_id = %d\n", device_id));
-	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 	return ret;
 }
 
@@ -4621,7 +4657,8 @@ static int pm8001_chip_phy_ctl_req(struct pm8001_hba_info *pm8001_ha,
 	payload.tag = cpu_to_le32(1);
 	payload.phyop_phyid =
 		cpu_to_le32(((phy_op & 0xff) << 8) | (phyId & 0x0F));
-	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 	return ret;
 }
 
@@ -4649,6 +4686,9 @@ static irqreturn_t
 pm8001_chip_isr(struct pm8001_hba_info *pm8001_ha, u8 vec)
 {
 	pm8001_chip_interrupt_disable(pm8001_ha, vec);
+	PM8001_DEVIO_DBG(pm8001_ha, pm8001_printk(
+		"irq vec %d, ODMR:0x%x\n",
+		vec, pm8001_cr32(pm8001_ha, 0, 0x30)));
 	process_oq(pm8001_ha, vec);
 	pm8001_chip_interrupt_enable(pm8001_ha, vec);
 	return IRQ_HANDLED;
@@ -4672,7 +4712,8 @@ static int send_task_abort(struct pm8001_hba_info *pm8001_ha, u32 opc,
 		task_abort.device_id = cpu_to_le32(dev_id);
 		task_abort.tag = cpu_to_le32(cmd_tag);
 	}
-	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &task_abort, 0);
+	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &task_abort,
+			sizeof(task_abort), 0);
 	return ret;
 }
 
@@ -4729,7 +4770,8 @@ int pm8001_chip_ssp_tm_req(struct pm8001_hba_info *pm8001_ha,
 	if (pm8001_ha->chip_id != chip_8001)
 		sspTMCmd.ds_ads_m = 0x08;
 	circularQ = &pm8001_ha->inbnd_q_tbl[0];
-	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &sspTMCmd, 0);
+	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &sspTMCmd,
+			sizeof(sspTMCmd), 0);
 	return ret;
 }
 
@@ -4819,7 +4861,8 @@ int pm8001_chip_get_nvmd_req(struct pm8001_hba_info *pm8001_ha,
 	default:
 		break;
 	}
-	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &nvmd_req, 0);
+	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &nvmd_req,
+			sizeof(nvmd_req), 0);
 	if (rc) {
 		kfree(fw_control_context);
 		pm8001_tag_free(pm8001_ha, tag);
@@ -4903,7 +4946,8 @@ int pm8001_chip_set_nvmd_req(struct pm8001_hba_info *pm8001_ha,
 	default:
 		break;
 	}
-	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &nvmd_req, 0);
+	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &nvmd_req,
+			sizeof(nvmd_req), 0);
 	if (rc) {
 		kfree(fw_control_context);
 		pm8001_tag_free(pm8001_ha, tag);
@@ -4938,7 +4982,8 @@ pm8001_chip_fw_flash_update_build(struct pm8001_hba_info *pm8001_ha,
 		cpu_to_le32(lower_32_bits(le64_to_cpu(info->sgl.addr)));
 	payload.sgl_addr_hi =
 		cpu_to_le32(upper_32_bits(le64_to_cpu(info->sgl.addr)));
-	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 	return ret;
 }
 
@@ -4960,6 +5005,8 @@ pm8001_chip_fw_flash_update_req(struct pm8001_hba_info *pm8001_ha,
 	if (!fw_control_context)
 		return -ENOMEM;
 	fw_control = (struct fw_control_info *)&ioctl_payload->func_specific;
+	PM8001_DEVIO_DBG(pm8001_ha, pm8001_printk(
+		"dma fw_control context input length :%x\n", fw_control->len));
 	memcpy(buffer, fw_control->buffer, fw_control->len);
 	flash_update_info.sgl.addr = cpu_to_le64(phys_addr);
 	flash_update_info.sgl.im_len.len = cpu_to_le32(fw_control->len);
@@ -5083,7 +5130,8 @@ pm8001_chip_set_dev_state_req(struct pm8001_hba_info *pm8001_ha,
 	payload.tag = cpu_to_le32(tag);
 	payload.device_id = cpu_to_le32(pm8001_dev->device_id);
 	payload.nds = cpu_to_le32(state);
-	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 	return rc;
 
 }
@@ -5108,7 +5156,8 @@ pm8001_chip_sas_re_initialization(struct pm8001_hba_info *pm8001_ha)
 	payload.SSAHOLT = cpu_to_le32(0xd << 25);
 	payload.sata_hol_tmo = cpu_to_le32(80);
 	payload.open_reject_cmdretries_data_retries = cpu_to_le32(0xff00ff);
-	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 	if (rc)
 		pm8001_tag_free(pm8001_ha, tag);
 	return rc;
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index 3374f553c617..c6d9da7b546e 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -41,6 +41,19 @@
 #include <linux/slab.h>
 #include "pm8001_sas.h"
 #include "pm8001_chips.h"
+#include "pm80xx_hwi.h"
+
+static ulong logging_level = PM8001_FAIL_LOGGING | PM8001_IOERR_LOGGING;
+module_param(logging_level, ulong, 0644);
+MODULE_PARM_DESC(logging_level, " bits for enabling logging info.");
+
+static ulong link_rate = LINKRATE_15 | LINKRATE_30 | LINKRATE_60 | LINKRATE_120;
+module_param(link_rate, ulong, 0644);
+MODULE_PARM_DESC(link_rate, "Enable link rate.\n"
+		" 1: Link rate 1.5G\n"
+		" 2: Link rate 3.0G\n"
+		" 4: Link rate 6.0G\n"
+		" 8: Link rate 12.0G\n");
 
 static struct scsi_transport_template *pm8001_stt;
 
@@ -432,7 +445,7 @@ static int pm8001_ioremap(struct pm8001_hba_info *pm8001_ha)
 		} else {
 			pm8001_ha->io_mem[logicalBar].membase	= 0;
 			pm8001_ha->io_mem[logicalBar].memsize	= 0;
-			pm8001_ha->io_mem[logicalBar].memvirtaddr = 0;
+			pm8001_ha->io_mem[logicalBar].memvirtaddr = NULL;
 		}
 		logicalBar++;
 	}
@@ -466,7 +479,15 @@ static struct pm8001_hba_info *pm8001_pci_alloc(struct pci_dev *pdev,
 	pm8001_ha->sas = sha;
 	pm8001_ha->shost = shost;
 	pm8001_ha->id = pm8001_id++;
-	pm8001_ha->logging_level = 0x01;
+	pm8001_ha->logging_level = logging_level;
+	if (link_rate >= 1 && link_rate <= 15)
+		pm8001_ha->link_rate = (link_rate << 8);
+	else {
+		pm8001_ha->link_rate = LINKRATE_15 | LINKRATE_30 |
+			LINKRATE_60 | LINKRATE_120;
+		PM8001_FAIL_DBG(pm8001_ha, pm8001_printk(
+			"Setting link rate to default value\n"));
+	}
 	sprintf(pm8001_ha->name, "%s%d", DRV_NAME, pm8001_ha->id);
 	/* IOMB size is 128 for 8088/89 controllers */
 	if (pm8001_ha->chip_id != chip_8001)
@@ -873,7 +894,6 @@ static u32 pm8001_setup_msix(struct pm8001_hba_info *pm8001_ha)
 	u32 number_of_intr;
 	int flag = 0;
 	int rc;
-	static char intr_drvname[PM8001_MAX_MSIX_VEC][sizeof(DRV_NAME)+3];
 
 	/* SPCv controllers supports 64 msi-x */
 	if (pm8001_ha->chip_id == chip_8001) {
@@ -894,14 +914,16 @@ static u32 pm8001_setup_msix(struct pm8001_hba_info *pm8001_ha)
 				rc, pm8001_ha->number_of_intr));
 
 	for (i = 0; i < number_of_intr; i++) {
-		snprintf(intr_drvname[i], sizeof(intr_drvname[0]),
-				DRV_NAME"%d", i);
+		snprintf(pm8001_ha->intr_drvname[i],
+			sizeof(pm8001_ha->intr_drvname[0]),
+			"%s-%d", pm8001_ha->name, i);
 		pm8001_ha->irq_vector[i].irq_id = i;
 		pm8001_ha->irq_vector[i].drv_inst = pm8001_ha;
 
 		rc = request_irq(pci_irq_vector(pm8001_ha->pdev, i),
 			pm8001_interrupt_handler_msix, flag,
-			intr_drvname[i], &(pm8001_ha->irq_vector[i]));
+			pm8001_ha->intr_drvname[i],
+			&(pm8001_ha->irq_vector[i]));
 		if (rc) {
 			for (j = 0; j < i; j++) {
 				free_irq(pci_irq_vector(pm8001_ha->pdev, i),
@@ -942,7 +964,7 @@ intx:
 	pm8001_ha->irq_vector[0].irq_id = 0;
 	pm8001_ha->irq_vector[0].drv_inst = pm8001_ha;
 	rc = request_irq(pdev->irq, pm8001_interrupt_handler_intx, IRQF_SHARED,
-		DRV_NAME, SHOST_TO_SAS_HA(pm8001_ha->shost));
+		pm8001_ha->name, SHOST_TO_SAS_HA(pm8001_ha->shost));
 	return rc;
 }
 
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index 7e48154e11c3..b7cbc312843e 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -119,7 +119,7 @@ int pm8001_mem_alloc(struct pci_dev *pdev, void **virt_addr,
 	mem_virt_alloc = dma_alloc_coherent(&pdev->dev, mem_size + align,
 					    &mem_dma_handle, GFP_KERNEL);
 	if (!mem_virt_alloc) {
-		pm8001_printk("memory allocation error\n");
+		pr_err("pm80xx: memory allocation error\n");
 		return -1;
 	}
 	*pphys_addr = mem_dma_handle;
@@ -249,6 +249,8 @@ int pm8001_phy_control(struct asd_sas_phy *sas_phy, enum phy_func func,
 		spin_unlock_irqrestore(&pm8001_ha->lock, flags);
 		return 0;
 	default:
+		PM8001_DEVIO_DBG(pm8001_ha,
+			pm8001_printk("func 0x%x\n", func));
 		rc = -EOPNOTSUPP;
 	}
 	msleep(300);
@@ -384,8 +386,9 @@ static int pm8001_task_exec(struct sas_task *task,
 	struct pm8001_port *port = NULL;
 	struct sas_task *t = task;
 	struct pm8001_ccb_info *ccb;
-	u32 tag = 0xdeadbeef, rc, n_elem = 0;
+	u32 tag = 0xdeadbeef, rc = 0, n_elem = 0;
 	unsigned long flags = 0;
+	enum sas_protocol task_proto = t->task_proto;
 
 	if (!dev->port) {
 		struct task_status_struct *tsm = &t->task_status;
@@ -410,7 +413,7 @@ static int pm8001_task_exec(struct sas_task *task,
 		pm8001_dev = dev->lldd_dev;
 		port = &pm8001_ha->port[sas_find_local_port_id(dev)];
 		if (DEV_IS_GONE(pm8001_dev) || !port->port_attached) {
-			if (sas_protocol_ata(t->task_proto)) {
+			if (sas_protocol_ata(task_proto)) {
 				struct task_status_struct *ts = &t->task_status;
 				ts->resp = SAS_TASK_UNDELIVERED;
 				ts->stat = SAS_PHY_DOWN;
@@ -432,7 +435,7 @@ static int pm8001_task_exec(struct sas_task *task,
 			goto err_out;
 		ccb = &pm8001_ha->ccb_info[tag];
 
-		if (!sas_protocol_ata(t->task_proto)) {
+		if (!sas_protocol_ata(task_proto)) {
 			if (t->num_scatter) {
 				n_elem = dma_map_sg(pm8001_ha->dev,
 					t->scatter,
@@ -452,7 +455,7 @@ static int pm8001_task_exec(struct sas_task *task,
 		ccb->ccb_tag = tag;
 		ccb->task = t;
 		ccb->device = pm8001_dev;
-		switch (t->task_proto) {
+		switch (task_proto) {
 		case SAS_PROTOCOL_SMP:
 			rc = pm8001_task_prep_smp(pm8001_ha, ccb);
 			break;
@@ -469,8 +472,7 @@ static int pm8001_task_exec(struct sas_task *task,
 			break;
 		default:
 			dev_printk(KERN_ERR, pm8001_ha->dev,
-				"unknown sas_task proto: 0x%x\n",
-				t->task_proto);
+				"unknown sas_task proto: 0x%x\n", task_proto);
 			rc = -EINVAL;
 			break;
 		}
@@ -493,7 +495,7 @@ err_out_tag:
 	pm8001_tag_free(pm8001_ha, tag);
 err_out:
 	dev_printk(KERN_ERR, pm8001_ha->dev, "pm8001 exec failed[%d]!\n", rc);
-	if (!sas_protocol_ata(t->task_proto))
+	if (!sas_protocol_ata(task_proto))
 		if (n_elem)
 			dma_unmap_sg(pm8001_ha->dev, t->scatter, t->num_scatter,
 				t->data_dir);
@@ -1179,7 +1181,7 @@ int pm8001_query_task(struct sas_task *task)
 			break;
 		}
 	}
-	pm8001_printk(":rc= %d\n", rc);
+	pr_err("pm80xx: rc= %d\n", rc);
 	return rc;
 }
 
@@ -1202,8 +1204,8 @@ int pm8001_abort_task(struct sas_task *task)
 	pm8001_dev = dev->lldd_dev;
 	pm8001_ha = pm8001_find_ha_by_dev(dev);
 	phy_id = pm8001_dev->attached_phy;
-	rc = pm8001_find_tag(task, &tag);
-	if (rc == 0) {
+	ret = pm8001_find_tag(task, &tag);
+	if (ret == 0) {
 		pm8001_printk("no tag for task:%p\n", task);
 		return TMF_RESP_FUNC_FAILED;
 	}
@@ -1241,26 +1243,50 @@ int pm8001_abort_task(struct sas_task *task)
 
 			/* 2. Send Phy Control Hard Reset */
 			reinit_completion(&completion);
+			phy->port_reset_status = PORT_RESET_TMO;
 			phy->reset_success = false;
 			phy->enable_completion = &completion;
 			phy->reset_completion = &completion_reset;
 			ret = PM8001_CHIP_DISP->phy_ctl_req(pm8001_ha, phy_id,
 				PHY_HARD_RESET);
-			if (ret)
-				goto out;
-			PM8001_MSG_DBG(pm8001_ha,
-				pm8001_printk("Waiting for local phy ctl\n"));
-			wait_for_completion(&completion);
-			if (!phy->reset_success)
+			if (ret) {
+				phy->enable_completion = NULL;
+				phy->reset_completion = NULL;
 				goto out;
+			}
 
-			/* 3. Wait for Port Reset complete / Port reset TMO */
+			/* In the case of the reset timeout/fail we still
+			 * abort the command at the firmware. The assumption
+			 * here is that the drive is off doing something so
+			 * that it's not processing requests, and we want to
+			 * avoid getting a completion for this and either
+			 * leaking the task in libsas or losing the race and
+			 * getting a double free.
+			 */
 			PM8001_MSG_DBG(pm8001_ha,
+				pm8001_printk("Waiting for local phy ctl\n"));
+			ret = wait_for_completion_timeout(&completion,
+					PM8001_TASK_TIMEOUT * HZ);
+			if (!ret || !phy->reset_success) {
+				phy->enable_completion = NULL;
+				phy->reset_completion = NULL;
+			} else {
+				/* 3. Wait for Port Reset complete or
+				 * Port reset TMO
+				 */
+				PM8001_MSG_DBG(pm8001_ha,
 				pm8001_printk("Waiting for Port reset\n"));
-			wait_for_completion(&completion_reset);
-			if (phy->port_reset_status) {
-				pm8001_dev_gone_notify(dev);
-				goto out;
+				ret = wait_for_completion_timeout(
+					&completion_reset,
+					PM8001_TASK_TIMEOUT * HZ);
+				if (!ret)
+					phy->reset_completion = NULL;
+				WARN_ON(phy->port_reset_status ==
+						PORT_RESET_TMO);
+				if (phy->port_reset_status == PORT_RESET_TMO) {
+					pm8001_dev_gone_notify(dev);
+					goto out;
+				}
 			}
 
 			/*
diff --git a/drivers/scsi/pm8001/pm8001_sas.h b/drivers/scsi/pm8001/pm8001_sas.h
index ff17c6aff63d..93438c8f67da 100644
--- a/drivers/scsi/pm8001/pm8001_sas.h
+++ b/drivers/scsi/pm8001/pm8001_sas.h
@@ -66,8 +66,11 @@
 #define PM8001_EH_LOGGING	0x10 /* libsas EH function logging*/
 #define PM8001_IOCTL_LOGGING	0x20 /* IOCTL message logging */
 #define PM8001_MSG_LOGGING	0x40 /* misc message logging */
-#define pm8001_printk(format, arg...)	printk(KERN_INFO "pm80xx %s %d:" \
-			format, __func__, __LINE__, ## arg)
+#define PM8001_DEV_LOGGING	0x80 /* development message logging */
+#define PM8001_DEVIO_LOGGING	0x100 /* development io message logging */
+#define PM8001_IOERR_LOGGING	0x200 /* development io err message logging */
+#define pm8001_printk(format, arg...)	pr_info("%s:: %s  %d:" \
+			format, pm8001_ha->name, __func__, __LINE__, ## arg)
 #define PM8001_CHECK_LOGGING(HBA, LEVEL, CMD)	\
 do {						\
 	if (unlikely(HBA->logging_level & LEVEL))	\
@@ -97,6 +100,14 @@ do {						\
 #define PM8001_MSG_DBG(HBA, CMD)		\
 	PM8001_CHECK_LOGGING(HBA, PM8001_MSG_LOGGING, CMD)
 
+#define PM8001_DEV_DBG(HBA, CMD)		\
+	PM8001_CHECK_LOGGING(HBA, PM8001_DEV_LOGGING, CMD)
+
+#define PM8001_DEVIO_DBG(HBA, CMD)		\
+	PM8001_CHECK_LOGGING(HBA, PM8001_DEVIO_LOGGING, CMD)
+
+#define PM8001_IOERR_DBG(HBA, CMD)		\
+	PM8001_CHECK_LOGGING(HBA, PM8001_IOERR_LOGGING, CMD)
 
 #define PM8001_USE_TASKLET
 #define PM8001_USE_MSIX
@@ -141,6 +152,8 @@ struct pm8001_ioctl_payload {
 #define MPI_FATAL_EDUMP_TABLE_HANDSHAKE            0x0C     /* FDDHSHK */
 #define MPI_FATAL_EDUMP_TABLE_STATUS               0x10     /* FDDTSTAT */
 #define MPI_FATAL_EDUMP_TABLE_ACCUM_LEN            0x14     /* ACCDDLEN */
+#define MPI_FATAL_EDUMP_TABLE_TOTAL_LEN		   0x18	    /* TOTALLEN */
+#define MPI_FATAL_EDUMP_TABLE_SIGNATURE		   0x1C     /* SIGNITURE */
 #define MPI_FATAL_EDUMP_HANDSHAKE_RDY              0x1
 #define MPI_FATAL_EDUMP_HANDSHAKE_BUSY             0x0
 #define MPI_FATAL_EDUMP_TABLE_STAT_RSVD                 0x0
@@ -496,6 +509,7 @@ struct pm8001_hba_info {
 	u32			forensic_last_offset;
 	u32			fatal_forensic_shift_offset;
 	u32			forensic_fatal_step;
+	u32			forensic_preserved_accumulated_transfer;
 	u32			evtlog_ib_offset;
 	u32			evtlog_ob_offset;
 	void __iomem	*msg_unit_tbl_addr;/*Message Unit Table Addr*/
@@ -530,11 +544,14 @@ struct pm8001_hba_info {
 	struct pm8001_ccb_info	*ccb_info;
 #ifdef PM8001_USE_MSIX
 	int			number_of_intr;/*will be used in remove()*/
+	char			intr_drvname[PM8001_MAX_MSIX_VEC]
+				[PM8001_NAME_LENGTH+1+3+1];
 #endif
 #ifdef PM8001_USE_TASKLET
 	struct tasklet_struct	tasklet[PM8001_MAX_MSIX_VEC];
 #endif
 	u32			logging_level;
+	u32			link_rate;
 	u32			fw_status;
 	u32			smp_exp_mode;
 	bool			controller_fatal_error;
@@ -663,7 +680,8 @@ int pm8001_mem_alloc(struct pci_dev *pdev, void **virt_addr,
 void pm8001_chip_iounmap(struct pm8001_hba_info *pm8001_ha);
 int pm8001_mpi_build_cmd(struct pm8001_hba_info *pm8001_ha,
 			struct inbound_queue_table *circularQ,
-			u32 opCode, void *payload, u32 responseQueue);
+			u32 opCode, void *payload, size_t nb,
+			u32 responseQueue);
 int pm8001_mpi_msg_free_get(struct inbound_queue_table *circularQ,
 				u16 messageSize, void **messagePtr);
 u32 pm8001_mpi_msg_free_set(struct pm8001_hba_info *pm8001_ha, void *pMsg,
diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c
index 73261902d75d..19601138e889 100644
--- a/drivers/scsi/pm8001/pm80xx_hwi.c
+++ b/drivers/scsi/pm8001/pm80xx_hwi.c
@@ -37,6 +37,7 @@
  * POSSIBILITY OF SUCH DAMAGES.
  *
  */
+ #include <linux/version.h>
  #include <linux/slab.h>
  #include "pm8001_sas.h"
  #include "pm80xx_hwi.h"
@@ -75,7 +76,7 @@ void pm80xx_pci_mem_copy(struct pm8001_hba_info  *pm8001_ha, u32 soffset,
 	destination1 = (u32 *)destination;
 
 	for (index = 0; index < dw_count; index += 4, destination1++) {
-		offset = (soffset + index / 4);
+		offset = (soffset + index);
 		if (offset < (64 * 1024)) {
 			value = pm8001_cr32(pm8001_ha, bus_base_number, offset);
 			*destination1 =  cpu_to_le32(value);
@@ -92,9 +93,12 @@ ssize_t pm80xx_get_fatal_dump(struct device *cdev,
 	struct pm8001_hba_info *pm8001_ha = sha->lldd_ha;
 	void __iomem *fatal_table_address = pm8001_ha->fatal_tbl_addr;
 	u32 accum_len , reg_val, index, *temp;
+	u32 status = 1;
 	unsigned long start;
 	u8 *direct_data;
 	char *fatal_error_data = buf;
+	u32 length_to_read;
+	u32 offset;
 
 	pm8001_ha->forensic_info.data_buf.direct_data = buf;
 	if (pm8001_ha->chip_id == chip_8001) {
@@ -104,16 +108,35 @@ ssize_t pm80xx_get_fatal_dump(struct device *cdev,
 		return (char *)pm8001_ha->forensic_info.data_buf.direct_data -
 			(char *)buf;
 	}
+	/* initialize variables for very first call from host application */
 	if (pm8001_ha->forensic_info.data_buf.direct_offset == 0) {
 		PM8001_IO_DBG(pm8001_ha,
 		pm8001_printk("forensic_info TYPE_NON_FATAL..............\n"));
 		direct_data = (u8 *)fatal_error_data;
 		pm8001_ha->forensic_info.data_type = TYPE_NON_FATAL;
 		pm8001_ha->forensic_info.data_buf.direct_len = SYSFS_OFFSET;
+		pm8001_ha->forensic_info.data_buf.direct_offset = 0;
 		pm8001_ha->forensic_info.data_buf.read_len = 0;
+		pm8001_ha->forensic_preserved_accumulated_transfer = 0;
 
-		pm8001_ha->forensic_info.data_buf.direct_data = direct_data;
+		/* Write signature to fatal dump table */
+		pm8001_mw32(fatal_table_address,
+				MPI_FATAL_EDUMP_TABLE_SIGNATURE, 0x1234abcd);
 
+		pm8001_ha->forensic_info.data_buf.direct_data = direct_data;
+		PM8001_IO_DBG(pm8001_ha,
+			pm8001_printk("ossaHwCB: status1 %d\n", status));
+		PM8001_IO_DBG(pm8001_ha,
+			pm8001_printk("ossaHwCB: read_len 0x%x\n",
+			pm8001_ha->forensic_info.data_buf.read_len));
+		PM8001_IO_DBG(pm8001_ha,
+			pm8001_printk("ossaHwCB: direct_len 0x%x\n",
+			pm8001_ha->forensic_info.data_buf.direct_len));
+		PM8001_IO_DBG(pm8001_ha,
+			pm8001_printk("ossaHwCB: direct_offset 0x%x\n",
+			pm8001_ha->forensic_info.data_buf.direct_offset));
+	}
+	if (pm8001_ha->forensic_info.data_buf.direct_offset == 0) {
 		/* start to get data */
 		/* Program the MEMBASE II Shifting Register with 0x00.*/
 		pm8001_cw32(pm8001_ha, 0, MEMBASE_II_SHIFT_REGISTER,
@@ -126,30 +149,66 @@ ssize_t pm80xx_get_fatal_dump(struct device *cdev,
 	/* Read until accum_len is retrived */
 	accum_len = pm8001_mr32(fatal_table_address,
 				MPI_FATAL_EDUMP_TABLE_ACCUM_LEN);
-	PM8001_IO_DBG(pm8001_ha, pm8001_printk("accum_len 0x%x\n",
-						accum_len));
+	/* Determine length of data between previously stored transfer length
+	 * and current accumulated transfer length
+	 */
+	length_to_read =
+		accum_len - pm8001_ha->forensic_preserved_accumulated_transfer;
+	PM8001_IO_DBG(pm8001_ha,
+		pm8001_printk("get_fatal_spcv: accum_len 0x%x\n", accum_len));
+	PM8001_IO_DBG(pm8001_ha,
+		pm8001_printk("get_fatal_spcv: length_to_read 0x%x\n",
+		length_to_read));
+	PM8001_IO_DBG(pm8001_ha,
+		pm8001_printk("get_fatal_spcv: last_offset 0x%x\n",
+		pm8001_ha->forensic_last_offset));
+	PM8001_IO_DBG(pm8001_ha,
+		pm8001_printk("get_fatal_spcv: read_len 0x%x\n",
+		pm8001_ha->forensic_info.data_buf.read_len));
+	PM8001_IO_DBG(pm8001_ha,
+		pm8001_printk("get_fatal_spcv:: direct_len 0x%x\n",
+		pm8001_ha->forensic_info.data_buf.direct_len));
+	PM8001_IO_DBG(pm8001_ha,
+		pm8001_printk("get_fatal_spcv:: direct_offset 0x%x\n",
+		pm8001_ha->forensic_info.data_buf.direct_offset));
+
+	/* If accumulated length failed to read correctly fail the attempt.*/
 	if (accum_len == 0xFFFFFFFF) {
 		PM8001_IO_DBG(pm8001_ha,
 			pm8001_printk("Possible PCI issue 0x%x not expected\n",
-				accum_len));
-		return -EIO;
+			accum_len));
+		return status;
 	}
-	if (accum_len == 0 || accum_len >= 0x100000) {
+	/* If accumulated length is zero fail the attempt */
+	if (accum_len == 0) {
 		pm8001_ha->forensic_info.data_buf.direct_data +=
 			sprintf(pm8001_ha->forensic_info.data_buf.direct_data,
-				"%08x ", 0xFFFFFFFF);
+			"%08x ", 0xFFFFFFFF);
 		return (char *)pm8001_ha->forensic_info.data_buf.direct_data -
 			(char *)buf;
 	}
+	/* Accumulated length is good so start capturing the first data */
 	temp = (u32 *)pm8001_ha->memoryMap.region[FORENSIC_MEM].virt_ptr;
 	if (pm8001_ha->forensic_fatal_step == 0) {
 moreData:
+		/* If data to read is less than SYSFS_OFFSET then reduce the
+		 * length of dataLen
+		 */
+		if (pm8001_ha->forensic_last_offset + SYSFS_OFFSET
+				> length_to_read) {
+			pm8001_ha->forensic_info.data_buf.direct_len =
+				length_to_read -
+				pm8001_ha->forensic_last_offset;
+		} else {
+			pm8001_ha->forensic_info.data_buf.direct_len =
+				SYSFS_OFFSET;
+		}
 		if (pm8001_ha->forensic_info.data_buf.direct_data) {
 			/* Data is in bar, copy to host memory */
-			pm80xx_pci_mem_copy(pm8001_ha, pm8001_ha->fatal_bar_loc,
-			 pm8001_ha->memoryMap.region[FORENSIC_MEM].virt_ptr,
-				pm8001_ha->forensic_info.data_buf.direct_len ,
-					1);
+			pm80xx_pci_mem_copy(pm8001_ha,
+			pm8001_ha->fatal_bar_loc,
+			pm8001_ha->memoryMap.region[FORENSIC_MEM].virt_ptr,
+			pm8001_ha->forensic_info.data_buf.direct_len, 1);
 		}
 		pm8001_ha->fatal_bar_loc +=
 			pm8001_ha->forensic_info.data_buf.direct_len;
@@ -160,21 +219,29 @@ moreData:
 		pm8001_ha->forensic_info.data_buf.read_len =
 			pm8001_ha->forensic_info.data_buf.direct_len;
 
-		if (pm8001_ha->forensic_last_offset  >= accum_len) {
+		if (pm8001_ha->forensic_last_offset  >= length_to_read) {
 			pm8001_ha->forensic_info.data_buf.direct_data +=
 			sprintf(pm8001_ha->forensic_info.data_buf.direct_data,
 				"%08x ", 3);
-			for (index = 0; index < (SYSFS_OFFSET / 4); index++) {
+			for (index = 0; index <
+				(pm8001_ha->forensic_info.data_buf.direct_len
+				 / 4); index++) {
 				pm8001_ha->forensic_info.data_buf.direct_data +=
-					sprintf(pm8001_ha->
-					 forensic_info.data_buf.direct_data,
-						"%08x ", *(temp + index));
+				sprintf(
+				pm8001_ha->forensic_info.data_buf.direct_data,
+				"%08x ", *(temp + index));
 			}
 
 			pm8001_ha->fatal_bar_loc = 0;
 			pm8001_ha->forensic_fatal_step = 1;
 			pm8001_ha->fatal_forensic_shift_offset = 0;
 			pm8001_ha->forensic_last_offset	= 0;
+			status = 0;
+			offset = (int)
+			((char *)pm8001_ha->forensic_info.data_buf.direct_data
+			- (char *)buf);
+			PM8001_IO_DBG(pm8001_ha,
+			pm8001_printk("get_fatal_spcv:return1 0x%x\n", offset));
 			return (char *)pm8001_ha->
 				forensic_info.data_buf.direct_data -
 				(char *)buf;
@@ -184,12 +251,20 @@ moreData:
 				sprintf(pm8001_ha->
 					forensic_info.data_buf.direct_data,
 					"%08x ", 2);
-			for (index = 0; index < (SYSFS_OFFSET / 4); index++) {
-				pm8001_ha->forensic_info.data_buf.direct_data +=
-					sprintf(pm8001_ha->
+			for (index = 0; index <
+				(pm8001_ha->forensic_info.data_buf.direct_len
+				 / 4); index++) {
+				pm8001_ha->forensic_info.data_buf.direct_data
+					+= sprintf(pm8001_ha->
 					forensic_info.data_buf.direct_data,
 					"%08x ", *(temp + index));
 			}
+			status = 0;
+			offset = (int)
+			((char *)pm8001_ha->forensic_info.data_buf.direct_data
+			- (char *)buf);
+			PM8001_IO_DBG(pm8001_ha,
+			pm8001_printk("get_fatal_spcv:return2 0x%x\n", offset));
 			return (char *)pm8001_ha->
 				forensic_info.data_buf.direct_data -
 				(char *)buf;
@@ -199,63 +274,122 @@ moreData:
 		pm8001_ha->forensic_info.data_buf.direct_data +=
 			sprintf(pm8001_ha->forensic_info.data_buf.direct_data,
 				"%08x ", 2);
-		for (index = 0; index < 256; index++) {
+		for (index = 0; index <
+			(pm8001_ha->forensic_info.data_buf.direct_len
+			 / 4) ; index++) {
 			pm8001_ha->forensic_info.data_buf.direct_data +=
 				sprintf(pm8001_ha->
-					forensic_info.data_buf.direct_data,
-						"%08x ", *(temp + index));
+				forensic_info.data_buf.direct_data,
+				"%08x ", *(temp + index));
 		}
 		pm8001_ha->fatal_forensic_shift_offset += 0x100;
 		pm8001_cw32(pm8001_ha, 0, MEMBASE_II_SHIFT_REGISTER,
 			pm8001_ha->fatal_forensic_shift_offset);
 		pm8001_ha->fatal_bar_loc = 0;
+		status = 0;
+		offset = (int)
+			((char *)pm8001_ha->forensic_info.data_buf.direct_data
+			- (char *)buf);
+		PM8001_IO_DBG(pm8001_ha,
+		pm8001_printk("get_fatal_spcv: return3 0x%x\n", offset));
 		return (char *)pm8001_ha->forensic_info.data_buf.direct_data -
 			(char *)buf;
 	}
 	if (pm8001_ha->forensic_fatal_step == 1) {
-		pm8001_ha->fatal_forensic_shift_offset = 0;
-		/* Read 64K of the debug data. */
-		pm8001_cw32(pm8001_ha, 0, MEMBASE_II_SHIFT_REGISTER,
-			pm8001_ha->fatal_forensic_shift_offset);
-		pm8001_mw32(fatal_table_address,
-			MPI_FATAL_EDUMP_TABLE_HANDSHAKE,
+		/* store previous accumulated length before triggering next
+		 * accumulated length update
+		 */
+		pm8001_ha->forensic_preserved_accumulated_transfer =
+			pm8001_mr32(fatal_table_address,
+			MPI_FATAL_EDUMP_TABLE_ACCUM_LEN);
+
+		/* continue capturing the fatal log until Dump status is 0x3 */
+		if (pm8001_mr32(fatal_table_address,
+			MPI_FATAL_EDUMP_TABLE_STATUS) <
+			MPI_FATAL_EDUMP_TABLE_STAT_NF_SUCCESS_DONE) {
+
+			/* reset fddstat bit by writing to zero*/
+			pm8001_mw32(fatal_table_address,
+					MPI_FATAL_EDUMP_TABLE_STATUS, 0x0);
+
+			/* set dump control value to '1' so that new data will
+			 * be transferred to shared memory
+			 */
+			pm8001_mw32(fatal_table_address,
+				MPI_FATAL_EDUMP_TABLE_HANDSHAKE,
 				MPI_FATAL_EDUMP_HANDSHAKE_RDY);
 
-		/* Poll FDDHSHK  until clear  */
-		start = jiffies + (2 * HZ); /* 2 sec */
+			/*Poll FDDHSHK  until clear */
+			start = jiffies + (2 * HZ); /* 2 sec */
 
-		do {
-			reg_val = pm8001_mr32(fatal_table_address,
+			do {
+				reg_val = pm8001_mr32(fatal_table_address,
 					MPI_FATAL_EDUMP_TABLE_HANDSHAKE);
-		} while ((reg_val) && time_before(jiffies, start));
+			} while ((reg_val) && time_before(jiffies, start));
 
-		if (reg_val != 0) {
-			PM8001_FAIL_DBG(pm8001_ha,
-			pm8001_printk("TIMEOUT:MEMBASE_II_SHIFT_REGISTER"
-			" = 0x%x\n", reg_val));
-			return -EIO;
-		}
-
-		/* Read the next 64K of the debug data. */
-		pm8001_ha->forensic_fatal_step = 0;
-		if (pm8001_mr32(fatal_table_address,
-			MPI_FATAL_EDUMP_TABLE_STATUS) !=
-				MPI_FATAL_EDUMP_TABLE_STAT_NF_SUCCESS_DONE) {
-			pm8001_mw32(fatal_table_address,
-				MPI_FATAL_EDUMP_TABLE_HANDSHAKE, 0);
-			goto moreData;
-		} else {
-			pm8001_ha->forensic_info.data_buf.direct_data +=
-				sprintf(pm8001_ha->
-					forensic_info.data_buf.direct_data,
-						"%08x ", 4);
-			pm8001_ha->forensic_info.data_buf.read_len = 0xFFFFFFFF;
-			pm8001_ha->forensic_info.data_buf.direct_len =  0;
-			pm8001_ha->forensic_info.data_buf.direct_offset = 0;
-			pm8001_ha->forensic_info.data_buf.read_len = 0;
+			if (reg_val != 0) {
+				PM8001_FAIL_DBG(pm8001_ha, pm8001_printk(
+				"TIMEOUT:MPI_FATAL_EDUMP_TABLE_HDSHAKE 0x%x\n",
+				reg_val));
+			       /* Fail the dump if a timeout occurs */
+				pm8001_ha->forensic_info.data_buf.direct_data +=
+				sprintf(
+				pm8001_ha->forensic_info.data_buf.direct_data,
+				"%08x ", 0xFFFFFFFF);
+				return((char *)
+				pm8001_ha->forensic_info.data_buf.direct_data
+				- (char *)buf);
+			}
+			/* Poll status register until set to 2 or
+			 * 3 for up to 2 seconds
+			 */
+			start = jiffies + (2 * HZ); /* 2 sec */
+
+			do {
+				reg_val = pm8001_mr32(fatal_table_address,
+					MPI_FATAL_EDUMP_TABLE_STATUS);
+			} while (((reg_val != 2) || (reg_val != 3)) &&
+					time_before(jiffies, start));
+
+			if (reg_val < 2) {
+				PM8001_FAIL_DBG(pm8001_ha, pm8001_printk(
+				"TIMEOUT:MPI_FATAL_EDUMP_TABLE_STATUS = 0x%x\n",
+				reg_val));
+				/* Fail the dump if a timeout occurs */
+				pm8001_ha->forensic_info.data_buf.direct_data +=
+				sprintf(
+				pm8001_ha->forensic_info.data_buf.direct_data,
+				"%08x ", 0xFFFFFFFF);
+				pm8001_cw32(pm8001_ha, 0,
+					MEMBASE_II_SHIFT_REGISTER,
+					pm8001_ha->fatal_forensic_shift_offset);
+			}
+			/* Read the next block of the debug data.*/
+			length_to_read = pm8001_mr32(fatal_table_address,
+			MPI_FATAL_EDUMP_TABLE_ACCUM_LEN) -
+			pm8001_ha->forensic_preserved_accumulated_transfer;
+			if (length_to_read != 0x0) {
+				pm8001_ha->forensic_fatal_step = 0;
+				goto moreData;
+			} else {
+				pm8001_ha->forensic_info.data_buf.direct_data +=
+				sprintf(
+				pm8001_ha->forensic_info.data_buf.direct_data,
+				"%08x ", 4);
+				pm8001_ha->forensic_info.data_buf.read_len
+								= 0xFFFFFFFF;
+				pm8001_ha->forensic_info.data_buf.direct_len
+								=  0;
+				pm8001_ha->forensic_info.data_buf.direct_offset
+								= 0;
+				pm8001_ha->forensic_info.data_buf.read_len = 0;
+			}
 		}
 	}
-
+	offset = (int)((char *)pm8001_ha->forensic_info.data_buf.direct_data
+			- (char *)buf);
+	PM8001_IO_DBG(pm8001_ha,
+		pm8001_printk("get_fatal_spcv: return4 0x%x\n", offset));
 	return (char *)pm8001_ha->forensic_info.data_buf.direct_data -
 		(char *)buf;
 }
@@ -317,6 +451,25 @@ static void read_main_config_table(struct pm8001_hba_info *pm8001_ha)
 		pm8001_mr32(address, MAIN_MPI_ILA_RELEASE_TYPE);
 	pm8001_ha->main_cfg_tbl.pm80xx_tbl.inc_fw_version =
 		pm8001_mr32(address, MAIN_MPI_INACTIVE_FW_VERSION);
+
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"Main cfg table: sign:%x interface rev:%x fw_rev:%x\n",
+		pm8001_ha->main_cfg_tbl.pm80xx_tbl.signature,
+		pm8001_ha->main_cfg_tbl.pm80xx_tbl.interface_rev,
+		pm8001_ha->main_cfg_tbl.pm80xx_tbl.firmware_rev));
+
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"table offset: gst:%x iq:%x oq:%x int vec:%x phy attr:%x\n",
+		pm8001_ha->main_cfg_tbl.pm80xx_tbl.gst_offset,
+		pm8001_ha->main_cfg_tbl.pm80xx_tbl.inbound_queue_offset,
+		pm8001_ha->main_cfg_tbl.pm80xx_tbl.outbound_queue_offset,
+		pm8001_ha->main_cfg_tbl.pm80xx_tbl.int_vec_table_offset,
+		pm8001_ha->main_cfg_tbl.pm80xx_tbl.phy_attr_table_offset));
+
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"Main cfg table; ila rev:%x Inactive fw rev:%x\n",
+		pm8001_ha->main_cfg_tbl.pm80xx_tbl.ila_version,
+		pm8001_ha->main_cfg_tbl.pm80xx_tbl.inc_fw_version));
 }
 
 /**
@@ -521,6 +674,11 @@ static void init_default_table_values(struct pm8001_hba_info *pm8001_ha)
 			pm8001_mr32(addressib, (offsetib + 0x18));
 		pm8001_ha->inbnd_q_tbl[i].producer_idx		= 0;
 		pm8001_ha->inbnd_q_tbl[i].consumer_index	= 0;
+
+		PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+			"IQ %d pi_bar 0x%x pi_offset 0x%x\n", i,
+			pm8001_ha->inbnd_q_tbl[i].pi_pci_bar,
+			pm8001_ha->inbnd_q_tbl[i].pi_offset));
 	}
 	for (i = 0; i < PM8001_MAX_SPCV_OUTB_NUM; i++) {
 		pm8001_ha->outbnd_q_tbl[i].element_size_cnt	=
@@ -549,6 +707,11 @@ static void init_default_table_values(struct pm8001_hba_info *pm8001_ha)
 			pm8001_mr32(addressob, (offsetob + 0x18));
 		pm8001_ha->outbnd_q_tbl[i].consumer_idx		= 0;
 		pm8001_ha->outbnd_q_tbl[i].producer_index	= 0;
+
+		PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+			"OQ %d ci_bar 0x%x ci_offset 0x%x\n", i,
+			pm8001_ha->outbnd_q_tbl[i].ci_pci_bar,
+			pm8001_ha->outbnd_q_tbl[i].ci_offset));
 	}
 }
 
@@ -582,6 +745,10 @@ static void update_main_config_table(struct pm8001_hba_info *pm8001_ha)
 					((pm8001_ha->number_of_intr - 1) << 8);
 	pm8001_mw32(address, MAIN_FATAL_ERROR_INTERRUPT,
 		pm8001_ha->main_cfg_tbl.pm80xx_tbl.fatal_err_interrupt);
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"Updated Fatal error interrupt vector 0x%x\n",
+		pm8001_mr32(address, MAIN_FATAL_ERROR_INTERRUPT)));
+
 	pm8001_mw32(address, MAIN_EVENT_CRC_CHECK,
 		pm8001_ha->main_cfg_tbl.pm80xx_tbl.crc_core_dump);
 
@@ -591,6 +758,9 @@ static void update_main_config_table(struct pm8001_hba_info *pm8001_ha)
 	pm8001_ha->main_cfg_tbl.pm80xx_tbl.gpio_led_mapping |= 0x20000000;
 	pm8001_mw32(address, MAIN_GPIO_LED_FLAGS_OFFSET,
 		pm8001_ha->main_cfg_tbl.pm80xx_tbl.gpio_led_mapping);
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"Programming DW 0x21 in main cfg table with 0x%x\n",
+		pm8001_mr32(address, MAIN_GPIO_LED_FLAGS_OFFSET)));
 
 	pm8001_mw32(address, MAIN_PORT_RECOVERY_TIMER,
 		pm8001_ha->main_cfg_tbl.pm80xx_tbl.port_recovery_timer);
@@ -629,6 +799,21 @@ static void update_inbnd_queue_table(struct pm8001_hba_info *pm8001_ha,
 		pm8001_ha->inbnd_q_tbl[number].ci_upper_base_addr);
 	pm8001_mw32(address, offset + IB_CI_BASE_ADDR_LO_OFFSET,
 		pm8001_ha->inbnd_q_tbl[number].ci_lower_base_addr);
+
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"IQ %d: Element pri size 0x%x\n",
+		number,
+		pm8001_ha->inbnd_q_tbl[number].element_pri_size_cnt));
+
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"IQ upr base addr 0x%x IQ lwr base addr 0x%x\n",
+		pm8001_ha->inbnd_q_tbl[number].upper_base_addr,
+		pm8001_ha->inbnd_q_tbl[number].lower_base_addr));
+
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"CI upper base addr 0x%x CI lower base addr 0x%x\n",
+		pm8001_ha->inbnd_q_tbl[number].ci_upper_base_addr,
+		pm8001_ha->inbnd_q_tbl[number].ci_lower_base_addr));
 }
 
 /**
@@ -652,6 +837,21 @@ static void update_outbnd_queue_table(struct pm8001_hba_info *pm8001_ha,
 		pm8001_ha->outbnd_q_tbl[number].pi_lower_base_addr);
 	pm8001_mw32(address, offset + OB_INTERRUPT_COALES_OFFSET,
 		pm8001_ha->outbnd_q_tbl[number].interrup_vec_cnt_delay);
+
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"OQ %d: Element pri size 0x%x\n",
+		number,
+		pm8001_ha->outbnd_q_tbl[number].element_size_cnt));
+
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"OQ upr base addr 0x%x OQ lwr base addr 0x%x\n",
+		pm8001_ha->outbnd_q_tbl[number].upper_base_addr,
+		pm8001_ha->outbnd_q_tbl[number].lower_base_addr));
+
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"PI upper base addr 0x%x PI lower base addr 0x%x\n",
+		pm8001_ha->outbnd_q_tbl[number].pi_upper_base_addr,
+		pm8001_ha->outbnd_q_tbl[number].pi_lower_base_addr));
 }
 
 /**
@@ -669,9 +869,9 @@ static int mpi_init_check(struct pm8001_hba_info *pm8001_ha)
 	pm8001_cw32(pm8001_ha, 0, MSGU_IBDB_SET, SPCv_MSGU_CFG_TABLE_UPDATE);
 	/* wait until Inbound DoorBell Clear Register toggled */
 	if (IS_SPCV_12G(pm8001_ha->pdev)) {
-		max_wait_count = 4 * 1000 * 1000;/* 4 sec */
+		max_wait_count = SPCV_DOORBELL_CLEAR_TIMEOUT;
 	} else {
-		max_wait_count = 2 * 1000 * 1000;/* 2 sec */
+		max_wait_count = SPC_DOORBELL_CLEAR_TIMEOUT;
 	}
 	do {
 		udelay(1);
@@ -797,7 +997,7 @@ static void init_pci_device_addresses(struct pm8001_hba_info *pm8001_ha)
 	value = pm8001_cr32(pm8001_ha, 0, MSGU_SCRATCH_PAD_0);
 	offset = value & 0x03FFFFFF; /* scratch pad 0 TBL address */
 
-	PM8001_INIT_DBG(pm8001_ha,
+	PM8001_DEV_DBG(pm8001_ha,
 		pm8001_printk("Scratchpad 0 Offset: 0x%x value 0x%x\n",
 				offset, value));
 	pcilogic = (value & 0xFC000000) >> 26;
@@ -885,7 +1085,12 @@ pm80xx_set_thermal_config(struct pm8001_hba_info *pm8001_ha)
 				(THERMAL_ENABLE << 8) | page_code;
 	payload.cfg_pg[1] = (LTEMPHIL << 24) | (RTEMPHIL << 8);
 
-	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"Setting up thermal config. cfg_pg 0 0x%x cfg_pg 1 0x%x\n",
+		payload.cfg_pg[0], payload.cfg_pg[1]));
+
+	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 	if (rc)
 		pm8001_tag_free(pm8001_ha, tag);
 	return rc;
@@ -967,7 +1172,8 @@ pm80xx_set_sas_protocol_timer_config(struct pm8001_hba_info *pm8001_ha)
 	memcpy(&payload.cfg_pg, &SASConfigPage,
 			 sizeof(SASProtocolTimerConfig_t));
 
-	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 	if (rc)
 		pm8001_tag_free(pm8001_ha, tag);
 
@@ -1090,7 +1296,12 @@ static int pm80xx_encrypt_update(struct pm8001_hba_info *pm8001_ha)
 	payload.new_curidx_ksop = ((1 << 24) | (1 << 16) | (1 << 8) |
 					KEK_MGMT_SUBOP_KEYCARDUPDATE);
 
-	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"Saving Encryption info to flash. payload 0x%x\n",
+		payload.new_curidx_ksop));
+
+	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 	if (rc)
 		pm8001_tag_free(pm8001_ha, tag);
 
@@ -1241,7 +1452,7 @@ pm80xx_chip_soft_rst(struct pm8001_hba_info *pm8001_ha)
 		pm8001_printk("reset register before write : 0x%x\n", regval));
 
 	pm8001_cw32(pm8001_ha, 0, SPC_REG_SOFT_RESET, SPCv_NORMAL_RESET_VALUE);
-	mdelay(500);
+	msleep(500);
 
 	regval = pm8001_cr32(pm8001_ha, 0, SPC_REG_SOFT_RESET);
 	PM8001_INIT_DBG(pm8001_ha,
@@ -1443,7 +1654,10 @@ static void pm80xx_send_abort_all(struct pm8001_hba_info *pm8001_ha,
 	task_abort.device_id = cpu_to_le32(pm8001_ha_dev->device_id);
 	task_abort.tag = cpu_to_le32(ccb_tag);
 
-	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &task_abort, 0);
+	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &task_abort,
+			sizeof(task_abort), 0);
+	PM8001_FAIL_DBG(pm8001_ha,
+		pm8001_printk("Executing abort task end\n"));
 	if (ret) {
 		sas_free_task(task);
 		pm8001_tag_free(pm8001_ha, ccb_tag);
@@ -1519,7 +1733,9 @@ static void pm80xx_send_read_log(struct pm8001_hba_info *pm8001_ha,
 	sata_cmd.ncqtag_atap_dir_m_dad |= ((0x1 << 7) | (0x5 << 9));
 	memcpy(&sata_cmd.sata_fis, &fis, sizeof(struct host_to_dev_fis));
 
-	res = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &sata_cmd, 0);
+	res = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &sata_cmd,
+			sizeof(sata_cmd), 0);
+	PM8001_FAIL_DBG(pm8001_ha, pm8001_printk("Executing read log end\n"));
 	if (res) {
 		sas_free_task(task);
 		pm8001_tag_free(pm8001_ha, ccb_tag);
@@ -1570,6 +1786,10 @@ mpi_ssp_completion(struct pm8001_hba_info *pm8001_ha , void *piomb)
 	if (unlikely(!t || !t->lldd_task || !t->dev))
 		return;
 	ts = &t->task_status;
+
+	PM8001_DEV_DBG(pm8001_ha, pm8001_printk(
+		"tag::0x%x, status::0x%x task::0x%p\n", tag, status, t));
+
 	/* Print sas address of IO failed device */
 	if ((status != IO_SUCCESS) && (status != IO_OVERFLOW) &&
 		(status != IO_UNDERFLOW))
@@ -1772,7 +1992,7 @@ mpi_ssp_completion(struct pm8001_hba_info *pm8001_ha , void *piomb)
 		ts->open_rej_reason = SAS_OREJ_RSVD_RETRY;
 		break;
 	default:
-		PM8001_IO_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("Unknown status 0x%x\n", status));
 		/* not allowed case. Therefore, return failed status */
 		ts->resp = SAS_TASK_COMPLETE;
@@ -1826,7 +2046,7 @@ static void mpi_ssp_event(struct pm8001_hba_info *pm8001_ha , void *piomb)
 	if (unlikely(!t || !t->lldd_task || !t->dev))
 		return;
 	ts = &t->task_status;
-	PM8001_IO_DBG(pm8001_ha,
+	PM8001_IOERR_DBG(pm8001_ha,
 		pm8001_printk("port_id:0x%x, tag:0x%x, event:0x%x\n",
 				port_id, tag, event));
 	switch (event) {
@@ -1963,7 +2183,7 @@ static void mpi_ssp_event(struct pm8001_hba_info *pm8001_ha , void *piomb)
 		ts->stat = SAS_DATA_OVERRUN;
 		break;
 	case IO_XFER_ERROR_INTERNAL_CRC_ERROR:
-		PM8001_IO_DBG(pm8001_ha,
+		PM8001_IOERR_DBG(pm8001_ha,
 			pm8001_printk("IO_XFR_ERROR_INTERNAL_CRC_ERROR\n"));
 		/* TBC: used default set values */
 		ts->resp = SAS_TASK_COMPLETE;
@@ -1974,7 +2194,7 @@ static void mpi_ssp_event(struct pm8001_hba_info *pm8001_ha , void *piomb)
 			pm8001_printk("IO_XFER_CMD_FRAME_ISSUED\n"));
 		return;
 	default:
-		PM8001_IO_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("Unknown status 0x%x\n", event));
 		/* not allowed case. Therefore, return failed status */
 		ts->resp = SAS_TASK_COMPLETE;
@@ -2062,6 +2282,12 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
 			pm8001_printk("ts null\n"));
 		return;
 	}
+
+	if (unlikely(status))
+		PM8001_IOERR_DBG(pm8001_ha, pm8001_printk(
+			"status:0x%x, tag:0x%x, task::0x%p\n",
+			status, tag, t));
+
 	/* Print sas address of IO failed device */
 	if ((status != IO_SUCCESS) && (status != IO_OVERFLOW) &&
 		(status != IO_UNDERFLOW)) {
@@ -2365,7 +2591,7 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
 		ts->open_rej_reason = SAS_OREJ_RSVD_RETRY;
 		break;
 	default:
-		PM8001_IO_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("Unknown status 0x%x\n", status));
 		/* not allowed case. Therefore, return failed status */
 		ts->resp = SAS_TASK_COMPLETE;
@@ -2382,6 +2608,8 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
 			pm8001_printk("task 0x%p done with io_status 0x%x"
 			" resp 0x%x stat 0x%x but aborted by upper layer!\n",
 			t, status, ts->resp, ts->stat));
+		if (t->slow_task)
+			complete(&t->slow_task->completion);
 		pm8001_ccb_task_free(pm8001_ha, t, ccb, tag);
 	} else {
 		spin_unlock_irqrestore(&t->task_state_lock, flags);
@@ -2435,7 +2663,7 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha , void *piomb)
 	}
 
 	ts = &t->task_status;
-	PM8001_IO_DBG(pm8001_ha,
+	PM8001_IOERR_DBG(pm8001_ha,
 		pm8001_printk("port_id:0x%x, tag:0x%x, event:0x%x\n",
 				port_id, tag, event));
 	switch (event) {
@@ -2655,6 +2883,9 @@ mpi_smp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
 	if (unlikely(!t || !t->lldd_task || !t->dev))
 		return;
 
+	PM8001_DEV_DBG(pm8001_ha,
+		pm8001_printk("tag::0x%x status::0x%x\n", tag, status));
+
 	switch (status) {
 
 	case IO_SUCCESS:
@@ -2822,7 +3053,7 @@ mpi_smp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
 		ts->open_rej_reason = SAS_OREJ_RSVD_RETRY;
 		break;
 	default:
-		PM8001_IO_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("Unknown status 0x%x\n", status));
 		ts->resp = SAS_TASK_COMPLETE;
 		ts->stat = SAS_DEV_NO_RESPONSE;
@@ -2873,7 +3104,8 @@ static void pm80xx_hw_event_ack_req(struct pm8001_hba_info *pm8001_ha,
 		((phyId & 0xFF) << 24) | (port_id & 0xFF));
 	payload.param0 = cpu_to_le32(param0);
 	payload.param1 = cpu_to_le32(param1);
-	pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 }
 
 static int pm80xx_chip_phy_ctl_req(struct pm8001_hba_info *pm8001_ha,
@@ -2964,7 +3196,7 @@ hw_event_sas_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb)
 		pm8001_get_lrate_mode(phy, link_rate);
 		break;
 	default:
-		PM8001_MSG_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("unknown device type(%x)\n", deviceType));
 		break;
 	}
@@ -2984,7 +3216,7 @@ hw_event_sas_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb)
 	pm8001_get_attached_sas_addr(phy, phy->sas_phy.attached_sas_addr);
 	spin_unlock_irqrestore(&phy->sas_phy.frame_rcvd_lock, flags);
 	if (pm8001_ha->flags == PM8001F_RUN_TIME)
-		mdelay(200);/*delay a moment to wait disk to spinup*/
+		msleep(200);/*delay a moment to wait disk to spinup*/
 	pm8001_bytes_dmaed(pm8001_ha, phy_id);
 }
 
@@ -3013,7 +3245,7 @@ hw_event_sata_phy_up(struct pm8001_hba_info *pm8001_ha, void *piomb)
 	struct sas_ha_struct *sas_ha = pm8001_ha->sas;
 	struct pm8001_phy *phy = &pm8001_ha->phy[phy_id];
 	unsigned long flags;
-	PM8001_MSG_DBG(pm8001_ha, pm8001_printk(
+	PM8001_DEVIO_DBG(pm8001_ha, pm8001_printk(
 		"port id %d, phy id %d link_rate %d portstate 0x%x\n",
 				port_id, phy_id, link_rate, portstate));
 
@@ -3101,7 +3333,7 @@ hw_event_phy_down(struct pm8001_hba_info *pm8001_ha, void *piomb)
 		break;
 	default:
 		port->port_attached = 0;
-		PM8001_MSG_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk(" Phy Down and(default) = 0x%x\n",
 			portstate));
 		break;
@@ -3130,8 +3362,10 @@ static int mpi_phy_start_resp(struct pm8001_hba_info *pm8001_ha, void *piomb)
 	if (status == 0) {
 		phy->phy_state = PHY_LINK_DOWN;
 		if (pm8001_ha->flags == PM8001F_RUN_TIME &&
-				phy->enable_completion != NULL)
+				phy->enable_completion != NULL) {
 			complete(phy->enable_completion);
+			phy->enable_completion = NULL;
+		}
 	}
 	return 0;
 
@@ -3191,7 +3425,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void *piomb)
 	struct pm8001_phy *phy = &pm8001_ha->phy[phy_id];
 	struct pm8001_port *port = &pm8001_ha->port[port_id];
 	struct asd_sas_phy *sas_phy = sas_ha->sas_phy[phy_id];
-	PM8001_MSG_DBG(pm8001_ha,
+	PM8001_DEV_DBG(pm8001_ha,
 		pm8001_printk("portid:%d phyid:%d event:0x%x status:0x%x\n",
 				port_id, phy_id, eventType, status));
 
@@ -3376,7 +3610,7 @@ static int mpi_hw_event(struct pm8001_hba_info *pm8001_ha, void *piomb)
 			pm8001_printk("EVENT_BROADCAST_ASYNCH_EVENT\n"));
 		break;
 	default:
-		PM8001_MSG_DBG(pm8001_ha,
+		PM8001_DEVIO_DBG(pm8001_ha,
 			pm8001_printk("Unknown event type 0x%x\n", eventType));
 		break;
 	}
@@ -3758,7 +3992,7 @@ static void process_one_iomb(struct pm8001_hba_info *pm8001_ha, void *piomb)
 		ssp_coalesced_comp_resp(pm8001_ha, piomb);
 		break;
 	default:
-		PM8001_MSG_DBG(pm8001_ha, pm8001_printk(
+		PM8001_DEVIO_DBG(pm8001_ha, pm8001_printk(
 			"Unknown outbound Queue IOMB OPC = 0x%x\n", opc));
 		break;
 	}
@@ -3991,8 +4225,8 @@ static int pm80xx_chip_smp_req(struct pm8001_hba_info *pm8001_ha,
 
 	build_smp_cmd(pm8001_dev->device_id, smp_cmd.tag,
 				&smp_cmd, pm8001_ha->smp_exp_mode, length);
-	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc,
-					(u32 *)&smp_cmd, 0);
+	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &smp_cmd,
+			sizeof(smp_cmd), 0);
 	if (rc)
 		goto err_out_2;
 	return 0;
@@ -4200,7 +4434,7 @@ static int pm80xx_chip_ssp_io_req(struct pm8001_hba_info *pm8001_ha,
 	}
 	q_index = (u32) (pm8001_dev->id & 0x00ffffff) % PM8001_MAX_OUTB_NUM;
 	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc,
-						&ssp_cmd, q_index);
+			&ssp_cmd, sizeof(ssp_cmd), q_index);
 	return ret;
 }
 
@@ -4441,7 +4675,7 @@ static int pm80xx_chip_sata_req(struct pm8001_hba_info *pm8001_ha,
 	}
 	q_index = (u32) (pm8001_ha_dev->id & 0x00ffffff) % PM8001_MAX_OUTB_NUM;
 	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc,
-						&sata_cmd, q_index);
+			&sata_cmd, sizeof(sata_cmd), q_index);
 	return ret;
 }
 
@@ -4465,23 +4699,9 @@ pm80xx_chip_phy_start_req(struct pm8001_hba_info *pm8001_ha, u8 phy_id)
 
 	PM8001_INIT_DBG(pm8001_ha,
 		pm8001_printk("PHY START REQ for phy_id %d\n", phy_id));
-	/*
-	 ** [0:7]	PHY Identifier
-	 ** [8:11]	link rate 1.5G, 3G, 6G
-	 ** [12:13] link mode 01b SAS mode; 10b SATA mode; 11b Auto mode
-	 ** [14]	0b disable spin up hold; 1b enable spin up hold
-	 ** [15] ob no change in current PHY analig setup 1b enable using SPAST
-	 */
-	if (!IS_SPCV_12G(pm8001_ha->pdev))
-		payload.ase_sh_lm_slr_phyid = cpu_to_le32(SPINHOLD_DISABLE |
-				LINKMODE_AUTO | LINKRATE_15 |
-				LINKRATE_30 | LINKRATE_60 | phy_id);
-	else
-		payload.ase_sh_lm_slr_phyid = cpu_to_le32(SPINHOLD_DISABLE |
-				LINKMODE_AUTO | LINKRATE_15 |
-				LINKRATE_30 | LINKRATE_60 | LINKRATE_120 |
-				phy_id);
 
+	payload.ase_sh_lm_slr_phyid = cpu_to_le32(SPINHOLD_DISABLE |
+			LINKMODE_AUTO | pm8001_ha->link_rate | phy_id);
 	/* SSC Disable and SAS Analog ST configuration */
 	/**
 	payload.ase_sh_lm_slr_phyid =
@@ -4494,9 +4714,10 @@ pm80xx_chip_phy_start_req(struct pm8001_hba_info *pm8001_ha, u8 phy_id)
 	payload.sas_identify.dev_type = SAS_END_DEVICE;
 	payload.sas_identify.initiator_bits = SAS_PROTOCOL_ALL;
 	memcpy(payload.sas_identify.sas_addr,
-	  &pm8001_ha->phy[phy_id].dev_sas_addr, SAS_ADDR_SIZE);
+	  &pm8001_ha->sas_addr, SAS_ADDR_SIZE);
 	payload.sas_identify.phy_id = phy_id;
-	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opcode, &payload, 0);
+	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opcode, &payload,
+			sizeof(payload), 0);
 	return ret;
 }
 
@@ -4518,7 +4739,8 @@ static int pm80xx_chip_phy_stop_req(struct pm8001_hba_info *pm8001_ha,
 	memset(&payload, 0, sizeof(payload));
 	payload.tag = cpu_to_le32(tag);
 	payload.phy_id = cpu_to_le32(phy_id);
-	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opcode, &payload, 0);
+	ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opcode, &payload,
+			sizeof(payload), 0);
 	return ret;
 }
 
@@ -4584,7 +4806,8 @@ static int pm80xx_chip_reg_dev_req(struct pm8001_hba_info *pm8001_ha,
 	memcpy(payload.sas_addr, pm8001_dev->sas_device->sas_addr,
 		SAS_ADDR_SIZE);
 
-	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 	if (rc)
 		pm8001_tag_free(pm8001_ha, tag);
 
@@ -4614,7 +4837,8 @@ static int pm80xx_chip_phy_ctl_req(struct pm8001_hba_info *pm8001_ha,
 	payload.tag = cpu_to_le32(tag);
 	payload.phyop_phyid =
 		cpu_to_le32(((phy_op & 0xFF) << 8) | (phyId & 0xFF));
-	return pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	return pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 }
 
 static u32 pm80xx_chip_is_our_interrupt(struct pm8001_hba_info *pm8001_ha)
@@ -4641,6 +4865,9 @@ static irqreturn_t
 pm80xx_chip_isr(struct pm8001_hba_info *pm8001_ha, u8 vec)
 {
 	pm80xx_chip_interrupt_disable(pm8001_ha, vec);
+	PM8001_DEVIO_DBG(pm8001_ha, pm8001_printk(
+		"irq vec %d, ODMR:0x%x\n",
+		vec, pm8001_cr32(pm8001_ha, 0, 0x30)));
 	process_oq(pm8001_ha, vec);
 	pm80xx_chip_interrupt_enable(pm8001_ha, vec);
 	return IRQ_HANDLED;
@@ -4669,7 +4896,8 @@ void mpi_set_phy_profile_req(struct pm8001_hba_info *pm8001_ha,
 		payload.reserved[j] =  cpu_to_le32(*((u32 *)buf + i));
 		j++;
 	}
-	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 	if (rc)
 		pm8001_tag_free(pm8001_ha, tag);
 }
@@ -4711,7 +4939,8 @@ void pm8001_set_phy_profile_single(struct pm8001_hba_info *pm8001_ha,
 	for (i = 0; i < length; i++)
 		payload.reserved[i] = cpu_to_le32(*(buf + i));
 
-	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload, 0);
+	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+			sizeof(payload), 0);
 	if (rc)
 		pm8001_tag_free(pm8001_ha, tag);
 
diff --git a/drivers/scsi/pm8001/pm80xx_hwi.h b/drivers/scsi/pm8001/pm80xx_hwi.h
index dc9ab7689060..701951a0f715 100644
--- a/drivers/scsi/pm8001/pm80xx_hwi.h
+++ b/drivers/scsi/pm8001/pm80xx_hwi.h
@@ -220,6 +220,9 @@
 #define SAS_DOPNRJT_RTRY_TMO            128
 #define SAS_COPNRJT_RTRY_TMO            128
 
+#define SPCV_DOORBELL_CLEAR_TIMEOUT	(30 * 1000 * 1000) /* 30 sec */
+#define SPC_DOORBELL_CLEAR_TIMEOUT	(15 * 1000 * 1000) /* 15 sec */
+
 /*
   Making ORR bigger than IT NEXUS LOSS which is 2000000us = 2 second.
   Assuming a bigger value 3 second, 3000000/128 = 23437.5 where 128
diff --git a/drivers/scsi/qedf/qedf_dbg.h b/drivers/scsi/qedf/qedf_dbg.h
index d979f095aeda..2386bfb73c46 100644
--- a/drivers/scsi/qedf/qedf_dbg.h
+++ b/drivers/scsi/qedf/qedf_dbg.h
@@ -42,7 +42,7 @@ extern uint qedf_debug;
 #define QEDF_LOG_LPORT		0x4000		/* lport logs */
 #define QEDF_LOG_ELS		0x8000		/* ELS logs */
 #define QEDF_LOG_NPIV		0x10000		/* NPIV logs */
-#define QEDF_LOG_SESS		0x20000		/* Conection setup, cleanup */
+#define QEDF_LOG_SESS		0x20000		/* Connection setup, cleanup */
 #define QEDF_LOG_TID		0x80000         /*
 						 * FW TID context acquire
 						 * free
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index 59ca98f12afd..604856e72cfb 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -1926,6 +1926,13 @@ static int qedf_fcoe_reset(struct Scsi_Host *shost)
 	return 0;
 }
 
+static void qedf_get_host_port_id(struct Scsi_Host *shost)
+{
+	struct fc_lport *lport = shost_priv(shost);
+
+	fc_host_port_id(shost) = lport->port_id;
+}
+
 static struct fc_host_statistics *qedf_fc_get_host_stats(struct Scsi_Host
 	*shost)
 {
@@ -1996,6 +2003,7 @@ static struct fc_function_template qedf_fc_transport_fn = {
 	.show_host_active_fc4s = 1,
 	.show_host_maxframe_size = 1,
 
+	.get_host_port_id = qedf_get_host_port_id,
 	.show_host_port_id = 1,
 	.show_host_supported_speeds = 1,
 	.get_host_speed = fc_get_host_speed,
diff --git a/drivers/scsi/qedi/qedi_dbg.h b/drivers/scsi/qedi/qedi_dbg.h
index 243acc8b520a..37d084086fd4 100644
--- a/drivers/scsi/qedi/qedi_dbg.h
+++ b/drivers/scsi/qedi/qedi_dbg.h
@@ -44,7 +44,7 @@ extern uint qedi_dbg_log;
 #define QEDI_LOG_LPORT		0x4000		/* lport logs */
 #define QEDI_LOG_ELS		0x8000		/* ELS logs */
 #define QEDI_LOG_NPIV		0x10000		/* NPIV logs */
-#define QEDI_LOG_SESS		0x20000		/* Conection setup, cleanup */
+#define QEDI_LOG_SESS		0x20000		/* Connection setup, cleanup */
 #define QEDI_LOG_UIO		0x40000		/* iSCSI UIO logs */
 #define QEDI_LOG_TID		0x80000         /* FW TID context acquire,
 						 * free
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 7259bce85e0e..ae97e2f310a3 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -102,8 +102,10 @@ qla2x00_sysfs_write_fw_dump(struct file *filp, struct kobject *kobj,
 			qla8044_idc_lock(ha);
 			qla82xx_set_reset_owner(vha);
 			qla8044_idc_unlock(ha);
-		} else
+		} else {
+			ha->fw_dump_mpi = 1;
 			qla2x00_system_error(vha);
+		}
 		break;
 	case 4:
 		if (IS_P3P_TYPE(ha)) {
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 6ffa9877c28b..460f443f6471 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -591,19 +591,23 @@ typedef struct srb {
 	 */
 	uint8_t cmd_type;
 	uint8_t pad[3];
-	atomic_t ref_count;
 	struct kref cmd_kref;	/* need to migrate ref_count over to this */
 	void *priv;
 	wait_queue_head_t nvme_ls_waitq;
 	struct fc_port *fcport;
 	struct scsi_qla_host *vha;
 	unsigned int start_timer:1;
+	unsigned int abort:1;
+	unsigned int aborted:1;
+	unsigned int completed:1;
+
 	uint32_t handle;
 	uint16_t flags;
 	uint16_t type;
 	const char *name;
 	int iocbs;
 	struct qla_qpair *qpair;
+	struct srb *cmd_sp;
 	struct list_head elem;
 	u32 gen1;	/* scratch */
 	u32 gen2;	/* scratch */
@@ -2277,7 +2281,7 @@ typedef struct {
 	uint8_t fabric_port_name[WWN_SIZE];
 	uint16_t fp_speed;
 	uint8_t fc4_type;
-	uint8_t fc4f_nvme;	/* nvme fc4 feature bits */
+	uint8_t fc4_features;
 } sw_info_t;
 
 /* FCP-4 types */
@@ -2445,7 +2449,7 @@ typedef struct fc_port {
 	u32 supported_classes;
 
 	uint8_t fc4_type;
-	uint8_t	fc4f_nvme;
+	uint8_t fc4_features;
 	uint8_t scan_state;
 
 	unsigned long last_queue_full;
@@ -2476,6 +2480,11 @@ typedef struct fc_port {
 	u16 n2n_chip_reset;
 } fc_port_t;
 
+enum {
+	FC4_PRIORITY_NVME = 1,
+	FC4_PRIORITY_FCP  = 2,
+};
+
 #define QLA_FCPORT_SCAN		1
 #define QLA_FCPORT_FOUND	2
 
@@ -4291,6 +4300,8 @@ struct qla_hw_data {
 	atomic_t        nvme_active_aen_cnt;
 	uint16_t        nvme_last_rptd_aen;             /* Last recorded aen count */
 
+	uint8_t fc4_type_priority;
+
 	atomic_t zio_threshold;
 	uint16_t last_zio_threshold;
 
@@ -4816,6 +4827,23 @@ struct sff_8247_a0 {
 	 ha->current_topology == ISP_CFG_N || \
 	 !ha->current_topology)
 
+#define NVME_TYPE(fcport) \
+	(fcport->fc4_type & FS_FC4TYPE_NVME) \
+
+#define FCP_TYPE(fcport) \
+	(fcport->fc4_type & FS_FC4TYPE_FCP) \
+
+#define NVME_ONLY_TARGET(fcport) \
+	(NVME_TYPE(fcport) && !FCP_TYPE(fcport))  \
+
+#define NVME_FCP_TARGET(fcport) \
+	(FCP_TYPE(fcport) && NVME_TYPE(fcport)) \
+
+#define NVME_TARGET(ha, fcport) \
+	((NVME_FCP_TARGET(fcport) && \
+	(ha->fc4_type_priority == FC4_PRIORITY_NVME)) || \
+	NVME_ONLY_TARGET(fcport)) \
+
 #include "qla_target.h"
 #include "qla_gbl.h"
 #include "qla_dbg.h"
diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h
index 732bb871c433..59f6903e5abe 100644
--- a/drivers/scsi/qla2xxx/qla_fw.h
+++ b/drivers/scsi/qla2xxx/qla_fw.h
@@ -2101,4 +2101,6 @@ struct qla_fcp_prio_cfg {
 #define FA_FLASH_LAYOUT_ADDR_83	(0x3F1000/4)
 #define FA_FLASH_LAYOUT_ADDR_28	(0x11000/4)
 
+#define NVRAM_DUAL_FCP_NVME_FLAG_OFFSET	0x196
+
 #endif
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index d11416dcee4e..5b163ad85c34 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -917,4 +917,5 @@ int qla2x00_set_data_rate(scsi_qla_host_t *vha, uint16_t mode);
 
 /* nvme.c */
 void qla_nvme_unregister_remote_port(struct fc_port *fcport);
+void qla_handle_els_plogi_done(scsi_qla_host_t *vha, struct event_arg *ea);
 #endif /* _QLA_GBL_H */
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index 5298ed10059f..67230688b05e 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -248,7 +248,7 @@ qla2x00_ga_nxt(scsi_qla_host_t *vha, fc_port_t *fcport)
 		    WWN_SIZE);
 
 		fcport->fc4_type = (ct_rsp->rsp.ga_nxt.fc4_types[2] & BIT_0) ?
-		    FC4_TYPE_FCP_SCSI : FC4_TYPE_OTHER;
+		    FS_FC4TYPE_FCP : FC4_TYPE_OTHER;
 
 		if (ct_rsp->rsp.ga_nxt.port_type != NS_N_PORT_TYPE &&
 		    ct_rsp->rsp.ga_nxt.port_type != NS_NL_PORT_TYPE)
@@ -2887,7 +2887,7 @@ qla2x00_gff_id(scsi_qla_host_t *vha, sw_info_t *list)
 	struct ct_sns_req	*ct_req;
 	struct ct_sns_rsp	*ct_rsp;
 	struct qla_hw_data *ha = vha->hw;
-	uint8_t fcp_scsi_features = 0;
+	uint8_t fcp_scsi_features = 0, nvme_features = 0;
 	struct ct_arg arg;
 
 	for (i = 0; i < ha->max_fibre_devices; i++) {
@@ -2933,14 +2933,19 @@ qla2x00_gff_id(scsi_qla_host_t *vha, sw_info_t *list)
 			   ct_rsp->rsp.gff_id.fc4_features[GFF_FCP_SCSI_OFFSET];
 			fcp_scsi_features &= 0x0f;
 
-			if (fcp_scsi_features)
-				list[i].fc4_type = FC4_TYPE_FCP_SCSI;
-			else
-				list[i].fc4_type = FC4_TYPE_OTHER;
+			if (fcp_scsi_features) {
+				list[i].fc4_type = FS_FC4TYPE_FCP;
+				list[i].fc4_features = fcp_scsi_features;
+			}
 
-			list[i].fc4f_nvme =
+			nvme_features =
 			    ct_rsp->rsp.gff_id.fc4_features[GFF_NVME_OFFSET];
-			list[i].fc4f_nvme &= 0xf;
+			nvme_features &= 0xf;
+
+			if (nvme_features) {
+				list[i].fc4_type |= FS_FC4TYPE_NVME;
+				list[i].fc4_features = nvme_features;
+			}
 		}
 
 		/* Last device exit. */
@@ -3005,7 +3010,7 @@ static void qla24xx_async_gpsc_sp_done(srb_t *sp, int res)
 	fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
 
 	if (res == QLA_FUNCTION_TIMEOUT)
-		return;
+		goto done;
 
 	if (res == (DID_ERROR << 16)) {
 		/* entry status error */
@@ -3435,6 +3440,8 @@ void qla24xx_async_gffid_sp_done(srb_t *sp, int res)
 	fc_port_t *fcport = sp->fcport;
 	struct ct_sns_rsp *ct_rsp;
 	struct event_arg ea;
+	uint8_t fc4_scsi_feat;
+	uint8_t fc4_nvme_feat;
 
 	ql_dbg(ql_dbg_disc, vha, 0x2133,
 	       "Async done-%s res %x ID %x. %8phC\n",
@@ -3442,24 +3449,25 @@ void qla24xx_async_gffid_sp_done(srb_t *sp, int res)
 
 	fcport->flags &= ~FCF_ASYNC_SENT;
 	ct_rsp = &fcport->ct_desc.ct_sns->p.rsp;
+	fc4_scsi_feat = ct_rsp->rsp.gff_id.fc4_features[GFF_FCP_SCSI_OFFSET];
+	fc4_nvme_feat = ct_rsp->rsp.gff_id.fc4_features[GFF_NVME_OFFSET];
+
 	/*
 	 * FC-GS-7, 5.2.3.12 FC-4 Features - format
 	 * The format of the FC-4 Features object, as defined by the FC-4,
 	 * Shall be an array of 4-bit values, one for each type code value
 	 */
 	if (!res) {
-		if (ct_rsp->rsp.gff_id.fc4_features[GFF_FCP_SCSI_OFFSET] & 0xf) {
+		if (fc4_scsi_feat & 0xf) {
 			/* w1 b00:03 */
-			fcport->fc4_type =
-			    ct_rsp->rsp.gff_id.fc4_features[GFF_FCP_SCSI_OFFSET];
-			fcport->fc4_type &= 0xf;
-	       }
+			fcport->fc4_type = FS_FC4TYPE_FCP;
+			fcport->fc4_features = fc4_scsi_feat & 0xf;
+		}
 
-		if (ct_rsp->rsp.gff_id.fc4_features[GFF_NVME_OFFSET] & 0xf) {
+		if (fc4_nvme_feat & 0xf) {
 			/* w5 [00:03]/28h */
-			fcport->fc4f_nvme =
-			    ct_rsp->rsp.gff_id.fc4_features[GFF_NVME_OFFSET];
-			fcport->fc4f_nvme &= 0xf;
+			fcport->fc4_type |= FS_FC4TYPE_NVME;
+			fcport->fc4_features = fc4_nvme_feat & 0xf;
 		}
 	}
 
@@ -3563,7 +3571,7 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp)
 	u8 recheck = 0;
 	u16 dup = 0, dup_cnt = 0;
 
-	ql_dbg(ql_dbg_disc, vha, 0xffff,
+	ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
 	    "%s enter\n", __func__);
 
 	if (sp->gen1 != vha->hw->base_qpair->chip_reset) {
@@ -3580,8 +3588,9 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp)
 			set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
 			set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
 		} else {
-			ql_dbg(ql_dbg_disc, vha, 0xffff,
-			    "Fabric scan failed on all retries.\n");
+			ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
+			    "%s: Fabric scan failed for %d retries.\n",
+			    __func__, vha->scan.scan_retry);
 		}
 		goto out;
 	}
@@ -4047,7 +4056,7 @@ done_free_sp:
 
 void qla24xx_async_gpnft_done(scsi_qla_host_t *vha, srb_t *sp)
 {
-	ql_dbg(ql_dbg_disc, vha, 0xffff,
+	ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
 	    "%s enter\n", __func__);
 	qla24xx_async_gnnft(vha, sp, sp->gen2);
 }
@@ -4061,7 +4070,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
 	u32 rspsz;
 	unsigned long flags;
 
-	ql_dbg(ql_dbg_disc, vha, 0xffff,
+	ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
 	    "%s enter\n", __func__);
 
 	if (!vha->flags.online)
@@ -4070,14 +4079,15 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
 	spin_lock_irqsave(&vha->work_lock, flags);
 	if (vha->scan.scan_flags & SF_SCANNING) {
 		spin_unlock_irqrestore(&vha->work_lock, flags);
-		ql_dbg(ql_dbg_disc, vha, 0xffff, "scan active\n");
+		ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
+		    "%s: scan active\n", __func__);
 		return rval;
 	}
 	vha->scan.scan_flags |= SF_SCANNING;
 	spin_unlock_irqrestore(&vha->work_lock, flags);
 
 	if (fc4_type == FC4_TYPE_FCP_SCSI) {
-		ql_dbg(ql_dbg_disc, vha, 0xffff,
+		ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
 		    "%s: Performing FCP Scan\n", __func__);
 
 		if (sp)
@@ -4132,7 +4142,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
 		}
 		sp->u.iocb_cmd.u.ctarg.rsp_size = rspsz;
 
-		ql_dbg(ql_dbg_disc, vha, 0xffff,
+		ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
 		    "%s scan list size %d\n", __func__, vha->scan.size);
 
 		memset(vha->scan.l, 0, vha->scan.size);
@@ -4197,8 +4207,8 @@ done_free_sp:
 	spin_lock_irqsave(&vha->work_lock, flags);
 	vha->scan.scan_flags &= ~SF_SCANNING;
 	if (vha->scan.scan_flags == 0) {
-		ql_dbg(ql_dbg_disc, vha, 0xffff,
-		    "%s: schedule\n", __func__);
+		ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
+		    "%s: Scan scheduled.\n", __func__);
 		vha->scan.scan_flags |= SF_QUEUED;
 		schedule_delayed_work(&vha->scan.scan_work, 5);
 	}
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 1d041313ec52..1dbee8800218 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -17,7 +17,6 @@
 #include <asm/prom.h>
 #endif
 
-#include <target/target_core_base.h>
 #include "qla_target.h"
 
 /*
@@ -101,8 +100,22 @@ static void qla24xx_abort_iocb_timeout(void *data)
 	u32 handle;
 	unsigned long flags;
 
+	if (sp->cmd_sp)
+		ql_dbg(ql_dbg_async, sp->vha, 0x507c,
+		    "Abort timeout - cmd hdl=%x, cmd type=%x hdl=%x, type=%x\n",
+		    sp->cmd_sp->handle, sp->cmd_sp->type,
+		    sp->handle, sp->type);
+	else
+		ql_dbg(ql_dbg_async, sp->vha, 0x507c,
+		    "Abort timeout 2 - hdl=%x, type=%x\n",
+		    sp->handle, sp->type);
+
 	spin_lock_irqsave(qpair->qp_lock_ptr, flags);
 	for (handle = 1; handle < qpair->req->num_outstanding_cmds; handle++) {
+		if (sp->cmd_sp && (qpair->req->outstanding_cmds[handle] ==
+		    sp->cmd_sp))
+			qpair->req->outstanding_cmds[handle] = NULL;
+
 		/* removing the abort */
 		if (qpair->req->outstanding_cmds[handle] == sp) {
 			qpair->req->outstanding_cmds[handle] = NULL;
@@ -111,6 +124,9 @@ static void qla24xx_abort_iocb_timeout(void *data)
 	}
 	spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
 
+	if (sp->cmd_sp)
+		sp->cmd_sp->done(sp->cmd_sp, QLA_OS_TIMER_EXPIRED);
+
 	abt->u.abt.comp_status = CS_TIMEOUT;
 	sp->done(sp, QLA_OS_TIMER_EXPIRED);
 }
@@ -142,6 +158,7 @@ static int qla24xx_async_abort_cmd(srb_t *cmd_sp, bool wait)
 	sp->type = SRB_ABT_CMD;
 	sp->name = "abort";
 	sp->qpair = cmd_sp->qpair;
+	sp->cmd_sp = cmd_sp;
 	if (wait)
 		sp->flags = SRB_WAKEUP_ON_COMP;
 
@@ -328,7 +345,7 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport,
 	else
 		lio->u.logio.flags |= SRB_LOGIN_COND_PLOGI;
 
-	if (fcport->fc4f_nvme)
+	if (NVME_TARGET(vha->hw, fcport))
 		lio->u.logio.flags |= SRB_LOGIN_SKIP_PRLI;
 
 	ql_dbg(ql_dbg_disc, vha, 0x2072,
@@ -726,19 +743,17 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 
 		loop_id = le16_to_cpu(e->nport_handle);
 		loop_id = (loop_id & 0x7fff);
-		if  (fcport->fc4f_nvme)
+		if (NVME_TARGET(vha->hw, fcport))
 			current_login_state = e->current_login_state >> 4;
 		else
 			current_login_state = e->current_login_state & 0xf;
 
-
 		ql_dbg(ql_dbg_disc, vha, 0x20e2,
-		    "%s found %8phC CLS [%x|%x] nvme %d ID[%02x%02x%02x|%02x%02x%02x] lid[%d|%d]\n",
+		    "%s found %8phC CLS [%x|%x] fc4_type %d ID[%06x|%06x] lid[%d|%d]\n",
 		    __func__, fcport->port_name,
 		    e->current_login_state, fcport->fw_login_state,
-		    fcport->fc4f_nvme, id.b.domain, id.b.area, id.b.al_pa,
-		    fcport->d_id.b.domain, fcport->d_id.b.area,
-		    fcport->d_id.b.al_pa, loop_id, fcport->loop_id);
+		    fcport->fc4_type, id.b24, fcport->d_id.b24,
+		    loop_id, fcport->loop_id);
 
 		switch (fcport->disc_state) {
 		case DSC_DELETE_PEND:
@@ -1135,19 +1150,18 @@ static void qla24xx_async_gpdb_sp_done(srb_t *sp, int res)
 	    "Async done-%s res %x, WWPN %8phC mb[1]=%x mb[2]=%x \n",
 	    sp->name, res, fcport->port_name, mb[1], mb[2]);
 
-	if (res == QLA_FUNCTION_TIMEOUT) {
-		dma_pool_free(sp->vha->hw->s_dma_pool, sp->u.iocb_cmd.u.mbx.in,
-			sp->u.iocb_cmd.u.mbx.in_dma);
-		return;
-	}
-
 	fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
+
+	if (res == QLA_FUNCTION_TIMEOUT)
+		goto done;
+
 	memset(&ea, 0, sizeof(ea));
 	ea.fcport = fcport;
 	ea.sp = sp;
 
 	qla24xx_handle_gpdb_event(vha, &ea);
 
+done:
 	dma_pool_free(ha->s_dma_pool, sp->u.iocb_cmd.u.mbx.in,
 		sp->u.iocb_cmd.u.mbx.in_dma);
 
@@ -1225,13 +1239,13 @@ qla24xx_async_prli(struct scsi_qla_host *vha, fc_port_t *fcport)
 	sp->done = qla2x00_async_prli_sp_done;
 	lio->u.logio.flags = 0;
 
-	if  (fcport->fc4f_nvme)
+	if (NVME_TARGET(vha->hw, fcport))
 		lio->u.logio.flags |= SRB_LOGIN_NVME_PRLI;
 
 	ql_dbg(ql_dbg_disc, vha, 0x211b,
 	    "Async-prli - %8phC hdl=%x, loopid=%x portid=%06x retries=%d %s.\n",
 	    fcport->port_name, sp->handle, fcport->loop_id, fcport->d_id.b24,
-	    fcport->login_retry, fcport->fc4f_nvme ? "nvme" : "fc");
+	    fcport->login_retry, NVME_TARGET(vha->hw, fcport) ? "nvme" : "fc");
 
 	rval = qla2x00_start_sp(sp);
 	if (rval != QLA_SUCCESS) {
@@ -1382,14 +1396,14 @@ void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea)
 	fcport->flags &= ~FCF_ASYNC_SENT;
 
 	ql_dbg(ql_dbg_disc, vha, 0x20d2,
-	    "%s %8phC DS %d LS %d nvme %x rc %d\n", __func__, fcport->port_name,
-	    fcport->disc_state, pd->current_login_state, fcport->fc4f_nvme,
-	    ea->rc);
+	    "%s %8phC DS %d LS %d fc4_type %x rc %d\n", __func__,
+	    fcport->port_name, fcport->disc_state, pd->current_login_state,
+	    fcport->fc4_type, ea->rc);
 
 	if (fcport->disc_state == DSC_DELETE_PEND)
 		return;
 
-	if (fcport->fc4f_nvme)
+	if (NVME_TARGET(vha->hw, fcport))
 		ls = pd->current_login_state >> 4;
 	else
 		ls = pd->current_login_state & 0xf;
@@ -1578,7 +1592,8 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 				ql_dbg(ql_dbg_disc, vha, 0x2118,
 				    "%s %d %8phC post %s PRLI\n",
 				    __func__, __LINE__, fcport->port_name,
-				    fcport->fc4f_nvme ? "NVME" : "FC");
+				    NVME_TARGET(vha->hw, fcport) ? "NVME" :
+				    "FC");
 				qla24xx_post_prli_work(vha, fcport);
 			}
 			break;
@@ -1701,6 +1716,15 @@ void qla24xx_handle_relogin_event(scsi_qla_host_t *vha,
 	qla24xx_fcport_handle_login(vha, fcport);
 }
 
+void qla_handle_els_plogi_done(scsi_qla_host_t *vha,
+				      struct event_arg *ea)
+{
+	ql_dbg(ql_dbg_disc, vha, 0x2118,
+	    "%s %d %8phC post PRLI\n",
+	    __func__, __LINE__, ea->fcport->port_name);
+	qla24xx_post_prli_work(vha, ea->fcport);
+}
+
 /*
  * RSCN(s) came in for this fcport, but the RSCN(s) was not able
  * to be consumed by the fcport
@@ -1860,38 +1884,26 @@ qla24xx_handle_prli_done_event(struct scsi_qla_host *vha, struct event_arg *ea)
 			break;
 		}
 
-		if (ea->fcport->fc4f_nvme) {
+		/*
+		 * Retry PRLI with other FC-4 type if failure occurred on dual
+		 * FCP/NVMe port
+		 */
+		if (NVME_FCP_TARGET(ea->fcport)) {
 			ql_dbg(ql_dbg_disc, vha, 0x2118,
-				"%s %d %8phC post fc4 prli\n",
-				__func__, __LINE__, ea->fcport->port_name);
-			ea->fcport->fc4f_nvme = 0;
-			qla24xx_post_prli_work(vha, ea->fcport);
-			return;
+				"%s %d %8phC post %s prli\n",
+				__func__, __LINE__, ea->fcport->port_name,
+				(ea->fcport->fc4_type & FS_FC4TYPE_NVME) ?
+				"NVMe" : "FCP");
+			if (vha->hw->fc4_type_priority == FC4_PRIORITY_NVME)
+				ea->fcport->fc4_type &= ~FS_FC4TYPE_NVME;
+			else
+				ea->fcport->fc4_type &= ~FS_FC4TYPE_FCP;
 		}
 
-		/* at this point both PRLI NVME & PRLI FCP failed */
-		if (N2N_TOPO(vha->hw)) {
-			if (ea->fcport->n2n_link_reset_cnt < 3) {
-				ea->fcport->n2n_link_reset_cnt++;
-				/*
-				 * remote port is not sending Plogi. Reset
-				 * link to kick start his state machine
-				 */
-				set_bit(N2N_LINK_RESET, &vha->dpc_flags);
-			} else {
-				ql_log(ql_log_warn, vha, 0x2119,
-				    "%s %d %8phC Unable to reconnect\n",
-				    __func__, __LINE__, ea->fcport->port_name);
-			}
-		} else {
-			/*
-			 * switch connect. login failed. Take connection
-			 * down and allow relogin to retrigger
-			 */
-			ea->fcport->flags &= ~FCF_ASYNC_SENT;
-			ea->fcport->keep_nport_handle = 0;
-			qlt_schedule_sess_for_deletion(ea->fcport);
-		}
+		ea->fcport->flags &= ~FCF_ASYNC_SENT;
+		ea->fcport->keep_nport_handle = 0;
+		ea->fcport->logout_on_delete = 1;
+		qlt_schedule_sess_for_deletion(ea->fcport);
 		break;
 	}
 }
@@ -1952,7 +1964,7 @@ qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea)
 		 * force a relogin attempt via implicit LOGO, PLOGI, and PRLI
 		 * requests.
 		 */
-		if (ea->fcport->fc4f_nvme) {
+		if (NVME_TARGET(vha->hw, ea->fcport)) {
 			ql_dbg(ql_dbg_disc, vha, 0x2117,
 				"%s %d %8phC post prli\n",
 				__func__, __LINE__, ea->fcport->port_name);
@@ -2206,8 +2218,18 @@ qla2x00_initialize_adapter(scsi_qla_host_t *vha)
 	ql_dbg(ql_dbg_init, vha, 0x0061,
 	    "Configure NVRAM parameters...\n");
 
+	/* Let priority default to FCP, can be overridden by nvram_config */
+	ha->fc4_type_priority = FC4_PRIORITY_FCP;
+
 	ha->isp_ops->nvram_config(vha);
 
+	if (ha->fc4_type_priority != FC4_PRIORITY_FCP &&
+	    ha->fc4_type_priority != FC4_PRIORITY_NVME)
+		ha->fc4_type_priority = FC4_PRIORITY_FCP;
+
+	ql_log(ql_log_info, vha, 0xffff, "FC4 priority set to %s\n",
+	       ha->fc4_type_priority == FC4_PRIORITY_FCP ? "FCP" : "NVMe");
+
 	if (ha->flags.disable_serdes) {
 		/* Mask HBA via NVRAM settings? */
 		ql_log(ql_log_info, vha, 0x0077,
@@ -5382,7 +5404,7 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 
 	qla2x00_iidma_fcport(vha, fcport);
 
-	if (fcport->fc4f_nvme) {
+	if (NVME_TARGET(vha->hw, fcport)) {
 		qla_nvme_register_remote(vha, fcport);
 		fcport->disc_state = DSC_LOGIN_COMPLETE;
 		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
@@ -5710,11 +5732,8 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha)
 				new_fcport->fc4_type = swl[swl_idx].fc4_type;
 
 				new_fcport->nvme_flag = 0;
-				new_fcport->fc4f_nvme = 0;
 				if (vha->flags.nvme_enabled &&
-				    swl[swl_idx].fc4f_nvme) {
-					new_fcport->fc4f_nvme =
-					    swl[swl_idx].fc4f_nvme;
+				    swl[swl_idx].fc4_type & FS_FC4TYPE_NVME) {
 					ql_log(ql_log_info, vha, 0x2131,
 					    "FOUND: NVME port %8phC as FC Type 28h\n",
 					    new_fcport->port_name);
@@ -5770,7 +5789,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha)
 
 		/* Bypass ports whose FCP-4 type is not FCP_SCSI */
 		if (ql2xgffidenable &&
-		    (new_fcport->fc4_type != FC4_TYPE_FCP_SCSI &&
+		    (!(new_fcport->fc4_type & FS_FC4TYPE_FCP) &&
 		    new_fcport->fc4_type != FC4_TYPE_UNKNOWN))
 			continue;
 
@@ -5839,7 +5858,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha)
 			break;
 		}
 
-		if (fcport->fc4f_nvme) {
+		if (NVME_TARGET(vha->hw, fcport)) {
 			if (fcport->disc_state == DSC_DELETE_PEND) {
 				fcport->disc_state = DSC_GNL;
 				vha->fcport_count--;
@@ -8514,6 +8533,9 @@ qla81xx_nvram_config(scsi_qla_host_t *vha)
 	/* N2N: driver will initiate Login instead of FW */
 	icb->firmware_options_3 |= BIT_8;
 
+	/* Determine NVMe/FCP priority for target ports */
+	ha->fc4_type_priority = qla2xxx_get_fc4_priority(vha);
+
 	if (rval) {
 		ql_log(ql_log_warn, vha, 0x0076,
 		    "NVRAM configuration failed.\n");
@@ -9003,8 +9025,6 @@ int qla2xxx_delete_qpair(struct scsi_qla_host *vha, struct qla_qpair *qpair)
 	struct qla_hw_data *ha = qpair->hw;
 
 	qpair->delete_in_progress = 1;
-	while (atomic_read(&qpair->ref_count))
-		msleep(500);
 
 	ret = qla25xx_delete_req_que(vha, qpair->req);
 	if (ret != QLA_SUCCESS)
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 0c3d907af769..352aba4127f7 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -307,3 +307,15 @@ qla_83xx_start_iocbs(struct qla_qpair *qpair)
 
 	WRT_REG_DWORD(req->req_q_in, req->ring_index);
 }
+
+static inline int
+qla2xxx_get_fc4_priority(struct scsi_qla_host *vha)
+{
+	uint32_t data;
+
+	data =
+	    ((uint8_t *)vha->hw->nvram)[NVRAM_DUAL_FCP_NVME_FLAG_OFFSET];
+
+
+	return (data >> 6) & BIT_0 ? FC4_PRIORITY_FCP : FC4_PRIORITY_NVME;
+}
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 518eb954cf42..b25f87ff8cde 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2740,6 +2740,10 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res)
 	struct scsi_qla_host *vha = sp->vha;
 	struct event_arg ea;
 	struct qla_work_evt *e;
+	struct fc_port *conflict_fcport;
+	port_id_t cid;	/* conflict Nport id */
+	u32 *fw_status = sp->u.iocb_cmd.u.els_plogi.fw_status;
+	u16 lid;
 
 	ql_dbg(ql_dbg_disc, vha, 0x3072,
 	    "%s ELS done rc %d hdl=%x, portid=%06x %8phC\n",
@@ -2751,14 +2755,101 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res)
 	if (sp->flags & SRB_WAKEUP_ON_COMP)
 		complete(&lio->u.els_plogi.comp);
 	else {
-		if (res) {
-			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-		} else {
+		switch (fw_status[0]) {
+		case CS_DATA_UNDERRUN:
+		case CS_COMPLETE:
 			memset(&ea, 0, sizeof(ea));
 			ea.fcport = fcport;
-			ea.data[0] = MBS_COMMAND_COMPLETE;
-			ea.sp = sp;
-			qla24xx_handle_plogi_done_event(vha, &ea);
+			ea.rc = res;
+			qla_handle_els_plogi_done(vha, &ea);
+			break;
+
+		case CS_IOCB_ERROR:
+			switch (fw_status[1]) {
+			case LSC_SCODE_PORTID_USED:
+				lid = fw_status[2] & 0xffff;
+				qlt_find_sess_invalidate_other(vha,
+				    wwn_to_u64(fcport->port_name),
+				    fcport->d_id, lid, &conflict_fcport);
+				if (conflict_fcport) {
+					/*
+					 * Another fcport shares the same
+					 * loop_id & nport id; conflict
+					 * fcport needs to finish cleanup
+					 * before this fcport can proceed
+					 * to login.
+					 */
+					conflict_fcport->conflict = fcport;
+					fcport->login_pause = 1;
+					ql_dbg(ql_dbg_disc, vha, 0x20ed,
+					    "%s %d %8phC pid %06x inuse with lid %#x post gidpn\n",
+					    __func__, __LINE__,
+					    fcport->port_name,
+					    fcport->d_id.b24, lid);
+				} else {
+					ql_dbg(ql_dbg_disc, vha, 0x20ed,
+					    "%s %d %8phC pid %06x inuse with lid %#x sched del\n",
+					    __func__, __LINE__,
+					    fcport->port_name,
+					    fcport->d_id.b24, lid);
+					qla2x00_clear_loop_id(fcport);
+					set_bit(lid, vha->hw->loop_id_map);
+					fcport->loop_id = lid;
+					fcport->keep_nport_handle = 0;
+					qlt_schedule_sess_for_deletion(fcport);
+				}
+				break;
+
+			case LSC_SCODE_NPORT_USED:
+				cid.b.domain = (fw_status[2] >> 16) & 0xff;
+				cid.b.area   = (fw_status[2] >>  8) & 0xff;
+				cid.b.al_pa  = fw_status[2] & 0xff;
+				cid.b.rsvd_1 = 0;
+
+				ql_dbg(ql_dbg_disc, vha, 0x20ec,
+				    "%s %d %8phC lid %#x in use with pid %06x post gnl\n",
+				    __func__, __LINE__, fcport->port_name,
+				    fcport->loop_id, cid.b24);
+				set_bit(fcport->loop_id,
+				    vha->hw->loop_id_map);
+				fcport->loop_id = FC_NO_LOOP_ID;
+				qla24xx_post_gnl_work(vha, fcport);
+				break;
+
+			case LSC_SCODE_NOXCB:
+				vha->hw->exch_starvation++;
+				if (vha->hw->exch_starvation > 5) {
+					ql_log(ql_log_warn, vha, 0xd046,
+					    "Exchange starvation. Resetting RISC\n");
+					vha->hw->exch_starvation = 0;
+					set_bit(ISP_ABORT_NEEDED,
+					    &vha->dpc_flags);
+					qla2xxx_wake_dpc(vha);
+				}
+				/* fall through */
+			default:
+				ql_dbg(ql_dbg_disc, vha, 0x20eb,
+				    "%s %8phC cmd error fw_status 0x%x 0x%x 0x%x\n",
+				    __func__, sp->fcport->port_name,
+				    fw_status[0], fw_status[1], fw_status[2]);
+
+				fcport->flags &= ~FCF_ASYNC_SENT;
+				fcport->disc_state = DSC_LOGIN_FAILED;
+				set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+				break;
+			}
+			break;
+
+		default:
+			ql_dbg(ql_dbg_disc, vha, 0x20eb,
+			    "%s %8phC cmd error 2 fw_status 0x%x 0x%x 0x%x\n",
+			    __func__, sp->fcport->port_name,
+			    fw_status[0], fw_status[1], fw_status[2]);
+
+			sp->fcport->flags &= ~FCF_ASYNC_SENT;
+			sp->fcport->disc_state = DSC_LOGIN_FAILED;
+			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+			break;
 		}
 
 		e = qla2x00_alloc_work(vha, QLA_EVT_UNMAP);
@@ -2792,11 +2883,12 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 		return -ENOMEM;
 	}
 
+	fcport->flags |= FCF_ASYNC_SENT;
+	fcport->disc_state = DSC_LOGIN_PEND;
 	elsio = &sp->u.iocb_cmd;
 	ql_dbg(ql_dbg_io, vha, 0x3073,
 	    "Enter: PLOGI portid=%06x\n", fcport->d_id.b24);
 
-	fcport->flags |= FCF_ASYNC_SENT;
 	sp->type = SRB_ELS_DCMD;
 	sp->name = "ELS_DCMD";
 	sp->fcport = fcport;
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 009fd5a33fcd..1b8f297449cf 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1227,11 +1227,32 @@ global_port_update:
 		break;
 
 	case MBA_IDC_AEN:
-		mb[4] = RD_REG_WORD(&reg24->mailbox4);
-		mb[5] = RD_REG_WORD(&reg24->mailbox5);
-		mb[6] = RD_REG_WORD(&reg24->mailbox6);
-		mb[7] = RD_REG_WORD(&reg24->mailbox7);
-		qla83xx_handle_8200_aen(vha, mb);
+		if (IS_QLA27XX(ha) || IS_QLA28XX(ha)) {
+			ha->flags.fw_init_done = 0;
+			ql_log(ql_log_warn, vha, 0xffff,
+			    "MPI Heartbeat stop. Chip reset needed. MB0[%xh] MB1[%xh] MB2[%xh] MB3[%xh]\n",
+			    mb[0], mb[1], mb[2], mb[3]);
+
+			if ((mb[1] & BIT_8) ||
+			    (mb[2] & BIT_8)) {
+				ql_log(ql_log_warn, vha, 0xd013,
+				    "MPI Heartbeat stop. FW dump needed\n");
+				ha->fw_dump_mpi = 1;
+				ha->isp_ops->fw_dump(vha, 1);
+			}
+			set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags);
+			qla2xxx_wake_dpc(vha);
+		} else if (IS_QLA83XX(ha)) {
+			mb[4] = RD_REG_WORD(&reg24->mailbox4);
+			mb[5] = RD_REG_WORD(&reg24->mailbox5);
+			mb[6] = RD_REG_WORD(&reg24->mailbox6);
+			mb[7] = RD_REG_WORD(&reg24->mailbox7);
+			qla83xx_handle_8200_aen(vha, mb);
+		} else {
+			ql_dbg(ql_dbg_async, vha, 0x5052,
+			    "skip Heartbeat processing mb0-3=[0x%04x] [0x%04x] [0x%04x] [0x%04x]\n",
+			    mb[0], mb[1], mb[2], mb[3]);
+		}
 		break;
 
 	case MBA_DPORT_DIAGNOSTICS:
@@ -2466,6 +2487,11 @@ qla2x00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt)
 		return;
 	}
 
+	if (sp->abort)
+		sp->aborted = 1;
+	else
+		sp->completed = 1;
+
 	if (sp->cmd_type != TYPE_SRB) {
 		req->outstanding_cmds[handle] = NULL;
 		ql_dbg(ql_dbg_io, vha, 0x3015,
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 4a1f21c11758..0cf94f05f008 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -1932,7 +1932,7 @@ qla2x00_get_port_database(scsi_qla_host_t *vha, fc_port_t *fcport, uint8_t opt)
 		pd24 = (struct port_database_24xx *) pd;
 
 		/* Check for logged in state. */
-		if (fcport->fc4f_nvme) {
+		if (NVME_TARGET(ha, fcport)) {
 			current_login_state = pd24->current_login_state >> 4;
 			last_login_state = pd24->last_login_state >> 4;
 		} else {
@@ -3899,8 +3899,9 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 				fcport->scan_state = QLA_FCPORT_FOUND;
 				fcport->n2n_flag = 1;
 				fcport->keep_nport_handle = 1;
+				fcport->fc4_type = FS_FC4TYPE_FCP;
 				if (vha->flags.nvme_enabled)
-					fcport->fc4f_nvme = 1;
+					fcport->fc4_type |= FS_FC4TYPE_NVME;
 
 				switch (fcport->disc_state) {
 				case DSC_DELETED:
@@ -6287,17 +6288,13 @@ int qla24xx_send_mb_cmd(struct scsi_qla_host *vha, mbx_cmd_t *mcp)
 	case  QLA_SUCCESS:
 		ql_dbg(ql_dbg_mbx, vha, 0x119d, "%s: %s done.\n",
 		    __func__, sp->name);
-		sp->free(sp);
 		break;
 	default:
 		ql_dbg(ql_dbg_mbx, vha, 0x119e, "%s: %s Failed. %x.\n",
 		    __func__, sp->name, rval);
-		sp->free(sp);
 		break;
 	}
 
-	return rval;
-
 done_free_sp:
 	sp->free(sp);
 done:
@@ -6362,7 +6359,7 @@ int __qla24xx_parse_gpdb(struct scsi_qla_host *vha, fc_port_t *fcport,
 	uint64_t zero = 0;
 	u8 current_login_state, last_login_state;
 
-	if (fcport->fc4f_nvme) {
+	if (NVME_TARGET(vha->hw, fcport)) {
 		current_login_state = pd->current_login_state >> 4;
 		last_login_state = pd->last_login_state >> 4;
 	} else {
@@ -6397,8 +6394,8 @@ int __qla24xx_parse_gpdb(struct scsi_qla_host *vha, fc_port_t *fcport,
 	fcport->d_id.b.al_pa = pd->port_id[2];
 	fcport->d_id.b.rsvd_1 = 0;
 
-	if (fcport->fc4f_nvme) {
-		fcport->port_type = 0;
+	if (NVME_TARGET(vha->hw, fcport)) {
+		fcport->port_type = FCT_NVME;
 		if ((pd->prli_svc_param_word_3[0] & BIT_5) == 0)
 			fcport->port_type |= FCT_NVME_INITIATOR;
 		if ((pd->prli_svc_param_word_3[0] & BIT_4) == 0)
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index 238240984bc1..eabc5127174e 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -946,7 +946,7 @@ int qla24xx_control_vp(scsi_qla_host_t *vha, int cmd)
 
 	sp = qla2x00_get_sp(base_vha, NULL, GFP_KERNEL);
 	if (!sp)
-		goto done;
+		return rval;
 
 	sp->type = SRB_CTRL_VP;
 	sp->name = "ctrl_vp";
@@ -962,7 +962,7 @@ int qla24xx_control_vp(scsi_qla_host_t *vha, int cmd)
 		ql_dbg(ql_dbg_async, vha, 0xffff,
 		    "%s: %s Failed submission. %x.\n",
 		    __func__, sp->name, rval);
-		goto done_free_sp;
+		goto done;
 	}
 
 	ql_dbg(ql_dbg_vport, vha, 0x113f, "%s hndl %x submitted\n",
@@ -980,16 +980,13 @@ int qla24xx_control_vp(scsi_qla_host_t *vha, int cmd)
 	case QLA_SUCCESS:
 		ql_dbg(ql_dbg_vport, vha, 0xffff, "%s: %s done.\n",
 		    __func__, sp->name);
-		goto done_free_sp;
+		break;
 	default:
 		ql_dbg(ql_dbg_vport, vha, 0xffff, "%s: %s Failed. %x.\n",
 		    __func__, sp->name, rval);
-		goto done_free_sp;
+		break;
 	}
 done:
-	return rval;
-
-done_free_sp:
 	sp->free(sp);
 	return rval;
 }
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 6cc19e060afc..941aa53363f5 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -224,8 +224,8 @@ static void qla_nvme_abort_work(struct work_struct *work)
 
 	if (ha->flags.host_shutting_down) {
 		ql_log(ql_log_info, sp->fcport->vha, 0xffff,
-		    "%s Calling done on sp: %p, type: 0x%x, sp->ref_count: 0x%x\n",
-		    __func__, sp, sp->type, atomic_read(&sp->ref_count));
+		    "%s Calling done on sp: %p, type: 0x%x\n",
+		    __func__, sp, sp->type);
 		sp->done(sp, 0);
 		goto out;
 	}
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 726ad4cbf4a6..8b84bc4a6ac8 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -698,11 +698,6 @@ void qla2x00_sp_compl(srb_t *sp, int res)
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
 	struct completion *comp = sp->comp;
 
-	if (WARN_ON_ONCE(atomic_read(&sp->ref_count) == 0))
-		return;
-
-	atomic_dec(&sp->ref_count);
-
 	sp->free(sp);
 	cmd->result = res;
 	CMD_SP(cmd) = NULL;
@@ -794,11 +789,6 @@ void qla2xxx_qpair_sp_compl(srb_t *sp, int res)
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
 	struct completion *comp = sp->comp;
 
-	if (WARN_ON_ONCE(atomic_read(&sp->ref_count) == 0))
-		return;
-
-	atomic_dec(&sp->ref_count);
-
 	sp->free(sp);
 	cmd->result = res;
 	CMD_SP(cmd) = NULL;
@@ -903,7 +893,7 @@ qla2xxx_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 
 	sp->u.scmd.cmd = cmd;
 	sp->type = SRB_SCSI_CMD;
-	atomic_set(&sp->ref_count, 1);
+
 	CMD_SP(cmd) = (void *)sp;
 	sp->free = qla2x00_sp_free_dma;
 	sp->done = qla2x00_sp_compl;
@@ -985,18 +975,16 @@ qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd,
 
 	sp->u.scmd.cmd = cmd;
 	sp->type = SRB_SCSI_CMD;
-	atomic_set(&sp->ref_count, 1);
 	CMD_SP(cmd) = (void *)sp;
 	sp->free = qla2xxx_qpair_sp_free_dma;
 	sp->done = qla2xxx_qpair_sp_compl;
-	sp->qpair = qpair;
 
 	rval = ha->isp_ops->start_scsi_mq(sp);
 	if (rval != QLA_SUCCESS) {
 		ql_dbg(ql_dbg_io + ql_dbg_verbose, vha, 0x3078,
 		    "Start scsi failed rval=%d for cmd=%p.\n", rval, cmd);
 		if (rval == QLA_INTERFACE_ERROR)
-			goto qc24_fail_command;
+			goto qc24_free_sp_fail_command;
 		goto qc24_host_busy_free_sp;
 	}
 
@@ -1008,6 +996,11 @@ qc24_host_busy_free_sp:
 qc24_target_busy:
 	return SCSI_MLQUEUE_TARGET_BUSY;
 
+qc24_free_sp_fail_command:
+	sp->free(sp);
+	CMD_SP(cmd) = NULL;
+	qla2xxx_rel_qpair_sp(sp->qpair, sp);
+
 qc24_fail_command:
 	cmd->scsi_done(cmd);
 
@@ -1184,16 +1177,6 @@ qla2x00_wait_for_chip_reset(scsi_qla_host_t *vha)
 	return return_status;
 }
 
-static int
-sp_get(struct srb *sp)
-{
-	if (!refcount_inc_not_zero((refcount_t *)&sp->ref_count))
-		/* kref get fail */
-		return ENXIO;
-	else
-		return 0;
-}
-
 #define ISP_REG_DISCONNECT 0xffffffffU
 /**************************************************************************
 * qla2x00_isp_reg_stat
@@ -1249,6 +1232,9 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 	uint64_t lun;
 	int rval;
 	struct qla_hw_data *ha = vha->hw;
+	uint32_t ratov_j;
+	struct qla_qpair *qpair;
+	unsigned long flags;
 
 	if (qla2x00_isp_reg_stat(ha)) {
 		ql_log(ql_log_info, vha, 0x8042,
@@ -1261,13 +1247,26 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 		return ret;
 
 	sp = scsi_cmd_priv(cmd);
+	qpair = sp->qpair;
 
-	if (sp->fcport && sp->fcport->deleted)
+	if ((sp->fcport && sp->fcport->deleted) || !qpair)
 		return SUCCESS;
 
-	/* Return if the command has already finished. */
-	if (sp_get(sp))
+	spin_lock_irqsave(qpair->qp_lock_ptr, flags);
+	if (sp->completed) {
+		spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
 		return SUCCESS;
+	}
+
+	if (sp->abort || sp->aborted) {
+		spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
+		return FAILED;
+	}
+
+	sp->abort = 1;
+	sp->comp = &comp;
+	spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
+
 
 	id = cmd->device->id;
 	lun = cmd->device->lun;
@@ -1276,47 +1275,37 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 	    "Aborting from RISC nexus=%ld:%d:%llu sp=%p cmd=%p handle=%x\n",
 	    vha->host_no, id, lun, sp, cmd, sp->handle);
 
+	/*
+	 * Abort will release the original Command/sp from FW. Let the
+	 * original command call scsi_done. In return, he will wakeup
+	 * this sleeping thread.
+	 */
 	rval = ha->isp_ops->abort_command(sp);
+
 	ql_dbg(ql_dbg_taskm, vha, 0x8003,
 	       "Abort command mbx cmd=%p, rval=%x.\n", cmd, rval);
 
+	/* Wait for the command completion. */
+	ratov_j = ha->r_a_tov/10 * 4 * 1000;
+	ratov_j = msecs_to_jiffies(ratov_j);
 	switch (rval) {
 	case QLA_SUCCESS:
-		/*
-		 * The command has been aborted. That means that the firmware
-		 * won't report a completion.
-		 */
-		sp->done(sp, DID_ABORT << 16);
-		ret = SUCCESS;
-		break;
-	case QLA_FUNCTION_PARAMETER_ERROR: {
-		/* Wait for the command completion. */
-		uint32_t ratov = ha->r_a_tov/10;
-		uint32_t ratov_j = msecs_to_jiffies(4 * ratov * 1000);
-
-		WARN_ON_ONCE(sp->comp);
-		sp->comp = &comp;
 		if (!wait_for_completion_timeout(&comp, ratov_j)) {
 			ql_dbg(ql_dbg_taskm, vha, 0xffff,
 			    "%s: Abort wait timer (4 * R_A_TOV[%d]) expired\n",
-			    __func__, ha->r_a_tov);
+			    __func__, ha->r_a_tov/10);
 			ret = FAILED;
 		} else {
 			ret = SUCCESS;
 		}
 		break;
-	}
 	default:
-		/*
-		 * Either abort failed or abort and completion raced. Let
-		 * the SCSI core retry the abort in the former case.
-		 */
 		ret = FAILED;
 		break;
 	}
 
 	sp->comp = NULL;
-	atomic_dec(&sp->ref_count);
+
 	ql_log(ql_log_info, vha, 0x801c,
 	    "Abort command issued nexus=%ld:%d:%llu -- %x.\n",
 	    vha->host_no, id, lun, ret);
@@ -1708,32 +1697,53 @@ static void qla2x00_abort_srb(struct qla_qpair *qp, srb_t *sp, const int res,
 	scsi_qla_host_t *vha = qp->vha;
 	struct qla_hw_data *ha = vha->hw;
 	int rval;
+	bool ret_cmd;
+	uint32_t ratov_j;
 
-	if (sp_get(sp))
+	if (qla2x00_chip_is_down(vha)) {
+		sp->done(sp, res);
 		return;
+	}
 
 	if (sp->type == SRB_NVME_CMD || sp->type == SRB_NVME_LS ||
 	    (sp->type == SRB_SCSI_CMD && !ha->flags.eeh_busy &&
 	     !test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags) &&
 	     !qla2x00_isp_reg_stat(ha))) {
+		if (sp->comp) {
+			sp->done(sp, res);
+			return;
+		}
+
 		sp->comp = &comp;
+		sp->abort =  1;
 		spin_unlock_irqrestore(qp->qp_lock_ptr, *flags);
-		rval = ha->isp_ops->abort_command(sp);
 
+		rval = ha->isp_ops->abort_command(sp);
+		/* Wait for command completion. */
+		ret_cmd = false;
+		ratov_j = ha->r_a_tov/10 * 4 * 1000;
+		ratov_j = msecs_to_jiffies(ratov_j);
 		switch (rval) {
 		case QLA_SUCCESS:
-			sp->done(sp, res);
+			if (wait_for_completion_timeout(&comp, ratov_j)) {
+				ql_dbg(ql_dbg_taskm, vha, 0xffff,
+				    "%s: Abort wait timer (4 * R_A_TOV[%d]) expired\n",
+				    __func__, ha->r_a_tov/10);
+				ret_cmd = true;
+			}
+			/* else FW return SP to driver */
 			break;
-		case QLA_FUNCTION_PARAMETER_ERROR:
-			wait_for_completion(&comp);
+		default:
+			ret_cmd = true;
 			break;
 		}
 
 		spin_lock_irqsave(qp->qp_lock_ptr, *flags);
-		sp->comp = NULL;
+		if (ret_cmd && (!sp->completed || !sp->aborted))
+			sp->done(sp, res);
+	} else {
+		sp->done(sp, res);
 	}
-
-	atomic_dec(&sp->ref_count);
 }
 
 static void
@@ -1755,7 +1765,6 @@ __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res)
 	for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) {
 		sp = req->outstanding_cmds[cnt];
 		if (sp) {
-			req->outstanding_cmds[cnt] = NULL;
 			switch (sp->cmd_type) {
 			case TYPE_SRB:
 				qla2x00_abort_srb(qp, sp, res, &flags);
@@ -1777,6 +1786,7 @@ __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res)
 			default:
 				break;
 			}
+			req->outstanding_cmds[cnt] = NULL;
 		}
 	}
 	spin_unlock_irqrestore(qp->qp_lock_ptr, flags);
@@ -3492,6 +3502,29 @@ disable_device:
 	return ret;
 }
 
+static void __qla_set_remove_flag(scsi_qla_host_t *base_vha)
+{
+	scsi_qla_host_t *vp;
+	unsigned long flags;
+	struct qla_hw_data *ha;
+
+	if (!base_vha)
+		return;
+
+	ha = base_vha->hw;
+
+	spin_lock_irqsave(&ha->vport_slock, flags);
+	list_for_each_entry(vp, &ha->vp_list, list)
+		set_bit(PFLG_DRIVER_REMOVING, &vp->pci_flags);
+
+	/*
+	 * Indicate device removal to prevent future board_disable
+	 * and wait until any pending board_disable has completed.
+	 */
+	set_bit(PFLG_DRIVER_REMOVING, &base_vha->pci_flags);
+	spin_unlock_irqrestore(&ha->vport_slock, flags);
+}
+
 static void
 qla2x00_shutdown(struct pci_dev *pdev)
 {
@@ -3508,7 +3541,7 @@ qla2x00_shutdown(struct pci_dev *pdev)
 	 * Prevent future board_disable and wait
 	 * until any pending board_disable has completed.
 	 */
-	set_bit(PFLG_DRIVER_REMOVING, &vha->pci_flags);
+	__qla_set_remove_flag(vha);
 	cancel_work_sync(&ha->board_disable);
 
 	if (!atomic_read(&pdev->enable_cnt))
@@ -3668,10 +3701,7 @@ qla2x00_remove_one(struct pci_dev *pdev)
 	ha = base_vha->hw;
 	ql_log(ql_log_info, base_vha, 0xb079,
 	    "Removing driver\n");
-
-	/* Indicate device removal to prevent future board_disable and wait
-	 * until any pending board_disable has completed. */
-	set_bit(PFLG_DRIVER_REMOVING, &base_vha->pci_flags);
+	__qla_set_remove_flag(base_vha);
 	cancel_work_sync(&ha->board_disable);
 
 	/*
@@ -4666,7 +4696,8 @@ qla2x00_mem_free(struct qla_hw_data *ha)
 	ha->sfp_data = NULL;
 
 	if (ha->flt)
-		dma_free_coherent(&ha->pdev->dev, SFP_DEV_SIZE,
+		dma_free_coherent(&ha->pdev->dev,
+		    sizeof(struct qla_flt_header) + FLT_REGIONS_SIZE,
 		    ha->flt, ha->flt_dma);
 	ha->flt = NULL;
 	ha->flt_dma = 0;
@@ -5042,19 +5073,17 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 			fcport->d_id = e->u.new_sess.id;
 			fcport->flags |= FCF_FABRIC_DEVICE;
 			fcport->fw_login_state = DSC_LS_PLOGI_PEND;
-			if (e->u.new_sess.fc4_type == FS_FC4TYPE_FCP)
-				fcport->fc4_type = FC4_TYPE_FCP_SCSI;
-
-			if (e->u.new_sess.fc4_type == FS_FC4TYPE_NVME) {
-				fcport->fc4_type = FC4_TYPE_OTHER;
-				fcport->fc4f_nvme = FC4_TYPE_NVME;
-			}
 
 			memcpy(fcport->port_name, e->u.new_sess.port_name,
 			    WWN_SIZE);
 
-			if (e->u.new_sess.fc4_type & FS_FCP_IS_N2N)
+			fcport->fc4_type = e->u.new_sess.fc4_type;
+			if (e->u.new_sess.fc4_type & FS_FCP_IS_N2N) {
+				fcport->fc4_type = FS_FC4TYPE_FCP;
 				fcport->n2n_flag = 1;
+				if (vha->flags.nvme_enabled)
+					fcport->fc4_type |= FS_FC4TYPE_NVME;
+			}
 
 		} else {
 			ql_dbg(ql_dbg_disc, vha, 0xffff,
@@ -5158,7 +5187,8 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 				fcport->flags &= ~FCF_FABRIC_DEVICE;
 				fcport->keep_nport_handle = 1;
 				if (vha->flags.nvme_enabled) {
-					fcport->fc4f_nvme = 1;
+					fcport->fc4_type =
+					    (FS_FC4TYPE_NVME | FS_FC4TYPE_FCP);
 					fcport->n2n_flag = 1;
 				}
 				fcport->fw_login_state = 0;
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index a06e56224a55..51b275a575a5 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -463,7 +463,7 @@ void qlt_response_pkt_all_vps(struct scsi_qla_host *vha,
 
 	case IMMED_NOTIFY_TYPE:
 	{
-		struct scsi_qla_host *host = vha;
+		struct scsi_qla_host *host;
 		struct imm_ntfy_from_isp *entry =
 		    (struct imm_ntfy_from_isp *)pkt;
 
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index 294d77c02cdf..5b0c057def2b 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -10,6 +10,7 @@
 #define ISPREG(vha)	(&(vha)->hw->iobase->isp24)
 #define IOBAR(reg)	offsetof(typeof(*(reg)), iobase_addr)
 #define IOBASE(vha)	IOBAR(ISPREG(vha))
+#define INVALID_ENTRY ((struct qla27xx_fwdt_entry *)0xffffffffffffffffUL)
 
 static inline void
 qla27xx_insert16(uint16_t value, void *buf, ulong *len)
@@ -261,6 +262,7 @@ qla27xx_fwdt_entry_t262(struct scsi_qla_host *vha,
 	ulong start = le32_to_cpu(ent->t262.start_addr);
 	ulong end = le32_to_cpu(ent->t262.end_addr);
 	ulong dwords;
+	int rc;
 
 	ql_dbg(ql_dbg_misc, vha, 0xd206,
 	    "%s: rdram(%x) [%lx]\n", __func__, ent->t262.ram_area, *len);
@@ -308,7 +310,13 @@ qla27xx_fwdt_entry_t262(struct scsi_qla_host *vha,
 	dwords = end - start + 1;
 	if (buf) {
 		buf += *len;
-		qla24xx_dump_ram(vha->hw, start, buf, dwords, &buf);
+		rc = qla24xx_dump_ram(vha->hw, start, buf, dwords, &buf);
+		if (rc != QLA_SUCCESS) {
+			ql_dbg(ql_dbg_async, vha, 0xffff,
+			    "%s: dump ram MB failed. Area %xh start %lxh end %lxh\n",
+			    __func__, area, start, end);
+			return INVALID_ENTRY;
+		}
 	}
 	*len += dwords * sizeof(uint32_t);
 done:
@@ -838,6 +846,13 @@ qla27xx_walk_template(struct scsi_qla_host *vha,
 		ent = qla27xx_find_entry(type)(vha, ent, buf, len);
 		if (!ent)
 			break;
+
+		if (ent == INVALID_ENTRY) {
+			*len = 0;
+			ql_dbg(ql_dbg_async, vha, 0xffff,
+			    "Unable to capture FW dump");
+			goto bailout;
+		}
 	}
 
 	if (tmp->count)
@@ -847,6 +862,9 @@ qla27xx_walk_template(struct scsi_qla_host *vha,
 	if (ent)
 		ql_dbg(ql_dbg_misc, vha, 0xd019,
 		    "%s: missing end entry\n", __func__);
+
+bailout:
+	cpu_to_le32s(&tmp->count);	/* endianize residual count */
 }
 
 static void
@@ -999,8 +1017,9 @@ qla27xx_fwdump(scsi_qla_host_t *vha, int hardware_locked)
 		uint j;
 		ulong len;
 		void *buf = vha->hw->fw_dump;
+		uint count = vha->hw->fw_dump_mpi ? 2 : 1;
 
-		for (j = 0; j < 2; j++, fwdt++, buf += len) {
+		for (j = 0; j < count; j++, fwdt++, buf += len) {
 			ql_log(ql_log_warn, vha, 0xd011,
 			    "-> fwdt%u running...\n", j);
 			if (!fwdt->template) {
@@ -1010,7 +1029,9 @@ qla27xx_fwdump(scsi_qla_host_t *vha, int hardware_locked)
 			}
 			len = qla27xx_execute_fwdt_template(vha,
 			    fwdt->template, buf);
-			if (len != fwdt->dump_size) {
+			if (len == 0) {
+				goto bailout;
+			} else if (len != fwdt->dump_size) {
 				ql_log(ql_log_warn, vha, 0xd013,
 				    "-> fwdt%u fwdump residual=%+ld\n",
 				    j, fwdt->dump_size - len);
@@ -1025,6 +1046,8 @@ qla27xx_fwdump(scsi_qla_host_t *vha, int hardware_locked)
 		qla2x00_post_uevent_work(vha, QLA_UEVENT_CODE_FW_DUMP);
 	}
 
+bailout:
+	vha->hw->fw_dump_mpi = 0;
 #ifndef __CHECKER__
 	if (!hardware_locked)
 		spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h
index a8f2a953ceff..03bd3b712b77 100644
--- a/drivers/scsi/qla2xxx/qla_version.h
+++ b/drivers/scsi/qla2xxx/qla_version.h
@@ -7,7 +7,7 @@
 /*
  * Driver version
  */
-#define QLA2XXX_VERSION      "10.01.00.19-k"
+#define QLA2XXX_VERSION      "10.01.00.21-k"
 
 #define QLA_DRIVER_MAJOR_VER	10
 #define QLA_DRIVER_MINOR_VER	1
diff --git a/drivers/scsi/qla4xxx/ql4_mbx.c b/drivers/scsi/qla4xxx/ql4_mbx.c
index dac9a7013208..02636b4785c5 100644
--- a/drivers/scsi/qla4xxx/ql4_mbx.c
+++ b/drivers/scsi/qla4xxx/ql4_mbx.c
@@ -640,9 +640,6 @@ int qla4xxx_initialize_fw_cb(struct scsi_qla_host * ha)
 
 	if (qla4xxx_get_ifcb(ha, &mbox_cmd[0], &mbox_sts[0], init_fw_cb_dma) !=
 	    QLA_SUCCESS) {
-		dma_free_coherent(&ha->pdev->dev,
-				  sizeof(struct addr_ctrl_blk),
-				  init_fw_cb, init_fw_cb_dma);
 		goto exit_init_fw_cb;
 	}
 
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 7a1b6c76f263..930e4803d888 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -186,7 +186,7 @@ void scsi_finish_command(struct scsi_cmnd *cmd)
 	struct scsi_driver *drv;
 	unsigned int good_bytes;
 
-	scsi_device_unbusy(sdev);
+	scsi_device_unbusy(sdev, cmd);
 
 	/*
 	 * Clear the flags that say that the device/target/host is no longer
@@ -465,10 +465,14 @@ void scsi_attach_vpd(struct scsi_device *sdev)
 		return;
 
 	for (i = 4; i < vpd_buf->len; i++) {
+		if (vpd_buf->data[i] == 0x0)
+			scsi_update_vpd_page(sdev, 0x0, &sdev->vpd_pg0);
 		if (vpd_buf->data[i] == 0x80)
 			scsi_update_vpd_page(sdev, 0x80, &sdev->vpd_pg80);
 		if (vpd_buf->data[i] == 0x83)
 			scsi_update_vpd_page(sdev, 0x83, &sdev->vpd_pg83);
+		if (vpd_buf->data[i] == 0x89)
+			scsi_update_vpd_page(sdev, 0x89, &sdev->vpd_pg89);
 	}
 	kfree(vpd_buf);
 }
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index d323523f5f9d..44cb054d5e66 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -1025,7 +1025,7 @@ static int fill_from_dev_buffer(struct scsi_cmnd *scp, unsigned char *arr,
 static int p_fill_from_dev_buffer(struct scsi_cmnd *scp, const void *arr,
 				  int arr_len, unsigned int off_dst)
 {
-	int act_len, n;
+	unsigned int act_len, n;
 	struct scsi_data_buffer *sdb = &scp->sdb;
 	off_t skip = off_dst;
 
@@ -1039,7 +1039,7 @@ static int p_fill_from_dev_buffer(struct scsi_cmnd *scp, const void *arr,
 	pr_debug("%s: off_dst=%u, scsi_bufflen=%u, act_len=%u, resid=%d\n",
 		 __func__, off_dst, scsi_bufflen(scp), act_len,
 		 scsi_get_resid(scp));
-	n = (int)scsi_bufflen(scp) - ((int)off_dst + act_len);
+	n = scsi_bufflen(scp) - (off_dst + act_len);
 	scsi_set_resid(scp, min(scsi_get_resid(scp), n));
 	return 0;
 }
@@ -5263,6 +5263,11 @@ static int __init scsi_debug_init(void)
 		return -EINVAL;
 	}
 
+	if (sdebug_num_tgts < 0) {
+		pr_err("num_tgts must be >= 0\n");
+		return -EINVAL;
+	}
+
 	if (sdebug_guard > 1) {
 		pr_err("guard must be 0 or 1\n");
 		return -EINVAL;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 91c007d26c1e..3e7a45d0daca 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -189,7 +189,7 @@ static void __scsi_queue_insert(struct scsi_cmnd *cmd, int reason, bool unbusy)
 	 * active on the host/device.
 	 */
 	if (unbusy)
-		scsi_device_unbusy(device);
+		scsi_device_unbusy(device, cmd);
 
 	/*
 	 * Requeue this command.  It will go before all other commands
@@ -321,20 +321,20 @@ static void scsi_init_cmd_errh(struct scsi_cmnd *cmd)
 }
 
 /*
- * Decrement the host_busy counter and wake up the error handler if necessary.
- * Avoid as follows that the error handler is not woken up if shost->host_busy
- * == shost->host_failed: use call_rcu() in scsi_eh_scmd_add() in combination
- * with an RCU read lock in this function to ensure that this function in its
- * entirety either finishes before scsi_eh_scmd_add() increases the
+ * Wake up the error handler if necessary. Avoid as follows that the error
+ * handler is not woken up if host in-flight requests number ==
+ * shost->host_failed: use call_rcu() in scsi_eh_scmd_add() in combination
+ * with an RCU read lock in this function to ensure that this function in
+ * its entirety either finishes before scsi_eh_scmd_add() increases the
  * host_failed counter or that it notices the shost state change made by
  * scsi_eh_scmd_add().
  */
-static void scsi_dec_host_busy(struct Scsi_Host *shost)
+static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
 {
 	unsigned long flags;
 
 	rcu_read_lock();
-	atomic_dec(&shost->host_busy);
+	__clear_bit(SCMD_STATE_INFLIGHT, &cmd->state);
 	if (unlikely(scsi_host_in_recovery(shost))) {
 		spin_lock_irqsave(shost->host_lock, flags);
 		if (shost->host_failed || shost->host_eh_scheduled)
@@ -344,12 +344,12 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost)
 	rcu_read_unlock();
 }
 
-void scsi_device_unbusy(struct scsi_device *sdev)
+void scsi_device_unbusy(struct scsi_device *sdev, struct scsi_cmnd *cmd)
 {
 	struct Scsi_Host *shost = sdev->host;
 	struct scsi_target *starget = scsi_target(sdev);
 
-	scsi_dec_host_busy(shost);
+	scsi_dec_host_busy(shost, cmd);
 
 	if (starget->can_queue > 0)
 		atomic_dec(&starget->target_busy);
@@ -430,9 +430,6 @@ static inline bool scsi_target_is_busy(struct scsi_target *starget)
 
 static inline bool scsi_host_is_busy(struct Scsi_Host *shost)
 {
-	if (shost->can_queue > 0 &&
-	    atomic_read(&shost->host_busy) >= shost->can_queue)
-		return true;
 	if (atomic_read(&shost->host_blocked) > 0)
 		return true;
 	if (shost->host_self_blocked)
@@ -1139,6 +1136,7 @@ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd)
 	unsigned int flags = cmd->flags & SCMD_PRESERVED_FLAGS;
 	unsigned long jiffies_at_alloc;
 	int retries;
+	bool in_flight;
 
 	if (!blk_rq_is_scsi(rq) && !(flags & SCMD_INITIALIZED)) {
 		flags |= SCMD_INITIALIZED;
@@ -1147,6 +1145,7 @@ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd)
 
 	jiffies_at_alloc = cmd->jiffies_at_alloc;
 	retries = cmd->retries;
+	in_flight = test_bit(SCMD_STATE_INFLIGHT, &cmd->state);
 	/* zero out the cmd, except for the embedded scsi_request */
 	memset((char *)cmd + sizeof(cmd->req), 0,
 		sizeof(*cmd) - sizeof(cmd->req) + dev->host->hostt->cmd_size);
@@ -1158,6 +1157,8 @@ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd)
 	INIT_DELAYED_WORK(&cmd->abort_work, scmd_eh_abort_handler);
 	cmd->jiffies_at_alloc = jiffies_at_alloc;
 	cmd->retries = retries;
+	if (in_flight)
+		__set_bit(SCMD_STATE_INFLIGHT, &cmd->state);
 
 	scsi_add_cmd_to_list(cmd);
 }
@@ -1367,16 +1368,14 @@ out_dec:
  */
 static inline int scsi_host_queue_ready(struct request_queue *q,
 				   struct Scsi_Host *shost,
-				   struct scsi_device *sdev)
+				   struct scsi_device *sdev,
+				   struct scsi_cmnd *cmd)
 {
-	unsigned int busy;
-
 	if (scsi_host_in_recovery(shost))
 		return 0;
 
-	busy = atomic_inc_return(&shost->host_busy) - 1;
 	if (atomic_read(&shost->host_blocked) > 0) {
-		if (busy)
+		if (scsi_host_busy(shost) > 0)
 			goto starved;
 
 		/*
@@ -1390,8 +1389,6 @@ static inline int scsi_host_queue_ready(struct request_queue *q,
 				     "unblocking host at zero depth\n"));
 	}
 
-	if (shost->can_queue > 0 && busy >= shost->can_queue)
-		goto starved;
 	if (shost->host_self_blocked)
 		goto starved;
 
@@ -1403,6 +1400,8 @@ static inline int scsi_host_queue_ready(struct request_queue *q,
 		spin_unlock_irq(shost->host_lock);
 	}
 
+	__set_bit(SCMD_STATE_INFLIGHT, &cmd->state);
+
 	return 1;
 
 starved:
@@ -1411,7 +1410,7 @@ starved:
 		list_add_tail(&sdev->starved_entry, &shost->starved_list);
 	spin_unlock_irq(shost->host_lock);
 out_dec:
-	scsi_dec_host_busy(shost);
+	scsi_dec_host_busy(shost, cmd);
 	return 0;
 }
 
@@ -1665,7 +1664,7 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 	ret = BLK_STS_RESOURCE;
 	if (!scsi_target_queue_ready(shost, sdev))
 		goto out_put_budget;
-	if (!scsi_host_queue_ready(q, shost, sdev))
+	if (!scsi_host_queue_ready(q, shost, sdev, cmd))
 		goto out_dec_target_busy;
 
 	if (!(req->rq_flags & RQF_DONTPREP)) {
@@ -1697,7 +1696,7 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 
 out_dec_host_busy:
-	scsi_dec_host_busy(shost);
+	scsi_dec_host_busy(shost, cmd);
 out_dec_target_busy:
 	if (scsi_target(sdev)->can_queue > 0)
 		atomic_dec(&scsi_target(sdev)->target_busy);
diff --git a/drivers/scsi/scsi_logging.c b/drivers/scsi/scsi_logging.c
index c6ed0b12e807..c91fa3feb930 100644
--- a/drivers/scsi/scsi_logging.c
+++ b/drivers/scsi/scsi_logging.c
@@ -390,6 +390,7 @@ void scsi_print_result(const struct scsi_cmnd *cmd, const char *msg,
 	const char *mlret_string = scsi_mlreturn_string(disposition);
 	const char *hb_string = scsi_hostbyte_string(cmd->result);
 	const char *db_string = scsi_driverbyte_string(cmd->result);
+	unsigned long cmd_age = (jiffies - cmd->jiffies_at_alloc) / HZ;
 
 	logbuf = scsi_log_reserve_buffer(&logbuf_len);
 	if (!logbuf)
@@ -431,10 +432,15 @@ void scsi_print_result(const struct scsi_cmnd *cmd, const char *msg,
 
 	if (db_string)
 		off += scnprintf(logbuf + off, logbuf_len - off,
-				 "driverbyte=%s", db_string);
+				 "driverbyte=%s ", db_string);
 	else
 		off += scnprintf(logbuf + off, logbuf_len - off,
-				 "driverbyte=0x%02x", driver_byte(cmd->result));
+				 "driverbyte=0x%02x ",
+				 driver_byte(cmd->result));
+
+	off += scnprintf(logbuf + off, logbuf_len - off,
+			 "cmd_age=%lus", cmd_age);
+
 out_printk:
 	dev_printk(KERN_INFO, &cmd->device->sdev_gendev, "%s", logbuf);
 	scsi_log_release_buffer(logbuf);
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index cc2859d76d81..3bff9f7aa684 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -87,7 +87,7 @@ int scsi_noretry_cmd(struct scsi_cmnd *scmd);
 extern void scsi_add_cmd_to_list(struct scsi_cmnd *cmd);
 extern void scsi_del_cmd_from_list(struct scsi_cmnd *cmd);
 extern int scsi_maybe_unblock_host(struct scsi_device *sdev);
-extern void scsi_device_unbusy(struct scsi_device *sdev);
+extern void scsi_device_unbusy(struct scsi_device *sdev, struct scsi_cmnd *cmd);
 extern void scsi_queue_insert(struct scsi_cmnd *cmd, int reason);
 extern void scsi_io_completion(struct scsi_cmnd *, unsigned int);
 extern void scsi_run_host_queues(struct Scsi_Host *shost);
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index cc51f4756077..677b5c5403d2 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -437,6 +437,7 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
 	struct device *parent;
 	struct list_head *this, *tmp;
 	struct scsi_vpd *vpd_pg80 = NULL, *vpd_pg83 = NULL;
+	struct scsi_vpd *vpd_pg0 = NULL, *vpd_pg89 = NULL;
 	unsigned long flags;
 
 	sdev = container_of(work, struct scsi_device, ew.work);
@@ -466,16 +467,24 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
 	sdev->request_queue = NULL;
 
 	mutex_lock(&sdev->inquiry_mutex);
+	vpd_pg0 = rcu_replace_pointer(sdev->vpd_pg0, vpd_pg0,
+				       lockdep_is_held(&sdev->inquiry_mutex));
 	vpd_pg80 = rcu_replace_pointer(sdev->vpd_pg80, vpd_pg80,
 				       lockdep_is_held(&sdev->inquiry_mutex));
 	vpd_pg83 = rcu_replace_pointer(sdev->vpd_pg83, vpd_pg83,
 				       lockdep_is_held(&sdev->inquiry_mutex));
+	vpd_pg89 = rcu_replace_pointer(sdev->vpd_pg89, vpd_pg89,
+				       lockdep_is_held(&sdev->inquiry_mutex));
 	mutex_unlock(&sdev->inquiry_mutex);
 
+	if (vpd_pg0)
+		kfree_rcu(vpd_pg0, rcu);
 	if (vpd_pg83)
 		kfree_rcu(vpd_pg83, rcu);
 	if (vpd_pg80)
 		kfree_rcu(vpd_pg80, rcu);
+	if (vpd_pg89)
+		kfree_rcu(vpd_pg89, rcu);
 	kfree(sdev->inquiry);
 	kfree(sdev);
 
@@ -868,6 +877,8 @@ static struct bin_attribute dev_attr_vpd_##_page = {		\
 
 sdev_vpd_pg_attr(pg83);
 sdev_vpd_pg_attr(pg80);
+sdev_vpd_pg_attr(pg89);
+sdev_vpd_pg_attr(pg0);
 
 static ssize_t show_inquiry(struct file *filep, struct kobject *kobj,
 			    struct bin_attribute *bin_attr,
@@ -1200,12 +1211,18 @@ static umode_t scsi_sdev_bin_attr_is_visible(struct kobject *kobj,
 	struct scsi_device *sdev = to_scsi_device(dev);
 
 
+	if (attr == &dev_attr_vpd_pg0 && !sdev->vpd_pg0)
+		return 0;
+
 	if (attr == &dev_attr_vpd_pg80 && !sdev->vpd_pg80)
 		return 0;
 
 	if (attr == &dev_attr_vpd_pg83 && !sdev->vpd_pg83)
 		return 0;
 
+	if (attr == &dev_attr_vpd_pg89 && !sdev->vpd_pg89)
+		return 0;
+
 	return S_IRUGO;
 }
 
@@ -1248,8 +1265,10 @@ static struct attribute *scsi_sdev_attrs[] = {
 };
 
 static struct bin_attribute *scsi_sdev_bin_attrs[] = {
+	&dev_attr_vpd_pg0,
 	&dev_attr_vpd_pg83,
 	&dev_attr_vpd_pg80,
+	&dev_attr_vpd_pg89,
 	&dev_attr_inquiry,
 	NULL
 };
@@ -1309,7 +1328,8 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev)
 	device_enable_async_suspend(&sdev->sdev_gendev);
 	scsi_autopm_get_target(starget);
 	pm_runtime_set_active(&sdev->sdev_gendev);
-	pm_runtime_forbid(&sdev->sdev_gendev);
+	if (!sdev->rpm_autosuspend)
+		pm_runtime_forbid(&sdev->sdev_gendev);
 	pm_runtime_enable(&sdev->sdev_gendev);
 	scsi_autopm_put_target(starget);
 
diff --git a/drivers/scsi/scsi_trace.c b/drivers/scsi/scsi_trace.c
index 0f17e7dac1b0..ac35c301c792 100644
--- a/drivers/scsi/scsi_trace.c
+++ b/drivers/scsi/scsi_trace.c
@@ -9,7 +9,7 @@
 #include <trace/events/scsi.h>
 
 #define SERVICE_ACTION16(cdb) (cdb[1] & 0x1f)
-#define SERVICE_ACTION32(cdb) ((cdb[8] << 8) | cdb[9])
+#define SERVICE_ACTION32(cdb) (get_unaligned_be16(&cdb[8]))
 
 static const char *
 scsi_trace_misc(struct trace_seq *, unsigned char *, int);
@@ -18,15 +18,18 @@ static const char *
 scsi_trace_rw6(struct trace_seq *p, unsigned char *cdb, int len)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
-	sector_t lba = 0, txlen = 0;
+	u32 lba = 0, txlen;
 
 	lba |= ((cdb[1] & 0x1F) << 16);
 	lba |=  (cdb[2] << 8);
 	lba |=   cdb[3];
-	txlen = cdb[4];
+	/*
+	 * From SBC-2: a TRANSFER LENGTH field set to zero specifies that 256
+	 * logical blocks shall be read (READ(6)) or written (WRITE(6)).
+	 */
+	txlen = cdb[4] ? cdb[4] : 256;
 
-	trace_seq_printf(p, "lba=%llu txlen=%llu",
-			 (unsigned long long)lba, (unsigned long long)txlen);
+	trace_seq_printf(p, "lba=%u txlen=%u", lba, txlen);
 	trace_seq_putc(p, 0);
 
 	return ret;
@@ -36,17 +39,12 @@ static const char *
 scsi_trace_rw10(struct trace_seq *p, unsigned char *cdb, int len)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
-	sector_t lba = 0, txlen = 0;
+	u32 lba, txlen;
 
-	lba |= (cdb[2] << 24);
-	lba |= (cdb[3] << 16);
-	lba |= (cdb[4] << 8);
-	lba |=  cdb[5];
-	txlen |= (cdb[7] << 8);
-	txlen |=  cdb[8];
+	lba = get_unaligned_be32(&cdb[2]);
+	txlen = get_unaligned_be16(&cdb[7]);
 
-	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
-			 (unsigned long long)lba, (unsigned long long)txlen,
+	trace_seq_printf(p, "lba=%u txlen=%u protect=%u", lba, txlen,
 			 cdb[1] >> 5);
 
 	if (cdb[0] == WRITE_SAME)
@@ -61,19 +59,12 @@ static const char *
 scsi_trace_rw12(struct trace_seq *p, unsigned char *cdb, int len)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
-	sector_t lba = 0, txlen = 0;
-
-	lba |= (cdb[2] << 24);
-	lba |= (cdb[3] << 16);
-	lba |= (cdb[4] << 8);
-	lba |=  cdb[5];
-	txlen |= (cdb[6] << 24);
-	txlen |= (cdb[7] << 16);
-	txlen |= (cdb[8] << 8);
-	txlen |=  cdb[9];
-
-	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
-			 (unsigned long long)lba, (unsigned long long)txlen,
+	u32 lba, txlen;
+
+	lba = get_unaligned_be32(&cdb[2]);
+	txlen = get_unaligned_be32(&cdb[6]);
+
+	trace_seq_printf(p, "lba=%u txlen=%u protect=%u", lba, txlen,
 			 cdb[1] >> 5);
 	trace_seq_putc(p, 0);
 
@@ -84,23 +75,13 @@ static const char *
 scsi_trace_rw16(struct trace_seq *p, unsigned char *cdb, int len)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
-	sector_t lba = 0, txlen = 0;
-
-	lba |= ((u64)cdb[2] << 56);
-	lba |= ((u64)cdb[3] << 48);
-	lba |= ((u64)cdb[4] << 40);
-	lba |= ((u64)cdb[5] << 32);
-	lba |= (cdb[6] << 24);
-	lba |= (cdb[7] << 16);
-	lba |= (cdb[8] << 8);
-	lba |=  cdb[9];
-	txlen |= (cdb[10] << 24);
-	txlen |= (cdb[11] << 16);
-	txlen |= (cdb[12] << 8);
-	txlen |=  cdb[13];
-
-	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
-			 (unsigned long long)lba, (unsigned long long)txlen,
+	u64 lba;
+	u32 txlen;
+
+	lba = get_unaligned_be64(&cdb[2]);
+	txlen = get_unaligned_be32(&cdb[10]);
+
+	trace_seq_printf(p, "lba=%llu txlen=%u protect=%u", lba, txlen,
 			 cdb[1] >> 5);
 
 	if (cdb[0] == WRITE_SAME_16)
@@ -115,8 +96,8 @@ static const char *
 scsi_trace_rw32(struct trace_seq *p, unsigned char *cdb, int len)
 {
 	const char *ret = trace_seq_buffer_ptr(p), *cmd;
-	sector_t lba = 0, txlen = 0;
-	u32 ei_lbrt = 0;
+	u64 lba;
+	u32 ei_lbrt, txlen;
 
 	switch (SERVICE_ACTION32(cdb)) {
 	case READ_32:
@@ -136,26 +117,12 @@ scsi_trace_rw32(struct trace_seq *p, unsigned char *cdb, int len)
 		goto out;
 	}
 
-	lba |= ((u64)cdb[12] << 56);
-	lba |= ((u64)cdb[13] << 48);
-	lba |= ((u64)cdb[14] << 40);
-	lba |= ((u64)cdb[15] << 32);
-	lba |= (cdb[16] << 24);
-	lba |= (cdb[17] << 16);
-	lba |= (cdb[18] << 8);
-	lba |=  cdb[19];
-	ei_lbrt |= (cdb[20] << 24);
-	ei_lbrt |= (cdb[21] << 16);
-	ei_lbrt |= (cdb[22] << 8);
-	ei_lbrt |=  cdb[23];
-	txlen |= (cdb[28] << 24);
-	txlen |= (cdb[29] << 16);
-	txlen |= (cdb[30] << 8);
-	txlen |=  cdb[31];
-
-	trace_seq_printf(p, "%s_32 lba=%llu txlen=%llu protect=%u ei_lbrt=%u",
-			 cmd, (unsigned long long)lba,
-			 (unsigned long long)txlen, cdb[10] >> 5, ei_lbrt);
+	lba = get_unaligned_be64(&cdb[12]);
+	ei_lbrt = get_unaligned_be32(&cdb[20]);
+	txlen = get_unaligned_be32(&cdb[28]);
+
+	trace_seq_printf(p, "%s_32 lba=%llu txlen=%u protect=%u ei_lbrt=%u",
+			 cmd, lba, txlen, cdb[10] >> 5, ei_lbrt);
 
 	if (SERVICE_ACTION32(cdb) == WRITE_SAME_32)
 		trace_seq_printf(p, " unmap=%u", cdb[10] >> 3 & 1);
@@ -170,7 +137,7 @@ static const char *
 scsi_trace_unmap(struct trace_seq *p, unsigned char *cdb, int len)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
-	unsigned int regions = cdb[7] << 8 | cdb[8];
+	unsigned int regions = get_unaligned_be16(&cdb[7]);
 
 	trace_seq_printf(p, "regions=%u", (regions - 8) / 16);
 	trace_seq_putc(p, 0);
@@ -182,8 +149,8 @@ static const char *
 scsi_trace_service_action_in(struct trace_seq *p, unsigned char *cdb, int len)
 {
 	const char *ret = trace_seq_buffer_ptr(p), *cmd;
-	sector_t lba = 0;
-	u32 alloc_len = 0;
+	u64 lba;
+	u32 alloc_len;
 
 	switch (SERVICE_ACTION16(cdb)) {
 	case SAI_READ_CAPACITY_16:
@@ -197,21 +164,10 @@ scsi_trace_service_action_in(struct trace_seq *p, unsigned char *cdb, int len)
 		goto out;
 	}
 
-	lba |= ((u64)cdb[2] << 56);
-	lba |= ((u64)cdb[3] << 48);
-	lba |= ((u64)cdb[4] << 40);
-	lba |= ((u64)cdb[5] << 32);
-	lba |= (cdb[6] << 24);
-	lba |= (cdb[7] << 16);
-	lba |= (cdb[8] << 8);
-	lba |=  cdb[9];
-	alloc_len |= (cdb[10] << 24);
-	alloc_len |= (cdb[11] << 16);
-	alloc_len |= (cdb[12] << 8);
-	alloc_len |=  cdb[13];
-
-	trace_seq_printf(p, "%s lba=%llu alloc_len=%u", cmd,
-			 (unsigned long long)lba, alloc_len);
+	lba = get_unaligned_be64(&cdb[2]);
+	alloc_len = get_unaligned_be32(&cdb[10]);
+
+	trace_seq_printf(p, "%s lba=%llu alloc_len=%u", cmd, lba, alloc_len);
 
 out:
 	trace_seq_putc(p, 0);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 13925021473d..7dc17821f873 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3390,6 +3390,10 @@ static int sd_probe(struct device *dev)
 	}
 
 	blk_pm_runtime_init(sdp->request_queue, dev);
+	if (sdp->rpm_autosuspend) {
+		pm_runtime_set_autosuspend_delay(dev,
+			sdp->host->hostt->rpm_autosuspend_delay);
+	}
 	device_add_disk(dev, gd, NULL);
 	if (sdkp->capacity)
 		sd_dif_config_host(sdkp);
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 9e4ef22b3579..160748ad9c0f 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -429,18 +429,26 @@ sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos)
 	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
 				      "sg_read: count=%d\n", (int) count));
 
-	if (!access_ok(buf, count))
-		return -EFAULT;
 	if (sfp->force_packid && (count >= SZ_SG_HEADER)) {
-		old_hdr = kmalloc(SZ_SG_HEADER, GFP_KERNEL);
-		if (!old_hdr)
-			return -ENOMEM;
-		if (__copy_from_user(old_hdr, buf, SZ_SG_HEADER)) {
-			retval = -EFAULT;
-			goto free_old_hdr;
-		}
+		old_hdr = memdup_user(buf, SZ_SG_HEADER);
+		if (IS_ERR(old_hdr))
+			return PTR_ERR(old_hdr);
 		if (old_hdr->reply_len < 0) {
 			if (count >= SZ_SG_IO_HDR) {
+				/*
+				 * This is stupid.
+				 *
+				 * We're copying the whole sg_io_hdr_t from user
+				 * space just to get the 'pack_id' field. But the
+				 * field is at different offsets for the compat
+				 * case, so we'll use "get_sg_io_hdr()" to copy
+				 * the whole thing and convert it.
+				 *
+				 * We could do something like just calculating the
+				 * offset based of 'in_compat_syscall()', but the
+				 * 'compat_sg_io_hdr' definition is in the wrong
+				 * place for that.
+				 */
 				sg_io_hdr_t *new_hdr;
 				new_hdr = kmalloc(SZ_SG_IO_HDR, GFP_KERNEL);
 				if (!new_hdr) {
@@ -537,7 +545,7 @@ sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos)
 
 	/* Now copy the result back to the user buffer.  */
 	if (count >= SZ_SG_HEADER) {
-		if (__copy_to_user(buf, old_hdr, SZ_SG_HEADER)) {
+		if (copy_to_user(buf, old_hdr, SZ_SG_HEADER)) {
 			retval = -EFAULT;
 			goto free_old_hdr;
 		}
@@ -623,11 +631,9 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	      scsi_block_when_processing_errors(sdp->device)))
 		return -ENXIO;
 
-	if (!access_ok(buf, count))
-		return -EFAULT;	/* protects following copy_from_user()s + get_user()s */
 	if (count < SZ_SG_HEADER)
 		return -EIO;
-	if (__copy_from_user(&old_hdr, buf, SZ_SG_HEADER))
+	if (copy_from_user(&old_hdr, buf, SZ_SG_HEADER))
 		return -EFAULT;
 	blocking = !(filp->f_flags & O_NONBLOCK);
 	if (old_hdr.reply_len < 0)
@@ -636,13 +642,15 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	if (count < (SZ_SG_HEADER + 6))
 		return -EIO;	/* The minimum scsi command length is 6 bytes. */
 
+	buf += SZ_SG_HEADER;
+	if (get_user(opcode, buf))
+		return -EFAULT;
+
 	if (!(srp = sg_add_request(sfp))) {
 		SCSI_LOG_TIMEOUT(1, sg_printk(KERN_INFO, sdp,
 					      "sg_write: queue full\n"));
 		return -EDOM;
 	}
-	buf += SZ_SG_HEADER;
-	__get_user(opcode, buf);
 	mutex_lock(&sfp->f_mutex);
 	if (sfp->next_cmd_len > 0) {
 		cmd_size = sfp->next_cmd_len;
@@ -685,7 +693,7 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	hp->flags = input_size;	/* structure abuse ... */
 	hp->pack_id = old_hdr.pack_id;
 	hp->usr_ptr = NULL;
-	if (__copy_from_user(cmnd, buf, cmd_size))
+	if (copy_from_user(cmnd, buf, cmd_size))
 		return -EFAULT;
 	/*
 	 * SG_DXFER_TO_FROM_DEV is functionally equivalent to SG_DXFER_FROM_DEV,
@@ -720,8 +728,6 @@ sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf,
 
 	if (count < SZ_SG_IO_HDR)
 		return -EINVAL;
-	if (!access_ok(buf, count))
-		return -EFAULT; /* protects following copy_from_user()s + get_user()s */
 
 	sfp->cmd_q = 1;	/* when sg_io_hdr seen, set command queuing on */
 	if (!(srp = sg_add_request(sfp))) {
@@ -759,11 +765,7 @@ sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf,
 		sg_remove_request(sfp, srp);
 		return -EMSGSIZE;
 	}
-	if (!access_ok(hp->cmdp, hp->cmd_len)) {
-		sg_remove_request(sfp, srp);
-		return -EFAULT;	/* protects following copy_from_user()s + get_user()s */
-	}
-	if (__copy_from_user(cmnd, hp->cmdp, hp->cmd_len)) {
+	if (copy_from_user(cmnd, hp->cmdp, hp->cmd_len)) {
 		sg_remove_request(sfp, srp);
 		return -EFAULT;
 	}
@@ -940,8 +942,6 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 			return -ENODEV;
 		if (!scsi_block_when_processing_errors(sdp->device))
 			return -ENXIO;
-		if (!access_ok(p, SZ_SG_IO_HDR))
-			return -EFAULT;
 		result = sg_new_write(sfp, filp, p, SZ_SG_IO_HDR,
 				 1, read_only, 1, &srp);
 		if (result < 0)
@@ -986,26 +986,21 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 	case SG_GET_LOW_DMA:
 		return put_user((int) sdp->device->host->unchecked_isa_dma, ip);
 	case SG_GET_SCSI_ID:
-		if (!access_ok(p, sizeof (sg_scsi_id_t)))
-			return -EFAULT;
-		else {
-			sg_scsi_id_t __user *sg_idp = p;
+		{
+			sg_scsi_id_t v;
 
 			if (atomic_read(&sdp->detaching))
 				return -ENODEV;
-			__put_user((int) sdp->device->host->host_no,
-				   &sg_idp->host_no);
-			__put_user((int) sdp->device->channel,
-				   &sg_idp->channel);
-			__put_user((int) sdp->device->id, &sg_idp->scsi_id);
-			__put_user((int) sdp->device->lun, &sg_idp->lun);
-			__put_user((int) sdp->device->type, &sg_idp->scsi_type);
-			__put_user((short) sdp->device->host->cmd_per_lun,
-				   &sg_idp->h_cmd_per_lun);
-			__put_user((short) sdp->device->queue_depth,
-				   &sg_idp->d_queue_depth);
-			__put_user(0, &sg_idp->unused[0]);
-			__put_user(0, &sg_idp->unused[1]);
+			memset(&v, 0, sizeof(v));
+			v.host_no = sdp->device->host->host_no;
+			v.channel = sdp->device->channel;
+			v.scsi_id = sdp->device->id;
+			v.lun = sdp->device->lun;
+			v.scsi_type = sdp->device->type;
+			v.h_cmd_per_lun = sdp->device->host->cmd_per_lun;
+			v.d_queue_depth = sdp->device->queue_depth;
+			if (copy_to_user(p, &v, sizeof(sg_scsi_id_t)))
+				return -EFAULT;
 			return 0;
 		}
 	case SG_SET_FORCE_PACK_ID:
@@ -1015,20 +1010,16 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 		sfp->force_packid = val ? 1 : 0;
 		return 0;
 	case SG_GET_PACK_ID:
-		if (!access_ok(ip, sizeof (int)))
-			return -EFAULT;
 		read_lock_irqsave(&sfp->rq_list_lock, iflags);
 		list_for_each_entry(srp, &sfp->rq_list, entry) {
 			if ((1 == srp->done) && (!srp->sg_io_owned)) {
 				read_unlock_irqrestore(&sfp->rq_list_lock,
 						       iflags);
-				__put_user(srp->header.pack_id, ip);
-				return 0;
+				return put_user(srp->header.pack_id, ip);
 			}
 		}
 		read_unlock_irqrestore(&sfp->rq_list_lock, iflags);
-		__put_user(-1, ip);
-		return 0;
+		return put_user(-1, ip);
 	case SG_GET_NUM_WAITING:
 		read_lock_irqsave(&sfp->rq_list_lock, iflags);
 		val = 0;
@@ -2017,12 +2008,12 @@ sg_read_oxfer(Sg_request * srp, char __user *outp, int num_read_xfer)
 	num = 1 << (PAGE_SHIFT + schp->page_order);
 	for (k = 0; k < schp->k_use_sg && schp->pages[k]; k++) {
 		if (num > num_read_xfer) {
-			if (__copy_to_user(outp, page_address(schp->pages[k]),
+			if (copy_to_user(outp, page_address(schp->pages[k]),
 					   num_read_xfer))
 				return -EFAULT;
 			break;
 		} else {
-			if (__copy_to_user(outp, page_address(schp->pages[k]),
+			if (copy_to_user(outp, page_address(schp->pages[k]),
 					   num))
 				return -EFAULT;
 			num_read_xfer -= num;
diff --git a/drivers/scsi/smartpqi/smartpqi.h b/drivers/scsi/smartpqi/smartpqi.h
index 79d2af36f655..1129fe7a27ed 100644
--- a/drivers/scsi/smartpqi/smartpqi.h
+++ b/drivers/scsi/smartpqi/smartpqi.h
@@ -276,7 +276,9 @@ struct pqi_raid_path_request {
 	u8	reserved4 : 2;
 	u8	additional_cdb_bytes_usage : 3;
 	u8	reserved5 : 3;
-	u8	cdb[32];
+	u8	cdb[16];
+	u8	reserved6[12];
+	__le32	timeout;
 	struct pqi_sg_descriptor
 		sg_descriptors[PQI_MAX_EMBEDDED_SG_DESCRIPTORS];
 };
@@ -385,7 +387,8 @@ struct pqi_task_management_request {
 	struct pqi_iu_header header;
 	__le16	request_id;
 	__le16	nexus_id;
-	u8	reserved[4];
+	u8	reserved[2];
+	__le16  timeout;
 	u8	lun_number[8];
 	__le16	protocol_specific;
 	__le16	outbound_queue_id_to_manage;
@@ -445,7 +448,7 @@ struct pqi_vendor_general_response {
 
 struct pqi_ofa_memory {
 	__le64	signature;	/* "OFA_QRM" */
-	__le16	version;	/* version of this struct(1 = 1st version) */
+	__le16	version;	/* version of this struct (1 = 1st version) */
 	u8	reserved[62];
 	__le32	bytes_allocated;	/* total allocated memory in bytes */
 	__le16	num_memory_descriptors;
@@ -761,6 +764,8 @@ struct pqi_config_table_firmware_features {
 #define PQI_FIRMWARE_FEATURE_OFA			0
 #define PQI_FIRMWARE_FEATURE_SMP			1
 #define PQI_FIRMWARE_FEATURE_SOFT_RESET_HANDSHAKE	11
+#define PQI_FIRMWARE_FEATURE_RAID_IU_TIMEOUT		13
+#define PQI_FIRMWARE_FEATURE_TMF_IU_TIMEOUT		14
 
 struct pqi_config_table_debug {
 	struct pqi_config_table_section_header header;
@@ -826,10 +831,17 @@ union pqi_reset_register {
 
 struct report_lun_header {
 	__be32	list_length;
-	u8	extended_response;
+	u8	flags;
 	u8	reserved[3];
 };
 
+/* for flags field of struct report_lun_header */
+#define CISS_REPORT_LOG_FLAG_UNIQUE_LUN_ID	(1 << 0)
+#define CISS_REPORT_LOG_FLAG_QUEUE_DEPTH	(1 << 5)
+#define CISS_REPORT_LOG_FLAG_DRIVE_TYPE_MIX	(1 << 6)
+
+#define CISS_REPORT_PHYS_FLAG_OTHER		(1 << 1)
+
 struct report_log_lun_extended_entry {
 	u8	lunid[8];
 	u8	volume_id[16];
@@ -851,7 +863,7 @@ struct report_phys_lun_extended_entry {
 };
 
 /* for device_flags field of struct report_phys_lun_extended_entry */
-#define REPORT_PHYS_LUN_DEV_FLAG_AIO_ENABLED	0x8
+#define CISS_REPORT_PHYS_DEV_FLAG_AIO_ENABLED	0x8
 
 struct report_phys_lun_extended {
 	struct report_lun_header header;
@@ -864,7 +876,7 @@ struct raid_map_disk_data {
 	u8	reserved[2];
 };
 
-/* constants for flags field of RAID map */
+/* for flags field of RAID map */
 #define RAID_MAP_ENCRYPTION_ENABLED	0x1
 
 struct raid_map {
@@ -907,7 +919,6 @@ struct pqi_scsi_dev {
 	u8	scsi3addr[8];
 	__be64	wwid;
 	u8	volume_id[16];
-	u8	unique_id[16];
 	u8	is_physical_device : 1;
 	u8	is_external_raid_device : 1;
 	u8	is_expander_smp_device : 1;
@@ -954,13 +965,9 @@ struct pqi_scsi_dev {
 };
 
 /* VPD inquiry pages */
-#define SCSI_VPD_SUPPORTED_PAGES	0x0	/* standard page */
-#define SCSI_VPD_DEVICE_ID		0x83	/* standard page */
 #define CISS_VPD_LV_DEVICE_GEOMETRY	0xc1	/* vendor-specific page */
 #define CISS_VPD_LV_BYPASS_STATUS	0xc2	/* vendor-specific page */
 #define CISS_VPD_LV_STATUS		0xc3	/* vendor-specific page */
-#define SCSI_VPD_HEADER_SZ		4
-#define SCSI_VPD_DEVICE_ID_IDX		8	/* Index of page id in page */
 
 #define VPD_PAGE	(1 << 8)
 
@@ -1130,13 +1137,16 @@ struct pqi_ctrl_info {
 	struct mutex	ofa_mutex; /* serialize ofa */
 	bool		controller_online;
 	bool		block_requests;
-	bool		in_shutdown;
+	bool		block_device_reset;
 	bool		in_ofa;
+	bool		in_shutdown;
 	u8		inbound_spanning_supported : 1;
 	u8		outbound_spanning_supported : 1;
 	u8		pqi_mode_enabled : 1;
 	u8		pqi_reset_quiesce_supported : 1;
 	u8		soft_reset_handshake_supported : 1;
+	u8		raid_iu_timeout_supported: 1;
+	u8		tmf_iu_timeout_supported: 1;
 
 	struct list_head scsi_device_list;
 	spinlock_t	scsi_device_list_lock;
@@ -1170,9 +1180,10 @@ struct pqi_ctrl_info {
 	spinlock_t	raid_bypass_retry_list_lock;
 	struct work_struct raid_bypass_retry_work;
 
-	struct          pqi_ofa_memory *pqi_ofa_mem_virt_addr;
-	dma_addr_t      pqi_ofa_mem_dma_handle;
-	void            **pqi_ofa_chunk_virt_addr;
+	struct pqi_ofa_memory *pqi_ofa_mem_virt_addr;
+	dma_addr_t	pqi_ofa_mem_dma_handle;
+	void		**pqi_ofa_chunk_virt_addr;
+	atomic_t	sync_cmds_outstanding;
 };
 
 enum pqi_ctrl_mode {
@@ -1191,10 +1202,6 @@ enum pqi_ctrl_mode {
 #define CISS_REPORT_PHYS	0xc3	/* Report Physical LUNs */
 #define CISS_GET_RAID_MAP	0xc8
 
-/* constants for CISS_REPORT_LOG/CISS_REPORT_PHYS commands */
-#define CISS_REPORT_LOG_EXTENDED		0x1
-#define CISS_REPORT_PHYS_EXTENDED		0x2
-
 /* BMIC commands */
 #define BMIC_IDENTIFY_CONTROLLER		0x11
 #define BMIC_IDENTIFY_PHYSICAL_DEVICE		0x15
@@ -1208,7 +1215,7 @@ enum pqi_ctrl_mode {
 #define BMIC_SET_DIAG_OPTIONS			0xf4
 #define BMIC_SENSE_DIAG_OPTIONS			0xf5
 
-#define CSMI_CC_SAS_SMP_PASSTHRU		0X17
+#define CSMI_CC_SAS_SMP_PASSTHRU		0x17
 
 #define SA_FLUSH_CACHE				0x1
 
@@ -1244,10 +1251,12 @@ struct bmic_sense_subsystem_info {
 	u8	ctrl_serial_number[16];
 };
 
-#define SA_EXPANDER_SMP_DEVICE		0x05
-#define SA_CONTROLLER_DEVICE		0x07
-/*SCSI Invalid Device Type for SAS devices*/
-#define PQI_SAS_SCSI_INVALID_DEVTYPE	0xff
+/* constants for device_type field */
+#define SA_DEVICE_TYPE_SATA		0x1
+#define SA_DEVICE_TYPE_SAS		0x2
+#define SA_DEVICE_TYPE_EXPANDER_SMP	0x5
+#define SA_DEVICE_TYPE_CONTROLLER	0x7
+#define SA_DEVICE_TYPE_NVME		0x9
 
 struct bmic_identify_physical_device {
 	u8	scsi_bus;		/* SCSI Bus number on controller */
@@ -1273,7 +1282,7 @@ struct bmic_identify_physical_device {
 	__le32	rpm;			/* drive rotational speed in RPM */
 	u8	device_type;		/* type of drive */
 	u8	sata_version;		/* only valid when device_type = */
-					/* BMIC_DEVICE_TYPE_SATA */
+					/* SA_DEVICE_TYPE_SATA */
 	__le64	big_total_block_count;
 	__le64	ris_starting_lba;
 	__le32	ris_size;
@@ -1396,18 +1405,6 @@ struct bmic_diag_options {
 
 #pragma pack()
 
-static inline struct pqi_ctrl_info *shost_to_hba(struct Scsi_Host *shost)
-{
-	void *hostdata = shost_priv(shost);
-
-	return *((struct pqi_ctrl_info **)hostdata);
-}
-
-static inline bool pqi_ctrl_offline(struct pqi_ctrl_info *ctrl_info)
-{
-	return !ctrl_info->controller_online;
-}
-
 static inline void pqi_ctrl_busy(struct pqi_ctrl_info *ctrl_info)
 {
 	atomic_inc(&ctrl_info->num_busy_threads);
@@ -1418,9 +1415,11 @@ static inline void pqi_ctrl_unbusy(struct pqi_ctrl_info *ctrl_info)
 	atomic_dec(&ctrl_info->num_busy_threads);
 }
 
-static inline bool pqi_ctrl_blocked(struct pqi_ctrl_info *ctrl_info)
+static inline struct pqi_ctrl_info *shost_to_hba(struct Scsi_Host *shost)
 {
-	return ctrl_info->block_requests;
+	void *hostdata = shost_priv(shost);
+
+	return *((struct pqi_ctrl_info **)hostdata);
 }
 
 void pqi_sas_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index ea5409bebf57..7b7ef3acb504 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -33,11 +33,11 @@
 #define BUILD_TIMESTAMP
 #endif
 
-#define DRIVER_VERSION		"1.2.8-026"
+#define DRIVER_VERSION		"1.2.10-025"
 #define DRIVER_MAJOR		1
 #define DRIVER_MINOR		2
-#define DRIVER_RELEASE		8
-#define DRIVER_REVISION		26
+#define DRIVER_RELEASE		10
+#define DRIVER_REVISION		25
 
 #define DRIVER_NAME		"Microsemi PQI Driver (v" \
 				DRIVER_VERSION BUILD_TIMESTAMP ")"
@@ -211,6 +211,11 @@ static inline bool pqi_is_external_raid_addr(u8 *scsi3addr)
 	return scsi3addr[2] != 0;
 }
 
+static inline bool pqi_ctrl_offline(struct pqi_ctrl_info *ctrl_info)
+{
+	return !ctrl_info->controller_online;
+}
+
 static inline void pqi_check_ctrl_health(struct pqi_ctrl_info *ctrl_info)
 {
 	if (ctrl_info->controller_online)
@@ -235,6 +240,21 @@ static inline void pqi_save_ctrl_mode(struct pqi_ctrl_info *ctrl_info,
 	sis_write_driver_scratch(ctrl_info, mode);
 }
 
+static inline void pqi_ctrl_block_device_reset(struct pqi_ctrl_info *ctrl_info)
+{
+	ctrl_info->block_device_reset = true;
+}
+
+static inline bool pqi_device_reset_blocked(struct pqi_ctrl_info *ctrl_info)
+{
+	return ctrl_info->block_device_reset;
+}
+
+static inline bool pqi_ctrl_blocked(struct pqi_ctrl_info *ctrl_info)
+{
+	return ctrl_info->block_requests;
+}
+
 static inline void pqi_ctrl_block_requests(struct pqi_ctrl_info *ctrl_info)
 {
 	ctrl_info->block_requests = true;
@@ -331,6 +351,16 @@ static inline bool pqi_device_in_remove(struct pqi_ctrl_info *ctrl_info,
 	return device->in_remove && !ctrl_info->in_shutdown;
 }
 
+static inline void pqi_ctrl_shutdown_start(struct pqi_ctrl_info *ctrl_info)
+{
+	ctrl_info->in_shutdown = true;
+}
+
+static inline bool pqi_ctrl_in_shutdown(struct pqi_ctrl_info *ctrl_info)
+{
+	return ctrl_info->in_shutdown;
+}
+
 static inline void pqi_schedule_rescan_worker_with_delay(
 	struct pqi_ctrl_info *ctrl_info, unsigned long delay)
 {
@@ -360,6 +390,11 @@ static inline void pqi_cancel_rescan_worker(struct pqi_ctrl_info *ctrl_info)
 	cancel_delayed_work_sync(&ctrl_info->rescan_work);
 }
 
+static inline void pqi_cancel_event_worker(struct pqi_ctrl_info *ctrl_info)
+{
+	cancel_work_sync(&ctrl_info->event_work);
+}
+
 static inline u32 pqi_read_heartbeat_counter(struct pqi_ctrl_info *ctrl_info)
 {
 	if (!ctrl_info->heartbeat_counter)
@@ -377,7 +412,7 @@ static inline u8 pqi_read_soft_reset_status(struct pqi_ctrl_info *ctrl_info)
 }
 
 static inline void pqi_clear_soft_reset_status(struct pqi_ctrl_info *ctrl_info,
-						u8 clear)
+	u8 clear)
 {
 	u8 status;
 
@@ -462,9 +497,9 @@ static int pqi_build_raid_path_request(struct pqi_ctrl_info *ctrl_info,
 		request->data_direction = SOP_READ_FLAG;
 		cdb[0] = cmd;
 		if (cmd == CISS_REPORT_PHYS)
-			cdb[1] = CISS_REPORT_PHYS_EXTENDED;
+			cdb[1] = CISS_REPORT_PHYS_FLAG_OTHER;
 		else
-			cdb[1] = CISS_REPORT_LOG_EXTENDED;
+			cdb[1] = CISS_REPORT_LOG_FLAG_UNIQUE_LUN_ID;
 		put_unaligned_be32(cdb_length, &cdb[6]);
 		break;
 	case CISS_GET_RAID_MAP:
@@ -567,13 +602,12 @@ static void pqi_free_io_request(struct pqi_io_request *io_request)
 }
 
 static int pqi_send_scsi_raid_request(struct pqi_ctrl_info *ctrl_info, u8 cmd,
-		u8 *scsi3addr, void *buffer, size_t buffer_length, u16 vpd_page,
-		struct pqi_raid_error_info *error_info,
-		unsigned long timeout_msecs)
+	u8 *scsi3addr, void *buffer, size_t buffer_length, u16 vpd_page,
+	struct pqi_raid_error_info *error_info,	unsigned long timeout_msecs)
 {
 	int rc;
-	enum dma_data_direction dir;
 	struct pqi_raid_path_request request;
+	enum dma_data_direction dir;
 
 	rc = pqi_build_raid_path_request(ctrl_info, &request,
 		cmd, scsi3addr, buffer,
@@ -581,44 +615,44 @@ static int pqi_send_scsi_raid_request(struct pqi_ctrl_info *ctrl_info, u8 cmd,
 	if (rc)
 		return rc;
 
-	rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header,
-		 0, error_info, timeout_msecs);
+	rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header, 0,
+		error_info, timeout_msecs);
 
 	pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1, dir);
+
 	return rc;
 }
 
-/* Helper functions for pqi_send_scsi_raid_request */
+/* helper functions for pqi_send_scsi_raid_request */
 
 static inline int pqi_send_ctrl_raid_request(struct pqi_ctrl_info *ctrl_info,
-		u8 cmd, void *buffer, size_t buffer_length)
+	u8 cmd, void *buffer, size_t buffer_length)
 {
 	return pqi_send_scsi_raid_request(ctrl_info, cmd, RAID_CTLR_LUNID,
-			buffer, buffer_length, 0, NULL, NO_TIMEOUT);
+		buffer, buffer_length, 0, NULL, NO_TIMEOUT);
 }
 
 static inline int pqi_send_ctrl_raid_with_error(struct pqi_ctrl_info *ctrl_info,
-		u8 cmd, void *buffer, size_t buffer_length,
-		struct pqi_raid_error_info *error_info)
+	u8 cmd, void *buffer, size_t buffer_length,
+	struct pqi_raid_error_info *error_info)
 {
 	return pqi_send_scsi_raid_request(ctrl_info, cmd, RAID_CTLR_LUNID,
-			buffer, buffer_length, 0, error_info, NO_TIMEOUT);
+		buffer, buffer_length, 0, error_info, NO_TIMEOUT);
 }
 
-
 static inline int pqi_identify_controller(struct pqi_ctrl_info *ctrl_info,
-		struct bmic_identify_controller *buffer)
+	struct bmic_identify_controller *buffer)
 {
 	return pqi_send_ctrl_raid_request(ctrl_info, BMIC_IDENTIFY_CONTROLLER,
-			buffer, sizeof(*buffer));
+		buffer, sizeof(*buffer));
 }
 
 static inline int pqi_sense_subsystem_info(struct  pqi_ctrl_info *ctrl_info,
-		struct bmic_sense_subsystem_info *sense_info)
+	struct bmic_sense_subsystem_info *sense_info)
 {
 	return pqi_send_ctrl_raid_request(ctrl_info,
-			BMIC_SENSE_SUBSYSTEM_INFORMATION,
-			sense_info, sizeof(*sense_info));
+		BMIC_SENSE_SUBSYSTEM_INFORMATION, sense_info,
+		sizeof(*sense_info));
 }
 
 static inline int pqi_scsi_inquiry(struct pqi_ctrl_info *ctrl_info,
@@ -628,83 +662,9 @@ static inline int pqi_scsi_inquiry(struct pqi_ctrl_info *ctrl_info,
 		buffer, buffer_length, vpd_page, NULL, NO_TIMEOUT);
 }
 
-static bool pqi_vpd_page_supported(struct pqi_ctrl_info *ctrl_info,
-	u8 *scsi3addr, u16 vpd_page)
-{
-	int rc;
-	int i;
-	int pages;
-	unsigned char *buf, bufsize;
-
-	buf = kzalloc(256, GFP_KERNEL);
-	if (!buf)
-		return false;
-
-	/* Get the size of the page list first */
-	rc = pqi_scsi_inquiry(ctrl_info, scsi3addr,
-				VPD_PAGE | SCSI_VPD_SUPPORTED_PAGES,
-				buf, SCSI_VPD_HEADER_SZ);
-	if (rc != 0)
-		goto exit_unsupported;
-
-	pages = buf[3];
-	if ((pages + SCSI_VPD_HEADER_SZ) <= 255)
-		bufsize = pages + SCSI_VPD_HEADER_SZ;
-	else
-		bufsize = 255;
-
-	/* Get the whole VPD page list */
-	rc = pqi_scsi_inquiry(ctrl_info, scsi3addr,
-				VPD_PAGE | SCSI_VPD_SUPPORTED_PAGES,
-				buf, bufsize);
-	if (rc != 0)
-		goto exit_unsupported;
-
-	pages = buf[3];
-	for (i = 1; i <= pages; i++)
-		if (buf[3 + i] == vpd_page)
-			goto exit_supported;
-
-exit_unsupported:
-	kfree(buf);
-	return false;
-
-exit_supported:
-	kfree(buf);
-	return true;
-}
-
-static int pqi_get_device_id(struct pqi_ctrl_info *ctrl_info,
-	u8 *scsi3addr, u8 *device_id, int buflen)
-{
-	int rc;
-	unsigned char *buf;
-
-	if (!pqi_vpd_page_supported(ctrl_info, scsi3addr, SCSI_VPD_DEVICE_ID))
-		return 1; /* function not supported */
-
-	buf = kzalloc(64, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	rc = pqi_scsi_inquiry(ctrl_info, scsi3addr,
-				VPD_PAGE | SCSI_VPD_DEVICE_ID,
-				buf, 64);
-	if (rc == 0) {
-		if (buflen > 16)
-			buflen = 16;
-		memcpy(device_id, &buf[SCSI_VPD_DEVICE_ID_IDX], buflen);
-	}
-
-	kfree(buf);
-
-	return rc;
-}
-
 static int pqi_identify_physical_device(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_scsi_dev *device,
-	struct bmic_identify_physical_device *buffer,
-	size_t buffer_length)
+	struct bmic_identify_physical_device *buffer, size_t buffer_length)
 {
 	int rc;
 	enum dma_data_direction dir;
@@ -725,6 +685,7 @@ static int pqi_identify_physical_device(struct pqi_ctrl_info *ctrl_info,
 		0, NULL, NO_TIMEOUT);
 
 	pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1, dir);
+
 	return rc;
 }
 
@@ -763,7 +724,7 @@ int pqi_csmi_smp_passthru(struct pqi_ctrl_info *ctrl_info,
 		buffer, buffer_length, error_info);
 }
 
-#define PQI_FETCH_PTRAID_DATA (1UL<<31)
+#define PQI_FETCH_PTRAID_DATA		(1 << 31)
 
 static int pqi_set_diag_rescan(struct pqi_ctrl_info *ctrl_info)
 {
@@ -775,14 +736,15 @@ static int pqi_set_diag_rescan(struct pqi_ctrl_info *ctrl_info)
 		return -ENOMEM;
 
 	rc = pqi_send_ctrl_raid_request(ctrl_info, BMIC_SENSE_DIAG_OPTIONS,
-					diag, sizeof(*diag));
+		diag, sizeof(*diag));
 	if (rc)
 		goto out;
 
 	diag->options |= cpu_to_le32(PQI_FETCH_PTRAID_DATA);
 
-	rc = pqi_send_ctrl_raid_request(ctrl_info, BMIC_SET_DIAG_OPTIONS,
-					diag, sizeof(*diag));
+	rc = pqi_send_ctrl_raid_request(ctrl_info, BMIC_SET_DIAG_OPTIONS, diag,
+		sizeof(*diag));
+
 out:
 	kfree(diag);
 
@@ -793,7 +755,7 @@ static inline int pqi_write_host_wellness(struct pqi_ctrl_info *ctrl_info,
 	void *buffer, size_t buffer_length)
 {
 	return pqi_send_ctrl_raid_request(ctrl_info, BMIC_WRITE_HOST_WELLNESS,
-					buffer, buffer_length);
+		buffer, buffer_length);
 }
 
 #pragma pack(1)
@@ -946,7 +908,7 @@ static inline int pqi_report_luns(struct pqi_ctrl_info *ctrl_info, u8 cmd,
 	void *buffer, size_t buffer_length)
 {
 	return pqi_send_ctrl_raid_request(ctrl_info, cmd, buffer,
-					buffer_length);
+		buffer_length);
 }
 
 static int pqi_report_phys_logical_luns(struct pqi_ctrl_info *ctrl_info, u8 cmd,
@@ -1280,9 +1242,9 @@ static void pqi_get_raid_bypass_status(struct pqi_ctrl_info *ctrl_info,
 	if (rc)
 		goto out;
 
-#define RAID_BYPASS_STATUS	4
-#define RAID_BYPASS_CONFIGURED	0x1
-#define RAID_BYPASS_ENABLED	0x2
+#define RAID_BYPASS_STATUS		4
+#define RAID_BYPASS_CONFIGURED		0x1
+#define RAID_BYPASS_ENABLED		0x2
 
 	bypass_status = buffer[RAID_BYPASS_STATUS];
 	device->raid_bypass_configured =
@@ -1385,14 +1347,6 @@ static int pqi_get_device_info(struct pqi_ctrl_info *ctrl_info,
 		}
 	}
 
-	if (pqi_get_device_id(ctrl_info, device->scsi3addr,
-		device->unique_id, sizeof(device->unique_id)) < 0)
-		dev_warn(&ctrl_info->pci_dev->dev,
-			"Can't get device id for scsi %d:%d:%d:%d\n",
-			ctrl_info->scsi_host->host_no,
-			device->bus, device->target,
-			device->lun);
-
 out:
 	kfree(buffer);
 
@@ -1413,6 +1367,7 @@ static void pqi_get_physical_disk_info(struct pqi_ctrl_info *ctrl_info,
 		device->queue_depth = PQI_PHYSICAL_DISK_DEFAULT_MAX_QUEUE_DEPTH;
 		return;
 	}
+
 	device->box_index = id_phys->box_index;
 	device->phys_box_on_bus = id_phys->phys_box_on_bus;
 	device->phy_connected_dev_type = id_phys->phy_connected_dev_type[0];
@@ -1828,7 +1783,7 @@ static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info,
 		device = new_device_list[i];
 
 		find_result = pqi_scsi_find_entry(ctrl_info, device,
-						&matching_device);
+			&matching_device);
 
 		switch (find_result) {
 		case DEVICE_SAME:
@@ -2057,9 +2012,8 @@ static int pqi_update_scsi_devices(struct pqi_ctrl_info *ctrl_info)
 			rc = -ENOMEM;
 			goto out;
 		}
-		if (pqi_hide_vsep) {
-			int i;
 
+		if (pqi_hide_vsep) {
 			for (i = num_physicals - 1; i >= 0; i--) {
 				phys_lun_ext_entry =
 						&physdev_list->lun_entries[i];
@@ -2132,7 +2086,7 @@ static int pqi_update_scsi_devices(struct pqi_ctrl_info *ctrl_info)
 		device->is_physical_device = is_physical_device;
 		if (is_physical_device) {
 			if (phys_lun_ext_entry->device_type ==
-				SA_EXPANDER_SMP_DEVICE)
+				SA_DEVICE_TYPE_EXPANDER_SMP)
 				device->is_expander_smp_device = true;
 		} else {
 			device->is_external_raid_device =
@@ -2169,16 +2123,13 @@ static int pqi_update_scsi_devices(struct pqi_ctrl_info *ctrl_info)
 		if (device->is_physical_device) {
 			device->wwid = phys_lun_ext_entry->wwid;
 			if ((phys_lun_ext_entry->device_flags &
-				REPORT_PHYS_LUN_DEV_FLAG_AIO_ENABLED) &&
+				CISS_REPORT_PHYS_DEV_FLAG_AIO_ENABLED) &&
 				phys_lun_ext_entry->aio_handle) {
 				device->aio_enabled = true;
-					device->aio_handle =
-						phys_lun_ext_entry->aio_handle;
+				device->aio_handle =
+					phys_lun_ext_entry->aio_handle;
 			}
-
-				pqi_get_physical_disk_info(ctrl_info,
-					device, id_phys);
-
+			pqi_get_physical_disk_info(ctrl_info, device, id_phys);
 		} else {
 			memcpy(device->volume_id, log_lun_ext_entry->volume_id,
 				sizeof(device->volume_id));
@@ -3158,7 +3109,7 @@ static enum pqi_soft_reset_status pqi_poll_for_soft_reset_status(
 }
 
 static void pqi_process_soft_reset(struct pqi_ctrl_info *ctrl_info,
-		enum pqi_soft_reset_status reset_status)
+	enum pqi_soft_reset_status reset_status)
 {
 	int rc;
 
@@ -3202,8 +3153,8 @@ static void pqi_ofa_process_event(struct pqi_ctrl_info *ctrl_info,
 
 	if (event_id == PQI_EVENT_OFA_QUIESCE) {
 		dev_info(&ctrl_info->pci_dev->dev,
-			 "Received Online Firmware Activation quiesce event for controller %u\n",
-			 ctrl_info->ctrl_id);
+			"Received Online Firmware Activation quiesce event for controller %u\n",
+			ctrl_info->ctrl_id);
 		pqi_ofa_ctrl_quiesce(ctrl_info);
 		pqi_acknowledge_event(ctrl_info, event);
 		if (ctrl_info->soft_reset_handshake_supported) {
@@ -3223,8 +3174,8 @@ static void pqi_ofa_process_event(struct pqi_ctrl_info *ctrl_info,
 		pqi_ofa_free_host_buffer(ctrl_info);
 		pqi_acknowledge_event(ctrl_info, event);
 		dev_info(&ctrl_info->pci_dev->dev,
-			 "Online Firmware Activation(%u) cancel reason : %u\n",
-			 ctrl_info->ctrl_id, event->ofa_cancel_reason);
+			"Online Firmware Activation(%u) cancel reason : %u\n",
+			ctrl_info->ctrl_id, event->ofa_cancel_reason);
 	}
 
 	mutex_unlock(&ctrl_info->ofa_mutex);
@@ -3403,7 +3354,7 @@ static unsigned int pqi_process_event_intr(struct pqi_ctrl_info *ctrl_info)
 #define PQI_LEGACY_INTX_MASK	0x1
 
 static inline void pqi_configure_legacy_intx(struct pqi_ctrl_info *ctrl_info,
-						bool enable_intx)
+	bool enable_intx)
 {
 	u32 intx_mask;
 	struct pqi_device_registers __iomem *pqi_registers;
@@ -3841,7 +3792,7 @@ static int pqi_create_admin_queues(struct pqi_ctrl_info *ctrl_info)
 		&pqi_registers->admin_oq_pi_addr);
 
 	reg = PQI_ADMIN_IQ_NUM_ELEMENTS |
-		(PQI_ADMIN_OQ_NUM_ELEMENTS) << 8 |
+		(PQI_ADMIN_OQ_NUM_ELEMENTS << 8) |
 		(admin_queues->int_msg_num << 16);
 	writel(reg, &pqi_registers->admin_iq_num_elements);
 	writel(PQI_CREATE_ADMIN_QUEUE_PAIR,
@@ -4048,8 +3999,8 @@ static void pqi_raid_synchronous_complete(struct pqi_io_request *io_request,
 	complete(waiting);
 }
 
-static int pqi_process_raid_io_error_synchronous(struct pqi_raid_error_info
-						*error_info)
+static int pqi_process_raid_io_error_synchronous(
+	struct pqi_raid_error_info *error_info)
 {
 	int rc = -EIO;
 
@@ -4122,6 +4073,8 @@ static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 		goto out;
 	}
 
+	atomic_inc(&ctrl_info->sync_cmds_outstanding);
+
 	io_request = pqi_alloc_io_request(ctrl_info);
 
 	put_unaligned_le16(io_request->index,
@@ -4168,6 +4121,7 @@ static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 
 	pqi_free_io_request(io_request);
 
+	atomic_dec(&ctrl_info->sync_cmds_outstanding);
 out:
 	up(&ctrl_info->sync_request_sem);
 
@@ -4665,11 +4619,11 @@ static void pqi_free_all_io_requests(struct pqi_ctrl_info *ctrl_info)
 
 static inline int pqi_alloc_error_buffer(struct pqi_ctrl_info *ctrl_info)
 {
-	ctrl_info->error_buffer = dma_alloc_coherent(&ctrl_info->pci_dev->dev,
-						     ctrl_info->error_buffer_length,
-						     &ctrl_info->error_buffer_dma_handle,
-						     GFP_KERNEL);
 
+	ctrl_info->error_buffer = dma_alloc_coherent(&ctrl_info->pci_dev->dev,
+				     ctrl_info->error_buffer_length,
+				     &ctrl_info->error_buffer_dma_handle,
+				     GFP_KERNEL);
 	if (!ctrl_info->error_buffer)
 		return -ENOMEM;
 
@@ -5402,7 +5356,7 @@ static int pqi_scsi_queue_command(struct Scsi_Host *shost,
 
 	pqi_ctrl_busy(ctrl_info);
 	if (pqi_ctrl_blocked(ctrl_info) || pqi_device_in_reset(device) ||
-	    pqi_ctrl_in_ofa(ctrl_info)) {
+	    pqi_ctrl_in_ofa(ctrl_info) || pqi_ctrl_in_shutdown(ctrl_info)) {
 		rc = SCSI_MLQUEUE_HOST_BUSY;
 		goto out;
 	}
@@ -5419,7 +5373,7 @@ static int pqi_scsi_queue_command(struct Scsi_Host *shost,
 	if (pqi_is_logical_device(device)) {
 		raid_bypassed = false;
 		if (device->raid_bypass_enabled &&
-				!blk_rq_is_passthrough(scmd->request)) {
+			!blk_rq_is_passthrough(scmd->request)) {
 			rc = pqi_raid_bypass_submit_scsi_cmd(ctrl_info, device,
 				scmd, queue_group);
 			if (rc == 0 || rc == SCSI_MLQUEUE_HOST_BUSY)
@@ -5650,6 +5604,18 @@ static int pqi_ctrl_wait_for_pending_io(struct pqi_ctrl_info *ctrl_info,
 	return 0;
 }
 
+static int pqi_ctrl_wait_for_pending_sync_cmds(struct pqi_ctrl_info *ctrl_info)
+{
+	while (atomic_read(&ctrl_info->sync_cmds_outstanding)) {
+		pqi_check_ctrl_health(ctrl_info);
+		if (pqi_ctrl_offline(ctrl_info))
+			return -ENXIO;
+		usleep_range(1000, 2000);
+	}
+
+	return 0;
+}
+
 static void pqi_lun_reset_complete(struct pqi_io_request *io_request,
 	void *context)
 {
@@ -5658,7 +5624,8 @@ static void pqi_lun_reset_complete(struct pqi_io_request *io_request,
 	complete(waiting);
 }
 
-#define PQI_LUN_RESET_TIMEOUT_SECS	10
+#define PQI_LUN_RESET_TIMEOUT_SECS		30
+#define PQI_LUN_RESET_POLL_COMPLETION_SECS	10
 
 static int pqi_wait_for_lun_reset_completion(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_scsi_dev *device, struct completion *wait)
@@ -5667,7 +5634,7 @@ static int pqi_wait_for_lun_reset_completion(struct pqi_ctrl_info *ctrl_info,
 
 	while (1) {
 		if (wait_for_completion_io_timeout(wait,
-			PQI_LUN_RESET_TIMEOUT_SECS * PQI_HZ)) {
+			PQI_LUN_RESET_POLL_COMPLETION_SECS * PQI_HZ)) {
 			rc = 0;
 			break;
 		}
@@ -5704,6 +5671,9 @@ static int pqi_lun_reset(struct pqi_ctrl_info *ctrl_info,
 	memcpy(request->lun_number, device->scsi3addr,
 		sizeof(request->lun_number));
 	request->task_management_function = SOP_TASK_MANAGEMENT_LUN_RESET;
+	if (ctrl_info->tmf_iu_timeout_supported)
+		put_unaligned_le16(PQI_LUN_RESET_TIMEOUT_SECS,
+					&request->timeout);
 
 	pqi_start_io(ctrl_info,
 		&ctrl_info->queue_groups[PQI_DEFAULT_QUEUE_GROUP], RAID_PATH,
@@ -5733,7 +5703,7 @@ static int _pqi_device_reset(struct pqi_ctrl_info *ctrl_info,
 
 	for (retries = 0;;) {
 		rc = pqi_lun_reset(ctrl_info, device);
-		if (rc != -EAGAIN || ++retries > PQI_LUN_RESET_RETRIES)
+		if (rc == 0 || ++retries > PQI_LUN_RESET_RETRIES)
 			break;
 		msleep(PQI_LUN_RESET_RETRY_INTERVAL_MSECS);
 	}
@@ -5787,17 +5757,17 @@ static int pqi_eh_device_reset_handler(struct scsi_cmnd *scmd)
 		shost->host_no, device->bus, device->target, device->lun);
 
 	pqi_check_ctrl_health(ctrl_info);
-	if (pqi_ctrl_offline(ctrl_info)) {
-		dev_err(&ctrl_info->pci_dev->dev,
-			"controller %u offlined - cannot send device reset\n",
-			ctrl_info->ctrl_id);
+	if (pqi_ctrl_offline(ctrl_info) ||
+		pqi_device_reset_blocked(ctrl_info)) {
 		rc = FAILED;
 		goto out;
 	}
 
 	pqi_wait_until_ofa_finished(ctrl_info);
 
+	atomic_inc(&ctrl_info->sync_cmds_outstanding);
 	rc = pqi_device_reset(ctrl_info, device);
+	atomic_dec(&ctrl_info->sync_cmds_outstanding);
 
 out:
 	dev_err(&ctrl_info->pci_dev->dev,
@@ -6066,6 +6036,9 @@ static int pqi_passthru_ioctl(struct pqi_ctrl_info *ctrl_info, void __user *arg)
 
 	put_unaligned_le16(iu_length, &request.header.iu_length);
 
+	if (ctrl_info->raid_iu_timeout_supported)
+		put_unaligned_le32(iocommand.Request.Timeout, &request.timeout);
+
 	rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header,
 		PQI_SYNC_FLAGS_INTERRUPTABLE, &pqi_error_info, NO_TIMEOUT);
 
@@ -6119,7 +6092,7 @@ static int pqi_ioctl(struct scsi_device *sdev, unsigned int cmd,
 
 	ctrl_info = shost_to_hba(sdev->host);
 
-	if (pqi_ctrl_in_ofa(ctrl_info))
+	if (pqi_ctrl_in_ofa(ctrl_info) || pqi_ctrl_in_shutdown(ctrl_info))
 		return -EBUSY;
 
 	switch (cmd) {
@@ -6160,14 +6133,8 @@ static ssize_t pqi_firmware_version_show(struct device *dev,
 static ssize_t pqi_driver_version_show(struct device *dev,
 	struct device_attribute *attr, char *buffer)
 {
-	struct Scsi_Host *shost;
-	struct pqi_ctrl_info *ctrl_info;
-
-	shost = class_to_shost(dev);
-	ctrl_info = shost_to_hba(shost);
-
-	return snprintf(buffer, PAGE_SIZE,
-		"%s\n", DRIVER_VERSION BUILD_TIMESTAMP);
+	return snprintf(buffer, PAGE_SIZE, "%s\n",
+			DRIVER_VERSION BUILD_TIMESTAMP);
 }
 
 static ssize_t pqi_serial_number_show(struct device *dev,
@@ -6283,7 +6250,7 @@ static ssize_t pqi_unique_id_show(struct device *dev,
 	struct scsi_device *sdev;
 	struct pqi_scsi_dev *device;
 	unsigned long flags;
-	unsigned char uid[16];
+	u8 unique_id[16];
 
 	sdev = to_scsi_device(dev);
 	ctrl_info = shost_to_hba(sdev->host);
@@ -6296,16 +6263,22 @@ static ssize_t pqi_unique_id_show(struct device *dev,
 			flags);
 		return -ENODEV;
 	}
-	memcpy(uid, device->unique_id, sizeof(uid));
+
+	if (device->is_physical_device) {
+		memset(unique_id, 0, 8);
+		memcpy(unique_id + 8, &device->wwid, sizeof(device->wwid));
+	} else {
+		memcpy(unique_id, device->volume_id, sizeof(device->volume_id));
+	}
 
 	spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
 
 	return snprintf(buffer, PAGE_SIZE,
 		"%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X\n",
-		uid[0], uid[1], uid[2], uid[3],
-		uid[4], uid[5], uid[6], uid[7],
-		uid[8], uid[9], uid[10], uid[11],
-		uid[12], uid[13], uid[14], uid[15]);
+		unique_id[0], unique_id[1], unique_id[2], unique_id[3],
+		unique_id[4], unique_id[5], unique_id[6], unique_id[7],
+		unique_id[8], unique_id[9], unique_id[10], unique_id[11],
+		unique_id[12], unique_id[13], unique_id[14], unique_id[15]);
 }
 
 static ssize_t pqi_lunid_show(struct device *dev,
@@ -6328,6 +6301,7 @@ static ssize_t pqi_lunid_show(struct device *dev,
 			flags);
 		return -ENODEV;
 	}
+
 	memcpy(lunid, device->scsi3addr, sizeof(lunid));
 
 	spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
@@ -6335,7 +6309,8 @@ static ssize_t pqi_lunid_show(struct device *dev,
 	return snprintf(buffer, PAGE_SIZE, "0x%8phN\n", lunid);
 }
 
-#define MAX_PATHS 8
+#define MAX_PATHS	8
+
 static ssize_t pqi_path_info_show(struct device *dev,
 	struct device_attribute *attr, char *buf)
 {
@@ -6347,9 +6322,9 @@ static ssize_t pqi_path_info_show(struct device *dev,
 	int output_len = 0;
 	u8 box;
 	u8 bay;
-	u8 path_map_index = 0;
+	u8 path_map_index;
 	char *active;
-	unsigned char phys_connector[2];
+	u8 phys_connector[2];
 
 	sdev = to_scsi_device(dev);
 	ctrl_info = shost_to_hba(sdev->host);
@@ -6365,7 +6340,7 @@ static ssize_t pqi_path_info_show(struct device *dev,
 
 	bay = device->bay;
 	for (i = 0; i < MAX_PATHS; i++) {
-		path_map_index = 1<<i;
+		path_map_index = 1 << i;
 		if (i == device->active_path_index)
 			active = "Active";
 		else if (device->path_map & path_map_index)
@@ -6416,10 +6391,10 @@ end_buffer:
 	}
 
 	spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
+
 	return output_len;
 }
 
-
 static ssize_t pqi_sas_address_show(struct device *dev,
 	struct device_attribute *attr, char *buffer)
 {
@@ -6440,6 +6415,7 @@ static ssize_t pqi_sas_address_show(struct device *dev,
 			flags);
 		return -ENODEV;
 	}
+
 	sas_address = device->sas_address;
 
 	spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
@@ -6844,6 +6820,27 @@ static void pqi_firmware_feature_status(struct pqi_ctrl_info *ctrl_info,
 		firmware_feature->feature_name);
 }
 
+static void pqi_ctrl_update_feature_flags(struct pqi_ctrl_info *ctrl_info,
+	struct pqi_firmware_feature *firmware_feature)
+{
+	switch (firmware_feature->feature_bit) {
+	case PQI_FIRMWARE_FEATURE_SOFT_RESET_HANDSHAKE:
+		ctrl_info->soft_reset_handshake_supported =
+			firmware_feature->enabled;
+		break;
+	case PQI_FIRMWARE_FEATURE_RAID_IU_TIMEOUT:
+		ctrl_info->raid_iu_timeout_supported =
+			firmware_feature->enabled;
+		break;
+	case PQI_FIRMWARE_FEATURE_TMF_IU_TIMEOUT:
+		ctrl_info->tmf_iu_timeout_supported =
+			firmware_feature->enabled;
+		break;
+	}
+
+	pqi_firmware_feature_status(ctrl_info, firmware_feature);
+}
+
 static inline void pqi_firmware_feature_update(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_firmware_feature *firmware_feature)
 {
@@ -6867,7 +6864,17 @@ static struct pqi_firmware_feature pqi_firmware_features[] = {
 	{
 		.feature_name = "New Soft Reset Handshake",
 		.feature_bit = PQI_FIRMWARE_FEATURE_SOFT_RESET_HANDSHAKE,
-		.feature_status = pqi_firmware_feature_status,
+		.feature_status = pqi_ctrl_update_feature_flags,
+	},
+	{
+		.feature_name = "RAID IU Timeout",
+		.feature_bit = PQI_FIRMWARE_FEATURE_RAID_IU_TIMEOUT,
+		.feature_status = pqi_ctrl_update_feature_flags,
+	},
+	{
+		.feature_name = "TMF IU Timeout",
+		.feature_bit = PQI_FIRMWARE_FEATURE_TMF_IU_TIMEOUT,
+		.feature_status = pqi_ctrl_update_feature_flags,
 	},
 };
 
@@ -6921,7 +6928,6 @@ static void pqi_process_firmware_features(
 		return;
 	}
 
-	ctrl_info->soft_reset_handshake_supported = false;
 	for (i = 0; i < ARRAY_SIZE(pqi_firmware_features); i++) {
 		if (!pqi_firmware_features[i].supported)
 			continue;
@@ -6929,10 +6935,6 @@ static void pqi_process_firmware_features(
 			firmware_features_iomem_addr,
 			pqi_firmware_features[i].feature_bit)) {
 			pqi_firmware_features[i].enabled = true;
-			if (pqi_firmware_features[i].feature_bit ==
-			    PQI_FIRMWARE_FEATURE_SOFT_RESET_HANDSHAKE)
-				ctrl_info->soft_reset_handshake_supported =
-									true;
 		}
 		pqi_firmware_feature_update(ctrl_info,
 			&pqi_firmware_features[i]);
@@ -7074,13 +7076,20 @@ static int pqi_force_sis_mode(struct pqi_ctrl_info *ctrl_info)
 	return pqi_revert_to_sis_mode(ctrl_info);
 }
 
+#define PQI_POST_RESET_DELAY_B4_MSGU_READY	5000
+
 static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
 {
 	int rc;
 
-	rc = pqi_force_sis_mode(ctrl_info);
-	if (rc)
-		return rc;
+	if (reset_devices) {
+		sis_soft_reset(ctrl_info);
+		msleep(PQI_POST_RESET_DELAY_B4_MSGU_READY);
+	} else {
+		rc = pqi_force_sis_mode(ctrl_info);
+		if (rc)
+			return rc;
+	}
 
 	/*
 	 * Wait until the controller is ready to start accepting SIS
@@ -7386,7 +7395,7 @@ static int pqi_ctrl_init_resume(struct pqi_ctrl_info *ctrl_info)
 	rc = pqi_get_ctrl_product_details(ctrl_info);
 	if (rc) {
 		dev_err(&ctrl_info->pci_dev->dev,
-			"error obtaining product detail\n");
+			"error obtaining product details\n");
 		return rc;
 	}
 
@@ -7514,6 +7523,7 @@ static struct pqi_ctrl_info *pqi_alloc_ctrl_info(int numa_node)
 
 	INIT_WORK(&ctrl_info->event_work, pqi_event_worker);
 	atomic_set(&ctrl_info->num_interrupts, 0);
+	atomic_set(&ctrl_info->sync_cmds_outstanding, 0);
 
 	INIT_DELAYED_WORK(&ctrl_info->rescan_work, pqi_rescan_worker);
 	INIT_DELAYED_WORK(&ctrl_info->update_time_work, pqi_update_time_worker);
@@ -7721,6 +7731,8 @@ static void pqi_ofa_setup_host_buffer(struct pqi_ctrl_info *ctrl_info,
 		dev_err(dev, "Failed to allocate host buffer of size = %u",
 			bytes_requested);
 	}
+
+	return;
 }
 
 static void pqi_ofa_free_host_buffer(struct pqi_ctrl_info *ctrl_info)
@@ -7787,8 +7799,6 @@ static int pqi_ofa_host_memory_update(struct pqi_ctrl_info *ctrl_info)
 		0, NULL, NO_TIMEOUT);
 }
 
-#define PQI_POST_RESET_DELAY_B4_MSGU_READY	5000
-
 static int pqi_ofa_ctrl_restart(struct pqi_ctrl_info *ctrl_info)
 {
 	msleep(PQI_POST_RESET_DELAY_B4_MSGU_READY);
@@ -7956,28 +7966,73 @@ static void pqi_pci_remove(struct pci_dev *pci_dev)
 	pqi_remove_ctrl(ctrl_info);
 }
 
+static void pqi_crash_if_pending_command(struct pqi_ctrl_info *ctrl_info)
+{
+	unsigned int i;
+	struct pqi_io_request *io_request;
+	struct scsi_cmnd *scmd;
+
+	for (i = 0; i < ctrl_info->max_io_slots; i++) {
+		io_request = &ctrl_info->io_request_pool[i];
+		if (atomic_read(&io_request->refcount) == 0)
+			continue;
+		scmd = io_request->scmd;
+		WARN_ON(scmd != NULL); /* IO command from SML */
+		WARN_ON(scmd == NULL); /* Non-IO cmd or driver initiated*/
+	}
+}
+
 static void pqi_shutdown(struct pci_dev *pci_dev)
 {
 	int rc;
 	struct pqi_ctrl_info *ctrl_info;
 
 	ctrl_info = pci_get_drvdata(pci_dev);
-	if (!ctrl_info)
-		goto error;
+	if (!ctrl_info) {
+		dev_err(&pci_dev->dev,
+			"cache could not be flushed\n");
+		return;
+	}
+
+	pqi_disable_events(ctrl_info);
+	pqi_wait_until_ofa_finished(ctrl_info);
+	pqi_cancel_update_time_worker(ctrl_info);
+	pqi_cancel_rescan_worker(ctrl_info);
+	pqi_cancel_event_worker(ctrl_info);
+
+	pqi_ctrl_shutdown_start(ctrl_info);
+	pqi_ctrl_wait_until_quiesced(ctrl_info);
+
+	rc = pqi_ctrl_wait_for_pending_io(ctrl_info, NO_TIMEOUT);
+	if (rc) {
+		dev_err(&pci_dev->dev,
+			"wait for pending I/O failed\n");
+		return;
+	}
+
+	pqi_ctrl_block_device_reset(ctrl_info);
+	pqi_wait_until_lun_reset_finished(ctrl_info);
 
 	/*
 	 * Write all data in the controller's battery-backed cache to
 	 * storage.
 	 */
 	rc = pqi_flush_cache(ctrl_info, SHUTDOWN);
-	pqi_free_interrupts(ctrl_info);
-	pqi_reset(ctrl_info);
-	if (rc == 0)
+	if (rc)
+		dev_err(&pci_dev->dev,
+			"unable to flush controller cache\n");
+
+	pqi_ctrl_block_requests(ctrl_info);
+
+	rc = pqi_ctrl_wait_for_pending_sync_cmds(ctrl_info);
+	if (rc) {
+		dev_err(&pci_dev->dev,
+			"wait for pending sync cmds failed\n");
 		return;
+	}
 
-error:
-	dev_warn(&pci_dev->dev,
-		"unable to flush controller cache\n");
+	pqi_crash_if_pending_command(ctrl_info);
+	pqi_reset(ctrl_info);
 }
 
 static void pqi_process_lockup_action_param(void)
@@ -8686,6 +8741,8 @@ static void __attribute__((unused)) verify_structures(void)
 	BUILD_BUG_ON(offsetof(struct pqi_raid_path_request,
 		cdb) != 32);
 	BUILD_BUG_ON(offsetof(struct pqi_raid_path_request,
+		timeout) != 60);
+	BUILD_BUG_ON(offsetof(struct pqi_raid_path_request,
 		sg_descriptors) != 64);
 	BUILD_BUG_ON(sizeof(struct pqi_raid_path_request) !=
 		PQI_OPERATIONAL_IQ_ELEMENT_LENGTH);
@@ -8840,6 +8897,8 @@ static void __attribute__((unused)) verify_structures(void)
 	BUILD_BUG_ON(offsetof(struct pqi_task_management_request,
 		nexus_id) != 10);
 	BUILD_BUG_ON(offsetof(struct pqi_task_management_request,
+		timeout) != 14);
+	BUILD_BUG_ON(offsetof(struct pqi_task_management_request,
 		lun_number) != 16);
 	BUILD_BUG_ON(offsetof(struct pqi_task_management_request,
 		protocol_specific) != 24);
diff --git a/drivers/scsi/smartpqi/smartpqi_sas_transport.c b/drivers/scsi/smartpqi/smartpqi_sas_transport.c
index 6776dfc1d317..b7289112455c 100644
--- a/drivers/scsi/smartpqi/smartpqi_sas_transport.c
+++ b/drivers/scsi/smartpqi/smartpqi_sas_transport.c
@@ -45,9 +45,9 @@ static void pqi_free_sas_phy(struct pqi_sas_phy *pqi_sas_phy)
 	struct sas_phy *phy = pqi_sas_phy->phy;
 
 	sas_port_delete_phy(pqi_sas_phy->parent_port->port, phy);
-	sas_phy_free(phy);
 	if (pqi_sas_phy->added_to_port)
 		list_del(&pqi_sas_phy->phy_list_entry);
+	sas_phy_delete(phy);
 	kfree(pqi_sas_phy);
 }
 
@@ -312,7 +312,6 @@ static int pqi_sas_get_linkerrors(struct sas_phy *phy)
 static int pqi_sas_get_enclosure_identifier(struct sas_rphy *rphy,
 	u64 *identifier)
 {
-
 	int rc;
 	unsigned long flags;
 	struct Scsi_Host *shost;
@@ -361,7 +360,7 @@ static int pqi_sas_get_enclosure_identifier(struct sas_rphy *rphy,
 		}
 	}
 
-	if (found_device->phy_connected_dev_type != SA_CONTROLLER_DEVICE) {
+	if (found_device->phy_connected_dev_type != SA_DEVICE_TYPE_CONTROLLER) {
 		rc = -EINVAL;
 		goto out;
 	}
@@ -382,12 +381,10 @@ out:
 	spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
 
 	return rc;
-
 }
 
 static int pqi_sas_get_bay_identifier(struct sas_rphy *rphy)
 {
-
 	int rc;
 	unsigned long flags;
 	struct pqi_ctrl_info *ctrl_info;
@@ -482,7 +479,6 @@ pqi_build_csmi_smp_passthru_buffer(struct sas_rphy *rphy,
 		req_size -= SMP_CRC_FIELD_LENGTH;
 
 	put_unaligned_le32(req_size, &parameters->request_length);
-
 	put_unaligned_le32(resp_size, &parameters->response_length);
 
 	sg_copy_to_buffer(job->request_payload.sg_list,
@@ -512,12 +508,12 @@ void pqi_sas_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
 	struct sas_rphy *rphy)
 {
 	int rc;
-	struct pqi_ctrl_info *ctrl_info = shost_to_hba(shost);
+	struct pqi_ctrl_info *ctrl_info;
 	struct bmic_csmi_smp_passthru_buffer *smp_buf;
 	struct pqi_raid_error_info error_info;
 	unsigned int reslen = 0;
 
-	pqi_ctrl_busy(ctrl_info);
+	ctrl_info = shost_to_hba(shost);
 
 	if (job->reply_payload.payload_len == 0) {
 		rc = -ENOMEM;
@@ -539,16 +535,6 @@ void pqi_sas_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
 		goto out;
 	}
 
-	if (pqi_ctrl_offline(ctrl_info)) {
-		rc = -ENXIO;
-		goto out;
-	}
-
-	if (pqi_ctrl_blocked(ctrl_info)) {
-		rc = -EBUSY;
-		goto out;
-	}
-
 	smp_buf = pqi_build_csmi_smp_passthru_buffer(rphy, job);
 	if (!smp_buf) {
 		rc = -ENOMEM;
diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c
index 955e4c938d49..701b842296f0 100644
--- a/drivers/scsi/sun3_scsi.c
+++ b/drivers/scsi/sun3_scsi.c
@@ -501,7 +501,7 @@ static struct scsi_host_template sun3_scsi_template = {
 	.eh_host_reset_handler	= sun3scsi_host_reset,
 	.can_queue		= 16,
 	.this_id		= 7,
-	.sg_tablesize		= SG_NONE,
+	.sg_tablesize		= 1,
 	.cmd_per_lun		= 2,
 	.dma_boundary		= PAGE_SIZE - 1,
 	.cmd_size		= NCR5380_CMD_SIZE,
@@ -523,7 +523,7 @@ static int __init sun3_scsi_probe(struct platform_device *pdev)
 		sun3_scsi_template.can_queue = setup_can_queue;
 	if (setup_cmd_per_lun > 0)
 		sun3_scsi_template.cmd_per_lun = setup_cmd_per_lun;
-	if (setup_sg_tablesize >= 0)
+	if (setup_sg_tablesize > 0)
 		sun3_scsi_template.sg_tablesize = setup_sg_tablesize;
 	if (setup_hostid >= 0)
 		sun3_scsi_template.this_id = setup_hostid & 7;
diff --git a/drivers/scsi/ufs/Kconfig b/drivers/scsi/ufs/Kconfig
index 0b845ab7c3bf..d14c2243e02a 100644
--- a/drivers/scsi/ufs/Kconfig
+++ b/drivers/scsi/ufs/Kconfig
@@ -132,6 +132,16 @@ config SCSI_UFS_HISI
 	  Select this if you have UFS controller on Hisilicon chipset.
 	  If unsure, say N.
 
+config SCSI_UFS_TI_J721E
+	tristate "TI glue layer for Cadence UFS Controller"
+	depends on OF && HAS_IOMEM && (ARCH_K3 || COMPILE_TEST)
+	help
+	  This selects driver for TI glue layer for Cadence UFS Host
+	  Controller IP.
+
+	  Selects this if you have TI platform with UFS controller.
+	  If unsure, say N.
+
 config SCSI_UFS_BSG
 	bool "Universal Flash Storage BSG device node"
 	depends on SCSI_UFSHCD
diff --git a/drivers/scsi/ufs/Makefile b/drivers/scsi/ufs/Makefile
index 2a9097939bcb..94c6c5d7334b 100644
--- a/drivers/scsi/ufs/Makefile
+++ b/drivers/scsi/ufs/Makefile
@@ -11,3 +11,4 @@ obj-$(CONFIG_SCSI_UFSHCD_PCI) += ufshcd-pci.o
 obj-$(CONFIG_SCSI_UFSHCD_PLATFORM) += ufshcd-pltfrm.o
 obj-$(CONFIG_SCSI_UFS_HISI) += ufs-hisi.o
 obj-$(CONFIG_SCSI_UFS_MEDIATEK) += ufs-mediatek.o
+obj-$(CONFIG_SCSI_UFS_TI_J721E) += ti-j721e-ufs.o
diff --git a/drivers/scsi/ufs/ti-j721e-ufs.c b/drivers/scsi/ufs/ti-j721e-ufs.c
new file mode 100644
index 000000000000..5216d228cdd9
--- /dev/null
+++ b/drivers/scsi/ufs/ti-j721e-ufs.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/
+//
+
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#define TI_UFS_SS_CTRL		0x4
+#define TI_UFS_SS_RST_N_PCS	BIT(0)
+#define TI_UFS_SS_CLK_26MHZ	BIT(4)
+
+static int ti_j721e_ufs_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	unsigned long clk_rate;
+	void __iomem *regbase;
+	struct clk *clk;
+	u32 reg = 0;
+	int ret;
+
+	regbase = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(regbase))
+		return PTR_ERR(regbase);
+
+	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(dev);
+		return ret;
+	}
+
+	/* Select MPHY refclk frequency */
+	clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(clk)) {
+		dev_err(dev, "Cannot claim MPHY clock.\n");
+		return PTR_ERR(clk);
+	}
+	clk_rate = clk_get_rate(clk);
+	if (clk_rate == 26000000)
+		reg |= TI_UFS_SS_CLK_26MHZ;
+	devm_clk_put(dev, clk);
+
+	/*  Take UFS slave device out of reset */
+	reg |= TI_UFS_SS_RST_N_PCS;
+	writel(reg, regbase + TI_UFS_SS_CTRL);
+
+	ret = of_platform_populate(pdev->dev.of_node, NULL, NULL,
+				   dev);
+	if (ret) {
+		dev_err(dev, "failed to populate child nodes %d\n", ret);
+		pm_runtime_put_sync(dev);
+	}
+
+	return ret;
+}
+
+static int ti_j721e_ufs_remove(struct platform_device *pdev)
+{
+	of_platform_depopulate(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
+
+	return 0;
+}
+
+static const struct of_device_id ti_j721e_ufs_of_match[] = {
+	{
+		.compatible = "ti,j721e-ufs",
+	},
+	{ },
+};
+
+static struct platform_driver ti_j721e_ufs_driver = {
+	.probe	= ti_j721e_ufs_probe,
+	.remove	= ti_j721e_ufs_remove,
+	.driver	= {
+		.name   = "ti-j721e-ufs",
+		.of_match_table = ti_j721e_ufs_of_match,
+	},
+};
+module_platform_driver(ti_j721e_ufs_driver);
+
+MODULE_AUTHOR("Vignesh Raghavendra <vigneshr@ti.com>");
+MODULE_DESCRIPTION("TI UFS host controller glue driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/scsi/ufs/ufs-hisi.c b/drivers/scsi/ufs/ufs-hisi.c
index 6bbb1679bb91..5d6487350a6c 100644
--- a/drivers/scsi/ufs/ufs-hisi.c
+++ b/drivers/scsi/ufs/ufs-hisi.c
@@ -452,10 +452,7 @@ static int ufs_hisi_get_resource(struct ufs_hisi_host *host)
 
 	/* get resource of ufs sys ctrl */
 	host->ufs_sys_ctrl = devm_platform_ioremap_resource(pdev, 1);
-	if (IS_ERR(host->ufs_sys_ctrl))
-		return PTR_ERR(host->ufs_sys_ctrl);
-
-	return 0;
+	return PTR_ERR_OR_ZERO(host->ufs_sys_ctrl);
 }
 
 static void ufs_hisi_set_pm_lvl(struct ufs_hba *hba)
diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c
index 0f6ff33ce52e..83e28edc3ac5 100644
--- a/drivers/scsi/ufs/ufs-mediatek.c
+++ b/drivers/scsi/ufs/ufs-mediatek.c
@@ -147,6 +147,9 @@ static int ufs_mtk_init(struct ufs_hba *hba)
 	if (err)
 		goto out_variant_clear;
 
+	/* Enable runtime autosuspend */
+	hba->caps |= UFSHCD_CAP_RPM_AUTOSUSPEND;
+
 	/*
 	 * ufshcd_vops_init() is invoked after
 	 * ufshcd_setup_clock(true) in ufshcd_hba_init() thus
diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c
index a5b71487a206..c69c29a1ceb9 100644
--- a/drivers/scsi/ufs/ufs-qcom.c
+++ b/drivers/scsi/ufs/ufs-qcom.c
@@ -246,6 +246,44 @@ static void ufs_qcom_select_unipro_mode(struct ufs_qcom_host *host)
 	mb();
 }
 
+/**
+ * ufs_qcom_host_reset - reset host controller and PHY
+ */
+static int ufs_qcom_host_reset(struct ufs_hba *hba)
+{
+	int ret = 0;
+	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
+
+	if (!host->core_reset) {
+		dev_warn(hba->dev, "%s: reset control not set\n", __func__);
+		goto out;
+	}
+
+	ret = reset_control_assert(host->core_reset);
+	if (ret) {
+		dev_err(hba->dev, "%s: core_reset assert failed, err = %d\n",
+				 __func__, ret);
+		goto out;
+	}
+
+	/*
+	 * The hardware requirement for delay between assert/deassert
+	 * is at least 3-4 sleep clock (32.7KHz) cycles, which comes to
+	 * ~125us (4/32768). To be on the safe side add 200us delay.
+	 */
+	usleep_range(200, 210);
+
+	ret = reset_control_deassert(host->core_reset);
+	if (ret)
+		dev_err(hba->dev, "%s: core_reset deassert failed, err = %d\n",
+				 __func__, ret);
+
+	usleep_range(1000, 1100);
+
+out:
+	return ret;
+}
+
 static int ufs_qcom_power_up_sequence(struct ufs_hba *hba)
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
@@ -254,6 +292,12 @@ static int ufs_qcom_power_up_sequence(struct ufs_hba *hba)
 	bool is_rate_B = (UFS_QCOM_LIMIT_HS_RATE == PA_HS_MODE_B)
 							? true : false;
 
+	/* Reset UFS Host Controller and PHY */
+	ret = ufs_qcom_host_reset(hba);
+	if (ret)
+		dev_warn(hba->dev, "%s: host reset returned %d\n",
+				  __func__, ret);
+
 	if (is_rate_B)
 		phy_set_mode(phy, PHY_MODE_UFS_HS_B);
 
@@ -1101,6 +1145,15 @@ static int ufs_qcom_init(struct ufs_hba *hba)
 	host->hba = hba;
 	ufshcd_set_variant(hba, host);
 
+	/* Setup the reset control of HCI */
+	host->core_reset = devm_reset_control_get(hba->dev, "rst");
+	if (IS_ERR(host->core_reset)) {
+		err = PTR_ERR(host->core_reset);
+		dev_warn(dev, "Failed to get reset control %d\n", err);
+		host->core_reset = NULL;
+		err = 0;
+	}
+
 	/* Fire up the reset controller. Failure here is non-fatal. */
 	host->rcdev.of_node = dev->of_node;
 	host->rcdev.ops = &ufs_qcom_reset_ops;
diff --git a/drivers/scsi/ufs/ufs-qcom.h b/drivers/scsi/ufs/ufs-qcom.h
index d401f174bb70..2d95e7cc7187 100644
--- a/drivers/scsi/ufs/ufs-qcom.h
+++ b/drivers/scsi/ufs/ufs-qcom.h
@@ -6,6 +6,7 @@
 #define UFS_QCOM_H_
 
 #include <linux/reset-controller.h>
+#include <linux/reset.h>
 
 #define MAX_UFS_QCOM_HOSTS	1
 #define MAX_U32                 (~(u32)0)
@@ -233,6 +234,8 @@ struct ufs_qcom_host {
 	u32 dbg_print_en;
 	struct ufs_qcom_testbus testbus;
 
+	/* Reset control of HCI */
+	struct reset_control *core_reset;
 	struct reset_controller_dev rcdev;
 
 	struct gpio_desc *device_reset;
diff --git a/drivers/scsi/ufs/ufs-sysfs.c b/drivers/scsi/ufs/ufs-sysfs.c
index 969a36b15897..ad2abc96c0f1 100644
--- a/drivers/scsi/ufs/ufs-sysfs.c
+++ b/drivers/scsi/ufs/ufs-sysfs.c
@@ -126,13 +126,16 @@ static void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit)
 		return;
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
-	if (hba->ahit == ahit)
-		goto out_unlock;
-	hba->ahit = ahit;
-	if (!pm_runtime_suspended(hba->dev))
-		ufshcd_writel(hba, hba->ahit, REG_AUTO_HIBERNATE_IDLE_TIMER);
-out_unlock:
+	if (hba->ahit != ahit)
+		hba->ahit = ahit;
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	if (!pm_runtime_suspended(hba->dev)) {
+		pm_runtime_get_sync(hba->dev);
+		ufshcd_hold(hba, false);
+		ufshcd_auto_hibern8_enable(hba);
+		ufshcd_release(hba);
+		pm_runtime_put(hba->dev);
+	}
 }
 
 /* Convert Auto-Hibernate Idle Timer register value to microseconds */
diff --git a/drivers/scsi/ufs/ufs_bsg.c b/drivers/scsi/ufs/ufs_bsg.c
index dc2f6d2b46ed..baeecee35d1e 100644
--- a/drivers/scsi/ufs/ufs_bsg.c
+++ b/drivers/scsi/ufs/ufs_bsg.c
@@ -162,6 +162,7 @@ out:
 
 /**
  * ufs_bsg_remove - detach and remove the added ufs-bsg node
+ * @hba: per adapter object
  *
  * Should be called when unloading the driver.
  */
diff --git a/drivers/scsi/ufs/ufshcd-dwc.c b/drivers/scsi/ufs/ufshcd-dwc.c
index fb9e2ff4f8d2..6a901da2d15a 100644
--- a/drivers/scsi/ufs/ufshcd-dwc.c
+++ b/drivers/scsi/ufs/ufshcd-dwc.c
@@ -80,7 +80,7 @@ static int ufshcd_dwc_link_is_up(struct ufs_hba *hba)
  */
 static int ufshcd_dwc_connection_setup(struct ufs_hba *hba)
 {
-	const struct ufshcd_dme_attr_val setup_attrs[] = {
+	static const struct ufshcd_dme_attr_val setup_attrs[] = {
 		{ UIC_ARG_MIB(T_CONNECTIONSTATE), 0, DME_LOCAL },
 		{ UIC_ARG_MIB(N_DEVICEID), 0, DME_LOCAL },
 		{ UIC_ARG_MIB(N_DEVICEID_VALID), 0, DME_LOCAL },
diff --git a/drivers/scsi/ufs/ufshcd-pltfrm.c b/drivers/scsi/ufs/ufshcd-pltfrm.c
index 8d40dc918f4e..76f9be71c31b 100644
--- a/drivers/scsi/ufs/ufshcd-pltfrm.c
+++ b/drivers/scsi/ufs/ufshcd-pltfrm.c
@@ -402,7 +402,6 @@ int ufshcd_pltfrm_init(struct platform_device *pdev,
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
-		dev_err(dev, "IRQ resource not available\n");
 		err = -ENODEV;
 		goto out;
 	}
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 11a87f51c442..b5966faf3e98 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -88,6 +88,9 @@
 /* Interrupt aggregation default timeout, unit: 40us */
 #define INT_AGGR_DEF_TO	0x02
 
+/* default delay of autosuspend: 2000 ms */
+#define RPM_AUTOSUSPEND_DELAY_MS 2000
+
 #define ufshcd_toggle_vreg(_dev, _vreg, _on)				\
 	({                                                              \
 		int _ret;                                               \
@@ -114,7 +117,7 @@ int ufshcd_dump_regs(struct ufs_hba *hba, size_t offset, size_t len,
 	if (offset % 4 != 0 || len % 4 != 0) /* keep readl happy */
 		return -EINVAL;
 
-	regs = kzalloc(len, GFP_KERNEL);
+	regs = kzalloc(len, GFP_ATOMIC);
 	if (!regs)
 		return -ENOMEM;
 
@@ -237,7 +240,7 @@ static struct ufs_dev_fix ufs_fixups[] = {
 	END_FIX
 };
 
-static void ufshcd_tmc_handler(struct ufs_hba *hba);
+static irqreturn_t 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);
@@ -1607,7 +1610,7 @@ static void ufshcd_gate_work(struct work_struct *work)
 	 * state to CLKS_ON.
 	 */
 	if (hba->clk_gating.is_suspended ||
-		(hba->clk_gating.state == REQ_CLKS_ON)) {
+		(hba->clk_gating.state != REQ_CLKS_OFF)) {
 		hba->clk_gating.state = CLKS_ON;
 		trace_ufshcd_clk_gating(dev_name(hba->dev),
 					hba->clk_gating.state);
@@ -1935,8 +1938,8 @@ int ufshcd_copy_query_response(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 			memcpy(hba->dev_cmd.query.descriptor, descp, resp_len);
 		} else {
 			dev_warn(hba->dev,
-				"%s: Response size is bigger than buffer",
-				__func__);
+				 "%s: rsp size %d is bigger than buffer size %d",
+				 __func__, resp_len, buf_len);
 			return -EINVAL;
 		}
 	}
@@ -2986,10 +2989,10 @@ static int __ufshcd_query_descriptor(struct ufs_hba *hba,
 		goto out_unlock;
 	}
 
-	hba->dev_cmd.query.descriptor = NULL;
 	*buf_len = be16_to_cpu(response->upiu_res.length);
 
 out_unlock:
+	hba->dev_cmd.query.descriptor = NULL;
 	mutex_unlock(&hba->dev_cmd.lock);
 out:
 	ufshcd_release(hba);
@@ -3856,6 +3859,9 @@ static int ufshcd_link_recovery(struct ufs_hba *hba)
 	ufshcd_set_eh_in_progress(hba);
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
+	/* Reset the attached device */
+	ufshcd_vops_device_reset(hba);
+
 	ret = ufshcd_host_reset_and_restore(hba);
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
@@ -3885,15 +3891,24 @@ static int __ufshcd_uic_hibern8_enter(struct ufs_hba *hba)
 			     ktime_to_us(ktime_sub(ktime_get(), start)), ret);
 
 	if (ret) {
+		int err;
+
 		dev_err(hba->dev, "%s: hibern8 enter failed. ret = %d\n",
 			__func__, ret);
 
 		/*
-		 * If link recovery fails then return error so that caller
-		 * don't retry the hibern8 enter again.
+		 * If link recovery fails then return error code returned from
+		 * ufshcd_link_recovery().
+		 * If link recovery succeeds then return -EAGAIN to attempt
+		 * hibern8 enter retry again.
 		 */
-		if (ufshcd_link_recovery(hba))
-			ret = -ENOLINK;
+		err = ufshcd_link_recovery(hba);
+		if (err) {
+			dev_err(hba->dev, "%s: link recovery failed", __func__);
+			ret = err;
+		} else {
+			ret = -EAGAIN;
+		}
 	} else
 		ufshcd_vops_hibern8_notify(hba, UIC_CMD_DME_HIBER_ENTER,
 								POST_CHANGE);
@@ -3907,7 +3922,7 @@ static int ufshcd_uic_hibern8_enter(struct ufs_hba *hba)
 
 	for (retries = UIC_HIBERN8_ENTER_RETRIES; retries > 0; retries--) {
 		ret = __ufshcd_uic_hibern8_enter(hba);
-		if (!ret || ret == -ENOLINK)
+		if (!ret)
 			goto out;
 	}
 out:
@@ -3941,7 +3956,7 @@ static int ufshcd_uic_hibern8_exit(struct ufs_hba *hba)
 	return ret;
 }
 
-static void ufshcd_auto_hibern8_enable(struct ufs_hba *hba)
+void ufshcd_auto_hibern8_enable(struct ufs_hba *hba)
 {
 	unsigned long flags;
 
@@ -4631,9 +4646,14 @@ static int ufshcd_change_queue_depth(struct scsi_device *sdev, int depth)
  */
 static int ufshcd_slave_configure(struct scsi_device *sdev)
 {
+	struct ufs_hba *hba = shost_priv(sdev->host);
 	struct request_queue *q = sdev->request_queue;
 
 	blk_queue_update_dma_pad(q, PRDT_DATA_BYTE_COUNT_PAD - 1);
+
+	if (ufshcd_is_rpm_autosuspend_allowed(hba))
+		sdev->rpm_autosuspend = 1;
+
 	return 0;
 }
 
@@ -4788,19 +4808,29 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
  * ufshcd_uic_cmd_compl - handle completion of uic command
  * @hba: per adapter instance
  * @intr_status: interrupt status generated by the controller
+ *
+ * Returns
+ *  IRQ_HANDLED - If interrupt is valid
+ *  IRQ_NONE    - If invalid interrupt
  */
-static void ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status)
+static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status)
 {
+	irqreturn_t retval = IRQ_NONE;
+
 	if ((intr_status & UIC_COMMAND_COMPL) && hba->active_uic_cmd) {
 		hba->active_uic_cmd->argument2 |=
 			ufshcd_get_uic_cmd_result(hba);
 		hba->active_uic_cmd->argument3 =
 			ufshcd_get_dme_attr_val(hba);
 		complete(&hba->active_uic_cmd->done);
+		retval = IRQ_HANDLED;
 	}
 
-	if ((intr_status & UFSHCD_UIC_PWR_MASK) && hba->uic_async_done)
+	if ((intr_status & UFSHCD_UIC_PWR_MASK) && hba->uic_async_done) {
 		complete(hba->uic_async_done);
+		retval = IRQ_HANDLED;
+	}
+	return retval;
 }
 
 /**
@@ -4856,8 +4886,12 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
 /**
  * ufshcd_transfer_req_compl - handle SCSI and query command completion
  * @hba: per adapter instance
+ *
+ * Returns
+ *  IRQ_HANDLED - If interrupt is valid
+ *  IRQ_NONE    - If invalid interrupt
  */
-static void ufshcd_transfer_req_compl(struct ufs_hba *hba)
+static irqreturn_t ufshcd_transfer_req_compl(struct ufs_hba *hba)
 {
 	unsigned long completed_reqs;
 	u32 tr_doorbell;
@@ -4876,7 +4910,12 @@ static void ufshcd_transfer_req_compl(struct ufs_hba *hba)
 	tr_doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 	completed_reqs = tr_doorbell ^ hba->outstanding_reqs;
 
-	__ufshcd_transfer_req_compl(hba, completed_reqs);
+	if (completed_reqs) {
+		__ufshcd_transfer_req_compl(hba, completed_reqs);
+		return IRQ_HANDLED;
+	} else {
+		return IRQ_NONE;
+	}
 }
 
 /**
@@ -5395,61 +5434,77 @@ out:
 /**
  * ufshcd_update_uic_error - check and set fatal UIC error flags.
  * @hba: per-adapter instance
+ *
+ * Returns
+ *  IRQ_HANDLED - If interrupt is valid
+ *  IRQ_NONE    - If invalid interrupt
  */
-static void ufshcd_update_uic_error(struct ufs_hba *hba)
+static irqreturn_t ufshcd_update_uic_error(struct ufs_hba *hba)
 {
 	u32 reg;
+	irqreturn_t retval = IRQ_NONE;
 
 	/* PHY layer lane error */
 	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_reg_hist(&hba->ufs_stats.pa_err, reg);
+		retval |= IRQ_HANDLED;
 	}
 
 	/* PA_INIT_ERROR is fatal and needs UIC reset */
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_DATA_LINK_LAYER);
-	if (reg)
+	if ((reg & UIC_DATA_LINK_LAYER_ERROR) &&
+	    (reg & UIC_DATA_LINK_LAYER_ERROR_CODE_MASK)) {
 		ufshcd_update_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 &
-		   UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS) {
-		if (reg & UIC_DATA_LINK_LAYER_ERROR_NAC_RECEIVED)
-			hba->uic_error |=
-				UFSHCD_UIC_DL_NAC_RECEIVED_ERROR;
-		else if (reg & UIC_DATA_LINK_LAYER_ERROR_TCx_REPLAY_TIMEOUT)
-			hba->uic_error |= UFSHCD_UIC_DL_TCx_REPLAY_ERROR;
+		if (reg & UIC_DATA_LINK_LAYER_ERROR_PA_INIT)
+			hba->uic_error |= UFSHCD_UIC_DL_PA_INIT_ERROR;
+		else if (hba->dev_quirks &
+				UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS) {
+			if (reg & UIC_DATA_LINK_LAYER_ERROR_NAC_RECEIVED)
+				hba->uic_error |=
+					UFSHCD_UIC_DL_NAC_RECEIVED_ERROR;
+			else if (reg & UIC_DATA_LINK_LAYER_ERROR_TCx_REPLAY_TIMEOUT)
+				hba->uic_error |= UFSHCD_UIC_DL_TCx_REPLAY_ERROR;
+		}
+		retval |= IRQ_HANDLED;
 	}
 
 	/* UIC NL/TL/DME errors needs software retry */
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_NETWORK_LAYER);
-	if (reg) {
+	if ((reg & UIC_NETWORK_LAYER_ERROR) &&
+	    (reg & UIC_NETWORK_LAYER_ERROR_CODE_MASK)) {
 		ufshcd_update_reg_hist(&hba->ufs_stats.nl_err, reg);
 		hba->uic_error |= UFSHCD_UIC_NL_ERROR;
+		retval |= IRQ_HANDLED;
 	}
 
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_TRANSPORT_LAYER);
-	if (reg) {
+	if ((reg & UIC_TRANSPORT_LAYER_ERROR) &&
+	    (reg & UIC_TRANSPORT_LAYER_ERROR_CODE_MASK)) {
 		ufshcd_update_reg_hist(&hba->ufs_stats.tl_err, reg);
 		hba->uic_error |= UFSHCD_UIC_TL_ERROR;
+		retval |= IRQ_HANDLED;
 	}
 
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_DME);
-	if (reg) {
+	if ((reg & UIC_DME_ERROR) &&
+	    (reg & UIC_DME_ERROR_CODE_MASK)) {
 		ufshcd_update_reg_hist(&hba->ufs_stats.dme_err, reg);
 		hba->uic_error |= UFSHCD_UIC_DME_ERROR;
+		retval |= IRQ_HANDLED;
 	}
 
 	dev_dbg(hba->dev, "%s: UIC error flags = 0x%08x\n",
 			__func__, hba->uic_error);
+	return retval;
 }
 
 static bool ufshcd_is_auto_hibern8_error(struct ufs_hba *hba,
@@ -5472,10 +5527,15 @@ static bool ufshcd_is_auto_hibern8_error(struct ufs_hba *hba,
 /**
  * ufshcd_check_errors - Check for errors that need s/w attention
  * @hba: per-adapter instance
+ *
+ * Returns
+ *  IRQ_HANDLED - If interrupt is valid
+ *  IRQ_NONE    - If invalid interrupt
  */
-static void ufshcd_check_errors(struct ufs_hba *hba)
+static irqreturn_t ufshcd_check_errors(struct ufs_hba *hba)
 {
 	bool queue_eh_work = false;
+	irqreturn_t retval = IRQ_NONE;
 
 	if (hba->errors & INT_FATAL_ERRORS) {
 		ufshcd_update_reg_hist(&hba->ufs_stats.fatal_err, hba->errors);
@@ -5484,7 +5544,7 @@ static void ufshcd_check_errors(struct ufs_hba *hba)
 
 	if (hba->errors & UIC_ERROR) {
 		hba->uic_error = 0;
-		ufshcd_update_uic_error(hba);
+		retval = ufshcd_update_uic_error(hba);
 		if (hba->uic_error)
 			queue_eh_work = true;
 	}
@@ -5532,6 +5592,7 @@ static void ufshcd_check_errors(struct ufs_hba *hba)
 			}
 			schedule_work(&hba->eh_work);
 		}
+		retval |= IRQ_HANDLED;
 	}
 	/*
 	 * if (!queue_eh_work) -
@@ -5539,44 +5600,62 @@ static void ufshcd_check_errors(struct ufs_hba *hba)
 	 * itself without s/w intervention or errors that will be
 	 * handled by the SCSI core layer.
 	 */
+	return retval;
 }
 
 /**
  * ufshcd_tmc_handler - handle task management function completion
  * @hba: per adapter instance
+ *
+ * Returns
+ *  IRQ_HANDLED - If interrupt is valid
+ *  IRQ_NONE    - If invalid interrupt
  */
-static void ufshcd_tmc_handler(struct ufs_hba *hba)
+static irqreturn_t ufshcd_tmc_handler(struct ufs_hba *hba)
 {
 	u32 tm_doorbell;
 
 	tm_doorbell = ufshcd_readl(hba, REG_UTP_TASK_REQ_DOOR_BELL);
 	hba->tm_condition = tm_doorbell ^ hba->outstanding_tasks;
-	wake_up(&hba->tm_wq);
+	if (hba->tm_condition) {
+		wake_up(&hba->tm_wq);
+		return IRQ_HANDLED;
+	} else {
+		return IRQ_NONE;
+	}
 }
 
 /**
  * ufshcd_sl_intr - Interrupt service routine
  * @hba: per adapter instance
  * @intr_status: contains interrupts generated by the controller
+ *
+ * Returns
+ *  IRQ_HANDLED - If interrupt is valid
+ *  IRQ_NONE    - If invalid interrupt
  */
-static void ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status)
+static irqreturn_t ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status)
 {
+	irqreturn_t retval = IRQ_NONE;
+
 	hba->errors = UFSHCD_ERROR_MASK & intr_status;
 
 	if (ufshcd_is_auto_hibern8_error(hba, intr_status))
 		hba->errors |= (UFSHCD_UIC_HIBERN8_MASK & intr_status);
 
 	if (hba->errors)
-		ufshcd_check_errors(hba);
+		retval |= ufshcd_check_errors(hba);
 
 	if (intr_status & UFSHCD_UIC_MASK)
-		ufshcd_uic_cmd_compl(hba, intr_status);
+		retval |= ufshcd_uic_cmd_compl(hba, intr_status);
 
 	if (intr_status & UTP_TASK_REQ_COMPL)
-		ufshcd_tmc_handler(hba);
+		retval |= ufshcd_tmc_handler(hba);
 
 	if (intr_status & UTP_TRANSFER_REQ_COMPL)
-		ufshcd_transfer_req_compl(hba);
+		retval |= ufshcd_transfer_req_compl(hba);
+
+	return retval;
 }
 
 /**
@@ -5584,8 +5663,9 @@ static void ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status)
  * @irq: irq number
  * @__hba: pointer to adapter instance
  *
- * Returns IRQ_HANDLED - If interrupt is valid
- *		IRQ_NONE - If invalid interrupt
+ * Returns
+ *  IRQ_HANDLED - If interrupt is valid
+ *  IRQ_NONE    - If invalid interrupt
  */
 static irqreturn_t ufshcd_intr(int irq, void *__hba)
 {
@@ -5608,14 +5688,18 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba)
 			intr_status & ufshcd_readl(hba, REG_INTERRUPT_ENABLE);
 		if (intr_status)
 			ufshcd_writel(hba, intr_status, REG_INTERRUPT_STATUS);
-		if (enabled_intr_status) {
-			ufshcd_sl_intr(hba, enabled_intr_status);
-			retval = IRQ_HANDLED;
-		}
+		if (enabled_intr_status)
+			retval |= ufshcd_sl_intr(hba, enabled_intr_status);
 
 		intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS);
 	} while (intr_status && --retries);
 
+	if (retval == IRQ_NONE) {
+		dev_err(hba->dev, "%s: Unhandled interrupt 0x%08x\n",
+					__func__, intr_status);
+		ufshcd_dump_regs(hba, 0, UFSHCI_REG_SPACE_SIZE, "host_regs: ");
+	}
+
 	spin_unlock(hba->host->host_lock);
 	return retval;
 }
@@ -5760,9 +5844,9 @@ static int ufshcd_issue_tm_cmd(struct ufs_hba *hba, int lun_id, int task_id,
  * @hba:	per-adapter instance
  * @req_upiu:	upiu request
  * @rsp_upiu:	upiu reply
- * @msgcode:	message code, one of UPIU Transaction Codes Initiator to Target
  * @desc_buff:	pointer to descriptor buffer, NULL if NA
  * @buff_len:	descriptor size, 0 if NA
+ * @cmd_type:	specifies the type (NOP, Query...)
  * @desc_op:	descriptor operation
  *
  * Those type of requests uses UTP Transfer Request Descriptor - utrd.
@@ -5776,7 +5860,7 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
 					struct utp_upiu_req *req_upiu,
 					struct utp_upiu_req *rsp_upiu,
 					u8 *desc_buff, int *buff_len,
-					int cmd_type,
+					enum dev_cmd_type cmd_type,
 					enum query_opcode desc_op)
 {
 	struct ufshcd_lrb *lrbp;
@@ -5856,7 +5940,9 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
 			memcpy(desc_buff, descp, resp_len);
 			*buff_len = resp_len;
 		} else {
-			dev_warn(hba->dev, "rsp size is bigger than buffer");
+			dev_warn(hba->dev,
+				 "%s: rsp size %d is bigger than buffer size %d",
+				 __func__, resp_len, *buff_len);
 			*buff_len = 0;
 			err = -EINVAL;
 		}
@@ -5891,7 +5977,7 @@ int ufshcd_exec_raw_upiu_cmd(struct ufs_hba *hba,
 			     enum query_opcode desc_op)
 {
 	int err;
-	int cmd_type = DEV_CMD_TYPE_QUERY;
+	enum dev_cmd_type cmd_type = DEV_CMD_TYPE_QUERY;
 	struct utp_task_req_desc treq = { { 0 }, };
 	int ocs_value;
 	u8 tm_f = be32_to_cpu(req_upiu->header.dword_1) >> 16 & MASK_TM_FUNC;
@@ -6770,23 +6856,13 @@ static void ufshcd_init_desc_sizes(struct ufs_hba *hba)
 		&hba->desc_size.geom_desc);
 	if (err)
 		hba->desc_size.geom_desc = QUERY_DESC_GEOMETRY_DEF_SIZE;
+
 	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_HEALTH, 0,
 		&hba->desc_size.hlth_desc);
 	if (err)
 		hba->desc_size.hlth_desc = QUERY_DESC_HEALTH_DEF_SIZE;
 }
 
-static void ufshcd_def_desc_sizes(struct ufs_hba *hba)
-{
-	hba->desc_size.dev_desc = QUERY_DESC_DEVICE_DEF_SIZE;
-	hba->desc_size.pwr_desc = QUERY_DESC_POWER_DEF_SIZE;
-	hba->desc_size.interc_desc = QUERY_DESC_INTERCONNECT_DEF_SIZE;
-	hba->desc_size.conf_desc = QUERY_DESC_CONFIGURATION_DEF_SIZE;
-	hba->desc_size.unit_desc = QUERY_DESC_UNIT_DEF_SIZE;
-	hba->desc_size.geom_desc = QUERY_DESC_GEOMETRY_DEF_SIZE;
-	hba->desc_size.hlth_desc = QUERY_DESC_HEALTH_DEF_SIZE;
-}
-
 static struct ufs_ref_clk ufs_ref_clk_freqs[] = {
 	{19200000, REF_CLK_FREQ_19_2_MHZ},
 	{26000000, REF_CLK_FREQ_26_MHZ},
@@ -6881,9 +6957,6 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 	/* UniPro link is active now */
 	ufshcd_set_link_active(hba);
 
-	/* Enable Auto-Hibernate if configured */
-	ufshcd_auto_hibern8_enable(hba);
-
 	ret = ufshcd_verify_dev_init(hba);
 	if (ret)
 		goto out;
@@ -6934,6 +7007,9 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 	/* set the state as operational after switching to desired gear */
 	hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
 
+	/* Enable Auto-Hibernate if configured */
+	ufshcd_auto_hibern8_enable(hba);
+
 	/*
 	 * If we are in error handling context or in power management callbacks
 	 * context, no need to scan the host
@@ -7069,6 +7145,7 @@ static struct scsi_host_template ufshcd_driver_template = {
 	.track_queue_depth	= 1,
 	.sdev_groups		= ufshcd_driver_groups,
 	.dma_boundary		= PAGE_SIZE - 1,
+	.rpm_autosuspend_delay	= RPM_AUTOSUSPEND_DELAY_MS,
 };
 
 static int ufshcd_config_vreg_load(struct device *dev, struct ufs_vreg *vreg,
@@ -7950,12 +8027,12 @@ static int ufshcd_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 	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);
-
 	/* Enable Auto-Hibernate if configured */
 	ufshcd_auto_hibern8_enable(hba);
 
+	/* Schedule clock gating in case of no access to UFS device yet */
+	ufshcd_release(hba);
+
 	goto out;
 
 set_old_link_state:
@@ -8274,9 +8351,6 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	hba->mmio_base = mmio_base;
 	hba->irq = irq;
 
-	/* Set descriptor lengths to specification defaults */
-	ufshcd_def_desc_sizes(hba);
-
 	err = ufshcd_hba_init(hba);
 	if (err)
 		goto out_error;
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index c94cfda52829..2740f6941ec6 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -716,6 +716,12 @@ struct ufs_hba {
 	 * the performance of ongoing read/write operations.
 	 */
 #define UFSHCD_CAP_KEEP_AUTO_BKOPS_ENABLED_EXCEPT_SUSPEND (1 << 5)
+	/*
+	 * This capability allows host controller driver to automatically
+	 * enable runtime power management by itself instead of waiting
+	 * for userspace to control the power management.
+	 */
+#define UFSHCD_CAP_RPM_AUTOSUSPEND (1 << 6)
 
 	struct devfreq *devfreq;
 	struct ufs_clk_scaling clk_scaling;
@@ -749,6 +755,10 @@ static inline bool ufshcd_can_autobkops_during_suspend(struct ufs_hba *hba)
 {
 	return hba->caps & UFSHCD_CAP_AUTO_BKOPS_SUSPEND;
 }
+static inline bool ufshcd_is_rpm_autosuspend_allowed(struct ufs_hba *hba)
+{
+	return hba->caps & UFSHCD_CAP_RPM_AUTOSUSPEND;
+}
 
 static inline bool ufshcd_is_intr_aggr_allowed(struct ufs_hba *hba)
 {
@@ -916,6 +926,8 @@ int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode,
 int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
 	enum flag_idn idn, bool *flag_res);
 
+void ufshcd_auto_hibern8_enable(struct ufs_hba *hba);
+
 #define SD_ASCII_STD true
 #define SD_RAW false
 int ufshcd_read_string_desc(struct ufs_hba *hba, u8 desc_index,
diff --git a/drivers/scsi/ufs/ufshci.h b/drivers/scsi/ufs/ufshci.h
index dbb75cd28dc8..c2961d37cc1c 100644
--- a/drivers/scsi/ufs/ufshci.h
+++ b/drivers/scsi/ufs/ufshci.h
@@ -195,7 +195,7 @@ enum {
 
 /* UECDL - Host UIC Error Code Data Link Layer 3Ch */
 #define UIC_DATA_LINK_LAYER_ERROR		0x80000000
-#define UIC_DATA_LINK_LAYER_ERROR_CODE_MASK	0x7FFF
+#define UIC_DATA_LINK_LAYER_ERROR_CODE_MASK	0xFFFF
 #define UIC_DATA_LINK_LAYER_ERROR_TCX_REP_TIMER_EXP	0x2
 #define UIC_DATA_LINK_LAYER_ERROR_AFCX_REQ_TIMER_EXP	0x4
 #define UIC_DATA_LINK_LAYER_ERROR_FCX_PRO_TIMER_EXP	0x8
diff --git a/drivers/scsi/zorro_esp.c b/drivers/scsi/zorro_esp.c
index ca8e3abeb2c7..a23a8e5794f5 100644
--- a/drivers/scsi/zorro_esp.c
+++ b/drivers/scsi/zorro_esp.c
@@ -218,7 +218,14 @@ static int fastlane_esp_irq_pending(struct esp *esp)
 static u32 zorro_esp_dma_length_limit(struct esp *esp, u32 dma_addr,
 					u32 dma_len)
 {
-	return dma_len > 0xFFFF ? 0xFFFF : dma_len;
+	return dma_len > (1U << 16) ? (1U << 16) : dma_len;
+}
+
+static u32 fastlane_esp_dma_length_limit(struct esp *esp, u32 dma_addr,
+					u32 dma_len)
+{
+	/* The old driver used 0xfffc as limit, so do that here too */
+	return dma_len > 0xfffc ? 0xfffc : dma_len;
 }
 
 static void zorro_esp_reset_dma(struct esp *esp)
@@ -604,7 +611,7 @@ static const struct esp_driver_ops fastlane_esp_ops = {
 	.esp_write8		= zorro_esp_write8,
 	.esp_read8		= zorro_esp_read8,
 	.irq_pending		= fastlane_esp_irq_pending,
-	.dma_length_limit	= zorro_esp_dma_length_limit,
+	.dma_length_limit	= fastlane_esp_dma_length_limit,
 	.reset_dma		= zorro_esp_reset_dma,
 	.dma_drain		= zorro_esp_dma_drain,
 	.dma_invalidate		= fastlane_esp_dma_invalidate,