Merge tag 'v4.10-rc1' into patchwork

Linux 4.10-rc1 * tag 'v4.10-rc1': (11427 commits) Linux 4.10-rc1 powerpc: Fix build warning on 32-bit PPC avoid spurious "may be used uninitialized" warning mm: add PageWaiters indicating tasks are waiting for a page bit mm: Use owner_priv bit for PageSwapCache, valid when PageSwapBacked ktime: Get rid of ktime_equal() ktime: Cleanup ktime_set() usage ktime: Get rid of the union clocksource: Use a plain u64 instead of cycle_t irqchip/armada-xp: Consolidate hotplug state space irqchip/gic: Consolidate hotplug state space coresight/etm3/4x: Consolidate hotplug state space cpu/hotplug: Cleanup state names cpu/hotplug: Remove obsolete cpu hotplug register/unregister functions staging/lustre/libcfs: Convert to hotplug state machine scsi/bnx2i: Convert to hotplug state machine scsi/bnx2fc: Convert to hotplug state machine cpu/hotplug: Prevent overwriting of callbacks x86/msr: Remove bogus cleanup from the error path bus: arm-ccn: Prevent hotplug callback leak ...
author: Mauro Carvalho Chehab <mchehab@s-opensource.com> 2016-12-26 19:11:35 +0300
committer: Mauro Carvalho Chehab <mchehab@s-opensource.com> 2016-12-26 19:11:35 +0300
commit: bd361f5de2b338218c276d17a510701a16075deb (patch)
tree: e0d60ab13fd29d7a56131c9364c9b53baba4940a /drivers/scsi
parent: c739c0a7c3c2472d7562b8f802cdce44d2597c8b (diff)
parent: 7ce7d89f48834cefece7804d38fc5d85382edf77 (diff)
download: linux-bd361f5de2b338218c276d17a510701a16075deb.tar.xz
183 files changed, 15558 insertions, 4881 deletions
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index a56a7b243e91..00e7968a1d70 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -1,8 +1,8 @@
 /*
    3w-9xxx.c -- 3ware 9000 Storage Controller device driver for Linux.
 
-   Written By: Adam Radford <linuxraid@lsi.com>
-   Modifications By: Tom Couch <linuxraid@lsi.com>
+   Written By: Adam Radford <aradford@gmail.com>
+   Modifications By: Tom Couch
 
    Copyright (C) 2004-2009 Applied Micro Circuits Corporation.
    Copyright (C) 2010 LSI Corporation.
@@ -41,10 +41,7 @@
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
    Bugs/Comments/Suggestions should be mailed to:
-   linuxraid@lsi.com
-
-   For more information, goto:
-   http://www.lsi.com
+   aradford@gmail.com
 
    Note: This version of the driver does not contain a bundled firmware
          image.
@@ -95,7 +92,7 @@
 #include <linux/slab.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_tcq.h>
diff --git a/drivers/scsi/3w-9xxx.h b/drivers/scsi/3w-9xxx.h
index 0fdc83cfa0e1..b6c208cc474f 100644
--- a/drivers/scsi/3w-9xxx.h
+++ b/drivers/scsi/3w-9xxx.h
@@ -1,8 +1,8 @@
 /*
    3w-9xxx.h -- 3ware 9000 Storage Controller device driver for Linux.
 
-   Written By: Adam Radford <linuxraid@lsi.com>
-   Modifications By: Tom Couch <linuxraid@lsi.com>
+   Written By: Adam Radford <aradford@gmail.com>
+   Modifications By: Tom Couch
 
    Copyright (C) 2004-2009 Applied Micro Circuits Corporation.
    Copyright (C) 2010 LSI Corporation.
@@ -41,10 +41,7 @@
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
    Bugs/Comments/Suggestions should be mailed to:
-   linuxraid@lsi.com
-
-   For more information, goto:
-   http://www.lsi.com
+   aradford@gmail.com
 */
 
 #ifndef _3W_9XXX_H
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index f8374850f714..b150e131b2e7 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -1,7 +1,7 @@
 /*
    3w-sas.c -- LSI 3ware SAS/SATA-RAID Controller device driver for Linux.
 
-   Written By: Adam Radford <linuxraid@lsi.com>
+   Written By: Adam Radford <aradford@gmail.com>
 
    Copyright (C) 2009 LSI Corporation.
 
@@ -43,10 +43,7 @@
    LSI 3ware 9750 6Gb/s SAS/SATA-RAID
 
    Bugs/Comments/Suggestions should be mailed to:
-   linuxraid@lsi.com
-
-   For more information, goto:
-   http://www.lsi.com
+   aradford@gmail.com
 
    History
    -------
@@ -67,7 +64,7 @@
 #include <linux/slab.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_tcq.h>
diff --git a/drivers/scsi/3w-sas.h b/drivers/scsi/3w-sas.h
index fec6449c7595..05e77d84c16d 100644
--- a/drivers/scsi/3w-sas.h
+++ b/drivers/scsi/3w-sas.h
@@ -1,7 +1,7 @@
 /*
    3w-sas.h -- LSI 3ware SAS/SATA-RAID Controller device driver for Linux.
 
-   Written By: Adam Radford <linuxraid@lsi.com>
+   Written By: Adam Radford <aradford@gmail.com>
 
    Copyright (C) 2009 LSI Corporation.
 
@@ -39,10 +39,7 @@
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
    Bugs/Comments/Suggestions should be mailed to:
-   linuxraid@lsi.com
-
-   For more information, goto:
-   http://www.lsi.com
+   aradford@gmail.com
 */
 
 #ifndef _3W_SAS_H
diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index 25aba1613e21..33261b690774 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -1,7 +1,7 @@
 /* 
    3w-xxxx.c -- 3ware Storage Controller device driver for Linux.
 
-   Written By: Adam Radford <linuxraid@lsi.com>
+   Written By: Adam Radford <aradford@gmail.com>
    Modifications By: Joel Jacobson <linux@3ware.com>
    		     Arnaldo Carvalho de Melo <acme@conectiva.com.br>
                      Brad Strand <linux@3ware.com>
@@ -47,10 +47,9 @@
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA 
 
    Bugs/Comments/Suggestions should be mailed to:                            
-   linuxraid@lsi.com
 
-   For more information, goto:
-   http://www.lsi.com
+   aradford@gmail.com
+
 
    History
    -------
@@ -211,7 +210,7 @@
 #include <linux/mutex.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_tcq.h>
diff --git a/drivers/scsi/3w-xxxx.h b/drivers/scsi/3w-xxxx.h
index 6f65e663d393..69e80c1ed1ca 100644
--- a/drivers/scsi/3w-xxxx.h
+++ b/drivers/scsi/3w-xxxx.h
@@ -1,7 +1,7 @@
 /* 
    3w-xxxx.h -- 3ware Storage Controller device driver for Linux.
    
-   Written By: Adam Radford <linuxraid@lsi.com>
+   Written By: Adam Radford <aradford@gmail.com>
    Modifications By: Joel Jacobson <linux@3ware.com>
    		     Arnaldo Carvalho de Melo <acme@conectiva.com.br>
                      Brad Strand <linux@3ware.com>
@@ -45,7 +45,8 @@
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA 
 
    Bugs/Comments/Suggestions should be mailed to:                            
-   linuxraid@lsi.com
+
+   aradford@gmail.com
    
    For more information, goto:
    http://www.lsi.com
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 3e2bdb90813c..a4f6b0d95515 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -263,6 +263,7 @@ config SCSI_SPI_ATTRS
 config SCSI_FC_ATTRS
 	tristate "FiberChannel Transport Attributes"
 	depends on SCSI && NET
+	select BLK_DEV_BSGLIB
 	select SCSI_NETLINK
 	help
 	  If you wish to export transport-specific information about
@@ -743,40 +744,18 @@ config SCSI_ISCI
 	  control unit found in the Intel(R) C600 series chipset.
 
 config SCSI_GENERIC_NCR5380
-	tristate "Generic NCR5380/53c400 SCSI PIO support"
-	depends on ISA && SCSI
+	tristate "Generic NCR5380/53c400 SCSI ISA card support"
+	depends on ISA && SCSI && HAS_IOPORT_MAP
 	select SCSI_SPI_ATTRS
 	---help---
-	  This is a driver for the old NCR 53c80 series of SCSI controllers
-	  on boards using PIO. Most boards such as the Trantor T130 fit this
-	  category, along with a large number of ISA 8bit controllers shipped
-	  for free with SCSI scanners. If you have a PAS16, T128 or DMX3191
-	  you should select the specific driver for that card rather than
-	  generic 5380 support.
-
-	  It is explained in section 3.8 of the SCSI-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.  If it doesn't work out
-	  of the box, you may have to change some settings in
-	  <file:drivers/scsi/g_NCR5380.h>.
+	  This is a driver for old ISA card SCSI controllers based on a
+	  NCR 5380, 53C80, 53C400, 53C400A, or DTC 436 device.
+	  Most boards such as the Trantor T130 fit this category, as do
+	  various 8-bit and 16-bit ISA cards bundled with SCSI scanners.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called g_NCR5380.
 
-config SCSI_GENERIC_NCR5380_MMIO
-	tristate "Generic NCR5380/53c400 SCSI MMIO support"
-	depends on ISA && SCSI
-	select SCSI_SPI_ATTRS
-	---help---
-	  This is a driver for the old NCR 53c80 series of SCSI controllers
-	  on boards using memory mapped I/O. 
-	  It is explained in section 3.8 of the SCSI-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.  If it doesn't work out
-	  of the box, you may have to change some settings in
-	  <file:drivers/scsi/g_NCR5380.h>.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called g_NCR5380_mmio.
-
 config SCSI_IPS
 	tristate "IBM ServeRAID support"
 	depends on PCI && SCSI
@@ -1254,6 +1233,7 @@ config SCSI_QLOGICPTI
 
 source "drivers/scsi/qla2xxx/Kconfig"
 source "drivers/scsi/qla4xxx/Kconfig"
+source "drivers/scsi/qedi/Kconfig"
 
 config SCSI_LPFC
 	tristate "Emulex LightPulse Fibre Channel Support"
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 38d938d7fe67..736b77414a4b 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -74,7 +74,6 @@ obj-$(CONFIG_SCSI_ISCI)		+= isci/
 obj-$(CONFIG_SCSI_IPS)		+= ips.o
 obj-$(CONFIG_SCSI_FUTURE_DOMAIN)+= fdomain.o
 obj-$(CONFIG_SCSI_GENERIC_NCR5380) += g_NCR5380.o
-obj-$(CONFIG_SCSI_GENERIC_NCR5380_MMIO) += g_NCR5380_mmio.o
 obj-$(CONFIG_SCSI_NCR53C406A)	+= NCR53c406a.o
 obj-$(CONFIG_SCSI_NCR_D700)	+= 53c700.o NCR_D700.o
 obj-$(CONFIG_SCSI_NCR_Q720)	+= NCR_Q720_mod.o
@@ -132,6 +131,7 @@ obj-$(CONFIG_PS3_ROM)		+= ps3rom.o
 obj-$(CONFIG_SCSI_CXGB3_ISCSI)	+= libiscsi.o libiscsi_tcp.o cxgbi/
 obj-$(CONFIG_SCSI_CXGB4_ISCSI)	+= libiscsi.o libiscsi_tcp.o cxgbi/
 obj-$(CONFIG_SCSI_BNX2_ISCSI)	+= libiscsi.o bnx2i/
+obj-$(CONFIG_QEDI)          += libiscsi.o qedi/
 obj-$(CONFIG_BE2ISCSI)		+= libiscsi.o be2iscsi/
 obj-$(CONFIG_SCSI_ESAS2R)	+= esas2r/
 obj-$(CONFIG_SCSI_PMCRAID)	+= pmcraid.o
@@ -173,6 +173,7 @@ hv_storvsc-y			:= storvsc_drv.o
 
 sd_mod-objs	:= sd.o
 sd_mod-$(CONFIG_BLK_DEV_INTEGRITY) += sd_dif.o
+sd_mod-$(CONFIG_BLK_DEV_ZONED) += sd_zbc.o
 
 sr_mod-objs	:= sr.o sr_ioctl.o sr_vendor.o
 ncr53c8xx-flags-$(CONFIG_SCSI_ZALON) \
diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index 790babc5ef66..4f5ca794bb71 100644
--- a/drivers/scsi/NCR5380.c
+++ b/drivers/scsi/NCR5380.c
@@ -97,9 +97,6 @@
  * and macros and include this file in your driver.
  *
  * These macros control options :
- * AUTOPROBE_IRQ - if defined, the NCR5380_probe_irq() function will be
- * defined.
- *
  * AUTOSENSE - if defined, REQUEST SENSE will be performed automatically
  * for commands that return with a CHECK CONDITION status.
  *
@@ -121,14 +118,13 @@
  *
  * Either real DMA *or* pseudo DMA may be implemented
  *
- * NCR5380_dma_write_setup(instance, src, count) - initialize
- * NCR5380_dma_read_setup(instance, dst, count) - initialize
- * NCR5380_dma_residual(instance); - residual count
+ * NCR5380_dma_xfer_len   - determine size of DMA/PDMA transfer
+ * NCR5380_dma_send_setup - execute DMA/PDMA from memory to 5380
+ * NCR5380_dma_recv_setup - execute DMA/PDMA from 5380 to memory
+ * NCR5380_dma_residual   - residual byte count
  *
  * The generic driver is initialized by calling NCR5380_init(instance),
- * after setting the appropriate host specific fields and ID.  If the
- * driver wishes to autoprobe for an IRQ line, the NCR5380_probe_irq(instance,
- * possible) function may be used.
+ * after setting the appropriate host specific fields and ID.
  */
 
 #ifndef NCR5380_io_delay
@@ -178,7 +174,7 @@ static inline void initialize_SCp(struct scsi_cmnd *cmd)
 
 /**
  * NCR5380_poll_politely2 - wait for two chip register values
- * @instance: controller to poll
+ * @hostdata: host private data
  * @reg1: 5380 register to poll
  * @bit1: Bitmask to check
  * @val1: Expected value
@@ -195,18 +191,14 @@ static inline void initialize_SCp(struct scsi_cmnd *cmd)
  * Returns 0 if either or both event(s) occurred otherwise -ETIMEDOUT.
  */
 
-static int NCR5380_poll_politely2(struct Scsi_Host *instance,
-                                  int reg1, int bit1, int val1,
-                                  int reg2, int bit2, int val2, int wait)
+static int NCR5380_poll_politely2(struct NCR5380_hostdata *hostdata,
+                                  unsigned int reg1, u8 bit1, u8 val1,
+                                  unsigned int reg2, u8 bit2, u8 val2,
+                                  unsigned long wait)
 {
-	struct NCR5380_hostdata *hostdata = shost_priv(instance);
+	unsigned long n = hostdata->poll_loops;
 	unsigned long deadline = jiffies + wait;
-	unsigned long n;
 
-	/* Busy-wait for up to 10 ms */
-	n = min(10000U, jiffies_to_usecs(wait));
-	n *= hostdata->accesses_per_ms;
-	n /= 2000;
 	do {
 		if ((NCR5380_read(reg1) & bit1) == val1)
 			return 0;
@@ -288,6 +280,7 @@ mrs[] = {
 
 static void NCR5380_print(struct Scsi_Host *instance)
 {
+	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	unsigned char status, data, basr, mr, icr, i;
 
 	data = NCR5380_read(CURRENT_SCSI_DATA_REG);
@@ -337,6 +330,7 @@ static struct {
 
 static void NCR5380_print_phase(struct Scsi_Host *instance)
 {
+	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	unsigned char status;
 	int i;
 
@@ -352,76 +346,6 @@ static void NCR5380_print_phase(struct Scsi_Host *instance)
 }
 #endif
 
-
-static int probe_irq;
-
-/**
- * probe_intr	-	helper for IRQ autoprobe
- * @irq: interrupt number
- * @dev_id: unused
- * @regs: unused
- *
- * Set a flag to indicate the IRQ in question was received. This is
- * used by the IRQ probe code.
- */
-
-static irqreturn_t probe_intr(int irq, void *dev_id)
-{
-	probe_irq = irq;
-	return IRQ_HANDLED;
-}
-
-/**
- * NCR5380_probe_irq	-	find the IRQ of an NCR5380
- * @instance: NCR5380 controller
- * @possible: bitmask of ISA IRQ lines
- *
- * Autoprobe for the IRQ line used by the NCR5380 by triggering an IRQ
- * and then looking to see what interrupt actually turned up.
- */
-
-static int __maybe_unused NCR5380_probe_irq(struct Scsi_Host *instance,
-						int possible)
-{
-	struct NCR5380_hostdata *hostdata = shost_priv(instance);
-	unsigned long timeout;
-	int trying_irqs, i, mask;
-
-	for (trying_irqs = 0, i = 1, mask = 2; i < 16; ++i, mask <<= 1)
-		if ((mask & possible) && (request_irq(i, &probe_intr, 0, "NCR-probe", NULL) == 0))
-			trying_irqs |= mask;
-
-	timeout = jiffies + msecs_to_jiffies(250);
-	probe_irq = NO_IRQ;
-
-	/*
-	 * A interrupt is triggered whenever BSY = false, SEL = true
-	 * and a bit set in the SELECT_ENABLE_REG is asserted on the
-	 * SCSI bus.
-	 *
-	 * Note that the bus is only driven when the phase control signals
-	 * (I/O, C/D, and MSG) match those in the TCR, so we must reset that
-	 * to zero.
-	 */
-
-	NCR5380_write(TARGET_COMMAND_REG, 0);
-	NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask);
-	NCR5380_write(OUTPUT_DATA_REG, hostdata->id_mask);
-	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE | ICR_ASSERT_DATA | ICR_ASSERT_SEL);
-
-	while (probe_irq == NO_IRQ && time_before(jiffies, timeout))
-		schedule_timeout_uninterruptible(1);
-
-	NCR5380_write(SELECT_ENABLE_REG, 0);
-	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
-
-	for (i = 1, mask = 2; i < 16; ++i, mask <<= 1)
-		if (trying_irqs & mask)
-			free_irq(i, NULL);
-
-	return probe_irq;
-}
-
 /**
  * NCR58380_info - report driver and host information
  * @instance: relevant scsi host instance
@@ -441,14 +365,14 @@ static void prepare_info(struct Scsi_Host *instance)
 	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 
 	snprintf(hostdata->info, sizeof(hostdata->info),
-	         "%s, io_port 0x%lx, n_io_port %d, "
-	         "base 0x%lx, irq %d, "
+	         "%s, irq %d, "
+		 "io_port 0x%lx, base 0x%lx, "
 	         "can_queue %d, cmd_per_lun %d, "
 	         "sg_tablesize %d, this_id %d, "
 	         "flags { %s%s%s}, "
 	         "options { %s} ",
-	         instance->hostt->name, instance->io_port, instance->n_io_port,
-	         instance->base, instance->irq,
+	         instance->hostt->name, instance->irq,
+		 hostdata->io_port, hostdata->base,
 	         instance->can_queue, instance->cmd_per_lun,
 	         instance->sg_tablesize, instance->this_id,
 	         hostdata->flags & FLAG_DMA_FIXUP     ? "DMA_FIXUP "     : "",
@@ -482,6 +406,7 @@ static int NCR5380_init(struct Scsi_Host *instance, int flags)
 	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	int i;
 	unsigned long deadline;
+	unsigned long accesses_per_ms;
 
 	instance->max_lun = 7;
 
@@ -530,7 +455,8 @@ static int NCR5380_init(struct Scsi_Host *instance, int flags)
 		++i;
 		cpu_relax();
 	} while (time_is_after_jiffies(deadline));
-	hostdata->accesses_per_ms = i / 256;
+	accesses_per_ms = i / 256;
+	hostdata->poll_loops = NCR5380_REG_POLL_TIME * accesses_per_ms / 2;
 
 	return 0;
 }
@@ -560,7 +486,7 @@ static int NCR5380_maybe_reset_bus(struct Scsi_Host *instance)
 		case 3:
 		case 5:
 			shost_printk(KERN_ERR, instance, "SCSI bus busy, waiting up to five seconds\n");
-			NCR5380_poll_politely(instance,
+			NCR5380_poll_politely(hostdata,
 			                      STATUS_REG, SR_BSY, 0, 5 * HZ);
 			break;
 		case 2:
@@ -871,7 +797,7 @@ static void NCR5380_dma_complete(struct Scsi_Host *instance)
 	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
 	NCR5380_read(RESET_PARITY_INTERRUPT_REG);
 
-	transferred = hostdata->dma_len - NCR5380_dma_residual(instance);
+	transferred = hostdata->dma_len - NCR5380_dma_residual(hostdata);
 	hostdata->dma_len = 0;
 
 	data = (unsigned char **)&hostdata->connected->SCp.ptr;
@@ -994,7 +920,7 @@ static irqreturn_t __maybe_unused NCR5380_intr(int irq, void *dev_id)
 		}
 		handled = 1;
 	} else {
-		shost_printk(KERN_NOTICE, instance, "interrupt without IRQ bit\n");
+		dsprintk(NDEBUG_INTR, instance, "interrupt without IRQ bit\n");
 #ifdef SUN3_SCSI_VME
 		dregs->csr |= CSR_DMA_ENABLE;
 #endif
@@ -1075,7 +1001,7 @@ static struct scsi_cmnd *NCR5380_select(struct Scsi_Host *instance,
 	 */
 
 	spin_unlock_irq(&hostdata->lock);
-	err = NCR5380_poll_politely2(instance, MODE_REG, MR_ARBITRATE, 0,
+	err = NCR5380_poll_politely2(hostdata, MODE_REG, MR_ARBITRATE, 0,
 	                INITIATOR_COMMAND_REG, ICR_ARBITRATION_PROGRESS,
 	                                       ICR_ARBITRATION_PROGRESS, HZ);
 	spin_lock_irq(&hostdata->lock);
@@ -1201,7 +1127,7 @@ static struct scsi_cmnd *NCR5380_select(struct Scsi_Host *instance,
 	 * selection.
 	 */
 
-	err = NCR5380_poll_politely(instance, STATUS_REG, SR_BSY, SR_BSY,
+	err = NCR5380_poll_politely(hostdata, STATUS_REG, SR_BSY, SR_BSY,
 	                            msecs_to_jiffies(250));
 
 	if ((NCR5380_read(STATUS_REG) & (SR_SEL | SR_IO)) == (SR_SEL | SR_IO)) {
@@ -1247,7 +1173,7 @@ static struct scsi_cmnd *NCR5380_select(struct Scsi_Host *instance,
 
 	/* Wait for start of REQ/ACK handshake */
 
-	err = NCR5380_poll_politely(instance, STATUS_REG, SR_REQ, SR_REQ, HZ);
+	err = NCR5380_poll_politely(hostdata, STATUS_REG, SR_REQ, SR_REQ, HZ);
 	spin_lock_irq(&hostdata->lock);
 	if (err < 0) {
 		shost_printk(KERN_ERR, instance, "select: REQ timeout\n");
@@ -1318,6 +1244,7 @@ static int NCR5380_transfer_pio(struct Scsi_Host *instance,
 				unsigned char *phase, int *count,
 				unsigned char **data)
 {
+	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	unsigned char p = *phase, tmp;
 	int c = *count;
 	unsigned char *d = *data;
@@ -1336,7 +1263,7 @@ static int NCR5380_transfer_pio(struct Scsi_Host *instance,
 		 * valid
 		 */
 
-		if (NCR5380_poll_politely(instance, STATUS_REG, SR_REQ, SR_REQ, HZ) < 0)
+		if (NCR5380_poll_politely(hostdata, STATUS_REG, SR_REQ, SR_REQ, HZ) < 0)
 			break;
 
 		dsprintk(NDEBUG_HANDSHAKE, instance, "REQ asserted\n");
@@ -1381,7 +1308,7 @@ static int NCR5380_transfer_pio(struct Scsi_Host *instance,
 			NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE | ICR_ASSERT_ACK);
 		}
 
-		if (NCR5380_poll_politely(instance,
+		if (NCR5380_poll_politely(hostdata,
 		                          STATUS_REG, SR_REQ, 0, 5 * HZ) < 0)
 			break;
 
@@ -1440,6 +1367,7 @@ static int NCR5380_transfer_pio(struct Scsi_Host *instance,
 
 static void do_reset(struct Scsi_Host *instance)
 {
+	struct NCR5380_hostdata __maybe_unused *hostdata = shost_priv(instance);
 	unsigned long flags;
 
 	local_irq_save(flags);
@@ -1462,6 +1390,7 @@ static void do_reset(struct Scsi_Host *instance)
 
 static int do_abort(struct Scsi_Host *instance)
 {
+	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	unsigned char *msgptr, phase, tmp;
 	int len;
 	int rc;
@@ -1479,7 +1408,7 @@ static int do_abort(struct Scsi_Host *instance)
 	 * the target sees, so we just handshake.
 	 */
 
-	rc = NCR5380_poll_politely(instance, STATUS_REG, SR_REQ, SR_REQ, 10 * HZ);
+	rc = NCR5380_poll_politely(hostdata, STATUS_REG, SR_REQ, SR_REQ, 10 * HZ);
 	if (rc < 0)
 		goto timeout;
 
@@ -1490,7 +1419,7 @@ static int do_abort(struct Scsi_Host *instance)
 	if (tmp != PHASE_MSGOUT) {
 		NCR5380_write(INITIATOR_COMMAND_REG,
 		              ICR_BASE | ICR_ASSERT_ATN | ICR_ASSERT_ACK);
-		rc = NCR5380_poll_politely(instance, STATUS_REG, SR_REQ, 0, 3 * HZ);
+		rc = NCR5380_poll_politely(hostdata, STATUS_REG, SR_REQ, 0, 3 * HZ);
 		if (rc < 0)
 			goto timeout;
 		NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE | ICR_ASSERT_ATN);
@@ -1575,9 +1504,9 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance,
 		 * starting the NCR. This is also the cleaner way for the TT.
 		 */
 		if (p & SR_IO)
-			result = NCR5380_dma_recv_setup(instance, d, c);
+			result = NCR5380_dma_recv_setup(hostdata, d, c);
 		else
-			result = NCR5380_dma_send_setup(instance, d, c);
+			result = NCR5380_dma_send_setup(hostdata, d, c);
 	}
 
 	/*
@@ -1609,9 +1538,9 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance,
 		 * NCR access, else the DMA setup gets trashed!
 		 */
 		if (p & SR_IO)
-			result = NCR5380_dma_recv_setup(instance, d, c);
+			result = NCR5380_dma_recv_setup(hostdata, d, c);
 		else
-			result = NCR5380_dma_send_setup(instance, d, c);
+			result = NCR5380_dma_send_setup(hostdata, d, c);
 	}
 
 	/* On failure, NCR5380_dma_xxxx_setup() returns a negative int. */
@@ -1678,12 +1607,12 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance,
 			 * byte.
 			 */
 
-			if (NCR5380_poll_politely(instance, BUS_AND_STATUS_REG,
+			if (NCR5380_poll_politely(hostdata, BUS_AND_STATUS_REG,
 			                          BASR_DRQ, BASR_DRQ, HZ) < 0) {
 				result = -1;
 				shost_printk(KERN_ERR, instance, "PDMA read: DRQ timeout\n");
 			}
-			if (NCR5380_poll_politely(instance, STATUS_REG,
+			if (NCR5380_poll_politely(hostdata, STATUS_REG,
 			                          SR_REQ, 0, HZ) < 0) {
 				result = -1;
 				shost_printk(KERN_ERR, instance, "PDMA read: !REQ timeout\n");
@@ -1694,7 +1623,7 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance,
 			 * Wait for the last byte to be sent.  If REQ is being asserted for
 			 * the byte we're interested, we'll ACK it and it will go false.
 			 */
-			if (NCR5380_poll_politely2(instance,
+			if (NCR5380_poll_politely2(hostdata,
 			     BUS_AND_STATUS_REG, BASR_DRQ, BASR_DRQ,
 			     BUS_AND_STATUS_REG, BASR_PHASE_MATCH, 0, HZ) < 0) {
 				result = -1;
@@ -1751,22 +1680,26 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 				NCR5380_dprint_phase(NDEBUG_INFORMATION, instance);
 			}
 #ifdef CONFIG_SUN3
-			if (phase == PHASE_CMDOUT) {
-				void *d;
-				unsigned long count;
+			if (phase == PHASE_CMDOUT &&
+			    sun3_dma_setup_done != cmd) {
+				int count;
 
 				if (!cmd->SCp.this_residual && cmd->SCp.buffers_residual) {
-					count = cmd->SCp.buffer->length;
-					d = sg_virt(cmd->SCp.buffer);
-				} else {
-					count = cmd->SCp.this_residual;
-					d = cmd->SCp.ptr;
+					++cmd->SCp.buffer;
+					--cmd->SCp.buffers_residual;
+					cmd->SCp.this_residual = cmd->SCp.buffer->length;
+					cmd->SCp.ptr = sg_virt(cmd->SCp.buffer);
 				}
 
-				if (sun3_dma_setup_done != cmd &&
-				    sun3scsi_dma_xfer_len(count, cmd) > 0) {
-					sun3scsi_dma_setup(instance, d, count,
-					                   rq_data_dir(cmd->request));
+				count = sun3scsi_dma_xfer_len(hostdata, cmd);
+
+				if (count > 0) {
+					if (rq_data_dir(cmd->request))
+						sun3scsi_dma_send_setup(hostdata,
+						                        cmd->SCp.ptr, count);
+					else
+						sun3scsi_dma_recv_setup(hostdata,
+						                        cmd->SCp.ptr, count);
 					sun3_dma_setup_done = cmd;
 				}
 #ifdef SUN3_SCSI_VME
@@ -1827,7 +1760,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 
 				transfersize = 0;
 				if (!cmd->device->borken)
-					transfersize = NCR5380_dma_xfer_len(instance, cmd, phase);
+					transfersize = NCR5380_dma_xfer_len(hostdata, cmd);
 
 				if (transfersize > 0) {
 					len = transfersize;
@@ -2073,7 +2006,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 			} /* switch(phase) */
 		} else {
 			spin_unlock_irq(&hostdata->lock);
-			NCR5380_poll_politely(instance, STATUS_REG, SR_REQ, SR_REQ, HZ);
+			NCR5380_poll_politely(hostdata, STATUS_REG, SR_REQ, SR_REQ, HZ);
 			spin_lock_irq(&hostdata->lock);
 		}
 	}
@@ -2119,7 +2052,7 @@ static void NCR5380_reselect(struct Scsi_Host *instance)
 	 */
 
 	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE | ICR_ASSERT_BSY);
-	if (NCR5380_poll_politely(instance,
+	if (NCR5380_poll_politely(hostdata,
 	                          STATUS_REG, SR_SEL, 0, 2 * HZ) < 0) {
 		NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
 		return;
@@ -2130,7 +2063,7 @@ static void NCR5380_reselect(struct Scsi_Host *instance)
 	 * Wait for target to go into MSGIN.
 	 */
 
-	if (NCR5380_poll_politely(instance,
+	if (NCR5380_poll_politely(hostdata,
 	                          STATUS_REG, SR_REQ, SR_REQ, 2 * HZ) < 0) {
 		do_abort(instance);
 		return;
@@ -2204,22 +2137,25 @@ static void NCR5380_reselect(struct Scsi_Host *instance)
 	}
 
 #ifdef CONFIG_SUN3
-	{
-		void *d;
-		unsigned long count;
+	if (sun3_dma_setup_done != tmp) {
+		int count;
 
 		if (!tmp->SCp.this_residual && tmp->SCp.buffers_residual) {
-			count = tmp->SCp.buffer->length;
-			d = sg_virt(tmp->SCp.buffer);
-		} else {
-			count = tmp->SCp.this_residual;
-			d = tmp->SCp.ptr;
+			++tmp->SCp.buffer;
+			--tmp->SCp.buffers_residual;
+			tmp->SCp.this_residual = tmp->SCp.buffer->length;
+			tmp->SCp.ptr = sg_virt(tmp->SCp.buffer);
 		}
 
-		if (sun3_dma_setup_done != tmp &&
-		    sun3scsi_dma_xfer_len(count, tmp) > 0) {
-			sun3scsi_dma_setup(instance, d, count,
-			                   rq_data_dir(tmp->request));
+		count = sun3scsi_dma_xfer_len(hostdata, tmp);
+
+		if (count > 0) {
+			if (rq_data_dir(tmp->request))
+				sun3scsi_dma_send_setup(hostdata,
+				                        tmp->SCp.ptr, count);
+			else
+				sun3scsi_dma_recv_setup(hostdata,
+				                        tmp->SCp.ptr, count);
 			sun3_dma_setup_done = tmp;
 		}
 	}
diff --git a/drivers/scsi/NCR5380.h b/drivers/scsi/NCR5380.h
index 965d92339455..51a3567a6fb2 100644
--- a/drivers/scsi/NCR5380.h
+++ b/drivers/scsi/NCR5380.h
@@ -199,16 +199,6 @@
 
 #define PHASE_SR_TO_TCR(phase) ((phase) >> 2)
 
-/*
- * These are "special" values for the irq and dma_channel fields of the 
- * Scsi_Host structure
- */
-
-#define DMA_NONE	255
-#define IRQ_AUTO	254
-#define DMA_AUTO	254
-#define PORT_AUTO	0xffff	/* autoprobe io port for 53c400a */
-
 #ifndef NO_IRQ
 #define NO_IRQ		0
 #endif
@@ -219,27 +209,32 @@
 #define FLAG_TOSHIBA_DELAY		128	/* Allow for borken CD-ROMs */
 
 struct NCR5380_hostdata {
-	NCR5380_implementation_fields;		/* implementation specific */
-	struct Scsi_Host *host;			/* Host backpointer */
-	unsigned char id_mask, id_higher_mask;	/* 1 << id, all bits greater */
-	unsigned char busy[8];			/* index = target, bit = lun */
-	int dma_len;				/* requested length of DMA */
-	unsigned char last_message;		/* last message OUT */
-	struct scsi_cmnd *connected;		/* currently connected cmnd */
-	struct scsi_cmnd *selecting;		/* cmnd to be connected */
-	struct list_head unissued;		/* waiting to be issued */
-	struct list_head autosense;		/* priority issue queue */
-	struct list_head disconnected;		/* waiting for reconnect */
-	spinlock_t lock;			/* protects this struct */
-	int flags;
-	struct scsi_eh_save ses;
-	struct scsi_cmnd *sensing;
+	NCR5380_implementation_fields;		/* Board-specific data */
+	u8 __iomem *io;				/* Remapped 5380 address */
+	u8 __iomem *pdma_io;			/* Remapped PDMA address */
+	unsigned long poll_loops;		/* Register polling limit */
+	spinlock_t lock;			/* Protects this struct */
+	struct scsi_cmnd *connected;		/* Currently connected cmnd */
+	struct list_head disconnected;		/* Waiting for reconnect */
+	struct Scsi_Host *host;			/* SCSI host backpointer */
+	struct workqueue_struct *work_q;	/* SCSI host work queue */
+	struct work_struct main_task;		/* Work item for main loop */
+	int flags;				/* Board-specific quirks */
+	int dma_len;				/* Requested length of DMA */
+	int read_overruns;	/* Transfer size reduction for DMA erratum */
+	unsigned long io_port;			/* Device IO port */
+	unsigned long base;			/* Device base address */
+	struct list_head unissued;		/* Waiting to be issued */
+	struct scsi_cmnd *selecting;		/* Cmnd to be connected */
+	struct list_head autosense;		/* Priority cmnd queue */
+	struct scsi_cmnd *sensing;		/* Cmnd needing autosense */
+	struct scsi_eh_save ses;		/* Cmnd state saved for EH */
+	unsigned char busy[8];			/* Index = target, bit = lun */
+	unsigned char id_mask;			/* 1 << Host ID */
+	unsigned char id_higher_mask;		/* All bits above id_mask */
+	unsigned char last_message;		/* Last Message Out */
+	unsigned long region_size;		/* Size of address/port range */
 	char info[256];
-	int read_overruns;                /* number of bytes to cut from a
-	                                   * transfer to handle chip overruns */
-	struct work_struct main_task;
-	struct workqueue_struct *work_q;
-	unsigned long accesses_per_ms;	/* chip register accesses per ms */
 };
 
 #ifdef __KERNEL__
@@ -252,6 +247,9 @@ struct NCR5380_cmd {
 
 #define NCR5380_PIO_CHUNK_SIZE		256
 
+/* Time limit (ms) to poll registers when IRQs are disabled, e.g. during PDMA */
+#define NCR5380_REG_POLL_TIME		15
+
 static inline struct scsi_cmnd *NCR5380_to_scmd(struct NCR5380_cmd *ncmd_ptr)
 {
 	return ((struct scsi_cmnd *)ncmd_ptr) - 1;
@@ -282,7 +280,6 @@ static void NCR5380_print(struct Scsi_Host *instance);
 #define NCR5380_dprint_phase(flg, arg) do {} while (0)
 #endif
 
-static int NCR5380_probe_irq(struct Scsi_Host *instance, int possible);
 static int NCR5380_init(struct Scsi_Host *instance, int flags);
 static int NCR5380_maybe_reset_bus(struct Scsi_Host *);
 static void NCR5380_exit(struct Scsi_Host *instance);
@@ -294,14 +291,45 @@ static void NCR5380_reselect(struct Scsi_Host *instance);
 static struct scsi_cmnd *NCR5380_select(struct Scsi_Host *, struct scsi_cmnd *);
 static int NCR5380_transfer_dma(struct Scsi_Host *instance, unsigned char *phase, int *count, unsigned char **data);
 static int NCR5380_transfer_pio(struct Scsi_Host *instance, unsigned char *phase, int *count, unsigned char **data);
-static int NCR5380_poll_politely2(struct Scsi_Host *, int, int, int, int, int, int, int);
+static int NCR5380_poll_politely2(struct NCR5380_hostdata *,
+                                  unsigned int, u8, u8,
+                                  unsigned int, u8, u8, unsigned long);
 
-static inline int NCR5380_poll_politely(struct Scsi_Host *instance,
-					int reg, int bit, int val, int wait)
+static inline int NCR5380_poll_politely(struct NCR5380_hostdata *hostdata,
+                                        unsigned int reg, u8 bit, u8 val,
+                                        unsigned long wait)
 {
-	return NCR5380_poll_politely2(instance, reg, bit, val,
+	if ((NCR5380_read(reg) & bit) == val)
+		return 0;
+
+	return NCR5380_poll_politely2(hostdata, reg, bit, val,
 						reg, bit, val, wait);
 }
 
+static int NCR5380_dma_xfer_len(struct NCR5380_hostdata *,
+                                struct scsi_cmnd *);
+static int NCR5380_dma_send_setup(struct NCR5380_hostdata *,
+                                  unsigned char *, int);
+static int NCR5380_dma_recv_setup(struct NCR5380_hostdata *,
+                                  unsigned char *, int);
+static int NCR5380_dma_residual(struct NCR5380_hostdata *);
+
+static inline int NCR5380_dma_xfer_none(struct NCR5380_hostdata *hostdata,
+                                        struct scsi_cmnd *cmd)
+{
+	return 0;
+}
+
+static inline int NCR5380_dma_setup_none(struct NCR5380_hostdata *hostdata,
+                                         unsigned char *data, int count)
+{
+	return 0;
+}
+
+static inline int NCR5380_dma_residual_none(struct NCR5380_hostdata *hostdata)
+{
+	return 0;
+}
+
 #endif				/* __KERNEL__ */
 #endif				/* NCR5380_H */
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index 6678d1fd897b..1ee7c654f7b8 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -32,7 +32,7 @@
 #include <linux/slab.h>
 #include <linux/completion.h>
 #include <linux/blkdev.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/highmem.h> /* For flush_kernel_dcache_page */
 #include <linux/module.h>
 
diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index 969c312de1be..f059c14efa0c 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -1246,7 +1246,6 @@ struct aac_dev
 	u32			max_msix;	/* max. MSI-X vectors */
 	u32			vector_cap;	/* MSI-X vector capab.*/
 	int			msi_enabled;	/* MSI/MSI-X enabled */
-	struct msix_entry	msixentry[AAC_MAX_MSIX];
 	struct aac_msix_ctx	aac_msix[AAC_MAX_MSIX]; /* context */
 	u8			adapter_shutdown;
 	u32			handle_pci_error;
diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c
index 5648b715fed9..e1daff230c7d 100644
--- a/drivers/scsi/aacraid/commctrl.c
+++ b/drivers/scsi/aacraid/commctrl.c
@@ -41,7 +41,7 @@
 #include <linux/delay.h> /* ssleep prototype */
 #include <linux/kthread.h>
 #include <linux/semaphore.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <scsi/scsi_host.h>
 
 #include "aacraid.h"
diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c
index 341ea327ae79..4f56b1003cc7 100644
--- a/drivers/scsi/aacraid/comminit.c
+++ b/drivers/scsi/aacraid/comminit.c
@@ -378,16 +378,12 @@ void aac_define_int_mode(struct aac_dev *dev)
 	if (msi_count > AAC_MAX_MSIX)
 		msi_count = AAC_MAX_MSIX;
 
-	for (i = 0; i < msi_count; i++)
-		dev->msixentry[i].entry = i;
-
 	if (msi_count > 1 &&
 	    pci_find_capability(dev->pdev, PCI_CAP_ID_MSIX)) {
 		min_msix = 2;
-		i = pci_enable_msix_range(dev->pdev,
-				    dev->msixentry,
-				    min_msix,
-				    msi_count);
+		i = pci_alloc_irq_vectors(dev->pdev,
+					  min_msix, msi_count,
+					  PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
 		if (i > 0) {
 			dev->msi_enabled = 1;
 			msi_count = i;
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 0aeecec1f5ea..9e7551fe4b19 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -2043,30 +2043,22 @@ int aac_acquire_irq(struct aac_dev *dev)
 	int i;
 	int j;
 	int ret = 0;
-	int cpu;
 
-	cpu = cpumask_first(cpu_online_mask);
 	if (!dev->sync_mode && dev->msi_enabled && dev->max_msix > 1) {
 		for (i = 0; i < dev->max_msix; i++) {
 			dev->aac_msix[i].vector_no = i;
 			dev->aac_msix[i].dev = dev;
-			if (request_irq(dev->msixentry[i].vector,
+			if (request_irq(pci_irq_vector(dev->pdev, i),
 					dev->a_ops.adapter_intr,
 					0, "aacraid", &(dev->aac_msix[i]))) {
 				printk(KERN_ERR "%s%d: Failed to register IRQ for vector %d.\n",
 						dev->name, dev->id, i);
 				for (j = 0 ; j < i ; j++)
-					free_irq(dev->msixentry[j].vector,
+					free_irq(pci_irq_vector(dev->pdev, j),
 						 &(dev->aac_msix[j]));
 				pci_disable_msix(dev->pdev);
 				ret = -1;
 			}
-			if (irq_set_affinity_hint(dev->msixentry[i].vector,
-							get_cpu_mask(cpu))) {
-				printk(KERN_ERR "%s%d: Failed to set IRQ affinity for cpu %d\n",
-					    dev->name, dev->id, cpu);
-			}
-			cpu = cpumask_next(cpu, cpu_online_mask);
 		}
 	} else {
 		dev->aac_msix[0].vector_no = 0;
@@ -2096,16 +2088,9 @@ void aac_free_irq(struct aac_dev *dev)
 	    dev->pdev->device == PMC_DEVICE_S8 ||
 	    dev->pdev->device == PMC_DEVICE_S9) {
 		if (dev->max_msix > 1) {
-			for (i = 0; i < dev->max_msix; i++) {
-				if (irq_set_affinity_hint(
-					dev->msixentry[i].vector, NULL)) {
-					printk(KERN_ERR "%s%d: Failed to reset IRQ affinity for cpu %d\n",
-					    dev->name, dev->id, cpu);
-				}
-				cpu = cpumask_next(cpu, cpu_online_mask);
-				free_irq(dev->msixentry[i].vector,
-						&(dev->aac_msix[i]));
-			}
+			for (i = 0; i < dev->max_msix; i++)
+				free_irq(pci_irq_vector(dev->pdev, i),
+					 &(dev->aac_msix[i]));
 		} else {
 			free_irq(dev->pdev->irq, &(dev->aac_msix[0]));
 		}
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 79871f3519ff..3ecbf20ca29f 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -160,7 +160,6 @@ static const struct pci_device_id aac_pci_tbl[] = {
 	{ 0x9005, 0x028b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 62 }, /* Adaptec PMC Series 6 (Tupelo) */
 	{ 0x9005, 0x028c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 63 }, /* Adaptec PMC Series 7 (Denali) */
 	{ 0x9005, 0x028d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 64 }, /* Adaptec PMC Series 8 */
-	{ 0x9005, 0x028f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 65 }, /* Adaptec PMC Series 9 */
 	{ 0,}
 };
 MODULE_DEVICE_TABLE(pci, aac_pci_tbl);
@@ -239,7 +238,6 @@ static struct aac_driver_ident aac_drivers[] = {
 	{ aac_src_init, "aacraid", "ADAPTEC ", "RAID            ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 6 (Tupelo) */
 	{ aac_srcv_init, "aacraid", "ADAPTEC ", "RAID            ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 7 (Denali) */
 	{ aac_srcv_init, "aacraid", "ADAPTEC ", "RAID            ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 8 */
-	{ aac_srcv_init, "aacraid", "ADAPTEC ", "RAID            ", 2, AAC_QUIRK_SRC } /* Adaptec PMC Series 9 */
 };
 
 /**
@@ -1071,7 +1069,6 @@ static struct scsi_host_template aac_driver_template = {
 static void __aac_shutdown(struct aac_dev * aac)
 {
 	int i;
-	int cpu;
 
 	aac_send_shutdown(aac);
 
@@ -1087,24 +1084,13 @@ static void __aac_shutdown(struct aac_dev * aac)
 		kthread_stop(aac->thread);
 	}
 	aac_adapter_disable_int(aac);
-	cpu = cpumask_first(cpu_online_mask);
 	if (aac->pdev->device == PMC_DEVICE_S6 ||
 	    aac->pdev->device == PMC_DEVICE_S7 ||
 	    aac->pdev->device == PMC_DEVICE_S8 ||
 	    aac->pdev->device == PMC_DEVICE_S9) {
 		if (aac->max_msix > 1) {
 			for (i = 0; i < aac->max_msix; i++) {
-				if (irq_set_affinity_hint(
-				    aac->msixentry[i].vector,
-				    NULL)) {
-					printk(KERN_ERR "%s%d: Failed to reset IRQ affinity for cpu %d\n",
-						aac->name,
-						aac->id,
-						cpu);
-				}
-				cpu = cpumask_next(cpu,
-						cpu_online_mask);
-				free_irq(aac->msixentry[i].vector,
+				free_irq(pci_irq_vector(aac->pdev, i),
 					 &(aac->aac_msix[i]));
 			}
 		} else {
@@ -1350,7 +1336,7 @@ static void aac_release_resources(struct aac_dev *aac)
 	    aac->pdev->device == PMC_DEVICE_S9) {
 		if (aac->max_msix > 1) {
 			for (i = 0; i < aac->max_msix; i++)
-				free_irq(aac->msixentry[i].vector,
+				free_irq(pci_irq_vector(aac->pdev, i),
 					&(aac->aac_msix[i]));
 		} else {
 			free_irq(aac->pdev->irq, &(aac->aac_msix[0]));
@@ -1396,13 +1382,13 @@ static int aac_acquire_resources(struct aac_dev *dev)
 			dev->aac_msix[i].vector_no = i;
 			dev->aac_msix[i].dev = dev;
 
-			if (request_irq(dev->msixentry[i].vector,
+			if (request_irq(pci_irq_vector(dev->pdev, i),
 					dev->a_ops.adapter_intr,
 					0, "aacraid", &(dev->aac_msix[i]))) {
 				printk(KERN_ERR "%s%d: Failed to register IRQ for vector %d.\n",
 						name, instance, i);
 				for (j = 0 ; j < i ; j++)
-					free_irq(dev->msixentry[j].vector,
+					free_irq(pci_irq_vector(dev->pdev, j),
 						 &(dev->aac_msix[j]));
 				pci_disable_msix(dev->pdev);
 				goto error_iounmap;
diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
index febbd83e2ecd..81dd0927246b 100644
--- a/drivers/scsi/advansys.c
+++ b/drivers/scsi/advansys.c
@@ -11030,6 +11030,9 @@ static int advansys_board_found(struct Scsi_Host *shost, unsigned int iop,
 		ASC_DBG(2, "AdvInitGetConfig()\n");
 
 		ret = AdvInitGetConfig(pdev, shost) ? -ENODEV : 0;
+#else
+		share_irq = 0;
+		ret = -ENODEV;
 #endif /* CONFIG_PCI */
 	}
 
diff --git a/drivers/scsi/aic7xxx/aicasm/aicasm.c b/drivers/scsi/aic7xxx/aicasm/aicasm.c
index 2e3117aa382f..21ac265280bf 100644
--- a/drivers/scsi/aic7xxx/aicasm/aicasm.c
+++ b/drivers/scsi/aic7xxx/aicasm/aicasm.c
@@ -254,7 +254,7 @@ main(int argc, char *argv[])
 	argv += optind;
 
 	if (argc != 1) {
-		fprintf(stderr, "%s: No input file specifiled\n", appname);
+		fprintf(stderr, "%s: No input file specified\n", appname);
 		usage();
 		/* NOTREACHED */
 	}
diff --git a/drivers/scsi/aic94xx/aic94xx_hwi.c b/drivers/scsi/aic94xx/aic94xx_hwi.c
index 7c713f797535..f2671a8fa7e3 100644
--- a/drivers/scsi/aic94xx/aic94xx_hwi.c
+++ b/drivers/scsi/aic94xx/aic94xx_hwi.c
@@ -228,8 +228,11 @@ static int asd_init_scbs(struct asd_ha_struct *asd_ha)
 	bitmap_bytes = (asd_ha->seq.tc_index_bitmap_bits+7)/8;
 	bitmap_bytes = BITS_TO_LONGS(bitmap_bytes*8)*sizeof(unsigned long);
 	asd_ha->seq.tc_index_bitmap = kzalloc(bitmap_bytes, GFP_KERNEL);
-	if (!asd_ha->seq.tc_index_bitmap)
+	if (!asd_ha->seq.tc_index_bitmap) {
+		kfree(asd_ha->seq.tc_index_array);
+		asd_ha->seq.tc_index_array = NULL;
 		return -ENOMEM;
+	}
 
 	spin_lock_init(&seq->tc_index_lock);
 
diff --git a/drivers/scsi/arcmsr/arcmsr.h b/drivers/scsi/arcmsr/arcmsr.h
index cf99f8cf4cdd..a254b32eba39 100644
--- a/drivers/scsi/arcmsr/arcmsr.h
+++ b/drivers/scsi/arcmsr/arcmsr.h
@@ -629,7 +629,6 @@ struct AdapterControlBlock
 	struct pci_dev *		pdev;
 	struct Scsi_Host *		host;
 	unsigned long			vir2phy_offset;
-	struct msix_entry	entries[ARCMST_NUM_MSIX_VECTORS];
 	/* Offset is used in making arc cdb physical to virtual calculations */
 	uint32_t			outbound_int_enable;
 	uint32_t			cdb_phyaddr_hi32;
@@ -671,8 +670,6 @@ struct AdapterControlBlock
 	/* iop init */
 	#define ACB_F_ABORT				0x0200
 	#define ACB_F_FIRMWARE_TRAP           		0x0400
-	#define ACB_F_MSI_ENABLED		0x1000
-	#define ACB_F_MSIX_ENABLED		0x2000
 	struct CommandControlBlock *			pccb_pool[ARCMSR_MAX_FREECCB_NUM];
 	/* used for memory free */
 	struct list_head		ccb_free_list;
@@ -725,7 +722,7 @@ struct AdapterControlBlock
 	atomic_t 			rq_map_token;
 	atomic_t			ante_token_value;
 	uint32_t	maxOutstanding;
-	int		msix_vector_count;
+	int		vector_count;
 };/* HW_DEVICE_EXTENSION */
 /*
 *******************************************************************************
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index f0cfb0451757..af032c46ec0e 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -61,7 +61,7 @@
 #include <linux/circ_buf.h>
 #include <asm/dma.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -720,51 +720,39 @@ static void arcmsr_message_isr_bh_fn(struct work_struct *work)
 static int
 arcmsr_request_irq(struct pci_dev *pdev, struct AdapterControlBlock *acb)
 {
-	int	i, j, r;
-	struct msix_entry entries[ARCMST_NUM_MSIX_VECTORS];
-
-	for (i = 0; i < ARCMST_NUM_MSIX_VECTORS; i++)
-		entries[i].entry = i;
-	r = pci_enable_msix_range(pdev, entries, 1, ARCMST_NUM_MSIX_VECTORS);
-	if (r < 0)
-		goto msi_int;
-	acb->msix_vector_count = r;
-	for (i = 0; i < r; i++) {
-		if (request_irq(entries[i].vector,
-			arcmsr_do_interrupt, 0, "arcmsr", acb)) {
+	unsigned long flags;
+	int nvec, i;
+
+	nvec = pci_alloc_irq_vectors(pdev, 1, ARCMST_NUM_MSIX_VECTORS,
+			PCI_IRQ_MSIX);
+	if (nvec > 0) {
+		pr_info("arcmsr%d: msi-x enabled\n", acb->host->host_no);
+		flags = 0;
+	} else {
+		nvec = pci_alloc_irq_vectors(pdev, 1, 1,
+				PCI_IRQ_MSI | PCI_IRQ_LEGACY);
+		if (nvec < 1)
+			return FAILED;
+
+		flags = IRQF_SHARED;
+	}
+
+	acb->vector_count = nvec;
+	for (i = 0; i < nvec; i++) {
+		if (request_irq(pci_irq_vector(pdev, i), arcmsr_do_interrupt,
+				flags, "arcmsr", acb)) {
 			pr_warn("arcmsr%d: request_irq =%d failed!\n",
-				acb->host->host_no, entries[i].vector);
-			for (j = 0 ; j < i ; j++)
-				free_irq(entries[j].vector, acb);
-			pci_disable_msix(pdev);
-			goto msi_int;
+				acb->host->host_no, pci_irq_vector(pdev, i));
+			goto out_free_irq;
 		}
-		acb->entries[i] = entries[i];
-	}
-	acb->acb_flags |= ACB_F_MSIX_ENABLED;
-	pr_info("arcmsr%d: msi-x enabled\n", acb->host->host_no);
-	return SUCCESS;
-msi_int:
-	if (pci_enable_msi_exact(pdev, 1) < 0)
-		goto legacy_int;
-	if (request_irq(pdev->irq, arcmsr_do_interrupt,
-		IRQF_SHARED, "arcmsr", acb)) {
-		pr_warn("arcmsr%d: request_irq =%d failed!\n",
-			acb->host->host_no, pdev->irq);
-		pci_disable_msi(pdev);
-		goto legacy_int;
-	}
-	acb->acb_flags |= ACB_F_MSI_ENABLED;
-	pr_info("arcmsr%d: msi enabled\n", acb->host->host_no);
-	return SUCCESS;
-legacy_int:
-	if (request_irq(pdev->irq, arcmsr_do_interrupt,
-		IRQF_SHARED, "arcmsr", acb)) {
-		pr_warn("arcmsr%d: request_irq = %d failed!\n",
-			acb->host->host_no, pdev->irq);
-		return FAILED;
 	}
+
 	return SUCCESS;
+out_free_irq:
+	while (--i >= 0)
+		free_irq(pci_irq_vector(pdev, i), acb);
+	pci_free_irq_vectors(pdev);
+	return FAILED;
 }
 
 static int arcmsr_probe(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -886,15 +874,9 @@ static void arcmsr_free_irq(struct pci_dev *pdev,
 {
 	int i;
 
-	if (acb->acb_flags & ACB_F_MSI_ENABLED) {
-		free_irq(pdev->irq, acb);
-		pci_disable_msi(pdev);
-	} else if (acb->acb_flags & ACB_F_MSIX_ENABLED) {
-		for (i = 0; i < acb->msix_vector_count; i++)
-			free_irq(acb->entries[i].vector, acb);
-		pci_disable_msix(pdev);
-	} else
-		free_irq(pdev->irq, acb);
+	for (i = 0; i < acb->vector_count; i++)
+		free_irq(pci_irq_vector(pdev, i), acb);
+	pci_free_irq_vectors(pdev);
 }
 
 static int arcmsr_suspend(struct pci_dev *pdev, pm_message_t state)
diff --git a/drivers/scsi/arm/cumana_1.c b/drivers/scsi/arm/cumana_1.c
index 8e9cfe8f22f5..a87b99c7fb9a 100644
--- a/drivers/scsi/arm/cumana_1.c
+++ b/drivers/scsi/arm/cumana_1.c
@@ -14,49 +14,48 @@
 #include <scsi/scsi_host.h>
 
 #define priv(host)			((struct NCR5380_hostdata *)(host)->hostdata)
-#define NCR5380_read(reg)		cumanascsi_read(instance, reg)
-#define NCR5380_write(reg, value)	cumanascsi_write(instance, reg, value)
+#define NCR5380_read(reg)		cumanascsi_read(hostdata, reg)
+#define NCR5380_write(reg, value)	cumanascsi_write(hostdata, reg, value)
 
-#define NCR5380_dma_xfer_len(instance, cmd, phase)	(cmd->transfersize)
+#define NCR5380_dma_xfer_len		cumanascsi_dma_xfer_len
 #define NCR5380_dma_recv_setup		cumanascsi_pread
 #define NCR5380_dma_send_setup		cumanascsi_pwrite
-#define NCR5380_dma_residual(instance)	(0)
+#define NCR5380_dma_residual		NCR5380_dma_residual_none
 
 #define NCR5380_intr			cumanascsi_intr
 #define NCR5380_queue_command		cumanascsi_queue_command
 #define NCR5380_info			cumanascsi_info
 
 #define NCR5380_implementation_fields	\
-	unsigned ctrl;			\
-	void __iomem *base;		\
-	void __iomem *dma
+	unsigned ctrl
 
-#include "../NCR5380.h"
+struct NCR5380_hostdata;
+static u8 cumanascsi_read(struct NCR5380_hostdata *, unsigned int);
+static void cumanascsi_write(struct NCR5380_hostdata *, unsigned int, u8);
 
-void cumanascsi_setup(char *str, int *ints)
-{
-}
+#include "../NCR5380.h"
 
 #define CTRL	0x16fc
 #define STAT	0x2004
 #define L(v)	(((v)<<16)|((v) & 0x0000ffff))
 #define H(v)	(((v)>>16)|((v) & 0xffff0000))
 
-static inline int cumanascsi_pwrite(struct Scsi_Host *host,
+static inline int cumanascsi_pwrite(struct NCR5380_hostdata *hostdata,
                                     unsigned char *addr, int len)
 {
   unsigned long *laddr;
-  void __iomem *dma = priv(host)->dma + 0x2000;
+  u8 __iomem *base = hostdata->io;
+  u8 __iomem *dma = hostdata->pdma_io + 0x2000;
 
   if(!len) return 0;
 
-  writeb(0x02, priv(host)->base + CTRL);
+  writeb(0x02, base + CTRL);
   laddr = (unsigned long *)addr;
   while(len >= 32)
   {
     unsigned int status;
     unsigned long v;
-    status = readb(priv(host)->base + STAT);
+    status = readb(base + STAT);
     if(status & 0x80)
       goto end;
     if(!(status & 0x40))
@@ -75,12 +74,12 @@ static inline int cumanascsi_pwrite(struct Scsi_Host *host,
   }
 
   addr = (unsigned char *)laddr;
-  writeb(0x12, priv(host)->base + CTRL);
+  writeb(0x12, base + CTRL);
 
   while(len > 0)
   {
     unsigned int status;
-    status = readb(priv(host)->base + STAT);
+    status = readb(base + STAT);
     if(status & 0x80)
       goto end;
     if(status & 0x40)
@@ -90,7 +89,7 @@ static inline int cumanascsi_pwrite(struct Scsi_Host *host,
         break;
     }
 
-    status = readb(priv(host)->base + STAT);
+    status = readb(base + STAT);
     if(status & 0x80)
       goto end;
     if(status & 0x40)
@@ -101,27 +100,28 @@ static inline int cumanascsi_pwrite(struct Scsi_Host *host,
     }
   }
 end:
-  writeb(priv(host)->ctrl | 0x40, priv(host)->base + CTRL);
+  writeb(hostdata->ctrl | 0x40, base + CTRL);
 
 	if (len)
 		return -1;
 	return 0;
 }
 
-static inline int cumanascsi_pread(struct Scsi_Host *host,
+static inline int cumanascsi_pread(struct NCR5380_hostdata *hostdata,
                                    unsigned char *addr, int len)
 {
   unsigned long *laddr;
-  void __iomem *dma = priv(host)->dma + 0x2000;
+  u8 __iomem *base = hostdata->io;
+  u8 __iomem *dma = hostdata->pdma_io + 0x2000;
 
   if(!len) return 0;
 
-  writeb(0x00, priv(host)->base + CTRL);
+  writeb(0x00, base + CTRL);
   laddr = (unsigned long *)addr;
   while(len >= 32)
   {
     unsigned int status;
-    status = readb(priv(host)->base + STAT);
+    status = readb(base + STAT);
     if(status & 0x80)
       goto end;
     if(!(status & 0x40))
@@ -140,12 +140,12 @@ static inline int cumanascsi_pread(struct Scsi_Host *host,
   }
 
   addr = (unsigned char *)laddr;
-  writeb(0x10, priv(host)->base + CTRL);
+  writeb(0x10, base + CTRL);
 
   while(len > 0)
   {
     unsigned int status;
-    status = readb(priv(host)->base + STAT);
+    status = readb(base + STAT);
     if(status & 0x80)
       goto end;
     if(status & 0x40)
@@ -155,7 +155,7 @@ static inline int cumanascsi_pread(struct Scsi_Host *host,
         break;
     }
 
-    status = readb(priv(host)->base + STAT);
+    status = readb(base + STAT);
     if(status & 0x80)
       goto end;
     if(status & 0x40)
@@ -166,37 +166,45 @@ static inline int cumanascsi_pread(struct Scsi_Host *host,
     }
   }
 end:
-  writeb(priv(host)->ctrl | 0x40, priv(host)->base + CTRL);
+  writeb(hostdata->ctrl | 0x40, base + CTRL);
 
 	if (len)
 		return -1;
 	return 0;
 }
 
-static unsigned char cumanascsi_read(struct Scsi_Host *host, unsigned int reg)
+static int cumanascsi_dma_xfer_len(struct NCR5380_hostdata *hostdata,
+                                   struct scsi_cmnd *cmd)
+{
+	return cmd->transfersize;
+}
+
+static u8 cumanascsi_read(struct NCR5380_hostdata *hostdata,
+                          unsigned int reg)
 {
-	void __iomem *base = priv(host)->base;
-	unsigned char val;
+	u8 __iomem *base = hostdata->io;
+	u8 val;
 
 	writeb(0, base + CTRL);
 
 	val = readb(base + 0x2100 + (reg << 2));
 
-	priv(host)->ctrl = 0x40;
+	hostdata->ctrl = 0x40;
 	writeb(0x40, base + CTRL);
 
 	return val;
 }
 
-static void cumanascsi_write(struct Scsi_Host *host, unsigned int reg, unsigned int value)
+static void cumanascsi_write(struct NCR5380_hostdata *hostdata,
+                             unsigned int reg, u8 value)
 {
-	void __iomem *base = priv(host)->base;
+	u8 __iomem *base = hostdata->io;
 
 	writeb(0, base + CTRL);
 
 	writeb(value, base + 0x2100 + (reg << 2));
 
-	priv(host)->ctrl = 0x40;
+	hostdata->ctrl = 0x40;
 	writeb(0x40, base + CTRL);
 }
 
@@ -235,11 +243,11 @@ static int cumanascsi1_probe(struct expansion_card *ec,
 		goto out_release;
 	}
 
-	priv(host)->base = ioremap(ecard_resource_start(ec, ECARD_RES_IOCSLOW),
-				   ecard_resource_len(ec, ECARD_RES_IOCSLOW));
-	priv(host)->dma = ioremap(ecard_resource_start(ec, ECARD_RES_MEMC),
-				  ecard_resource_len(ec, ECARD_RES_MEMC));
-	if (!priv(host)->base || !priv(host)->dma) {
+	priv(host)->io = ioremap(ecard_resource_start(ec, ECARD_RES_IOCSLOW),
+	                         ecard_resource_len(ec, ECARD_RES_IOCSLOW));
+	priv(host)->pdma_io = ioremap(ecard_resource_start(ec, ECARD_RES_MEMC),
+	                              ecard_resource_len(ec, ECARD_RES_MEMC));
+	if (!priv(host)->io || !priv(host)->pdma_io) {
 		ret = -ENOMEM;
 		goto out_unmap;
 	}
@@ -253,7 +261,7 @@ static int cumanascsi1_probe(struct expansion_card *ec,
 	NCR5380_maybe_reset_bus(host);
 
         priv(host)->ctrl = 0;
-        writeb(0, priv(host)->base + CTRL);
+        writeb(0, priv(host)->io + CTRL);
 
 	ret = request_irq(host->irq, cumanascsi_intr, 0,
 			  "CumanaSCSI-1", host);
@@ -275,8 +283,8 @@ static int cumanascsi1_probe(struct expansion_card *ec,
  out_exit:
 	NCR5380_exit(host);
  out_unmap:
-	iounmap(priv(host)->base);
-	iounmap(priv(host)->dma);
+	iounmap(priv(host)->io);
+	iounmap(priv(host)->pdma_io);
 	scsi_host_put(host);
  out_release:
 	ecard_release_resources(ec);
@@ -287,15 +295,17 @@ static int cumanascsi1_probe(struct expansion_card *ec,
 static void cumanascsi1_remove(struct expansion_card *ec)
 {
 	struct Scsi_Host *host = ecard_get_drvdata(ec);
+	void __iomem *base = priv(host)->io;
+	void __iomem *dma = priv(host)->pdma_io;
 
 	ecard_set_drvdata(ec, NULL);
 
 	scsi_remove_host(host);
 	free_irq(host->irq, host);
 	NCR5380_exit(host);
-	iounmap(priv(host)->base);
-	iounmap(priv(host)->dma);
 	scsi_host_put(host);
+	iounmap(base);
+	iounmap(dma);
 	ecard_release_resources(ec);
 }
 
diff --git a/drivers/scsi/arm/oak.c b/drivers/scsi/arm/oak.c
index a396024a3cae..6be6666534d4 100644
--- a/drivers/scsi/arm/oak.c
+++ b/drivers/scsi/arm/oak.c
@@ -16,21 +16,18 @@
 
 #define priv(host)			((struct NCR5380_hostdata *)(host)->hostdata)
 
-#define NCR5380_read(reg) \
-	readb(priv(instance)->base + ((reg) << 2))
-#define NCR5380_write(reg, value) \
-	writeb(value, priv(instance)->base + ((reg) << 2))
+#define NCR5380_read(reg)           readb(hostdata->io + ((reg) << 2))
+#define NCR5380_write(reg, value)   writeb(value, hostdata->io + ((reg) << 2))
 
-#define NCR5380_dma_xfer_len(instance, cmd, phase)	(0)
+#define NCR5380_dma_xfer_len		NCR5380_dma_xfer_none
 #define NCR5380_dma_recv_setup		oakscsi_pread
 #define NCR5380_dma_send_setup		oakscsi_pwrite
-#define NCR5380_dma_residual(instance)	(0)
+#define NCR5380_dma_residual		NCR5380_dma_residual_none
 
 #define NCR5380_queue_command		oakscsi_queue_command
 #define NCR5380_info			oakscsi_info
 
-#define NCR5380_implementation_fields	\
-	void __iomem *base
+#define NCR5380_implementation_fields	/* none */
 
 #include "../NCR5380.h"
 
@@ -40,10 +37,10 @@
 #define STAT	((128 + 16) << 2)
 #define DATA	((128 + 8) << 2)
 
-static inline int oakscsi_pwrite(struct Scsi_Host *instance,
+static inline int oakscsi_pwrite(struct NCR5380_hostdata *hostdata,
                                  unsigned char *addr, int len)
 {
-  void __iomem *base = priv(instance)->base;
+  u8 __iomem *base = hostdata->io;
 
 printk("writing %p len %d\n",addr, len);
 
@@ -55,10 +52,11 @@ printk("writing %p len %d\n",addr, len);
   return 0;
 }
 
-static inline int oakscsi_pread(struct Scsi_Host *instance,
+static inline int oakscsi_pread(struct NCR5380_hostdata *hostdata,
                                 unsigned char *addr, int len)
 {
-  void __iomem *base = priv(instance)->base;
+  u8 __iomem *base = hostdata->io;
+
 printk("reading %p len %d\n", addr, len);
   while(len > 0)
   {
@@ -133,15 +131,14 @@ static int oakscsi_probe(struct expansion_card *ec, const struct ecard_id *id)
 		goto release;
 	}
 
-	priv(host)->base = ioremap(ecard_resource_start(ec, ECARD_RES_MEMC),
-				   ecard_resource_len(ec, ECARD_RES_MEMC));
-	if (!priv(host)->base) {
+	priv(host)->io = ioremap(ecard_resource_start(ec, ECARD_RES_MEMC),
+	                         ecard_resource_len(ec, ECARD_RES_MEMC));
+	if (!priv(host)->io) {
 		ret = -ENOMEM;
 		goto unreg;
 	}
 
 	host->irq = NO_IRQ;
-	host->n_io_port = 255;
 
 	ret = NCR5380_init(host, FLAG_DMA_FIXUP | FLAG_LATE_DMA_SETUP);
 	if (ret)
@@ -159,7 +156,7 @@ static int oakscsi_probe(struct expansion_card *ec, const struct ecard_id *id)
  out_exit:
 	NCR5380_exit(host);
  out_unmap:
-	iounmap(priv(host)->base);
+	iounmap(priv(host)->io);
  unreg:
 	scsi_host_put(host);
  release:
@@ -171,13 +168,14 @@ static int oakscsi_probe(struct expansion_card *ec, const struct ecard_id *id)
 static void oakscsi_remove(struct expansion_card *ec)
 {
 	struct Scsi_Host *host = ecard_get_drvdata(ec);
+	void __iomem *base = priv(host)->io;
 
 	ecard_set_drvdata(ec, NULL);
 	scsi_remove_host(host);
 
 	NCR5380_exit(host);
-	iounmap(priv(host)->base);
 	scsi_host_put(host);
+	iounmap(base);
 	ecard_release_resources(ec);
 }
 
diff --git a/drivers/scsi/atari_scsi.c b/drivers/scsi/atari_scsi.c
index a59ad94ea52b..105b35393ce9 100644
--- a/drivers/scsi/atari_scsi.c
+++ b/drivers/scsi/atari_scsi.c
@@ -57,6 +57,9 @@
 
 #define NCR5380_implementation_fields   /* none */
 
+static u8 (*atari_scsi_reg_read)(unsigned int);
+static void (*atari_scsi_reg_write)(unsigned int, u8);
+
 #define NCR5380_read(reg)               atari_scsi_reg_read(reg)
 #define NCR5380_write(reg, value)       atari_scsi_reg_write(reg, value)
 
@@ -64,14 +67,10 @@
 #define NCR5380_abort                   atari_scsi_abort
 #define NCR5380_info                    atari_scsi_info
 
-#define NCR5380_dma_recv_setup(instance, data, count) \
-        atari_scsi_dma_setup(instance, data, count, 0)
-#define NCR5380_dma_send_setup(instance, data, count) \
-        atari_scsi_dma_setup(instance, data, count, 1)
-#define NCR5380_dma_residual(instance) \
-        atari_scsi_dma_residual(instance)
-#define NCR5380_dma_xfer_len(instance, cmd, phase) \
-        atari_dma_xfer_len(cmd->SCp.this_residual, cmd, !((phase) & SR_IO))
+#define NCR5380_dma_xfer_len            atari_scsi_dma_xfer_len
+#define NCR5380_dma_recv_setup          atari_scsi_dma_recv_setup
+#define NCR5380_dma_send_setup          atari_scsi_dma_send_setup
+#define NCR5380_dma_residual            atari_scsi_dma_residual
 
 #define NCR5380_acquire_dma_irq(instance)      falcon_get_lock(instance)
 #define NCR5380_release_dma_irq(instance)      falcon_release_lock()
@@ -126,9 +125,6 @@ static inline unsigned long SCSI_DMA_GETADR(void)
 
 static void atari_scsi_fetch_restbytes(void);
 
-static unsigned char (*atari_scsi_reg_read)(unsigned char reg);
-static void (*atari_scsi_reg_write)(unsigned char reg, unsigned char value);
-
 static unsigned long	atari_dma_residual, atari_dma_startaddr;
 static short		atari_dma_active;
 /* pointer to the dribble buffer */
@@ -457,15 +453,14 @@ static int __init atari_scsi_setup(char *str)
 __setup("atascsi=", atari_scsi_setup);
 #endif /* !MODULE */
 
-
-static unsigned long atari_scsi_dma_setup(struct Scsi_Host *instance,
+static unsigned long atari_scsi_dma_setup(struct NCR5380_hostdata *hostdata,
 					  void *data, unsigned long count,
 					  int dir)
 {
 	unsigned long addr = virt_to_phys(data);
 
-	dprintk(NDEBUG_DMA, "scsi%d: setting up dma, data = %p, phys = %lx, count = %ld, "
-		   "dir = %d\n", instance->host_no, data, addr, count, dir);
+	dprintk(NDEBUG_DMA, "scsi%d: setting up dma, data = %p, phys = %lx, count = %ld, dir = %d\n",
+	        hostdata->host->host_no, data, addr, count, dir);
 
 	if (!IS_A_TT() && !STRAM_ADDR(addr)) {
 		/* If we have a non-DMAable address on a Falcon, use the dribble
@@ -522,8 +517,19 @@ static unsigned long atari_scsi_dma_setup(struct Scsi_Host *instance,
 	return count;
 }
 
+static inline int atari_scsi_dma_recv_setup(struct NCR5380_hostdata *hostdata,
+                                            unsigned char *data, int count)
+{
+	return atari_scsi_dma_setup(hostdata, data, count, 0);
+}
+
+static inline int atari_scsi_dma_send_setup(struct NCR5380_hostdata *hostdata,
+                                            unsigned char *data, int count)
+{
+	return atari_scsi_dma_setup(hostdata, data, count, 1);
+}
 
-static long atari_scsi_dma_residual(struct Scsi_Host *instance)
+static int atari_scsi_dma_residual(struct NCR5380_hostdata *hostdata)
 {
 	return atari_dma_residual;
 }
@@ -564,10 +570,11 @@ static int falcon_classify_cmd(struct scsi_cmnd *cmd)
  * the overrun problem, so this question is academic :-)
  */
 
-static unsigned long atari_dma_xfer_len(unsigned long wanted_len,
-					struct scsi_cmnd *cmd, int write_flag)
+static int atari_scsi_dma_xfer_len(struct NCR5380_hostdata *hostdata,
+                                   struct scsi_cmnd *cmd)
 {
-	unsigned long	possible_len, limit;
+	int wanted_len = cmd->SCp.this_residual;
+	int possible_len, limit;
 
 	if (wanted_len < DMA_MIN_SIZE)
 		return 0;
@@ -604,7 +611,7 @@ static unsigned long atari_dma_xfer_len(unsigned long wanted_len,
 	 * use the dribble buffer and thus can do only STRAM_BUFFER_SIZE bytes.
 	 */
 
-	if (write_flag) {
+	if (cmd->sc_data_direction == DMA_TO_DEVICE) {
 		/* Write operation can always use the DMA, but the transfer size must
 		 * be rounded up to the next multiple of 512 (atari_dma_setup() does
 		 * this).
@@ -644,8 +651,8 @@ static unsigned long atari_dma_xfer_len(unsigned long wanted_len,
 		possible_len = limit;
 
 	if (possible_len != wanted_len)
-		dprintk(NDEBUG_DMA, "Sorry, must cut DMA transfer size to %ld bytes "
-			   "instead of %ld\n", possible_len, wanted_len);
+		dprintk(NDEBUG_DMA, "DMA transfer now %d bytes instead of %d\n",
+		        possible_len, wanted_len);
 
 	return possible_len;
 }
@@ -658,26 +665,38 @@ static unsigned long atari_dma_xfer_len(unsigned long wanted_len,
  * NCR5380_write call these functions via function pointers.
  */
 
-static unsigned char atari_scsi_tt_reg_read(unsigned char reg)
+static u8 atari_scsi_tt_reg_read(unsigned int reg)
 {
 	return tt_scsi_regp[reg * 2];
 }
 
-static void atari_scsi_tt_reg_write(unsigned char reg, unsigned char value)
+static void atari_scsi_tt_reg_write(unsigned int reg, u8 value)
 {
 	tt_scsi_regp[reg * 2] = value;
 }
 
-static unsigned char atari_scsi_falcon_reg_read(unsigned char reg)
+static u8 atari_scsi_falcon_reg_read(unsigned int reg)
 {
-	dma_wd.dma_mode_status= (u_short)(0x88 + reg);
-	return (u_char)dma_wd.fdc_acces_seccount;
+	unsigned long flags;
+	u8 result;
+
+	reg += 0x88;
+	local_irq_save(flags);
+	dma_wd.dma_mode_status = (u_short)reg;
+	result = (u8)dma_wd.fdc_acces_seccount;
+	local_irq_restore(flags);
+	return result;
 }
 
-static void atari_scsi_falcon_reg_write(unsigned char reg, unsigned char value)
+static void atari_scsi_falcon_reg_write(unsigned int reg, u8 value)
 {
-	dma_wd.dma_mode_status = (u_short)(0x88 + reg);
+	unsigned long flags;
+
+	reg += 0x88;
+	local_irq_save(flags);
+	dma_wd.dma_mode_status = (u_short)reg;
 	dma_wd.fdc_acces_seccount = (u_short)value;
+	local_irq_restore(flags);
 }
 
 
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index d9239c2d49b1..b5112d6d7e73 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -3049,8 +3049,10 @@ static int beiscsi_create_eqs(struct beiscsi_hba *phba,
 		eq_vaddress = pci_alloc_consistent(phba->pcidev,
 						   num_eq_pages * PAGE_SIZE,
 						   &paddr);
-		if (!eq_vaddress)
+		if (!eq_vaddress) {
+			ret = -ENOMEM;
 			goto create_eq_error;
+		}
 
 		mem->va = eq_vaddress;
 		ret = be_fill_queue(eq, phba->params.num_eq_entries,
@@ -3113,8 +3115,10 @@ static int beiscsi_create_cqs(struct beiscsi_hba *phba,
 		cq_vaddress = pci_alloc_consistent(phba->pcidev,
 						   num_cq_pages * PAGE_SIZE,
 						   &paddr);
-		if (!cq_vaddress)
+		if (!cq_vaddress) {
+			ret = -ENOMEM;
 			goto create_cq_error;
+		}
 
 		ret = be_fill_queue(cq, phba->params.num_cq_entries,
 				    sizeof(struct sol_cqe), cq_vaddress);
diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c
index aebc4ddb3060..ac05317bba7f 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.c
+++ b/drivers/scsi/be2iscsi/be_mgmt.c
@@ -1083,7 +1083,7 @@ unsigned int beiscsi_boot_get_sinfo(struct beiscsi_hba *phba)
 	nonemb_cmd = &phba->boot_struct.nonemb_cmd;
 	nonemb_cmd->size = sizeof(*resp);
 	nonemb_cmd->va = pci_alloc_consistent(phba->ctrl.pdev,
-					      sizeof(nonemb_cmd->size),
+					      nonemb_cmd->size,
 					      &nonemb_cmd->dma);
 	if (!nonemb_cmd->va) {
 		mutex_unlock(&ctrl->mbox_lock);
diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h
index 713745da44c6..0f9fab770339 100644
--- a/drivers/scsi/bfa/bfa_ioc.h
+++ b/drivers/scsi/bfa/bfa_ioc.h
@@ -111,20 +111,24 @@ struct bfa_meminfo_s {
 	struct bfa_mem_kva_s kva_info;
 };
 
-/* BFA memory segment setup macros */
-#define bfa_mem_dma_setup(_meminfo, _dm_ptr, _seg_sz) do {	\
-	((bfa_mem_dma_t *)(_dm_ptr))->mem_len = (_seg_sz);	\
-	if (_seg_sz)						\
-		list_add_tail(&((bfa_mem_dma_t *)_dm_ptr)->qe,	\
-			      &(_meminfo)->dma_info.qe);	\
-} while (0)
+/* BFA memory segment setup helpers */
+static inline void bfa_mem_dma_setup(struct bfa_meminfo_s *meminfo,
+				     struct bfa_mem_dma_s *dm_ptr,
+				     size_t seg_sz)
+{
+	dm_ptr->mem_len = seg_sz;
+	if (seg_sz)
+		list_add_tail(&dm_ptr->qe, &meminfo->dma_info.qe);
+}
 
-#define bfa_mem_kva_setup(_meminfo, _kva_ptr, _seg_sz) do {	\
-	((bfa_mem_kva_t *)(_kva_ptr))->mem_len = (_seg_sz);	\
-	if (_seg_sz)						\
-		list_add_tail(&((bfa_mem_kva_t *)_kva_ptr)->qe,	\
-			      &(_meminfo)->kva_info.qe);	\
-} while (0)
+static inline void bfa_mem_kva_setup(struct bfa_meminfo_s *meminfo,
+				     struct bfa_mem_kva_s *kva_ptr,
+				     size_t seg_sz)
+{
+	kva_ptr->mem_len = seg_sz;
+	if (seg_sz)
+		list_add_tail(&kva_ptr->qe, &meminfo->kva_info.qe);
+}
 
 /* BFA dma memory segments iterator */
 #define bfa_mem_dma_sptr(_mod, _i)	(&(_mod)->dma_seg[(_i)])
diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c
index 9d253cb83ee7..d9e15210b110 100644
--- a/drivers/scsi/bfa/bfad.c
+++ b/drivers/scsi/bfa/bfad.c
@@ -27,7 +27,7 @@
 #include <linux/fs.h>
 #include <linux/pci.h>
 #include <linux/firmware.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/fcntl.h>
 
 #include "bfad_drv.h"
diff --git a/drivers/scsi/bfa/bfad_bsg.c b/drivers/scsi/bfa/bfad_bsg.c
index d1ad0208dfe7..a9a00169ad91 100644
--- a/drivers/scsi/bfa/bfad_bsg.c
+++ b/drivers/scsi/bfa/bfad_bsg.c
@@ -3130,11 +3130,12 @@ bfad_iocmd_handler(struct bfad_s *bfad, unsigned int cmd, void *iocmd,
 }
 
 static int
-bfad_im_bsg_vendor_request(struct fc_bsg_job *job)
+bfad_im_bsg_vendor_request(struct bsg_job *job)
 {
-	uint32_t vendor_cmd = job->request->rqst_data.h_vendor.vendor_cmd[0];
-	struct bfad_im_port_s *im_port =
-			(struct bfad_im_port_s *) job->shost->hostdata[0];
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
+	uint32_t vendor_cmd = bsg_request->rqst_data.h_vendor.vendor_cmd[0];
+	struct bfad_im_port_s *im_port = shost_priv(fc_bsg_to_shost(job));
 	struct bfad_s *bfad = im_port->bfad;
 	struct request_queue *request_q = job->req->q;
 	void *payload_kbuf;
@@ -3175,18 +3176,19 @@ bfad_im_bsg_vendor_request(struct fc_bsg_job *job)
 
 	/* Fill the BSG job reply data */
 	job->reply_len = job->reply_payload.payload_len;
-	job->reply->reply_payload_rcv_len = job->reply_payload.payload_len;
-	job->reply->result = rc;
+	bsg_reply->reply_payload_rcv_len = job->reply_payload.payload_len;
+	bsg_reply->result = rc;
 
-	job->job_done(job);
+	bsg_job_done(job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	return rc;
 error:
 	/* free the command buffer */
 	kfree(payload_kbuf);
 out:
-	job->reply->result = rc;
+	bsg_reply->result = rc;
 	job->reply_len = sizeof(uint32_t);
-	job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 	return rc;
 }
 
@@ -3312,7 +3314,7 @@ bfad_fcxp_free_mem(struct bfad_s *bfad, struct bfad_buf_info *buf_base,
 }
 
 int
-bfad_fcxp_bsg_send(struct fc_bsg_job *job, struct bfad_fcxp *drv_fcxp,
+bfad_fcxp_bsg_send(struct bsg_job *job, struct bfad_fcxp *drv_fcxp,
 		   bfa_bsg_fcpt_t *bsg_fcpt)
 {
 	struct bfa_fcxp_s *hal_fcxp;
@@ -3352,28 +3354,29 @@ bfad_fcxp_bsg_send(struct fc_bsg_job *job, struct bfad_fcxp *drv_fcxp,
 }
 
 int
-bfad_im_bsg_els_ct_request(struct fc_bsg_job *job)
+bfad_im_bsg_els_ct_request(struct bsg_job *job)
 {
 	struct bfa_bsg_data *bsg_data;
-	struct bfad_im_port_s *im_port =
-			(struct bfad_im_port_s *) job->shost->hostdata[0];
+	struct bfad_im_port_s *im_port = shost_priv(fc_bsg_to_shost(job));
 	struct bfad_s *bfad = im_port->bfad;
 	bfa_bsg_fcpt_t *bsg_fcpt;
 	struct bfad_fcxp    *drv_fcxp;
 	struct bfa_fcs_lport_s *fcs_port;
 	struct bfa_fcs_rport_s *fcs_rport;
-	uint32_t command_type = job->request->msgcode;
+	struct fc_bsg_request *bsg_request = bsg_request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
+	uint32_t command_type = bsg_request->msgcode;
 	unsigned long flags;
 	struct bfad_buf_info *rsp_buf_info;
 	void *req_kbuf = NULL, *rsp_kbuf = NULL;
 	int rc = -EINVAL;
 
 	job->reply_len  = sizeof(uint32_t);	/* Atleast uint32_t reply_len */
-	job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 
 	/* Get the payload passed in from userspace */
-	bsg_data = (struct bfa_bsg_data *) (((char *)job->request) +
-					sizeof(struct fc_bsg_request));
+	bsg_data = (struct bfa_bsg_data *) (((char *)bsg_request) +
+					    sizeof(struct fc_bsg_request));
 	if (bsg_data == NULL)
 		goto out;
 
@@ -3517,13 +3520,13 @@ bfad_im_bsg_els_ct_request(struct fc_bsg_job *job)
 	/* fill the job->reply data */
 	if (drv_fcxp->req_status == BFA_STATUS_OK) {
 		job->reply_len = drv_fcxp->rsp_len;
-		job->reply->reply_payload_rcv_len = drv_fcxp->rsp_len;
-		job->reply->reply_data.ctels_reply.status = FC_CTELS_STATUS_OK;
+		bsg_reply->reply_payload_rcv_len = drv_fcxp->rsp_len;
+		bsg_reply->reply_data.ctels_reply.status = FC_CTELS_STATUS_OK;
 	} else {
-		job->reply->reply_payload_rcv_len =
+		bsg_reply->reply_payload_rcv_len =
 					sizeof(struct fc_bsg_ctels_reply);
 		job->reply_len = sizeof(uint32_t);
-		job->reply->reply_data.ctels_reply.status =
+		bsg_reply->reply_data.ctels_reply.status =
 						FC_CTELS_STATUS_REJECT;
 	}
 
@@ -3549,20 +3552,23 @@ out_free_mem:
 	kfree(bsg_fcpt);
 	kfree(drv_fcxp);
 out:
-	job->reply->result = rc;
+	bsg_reply->result = rc;
 
 	if (rc == BFA_STATUS_OK)
-		job->job_done(job);
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 
 	return rc;
 }
 
 int
-bfad_im_bsg_request(struct fc_bsg_job *job)
+bfad_im_bsg_request(struct bsg_job *job)
 {
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	uint32_t rc = BFA_STATUS_OK;
 
-	switch (job->request->msgcode) {
+	switch (bsg_request->msgcode) {
 	case FC_BSG_HST_VENDOR:
 		/* Process BSG HST Vendor requests */
 		rc = bfad_im_bsg_vendor_request(job);
@@ -3575,8 +3581,8 @@ bfad_im_bsg_request(struct fc_bsg_job *job)
 		rc = bfad_im_bsg_els_ct_request(job);
 		break;
 	default:
-		job->reply->result = rc = -EINVAL;
-		job->reply->reply_payload_rcv_len = 0;
+		bsg_reply->result = rc = -EINVAL;
+		bsg_reply->reply_payload_rcv_len = 0;
 		break;
 	}
 
@@ -3584,7 +3590,7 @@ bfad_im_bsg_request(struct fc_bsg_job *job)
 }
 
 int
-bfad_im_bsg_timeout(struct fc_bsg_job *job)
+bfad_im_bsg_timeout(struct bsg_job *job)
 {
 	/* Don't complete the BSG job request - return -EAGAIN
 	 * to reset bsg job timeout : for ELS/CT pass thru we
diff --git a/drivers/scsi/bfa/bfad_im.h b/drivers/scsi/bfa/bfad_im.h
index 836fdc221edd..c81ec2a77ef5 100644
--- a/drivers/scsi/bfa/bfad_im.h
+++ b/drivers/scsi/bfa/bfad_im.h
@@ -166,8 +166,8 @@ extern struct device_attribute *bfad_im_vport_attrs[];
 
 irqreturn_t bfad_intx(int irq, void *dev_id);
 
-int bfad_im_bsg_request(struct fc_bsg_job *job);
-int bfad_im_bsg_timeout(struct fc_bsg_job *job);
+int bfad_im_bsg_request(struct bsg_job *job);
+int bfad_im_bsg_timeout(struct bsg_job *job);
 
 /*
  * Macro to set the SCSI device sdev_bflags - sdev_bflags are used by the
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index f9ddb6156f14..c639d5a02656 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -127,13 +127,6 @@ module_param_named(log_fka, bnx2fc_log_fka, uint, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(log_fka, " Print message to kernel log when fcoe is "
 	"initiating a FIP keep alive when debug logging is enabled.");
 
-static int bnx2fc_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu);
-/* notification function for CPU hotplug events */
-static struct notifier_block bnx2fc_cpu_notifier = {
-	.notifier_call = bnx2fc_cpu_callback,
-};
-
 static inline struct net_device *bnx2fc_netdev(const struct fc_lport *lport)
 {
 	return ((struct bnx2fc_interface *)
@@ -970,7 +963,6 @@ static int bnx2fc_libfc_config(struct fc_lport *lport)
 		sizeof(struct libfc_function_template));
 	fc_elsct_init(lport);
 	fc_exch_init(lport);
-	fc_rport_init(lport);
 	fc_disc_init(lport);
 	fc_disc_config(lport, lport);
 	return 0;
@@ -2623,37 +2615,19 @@ static void bnx2fc_percpu_thread_destroy(unsigned int cpu)
 		kthread_stop(thread);
 }
 
-/**
- * bnx2fc_cpu_callback - Handler for CPU hotplug events
- *
- * @nfb:    The callback data block
- * @action: The event triggering the callback
- * @hcpu:   The index of the CPU that the event is for
- *
- * This creates or destroys per-CPU data for fcoe
- *
- * Returns NOTIFY_OK always.
- */
-static int bnx2fc_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu)
+
+static int bnx2fc_cpu_online(unsigned int cpu)
 {
-	unsigned cpu = (unsigned long)hcpu;
+	printk(PFX "CPU %x online: Create Rx thread\n", cpu);
+	bnx2fc_percpu_thread_create(cpu);
+	return 0;
+}
 
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		printk(PFX "CPU %x online: Create Rx thread\n", cpu);
-		bnx2fc_percpu_thread_create(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		printk(PFX "CPU %x offline: Remove Rx thread\n", cpu);
-		bnx2fc_percpu_thread_destroy(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+static int bnx2fc_cpu_dead(unsigned int cpu)
+{
+	printk(PFX "CPU %x offline: Remove Rx thread\n", cpu);
+	bnx2fc_percpu_thread_destroy(cpu);
+	return 0;
 }
 
 static int bnx2fc_slave_configure(struct scsi_device *sdev)
@@ -2665,6 +2639,8 @@ static int bnx2fc_slave_configure(struct scsi_device *sdev)
 	return 0;
 }
 
+static enum cpuhp_state bnx2fc_online_state;
+
 /**
  * bnx2fc_mod_init - module init entry point
  *
@@ -2725,21 +2701,31 @@ static int __init bnx2fc_mod_init(void)
 		spin_lock_init(&p->fp_work_lock);
 	}
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
-	for_each_online_cpu(cpu) {
+	for_each_online_cpu(cpu)
 		bnx2fc_percpu_thread_create(cpu);
-	}
 
-	/* Initialize per CPU interrupt thread */
-	__register_hotcpu_notifier(&bnx2fc_cpu_notifier);
+	rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				       "scsi/bnx2fc:online",
+				       bnx2fc_cpu_online, NULL);
+	if (rc < 0)
+		goto stop_threads;
+	bnx2fc_online_state = rc;
 
-	cpu_notifier_register_done();
+	cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD, "scsi/bnx2fc:dead",
+				  NULL, bnx2fc_cpu_dead);
+	put_online_cpus();
 
 	cnic_register_driver(CNIC_ULP_FCOE, &bnx2fc_cnic_cb);
 
 	return 0;
 
+stop_threads:
+	for_each_online_cpu(cpu)
+		bnx2fc_percpu_thread_destroy(cpu);
+	put_online_cpus();
+	kthread_stop(l2_thread);
 free_wq:
 	destroy_workqueue(bnx2fc_wq);
 release_bt:
@@ -2798,16 +2784,16 @@ static void __exit bnx2fc_mod_exit(void)
 	if (l2_thread)
 		kthread_stop(l2_thread);
 
-	cpu_notifier_register_begin();
-
+	get_online_cpus();
 	/* Destroy per cpu threads */
 	for_each_online_cpu(cpu) {
 		bnx2fc_percpu_thread_destroy(cpu);
 	}
 
-	__unregister_hotcpu_notifier(&bnx2fc_cpu_notifier);
+	cpuhp_remove_state_nocalls(bnx2fc_online_state);
+	cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD);
 
-	cpu_notifier_register_done();
+	put_online_cpus();
 
 	destroy_workqueue(bnx2fc_wq);
 	/*
diff --git a/drivers/scsi/bnx2fc/bnx2fc_tgt.c b/drivers/scsi/bnx2fc/bnx2fc_tgt.c
index 08ec318afb99..739bfb62aff6 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_tgt.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_tgt.c
@@ -80,7 +80,6 @@ static void bnx2fc_offload_session(struct fcoe_port *port,
 					struct bnx2fc_rport *tgt,
 					struct fc_rport_priv *rdata)
 {
-	struct fc_lport *lport = rdata->local_port;
 	struct fc_rport *rport = rdata->rport;
 	struct bnx2fc_interface *interface = port->priv;
 	struct bnx2fc_hba *hba = interface->hba;
@@ -160,7 +159,7 @@ ofld_err:
 tgt_init_err:
 	if (tgt->fcoe_conn_id != -1)
 		bnx2fc_free_conn_id(hba, tgt->fcoe_conn_id);
-	lport->tt.rport_logoff(rdata);
+	fc_rport_logoff(rdata);
 }
 
 void bnx2fc_flush_active_ios(struct bnx2fc_rport *tgt)
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index c8b410c24cf0..86afc002814c 100644
--- a/drivers/scsi/bnx2i/bnx2i_init.c
+++ b/drivers/scsi/bnx2i/bnx2i_init.c
@@ -70,14 +70,6 @@ u64 iscsi_error_mask = 0x00;
 
 DEFINE_PER_CPU(struct bnx2i_percpu_s, bnx2i_percpu);
 
-static int bnx2i_cpu_callback(struct notifier_block *nfb,
-			      unsigned long action, void *hcpu);
-/* notification function for CPU hotplug events */
-static struct notifier_block bnx2i_cpu_notifier = {
-	.notifier_call = bnx2i_cpu_callback,
-};
-
-
 /**
  * bnx2i_identify_device - identifies NetXtreme II device type
  * @hba: 		Adapter structure pointer
@@ -461,41 +453,21 @@ static void bnx2i_percpu_thread_destroy(unsigned int cpu)
 		kthread_stop(thread);
 }
 
-
-/**
- * bnx2i_cpu_callback - Handler for CPU hotplug events
- *
- * @nfb:	The callback data block
- * @action:	The event triggering the callback
- * @hcpu:	The index of the CPU that the event is for
- *
- * This creates or destroys per-CPU data for iSCSI
- *
- * Returns NOTIFY_OK always.
- */
-static int bnx2i_cpu_callback(struct notifier_block *nfb,
-			      unsigned long action, void *hcpu)
+static int bnx2i_cpu_online(unsigned int cpu)
 {
-	unsigned cpu = (unsigned long)hcpu;
+	pr_info("bnx2i: CPU %x online: Create Rx thread\n", cpu);
+	bnx2i_percpu_thread_create(cpu);
+	return 0;
+}
 
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		printk(KERN_INFO "bnx2i: CPU %x online: Create Rx thread\n",
-			cpu);
-		bnx2i_percpu_thread_create(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		printk(KERN_INFO "CPU %x offline: Remove Rx thread\n", cpu);
-		bnx2i_percpu_thread_destroy(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+static int bnx2i_cpu_dead(unsigned int cpu)
+{
+	pr_info("CPU %x offline: Remove Rx thread\n", cpu);
+	bnx2i_percpu_thread_destroy(cpu);
+	return 0;
 }
 
+static enum cpuhp_state bnx2i_online_state;
 
 /**
  * bnx2i_mod_init - module init entry point
@@ -539,18 +511,28 @@ static int __init bnx2i_mod_init(void)
 		p->iothread = NULL;
 	}
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
 	for_each_online_cpu(cpu)
 		bnx2i_percpu_thread_create(cpu);
 
-	/* Initialize per CPU interrupt thread */
-	__register_hotcpu_notifier(&bnx2i_cpu_notifier);
-
-	cpu_notifier_register_done();
+	err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				       "scsi/bnx2i:online",
+				       bnx2i_cpu_online, NULL);
+	if (err < 0)
+		goto remove_threads;
+	bnx2i_online_state = err;
 
+	cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2I_DEAD, "scsi/bnx2i:dead",
+				  NULL, bnx2i_cpu_dead);
+	put_online_cpus();
 	return 0;
 
+remove_threads:
+	for_each_online_cpu(cpu)
+		bnx2i_percpu_thread_destroy(cpu);
+	put_online_cpus();
+	cnic_unregister_driver(CNIC_ULP_ISCSI);
 unreg_xport:
 	iscsi_unregister_transport(&bnx2i_iscsi_transport);
 out:
@@ -587,14 +569,14 @@ static void __exit bnx2i_mod_exit(void)
 	}
 	mutex_unlock(&bnx2i_dev_lock);
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
 	for_each_online_cpu(cpu)
 		bnx2i_percpu_thread_destroy(cpu);
 
-	__unregister_hotcpu_notifier(&bnx2i_cpu_notifier);
-
-	cpu_notifier_register_done();
+	cpuhp_remove_state_nocalls(bnx2i_online_state);
+	cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2I_DEAD);
+	put_online_cpus();
 
 	iscsi_unregister_transport(&bnx2i_iscsi_transport);
 	cnic_unregister_driver(CNIC_ULP_ISCSI);
diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index 0039bebaa9e2..9a2fdc305cf2 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -85,6 +85,7 @@ static inline int send_tx_flowc_wr(struct cxgbi_sock *);
 static const struct cxgb4_uld_info cxgb4i_uld_info = {
 	.name = DRV_MODULE_NAME,
 	.nrxq = MAX_ULD_QSETS,
+	.ntxq = MAX_ULD_QSETS,
 	.rxq_size = 1024,
 	.lro = false,
 	.add = t4_uld_add,
@@ -188,7 +189,6 @@ static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb,
 				struct l2t_entry *e)
 {
 	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(csk->cdev);
-	int t4 = is_t4(lldi->adapter_type);
 	int wscale = cxgbi_sock_compute_wscale(csk->mss_idx);
 	unsigned long long opt0;
 	unsigned int opt2;
@@ -231,7 +231,7 @@ static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb,
 			csk, &req->local_ip, ntohs(req->local_port),
 			&req->peer_ip, ntohs(req->peer_port),
 			csk->atid, csk->rss_qid);
-	} else {
+	} else if (is_t5(lldi->adapter_type)) {
 		struct cpl_t5_act_open_req *req =
 				(struct cpl_t5_act_open_req *)skb->head;
 		u32 isn = (prandom_u32() & ~7UL) - 1;
@@ -259,12 +259,45 @@ static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb,
 			csk, &req->local_ip, ntohs(req->local_port),
 			&req->peer_ip, ntohs(req->peer_port),
 			csk->atid, csk->rss_qid);
+	} else {
+		struct cpl_t6_act_open_req *req =
+				(struct cpl_t6_act_open_req *)skb->head;
+		u32 isn = (prandom_u32() & ~7UL) - 1;
+
+		INIT_TP_WR(req, 0);
+		OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ACT_OPEN_REQ,
+							    qid_atid));
+		req->local_port = csk->saddr.sin_port;
+		req->peer_port = csk->daddr.sin_port;
+		req->local_ip = csk->saddr.sin_addr.s_addr;
+		req->peer_ip = csk->daddr.sin_addr.s_addr;
+		req->opt0 = cpu_to_be64(opt0);
+		req->params = cpu_to_be64(FILTER_TUPLE_V(
+				cxgb4_select_ntuple(
+					csk->cdev->ports[csk->port_id],
+					csk->l2t)));
+		req->rsvd = cpu_to_be32(isn);
+
+		opt2 |= T5_ISS_VALID;
+		opt2 |= RX_FC_DISABLE_F;
+		opt2 |= T5_OPT_2_VALID_F;
+
+		req->opt2 = cpu_to_be32(opt2);
+		req->rsvd2 = cpu_to_be32(0);
+		req->opt3 = cpu_to_be32(0);
+
+		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
+			  "csk t6 0x%p, %pI4:%u-%pI4:%u, atid %d, qid %u.\n",
+			  csk, &req->local_ip, ntohs(req->local_port),
+			  &req->peer_ip, ntohs(req->peer_port),
+			  csk->atid, csk->rss_qid);
 	}
 
 	set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->port_id);
 
 	pr_info_ipaddr("t%d csk 0x%p,%u,0x%lx,%u, rss_qid %u.\n",
-		       (&csk->saddr), (&csk->daddr), t4 ? 4 : 5, csk,
+		       (&csk->saddr), (&csk->daddr),
+		       CHELSIO_CHIP_VERSION(lldi->adapter_type), csk,
 		       csk->state, csk->flags, csk->atid, csk->rss_qid);
 
 	cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t);
@@ -275,7 +308,6 @@ static void send_act_open_req6(struct cxgbi_sock *csk, struct sk_buff *skb,
 			       struct l2t_entry *e)
 {
 	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(csk->cdev);
-	int t4 = is_t4(lldi->adapter_type);
 	int wscale = cxgbi_sock_compute_wscale(csk->mss_idx);
 	unsigned long long opt0;
 	unsigned int opt2;
@@ -293,10 +325,9 @@ static void send_act_open_req6(struct cxgbi_sock *csk, struct sk_buff *skb,
 
 	opt2 = RX_CHANNEL_V(0) |
 		RSS_QUEUE_VALID_F |
-		RX_FC_DISABLE_F |
 		RSS_QUEUE_V(csk->rss_qid);
 
-	if (t4) {
+	if (is_t4(lldi->adapter_type)) {
 		struct cpl_act_open_req6 *req =
 			    (struct cpl_act_open_req6 *)skb->head;
 
@@ -321,7 +352,7 @@ static void send_act_open_req6(struct cxgbi_sock *csk, struct sk_buff *skb,
 		req->params = cpu_to_be32(cxgb4_select_ntuple(
 					  csk->cdev->ports[csk->port_id],
 					  csk->l2t));
-	} else {
+	} else if (is_t5(lldi->adapter_type)) {
 		struct cpl_t5_act_open_req6 *req =
 				(struct cpl_t5_act_open_req6 *)skb->head;
 
@@ -344,12 +375,41 @@ static void send_act_open_req6(struct cxgbi_sock *csk, struct sk_buff *skb,
 		req->params = cpu_to_be64(FILTER_TUPLE_V(cxgb4_select_ntuple(
 					  csk->cdev->ports[csk->port_id],
 					  csk->l2t)));
+	} else {
+		struct cpl_t6_act_open_req6 *req =
+				(struct cpl_t6_act_open_req6 *)skb->head;
+
+		INIT_TP_WR(req, 0);
+		OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ACT_OPEN_REQ6,
+							    qid_atid));
+		req->local_port = csk->saddr6.sin6_port;
+		req->peer_port = csk->daddr6.sin6_port;
+		req->local_ip_hi = *(__be64 *)(csk->saddr6.sin6_addr.s6_addr);
+		req->local_ip_lo = *(__be64 *)(csk->saddr6.sin6_addr.s6_addr +
+									8);
+		req->peer_ip_hi = *(__be64 *)(csk->daddr6.sin6_addr.s6_addr);
+		req->peer_ip_lo = *(__be64 *)(csk->daddr6.sin6_addr.s6_addr +
+									8);
+		req->opt0 = cpu_to_be64(opt0);
+
+		opt2 |= RX_FC_DISABLE_F;
+		opt2 |= T5_OPT_2_VALID_F;
+
+		req->opt2 = cpu_to_be32(opt2);
+
+		req->params = cpu_to_be64(FILTER_TUPLE_V(cxgb4_select_ntuple(
+					  csk->cdev->ports[csk->port_id],
+					  csk->l2t)));
+
+		req->rsvd2 = cpu_to_be32(0);
+		req->opt3 = cpu_to_be32(0);
 	}
 
 	set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->port_id);
 
 	pr_info("t%d csk 0x%p,%u,0x%lx,%u, [%pI6]:%u-[%pI6]:%u, rss_qid %u.\n",
-		t4 ? 4 : 5, csk, csk->state, csk->flags, csk->atid,
+		CHELSIO_CHIP_VERSION(lldi->adapter_type), csk, csk->state,
+		csk->flags, csk->atid,
 		&csk->saddr6.sin6_addr, ntohs(csk->saddr.sin_port),
 		&csk->daddr6.sin6_addr, ntohs(csk->daddr.sin_port),
 		csk->rss_qid);
@@ -741,7 +801,7 @@ static void do_act_establish(struct cxgbi_device *cdev, struct sk_buff *skb)
 		       (&csk->saddr), (&csk->daddr),
 		       atid, tid, csk, csk->state, csk->flags, rcv_isn);
 
-	module_put(THIS_MODULE);
+	module_put(cdev->owner);
 
 	cxgbi_sock_get(csk);
 	csk->tid = tid;
@@ -890,7 +950,7 @@ static void do_act_open_rpl(struct cxgbi_device *cdev, struct sk_buff *skb)
 	if (is_neg_adv(status))
 		goto rel_skb;
 
-	module_put(THIS_MODULE);
+	module_put(cdev->owner);
 
 	if (status && status != CPL_ERR_TCAM_FULL &&
 	    status != CPL_ERR_CONN_EXIST &&
@@ -1172,6 +1232,101 @@ rel_skb:
 	__kfree_skb(skb);
 }
 
+static void do_rx_iscsi_data(struct cxgbi_device *cdev, struct sk_buff *skb)
+{
+	struct cxgbi_sock *csk;
+	struct cpl_iscsi_hdr *cpl = (struct cpl_iscsi_hdr *)skb->data;
+	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
+	struct tid_info *t = lldi->tids;
+	struct sk_buff *lskb;
+	u32 tid = GET_TID(cpl);
+	u16 pdu_len_ddp = be16_to_cpu(cpl->pdu_len_ddp);
+
+	csk = lookup_tid(t, tid);
+	if (unlikely(!csk)) {
+		pr_err("can't find conn. for tid %u.\n", tid);
+		goto rel_skb;
+	}
+
+	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
+		  "csk 0x%p,%u,0x%lx, tid %u, skb 0x%p,%u, 0x%x.\n",
+		  csk, csk->state, csk->flags, csk->tid, skb,
+		  skb->len, pdu_len_ddp);
+
+	spin_lock_bh(&csk->lock);
+
+	if (unlikely(csk->state >= CTP_PASSIVE_CLOSE)) {
+		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
+			  "csk 0x%p,%u,0x%lx,%u, bad state.\n",
+			  csk, csk->state, csk->flags, csk->tid);
+
+		if (csk->state != CTP_ABORTING)
+			goto abort_conn;
+		else
+			goto discard;
+	}
+
+	cxgbi_skcb_tcp_seq(skb) = be32_to_cpu(cpl->seq);
+	cxgbi_skcb_flags(skb) = 0;
+
+	skb_reset_transport_header(skb);
+	__skb_pull(skb, sizeof(*cpl));
+	__pskb_trim(skb, ntohs(cpl->len));
+
+	if (!csk->skb_ulp_lhdr)
+		csk->skb_ulp_lhdr = skb;
+
+	lskb = csk->skb_ulp_lhdr;
+	cxgbi_skcb_set_flag(lskb, SKCBF_RX_DATA);
+
+	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
+		  "csk 0x%p,%u,0x%lx, skb 0x%p data, 0x%p.\n",
+		  csk, csk->state, csk->flags, skb, lskb);
+
+	__skb_queue_tail(&csk->receive_queue, skb);
+	spin_unlock_bh(&csk->lock);
+	return;
+
+abort_conn:
+	send_abort_req(csk);
+discard:
+	spin_unlock_bh(&csk->lock);
+rel_skb:
+	__kfree_skb(skb);
+}
+
+static void
+cxgb4i_process_ddpvld(struct cxgbi_sock *csk,
+		      struct sk_buff *skb, u32 ddpvld)
+{
+	if (ddpvld & (1 << CPL_RX_DDP_STATUS_HCRC_SHIFT)) {
+		pr_info("csk 0x%p, lhdr 0x%p, status 0x%x, hcrc bad 0x%lx.\n",
+			csk, skb, ddpvld, cxgbi_skcb_flags(skb));
+		cxgbi_skcb_set_flag(skb, SKCBF_RX_HCRC_ERR);
+	}
+
+	if (ddpvld & (1 << CPL_RX_DDP_STATUS_DCRC_SHIFT)) {
+		pr_info("csk 0x%p, lhdr 0x%p, status 0x%x, dcrc bad 0x%lx.\n",
+			csk, skb, ddpvld, cxgbi_skcb_flags(skb));
+		cxgbi_skcb_set_flag(skb, SKCBF_RX_DCRC_ERR);
+	}
+
+	if (ddpvld & (1 << CPL_RX_DDP_STATUS_PAD_SHIFT)) {
+		log_debug(1 << CXGBI_DBG_PDU_RX,
+			  "csk 0x%p, lhdr 0x%p, status 0x%x, pad bad.\n",
+			  csk, skb, ddpvld);
+		cxgbi_skcb_set_flag(skb, SKCBF_RX_PAD_ERR);
+	}
+
+	if ((ddpvld & (1 << CPL_RX_DDP_STATUS_DDP_SHIFT)) &&
+	    !cxgbi_skcb_test_flag(skb, SKCBF_RX_DATA)) {
+		log_debug(1 << CXGBI_DBG_PDU_RX,
+			  "csk 0x%p, lhdr 0x%p, 0x%x, data ddp'ed.\n",
+			  csk, skb, ddpvld);
+		cxgbi_skcb_set_flag(skb, SKCBF_RX_DATA_DDPD);
+	}
+}
+
 static void do_rx_data_ddp(struct cxgbi_device *cdev,
 				  struct sk_buff *skb)
 {
@@ -1181,7 +1336,7 @@ static void do_rx_data_ddp(struct cxgbi_device *cdev,
 	unsigned int tid = GET_TID(rpl);
 	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
 	struct tid_info *t = lldi->tids;
-	unsigned int status = ntohl(rpl->ddpvld);
+	u32 ddpvld = be32_to_cpu(rpl->ddpvld);
 
 	csk = lookup_tid(t, tid);
 	if (unlikely(!csk)) {
@@ -1191,7 +1346,7 @@ static void do_rx_data_ddp(struct cxgbi_device *cdev,
 
 	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
 		"csk 0x%p,%u,0x%lx, skb 0x%p,0x%x, lhdr 0x%p.\n",
-		csk, csk->state, csk->flags, skb, status, csk->skb_ulp_lhdr);
+		csk, csk->state, csk->flags, skb, ddpvld, csk->skb_ulp_lhdr);
 
 	spin_lock_bh(&csk->lock);
 
@@ -1219,29 +1374,8 @@ static void do_rx_data_ddp(struct cxgbi_device *cdev,
 		pr_info("tid 0x%x, RX_DATA_DDP pdulen %u != %u.\n",
 			csk->tid, ntohs(rpl->len), cxgbi_skcb_rx_pdulen(lskb));
 
-	if (status & (1 << CPL_RX_DDP_STATUS_HCRC_SHIFT)) {
-		pr_info("csk 0x%p, lhdr 0x%p, status 0x%x, hcrc bad 0x%lx.\n",
-			csk, lskb, status, cxgbi_skcb_flags(lskb));
-		cxgbi_skcb_set_flag(lskb, SKCBF_RX_HCRC_ERR);
-	}
-	if (status & (1 << CPL_RX_DDP_STATUS_DCRC_SHIFT)) {
-		pr_info("csk 0x%p, lhdr 0x%p, status 0x%x, dcrc bad 0x%lx.\n",
-			csk, lskb, status, cxgbi_skcb_flags(lskb));
-		cxgbi_skcb_set_flag(lskb, SKCBF_RX_DCRC_ERR);
-	}
-	if (status & (1 << CPL_RX_DDP_STATUS_PAD_SHIFT)) {
-		log_debug(1 << CXGBI_DBG_PDU_RX,
-			"csk 0x%p, lhdr 0x%p, status 0x%x, pad bad.\n",
-			csk, lskb, status);
-		cxgbi_skcb_set_flag(lskb, SKCBF_RX_PAD_ERR);
-	}
-	if ((status & (1 << CPL_RX_DDP_STATUS_DDP_SHIFT)) &&
-		!cxgbi_skcb_test_flag(lskb, SKCBF_RX_DATA)) {
-		log_debug(1 << CXGBI_DBG_PDU_RX,
-			"csk 0x%p, lhdr 0x%p, 0x%x, data ddp'ed.\n",
-			csk, lskb, status);
-		cxgbi_skcb_set_flag(lskb, SKCBF_RX_DATA_DDPD);
-	}
+	cxgb4i_process_ddpvld(csk, lskb, ddpvld);
+
 	log_debug(1 << CXGBI_DBG_PDU_RX,
 		"csk 0x%p, lskb 0x%p, f 0x%lx.\n",
 		csk, lskb, cxgbi_skcb_flags(lskb));
@@ -1259,6 +1393,98 @@ rel_skb:
 	__kfree_skb(skb);
 }
 
+static void
+do_rx_iscsi_cmp(struct cxgbi_device *cdev, struct sk_buff *skb)
+{
+	struct cxgbi_sock *csk;
+	struct cpl_rx_iscsi_cmp *rpl = (struct cpl_rx_iscsi_cmp *)skb->data;
+	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
+	struct tid_info *t = lldi->tids;
+	struct sk_buff *data_skb = NULL;
+	u32 tid = GET_TID(rpl);
+	u32 ddpvld = be32_to_cpu(rpl->ddpvld);
+	u32 seq = be32_to_cpu(rpl->seq);
+	u16 pdu_len_ddp = be16_to_cpu(rpl->pdu_len_ddp);
+
+	csk = lookup_tid(t, tid);
+	if (unlikely(!csk)) {
+		pr_err("can't find connection for tid %u.\n", tid);
+		goto rel_skb;
+	}
+
+	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
+		  "csk 0x%p,%u,0x%lx, skb 0x%p,0x%x, lhdr 0x%p, len %u, "
+		  "pdu_len_ddp %u, status %u.\n",
+		  csk, csk->state, csk->flags, skb, ddpvld, csk->skb_ulp_lhdr,
+		  ntohs(rpl->len), pdu_len_ddp,  rpl->status);
+
+	spin_lock_bh(&csk->lock);
+
+	if (unlikely(csk->state >= CTP_PASSIVE_CLOSE)) {
+		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
+			  "csk 0x%p,%u,0x%lx,%u, bad state.\n",
+			  csk, csk->state, csk->flags, csk->tid);
+
+		if (csk->state != CTP_ABORTING)
+			goto abort_conn;
+		else
+			goto discard;
+	}
+
+	cxgbi_skcb_tcp_seq(skb) = seq;
+	cxgbi_skcb_flags(skb) = 0;
+	cxgbi_skcb_rx_pdulen(skb) = 0;
+
+	skb_reset_transport_header(skb);
+	__skb_pull(skb, sizeof(*rpl));
+	__pskb_trim(skb, be16_to_cpu(rpl->len));
+
+	csk->rcv_nxt = seq + pdu_len_ddp;
+
+	if (csk->skb_ulp_lhdr) {
+		data_skb = skb_peek(&csk->receive_queue);
+		if (!data_skb ||
+		    !cxgbi_skcb_test_flag(data_skb, SKCBF_RX_DATA)) {
+			pr_err("Error! freelist data not found 0x%p, tid %u\n",
+			       data_skb, tid);
+
+			goto abort_conn;
+		}
+		__skb_unlink(data_skb, &csk->receive_queue);
+
+		cxgbi_skcb_set_flag(skb, SKCBF_RX_DATA);
+
+		__skb_queue_tail(&csk->receive_queue, skb);
+		__skb_queue_tail(&csk->receive_queue, data_skb);
+	} else {
+		 __skb_queue_tail(&csk->receive_queue, skb);
+	}
+
+	csk->skb_ulp_lhdr = NULL;
+
+	cxgbi_skcb_set_flag(skb, SKCBF_RX_HDR);
+	cxgbi_skcb_set_flag(skb, SKCBF_RX_STATUS);
+	cxgbi_skcb_set_flag(skb, SKCBF_RX_ISCSI_COMPL);
+	cxgbi_skcb_rx_ddigest(skb) = be32_to_cpu(rpl->ulp_crc);
+
+	cxgb4i_process_ddpvld(csk, skb, ddpvld);
+
+	log_debug(1 << CXGBI_DBG_PDU_RX, "csk 0x%p, skb 0x%p, f 0x%lx.\n",
+		  csk, skb, cxgbi_skcb_flags(skb));
+
+	cxgbi_conn_pdu_ready(csk);
+	spin_unlock_bh(&csk->lock);
+
+	return;
+
+abort_conn:
+	send_abort_req(csk);
+discard:
+	spin_unlock_bh(&csk->lock);
+rel_skb:
+	__kfree_skb(skb);
+}
+
 static void do_fw4_ack(struct cxgbi_device *cdev, struct sk_buff *skb)
 {
 	struct cxgbi_sock *csk;
@@ -1381,7 +1607,6 @@ static int init_act_open(struct cxgbi_sock *csk)
 	void *daddr;
 	unsigned int step;
 	unsigned int size, size6;
-	int t4 = is_t4(lldi->adapter_type);
 	unsigned int linkspeed;
 	unsigned int rcv_winf, snd_winf;
 
@@ -1410,7 +1635,7 @@ static int init_act_open(struct cxgbi_sock *csk)
 	csk->atid = cxgb4_alloc_atid(lldi->tids, csk);
 	if (csk->atid < 0) {
 		pr_err("%s, NO atid available.\n", ndev->name);
-		return -EINVAL;
+		goto rel_resource_without_clip;
 	}
 	cxgbi_sock_set_flag(csk, CTPF_HAS_ATID);
 	cxgbi_sock_get(csk);
@@ -1427,12 +1652,15 @@ static int init_act_open(struct cxgbi_sock *csk)
 		cxgb4_clip_get(ndev, (const u32 *)&csk->saddr6.sin6_addr, 1);
 #endif
 
-	if (t4) {
+	if (is_t4(lldi->adapter_type)) {
 		size = sizeof(struct cpl_act_open_req);
 		size6 = sizeof(struct cpl_act_open_req6);
-	} else {
+	} else if (is_t5(lldi->adapter_type)) {
 		size = sizeof(struct cpl_t5_act_open_req);
 		size6 = sizeof(struct cpl_t5_act_open_req6);
+	} else {
+		size = sizeof(struct cpl_t6_act_open_req);
+		size6 = sizeof(struct cpl_t6_act_open_req6);
 	}
 
 	if (csk->csk_family == AF_INET)
@@ -1451,8 +1679,8 @@ static int init_act_open(struct cxgbi_sock *csk)
 		csk->mtu = dst_mtu(csk->dst);
 	cxgb4_best_mtu(lldi->mtus, csk->mtu, &csk->mss_idx);
 	csk->tx_chan = cxgb4_port_chan(ndev);
-	/* SMT two entries per row */
-	csk->smac_idx = ((cxgb4_port_viid(ndev) & 0x7F)) << 1;
+	csk->smac_idx = cxgb4_tp_smt_idx(lldi->adapter_type,
+					 cxgb4_port_viid(ndev));
 	step = lldi->ntxq / lldi->nchan;
 	csk->txq_idx = cxgb4_port_idx(ndev) * step;
 	step = lldi->nrxq / lldi->nchan;
@@ -1485,7 +1713,11 @@ static int init_act_open(struct cxgbi_sock *csk)
 		       csk->mtu, csk->mss_idx, csk->smac_idx);
 
 	/* must wait for either a act_open_rpl or act_open_establish */
-	try_module_get(THIS_MODULE);
+	if (!try_module_get(cdev->owner)) {
+		pr_err("%s, try_module_get failed.\n", ndev->name);
+		goto rel_resource;
+	}
+
 	cxgbi_sock_set_state(csk, CTP_ACTIVE_OPEN);
 	if (csk->csk_family == AF_INET)
 		send_act_open_req(csk, skb, csk->l2t);
@@ -1520,10 +1752,11 @@ static cxgb4i_cplhandler_func cxgb4i_cplhandlers[NUM_CPL_CMDS] = {
 	[CPL_CLOSE_CON_RPL] = do_close_con_rpl,
 	[CPL_FW4_ACK] = do_fw4_ack,
 	[CPL_ISCSI_HDR] = do_rx_iscsi_hdr,
-	[CPL_ISCSI_DATA] = do_rx_iscsi_hdr,
+	[CPL_ISCSI_DATA] = do_rx_iscsi_data,
 	[CPL_SET_TCB_RPL] = do_set_tcb_rpl,
 	[CPL_RX_DATA_DDP] = do_rx_data_ddp,
 	[CPL_RX_ISCSI_DDP] = do_rx_data_ddp,
+	[CPL_RX_ISCSI_CMP] = do_rx_iscsi_cmp,
 	[CPL_RX_DATA] = do_rx_data,
 };
 
@@ -1793,10 +2026,12 @@ static void *t4_uld_add(const struct cxgb4_lld_info *lldi)
 	cdev->nports = lldi->nports;
 	cdev->mtus = lldi->mtus;
 	cdev->nmtus = NMTUS;
-	cdev->rx_credit_thres = cxgb4i_rx_credit_thres;
+	cdev->rx_credit_thres = (CHELSIO_CHIP_VERSION(lldi->adapter_type) <=
+				 CHELSIO_T5) ? cxgb4i_rx_credit_thres : 0;
 	cdev->skb_tx_rsvd = CXGB4I_TX_HEADER_LEN;
 	cdev->skb_rx_extra = sizeof(struct cpl_iscsi_hdr);
 	cdev->itp = &cxgb4i_iscsi_transport;
+	cdev->owner = THIS_MODULE;
 
 	cdev->pfvf = FW_VIID_PFN_G(cxgb4_port_viid(lldi->ports[0]))
 			<< FW_VIID_PFN_S;
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index 2ffe029ff2b6..9167bcd9fffe 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -642,6 +642,12 @@ static struct cxgbi_sock *cxgbi_check_route(struct sockaddr *dst_addr)
 			n->dev->name, ndev->name, mtu);
 	}
 
+	if (!(ndev->flags & IFF_UP) || !netif_carrier_ok(ndev)) {
+		pr_info("%s interface not up.\n", ndev->name);
+		err = -ENETDOWN;
+		goto rel_neigh;
+	}
+
 	cdev = cxgbi_device_find_by_netdev(ndev, &port);
 	if (!cdev) {
 		pr_info("dst %pI4, %s, NOT cxgbi device.\n",
@@ -736,6 +742,12 @@ static struct cxgbi_sock *cxgbi_check_route6(struct sockaddr *dst_addr)
 	}
 	ndev = n->dev;
 
+	if (!(ndev->flags & IFF_UP) || !netif_carrier_ok(ndev)) {
+		pr_info("%s interface not up.\n", ndev->name);
+		err = -ENETDOWN;
+		goto rel_rt;
+	}
+
 	if (ipv6_addr_is_multicast(&daddr6->sin6_addr)) {
 		pr_info("multi-cast route %pI6 port %u, dev %s.\n",
 			daddr6->sin6_addr.s6_addr,
@@ -896,6 +908,7 @@ EXPORT_SYMBOL_GPL(cxgbi_sock_fail_act_open);
 void cxgbi_sock_act_open_req_arp_failure(void *handle, struct sk_buff *skb)
 {
 	struct cxgbi_sock *csk = (struct cxgbi_sock *)skb->sk;
+	struct module *owner = csk->cdev->owner;
 
 	log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
 		csk, (csk)->state, (csk)->flags, (csk)->tid);
@@ -906,6 +919,8 @@ void cxgbi_sock_act_open_req_arp_failure(void *handle, struct sk_buff *skb)
 	spin_unlock_bh(&csk->lock);
 	cxgbi_sock_put(csk);
 	__kfree_skb(skb);
+
+	module_put(owner);
 }
 EXPORT_SYMBOL_GPL(cxgbi_sock_act_open_req_arp_failure);
 
@@ -1574,6 +1589,25 @@ static int skb_read_pdu_bhs(struct iscsi_conn *conn, struct sk_buff *skb)
 		return -EIO;
 	}
 
+	if (cxgbi_skcb_test_flag(skb, SKCBF_RX_ISCSI_COMPL) &&
+	    cxgbi_skcb_test_flag(skb, SKCBF_RX_DATA_DDPD)) {
+		/* If completion flag is set and data is directly
+		 * placed in to the host memory then update
+		 * task->exp_datasn to the datasn in completion
+		 * iSCSI hdr as T6 adapter generates completion only
+		 * for the last pdu of a sequence.
+		 */
+		itt_t itt = ((struct iscsi_data *)skb->data)->itt;
+		struct iscsi_task *task = iscsi_itt_to_ctask(conn, itt);
+		u32 data_sn = be32_to_cpu(((struct iscsi_data *)
+							skb->data)->datasn);
+		if (task && task->sc) {
+			struct iscsi_tcp_task *tcp_task = task->dd_data;
+
+			tcp_task->exp_datasn = data_sn;
+		}
+	}
+
 	return read_pdu_skb(conn, skb, 0, 0);
 }
 
@@ -1627,15 +1661,15 @@ static void csk_return_rx_credits(struct cxgbi_sock *csk, int copied)
 		csk->rcv_wup, cdev->rx_credit_thres,
 		csk->rcv_win);
 
+	if (!cdev->rx_credit_thres)
+		return;
+
 	if (csk->state != CTP_ESTABLISHED)
 		return;
 
 	credits = csk->copied_seq - csk->rcv_wup;
 	if (unlikely(!credits))
 		return;
-	if (unlikely(cdev->rx_credit_thres == 0))
-		return;
-
 	must_send = credits + 16384 >= csk->rcv_win;
 	if (must_send || credits >= cdev->rx_credit_thres)
 		csk->rcv_wup += cdev->csk_send_rx_credits(csk, credits);
diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h
index e7802738f5d2..95ba99044c3e 100644
--- a/drivers/scsi/cxgbi/libcxgbi.h
+++ b/drivers/scsi/cxgbi/libcxgbi.h
@@ -207,6 +207,7 @@ enum cxgbi_skcb_flags {
 	SKCBF_RX_HDR,		/* received pdu header */
 	SKCBF_RX_DATA,		/* received pdu payload */
 	SKCBF_RX_STATUS,	/* received ddp status */
+	SKCBF_RX_ISCSI_COMPL,   /* received iscsi completion */
 	SKCBF_RX_DATA_DDPD,	/* pdu payload ddp'd */
 	SKCBF_RX_HCRC_ERR,	/* header digest error */
 	SKCBF_RX_DCRC_ERR,	/* data digest error */
@@ -467,6 +468,7 @@ struct cxgbi_device {
 	struct pci_dev *pdev;
 	struct dentry *debugfs_root;
 	struct iscsi_transport *itp;
+	struct module *owner;
 
 	unsigned int pfvf;
 	unsigned int rx_credit_thres;
diff --git a/drivers/scsi/cxlflash/common.h b/drivers/scsi/cxlflash/common.h
index 6e6815545a71..0e9de5d62da2 100644
--- a/drivers/scsi/cxlflash/common.h
+++ b/drivers/scsi/cxlflash/common.h
@@ -19,6 +19,7 @@
 #include <linux/rwsem.h>
 #include <linux/types.h>
 #include <scsi/scsi.h>
+#include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
 
 extern const struct file_operations cxlflash_cxl_fops;
@@ -62,11 +63,6 @@ static inline void check_sizes(void)
 /* AFU defines a fixed size of 4K for command buffers (borrow 4K page define) */
 #define CMD_BUFSIZE     SIZE_4K
 
-/* flags in IOA status area for host use */
-#define B_DONE       0x01
-#define B_ERROR      0x02	/* set with B_DONE */
-#define B_TIMEOUT    0x04	/* set with B_DONE & B_ERROR */
-
 enum cxlflash_lr_state {
 	LINK_RESET_INVALID,
 	LINK_RESET_REQUIRED,
@@ -132,12 +128,9 @@ struct cxlflash_cfg {
 struct afu_cmd {
 	struct sisl_ioarcb rcb;	/* IOARCB (cache line aligned) */
 	struct sisl_ioasa sa;	/* IOASA must follow IOARCB */
-	spinlock_t slock;
-	struct completion cevent;
-	char *buf;		/* per command buffer */
 	struct afu *parent;
-	int slot;
-	atomic_t free;
+	struct scsi_cmnd *scp;
+	struct completion cevent;
 
 	u8 cmd_tmf:1;
 
@@ -147,19 +140,31 @@ struct afu_cmd {
 	 */
 } __aligned(cache_line_size());
 
+static inline struct afu_cmd *sc_to_afuc(struct scsi_cmnd *sc)
+{
+	return PTR_ALIGN(scsi_cmd_priv(sc), __alignof__(struct afu_cmd));
+}
+
+static inline struct afu_cmd *sc_to_afucz(struct scsi_cmnd *sc)
+{
+	struct afu_cmd *afuc = sc_to_afuc(sc);
+
+	memset(afuc, 0, sizeof(*afuc));
+	return afuc;
+}
+
 struct afu {
 	/* Stuff requiring alignment go first. */
 
 	u64 rrq_entry[NUM_RRQ_ENTRY];	/* 2K RRQ */
-	/*
-	 * Command & data for AFU commands.
-	 */
-	struct afu_cmd cmd[CXLFLASH_NUM_CMDS];
 
 	/* Beware of alignment till here. Preferably introduce new
 	 * fields after this point
 	 */
 
+	int (*send_cmd)(struct afu *, struct afu_cmd *);
+	void (*context_reset)(struct afu_cmd *);
+
 	/* AFU HW */
 	struct cxl_ioctl_start_work work;
 	struct cxlflash_afu_map __iomem *afu_map;	/* entire MMIO map */
@@ -173,10 +178,10 @@ struct afu {
 	u64 *hrrq_end;
 	u64 *hrrq_curr;
 	bool toggle;
-	bool read_room;
-	atomic64_t room;
+	atomic_t cmds_active;	/* Number of currently active AFU commands */
+	s64 room;
+	spinlock_t rrin_slock; /* Lock to rrin queuing and cmd_room updates */
 	u64 hb;
-	u32 cmd_couts;		/* Number of command checkouts */
 	u32 internal_lun;	/* User-desired LUN mode for this AFU */
 
 	char version[16];
diff --git a/drivers/scsi/cxlflash/lunmgt.c b/drivers/scsi/cxlflash/lunmgt.c
index a0923cade6f3..6c318db90c85 100644
--- a/drivers/scsi/cxlflash/lunmgt.c
+++ b/drivers/scsi/cxlflash/lunmgt.c
@@ -254,8 +254,14 @@ int cxlflash_manage_lun(struct scsi_device *sdev,
 		if (lli->parent->mode != MODE_NONE)
 			rc = -EBUSY;
 		else {
+			/*
+			 * Clean up local LUN for this port and reset table
+			 * tracking when no more references exist.
+			 */
 			sdev->hostdata = NULL;
 			lli->port_sel &= ~CHAN2PORT(chan);
+			if (lli->port_sel == 0U)
+				lli->in_table = false;
 		}
 	}
 
diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index b301655f91cd..b17ebf6d0a7e 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -35,67 +35,6 @@ MODULE_AUTHOR("Matthew R. Ochs <mrochs@linux.vnet.ibm.com>");
 MODULE_LICENSE("GPL");
 
 /**
- * cmd_checkout() - checks out an AFU command
- * @afu:	AFU to checkout from.
- *
- * Commands are checked out in a round-robin fashion. Note that since
- * the command pool is larger than the hardware queue, the majority of
- * times we will only loop once or twice before getting a command. The
- * buffer and CDB within the command are initialized (zeroed) prior to
- * returning.
- *
- * Return: The checked out command or NULL when command pool is empty.
- */
-static struct afu_cmd *cmd_checkout(struct afu *afu)
-{
-	int k, dec = CXLFLASH_NUM_CMDS;
-	struct afu_cmd *cmd;
-
-	while (dec--) {
-		k = (afu->cmd_couts++ & (CXLFLASH_NUM_CMDS - 1));
-
-		cmd = &afu->cmd[k];
-
-		if (!atomic_dec_if_positive(&cmd->free)) {
-			pr_devel("%s: returning found index=%d cmd=%p\n",
-				 __func__, cmd->slot, cmd);
-			memset(cmd->buf, 0, CMD_BUFSIZE);
-			memset(cmd->rcb.cdb, 0, sizeof(cmd->rcb.cdb));
-			return cmd;
-		}
-	}
-
-	return NULL;
-}
-
-/**
- * cmd_checkin() - checks in an AFU command
- * @cmd:	AFU command to checkin.
- *
- * Safe to pass commands that have already been checked in. Several
- * internal tracking fields are reset as part of the checkin. Note
- * that these are intentionally reset prior to toggling the free bit
- * to avoid clobbering values in the event that the command is checked
- * out right away.
- */
-static void cmd_checkin(struct afu_cmd *cmd)
-{
-	cmd->rcb.scp = NULL;
-	cmd->rcb.timeout = 0;
-	cmd->sa.ioasc = 0;
-	cmd->cmd_tmf = false;
-	cmd->sa.host_use[0] = 0; /* clears both completion and retry bytes */
-
-	if (unlikely(atomic_inc_return(&cmd->free) != 1)) {
-		pr_err("%s: Freeing cmd (%d) that is not in use!\n",
-		       __func__, cmd->slot);
-		return;
-	}
-
-	pr_devel("%s: released cmd %p index=%d\n", __func__, cmd, cmd->slot);
-}
-
-/**
  * process_cmd_err() - command error handler
  * @cmd:	AFU command that experienced the error.
  * @scp:	SCSI command associated with the AFU command in error.
@@ -212,7 +151,7 @@ static void process_cmd_err(struct afu_cmd *cmd, struct scsi_cmnd *scp)
  *
  * Prepares and submits command that has either completed or timed out to
  * the SCSI stack. Checks AFU command back into command pool for non-internal
- * (rcb.scp populated) commands.
+ * (cmd->scp populated) commands.
  */
 static void cmd_complete(struct afu_cmd *cmd)
 {
@@ -222,19 +161,14 @@ static void cmd_complete(struct afu_cmd *cmd)
 	struct cxlflash_cfg *cfg = afu->parent;
 	bool cmd_is_tmf;
 
-	spin_lock_irqsave(&cmd->slock, lock_flags);
-	cmd->sa.host_use_b[0] |= B_DONE;
-	spin_unlock_irqrestore(&cmd->slock, lock_flags);
-
-	if (cmd->rcb.scp) {
-		scp = cmd->rcb.scp;
+	if (cmd->scp) {
+		scp = cmd->scp;
 		if (unlikely(cmd->sa.ioasc))
 			process_cmd_err(cmd, scp);
 		else
 			scp->result = (DID_OK << 16);
 
 		cmd_is_tmf = cmd->cmd_tmf;
-		cmd_checkin(cmd); /* Don't use cmd after here */
 
 		pr_debug_ratelimited("%s: calling scsi_done scp=%p result=%X "
 				     "ioasc=%d\n", __func__, scp, scp->result,
@@ -254,49 +188,19 @@ static void cmd_complete(struct afu_cmd *cmd)
 }
 
 /**
- * context_reset() - timeout handler for AFU commands
+ * context_reset_ioarrin() - reset command owner context via IOARRIN register
  * @cmd:	AFU command that timed out.
- *
- * Sends a reset to the AFU.
  */
-static void context_reset(struct afu_cmd *cmd)
+static void context_reset_ioarrin(struct afu_cmd *cmd)
 {
 	int nretry = 0;
 	u64 rrin = 0x1;
-	u64 room = 0;
 	struct afu *afu = cmd->parent;
-	ulong lock_flags;
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
 
 	pr_debug("%s: cmd=%p\n", __func__, cmd);
 
-	spin_lock_irqsave(&cmd->slock, lock_flags);
-
-	/* Already completed? */
-	if (cmd->sa.host_use_b[0] & B_DONE) {
-		spin_unlock_irqrestore(&cmd->slock, lock_flags);
-		return;
-	}
-
-	cmd->sa.host_use_b[0] |= (B_DONE | B_ERROR | B_TIMEOUT);
-	spin_unlock_irqrestore(&cmd->slock, lock_flags);
-
-	/*
-	 * We really want to send this reset at all costs, so spread
-	 * out wait time on successive retries for available room.
-	 */
-	do {
-		room = readq_be(&afu->host_map->cmd_room);
-		atomic64_set(&afu->room, room);
-		if (room)
-			goto write_rrin;
-		udelay(1 << nretry);
-	} while (nretry++ < MC_ROOM_RETRY_CNT);
-
-	pr_err("%s: no cmd_room to send reset\n", __func__);
-	return;
-
-write_rrin:
-	nretry = 0;
 	writeq_be(rrin, &afu->host_map->ioarrin);
 	do {
 		rrin = readq_be(&afu->host_map->ioarrin);
@@ -305,93 +209,81 @@ write_rrin:
 		/* Double delay each time */
 		udelay(1 << nretry);
 	} while (nretry++ < MC_ROOM_RETRY_CNT);
+
+	dev_dbg(dev, "%s: returning rrin=0x%016llX nretry=%d\n",
+		__func__, rrin, nretry);
 }
 
 /**
- * send_cmd() - sends an AFU command
+ * send_cmd_ioarrin() - sends an AFU command via IOARRIN register
  * @afu:	AFU associated with the host.
  * @cmd:	AFU command to send.
  *
  * Return:
  *	0 on success, SCSI_MLQUEUE_HOST_BUSY on failure
  */
-static int send_cmd(struct afu *afu, struct afu_cmd *cmd)
+static int send_cmd_ioarrin(struct afu *afu, struct afu_cmd *cmd)
 {
 	struct cxlflash_cfg *cfg = afu->parent;
 	struct device *dev = &cfg->dev->dev;
-	int nretry = 0;
 	int rc = 0;
-	u64 room;
-	long newval;
+	s64 room;
+	ulong lock_flags;
 
 	/*
-	 * This routine is used by critical users such an AFU sync and to
-	 * send a task management function (TMF). Thus we want to retry a
-	 * bit before returning an error. To avoid the performance penalty
-	 * of MMIO, we spread the update of 'room' over multiple commands.
+	 * To avoid the performance penalty of MMIO, spread the update of
+	 * 'room' over multiple commands.
 	 */
-retry:
-	newval = atomic64_dec_if_positive(&afu->room);
-	if (!newval) {
-		do {
-			room = readq_be(&afu->host_map->cmd_room);
-			atomic64_set(&afu->room, room);
-			if (room)
-				goto write_ioarrin;
-			udelay(1 << nretry);
-		} while (nretry++ < MC_ROOM_RETRY_CNT);
-
-		dev_err(dev, "%s: no cmd_room to send 0x%X\n",
-		       __func__, cmd->rcb.cdb[0]);
-
-		goto no_room;
-	} else if (unlikely(newval < 0)) {
-		/* This should be rare. i.e. Only if two threads race and
-		 * decrement before the MMIO read is done. In this case
-		 * just benefit from the other thread having updated
-		 * afu->room.
-		 */
-		if (nretry++ < MC_ROOM_RETRY_CNT) {
-			udelay(1 << nretry);
-			goto retry;
+	spin_lock_irqsave(&afu->rrin_slock, lock_flags);
+	if (--afu->room < 0) {
+		room = readq_be(&afu->host_map->cmd_room);
+		if (room <= 0) {
+			dev_dbg_ratelimited(dev, "%s: no cmd_room to send "
+					    "0x%02X, room=0x%016llX\n",
+					    __func__, cmd->rcb.cdb[0], room);
+			afu->room = 0;
+			rc = SCSI_MLQUEUE_HOST_BUSY;
+			goto out;
 		}
-
-		goto no_room;
+		afu->room = room - 1;
 	}
 
-write_ioarrin:
 	writeq_be((u64)&cmd->rcb, &afu->host_map->ioarrin);
 out:
+	spin_unlock_irqrestore(&afu->rrin_slock, lock_flags);
 	pr_devel("%s: cmd=%p len=%d ea=%p rc=%d\n", __func__, cmd,
 		 cmd->rcb.data_len, (void *)cmd->rcb.data_ea, rc);
 	return rc;
-
-no_room:
-	afu->read_room = true;
-	kref_get(&cfg->afu->mapcount);
-	schedule_work(&cfg->work_q);
-	rc = SCSI_MLQUEUE_HOST_BUSY;
-	goto out;
 }
 
 /**
  * wait_resp() - polls for a response or timeout to a sent AFU command
  * @afu:	AFU associated with the host.
  * @cmd:	AFU command that was sent.
+ *
+ * Return:
+ *	0 on success, -1 on timeout/error
  */
-static void wait_resp(struct afu *afu, struct afu_cmd *cmd)
+static int wait_resp(struct afu *afu, struct afu_cmd *cmd)
 {
+	int rc = 0;
 	ulong timeout = msecs_to_jiffies(cmd->rcb.timeout * 2 * 1000);
 
 	timeout = wait_for_completion_timeout(&cmd->cevent, timeout);
-	if (!timeout)
-		context_reset(cmd);
+	if (!timeout) {
+		afu->context_reset(cmd);
+		rc = -1;
+	}
 
-	if (unlikely(cmd->sa.ioasc != 0))
+	if (unlikely(cmd->sa.ioasc != 0)) {
 		pr_err("%s: CMD 0x%X failed, IOASC: flags 0x%X, afu_rc 0x%X, "
 		       "scsi_rc 0x%X, fc_rc 0x%X\n", __func__, cmd->rcb.cdb[0],
 		       cmd->sa.rc.flags, cmd->sa.rc.afu_rc, cmd->sa.rc.scsi_rc,
 		       cmd->sa.rc.fc_rc);
+		rc = -1;
+	}
+
+	return rc;
 }
 
 /**
@@ -405,24 +297,15 @@ static void wait_resp(struct afu *afu, struct afu_cmd *cmd)
  */
 static int send_tmf(struct afu *afu, struct scsi_cmnd *scp, u64 tmfcmd)
 {
-	struct afu_cmd *cmd;
-
 	u32 port_sel = scp->device->channel + 1;
-	short lflag = 0;
 	struct Scsi_Host *host = scp->device->host;
 	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
+	struct afu_cmd *cmd = sc_to_afucz(scp);
 	struct device *dev = &cfg->dev->dev;
 	ulong lock_flags;
 	int rc = 0;
 	ulong to;
 
-	cmd = cmd_checkout(afu);
-	if (unlikely(!cmd)) {
-		dev_err(dev, "%s: could not get a free command\n", __func__);
-		rc = SCSI_MLQUEUE_HOST_BUSY;
-		goto out;
-	}
-
 	/* When Task Management Function is active do not send another */
 	spin_lock_irqsave(&cfg->tmf_slock, lock_flags);
 	if (cfg->tmf_active)
@@ -430,28 +313,23 @@ static int send_tmf(struct afu *afu, struct scsi_cmnd *scp, u64 tmfcmd)
 						  !cfg->tmf_active,
 						  cfg->tmf_slock);
 	cfg->tmf_active = true;
-	cmd->cmd_tmf = true;
 	spin_unlock_irqrestore(&cfg->tmf_slock, lock_flags);
 
+	cmd->scp = scp;
+	cmd->parent = afu;
+	cmd->cmd_tmf = true;
+
 	cmd->rcb.ctx_id = afu->ctx_hndl;
+	cmd->rcb.msi = SISL_MSI_RRQ_UPDATED;
 	cmd->rcb.port_sel = port_sel;
 	cmd->rcb.lun_id = lun_to_lunid(scp->device->lun);
-
-	lflag = SISL_REQ_FLAGS_TMF_CMD;
-
 	cmd->rcb.req_flags = (SISL_REQ_FLAGS_PORT_LUN_ID |
-			      SISL_REQ_FLAGS_SUP_UNDERRUN | lflag);
-
-	/* Stash the scp in the reserved field, for reuse during interrupt */
-	cmd->rcb.scp = scp;
-
-	/* Copy the CDB from the cmd passed in */
+			      SISL_REQ_FLAGS_SUP_UNDERRUN |
+			      SISL_REQ_FLAGS_TMF_CMD);
 	memcpy(cmd->rcb.cdb, &tmfcmd, sizeof(tmfcmd));
 
-	/* Send the command */
-	rc = send_cmd(afu, cmd);
+	rc = afu->send_cmd(afu, cmd);
 	if (unlikely(rc)) {
-		cmd_checkin(cmd);
 		spin_lock_irqsave(&cfg->tmf_slock, lock_flags);
 		cfg->tmf_active = false;
 		spin_unlock_irqrestore(&cfg->tmf_slock, lock_flags);
@@ -507,12 +385,12 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
 	struct afu *afu = cfg->afu;
 	struct device *dev = &cfg->dev->dev;
-	struct afu_cmd *cmd;
+	struct afu_cmd *cmd = sc_to_afucz(scp);
+	struct scatterlist *sg = scsi_sglist(scp);
 	u32 port_sel = scp->device->channel + 1;
-	int nseg, i, ncount;
-	struct scatterlist *sg;
+	u16 req_flags = SISL_REQ_FLAGS_SUP_UNDERRUN;
 	ulong lock_flags;
-	short lflag = 0;
+	int nseg = 0;
 	int rc = 0;
 	int kref_got = 0;
 
@@ -552,55 +430,38 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 		break;
 	}
 
-	cmd = cmd_checkout(afu);
-	if (unlikely(!cmd)) {
-		dev_err(dev, "%s: could not get a free command\n", __func__);
-		rc = SCSI_MLQUEUE_HOST_BUSY;
-		goto out;
-	}
-
 	kref_get(&cfg->afu->mapcount);
 	kref_got = 1;
 
+	if (likely(sg)) {
+		nseg = scsi_dma_map(scp);
+		if (unlikely(nseg < 0)) {
+			dev_err(dev, "%s: Fail DMA map!\n", __func__);
+			rc = SCSI_MLQUEUE_HOST_BUSY;
+			goto out;
+		}
+
+		cmd->rcb.data_len = sg_dma_len(sg);
+		cmd->rcb.data_ea = sg_dma_address(sg);
+	}
+
+	cmd->scp = scp;
+	cmd->parent = afu;
+
 	cmd->rcb.ctx_id = afu->ctx_hndl;
+	cmd->rcb.msi = SISL_MSI_RRQ_UPDATED;
 	cmd->rcb.port_sel = port_sel;
 	cmd->rcb.lun_id = lun_to_lunid(scp->device->lun);
 
 	if (scp->sc_data_direction == DMA_TO_DEVICE)
-		lflag = SISL_REQ_FLAGS_HOST_WRITE;
-	else
-		lflag = SISL_REQ_FLAGS_HOST_READ;
-
-	cmd->rcb.req_flags = (SISL_REQ_FLAGS_PORT_LUN_ID |
-			      SISL_REQ_FLAGS_SUP_UNDERRUN | lflag);
-
-	/* Stash the scp in the reserved field, for reuse during interrupt */
-	cmd->rcb.scp = scp;
-
-	nseg = scsi_dma_map(scp);
-	if (unlikely(nseg < 0)) {
-		dev_err(dev, "%s: Fail DMA map! nseg=%d\n",
-			__func__, nseg);
-		rc = SCSI_MLQUEUE_HOST_BUSY;
-		goto out;
-	}
+		req_flags |= SISL_REQ_FLAGS_HOST_WRITE;
 
-	ncount = scsi_sg_count(scp);
-	scsi_for_each_sg(scp, sg, ncount, i) {
-		cmd->rcb.data_len = sg_dma_len(sg);
-		cmd->rcb.data_ea = sg_dma_address(sg);
-	}
-
-	/* Copy the CDB from the scsi_cmnd passed in */
+	cmd->rcb.req_flags = req_flags;
 	memcpy(cmd->rcb.cdb, scp->cmnd, sizeof(cmd->rcb.cdb));
 
-	/* Send the command */
-	rc = send_cmd(afu, cmd);
-	if (unlikely(rc)) {
-		cmd_checkin(cmd);
+	rc = afu->send_cmd(afu, cmd);
+	if (unlikely(rc))
 		scsi_dma_unmap(scp);
-	}
-
 out:
 	if (kref_got)
 		kref_put(&afu->mapcount, afu_unmap);
@@ -628,17 +489,9 @@ static void cxlflash_wait_for_pci_err_recovery(struct cxlflash_cfg *cfg)
  */
 static void free_mem(struct cxlflash_cfg *cfg)
 {
-	int i;
-	char *buf = NULL;
 	struct afu *afu = cfg->afu;
 
 	if (cfg->afu) {
-		for (i = 0; i < CXLFLASH_NUM_CMDS; i++) {
-			buf = afu->cmd[i].buf;
-			if (!((u64)buf & (PAGE_SIZE - 1)))
-				free_page((ulong)buf);
-		}
-
 		free_pages((ulong)afu, get_order(sizeof(struct afu)));
 		cfg->afu = NULL;
 	}
@@ -650,30 +503,16 @@ static void free_mem(struct cxlflash_cfg *cfg)
  *
  * Safe to call with AFU in a partially allocated/initialized state.
  *
- * Cleans up all state associated with the command queue, and unmaps
+ * Waits for any active internal AFU commands to timeout and then unmaps
  * the MMIO space.
- *
- *  - complete() will take care of commands we initiated (they'll be checked
- *  in as part of the cleanup that occurs after the completion)
- *
- *  - cmd_checkin() will take care of entries that we did not initiate and that
- *  have not (and will not) complete because they are sitting on a [now stale]
- *  hardware queue
  */
 static void stop_afu(struct cxlflash_cfg *cfg)
 {
-	int i;
 	struct afu *afu = cfg->afu;
-	struct afu_cmd *cmd;
 
 	if (likely(afu)) {
-		for (i = 0; i < CXLFLASH_NUM_CMDS; i++) {
-			cmd = &afu->cmd[i];
-			complete(&cmd->cevent);
-			if (!atomic_read(&cmd->free))
-				cmd_checkin(cmd);
-		}
-
+		while (atomic_read(&afu->cmds_active))
+			ssleep(1);
 		if (likely(afu->afu_map)) {
 			cxl_psa_unmap((void __iomem *)afu->afu_map);
 			afu->afu_map = NULL;
@@ -886,8 +725,6 @@ static void cxlflash_remove(struct pci_dev *pdev)
 static int alloc_mem(struct cxlflash_cfg *cfg)
 {
 	int rc = 0;
-	int i;
-	char *buf = NULL;
 	struct device *dev = &cfg->dev->dev;
 
 	/* AFU is ~12k, i.e. only one 64k page or up to four 4k pages */
@@ -901,25 +738,6 @@ static int alloc_mem(struct cxlflash_cfg *cfg)
 	}
 	cfg->afu->parent = cfg;
 	cfg->afu->afu_map = NULL;
-
-	for (i = 0; i < CXLFLASH_NUM_CMDS; buf += CMD_BUFSIZE, i++) {
-		if (!((u64)buf & (PAGE_SIZE - 1))) {
-			buf = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-			if (unlikely(!buf)) {
-				dev_err(dev,
-					"%s: Allocate command buffers fail!\n",
-				       __func__);
-				rc = -ENOMEM;
-				free_mem(cfg);
-				goto out;
-			}
-		}
-
-		cfg->afu->cmd[i].buf = buf;
-		atomic_set(&cfg->afu->cmd[i].free, 1);
-		cfg->afu->cmd[i].slot = i;
-	}
-
 out:
 	return rc;
 }
@@ -1549,13 +1367,6 @@ static void init_pcr(struct cxlflash_cfg *cfg)
 
 	/* Program the Endian Control for the master context */
 	writeq_be(SISL_ENDIAN_CTRL, &afu->host_map->endian_ctrl);
-
-	/* Initialize cmd fields that never change */
-	for (i = 0; i < CXLFLASH_NUM_CMDS; i++) {
-		afu->cmd[i].rcb.ctx_id = afu->ctx_hndl;
-		afu->cmd[i].rcb.msi = SISL_MSI_RRQ_UPDATED;
-		afu->cmd[i].rcb.rrq = 0x0;
-	}
 }
 
 /**
@@ -1644,19 +1455,8 @@ out:
 static int start_afu(struct cxlflash_cfg *cfg)
 {
 	struct afu *afu = cfg->afu;
-	struct afu_cmd *cmd;
-
-	int i = 0;
 	int rc = 0;
 
-	for (i = 0; i < CXLFLASH_NUM_CMDS; i++) {
-		cmd = &afu->cmd[i];
-
-		init_completion(&cmd->cevent);
-		spin_lock_init(&cmd->slock);
-		cmd->parent = afu;
-	}
-
 	init_pcr(cfg);
 
 	/* After an AFU reset, RRQ entries are stale, clear them */
@@ -1829,6 +1629,9 @@ static int init_afu(struct cxlflash_cfg *cfg)
 		goto err2;
 	}
 
+	afu->send_cmd = send_cmd_ioarrin;
+	afu->context_reset = context_reset_ioarrin;
+
 	pr_debug("%s: afu version %s, interface version 0x%llX\n", __func__,
 		 afu->version, afu->interface_version);
 
@@ -1840,7 +1643,8 @@ static int init_afu(struct cxlflash_cfg *cfg)
 	}
 
 	afu_err_intr_init(cfg->afu);
-	atomic64_set(&afu->room, readq_be(&afu->host_map->cmd_room));
+	spin_lock_init(&afu->rrin_slock);
+	afu->room = readq_be(&afu->host_map->cmd_room);
 
 	/* Restore the LUN mappings */
 	cxlflash_restore_luntable(cfg);
@@ -1884,8 +1688,8 @@ int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t ctx_hndl_u,
 	struct cxlflash_cfg *cfg = afu->parent;
 	struct device *dev = &cfg->dev->dev;
 	struct afu_cmd *cmd = NULL;
+	char *buf = NULL;
 	int rc = 0;
-	int retry_cnt = 0;
 	static DEFINE_MUTEX(sync_active);
 
 	if (cfg->state != STATE_NORMAL) {
@@ -1894,27 +1698,23 @@ int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t ctx_hndl_u,
 	}
 
 	mutex_lock(&sync_active);
-retry:
-	cmd = cmd_checkout(afu);
-	if (unlikely(!cmd)) {
-		retry_cnt++;
-		udelay(1000 * retry_cnt);
-		if (retry_cnt < MC_RETRY_CNT)
-			goto retry;
-		dev_err(dev, "%s: could not get a free command\n", __func__);
+	atomic_inc(&afu->cmds_active);
+	buf = kzalloc(sizeof(*cmd) + __alignof__(*cmd) - 1, GFP_KERNEL);
+	if (unlikely(!buf)) {
+		dev_err(dev, "%s: no memory for command\n", __func__);
 		rc = -1;
 		goto out;
 	}
 
-	pr_debug("%s: afu=%p cmd=%p %d\n", __func__, afu, cmd, ctx_hndl_u);
+	cmd = (struct afu_cmd *)PTR_ALIGN(buf, __alignof__(*cmd));
+	init_completion(&cmd->cevent);
+	cmd->parent = afu;
 
-	memset(cmd->rcb.cdb, 0, sizeof(cmd->rcb.cdb));
+	pr_debug("%s: afu=%p cmd=%p %d\n", __func__, afu, cmd, ctx_hndl_u);
 
 	cmd->rcb.req_flags = SISL_REQ_FLAGS_AFU_CMD;
-	cmd->rcb.port_sel = 0x0;	/* NA */
-	cmd->rcb.lun_id = 0x0;	/* NA */
-	cmd->rcb.data_len = 0x0;
-	cmd->rcb.data_ea = 0x0;
+	cmd->rcb.ctx_id = afu->ctx_hndl;
+	cmd->rcb.msi = SISL_MSI_RRQ_UPDATED;
 	cmd->rcb.timeout = MC_AFU_SYNC_TIMEOUT;
 
 	cmd->rcb.cdb[0] = 0xC0;	/* AFU Sync */
@@ -1924,20 +1724,17 @@ retry:
 	*((__be16 *)&cmd->rcb.cdb[2]) = cpu_to_be16(ctx_hndl_u);
 	*((__be32 *)&cmd->rcb.cdb[4]) = cpu_to_be32(res_hndl_u);
 
-	rc = send_cmd(afu, cmd);
+	rc = afu->send_cmd(afu, cmd);
 	if (unlikely(rc))
 		goto out;
 
-	wait_resp(afu, cmd);
-
-	/* Set on timeout */
-	if (unlikely((cmd->sa.ioasc != 0) ||
-		     (cmd->sa.host_use_b[0] & B_ERROR)))
+	rc = wait_resp(afu, cmd);
+	if (unlikely(rc))
 		rc = -1;
 out:
+	atomic_dec(&afu->cmds_active);
 	mutex_unlock(&sync_active);
-	if (cmd)
-		cmd_checkin(cmd);
+	kfree(buf);
 	pr_debug("%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
@@ -2376,8 +2173,9 @@ static struct scsi_host_template driver_template = {
 	.change_queue_depth = cxlflash_change_queue_depth,
 	.cmd_per_lun = CXLFLASH_MAX_CMDS_PER_LUN,
 	.can_queue = CXLFLASH_MAX_CMDS,
+	.cmd_size = sizeof(struct afu_cmd) + __alignof__(struct afu_cmd) - 1,
 	.this_id = -1,
-	.sg_tablesize = SG_NONE,	/* No scatter gather support */
+	.sg_tablesize = 1,	/* No scatter gather support */
 	.max_sectors = CXLFLASH_MAX_SECTORS,
 	.use_clustering = ENABLE_CLUSTERING,
 	.shost_attrs = cxlflash_host_attrs,
@@ -2412,7 +2210,6 @@ MODULE_DEVICE_TABLE(pci, cxlflash_pci_table);
  * Handles the following events:
  * - Link reset which cannot be performed on interrupt context due to
  * blocking up to a few seconds
- * - Read AFU command room
  * - Rescan the host
  */
 static void cxlflash_worker_thread(struct work_struct *work)
@@ -2449,11 +2246,6 @@ static void cxlflash_worker_thread(struct work_struct *work)
 		cfg->lr_state = LINK_RESET_COMPLETE;
 	}
 
-	if (afu->read_room) {
-		atomic64_set(&afu->room, readq_be(&afu->host_map->cmd_room));
-		afu->read_room = false;
-	}
-
 	spin_unlock_irqrestore(cfg->host->host_lock, lock_flags);
 
 	if (atomic_dec_if_positive(&cfg->scan_host_needed) >= 0)
diff --git a/drivers/scsi/cxlflash/sislite.h b/drivers/scsi/cxlflash/sislite.h
index 347fc1671975..1a2d09c148b3 100644
--- a/drivers/scsi/cxlflash/sislite.h
+++ b/drivers/scsi/cxlflash/sislite.h
@@ -72,7 +72,7 @@ struct sisl_ioarcb {
 	u16 timeout;		/* in units specified by req_flags */
 	u32 rsvd1;
 	u8 cdb[16];		/* must be in big endian */
-	struct scsi_cmnd *scp;
+	u64 reserved;		/* Reserved area */
 } __packed;
 
 struct sisl_rc {
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 7bb20684e9fa..d704752b6332 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -95,7 +95,7 @@ struct alua_port_group {
 
 struct alua_dh_data {
 	struct list_head	node;
-	struct alua_port_group	*pg;
+	struct alua_port_group __rcu *pg;
 	int			group_id;
 	spinlock_t		pg_lock;
 	struct scsi_device	*sdev;
@@ -154,7 +154,8 @@ static int submit_rtpg(struct scsi_device *sdev, unsigned char *buff,
 	return scsi_execute_req_flags(sdev, cdb, DMA_FROM_DEVICE,
 				      buff, bufflen, sshdr,
 				      ALUA_FAILOVER_TIMEOUT * HZ,
-				      ALUA_FAILOVER_RETRIES, NULL, req_flags);
+				      ALUA_FAILOVER_RETRIES, NULL,
+				      req_flags, 0);
 }
 
 /*
@@ -187,7 +188,8 @@ static int submit_stpg(struct scsi_device *sdev, int group_id,
 	return scsi_execute_req_flags(sdev, cdb, DMA_TO_DEVICE,
 				      stpg_data, stpg_len,
 				      sshdr, ALUA_FAILOVER_TIMEOUT * HZ,
-				      ALUA_FAILOVER_RETRIES, NULL, req_flags);
+				      ALUA_FAILOVER_RETRIES, NULL,
+				      req_flags, 0);
 }
 
 static struct alua_port_group *alua_find_get_pg(char *id_str, size_t id_size,
@@ -369,7 +371,7 @@ static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h,
 
 	/* Check for existing port group references */
 	spin_lock(&h->pg_lock);
-	old_pg = h->pg;
+	old_pg = rcu_dereference_protected(h->pg, lockdep_is_held(&h->pg_lock));
 	if (old_pg != pg) {
 		/* port group has changed. Update to new port group */
 		if (h->pg) {
@@ -388,7 +390,9 @@ static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h,
 		list_add_rcu(&h->node, &pg->dh_list);
 	spin_unlock_irqrestore(&pg->lock, flags);
 
-	alua_rtpg_queue(h->pg, sdev, NULL, true);
+	alua_rtpg_queue(rcu_dereference_protected(h->pg,
+						  lockdep_is_held(&h->pg_lock)),
+			sdev, NULL, true);
 	spin_unlock(&h->pg_lock);
 
 	if (old_pg)
@@ -940,7 +944,7 @@ static int alua_initialize(struct scsi_device *sdev, struct alua_dh_data *h)
 static int alua_set_params(struct scsi_device *sdev, const char *params)
 {
 	struct alua_dh_data *h = sdev->handler_data;
-	struct alua_port_group __rcu *pg = NULL;
+	struct alua_port_group *pg = NULL;
 	unsigned int optimize = 0, argc;
 	const char *p = params;
 	int result = SCSI_DH_OK;
@@ -987,7 +991,7 @@ static int alua_activate(struct scsi_device *sdev,
 	struct alua_dh_data *h = sdev->handler_data;
 	int err = SCSI_DH_OK;
 	struct alua_queue_data *qdata;
-	struct alua_port_group __rcu *pg;
+	struct alua_port_group *pg;
 
 	qdata = kzalloc(sizeof(*qdata), GFP_KERNEL);
 	if (!qdata) {
@@ -1051,7 +1055,7 @@ static void alua_check(struct scsi_device *sdev, bool force)
 static int alua_prep_fn(struct scsi_device *sdev, struct request *req)
 {
 	struct alua_dh_data *h = sdev->handler_data;
-	struct alua_port_group __rcu *pg;
+	struct alua_port_group *pg;
 	unsigned char state = SCSI_ACCESS_STATE_OPTIMAL;
 	int ret = BLKPREP_OK;
 
@@ -1066,7 +1070,7 @@ static int alua_prep_fn(struct scsi_device *sdev, struct request *req)
 		 state != SCSI_ACCESS_STATE_ACTIVE &&
 		 state != SCSI_ACCESS_STATE_LBA) {
 		ret = BLKPREP_KILL;
-		req->cmd_flags |= REQ_QUIET;
+		req->rq_flags |= RQF_QUIET;
 	}
 	return ret;
 
@@ -1121,7 +1125,7 @@ static void alua_bus_detach(struct scsi_device *sdev)
 	struct alua_port_group *pg;
 
 	spin_lock(&h->pg_lock);
-	pg = h->pg;
+	pg = rcu_dereference_protected(h->pg, lockdep_is_held(&h->pg_lock));
 	rcu_assign_pointer(h->pg, NULL);
 	h->sdev = NULL;
 	spin_unlock(&h->pg_lock);
diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c
index 375d81850f15..5b80746980b8 100644
--- a/drivers/scsi/device_handler/scsi_dh_emc.c
+++ b/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -452,7 +452,7 @@ static int clariion_prep_fn(struct scsi_device *sdev, struct request *req)
 
 	if (h->lun_state != CLARIION_LUN_OWNED) {
 		ret = BLKPREP_KILL;
-		req->cmd_flags |= REQ_QUIET;
+		req->rq_flags |= RQF_QUIET;
 	}
 	return ret;
 
diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
index 9406d5f4a3d3..308e87195dc1 100644
--- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c
+++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
@@ -266,7 +266,7 @@ static int hp_sw_prep_fn(struct scsi_device *sdev, struct request *req)
 
 	if (h->path_state != HP_SW_PATH_ACTIVE) {
 		ret = BLKPREP_KILL;
-		req->cmd_flags |= REQ_QUIET;
+		req->rq_flags |= RQF_QUIET;
 	}
 	return ret;
 
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index 06fbd0b0c68a..00d9c326158e 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -724,7 +724,7 @@ static int rdac_prep_fn(struct scsi_device *sdev, struct request *req)
 
 	if (h->state != RDAC_STATE_ACTIVE) {
 		ret = BLKPREP_KILL;
-		req->cmd_flags |= REQ_QUIET;
+		req->rq_flags |= RQF_QUIET;
 	}
 	return ret;
 
diff --git a/drivers/scsi/dmx3191d.c b/drivers/scsi/dmx3191d.c
index 9b5a457d4bca..6af3394d051d 100644
--- a/drivers/scsi/dmx3191d.c
+++ b/drivers/scsi/dmx3191d.c
@@ -34,13 +34,13 @@
  * Definitions for the generic 5380 driver.
  */
 
-#define NCR5380_read(reg)		inb(instance->io_port + reg)
-#define NCR5380_write(reg, value)	outb(value, instance->io_port + reg)
+#define NCR5380_read(reg)		inb(hostdata->base + (reg))
+#define NCR5380_write(reg, value)	outb(value, hostdata->base + (reg))
 
-#define NCR5380_dma_xfer_len(instance, cmd, phase)	(0)
-#define NCR5380_dma_recv_setup(instance, dst, len)	(0)
-#define NCR5380_dma_send_setup(instance, src, len)	(0)
-#define NCR5380_dma_residual(instance)			(0)
+#define NCR5380_dma_xfer_len		NCR5380_dma_xfer_none
+#define NCR5380_dma_recv_setup		NCR5380_dma_setup_none
+#define NCR5380_dma_send_setup		NCR5380_dma_setup_none
+#define NCR5380_dma_residual		NCR5380_dma_residual_none
 
 #define NCR5380_implementation_fields	/* none */
 
@@ -71,6 +71,7 @@ static int dmx3191d_probe_one(struct pci_dev *pdev,
 			      const struct pci_device_id *id)
 {
 	struct Scsi_Host *shost;
+	struct NCR5380_hostdata *hostdata;
 	unsigned long io;
 	int error = -ENODEV;
 
@@ -88,7 +89,9 @@ static int dmx3191d_probe_one(struct pci_dev *pdev,
 			sizeof(struct NCR5380_hostdata));
 	if (!shost)
 		goto out_release_region;       
-	shost->io_port = io;
+
+	hostdata = shost_priv(shost);
+	hostdata->base = io;
 
 	/* This card does not seem to raise an interrupt on pdev->irq.
 	 * Steam-powered SCSI controllers run without an IRQ anyway.
@@ -125,7 +128,8 @@ out_host_put:
 static void dmx3191d_remove_one(struct pci_dev *pdev)
 {
 	struct Scsi_Host *shost = pci_get_drvdata(pdev);
-	unsigned long io = shost->io_port;
+	struct NCR5380_hostdata *hostdata = shost_priv(shost);
+	unsigned long io = hostdata->base;
 
 	scsi_remove_host(shost);
 
@@ -149,18 +153,7 @@ static struct pci_driver dmx3191d_pci_driver = {
 	.remove		= dmx3191d_remove_one,
 };
 
-static int __init dmx3191d_init(void)
-{
-	return pci_register_driver(&dmx3191d_pci_driver);
-}
-
-static void __exit dmx3191d_exit(void)
-{
-	pci_unregister_driver(&dmx3191d_pci_driver);
-}
-
-module_init(dmx3191d_init);
-module_exit(dmx3191d_exit);
+module_pci_driver(dmx3191d_pci_driver);
 
 MODULE_AUTHOR("Massimo Piccioni <dafastidio@libero.it>");
 MODULE_DESCRIPTION("Domex DMX3191D SCSI driver");
diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c
index 21c8d210c456..5f75e638ec95 100644
--- a/drivers/scsi/dpt_i2o.c
+++ b/drivers/scsi/dpt_i2o.c
@@ -37,7 +37,7 @@ MODULE_DESCRIPTION("Adaptec I2O RAID Driver");
 ////////////////////////////////////////////////////////////////
 
 #include <linux/ioctl.h>	/* For SCSI-Passthrough */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/stat.h>
 #include <linux/slab.h>		/* for kmalloc() */
@@ -651,7 +651,6 @@ static u32 adpt_ioctl_to_context(adpt_hba * pHba, void *reply)
 	}
 	spin_unlock_irqrestore(pHba->host->host_lock, flags);
 	if (i >= nr) {
-		kfree (reply);
 		printk(KERN_WARNING"%s: Too many outstanding "
 				"ioctl commands\n", pHba->name);
 		return (u32)-1;
@@ -1754,8 +1753,10 @@ static int adpt_i2o_passthru(adpt_hba* pHba, u32 __user *arg)
 	sg_offset = (msg[0]>>4)&0xf;
 	msg[2] = 0x40000000; // IOCTL context
 	msg[3] = adpt_ioctl_to_context(pHba, reply);
-	if (msg[3] == (u32)-1)
+	if (msg[3] == (u32)-1) {
+		kfree(reply);
 		return -EBUSY;
+	}
 
 	memset(sg_list,0, sizeof(sg_list[0])*pHba->sg_tablesize);
 	if(sg_offset) {
@@ -3350,7 +3351,7 @@ static int adpt_i2o_query_scalar(adpt_hba* pHba, int tid,
 	if (opblk_va == NULL) {
 		dma_free_coherent(&pHba->pDev->dev, sizeof(u8) * (8+buflen),
 			resblk_va, resblk_pa);
-		printk(KERN_CRIT "%s: query operatio failed; Out of memory.\n",
+		printk(KERN_CRIT "%s: query operation failed; Out of memory.\n",
 			pHba->name);
 		return -ENOMEM;
 	}
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 9bd41a35a78a..59150cad0353 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -63,6 +63,14 @@ unsigned int fcoe_debug_logging;
 module_param_named(debug_logging, fcoe_debug_logging, int, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(debug_logging, "a bit mask of logging levels");
 
+unsigned int fcoe_e_d_tov = 2 * 1000;
+module_param_named(e_d_tov, fcoe_e_d_tov, int, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(e_d_tov, "E_D_TOV in ms, default 2000");
+
+unsigned int fcoe_r_a_tov = 2 * 2 * 1000;
+module_param_named(r_a_tov, fcoe_r_a_tov, int, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(r_a_tov, "R_A_TOV in ms, default 4000");
+
 static DEFINE_MUTEX(fcoe_config_mutex);
 
 static struct workqueue_struct *fcoe_wq;
@@ -582,7 +590,8 @@ static void fcoe_fip_send(struct fcoe_ctlr *fip, struct sk_buff *skb)
 	 * Use default VLAN for FIP VLAN discovery protocol
 	 */
 	frame = (struct fip_frame *)skb->data;
-	if (frame->fip.fip_op == ntohs(FIP_OP_VLAN) &&
+	if (ntohs(frame->eth.h_proto) == ETH_P_FIP &&
+	    ntohs(frame->fip.fip_op) == FIP_OP_VLAN &&
 	    fcoe->realdev != fcoe->netdev)
 		skb->dev = fcoe->realdev;
 	else
@@ -633,8 +642,8 @@ static int fcoe_lport_config(struct fc_lport *lport)
 	lport->qfull = 0;
 	lport->max_retry_count = 3;
 	lport->max_rport_retry_count = 3;
-	lport->e_d_tov = 2 * 1000;	/* FC-FS default */
-	lport->r_a_tov = 2 * 2 * 1000;
+	lport->e_d_tov = fcoe_e_d_tov;
+	lport->r_a_tov = fcoe_r_a_tov;
 	lport->service_params = (FCP_SPPF_INIT_FCN | FCP_SPPF_RD_XRDY_DIS |
 				 FCP_SPPF_RETRY | FCP_SPPF_CONF_COMPL);
 	lport->does_npiv = 1;
@@ -2160,11 +2169,13 @@ static bool fcoe_match(struct net_device *netdev)
  */
 static void fcoe_dcb_create(struct fcoe_interface *fcoe)
 {
+	int ctlr_prio = TC_PRIO_BESTEFFORT;
+	int fcoe_prio = TC_PRIO_INTERACTIVE;
+	struct fcoe_ctlr *ctlr = fcoe_to_ctlr(fcoe);
 #ifdef CONFIG_DCB
 	int dcbx;
 	u8 fup, up;
 	struct net_device *netdev = fcoe->realdev;
-	struct fcoe_ctlr *ctlr = fcoe_to_ctlr(fcoe);
 	struct dcb_app app = {
 				.priority = 0,
 				.protocol = ETH_P_FCOE
@@ -2186,10 +2197,12 @@ static void fcoe_dcb_create(struct fcoe_interface *fcoe)
 			fup = dcb_getapp(netdev, &app);
 		}
 
-		fcoe->priority = ffs(up) ? ffs(up) - 1 : 0;
-		ctlr->priority = ffs(fup) ? ffs(fup) - 1 : fcoe->priority;
+		fcoe_prio = ffs(up) ? ffs(up) - 1 : 0;
+		ctlr_prio = ffs(fup) ? ffs(fup) - 1 : fcoe_prio;
 	}
 #endif
+	fcoe->priority = fcoe_prio;
+	ctlr->priority = ctlr_prio;
 }
 
 enum fcoe_create_link_state {
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index dcf36537a767..cea57e27e713 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -801,6 +801,8 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport,
 	return -EINPROGRESS;
 drop:
 	kfree_skb(skb);
+	LIBFCOE_FIP_DBG(fip, "drop els_send op %u d_id %x\n",
+			op, ntoh24(fh->fh_d_id));
 	return -EINVAL;
 }
 EXPORT_SYMBOL(fcoe_ctlr_els_send);
@@ -1316,7 +1318,7 @@ drop:
  * The overall length has already been checked.
  */
 static void fcoe_ctlr_recv_clr_vlink(struct fcoe_ctlr *fip,
-				     struct fip_header *fh)
+				     struct sk_buff *skb)
 {
 	struct fip_desc *desc;
 	struct fip_mac_desc *mp;
@@ -1331,14 +1333,18 @@ static void fcoe_ctlr_recv_clr_vlink(struct fcoe_ctlr *fip,
 	int num_vlink_desc;
 	int reset_phys_port = 0;
 	struct fip_vn_desc **vlink_desc_arr = NULL;
+	struct fip_header *fh = (struct fip_header *)skb->data;
+	struct ethhdr *eh = eth_hdr(skb);
 
 	LIBFCOE_FIP_DBG(fip, "Clear Virtual Link received\n");
 
-	if (!fcf || !lport->port_id) {
+	if (!fcf) {
 		/*
 		 * We are yet to select best FCF, but we got CVL in the
 		 * meantime. reset the ctlr and let it rediscover the FCF
 		 */
+		LIBFCOE_FIP_DBG(fip, "Resetting fcoe_ctlr as FCF has not been "
+		    "selected yet\n");
 		mutex_lock(&fip->ctlr_mutex);
 		fcoe_ctlr_reset(fip);
 		mutex_unlock(&fip->ctlr_mutex);
@@ -1346,6 +1352,31 @@ static void fcoe_ctlr_recv_clr_vlink(struct fcoe_ctlr *fip,
 	}
 
 	/*
+	 * If we've selected an FCF check that the CVL is from there to avoid
+	 * processing CVLs from an unexpected source.  If it is from an
+	 * unexpected source drop it on the floor.
+	 */
+	if (!ether_addr_equal(eh->h_source, fcf->fcf_mac)) {
+		LIBFCOE_FIP_DBG(fip, "Dropping CVL due to source address "
+		    "mismatch with FCF src=%pM\n", eh->h_source);
+		return;
+	}
+
+	/*
+	 * If we haven't logged into the fabric but receive a CVL we should
+	 * reset everything and go back to solicitation.
+	 */
+	if (!lport->port_id) {
+		LIBFCOE_FIP_DBG(fip, "lport not logged in, resoliciting\n");
+		mutex_lock(&fip->ctlr_mutex);
+		fcoe_ctlr_reset(fip);
+		mutex_unlock(&fip->ctlr_mutex);
+		fc_lport_reset(fip->lp);
+		fcoe_ctlr_solicit(fip, NULL);
+		return;
+	}
+
+	/*
 	 * mask of required descriptors.  Validating each one clears its bit.
 	 */
 	desc_mask = BIT(FIP_DT_MAC) | BIT(FIP_DT_NAME);
@@ -1576,7 +1607,7 @@ static int fcoe_ctlr_recv_handler(struct fcoe_ctlr *fip, struct sk_buff *skb)
 	if (op == FIP_OP_DISC && sub == FIP_SC_ADV)
 		fcoe_ctlr_recv_adv(fip, skb);
 	else if (op == FIP_OP_CTRL && sub == FIP_SC_CLR_VLINK)
-		fcoe_ctlr_recv_clr_vlink(fip, fiph);
+		fcoe_ctlr_recv_clr_vlink(fip, skb);
 	kfree_skb(skb);
 	return 0;
 drop:
@@ -2122,7 +2153,7 @@ static void fcoe_ctlr_vn_rport_callback(struct fc_lport *lport,
 			LIBFCOE_FIP_DBG(fip,
 					"rport FLOGI limited port_id %6.6x\n",
 					rdata->ids.port_id);
-			lport->tt.rport_logoff(rdata);
+			fc_rport_logoff(rdata);
 		}
 		break;
 	default:
@@ -2145,9 +2176,15 @@ static void fcoe_ctlr_disc_stop_locked(struct fc_lport *lport)
 {
 	struct fc_rport_priv *rdata;
 
+	rcu_read_lock();
+	list_for_each_entry_rcu(rdata, &lport->disc.rports, peers) {
+		if (kref_get_unless_zero(&rdata->kref)) {
+			fc_rport_logoff(rdata);
+			kref_put(&rdata->kref, fc_rport_destroy);
+		}
+	}
+	rcu_read_unlock();
 	mutex_lock(&lport->disc.disc_mutex);
-	list_for_each_entry_rcu(rdata, &lport->disc.rports, peers)
-		lport->tt.rport_logoff(rdata);
 	lport->disc.disc_callback = NULL;
 	mutex_unlock(&lport->disc.disc_mutex);
 }
@@ -2178,7 +2215,7 @@ static void fcoe_ctlr_disc_stop(struct fc_lport *lport)
 static void fcoe_ctlr_disc_stop_final(struct fc_lport *lport)
 {
 	fcoe_ctlr_disc_stop(lport);
-	lport->tt.rport_flush_queue();
+	fc_rport_flush_queue();
 	synchronize_rcu();
 }
 
@@ -2393,6 +2430,8 @@ static void fcoe_ctlr_vn_probe_req(struct fcoe_ctlr *fip,
 	switch (fip->state) {
 	case FIP_ST_VNMP_CLAIM:
 	case FIP_ST_VNMP_UP:
+		LIBFCOE_FIP_DBG(fip, "vn_probe_req: send reply, state %x\n",
+				fip->state);
 		fcoe_ctlr_vn_send(fip, FIP_SC_VN_PROBE_REP,
 				  frport->enode_mac, 0);
 		break;
@@ -2407,15 +2446,21 @@ static void fcoe_ctlr_vn_probe_req(struct fcoe_ctlr *fip,
 		 */
 		if (fip->lp->wwpn > rdata->ids.port_name &&
 		    !(frport->flags & FIP_FL_REC_OR_P2P)) {
+			LIBFCOE_FIP_DBG(fip, "vn_probe_req: "
+					"port_id collision\n");
 			fcoe_ctlr_vn_send(fip, FIP_SC_VN_PROBE_REP,
 					  frport->enode_mac, 0);
 			break;
 		}
 		/* fall through */
 	case FIP_ST_VNMP_START:
+		LIBFCOE_FIP_DBG(fip, "vn_probe_req: "
+				"restart VN2VN negotiation\n");
 		fcoe_ctlr_vn_restart(fip);
 		break;
 	default:
+		LIBFCOE_FIP_DBG(fip, "vn_probe_req: ignore state %x\n",
+				fip->state);
 		break;
 	}
 }
@@ -2437,9 +2482,12 @@ static void fcoe_ctlr_vn_probe_reply(struct fcoe_ctlr *fip,
 	case FIP_ST_VNMP_PROBE1:
 	case FIP_ST_VNMP_PROBE2:
 	case FIP_ST_VNMP_CLAIM:
+		LIBFCOE_FIP_DBG(fip, "vn_probe_reply: restart state %x\n",
+				fip->state);
 		fcoe_ctlr_vn_restart(fip);
 		break;
 	case FIP_ST_VNMP_UP:
+		LIBFCOE_FIP_DBG(fip, "vn_probe_reply: send claim notify\n");
 		fcoe_ctlr_vn_send_claim(fip);
 		break;
 	default:
@@ -2467,26 +2515,33 @@ static void fcoe_ctlr_vn_add(struct fcoe_ctlr *fip, struct fc_rport_priv *new)
 		return;
 
 	mutex_lock(&lport->disc.disc_mutex);
-	rdata = lport->tt.rport_create(lport, port_id);
+	rdata = fc_rport_create(lport, port_id);
 	if (!rdata) {
 		mutex_unlock(&lport->disc.disc_mutex);
 		return;
 	}
+	mutex_lock(&rdata->rp_mutex);
+	mutex_unlock(&lport->disc.disc_mutex);
 
 	rdata->ops = &fcoe_ctlr_vn_rport_ops;
 	rdata->disc_id = lport->disc.disc_id;
 
 	ids = &rdata->ids;
 	if ((ids->port_name != -1 && ids->port_name != new->ids.port_name) ||
-	    (ids->node_name != -1 && ids->node_name != new->ids.node_name))
-		lport->tt.rport_logoff(rdata);
+	    (ids->node_name != -1 && ids->node_name != new->ids.node_name)) {
+		mutex_unlock(&rdata->rp_mutex);
+		LIBFCOE_FIP_DBG(fip, "vn_add rport logoff %6.6x\n", port_id);
+		fc_rport_logoff(rdata);
+		mutex_lock(&rdata->rp_mutex);
+	}
 	ids->port_name = new->ids.port_name;
 	ids->node_name = new->ids.node_name;
-	mutex_unlock(&lport->disc.disc_mutex);
+	mutex_unlock(&rdata->rp_mutex);
 
 	frport = fcoe_ctlr_rport(rdata);
-	LIBFCOE_FIP_DBG(fip, "vn_add rport %6.6x %s\n",
-			port_id, frport->fcoe_len ? "old" : "new");
+	LIBFCOE_FIP_DBG(fip, "vn_add rport %6.6x %s state %d\n",
+			port_id, frport->fcoe_len ? "old" : "new",
+			rdata->rp_state);
 	*frport = *fcoe_ctlr_rport(new);
 	frport->time = 0;
 }
@@ -2506,12 +2561,12 @@ static int fcoe_ctlr_vn_lookup(struct fcoe_ctlr *fip, u32 port_id, u8 *mac)
 	struct fcoe_rport *frport;
 	int ret = -1;
 
-	rdata = lport->tt.rport_lookup(lport, port_id);
+	rdata = fc_rport_lookup(lport, port_id);
 	if (rdata) {
 		frport = fcoe_ctlr_rport(rdata);
 		memcpy(mac, frport->enode_mac, ETH_ALEN);
 		ret = 0;
-		kref_put(&rdata->kref, lport->tt.rport_destroy);
+		kref_put(&rdata->kref, fc_rport_destroy);
 	}
 	return ret;
 }
@@ -2529,6 +2584,7 @@ static void fcoe_ctlr_vn_claim_notify(struct fcoe_ctlr *fip,
 	struct fcoe_rport *frport = fcoe_ctlr_rport(new);
 
 	if (frport->flags & FIP_FL_REC_OR_P2P) {
+		LIBFCOE_FIP_DBG(fip, "send probe req for P2P/REC\n");
 		fcoe_ctlr_vn_send(fip, FIP_SC_VN_PROBE_REQ, fcoe_all_vn2vn, 0);
 		return;
 	}
@@ -2536,25 +2592,37 @@ static void fcoe_ctlr_vn_claim_notify(struct fcoe_ctlr *fip,
 	case FIP_ST_VNMP_START:
 	case FIP_ST_VNMP_PROBE1:
 	case FIP_ST_VNMP_PROBE2:
-		if (new->ids.port_id == fip->port_id)
+		if (new->ids.port_id == fip->port_id) {
+			LIBFCOE_FIP_DBG(fip, "vn_claim_notify: "
+					"restart, state %d\n",
+					fip->state);
 			fcoe_ctlr_vn_restart(fip);
+		}
 		break;
 	case FIP_ST_VNMP_CLAIM:
 	case FIP_ST_VNMP_UP:
 		if (new->ids.port_id == fip->port_id) {
 			if (new->ids.port_name > fip->lp->wwpn) {
+				LIBFCOE_FIP_DBG(fip, "vn_claim_notify: "
+						"restart, port_id collision\n");
 				fcoe_ctlr_vn_restart(fip);
 				break;
 			}
+			LIBFCOE_FIP_DBG(fip, "vn_claim_notify: "
+					"send claim notify\n");
 			fcoe_ctlr_vn_send_claim(fip);
 			break;
 		}
+		LIBFCOE_FIP_DBG(fip, "vn_claim_notify: send reply to %x\n",
+				new->ids.port_id);
 		fcoe_ctlr_vn_send(fip, FIP_SC_VN_CLAIM_REP, frport->enode_mac,
 				  min((u32)frport->fcoe_len,
 				      fcoe_ctlr_fcoe_size(fip)));
 		fcoe_ctlr_vn_add(fip, new);
 		break;
 	default:
+		LIBFCOE_FIP_DBG(fip, "vn_claim_notify: "
+				"ignoring claim from %x\n", new->ids.port_id);
 		break;
 	}
 }
@@ -2591,19 +2659,26 @@ static void fcoe_ctlr_vn_beacon(struct fcoe_ctlr *fip,
 
 	frport = fcoe_ctlr_rport(new);
 	if (frport->flags & FIP_FL_REC_OR_P2P) {
+		LIBFCOE_FIP_DBG(fip, "p2p beacon while in vn2vn mode\n");
 		fcoe_ctlr_vn_send(fip, FIP_SC_VN_PROBE_REQ, fcoe_all_vn2vn, 0);
 		return;
 	}
-	rdata = lport->tt.rport_lookup(lport, new->ids.port_id);
+	rdata = fc_rport_lookup(lport, new->ids.port_id);
 	if (rdata) {
 		if (rdata->ids.node_name == new->ids.node_name &&
 		    rdata->ids.port_name == new->ids.port_name) {
 			frport = fcoe_ctlr_rport(rdata);
-			if (!frport->time && fip->state == FIP_ST_VNMP_UP)
-				lport->tt.rport_login(rdata);
+			LIBFCOE_FIP_DBG(fip, "beacon from rport %x\n",
+					rdata->ids.port_id);
+			if (!frport->time && fip->state == FIP_ST_VNMP_UP) {
+				LIBFCOE_FIP_DBG(fip, "beacon expired "
+						"for rport %x\n",
+						rdata->ids.port_id);
+				fc_rport_login(rdata);
+			}
 			frport->time = jiffies;
 		}
-		kref_put(&rdata->kref, lport->tt.rport_destroy);
+		kref_put(&rdata->kref, fc_rport_destroy);
 		return;
 	}
 	if (fip->state != FIP_ST_VNMP_UP)
@@ -2638,11 +2713,15 @@ static unsigned long fcoe_ctlr_vn_age(struct fcoe_ctlr *fip)
 	unsigned long deadline;
 
 	next_time = jiffies + msecs_to_jiffies(FIP_VN_BEACON_INT * 10);
-	mutex_lock(&lport->disc.disc_mutex);
+	rcu_read_lock();
 	list_for_each_entry_rcu(rdata, &lport->disc.rports, peers) {
+		if (!kref_get_unless_zero(&rdata->kref))
+			continue;
 		frport = fcoe_ctlr_rport(rdata);
-		if (!frport->time)
+		if (!frport->time) {
+			kref_put(&rdata->kref, fc_rport_destroy);
 			continue;
+		}
 		deadline = frport->time +
 			   msecs_to_jiffies(FIP_VN_BEACON_INT * 25 / 10);
 		if (time_after_eq(jiffies, deadline)) {
@@ -2650,11 +2729,12 @@ static unsigned long fcoe_ctlr_vn_age(struct fcoe_ctlr *fip)
 			LIBFCOE_FIP_DBG(fip,
 				"port %16.16llx fc_id %6.6x beacon expired\n",
 				rdata->ids.port_name, rdata->ids.port_id);
-			lport->tt.rport_logoff(rdata);
+			fc_rport_logoff(rdata);
 		} else if (time_before(deadline, next_time))
 			next_time = deadline;
+		kref_put(&rdata->kref, fc_rport_destroy);
 	}
-	mutex_unlock(&lport->disc.disc_mutex);
+	rcu_read_unlock();
 	return next_time;
 }
 
@@ -2674,11 +2754,21 @@ static int fcoe_ctlr_vn_recv(struct fcoe_ctlr *fip, struct sk_buff *skb)
 		struct fc_rport_priv rdata;
 		struct fcoe_rport frport;
 	} buf;
-	int rc;
+	int rc, vlan_id = 0;
 
 	fiph = (struct fip_header *)skb->data;
 	sub = fiph->fip_subcode;
 
+	if (fip->lp->vlan)
+		vlan_id = skb_vlan_tag_get_id(skb);
+
+	if (vlan_id && vlan_id != fip->lp->vlan) {
+		LIBFCOE_FIP_DBG(fip, "vn_recv drop frame sub %x vlan %d\n",
+				sub, vlan_id);
+		rc = -EAGAIN;
+		goto drop;
+	}
+
 	rc = fcoe_ctlr_vn_parse(fip, skb, &buf.rdata);
 	if (rc) {
 		LIBFCOE_FIP_DBG(fip, "vn_recv vn_parse error %d\n", rc);
@@ -2941,7 +3031,7 @@ static void fcoe_ctlr_disc_recv(struct fc_lport *lport, struct fc_frame *fp)
 
 	rjt_data.reason = ELS_RJT_UNSUP;
 	rjt_data.explan = ELS_EXPL_NONE;
-	lport->tt.seq_els_rsp_send(fp, ELS_LS_RJT, &rjt_data);
+	fc_seq_els_rsp_send(fp, ELS_LS_RJT, &rjt_data);
 	fc_frame_free(fp);
 }
 
@@ -2991,12 +3081,17 @@ static void fcoe_ctlr_vn_disc(struct fcoe_ctlr *fip)
 	mutex_lock(&disc->disc_mutex);
 	callback = disc->pending ? disc->disc_callback : NULL;
 	disc->pending = 0;
+	mutex_unlock(&disc->disc_mutex);
+	rcu_read_lock();
 	list_for_each_entry_rcu(rdata, &disc->rports, peers) {
+		if (!kref_get_unless_zero(&rdata->kref))
+			continue;
 		frport = fcoe_ctlr_rport(rdata);
 		if (frport->time)
-			lport->tt.rport_login(rdata);
+			fc_rport_login(rdata);
+		kref_put(&rdata->kref, fc_rport_destroy);
 	}
-	mutex_unlock(&disc->disc_mutex);
+	rcu_read_unlock();
 	if (callback)
 		callback(lport, DISC_EV_SUCCESS);
 }
@@ -3015,11 +3110,13 @@ static void fcoe_ctlr_vn_timeout(struct fcoe_ctlr *fip)
 	switch (fip->state) {
 	case FIP_ST_VNMP_START:
 		fcoe_ctlr_set_state(fip, FIP_ST_VNMP_PROBE1);
+		LIBFCOE_FIP_DBG(fip, "vn_timeout: send 1st probe request\n");
 		fcoe_ctlr_vn_send(fip, FIP_SC_VN_PROBE_REQ, fcoe_all_vn2vn, 0);
 		next_time = jiffies + msecs_to_jiffies(FIP_VN_PROBE_WAIT);
 		break;
 	case FIP_ST_VNMP_PROBE1:
 		fcoe_ctlr_set_state(fip, FIP_ST_VNMP_PROBE2);
+		LIBFCOE_FIP_DBG(fip, "vn_timeout: send 2nd probe request\n");
 		fcoe_ctlr_vn_send(fip, FIP_SC_VN_PROBE_REQ, fcoe_all_vn2vn, 0);
 		next_time = jiffies + msecs_to_jiffies(FIP_VN_ANN_WAIT);
 		break;
@@ -3030,6 +3127,7 @@ static void fcoe_ctlr_vn_timeout(struct fcoe_ctlr *fip)
 		hton24(mac + 3, new_port_id);
 		fcoe_ctlr_map_dest(fip);
 		fip->update_mac(fip->lp, mac);
+		LIBFCOE_FIP_DBG(fip, "vn_timeout: send claim notify\n");
 		fcoe_ctlr_vn_send_claim(fip);
 		next_time = jiffies + msecs_to_jiffies(FIP_VN_ANN_WAIT);
 		break;
@@ -3041,6 +3139,7 @@ static void fcoe_ctlr_vn_timeout(struct fcoe_ctlr *fip)
 		next_time = fip->sol_time + msecs_to_jiffies(FIP_VN_ANN_WAIT);
 		if (time_after_eq(jiffies, next_time)) {
 			fcoe_ctlr_set_state(fip, FIP_ST_VNMP_UP);
+			LIBFCOE_FIP_DBG(fip, "vn_timeout: send vn2vn beacon\n");
 			fcoe_ctlr_vn_send(fip, FIP_SC_VN_BEACON,
 					  fcoe_all_vn2vn, 0);
 			next_time = jiffies + msecs_to_jiffies(FIP_VN_ANN_WAIT);
@@ -3051,6 +3150,7 @@ static void fcoe_ctlr_vn_timeout(struct fcoe_ctlr *fip)
 	case FIP_ST_VNMP_UP:
 		next_time = fcoe_ctlr_vn_age(fip);
 		if (time_after_eq(jiffies, fip->port_ka_time)) {
+			LIBFCOE_FIP_DBG(fip, "vn_timeout: send vn2vn beacon\n");
 			fcoe_ctlr_vn_send(fip, FIP_SC_VN_BEACON,
 					  fcoe_all_vn2vn, 0);
 			fip->port_ka_time = jiffies +
@@ -3135,7 +3235,6 @@ int fcoe_libfc_config(struct fc_lport *lport, struct fcoe_ctlr *fip,
 	fc_exch_init(lport);
 	fc_elsct_init(lport);
 	fc_lport_init(lport);
-	fc_rport_init(lport);
 	fc_disc_init(lport);
 	fcoe_ctlr_mode_set(lport, fip, fip->mode);
 	return 0;
diff --git a/drivers/scsi/fcoe/fcoe_sysfs.c b/drivers/scsi/fcoe/fcoe_sysfs.c
index 0675fd128734..9cf3d56296ab 100644
--- a/drivers/scsi/fcoe/fcoe_sysfs.c
+++ b/drivers/scsi/fcoe/fcoe_sysfs.c
@@ -335,16 +335,24 @@ static ssize_t store_ctlr_enabled(struct device *dev,
 				  const char *buf, size_t count)
 {
 	struct fcoe_ctlr_device *ctlr = dev_to_ctlr(dev);
+	bool enabled;
 	int rc;
 
+	if (*buf == '1')
+		enabled = true;
+	else if (*buf == '0')
+		enabled = false;
+	else
+		return -EINVAL;
+
 	switch (ctlr->enabled) {
 	case FCOE_CTLR_ENABLED:
-		if (*buf == '1')
+		if (enabled)
 			return count;
 		ctlr->enabled = FCOE_CTLR_DISABLED;
 		break;
 	case FCOE_CTLR_DISABLED:
-		if (*buf == '0')
+		if (!enabled)
 			return count;
 		ctlr->enabled = FCOE_CTLR_ENABLED;
 		break;
@@ -424,6 +432,75 @@ static FCOE_DEVICE_ATTR(ctlr, fip_vlan_responder, S_IRUGO | S_IWUSR,
 			store_ctlr_fip_resp);
 
 static ssize_t
+fcoe_ctlr_var_store(u32 *var, const char *buf, size_t count)
+{
+	int err;
+	unsigned long v;
+
+	err = kstrtoul(buf, 10, &v);
+	if (err || v > UINT_MAX)
+		return -EINVAL;
+
+	*var = v;
+
+	return count;
+}
+
+static ssize_t store_ctlr_r_a_tov(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct fcoe_ctlr_device *ctlr_dev = dev_to_ctlr(dev);
+	struct fcoe_ctlr *ctlr = fcoe_ctlr_device_priv(ctlr_dev);
+
+	if (ctlr_dev->enabled == FCOE_CTLR_ENABLED)
+		return -EBUSY;
+	if (ctlr_dev->enabled == FCOE_CTLR_DISABLED)
+		return fcoe_ctlr_var_store(&ctlr->lp->r_a_tov, buf, count);
+	return -ENOTSUPP;
+}
+
+static ssize_t show_ctlr_r_a_tov(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	struct fcoe_ctlr_device *ctlr_dev = dev_to_ctlr(dev);
+	struct fcoe_ctlr *ctlr = fcoe_ctlr_device_priv(ctlr_dev);
+
+	return sprintf(buf, "%d\n", ctlr->lp->r_a_tov);
+}
+
+static FCOE_DEVICE_ATTR(ctlr, r_a_tov, S_IRUGO | S_IWUSR,
+			show_ctlr_r_a_tov, store_ctlr_r_a_tov);
+
+static ssize_t store_ctlr_e_d_tov(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct fcoe_ctlr_device *ctlr_dev = dev_to_ctlr(dev);
+	struct fcoe_ctlr *ctlr = fcoe_ctlr_device_priv(ctlr_dev);
+
+	if (ctlr_dev->enabled == FCOE_CTLR_ENABLED)
+		return -EBUSY;
+	if (ctlr_dev->enabled == FCOE_CTLR_DISABLED)
+		return fcoe_ctlr_var_store(&ctlr->lp->e_d_tov, buf, count);
+	return -ENOTSUPP;
+}
+
+static ssize_t show_ctlr_e_d_tov(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	struct fcoe_ctlr_device *ctlr_dev = dev_to_ctlr(dev);
+	struct fcoe_ctlr *ctlr = fcoe_ctlr_device_priv(ctlr_dev);
+
+	return sprintf(buf, "%d\n", ctlr->lp->e_d_tov);
+}
+
+static FCOE_DEVICE_ATTR(ctlr, e_d_tov, S_IRUGO | S_IWUSR,
+			show_ctlr_e_d_tov, store_ctlr_e_d_tov);
+
+static ssize_t
 store_private_fcoe_ctlr_fcf_dev_loss_tmo(struct device *dev,
 					 struct device_attribute *attr,
 					 const char *buf, size_t count)
@@ -507,6 +584,8 @@ static struct attribute_group fcoe_ctlr_lesb_attr_group = {
 static struct attribute *fcoe_ctlr_attrs[] = {
 	&device_attr_fcoe_ctlr_fip_vlan_responder.attr,
 	&device_attr_fcoe_ctlr_fcf_dev_loss_tmo.attr,
+	&device_attr_fcoe_ctlr_r_a_tov.attr,
+	&device_attr_fcoe_ctlr_e_d_tov.attr,
 	&device_attr_fcoe_ctlr_enabled.attr,
 	&device_attr_fcoe_ctlr_mode.attr,
 	NULL,
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index d9fd2f841585..2544a37ece0a 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -441,30 +441,38 @@ static int fnic_queuecommand_lck(struct scsi_cmnd *sc, void (*done)(struct scsi_
 	unsigned long ptr;
 	spinlock_t *io_lock = NULL;
 	int io_lock_acquired = 0;
+	struct fc_rport_libfc_priv *rp;
 
 	if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_IO_BLOCKED)))
 		return SCSI_MLQUEUE_HOST_BUSY;
 
 	rport = starget_to_rport(scsi_target(sc->device));
+	if (!rport) {
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+				"returning DID_NO_CONNECT for IO as rport is NULL\n");
+		sc->result = DID_NO_CONNECT << 16;
+		done(sc);
+		return 0;
+	}
+
 	ret = fc_remote_port_chkready(rport);
 	if (ret) {
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+				"rport is not ready\n");
 		atomic64_inc(&fnic_stats->misc_stats.rport_not_ready);
 		sc->result = ret;
 		done(sc);
 		return 0;
 	}
 
-	if (rport) {
-		struct fc_rport_libfc_priv *rp = rport->dd_data;
-
-		if (!rp || rp->rp_state != RPORT_ST_READY) {
-			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+	rp = rport->dd_data;
+	if (!rp || rp->rp_state != RPORT_ST_READY) {
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
 				"returning DID_NO_CONNECT for IO as rport is removed\n");
-			atomic64_inc(&fnic_stats->misc_stats.rport_not_ready);
-			sc->result = DID_NO_CONNECT<<16;
-			done(sc);
-			return 0;
-		}
+		atomic64_inc(&fnic_stats->misc_stats.rport_not_ready);
+		sc->result = DID_NO_CONNECT<<16;
+		done(sc);
+		return 0;
 	}
 
 	if (lp->state != LPORT_ST_READY || !(lp->link_up))
@@ -2543,7 +2551,7 @@ int fnic_reset(struct Scsi_Host *shost)
 	 * Reset local port, this will clean up libFC exchanges,
 	 * reset remote port sessions, and if link is up, begin flogi
 	 */
-	ret = lp->tt.lport_reset(lp);
+	ret = fc_lport_reset(lp);
 
 	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
 		      "Returning from fnic reset %s\n",
diff --git a/drivers/scsi/fnic/fnic_trace.c b/drivers/scsi/fnic/fnic_trace.c
index 4e15c4bf0795..5a5fa01576b7 100644
--- a/drivers/scsi/fnic/fnic_trace.c
+++ b/drivers/scsi/fnic/fnic_trace.c
@@ -613,7 +613,7 @@ int fnic_fc_trace_set_data(u32 host_no, u8 frame_type,
 			fc_trace_entries.rd_idx = 0;
 	}
 
-	fc_buf->time_stamp = CURRENT_TIME;
+	ktime_get_real_ts64(&fc_buf->time_stamp);
 	fc_buf->host_no = host_no;
 	fc_buf->frame_type = frame_type;
 
@@ -740,7 +740,7 @@ void copy_and_format_trace_data(struct fc_trace_hdr *tdata,
 
 	len = *orig_len;
 
-	time_to_tm(tdata->time_stamp.tv_sec, 0, &tm);
+	time64_to_tm(tdata->time_stamp.tv_sec, 0, &tm);
 
 	fmt = "%02d:%02d:%04ld %02d:%02d:%02d.%09lu ns%8x       %c%8x\t";
 	len += snprintf(fnic_dbgfs_prt->buffer + len,
diff --git a/drivers/scsi/fnic/fnic_trace.h b/drivers/scsi/fnic/fnic_trace.h
index a8aa0578fcb0..e375d0c2eaaf 100644
--- a/drivers/scsi/fnic/fnic_trace.h
+++ b/drivers/scsi/fnic/fnic_trace.h
@@ -72,7 +72,7 @@ struct fnic_trace_data {
 typedef struct fnic_trace_data fnic_trace_data_t;
 
 struct fc_trace_hdr {
-	struct timespec time_stamp;
+	struct timespec64 time_stamp;
 	u32 host_no;
 	u8 frame_type;
 	u8 frame_len;
diff --git a/drivers/scsi/fnic/vnic_dev.c b/drivers/scsi/fnic/vnic_dev.c
index 9795d6f3e197..ba69d6112fa1 100644
--- a/drivers/scsi/fnic/vnic_dev.c
+++ b/drivers/scsi/fnic/vnic_dev.c
@@ -499,10 +499,7 @@ void vnic_dev_add_addr(struct vnic_dev *vdev, u8 *addr)
 
 	err = vnic_dev_cmd(vdev, CMD_ADDR_ADD, &a0, &a1, wait);
 	if (err)
-		printk(KERN_ERR
-			"Can't add addr [%02x:%02x:%02x:%02x:%02x:%02x], %d\n",
-			addr[0], addr[1], addr[2], addr[3], addr[4], addr[5],
-			err);
+		pr_err("Can't add addr [%pM], %d\n", addr, err);
 }
 
 void vnic_dev_del_addr(struct vnic_dev *vdev, u8 *addr)
@@ -517,10 +514,7 @@ void vnic_dev_del_addr(struct vnic_dev *vdev, u8 *addr)
 
 	err = vnic_dev_cmd(vdev, CMD_ADDR_DEL, &a0, &a1, wait);
 	if (err)
-		printk(KERN_ERR
-			"Can't del addr [%02x:%02x:%02x:%02x:%02x:%02x], %d\n",
-			addr[0], addr[1], addr[2], addr[3], addr[4], addr[5],
-			err);
+		pr_err("Can't del addr [%pM], %d\n", addr, err);
 }
 
 int vnic_dev_notify_set(struct vnic_dev *vdev, u16 intr)
diff --git a/drivers/scsi/g_NCR5380.c b/drivers/scsi/g_NCR5380.c
index cbf010324c18..6f9665d50d84 100644
--- a/drivers/scsi/g_NCR5380.c
+++ b/drivers/scsi/g_NCR5380.c
@@ -37,7 +37,7 @@
 #define MAX_CARDS 8
 
 /* old-style parameters for compatibility */
-static int ncr_irq;
+static int ncr_irq = -1;
 static int ncr_addr;
 static int ncr_5380;
 static int ncr_53c400;
@@ -52,9 +52,9 @@ module_param(ncr_53c400a, int, 0);
 module_param(dtc_3181e, int, 0);
 module_param(hp_c2502, int, 0);
 
-static int irq[] = { 0, 0, 0, 0, 0, 0, 0, 0 };
+static int irq[] = { -1, -1, -1, -1, -1, -1, -1, -1 };
 module_param_array(irq, int, NULL, 0);
-MODULE_PARM_DESC(irq, "IRQ number(s)");
+MODULE_PARM_DESC(irq, "IRQ number(s) (0=none, 254=auto [default])");
 
 static int base[] = { 0, 0, 0, 0, 0, 0, 0, 0 };
 module_param_array(base, int, NULL, 0);
@@ -64,9 +64,59 @@ static int card[] = { -1, -1, -1, -1, -1, -1, -1, -1 };
 module_param_array(card, int, NULL, 0);
 MODULE_PARM_DESC(card, "card type (0=NCR5380, 1=NCR53C400, 2=NCR53C400A, 3=DTC3181E, 4=HP C2502)");
 
+MODULE_ALIAS("g_NCR5380_mmio");
 MODULE_LICENSE("GPL");
 
-#ifndef SCSI_G_NCR5380_MEM
+static void g_NCR5380_trigger_irq(struct Scsi_Host *instance)
+{
+	struct NCR5380_hostdata *hostdata = shost_priv(instance);
+
+	/*
+	 * An interrupt is triggered whenever BSY = false, SEL = true
+	 * and a bit set in the SELECT_ENABLE_REG is asserted on the
+	 * SCSI bus.
+	 *
+	 * Note that the bus is only driven when the phase control signals
+	 * (I/O, C/D, and MSG) match those in the TCR.
+	 */
+	NCR5380_write(TARGET_COMMAND_REG,
+	              PHASE_SR_TO_TCR(NCR5380_read(STATUS_REG) & PHASE_MASK));
+	NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask);
+	NCR5380_write(OUTPUT_DATA_REG, hostdata->id_mask);
+	NCR5380_write(INITIATOR_COMMAND_REG,
+	              ICR_BASE | ICR_ASSERT_DATA | ICR_ASSERT_SEL);
+
+	msleep(1);
+
+	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
+	NCR5380_write(SELECT_ENABLE_REG, 0);
+	NCR5380_write(TARGET_COMMAND_REG, 0);
+}
+
+/**
+ * g_NCR5380_probe_irq - find the IRQ of a NCR5380 or equivalent
+ * @instance: SCSI host instance
+ *
+ * Autoprobe for the IRQ line used by the card by triggering an IRQ
+ * and then looking to see what interrupt actually turned up.
+ */
+
+static int g_NCR5380_probe_irq(struct Scsi_Host *instance)
+{
+	struct NCR5380_hostdata *hostdata = shost_priv(instance);
+	int irq_mask, irq;
+
+	NCR5380_read(RESET_PARITY_INTERRUPT_REG);
+	irq_mask = probe_irq_on();
+	g_NCR5380_trigger_irq(instance);
+	irq = probe_irq_off(irq_mask);
+	NCR5380_read(RESET_PARITY_INTERRUPT_REG);
+
+	if (irq <= 0)
+		return NO_IRQ;
+	return irq;
+}
+
 /*
  * Configure I/O address of 53C400A or DTC436 by writing magic numbers
  * to ports 0x779 and 0x379.
@@ -81,47 +131,64 @@ static void magic_configure(int idx, u8 irq, u8 magic[])
 	outb(magic[3], 0x379);
 	outb(magic[4], 0x379);
 
-	/* allowed IRQs for HP C2502 */
-	if (irq != 2 && irq != 3 && irq != 4 && irq != 5 && irq != 7)
-		irq = 0;
+	if (irq == 9)
+		irq = 2;
+
 	if (idx >= 0 && idx <= 7)
 		cfg = 0x80 | idx | (irq << 4);
 	outb(cfg, 0x379);
 }
-#endif
+
+static irqreturn_t legacy_empty_irq_handler(int irq, void *dev_id)
+{
+	return IRQ_HANDLED;
+}
+
+static int legacy_find_free_irq(int *irq_table)
+{
+	while (*irq_table != -1) {
+		if (!request_irq(*irq_table, legacy_empty_irq_handler,
+		                 IRQF_PROBE_SHARED, "Test IRQ",
+		                 (void *)irq_table)) {
+			free_irq(*irq_table, (void *) irq_table);
+			return *irq_table;
+		}
+		irq_table++;
+	}
+	return -1;
+}
+
+static unsigned int ncr_53c400a_ports[] = {
+	0x280, 0x290, 0x300, 0x310, 0x330, 0x340, 0x348, 0x350, 0
+};
+static unsigned int dtc_3181e_ports[] = {
+	0x220, 0x240, 0x280, 0x2a0, 0x2c0, 0x300, 0x320, 0x340, 0
+};
+static u8 ncr_53c400a_magic[] = {	/* 53C400A & DTC436 */
+	0x59, 0xb9, 0xc5, 0xae, 0xa6
+};
+static u8 hp_c2502_magic[] = {	/* HP C2502 */
+	0x0f, 0x22, 0xf0, 0x20, 0x80
+};
+static int hp_c2502_irqs[] = {
+	9, 5, 7, 3, 4, -1
+};
 
 static int generic_NCR5380_init_one(struct scsi_host_template *tpnt,
 			struct device *pdev, int base, int irq, int board)
 {
-	unsigned int *ports;
+	bool is_pmio = base <= 0xffff;
+	int ret;
+	int flags = 0;
+	unsigned int *ports = NULL;
 	u8 *magic = NULL;
-#ifndef SCSI_G_NCR5380_MEM
 	int i;
 	int port_idx = -1;
 	unsigned long region_size;
-#endif
-	static unsigned int ncr_53c400a_ports[] = {
-		0x280, 0x290, 0x300, 0x310, 0x330, 0x340, 0x348, 0x350, 0
-	};
-	static unsigned int dtc_3181e_ports[] = {
-		0x220, 0x240, 0x280, 0x2a0, 0x2c0, 0x300, 0x320, 0x340, 0
-	};
-	static u8 ncr_53c400a_magic[] = {	/* 53C400A & DTC436 */
-		0x59, 0xb9, 0xc5, 0xae, 0xa6
-	};
-	static u8 hp_c2502_magic[] = {	/* HP C2502 */
-		0x0f, 0x22, 0xf0, 0x20, 0x80
-	};
-	int flags, ret;
 	struct Scsi_Host *instance;
 	struct NCR5380_hostdata *hostdata;
-#ifdef SCSI_G_NCR5380_MEM
-	void __iomem *iomem;
-	resource_size_t iomem_size;
-#endif
+	u8 __iomem *iomem;
 
-	ports = NULL;
-	flags = 0;
 	switch (board) {
 	case BOARD_NCR5380:
 		flags = FLAG_NO_PSEUDO_DMA | FLAG_DMA_FIXUP;
@@ -140,8 +207,7 @@ static int generic_NCR5380_init_one(struct scsi_host_template *tpnt,
 		break;
 	}
 
-#ifndef SCSI_G_NCR5380_MEM
-	if (ports && magic) {
+	if (is_pmio && ports && magic) {
 		/* wakeup sequence for the NCR53C400A and DTC3181E */
 
 		/* Disable the adapter and look for a free io port */
@@ -170,84 +236,96 @@ static int generic_NCR5380_init_one(struct scsi_host_template *tpnt,
 		if (ports[i]) {
 			/* At this point we have our region reserved */
 			magic_configure(i, 0, magic); /* no IRQ yet */
-			outb(0xc0, ports[i] + 9);
-			if (inb(ports[i] + 9) != 0x80) {
+			base = ports[i];
+			outb(0xc0, base + 9);
+			if (inb(base + 9) != 0x80) {
 				ret = -ENODEV;
 				goto out_release;
 			}
-			base = ports[i];
 			port_idx = i;
 		} else
 			return -EINVAL;
-	}
-	else
-	{
+	} else if (is_pmio) {
 		/* NCR5380 - no configuration, just grab */
 		region_size = 8;
 		if (!base || !request_region(base, region_size, "ncr5380"))
 			return -EBUSY;
+	} else {	/* MMIO */
+		region_size = NCR53C400_region_size;
+		if (!request_mem_region(base, region_size, "ncr5380"))
+			return -EBUSY;
 	}
-#else
-	iomem_size = NCR53C400_region_size;
-	if (!request_mem_region(base, iomem_size, "ncr5380"))
-		return -EBUSY;
-	iomem = ioremap(base, iomem_size);
+
+	if (is_pmio)
+		iomem = ioport_map(base, region_size);
+	else
+		iomem = ioremap(base, region_size);
+
 	if (!iomem) {
-		release_mem_region(base, iomem_size);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out_release;
 	}
-#endif
+
 	instance = scsi_host_alloc(tpnt, sizeof(struct NCR5380_hostdata));
 	if (instance == NULL) {
 		ret = -ENOMEM;
-		goto out_release;
+		goto out_unmap;
 	}
 	hostdata = shost_priv(instance);
 
-#ifndef SCSI_G_NCR5380_MEM
-	instance->io_port = base;
-	instance->n_io_port = region_size;
-	hostdata->io_width = 1; /* 8-bit PDMA by default */
-
-	/*
-	 * On NCR53C400 boards, NCR5380 registers are mapped 8 past
-	 * the base address.
-	 */
-	switch (board) {
-	case BOARD_NCR53C400:
-		instance->io_port += 8;
-		hostdata->c400_ctl_status = 0;
-		hostdata->c400_blk_cnt = 1;
-		hostdata->c400_host_buf = 4;
-		break;
-	case BOARD_DTC3181E:
-		hostdata->io_width = 2;	/* 16-bit PDMA */
-		/* fall through */
-	case BOARD_NCR53C400A:
-	case BOARD_HP_C2502:
-		hostdata->c400_ctl_status = 9;
-		hostdata->c400_blk_cnt = 10;
-		hostdata->c400_host_buf = 8;
-		break;
+	hostdata->io = iomem;
+	hostdata->region_size = region_size;
+
+	if (is_pmio) {
+		hostdata->io_port = base;
+		hostdata->io_width = 1; /* 8-bit PDMA by default */
+		hostdata->offset = 0;
+
+		/*
+		 * On NCR53C400 boards, NCR5380 registers are mapped 8 past
+		 * the base address.
+		 */
+		switch (board) {
+		case BOARD_NCR53C400:
+			hostdata->io_port += 8;
+			hostdata->c400_ctl_status = 0;
+			hostdata->c400_blk_cnt = 1;
+			hostdata->c400_host_buf = 4;
+			break;
+		case BOARD_DTC3181E:
+			hostdata->io_width = 2;	/* 16-bit PDMA */
+			/* fall through */
+		case BOARD_NCR53C400A:
+		case BOARD_HP_C2502:
+			hostdata->c400_ctl_status = 9;
+			hostdata->c400_blk_cnt = 10;
+			hostdata->c400_host_buf = 8;
+			break;
+		}
+	} else {
+		hostdata->base = base;
+		hostdata->offset = NCR53C400_mem_base;
+		switch (board) {
+		case BOARD_NCR53C400:
+			hostdata->c400_ctl_status = 0x100;
+			hostdata->c400_blk_cnt = 0x101;
+			hostdata->c400_host_buf = 0x104;
+			break;
+		case BOARD_DTC3181E:
+		case BOARD_NCR53C400A:
+		case BOARD_HP_C2502:
+			pr_err(DRV_MODULE_NAME ": unknown register offsets\n");
+			ret = -EINVAL;
+			goto out_unregister;
+		}
 	}
-#else
-	instance->base = base;
-	hostdata->iomem = iomem;
-	hostdata->iomem_size = iomem_size;
-	switch (board) {
-	case BOARD_NCR53C400:
-		hostdata->c400_ctl_status = 0x100;
-		hostdata->c400_blk_cnt = 0x101;
-		hostdata->c400_host_buf = 0x104;
-		break;
-	case BOARD_DTC3181E:
-	case BOARD_NCR53C400A:
-	case BOARD_HP_C2502:
-		pr_err(DRV_MODULE_NAME ": unknown register offsets\n");
-		ret = -EINVAL;
+
+	/* Check for vacant slot */
+	NCR5380_write(MODE_REG, 0);
+	if (NCR5380_read(MODE_REG) != 0) {
+		ret = -ENODEV;
 		goto out_unregister;
 	}
-#endif
 
 	ret = NCR5380_init(instance, flags | FLAG_LATE_DMA_SETUP);
 	if (ret)
@@ -263,33 +341,59 @@ static int generic_NCR5380_init_one(struct scsi_host_template *tpnt,
 
 	NCR5380_maybe_reset_bus(instance);
 
-	if (irq != IRQ_AUTO)
-		instance->irq = irq;
-	else
-		instance->irq = NCR5380_probe_irq(instance, 0xffff);
-
 	/* Compatibility with documented NCR5380 kernel parameters */
-	if (instance->irq == 255)
-		instance->irq = NO_IRQ;
+	if (irq == 255 || irq == 0)
+		irq = NO_IRQ;
+	else if (irq == -1)
+		irq = IRQ_AUTO;
+
+	if (board == BOARD_HP_C2502) {
+		int *irq_table = hp_c2502_irqs;
+		int board_irq = -1;
+
+		switch (irq) {
+		case NO_IRQ:
+			board_irq = 0;
+			break;
+		case IRQ_AUTO:
+			board_irq = legacy_find_free_irq(irq_table);
+			break;
+		default:
+			while (*irq_table != -1)
+				if (*irq_table++ == irq)
+					board_irq = irq;
+		}
+
+		if (board_irq <= 0) {
+			board_irq = 0;
+			irq = NO_IRQ;
+		}
+
+		magic_configure(port_idx, board_irq, magic);
+	}
+
+	if (irq == IRQ_AUTO) {
+		instance->irq = g_NCR5380_probe_irq(instance);
+		if (instance->irq == NO_IRQ)
+			shost_printk(KERN_INFO, instance, "no irq detected\n");
+	} else {
+		instance->irq = irq;
+		if (instance->irq == NO_IRQ)
+			shost_printk(KERN_INFO, instance, "no irq provided\n");
+	}
 
 	if (instance->irq != NO_IRQ) {
-#ifndef SCSI_G_NCR5380_MEM
-		/* set IRQ for HP C2502 */
-		if (board == BOARD_HP_C2502)
-			magic_configure(port_idx, instance->irq, magic);
-#endif
 		if (request_irq(instance->irq, generic_NCR5380_intr,
 				0, "NCR5380", instance)) {
-			printk(KERN_WARNING "scsi%d : IRQ%d not free, interrupts disabled\n", instance->host_no, instance->irq);
 			instance->irq = NO_IRQ;
+			shost_printk(KERN_INFO, instance,
+			             "irq %d denied\n", instance->irq);
+		} else {
+			shost_printk(KERN_INFO, instance,
+			             "irq %d acquired\n", instance->irq);
 		}
 	}
 
-	if (instance->irq == NO_IRQ) {
-		printk(KERN_INFO "scsi%d : interrupts not enabled. for better interactive performance,\n", instance->host_no);
-		printk(KERN_INFO "scsi%d : please jumper the board for a free IRQ.\n", instance->host_no);
-	}
-
 	ret = scsi_add_host(instance, pdev);
 	if (ret)
 		goto out_free_irq;
@@ -303,38 +407,39 @@ out_free_irq:
 	NCR5380_exit(instance);
 out_unregister:
 	scsi_host_put(instance);
-out_release:
-#ifndef SCSI_G_NCR5380_MEM
-	release_region(base, region_size);
-#else
+out_unmap:
 	iounmap(iomem);
-	release_mem_region(base, iomem_size);
-#endif
+out_release:
+	if (is_pmio)
+		release_region(base, region_size);
+	else
+		release_mem_region(base, region_size);
 	return ret;
 }
 
 static void generic_NCR5380_release_resources(struct Scsi_Host *instance)
 {
+	struct NCR5380_hostdata *hostdata = shost_priv(instance);
+	void __iomem *iomem = hostdata->io;
+	unsigned long io_port = hostdata->io_port;
+	unsigned long base = hostdata->base;
+	unsigned long region_size = hostdata->region_size;
+
 	scsi_remove_host(instance);
 	if (instance->irq != NO_IRQ)
 		free_irq(instance->irq, instance);
 	NCR5380_exit(instance);
-#ifndef SCSI_G_NCR5380_MEM
-	release_region(instance->io_port, instance->n_io_port);
-#else
-	{
-		struct NCR5380_hostdata *hostdata = shost_priv(instance);
-
-		iounmap(hostdata->iomem);
-		release_mem_region(instance->base, hostdata->iomem_size);
-	}
-#endif
 	scsi_host_put(instance);
+	iounmap(iomem);
+	if (io_port)
+		release_region(io_port, region_size);
+	else
+		release_mem_region(base, region_size);
 }
 
 /**
  *	generic_NCR5380_pread - pseudo DMA read
- *	@instance: adapter to read from
+ *	@hostdata: scsi host private data
  *	@dst: buffer to read into
  *	@len: buffer length
  *
@@ -342,10 +447,9 @@ static void generic_NCR5380_release_resources(struct Scsi_Host *instance)
  *	controller
  */
  
-static inline int generic_NCR5380_pread(struct Scsi_Host *instance,
+static inline int generic_NCR5380_pread(struct NCR5380_hostdata *hostdata,
                                         unsigned char *dst, int len)
 {
-	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	int blocks = len / 128;
 	int start = 0;
 
@@ -361,18 +465,16 @@ static inline int generic_NCR5380_pread(struct Scsi_Host *instance,
 		while (NCR5380_read(hostdata->c400_ctl_status) & CSR_HOST_BUF_NOT_RDY)
 			; /* FIXME - no timeout */
 
-#ifndef SCSI_G_NCR5380_MEM
-		if (hostdata->io_width == 2)
-			insw(instance->io_port + hostdata->c400_host_buf,
+		if (hostdata->io_port && hostdata->io_width == 2)
+			insw(hostdata->io_port + hostdata->c400_host_buf,
 							dst + start, 64);
-		else
-			insb(instance->io_port + hostdata->c400_host_buf,
+		else if (hostdata->io_port)
+			insb(hostdata->io_port + hostdata->c400_host_buf,
 							dst + start, 128);
-#else
-		/* implies SCSI_G_NCR5380_MEM */
-		memcpy_fromio(dst + start,
-		              hostdata->iomem + NCR53C400_host_buffer, 128);
-#endif
+		else
+			memcpy_fromio(dst + start,
+				hostdata->io + NCR53C400_host_buffer, 128);
+
 		start += 128;
 		blocks--;
 	}
@@ -381,18 +483,16 @@ static inline int generic_NCR5380_pread(struct Scsi_Host *instance,
 		while (NCR5380_read(hostdata->c400_ctl_status) & CSR_HOST_BUF_NOT_RDY)
 			; /* FIXME - no timeout */
 
-#ifndef SCSI_G_NCR5380_MEM
-		if (hostdata->io_width == 2)
-			insw(instance->io_port + hostdata->c400_host_buf,
+		if (hostdata->io_port && hostdata->io_width == 2)
+			insw(hostdata->io_port + hostdata->c400_host_buf,
 							dst + start, 64);
-		else
-			insb(instance->io_port + hostdata->c400_host_buf,
+		else if (hostdata->io_port)
+			insb(hostdata->io_port + hostdata->c400_host_buf,
 							dst + start, 128);
-#else
-		/* implies SCSI_G_NCR5380_MEM */
-		memcpy_fromio(dst + start,
-		              hostdata->iomem + NCR53C400_host_buffer, 128);
-#endif
+		else
+			memcpy_fromio(dst + start,
+				hostdata->io + NCR53C400_host_buffer, 128);
+
 		start += 128;
 		blocks--;
 	}
@@ -412,7 +512,7 @@ static inline int generic_NCR5380_pread(struct Scsi_Host *instance,
 
 /**
  *	generic_NCR5380_pwrite - pseudo DMA write
- *	@instance: adapter to read from
+ *	@hostdata: scsi host private data
  *	@dst: buffer to read into
  *	@len: buffer length
  *
@@ -420,10 +520,9 @@ static inline int generic_NCR5380_pread(struct Scsi_Host *instance,
  *	controller
  */
 
-static inline int generic_NCR5380_pwrite(struct Scsi_Host *instance,
+static inline int generic_NCR5380_pwrite(struct NCR5380_hostdata *hostdata,
                                          unsigned char *src, int len)
 {
-	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	int blocks = len / 128;
 	int start = 0;
 
@@ -439,18 +538,17 @@ static inline int generic_NCR5380_pwrite(struct Scsi_Host *instance,
 			break;
 		while (NCR5380_read(hostdata->c400_ctl_status) & CSR_HOST_BUF_NOT_RDY)
 			; // FIXME - timeout
-#ifndef SCSI_G_NCR5380_MEM
-		if (hostdata->io_width == 2)
-			outsw(instance->io_port + hostdata->c400_host_buf,
+
+		if (hostdata->io_port && hostdata->io_width == 2)
+			outsw(hostdata->io_port + hostdata->c400_host_buf,
 							src + start, 64);
-		else
-			outsb(instance->io_port + hostdata->c400_host_buf,
+		else if (hostdata->io_port)
+			outsb(hostdata->io_port + hostdata->c400_host_buf,
 							src + start, 128);
-#else
-		/* implies SCSI_G_NCR5380_MEM */
-		memcpy_toio(hostdata->iomem + NCR53C400_host_buffer,
-		            src + start, 128);
-#endif
+		else
+			memcpy_toio(hostdata->io + NCR53C400_host_buffer,
+			            src + start, 128);
+
 		start += 128;
 		blocks--;
 	}
@@ -458,18 +556,16 @@ static inline int generic_NCR5380_pwrite(struct Scsi_Host *instance,
 		while (NCR5380_read(hostdata->c400_ctl_status) & CSR_HOST_BUF_NOT_RDY)
 			; // FIXME - no timeout
 
-#ifndef SCSI_G_NCR5380_MEM
-		if (hostdata->io_width == 2)
-			outsw(instance->io_port + hostdata->c400_host_buf,
+		if (hostdata->io_port && hostdata->io_width == 2)
+			outsw(hostdata->io_port + hostdata->c400_host_buf,
 							src + start, 64);
-		else
-			outsb(instance->io_port + hostdata->c400_host_buf,
+		else if (hostdata->io_port)
+			outsb(hostdata->io_port + hostdata->c400_host_buf,
 							src + start, 128);
-#else
-		/* implies SCSI_G_NCR5380_MEM */
-		memcpy_toio(hostdata->iomem + NCR53C400_host_buffer,
-		            src + start, 128);
-#endif
+		else
+			memcpy_toio(hostdata->io + NCR53C400_host_buffer,
+			            src + start, 128);
+
 		start += 128;
 		blocks--;
 	}
@@ -489,10 +585,9 @@ static inline int generic_NCR5380_pwrite(struct Scsi_Host *instance,
 	return 0;
 }
 
-static int generic_NCR5380_dma_xfer_len(struct Scsi_Host *instance,
+static int generic_NCR5380_dma_xfer_len(struct NCR5380_hostdata *hostdata,
                                         struct scsi_cmnd *cmd)
 {
-	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	int transfersize = cmd->transfersize;
 
 	if (hostdata->flags & FLAG_NO_PSEUDO_DMA)
@@ -566,7 +661,7 @@ static struct isa_driver generic_NCR5380_isa_driver = {
 	},
 };
 
-#if !defined(SCSI_G_NCR5380_MEM) && defined(CONFIG_PNP)
+#ifdef CONFIG_PNP
 static struct pnp_device_id generic_NCR5380_pnp_ids[] = {
 	{ .id = "DTC436e", .driver_data = BOARD_DTC3181E },
 	{ .id = "" }
@@ -600,7 +695,7 @@ static struct pnp_driver generic_NCR5380_pnp_driver = {
 	.probe		= generic_NCR5380_pnp_probe,
 	.remove		= generic_NCR5380_pnp_remove,
 };
-#endif /* !defined(SCSI_G_NCR5380_MEM) && defined(CONFIG_PNP) */
+#endif /* defined(CONFIG_PNP) */
 
 static int pnp_registered, isa_registered;
 
@@ -609,7 +704,7 @@ static int __init generic_NCR5380_init(void)
 	int ret = 0;
 
 	/* compatibility with old-style parameters */
-	if (irq[0] == 0 && base[0] == 0 && card[0] == -1) {
+	if (irq[0] == -1 && base[0] == 0 && card[0] == -1) {
 		irq[0] = ncr_irq;
 		base[0] = ncr_addr;
 		if (ncr_5380)
@@ -624,7 +719,7 @@ static int __init generic_NCR5380_init(void)
 			card[0] = BOARD_HP_C2502;
 	}
 
-#if !defined(SCSI_G_NCR5380_MEM) && defined(CONFIG_PNP)
+#ifdef CONFIG_PNP
 	if (!pnp_register_driver(&generic_NCR5380_pnp_driver))
 		pnp_registered = 1;
 #endif
@@ -637,7 +732,7 @@ static int __init generic_NCR5380_init(void)
 
 static void __exit generic_NCR5380_exit(void)
 {
-#if !defined(SCSI_G_NCR5380_MEM) && defined(CONFIG_PNP)
+#ifdef CONFIG_PNP
 	if (pnp_registered)
 		pnp_unregister_driver(&generic_NCR5380_pnp_driver);
 #endif
diff --git a/drivers/scsi/g_NCR5380.h b/drivers/scsi/g_NCR5380.h
index b175b9234458..81b22d989648 100644
--- a/drivers/scsi/g_NCR5380.h
+++ b/drivers/scsi/g_NCR5380.h
@@ -14,49 +14,28 @@
 #ifndef GENERIC_NCR5380_H
 #define GENERIC_NCR5380_H
 
-#ifndef SCSI_G_NCR5380_MEM
 #define DRV_MODULE_NAME "g_NCR5380"
 
 #define NCR5380_read(reg) \
-	inb(instance->io_port + (reg))
+	ioread8(hostdata->io + hostdata->offset + (reg))
 #define NCR5380_write(reg, value) \
-	outb(value, instance->io_port + (reg))
+	iowrite8(value, hostdata->io + hostdata->offset + (reg))
 
 #define NCR5380_implementation_fields \
+	int offset; \
 	int c400_ctl_status; \
 	int c400_blk_cnt; \
 	int c400_host_buf; \
 	int io_width;
 
-#else 
-/* therefore SCSI_G_NCR5380_MEM */
-#define DRV_MODULE_NAME "g_NCR5380_mmio"
-
 #define NCR53C400_mem_base 0x3880
 #define NCR53C400_host_buffer 0x3900
 #define NCR53C400_region_size 0x3a00
 
-#define NCR5380_read(reg) \
-	readb(((struct NCR5380_hostdata *)shost_priv(instance))->iomem + \
-	      NCR53C400_mem_base + (reg))
-#define NCR5380_write(reg, value) \
-	writeb(value, ((struct NCR5380_hostdata *)shost_priv(instance))->iomem + \
-	       NCR53C400_mem_base + (reg))
-
-#define NCR5380_implementation_fields \
-	void __iomem *iomem; \
-	resource_size_t iomem_size; \
-	int c400_ctl_status; \
-	int c400_blk_cnt; \
-	int c400_host_buf;
-
-#endif
-
-#define NCR5380_dma_xfer_len(instance, cmd, phase) \
-        generic_NCR5380_dma_xfer_len(instance, cmd)
+#define NCR5380_dma_xfer_len		generic_NCR5380_dma_xfer_len
 #define NCR5380_dma_recv_setup		generic_NCR5380_pread
 #define NCR5380_dma_send_setup		generic_NCR5380_pwrite
-#define NCR5380_dma_residual(instance)	(0)
+#define NCR5380_dma_residual		NCR5380_dma_residual_none
 
 #define NCR5380_intr generic_NCR5380_intr
 #define NCR5380_queue_command generic_NCR5380_queue_command
@@ -72,5 +51,6 @@
 #define BOARD_DTC3181E	3
 #define BOARD_HP_C2502	4
 
-#endif /* GENERIC_NCR5380_H */
+#define IRQ_AUTO	254
 
+#endif /* GENERIC_NCR5380_H */
diff --git a/drivers/scsi/g_NCR5380_mmio.c b/drivers/scsi/g_NCR5380_mmio.c
deleted file mode 100644
index 8cdde71ba0c8..000000000000
--- a/drivers/scsi/g_NCR5380_mmio.c
+++ /dev/null
@@ -1,10 +0,0 @@
-/*
- *	There is probably a nicer way to do this but this one makes
- *	pretty obvious what is happening. We rebuild the same file with
- *	different options for mmio versus pio.
- */
-
-#define SCSI_G_NCR5380_MEM
-
-#include "g_NCR5380.c"
-
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index 0a767740bf02..d020a13646ae 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -130,7 +130,7 @@
 
 #include <asm/dma.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/spinlock.h>
 #include <linux/blkdev.h>
 #include <linux/scatterlist.h>
diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 72c98522bd26..c0cd505a9ef7 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -13,6 +13,7 @@
 #define _HISI_SAS_H_
 
 #include <linux/acpi.h>
+#include <linux/clk.h>
 #include <linux/dmapool.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
@@ -110,7 +111,7 @@ struct hisi_sas_device {
 	struct domain_device	*sas_device;
 	u64 attached_phy;
 	u64 device_id;
-	u64 running_req;
+	atomic64_t running_req;
 	u8 dev_status;
 };
 
@@ -149,7 +150,8 @@ struct hisi_sas_hw {
 				struct domain_device *device);
 	struct hisi_sas_device *(*alloc_dev)(struct domain_device *device);
 	void (*sl_notify)(struct hisi_hba *hisi_hba, int phy_no);
-	int (*get_free_slot)(struct hisi_hba *hisi_hba, int *q, int *s);
+	int (*get_free_slot)(struct hisi_hba *hisi_hba, u32 dev_id,
+			int *q, int *s);
 	void (*start_delivery)(struct hisi_hba *hisi_hba);
 	int (*prep_ssp)(struct hisi_hba *hisi_hba,
 			struct hisi_sas_slot *slot, int is_tmf,
@@ -166,6 +168,9 @@ struct hisi_sas_hw {
 	void (*phy_enable)(struct hisi_hba *hisi_hba, int phy_no);
 	void (*phy_disable)(struct hisi_hba *hisi_hba, int phy_no);
 	void (*phy_hard_reset)(struct hisi_hba *hisi_hba, int phy_no);
+	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 (*free_device)(struct hisi_hba *hisi_hba,
 			    struct hisi_sas_device *dev);
 	int (*get_wideport_bitmap)(struct hisi_hba *hisi_hba, int port_id);
@@ -183,6 +188,7 @@ struct hisi_hba {
 	u32 ctrl_reset_reg;
 	u32 ctrl_reset_sts_reg;
 	u32 ctrl_clock_ena_reg;
+	u32 refclk_frequency_mhz;
 	u8 sas_addr[SAS_ADDR_SIZE];
 
 	int n_phy;
@@ -205,7 +211,6 @@ struct hisi_hba {
 	struct hisi_sas_port port[HISI_SAS_MAX_PHYS];
 
 	int	queue_count;
-	int	queue;
 	struct hisi_sas_slot	*slot_prep;
 
 	struct dma_pool *sge_page_pool;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 2f872f784e10..d50e9cfefd24 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -162,8 +162,8 @@ out:
 	hisi_sas_slot_task_free(hisi_hba, task, abort_slot);
 	if (task->task_done)
 		task->task_done(task);
-	if (sas_dev && sas_dev->running_req)
-		sas_dev->running_req--;
+	if (sas_dev)
+		atomic64_dec(&sas_dev->running_req);
 }
 
 static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
@@ -232,8 +232,8 @@ static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
 		rc = hisi_sas_slot_index_alloc(hisi_hba, &slot_idx);
 	if (rc)
 		goto err_out;
-	rc = hisi_hba->hw->get_free_slot(hisi_hba, &dlvry_queue,
-					 &dlvry_queue_slot);
+	rc = hisi_hba->hw->get_free_slot(hisi_hba, sas_dev->device_id,
+					&dlvry_queue, &dlvry_queue_slot);
 	if (rc)
 		goto err_out_tag;
 
@@ -303,7 +303,7 @@ static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
 
 	hisi_hba->slot_prep = slot;
 
-	sas_dev->running_req++;
+	atomic64_inc(&sas_dev->running_req);
 	++(*pass);
 
 	return 0;
@@ -369,9 +369,14 @@ static void hisi_sas_bytes_dmaed(struct hisi_hba *hisi_hba, int phy_no)
 		struct sas_phy *sphy = sas_phy->phy;
 
 		sphy->negotiated_linkrate = sas_phy->linkrate;
-		sphy->minimum_linkrate = phy->minimum_linkrate;
 		sphy->minimum_linkrate_hw = SAS_LINK_RATE_1_5_GBPS;
-		sphy->maximum_linkrate = phy->maximum_linkrate;
+		sphy->maximum_linkrate_hw =
+			hisi_hba->hw->phy_get_max_linkrate();
+		if (sphy->minimum_linkrate == SAS_LINK_RATE_UNKNOWN)
+			sphy->minimum_linkrate = phy->minimum_linkrate;
+
+		if (sphy->maximum_linkrate == SAS_LINK_RATE_UNKNOWN)
+			sphy->maximum_linkrate = phy->maximum_linkrate;
 	}
 
 	if (phy->phy_type & PORT_TYPE_SAS) {
@@ -537,7 +542,7 @@ 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 = &hisi_hba->port[sas_phy->id];
+	struct hisi_sas_port *port = &hisi_hba->port[phy->port_id];
 	unsigned long flags;
 
 	if (!sas_port)
@@ -645,6 +650,9 @@ static int hisi_sas_control_phy(struct asd_sas_phy *sas_phy, enum phy_func func,
 		break;
 
 	case PHY_FUNC_SET_LINK_RATE:
+		hisi_hba->hw->phy_set_linkrate(hisi_hba, phy_no, funcdata);
+		break;
+
 	case PHY_FUNC_RELEASE_SPINUP_HOLD:
 	default:
 		return -EOPNOTSUPP;
@@ -764,7 +772,8 @@ static int hisi_sas_exec_internal_tmf_task(struct domain_device *device,
 		task = NULL;
 	}
 ex_err:
-	WARN_ON(retry == TASK_RETRY);
+	if (retry == TASK_RETRY)
+		dev_warn(dev, "abort tmf: executing internal task failed!\n");
 	sas_free_task(task);
 	return res;
 }
@@ -960,6 +969,9 @@ static int hisi_sas_query_task(struct sas_task *task)
 		case TMF_RESP_FUNC_FAILED:
 		case TMF_RESP_FUNC_COMPLETE:
 			break;
+		default:
+			rc = TMF_RESP_FUNC_FAILED;
+			break;
 		}
 	}
 	return rc;
@@ -987,8 +999,8 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, u64 device_id,
 	rc = hisi_sas_slot_index_alloc(hisi_hba, &slot_idx);
 	if (rc)
 		goto err_out;
-	rc = hisi_hba->hw->get_free_slot(hisi_hba, &dlvry_queue,
-					 &dlvry_queue_slot);
+	rc = hisi_hba->hw->get_free_slot(hisi_hba, sas_dev->device_id,
+					&dlvry_queue, &dlvry_queue_slot);
 	if (rc)
 		goto err_out_tag;
 
@@ -1023,7 +1035,8 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, u64 device_id,
 
 	hisi_hba->slot_prep = slot;
 
-	sas_dev->running_req++;
+	atomic64_inc(&sas_dev->running_req);
+
 	/* send abort command to our chip */
 	hisi_hba->hw->start_delivery(hisi_hba);
 
@@ -1396,10 +1409,13 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
 	struct hisi_hba *hisi_hba;
 	struct device *dev = &pdev->dev;
 	struct device_node *np = pdev->dev.of_node;
+	struct clk *refclk;
 
 	shost = scsi_host_alloc(&hisi_sas_sht, sizeof(*hisi_hba));
-	if (!shost)
-		goto err_out;
+	if (!shost) {
+		dev_err(dev, "scsi host alloc failed\n");
+		return NULL;
+	}
 	hisi_hba = shost_priv(shost);
 
 	hisi_hba->hw = hw;
@@ -1432,6 +1448,12 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
 			goto err_out;
 	}
 
+	refclk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(refclk))
+		dev_info(dev, "no ref clk property\n");
+	else
+		hisi_hba->refclk_frequency_mhz = clk_get_rate(refclk) / 1000000;
+
 	if (device_property_read_u32(dev, "phy-count", &hisi_hba->n_phy))
 		goto err_out;
 
@@ -1457,6 +1479,7 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
 
 	return shost;
 err_out:
+	kfree(shost);
 	dev_err(dev, "shost alloc failed\n");
 	return NULL;
 }
@@ -1483,10 +1506,8 @@ int hisi_sas_probe(struct platform_device *pdev,
 	int rc, phy_nr, port_nr, i;
 
 	shost = hisi_sas_shost_alloc(pdev, hw);
-	if (!shost) {
-		rc = -ENOMEM;
-		goto err_out_ha;
-	}
+	if (!shost)
+		return -ENOMEM;
 
 	sha = SHOST_TO_SAS_HA(shost);
 	hisi_hba = shost_priv(shost);
@@ -1496,12 +1517,13 @@ int hisi_sas_probe(struct platform_device *pdev,
 
 	arr_phy = devm_kcalloc(dev, phy_nr, sizeof(void *), GFP_KERNEL);
 	arr_port = devm_kcalloc(dev, port_nr, sizeof(void *), GFP_KERNEL);
-	if (!arr_phy || !arr_port)
-		return -ENOMEM;
+	if (!arr_phy || !arr_port) {
+		rc = -ENOMEM;
+		goto err_out_ha;
+	}
 
 	sha->sas_phy = arr_phy;
 	sha->sas_port = arr_port;
-	sha->core.shost = shost;
 	sha->lldd_ha = hisi_hba;
 
 	shost->transportt = hisi_sas_stt;
@@ -1546,6 +1568,7 @@ int hisi_sas_probe(struct platform_device *pdev,
 err_out_register_ha:
 	scsi_remove_host(shost);
 err_out_ha:
+	hisi_sas_free(hisi_hba);
 	kfree(shost);
 	return rc;
 }
@@ -1555,12 +1578,14 @@ int hisi_sas_remove(struct platform_device *pdev)
 {
 	struct sas_ha_struct *sha = platform_get_drvdata(pdev);
 	struct hisi_hba *hisi_hba = sha->lldd_ha;
+	struct Scsi_Host *shost = sha->core.shost;
 
 	scsi_remove_host(sha->core.shost);
 	sas_unregister_ha(sha);
 	sas_remove_host(sha->core.shost);
 
 	hisi_sas_free(hisi_hba);
+	kfree(shost);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(hisi_sas_remove);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index c0ac49d8bc8d..8a1be0ba8a22 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -843,6 +843,49 @@ static void sl_notify_v1_hw(struct hisi_hba *hisi_hba, int phy_no)
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_CONTROL, sl_control);
 }
 
+static enum sas_linkrate phy_get_max_linkrate_v1_hw(void)
+{
+	return SAS_LINK_RATE_6_0_GBPS;
+}
+
+static void phy_set_linkrate_v1_hw(struct hisi_hba *hisi_hba, int phy_no,
+		struct sas_phy_linkrates *r)
+{
+	u32 prog_phy_link_rate =
+		hisi_sas_phy_read32(hisi_hba, phy_no, PROG_PHY_LINK_RATE);
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+	struct asd_sas_phy *sas_phy = &phy->sas_phy;
+	int i;
+	enum sas_linkrate min, max;
+	u32 rate_mask = 0;
+
+	if (r->maximum_linkrate == SAS_LINK_RATE_UNKNOWN) {
+		max = sas_phy->phy->maximum_linkrate;
+		min = r->minimum_linkrate;
+	} else if (r->minimum_linkrate == SAS_LINK_RATE_UNKNOWN) {
+		max = r->maximum_linkrate;
+		min = sas_phy->phy->minimum_linkrate;
+	} else
+		return;
+
+	sas_phy->phy->maximum_linkrate = max;
+	sas_phy->phy->minimum_linkrate = min;
+
+	min -= SAS_LINK_RATE_1_5_GBPS;
+	max -= SAS_LINK_RATE_1_5_GBPS;
+
+	for (i = 0; i <= max; i++)
+		rate_mask |= 1 << (i * 2);
+
+	prog_phy_link_rate &= ~0xff;
+	prog_phy_link_rate |= rate_mask;
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, PROG_PHY_LINK_RATE,
+			prog_phy_link_rate);
+
+	phy_hard_reset_v1_hw(hisi_hba, phy_no);
+}
+
 static int get_wideport_bitmap_v1_hw(struct hisi_hba *hisi_hba, int port_id)
 {
 	int i, bitmap = 0;
@@ -862,29 +905,23 @@ static int get_wideport_bitmap_v1_hw(struct hisi_hba *hisi_hba, int port_id)
  * The callpath to this function and upto writing the write
  * queue pointer should be safe from interruption.
  */
-static int get_free_slot_v1_hw(struct hisi_hba *hisi_hba, int *q, int *s)
+static int get_free_slot_v1_hw(struct hisi_hba *hisi_hba, u32 dev_id,
+				int *q, int *s)
 {
 	struct device *dev = &hisi_hba->pdev->dev;
 	struct hisi_sas_dq *dq;
 	u32 r, w;
-	int queue = hisi_hba->queue;
-
-	while (1) {
-		dq = &hisi_hba->dq[queue];
-		w = dq->wr_point;
-		r = hisi_sas_read32_relaxed(hisi_hba,
-				    DLVRY_Q_0_RD_PTR + (queue * 0x14));
-		if (r == (w+1) % HISI_SAS_QUEUE_SLOTS) {
-			queue = (queue + 1) % hisi_hba->queue_count;
-			if (queue == hisi_hba->queue) {
-				dev_warn(dev, "could not find free slot\n");
-				return -EAGAIN;
-			}
-			continue;
-		}
-		break;
+	int queue = dev_id % hisi_hba->queue_count;
+
+	dq = &hisi_hba->dq[queue];
+	w = dq->wr_point;
+	r = hisi_sas_read32_relaxed(hisi_hba,
+				DLVRY_Q_0_RD_PTR + (queue * 0x14));
+	if (r == (w+1) % HISI_SAS_QUEUE_SLOTS) {
+		dev_warn(dev, "could not find free slot\n");
+		return -EAGAIN;
 	}
-	hisi_hba->queue = (queue + 1) % hisi_hba->queue_count;
+
 	*q = queue;
 	*s = w;
 	return 0;
@@ -1372,8 +1409,8 @@ static int slot_complete_v1_hw(struct hisi_hba *hisi_hba,
 	}
 
 out:
-	if (sas_dev && sas_dev->running_req)
-		sas_dev->running_req--;
+	if (sas_dev)
+		atomic64_dec(&sas_dev->running_req);
 
 	hisi_sas_slot_task_free(hisi_hba, task, slot);
 	sts = ts->stat;
@@ -1824,6 +1861,8 @@ static const struct hisi_sas_hw hisi_sas_v1_hw = {
 	.phy_enable = enable_phy_v1_hw,
 	.phy_disable = disable_phy_v1_hw,
 	.phy_hard_reset = phy_hard_reset_v1_hw,
+	.phy_set_linkrate = phy_set_linkrate_v1_hw,
+	.phy_get_max_linkrate = phy_get_max_linkrate_v1_hw,
 	.get_wideport_bitmap = get_wideport_bitmap_v1_hw,
 	.max_command_entries = HISI_SAS_COMMAND_ENTRIES_V1_HW,
 	.complete_hdr_size = sizeof(struct hisi_sas_complete_v1_hdr),
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 9825a3f49f53..b934aec1eebb 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -55,10 +55,44 @@
 #define HGC_DFX_CFG2			0xc0
 #define HGC_IOMB_PROC1_STATUS	0x104
 #define CFG_1US_TIMER_TRSH		0xcc
+#define HGC_LM_DFX_STATUS2		0x128
+#define HGC_LM_DFX_STATUS2_IOSTLIST_OFF		0
+#define HGC_LM_DFX_STATUS2_IOSTLIST_MSK	(0xfff << \
+					 HGC_LM_DFX_STATUS2_IOSTLIST_OFF)
+#define HGC_LM_DFX_STATUS2_ITCTLIST_OFF		12
+#define HGC_LM_DFX_STATUS2_ITCTLIST_MSK	(0x7ff << \
+					 HGC_LM_DFX_STATUS2_ITCTLIST_OFF)
+#define HGC_CQE_ECC_ADDR		0x13c
+#define HGC_CQE_ECC_1B_ADDR_OFF	0
+#define HGC_CQE_ECC_1B_ADDR_MSK	(0x3f << HGC_CQE_ECC_1B_ADDR_OFF)
+#define HGC_CQE_ECC_MB_ADDR_OFF	8
+#define HGC_CQE_ECC_MB_ADDR_MSK (0x3f << HGC_CQE_ECC_MB_ADDR_OFF)
+#define HGC_IOST_ECC_ADDR		0x140
+#define HGC_IOST_ECC_1B_ADDR_OFF	0
+#define HGC_IOST_ECC_1B_ADDR_MSK	(0x3ff << HGC_IOST_ECC_1B_ADDR_OFF)
+#define HGC_IOST_ECC_MB_ADDR_OFF	16
+#define HGC_IOST_ECC_MB_ADDR_MSK	(0x3ff << HGC_IOST_ECC_MB_ADDR_OFF)
+#define HGC_DQE_ECC_ADDR		0x144
+#define HGC_DQE_ECC_1B_ADDR_OFF	0
+#define HGC_DQE_ECC_1B_ADDR_MSK	(0xfff << HGC_DQE_ECC_1B_ADDR_OFF)
+#define HGC_DQE_ECC_MB_ADDR_OFF	16
+#define HGC_DQE_ECC_MB_ADDR_MSK (0xfff << HGC_DQE_ECC_MB_ADDR_OFF)
 #define HGC_INVLD_DQE_INFO		0x148
 #define HGC_INVLD_DQE_INFO_FB_CH0_OFF	9
 #define HGC_INVLD_DQE_INFO_FB_CH0_MSK	(0x1 << HGC_INVLD_DQE_INFO_FB_CH0_OFF)
 #define HGC_INVLD_DQE_INFO_FB_CH3_OFF	18
+#define HGC_ITCT_ECC_ADDR		0x150
+#define HGC_ITCT_ECC_1B_ADDR_OFF		0
+#define HGC_ITCT_ECC_1B_ADDR_MSK		(0x3ff << \
+						 HGC_ITCT_ECC_1B_ADDR_OFF)
+#define HGC_ITCT_ECC_MB_ADDR_OFF		16
+#define HGC_ITCT_ECC_MB_ADDR_MSK		(0x3ff << \
+						 HGC_ITCT_ECC_MB_ADDR_OFF)
+#define HGC_AXI_FIFO_ERR_INFO	0x154
+#define AXI_ERR_INFO_OFF		0
+#define AXI_ERR_INFO_MSK		(0xff << AXI_ERR_INFO_OFF)
+#define FIFO_ERR_INFO_OFF		8
+#define FIFO_ERR_INFO_MSK		(0xff << FIFO_ERR_INFO_OFF)
 #define INT_COAL_EN			0x19c
 #define OQ_INT_COAL_TIME		0x1a0
 #define OQ_INT_COAL_CNT			0x1a4
@@ -73,13 +107,41 @@
 #define ENT_INT_SRC1_D2H_FIS_CH1_MSK	(0x1 << ENT_INT_SRC1_D2H_FIS_CH1_OFF)
 #define ENT_INT_SRC2			0x1bc
 #define ENT_INT_SRC3			0x1c0
+#define ENT_INT_SRC3_WP_DEPTH_OFF		8
+#define ENT_INT_SRC3_IPTT_SLOT_NOMATCH_OFF	9
+#define ENT_INT_SRC3_RP_DEPTH_OFF		10
+#define ENT_INT_SRC3_AXI_OFF			11
+#define ENT_INT_SRC3_FIFO_OFF			12
+#define ENT_INT_SRC3_LM_OFF				14
 #define ENT_INT_SRC3_ITC_INT_OFF	15
 #define ENT_INT_SRC3_ITC_INT_MSK	(0x1 << ENT_INT_SRC3_ITC_INT_OFF)
+#define ENT_INT_SRC3_ABT_OFF		16
 #define ENT_INT_SRC_MSK1		0x1c4
 #define ENT_INT_SRC_MSK2		0x1c8
 #define ENT_INT_SRC_MSK3		0x1cc
 #define ENT_INT_SRC_MSK3_ENT95_MSK_OFF	31
 #define ENT_INT_SRC_MSK3_ENT95_MSK_MSK	(0x1 << ENT_INT_SRC_MSK3_ENT95_MSK_OFF)
+#define SAS_ECC_INTR			0x1e8
+#define SAS_ECC_INTR_DQE_ECC_1B_OFF		0
+#define SAS_ECC_INTR_DQE_ECC_MB_OFF		1
+#define SAS_ECC_INTR_IOST_ECC_1B_OFF	2
+#define SAS_ECC_INTR_IOST_ECC_MB_OFF	3
+#define SAS_ECC_INTR_ITCT_ECC_MB_OFF	4
+#define SAS_ECC_INTR_ITCT_ECC_1B_OFF	5
+#define SAS_ECC_INTR_IOSTLIST_ECC_MB_OFF	6
+#define SAS_ECC_INTR_IOSTLIST_ECC_1B_OFF	7
+#define SAS_ECC_INTR_ITCTLIST_ECC_1B_OFF	8
+#define SAS_ECC_INTR_ITCTLIST_ECC_MB_OFF	9
+#define SAS_ECC_INTR_CQE_ECC_1B_OFF		10
+#define SAS_ECC_INTR_CQE_ECC_MB_OFF		11
+#define SAS_ECC_INTR_NCQ_MEM0_ECC_MB_OFF	12
+#define SAS_ECC_INTR_NCQ_MEM0_ECC_1B_OFF	13
+#define SAS_ECC_INTR_NCQ_MEM1_ECC_MB_OFF	14
+#define SAS_ECC_INTR_NCQ_MEM1_ECC_1B_OFF	15
+#define SAS_ECC_INTR_NCQ_MEM2_ECC_MB_OFF	16
+#define SAS_ECC_INTR_NCQ_MEM2_ECC_1B_OFF	17
+#define SAS_ECC_INTR_NCQ_MEM3_ECC_MB_OFF	18
+#define SAS_ECC_INTR_NCQ_MEM3_ECC_1B_OFF	19
 #define SAS_ECC_INTR_MSK		0x1ec
 #define HGC_ERR_STAT_EN			0x238
 #define DLVRY_Q_0_BASE_ADDR_LO		0x260
@@ -94,7 +156,20 @@
 #define COMPL_Q_0_DEPTH			0x4e8
 #define COMPL_Q_0_WR_PTR		0x4ec
 #define COMPL_Q_0_RD_PTR		0x4f0
-
+#define HGC_RXM_DFX_STATUS14	0xae8
+#define HGC_RXM_DFX_STATUS14_MEM0_OFF		0
+#define HGC_RXM_DFX_STATUS14_MEM0_MSK		(0x1ff << \
+						 HGC_RXM_DFX_STATUS14_MEM0_OFF)
+#define HGC_RXM_DFX_STATUS14_MEM1_OFF		9
+#define HGC_RXM_DFX_STATUS14_MEM1_MSK		(0x1ff << \
+						 HGC_RXM_DFX_STATUS14_MEM1_OFF)
+#define HGC_RXM_DFX_STATUS14_MEM2_OFF		18
+#define HGC_RXM_DFX_STATUS14_MEM2_MSK		(0x1ff << \
+						 HGC_RXM_DFX_STATUS14_MEM2_OFF)
+#define HGC_RXM_DFX_STATUS15	0xaec
+#define HGC_RXM_DFX_STATUS15_MEM3_OFF		0
+#define HGC_RXM_DFX_STATUS15_MEM3_MSK		(0x1ff << \
+						 HGC_RXM_DFX_STATUS15_MEM3_OFF)
 /* phy registers need init */
 #define PORT_BASE			(0x2000)
 
@@ -119,6 +194,9 @@
 #define SL_CONTROL_NOTIFY_EN_MSK	(0x1 << SL_CONTROL_NOTIFY_EN_OFF)
 #define SL_CONTROL_CTA_OFF		17
 #define SL_CONTROL_CTA_MSK		(0x1 << SL_CONTROL_CTA_OFF)
+#define RX_PRIMS_STATUS         (PORT_BASE + 0x98)
+#define RX_BCAST_CHG_OFF        1
+#define RX_BCAST_CHG_MSK        (0x1 << RX_BCAST_CHG_OFF)
 #define TX_ID_DWORD0			(PORT_BASE + 0x9c)
 #define TX_ID_DWORD1			(PORT_BASE + 0xa0)
 #define TX_ID_DWORD2			(PORT_BASE + 0xa4)
@@ -267,6 +345,8 @@
 #define ITCT_HDR_RTOLT_OFF		48
 #define ITCT_HDR_RTOLT_MSK		(0xffffULL << ITCT_HDR_RTOLT_OFF)
 
+#define HISI_SAS_FATAL_INT_NR	2
+
 struct hisi_sas_complete_v2_hdr {
 	__le32 dw0;
 	__le32 dw1;
@@ -659,8 +739,6 @@ static void free_device_v2_hw(struct hisi_hba *hisi_hba,
 			qw0 &= ~(1 << ITCT_HDR_VALID_OFF);
 			hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
 					 ENT_INT_SRC3_ITC_INT_MSK);
-			hisi_hba->devices[dev_id].dev_type = SAS_PHY_UNUSED;
-			hisi_hba->devices[dev_id].dev_status = HISI_SAS_DEV_NORMAL;
 
 			/* clear the itct */
 			hisi_sas_write32(hisi_hba, ITCT_CLR, 0);
@@ -808,7 +886,7 @@ static void init_reg_v2_hw(struct hisi_hba *hisi_hba)
 	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK1, 0x7efefefe);
 	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK2, 0x7efefefe);
 	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK3, 0x7ffffffe);
-	hisi_sas_write32(hisi_hba, SAS_ECC_INTR_MSK, 0xfffff3c0);
+	hisi_sas_write32(hisi_hba, SAS_ECC_INTR_MSK, 0xfff00c30);
 	for (i = 0; i < hisi_hba->queue_count; i++)
 		hisi_sas_write32(hisi_hba, OQ0_INT_SRC_MSK+0x4*i, 0);
 
@@ -824,7 +902,7 @@ static void init_reg_v2_hw(struct hisi_hba *hisi_hba)
 		hisi_sas_phy_write32(hisi_hba, i, DONE_RECEIVED_TIME, 0x10);
 		hisi_sas_phy_write32(hisi_hba, i, CHL_INT0, 0xffffffff);
 		hisi_sas_phy_write32(hisi_hba, i, CHL_INT1, 0xffffffff);
-		hisi_sas_phy_write32(hisi_hba, i, CHL_INT2, 0xffffffff);
+		hisi_sas_phy_write32(hisi_hba, i, CHL_INT2, 0xfff87fff);
 		hisi_sas_phy_write32(hisi_hba, i, RXOP_CHECK_CFG_H, 0x1000);
 		hisi_sas_phy_write32(hisi_hba, i, CHL_INT1_MSK, 0xffffffff);
 		hisi_sas_phy_write32(hisi_hba, i, CHL_INT2_MSK, 0x8ffffbff);
@@ -836,7 +914,9 @@ static void init_reg_v2_hw(struct hisi_hba *hisi_hba)
 		hisi_sas_phy_write32(hisi_hba, i, SL_RX_BCAST_CHK_MSK, 0x0);
 		hisi_sas_phy_write32(hisi_hba, i, CHL_INT_COAL_EN, 0x0);
 		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_OOB_RESTART_MSK, 0x0);
-		hisi_sas_phy_write32(hisi_hba, i, PHY_CTRL, 0x199B694);
+		if (hisi_hba->refclk_frequency_mhz == 66)
+			hisi_sas_phy_write32(hisi_hba, i, PHY_CTRL, 0x199B694);
+		/* else, do nothing -> leave it how you found it */
 	}
 
 	for (i = 0; i < hisi_hba->queue_count; i++) {
@@ -980,6 +1060,49 @@ static void sl_notify_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_CONTROL, sl_control);
 }
 
+static enum sas_linkrate phy_get_max_linkrate_v2_hw(void)
+{
+	return SAS_LINK_RATE_12_0_GBPS;
+}
+
+static void phy_set_linkrate_v2_hw(struct hisi_hba *hisi_hba, int phy_no,
+		struct sas_phy_linkrates *r)
+{
+	u32 prog_phy_link_rate =
+		hisi_sas_phy_read32(hisi_hba, phy_no, PROG_PHY_LINK_RATE);
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+	struct asd_sas_phy *sas_phy = &phy->sas_phy;
+	int i;
+	enum sas_linkrate min, max;
+	u32 rate_mask = 0;
+
+	if (r->maximum_linkrate == SAS_LINK_RATE_UNKNOWN) {
+		max = sas_phy->phy->maximum_linkrate;
+		min = r->minimum_linkrate;
+	} else if (r->minimum_linkrate == SAS_LINK_RATE_UNKNOWN) {
+		max = r->maximum_linkrate;
+		min = sas_phy->phy->minimum_linkrate;
+	} else
+		return;
+
+	sas_phy->phy->maximum_linkrate = max;
+	sas_phy->phy->minimum_linkrate = min;
+
+	min -= SAS_LINK_RATE_1_5_GBPS;
+	max -= SAS_LINK_RATE_1_5_GBPS;
+
+	for (i = 0; i <= max; i++)
+		rate_mask |= 1 << (i * 2);
+
+	prog_phy_link_rate &= ~0xff;
+	prog_phy_link_rate |= rate_mask;
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, PROG_PHY_LINK_RATE,
+			prog_phy_link_rate);
+
+	phy_hard_reset_v2_hw(hisi_hba, phy_no);
+}
+
 static int get_wideport_bitmap_v2_hw(struct hisi_hba *hisi_hba, int port_id)
 {
 	int i, bitmap = 0;
@@ -1010,29 +1133,24 @@ static int get_wideport_bitmap_v2_hw(struct hisi_hba *hisi_hba, int port_id)
  * The callpath to this function and upto writing the write
  * queue pointer should be safe from interruption.
  */
-static int get_free_slot_v2_hw(struct hisi_hba *hisi_hba, int *q, int *s)
+static int get_free_slot_v2_hw(struct hisi_hba *hisi_hba, u32 dev_id,
+				int *q, int *s)
 {
 	struct device *dev = &hisi_hba->pdev->dev;
 	struct hisi_sas_dq *dq;
 	u32 r, w;
-	int queue = hisi_hba->queue;
-
-	while (1) {
-		dq = &hisi_hba->dq[queue];
-		w = dq->wr_point;
-		r = hisi_sas_read32_relaxed(hisi_hba,
-					    DLVRY_Q_0_RD_PTR + (queue * 0x14));
-		if (r == (w+1) % HISI_SAS_QUEUE_SLOTS) {
-			queue = (queue + 1) % hisi_hba->queue_count;
-			if (queue == hisi_hba->queue) {
-				dev_warn(dev, "could not find free slot\n");
-				return -EAGAIN;
-			}
-			continue;
-		}
-		break;
+	int queue = dev_id % hisi_hba->queue_count;
+
+	dq = &hisi_hba->dq[queue];
+	w = dq->wr_point;
+	r = hisi_sas_read32_relaxed(hisi_hba,
+				DLVRY_Q_0_RD_PTR + (queue * 0x14));
+	if (r == (w+1) % HISI_SAS_QUEUE_SLOTS) {
+		dev_warn(dev, "full queue=%d r=%d w=%d\n\n",
+				queue, r, w);
+		return -EAGAIN;
 	}
-	hisi_hba->queue = (queue + 1) % hisi_hba->queue_count;
+
 	*q = queue;
 	*s = w;
 	return 0;
@@ -1653,8 +1771,8 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot,
 	}
 
 out:
-	if (sas_dev && sas_dev->running_req)
-		sas_dev->running_req--;
+	if (sas_dev)
+		atomic64_dec(&sas_dev->running_req);
 
 	hisi_sas_slot_task_free(hisi_hba, task, slot);
 	sts = ts->stat;
@@ -1675,6 +1793,7 @@ static u8 get_ata_protocol(u8 cmd, int direction)
 	case ATA_CMD_NCQ_NON_DATA:
 	return SATA_PROTOCOL_FPDMA;
 
+	case ATA_CMD_DOWNLOAD_MICRO:
 	case ATA_CMD_ID_ATA:
 	case ATA_CMD_PMP_READ:
 	case ATA_CMD_READ_LOG_EXT:
@@ -1686,18 +1805,27 @@ static u8 get_ata_protocol(u8 cmd, int direction)
 	case ATA_CMD_PIO_WRITE_EXT:
 	return SATA_PROTOCOL_PIO;
 
+	case ATA_CMD_DSM:
+	case ATA_CMD_DOWNLOAD_MICRO_DMA:
+	case ATA_CMD_PMP_READ_DMA:
+	case ATA_CMD_PMP_WRITE_DMA:
 	case ATA_CMD_READ:
 	case ATA_CMD_READ_EXT:
 	case ATA_CMD_READ_LOG_DMA_EXT:
+	case ATA_CMD_READ_STREAM_DMA_EXT:
+	case ATA_CMD_TRUSTED_RCV_DMA:
+	case ATA_CMD_TRUSTED_SND_DMA:
 	case ATA_CMD_WRITE:
 	case ATA_CMD_WRITE_EXT:
+	case ATA_CMD_WRITE_FUA_EXT:
 	case ATA_CMD_WRITE_QUEUED:
 	case ATA_CMD_WRITE_LOG_DMA_EXT:
+	case ATA_CMD_WRITE_STREAM_DMA_EXT:
 	return SATA_PROTOCOL_DMA;
 
-	case ATA_CMD_DOWNLOAD_MICRO:
-	case ATA_CMD_DEV_RESET:
 	case ATA_CMD_CHK_POWER:
+	case ATA_CMD_DEV_RESET:
+	case ATA_CMD_EDD:
 	case ATA_CMD_FLUSH:
 	case ATA_CMD_FLUSH_EXT:
 	case ATA_CMD_VERIFY:
@@ -1970,9 +2098,12 @@ static void phy_bcast_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
 	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
 	struct sas_ha_struct *sas_ha = &hisi_hba->sha;
+	u32 bcast_status;
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
-	sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
+	bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS);
+	if (bcast_status & RX_BCAST_CHG_MSK)
+		sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
 			     CHL_INT0_SL_RX_BCST_ACK_MSK);
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 0);
@@ -2005,8 +2136,9 @@ static irqreturn_t int_chnl_int_v2_hw(int irq_no, void *p)
 			if (irq_value1) {
 				if (irq_value1 & (CHL_INT1_DMAC_RX_ECC_ERR_MSK |
 						  CHL_INT1_DMAC_TX_ECC_ERR_MSK))
-					panic("%s: DMAC RX/TX ecc bad error! (0x%x)",
-						dev_name(dev), irq_value1);
+					panic("%s: DMAC RX/TX ecc bad error!\
+					       (0x%x)",
+					      dev_name(dev), irq_value1);
 
 				hisi_sas_phy_write32(hisi_hba, phy_no,
 						     CHL_INT1, irq_value1);
@@ -2037,6 +2169,318 @@ static irqreturn_t int_chnl_int_v2_hw(int irq_no, void *p)
 	return IRQ_HANDLED;
 }
 
+static void
+one_bit_ecc_error_process_v2_hw(struct hisi_hba *hisi_hba, u32 irq_value)
+{
+	struct device *dev = &hisi_hba->pdev->dev;
+	u32 reg_val;
+
+	if (irq_value & BIT(SAS_ECC_INTR_DQE_ECC_1B_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_DQE_ECC_ADDR);
+		dev_warn(dev, "hgc_dqe_acc1b_intr found: \
+			       Ram address is 0x%08X\n",
+			 (reg_val & HGC_DQE_ECC_1B_ADDR_MSK) >>
+			 HGC_DQE_ECC_1B_ADDR_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_IOST_ECC_1B_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_IOST_ECC_ADDR);
+		dev_warn(dev, "hgc_iost_acc1b_intr found: \
+			       Ram address is 0x%08X\n",
+			 (reg_val & HGC_IOST_ECC_1B_ADDR_MSK) >>
+			 HGC_IOST_ECC_1B_ADDR_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_ITCT_ECC_1B_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_ITCT_ECC_ADDR);
+		dev_warn(dev, "hgc_itct_acc1b_intr found: \
+			       Ram address is 0x%08X\n",
+			 (reg_val & HGC_ITCT_ECC_1B_ADDR_MSK) >>
+			 HGC_ITCT_ECC_1B_ADDR_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_IOSTLIST_ECC_1B_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_LM_DFX_STATUS2);
+		dev_warn(dev, "hgc_iostl_acc1b_intr found: \
+			       memory address is 0x%08X\n",
+			 (reg_val & HGC_LM_DFX_STATUS2_IOSTLIST_MSK) >>
+			 HGC_LM_DFX_STATUS2_IOSTLIST_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_ITCTLIST_ECC_1B_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_LM_DFX_STATUS2);
+		dev_warn(dev, "hgc_itctl_acc1b_intr found: \
+			       memory address is 0x%08X\n",
+			 (reg_val & HGC_LM_DFX_STATUS2_ITCTLIST_MSK) >>
+			 HGC_LM_DFX_STATUS2_ITCTLIST_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_CQE_ECC_1B_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_CQE_ECC_ADDR);
+		dev_warn(dev, "hgc_cqe_acc1b_intr found: \
+			       Ram address is 0x%08X\n",
+			 (reg_val & HGC_CQE_ECC_1B_ADDR_MSK) >>
+			 HGC_CQE_ECC_1B_ADDR_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_NCQ_MEM0_ECC_1B_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_RXM_DFX_STATUS14);
+		dev_warn(dev, "rxm_mem0_acc1b_intr found: \
+			       memory address is 0x%08X\n",
+			 (reg_val & HGC_RXM_DFX_STATUS14_MEM0_MSK) >>
+			 HGC_RXM_DFX_STATUS14_MEM0_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_NCQ_MEM1_ECC_1B_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_RXM_DFX_STATUS14);
+		dev_warn(dev, "rxm_mem1_acc1b_intr found: \
+			       memory address is 0x%08X\n",
+			 (reg_val & HGC_RXM_DFX_STATUS14_MEM1_MSK) >>
+			 HGC_RXM_DFX_STATUS14_MEM1_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_NCQ_MEM2_ECC_1B_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_RXM_DFX_STATUS14);
+		dev_warn(dev, "rxm_mem2_acc1b_intr found: \
+			       memory address is 0x%08X\n",
+			 (reg_val & HGC_RXM_DFX_STATUS14_MEM2_MSK) >>
+			 HGC_RXM_DFX_STATUS14_MEM2_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_NCQ_MEM3_ECC_1B_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_RXM_DFX_STATUS15);
+		dev_warn(dev, "rxm_mem3_acc1b_intr found: \
+			       memory address is 0x%08X\n",
+			 (reg_val & HGC_RXM_DFX_STATUS15_MEM3_MSK) >>
+			 HGC_RXM_DFX_STATUS15_MEM3_OFF);
+	}
+
+}
+
+static void multi_bit_ecc_error_process_v2_hw(struct hisi_hba *hisi_hba,
+		u32 irq_value)
+{
+	u32 reg_val;
+	struct device *dev = &hisi_hba->pdev->dev;
+
+	if (irq_value & BIT(SAS_ECC_INTR_DQE_ECC_MB_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_DQE_ECC_ADDR);
+		panic("%s: hgc_dqe_accbad_intr (0x%x) found: \
+		       Ram address is 0x%08X\n",
+		      dev_name(dev), irq_value,
+		      (reg_val & HGC_DQE_ECC_MB_ADDR_MSK) >>
+		      HGC_DQE_ECC_MB_ADDR_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_IOST_ECC_MB_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_IOST_ECC_ADDR);
+		panic("%s: hgc_iost_accbad_intr (0x%x) found: \
+		       Ram address is 0x%08X\n",
+		      dev_name(dev), irq_value,
+		      (reg_val & HGC_IOST_ECC_MB_ADDR_MSK) >>
+		      HGC_IOST_ECC_MB_ADDR_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_ITCT_ECC_MB_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_ITCT_ECC_ADDR);
+		panic("%s: hgc_itct_accbad_intr (0x%x) found: \
+		       Ram address is 0x%08X\n",
+		      dev_name(dev), irq_value,
+		      (reg_val & HGC_ITCT_ECC_MB_ADDR_MSK) >>
+		      HGC_ITCT_ECC_MB_ADDR_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_IOSTLIST_ECC_MB_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_LM_DFX_STATUS2);
+		panic("%s: hgc_iostl_accbad_intr (0x%x) found: \
+		       memory address is 0x%08X\n",
+		      dev_name(dev), irq_value,
+		      (reg_val & HGC_LM_DFX_STATUS2_IOSTLIST_MSK) >>
+		      HGC_LM_DFX_STATUS2_IOSTLIST_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_ITCTLIST_ECC_MB_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_LM_DFX_STATUS2);
+		panic("%s: hgc_itctl_accbad_intr (0x%x) found: \
+		       memory address is 0x%08X\n",
+		      dev_name(dev), irq_value,
+		      (reg_val & HGC_LM_DFX_STATUS2_ITCTLIST_MSK) >>
+		      HGC_LM_DFX_STATUS2_ITCTLIST_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_CQE_ECC_MB_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_CQE_ECC_ADDR);
+		panic("%s: hgc_cqe_accbad_intr (0x%x) found: \
+		       Ram address is 0x%08X\n",
+		      dev_name(dev), irq_value,
+		      (reg_val & HGC_CQE_ECC_MB_ADDR_MSK) >>
+		      HGC_CQE_ECC_MB_ADDR_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_NCQ_MEM0_ECC_MB_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_RXM_DFX_STATUS14);
+		panic("%s: rxm_mem0_accbad_intr (0x%x) found: \
+		       memory address is 0x%08X\n",
+		      dev_name(dev), irq_value,
+		      (reg_val & HGC_RXM_DFX_STATUS14_MEM0_MSK) >>
+		      HGC_RXM_DFX_STATUS14_MEM0_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_NCQ_MEM1_ECC_MB_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_RXM_DFX_STATUS14);
+		panic("%s: rxm_mem1_accbad_intr (0x%x) found: \
+		       memory address is 0x%08X\n",
+		      dev_name(dev), irq_value,
+		      (reg_val & HGC_RXM_DFX_STATUS14_MEM1_MSK) >>
+		      HGC_RXM_DFX_STATUS14_MEM1_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_NCQ_MEM2_ECC_MB_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_RXM_DFX_STATUS14);
+		panic("%s: rxm_mem2_accbad_intr (0x%x) found: \
+		       memory address is 0x%08X\n",
+		      dev_name(dev), irq_value,
+		      (reg_val & HGC_RXM_DFX_STATUS14_MEM2_MSK) >>
+		      HGC_RXM_DFX_STATUS14_MEM2_OFF);
+	}
+
+	if (irq_value & BIT(SAS_ECC_INTR_NCQ_MEM3_ECC_MB_OFF)) {
+		reg_val = hisi_sas_read32(hisi_hba, HGC_RXM_DFX_STATUS15);
+		panic("%s: rxm_mem3_accbad_intr (0x%x) found: \
+		       memory address is 0x%08X\n",
+		      dev_name(dev), irq_value,
+		      (reg_val & HGC_RXM_DFX_STATUS15_MEM3_MSK) >>
+		      HGC_RXM_DFX_STATUS15_MEM3_OFF);
+	}
+
+}
+
+static irqreturn_t fatal_ecc_int_v2_hw(int irq_no, void *p)
+{
+	struct hisi_hba *hisi_hba = p;
+	u32 irq_value, irq_msk;
+
+	irq_msk = hisi_sas_read32(hisi_hba, SAS_ECC_INTR_MSK);
+	hisi_sas_write32(hisi_hba, SAS_ECC_INTR_MSK, irq_msk | 0xffffffff);
+
+	irq_value = hisi_sas_read32(hisi_hba, SAS_ECC_INTR);
+	if (irq_value) {
+		one_bit_ecc_error_process_v2_hw(hisi_hba, irq_value);
+		multi_bit_ecc_error_process_v2_hw(hisi_hba, irq_value);
+	}
+
+	hisi_sas_write32(hisi_hba, SAS_ECC_INTR, irq_value);
+	hisi_sas_write32(hisi_hba, SAS_ECC_INTR_MSK, irq_msk);
+
+	return IRQ_HANDLED;
+}
+
+#define AXI_ERR_NR	8
+static const char axi_err_info[AXI_ERR_NR][32] = {
+	"IOST_AXI_W_ERR",
+	"IOST_AXI_R_ERR",
+	"ITCT_AXI_W_ERR",
+	"ITCT_AXI_R_ERR",
+	"SATA_AXI_W_ERR",
+	"SATA_AXI_R_ERR",
+	"DQE_AXI_R_ERR",
+	"CQE_AXI_W_ERR"
+};
+
+#define FIFO_ERR_NR	5
+static const char fifo_err_info[FIFO_ERR_NR][32] = {
+	"CQE_WINFO_FIFO",
+	"CQE_MSG_FIFIO",
+	"GETDQE_FIFO",
+	"CMDP_FIFO",
+	"AWTCTRL_FIFO"
+};
+
+static irqreturn_t fatal_axi_int_v2_hw(int irq_no, void *p)
+{
+	struct hisi_hba *hisi_hba = p;
+	u32 irq_value, irq_msk, err_value;
+	struct device *dev = &hisi_hba->pdev->dev;
+
+	irq_msk = hisi_sas_read32(hisi_hba, ENT_INT_SRC_MSK3);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK3, irq_msk | 0xfffffffe);
+
+	irq_value = hisi_sas_read32(hisi_hba, ENT_INT_SRC3);
+	if (irq_value) {
+		if (irq_value & BIT(ENT_INT_SRC3_WP_DEPTH_OFF)) {
+			hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
+					1 << ENT_INT_SRC3_WP_DEPTH_OFF);
+			panic("%s: write pointer and depth error (0x%x) \
+			       found!\n",
+			      dev_name(dev), irq_value);
+		}
+
+		if (irq_value & BIT(ENT_INT_SRC3_IPTT_SLOT_NOMATCH_OFF)) {
+			hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
+					 1 <<
+					 ENT_INT_SRC3_IPTT_SLOT_NOMATCH_OFF);
+			panic("%s: iptt no match slot error (0x%x) found!\n",
+			      dev_name(dev), irq_value);
+		}
+
+		if (irq_value & BIT(ENT_INT_SRC3_RP_DEPTH_OFF))
+			panic("%s: read pointer and depth error (0x%x) \
+			       found!\n",
+			      dev_name(dev), irq_value);
+
+		if (irq_value & BIT(ENT_INT_SRC3_AXI_OFF)) {
+			int i;
+
+			hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
+					1 << ENT_INT_SRC3_AXI_OFF);
+			err_value = hisi_sas_read32(hisi_hba,
+						    HGC_AXI_FIFO_ERR_INFO);
+
+			for (i = 0; i < AXI_ERR_NR; i++) {
+				if (err_value & BIT(i))
+					panic("%s: %s (0x%x) found!\n",
+					       dev_name(dev),
+					      axi_err_info[i], irq_value);
+			}
+		}
+
+		if (irq_value & BIT(ENT_INT_SRC3_FIFO_OFF)) {
+			int i;
+
+			hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
+					1 << ENT_INT_SRC3_FIFO_OFF);
+			err_value = hisi_sas_read32(hisi_hba,
+						    HGC_AXI_FIFO_ERR_INFO);
+
+			for (i = 0; i < FIFO_ERR_NR; i++) {
+				if (err_value & BIT(AXI_ERR_NR + i))
+					panic("%s: %s (0x%x) found!\n",
+					      dev_name(dev),
+					      fifo_err_info[i], irq_value);
+			}
+
+		}
+
+		if (irq_value & BIT(ENT_INT_SRC3_LM_OFF)) {
+			hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
+					1 << ENT_INT_SRC3_LM_OFF);
+			panic("%s: LM add/fetch list error (0x%x) found!\n",
+			      dev_name(dev), irq_value);
+		}
+
+		if (irq_value & BIT(ENT_INT_SRC3_ABT_OFF)) {
+			hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
+					1 << ENT_INT_SRC3_ABT_OFF);
+			panic("%s: SAS_HGC_ABT fetch LM list error (0x%x) found!\n",
+			      dev_name(dev), irq_value);
+		}
+	}
+
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK3, irq_msk);
+
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)
 {
 	struct hisi_sas_cq *cq = p;
@@ -2136,6 +2580,16 @@ static irqreturn_t sata_int_v2_hw(int irq_no, void *p)
 		goto end;
 	}
 
+	/* check ERR bit of Status Register */
+	if (fis->status & ATA_ERR) {
+		dev_warn(dev, "sata int: phy%d FIS status: 0x%x\n", phy_no,
+				fis->status);
+		disable_phy_v2_hw(hisi_hba, phy_no);
+		enable_phy_v2_hw(hisi_hba, phy_no);
+		res = IRQ_NONE;
+		goto end;
+	}
+
 	if (unlikely(phy_no == 8)) {
 		u32 port_state = hisi_sas_read32(hisi_hba, PORT_STATE);
 
@@ -2190,6 +2644,11 @@ static irq_handler_t phy_interrupts[HISI_SAS_PHY_INT_NR] = {
 	int_chnl_int_v2_hw,
 };
 
+static irq_handler_t fatal_interrupts[HISI_SAS_FATAL_INT_NR] = {
+	fatal_ecc_int_v2_hw,
+	fatal_axi_int_v2_hw
+};
+
 /**
  * There is a limitation in the hip06 chipset that we need
  * to map in all mbigen interrupts, even if they are not used.
@@ -2245,6 +2704,26 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 		}
 	}
 
+	for (i = 0; i < HISI_SAS_FATAL_INT_NR; i++) {
+		int idx = i;
+
+		irq = irq_map[idx + 81];
+		if (!irq) {
+			dev_err(dev, "irq init: fail map fatal interrupt %d\n",
+				idx);
+			return -ENOENT;
+		}
+
+		rc = devm_request_irq(dev, irq, fatal_interrupts[i], 0,
+				      DRV_NAME " fatal", hisi_hba);
+		if (rc) {
+			dev_err(dev,
+				"irq init: could not request fatal interrupt %d, rc=%d\n",
+				irq, rc);
+			return -ENOENT;
+		}
+	}
+
 	for (i = 0; i < hisi_hba->queue_count; i++) {
 		int idx = i + 96; /* First cq interrupt is irq96 */
 
@@ -2303,12 +2782,26 @@ static const struct hisi_sas_hw hisi_sas_v2_hw = {
 	.phy_enable = enable_phy_v2_hw,
 	.phy_disable = disable_phy_v2_hw,
 	.phy_hard_reset = phy_hard_reset_v2_hw,
+	.phy_set_linkrate = phy_set_linkrate_v2_hw,
+	.phy_get_max_linkrate = phy_get_max_linkrate_v2_hw,
 	.max_command_entries = HISI_SAS_COMMAND_ENTRIES_V2_HW,
 	.complete_hdr_size = sizeof(struct hisi_sas_complete_v2_hdr),
 };
 
 static int hisi_sas_v2_probe(struct platform_device *pdev)
 {
+	/*
+	 * Check if we should defer the probe before we probe the
+	 * upper layer, as it's hard to defer later on.
+	 */
+	int ret = platform_get_irq(pdev, 0);
+
+	if (ret < 0) {
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "cannot obtain irq\n");
+		return ret;
+	}
+
 	return hisi_sas_probe(pdev, &hisi_sas_v2_hw);
 }
 
@@ -2319,6 +2812,7 @@ static int hisi_sas_v2_remove(struct platform_device *pdev)
 
 static const struct of_device_id sas_v2_of_match[] = {
 	{ .compatible = "hisilicon,hip06-sas-v2",},
+	{ .compatible = "hisilicon,hip07-sas-v2",},
 	{},
 };
 MODULE_DEVICE_TABLE(of, sas_v2_of_match);
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index d007ec18179a..cbc0c5fe5a60 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -276,6 +276,9 @@ static int hpsa_find_cfg_addrs(struct pci_dev *pdev, void __iomem *vaddr,
 static int hpsa_pci_find_memory_BAR(struct pci_dev *pdev,
 				    unsigned long *memory_bar);
 static int hpsa_lookup_board_id(struct pci_dev *pdev, u32 *board_id);
+static int wait_for_device_to_become_ready(struct ctlr_info *h,
+					   unsigned char lunaddr[],
+					   int reply_queue);
 static int hpsa_wait_for_board_state(struct pci_dev *pdev, void __iomem *vaddr,
 				     int wait_for_ready);
 static inline void finish_cmd(struct CommandList *c);
@@ -700,9 +703,7 @@ static ssize_t lunid_show(struct device *dev,
 	}
 	memcpy(lunid, hdev->scsi3addr, sizeof(lunid));
 	spin_unlock_irqrestore(&h->lock, flags);
-	return snprintf(buf, 20, "0x%02x%02x%02x%02x%02x%02x%02x%02x\n",
-		lunid[0], lunid[1], lunid[2], lunid[3],
-		lunid[4], lunid[5], lunid[6], lunid[7]);
+	return snprintf(buf, 20, "0x%8phN\n", lunid);
 }
 
 static ssize_t unique_id_show(struct device *dev,
@@ -864,6 +865,16 @@ static ssize_t path_info_show(struct device *dev,
 	return output_len;
 }
 
+static ssize_t host_show_ctlr_num(struct device *dev,
+	struct device_attribute *attr, char *buf)
+{
+	struct ctlr_info *h;
+	struct Scsi_Host *shost = class_to_shost(dev);
+
+	h = shost_to_hba(shost);
+	return snprintf(buf, 20, "%d\n", h->ctlr);
+}
+
 static DEVICE_ATTR(raid_level, S_IRUGO, raid_level_show, NULL);
 static DEVICE_ATTR(lunid, S_IRUGO, lunid_show, NULL);
 static DEVICE_ATTR(unique_id, S_IRUGO, unique_id_show, NULL);
@@ -887,6 +898,8 @@ static DEVICE_ATTR(resettable, S_IRUGO,
 	host_show_resettable, NULL);
 static DEVICE_ATTR(lockup_detected, S_IRUGO,
 	host_show_lockup_detected, NULL);
+static DEVICE_ATTR(ctlr_num, S_IRUGO,
+	host_show_ctlr_num, NULL);
 
 static struct device_attribute *hpsa_sdev_attrs[] = {
 	&dev_attr_raid_level,
@@ -907,6 +920,7 @@ static struct device_attribute *hpsa_shost_attrs[] = {
 	&dev_attr_hp_ssd_smart_path_status,
 	&dev_attr_raid_offload_debug,
 	&dev_attr_lockup_detected,
+	&dev_attr_ctlr_num,
 	NULL,
 };
 
@@ -1001,7 +1015,7 @@ static void set_performant_mode(struct ctlr_info *h, struct CommandList *c,
 {
 	if (likely(h->transMethod & CFGTBL_Trans_Performant)) {
 		c->busaddr |= 1 | (h->blockFetchTable[c->Header.SGList] << 1);
-		if (unlikely(!h->msix_vector))
+		if (unlikely(!h->msix_vectors))
 			return;
 		if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
 			c->Header.ReplyQueue =
@@ -1543,10 +1557,9 @@ static void hpsa_monitor_offline_device(struct ctlr_info *h,
 
 	/* Device is not on the list, add it. */
 	device = kmalloc(sizeof(*device), GFP_KERNEL);
-	if (!device) {
-		dev_warn(&h->pdev->dev, "out of memory in %s\n", __func__);
+	if (!device)
 		return;
-	}
+
 	memcpy(device->scsi3addr, scsi3addr, sizeof(device->scsi3addr));
 	spin_lock_irqsave(&h->offline_device_lock, flags);
 	list_add_tail(&device->offline_list, &h->offline_device_list);
@@ -2009,7 +2022,7 @@ static struct hpsa_scsi_dev_t *lookup_hpsa_scsi_dev(struct ctlr_info *h,
 
 static int hpsa_slave_alloc(struct scsi_device *sdev)
 {
-	struct hpsa_scsi_dev_t *sd;
+	struct hpsa_scsi_dev_t *sd = NULL;
 	unsigned long flags;
 	struct ctlr_info *h;
 
@@ -2026,7 +2039,8 @@ static int hpsa_slave_alloc(struct scsi_device *sdev)
 			sd->target = sdev_id(sdev);
 			sd->lun = sdev->lun;
 		}
-	} else
+	}
+	if (!sd)
 		sd = lookup_hpsa_scsi_dev(h, sdev_channel(sdev),
 					sdev_id(sdev), sdev->lun);
 
@@ -2127,17 +2141,15 @@ static int hpsa_alloc_sg_chain_blocks(struct ctlr_info *h)
 
 	h->cmd_sg_list = kzalloc(sizeof(*h->cmd_sg_list) * h->nr_cmds,
 				GFP_KERNEL);
-	if (!h->cmd_sg_list) {
-		dev_err(&h->pdev->dev, "Failed to allocate SG list\n");
+	if (!h->cmd_sg_list)
 		return -ENOMEM;
-	}
+
 	for (i = 0; i < h->nr_cmds; i++) {
 		h->cmd_sg_list[i] = kmalloc(sizeof(*h->cmd_sg_list[i]) *
 						h->chainsize, GFP_KERNEL);
-		if (!h->cmd_sg_list[i]) {
-			dev_err(&h->pdev->dev, "Failed to allocate cmd SG\n");
+		if (!h->cmd_sg_list[i])
 			goto clean;
-		}
+
 	}
 	return 0;
 
@@ -2540,7 +2552,7 @@ static void complete_scsi_command(struct CommandList *cp)
 
 	if ((unlikely(hpsa_is_pending_event(cp)))) {
 		if (cp->reset_pending)
-			return hpsa_cmd_resolve_and_free(h, cp);
+			return hpsa_cmd_free_and_done(h, cp, cmd);
 		if (cp->abort_pending)
 			return hpsa_cmd_abort_and_free(h, cp, cmd);
 	}
@@ -2823,14 +2835,8 @@ static void hpsa_print_cmd(struct ctlr_info *h, char *txt,
 	const u8 *cdb = c->Request.CDB;
 	const u8 *lun = c->Header.LUN.LunAddrBytes;
 
-	dev_warn(&h->pdev->dev, "%s: LUN:%02x%02x%02x%02x%02x%02x%02x%02x"
-	" CDB:%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x\n",
-		txt, lun[0], lun[1], lun[2], lun[3],
-		lun[4], lun[5], lun[6], lun[7],
-		cdb[0], cdb[1], cdb[2], cdb[3],
-		cdb[4], cdb[5], cdb[6], cdb[7],
-		cdb[8], cdb[9], cdb[10], cdb[11],
-		cdb[12], cdb[13], cdb[14], cdb[15]);
+	dev_warn(&h->pdev->dev, "%s: LUN:%8phN CDB:%16phN\n",
+		 txt, lun, cdb);
 }
 
 static void hpsa_scsi_interpret_error(struct ctlr_info *h,
@@ -3079,6 +3085,8 @@ static int hpsa_do_reset(struct ctlr_info *h, struct hpsa_scsi_dev_t *dev,
 
 	if (unlikely(rc))
 		atomic_set(&dev->reset_cmds_out, 0);
+	else
+		wait_for_device_to_become_ready(h, scsi3addr, 0);
 
 	mutex_unlock(&h->reset_mutex);
 	return rc;
@@ -3443,11 +3451,8 @@ static void hpsa_get_sas_address(struct ctlr_info *h, unsigned char *scsi3addr,
 		struct bmic_sense_subsystem_info *ssi;
 
 		ssi = kzalloc(sizeof(*ssi), GFP_KERNEL);
-		if (ssi == NULL) {
-			dev_warn(&h->pdev->dev,
-				"%s: out of memory\n", __func__);
+		if (!ssi)
 			return;
-		}
 
 		rc = hpsa_bmic_sense_subsystem_information(h,
 					scsi3addr, 0, ssi, sizeof(*ssi));
@@ -3622,8 +3627,32 @@ out:
 static inline int hpsa_scsi_do_report_phys_luns(struct ctlr_info *h,
 		struct ReportExtendedLUNdata *buf, int bufsize)
 {
-	return hpsa_scsi_do_report_luns(h, 0, buf, bufsize,
-						HPSA_REPORT_PHYS_EXTENDED);
+	int rc;
+	struct ReportLUNdata *lbuf;
+
+	rc = hpsa_scsi_do_report_luns(h, 0, buf, bufsize,
+				      HPSA_REPORT_PHYS_EXTENDED);
+	if (!rc || !hpsa_allow_any)
+		return rc;
+
+	/* REPORT PHYS EXTENDED is not supported */
+	lbuf = kzalloc(sizeof(*lbuf), GFP_KERNEL);
+	if (!lbuf)
+		return -ENOMEM;
+
+	rc = hpsa_scsi_do_report_luns(h, 0, lbuf, sizeof(*lbuf), 0);
+	if (!rc) {
+		int i;
+		u32 nphys;
+
+		/* Copy ReportLUNdata header */
+		memcpy(buf, lbuf, 8);
+		nphys = be32_to_cpu(*((__be32 *)lbuf->LUNListLength)) / 8;
+		for (i = 0; i < nphys; i++)
+			memcpy(buf->LUN[i].lunid, lbuf->LUN[i], 8);
+	}
+	kfree(lbuf);
+	return rc;
 }
 
 static inline int hpsa_scsi_do_report_log_luns(struct ctlr_info *h,
@@ -3840,6 +3869,7 @@ static int hpsa_update_device_info(struct ctlr_info *h,
 		sizeof(this_device->vendor));
 	memcpy(this_device->model, &inq_buff[16],
 		sizeof(this_device->model));
+	this_device->rev = inq_buff[2];
 	memset(this_device->device_id, 0,
 		sizeof(this_device->device_id));
 	if (hpsa_get_device_id(h, scsi3addr, this_device->device_id, 8,
@@ -3929,10 +3959,14 @@ static void figure_bus_target_lun(struct ctlr_info *h,
 
 	if (!is_logical_dev_addr_mode(lunaddrbytes)) {
 		/* physical device, target and lun filled in later */
-		if (is_hba_lunid(lunaddrbytes))
+		if (is_hba_lunid(lunaddrbytes)) {
+			int bus = HPSA_HBA_BUS;
+
+			if (!device->rev)
+				bus = HPSA_LEGACY_HBA_BUS;
 			hpsa_set_bus_target_lun(device,
-					HPSA_HBA_BUS, 0, lunid & 0x3fff);
-		else
+					bus, 0, lunid & 0x3fff);
+		} else
 			/* defer target, lun assignment for physical devices */
 			hpsa_set_bus_target_lun(device,
 					HPSA_PHYSICAL_DEVICE_BUS, -1, -1);
@@ -4295,8 +4329,6 @@ static void hpsa_update_scsi_devices(struct ctlr_info *h)
 
 		currentsd[i] = kzalloc(sizeof(*currentsd[i]), GFP_KERNEL);
 		if (!currentsd[i]) {
-			dev_warn(&h->pdev->dev, "out of memory at %s:%d\n",
-				__FILE__, __LINE__);
 			h->drv_req_rescan = 1;
 			goto out;
 		}
@@ -5482,7 +5514,7 @@ static int hpsa_scsi_queue_command(struct Scsi_Host *sh, struct scsi_cmnd *cmd)
 
 	dev = cmd->device->hostdata;
 	if (!dev) {
-		cmd->result = NOT_READY << 16; /* host byte */
+		cmd->result = DID_NO_CONNECT << 16;
 		cmd->scsi_done(cmd);
 		return 0;
 	}
@@ -5563,6 +5595,14 @@ static void hpsa_scan_start(struct Scsi_Host *sh)
 	if (unlikely(lockup_detected(h)))
 		return hpsa_scan_complete(h);
 
+	/*
+	 * Do the scan after a reset completion
+	 */
+	if (h->reset_in_progress) {
+		h->drv_req_rescan = 1;
+		return;
+	}
+
 	hpsa_update_scsi_devices(h);
 
 	hpsa_scan_complete(h);
@@ -5618,7 +5658,7 @@ static int hpsa_scsi_host_alloc(struct ctlr_info *h)
 	sh->sg_tablesize = h->maxsgentries;
 	sh->transportt = hpsa_sas_transport_template;
 	sh->hostdata[0] = (unsigned long) h;
-	sh->irq = h->intr[h->intr_mode];
+	sh->irq = pci_irq_vector(h->pdev, 0);
 	sh->unique_id = sh->irq;
 
 	h->scsi_host = sh;
@@ -5993,11 +6033,9 @@ static int hpsa_send_reset_as_abort_ioaccel2(struct ctlr_info *h,
 
 	if (h->raid_offload_debug > 0)
 		dev_info(&h->pdev->dev,
-			"scsi %d:%d:%d:%d %s scsi3addr 0x%02x%02x%02x%02x%02x%02x%02x%02x\n",
+			"scsi %d:%d:%d:%d %s scsi3addr 0x%8phN\n",
 			h->scsi_host->host_no, dev->bus, dev->target, dev->lun,
-			"Reset as abort",
-			scsi3addr[0], scsi3addr[1], scsi3addr[2], scsi3addr[3],
-			scsi3addr[4], scsi3addr[5], scsi3addr[6], scsi3addr[7]);
+			"Reset as abort", scsi3addr);
 
 	if (!dev->offload_enabled) {
 		dev_warn(&h->pdev->dev,
@@ -6014,32 +6052,28 @@ static int hpsa_send_reset_as_abort_ioaccel2(struct ctlr_info *h,
 	/* send the reset */
 	if (h->raid_offload_debug > 0)
 		dev_info(&h->pdev->dev,
-			"Reset as abort: Resetting physical device at scsi3addr 0x%02x%02x%02x%02x%02x%02x%02x%02x\n",
-			psa[0], psa[1], psa[2], psa[3],
-			psa[4], psa[5], psa[6], psa[7]);
+			"Reset as abort: Resetting physical device at scsi3addr 0x%8phN\n",
+			psa);
 	rc = hpsa_do_reset(h, dev, psa, HPSA_PHYS_TARGET_RESET, reply_queue);
 	if (rc != 0) {
 		dev_warn(&h->pdev->dev,
-			"Reset as abort: Failed on physical device at scsi3addr 0x%02x%02x%02x%02x%02x%02x%02x%02x\n",
-			psa[0], psa[1], psa[2], psa[3],
-			psa[4], psa[5], psa[6], psa[7]);
+			"Reset as abort: Failed on physical device at scsi3addr 0x%8phN\n",
+			psa);
 		return rc; /* failed to reset */
 	}
 
 	/* wait for device to recover */
 	if (wait_for_device_to_become_ready(h, psa, reply_queue) != 0) {
 		dev_warn(&h->pdev->dev,
-			"Reset as abort: Failed: Device never recovered from reset: 0x%02x%02x%02x%02x%02x%02x%02x%02x\n",
-			psa[0], psa[1], psa[2], psa[3],
-			psa[4], psa[5], psa[6], psa[7]);
+			"Reset as abort: Failed: Device never recovered from reset: 0x%8phN\n",
+			psa);
 		return -1;  /* failed to recover */
 	}
 
 	/* device recovered */
 	dev_info(&h->pdev->dev,
-		"Reset as abort: Device recovered from reset: scsi3addr 0x%02x%02x%02x%02x%02x%02x%02x%02x\n",
-		psa[0], psa[1], psa[2], psa[3],
-		psa[4], psa[5], psa[6], psa[7]);
+		"Reset as abort: Device recovered from reset: scsi3addr 0x%8phN\n",
+		psa);
 
 	return rc; /* success */
 }
@@ -6657,8 +6691,7 @@ static int hpsa_big_passthru_ioctl(struct ctlr_info *h, void __user *argp)
 		return -EINVAL;
 	if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
-	ioc = (BIG_IOCTL_Command_struct *)
-	    kmalloc(sizeof(*ioc), GFP_KERNEL);
+	ioc = kmalloc(sizeof(*ioc), GFP_KERNEL);
 	if (!ioc) {
 		status = -ENOMEM;
 		goto cleanup1;
@@ -7652,67 +7685,41 @@ static int find_PCI_BAR_index(struct pci_dev *pdev, unsigned long pci_bar_addr)
 
 static void hpsa_disable_interrupt_mode(struct ctlr_info *h)
 {
-	if (h->msix_vector) {
-		if (h->pdev->msix_enabled)
-			pci_disable_msix(h->pdev);
-		h->msix_vector = 0;
-	} else if (h->msi_vector) {
-		if (h->pdev->msi_enabled)
-			pci_disable_msi(h->pdev);
-		h->msi_vector = 0;
-	}
+	pci_free_irq_vectors(h->pdev);
+	h->msix_vectors = 0;
 }
 
 /* If MSI/MSI-X is supported by the kernel we will try to enable it on
  * controllers that are capable. If not, we use legacy INTx mode.
  */
-static void hpsa_interrupt_mode(struct ctlr_info *h)
+static int hpsa_interrupt_mode(struct ctlr_info *h)
 {
-#ifdef CONFIG_PCI_MSI
-	int err, i;
-	struct msix_entry hpsa_msix_entries[MAX_REPLY_QUEUES];
-
-	for (i = 0; i < MAX_REPLY_QUEUES; i++) {
-		hpsa_msix_entries[i].vector = 0;
-		hpsa_msix_entries[i].entry = i;
-	}
+	unsigned int flags = PCI_IRQ_LEGACY;
+	int ret;
 
 	/* Some boards advertise MSI but don't really support it */
-	if ((h->board_id == 0x40700E11) || (h->board_id == 0x40800E11) ||
-	    (h->board_id == 0x40820E11) || (h->board_id == 0x40830E11))
-		goto default_int_mode;
-	if (pci_find_capability(h->pdev, PCI_CAP_ID_MSIX)) {
-		dev_info(&h->pdev->dev, "MSI-X capable controller\n");
-		h->msix_vector = MAX_REPLY_QUEUES;
-		if (h->msix_vector > num_online_cpus())
-			h->msix_vector = num_online_cpus();
-		err = pci_enable_msix_range(h->pdev, hpsa_msix_entries,
-					    1, h->msix_vector);
-		if (err < 0) {
-			dev_warn(&h->pdev->dev, "MSI-X init failed %d\n", err);
-			h->msix_vector = 0;
-			goto single_msi_mode;
-		} else if (err < h->msix_vector) {
-			dev_warn(&h->pdev->dev, "only %d MSI-X vectors "
-			       "available\n", err);
+	switch (h->board_id) {
+	case 0x40700E11:
+	case 0x40800E11:
+	case 0x40820E11:
+	case 0x40830E11:
+		break;
+	default:
+		ret = pci_alloc_irq_vectors(h->pdev, 1, MAX_REPLY_QUEUES,
+				PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
+		if (ret > 0) {
+			h->msix_vectors = ret;
+			return 0;
 		}
-		h->msix_vector = err;
-		for (i = 0; i < h->msix_vector; i++)
-			h->intr[i] = hpsa_msix_entries[i].vector;
-		return;
-	}
-single_msi_mode:
-	if (pci_find_capability(h->pdev, PCI_CAP_ID_MSI)) {
-		dev_info(&h->pdev->dev, "MSI capable controller\n");
-		if (!pci_enable_msi(h->pdev))
-			h->msi_vector = 1;
-		else
-			dev_warn(&h->pdev->dev, "MSI init failed\n");
+
+		flags |= PCI_IRQ_MSI;
+		break;
 	}
-default_int_mode:
-#endif				/* CONFIG_PCI_MSI */
-	/* if we get here we're going to use the default interrupt mode */
-	h->intr[h->intr_mode] = h->pdev->irq;
+
+	ret = pci_alloc_irq_vectors(h->pdev, 1, 1, flags);
+	if (ret < 0)
+		return ret;
+	return 0;
 }
 
 static int hpsa_lookup_board_id(struct pci_dev *pdev, u32 *board_id)
@@ -8068,7 +8075,9 @@ static int hpsa_pci_init(struct ctlr_info *h)
 
 	pci_set_master(h->pdev);
 
-	hpsa_interrupt_mode(h);
+	err = hpsa_interrupt_mode(h);
+	if (err)
+		goto clean1;
 	err = hpsa_pci_find_memory_BAR(h->pdev, &h->paddr);
 	if (err)
 		goto clean2;	/* intmode+region, pci */
@@ -8104,6 +8113,7 @@ clean3:	/* vaddr, intmode+region, pci */
 	h->vaddr = NULL;
 clean2:	/* intmode+region, pci */
 	hpsa_disable_interrupt_mode(h);
+clean1:
 	/*
 	 * call pci_disable_device before pci_release_regions per
 	 * Documentation/PCI/pci.txt
@@ -8237,34 +8247,20 @@ clean_up:
 	return -ENOMEM;
 }
 
-static void hpsa_irq_affinity_hints(struct ctlr_info *h)
-{
-	int i, cpu;
-
-	cpu = cpumask_first(cpu_online_mask);
-	for (i = 0; i < h->msix_vector; i++) {
-		irq_set_affinity_hint(h->intr[i], get_cpu_mask(cpu));
-		cpu = cpumask_next(cpu, cpu_online_mask);
-	}
-}
-
 /* clear affinity hints and free MSI-X, MSI, or legacy INTx vectors */
 static void hpsa_free_irqs(struct ctlr_info *h)
 {
 	int i;
 
-	if (!h->msix_vector || h->intr_mode != PERF_MODE_INT) {
+	if (!h->msix_vectors || h->intr_mode != PERF_MODE_INT) {
 		/* Single reply queue, only one irq to free */
-		i = h->intr_mode;
-		irq_set_affinity_hint(h->intr[i], NULL);
-		free_irq(h->intr[i], &h->q[i]);
-		h->q[i] = 0;
+		free_irq(pci_irq_vector(h->pdev, 0), &h->q[h->intr_mode]);
+		h->q[h->intr_mode] = 0;
 		return;
 	}
 
-	for (i = 0; i < h->msix_vector; i++) {
-		irq_set_affinity_hint(h->intr[i], NULL);
-		free_irq(h->intr[i], &h->q[i]);
+	for (i = 0; i < h->msix_vectors; i++) {
+		free_irq(pci_irq_vector(h->pdev, i), &h->q[i]);
 		h->q[i] = 0;
 	}
 	for (; i < MAX_REPLY_QUEUES; i++)
@@ -8285,11 +8281,11 @@ static int hpsa_request_irqs(struct ctlr_info *h,
 	for (i = 0; i < MAX_REPLY_QUEUES; i++)
 		h->q[i] = (u8) i;
 
-	if (h->intr_mode == PERF_MODE_INT && h->msix_vector > 0) {
+	if (h->intr_mode == PERF_MODE_INT && h->msix_vectors > 0) {
 		/* If performant mode and MSI-X, use multiple reply queues */
-		for (i = 0; i < h->msix_vector; i++) {
+		for (i = 0; i < h->msix_vectors; i++) {
 			sprintf(h->intrname[i], "%s-msix%d", h->devname, i);
-			rc = request_irq(h->intr[i], msixhandler,
+			rc = request_irq(pci_irq_vector(h->pdev, i), msixhandler,
 					0, h->intrname[i],
 					&h->q[i]);
 			if (rc) {
@@ -8297,9 +8293,9 @@ static int hpsa_request_irqs(struct ctlr_info *h,
 
 				dev_err(&h->pdev->dev,
 					"failed to get irq %d for %s\n",
-				       h->intr[i], h->devname);
+				       pci_irq_vector(h->pdev, i), h->devname);
 				for (j = 0; j < i; j++) {
-					free_irq(h->intr[j], &h->q[j]);
+					free_irq(pci_irq_vector(h->pdev, j), &h->q[j]);
 					h->q[j] = 0;
 				}
 				for (; j < MAX_REPLY_QUEUES; j++)
@@ -8307,33 +8303,27 @@ static int hpsa_request_irqs(struct ctlr_info *h,
 				return rc;
 			}
 		}
-		hpsa_irq_affinity_hints(h);
 	} else {
 		/* Use single reply pool */
-		if (h->msix_vector > 0 || h->msi_vector) {
-			if (h->msix_vector)
-				sprintf(h->intrname[h->intr_mode],
-					"%s-msix", h->devname);
-			else
-				sprintf(h->intrname[h->intr_mode],
-					"%s-msi", h->devname);
-			rc = request_irq(h->intr[h->intr_mode],
+		if (h->msix_vectors > 0 || h->pdev->msi_enabled) {
+			sprintf(h->intrname[0], "%s-msi%s", h->devname,
+				h->msix_vectors ? "x" : "");
+			rc = request_irq(pci_irq_vector(h->pdev, 0),
 				msixhandler, 0,
-				h->intrname[h->intr_mode],
+				h->intrname[0],
 				&h->q[h->intr_mode]);
 		} else {
 			sprintf(h->intrname[h->intr_mode],
 				"%s-intx", h->devname);
-			rc = request_irq(h->intr[h->intr_mode],
+			rc = request_irq(pci_irq_vector(h->pdev, 0),
 				intxhandler, IRQF_SHARED,
-				h->intrname[h->intr_mode],
+				h->intrname[0],
 				&h->q[h->intr_mode]);
 		}
-		irq_set_affinity_hint(h->intr[h->intr_mode], NULL);
 	}
 	if (rc) {
 		dev_err(&h->pdev->dev, "failed to get irq %d for %s\n",
-		       h->intr[h->intr_mode], h->devname);
+		       pci_irq_vector(h->pdev, 0), h->devname);
 		hpsa_free_irqs(h);
 		return -ENODEV;
 	}
@@ -8599,14 +8589,12 @@ static int hpsa_luns_changed(struct ctlr_info *h)
 	 */
 
 	if (!h->lastlogicals)
-		goto out;
+		return rc;
 
 	logdev = kzalloc(sizeof(*logdev), GFP_KERNEL);
-	if (!logdev) {
-		dev_warn(&h->pdev->dev,
-			"Out of memory, can't track lun changes.\n");
-		goto out;
-	}
+	if (!logdev)
+		return rc;
+
 	if (hpsa_scsi_do_report_luns(h, 1, logdev, sizeof(*logdev), 0)) {
 		dev_warn(&h->pdev->dev,
 			"report luns failed, can't track lun changes.\n");
@@ -8634,6 +8622,14 @@ static void hpsa_rescan_ctlr_worker(struct work_struct *work)
 	if (h->remove_in_progress)
 		return;
 
+	/*
+	 * Do the scan after the reset
+	 */
+	if (h->reset_in_progress) {
+		h->drv_req_rescan = 1;
+		return;
+	}
+
 	if (hpsa_ctlr_needs_rescan(h) || hpsa_offline_devices_ready(h)) {
 		scsi_host_get(h->scsi_host);
 		hpsa_ack_ctlr_events(h);
@@ -8992,11 +8988,8 @@ static void hpsa_disable_rld_caching(struct ctlr_info *h)
 		return;
 
 	options = kzalloc(sizeof(*options), GFP_KERNEL);
-	if (!options) {
-		dev_err(&h->pdev->dev,
-			"Error: failed to disable rld caching, during alloc.\n");
+	if (!options)
 		return;
-	}
 
 	c = cmd_alloc(h);
 
@@ -9519,7 +9512,7 @@ static int hpsa_put_ctlr_into_performant_mode(struct ctlr_info *h)
 			return rc;
 	}
 
-	h->nreply_queues = h->msix_vector > 0 ? h->msix_vector : 1;
+	h->nreply_queues = h->msix_vectors > 0 ? h->msix_vectors : 1;
 	hpsa_get_max_perf_mode_cmds(h);
 	/* Performant mode ring buffer and supporting data structures */
 	h->reply_queue_size = h->max_commands * sizeof(u64);
diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h
index 82cdfad874f3..64e98295b707 100644
--- a/drivers/scsi/hpsa.h
+++ b/drivers/scsi/hpsa.h
@@ -69,6 +69,7 @@ struct hpsa_scsi_dev_t {
 	u64 sas_address;
 	unsigned char vendor[8];        /* bytes 8-15 of inquiry data */
 	unsigned char model[16];        /* bytes 16-31 of inquiry data */
+	unsigned char rev;		/* byte 2 of inquiry data */
 	unsigned char raid_level;	/* from inquiry page 0xC1 */
 	unsigned char volume_offline;	/* discovered via TUR or VPD */
 	u16 queue_depth;		/* max queue_depth for this device */
@@ -175,9 +176,7 @@ struct ctlr_info {
 #	define DOORBELL_INT	1
 #	define SIMPLE_MODE_INT	2
 #	define MEMQ_MODE_INT	3
-	unsigned int intr[MAX_REPLY_QUEUES];
-	unsigned int msix_vector;
-	unsigned int msi_vector;
+	unsigned int msix_vectors;
 	int intr_mode; /* either PERF_MODE_INT or SIMPLE_MODE_INT */
 	struct access_method access;
 
@@ -402,6 +401,7 @@ struct offline_device_entry {
 #define HPSA_RAID_VOLUME_BUS		1
 #define HPSA_EXTERNAL_RAID_VOLUME_BUS	2
 #define HPSA_HBA_BUS			0
+#define HPSA_LEGACY_HBA_BUS		3
 
 /*
 	Send the command to the hardware
@@ -464,7 +464,7 @@ static unsigned long SA5_performant_completed(struct ctlr_info *h, u8 q)
 	unsigned long register_value = FIFO_EMPTY;
 
 	/* msi auto clears the interrupt pending bit. */
-	if (unlikely(!(h->msi_vector || h->msix_vector))) {
+	if (unlikely(!(h->pdev->msi_enabled || h->msix_vectors))) {
 		/* flush the controller write of the reply queue by reading
 		 * outbound doorbell status register.
 		 */
diff --git a/drivers/scsi/hptiop.c b/drivers/scsi/hptiop.c
index a83f705ed8a5..db17ad15b0c1 100644
--- a/drivers/scsi/hptiop.c
+++ b/drivers/scsi/hptiop.c
@@ -26,7 +26,7 @@
 #include <linux/timer.h>
 #include <linux/spinlock.h>
 #include <linux/gfp.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/div64.h>
 #include <scsi/scsi_cmnd.h>
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 7e487c78279c..78b72c28a55d 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -32,6 +32,7 @@
 #include <linux/of.h>
 #include <linux/pm.h>
 #include <linux/stringify.h>
+#include <linux/bsg-lib.h>
 #include <asm/firmware.h>
 #include <asm/irq.h>
 #include <asm/vio.h>
@@ -1701,14 +1702,14 @@ static void ibmvfc_bsg_timeout_done(struct ibmvfc_event *evt)
 
 /**
  * ibmvfc_bsg_timeout - Handle a BSG timeout
- * @job:	struct fc_bsg_job that timed out
+ * @job:	struct bsg_job that timed out
  *
  * Returns:
  *	0 on success / other on failure
  **/
-static int ibmvfc_bsg_timeout(struct fc_bsg_job *job)
+static int ibmvfc_bsg_timeout(struct bsg_job *job)
 {
-	struct ibmvfc_host *vhost = shost_priv(job->shost);
+	struct ibmvfc_host *vhost = shost_priv(fc_bsg_to_shost(job));
 	unsigned long port_id = (unsigned long)job->dd_data;
 	struct ibmvfc_event *evt;
 	struct ibmvfc_tmf *tmf;
@@ -1814,41 +1815,43 @@ unlock_out:
 
 /**
  * ibmvfc_bsg_request - Handle a BSG request
- * @job:	struct fc_bsg_job to be executed
+ * @job:	struct bsg_job to be executed
  *
  * Returns:
  *	0 on success / other on failure
  **/
-static int ibmvfc_bsg_request(struct fc_bsg_job *job)
+static int ibmvfc_bsg_request(struct bsg_job *job)
 {
-	struct ibmvfc_host *vhost = shost_priv(job->shost);
-	struct fc_rport *rport = job->rport;
+	struct ibmvfc_host *vhost = shost_priv(fc_bsg_to_shost(job));
+	struct fc_rport *rport = fc_bsg_to_rport(job);
 	struct ibmvfc_passthru_mad *mad;
 	struct ibmvfc_event *evt;
 	union ibmvfc_iu rsp_iu;
 	unsigned long flags, port_id = -1;
-	unsigned int code = job->request->msgcode;
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
+	unsigned int code = bsg_request->msgcode;
 	int rc = 0, req_seg, rsp_seg, issue_login = 0;
 	u32 fc_flags, rsp_len;
 
 	ENTER;
-	job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 	if (rport)
 		port_id = rport->port_id;
 
 	switch (code) {
 	case FC_BSG_HST_ELS_NOLOGIN:
-		port_id = (job->request->rqst_data.h_els.port_id[0] << 16) |
-			(job->request->rqst_data.h_els.port_id[1] << 8) |
-			job->request->rqst_data.h_els.port_id[2];
+		port_id = (bsg_request->rqst_data.h_els.port_id[0] << 16) |
+			(bsg_request->rqst_data.h_els.port_id[1] << 8) |
+			bsg_request->rqst_data.h_els.port_id[2];
 	case FC_BSG_RPT_ELS:
 		fc_flags = IBMVFC_FC_ELS;
 		break;
 	case FC_BSG_HST_CT:
 		issue_login = 1;
-		port_id = (job->request->rqst_data.h_ct.port_id[0] << 16) |
-			(job->request->rqst_data.h_ct.port_id[1] << 8) |
-			job->request->rqst_data.h_ct.port_id[2];
+		port_id = (bsg_request->rqst_data.h_ct.port_id[0] << 16) |
+			(bsg_request->rqst_data.h_ct.port_id[1] << 8) |
+			bsg_request->rqst_data.h_ct.port_id[2];
 	case FC_BSG_RPT_CT:
 		fc_flags = IBMVFC_FC_CT_IU;
 		break;
@@ -1937,13 +1940,14 @@ static int ibmvfc_bsg_request(struct fc_bsg_job *job)
 	if (rsp_iu.passthru.common.status)
 		rc = -EIO;
 	else
-		job->reply->reply_payload_rcv_len = rsp_len;
+		bsg_reply->reply_payload_rcv_len = rsp_len;
 
 	spin_lock_irqsave(vhost->host->host_lock, flags);
 	ibmvfc_free_event(evt);
 	spin_unlock_irqrestore(vhost->host->host_lock, flags);
-	job->reply->result = rc;
-	job->job_done(job);
+	bsg_reply->result = rc;
+	bsg_job_done(job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	rc = 0;
 out:
 	dma_unmap_sg(vhost->dev, job->request_payload.sg_list,
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index d9534ee6ef52..50cd01165e35 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -95,6 +95,7 @@ static int fast_fail = 1;
 static int client_reserve = 1;
 static char partition_name[97] = "UNKNOWN";
 static unsigned int partition_number = -1;
+static LIST_HEAD(ibmvscsi_head);
 
 static struct scsi_transport_template *ibmvscsi_transport_template;
 
@@ -232,6 +233,7 @@ static void ibmvscsi_task(void *data)
 		while ((crq = crq_queue_next_crq(&hostdata->queue)) != NULL) {
 			ibmvscsi_handle_crq(crq, hostdata);
 			crq->valid = VIOSRP_CRQ_FREE;
+			wmb();
 		}
 
 		vio_enable_interrupts(vdev);
@@ -240,6 +242,7 @@ static void ibmvscsi_task(void *data)
 			vio_disable_interrupts(vdev);
 			ibmvscsi_handle_crq(crq, hostdata);
 			crq->valid = VIOSRP_CRQ_FREE;
+			wmb();
 		} else {
 			done = 1;
 		}
@@ -992,7 +995,7 @@ static void handle_cmd_rsp(struct srp_event_struct *evt_struct)
 	if (unlikely(rsp->opcode != SRP_RSP)) {
 		if (printk_ratelimit())
 			dev_warn(evt_struct->hostdata->dev,
-				 "bad SRP RSP type %d\n", rsp->opcode);
+				 "bad SRP RSP type %#02x\n", rsp->opcode);
 	}
 	
 	if (cmnd) {
@@ -2270,6 +2273,7 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	}
 
 	dev_set_drvdata(&vdev->dev, hostdata);
+	list_add_tail(&hostdata->host_list, &ibmvscsi_head);
 	return 0;
 
       add_srp_port_failed:
@@ -2291,6 +2295,7 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 static int ibmvscsi_remove(struct vio_dev *vdev)
 {
 	struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev);
+	list_del(&hostdata->host_list);
 	unmap_persist_bufs(hostdata);
 	release_event_pool(&hostdata->pool, hostdata);
 	ibmvscsi_release_crq_queue(&hostdata->queue, hostdata,
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.h b/drivers/scsi/ibmvscsi/ibmvscsi.h
index e0f6c3aeb4ee..3a7875575616 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.h
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.h
@@ -90,6 +90,7 @@ struct event_pool {
 
 /* all driver data associated with a host adapter */
 struct ibmvscsi_host_data {
+	struct list_head host_list;
 	atomic_t request_limit;
 	int client_migrated;
 	int reset_crq;
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 642b739ad0da..3d3768aaab4f 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -22,7 +22,7 @@
  *
  ****************************************************************************/
 
-#define pr_fmt(fmt)     KBUILD_MODNAME ": " fmt
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -30,6 +30,7 @@
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/string.h>
+#include <linux/delay.h>
 
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
@@ -81,7 +82,7 @@ static void ibmvscsis_determine_resid(struct se_cmd *se_cmd,
 		}
 	} else if (se_cmd->se_cmd_flags & SCF_OVERFLOW_BIT) {
 		if (se_cmd->data_direction == DMA_TO_DEVICE) {
-			/*  residual data from an overflow write */
+			/* residual data from an overflow write */
 			rsp->flags = SRP_RSP_FLAG_DOOVER;
 			rsp->data_out_res_cnt = cpu_to_be32(residual_count);
 		} else if (se_cmd->data_direction == DMA_FROM_DEVICE) {
@@ -101,7 +102,7 @@ static void ibmvscsis_determine_resid(struct se_cmd *se_cmd,
  * and the function returns TRUE.
  *
  * EXECUTION ENVIRONMENT:
- *      Interrupt or Process environment
+ *	Interrupt or Process environment
  */
 static bool connection_broken(struct scsi_info *vscsi)
 {
@@ -324,7 +325,7 @@ static struct viosrp_crq *ibmvscsis_cmd_q_dequeue(uint mask,
 }
 
 /**
- * ibmvscsis_send_init_message() -  send initialize message to the client
+ * ibmvscsis_send_init_message() - send initialize message to the client
  * @vscsi:	Pointer to our adapter structure
  * @format:	Which Init Message format to send
  *
@@ -382,13 +383,13 @@ static long ibmvscsis_check_init_msg(struct scsi_info *vscsi, uint *format)
 					      vscsi->cmd_q.base_addr);
 		if (crq) {
 			*format = (uint)(crq->format);
-			rc =  ERROR;
+			rc = ERROR;
 			crq->valid = INVALIDATE_CMD_RESP_EL;
 			dma_rmb();
 		}
 	} else {
 		*format = (uint)(crq->format);
-		rc =  ERROR;
+		rc = ERROR;
 		crq->valid = INVALIDATE_CMD_RESP_EL;
 		dma_rmb();
 	}
@@ -397,166 +398,6 @@ static long ibmvscsis_check_init_msg(struct scsi_info *vscsi, uint *format)
 }
 
 /**
- * ibmvscsis_establish_new_q() - Establish new CRQ queue
- * @vscsi:	Pointer to our adapter structure
- * @new_state:	New state being established after resetting the queue
- *
- * Must be called with interrupt lock held.
- */
-static long ibmvscsis_establish_new_q(struct scsi_info *vscsi,  uint new_state)
-{
-	long rc = ADAPT_SUCCESS;
-	uint format;
-
-	vscsi->flags &= PRESERVE_FLAG_FIELDS;
-	vscsi->rsp_q_timer.timer_pops = 0;
-	vscsi->debit = 0;
-	vscsi->credit = 0;
-
-	rc = vio_enable_interrupts(vscsi->dma_dev);
-	if (rc) {
-		pr_warn("reset_queue: failed to enable interrupts, rc %ld\n",
-			rc);
-		return rc;
-	}
-
-	rc = ibmvscsis_check_init_msg(vscsi, &format);
-	if (rc) {
-		dev_err(&vscsi->dev, "reset_queue: check_init_msg failed, rc %ld\n",
-			rc);
-		return rc;
-	}
-
-	if (format == UNUSED_FORMAT && new_state == WAIT_CONNECTION) {
-		rc = ibmvscsis_send_init_message(vscsi, INIT_MSG);
-		switch (rc) {
-		case H_SUCCESS:
-		case H_DROPPED:
-		case H_CLOSED:
-			rc = ADAPT_SUCCESS;
-			break;
-
-		case H_PARAMETER:
-		case H_HARDWARE:
-			break;
-
-		default:
-			vscsi->state = UNDEFINED;
-			rc = H_HARDWARE;
-			break;
-		}
-	}
-
-	return rc;
-}
-
-/**
- * ibmvscsis_reset_queue() - Reset CRQ Queue
- * @vscsi:	Pointer to our adapter structure
- * @new_state:	New state to establish after resetting the queue
- *
- * This function calls h_free_q and then calls h_reg_q and does all
- * of the bookkeeping to get us back to where we can communicate.
- *
- * Actually, we don't always call h_free_crq.  A problem was discovered
- * where one partition would close and reopen his queue, which would
- * cause his partner to get a transport event, which would cause him to
- * close and reopen his queue, which would cause the original partition
- * to get a transport event, etc., etc.  To prevent this, we don't
- * actually close our queue if the client initiated the reset, (i.e.
- * either we got a transport event or we have detected that the client's
- * queue is gone)
- *
- * EXECUTION ENVIRONMENT:
- *	Process environment, called with interrupt lock held
- */
-static void ibmvscsis_reset_queue(struct scsi_info *vscsi, uint new_state)
-{
-	int bytes;
-	long rc = ADAPT_SUCCESS;
-
-	pr_debug("reset_queue: flags 0x%x\n", vscsi->flags);
-
-	/* don't reset, the client did it for us */
-	if (vscsi->flags & (CLIENT_FAILED | TRANS_EVENT)) {
-		vscsi->flags &=  PRESERVE_FLAG_FIELDS;
-		vscsi->rsp_q_timer.timer_pops = 0;
-		vscsi->debit = 0;
-		vscsi->credit = 0;
-		vscsi->state = new_state;
-		vio_enable_interrupts(vscsi->dma_dev);
-	} else {
-		rc = ibmvscsis_free_command_q(vscsi);
-		if (rc == ADAPT_SUCCESS) {
-			vscsi->state = new_state;
-
-			bytes = vscsi->cmd_q.size * PAGE_SIZE;
-			rc = h_reg_crq(vscsi->dds.unit_id,
-				       vscsi->cmd_q.crq_token, bytes);
-			if (rc == H_CLOSED || rc == H_SUCCESS) {
-				rc = ibmvscsis_establish_new_q(vscsi,
-							       new_state);
-			}
-
-			if (rc != ADAPT_SUCCESS) {
-				pr_debug("reset_queue: reg_crq rc %ld\n", rc);
-
-				vscsi->state = ERR_DISCONNECTED;
-				vscsi->flags |=  RESPONSE_Q_DOWN;
-				ibmvscsis_free_command_q(vscsi);
-			}
-		} else {
-			vscsi->state = ERR_DISCONNECTED;
-			vscsi->flags |= RESPONSE_Q_DOWN;
-		}
-	}
-}
-
-/**
- * ibmvscsis_free_cmd_resources() - Free command resources
- * @vscsi:	Pointer to our adapter structure
- * @cmd:	Command which is not longer in use
- *
- * Must be called with interrupt lock held.
- */
-static void ibmvscsis_free_cmd_resources(struct scsi_info *vscsi,
-					 struct ibmvscsis_cmd *cmd)
-{
-	struct iu_entry *iue = cmd->iue;
-
-	switch (cmd->type) {
-	case TASK_MANAGEMENT:
-	case SCSI_CDB:
-		/*
-		 * When the queue goes down this value is cleared, so it
-		 * cannot be cleared in this general purpose function.
-		 */
-		if (vscsi->debit)
-			vscsi->debit -= 1;
-		break;
-	case ADAPTER_MAD:
-		vscsi->flags &= ~PROCESSING_MAD;
-		break;
-	case UNSET_TYPE:
-		break;
-	default:
-		dev_err(&vscsi->dev, "free_cmd_resources unknown type %d\n",
-			cmd->type);
-		break;
-	}
-
-	cmd->iue = NULL;
-	list_add_tail(&cmd->list, &vscsi->free_cmd);
-	srp_iu_put(iue);
-
-	if (list_empty(&vscsi->active_q) && list_empty(&vscsi->schedule_q) &&
-	    list_empty(&vscsi->waiting_rsp) && (vscsi->flags & WAIT_FOR_IDLE)) {
-		vscsi->flags &= ~WAIT_FOR_IDLE;
-		complete(&vscsi->wait_idle);
-	}
-}
-
-/**
  * ibmvscsis_disconnect() - Helper function to disconnect
  * @work:	Pointer to work_struct, gives access to our adapter structure
  *
@@ -575,7 +416,6 @@ static void ibmvscsis_disconnect(struct work_struct *work)
 					       proc_work);
 	u16 new_state;
 	bool wait_idle = false;
-	long rc = ADAPT_SUCCESS;
 
 	spin_lock_bh(&vscsi->intr_lock);
 	new_state = vscsi->new_state;
@@ -589,7 +429,7 @@ static void ibmvscsis_disconnect(struct work_struct *work)
 	 * should transitition to the new state
 	 */
 	switch (vscsi->state) {
-	/*  Should never be called while in this state. */
+	/* Should never be called while in this state. */
 	case NO_QUEUE:
 	/*
 	 * Can never transition from this state;
@@ -628,30 +468,24 @@ static void ibmvscsis_disconnect(struct work_struct *work)
 			vscsi->state = new_state;
 		break;
 
-	/*
-	 * If this is a transition into an error state.
-	 * a client is attempting to establish a connection
-	 * and has violated the RPA protocol.
-	 * There can be nothing pending on the adapter although
-	 * there can be requests in the command queue.
-	 */
 	case WAIT_ENABLED:
-	case PART_UP_WAIT_ENAB:
 		switch (new_state) {
-		case ERR_DISCONNECT:
-			vscsi->flags |= RESPONSE_Q_DOWN;
+		case UNCONFIGURING:
 			vscsi->state = new_state;
+			vscsi->flags |= RESPONSE_Q_DOWN;
 			vscsi->flags &= ~(SCHEDULE_DISCONNECT |
 					  DISCONNECT_SCHEDULED);
-			ibmvscsis_free_command_q(vscsi);
-			break;
-		case ERR_DISCONNECT_RECONNECT:
-			ibmvscsis_reset_queue(vscsi, WAIT_ENABLED);
+			dma_rmb();
+			if (vscsi->flags & CFG_SLEEPING) {
+				vscsi->flags &= ~CFG_SLEEPING;
+				complete(&vscsi->unconfig);
+			}
 			break;
 
 		/* should never happen */
+		case ERR_DISCONNECT:
+		case ERR_DISCONNECT_RECONNECT:
 		case WAIT_IDLE:
-			rc = ERROR;
 			dev_err(&vscsi->dev, "disconnect: invalid state %d for WAIT_IDLE\n",
 				vscsi->state);
 			break;
@@ -660,6 +494,13 @@ static void ibmvscsis_disconnect(struct work_struct *work)
 
 	case WAIT_IDLE:
 		switch (new_state) {
+		case UNCONFIGURING:
+			vscsi->flags |= RESPONSE_Q_DOWN;
+			vscsi->state = new_state;
+			vscsi->flags &= ~(SCHEDULE_DISCONNECT |
+					  DISCONNECT_SCHEDULED);
+			ibmvscsis_free_command_q(vscsi);
+			break;
 		case ERR_DISCONNECT:
 		case ERR_DISCONNECT_RECONNECT:
 			vscsi->state = new_state;
@@ -788,7 +629,6 @@ static void ibmvscsis_post_disconnect(struct scsi_info *vscsi, uint new_state,
 			break;
 
 		case WAIT_ENABLED:
-		case PART_UP_WAIT_ENAB:
 		case WAIT_IDLE:
 		case WAIT_CONNECTION:
 		case CONNECTED:
@@ -806,6 +646,310 @@ static void ibmvscsis_post_disconnect(struct scsi_info *vscsi, uint new_state,
 }
 
 /**
+ * ibmvscsis_handle_init_compl_msg() - Respond to an Init Complete Message
+ * @vscsi:	Pointer to our adapter structure
+ *
+ * Must be called with interrupt lock held.
+ */
+static long ibmvscsis_handle_init_compl_msg(struct scsi_info *vscsi)
+{
+	long rc = ADAPT_SUCCESS;
+
+	switch (vscsi->state) {
+	case NO_QUEUE:
+	case ERR_DISCONNECT:
+	case ERR_DISCONNECT_RECONNECT:
+	case ERR_DISCONNECTED:
+	case UNCONFIGURING:
+	case UNDEFINED:
+		rc = ERROR;
+		break;
+
+	case WAIT_CONNECTION:
+		vscsi->state = CONNECTED;
+		break;
+
+	case WAIT_IDLE:
+	case SRP_PROCESSING:
+	case CONNECTED:
+	case WAIT_ENABLED:
+	default:
+		rc = ERROR;
+		dev_err(&vscsi->dev, "init_msg: invalid state %d to get init compl msg\n",
+			vscsi->state);
+		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
+		break;
+	}
+
+	return rc;
+}
+
+/**
+ * ibmvscsis_handle_init_msg() - Respond to an Init Message
+ * @vscsi:	Pointer to our adapter structure
+ *
+ * Must be called with interrupt lock held.
+ */
+static long ibmvscsis_handle_init_msg(struct scsi_info *vscsi)
+{
+	long rc = ADAPT_SUCCESS;
+
+	switch (vscsi->state) {
+	case WAIT_CONNECTION:
+		rc = ibmvscsis_send_init_message(vscsi, INIT_COMPLETE_MSG);
+		switch (rc) {
+		case H_SUCCESS:
+			vscsi->state = CONNECTED;
+			break;
+
+		case H_PARAMETER:
+			dev_err(&vscsi->dev, "init_msg: failed to send, rc %ld\n",
+				rc);
+			ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT, 0);
+			break;
+
+		case H_DROPPED:
+			dev_err(&vscsi->dev, "init_msg: failed to send, rc %ld\n",
+				rc);
+			rc = ERROR;
+			ibmvscsis_post_disconnect(vscsi,
+						  ERR_DISCONNECT_RECONNECT, 0);
+			break;
+
+		case H_CLOSED:
+			pr_warn("init_msg: failed to send, rc %ld\n", rc);
+			rc = 0;
+			break;
+		}
+		break;
+
+	case UNDEFINED:
+		rc = ERROR;
+		break;
+
+	case UNCONFIGURING:
+		break;
+
+	case WAIT_ENABLED:
+	case CONNECTED:
+	case SRP_PROCESSING:
+	case WAIT_IDLE:
+	case NO_QUEUE:
+	case ERR_DISCONNECT:
+	case ERR_DISCONNECT_RECONNECT:
+	case ERR_DISCONNECTED:
+	default:
+		rc = ERROR;
+		dev_err(&vscsi->dev, "init_msg: invalid state %d to get init msg\n",
+			vscsi->state);
+		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
+		break;
+	}
+
+	return rc;
+}
+
+/**
+ * ibmvscsis_init_msg() - Respond to an init message
+ * @vscsi:	Pointer to our adapter structure
+ * @crq:	Pointer to CRQ element containing the Init Message
+ *
+ * EXECUTION ENVIRONMENT:
+ *	Interrupt, interrupt lock held
+ */
+static long ibmvscsis_init_msg(struct scsi_info *vscsi, struct viosrp_crq *crq)
+{
+	long rc = ADAPT_SUCCESS;
+
+	pr_debug("init_msg: state 0x%hx\n", vscsi->state);
+
+	rc = h_vioctl(vscsi->dds.unit_id, H_GET_PARTNER_INFO,
+		      (u64)vscsi->map_ioba | ((u64)PAGE_SIZE << 32), 0, 0, 0,
+		      0);
+	if (rc == H_SUCCESS) {
+		vscsi->client_data.partition_number =
+			be64_to_cpu(*(u64 *)vscsi->map_buf);
+		pr_debug("init_msg, part num %d\n",
+			 vscsi->client_data.partition_number);
+	} else {
+		pr_debug("init_msg h_vioctl rc %ld\n", rc);
+		rc = ADAPT_SUCCESS;
+	}
+
+	if (crq->format == INIT_MSG) {
+		rc = ibmvscsis_handle_init_msg(vscsi);
+	} else if (crq->format == INIT_COMPLETE_MSG) {
+		rc = ibmvscsis_handle_init_compl_msg(vscsi);
+	} else {
+		rc = ERROR;
+		dev_err(&vscsi->dev, "init_msg: invalid format %d\n",
+			(uint)crq->format);
+		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
+	}
+
+	return rc;
+}
+
+/**
+ * ibmvscsis_establish_new_q() - Establish new CRQ queue
+ * @vscsi:	Pointer to our adapter structure
+ *
+ * Must be called with interrupt lock held.
+ */
+static long ibmvscsis_establish_new_q(struct scsi_info *vscsi)
+{
+	long rc = ADAPT_SUCCESS;
+	uint format;
+
+	vscsi->flags &= PRESERVE_FLAG_FIELDS;
+	vscsi->rsp_q_timer.timer_pops = 0;
+	vscsi->debit = 0;
+	vscsi->credit = 0;
+
+	rc = vio_enable_interrupts(vscsi->dma_dev);
+	if (rc) {
+		pr_warn("establish_new_q: failed to enable interrupts, rc %ld\n",
+			rc);
+		return rc;
+	}
+
+	rc = ibmvscsis_check_init_msg(vscsi, &format);
+	if (rc) {
+		dev_err(&vscsi->dev, "establish_new_q: check_init_msg failed, rc %ld\n",
+			rc);
+		return rc;
+	}
+
+	if (format == UNUSED_FORMAT) {
+		rc = ibmvscsis_send_init_message(vscsi, INIT_MSG);
+		switch (rc) {
+		case H_SUCCESS:
+		case H_DROPPED:
+		case H_CLOSED:
+			rc = ADAPT_SUCCESS;
+			break;
+
+		case H_PARAMETER:
+		case H_HARDWARE:
+			break;
+
+		default:
+			vscsi->state = UNDEFINED;
+			rc = H_HARDWARE;
+			break;
+		}
+	} else if (format == INIT_MSG) {
+		rc = ibmvscsis_handle_init_msg(vscsi);
+	}
+
+	return rc;
+}
+
+/**
+ * ibmvscsis_reset_queue() - Reset CRQ Queue
+ * @vscsi:	Pointer to our adapter structure
+ *
+ * This function calls h_free_q and then calls h_reg_q and does all
+ * of the bookkeeping to get us back to where we can communicate.
+ *
+ * Actually, we don't always call h_free_crq.  A problem was discovered
+ * where one partition would close and reopen his queue, which would
+ * cause his partner to get a transport event, which would cause him to
+ * close and reopen his queue, which would cause the original partition
+ * to get a transport event, etc., etc.  To prevent this, we don't
+ * actually close our queue if the client initiated the reset, (i.e.
+ * either we got a transport event or we have detected that the client's
+ * queue is gone)
+ *
+ * EXECUTION ENVIRONMENT:
+ *	Process environment, called with interrupt lock held
+ */
+static void ibmvscsis_reset_queue(struct scsi_info *vscsi)
+{
+	int bytes;
+	long rc = ADAPT_SUCCESS;
+
+	pr_debug("reset_queue: flags 0x%x\n", vscsi->flags);
+
+	/* don't reset, the client did it for us */
+	if (vscsi->flags & (CLIENT_FAILED | TRANS_EVENT)) {
+		vscsi->flags &= PRESERVE_FLAG_FIELDS;
+		vscsi->rsp_q_timer.timer_pops = 0;
+		vscsi->debit = 0;
+		vscsi->credit = 0;
+		vscsi->state = WAIT_CONNECTION;
+		vio_enable_interrupts(vscsi->dma_dev);
+	} else {
+		rc = ibmvscsis_free_command_q(vscsi);
+		if (rc == ADAPT_SUCCESS) {
+			vscsi->state = WAIT_CONNECTION;
+
+			bytes = vscsi->cmd_q.size * PAGE_SIZE;
+			rc = h_reg_crq(vscsi->dds.unit_id,
+				       vscsi->cmd_q.crq_token, bytes);
+			if (rc == H_CLOSED || rc == H_SUCCESS) {
+				rc = ibmvscsis_establish_new_q(vscsi);
+			}
+
+			if (rc != ADAPT_SUCCESS) {
+				pr_debug("reset_queue: reg_crq rc %ld\n", rc);
+
+				vscsi->state = ERR_DISCONNECTED;
+				vscsi->flags |= RESPONSE_Q_DOWN;
+				ibmvscsis_free_command_q(vscsi);
+			}
+		} else {
+			vscsi->state = ERR_DISCONNECTED;
+			vscsi->flags |= RESPONSE_Q_DOWN;
+		}
+	}
+}
+
+/**
+ * ibmvscsis_free_cmd_resources() - Free command resources
+ * @vscsi:	Pointer to our adapter structure
+ * @cmd:	Command which is not longer in use
+ *
+ * Must be called with interrupt lock held.
+ */
+static void ibmvscsis_free_cmd_resources(struct scsi_info *vscsi,
+					 struct ibmvscsis_cmd *cmd)
+{
+	struct iu_entry *iue = cmd->iue;
+
+	switch (cmd->type) {
+	case TASK_MANAGEMENT:
+	case SCSI_CDB:
+		/*
+		 * When the queue goes down this value is cleared, so it
+		 * cannot be cleared in this general purpose function.
+		 */
+		if (vscsi->debit)
+			vscsi->debit -= 1;
+		break;
+	case ADAPTER_MAD:
+		vscsi->flags &= ~PROCESSING_MAD;
+		break;
+	case UNSET_TYPE:
+		break;
+	default:
+		dev_err(&vscsi->dev, "free_cmd_resources unknown type %d\n",
+			cmd->type);
+		break;
+	}
+
+	cmd->iue = NULL;
+	list_add_tail(&cmd->list, &vscsi->free_cmd);
+	srp_iu_put(iue);
+
+	if (list_empty(&vscsi->active_q) && list_empty(&vscsi->schedule_q) &&
+	    list_empty(&vscsi->waiting_rsp) && (vscsi->flags & WAIT_FOR_IDLE)) {
+		vscsi->flags &= ~WAIT_FOR_IDLE;
+		complete(&vscsi->wait_idle);
+	}
+}
+
+/**
  * ibmvscsis_trans_event() - Handle a Transport Event
  * @vscsi:	Pointer to our adapter structure
  * @crq:	Pointer to CRQ entry containing the Transport Event
@@ -863,10 +1007,6 @@ static long ibmvscsis_trans_event(struct scsi_info *vscsi,
 						   TRANS_EVENT));
 			break;
 
-		case PART_UP_WAIT_ENAB:
-			vscsi->state = WAIT_ENABLED;
-			break;
-
 		case SRP_PROCESSING:
 			if ((vscsi->debit > 0) ||
 			    !list_empty(&vscsi->schedule_q) ||
@@ -895,7 +1035,7 @@ static long ibmvscsis_trans_event(struct scsi_info *vscsi,
 		}
 	}
 
-	rc =  vscsi->flags & SCHEDULE_DISCONNECT;
+	rc = vscsi->flags & SCHEDULE_DISCONNECT;
 
 	pr_debug("Leaving trans_event: flags 0x%x, state 0x%hx, rc %ld\n",
 		 vscsi->flags, vscsi->state, rc);
@@ -1066,16 +1206,28 @@ static void ibmvscsis_adapter_idle(struct scsi_info *vscsi)
 		free_qs = true;
 
 	switch (vscsi->state) {
+	case UNCONFIGURING:
+		ibmvscsis_free_command_q(vscsi);
+		dma_rmb();
+		isync();
+		if (vscsi->flags & CFG_SLEEPING) {
+			vscsi->flags &= ~CFG_SLEEPING;
+			complete(&vscsi->unconfig);
+		}
+		break;
 	case ERR_DISCONNECT_RECONNECT:
-		ibmvscsis_reset_queue(vscsi, WAIT_CONNECTION);
+		ibmvscsis_reset_queue(vscsi);
 		pr_debug("adapter_idle, disc_rec: flags 0x%x\n", vscsi->flags);
 		break;
 
 	case ERR_DISCONNECT:
 		ibmvscsis_free_command_q(vscsi);
-		vscsi->flags &= ~DISCONNECT_SCHEDULED;
+		vscsi->flags &= ~(SCHEDULE_DISCONNECT | DISCONNECT_SCHEDULED);
 		vscsi->flags |= RESPONSE_Q_DOWN;
-		vscsi->state = ERR_DISCONNECTED;
+		if (vscsi->tport.enabled)
+			vscsi->state = ERR_DISCONNECTED;
+		else
+			vscsi->state = WAIT_ENABLED;
 		pr_debug("adapter_idle, disc: flags 0x%x, state 0x%hx\n",
 			 vscsi->flags, vscsi->state);
 		break;
@@ -1220,7 +1372,7 @@ static long ibmvscsis_copy_crq_packet(struct scsi_info *vscsi,
  * @iue:	Information Unit containing the Adapter Info MAD request
  *
  * EXECUTION ENVIRONMENT:
- *	Interrupt adpater lock is held
+ *	Interrupt adapter lock is held
  */
 static long ibmvscsis_adapter_info(struct scsi_info *vscsi,
 				   struct iu_entry *iue)
@@ -1542,7 +1694,7 @@ static void srp_snd_msg_failed(struct scsi_info *vscsi, long rc)
 		if (!vscsi->rsp_q_timer.started) {
 			if (vscsi->rsp_q_timer.timer_pops <
 			    MAX_TIMER_POPS) {
-				kt = ktime_set(0, WAIT_NANO_SECONDS);
+				kt = WAIT_NANO_SECONDS;
 			} else {
 				/*
 				 * slide the timeslice if the maximum
@@ -1620,8 +1772,8 @@ static void ibmvscsis_send_messages(struct scsi_info *vscsi)
 					be64_to_cpu(msg_hi),
 					be64_to_cpu(cmd->rsp.tag));
 
-			pr_debug("send_messages: tag 0x%llx, rc %ld\n",
-				 be64_to_cpu(cmd->rsp.tag), rc);
+			pr_debug("send_messages: cmd %p, tag 0x%llx, rc %ld\n",
+				 cmd, be64_to_cpu(cmd->rsp.tag), rc);
 
 			/* if all ok free up the command element resources */
 			if (rc == H_SUCCESS) {
@@ -1691,7 +1843,7 @@ static void ibmvscsis_send_mad_resp(struct scsi_info *vscsi,
  * @crq:	Pointer to the CRQ entry containing the MAD request
  *
  * EXECUTION ENVIRONMENT:
- *	Interrupt  called with adapter lock held
+ *	Interrupt, called with adapter lock held
  */
 static long ibmvscsis_mad(struct scsi_info *vscsi, struct viosrp_crq *crq)
 {
@@ -1745,14 +1897,7 @@ static long ibmvscsis_mad(struct scsi_info *vscsi, struct viosrp_crq *crq)
 
 		pr_debug("mad: type %d\n", be32_to_cpu(mad->type));
 
-		if (be16_to_cpu(mad->length) < 0) {
-			dev_err(&vscsi->dev, "mad: length is < 0\n");
-			ibmvscsis_post_disconnect(vscsi,
-						  ERR_DISCONNECT_RECONNECT, 0);
-			rc = SRP_VIOLATION;
-		} else {
-			rc = ibmvscsis_process_mad(vscsi, iue);
-		}
+		rc = ibmvscsis_process_mad(vscsi, iue);
 
 		pr_debug("mad: status %hd, rc %ld\n", be16_to_cpu(mad->status),
 			 rc);
@@ -1864,7 +2009,7 @@ static long ibmvscsis_srp_login_rej(struct scsi_info *vscsi,
 		break;
 	case H_PERMISSION:
 		if (connection_broken(vscsi))
-			flag_bits =  RESPONSE_Q_DOWN | CLIENT_FAILED;
+			flag_bits = RESPONSE_Q_DOWN | CLIENT_FAILED;
 		dev_err(&vscsi->dev, "login_rej: error copying to client, rc %ld\n",
 			rc);
 		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT,
@@ -2187,156 +2332,6 @@ static long ibmvscsis_ping_response(struct scsi_info *vscsi)
 }
 
 /**
- * ibmvscsis_handle_init_compl_msg() - Respond to an Init Complete Message
- * @vscsi:	Pointer to our adapter structure
- *
- * Must be called with interrupt lock held.
- */
-static long ibmvscsis_handle_init_compl_msg(struct scsi_info *vscsi)
-{
-	long rc = ADAPT_SUCCESS;
-
-	switch (vscsi->state) {
-	case NO_QUEUE:
-	case ERR_DISCONNECT:
-	case ERR_DISCONNECT_RECONNECT:
-	case ERR_DISCONNECTED:
-	case UNCONFIGURING:
-	case UNDEFINED:
-		rc = ERROR;
-		break;
-
-	case WAIT_CONNECTION:
-		vscsi->state = CONNECTED;
-		break;
-
-	case WAIT_IDLE:
-	case SRP_PROCESSING:
-	case CONNECTED:
-	case WAIT_ENABLED:
-	case PART_UP_WAIT_ENAB:
-	default:
-		rc = ERROR;
-		dev_err(&vscsi->dev, "init_msg: invalid state %d to get init compl msg\n",
-			vscsi->state);
-		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
-		break;
-	}
-
-	return rc;
-}
-
-/**
- * ibmvscsis_handle_init_msg() - Respond to an Init Message
- * @vscsi:	Pointer to our adapter structure
- *
- * Must be called with interrupt lock held.
- */
-static long ibmvscsis_handle_init_msg(struct scsi_info *vscsi)
-{
-	long rc = ADAPT_SUCCESS;
-
-	switch (vscsi->state) {
-	case WAIT_ENABLED:
-		vscsi->state = PART_UP_WAIT_ENAB;
-		break;
-
-	case WAIT_CONNECTION:
-		rc = ibmvscsis_send_init_message(vscsi, INIT_COMPLETE_MSG);
-		switch (rc) {
-		case H_SUCCESS:
-			vscsi->state = CONNECTED;
-			break;
-
-		case H_PARAMETER:
-			dev_err(&vscsi->dev, "init_msg: failed to send, rc %ld\n",
-				rc);
-			ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT, 0);
-			break;
-
-		case H_DROPPED:
-			dev_err(&vscsi->dev, "init_msg: failed to send, rc %ld\n",
-				rc);
-			rc = ERROR;
-			ibmvscsis_post_disconnect(vscsi,
-						  ERR_DISCONNECT_RECONNECT, 0);
-			break;
-
-		case H_CLOSED:
-			pr_warn("init_msg: failed to send, rc %ld\n", rc);
-			rc = 0;
-			break;
-		}
-		break;
-
-	case UNDEFINED:
-		rc = ERROR;
-		break;
-
-	case UNCONFIGURING:
-		break;
-
-	case PART_UP_WAIT_ENAB:
-	case CONNECTED:
-	case SRP_PROCESSING:
-	case WAIT_IDLE:
-	case NO_QUEUE:
-	case ERR_DISCONNECT:
-	case ERR_DISCONNECT_RECONNECT:
-	case ERR_DISCONNECTED:
-	default:
-		rc = ERROR;
-		dev_err(&vscsi->dev, "init_msg: invalid state %d to get init msg\n",
-			vscsi->state);
-		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
-		break;
-	}
-
-	return rc;
-}
-
-/**
- * ibmvscsis_init_msg() - Respond to an init message
- * @vscsi:	Pointer to our adapter structure
- * @crq:	Pointer to CRQ element containing the Init Message
- *
- * EXECUTION ENVIRONMENT:
- *	Interrupt, interrupt lock held
- */
-static long ibmvscsis_init_msg(struct scsi_info *vscsi, struct viosrp_crq *crq)
-{
-	long rc = ADAPT_SUCCESS;
-
-	pr_debug("init_msg: state 0x%hx\n", vscsi->state);
-
-	rc = h_vioctl(vscsi->dds.unit_id, H_GET_PARTNER_INFO,
-		      (u64)vscsi->map_ioba | ((u64)PAGE_SIZE << 32), 0, 0, 0,
-		      0);
-	if (rc == H_SUCCESS) {
-		vscsi->client_data.partition_number =
-			be64_to_cpu(*(u64 *)vscsi->map_buf);
-		pr_debug("init_msg, part num %d\n",
-			 vscsi->client_data.partition_number);
-	} else {
-		pr_debug("init_msg h_vioctl rc %ld\n", rc);
-		rc = ADAPT_SUCCESS;
-	}
-
-	if (crq->format == INIT_MSG) {
-		rc = ibmvscsis_handle_init_msg(vscsi);
-	} else if (crq->format == INIT_COMPLETE_MSG) {
-		rc = ibmvscsis_handle_init_compl_msg(vscsi);
-	} else {
-		rc = ERROR;
-		dev_err(&vscsi->dev, "init_msg: invalid format %d\n",
-			(uint)crq->format);
-		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
-	}
-
-	return rc;
-}
-
-/**
  * ibmvscsis_parse_command() - Parse an element taken from the cmd rsp queue.
  * @vscsi:	Pointer to our adapter structure
  * @crq:	Pointer to CRQ element containing the SRP request
@@ -2391,7 +2386,7 @@ static long ibmvscsis_parse_command(struct scsi_info *vscsi,
 		break;
 
 	case VALID_TRANS_EVENT:
-		rc =  ibmvscsis_trans_event(vscsi, crq);
+		rc = ibmvscsis_trans_event(vscsi, crq);
 		break;
 
 	case VALID_INIT_MSG:
@@ -2522,7 +2517,6 @@ static void ibmvscsis_parse_cmd(struct scsi_info *vscsi,
 		dev_err(&vscsi->dev, "0x%llx: parsing SRP descriptor table failed.\n",
 			srp->tag);
 		goto fail;
-		return;
 	}
 
 	cmd->rsp.sol_not = srp->sol_not;
@@ -2559,6 +2553,10 @@ static void ibmvscsis_parse_cmd(struct scsi_info *vscsi,
 			       data_len, attr, dir, 0);
 	if (rc) {
 		dev_err(&vscsi->dev, "target_submit_cmd failed, rc %d\n", rc);
+		spin_lock_bh(&vscsi->intr_lock);
+		list_del(&cmd->list);
+		ibmvscsis_free_cmd_resources(vscsi, cmd);
+		spin_unlock_bh(&vscsi->intr_lock);
 		goto fail;
 	}
 	return;
@@ -2638,6 +2636,9 @@ static void ibmvscsis_parse_task(struct scsi_info *vscsi,
 		if (rc) {
 			dev_err(&vscsi->dev, "target_submit_tmr failed, rc %d\n",
 				rc);
+			spin_lock_bh(&vscsi->intr_lock);
+			list_del(&cmd->list);
+			spin_unlock_bh(&vscsi->intr_lock);
 			cmd->se_cmd.se_tmr_req->response =
 				TMR_FUNCTION_REJECTED;
 		}
@@ -2786,36 +2787,6 @@ static irqreturn_t ibmvscsis_interrupt(int dummy, void *data)
 }
 
 /**
- * ibmvscsis_check_q() - Helper function to Check Init Message Valid
- * @vscsi:	Pointer to our adapter structure
- *
- * Checks if a initialize message was queued by the initiatior
- * while the timing window was open.  This function is called from
- * probe after the CRQ is created and interrupts are enabled.
- * It would only be used by adapters who wait for some event before
- * completing the init handshake with the client.  For ibmvscsi, this
- * event is waiting for the port to be enabled.
- *
- * EXECUTION ENVIRONMENT:
- *	Process level only, interrupt lock held
- */
-static long ibmvscsis_check_q(struct scsi_info *vscsi)
-{
-	uint format;
-	long rc;
-
-	rc = ibmvscsis_check_init_msg(vscsi, &format);
-	if (rc)
-		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
-	else if (format == UNUSED_FORMAT)
-		vscsi->state = WAIT_ENABLED;
-	else
-		vscsi->state = PART_UP_WAIT_ENAB;
-
-	return rc;
-}
-
-/**
  * ibmvscsis_enable_change_state() - Set new state based on enabled status
  * @vscsi:	Pointer to our adapter structure
  *
@@ -2826,77 +2797,19 @@ static long ibmvscsis_check_q(struct scsi_info *vscsi)
  */
 static long ibmvscsis_enable_change_state(struct scsi_info *vscsi)
 {
+	int bytes;
 	long rc = ADAPT_SUCCESS;
 
-handle_state_change:
-	switch (vscsi->state) {
-	case WAIT_ENABLED:
-		rc = ibmvscsis_send_init_message(vscsi, INIT_MSG);
-		switch (rc) {
-		case H_SUCCESS:
-		case H_DROPPED:
-		case H_CLOSED:
-			vscsi->state =  WAIT_CONNECTION;
-			rc = ADAPT_SUCCESS;
-			break;
-
-		case H_PARAMETER:
-			break;
-
-		case H_HARDWARE:
-			break;
-
-		default:
-			vscsi->state = UNDEFINED;
-			rc = H_HARDWARE;
-			break;
-		}
-		break;
-	case PART_UP_WAIT_ENAB:
-		rc = ibmvscsis_send_init_message(vscsi, INIT_COMPLETE_MSG);
-		switch (rc) {
-		case H_SUCCESS:
-			vscsi->state = CONNECTED;
-			rc = ADAPT_SUCCESS;
-			break;
-
-		case H_DROPPED:
-		case H_CLOSED:
-			vscsi->state = WAIT_ENABLED;
-			goto handle_state_change;
-
-		case H_PARAMETER:
-			break;
-
-		case H_HARDWARE:
-			break;
-
-		default:
-			rc = H_HARDWARE;
-			break;
-		}
-		break;
-
-	case WAIT_CONNECTION:
-	case WAIT_IDLE:
-	case SRP_PROCESSING:
-	case CONNECTED:
-		rc = ADAPT_SUCCESS;
-		break;
-		/* should not be able to get here */
-	case UNCONFIGURING:
-		rc = ERROR;
-		vscsi->state = UNDEFINED;
-		break;
+	bytes = vscsi->cmd_q.size * PAGE_SIZE;
+	rc = h_reg_crq(vscsi->dds.unit_id, vscsi->cmd_q.crq_token, bytes);
+	if (rc == H_CLOSED || rc == H_SUCCESS) {
+		vscsi->state = WAIT_CONNECTION;
+		rc = ibmvscsis_establish_new_q(vscsi);
+	}
 
-		/* driver should never allow this to happen */
-	case ERR_DISCONNECT:
-	case ERR_DISCONNECT_RECONNECT:
-	default:
-		dev_err(&vscsi->dev, "in invalid state %d during enable_change_state\n",
-			vscsi->state);
-		rc = ADAPT_SUCCESS;
-		break;
+	if (rc != ADAPT_SUCCESS) {
+		vscsi->state = ERR_DISCONNECTED;
+		vscsi->flags |= RESPONSE_Q_DOWN;
 	}
 
 	return rc;
@@ -2916,7 +2829,6 @@ handle_state_change:
  */
 static long ibmvscsis_create_command_q(struct scsi_info *vscsi, int num_cmds)
 {
-	long rc = 0;
 	int pages;
 	struct vio_dev *vdev = vscsi->dma_dev;
 
@@ -2940,22 +2852,7 @@ static long ibmvscsis_create_command_q(struct scsi_info *vscsi, int num_cmds)
 		return -ENOMEM;
 	}
 
-	rc =  h_reg_crq(vscsi->dds.unit_id, vscsi->cmd_q.crq_token, PAGE_SIZE);
-	if (rc) {
-		if (rc == H_CLOSED) {
-			vscsi->state = WAIT_ENABLED;
-			rc = 0;
-		} else {
-			dma_unmap_single(&vdev->dev, vscsi->cmd_q.crq_token,
-					 PAGE_SIZE, DMA_BIDIRECTIONAL);
-			free_page((unsigned long)vscsi->cmd_q.base_addr);
-			rc = -ENODEV;
-		}
-	} else {
-		vscsi->state = WAIT_ENABLED;
-	}
-
-	return rc;
+	return 0;
 }
 
 /**
@@ -3270,7 +3167,7 @@ static void ibmvscsis_handle_crq(unsigned long data)
 	/*
 	 * if we are in a path where we are waiting for all pending commands
 	 * to complete because we received a transport event and anything in
-	 * the command queue is for a new connection,  do nothing
+	 * the command queue is for a new connection, do nothing
 	 */
 	if (TARGET_STOP(vscsi)) {
 		vio_enable_interrupts(vscsi->dma_dev);
@@ -3314,7 +3211,7 @@ cmd_work:
 				 * everything but transport events on the queue
 				 *
 				 * need to decrement the queue index so we can
-				 * look at the elment again
+				 * look at the element again
 				 */
 				if (vscsi->cmd_q.index)
 					vscsi->cmd_q.index -= 1;
@@ -3378,7 +3275,8 @@ static int ibmvscsis_probe(struct vio_dev *vdev,
 	INIT_LIST_HEAD(&vscsi->waiting_rsp);
 	INIT_LIST_HEAD(&vscsi->active_q);
 
-	snprintf(vscsi->tport.tport_name, 256, "%s", dev_name(&vdev->dev));
+	snprintf(vscsi->tport.tport_name, IBMVSCSIS_NAMELEN, "%s",
+		 dev_name(&vdev->dev));
 
 	pr_debug("probe tport_name: %s\n", vscsi->tport.tport_name);
 
@@ -3393,6 +3291,9 @@ static int ibmvscsis_probe(struct vio_dev *vdev,
 	strncat(vscsi->eye, vdev->name, MAX_EYE);
 
 	vscsi->dds.unit_id = vdev->unit_address;
+	strncpy(vscsi->dds.partition_name, partition_name,
+		sizeof(vscsi->dds.partition_name));
+	vscsi->dds.partition_num = partition_number;
 
 	spin_lock_bh(&ibmvscsis_dev_lock);
 	list_add_tail(&vscsi->list, &ibmvscsis_dev_list);
@@ -3469,6 +3370,7 @@ static int ibmvscsis_probe(struct vio_dev *vdev,
 		     (unsigned long)vscsi);
 
 	init_completion(&vscsi->wait_idle);
+	init_completion(&vscsi->unconfig);
 
 	snprintf(wq_name, 24, "ibmvscsis%s", dev_name(&vdev->dev));
 	vscsi->work_q = create_workqueue(wq_name);
@@ -3485,31 +3387,12 @@ static int ibmvscsis_probe(struct vio_dev *vdev,
 		goto destroy_WQ;
 	}
 
-	spin_lock_bh(&vscsi->intr_lock);
-	vio_enable_interrupts(vdev);
-	if (rc) {
-		dev_err(&vscsi->dev, "enabling interrupts failed, rc %d\n", rc);
-		rc = -ENODEV;
-		spin_unlock_bh(&vscsi->intr_lock);
-		goto free_irq;
-	}
-
-	if (ibmvscsis_check_q(vscsi)) {
-		rc = ERROR;
-		dev_err(&vscsi->dev, "probe: check_q failed, rc %d\n", rc);
-		spin_unlock_bh(&vscsi->intr_lock);
-		goto disable_interrupt;
-	}
-	spin_unlock_bh(&vscsi->intr_lock);
+	vscsi->state = WAIT_ENABLED;
 
 	dev_set_drvdata(&vdev->dev, vscsi);
 
 	return 0;
 
-disable_interrupt:
-	vio_disable_interrupts(vdev);
-free_irq:
-	free_irq(vdev->irq, vscsi);
 destroy_WQ:
 	destroy_workqueue(vscsi->work_q);
 unmap_buf:
@@ -3543,10 +3426,11 @@ static int ibmvscsis_remove(struct vio_dev *vdev)
 
 	pr_debug("remove (%s)\n", dev_name(&vscsi->dma_dev->dev));
 
-	/*
-	 * TBD: Need to handle if there are commands on the waiting_rsp q
-	 *      Actually, can there still be cmds outstanding to tcm?
-	 */
+	spin_lock_bh(&vscsi->intr_lock);
+	ibmvscsis_post_disconnect(vscsi, UNCONFIGURING, 0);
+	vscsi->flags |= CFG_SLEEPING;
+	spin_unlock_bh(&vscsi->intr_lock);
+	wait_for_completion(&vscsi->unconfig);
 
 	vio_disable_interrupts(vdev);
 	free_irq(vdev->irq, vscsi);
@@ -3555,7 +3439,6 @@ static int ibmvscsis_remove(struct vio_dev *vdev)
 			 DMA_BIDIRECTIONAL);
 	kfree(vscsi->map_buf);
 	tasklet_kill(&vscsi->work_task);
-	ibmvscsis_unregister_command_q(vscsi);
 	ibmvscsis_destroy_command_q(vscsi);
 	ibmvscsis_freetimer(vscsi);
 	ibmvscsis_free_cmds(vscsi);
@@ -3609,7 +3492,7 @@ static int ibmvscsis_get_system_info(void)
 
 	num = of_get_property(rootdn, "ibm,partition-no", NULL);
 	if (num)
-		partition_number = *num;
+		partition_number = of_read_number(num, 1);
 
 	of_node_put(rootdn);
 
@@ -3903,18 +3786,22 @@ static ssize_t ibmvscsis_tpg_enable_store(struct config_item *item,
 	}
 
 	if (tmp) {
-		tport->enabled = true;
 		spin_lock_bh(&vscsi->intr_lock);
+		tport->enabled = true;
 		lrc = ibmvscsis_enable_change_state(vscsi);
 		if (lrc)
 			pr_err("enable_change_state failed, rc %ld state %d\n",
 			       lrc, vscsi->state);
 		spin_unlock_bh(&vscsi->intr_lock);
 	} else {
+		spin_lock_bh(&vscsi->intr_lock);
 		tport->enabled = false;
+		/* This simulates the server going down */
+		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT, 0);
+		spin_unlock_bh(&vscsi->intr_lock);
 	}
 
-	pr_debug("tpg_enable_store, state %d\n", vscsi->state);
+	pr_debug("tpg_enable_store, tmp %ld, state %d\n", tmp, vscsi->state);
 
 	return count;
 }
@@ -3983,10 +3870,10 @@ static struct attribute *ibmvscsis_dev_attrs[] = {
 ATTRIBUTE_GROUPS(ibmvscsis_dev);
 
 static struct class ibmvscsis_class = {
-	.name           = "ibmvscsis",
-	.dev_release    = ibmvscsis_dev_release,
-	.class_attrs    = ibmvscsis_class_attrs,
-	.dev_groups     = ibmvscsis_dev_groups,
+	.name		= "ibmvscsis",
+	.dev_release	= ibmvscsis_dev_release,
+	.class_attrs	= ibmvscsis_class_attrs,
+	.dev_groups	= ibmvscsis_dev_groups,
 };
 
 static struct vio_device_id ibmvscsis_device_table[] = {
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h
index 981a0c992b6c..65c6189885ab 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h
@@ -26,6 +26,7 @@
 #ifndef __H_IBMVSCSI_TGT
 #define __H_IBMVSCSI_TGT
 
+#include <linux/interrupt.h>
 #include "libsrp.h"
 
 #define SYS_ID_NAME_LEN		64
@@ -204,8 +205,6 @@ struct scsi_info {
 	struct list_head waiting_rsp;
 #define NO_QUEUE                    0x00
 #define WAIT_ENABLED                0X01
-	/* driver has received an initialize command */
-#define PART_UP_WAIT_ENAB           0x02
 #define WAIT_CONNECTION             0x04
 	/* have established a connection */
 #define CONNECTED                   0x08
@@ -259,6 +258,8 @@ struct scsi_info {
 #define SCHEDULE_DISCONNECT           0x00400
 	/* disconnect handler is scheduled */
 #define DISCONNECT_SCHEDULED          0x00800
+	/* remove function is sleeping */
+#define CFG_SLEEPING                  0x01000
 	u32 flags;
 	/* adapter lock */
 	spinlock_t intr_lock;
@@ -287,6 +288,7 @@ struct scsi_info {
 
 	struct workqueue_struct *work_q;
 	struct completion wait_idle;
+	struct completion unconfig;
 	struct device dev;
 	struct vio_dev *dma_dev;
 	struct srp_target target;
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 532474109624..835c59c777f2 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -186,16 +186,16 @@ static const struct ipr_chip_cfg_t ipr_chip_cfg[] = {
 };
 
 static const struct ipr_chip_t ipr_chip[] = {
-	{ PCI_VENDOR_ID_MYLEX, PCI_DEVICE_ID_IBM_GEMSTONE, IPR_USE_LSI, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[0] },
-	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CITRINE, IPR_USE_LSI, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[0] },
-	{ PCI_VENDOR_ID_ADAPTEC2, PCI_DEVICE_ID_ADAPTEC2_OBSIDIAN, IPR_USE_LSI, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[0] },
-	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_OBSIDIAN, IPR_USE_LSI, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[0] },
-	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_OBSIDIAN_E, IPR_USE_MSI, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[0] },
-	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_SNIPE, IPR_USE_LSI, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[1] },
-	{ PCI_VENDOR_ID_ADAPTEC2, PCI_DEVICE_ID_ADAPTEC2_SCAMP, IPR_USE_LSI, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[1] },
-	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CROC_FPGA_E2, IPR_USE_MSI, IPR_SIS64, IPR_MMIO, &ipr_chip_cfg[2] },
-	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CROCODILE, IPR_USE_MSI, IPR_SIS64, IPR_MMIO, &ipr_chip_cfg[2] },
-	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_RATTLESNAKE, IPR_USE_MSI, IPR_SIS64, IPR_MMIO, &ipr_chip_cfg[2] }
+	{ PCI_VENDOR_ID_MYLEX, PCI_DEVICE_ID_IBM_GEMSTONE, false, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[0] },
+	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CITRINE, false, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[0] },
+	{ PCI_VENDOR_ID_ADAPTEC2, PCI_DEVICE_ID_ADAPTEC2_OBSIDIAN, false, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[0] },
+	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_OBSIDIAN, false, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[0] },
+	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_OBSIDIAN_E, true, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[0] },
+	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_SNIPE, false, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[1] },
+	{ PCI_VENDOR_ID_ADAPTEC2, PCI_DEVICE_ID_ADAPTEC2_SCAMP, false, IPR_SIS32, IPR_PCI_CFG, &ipr_chip_cfg[1] },
+	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CROC_FPGA_E2, true, IPR_SIS64, IPR_MMIO, &ipr_chip_cfg[2] },
+	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CROCODILE, true, IPR_SIS64, IPR_MMIO, &ipr_chip_cfg[2] },
+	{ PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_RATTLESNAKE, true, IPR_SIS64, IPR_MMIO, &ipr_chip_cfg[2] }
 };
 
 static int ipr_max_bus_speeds[] = {
@@ -9439,23 +9439,11 @@ static void ipr_free_mem(struct ipr_ioa_cfg *ioa_cfg)
 static void ipr_free_irqs(struct ipr_ioa_cfg *ioa_cfg)
 {
 	struct pci_dev *pdev = ioa_cfg->pdev;
+	int i;
 
-	if (ioa_cfg->intr_flag == IPR_USE_MSI ||
-	    ioa_cfg->intr_flag == IPR_USE_MSIX) {
-		int i;
-		for (i = 0; i < ioa_cfg->nvectors; i++)
-			free_irq(ioa_cfg->vectors_info[i].vec,
-				 &ioa_cfg->hrrq[i]);
-	} else
-		free_irq(pdev->irq, &ioa_cfg->hrrq[0]);
-
-	if (ioa_cfg->intr_flag == IPR_USE_MSI) {
-		pci_disable_msi(pdev);
-		ioa_cfg->intr_flag &= ~IPR_USE_MSI;
-	} else if (ioa_cfg->intr_flag == IPR_USE_MSIX) {
-		pci_disable_msix(pdev);
-		ioa_cfg->intr_flag &= ~IPR_USE_MSIX;
-	}
+	for (i = 0; i < ioa_cfg->nvectors; i++)
+		free_irq(pci_irq_vector(pdev, i), &ioa_cfg->hrrq[i]);
+	pci_free_irq_vectors(pdev);
 }
 
 /**
@@ -9883,45 +9871,6 @@ static void ipr_wait_for_pci_err_recovery(struct ipr_ioa_cfg *ioa_cfg)
 	}
 }
 
-static int ipr_enable_msix(struct ipr_ioa_cfg *ioa_cfg)
-{
-	struct msix_entry entries[IPR_MAX_MSIX_VECTORS];
-	int i, vectors;
-
-	for (i = 0; i < ARRAY_SIZE(entries); ++i)
-		entries[i].entry = i;
-
-	vectors = pci_enable_msix_range(ioa_cfg->pdev,
-					entries, 1, ipr_number_of_msix);
-	if (vectors < 0) {
-		ipr_wait_for_pci_err_recovery(ioa_cfg);
-		return vectors;
-	}
-
-	for (i = 0; i < vectors; i++)
-		ioa_cfg->vectors_info[i].vec = entries[i].vector;
-	ioa_cfg->nvectors = vectors;
-
-	return 0;
-}
-
-static int ipr_enable_msi(struct ipr_ioa_cfg *ioa_cfg)
-{
-	int i, vectors;
-
-	vectors = pci_enable_msi_range(ioa_cfg->pdev, 1, ipr_number_of_msix);
-	if (vectors < 0) {
-		ipr_wait_for_pci_err_recovery(ioa_cfg);
-		return vectors;
-	}
-
-	for (i = 0; i < vectors; i++)
-		ioa_cfg->vectors_info[i].vec = ioa_cfg->pdev->irq + i;
-	ioa_cfg->nvectors = vectors;
-
-	return 0;
-}
-
 static void name_msi_vectors(struct ipr_ioa_cfg *ioa_cfg)
 {
 	int vec_idx, n = sizeof(ioa_cfg->vectors_info[0].desc) - 1;
@@ -9934,19 +9883,20 @@ static void name_msi_vectors(struct ipr_ioa_cfg *ioa_cfg)
 	}
 }
 
-static int ipr_request_other_msi_irqs(struct ipr_ioa_cfg *ioa_cfg)
+static int ipr_request_other_msi_irqs(struct ipr_ioa_cfg *ioa_cfg,
+		struct pci_dev *pdev)
 {
 	int i, rc;
 
 	for (i = 1; i < ioa_cfg->nvectors; i++) {
-		rc = request_irq(ioa_cfg->vectors_info[i].vec,
+		rc = request_irq(pci_irq_vector(pdev, i),
 			ipr_isr_mhrrq,
 			0,
 			ioa_cfg->vectors_info[i].desc,
 			&ioa_cfg->hrrq[i]);
 		if (rc) {
 			while (--i >= 0)
-				free_irq(ioa_cfg->vectors_info[i].vec,
+				free_irq(pci_irq_vector(pdev, i),
 					&ioa_cfg->hrrq[i]);
 			return rc;
 		}
@@ -9984,8 +9934,7 @@ static irqreturn_t ipr_test_intr(int irq, void *devp)
  * ipr_test_msi - Test for Message Signaled Interrupt (MSI) support.
  * @pdev:		PCI device struct
  *
- * Description: The return value from pci_enable_msi_range() can not always be
- * trusted.  This routine sets up and initiates a test interrupt to determine
+ * Description: This routine sets up and initiates a test interrupt to determine
  * if the interrupt is received via the ipr_test_intr() service routine.
  * If the tests fails, the driver will fall back to LSI.
  *
@@ -9997,6 +9946,7 @@ static int ipr_test_msi(struct ipr_ioa_cfg *ioa_cfg, struct pci_dev *pdev)
 	int rc;
 	volatile u32 int_reg;
 	unsigned long lock_flags = 0;
+	int irq = pci_irq_vector(pdev, 0);
 
 	ENTER;
 
@@ -10008,15 +9958,12 @@ static int ipr_test_msi(struct ipr_ioa_cfg *ioa_cfg, struct pci_dev *pdev)
 	int_reg = readl(ioa_cfg->regs.sense_interrupt_mask_reg);
 	spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
 
-	if (ioa_cfg->intr_flag == IPR_USE_MSIX)
-		rc = request_irq(ioa_cfg->vectors_info[0].vec, ipr_test_intr, 0, IPR_NAME, ioa_cfg);
-	else
-		rc = request_irq(pdev->irq, ipr_test_intr, 0, IPR_NAME, ioa_cfg);
+	rc = request_irq(irq, ipr_test_intr, 0, IPR_NAME, ioa_cfg);
 	if (rc) {
-		dev_err(&pdev->dev, "Can not assign irq %d\n", pdev->irq);
+		dev_err(&pdev->dev, "Can not assign irq %d\n", irq);
 		return rc;
 	} else if (ipr_debug)
-		dev_info(&pdev->dev, "IRQ assigned: %d\n", pdev->irq);
+		dev_info(&pdev->dev, "IRQ assigned: %d\n", irq);
 
 	writel(IPR_PCII_IO_DEBUG_ACKNOWLEDGE, ioa_cfg->regs.sense_interrupt_reg32);
 	int_reg = readl(ioa_cfg->regs.sense_interrupt_reg);
@@ -10033,10 +9980,7 @@ static int ipr_test_msi(struct ipr_ioa_cfg *ioa_cfg, struct pci_dev *pdev)
 
 	spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
 
-	if (ioa_cfg->intr_flag == IPR_USE_MSIX)
-		free_irq(ioa_cfg->vectors_info[0].vec, ioa_cfg);
-	else
-		free_irq(pdev->irq, ioa_cfg);
+	free_irq(irq, ioa_cfg);
 
 	LEAVE;
 
@@ -10060,6 +10004,7 @@ static int ipr_probe_ioa(struct pci_dev *pdev,
 	int rc = PCIBIOS_SUCCESSFUL;
 	volatile u32 mask, uproc, interrupts;
 	unsigned long lock_flags, driver_lock_flags;
+	unsigned int irq_flag;
 
 	ENTER;
 
@@ -10175,18 +10120,18 @@ static int ipr_probe_ioa(struct pci_dev *pdev,
 		ipr_number_of_msix = IPR_MAX_MSIX_VECTORS;
 	}
 
-	if (ioa_cfg->ipr_chip->intr_type == IPR_USE_MSI &&
-			ipr_enable_msix(ioa_cfg) == 0)
-		ioa_cfg->intr_flag = IPR_USE_MSIX;
-	else if (ioa_cfg->ipr_chip->intr_type == IPR_USE_MSI &&
-			ipr_enable_msi(ioa_cfg) == 0)
-		ioa_cfg->intr_flag = IPR_USE_MSI;
-	else {
-		ioa_cfg->intr_flag = IPR_USE_LSI;
-		ioa_cfg->clear_isr = 1;
-		ioa_cfg->nvectors = 1;
-		dev_info(&pdev->dev, "Cannot enable MSI.\n");
+	irq_flag = PCI_IRQ_LEGACY;
+	if (ioa_cfg->ipr_chip->has_msi)
+		irq_flag |= PCI_IRQ_MSI | PCI_IRQ_MSIX;
+	rc = pci_alloc_irq_vectors(pdev, 1, ipr_number_of_msix, irq_flag);
+	if (rc < 0) {
+		ipr_wait_for_pci_err_recovery(ioa_cfg);
+		goto cleanup_nomem;
 	}
+	ioa_cfg->nvectors = rc;
+
+	if (!pdev->msi_enabled && !pdev->msix_enabled)
+		ioa_cfg->clear_isr = 1;
 
 	pci_set_master(pdev);
 
@@ -10199,33 +10144,23 @@ static int ipr_probe_ioa(struct pci_dev *pdev,
 		}
 	}
 
-	if (ioa_cfg->intr_flag == IPR_USE_MSI ||
-	    ioa_cfg->intr_flag == IPR_USE_MSIX) {
+	if (pdev->msi_enabled || pdev->msix_enabled) {
 		rc = ipr_test_msi(ioa_cfg, pdev);
-		if (rc == -EOPNOTSUPP) {
+		switch (rc) {
+		case 0:
+			dev_info(&pdev->dev,
+				"Request for %d MSI%ss succeeded.", ioa_cfg->nvectors,
+				pdev->msix_enabled ? "-X" : "");
+			break;
+		case -EOPNOTSUPP:
 			ipr_wait_for_pci_err_recovery(ioa_cfg);
-			if (ioa_cfg->intr_flag == IPR_USE_MSI) {
-				ioa_cfg->intr_flag &= ~IPR_USE_MSI;
-				pci_disable_msi(pdev);
-			 } else if (ioa_cfg->intr_flag == IPR_USE_MSIX) {
-				ioa_cfg->intr_flag &= ~IPR_USE_MSIX;
-				pci_disable_msix(pdev);
-			}
+			pci_free_irq_vectors(pdev);
 
-			ioa_cfg->intr_flag = IPR_USE_LSI;
 			ioa_cfg->nvectors = 1;
-		}
-		else if (rc)
+			ioa_cfg->clear_isr = 1;
+			break;
+		default:
 			goto out_msi_disable;
-		else {
-			if (ioa_cfg->intr_flag == IPR_USE_MSI)
-				dev_info(&pdev->dev,
-					"Request for %d MSIs succeeded with starting IRQ: %d\n",
-					ioa_cfg->nvectors, pdev->irq);
-			else if (ioa_cfg->intr_flag == IPR_USE_MSIX)
-				dev_info(&pdev->dev,
-					"Request for %d MSIXs succeeded.",
-					ioa_cfg->nvectors);
 		}
 	}
 
@@ -10273,15 +10208,13 @@ static int ipr_probe_ioa(struct pci_dev *pdev,
 	ipr_mask_and_clear_interrupts(ioa_cfg, ~IPR_PCII_IOA_TRANS_TO_OPER);
 	spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
 
-	if (ioa_cfg->intr_flag == IPR_USE_MSI
-			|| ioa_cfg->intr_flag == IPR_USE_MSIX) {
+	if (pdev->msi_enabled || pdev->msix_enabled) {
 		name_msi_vectors(ioa_cfg);
-		rc = request_irq(ioa_cfg->vectors_info[0].vec, ipr_isr,
-			0,
+		rc = request_irq(pci_irq_vector(pdev, 0), ipr_isr, 0,
 			ioa_cfg->vectors_info[0].desc,
 			&ioa_cfg->hrrq[0]);
 		if (!rc)
-			rc = ipr_request_other_msi_irqs(ioa_cfg);
+			rc = ipr_request_other_msi_irqs(ioa_cfg, pdev);
 	} else {
 		rc = request_irq(pdev->irq, ipr_isr,
 			 IRQF_SHARED,
@@ -10323,10 +10256,7 @@ cleanup_nolog:
 	ipr_free_mem(ioa_cfg);
 out_msi_disable:
 	ipr_wait_for_pci_err_recovery(ioa_cfg);
-	if (ioa_cfg->intr_flag == IPR_USE_MSI)
-		pci_disable_msi(pdev);
-	else if (ioa_cfg->intr_flag == IPR_USE_MSIX)
-		pci_disable_msix(pdev);
+	pci_free_irq_vectors(pdev);
 cleanup_nomem:
 	iounmap(ipr_regs);
 out_disable:
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index 8995053d01b3..b7d2e98eb45b 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -1413,10 +1413,7 @@ struct ipr_chip_cfg_t {
 struct ipr_chip_t {
 	u16 vendor;
 	u16 device;
-	u16 intr_type;
-#define IPR_USE_LSI			0x00
-#define IPR_USE_MSI			0x01
-#define IPR_USE_MSIX			0x02
+	bool has_msi;
 	u16 sis_type;
 #define IPR_SIS32			0x00
 #define IPR_SIS64			0x01
@@ -1593,11 +1590,9 @@ struct ipr_ioa_cfg {
 	struct ipr_cmnd **ipr_cmnd_list;
 	dma_addr_t *ipr_cmnd_list_dma;
 
-	u16 intr_flag;
 	unsigned int nvectors;
 
 	struct {
-		unsigned short vec;
 		char desc[22];
 	} vectors_info[IPR_MAX_MSIX_VECTORS];
 
diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c
index 02cb76fd4420..3419e1bcdff6 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -2241,9 +2241,6 @@ ips_get_bios_version(ips_ha_t * ha, int intr)
 	uint8_t minor;
 	uint8_t subminor;
 	uint8_t *buffer;
-	char hexDigits[] =
-	    { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C',
-     'D', 'E', 'F' };
 
 	METHOD_TRACE("ips_get_bios_version", 1);
 
@@ -2374,13 +2371,13 @@ ips_get_bios_version(ips_ha_t * ha, int intr)
 		}
 	}
 
-	ha->bios_version[0] = hexDigits[(major & 0xF0) >> 4];
+	ha->bios_version[0] = hex_asc_upper_hi(major);
 	ha->bios_version[1] = '.';
-	ha->bios_version[2] = hexDigits[major & 0x0F];
-	ha->bios_version[3] = hexDigits[subminor];
+	ha->bios_version[2] = hex_asc_upper_lo(major);
+	ha->bios_version[3] = hex_asc_upper_lo(subminor);
 	ha->bios_version[4] = '.';
-	ha->bios_version[5] = hexDigits[(minor & 0xF0) >> 4];
-	ha->bios_version[6] = hexDigits[minor & 0x0F];
+	ha->bios_version[5] = hex_asc_upper_hi(minor);
+	ha->bios_version[6] = hex_asc_upper_lo(minor);
 	ha->bios_version[7] = 0;
 }
 
diff --git a/drivers/scsi/ips.h b/drivers/scsi/ips.h
index 45b9566b928e..b782bb60baf0 100644
--- a/drivers/scsi/ips.h
+++ b/drivers/scsi/ips.h
@@ -51,7 +51,7 @@
    #define _IPS_H_
 
 #include <linux/nmi.h>
-   #include <asm/uaccess.h>
+#include <linux/uaccess.h>
    #include <asm/io.h>
 
    /*
diff --git a/drivers/scsi/isci/host.h b/drivers/scsi/isci/host.h
index 22a9bb1abae1..b3539928073c 100644
--- a/drivers/scsi/isci/host.h
+++ b/drivers/scsi/isci/host.h
@@ -295,7 +295,6 @@ enum sci_controller_states {
 #define SCI_MAX_MSIX_INT (SCI_NUM_MSI_X_INT*SCI_MAX_CONTROLLERS)
 
 struct isci_pci_info {
-	struct msix_entry msix_entries[SCI_MAX_MSIX_INT];
 	struct isci_host *hosts[SCI_MAX_CONTROLLERS];
 	struct isci_orom *orom;
 };
diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c
index 77128d680e3b..0b5b5db0d0f8 100644
--- a/drivers/scsi/isci/init.c
+++ b/drivers/scsi/isci/init.c
@@ -350,16 +350,12 @@ static int isci_setup_interrupts(struct pci_dev *pdev)
 	 */
 	num_msix = num_controllers(pdev) * SCI_NUM_MSI_X_INT;
 
-	for (i = 0; i < num_msix; i++)
-		pci_info->msix_entries[i].entry = i;
-
-	err = pci_enable_msix_exact(pdev, pci_info->msix_entries, num_msix);
-	if (err)
+	err = pci_alloc_irq_vectors(pdev, num_msix, num_msix, PCI_IRQ_MSIX);
+	if (err < 0)
 		goto intx;
 
 	for (i = 0; i < num_msix; i++) {
 		int id = i / SCI_NUM_MSI_X_INT;
-		struct msix_entry *msix = &pci_info->msix_entries[i];
 		irq_handler_t isr;
 
 		ihost = pci_info->hosts[id];
@@ -369,8 +365,8 @@ static int isci_setup_interrupts(struct pci_dev *pdev)
 		else
 			isr = isci_msix_isr;
 
-		err = devm_request_irq(&pdev->dev, msix->vector, isr, 0,
-				       DRV_NAME"-msix", ihost);
+		err = devm_request_irq(&pdev->dev, pci_irq_vector(pdev, i),
+				isr, 0, DRV_NAME"-msix", ihost);
 		if (!err)
 			continue;
 
@@ -378,18 +374,19 @@ static int isci_setup_interrupts(struct pci_dev *pdev)
 		while (i--) {
 			id = i / SCI_NUM_MSI_X_INT;
 			ihost = pci_info->hosts[id];
-			msix = &pci_info->msix_entries[i];
-			devm_free_irq(&pdev->dev, msix->vector, ihost);
+			devm_free_irq(&pdev->dev, pci_irq_vector(pdev, i),
+					ihost);
 		}
-		pci_disable_msix(pdev);
+		pci_free_irq_vectors(pdev);
 		goto intx;
 	}
 	return 0;
 
  intx:
 	for_each_isci_host(i, ihost, pdev) {
-		err = devm_request_irq(&pdev->dev, pdev->irq, isci_intx_isr,
-				       IRQF_SHARED, DRV_NAME"-intx", ihost);
+		err = devm_request_irq(&pdev->dev, pci_irq_vector(pdev, 0),
+				isci_intx_isr, IRQF_SHARED, DRV_NAME"-intx",
+				ihost);
 		if (err)
 			break;
 	}
diff --git a/drivers/scsi/isci/probe_roms.c b/drivers/scsi/isci/probe_roms.c
index 8ac646e5eddc..a2bbe46f8ccb 100644
--- a/drivers/scsi/isci/probe_roms.c
+++ b/drivers/scsi/isci/probe_roms.c
@@ -54,6 +54,7 @@ struct isci_orom *isci_request_oprom(struct pci_dev *pdev)
 	len = pci_biosrom_size(pdev);
 	rom = devm_kzalloc(&pdev->dev, sizeof(*rom), GFP_KERNEL);
 	if (!rom) {
+		pci_unmap_biosrom(oprom);
 		dev_warn(&pdev->dev,
 			 "Unable to allocate memory for orom\n");
 		return NULL;
diff --git a/drivers/scsi/isci/remote_node_context.c b/drivers/scsi/isci/remote_node_context.c
index 1910100638a2..e3f2a5359d71 100644
--- a/drivers/scsi/isci/remote_node_context.c
+++ b/drivers/scsi/isci/remote_node_context.c
@@ -66,6 +66,9 @@ const char *rnc_state_name(enum scis_sds_remote_node_context_states state)
 {
 	static const char * const strings[] = RNC_STATES;
 
+	if (state >= ARRAY_SIZE(strings))
+		return "UNKNOWN";
+
 	return strings[state];
 }
 #undef C
@@ -454,7 +457,7 @@ enum sci_status sci_remote_node_context_event_handler(struct sci_remote_node_con
 				 * the device since it's being invalidated anyway */
 				dev_warn(scirdev_to_dev(rnc_to_dev(sci_rnc)),
 					"%s: SCIC Remote Node Context 0x%p was "
-					"suspeneded by hardware while being "
+					"suspended by hardware while being "
 					"invalidated.\n", __func__, sci_rnc);
 				break;
 			default:
@@ -473,7 +476,7 @@ enum sci_status sci_remote_node_context_event_handler(struct sci_remote_node_con
 				 * the device since it's being resumed anyway */
 				dev_warn(scirdev_to_dev(rnc_to_dev(sci_rnc)),
 					"%s: SCIC Remote Node Context 0x%p was "
-					"suspeneded by hardware while being resumed.\n",
+					"suspended by hardware while being resumed.\n",
 					__func__, sci_rnc);
 				break;
 			default:
diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c
index b709d2b20880..47f66e949745 100644
--- a/drivers/scsi/isci/request.c
+++ b/drivers/scsi/isci/request.c
@@ -2473,7 +2473,7 @@ static void isci_request_process_response_iu(
 		"%s: resp_iu = %p "
 		"resp_iu->status = 0x%x,\nresp_iu->datapres = %d "
 		"resp_iu->response_data_len = %x, "
-		"resp_iu->sense_data_len = %x\nrepsonse data: ",
+		"resp_iu->sense_data_len = %x\nresponse data: ",
 		__func__,
 		resp_iu,
 		resp_iu->status,
diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c
index 880a9068ca12..6103231104da 100644
--- a/drivers/scsi/libfc/fc_disc.c
+++ b/drivers/scsi/libfc/fc_disc.c
@@ -68,10 +68,14 @@ static void fc_disc_stop_rports(struct fc_disc *disc)
 
 	lport = fc_disc_lport(disc);
 
-	mutex_lock(&disc->disc_mutex);
-	list_for_each_entry_rcu(rdata, &disc->rports, peers)
-		lport->tt.rport_logoff(rdata);
-	mutex_unlock(&disc->disc_mutex);
+	rcu_read_lock();
+	list_for_each_entry_rcu(rdata, &disc->rports, peers) {
+		if (kref_get_unless_zero(&rdata->kref)) {
+			fc_rport_logoff(rdata);
+			kref_put(&rdata->kref, fc_rport_destroy);
+		}
+	}
+	rcu_read_unlock();
 }
 
 /**
@@ -150,7 +154,7 @@ static void fc_disc_recv_rscn_req(struct fc_disc *disc, struct fc_frame *fp)
 			break;
 		}
 	}
-	lport->tt.seq_els_rsp_send(fp, ELS_LS_ACC, NULL);
+	fc_seq_els_rsp_send(fp, ELS_LS_ACC, NULL);
 
 	/*
 	 * If not doing a complete rediscovery, do GPN_ID on
@@ -178,7 +182,7 @@ reject:
 	FC_DISC_DBG(disc, "Received a bad RSCN frame\n");
 	rjt_data.reason = ELS_RJT_LOGIC;
 	rjt_data.explan = ELS_EXPL_NONE;
-	lport->tt.seq_els_rsp_send(fp, ELS_LS_RJT, &rjt_data);
+	fc_seq_els_rsp_send(fp, ELS_LS_RJT, &rjt_data);
 	fc_frame_free(fp);
 }
 
@@ -289,15 +293,19 @@ static void fc_disc_done(struct fc_disc *disc, enum fc_disc_event event)
 	 * Skip ports which were never discovered.  These are the dNS port
 	 * and ports which were created by PLOGI.
 	 */
+	rcu_read_lock();
 	list_for_each_entry_rcu(rdata, &disc->rports, peers) {
-		if (!rdata->disc_id)
+		if (!kref_get_unless_zero(&rdata->kref))
 			continue;
-		if (rdata->disc_id == disc->disc_id)
-			lport->tt.rport_login(rdata);
-		else
-			lport->tt.rport_logoff(rdata);
+		if (rdata->disc_id) {
+			if (rdata->disc_id == disc->disc_id)
+				fc_rport_login(rdata);
+			else
+				fc_rport_logoff(rdata);
+		}
+		kref_put(&rdata->kref, fc_rport_destroy);
 	}
-
+	rcu_read_unlock();
 	mutex_unlock(&disc->disc_mutex);
 	disc->disc_callback(lport, event);
 	mutex_lock(&disc->disc_mutex);
@@ -446,7 +454,7 @@ static int fc_disc_gpn_ft_parse(struct fc_disc *disc, void *buf, size_t len)
 
 		if (ids.port_id != lport->port_id &&
 		    ids.port_name != lport->wwpn) {
-			rdata = lport->tt.rport_create(lport, ids.port_id);
+			rdata = fc_rport_create(lport, ids.port_id);
 			if (rdata) {
 				rdata->ids.port_name = ids.port_name;
 				rdata->disc_id = disc->disc_id;
@@ -592,7 +600,6 @@ static void fc_disc_gpn_id_resp(struct fc_seq *sp, struct fc_frame *fp,
 	lport = rdata->local_port;
 	disc = &lport->disc;
 
-	mutex_lock(&disc->disc_mutex);
 	if (PTR_ERR(fp) == -FC_EX_CLOSED)
 		goto out;
 	if (IS_ERR(fp))
@@ -607,37 +614,41 @@ static void fc_disc_gpn_id_resp(struct fc_seq *sp, struct fc_frame *fp,
 			goto redisc;
 		pn = (struct fc_ns_gid_pn *)(cp + 1);
 		port_name = get_unaligned_be64(&pn->fn_wwpn);
+		mutex_lock(&rdata->rp_mutex);
 		if (rdata->ids.port_name == -1)
 			rdata->ids.port_name = port_name;
 		else if (rdata->ids.port_name != port_name) {
 			FC_DISC_DBG(disc, "GPN_ID accepted.  WWPN changed. "
 				    "Port-id %6.6x wwpn %16.16llx\n",
 				    rdata->ids.port_id, port_name);
-			lport->tt.rport_logoff(rdata);
-
-			new_rdata = lport->tt.rport_create(lport,
-							   rdata->ids.port_id);
+			mutex_unlock(&rdata->rp_mutex);
+			fc_rport_logoff(rdata);
+			mutex_lock(&lport->disc.disc_mutex);
+			new_rdata = fc_rport_create(lport, rdata->ids.port_id);
+			mutex_unlock(&lport->disc.disc_mutex);
 			if (new_rdata) {
 				new_rdata->disc_id = disc->disc_id;
-				lport->tt.rport_login(new_rdata);
+				fc_rport_login(new_rdata);
 			}
 			goto out;
 		}
 		rdata->disc_id = disc->disc_id;
-		lport->tt.rport_login(rdata);
+		mutex_unlock(&rdata->rp_mutex);
+		fc_rport_login(rdata);
 	} else if (ntohs(cp->ct_cmd) == FC_FS_RJT) {
 		FC_DISC_DBG(disc, "GPN_ID rejected reason %x exp %x\n",
 			    cp->ct_reason, cp->ct_explan);
-		lport->tt.rport_logoff(rdata);
+		fc_rport_logoff(rdata);
 	} else {
 		FC_DISC_DBG(disc, "GPN_ID unexpected response code %x\n",
 			    ntohs(cp->ct_cmd));
 redisc:
+		mutex_lock(&disc->disc_mutex);
 		fc_disc_restart(disc);
+		mutex_unlock(&disc->disc_mutex);
 	}
 out:
-	mutex_unlock(&disc->disc_mutex);
-	kref_put(&rdata->kref, lport->tt.rport_destroy);
+	kref_put(&rdata->kref, fc_rport_destroy);
 }
 
 /**
@@ -678,7 +689,7 @@ static int fc_disc_single(struct fc_lport *lport, struct fc_disc_port *dp)
 {
 	struct fc_rport_priv *rdata;
 
-	rdata = lport->tt.rport_create(lport, dp->port_id);
+	rdata = fc_rport_create(lport, dp->port_id);
 	if (!rdata)
 		return -ENOMEM;
 	rdata->disc_id = 0;
@@ -708,7 +719,7 @@ static void fc_disc_stop(struct fc_lport *lport)
 static void fc_disc_stop_final(struct fc_lport *lport)
 {
 	fc_disc_stop(lport);
-	lport->tt.rport_flush_queue();
+	fc_rport_flush_queue();
 }
 
 /**
diff --git a/drivers/scsi/libfc/fc_elsct.c b/drivers/scsi/libfc/fc_elsct.c
index c2384d501470..6384a98048af 100644
--- a/drivers/scsi/libfc/fc_elsct.c
+++ b/drivers/scsi/libfc/fc_elsct.c
@@ -67,7 +67,7 @@ struct fc_seq *fc_elsct_send(struct fc_lport *lport, u32 did,
 	fc_fill_fc_hdr(fp, r_ctl, did, lport->port_id, fh_type,
 		       FC_FCTL_REQ, 0);
 
-	return lport->tt.exch_seq_send(lport, fp, resp, NULL, arg, timer_msec);
+	return fc_exch_seq_send(lport, fp, resp, NULL, arg, timer_msec);
 }
 EXPORT_SYMBOL(fc_elsct_send);
 
diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 16ca31ad5ec0..42bcf7f3a0f9 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -94,6 +94,7 @@ struct fc_exch_pool {
 struct fc_exch_mgr {
 	struct fc_exch_pool __percpu *pool;
 	mempool_t	*ep_pool;
+	struct fc_lport	*lport;
 	enum fc_class	class;
 	struct kref	kref;
 	u16		min_xid;
@@ -362,8 +363,10 @@ static inline void fc_exch_timer_set_locked(struct fc_exch *ep,
 
 	fc_exch_hold(ep);		/* hold for timer */
 	if (!queue_delayed_work(fc_exch_workqueue, &ep->timeout_work,
-				msecs_to_jiffies(timer_msec)))
+				msecs_to_jiffies(timer_msec))) {
+		FC_EXCH_DBG(ep, "Exchange already queued\n");
 		fc_exch_release(ep);
+	}
 }
 
 /**
@@ -406,6 +409,8 @@ static int fc_exch_done_locked(struct fc_exch *ep)
 	return rc;
 }
 
+static struct fc_exch fc_quarantine_exch;
+
 /**
  * fc_exch_ptr_get() - Return an exchange from an exchange pool
  * @pool:  Exchange Pool to get an exchange from
@@ -450,14 +455,17 @@ static void fc_exch_delete(struct fc_exch *ep)
 
 	/* update cache of free slot */
 	index = (ep->xid - ep->em->min_xid) >> fc_cpu_order;
-	if (pool->left == FC_XID_UNKNOWN)
-		pool->left = index;
-	else if (pool->right == FC_XID_UNKNOWN)
-		pool->right = index;
-	else
-		pool->next_index = index;
-
-	fc_exch_ptr_set(pool, index, NULL);
+	if (!(ep->state & FC_EX_QUARANTINE)) {
+		if (pool->left == FC_XID_UNKNOWN)
+			pool->left = index;
+		else if (pool->right == FC_XID_UNKNOWN)
+			pool->right = index;
+		else
+			pool->next_index = index;
+		fc_exch_ptr_set(pool, index, NULL);
+	} else {
+		fc_exch_ptr_set(pool, index, &fc_quarantine_exch);
+	}
 	list_del(&ep->ex_list);
 	spin_unlock_bh(&pool->lock);
 	fc_exch_release(ep);	/* drop hold for exch in mp */
@@ -525,8 +533,7 @@ out:
  * Note: The frame will be freed either by a direct call to fc_frame_free(fp)
  * or indirectly by calling libfc_function_template.frame_send().
  */
-static int fc_seq_send(struct fc_lport *lport, struct fc_seq *sp,
-		       struct fc_frame *fp)
+int fc_seq_send(struct fc_lport *lport, struct fc_seq *sp, struct fc_frame *fp)
 {
 	struct fc_exch *ep;
 	int error;
@@ -536,6 +543,7 @@ static int fc_seq_send(struct fc_lport *lport, struct fc_seq *sp,
 	spin_unlock_bh(&ep->ex_lock);
 	return error;
 }
+EXPORT_SYMBOL(fc_seq_send);
 
 /**
  * fc_seq_alloc() - Allocate a sequence for a given exchange
@@ -577,7 +585,7 @@ static struct fc_seq *fc_seq_start_next_locked(struct fc_seq *sp)
  *			 for a given sequence/exchange pair
  * @sp: The sequence/exchange to get a new exchange for
  */
-static struct fc_seq *fc_seq_start_next(struct fc_seq *sp)
+struct fc_seq *fc_seq_start_next(struct fc_seq *sp)
 {
 	struct fc_exch *ep = fc_seq_exch(sp);
 
@@ -587,16 +595,16 @@ static struct fc_seq *fc_seq_start_next(struct fc_seq *sp)
 
 	return sp;
 }
+EXPORT_SYMBOL(fc_seq_start_next);
 
 /*
  * Set the response handler for the exchange associated with a sequence.
  *
  * Note: May sleep if invoked from outside a response handler.
  */
-static void fc_seq_set_resp(struct fc_seq *sp,
-			    void (*resp)(struct fc_seq *, struct fc_frame *,
-					 void *),
-			    void *arg)
+void fc_seq_set_resp(struct fc_seq *sp,
+		     void (*resp)(struct fc_seq *, struct fc_frame *, void *),
+		     void *arg)
 {
 	struct fc_exch *ep = fc_seq_exch(sp);
 	DEFINE_WAIT(wait);
@@ -615,12 +623,20 @@ static void fc_seq_set_resp(struct fc_seq *sp,
 	ep->arg = arg;
 	spin_unlock_bh(&ep->ex_lock);
 }
+EXPORT_SYMBOL(fc_seq_set_resp);
 
 /**
  * fc_exch_abort_locked() - Abort an exchange
  * @ep:	The exchange to be aborted
  * @timer_msec: The period of time to wait before aborting
  *
+ * Abort an exchange and sequence. Generally called because of a
+ * exchange timeout or an abort from the upper layer.
+ *
+ * A timer_msec can be specified for abort timeout, if non-zero
+ * timer_msec value is specified then exchange resp handler
+ * will be called with timeout error if no response to abort.
+ *
  * Locking notes:  Called with exch lock held
  *
  * Return value: 0 on success else error code
@@ -632,9 +648,13 @@ static int fc_exch_abort_locked(struct fc_exch *ep,
 	struct fc_frame *fp;
 	int error;
 
+	FC_EXCH_DBG(ep, "exch: abort, time %d msecs\n", timer_msec);
 	if (ep->esb_stat & (ESB_ST_COMPLETE | ESB_ST_ABNORMAL) ||
-	    ep->state & (FC_EX_DONE | FC_EX_RST_CLEANUP))
+	    ep->state & (FC_EX_DONE | FC_EX_RST_CLEANUP)) {
+		FC_EXCH_DBG(ep, "exch: already completed esb %x state %x\n",
+			    ep->esb_stat, ep->state);
 		return -ENXIO;
+	}
 
 	/*
 	 * Send the abort on a new sequence if possible.
@@ -680,8 +700,7 @@ static int fc_exch_abort_locked(struct fc_exch *ep,
  *
  * Return value: 0 on success else error code
  */
-static int fc_seq_exch_abort(const struct fc_seq *req_sp,
-			     unsigned int timer_msec)
+int fc_seq_exch_abort(const struct fc_seq *req_sp, unsigned int timer_msec)
 {
 	struct fc_exch *ep;
 	int error;
@@ -758,7 +777,7 @@ static void fc_exch_timeout(struct work_struct *work)
 	u32 e_stat;
 	int rc = 1;
 
-	FC_EXCH_DBG(ep, "Exchange timed out\n");
+	FC_EXCH_DBG(ep, "Exchange timed out state %x\n", ep->state);
 
 	spin_lock_bh(&ep->ex_lock);
 	if (ep->state & (FC_EX_RST_CLEANUP | FC_EX_DONE))
@@ -821,14 +840,18 @@ static struct fc_exch *fc_exch_em_alloc(struct fc_lport *lport,
 
 	/* peek cache of free slot */
 	if (pool->left != FC_XID_UNKNOWN) {
-		index = pool->left;
-		pool->left = FC_XID_UNKNOWN;
-		goto hit;
+		if (!WARN_ON(fc_exch_ptr_get(pool, pool->left))) {
+			index = pool->left;
+			pool->left = FC_XID_UNKNOWN;
+			goto hit;
+		}
 	}
 	if (pool->right != FC_XID_UNKNOWN) {
-		index = pool->right;
-		pool->right = FC_XID_UNKNOWN;
-		goto hit;
+		if (!WARN_ON(fc_exch_ptr_get(pool, pool->right))) {
+			index = pool->right;
+			pool->right = FC_XID_UNKNOWN;
+			goto hit;
+		}
 	}
 
 	index = pool->next_index;
@@ -888,14 +911,19 @@ err:
  * EM is selected when a NULL match function pointer is encountered
  * or when a call to a match function returns true.
  */
-static inline struct fc_exch *fc_exch_alloc(struct fc_lport *lport,
-					    struct fc_frame *fp)
+static struct fc_exch *fc_exch_alloc(struct fc_lport *lport,
+				     struct fc_frame *fp)
 {
 	struct fc_exch_mgr_anchor *ema;
+	struct fc_exch *ep;
 
-	list_for_each_entry(ema, &lport->ema_list, ema_list)
-		if (!ema->match || ema->match(fp))
-			return fc_exch_em_alloc(lport, ema->mp);
+	list_for_each_entry(ema, &lport->ema_list, ema_list) {
+		if (!ema->match || ema->match(fp)) {
+			ep = fc_exch_em_alloc(lport, ema->mp);
+			if (ep)
+				return ep;
+		}
+	}
 	return NULL;
 }
 
@@ -906,14 +934,17 @@ static inline struct fc_exch *fc_exch_alloc(struct fc_lport *lport,
  */
 static struct fc_exch *fc_exch_find(struct fc_exch_mgr *mp, u16 xid)
 {
+	struct fc_lport *lport = mp->lport;
 	struct fc_exch_pool *pool;
 	struct fc_exch *ep = NULL;
 	u16 cpu = xid & fc_cpu_mask;
 
+	if (xid == FC_XID_UNKNOWN)
+		return NULL;
+
 	if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) {
-		printk_ratelimited(KERN_ERR
-			"libfc: lookup request for XID = %d, "
-			"indicates invalid CPU %d\n", xid, cpu);
+		pr_err("host%u: lport %6.6x: xid %d invalid CPU %d\n:",
+		       lport->host->host_no, lport->port_id, xid, cpu);
 		return NULL;
 	}
 
@@ -921,6 +952,10 @@ static struct fc_exch *fc_exch_find(struct fc_exch_mgr *mp, u16 xid)
 		pool = per_cpu_ptr(mp->pool, cpu);
 		spin_lock_bh(&pool->lock);
 		ep = fc_exch_ptr_get(pool, (xid - mp->min_xid) >> fc_cpu_order);
+		if (ep == &fc_quarantine_exch) {
+			FC_LPORT_DBG(lport, "xid %x quarantined\n", xid);
+			ep = NULL;
+		}
 		if (ep) {
 			WARN_ON(ep->xid != xid);
 			fc_exch_hold(ep);
@@ -938,7 +973,7 @@ static struct fc_exch *fc_exch_find(struct fc_exch_mgr *mp, u16 xid)
  *
  * Note: May sleep if invoked from outside a response handler.
  */
-static void fc_exch_done(struct fc_seq *sp)
+void fc_exch_done(struct fc_seq *sp)
 {
 	struct fc_exch *ep = fc_seq_exch(sp);
 	int rc;
@@ -951,6 +986,7 @@ static void fc_exch_done(struct fc_seq *sp)
 	if (!rc)
 		fc_exch_delete(ep);
 }
+EXPORT_SYMBOL(fc_exch_done);
 
 /**
  * fc_exch_resp() - Allocate a new exchange for a response frame
@@ -1197,8 +1233,8 @@ static void fc_exch_set_addr(struct fc_exch *ep,
  *
  * The received frame is not freed.
  */
-static void fc_seq_els_rsp_send(struct fc_frame *fp, enum fc_els_cmd els_cmd,
-				struct fc_seq_els_data *els_data)
+void fc_seq_els_rsp_send(struct fc_frame *fp, enum fc_els_cmd els_cmd,
+			 struct fc_seq_els_data *els_data)
 {
 	switch (els_cmd) {
 	case ELS_LS_RJT:
@@ -1217,6 +1253,7 @@ static void fc_seq_els_rsp_send(struct fc_frame *fp, enum fc_els_cmd els_cmd,
 		FC_LPORT_DBG(fr_dev(fp), "Invalid ELS CMD:%x\n", els_cmd);
 	}
 }
+EXPORT_SYMBOL_GPL(fc_seq_els_rsp_send);
 
 /**
  * fc_seq_send_last() - Send a sequence that is the last in the exchange
@@ -1258,8 +1295,10 @@ static void fc_seq_send_ack(struct fc_seq *sp, const struct fc_frame *rx_fp)
 	 */
 	if (fc_sof_needs_ack(fr_sof(rx_fp))) {
 		fp = fc_frame_alloc(lport, 0);
-		if (!fp)
+		if (!fp) {
+			FC_EXCH_DBG(ep, "Drop ACK request, out of memory\n");
 			return;
+		}
 
 		fh = fc_frame_header_get(fp);
 		fh->fh_r_ctl = FC_RCTL_ACK_1;
@@ -1312,13 +1351,18 @@ static void fc_exch_send_ba_rjt(struct fc_frame *rx_fp,
 	struct fc_frame_header *rx_fh;
 	struct fc_frame_header *fh;
 	struct fc_ba_rjt *rp;
+	struct fc_seq *sp;
 	struct fc_lport *lport;
 	unsigned int f_ctl;
 
 	lport = fr_dev(rx_fp);
+	sp = fr_seq(rx_fp);
 	fp = fc_frame_alloc(lport, sizeof(*rp));
-	if (!fp)
+	if (!fp) {
+		FC_EXCH_DBG(fc_seq_exch(sp),
+			     "Drop BA_RJT request, out of memory\n");
 		return;
+	}
 	fh = fc_frame_header_get(fp);
 	rx_fh = fc_frame_header_get(rx_fp);
 
@@ -1383,14 +1427,17 @@ static void fc_exch_recv_abts(struct fc_exch *ep, struct fc_frame *rx_fp)
 	if (!ep)
 		goto reject;
 
+	FC_EXCH_DBG(ep, "exch: ABTS received\n");
 	fp = fc_frame_alloc(ep->lp, sizeof(*ap));
-	if (!fp)
+	if (!fp) {
+		FC_EXCH_DBG(ep, "Drop ABTS request, out of memory\n");
 		goto free;
+	}
 
 	spin_lock_bh(&ep->ex_lock);
 	if (ep->esb_stat & ESB_ST_COMPLETE) {
 		spin_unlock_bh(&ep->ex_lock);
-
+		FC_EXCH_DBG(ep, "exch: ABTS rejected, exchange complete\n");
 		fc_frame_free(fp);
 		goto reject;
 	}
@@ -1433,7 +1480,7 @@ reject:
  * A reference will be held on the exchange/sequence for the caller, which
  * must call fc_seq_release().
  */
-static struct fc_seq *fc_seq_assign(struct fc_lport *lport, struct fc_frame *fp)
+struct fc_seq *fc_seq_assign(struct fc_lport *lport, struct fc_frame *fp)
 {
 	struct fc_exch_mgr_anchor *ema;
 
@@ -1447,15 +1494,17 @@ static struct fc_seq *fc_seq_assign(struct fc_lport *lport, struct fc_frame *fp)
 			break;
 	return fr_seq(fp);
 }
+EXPORT_SYMBOL(fc_seq_assign);
 
 /**
  * fc_seq_release() - Release the hold
  * @sp:    The sequence.
  */
-static void fc_seq_release(struct fc_seq *sp)
+void fc_seq_release(struct fc_seq *sp)
 {
 	fc_exch_release(fc_seq_exch(sp));
 }
+EXPORT_SYMBOL(fc_seq_release);
 
 /**
  * fc_exch_recv_req() - Handler for an incoming request
@@ -1491,7 +1540,7 @@ static void fc_exch_recv_req(struct fc_lport *lport, struct fc_exch_mgr *mp,
 	 * The upper-level protocol may request one later, if needed.
 	 */
 	if (fh->fh_rx_id == htons(FC_XID_UNKNOWN))
-		return lport->tt.lport_recv(lport, fp);
+		return fc_lport_recv(lport, fp);
 
 	reject = fc_seq_lookup_recip(lport, mp, fp);
 	if (reject == FC_RJT_NONE) {
@@ -1512,7 +1561,7 @@ static void fc_exch_recv_req(struct fc_lport *lport, struct fc_exch_mgr *mp,
 		 * first.
 		 */
 		if (!fc_invoke_resp(ep, sp, fp))
-			lport->tt.lport_recv(lport, fp);
+			fc_lport_recv(lport, fp);
 		fc_exch_release(ep);	/* release from lookup */
 	} else {
 		FC_LPORT_DBG(lport, "exch/seq lookup failed: reject %x\n",
@@ -1562,9 +1611,6 @@ static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp)
 	if (fc_sof_is_init(sof)) {
 		sp->ssb_stat |= SSB_ST_RESP;
 		sp->id = fh->fh_seq_id;
-	} else if (sp->id != fh->fh_seq_id) {
-		atomic_inc(&mp->stats.seq_not_found);
-		goto rel;
 	}
 
 	f_ctl = ntoh24(fh->fh_f_ctl);
@@ -1761,7 +1807,10 @@ static void fc_exch_recv_bls(struct fc_exch_mgr *mp, struct fc_frame *fp)
 				fc_frame_free(fp);
 			break;
 		case FC_RCTL_BA_ABTS:
-			fc_exch_recv_abts(ep, fp);
+			if (ep)
+				fc_exch_recv_abts(ep, fp);
+			else
+				fc_frame_free(fp);
 			break;
 		default:			/* ignore junk */
 			fc_frame_free(fp);
@@ -1784,11 +1833,16 @@ static void fc_seq_ls_acc(struct fc_frame *rx_fp)
 	struct fc_lport *lport;
 	struct fc_els_ls_acc *acc;
 	struct fc_frame *fp;
+	struct fc_seq *sp;
 
 	lport = fr_dev(rx_fp);
+	sp = fr_seq(rx_fp);
 	fp = fc_frame_alloc(lport, sizeof(*acc));
-	if (!fp)
+	if (!fp) {
+		FC_EXCH_DBG(fc_seq_exch(sp),
+			    "exch: drop LS_ACC, out of memory\n");
 		return;
+	}
 	acc = fc_frame_payload_get(fp, sizeof(*acc));
 	memset(acc, 0, sizeof(*acc));
 	acc->la_cmd = ELS_LS_ACC;
@@ -1811,11 +1865,16 @@ static void fc_seq_ls_rjt(struct fc_frame *rx_fp, enum fc_els_rjt_reason reason,
 	struct fc_lport *lport;
 	struct fc_els_ls_rjt *rjt;
 	struct fc_frame *fp;
+	struct fc_seq *sp;
 
 	lport = fr_dev(rx_fp);
+	sp = fr_seq(rx_fp);
 	fp = fc_frame_alloc(lport, sizeof(*rjt));
-	if (!fp)
+	if (!fp) {
+		FC_EXCH_DBG(fc_seq_exch(sp),
+			    "exch: drop LS_ACC, out of memory\n");
 		return;
+	}
 	rjt = fc_frame_payload_get(fp, sizeof(*rjt));
 	memset(rjt, 0, sizeof(*rjt));
 	rjt->er_cmd = ELS_LS_RJT;
@@ -1960,8 +2019,7 @@ static void fc_exch_els_rec(struct fc_frame *rfp)
 	enum fc_els_rjt_reason reason = ELS_RJT_LOGIC;
 	enum fc_els_rjt_explan explan;
 	u32 sid;
-	u16 rxid;
-	u16 oxid;
+	u16 xid, rxid, oxid;
 
 	lport = fr_dev(rfp);
 	rp = fc_frame_payload_get(rfp, sizeof(*rp));
@@ -1972,18 +2030,35 @@ static void fc_exch_els_rec(struct fc_frame *rfp)
 	rxid = ntohs(rp->rec_rx_id);
 	oxid = ntohs(rp->rec_ox_id);
 
-	ep = fc_exch_lookup(lport,
-			    sid == fc_host_port_id(lport->host) ? oxid : rxid);
 	explan = ELS_EXPL_OXID_RXID;
-	if (!ep)
+	if (sid == fc_host_port_id(lport->host))
+		xid = oxid;
+	else
+		xid = rxid;
+	if (xid == FC_XID_UNKNOWN) {
+		FC_LPORT_DBG(lport,
+			     "REC request from %x: invalid rxid %x oxid %x\n",
+			     sid, rxid, oxid);
+		goto reject;
+	}
+	ep = fc_exch_lookup(lport, xid);
+	if (!ep) {
+		FC_LPORT_DBG(lport,
+			     "REC request from %x: rxid %x oxid %x not found\n",
+			     sid, rxid, oxid);
 		goto reject;
+	}
+	FC_EXCH_DBG(ep, "REC request from %x: rxid %x oxid %x\n",
+		    sid, rxid, oxid);
 	if (ep->oid != sid || oxid != ep->oxid)
 		goto rel;
 	if (rxid != FC_XID_UNKNOWN && rxid != ep->rxid)
 		goto rel;
 	fp = fc_frame_alloc(lport, sizeof(*acc));
-	if (!fp)
+	if (!fp) {
+		FC_EXCH_DBG(ep, "Drop REC request, out of memory\n");
 		goto out;
+	}
 
 	acc = fc_frame_payload_get(fp, sizeof(*acc));
 	memset(acc, 0, sizeof(*acc));
@@ -2065,6 +2140,24 @@ cleanup:
  * @arg:	The argument to be passed to the response handler
  * @timer_msec: The timeout period for the exchange
  *
+ * The exchange response handler is set in this routine to resp()
+ * function pointer. It can be called in two scenarios: if a timeout
+ * occurs or if a response frame is received for the exchange. The
+ * fc_frame pointer in response handler will also indicate timeout
+ * as error using IS_ERR related macros.
+ *
+ * The exchange destructor handler is also set in this routine.
+ * The destructor handler is invoked by EM layer when exchange
+ * is about to free, this can be used by caller to free its
+ * resources along with exchange free.
+ *
+ * The arg is passed back to resp and destructor handler.
+ *
+ * The timeout value (in msec) for an exchange is set if non zero
+ * timer_msec argument is specified. The timer is canceled when
+ * it fires or when the exchange is done. The exchange timeout handler
+ * is registered by EM layer.
+ *
  * The frame pointer with some of the header's fields must be
  * filled before calling this routine, those fields are:
  *
@@ -2075,14 +2168,13 @@ cleanup:
  * - frame control
  * - parameter or relative offset
  */
-static struct fc_seq *fc_exch_seq_send(struct fc_lport *lport,
-				       struct fc_frame *fp,
-				       void (*resp)(struct fc_seq *,
-						    struct fc_frame *fp,
-						    void *arg),
-				       void (*destructor)(struct fc_seq *,
-							  void *),
-				       void *arg, u32 timer_msec)
+struct fc_seq *fc_exch_seq_send(struct fc_lport *lport,
+				struct fc_frame *fp,
+				void (*resp)(struct fc_seq *,
+					     struct fc_frame *fp,
+					     void *arg),
+				void (*destructor)(struct fc_seq *, void *),
+				void *arg, u32 timer_msec)
 {
 	struct fc_exch *ep;
 	struct fc_seq *sp = NULL;
@@ -2101,7 +2193,7 @@ static struct fc_seq *fc_exch_seq_send(struct fc_lport *lport,
 	ep->resp = resp;
 	ep->destructor = destructor;
 	ep->arg = arg;
-	ep->r_a_tov = FC_DEF_R_A_TOV;
+	ep->r_a_tov = lport->r_a_tov;
 	ep->lp = lport;
 	sp = &ep->seq;
 
@@ -2135,6 +2227,7 @@ err:
 		fc_exch_delete(ep);
 	return NULL;
 }
+EXPORT_SYMBOL(fc_exch_seq_send);
 
 /**
  * fc_exch_rrq() - Send an ELS RRQ (Reinstate Recovery Qualifier) command
@@ -2176,6 +2269,7 @@ static void fc_exch_rrq(struct fc_exch *ep)
 		return;
 
 retry:
+	FC_EXCH_DBG(ep, "exch: RRQ send failed\n");
 	spin_lock_bh(&ep->ex_lock);
 	if (ep->state & (FC_EX_RST_CLEANUP | FC_EX_DONE)) {
 		spin_unlock_bh(&ep->ex_lock);
@@ -2218,6 +2312,8 @@ static void fc_exch_els_rrq(struct fc_frame *fp)
 	if (!ep)
 		goto reject;
 	spin_lock_bh(&ep->ex_lock);
+	FC_EXCH_DBG(ep, "RRQ request from %x: xid %x rxid %x oxid %x\n",
+		    sid, xid, ntohs(rp->rrq_rx_id), ntohs(rp->rrq_ox_id));
 	if (ep->oxid != ntohs(rp->rrq_ox_id))
 		goto unlock_reject;
 	if (ep->rxid != ntohs(rp->rrq_rx_id) &&
@@ -2385,6 +2481,7 @@ struct fc_exch_mgr *fc_exch_mgr_alloc(struct fc_lport *lport,
 		return NULL;
 
 	mp->class = class;
+	mp->lport = lport;
 	/* adjust em exch xid range for offload */
 	mp->min_xid = min_xid;
 
@@ -2558,36 +2655,9 @@ EXPORT_SYMBOL(fc_exch_recv);
  */
 int fc_exch_init(struct fc_lport *lport)
 {
-	if (!lport->tt.seq_start_next)
-		lport->tt.seq_start_next = fc_seq_start_next;
-
-	if (!lport->tt.seq_set_resp)
-		lport->tt.seq_set_resp = fc_seq_set_resp;
-
-	if (!lport->tt.exch_seq_send)
-		lport->tt.exch_seq_send = fc_exch_seq_send;
-
-	if (!lport->tt.seq_send)
-		lport->tt.seq_send = fc_seq_send;
-
-	if (!lport->tt.seq_els_rsp_send)
-		lport->tt.seq_els_rsp_send = fc_seq_els_rsp_send;
-
-	if (!lport->tt.exch_done)
-		lport->tt.exch_done = fc_exch_done;
-
 	if (!lport->tt.exch_mgr_reset)
 		lport->tt.exch_mgr_reset = fc_exch_mgr_reset;
 
-	if (!lport->tt.seq_exch_abort)
-		lport->tt.seq_exch_abort = fc_seq_exch_abort;
-
-	if (!lport->tt.seq_assign)
-		lport->tt.seq_assign = fc_seq_assign;
-
-	if (!lport->tt.seq_release)
-		lport->tt.seq_release = fc_seq_release;
-
 	return 0;
 }
 EXPORT_SYMBOL(fc_exch_init);
diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index 5121272f28fd..0e67621477a8 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -122,6 +122,7 @@ static void fc_fcp_srr_error(struct fc_fcp_pkt *, struct fc_frame *);
 #define FC_HRD_ERROR		9
 #define FC_CRC_ERROR		10
 #define FC_TIMED_OUT		11
+#define FC_TRANS_RESET		12
 
 /*
  * Error recovery timeout values.
@@ -195,7 +196,7 @@ static void fc_fcp_pkt_hold(struct fc_fcp_pkt *fsp)
  * @seq: The sequence that the FCP packet is on (required by destructor API)
  * @fsp: The FCP packet to be released
  *
- * This routine is called by a destructor callback in the exch_seq_send()
+ * This routine is called by a destructor callback in the fc_exch_seq_send()
  * routine of the libfc Transport Template. The 'struct fc_seq' is a required
  * argument even though it is not used by this routine.
  *
@@ -253,8 +254,21 @@ static inline void fc_fcp_unlock_pkt(struct fc_fcp_pkt *fsp)
  */
 static void fc_fcp_timer_set(struct fc_fcp_pkt *fsp, unsigned long delay)
 {
-	if (!(fsp->state & FC_SRB_COMPL))
+	if (!(fsp->state & FC_SRB_COMPL)) {
 		mod_timer(&fsp->timer, jiffies + delay);
+		fsp->timer_delay = delay;
+	}
+}
+
+static void fc_fcp_abort_done(struct fc_fcp_pkt *fsp)
+{
+	fsp->state |= FC_SRB_ABORTED;
+	fsp->state &= ~FC_SRB_ABORT_PENDING;
+
+	if (fsp->wait_for_comp)
+		complete(&fsp->tm_done);
+	else
+		fc_fcp_complete_locked(fsp);
 }
 
 /**
@@ -264,6 +278,8 @@ static void fc_fcp_timer_set(struct fc_fcp_pkt *fsp, unsigned long delay)
  */
 static int fc_fcp_send_abort(struct fc_fcp_pkt *fsp)
 {
+	int rc;
+
 	if (!fsp->seq_ptr)
 		return -EINVAL;
 
@@ -271,7 +287,16 @@ static int fc_fcp_send_abort(struct fc_fcp_pkt *fsp)
 	put_cpu();
 
 	fsp->state |= FC_SRB_ABORT_PENDING;
-	return fsp->lp->tt.seq_exch_abort(fsp->seq_ptr, 0);
+	rc = fc_seq_exch_abort(fsp->seq_ptr, 0);
+	/*
+	 * fc_seq_exch_abort() might return -ENXIO if
+	 * the sequence is already completed
+	 */
+	if (rc == -ENXIO) {
+		fc_fcp_abort_done(fsp);
+		rc = 0;
+	}
+	return rc;
 }
 
 /**
@@ -283,16 +308,16 @@ static int fc_fcp_send_abort(struct fc_fcp_pkt *fsp)
  * fc_io_compl() will notify the SCSI-ml that the I/O is done.
  * The SCSI-ml will retry the command.
  */
-static void fc_fcp_retry_cmd(struct fc_fcp_pkt *fsp)
+static void fc_fcp_retry_cmd(struct fc_fcp_pkt *fsp, int status_code)
 {
 	if (fsp->seq_ptr) {
-		fsp->lp->tt.exch_done(fsp->seq_ptr);
+		fc_exch_done(fsp->seq_ptr);
 		fsp->seq_ptr = NULL;
 	}
 
 	fsp->state &= ~FC_SRB_ABORT_PENDING;
 	fsp->io_status = 0;
-	fsp->status_code = FC_ERROR;
+	fsp->status_code = status_code;
 	fc_fcp_complete_locked(fsp);
 }
 
@@ -402,8 +427,6 @@ static void fc_fcp_can_queue_ramp_down(struct fc_lport *lport)
 	if (!can_queue)
 		can_queue = 1;
 	lport->host->can_queue = can_queue;
-	shost_printk(KERN_ERR, lport->host, "libfc: Could not allocate frame.\n"
-		     "Reducing can_queue to %d.\n", can_queue);
 
 unlock:
 	spin_unlock_irqrestore(lport->host->host_lock, flags);
@@ -430,10 +453,29 @@ static inline struct fc_frame *fc_fcp_frame_alloc(struct fc_lport *lport,
 	put_cpu();
 	/* error case */
 	fc_fcp_can_queue_ramp_down(lport);
+	shost_printk(KERN_ERR, lport->host,
+		     "libfc: Could not allocate frame, "
+		     "reducing can_queue to %d.\n", lport->host->can_queue);
 	return NULL;
 }
 
 /**
+ * get_fsp_rec_tov() - Helper function to get REC_TOV
+ * @fsp: the FCP packet
+ *
+ * Returns rec tov in jiffies as rpriv->e_d_tov + 1 second
+ */
+static inline unsigned int get_fsp_rec_tov(struct fc_fcp_pkt *fsp)
+{
+	struct fc_rport_libfc_priv *rpriv = fsp->rport->dd_data;
+	unsigned int e_d_tov = FC_DEF_E_D_TOV;
+
+	if (rpriv && rpriv->e_d_tov > e_d_tov)
+		e_d_tov = rpriv->e_d_tov;
+	return msecs_to_jiffies(e_d_tov) + HZ;
+}
+
+/**
  * fc_fcp_recv_data() - Handler for receiving SCSI-FCP data from a target
  * @fsp: The FCP packet the data is on
  * @fp:	 The data frame
@@ -536,8 +578,10 @@ crc_err:
 	 * and completes the transfer, call the completion handler.
 	 */
 	if (unlikely(fsp->state & FC_SRB_RCV_STATUS) &&
-	    fsp->xfer_len == fsp->data_len - fsp->scsi_resid)
+	    fsp->xfer_len == fsp->data_len - fsp->scsi_resid) {
+		FC_FCP_DBG( fsp, "complete out-of-order sequence\n" );
 		fc_fcp_complete_locked(fsp);
+	}
 	return;
 err:
 	fc_fcp_recovery(fsp, host_bcode);
@@ -609,7 +653,7 @@ static int fc_fcp_send_data(struct fc_fcp_pkt *fsp, struct fc_seq *seq,
 	remaining = seq_blen;
 	fh_parm_offset = frame_offset = offset;
 	tlen = 0;
-	seq = lport->tt.seq_start_next(seq);
+	seq = fc_seq_start_next(seq);
 	f_ctl = FC_FC_REL_OFF;
 	WARN_ON(!seq);
 
@@ -687,7 +731,7 @@ static int fc_fcp_send_data(struct fc_fcp_pkt *fsp, struct fc_seq *seq,
 		/*
 		 * send fragment using for a sequence.
 		 */
-		error = lport->tt.seq_send(lport, seq, fp);
+		error = fc_seq_send(lport, seq, fp);
 		if (error) {
 			WARN_ON(1);		/* send error should be rare */
 			return error;
@@ -727,15 +771,8 @@ static void fc_fcp_abts_resp(struct fc_fcp_pkt *fsp, struct fc_frame *fp)
 		ba_done = 0;
 	}
 
-	if (ba_done) {
-		fsp->state |= FC_SRB_ABORTED;
-		fsp->state &= ~FC_SRB_ABORT_PENDING;
-
-		if (fsp->wait_for_comp)
-			complete(&fsp->tm_done);
-		else
-			fc_fcp_complete_locked(fsp);
-	}
+	if (ba_done)
+		fc_fcp_abort_done(fsp);
 }
 
 /**
@@ -764,8 +801,11 @@ static void fc_fcp_recv(struct fc_seq *seq, struct fc_frame *fp, void *arg)
 	fh = fc_frame_header_get(fp);
 	r_ctl = fh->fh_r_ctl;
 
-	if (lport->state != LPORT_ST_READY)
+	if (lport->state != LPORT_ST_READY) {
+		FC_FCP_DBG(fsp, "lport state %d, ignoring r_ctl %x\n",
+			   lport->state, r_ctl);
 		goto out;
+	}
 	if (fc_fcp_lock_pkt(fsp))
 		goto out;
 
@@ -774,8 +814,10 @@ static void fc_fcp_recv(struct fc_seq *seq, struct fc_frame *fp, void *arg)
 		goto unlock;
 	}
 
-	if (fsp->state & (FC_SRB_ABORTED | FC_SRB_ABORT_PENDING))
+	if (fsp->state & (FC_SRB_ABORTED | FC_SRB_ABORT_PENDING)) {
+		FC_FCP_DBG(fsp, "command aborted, ignoring r_ctl %x\n", r_ctl);
 		goto unlock;
+	}
 
 	if (r_ctl == FC_RCTL_DD_DATA_DESC) {
 		/*
@@ -910,7 +952,16 @@ static void fc_fcp_resp(struct fc_fcp_pkt *fsp, struct fc_frame *fp)
 			 * Wait a at least one jiffy to see if it is delivered.
 			 * If this expires without data, we may do SRR.
 			 */
-			fc_fcp_timer_set(fsp, 2);
+			if (fsp->lp->qfull) {
+				FC_FCP_DBG(fsp, "tgt %6.6x queue busy retry\n",
+					   fsp->rport->port_id);
+				return;
+			}
+			FC_FCP_DBG(fsp, "tgt %6.6x xfer len %zx data underrun "
+				   "len %x, data len %x\n",
+				   fsp->rport->port_id,
+				   fsp->xfer_len, expected_len, fsp->data_len);
+			fc_fcp_timer_set(fsp, get_fsp_rec_tov(fsp));
 			return;
 		}
 		fsp->status_code = FC_DATA_OVRRUN;
@@ -959,8 +1010,11 @@ static void fc_fcp_complete_locked(struct fc_fcp_pkt *fsp)
 		if (fsp->cdb_status == SAM_STAT_GOOD &&
 		    fsp->xfer_len < fsp->data_len && !fsp->io_status &&
 		    (!(fsp->scsi_comp_flags & FCP_RESID_UNDER) ||
-		     fsp->xfer_len < fsp->data_len - fsp->scsi_resid))
+		     fsp->xfer_len < fsp->data_len - fsp->scsi_resid)) {
+			FC_FCP_DBG(fsp, "data underrun, xfer %zx data %x\n",
+				    fsp->xfer_len, fsp->data_len);
 			fsp->status_code = FC_DATA_UNDRUN;
+		}
 	}
 
 	seq = fsp->seq_ptr;
@@ -970,7 +1024,7 @@ static void fc_fcp_complete_locked(struct fc_fcp_pkt *fsp)
 			struct fc_frame *conf_frame;
 			struct fc_seq *csp;
 
-			csp = lport->tt.seq_start_next(seq);
+			csp = fc_seq_start_next(seq);
 			conf_frame = fc_fcp_frame_alloc(fsp->lp, 0);
 			if (conf_frame) {
 				f_ctl = FC_FC_SEQ_INIT;
@@ -979,10 +1033,10 @@ static void fc_fcp_complete_locked(struct fc_fcp_pkt *fsp)
 				fc_fill_fc_hdr(conf_frame, FC_RCTL_DD_SOL_CTL,
 					       ep->did, ep->sid,
 					       FC_TYPE_FCP, f_ctl, 0);
-				lport->tt.seq_send(lport, csp, conf_frame);
+				fc_seq_send(lport, csp, conf_frame);
 			}
 		}
-		lport->tt.exch_done(seq);
+		fc_exch_done(seq);
 	}
 	/*
 	 * Some resets driven by SCSI are not I/Os and do not have
@@ -1000,10 +1054,8 @@ static void fc_fcp_complete_locked(struct fc_fcp_pkt *fsp)
  */
 static void fc_fcp_cleanup_cmd(struct fc_fcp_pkt *fsp, int error)
 {
-	struct fc_lport *lport = fsp->lp;
-
 	if (fsp->seq_ptr) {
-		lport->tt.exch_done(fsp->seq_ptr);
+		fc_exch_done(fsp->seq_ptr);
 		fsp->seq_ptr = NULL;
 	}
 	fsp->status_code = error;
@@ -1116,19 +1168,6 @@ static int fc_fcp_pkt_send(struct fc_lport *lport, struct fc_fcp_pkt *fsp)
 }
 
 /**
- * get_fsp_rec_tov() - Helper function to get REC_TOV
- * @fsp: the FCP packet
- *
- * Returns rec tov in jiffies as rpriv->e_d_tov + 1 second
- */
-static inline unsigned int get_fsp_rec_tov(struct fc_fcp_pkt *fsp)
-{
-	struct fc_rport_libfc_priv *rpriv = fsp->rport->dd_data;
-
-	return msecs_to_jiffies(rpriv->e_d_tov) + HZ;
-}
-
-/**
  * fc_fcp_cmd_send() - Send a FCP command
  * @lport: The local port to send the command on
  * @fsp:   The FCP packet the command is on
@@ -1165,8 +1204,7 @@ static int fc_fcp_cmd_send(struct fc_lport *lport, struct fc_fcp_pkt *fsp,
 		       rpriv->local_port->port_id, FC_TYPE_FCP,
 		       FC_FCTL_REQ, 0);
 
-	seq = lport->tt.exch_seq_send(lport, fp, resp, fc_fcp_pkt_destroy,
-				      fsp, 0);
+	seq = fc_exch_seq_send(lport, fp, resp, fc_fcp_pkt_destroy, fsp, 0);
 	if (!seq) {
 		rc = -1;
 		goto unlock;
@@ -1196,7 +1234,7 @@ static void fc_fcp_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp)
 		return;
 
 	if (error == -FC_EX_CLOSED) {
-		fc_fcp_retry_cmd(fsp);
+		fc_fcp_retry_cmd(fsp, FC_ERROR);
 		goto unlock;
 	}
 
@@ -1222,8 +1260,16 @@ static int fc_fcp_pkt_abort(struct fc_fcp_pkt *fsp)
 	int rc = FAILED;
 	unsigned long ticks_left;
 
-	if (fc_fcp_send_abort(fsp))
+	FC_FCP_DBG(fsp, "pkt abort state %x\n", fsp->state);
+	if (fc_fcp_send_abort(fsp)) {
+		FC_FCP_DBG(fsp, "failed to send abort\n");
 		return FAILED;
+	}
+
+	if (fsp->state & FC_SRB_ABORTED) {
+		FC_FCP_DBG(fsp, "target abort cmd  completed\n");
+		return SUCCESS;
+	}
 
 	init_completion(&fsp->tm_done);
 	fsp->wait_for_comp = 1;
@@ -1301,7 +1347,7 @@ static int fc_lun_reset(struct fc_lport *lport, struct fc_fcp_pkt *fsp,
 
 	spin_lock_bh(&fsp->scsi_pkt_lock);
 	if (fsp->seq_ptr) {
-		lport->tt.exch_done(fsp->seq_ptr);
+		fc_exch_done(fsp->seq_ptr);
 		fsp->seq_ptr = NULL;
 	}
 	fsp->wait_for_comp = 0;
@@ -1355,7 +1401,7 @@ static void fc_tm_done(struct fc_seq *seq, struct fc_frame *fp, void *arg)
 	if (fh->fh_type != FC_TYPE_BLS)
 		fc_fcp_resp(fsp, fp);
 	fsp->seq_ptr = NULL;
-	fsp->lp->tt.exch_done(seq);
+	fc_exch_done(seq);
 out_unlock:
 	fc_fcp_unlock_pkt(fsp);
 out:
@@ -1394,6 +1440,15 @@ static void fc_fcp_timeout(unsigned long data)
 	if (fsp->cdb_cmd.fc_tm_flags)
 		goto unlock;
 
+	if (fsp->lp->qfull) {
+		FC_FCP_DBG(fsp, "fcp timeout, resetting timer delay %d\n",
+			   fsp->timer_delay);
+		setup_timer(&fsp->timer, fc_fcp_timeout, (unsigned long)fsp);
+		fc_fcp_timer_set(fsp, fsp->timer_delay);
+		goto unlock;
+	}
+	FC_FCP_DBG(fsp, "fcp timeout, delay %d flags %x state %x\n",
+		   fsp->timer_delay, rpriv->flags, fsp->state);
 	fsp->state |= FC_SRB_FCP_PROCESSING_TMO;
 
 	if (rpriv->flags & FC_RP_FLAGS_REC_SUPPORTED)
@@ -1486,8 +1541,8 @@ static void fc_fcp_rec_resp(struct fc_seq *seq, struct fc_frame *fp, void *arg)
 		rjt = fc_frame_payload_get(fp, sizeof(*rjt));
 		switch (rjt->er_reason) {
 		default:
-			FC_FCP_DBG(fsp, "device %x unexpected REC reject "
-				   "reason %d expl %d\n",
+			FC_FCP_DBG(fsp,
+				   "device %x invalid REC reject %d/%d\n",
 				   fsp->rport->port_id, rjt->er_reason,
 				   rjt->er_explan);
 			/* fall through */
@@ -1503,18 +1558,23 @@ static void fc_fcp_rec_resp(struct fc_seq *seq, struct fc_frame *fp, void *arg)
 			break;
 		case ELS_RJT_LOGIC:
 		case ELS_RJT_UNAB:
+			FC_FCP_DBG(fsp, "device %x REC reject %d/%d\n",
+				   fsp->rport->port_id, rjt->er_reason,
+				   rjt->er_explan);
 			/*
-			 * If no data transfer, the command frame got dropped
-			 * so we just retry.  If data was transferred, we
-			 * lost the response but the target has no record,
-			 * so we abort and retry.
+			 * If response got lost or is stuck in the
+			 * queue somewhere we have no idea if and when
+			 * the response will be received. So quarantine
+			 * the xid and retry the command.
 			 */
-			if (rjt->er_explan == ELS_EXPL_OXID_RXID &&
-			    fsp->xfer_len == 0) {
-				fc_fcp_retry_cmd(fsp);
+			if (rjt->er_explan == ELS_EXPL_OXID_RXID) {
+				struct fc_exch *ep = fc_seq_exch(fsp->seq_ptr);
+				ep->state |= FC_EX_QUARANTINE;
+				fsp->state |= FC_SRB_ABORTED;
+				fc_fcp_retry_cmd(fsp, FC_TRANS_RESET);
 				break;
 			}
-			fc_fcp_recovery(fsp, FC_ERROR);
+			fc_fcp_recovery(fsp, FC_TRANS_RESET);
 			break;
 		}
 	} else if (opcode == ELS_LS_ACC) {
@@ -1608,7 +1668,9 @@ static void fc_fcp_rec_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp)
 
 	switch (error) {
 	case -FC_EX_CLOSED:
-		fc_fcp_retry_cmd(fsp);
+		FC_FCP_DBG(fsp, "REC %p fid %6.6x exchange closed\n",
+			   fsp, fsp->rport->port_id);
+		fc_fcp_retry_cmd(fsp, FC_ERROR);
 		break;
 
 	default:
@@ -1622,8 +1684,8 @@ static void fc_fcp_rec_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp)
 		 * Assume REC or LS_ACC was lost.
 		 * The exchange manager will have aborted REC, so retry.
 		 */
-		FC_FCP_DBG(fsp, "REC fid %6.6x error error %d retry %d/%d\n",
-			   fsp->rport->port_id, error, fsp->recov_retry,
+		FC_FCP_DBG(fsp, "REC %p fid %6.6x exchange timeout retry %d/%d\n",
+			   fsp, fsp->rport->port_id, fsp->recov_retry,
 			   FC_MAX_RECOV_RETRY);
 		if (fsp->recov_retry++ < FC_MAX_RECOV_RETRY)
 			fc_fcp_rec(fsp);
@@ -1642,6 +1704,7 @@ out:
  */
 static void fc_fcp_recovery(struct fc_fcp_pkt *fsp, u8 code)
 {
+	FC_FCP_DBG(fsp, "start recovery code %x\n", code);
 	fsp->status_code = code;
 	fsp->cdb_status = 0;
 	fsp->io_status = 0;
@@ -1668,7 +1731,6 @@ static void fc_fcp_srr(struct fc_fcp_pkt *fsp, enum fc_rctl r_ctl, u32 offset)
 	struct fc_seq *seq;
 	struct fcp_srr *srr;
 	struct fc_frame *fp;
-	unsigned int rec_tov;
 
 	rport = fsp->rport;
 	rpriv = rport->dd_data;
@@ -1692,10 +1754,9 @@ static void fc_fcp_srr(struct fc_fcp_pkt *fsp, enum fc_rctl r_ctl, u32 offset)
 		       rpriv->local_port->port_id, FC_TYPE_FCP,
 		       FC_FCTL_REQ, 0);
 
-	rec_tov = get_fsp_rec_tov(fsp);
-	seq = lport->tt.exch_seq_send(lport, fp, fc_fcp_srr_resp,
-				      fc_fcp_pkt_destroy,
-				      fsp, jiffies_to_msecs(rec_tov));
+	seq = fc_exch_seq_send(lport, fp, fc_fcp_srr_resp,
+			       fc_fcp_pkt_destroy,
+			       fsp, get_fsp_rec_tov(fsp));
 	if (!seq)
 		goto retry;
 
@@ -1706,7 +1767,7 @@ static void fc_fcp_srr(struct fc_fcp_pkt *fsp, enum fc_rctl r_ctl, u32 offset)
 	fc_fcp_pkt_hold(fsp);		/* hold for outstanding SRR */
 	return;
 retry:
-	fc_fcp_retry_cmd(fsp);
+	fc_fcp_retry_cmd(fsp, FC_TRANS_RESET);
 }
 
 /**
@@ -1730,9 +1791,9 @@ static void fc_fcp_srr_resp(struct fc_seq *seq, struct fc_frame *fp, void *arg)
 
 	fh = fc_frame_header_get(fp);
 	/*
-	 * BUG? fc_fcp_srr_error calls exch_done which would release
+	 * BUG? fc_fcp_srr_error calls fc_exch_done which would release
 	 * the ep. But if fc_fcp_srr_error had got -FC_EX_TIMEOUT,
-	 * then fc_exch_timeout would be sending an abort. The exch_done
+	 * then fc_exch_timeout would be sending an abort. The fc_exch_done
 	 * call by fc_fcp_srr_error would prevent fc_exch.c from seeing
 	 * an abort response though.
 	 */
@@ -1753,7 +1814,7 @@ static void fc_fcp_srr_resp(struct fc_seq *seq, struct fc_frame *fp, void *arg)
 	}
 	fc_fcp_unlock_pkt(fsp);
 out:
-	fsp->lp->tt.exch_done(seq);
+	fc_exch_done(seq);
 	fc_frame_free(fp);
 }
 
@@ -1768,20 +1829,22 @@ static void fc_fcp_srr_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp)
 		goto out;
 	switch (PTR_ERR(fp)) {
 	case -FC_EX_TIMEOUT:
+		FC_FCP_DBG(fsp, "SRR timeout, retries %d\n", fsp->recov_retry);
 		if (fsp->recov_retry++ < FC_MAX_RECOV_RETRY)
 			fc_fcp_rec(fsp);
 		else
 			fc_fcp_recovery(fsp, FC_TIMED_OUT);
 		break;
 	case -FC_EX_CLOSED:			/* e.g., link failure */
+		FC_FCP_DBG(fsp, "SRR error, exchange closed\n");
 		/* fall through */
 	default:
-		fc_fcp_retry_cmd(fsp);
+		fc_fcp_retry_cmd(fsp, FC_ERROR);
 		break;
 	}
 	fc_fcp_unlock_pkt(fsp);
 out:
-	fsp->lp->tt.exch_done(fsp->recov_seq);
+	fc_exch_done(fsp->recov_seq);
 }
 
 /**
@@ -1832,8 +1895,13 @@ int fc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc_cmd)
 	rpriv = rport->dd_data;
 
 	if (!fc_fcp_lport_queue_ready(lport)) {
-		if (lport->qfull)
+		if (lport->qfull) {
 			fc_fcp_can_queue_ramp_down(lport);
+			shost_printk(KERN_ERR, lport->host,
+				     "libfc: queue full, "
+				     "reducing can_queue to %d.\n",
+				     lport->host->can_queue);
+		}
 		rc = SCSI_MLQUEUE_HOST_BUSY;
 		goto out;
 	}
@@ -1980,15 +2048,26 @@ static void fc_io_compl(struct fc_fcp_pkt *fsp)
 		sc_cmd->result = (DID_ERROR << 16) | fsp->cdb_status;
 		break;
 	case FC_CMD_ABORTED:
-		FC_FCP_DBG(fsp, "Returning DID_ERROR to scsi-ml "
-			  "due to FC_CMD_ABORTED\n");
-		sc_cmd->result = (DID_ERROR << 16) | fsp->io_status;
+		if (host_byte(sc_cmd->result) == DID_TIME_OUT)
+			FC_FCP_DBG(fsp, "Returning DID_TIME_OUT to scsi-ml "
+				   "due to FC_CMD_ABORTED\n");
+		else {
+			FC_FCP_DBG(fsp, "Returning DID_ERROR to scsi-ml "
+				   "due to FC_CMD_ABORTED\n");
+			set_host_byte(sc_cmd, DID_ERROR);
+		}
+		sc_cmd->result |= fsp->io_status;
 		break;
 	case FC_CMD_RESET:
 		FC_FCP_DBG(fsp, "Returning DID_RESET to scsi-ml "
 			   "due to FC_CMD_RESET\n");
 		sc_cmd->result = (DID_RESET << 16);
 		break;
+	case FC_TRANS_RESET:
+		FC_FCP_DBG(fsp, "Returning DID_SOFT_ERROR to scsi-ml "
+			   "due to FC_TRANS_RESET\n");
+		sc_cmd->result = (DID_SOFT_ERROR << 16);
+		break;
 	case FC_HRD_ERROR:
 		FC_FCP_DBG(fsp, "Returning DID_NO_CONNECT to scsi-ml "
 			   "due to FC_HRD_ERROR\n");
@@ -2142,7 +2221,7 @@ int fc_eh_host_reset(struct scsi_cmnd *sc_cmd)
 
 	fc_block_scsi_eh(sc_cmd);
 
-	lport->tt.lport_reset(lport);
+	fc_lport_reset(lport);
 	wait_tmo = jiffies + FC_HOST_RESET_TIMEOUT;
 	while (!fc_fcp_lport_queue_ready(lport) && time_before(jiffies,
 							       wait_tmo))
diff --git a/drivers/scsi/libfc/fc_libfc.c b/drivers/scsi/libfc/fc_libfc.c
index c11a638f32e6..d623d084b7ec 100644
--- a/drivers/scsi/libfc/fc_libfc.c
+++ b/drivers/scsi/libfc/fc_libfc.c
@@ -226,7 +226,7 @@ void fc_fill_reply_hdr(struct fc_frame *fp, const struct fc_frame *in_fp,
 
 	sp = fr_seq(in_fp);
 	if (sp)
-		fr_seq(fp) = fr_dev(in_fp)->tt.seq_start_next(sp);
+		fr_seq(fp) = fc_seq_start_next(sp);
 	fc_fill_hdr(fp, in_fp, r_ctl, FC_FCTL_RESP, 0, parm_offset);
 }
 EXPORT_SYMBOL(fc_fill_reply_hdr);
diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c
index 04ce7cfb6d1b..919736a74ffa 100644
--- a/drivers/scsi/libfc/fc_lport.c
+++ b/drivers/scsi/libfc/fc_lport.c
@@ -149,7 +149,7 @@ static const char *fc_lport_state_names[] = {
  * @offset:   The offset into the response data
  */
 struct fc_bsg_info {
-	struct fc_bsg_job *job;
+	struct bsg_job *job;
 	struct fc_lport *lport;
 	u16 rsp_code;
 	struct scatterlist *sg;
@@ -200,7 +200,7 @@ static void fc_lport_rport_callback(struct fc_lport *lport,
 				     "in the DNS or FDMI state, it's in the "
 				     "%d state", rdata->ids.port_id,
 				     lport->state);
-			lport->tt.rport_logoff(rdata);
+			fc_rport_logoff(rdata);
 		}
 		break;
 	case RPORT_EV_LOGO:
@@ -237,23 +237,26 @@ static const char *fc_lport_state(struct fc_lport *lport)
  * @remote_fid:	 The FID of the ptp rport
  * @remote_wwpn: The WWPN of the ptp rport
  * @remote_wwnn: The WWNN of the ptp rport
+ *
+ * Locking Note: The lport lock is expected to be held before calling
+ * this routine.
  */
 static void fc_lport_ptp_setup(struct fc_lport *lport,
 			       u32 remote_fid, u64 remote_wwpn,
 			       u64 remote_wwnn)
 {
-	mutex_lock(&lport->disc.disc_mutex);
 	if (lport->ptp_rdata) {
-		lport->tt.rport_logoff(lport->ptp_rdata);
-		kref_put(&lport->ptp_rdata->kref, lport->tt.rport_destroy);
+		fc_rport_logoff(lport->ptp_rdata);
+		kref_put(&lport->ptp_rdata->kref, fc_rport_destroy);
 	}
-	lport->ptp_rdata = lport->tt.rport_create(lport, remote_fid);
+	mutex_lock(&lport->disc.disc_mutex);
+	lport->ptp_rdata = fc_rport_create(lport, remote_fid);
 	kref_get(&lport->ptp_rdata->kref);
 	lport->ptp_rdata->ids.port_name = remote_wwpn;
 	lport->ptp_rdata->ids.node_name = remote_wwnn;
 	mutex_unlock(&lport->disc.disc_mutex);
 
-	lport->tt.rport_login(lport->ptp_rdata);
+	fc_rport_login(lport->ptp_rdata);
 
 	fc_lport_enter_ready(lport);
 }
@@ -308,7 +311,7 @@ struct fc_host_statistics *fc_get_host_stats(struct Scsi_Host *shost)
 	fc_stats = &lport->host_stats;
 	memset(fc_stats, 0, sizeof(struct fc_host_statistics));
 
-	fc_stats->seconds_since_last_reset = (lport->boot_time - jiffies) / HZ;
+	fc_stats->seconds_since_last_reset = (jiffies - lport->boot_time) / HZ;
 
 	for_each_possible_cpu(cpu) {
 		struct fc_stats *stats;
@@ -409,7 +412,7 @@ static void fc_lport_recv_rlir_req(struct fc_lport *lport, struct fc_frame *fp)
 	FC_LPORT_DBG(lport, "Received RLIR request while in state %s\n",
 		     fc_lport_state(lport));
 
-	lport->tt.seq_els_rsp_send(fp, ELS_LS_ACC, NULL);
+	fc_seq_els_rsp_send(fp, ELS_LS_ACC, NULL);
 	fc_frame_free(fp);
 }
 
@@ -478,7 +481,7 @@ static void fc_lport_recv_rnid_req(struct fc_lport *lport,
 	if (!req) {
 		rjt_data.reason = ELS_RJT_LOGIC;
 		rjt_data.explan = ELS_EXPL_NONE;
-		lport->tt.seq_els_rsp_send(in_fp, ELS_LS_RJT, &rjt_data);
+		fc_seq_els_rsp_send(in_fp, ELS_LS_RJT, &rjt_data);
 	} else {
 		fmt = req->rnid_fmt;
 		len = sizeof(*rp);
@@ -518,7 +521,7 @@ static void fc_lport_recv_rnid_req(struct fc_lport *lport,
  */
 static void fc_lport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
 {
-	lport->tt.seq_els_rsp_send(fp, ELS_LS_ACC, NULL);
+	fc_seq_els_rsp_send(fp, ELS_LS_ACC, NULL);
 	fc_lport_enter_reset(lport);
 	fc_frame_free(fp);
 }
@@ -620,9 +623,9 @@ int fc_fabric_logoff(struct fc_lport *lport)
 	lport->tt.disc_stop_final(lport);
 	mutex_lock(&lport->lp_mutex);
 	if (lport->dns_rdata)
-		lport->tt.rport_logoff(lport->dns_rdata);
+		fc_rport_logoff(lport->dns_rdata);
 	mutex_unlock(&lport->lp_mutex);
-	lport->tt.rport_flush_queue();
+	fc_rport_flush_queue();
 	mutex_lock(&lport->lp_mutex);
 	fc_lport_enter_logo(lport);
 	mutex_unlock(&lport->lp_mutex);
@@ -899,7 +902,7 @@ static void fc_lport_recv_els_req(struct fc_lport *lport,
 		/*
 		 * Check opcode.
 		 */
-		recv = lport->tt.rport_recv_req;
+		recv = fc_rport_recv_req;
 		switch (fc_frame_payload_op(fp)) {
 		case ELS_FLOGI:
 			if (!lport->point_to_multipoint)
@@ -941,15 +944,14 @@ struct fc4_prov fc_lport_els_prov = {
 };
 
 /**
- * fc_lport_recv_req() - The generic lport request handler
+ * fc_lport_recv() - The generic lport request handler
  * @lport: The lport that received the request
  * @fp: The frame the request is in
  *
  * Locking Note: This function should not be called with the lport
  *		 lock held because it may grab the lock.
  */
-static void fc_lport_recv_req(struct fc_lport *lport,
-			      struct fc_frame *fp)
+void fc_lport_recv(struct fc_lport *lport, struct fc_frame *fp)
 {
 	struct fc_frame_header *fh = fc_frame_header_get(fp);
 	struct fc_seq *sp = fr_seq(fp);
@@ -978,8 +980,9 @@ drop:
 	FC_LPORT_DBG(lport, "dropping unexpected frame type %x\n", fh->fh_type);
 	fc_frame_free(fp);
 	if (sp)
-		lport->tt.exch_done(sp);
+		fc_exch_done(sp);
 }
+EXPORT_SYMBOL(fc_lport_recv);
 
 /**
  * fc_lport_reset() - Reset a local port
@@ -1007,12 +1010,14 @@ EXPORT_SYMBOL(fc_lport_reset);
  */
 static void fc_lport_reset_locked(struct fc_lport *lport)
 {
-	if (lport->dns_rdata)
-		lport->tt.rport_logoff(lport->dns_rdata);
+	if (lport->dns_rdata) {
+		fc_rport_logoff(lport->dns_rdata);
+		lport->dns_rdata = NULL;
+	}
 
 	if (lport->ptp_rdata) {
-		lport->tt.rport_logoff(lport->ptp_rdata);
-		kref_put(&lport->ptp_rdata->kref, lport->tt.rport_destroy);
+		fc_rport_logoff(lport->ptp_rdata);
+		kref_put(&lport->ptp_rdata->kref, fc_rport_destroy);
 		lport->ptp_rdata = NULL;
 	}
 
@@ -1426,13 +1431,13 @@ static void fc_lport_enter_dns(struct fc_lport *lport)
 	fc_lport_state_enter(lport, LPORT_ST_DNS);
 
 	mutex_lock(&lport->disc.disc_mutex);
-	rdata = lport->tt.rport_create(lport, FC_FID_DIR_SERV);
+	rdata = fc_rport_create(lport, FC_FID_DIR_SERV);
 	mutex_unlock(&lport->disc.disc_mutex);
 	if (!rdata)
 		goto err;
 
 	rdata->ops = &fc_lport_rport_ops;
-	lport->tt.rport_login(rdata);
+	fc_rport_login(rdata);
 	return;
 
 err:
@@ -1543,13 +1548,13 @@ static void fc_lport_enter_fdmi(struct fc_lport *lport)
 	fc_lport_state_enter(lport, LPORT_ST_FDMI);
 
 	mutex_lock(&lport->disc.disc_mutex);
-	rdata = lport->tt.rport_create(lport, FC_FID_MGMT_SERV);
+	rdata = fc_rport_create(lport, FC_FID_MGMT_SERV);
 	mutex_unlock(&lport->disc.disc_mutex);
 	if (!rdata)
 		goto err;
 
 	rdata->ops = &fc_lport_rport_ops;
-	lport->tt.rport_login(rdata);
+	fc_rport_login(rdata);
 	return;
 
 err:
@@ -1772,7 +1777,7 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp,
 	if ((csp_flags & FC_SP_FT_FPORT) == 0) {
 		if (e_d_tov > lport->e_d_tov)
 			lport->e_d_tov = e_d_tov;
-		lport->r_a_tov = 2 * e_d_tov;
+		lport->r_a_tov = 2 * lport->e_d_tov;
 		fc_lport_set_port_id(lport, did, fp);
 		printk(KERN_INFO "host%d: libfc: "
 		       "Port (%6.6x) entered "
@@ -1784,8 +1789,10 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp,
 				   get_unaligned_be64(
 					   &flp->fl_wwnn));
 	} else {
-		lport->e_d_tov = e_d_tov;
-		lport->r_a_tov = r_a_tov;
+		if (e_d_tov > lport->e_d_tov)
+			lport->e_d_tov = e_d_tov;
+		if (r_a_tov > lport->r_a_tov)
+			lport->r_a_tov = r_a_tov;
 		fc_host_fabric_name(lport->host) =
 			get_unaligned_be64(&flp->fl_wwnn);
 		fc_lport_set_port_id(lport, did, fp);
@@ -1858,12 +1865,6 @@ EXPORT_SYMBOL(fc_lport_config);
  */
 int fc_lport_init(struct fc_lport *lport)
 {
-	if (!lport->tt.lport_recv)
-		lport->tt.lport_recv = fc_lport_recv_req;
-
-	if (!lport->tt.lport_reset)
-		lport->tt.lport_reset = fc_lport_reset;
-
 	fc_host_port_type(lport->host) = FC_PORTTYPE_NPORT;
 	fc_host_node_name(lport->host) = lport->wwnn;
 	fc_host_port_name(lport->host) = lport->wwpn;
@@ -1900,18 +1901,19 @@ static void fc_lport_bsg_resp(struct fc_seq *sp, struct fc_frame *fp,
 			      void *info_arg)
 {
 	struct fc_bsg_info *info = info_arg;
-	struct fc_bsg_job *job = info->job;
+	struct bsg_job *job = info->job;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct fc_lport *lport = info->lport;
 	struct fc_frame_header *fh;
 	size_t len;
 	void *buf;
 
 	if (IS_ERR(fp)) {
-		job->reply->result = (PTR_ERR(fp) == -FC_EX_CLOSED) ?
+		bsg_reply->result = (PTR_ERR(fp) == -FC_EX_CLOSED) ?
 			-ECONNABORTED : -ETIMEDOUT;
 		job->reply_len = sizeof(uint32_t);
-		job->state_flags |= FC_RQST_STATE_DONE;
-		job->job_done(job);
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 		kfree(info);
 		return;
 	}
@@ -1928,25 +1930,25 @@ static void fc_lport_bsg_resp(struct fc_seq *sp, struct fc_frame *fp,
 			(unsigned short)fc_frame_payload_op(fp);
 
 		/* Save the reply status of the job */
-		job->reply->reply_data.ctels_reply.status =
+		bsg_reply->reply_data.ctels_reply.status =
 			(cmd == info->rsp_code) ?
 			FC_CTELS_STATUS_OK : FC_CTELS_STATUS_REJECT;
 	}
 
-	job->reply->reply_payload_rcv_len +=
+	bsg_reply->reply_payload_rcv_len +=
 		fc_copy_buffer_to_sglist(buf, len, info->sg, &info->nents,
 					 &info->offset, NULL);
 
 	if (fr_eof(fp) == FC_EOF_T &&
 	    (ntoh24(fh->fh_f_ctl) & (FC_FC_LAST_SEQ | FC_FC_END_SEQ)) ==
 	    (FC_FC_LAST_SEQ | FC_FC_END_SEQ)) {
-		if (job->reply->reply_payload_rcv_len >
+		if (bsg_reply->reply_payload_rcv_len >
 		    job->reply_payload.payload_len)
-			job->reply->reply_payload_rcv_len =
+			bsg_reply->reply_payload_rcv_len =
 				job->reply_payload.payload_len;
-		job->reply->result = 0;
-		job->state_flags |= FC_RQST_STATE_DONE;
-		job->job_done(job);
+		bsg_reply->result = 0;
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 		kfree(info);
 	}
 	fc_frame_free(fp);
@@ -1962,7 +1964,7 @@ static void fc_lport_bsg_resp(struct fc_seq *sp, struct fc_frame *fp,
  * Locking Note: The lport lock is expected to be held before calling
  * this routine.
  */
-static int fc_lport_els_request(struct fc_bsg_job *job,
+static int fc_lport_els_request(struct bsg_job *job,
 				struct fc_lport *lport,
 				u32 did, u32 tov)
 {
@@ -2005,8 +2007,8 @@ static int fc_lport_els_request(struct fc_bsg_job *job,
 	info->nents = job->reply_payload.sg_cnt;
 	info->sg = job->reply_payload.sg_list;
 
-	if (!lport->tt.exch_seq_send(lport, fp, fc_lport_bsg_resp,
-				     NULL, info, tov)) {
+	if (!fc_exch_seq_send(lport, fp, fc_lport_bsg_resp,
+			      NULL, info, tov)) {
 		kfree(info);
 		return -ECOMM;
 	}
@@ -2023,7 +2025,7 @@ static int fc_lport_els_request(struct fc_bsg_job *job,
  * Locking Note: The lport lock is expected to be held before calling
  * this routine.
  */
-static int fc_lport_ct_request(struct fc_bsg_job *job,
+static int fc_lport_ct_request(struct bsg_job *job,
 			       struct fc_lport *lport, u32 did, u32 tov)
 {
 	struct fc_bsg_info *info;
@@ -2066,8 +2068,8 @@ static int fc_lport_ct_request(struct fc_bsg_job *job,
 	info->nents = job->reply_payload.sg_cnt;
 	info->sg = job->reply_payload.sg_list;
 
-	if (!lport->tt.exch_seq_send(lport, fp, fc_lport_bsg_resp,
-				     NULL, info, tov)) {
+	if (!fc_exch_seq_send(lport, fp, fc_lport_bsg_resp,
+			      NULL, info, tov)) {
 		kfree(info);
 		return -ECOMM;
 	}
@@ -2079,25 +2081,27 @@ static int fc_lport_ct_request(struct fc_bsg_job *job,
  *			    FC Passthrough requests
  * @job: The BSG passthrough job
  */
-int fc_lport_bsg_request(struct fc_bsg_job *job)
+int fc_lport_bsg_request(struct bsg_job *job)
 {
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct request *rsp = job->req->next_rq;
-	struct Scsi_Host *shost = job->shost;
+	struct Scsi_Host *shost = fc_bsg_to_shost(job);
 	struct fc_lport *lport = shost_priv(shost);
 	struct fc_rport *rport;
 	struct fc_rport_priv *rdata;
 	int rc = -EINVAL;
 	u32 did, tov;
 
-	job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 	if (rsp)
 		rsp->resid_len = job->reply_payload.payload_len;
 
 	mutex_lock(&lport->lp_mutex);
 
-	switch (job->request->msgcode) {
+	switch (bsg_request->msgcode) {
 	case FC_BSG_RPT_ELS:
-		rport = job->rport;
+		rport = fc_bsg_to_rport(job);
 		if (!rport)
 			break;
 
@@ -2107,7 +2111,7 @@ int fc_lport_bsg_request(struct fc_bsg_job *job)
 		break;
 
 	case FC_BSG_RPT_CT:
-		rport = job->rport;
+		rport = fc_bsg_to_rport(job);
 		if (!rport)
 			break;
 
@@ -2117,25 +2121,25 @@ int fc_lport_bsg_request(struct fc_bsg_job *job)
 		break;
 
 	case FC_BSG_HST_CT:
-		did = ntoh24(job->request->rqst_data.h_ct.port_id);
+		did = ntoh24(bsg_request->rqst_data.h_ct.port_id);
 		if (did == FC_FID_DIR_SERV) {
 			rdata = lport->dns_rdata;
 			if (!rdata)
 				break;
 			tov = rdata->e_d_tov;
 		} else {
-			rdata = lport->tt.rport_lookup(lport, did);
+			rdata = fc_rport_lookup(lport, did);
 			if (!rdata)
 				break;
 			tov = rdata->e_d_tov;
-			kref_put(&rdata->kref, lport->tt.rport_destroy);
+			kref_put(&rdata->kref, fc_rport_destroy);
 		}
 
 		rc = fc_lport_ct_request(job, lport, did, tov);
 		break;
 
 	case FC_BSG_HST_ELS_NOLOGIN:
-		did = ntoh24(job->request->rqst_data.h_els.port_id);
+		did = ntoh24(bsg_request->rqst_data.h_els.port_id);
 		rc = fc_lport_els_request(job, lport, did, lport->e_d_tov);
 		break;
 	}
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index 97aeaddd600d..c991f3b822f8 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -44,6 +44,19 @@
  * path this potential over-use of the mutex is acceptable.
  */
 
+/*
+ * RPORT REFERENCE COUNTING
+ *
+ * A rport reference should be taken when:
+ * - an rport is allocated
+ * - a workqueue item is scheduled
+ * - an ELS request is send
+ * The reference should be dropped when:
+ * - the workqueue function has finished
+ * - the ELS response is handled
+ * - an rport is removed
+ */
+
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
@@ -74,8 +87,8 @@ static void fc_rport_recv_prli_req(struct fc_rport_priv *, struct fc_frame *);
 static void fc_rport_recv_prlo_req(struct fc_rport_priv *, struct fc_frame *);
 static void fc_rport_recv_logo_req(struct fc_lport *, struct fc_frame *);
 static void fc_rport_timeout(struct work_struct *);
-static void fc_rport_error(struct fc_rport_priv *, struct fc_frame *);
-static void fc_rport_error_retry(struct fc_rport_priv *, struct fc_frame *);
+static void fc_rport_error(struct fc_rport_priv *, int);
+static void fc_rport_error_retry(struct fc_rport_priv *, int);
 static void fc_rport_work(struct work_struct *);
 
 static const char *fc_rport_state_names[] = {
@@ -98,8 +111,8 @@ static const char *fc_rport_state_names[] = {
  * The reference count of the fc_rport_priv structure is
  * increased by one.
  */
-static struct fc_rport_priv *fc_rport_lookup(const struct fc_lport *lport,
-					     u32 port_id)
+struct fc_rport_priv *fc_rport_lookup(const struct fc_lport *lport,
+				      u32 port_id)
 {
 	struct fc_rport_priv *rdata = NULL, *tmp_rdata;
 
@@ -113,6 +126,7 @@ static struct fc_rport_priv *fc_rport_lookup(const struct fc_lport *lport,
 	rcu_read_unlock();
 	return rdata;
 }
+EXPORT_SYMBOL(fc_rport_lookup);
 
 /**
  * fc_rport_create() - Create a new remote port
@@ -123,12 +137,11 @@ static struct fc_rport_priv *fc_rport_lookup(const struct fc_lport *lport,
  *
  * Locking note:  must be called with the disc_mutex held.
  */
-static struct fc_rport_priv *fc_rport_create(struct fc_lport *lport,
-					     u32 port_id)
+struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id)
 {
 	struct fc_rport_priv *rdata;
 
-	rdata = lport->tt.rport_lookup(lport, port_id);
+	rdata = fc_rport_lookup(lport, port_id);
 	if (rdata)
 		return rdata;
 
@@ -158,18 +171,20 @@ static struct fc_rport_priv *fc_rport_create(struct fc_lport *lport,
 	}
 	return rdata;
 }
+EXPORT_SYMBOL(fc_rport_create);
 
 /**
  * fc_rport_destroy() - Free a remote port after last reference is released
  * @kref: The remote port's kref
  */
-static void fc_rport_destroy(struct kref *kref)
+void fc_rport_destroy(struct kref *kref)
 {
 	struct fc_rport_priv *rdata;
 
 	rdata = container_of(kref, struct fc_rport_priv, kref);
 	kfree_rcu(rdata, rcu);
 }
+EXPORT_SYMBOL(fc_rport_destroy);
 
 /**
  * fc_rport_state() - Return a string identifying the remote port's state
@@ -242,6 +257,8 @@ static void fc_rport_state_enter(struct fc_rport_priv *rdata,
 /**
  * fc_rport_work() - Handler for remote port events in the rport_event_queue
  * @work: Handle to the remote port being dequeued
+ *
+ * Reference counting: drops kref on return
  */
 static void fc_rport_work(struct work_struct *work)
 {
@@ -272,12 +289,14 @@ static void fc_rport_work(struct work_struct *work)
 		kref_get(&rdata->kref);
 		mutex_unlock(&rdata->rp_mutex);
 
-		if (!rport)
+		if (!rport) {
+			FC_RPORT_DBG(rdata, "No rport!\n");
 			rport = fc_remote_port_add(lport->host, 0, &ids);
+		}
 		if (!rport) {
 			FC_RPORT_DBG(rdata, "Failed to add the rport\n");
-			lport->tt.rport_logoff(rdata);
-			kref_put(&rdata->kref, lport->tt.rport_destroy);
+			fc_rport_logoff(rdata);
+			kref_put(&rdata->kref, fc_rport_destroy);
 			return;
 		}
 		mutex_lock(&rdata->rp_mutex);
@@ -303,7 +322,7 @@ static void fc_rport_work(struct work_struct *work)
 			FC_RPORT_DBG(rdata, "lld callback ev %d\n", event);
 			rdata->lld_event_callback(lport, rdata, event);
 		}
-		kref_put(&rdata->kref, lport->tt.rport_destroy);
+		kref_put(&rdata->kref, fc_rport_destroy);
 		break;
 
 	case RPORT_EV_FAILED:
@@ -329,7 +348,8 @@ static void fc_rport_work(struct work_struct *work)
 			FC_RPORT_DBG(rdata, "lld callback ev %d\n", event);
 			rdata->lld_event_callback(lport, rdata, event);
 		}
-		cancel_delayed_work_sync(&rdata->retry_work);
+		if (cancel_delayed_work_sync(&rdata->retry_work))
+			kref_put(&rdata->kref, fc_rport_destroy);
 
 		/*
 		 * Reset any outstanding exchanges before freeing rport.
@@ -351,7 +371,7 @@ static void fc_rport_work(struct work_struct *work)
 			if (port_id == FC_FID_DIR_SERV) {
 				rdata->event = RPORT_EV_NONE;
 				mutex_unlock(&rdata->rp_mutex);
-				kref_put(&rdata->kref, lport->tt.rport_destroy);
+				kref_put(&rdata->kref, fc_rport_destroy);
 			} else if ((rdata->flags & FC_RP_STARTED) &&
 				   rdata->major_retries <
 				   lport->max_rport_retry_count) {
@@ -362,17 +382,21 @@ static void fc_rport_work(struct work_struct *work)
 				mutex_unlock(&rdata->rp_mutex);
 			} else {
 				FC_RPORT_DBG(rdata, "work delete\n");
+				mutex_lock(&lport->disc.disc_mutex);
 				list_del_rcu(&rdata->peers);
+				mutex_unlock(&lport->disc.disc_mutex);
 				mutex_unlock(&rdata->rp_mutex);
-				kref_put(&rdata->kref, lport->tt.rport_destroy);
+				kref_put(&rdata->kref, fc_rport_destroy);
 			}
 		} else {
 			/*
 			 * Re-open for events.  Reissue READY event if ready.
 			 */
 			rdata->event = RPORT_EV_NONE;
-			if (rdata->rp_state == RPORT_ST_READY)
+			if (rdata->rp_state == RPORT_ST_READY) {
+				FC_RPORT_DBG(rdata, "work reopen\n");
 				fc_rport_enter_ready(rdata);
+			}
 			mutex_unlock(&rdata->rp_mutex);
 		}
 		break;
@@ -381,12 +405,21 @@ static void fc_rport_work(struct work_struct *work)
 		mutex_unlock(&rdata->rp_mutex);
 		break;
 	}
+	kref_put(&rdata->kref, fc_rport_destroy);
 }
 
 /**
  * fc_rport_login() - Start the remote port login state machine
  * @rdata: The remote port to be logged in to
  *
+ * Initiates the RP state machine. It is called from the LP module.
+ * This function will issue the following commands to the N_Port
+ * identified by the FC ID provided.
+ *
+ * - PLOGI
+ * - PRLI
+ * - RTV
+ *
  * Locking Note: Called without the rport lock held. This
  * function will hold the rport lock, call an _enter_*
  * function and then unlock the rport.
@@ -395,10 +428,16 @@ static void fc_rport_work(struct work_struct *work)
  * If it appears we are already logged in, ADISC is used to verify
  * the setup.
  */
-static int fc_rport_login(struct fc_rport_priv *rdata)
+int fc_rport_login(struct fc_rport_priv *rdata)
 {
 	mutex_lock(&rdata->rp_mutex);
 
+	if (rdata->flags & FC_RP_STARTED) {
+		FC_RPORT_DBG(rdata, "port already started\n");
+		mutex_unlock(&rdata->rp_mutex);
+		return 0;
+	}
+
 	rdata->flags |= FC_RP_STARTED;
 	switch (rdata->rp_state) {
 	case RPORT_ST_READY:
@@ -408,15 +447,20 @@ static int fc_rport_login(struct fc_rport_priv *rdata)
 	case RPORT_ST_DELETE:
 		FC_RPORT_DBG(rdata, "Restart deleted port\n");
 		break;
-	default:
+	case RPORT_ST_INIT:
 		FC_RPORT_DBG(rdata, "Login to port\n");
 		fc_rport_enter_flogi(rdata);
 		break;
+	default:
+		FC_RPORT_DBG(rdata, "Login in progress, state %s\n",
+			     fc_rport_state(rdata));
+		break;
 	}
 	mutex_unlock(&rdata->rp_mutex);
 
 	return 0;
 }
+EXPORT_SYMBOL(fc_rport_login);
 
 /**
  * fc_rport_enter_delete() - Schedule a remote port to be deleted
@@ -431,6 +475,8 @@ static int fc_rport_login(struct fc_rport_priv *rdata)
  * Set the new event so that the old pending event will not occur.
  * Since we have the mutex, even if fc_rport_work() is already started,
  * it'll see the new event.
+ *
+ * Reference counting: does not modify kref
  */
 static void fc_rport_enter_delete(struct fc_rport_priv *rdata,
 				  enum fc_rport_event event)
@@ -442,8 +488,11 @@ static void fc_rport_enter_delete(struct fc_rport_priv *rdata,
 
 	fc_rport_state_enter(rdata, RPORT_ST_DELETE);
 
-	if (rdata->event == RPORT_EV_NONE)
-		queue_work(rport_event_queue, &rdata->event_work);
+	kref_get(&rdata->kref);
+	if (rdata->event == RPORT_EV_NONE &&
+	    !queue_work(rport_event_queue, &rdata->event_work))
+		kref_put(&rdata->kref, fc_rport_destroy);
+
 	rdata->event = event;
 }
 
@@ -455,7 +504,7 @@ static void fc_rport_enter_delete(struct fc_rport_priv *rdata,
  * function will hold the rport lock, call an _enter_*
  * function and then unlock the rport.
  */
-static int fc_rport_logoff(struct fc_rport_priv *rdata)
+int fc_rport_logoff(struct fc_rport_priv *rdata)
 {
 	struct fc_lport *lport = rdata->local_port;
 	u32 port_id = rdata->ids.port_id;
@@ -489,6 +538,7 @@ out:
 	mutex_unlock(&rdata->rp_mutex);
 	return 0;
 }
+EXPORT_SYMBOL(fc_rport_logoff);
 
 /**
  * fc_rport_enter_ready() - Transition to the RPORT_ST_READY state
@@ -496,6 +546,8 @@ out:
  *
  * Locking Note: The rport lock is expected to be held before calling
  * this routine.
+ *
+ * Reference counting: schedules workqueue, does not modify kref
  */
 static void fc_rport_enter_ready(struct fc_rport_priv *rdata)
 {
@@ -503,8 +555,11 @@ static void fc_rport_enter_ready(struct fc_rport_priv *rdata)
 
 	FC_RPORT_DBG(rdata, "Port is Ready\n");
 
-	if (rdata->event == RPORT_EV_NONE)
-		queue_work(rport_event_queue, &rdata->event_work);
+	kref_get(&rdata->kref);
+	if (rdata->event == RPORT_EV_NONE &&
+	    !queue_work(rport_event_queue, &rdata->event_work))
+		kref_put(&rdata->kref, fc_rport_destroy);
+
 	rdata->event = RPORT_EV_READY;
 }
 
@@ -515,6 +570,8 @@ static void fc_rport_enter_ready(struct fc_rport_priv *rdata)
  * Locking Note: Called without the rport lock held. This
  * function will hold the rport lock, call an _enter_*
  * function and then unlock the rport.
+ *
+ * Reference counting: Drops kref on return.
  */
 static void fc_rport_timeout(struct work_struct *work)
 {
@@ -522,6 +579,7 @@ static void fc_rport_timeout(struct work_struct *work)
 		container_of(work, struct fc_rport_priv, retry_work.work);
 
 	mutex_lock(&rdata->rp_mutex);
+	FC_RPORT_DBG(rdata, "Port timeout, state %s\n", fc_rport_state(rdata));
 
 	switch (rdata->rp_state) {
 	case RPORT_ST_FLOGI:
@@ -547,23 +605,25 @@ static void fc_rport_timeout(struct work_struct *work)
 	}
 
 	mutex_unlock(&rdata->rp_mutex);
+	kref_put(&rdata->kref, fc_rport_destroy);
 }
 
 /**
  * fc_rport_error() - Error handler, called once retries have been exhausted
  * @rdata: The remote port the error is happened on
- * @fp:	   The error code encapsulated in a frame pointer
+ * @err:   The error code
  *
  * Locking Note: The rport lock is expected to be held before
  * calling this routine
+ *
+ * Reference counting: does not modify kref
  */
-static void fc_rport_error(struct fc_rport_priv *rdata, struct fc_frame *fp)
+static void fc_rport_error(struct fc_rport_priv *rdata, int err)
 {
 	struct fc_lport *lport = rdata->local_port;
 
-	FC_RPORT_DBG(rdata, "Error %ld in state %s, retries %d\n",
-		     IS_ERR(fp) ? -PTR_ERR(fp) : 0,
-		     fc_rport_state(rdata), rdata->retries);
+	FC_RPORT_DBG(rdata, "Error %d in state %s, retries %d\n",
+		     -err, fc_rport_state(rdata), rdata->retries);
 
 	switch (rdata->rp_state) {
 	case RPORT_ST_FLOGI:
@@ -595,36 +655,39 @@ static void fc_rport_error(struct fc_rport_priv *rdata, struct fc_frame *fp)
 /**
  * fc_rport_error_retry() - Handler for remote port state retries
  * @rdata: The remote port whose state is to be retried
- * @fp:	   The error code encapsulated in a frame pointer
+ * @err:   The error code
  *
  * If the error was an exchange timeout retry immediately,
  * otherwise wait for E_D_TOV.
  *
  * Locking Note: The rport lock is expected to be held before
  * calling this routine
+ *
+ * Reference counting: increments kref when scheduling retry_work
  */
-static void fc_rport_error_retry(struct fc_rport_priv *rdata,
-				 struct fc_frame *fp)
+static void fc_rport_error_retry(struct fc_rport_priv *rdata, int err)
 {
-	unsigned long delay = msecs_to_jiffies(FC_DEF_E_D_TOV);
+	unsigned long delay = msecs_to_jiffies(rdata->e_d_tov);
 
 	/* make sure this isn't an FC_EX_CLOSED error, never retry those */
-	if (PTR_ERR(fp) == -FC_EX_CLOSED)
+	if (err == -FC_EX_CLOSED)
 		goto out;
 
 	if (rdata->retries < rdata->local_port->max_rport_retry_count) {
-		FC_RPORT_DBG(rdata, "Error %ld in state %s, retrying\n",
-			     PTR_ERR(fp), fc_rport_state(rdata));
+		FC_RPORT_DBG(rdata, "Error %d in state %s, retrying\n",
+			     err, fc_rport_state(rdata));
 		rdata->retries++;
 		/* no additional delay on exchange timeouts */
-		if (PTR_ERR(fp) == -FC_EX_TIMEOUT)
+		if (err == -FC_EX_TIMEOUT)
 			delay = 0;
-		schedule_delayed_work(&rdata->retry_work, delay);
+		kref_get(&rdata->kref);
+		if (!schedule_delayed_work(&rdata->retry_work, delay))
+			kref_put(&rdata->kref, fc_rport_destroy);
 		return;
 	}
 
 out:
-	fc_rport_error(rdata, fp);
+	fc_rport_error(rdata, err);
 }
 
 /**
@@ -684,8 +747,11 @@ static void fc_rport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp,
 	struct fc_lport *lport = rdata->local_port;
 	struct fc_els_flogi *flogi;
 	unsigned int r_a_tov;
+	u8 opcode;
+	int err = 0;
 
-	FC_RPORT_DBG(rdata, "Received a FLOGI %s\n", fc_els_resp_type(fp));
+	FC_RPORT_DBG(rdata, "Received a FLOGI %s\n",
+		     IS_ERR(fp) ? "error" : fc_els_resp_type(fp));
 
 	if (fp == ERR_PTR(-FC_EX_CLOSED))
 		goto put;
@@ -701,18 +767,34 @@ static void fc_rport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp,
 	}
 
 	if (IS_ERR(fp)) {
-		fc_rport_error(rdata, fp);
+		fc_rport_error(rdata, PTR_ERR(fp));
 		goto err;
 	}
-
-	if (fc_frame_payload_op(fp) != ELS_LS_ACC)
+	opcode = fc_frame_payload_op(fp);
+	if (opcode == ELS_LS_RJT) {
+		struct fc_els_ls_rjt *rjt;
+
+		rjt = fc_frame_payload_get(fp, sizeof(*rjt));
+		FC_RPORT_DBG(rdata, "FLOGI ELS rejected, reason %x expl %x\n",
+			     rjt->er_reason, rjt->er_explan);
+		err = -FC_EX_ELS_RJT;
 		goto bad;
-	if (fc_rport_login_complete(rdata, fp))
+	} else if (opcode != ELS_LS_ACC) {
+		FC_RPORT_DBG(rdata, "FLOGI ELS invalid opcode %x\n", opcode);
+		err = -FC_EX_ELS_RJT;
 		goto bad;
+	}
+	if (fc_rport_login_complete(rdata, fp)) {
+		FC_RPORT_DBG(rdata, "FLOGI failed, no login\n");
+		err = -FC_EX_INV_LOGIN;
+		goto bad;
+	}
 
 	flogi = fc_frame_payload_get(fp, sizeof(*flogi));
-	if (!flogi)
+	if (!flogi) {
+		err = -FC_EX_ALLOC_ERR;
 		goto bad;
+	}
 	r_a_tov = ntohl(flogi->fl_csp.sp_r_a_tov);
 	if (r_a_tov > rdata->r_a_tov)
 		rdata->r_a_tov = r_a_tov;
@@ -726,11 +808,11 @@ out:
 err:
 	mutex_unlock(&rdata->rp_mutex);
 put:
-	kref_put(&rdata->kref, lport->tt.rport_destroy);
+	kref_put(&rdata->kref, fc_rport_destroy);
 	return;
 bad:
 	FC_RPORT_DBG(rdata, "Bad FLOGI response\n");
-	fc_rport_error_retry(rdata, fp);
+	fc_rport_error_retry(rdata, err);
 	goto out;
 }
 
@@ -740,6 +822,8 @@ bad:
  *
  * Locking Note: The rport lock is expected to be held before calling
  * this routine.
+ *
+ * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_flogi(struct fc_rport_priv *rdata)
 {
@@ -756,20 +840,23 @@ static void fc_rport_enter_flogi(struct fc_rport_priv *rdata)
 
 	fp = fc_frame_alloc(lport, sizeof(struct fc_els_flogi));
 	if (!fp)
-		return fc_rport_error_retry(rdata, fp);
+		return fc_rport_error_retry(rdata, -FC_EX_ALLOC_ERR);
 
+	kref_get(&rdata->kref);
 	if (!lport->tt.elsct_send(lport, rdata->ids.port_id, fp, ELS_FLOGI,
 				  fc_rport_flogi_resp, rdata,
-				  2 * lport->r_a_tov))
-		fc_rport_error_retry(rdata, NULL);
-	else
-		kref_get(&rdata->kref);
+				  2 * lport->r_a_tov)) {
+		fc_rport_error_retry(rdata, -FC_EX_XMIT_ERR);
+		kref_put(&rdata->kref, fc_rport_destroy);
+	}
 }
 
 /**
  * fc_rport_recv_flogi_req() - Handle Fabric Login (FLOGI) request in p-mp mode
  * @lport: The local port that received the PLOGI request
  * @rx_fp: The PLOGI request frame
+ *
+ * Reference counting: drops kref on return
  */
 static void fc_rport_recv_flogi_req(struct fc_lport *lport,
 				    struct fc_frame *rx_fp)
@@ -799,7 +886,7 @@ static void fc_rport_recv_flogi_req(struct fc_lport *lport,
 		goto reject;
 	}
 
-	rdata = lport->tt.rport_lookup(lport, sid);
+	rdata = fc_rport_lookup(lport, sid);
 	if (!rdata) {
 		rjt_data.reason = ELS_RJT_FIP;
 		rjt_data.explan = ELS_EXPL_NOT_NEIGHBOR;
@@ -824,8 +911,7 @@ static void fc_rport_recv_flogi_req(struct fc_lport *lport,
 		 * RPORT wouldn;t have created and 'rport_lookup' would have
 		 * failed anyway in that case.
 		 */
-		if (lport->point_to_multipoint)
-			break;
+		break;
 	case RPORT_ST_DELETE:
 		mutex_unlock(&rdata->rp_mutex);
 		rjt_data.reason = ELS_RJT_FIP;
@@ -867,20 +953,27 @@ static void fc_rport_recv_flogi_req(struct fc_lport *lport,
 	fc_fill_reply_hdr(fp, rx_fp, FC_RCTL_ELS_REP, 0);
 	lport->tt.frame_send(lport, fp);
 
-	if (rdata->ids.port_name < lport->wwpn)
-		fc_rport_enter_plogi(rdata);
-	else
-		fc_rport_state_enter(rdata, RPORT_ST_PLOGI_WAIT);
+	/*
+	 * Do not proceed with the state machine if our
+	 * FLOGI has crossed with an FLOGI from the
+	 * remote port; wait for the FLOGI response instead.
+	 */
+	if (rdata->rp_state != RPORT_ST_FLOGI) {
+		if (rdata->ids.port_name < lport->wwpn)
+			fc_rport_enter_plogi(rdata);
+		else
+			fc_rport_state_enter(rdata, RPORT_ST_PLOGI_WAIT);
+	}
 out:
 	mutex_unlock(&rdata->rp_mutex);
-	kref_put(&rdata->kref, lport->tt.rport_destroy);
+	kref_put(&rdata->kref, fc_rport_destroy);
 	fc_frame_free(rx_fp);
 	return;
 
 reject_put:
-	kref_put(&rdata->kref, lport->tt.rport_destroy);
+	kref_put(&rdata->kref, fc_rport_destroy);
 reject:
-	lport->tt.seq_els_rsp_send(rx_fp, ELS_LS_RJT, &rjt_data);
+	fc_seq_els_rsp_send(rx_fp, ELS_LS_RJT, &rjt_data);
 	fc_frame_free(rx_fp);
 }
 
@@ -904,10 +997,13 @@ static void fc_rport_plogi_resp(struct fc_seq *sp, struct fc_frame *fp,
 	u16 cssp_seq;
 	u8 op;
 
-	mutex_lock(&rdata->rp_mutex);
-
 	FC_RPORT_DBG(rdata, "Received a PLOGI %s\n", fc_els_resp_type(fp));
 
+	if (fp == ERR_PTR(-FC_EX_CLOSED))
+		goto put;
+
+	mutex_lock(&rdata->rp_mutex);
+
 	if (rdata->rp_state != RPORT_ST_PLOGI) {
 		FC_RPORT_DBG(rdata, "Received a PLOGI response, but in state "
 			     "%s\n", fc_rport_state(rdata));
@@ -917,7 +1013,7 @@ static void fc_rport_plogi_resp(struct fc_seq *sp, struct fc_frame *fp,
 	}
 
 	if (IS_ERR(fp)) {
-		fc_rport_error_retry(rdata, fp);
+		fc_rport_error_retry(rdata, PTR_ERR(fp));
 		goto err;
 	}
 
@@ -939,14 +1035,20 @@ static void fc_rport_plogi_resp(struct fc_seq *sp, struct fc_frame *fp,
 		rdata->max_seq = csp_seq;
 		rdata->maxframe_size = fc_plogi_get_maxframe(plp, lport->mfs);
 		fc_rport_enter_prli(rdata);
-	} else
-		fc_rport_error_retry(rdata, fp);
+	} else {
+		struct fc_els_ls_rjt *rjt;
 
+		rjt = fc_frame_payload_get(fp, sizeof(*rjt));
+		FC_RPORT_DBG(rdata, "PLOGI ELS rejected, reason %x expl %x\n",
+			     rjt->er_reason, rjt->er_explan);
+		fc_rport_error_retry(rdata, -FC_EX_ELS_RJT);
+	}
 out:
 	fc_frame_free(fp);
 err:
 	mutex_unlock(&rdata->rp_mutex);
-	kref_put(&rdata->kref, lport->tt.rport_destroy);
+put:
+	kref_put(&rdata->kref, fc_rport_destroy);
 }
 
 static bool
@@ -969,6 +1071,8 @@ fc_rport_compatible_roles(struct fc_lport *lport, struct fc_rport_priv *rdata)
  *
  * Locking Note: The rport lock is expected to be held before calling
  * this routine.
+ *
+ * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_plogi(struct fc_rport_priv *rdata)
 {
@@ -990,17 +1094,18 @@ static void fc_rport_enter_plogi(struct fc_rport_priv *rdata)
 	fp = fc_frame_alloc(lport, sizeof(struct fc_els_flogi));
 	if (!fp) {
 		FC_RPORT_DBG(rdata, "%s frame alloc failed\n", __func__);
-		fc_rport_error_retry(rdata, fp);
+		fc_rport_error_retry(rdata, -FC_EX_ALLOC_ERR);
 		return;
 	}
 	rdata->e_d_tov = lport->e_d_tov;
 
+	kref_get(&rdata->kref);
 	if (!lport->tt.elsct_send(lport, rdata->ids.port_id, fp, ELS_PLOGI,
 				  fc_rport_plogi_resp, rdata,
-				  2 * lport->r_a_tov))
-		fc_rport_error_retry(rdata, NULL);
-	else
-		kref_get(&rdata->kref);
+				  2 * lport->r_a_tov)) {
+		fc_rport_error_retry(rdata, -FC_EX_XMIT_ERR);
+		kref_put(&rdata->kref, fc_rport_destroy);
+	}
 }
 
 /**
@@ -1022,16 +1127,20 @@ static void fc_rport_prli_resp(struct fc_seq *sp, struct fc_frame *fp,
 		struct fc_els_spp spp;
 	} *pp;
 	struct fc_els_spp temp_spp;
+	struct fc_els_ls_rjt *rjt;
 	struct fc4_prov *prov;
 	u32 roles = FC_RPORT_ROLE_UNKNOWN;
 	u32 fcp_parm = 0;
 	u8 op;
-	u8 resp_code = 0;
-
-	mutex_lock(&rdata->rp_mutex);
+	enum fc_els_spp_resp resp_code;
 
 	FC_RPORT_DBG(rdata, "Received a PRLI %s\n", fc_els_resp_type(fp));
 
+	if (fp == ERR_PTR(-FC_EX_CLOSED))
+		goto put;
+
+	mutex_lock(&rdata->rp_mutex);
+
 	if (rdata->rp_state != RPORT_ST_PRLI) {
 		FC_RPORT_DBG(rdata, "Received a PRLI response, but in state "
 			     "%s\n", fc_rport_state(rdata));
@@ -1041,7 +1150,7 @@ static void fc_rport_prli_resp(struct fc_seq *sp, struct fc_frame *fp,
 	}
 
 	if (IS_ERR(fp)) {
-		fc_rport_error_retry(rdata, fp);
+		fc_rport_error_retry(rdata, PTR_ERR(fp));
 		goto err;
 	}
 
@@ -1055,14 +1164,14 @@ static void fc_rport_prli_resp(struct fc_seq *sp, struct fc_frame *fp,
 			goto out;
 
 		resp_code = (pp->spp.spp_flags & FC_SPP_RESP_MASK);
-		FC_RPORT_DBG(rdata, "PRLI spp_flags = 0x%x\n",
-			     pp->spp.spp_flags);
+		FC_RPORT_DBG(rdata, "PRLI spp_flags = 0x%x spp_type 0x%x\n",
+			     pp->spp.spp_flags, pp->spp.spp_type);
 		rdata->spp_type = pp->spp.spp_type;
 		if (resp_code != FC_SPP_RESP_ACK) {
 			if (resp_code == FC_SPP_RESP_CONF)
-				fc_rport_error(rdata, fp);
+				fc_rport_error(rdata, -FC_EX_SEQ_ERR);
 			else
-				fc_rport_error_retry(rdata, fp);
+				fc_rport_error_retry(rdata, -FC_EX_SEQ_ERR);
 			goto out;
 		}
 		if (pp->prli.prli_spp_len < sizeof(pp->spp))
@@ -1074,13 +1183,25 @@ static void fc_rport_prli_resp(struct fc_seq *sp, struct fc_frame *fp,
 		if (fcp_parm & FCP_SPPF_CONF_COMPL)
 			rdata->flags |= FC_RP_FLAGS_CONF_REQ;
 
-		prov = fc_passive_prov[FC_TYPE_FCP];
+		/*
+		 * Call prli provider if we should act as a target
+		 */
+		prov = fc_passive_prov[rdata->spp_type];
 		if (prov) {
 			memset(&temp_spp, 0, sizeof(temp_spp));
 			prov->prli(rdata, pp->prli.prli_spp_len,
 				   &pp->spp, &temp_spp);
 		}
-
+		/*
+		 * Check if the image pair could be established
+		 */
+		if (rdata->spp_type != FC_TYPE_FCP ||
+		    !(pp->spp.spp_flags & FC_SPP_EST_IMG_PAIR)) {
+			/*
+			 * Nope; we can't use this port as a target.
+			 */
+			fcp_parm &= ~FCP_SPPF_TARG_FCN;
+		}
 		rdata->supported_classes = FC_COS_CLASS3;
 		if (fcp_parm & FCP_SPPF_INIT_FCN)
 			roles |= FC_RPORT_ROLE_FCP_INITIATOR;
@@ -1091,15 +1212,18 @@ static void fc_rport_prli_resp(struct fc_seq *sp, struct fc_frame *fp,
 		fc_rport_enter_rtv(rdata);
 
 	} else {
-		FC_RPORT_DBG(rdata, "Bad ELS response for PRLI command\n");
-		fc_rport_error_retry(rdata, fp);
+		rjt = fc_frame_payload_get(fp, sizeof(*rjt));
+		FC_RPORT_DBG(rdata, "PRLI ELS rejected, reason %x expl %x\n",
+			     rjt->er_reason, rjt->er_explan);
+		fc_rport_error_retry(rdata, FC_EX_ELS_RJT);
 	}
 
 out:
 	fc_frame_free(fp);
 err:
 	mutex_unlock(&rdata->rp_mutex);
-	kref_put(&rdata->kref, rdata->local_port->tt.rport_destroy);
+put:
+	kref_put(&rdata->kref, fc_rport_destroy);
 }
 
 /**
@@ -1108,6 +1232,8 @@ err:
  *
  * Locking Note: The rport lock is expected to be held before calling
  * this routine.
+ *
+ * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_prli(struct fc_rport_priv *rdata)
 {
@@ -1128,6 +1254,15 @@ static void fc_rport_enter_prli(struct fc_rport_priv *rdata)
 		return;
 	}
 
+	/*
+	 * And if the local port does not support the initiator function
+	 * there's no need to send a PRLI, either.
+	 */
+	if (!(lport->service_params & FCP_SPPF_INIT_FCN)) {
+		    fc_rport_enter_ready(rdata);
+		    return;
+	}
+
 	FC_RPORT_DBG(rdata, "Port entered PRLI state from %s state\n",
 		     fc_rport_state(rdata));
 
@@ -1135,7 +1270,7 @@ static void fc_rport_enter_prli(struct fc_rport_priv *rdata)
 
 	fp = fc_frame_alloc(lport, sizeof(*pp));
 	if (!fp) {
-		fc_rport_error_retry(rdata, fp);
+		fc_rport_error_retry(rdata, -FC_EX_ALLOC_ERR);
 		return;
 	}
 
@@ -1151,15 +1286,16 @@ static void fc_rport_enter_prli(struct fc_rport_priv *rdata)
 		       fc_host_port_id(lport->host), FC_TYPE_ELS,
 		       FC_FC_FIRST_SEQ | FC_FC_END_SEQ | FC_FC_SEQ_INIT, 0);
 
-	if (!lport->tt.exch_seq_send(lport, fp, fc_rport_prli_resp,
-				    NULL, rdata, 2 * lport->r_a_tov))
-		fc_rport_error_retry(rdata, NULL);
-	else
-		kref_get(&rdata->kref);
+	kref_get(&rdata->kref);
+	if (!fc_exch_seq_send(lport, fp, fc_rport_prli_resp,
+			      NULL, rdata, 2 * lport->r_a_tov)) {
+		fc_rport_error_retry(rdata, -FC_EX_XMIT_ERR);
+		kref_put(&rdata->kref, fc_rport_destroy);
+	}
 }
 
 /**
- * fc_rport_els_rtv_resp() - Handler for Request Timeout Value (RTV) responses
+ * fc_rport_rtv_resp() - Handler for Request Timeout Value (RTV) responses
  * @sp:	       The sequence the RTV was on
  * @fp:	       The RTV response frame
  * @rdata_arg: The remote port that sent the RTV response
@@ -1176,10 +1312,13 @@ static void fc_rport_rtv_resp(struct fc_seq *sp, struct fc_frame *fp,
 	struct fc_rport_priv *rdata = rdata_arg;
 	u8 op;
 
-	mutex_lock(&rdata->rp_mutex);
-
 	FC_RPORT_DBG(rdata, "Received a RTV %s\n", fc_els_resp_type(fp));
 
+	if (fp == ERR_PTR(-FC_EX_CLOSED))
+		goto put;
+
+	mutex_lock(&rdata->rp_mutex);
+
 	if (rdata->rp_state != RPORT_ST_RTV) {
 		FC_RPORT_DBG(rdata, "Received a RTV response, but in state "
 			     "%s\n", fc_rport_state(rdata));
@@ -1189,7 +1328,7 @@ static void fc_rport_rtv_resp(struct fc_seq *sp, struct fc_frame *fp,
 	}
 
 	if (IS_ERR(fp)) {
-		fc_rport_error(rdata, fp);
+		fc_rport_error(rdata, PTR_ERR(fp));
 		goto err;
 	}
 
@@ -1205,13 +1344,15 @@ static void fc_rport_rtv_resp(struct fc_seq *sp, struct fc_frame *fp,
 			tov = ntohl(rtv->rtv_r_a_tov);
 			if (tov == 0)
 				tov = 1;
-			rdata->r_a_tov = tov;
+			if (tov > rdata->r_a_tov)
+				rdata->r_a_tov = tov;
 			tov = ntohl(rtv->rtv_e_d_tov);
 			if (toq & FC_ELS_RTV_EDRES)
 				tov /= 1000000;
 			if (tov == 0)
 				tov = 1;
-			rdata->e_d_tov = tov;
+			if (tov > rdata->e_d_tov)
+				rdata->e_d_tov = tov;
 		}
 	}
 
@@ -1221,7 +1362,8 @@ out:
 	fc_frame_free(fp);
 err:
 	mutex_unlock(&rdata->rp_mutex);
-	kref_put(&rdata->kref, rdata->local_port->tt.rport_destroy);
+put:
+	kref_put(&rdata->kref, fc_rport_destroy);
 }
 
 /**
@@ -1230,6 +1372,8 @@ err:
  *
  * Locking Note: The rport lock is expected to be held before calling
  * this routine.
+ *
+ * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_rtv(struct fc_rport_priv *rdata)
 {
@@ -1243,16 +1387,52 @@ static void fc_rport_enter_rtv(struct fc_rport_priv *rdata)
 
 	fp = fc_frame_alloc(lport, sizeof(struct fc_els_rtv));
 	if (!fp) {
-		fc_rport_error_retry(rdata, fp);
+		fc_rport_error_retry(rdata, -FC_EX_ALLOC_ERR);
 		return;
 	}
 
+	kref_get(&rdata->kref);
 	if (!lport->tt.elsct_send(lport, rdata->ids.port_id, fp, ELS_RTV,
 				  fc_rport_rtv_resp, rdata,
-				  2 * lport->r_a_tov))
-		fc_rport_error_retry(rdata, NULL);
-	else
-		kref_get(&rdata->kref);
+				  2 * lport->r_a_tov)) {
+		fc_rport_error_retry(rdata, -FC_EX_XMIT_ERR);
+		kref_put(&rdata->kref, fc_rport_destroy);
+	}
+}
+
+/**
+ * fc_rport_recv_rtv_req() - Handler for Read Timeout Value (RTV) requests
+ * @rdata: The remote port that sent the RTV request
+ * @in_fp: The RTV request frame
+ *
+ * Locking Note:  Called with the lport and rport locks held.
+ */
+static void fc_rport_recv_rtv_req(struct fc_rport_priv *rdata,
+				  struct fc_frame *in_fp)
+{
+	struct fc_lport *lport = rdata->local_port;
+	struct fc_frame *fp;
+	struct fc_els_rtv_acc *rtv;
+	struct fc_seq_els_data rjt_data;
+
+	FC_RPORT_DBG(rdata, "Received RTV request\n");
+
+	fp = fc_frame_alloc(lport, sizeof(*rtv));
+	if (!fp) {
+		rjt_data.reason = ELS_RJT_UNAB;
+		rjt_data.reason = ELS_EXPL_INSUF_RES;
+		fc_seq_els_rsp_send(in_fp, ELS_LS_RJT, &rjt_data);
+		goto drop;
+	}
+	rtv = fc_frame_payload_get(fp, sizeof(*rtv));
+	rtv->rtv_cmd = ELS_LS_ACC;
+	rtv->rtv_r_a_tov = htonl(lport->r_a_tov);
+	rtv->rtv_e_d_tov = htonl(lport->e_d_tov);
+	rtv->rtv_toq = 0;
+	fc_fill_reply_hdr(fp, in_fp, FC_RCTL_ELS_REP, 0);
+	lport->tt.frame_send(lport, fp);
+drop:
+	fc_frame_free(in_fp);
 }
 
 /**
@@ -1262,15 +1442,16 @@ static void fc_rport_enter_rtv(struct fc_rport_priv *rdata)
  * @lport_arg: The local port
  */
 static void fc_rport_logo_resp(struct fc_seq *sp, struct fc_frame *fp,
-			       void *lport_arg)
+			       void *rdata_arg)
 {
-	struct fc_lport *lport = lport_arg;
+	struct fc_rport_priv *rdata = rdata_arg;
+	struct fc_lport *lport = rdata->local_port;
 
 	FC_RPORT_ID_DBG(lport, fc_seq_exch(sp)->did,
 			"Received a LOGO %s\n", fc_els_resp_type(fp));
-	if (IS_ERR(fp))
-		return;
-	fc_frame_free(fp);
+	if (!IS_ERR(fp))
+		fc_frame_free(fp);
+	kref_put(&rdata->kref, fc_rport_destroy);
 }
 
 /**
@@ -1279,6 +1460,8 @@ static void fc_rport_logo_resp(struct fc_seq *sp, struct fc_frame *fp,
  *
  * Locking Note: The rport lock is expected to be held before calling
  * this routine.
+ *
+ * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_logo(struct fc_rport_priv *rdata)
 {
@@ -1291,8 +1474,10 @@ static void fc_rport_enter_logo(struct fc_rport_priv *rdata)
 	fp = fc_frame_alloc(lport, sizeof(struct fc_els_logo));
 	if (!fp)
 		return;
-	(void)lport->tt.elsct_send(lport, rdata->ids.port_id, fp, ELS_LOGO,
-				   fc_rport_logo_resp, lport, 0);
+	kref_get(&rdata->kref);
+	if (!lport->tt.elsct_send(lport, rdata->ids.port_id, fp, ELS_LOGO,
+				  fc_rport_logo_resp, rdata, 0))
+		kref_put(&rdata->kref, fc_rport_destroy);
 }
 
 /**
@@ -1312,10 +1497,13 @@ static void fc_rport_adisc_resp(struct fc_seq *sp, struct fc_frame *fp,
 	struct fc_els_adisc *adisc;
 	u8 op;
 
-	mutex_lock(&rdata->rp_mutex);
-
 	FC_RPORT_DBG(rdata, "Received a ADISC response\n");
 
+	if (fp == ERR_PTR(-FC_EX_CLOSED))
+		goto put;
+
+	mutex_lock(&rdata->rp_mutex);
+
 	if (rdata->rp_state != RPORT_ST_ADISC) {
 		FC_RPORT_DBG(rdata, "Received a ADISC resp but in state %s\n",
 			     fc_rport_state(rdata));
@@ -1325,7 +1513,7 @@ static void fc_rport_adisc_resp(struct fc_seq *sp, struct fc_frame *fp,
 	}
 
 	if (IS_ERR(fp)) {
-		fc_rport_error(rdata, fp);
+		fc_rport_error(rdata, PTR_ERR(fp));
 		goto err;
 	}
 
@@ -1350,7 +1538,8 @@ out:
 	fc_frame_free(fp);
 err:
 	mutex_unlock(&rdata->rp_mutex);
-	kref_put(&rdata->kref, rdata->local_port->tt.rport_destroy);
+put:
+	kref_put(&rdata->kref, fc_rport_destroy);
 }
 
 /**
@@ -1359,6 +1548,8 @@ err:
  *
  * Locking Note: The rport lock is expected to be held before calling
  * this routine.
+ *
+ * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_adisc(struct fc_rport_priv *rdata)
 {
@@ -1372,15 +1563,16 @@ static void fc_rport_enter_adisc(struct fc_rport_priv *rdata)
 
 	fp = fc_frame_alloc(lport, sizeof(struct fc_els_adisc));
 	if (!fp) {
-		fc_rport_error_retry(rdata, fp);
+		fc_rport_error_retry(rdata, -FC_EX_ALLOC_ERR);
 		return;
 	}
+	kref_get(&rdata->kref);
 	if (!lport->tt.elsct_send(lport, rdata->ids.port_id, fp, ELS_ADISC,
 				  fc_rport_adisc_resp, rdata,
-				  2 * lport->r_a_tov))
-		fc_rport_error_retry(rdata, NULL);
-	else
-		kref_get(&rdata->kref);
+				  2 * lport->r_a_tov)) {
+		fc_rport_error_retry(rdata, -FC_EX_XMIT_ERR);
+		kref_put(&rdata->kref, fc_rport_destroy);
+	}
 }
 
 /**
@@ -1404,7 +1596,7 @@ static void fc_rport_recv_adisc_req(struct fc_rport_priv *rdata,
 	if (!adisc) {
 		rjt_data.reason = ELS_RJT_PROT;
 		rjt_data.explan = ELS_EXPL_INV_LEN;
-		lport->tt.seq_els_rsp_send(in_fp, ELS_LS_RJT, &rjt_data);
+		fc_seq_els_rsp_send(in_fp, ELS_LS_RJT, &rjt_data);
 		goto drop;
 	}
 
@@ -1480,7 +1672,7 @@ static void fc_rport_recv_rls_req(struct fc_rport_priv *rdata,
 	goto out;
 
 out_rjt:
-	lport->tt.seq_els_rsp_send(rx_fp, ELS_LS_RJT, &rjt_data);
+	fc_seq_els_rsp_send(rx_fp, ELS_LS_RJT, &rjt_data);
 out:
 	fc_frame_free(rx_fp);
 }
@@ -1494,15 +1686,21 @@ out:
  * The ELS opcode has already been validated by the caller.
  *
  * Locking Note: Called with the lport lock held.
+ *
+ * Reference counting: does not modify kref
  */
 static void fc_rport_recv_els_req(struct fc_lport *lport, struct fc_frame *fp)
 {
 	struct fc_rport_priv *rdata;
 	struct fc_seq_els_data els_data;
 
-	rdata = lport->tt.rport_lookup(lport, fc_frame_sid(fp));
-	if (!rdata)
+	rdata = fc_rport_lookup(lport, fc_frame_sid(fp));
+	if (!rdata) {
+		FC_RPORT_ID_DBG(lport, fc_frame_sid(fp),
+				"Received ELS 0x%02x from non-logged-in port\n",
+				fc_frame_payload_op(fp));
 		goto reject;
+	}
 
 	mutex_lock(&rdata->rp_mutex);
 
@@ -1512,9 +1710,21 @@ static void fc_rport_recv_els_req(struct fc_lport *lport, struct fc_frame *fp)
 	case RPORT_ST_READY:
 	case RPORT_ST_ADISC:
 		break;
+	case RPORT_ST_PLOGI:
+		if (fc_frame_payload_op(fp) == ELS_PRLI) {
+			FC_RPORT_DBG(rdata, "Reject ELS PRLI "
+				     "while in state %s\n",
+				     fc_rport_state(rdata));
+			mutex_unlock(&rdata->rp_mutex);
+			kref_put(&rdata->kref, fc_rport_destroy);
+			goto busy;
+		}
 	default:
+		FC_RPORT_DBG(rdata,
+			     "Reject ELS 0x%02x while in state %s\n",
+			     fc_frame_payload_op(fp), fc_rport_state(rdata));
 		mutex_unlock(&rdata->rp_mutex);
-		kref_put(&rdata->kref, lport->tt.rport_destroy);
+		kref_put(&rdata->kref, fc_rport_destroy);
 		goto reject;
 	}
 
@@ -1529,30 +1739,41 @@ static void fc_rport_recv_els_req(struct fc_lport *lport, struct fc_frame *fp)
 		fc_rport_recv_adisc_req(rdata, fp);
 		break;
 	case ELS_RRQ:
-		lport->tt.seq_els_rsp_send(fp, ELS_RRQ, NULL);
+		fc_seq_els_rsp_send(fp, ELS_RRQ, NULL);
 		fc_frame_free(fp);
 		break;
 	case ELS_REC:
-		lport->tt.seq_els_rsp_send(fp, ELS_REC, NULL);
+		fc_seq_els_rsp_send(fp, ELS_REC, NULL);
 		fc_frame_free(fp);
 		break;
 	case ELS_RLS:
 		fc_rport_recv_rls_req(rdata, fp);
 		break;
+	case ELS_RTV:
+		fc_rport_recv_rtv_req(rdata, fp);
+		break;
 	default:
 		fc_frame_free(fp);	/* can't happen */
 		break;
 	}
 
 	mutex_unlock(&rdata->rp_mutex);
-	kref_put(&rdata->kref, rdata->local_port->tt.rport_destroy);
+	kref_put(&rdata->kref, fc_rport_destroy);
 	return;
 
 reject:
 	els_data.reason = ELS_RJT_UNAB;
 	els_data.explan = ELS_EXPL_PLOGI_REQD;
-	lport->tt.seq_els_rsp_send(fp, ELS_LS_RJT, &els_data);
+	fc_seq_els_rsp_send(fp, ELS_LS_RJT, &els_data);
+	fc_frame_free(fp);
+	return;
+
+busy:
+	els_data.reason = ELS_RJT_BUSY;
+	els_data.explan = ELS_EXPL_NONE;
+	fc_seq_els_rsp_send(fp, ELS_LS_RJT, &els_data);
 	fc_frame_free(fp);
+	return;
 }
 
 /**
@@ -1561,8 +1782,10 @@ reject:
  * @fp:	   The request frame
  *
  * Locking Note: Called with the lport lock held.
+ *
+ * Reference counting: does not modify kref
  */
-static void fc_rport_recv_req(struct fc_lport *lport, struct fc_frame *fp)
+void fc_rport_recv_req(struct fc_lport *lport, struct fc_frame *fp)
 {
 	struct fc_seq_els_data els_data;
 
@@ -1588,16 +1811,18 @@ static void fc_rport_recv_req(struct fc_lport *lport, struct fc_frame *fp)
 	case ELS_RRQ:
 	case ELS_REC:
 	case ELS_RLS:
+	case ELS_RTV:
 		fc_rport_recv_els_req(lport, fp);
 		break;
 	default:
 		els_data.reason = ELS_RJT_UNSUP;
 		els_data.explan = ELS_EXPL_NONE;
-		lport->tt.seq_els_rsp_send(fp, ELS_LS_RJT, &els_data);
+		fc_seq_els_rsp_send(fp, ELS_LS_RJT, &els_data);
 		fc_frame_free(fp);
 		break;
 	}
 }
+EXPORT_SYMBOL(fc_rport_recv_req);
 
 /**
  * fc_rport_recv_plogi_req() - Handler for Port Login (PLOGI) requests
@@ -1605,6 +1830,8 @@ static void fc_rport_recv_req(struct fc_lport *lport, struct fc_frame *fp)
  * @rx_fp: The PLOGI request frame
  *
  * Locking Note: The rport lock is held before calling this function.
+ *
+ * Reference counting: increments kref on return
  */
 static void fc_rport_recv_plogi_req(struct fc_lport *lport,
 				    struct fc_frame *rx_fp)
@@ -1630,7 +1857,7 @@ static void fc_rport_recv_plogi_req(struct fc_lport *lport,
 
 	disc = &lport->disc;
 	mutex_lock(&disc->disc_mutex);
-	rdata = lport->tt.rport_create(lport, sid);
+	rdata = fc_rport_create(lport, sid);
 	if (!rdata) {
 		mutex_unlock(&disc->disc_mutex);
 		rjt_data.reason = ELS_RJT_UNAB;
@@ -1718,7 +1945,7 @@ out:
 	return;
 
 reject:
-	lport->tt.seq_els_rsp_send(fp, ELS_LS_RJT, &rjt_data);
+	fc_seq_els_rsp_send(fp, ELS_LS_RJT, &rjt_data);
 	fc_frame_free(fp);
 }
 
@@ -1744,7 +1971,6 @@ static void fc_rport_recv_prli_req(struct fc_rport_priv *rdata,
 	unsigned int len;
 	unsigned int plen;
 	enum fc_els_spp_resp resp;
-	enum fc_els_spp_resp passive;
 	struct fc_seq_els_data rjt_data;
 	struct fc4_prov *prov;
 
@@ -1794,15 +2020,21 @@ static void fc_rport_recv_prli_req(struct fc_rport_priv *rdata,
 		resp = 0;
 
 		if (rspp->spp_type < FC_FC4_PROV_SIZE) {
+			enum fc_els_spp_resp active = 0, passive = 0;
+
 			prov = fc_active_prov[rspp->spp_type];
 			if (prov)
-				resp = prov->prli(rdata, plen, rspp, spp);
+				active = prov->prli(rdata, plen, rspp, spp);
 			prov = fc_passive_prov[rspp->spp_type];
-			if (prov) {
+			if (prov)
 				passive = prov->prli(rdata, plen, rspp, spp);
-				if (!resp || passive == FC_SPP_RESP_ACK)
-					resp = passive;
-			}
+			if (!active || passive == FC_SPP_RESP_ACK)
+				resp = passive;
+			else
+				resp = active;
+			FC_RPORT_DBG(rdata, "PRLI rspp type %x "
+				     "active %x passive %x\n",
+				     rspp->spp_type, active, passive);
 		}
 		if (!resp) {
 			if (spp->spp_flags & FC_SPP_EST_IMG_PAIR)
@@ -1823,20 +2055,13 @@ static void fc_rport_recv_prli_req(struct fc_rport_priv *rdata,
 	fc_fill_reply_hdr(fp, rx_fp, FC_RCTL_ELS_REP, 0);
 	lport->tt.frame_send(lport, fp);
 
-	switch (rdata->rp_state) {
-	case RPORT_ST_PRLI:
-		fc_rport_enter_ready(rdata);
-		break;
-	default:
-		break;
-	}
 	goto drop;
 
 reject_len:
 	rjt_data.reason = ELS_RJT_PROT;
 	rjt_data.explan = ELS_EXPL_INV_LEN;
 reject:
-	lport->tt.seq_els_rsp_send(rx_fp, ELS_LS_RJT, &rjt_data);
+	fc_seq_els_rsp_send(rx_fp, ELS_LS_RJT, &rjt_data);
 drop:
 	fc_frame_free(rx_fp);
 }
@@ -1907,7 +2132,7 @@ reject_len:
 	rjt_data.reason = ELS_RJT_PROT;
 	rjt_data.explan = ELS_EXPL_INV_LEN;
 reject:
-	lport->tt.seq_els_rsp_send(rx_fp, ELS_LS_RJT, &rjt_data);
+	fc_seq_els_rsp_send(rx_fp, ELS_LS_RJT, &rjt_data);
 drop:
 	fc_frame_free(rx_fp);
 }
@@ -1919,17 +2144,19 @@ drop:
  *
  * Locking Note: The rport lock is expected to be held before calling
  * this function.
+ *
+ * Reference counting: drops kref on return
  */
 static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
 {
 	struct fc_rport_priv *rdata;
 	u32 sid;
 
-	lport->tt.seq_els_rsp_send(fp, ELS_LS_ACC, NULL);
+	fc_seq_els_rsp_send(fp, ELS_LS_ACC, NULL);
 
 	sid = fc_frame_sid(fp);
 
-	rdata = lport->tt.rport_lookup(lport, sid);
+	rdata = fc_rport_lookup(lport, sid);
 	if (rdata) {
 		mutex_lock(&rdata->rp_mutex);
 		FC_RPORT_DBG(rdata, "Received LOGO request while in state %s\n",
@@ -1937,7 +2164,7 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
 
 		fc_rport_enter_delete(rdata, RPORT_EV_STOP);
 		mutex_unlock(&rdata->rp_mutex);
-		kref_put(&rdata->kref, rdata->local_port->tt.rport_destroy);
+		kref_put(&rdata->kref, fc_rport_destroy);
 	} else
 		FC_RPORT_ID_DBG(lport, sid,
 				"Received LOGO from non-logged-in port\n");
@@ -1947,41 +2174,11 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
 /**
  * fc_rport_flush_queue() - Flush the rport_event_queue
  */
-static void fc_rport_flush_queue(void)
+void fc_rport_flush_queue(void)
 {
 	flush_workqueue(rport_event_queue);
 }
-
-/**
- * fc_rport_init() - Initialize the remote port layer for a local port
- * @lport: The local port to initialize the remote port layer for
- */
-int fc_rport_init(struct fc_lport *lport)
-{
-	if (!lport->tt.rport_lookup)
-		lport->tt.rport_lookup = fc_rport_lookup;
-
-	if (!lport->tt.rport_create)
-		lport->tt.rport_create = fc_rport_create;
-
-	if (!lport->tt.rport_login)
-		lport->tt.rport_login = fc_rport_login;
-
-	if (!lport->tt.rport_logoff)
-		lport->tt.rport_logoff = fc_rport_logoff;
-
-	if (!lport->tt.rport_recv_req)
-		lport->tt.rport_recv_req = fc_rport_recv_req;
-
-	if (!lport->tt.rport_flush_queue)
-		lport->tt.rport_flush_queue = fc_rport_flush_queue;
-
-	if (!lport->tt.rport_destroy)
-		lport->tt.rport_destroy = fc_rport_destroy;
-
-	return 0;
-}
-EXPORT_SYMBOL(fc_rport_init);
+EXPORT_SYMBOL(fc_rport_flush_queue);
 
 /**
  * fc_rport_fcp_prli() - Handle incoming PRLI for the FCP initiator.
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index b484859464f6..8a20b4e86224 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -648,6 +648,10 @@ struct lpfc_hba {
 #define HBA_FCP_IOQ_FLUSH	0x8000 /* FCP I/O queues being flushed */
 #define HBA_FW_DUMP_OP		0x10000 /* Skips fn reset before FW dump */
 #define HBA_RECOVERABLE_UE	0x20000 /* Firmware supports recoverable UE */
+#define HBA_FORCED_LINK_SPEED	0x40000 /*
+					 * Firmware supports Forced Link Speed
+					 * capability
+					 */
 	uint32_t fcp_ring_in_use; /* When polling test if intr-hndlr active*/
 	struct lpfc_dmabuf slim2p;
 
@@ -746,6 +750,8 @@ struct lpfc_hba {
 	uint32_t cfg_oas_priority;
 	uint32_t cfg_XLanePriority;
 	uint32_t cfg_enable_bg;
+	uint32_t cfg_prot_mask;
+	uint32_t cfg_prot_guard;
 	uint32_t cfg_hostmem_hgp;
 	uint32_t cfg_log_verbose;
 	uint32_t cfg_aer_support;
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index f1019908800e..c84775562c65 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -2759,18 +2759,14 @@ LPFC_ATTR_R(enable_npiv, 1, 0, 1,
 LPFC_ATTR_R(fcf_failover_policy, 1, 1, 2,
 	"FCF Fast failover=1 Priority failover=2");
 
-int lpfc_enable_rrq = 2;
-module_param(lpfc_enable_rrq, int, S_IRUGO);
-MODULE_PARM_DESC(lpfc_enable_rrq, "Enable RRQ functionality");
-lpfc_param_show(enable_rrq);
 /*
 # lpfc_enable_rrq: Track XRI/OXID reuse after IO failures
 #	0x0 = disabled, XRI/OXID use not tracked.
 #	0x1 = XRI/OXID reuse is timed with ratov, RRQ sent.
 #	0x2 = XRI/OXID reuse is timed with ratov, No RRQ sent.
 */
-lpfc_param_init(enable_rrq, 2, 0, 2);
-static DEVICE_ATTR(lpfc_enable_rrq, S_IRUGO, lpfc_enable_rrq_show, NULL);
+LPFC_ATTR_R(enable_rrq, 2, 0, 2,
+	"Enable RRQ functionality");
 
 /*
 # lpfc_suppress_link_up:  Bring link up at initialization
@@ -2827,14 +2823,8 @@ lpfc_txcmplq_hw_show(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(txcmplq_hw, S_IRUGO,
 			 lpfc_txcmplq_hw_show, NULL);
 
-int lpfc_iocb_cnt = 2;
-module_param(lpfc_iocb_cnt, int, S_IRUGO);
-MODULE_PARM_DESC(lpfc_iocb_cnt,
+LPFC_ATTR_R(iocb_cnt, 2, 1, 5,
 	"Number of IOCBs alloc for ELS, CT, and ABTS: 1k to 5k IOCBs");
-lpfc_param_show(iocb_cnt);
-lpfc_param_init(iocb_cnt, 2, 1, 5);
-static DEVICE_ATTR(lpfc_iocb_cnt, S_IRUGO,
-			 lpfc_iocb_cnt_show, NULL);
 
 /*
 # lpfc_nodev_tmo: If set, it will hold all I/O errors on devices that disappear
@@ -2887,9 +2877,9 @@ lpfc_nodev_tmo_init(struct lpfc_vport *vport, int val)
 		vport->cfg_nodev_tmo = vport->cfg_devloss_tmo;
 		if (val != LPFC_DEF_DEVLOSS_TMO)
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
-					 "0407 Ignoring nodev_tmo module "
-					 "parameter because devloss_tmo is "
-					 "set.\n");
+					 "0407 Ignoring lpfc_nodev_tmo module "
+					 "parameter because lpfc_devloss_tmo "
+					 "is set.\n");
 		return 0;
 	}
 
@@ -2948,8 +2938,8 @@ lpfc_nodev_tmo_set(struct lpfc_vport *vport, int val)
 	if (vport->dev_loss_tmo_changed ||
 	    (lpfc_devloss_tmo != LPFC_DEF_DEVLOSS_TMO)) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
-				 "0401 Ignoring change to nodev_tmo "
-				 "because devloss_tmo is set.\n");
+				 "0401 Ignoring change to lpfc_nodev_tmo "
+				 "because lpfc_devloss_tmo is set.\n");
 		return 0;
 	}
 	if (val >= LPFC_MIN_DEVLOSS_TMO && val <= LPFC_MAX_DEVLOSS_TMO) {
@@ -2964,7 +2954,7 @@ lpfc_nodev_tmo_set(struct lpfc_vport *vport, int val)
 		return 0;
 	}
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
-			 "0403 lpfc_nodev_tmo attribute cannot be set to"
+			 "0403 lpfc_nodev_tmo attribute cannot be set to "
 			 "%d, allowed range is [%d, %d]\n",
 			 val, LPFC_MIN_DEVLOSS_TMO, LPFC_MAX_DEVLOSS_TMO);
 	return -EINVAL;
@@ -3015,8 +3005,8 @@ lpfc_devloss_tmo_set(struct lpfc_vport *vport, int val)
 	}
 
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
-			 "0404 lpfc_devloss_tmo attribute cannot be set to"
-			 " %d, allowed range is [%d, %d]\n",
+			 "0404 lpfc_devloss_tmo attribute cannot be set to "
+			 "%d, allowed range is [%d, %d]\n",
 			 val, LPFC_MIN_DEVLOSS_TMO, LPFC_MAX_DEVLOSS_TMO);
 	return -EINVAL;
 }
@@ -3204,6 +3194,8 @@ LPFC_VPORT_ATTR_R(scan_down, 1, 0, 1,
 # Set loop mode if you want to run as an NL_Port. Value range is [0,0x6].
 # Default value is 0.
 */
+LPFC_ATTR(topology, 0, 0, 6,
+	"Select Fibre Channel topology");
 
 /**
  * lpfc_topology_set - Set the adapters topology field
@@ -3281,11 +3273,8 @@ lpfc_topology_store(struct device *dev, struct device_attribute *attr,
 		phba->brd_no, val);
 	return -EINVAL;
 }
-static int lpfc_topology = 0;
-module_param(lpfc_topology, int, S_IRUGO);
-MODULE_PARM_DESC(lpfc_topology, "Select Fibre Channel topology");
+
 lpfc_param_show(topology)
-lpfc_param_init(topology, 0, 0, 6)
 static DEVICE_ATTR(lpfc_topology, S_IRUGO | S_IWUSR,
 		lpfc_topology_show, lpfc_topology_store);
 
@@ -3679,7 +3668,12 @@ lpfc_link_speed_store(struct device *dev, struct device_attribute *attr,
 	int nolip = 0;
 	const char *val_buf = buf;
 	int err;
-	uint32_t prev_val;
+	uint32_t prev_val, if_type;
+
+	if_type = bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf);
+	if (if_type == LPFC_SLI_INTF_IF_TYPE_2 &&
+	    phba->hba_flag & HBA_FORCED_LINK_SPEED)
+		return -EPERM;
 
 	if (!strncmp(buf, "nolip ", strlen("nolip "))) {
 		nolip = 1;
@@ -3789,6 +3783,9 @@ static DEVICE_ATTR(lpfc_link_speed, S_IRUGO | S_IWUSR,
 #       1  = aer supported and enabled (default)
 # Value range is [0,1]. Default value is 1.
 */
+LPFC_ATTR(aer_support, 1, 0, 1,
+	"Enable PCIe device AER support");
+lpfc_param_show(aer_support)
 
 /**
  * lpfc_aer_support_store - Set the adapter for aer support
@@ -3871,46 +3868,6 @@ lpfc_aer_support_store(struct device *dev, struct device_attribute *attr,
 	return rc;
 }
 
-static int lpfc_aer_support = 1;
-module_param(lpfc_aer_support, int, S_IRUGO);
-MODULE_PARM_DESC(lpfc_aer_support, "Enable PCIe device AER support");
-lpfc_param_show(aer_support)
-
-/**
- * lpfc_aer_support_init - Set the initial adapters aer support flag
- * @phba: lpfc_hba pointer.
- * @val: enable aer or disable aer flag.
- *
- * Description:
- * If val is in a valid range [0,1], then set the adapter's initial
- * cfg_aer_support field. It will be up to the driver's probe_one
- * routine to determine whether the device's AER support can be set
- * or not.
- *
- * Notes:
- * If the value is not in range log a kernel error message, and
- * choose the default value of setting AER support and return.
- *
- * Returns:
- * zero if val saved.
- * -EINVAL val out of range
- **/
-static int
-lpfc_aer_support_init(struct lpfc_hba *phba, int val)
-{
-	if (val == 0 || val == 1) {
-		phba->cfg_aer_support = val;
-		return 0;
-	}
-	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-			"2712 lpfc_aer_support attribute value %d out "
-			"of range, allowed values are 0|1, setting it "
-			"to default value of 1\n", val);
-	/* By default, try to enable AER on a device */
-	phba->cfg_aer_support = 1;
-	return -EINVAL;
-}
-
 static DEVICE_ATTR(lpfc_aer_support, S_IRUGO | S_IWUSR,
 		   lpfc_aer_support_show, lpfc_aer_support_store);
 
@@ -4055,39 +4012,10 @@ lpfc_sriov_nr_virtfn_store(struct device *dev, struct device_attribute *attr,
 	return rc;
 }
 
-static int lpfc_sriov_nr_virtfn = LPFC_DEF_VFN_PER_PFN;
-module_param(lpfc_sriov_nr_virtfn, int, S_IRUGO|S_IWUSR);
-MODULE_PARM_DESC(lpfc_sriov_nr_virtfn, "Enable PCIe device SR-IOV virtual fn");
-lpfc_param_show(sriov_nr_virtfn)
-
-/**
- * lpfc_sriov_nr_virtfn_init - Set the initial sr-iov virtual function enable
- * @phba: lpfc_hba pointer.
- * @val: link speed value.
- *
- * Description:
- * If val is in a valid range [0,255], then set the adapter's initial
- * cfg_sriov_nr_virtfn field. If it's greater than the maximum, the maximum
- * number shall be used instead. It will be up to the driver's probe_one
- * routine to determine whether the device's SR-IOV is supported or not.
- *
- * Returns:
- * zero if val saved.
- * -EINVAL val out of range
- **/
-static int
-lpfc_sriov_nr_virtfn_init(struct lpfc_hba *phba, int val)
-{
-	if (val >= 0 && val <= LPFC_MAX_VFN_PER_PFN) {
-		phba->cfg_sriov_nr_virtfn = val;
-		return 0;
-	}
+LPFC_ATTR(sriov_nr_virtfn, LPFC_DEF_VFN_PER_PFN, 0, LPFC_MAX_VFN_PER_PFN,
+	"Enable PCIe device SR-IOV virtual fn");
 
-	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-			"3017 Enabling %d virtual functions is not "
-			"allowed.\n", val);
-	return -EINVAL;
-}
+lpfc_param_show(sriov_nr_virtfn)
 static DEVICE_ATTR(lpfc_sriov_nr_virtfn, S_IRUGO | S_IWUSR,
 		   lpfc_sriov_nr_virtfn_show, lpfc_sriov_nr_virtfn_store);
 
@@ -4251,7 +4179,8 @@ lpfc_fcp_imax_init(struct lpfc_hba *phba, int val)
 	}
 
 	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-			"3016 fcp_imax: %d out of range, using default\n", val);
+			"3016 lpfc_fcp_imax: %d out of range, using default\n",
+			val);
 	phba->cfg_fcp_imax = LPFC_DEF_IMAX;
 
 	return 0;
@@ -4401,8 +4330,8 @@ lpfc_fcp_cpu_map_init(struct lpfc_hba *phba, int val)
 	}
 
 	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-			"3326 fcp_cpu_map: %d out of range, using default\n",
-			val);
+			"3326 lpfc_fcp_cpu_map: %d out of range, using "
+			"default\n", val);
 	phba->cfg_fcp_cpu_map = LPFC_DRIVER_CPU_MAP;
 
 	return 0;
@@ -4441,12 +4370,10 @@ LPFC_VPORT_ATTR_RW(first_burst_size, 0, 0, 65536,
 # to limit the I/O completion time to the parameter value.
 # The value is set in milliseconds.
 */
-static int lpfc_max_scsicmpl_time;
-module_param(lpfc_max_scsicmpl_time, int, S_IRUGO);
-MODULE_PARM_DESC(lpfc_max_scsicmpl_time,
+LPFC_VPORT_ATTR(max_scsicmpl_time, 0, 0, 60000,
 	"Use command completion time to control queue depth");
+
 lpfc_vport_param_show(max_scsicmpl_time);
-lpfc_vport_param_init(max_scsicmpl_time, 0, 0, 60000);
 static int
 lpfc_max_scsicmpl_time_set(struct lpfc_vport *vport, int val)
 {
@@ -4691,12 +4618,15 @@ unsigned int lpfc_fcp_look_ahead = LPFC_LOOK_AHEAD_OFF;
 #		HBA supports DIX Type 1: Host to HBA  Type 1 protection
 #
 */
-unsigned int lpfc_prot_mask = SHOST_DIF_TYPE1_PROTECTION |
-			      SHOST_DIX_TYPE0_PROTECTION |
-			      SHOST_DIX_TYPE1_PROTECTION;
-
-module_param(lpfc_prot_mask, uint, S_IRUGO);
-MODULE_PARM_DESC(lpfc_prot_mask, "host protection mask");
+LPFC_ATTR(prot_mask,
+	(SHOST_DIF_TYPE1_PROTECTION |
+	SHOST_DIX_TYPE0_PROTECTION |
+	SHOST_DIX_TYPE1_PROTECTION),
+	0,
+	(SHOST_DIF_TYPE1_PROTECTION |
+	SHOST_DIX_TYPE0_PROTECTION |
+	SHOST_DIX_TYPE1_PROTECTION),
+	"T10-DIF host protection capabilities mask");
 
 /*
 # lpfc_prot_guard: i
@@ -4706,9 +4636,9 @@ MODULE_PARM_DESC(lpfc_prot_mask, "host protection mask");
 #	- Default will result in registering capabilities for all guard types
 #
 */
-unsigned char lpfc_prot_guard = SHOST_DIX_GUARD_IP;
-module_param(lpfc_prot_guard, byte, S_IRUGO);
-MODULE_PARM_DESC(lpfc_prot_guard, "host protection guard type");
+LPFC_ATTR(prot_guard,
+	SHOST_DIX_GUARD_IP, SHOST_DIX_GUARD_CRC, SHOST_DIX_GUARD_IP,
+	"T10-DIF host protection guard type");
 
 /*
  * Delay initial NPort discovery when Clean Address bit is cleared in
@@ -5828,6 +5758,8 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	phba->cfg_oas_flags = 0;
 	phba->cfg_oas_priority = 0;
 	lpfc_enable_bg_init(phba, lpfc_enable_bg);
+	lpfc_prot_mask_init(phba, lpfc_prot_mask);
+	lpfc_prot_guard_init(phba, lpfc_prot_guard);
 	if (phba->sli_rev == LPFC_SLI_REV4)
 		phba->cfg_poll = 0;
 	else
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index 05dcc2abd541..7dca4d6a8883 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/list.h>
+#include <linux/bsg-lib.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_host.h>
@@ -97,7 +98,7 @@ struct lpfc_bsg_menlo {
 #define TYPE_MENLO	4
 struct bsg_job_data {
 	uint32_t type;
-	struct fc_bsg_job *set_job; /* job waiting for this iocb to finish */
+	struct bsg_job *set_job; /* job waiting for this iocb to finish */
 	union {
 		struct lpfc_bsg_event *evt;
 		struct lpfc_bsg_iocb iocb;
@@ -211,7 +212,7 @@ lpfc_alloc_bsg_buffers(struct lpfc_hba *phba, unsigned int size,
 
 static unsigned int
 lpfc_bsg_copy_data(struct lpfc_dmabuf *dma_buffers,
-		   struct fc_bsg_buffer *bsg_buffers,
+		   struct bsg_buffer *bsg_buffers,
 		   unsigned int bytes_to_transfer, int to_buffers)
 {
 
@@ -297,7 +298,8 @@ lpfc_bsg_send_mgmt_cmd_cmp(struct lpfc_hba *phba,
 			struct lpfc_iocbq *rspiocbq)
 {
 	struct bsg_job_data *dd_data;
-	struct fc_bsg_job *job;
+	struct bsg_job *job;
+	struct fc_bsg_reply *bsg_reply;
 	IOCB_t *rsp;
 	struct lpfc_dmabuf *bmp, *cmp, *rmp;
 	struct lpfc_nodelist *ndlp;
@@ -312,6 +314,7 @@ lpfc_bsg_send_mgmt_cmd_cmp(struct lpfc_hba *phba,
 	spin_lock_irqsave(&phba->ct_ev_lock, flags);
 	job = dd_data->set_job;
 	if (job) {
+		bsg_reply = job->reply;
 		/* Prevent timeout handling from trying to abort job */
 		job->dd_data = NULL;
 	}
@@ -350,7 +353,7 @@ lpfc_bsg_send_mgmt_cmd_cmp(struct lpfc_hba *phba,
 			}
 		} else {
 			rsp_size = rsp->un.genreq64.bdl.bdeSize;
-			job->reply->reply_payload_rcv_len =
+			bsg_reply->reply_payload_rcv_len =
 				lpfc_bsg_copy_data(rmp, &job->reply_payload,
 						   rsp_size, 0);
 		}
@@ -367,8 +370,9 @@ lpfc_bsg_send_mgmt_cmd_cmp(struct lpfc_hba *phba,
 	/* Complete the job if the job is still active */
 
 	if (job) {
-		job->reply->result = rc;
-		job->job_done(job);
+		bsg_reply->result = rc;
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	}
 	return;
 }
@@ -378,12 +382,13 @@ lpfc_bsg_send_mgmt_cmd_cmp(struct lpfc_hba *phba,
  * @job: fc_bsg_job to handle
  **/
 static int
-lpfc_bsg_send_mgmt_cmd(struct fc_bsg_job *job)
+lpfc_bsg_send_mgmt_cmd(struct bsg_job *job)
 {
-	struct lpfc_vport *vport = (struct lpfc_vport *)job->shost->hostdata;
+	struct lpfc_vport *vport = shost_priv(fc_bsg_to_shost(job));
 	struct lpfc_hba *phba = vport->phba;
-	struct lpfc_rport_data *rdata = job->rport->dd_data;
+	struct lpfc_rport_data *rdata = fc_bsg_to_rport(job)->dd_data;
 	struct lpfc_nodelist *ndlp = rdata->pnode;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct ulp_bde64 *bpl = NULL;
 	uint32_t timeout;
 	struct lpfc_iocbq *cmdiocbq = NULL;
@@ -398,7 +403,7 @@ lpfc_bsg_send_mgmt_cmd(struct fc_bsg_job *job)
 	int iocb_stat;
 
 	/* in case no data is transferred */
-	job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 
 	/* allocate our bsg tracking structure */
 	dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL);
@@ -542,7 +547,7 @@ no_ndlp:
 	kfree(dd_data);
 no_dd_data:
 	/* make error code available to userspace */
-	job->reply->result = rc;
+	bsg_reply->result = rc;
 	job->dd_data = NULL;
 	return rc;
 }
@@ -570,7 +575,8 @@ lpfc_bsg_rport_els_cmp(struct lpfc_hba *phba,
 			struct lpfc_iocbq *rspiocbq)
 {
 	struct bsg_job_data *dd_data;
-	struct fc_bsg_job *job;
+	struct bsg_job *job;
+	struct fc_bsg_reply *bsg_reply;
 	IOCB_t *rsp;
 	struct lpfc_nodelist *ndlp;
 	struct lpfc_dmabuf *pcmd = NULL, *prsp = NULL;
@@ -588,6 +594,7 @@ lpfc_bsg_rport_els_cmp(struct lpfc_hba *phba,
 	spin_lock_irqsave(&phba->ct_ev_lock, flags);
 	job = dd_data->set_job;
 	if (job) {
+		bsg_reply = job->reply;
 		/* Prevent timeout handling from trying to abort job  */
 		job->dd_data = NULL;
 	}
@@ -609,17 +616,17 @@ lpfc_bsg_rport_els_cmp(struct lpfc_hba *phba,
 	if (job) {
 		if (rsp->ulpStatus == IOSTAT_SUCCESS) {
 			rsp_size = rsp->un.elsreq64.bdl.bdeSize;
-			job->reply->reply_payload_rcv_len =
+			bsg_reply->reply_payload_rcv_len =
 				sg_copy_from_buffer(job->reply_payload.sg_list,
 						    job->reply_payload.sg_cnt,
 						    prsp->virt,
 						    rsp_size);
 		} else if (rsp->ulpStatus == IOSTAT_LS_RJT) {
-			job->reply->reply_payload_rcv_len =
+			bsg_reply->reply_payload_rcv_len =
 				sizeof(struct fc_bsg_ctels_reply);
 			/* LS_RJT data returned in word 4 */
 			rjt_data = (uint8_t *)&rsp->un.ulpWord[4];
-			els_reply = &job->reply->reply_data.ctels_reply;
+			els_reply = &bsg_reply->reply_data.ctels_reply;
 			els_reply->status = FC_CTELS_STATUS_REJECT;
 			els_reply->rjt_data.action = rjt_data[3];
 			els_reply->rjt_data.reason_code = rjt_data[2];
@@ -637,8 +644,9 @@ lpfc_bsg_rport_els_cmp(struct lpfc_hba *phba,
 	/* Complete the job if the job is still active */
 
 	if (job) {
-		job->reply->result = rc;
-		job->job_done(job);
+		bsg_reply->result = rc;
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	}
 	return;
 }
@@ -648,12 +656,14 @@ lpfc_bsg_rport_els_cmp(struct lpfc_hba *phba,
  * @job: fc_bsg_job to handle
  **/
 static int
-lpfc_bsg_rport_els(struct fc_bsg_job *job)
+lpfc_bsg_rport_els(struct bsg_job *job)
 {
-	struct lpfc_vport *vport = (struct lpfc_vport *)job->shost->hostdata;
+	struct lpfc_vport *vport = shost_priv(fc_bsg_to_shost(job));
 	struct lpfc_hba *phba = vport->phba;
-	struct lpfc_rport_data *rdata = job->rport->dd_data;
+	struct lpfc_rport_data *rdata = fc_bsg_to_rport(job)->dd_data;
 	struct lpfc_nodelist *ndlp = rdata->pnode;
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	uint32_t elscmd;
 	uint32_t cmdsize;
 	struct lpfc_iocbq *cmdiocbq;
@@ -664,7 +674,7 @@ lpfc_bsg_rport_els(struct fc_bsg_job *job)
 	int rc = 0;
 
 	/* in case no data is transferred */
-	job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 
 	/* verify the els command is not greater than the
 	 * maximum ELS transfer size.
@@ -684,7 +694,7 @@ lpfc_bsg_rport_els(struct fc_bsg_job *job)
 		goto no_dd_data;
 	}
 
-	elscmd = job->request->rqst_data.r_els.els_code;
+	elscmd = bsg_request->rqst_data.r_els.els_code;
 	cmdsize = job->request_payload.payload_len;
 
 	if (!lpfc_nlp_get(ndlp)) {
@@ -771,7 +781,7 @@ free_dd_data:
 
 no_dd_data:
 	/* make error code available to userspace */
-	job->reply->result = rc;
+	bsg_reply->result = rc;
 	job->dd_data = NULL;
 	return rc;
 }
@@ -917,7 +927,8 @@ lpfc_bsg_ct_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	struct lpfc_dmabuf *bdeBuf2 = piocbq->context3;
 	struct lpfc_hbq_entry *hbqe;
 	struct lpfc_sli_ct_request *ct_req;
-	struct fc_bsg_job *job = NULL;
+	struct bsg_job *job = NULL;
+	struct fc_bsg_reply *bsg_reply;
 	struct bsg_job_data *dd_data = NULL;
 	unsigned long flags;
 	int size = 0;
@@ -1120,13 +1131,15 @@ lpfc_bsg_ct_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		dd_data->set_job = NULL;
 		lpfc_bsg_event_unref(evt);
 		if (job) {
-			job->reply->reply_payload_rcv_len = size;
+			bsg_reply = job->reply;
+			bsg_reply->reply_payload_rcv_len = size;
 			/* make error code available to userspace */
-			job->reply->result = 0;
+			bsg_reply->result = 0;
 			job->dd_data = NULL;
 			/* complete the job back to userspace */
 			spin_unlock_irqrestore(&phba->ct_ev_lock, flags);
-			job->job_done(job);
+			bsg_job_done(job, bsg_reply->result,
+				       bsg_reply->reply_payload_rcv_len);
 			spin_lock_irqsave(&phba->ct_ev_lock, flags);
 		}
 	}
@@ -1187,10 +1200,11 @@ lpfc_bsg_ct_unsol_abort(struct lpfc_hba *phba, struct hbq_dmabuf *dmabuf)
  * @job: SET_EVENT fc_bsg_job
  **/
 static int
-lpfc_bsg_hba_set_event(struct fc_bsg_job *job)
+lpfc_bsg_hba_set_event(struct bsg_job *job)
 {
-	struct lpfc_vport *vport = (struct lpfc_vport *)job->shost->hostdata;
+	struct lpfc_vport *vport = shost_priv(fc_bsg_to_shost(job));
 	struct lpfc_hba *phba = vport->phba;
+	struct fc_bsg_request *bsg_request = job->request;
 	struct set_ct_event *event_req;
 	struct lpfc_bsg_event *evt;
 	int rc = 0;
@@ -1208,7 +1222,7 @@ lpfc_bsg_hba_set_event(struct fc_bsg_job *job)
 	}
 
 	event_req = (struct set_ct_event *)
-		job->request->rqst_data.h_vendor.vendor_cmd;
+		bsg_request->rqst_data.h_vendor.vendor_cmd;
 	ev_mask = ((uint32_t)(unsigned long)event_req->type_mask &
 				FC_REG_EVENT_MASK);
 	spin_lock_irqsave(&phba->ct_ev_lock, flags);
@@ -1271,10 +1285,12 @@ job_error:
  * @job: GET_EVENT fc_bsg_job
  **/
 static int
-lpfc_bsg_hba_get_event(struct fc_bsg_job *job)
+lpfc_bsg_hba_get_event(struct bsg_job *job)
 {
-	struct lpfc_vport *vport = (struct lpfc_vport *)job->shost->hostdata;
+	struct lpfc_vport *vport = shost_priv(fc_bsg_to_shost(job));
 	struct lpfc_hba *phba = vport->phba;
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct get_ct_event *event_req;
 	struct get_ct_event_reply *event_reply;
 	struct lpfc_bsg_event *evt, *evt_next;
@@ -1292,10 +1308,10 @@ lpfc_bsg_hba_get_event(struct fc_bsg_job *job)
 	}
 
 	event_req = (struct get_ct_event *)
-		job->request->rqst_data.h_vendor.vendor_cmd;
+		bsg_request->rqst_data.h_vendor.vendor_cmd;
 
 	event_reply = (struct get_ct_event_reply *)
-		job->reply->reply_data.vendor_reply.vendor_rsp;
+		bsg_reply->reply_data.vendor_reply.vendor_rsp;
 	spin_lock_irqsave(&phba->ct_ev_lock, flags);
 	list_for_each_entry_safe(evt, evt_next, &phba->ct_ev_waiters, node) {
 		if (evt->reg_id == event_req->ev_reg_id) {
@@ -1315,7 +1331,7 @@ lpfc_bsg_hba_get_event(struct fc_bsg_job *job)
 	 * an error indicating that there isn't anymore
 	 */
 	if (evt_dat == NULL) {
-		job->reply->reply_payload_rcv_len = 0;
+		bsg_reply->reply_payload_rcv_len = 0;
 		rc = -ENOENT;
 		goto job_error;
 	}
@@ -1331,12 +1347,12 @@ lpfc_bsg_hba_get_event(struct fc_bsg_job *job)
 	event_reply->type = evt_dat->type;
 	event_reply->immed_data = evt_dat->immed_dat;
 	if (evt_dat->len > 0)
-		job->reply->reply_payload_rcv_len =
+		bsg_reply->reply_payload_rcv_len =
 			sg_copy_from_buffer(job->request_payload.sg_list,
 					    job->request_payload.sg_cnt,
 					    evt_dat->data, evt_dat->len);
 	else
-		job->reply->reply_payload_rcv_len = 0;
+		bsg_reply->reply_payload_rcv_len = 0;
 
 	if (evt_dat) {
 		kfree(evt_dat->data);
@@ -1347,13 +1363,14 @@ lpfc_bsg_hba_get_event(struct fc_bsg_job *job)
 	lpfc_bsg_event_unref(evt);
 	spin_unlock_irqrestore(&phba->ct_ev_lock, flags);
 	job->dd_data = NULL;
-	job->reply->result = 0;
-	job->job_done(job);
+	bsg_reply->result = 0;
+	bsg_job_done(job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	return 0;
 
 job_error:
 	job->dd_data = NULL;
-	job->reply->result = rc;
+	bsg_reply->result = rc;
 	return rc;
 }
 
@@ -1380,7 +1397,8 @@ lpfc_issue_ct_rsp_cmp(struct lpfc_hba *phba,
 			struct lpfc_iocbq *rspiocbq)
 {
 	struct bsg_job_data *dd_data;
-	struct fc_bsg_job *job;
+	struct bsg_job *job;
+	struct fc_bsg_reply *bsg_reply;
 	IOCB_t *rsp;
 	struct lpfc_dmabuf *bmp, *cmp;
 	struct lpfc_nodelist *ndlp;
@@ -1411,6 +1429,7 @@ lpfc_issue_ct_rsp_cmp(struct lpfc_hba *phba,
 	/* Copy the completed job data or set the error status */
 
 	if (job) {
+		bsg_reply = job->reply;
 		if (rsp->ulpStatus) {
 			if (rsp->ulpStatus == IOSTAT_LOCAL_REJECT) {
 				switch (rsp->un.ulpWord[4] & IOERR_PARAM_MASK) {
@@ -1428,7 +1447,7 @@ lpfc_issue_ct_rsp_cmp(struct lpfc_hba *phba,
 				rc = -EACCES;
 			}
 		} else {
-			job->reply->reply_payload_rcv_len = 0;
+			bsg_reply->reply_payload_rcv_len = 0;
 		}
 	}
 
@@ -1442,8 +1461,9 @@ lpfc_issue_ct_rsp_cmp(struct lpfc_hba *phba,
 	/* Complete the job if the job is still active */
 
 	if (job) {
-		job->reply->result = rc;
-		job->job_done(job);
+		bsg_reply->result = rc;
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	}
 	return;
 }
@@ -1457,7 +1477,7 @@ lpfc_issue_ct_rsp_cmp(struct lpfc_hba *phba,
  * @num_entry: Number of enties in the bde.
  **/
 static int
-lpfc_issue_ct_rsp(struct lpfc_hba *phba, struct fc_bsg_job *job, uint32_t tag,
+lpfc_issue_ct_rsp(struct lpfc_hba *phba, struct bsg_job *job, uint32_t tag,
 		  struct lpfc_dmabuf *cmp, struct lpfc_dmabuf *bmp,
 		  int num_entry)
 {
@@ -1603,12 +1623,14 @@ no_dd_data:
  * @job: SEND_MGMT_RESP fc_bsg_job
  **/
 static int
-lpfc_bsg_send_mgmt_rsp(struct fc_bsg_job *job)
+lpfc_bsg_send_mgmt_rsp(struct bsg_job *job)
 {
-	struct lpfc_vport *vport = (struct lpfc_vport *)job->shost->hostdata;
+	struct lpfc_vport *vport = shost_priv(fc_bsg_to_shost(job));
 	struct lpfc_hba *phba = vport->phba;
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct send_mgmt_resp *mgmt_resp = (struct send_mgmt_resp *)
-		job->request->rqst_data.h_vendor.vendor_cmd;
+		bsg_request->rqst_data.h_vendor.vendor_cmd;
 	struct ulp_bde64 *bpl;
 	struct lpfc_dmabuf *bmp = NULL, *cmp = NULL;
 	int bpl_entries;
@@ -1618,7 +1640,7 @@ lpfc_bsg_send_mgmt_rsp(struct fc_bsg_job *job)
 	int rc = 0;
 
 	/* in case no data is transferred */
-	job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 
 	if (!reqbfrcnt || (reqbfrcnt > (80 * BUF_SZ_4K))) {
 		rc = -ERANGE;
@@ -1664,7 +1686,7 @@ send_mgmt_rsp_free_bmp:
 	kfree(bmp);
 send_mgmt_rsp_exit:
 	/* make error code available to userspace */
-	job->reply->result = rc;
+	bsg_reply->result = rc;
 	job->dd_data = NULL;
 	return rc;
 }
@@ -1760,8 +1782,10 @@ lpfc_bsg_diag_mode_exit(struct lpfc_hba *phba)
  * All of this is done in-line.
  */
 static int
-lpfc_sli3_bsg_diag_loopback_mode(struct lpfc_hba *phba, struct fc_bsg_job *job)
+lpfc_sli3_bsg_diag_loopback_mode(struct lpfc_hba *phba, struct bsg_job *job)
 {
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct diag_mode_set *loopback_mode;
 	uint32_t link_flags;
 	uint32_t timeout;
@@ -1771,7 +1795,7 @@ lpfc_sli3_bsg_diag_loopback_mode(struct lpfc_hba *phba, struct fc_bsg_job *job)
 	int rc = 0;
 
 	/* no data to return just the return code */
-	job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 
 	if (job->request_len < sizeof(struct fc_bsg_request) +
 	    sizeof(struct diag_mode_set)) {
@@ -1791,7 +1815,7 @@ lpfc_sli3_bsg_diag_loopback_mode(struct lpfc_hba *phba, struct fc_bsg_job *job)
 
 	/* bring the link to diagnostic mode */
 	loopback_mode = (struct diag_mode_set *)
-		job->request->rqst_data.h_vendor.vendor_cmd;
+		bsg_request->rqst_data.h_vendor.vendor_cmd;
 	link_flags = loopback_mode->type;
 	timeout = loopback_mode->timeout * 100;
 
@@ -1864,10 +1888,11 @@ loopback_mode_exit:
 
 job_error:
 	/* make error code available to userspace */
-	job->reply->result = rc;
+	bsg_reply->result = rc;
 	/* complete the job back to userspace if no error */
 	if (rc == 0)
-		job->job_done(job);
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	return rc;
 }
 
@@ -2015,14 +2040,16 @@ lpfc_sli4_diag_fcport_reg_setup(struct lpfc_hba *phba)
  * loopback mode in order to perform a diagnostic loopback test.
  */
 static int
-lpfc_sli4_bsg_diag_loopback_mode(struct lpfc_hba *phba, struct fc_bsg_job *job)
+lpfc_sli4_bsg_diag_loopback_mode(struct lpfc_hba *phba, struct bsg_job *job)
 {
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct diag_mode_set *loopback_mode;
 	uint32_t link_flags, timeout;
 	int i, rc = 0;
 
 	/* no data to return just the return code */
-	job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 
 	if (job->request_len < sizeof(struct fc_bsg_request) +
 	    sizeof(struct diag_mode_set)) {
@@ -2054,7 +2081,7 @@ lpfc_sli4_bsg_diag_loopback_mode(struct lpfc_hba *phba, struct fc_bsg_job *job)
 	lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
 			"3129 Bring link to diagnostic state.\n");
 	loopback_mode = (struct diag_mode_set *)
-		job->request->rqst_data.h_vendor.vendor_cmd;
+		bsg_request->rqst_data.h_vendor.vendor_cmd;
 	link_flags = loopback_mode->type;
 	timeout = loopback_mode->timeout * 100;
 
@@ -2151,10 +2178,11 @@ loopback_mode_exit:
 
 job_error:
 	/* make error code available to userspace */
-	job->reply->result = rc;
+	bsg_reply->result = rc;
 	/* complete the job back to userspace if no error */
 	if (rc == 0)
-		job->job_done(job);
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	return rc;
 }
 
@@ -2166,17 +2194,17 @@ job_error:
  * command from the user to proper driver action routines.
  */
 static int
-lpfc_bsg_diag_loopback_mode(struct fc_bsg_job *job)
+lpfc_bsg_diag_loopback_mode(struct bsg_job *job)
 {
 	struct Scsi_Host *shost;
 	struct lpfc_vport *vport;
 	struct lpfc_hba *phba;
 	int rc;
 
-	shost = job->shost;
+	shost = fc_bsg_to_shost(job);
 	if (!shost)
 		return -ENODEV;
-	vport = (struct lpfc_vport *)job->shost->hostdata;
+	vport = shost_priv(shost);
 	if (!vport)
 		return -ENODEV;
 	phba = vport->phba;
@@ -2202,8 +2230,10 @@ lpfc_bsg_diag_loopback_mode(struct fc_bsg_job *job)
  * command from the user to proper driver action routines.
  */
 static int
-lpfc_sli4_bsg_diag_mode_end(struct fc_bsg_job *job)
+lpfc_sli4_bsg_diag_mode_end(struct bsg_job *job)
 {
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct Scsi_Host *shost;
 	struct lpfc_vport *vport;
 	struct lpfc_hba *phba;
@@ -2211,10 +2241,10 @@ lpfc_sli4_bsg_diag_mode_end(struct fc_bsg_job *job)
 	uint32_t timeout;
 	int rc, i;
 
-	shost = job->shost;
+	shost = fc_bsg_to_shost(job);
 	if (!shost)
 		return -ENODEV;
-	vport = (struct lpfc_vport *)job->shost->hostdata;
+	vport = shost_priv(shost);
 	if (!vport)
 		return -ENODEV;
 	phba = vport->phba;
@@ -2232,7 +2262,7 @@ lpfc_sli4_bsg_diag_mode_end(struct fc_bsg_job *job)
 	phba->link_flag &= ~LS_LOOPBACK_MODE;
 	spin_unlock_irq(&phba->hbalock);
 	loopback_mode_end_cmd = (struct diag_mode_set *)
-			job->request->rqst_data.h_vendor.vendor_cmd;
+			bsg_request->rqst_data.h_vendor.vendor_cmd;
 	timeout = loopback_mode_end_cmd->timeout * 100;
 
 	rc = lpfc_sli4_bsg_set_link_diag_state(phba, 0);
@@ -2263,10 +2293,11 @@ lpfc_sli4_bsg_diag_mode_end(struct fc_bsg_job *job)
 
 loopback_mode_end_exit:
 	/* make return code available to userspace */
-	job->reply->result = rc;
+	bsg_reply->result = rc;
 	/* complete the job back to userspace if no error */
 	if (rc == 0)
-		job->job_done(job);
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	return rc;
 }
 
@@ -2278,8 +2309,10 @@ loopback_mode_end_exit:
  * applicaiton.
  */
 static int
-lpfc_sli4_bsg_link_diag_test(struct fc_bsg_job *job)
+lpfc_sli4_bsg_link_diag_test(struct bsg_job *job)
 {
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct Scsi_Host *shost;
 	struct lpfc_vport *vport;
 	struct lpfc_hba *phba;
@@ -2292,12 +2325,12 @@ lpfc_sli4_bsg_link_diag_test(struct fc_bsg_job *job)
 	struct diag_status *diag_status_reply;
 	int mbxstatus, rc = 0;
 
-	shost = job->shost;
+	shost = fc_bsg_to_shost(job);
 	if (!shost) {
 		rc = -ENODEV;
 		goto job_error;
 	}
-	vport = (struct lpfc_vport *)job->shost->hostdata;
+	vport = shost_priv(shost);
 	if (!vport) {
 		rc = -ENODEV;
 		goto job_error;
@@ -2335,7 +2368,7 @@ lpfc_sli4_bsg_link_diag_test(struct fc_bsg_job *job)
 		goto job_error;
 
 	link_diag_test_cmd = (struct sli4_link_diag *)
-			 job->request->rqst_data.h_vendor.vendor_cmd;
+			 bsg_request->rqst_data.h_vendor.vendor_cmd;
 
 	rc = lpfc_sli4_bsg_set_link_diag_state(phba, 1);
 
@@ -2385,7 +2418,7 @@ lpfc_sli4_bsg_link_diag_test(struct fc_bsg_job *job)
 	}
 
 	diag_status_reply = (struct diag_status *)
-			    job->reply->reply_data.vendor_reply.vendor_rsp;
+			    bsg_reply->reply_data.vendor_reply.vendor_rsp;
 
 	if (job->reply_len <
 	    sizeof(struct fc_bsg_request) + sizeof(struct diag_status)) {
@@ -2413,10 +2446,11 @@ link_diag_test_exit:
 
 job_error:
 	/* make error code available to userspace */
-	job->reply->result = rc;
+	bsg_reply->result = rc;
 	/* complete the job back to userspace if no error */
 	if (rc == 0)
-		job->job_done(job);
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	return rc;
 }
 
@@ -2982,9 +3016,10 @@ err_post_rxbufs_exit:
  * of loopback mode.
  **/
 static int
-lpfc_bsg_diag_loopback_run(struct fc_bsg_job *job)
+lpfc_bsg_diag_loopback_run(struct bsg_job *job)
 {
-	struct lpfc_vport *vport = (struct lpfc_vport *)job->shost->hostdata;
+	struct lpfc_vport *vport = shost_priv(fc_bsg_to_shost(job));
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_bsg_event *evt;
 	struct event_data *evdat;
@@ -3012,7 +3047,7 @@ lpfc_bsg_diag_loopback_run(struct fc_bsg_job *job)
 	uint32_t total_mem;
 
 	/* in case no data is returned return just the return code */
-	job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 
 	if (job->request_len <
 	    sizeof(struct fc_bsg_request) + sizeof(struct diag_mode_test)) {
@@ -3237,11 +3272,11 @@ lpfc_bsg_diag_loopback_run(struct fc_bsg_job *job)
 			rc = IOCB_SUCCESS;
 			/* skip over elx loopback header */
 			rx_databuf += ELX_LOOPBACK_HEADER_SZ;
-			job->reply->reply_payload_rcv_len =
+			bsg_reply->reply_payload_rcv_len =
 				sg_copy_from_buffer(job->reply_payload.sg_list,
 						    job->reply_payload.sg_cnt,
 						    rx_databuf, size);
-			job->reply->reply_payload_rcv_len = size;
+			bsg_reply->reply_payload_rcv_len = size;
 		}
 	}
 
@@ -3271,11 +3306,12 @@ err_loopback_test_exit:
 loopback_test_exit:
 	kfree(dataout);
 	/* make error code available to userspace */
-	job->reply->result = rc;
+	bsg_reply->result = rc;
 	job->dd_data = NULL;
 	/* complete the job back to userspace if no error */
 	if (rc == IOCB_SUCCESS)
-		job->job_done(job);
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	return rc;
 }
 
@@ -3284,9 +3320,10 @@ loopback_test_exit:
  * @job: GET_DFC_REV fc_bsg_job
  **/
 static int
-lpfc_bsg_get_dfc_rev(struct fc_bsg_job *job)
+lpfc_bsg_get_dfc_rev(struct bsg_job *job)
 {
-	struct lpfc_vport *vport = (struct lpfc_vport *)job->shost->hostdata;
+	struct lpfc_vport *vport = shost_priv(fc_bsg_to_shost(job));
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct lpfc_hba *phba = vport->phba;
 	struct get_mgmt_rev_reply *event_reply;
 	int rc = 0;
@@ -3301,7 +3338,7 @@ lpfc_bsg_get_dfc_rev(struct fc_bsg_job *job)
 	}
 
 	event_reply = (struct get_mgmt_rev_reply *)
-		job->reply->reply_data.vendor_reply.vendor_rsp;
+		bsg_reply->reply_data.vendor_reply.vendor_rsp;
 
 	if (job->reply_len <
 	    sizeof(struct fc_bsg_request) + sizeof(struct get_mgmt_rev_reply)) {
@@ -3315,9 +3352,10 @@ lpfc_bsg_get_dfc_rev(struct fc_bsg_job *job)
 	event_reply->info.a_Major = MANAGEMENT_MAJOR_REV;
 	event_reply->info.a_Minor = MANAGEMENT_MINOR_REV;
 job_error:
-	job->reply->result = rc;
+	bsg_reply->result = rc;
 	if (rc == 0)
-		job->job_done(job);
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	return rc;
 }
 
@@ -3336,7 +3374,8 @@ static void
 lpfc_bsg_issue_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 {
 	struct bsg_job_data *dd_data;
-	struct fc_bsg_job *job;
+	struct fc_bsg_reply *bsg_reply;
+	struct bsg_job *job;
 	uint32_t size;
 	unsigned long flags;
 	uint8_t *pmb, *pmb_buf;
@@ -3364,8 +3403,9 @@ lpfc_bsg_issue_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 	/* Copy the mailbox data to the job if it is still active */
 
 	if (job) {
+		bsg_reply = job->reply;
 		size = job->reply_payload.payload_len;
-		job->reply->reply_payload_rcv_len =
+		bsg_reply->reply_payload_rcv_len =
 			sg_copy_from_buffer(job->reply_payload.sg_list,
 					    job->reply_payload.sg_cnt,
 					    pmb_buf, size);
@@ -3379,8 +3419,9 @@ lpfc_bsg_issue_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 	/* Complete the job if the job is still active */
 
 	if (job) {
-		job->reply->result = 0;
-		job->job_done(job);
+		bsg_reply->result = 0;
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	}
 	return;
 }
@@ -3510,11 +3551,12 @@ lpfc_bsg_mbox_ext_session_reset(struct lpfc_hba *phba)
  * This is routine handles BSG job for mailbox commands completions with
  * multiple external buffers.
  **/
-static struct fc_bsg_job *
+static struct bsg_job *
 lpfc_bsg_issue_mbox_ext_handle_job(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 {
 	struct bsg_job_data *dd_data;
-	struct fc_bsg_job *job;
+	struct bsg_job *job;
+	struct fc_bsg_reply *bsg_reply;
 	uint8_t *pmb, *pmb_buf;
 	unsigned long flags;
 	uint32_t size;
@@ -3529,6 +3571,7 @@ lpfc_bsg_issue_mbox_ext_handle_job(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 	spin_lock_irqsave(&phba->ct_ev_lock, flags);
 	job = dd_data->set_job;
 	if (job) {
+		bsg_reply = job->reply;
 		/* Prevent timeout handling from trying to abort job  */
 		job->dd_data = NULL;
 	}
@@ -3559,13 +3602,13 @@ lpfc_bsg_issue_mbox_ext_handle_job(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 
 	if (job) {
 		size = job->reply_payload.payload_len;
-		job->reply->reply_payload_rcv_len =
+		bsg_reply->reply_payload_rcv_len =
 			sg_copy_from_buffer(job->reply_payload.sg_list,
 					    job->reply_payload.sg_cnt,
 					    pmb_buf, size);
 
 		/* result for successful */
-		job->reply->result = 0;
+		bsg_reply->result = 0;
 
 		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
 				"2937 SLI_CONFIG ext-buffer maibox command "
@@ -3603,7 +3646,8 @@ lpfc_bsg_issue_mbox_ext_handle_job(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 static void
 lpfc_bsg_issue_read_mbox_ext_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 {
-	struct fc_bsg_job *job;
+	struct bsg_job *job;
+	struct fc_bsg_reply *bsg_reply;
 
 	job = lpfc_bsg_issue_mbox_ext_handle_job(phba, pmboxq);
 
@@ -3623,9 +3667,11 @@ lpfc_bsg_issue_read_mbox_ext_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 	mempool_free(pmboxq, phba->mbox_mem_pool);
 
 	/* if the job is still active, call job done */
-	if (job)
-		job->job_done(job);
-
+	if (job) {
+		bsg_reply = job->reply;
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
+	}
 	return;
 }
 
@@ -3640,7 +3686,8 @@ lpfc_bsg_issue_read_mbox_ext_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 static void
 lpfc_bsg_issue_write_mbox_ext_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 {
-	struct fc_bsg_job *job;
+	struct bsg_job *job;
+	struct fc_bsg_reply *bsg_reply;
 
 	job = lpfc_bsg_issue_mbox_ext_handle_job(phba, pmboxq);
 
@@ -3658,8 +3705,11 @@ lpfc_bsg_issue_write_mbox_ext_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 	lpfc_bsg_mbox_ext_session_reset(phba);
 
 	/* if the job is still active, call job done */
-	if (job)
-		job->job_done(job);
+	if (job) {
+		bsg_reply = job->reply;
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
+	}
 
 	return;
 }
@@ -3768,10 +3818,11 @@ lpfc_bsg_sli_cfg_dma_desc_setup(struct lpfc_hba *phba, enum nemb_type nemb_tp,
  * non-embedded external bufffers.
  **/
 static int
-lpfc_bsg_sli_cfg_read_cmd_ext(struct lpfc_hba *phba, struct fc_bsg_job *job,
+lpfc_bsg_sli_cfg_read_cmd_ext(struct lpfc_hba *phba, struct bsg_job *job,
 			      enum nemb_type nemb_tp,
 			      struct lpfc_dmabuf *dmabuf)
 {
+	struct fc_bsg_request *bsg_request = job->request;
 	struct lpfc_sli_config_mbox *sli_cfg_mbx;
 	struct dfc_mbox_req *mbox_req;
 	struct lpfc_dmabuf *curr_dmabuf, *next_dmabuf;
@@ -3784,7 +3835,7 @@ lpfc_bsg_sli_cfg_read_cmd_ext(struct lpfc_hba *phba, struct fc_bsg_job *job,
 	int rc, i;
 
 	mbox_req =
-	   (struct dfc_mbox_req *)job->request->rqst_data.h_vendor.vendor_cmd;
+	   (struct dfc_mbox_req *)bsg_request->rqst_data.h_vendor.vendor_cmd;
 
 	/* pointer to the start of mailbox command */
 	sli_cfg_mbx = (struct lpfc_sli_config_mbox *)dmabuf->virt;
@@ -3955,10 +4006,12 @@ job_error:
  * non-embedded external bufffers.
  **/
 static int
-lpfc_bsg_sli_cfg_write_cmd_ext(struct lpfc_hba *phba, struct fc_bsg_job *job,
+lpfc_bsg_sli_cfg_write_cmd_ext(struct lpfc_hba *phba, struct bsg_job *job,
 			       enum nemb_type nemb_tp,
 			       struct lpfc_dmabuf *dmabuf)
 {
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct dfc_mbox_req *mbox_req;
 	struct lpfc_sli_config_mbox *sli_cfg_mbx;
 	uint32_t ext_buf_cnt;
@@ -3969,7 +4022,7 @@ lpfc_bsg_sli_cfg_write_cmd_ext(struct lpfc_hba *phba, struct fc_bsg_job *job,
 	int rc = SLI_CONFIG_NOT_HANDLED, i;
 
 	mbox_req =
-	   (struct dfc_mbox_req *)job->request->rqst_data.h_vendor.vendor_cmd;
+	   (struct dfc_mbox_req *)bsg_request->rqst_data.h_vendor.vendor_cmd;
 
 	/* pointer to the start of mailbox command */
 	sli_cfg_mbx = (struct lpfc_sli_config_mbox *)dmabuf->virt;
@@ -4096,8 +4149,9 @@ lpfc_bsg_sli_cfg_write_cmd_ext(struct lpfc_hba *phba, struct fc_bsg_job *job,
 
 	/* wait for additoinal external buffers */
 
-	job->reply->result = 0;
-	job->job_done(job);
+	bsg_reply->result = 0;
+	bsg_job_done(job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	return SLI_CONFIG_HANDLED;
 
 job_error:
@@ -4119,7 +4173,7 @@ job_error:
  * with embedded sussystem 0x1 and opcodes with external HBDs.
  **/
 static int
-lpfc_bsg_handle_sli_cfg_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
+lpfc_bsg_handle_sli_cfg_mbox(struct lpfc_hba *phba, struct bsg_job *job,
 			     struct lpfc_dmabuf *dmabuf)
 {
 	struct lpfc_sli_config_mbox *sli_cfg_mbx;
@@ -4268,8 +4322,9 @@ lpfc_bsg_mbox_ext_abort(struct lpfc_hba *phba)
  * user space through BSG.
  **/
 static int
-lpfc_bsg_read_ebuf_get(struct lpfc_hba *phba, struct fc_bsg_job *job)
+lpfc_bsg_read_ebuf_get(struct lpfc_hba *phba, struct bsg_job *job)
 {
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct lpfc_sli_config_mbox *sli_cfg_mbx;
 	struct lpfc_dmabuf *dmabuf;
 	uint8_t *pbuf;
@@ -4307,7 +4362,7 @@ lpfc_bsg_read_ebuf_get(struct lpfc_hba *phba, struct fc_bsg_job *job)
 					dmabuf, index);
 
 	pbuf = (uint8_t *)dmabuf->virt;
-	job->reply->reply_payload_rcv_len =
+	bsg_reply->reply_payload_rcv_len =
 		sg_copy_from_buffer(job->reply_payload.sg_list,
 				    job->reply_payload.sg_cnt,
 				    pbuf, size);
@@ -4321,8 +4376,9 @@ lpfc_bsg_read_ebuf_get(struct lpfc_hba *phba, struct fc_bsg_job *job)
 		lpfc_bsg_mbox_ext_session_reset(phba);
 	}
 
-	job->reply->result = 0;
-	job->job_done(job);
+	bsg_reply->result = 0;
+	bsg_job_done(job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 
 	return SLI_CONFIG_HANDLED;
 }
@@ -4336,9 +4392,10 @@ lpfc_bsg_read_ebuf_get(struct lpfc_hba *phba, struct fc_bsg_job *job)
  * from user space through BSG.
  **/
 static int
-lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct fc_bsg_job *job,
+lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job,
 			struct lpfc_dmabuf *dmabuf)
 {
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct bsg_job_data *dd_data = NULL;
 	LPFC_MBOXQ_t *pmboxq = NULL;
 	MAILBOX_t *pmb;
@@ -4436,8 +4493,9 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct fc_bsg_job *job,
 	}
 
 	/* wait for additoinal external buffers */
-	job->reply->result = 0;
-	job->job_done(job);
+	bsg_reply->result = 0;
+	bsg_job_done(job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	return SLI_CONFIG_HANDLED;
 
 job_error:
@@ -4457,7 +4515,7 @@ job_error:
  * command with multiple non-embedded external buffers.
  **/
 static int
-lpfc_bsg_handle_sli_cfg_ebuf(struct lpfc_hba *phba, struct fc_bsg_job *job,
+lpfc_bsg_handle_sli_cfg_ebuf(struct lpfc_hba *phba, struct bsg_job *job,
 			     struct lpfc_dmabuf *dmabuf)
 {
 	int rc;
@@ -4502,14 +4560,15 @@ lpfc_bsg_handle_sli_cfg_ebuf(struct lpfc_hba *phba, struct fc_bsg_job *job,
  * (0x9B) mailbox commands and external buffers.
  **/
 static int
-lpfc_bsg_handle_sli_cfg_ext(struct lpfc_hba *phba, struct fc_bsg_job *job,
+lpfc_bsg_handle_sli_cfg_ext(struct lpfc_hba *phba, struct bsg_job *job,
 			    struct lpfc_dmabuf *dmabuf)
 {
+	struct fc_bsg_request *bsg_request = job->request;
 	struct dfc_mbox_req *mbox_req;
 	int rc = SLI_CONFIG_NOT_HANDLED;
 
 	mbox_req =
-	   (struct dfc_mbox_req *)job->request->rqst_data.h_vendor.vendor_cmd;
+	   (struct dfc_mbox_req *)bsg_request->rqst_data.h_vendor.vendor_cmd;
 
 	/* mbox command with/without single external buffer */
 	if (mbox_req->extMboxTag == 0 && mbox_req->extSeqNum == 0)
@@ -4579,9 +4638,11 @@ sli_cfg_ext_error:
  * let our completion handler finish the command.
  **/
 static int
-lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
+lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct bsg_job *job,
 	struct lpfc_vport *vport)
 {
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	LPFC_MBOXQ_t *pmboxq = NULL; /* internal mailbox queue */
 	MAILBOX_t *pmb; /* shortcut to the pmboxq mailbox */
 	/* a 4k buffer to hold the mb and extended data from/to the bsg */
@@ -4600,7 +4661,7 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 	uint32_t size;
 
 	/* in case no data is transferred */
-	job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 
 	/* sanity check to protect driver */
 	if (job->reply_payload.payload_len > BSG_MBOX_SIZE ||
@@ -4619,7 +4680,7 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 	}
 
 	mbox_req =
-	    (struct dfc_mbox_req *)job->request->rqst_data.h_vendor.vendor_cmd;
+	    (struct dfc_mbox_req *)bsg_request->rqst_data.h_vendor.vendor_cmd;
 
 	/* check if requested extended data lengths are valid */
 	if ((mbox_req->inExtWLen > BSG_MBOX_SIZE/sizeof(uint32_t)) ||
@@ -4841,7 +4902,7 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct fc_bsg_job *job,
 
 		/* job finished, copy the data */
 		memcpy(pmbx, pmb, sizeof(*pmb));
-		job->reply->reply_payload_rcv_len =
+		bsg_reply->reply_payload_rcv_len =
 			sg_copy_from_buffer(job->reply_payload.sg_list,
 					    job->reply_payload.sg_cnt,
 					    pmbx, size);
@@ -4870,15 +4931,17 @@ job_cont:
  * @job: MBOX fc_bsg_job for LPFC_BSG_VENDOR_MBOX.
  **/
 static int
-lpfc_bsg_mbox_cmd(struct fc_bsg_job *job)
+lpfc_bsg_mbox_cmd(struct bsg_job *job)
 {
-	struct lpfc_vport *vport = (struct lpfc_vport *)job->shost->hostdata;
+	struct lpfc_vport *vport = shost_priv(fc_bsg_to_shost(job));
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct lpfc_hba *phba = vport->phba;
 	struct dfc_mbox_req *mbox_req;
 	int rc = 0;
 
 	/* mix-and-match backward compatibility */
-	job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 	if (job->request_len <
 	    sizeof(struct fc_bsg_request) + sizeof(struct dfc_mbox_req)) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
@@ -4889,7 +4952,7 @@ lpfc_bsg_mbox_cmd(struct fc_bsg_job *job)
 				      sizeof(struct fc_bsg_request)),
 				(int)sizeof(struct dfc_mbox_req));
 		mbox_req = (struct dfc_mbox_req *)
-				job->request->rqst_data.h_vendor.vendor_cmd;
+				bsg_request->rqst_data.h_vendor.vendor_cmd;
 		mbox_req->extMboxTag = 0;
 		mbox_req->extSeqNum = 0;
 	}
@@ -4898,15 +4961,16 @@ lpfc_bsg_mbox_cmd(struct fc_bsg_job *job)
 
 	if (rc == 0) {
 		/* job done */
-		job->reply->result = 0;
+		bsg_reply->result = 0;
 		job->dd_data = NULL;
-		job->job_done(job);
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	} else if (rc == 1)
 		/* job submitted, will complete later*/
 		rc = 0; /* return zero, no error */
 	else {
 		/* some error occurred */
-		job->reply->result = rc;
+		bsg_reply->result = rc;
 		job->dd_data = NULL;
 	}
 
@@ -4936,7 +5000,8 @@ lpfc_bsg_menlo_cmd_cmp(struct lpfc_hba *phba,
 			struct lpfc_iocbq *rspiocbq)
 {
 	struct bsg_job_data *dd_data;
-	struct fc_bsg_job *job;
+	struct bsg_job *job;
+	struct fc_bsg_reply *bsg_reply;
 	IOCB_t *rsp;
 	struct lpfc_dmabuf *bmp, *cmp, *rmp;
 	struct lpfc_bsg_menlo *menlo;
@@ -4956,6 +5021,7 @@ lpfc_bsg_menlo_cmd_cmp(struct lpfc_hba *phba,
 	spin_lock_irqsave(&phba->ct_ev_lock, flags);
 	job = dd_data->set_job;
 	if (job) {
+		bsg_reply = job->reply;
 		/* Prevent timeout handling from trying to abort job  */
 		job->dd_data = NULL;
 	}
@@ -4970,7 +5036,7 @@ lpfc_bsg_menlo_cmd_cmp(struct lpfc_hba *phba,
 		 */
 
 		menlo_resp = (struct menlo_response *)
-			job->reply->reply_data.vendor_reply.vendor_rsp;
+			bsg_reply->reply_data.vendor_reply.vendor_rsp;
 		menlo_resp->xri = rsp->ulpContext;
 		if (rsp->ulpStatus) {
 			if (rsp->ulpStatus == IOSTAT_LOCAL_REJECT) {
@@ -4990,7 +5056,7 @@ lpfc_bsg_menlo_cmd_cmp(struct lpfc_hba *phba,
 			}
 		} else {
 			rsp_size = rsp->un.genreq64.bdl.bdeSize;
-			job->reply->reply_payload_rcv_len =
+			bsg_reply->reply_payload_rcv_len =
 				lpfc_bsg_copy_data(rmp, &job->reply_payload,
 						   rsp_size, 0);
 		}
@@ -5007,8 +5073,9 @@ lpfc_bsg_menlo_cmd_cmp(struct lpfc_hba *phba,
 	/* Complete the job if active */
 
 	if (job) {
-		job->reply->result = rc;
-		job->job_done(job);
+		bsg_reply->result = rc;
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	}
 
 	return;
@@ -5024,9 +5091,11 @@ lpfc_bsg_menlo_cmd_cmp(struct lpfc_hba *phba,
  * supplied in the menlo request header xri field.
  **/
 static int
-lpfc_menlo_cmd(struct fc_bsg_job *job)
+lpfc_menlo_cmd(struct bsg_job *job)
 {
-	struct lpfc_vport *vport = (struct lpfc_vport *)job->shost->hostdata;
+	struct lpfc_vport *vport = shost_priv(fc_bsg_to_shost(job));
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_iocbq *cmdiocbq;
 	IOCB_t *cmd;
@@ -5039,7 +5108,7 @@ lpfc_menlo_cmd(struct fc_bsg_job *job)
 	struct ulp_bde64 *bpl = NULL;
 
 	/* in case no data is returned return just the return code */
-	job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 
 	if (job->request_len <
 	    sizeof(struct fc_bsg_request) +
@@ -5069,7 +5138,7 @@ lpfc_menlo_cmd(struct fc_bsg_job *job)
 	}
 
 	menlo_cmd = (struct menlo_command *)
-		job->request->rqst_data.h_vendor.vendor_cmd;
+		bsg_request->rqst_data.h_vendor.vendor_cmd;
 
 	/* allocate our bsg tracking structure */
 	dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL);
@@ -5180,19 +5249,65 @@ free_dd:
 	kfree(dd_data);
 no_dd_data:
 	/* make error code available to userspace */
-	job->reply->result = rc;
+	bsg_reply->result = rc;
 	job->dd_data = NULL;
 	return rc;
 }
 
+static int
+lpfc_forced_link_speed(struct bsg_job *job)
+{
+	struct Scsi_Host *shost = fc_bsg_to_shost(job);
+	struct lpfc_vport *vport = shost_priv(shost);
+	struct lpfc_hba *phba = vport->phba;
+	struct fc_bsg_reply *bsg_reply = job->reply;
+	struct forced_link_speed_support_reply *forced_reply;
+	int rc = 0;
+
+	if (job->request_len <
+	    sizeof(struct fc_bsg_request) +
+	    sizeof(struct get_forced_link_speed_support)) {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_LIBDFC,
+				"0048 Received FORCED_LINK_SPEED request "
+				"below minimum size\n");
+		rc = -EINVAL;
+		goto job_error;
+	}
+
+	forced_reply = (struct forced_link_speed_support_reply *)
+		bsg_reply->reply_data.vendor_reply.vendor_rsp;
+
+	if (job->reply_len <
+	    sizeof(struct fc_bsg_request) +
+	    sizeof(struct forced_link_speed_support_reply)) {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_LIBDFC,
+				"0049 Received FORCED_LINK_SPEED reply below "
+				"minimum size\n");
+		rc = -EINVAL;
+		goto job_error;
+	}
+
+	forced_reply->supported = (phba->hba_flag & HBA_FORCED_LINK_SPEED)
+				   ? LPFC_FORCED_LINK_SPEED_SUPPORTED
+				   : LPFC_FORCED_LINK_SPEED_NOT_SUPPORTED;
+job_error:
+	bsg_reply->result = rc;
+	if (rc == 0)
+		bsg_job_done(job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
+	return rc;
+}
+
 /**
  * lpfc_bsg_hst_vendor - process a vendor-specific fc_bsg_job
  * @job: fc_bsg_job to handle
  **/
 static int
-lpfc_bsg_hst_vendor(struct fc_bsg_job *job)
+lpfc_bsg_hst_vendor(struct bsg_job *job)
 {
-	int command = job->request->rqst_data.h_vendor.vendor_cmd[0];
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
+	int command = bsg_request->rqst_data.h_vendor.vendor_cmd[0];
 	int rc;
 
 	switch (command) {
@@ -5227,11 +5342,14 @@ lpfc_bsg_hst_vendor(struct fc_bsg_job *job)
 	case LPFC_BSG_VENDOR_MENLO_DATA:
 		rc = lpfc_menlo_cmd(job);
 		break;
+	case LPFC_BSG_VENDOR_FORCED_LINK_SPEED:
+		rc = lpfc_forced_link_speed(job);
+		break;
 	default:
 		rc = -EINVAL;
-		job->reply->reply_payload_rcv_len = 0;
+		bsg_reply->reply_payload_rcv_len = 0;
 		/* make error code available to userspace */
-		job->reply->result = rc;
+		bsg_reply->result = rc;
 		break;
 	}
 
@@ -5243,12 +5361,14 @@ lpfc_bsg_hst_vendor(struct fc_bsg_job *job)
  * @job: fc_bsg_job to handle
  **/
 int
-lpfc_bsg_request(struct fc_bsg_job *job)
+lpfc_bsg_request(struct bsg_job *job)
 {
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	uint32_t msgcode;
 	int rc;
 
-	msgcode = job->request->msgcode;
+	msgcode = bsg_request->msgcode;
 	switch (msgcode) {
 	case FC_BSG_HST_VENDOR:
 		rc = lpfc_bsg_hst_vendor(job);
@@ -5261,9 +5381,9 @@ lpfc_bsg_request(struct fc_bsg_job *job)
 		break;
 	default:
 		rc = -EINVAL;
-		job->reply->reply_payload_rcv_len = 0;
+		bsg_reply->reply_payload_rcv_len = 0;
 		/* make error code available to userspace */
-		job->reply->result = rc;
+		bsg_reply->result = rc;
 		break;
 	}
 
@@ -5278,9 +5398,9 @@ lpfc_bsg_request(struct fc_bsg_job *job)
  * the waiting function which will handle passing the error back to userspace
  **/
 int
-lpfc_bsg_timeout(struct fc_bsg_job *job)
+lpfc_bsg_timeout(struct bsg_job *job)
 {
-	struct lpfc_vport *vport = (struct lpfc_vport *)job->shost->hostdata;
+	struct lpfc_vport *vport = shost_priv(fc_bsg_to_shost(job));
 	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_iocbq *cmdiocb;
 	struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
diff --git a/drivers/scsi/lpfc/lpfc_bsg.h b/drivers/scsi/lpfc/lpfc_bsg.h
index e557bcdbcb19..f2247aa4fa17 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.h
+++ b/drivers/scsi/lpfc/lpfc_bsg.h
@@ -35,6 +35,7 @@
 #define LPFC_BSG_VENDOR_MENLO_DATA		9
 #define LPFC_BSG_VENDOR_DIAG_MODE_END		10
 #define LPFC_BSG_VENDOR_LINK_DIAG_TEST		11
+#define LPFC_BSG_VENDOR_FORCED_LINK_SPEED	14
 
 struct set_ct_event {
 	uint32_t command;
@@ -284,6 +285,15 @@ struct lpfc_sli_config_mbox {
 	} un;
 };
 
+#define LPFC_FORCED_LINK_SPEED_NOT_SUPPORTED	0
+#define LPFC_FORCED_LINK_SPEED_SUPPORTED	1
+struct get_forced_link_speed_support {
+	uint32_t command;
+};
+struct forced_link_speed_support_reply {
+	uint8_t supported;
+};
+
 /* driver only */
 #define SLI_CONFIG_NOT_HANDLED		0
 #define SLI_CONFIG_HANDLED		1
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index bd7576d452f2..15d2bfdf582d 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -397,8 +397,6 @@ extern spinlock_t _dump_buf_lock;
 extern int _dump_buf_done;
 extern spinlock_t pgcnt_lock;
 extern unsigned int pgcnt;
-extern unsigned int lpfc_prot_mask;
-extern unsigned char lpfc_prot_guard;
 extern unsigned int lpfc_fcp_look_ahead;
 
 /* Interface exported by fabric iocb scheduler */
@@ -431,8 +429,8 @@ struct lpfc_sglq *__lpfc_get_active_sglq(struct lpfc_hba *, uint16_t);
 #define HBA_EVENT_LINK_DOWN              3
 
 /* functions to support SGIOv4/bsg interface */
-int lpfc_bsg_request(struct fc_bsg_job *);
-int lpfc_bsg_timeout(struct fc_bsg_job *);
+int lpfc_bsg_request(struct bsg_job *);
+int lpfc_bsg_timeout(struct bsg_job *);
 int lpfc_bsg_ct_unsol_event(struct lpfc_hba *, struct lpfc_sli_ring *,
 			     struct lpfc_iocbq *);
 int lpfc_bsg_ct_unsol_abort(struct lpfc_hba *, struct hbq_dmabuf *);
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index b7d54bfb1df9..236e4e51d161 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -7610,7 +7610,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	/* reject till our FLOGI completes */
 	if ((vport->port_state < LPFC_FABRIC_CFG_LINK) &&
 	    (cmd != ELS_CMD_FLOGI)) {
-		rjt_err = LSRJT_UNABLE_TPC;
+		rjt_err = LSRJT_LOGICAL_BSY;
 		rjt_exp = LSEXP_NOTHING_MORE;
 		goto lsrjt;
 	}
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index ee8022737591..5646699b0516 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -921,6 +921,7 @@ struct mbox_header {
 #define LPFC_MBOX_OPCODE_GET_PORT_NAME			0x4D
 #define LPFC_MBOX_OPCODE_MQ_CREATE_EXT			0x5A
 #define LPFC_MBOX_OPCODE_GET_VPD_DATA			0x5B
+#define LPFC_MBOX_OPCODE_SET_HOST_DATA			0x5D
 #define LPFC_MBOX_OPCODE_SEND_ACTIVATION		0x73
 #define LPFC_MBOX_OPCODE_RESET_LICENSES			0x74
 #define LPFC_MBOX_OPCODE_GET_RSRC_EXTENT_INFO		0x9A
@@ -2289,6 +2290,9 @@ struct lpfc_mbx_read_config {
 #define lpfc_mbx_rd_conf_r_a_tov_SHIFT		0
 #define lpfc_mbx_rd_conf_r_a_tov_MASK		0x0000FFFF
 #define lpfc_mbx_rd_conf_r_a_tov_WORD		word6
+#define lpfc_mbx_rd_conf_link_speed_SHIFT	16
+#define lpfc_mbx_rd_conf_link_speed_MASK	0x0000FFFF
+#define lpfc_mbx_rd_conf_link_speed_WORD	word6
 	uint32_t rsvd_7;
 	uint32_t rsvd_8;
 	uint32_t word9;
@@ -2919,6 +2923,16 @@ struct lpfc_mbx_set_feature {
 };
 
 
+#define LPFC_SET_HOST_OS_DRIVER_VERSION    0x2
+struct lpfc_mbx_set_host_data {
+#define LPFC_HOST_OS_DRIVER_VERSION_SIZE   48
+	struct mbox_header header;
+	uint32_t param_id;
+	uint32_t param_len;
+	uint8_t  data[LPFC_HOST_OS_DRIVER_VERSION_SIZE];
+};
+
+
 struct lpfc_mbx_get_sli4_parameters {
 	struct mbox_header header;
 	struct lpfc_sli4_parameters sli4_parameters;
@@ -3313,6 +3327,7 @@ struct lpfc_mqe {
 		struct lpfc_mbx_get_port_name get_port_name;
 		struct lpfc_mbx_set_feature  set_feature;
 		struct lpfc_mbx_memory_dump_type3 mem_dump_type3;
+		struct lpfc_mbx_set_host_data set_host_data;
 		struct lpfc_mbx_nop nop;
 	} un;
 };
@@ -3981,7 +3996,8 @@ union lpfc_wqe128 {
 	struct gen_req64_wqe gen_req;
 };
 
-#define LPFC_GROUP_OJECT_MAGIC_NUM		0xfeaa0001
+#define LPFC_GROUP_OJECT_MAGIC_G5		0xfeaa0001
+#define LPFC_GROUP_OJECT_MAGIC_G6		0xfeaa0003
 #define LPFC_FILE_TYPE_GROUP			0xf7
 #define LPFC_FILE_ID_GROUP			0xa2
 struct lpfc_grp_hdr {
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 734a0428ef0e..4776fd85514f 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -6279,34 +6279,36 @@ lpfc_setup_bg(struct lpfc_hba *phba, struct Scsi_Host *shost)
 	uint32_t old_guard;
 
 	int pagecnt = 10;
-	if (lpfc_prot_mask && lpfc_prot_guard) {
+	if (phba->cfg_prot_mask && phba->cfg_prot_guard) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"1478 Registering BlockGuard with the "
 				"SCSI layer\n");
 
-		old_mask = lpfc_prot_mask;
-		old_guard = lpfc_prot_guard;
+		old_mask = phba->cfg_prot_mask;
+		old_guard = phba->cfg_prot_guard;
 
 		/* Only allow supported values */
-		lpfc_prot_mask &= (SHOST_DIF_TYPE1_PROTECTION |
+		phba->cfg_prot_mask &= (SHOST_DIF_TYPE1_PROTECTION |
 			SHOST_DIX_TYPE0_PROTECTION |
 			SHOST_DIX_TYPE1_PROTECTION);
-		lpfc_prot_guard &= (SHOST_DIX_GUARD_IP | SHOST_DIX_GUARD_CRC);
+		phba->cfg_prot_guard &= (SHOST_DIX_GUARD_IP |
+					 SHOST_DIX_GUARD_CRC);
 
 		/* DIF Type 1 protection for profiles AST1/C1 is end to end */
-		if (lpfc_prot_mask == SHOST_DIX_TYPE1_PROTECTION)
-			lpfc_prot_mask |= SHOST_DIF_TYPE1_PROTECTION;
+		if (phba->cfg_prot_mask == SHOST_DIX_TYPE1_PROTECTION)
+			phba->cfg_prot_mask |= SHOST_DIF_TYPE1_PROTECTION;
 
-		if (lpfc_prot_mask && lpfc_prot_guard) {
-			if ((old_mask != lpfc_prot_mask) ||
-				(old_guard != lpfc_prot_guard))
+		if (phba->cfg_prot_mask && phba->cfg_prot_guard) {
+			if ((old_mask != phba->cfg_prot_mask) ||
+				(old_guard != phba->cfg_prot_guard))
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 					"1475 Registering BlockGuard with the "
 					"SCSI layer: mask %d  guard %d\n",
-					lpfc_prot_mask, lpfc_prot_guard);
+					phba->cfg_prot_mask,
+					phba->cfg_prot_guard);
 
-			scsi_host_set_prot(shost, lpfc_prot_mask);
-			scsi_host_set_guard(shost, lpfc_prot_guard);
+			scsi_host_set_prot(shost, phba->cfg_prot_mask);
+			scsi_host_set_guard(shost, phba->cfg_prot_guard);
 		} else
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"1479 Not Registering BlockGuard with the SCSI "
@@ -6929,6 +6931,8 @@ lpfc_sli4_read_config(struct lpfc_hba *phba)
 	struct lpfc_mbx_get_func_cfg *get_func_cfg;
 	struct lpfc_rsrc_desc_fcfcoe *desc;
 	char *pdesc_0;
+	uint16_t forced_link_speed;
+	uint32_t if_type;
 	int length, i, rc = 0, rc2;
 
 	pmb = (LPFC_MBOXQ_t *) mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
@@ -7022,6 +7026,58 @@ lpfc_sli4_read_config(struct lpfc_hba *phba)
 	if (rc)
 		goto read_cfg_out;
 
+	/* Update link speed if forced link speed is supported */
+	if_type = bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf);
+	if (if_type == LPFC_SLI_INTF_IF_TYPE_2) {
+		forced_link_speed =
+			bf_get(lpfc_mbx_rd_conf_link_speed, rd_config);
+		if (forced_link_speed) {
+			phba->hba_flag |= HBA_FORCED_LINK_SPEED;
+
+			switch (forced_link_speed) {
+			case LINK_SPEED_1G:
+				phba->cfg_link_speed =
+					LPFC_USER_LINK_SPEED_1G;
+				break;
+			case LINK_SPEED_2G:
+				phba->cfg_link_speed =
+					LPFC_USER_LINK_SPEED_2G;
+				break;
+			case LINK_SPEED_4G:
+				phba->cfg_link_speed =
+					LPFC_USER_LINK_SPEED_4G;
+				break;
+			case LINK_SPEED_8G:
+				phba->cfg_link_speed =
+					LPFC_USER_LINK_SPEED_8G;
+				break;
+			case LINK_SPEED_10G:
+				phba->cfg_link_speed =
+					LPFC_USER_LINK_SPEED_10G;
+				break;
+			case LINK_SPEED_16G:
+				phba->cfg_link_speed =
+					LPFC_USER_LINK_SPEED_16G;
+				break;
+			case LINK_SPEED_32G:
+				phba->cfg_link_speed =
+					LPFC_USER_LINK_SPEED_32G;
+				break;
+			case 0xffff:
+				phba->cfg_link_speed =
+					LPFC_USER_LINK_SPEED_AUTO;
+				break;
+			default:
+				lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+						"0047 Unrecognized link "
+						"speed : %d\n",
+						forced_link_speed);
+				phba->cfg_link_speed =
+					LPFC_USER_LINK_SPEED_AUTO;
+			}
+		}
+	}
+
 	/* Reset the DFT_HBA_Q_DEPTH to the max xri  */
 	length = phba->sli4_hba.max_cfg_param.max_xri -
 			lpfc_sli4_get_els_iocb_cnt(phba);
@@ -7256,6 +7312,7 @@ int
 lpfc_sli4_queue_create(struct lpfc_hba *phba)
 {
 	struct lpfc_queue *qdesc;
+	uint32_t wqesize;
 	int idx;
 
 	/*
@@ -7340,15 +7397,10 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 		phba->sli4_hba.fcp_cq[idx] = qdesc;
 
 		/* Create Fast Path FCP WQs */
-		if (phba->fcp_embed_io) {
-			qdesc = lpfc_sli4_queue_alloc(phba,
-						      LPFC_WQE128_SIZE,
-						      LPFC_WQE128_DEF_COUNT);
-		} else {
-			qdesc = lpfc_sli4_queue_alloc(phba,
-						      phba->sli4_hba.wq_esize,
-						      phba->sli4_hba.wq_ecount);
-		}
+		wqesize = (phba->fcp_embed_io) ?
+				LPFC_WQE128_SIZE : phba->sli4_hba.wq_esize;
+		qdesc = lpfc_sli4_queue_alloc(phba, wqesize,
+						phba->sli4_hba.wq_ecount);
 		if (!qdesc) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 					"0503 Failed allocate fast-path FCP "
@@ -10260,6 +10312,7 @@ lpfc_write_firmware(const struct firmware *fw, void *context)
 	int i, rc = 0;
 	struct lpfc_dmabuf *dmabuf, *next;
 	uint32_t offset = 0, temp_offset = 0;
+	uint32_t magic_number, ftype, fid, fsize;
 
 	/* It can be null in no-wait mode, sanity check */
 	if (!fw) {
@@ -10268,18 +10321,19 @@ lpfc_write_firmware(const struct firmware *fw, void *context)
 	}
 	image = (struct lpfc_grp_hdr *)fw->data;
 
+	magic_number = be32_to_cpu(image->magic_number);
+	ftype = bf_get_be32(lpfc_grp_hdr_file_type, image);
+	fid = bf_get_be32(lpfc_grp_hdr_id, image),
+	fsize = be32_to_cpu(image->size);
+
 	INIT_LIST_HEAD(&dma_buffer_list);
-	if ((be32_to_cpu(image->magic_number) != LPFC_GROUP_OJECT_MAGIC_NUM) ||
-	    (bf_get_be32(lpfc_grp_hdr_file_type, image) !=
-	     LPFC_FILE_TYPE_GROUP) ||
-	    (bf_get_be32(lpfc_grp_hdr_id, image) != LPFC_FILE_ID_GROUP) ||
-	    (be32_to_cpu(image->size) != fw->size)) {
+	if ((magic_number != LPFC_GROUP_OJECT_MAGIC_G5 &&
+	     magic_number != LPFC_GROUP_OJECT_MAGIC_G6) ||
+	    ftype != LPFC_FILE_TYPE_GROUP || fsize != fw->size) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"3022 Invalid FW image found. "
-				"Magic:%x Type:%x ID:%x\n",
-				be32_to_cpu(image->magic_number),
-				bf_get_be32(lpfc_grp_hdr_file_type, image),
-				bf_get_be32(lpfc_grp_hdr_id, image));
+				"Magic:%x Type:%x ID:%x Size %d %zd\n",
+				magic_number, ftype, fid, fsize, fw->size);
 		rc = -EINVAL;
 		goto release_out;
 	}
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index d197aa176dee..ad350d969bdc 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -413,15 +413,13 @@ lpfc_new_scsi_buf_s3(struct lpfc_vport *vport, int num_to_alloc)
 		 * struct fcp_cmnd, struct fcp_rsp and the number of bde's
 		 * necessary to support the sg_tablesize.
 		 */
-		psb->data = pci_pool_alloc(phba->lpfc_scsi_dma_buf_pool,
+		psb->data = pci_pool_zalloc(phba->lpfc_scsi_dma_buf_pool,
 					GFP_KERNEL, &psb->dma_handle);
 		if (!psb->data) {
 			kfree(psb);
 			break;
 		}
 
-		/* Initialize virtual ptrs to dma_buf region. */
-		memset(psb->data, 0, phba->cfg_sg_dma_buf_size);
 
 		/* Allocate iotag for psb->cur_iocbq. */
 		iotag = lpfc_sli_next_iotag(phba, &psb->cur_iocbq);
@@ -607,7 +605,7 @@ lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *phba,
 }
 
 /**
- * lpfc_sli4_post_scsi_sgl_list - Psot blocks of scsi buffer sgls from a list
+ * lpfc_sli4_post_scsi_sgl_list - Post blocks of scsi buffer sgls from a list
  * @phba: pointer to lpfc hba data structure.
  * @post_sblist: pointer to the scsi buffer list.
  *
@@ -736,7 +734,7 @@ lpfc_sli4_post_scsi_sgl_list(struct lpfc_hba *phba,
 }
 
 /**
- * lpfc_sli4_repost_scsi_sgl_list - Repsot all the allocated scsi buffer sgls
+ * lpfc_sli4_repost_scsi_sgl_list - Repost all the allocated scsi buffer sgls
  * @phba: pointer to lpfc hba data structure.
  *
  * This routine walks the list of scsi buffers that have been allocated and
@@ -821,13 +819,12 @@ lpfc_new_scsi_buf_s4(struct lpfc_vport *vport, int num_to_alloc)
 		 * for the struct fcp_cmnd, struct fcp_rsp and the number
 		 * of bde's necessary to support the sg_tablesize.
 		 */
-		psb->data = pci_pool_alloc(phba->lpfc_scsi_dma_buf_pool,
+		psb->data = pci_pool_zalloc(phba->lpfc_scsi_dma_buf_pool,
 						GFP_KERNEL, &psb->dma_handle);
 		if (!psb->data) {
 			kfree(psb);
 			break;
 		}
-		memset(psb->data, 0, phba->cfg_sg_dma_buf_size);
 
 		/*
 		 * 4K Page alignment is CRITICAL to BlockGuard, double check
@@ -857,7 +854,7 @@ lpfc_new_scsi_buf_s4(struct lpfc_vport *vport, int num_to_alloc)
 				psb->data, psb->dma_handle);
 			kfree(psb);
 			lpfc_printf_log(phba, KERN_ERR, LOG_FCP,
-					"3368 Failed to allocated IOTAG for"
+					"3368 Failed to allocate IOTAG for"
 					" XRI:0x%x\n", lxri);
 			lpfc_sli4_free_xri(phba, lxri);
 			break;
@@ -1136,7 +1133,7 @@ lpfc_release_scsi_buf(struct lpfc_hba *phba, struct lpfc_scsi_buf *psb)
  *
  * This routine does the pci dma mapping for scatter-gather list of scsi cmnd
  * field of @lpfc_cmd for device with SLI-3 interface spec. This routine scans
- * through sg elements and format the bdea. This routine also initializes all
+ * through sg elements and format the bde. This routine also initializes all
  * IOCB fields which are dependent on scsi command request buffer.
  *
  * Return codes:
@@ -1269,13 +1266,16 @@ lpfc_scsi_prep_dma_buf_s3(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd)
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 
-/* Return if if error injection is detected by Initiator */
+/* Return BG_ERR_INIT if error injection is detected by Initiator */
 #define BG_ERR_INIT	0x1
-/* Return if if error injection is detected by Target */
+/* Return BG_ERR_TGT if error injection is detected by Target */
 #define BG_ERR_TGT	0x2
-/* Return if if swapping CSUM<-->CRC is required for error injection */
+/* Return BG_ERR_SWAP if swapping CSUM<-->CRC is required for error injection */
 #define BG_ERR_SWAP	0x10
-/* Return if disabling Guard/Ref/App checking is required for error injection */
+/**
+ * Return BG_ERR_CHECK if disabling Guard/Ref/App checking is required for
+ * error injection
+ **/
 #define BG_ERR_CHECK	0x20
 
 /**
@@ -4139,13 +4139,13 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 
 	lpfc_scsi_unprep_dma_buf(phba, lpfc_cmd);
 
-	/* The sdev is not guaranteed to be valid post scsi_done upcall. */
-	cmd->scsi_done(cmd);
-
 	spin_lock_irqsave(&phba->hbalock, flags);
 	lpfc_cmd->pCmd = NULL;
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 
+	/* The sdev is not guaranteed to be valid post scsi_done upcall. */
+	cmd->scsi_done(cmd);
+
 	/*
 	 * If there is a thread waiting for command completion
 	 * wake up the thread.
@@ -4822,7 +4822,7 @@ wait_for_cmpl:
 		ret = FAILED;
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_FCP,
 				 "0748 abort handler timed out waiting "
-				 "for abortng I/O (xri:x%x) to complete: "
+				 "for aborting I/O (xri:x%x) to complete: "
 				 "ret %#x, ID %d, LUN %llu\n",
 				 iocb->sli4_xritag, ret,
 				 cmnd->device->id, cmnd->device->lun);
@@ -4945,26 +4945,30 @@ lpfc_check_fcp_rsp(struct lpfc_vport *vport, struct lpfc_scsi_buf *lpfc_cmd)
  *   0x2002 - Success.
  **/
 static int
-lpfc_send_taskmgmt(struct lpfc_vport *vport, struct lpfc_rport_data *rdata,
-		    unsigned  tgt_id, uint64_t lun_id,
-		    uint8_t task_mgmt_cmd)
+lpfc_send_taskmgmt(struct lpfc_vport *vport, struct scsi_cmnd *cmnd,
+		   unsigned int tgt_id, uint64_t lun_id,
+		   uint8_t task_mgmt_cmd)
 {
 	struct lpfc_hba   *phba = vport->phba;
 	struct lpfc_scsi_buf *lpfc_cmd;
 	struct lpfc_iocbq *iocbq;
 	struct lpfc_iocbq *iocbqrsp;
-	struct lpfc_nodelist *pnode = rdata->pnode;
+	struct lpfc_rport_data *rdata;
+	struct lpfc_nodelist *pnode;
 	int ret;
 	int status;
 
-	if (!pnode || !NLP_CHK_NODE_ACT(pnode))
+	rdata = lpfc_rport_data_from_scsi_device(cmnd->device);
+	if (!rdata || !rdata->pnode || !NLP_CHK_NODE_ACT(rdata->pnode))
 		return FAILED;
+	pnode = rdata->pnode;
 
-	lpfc_cmd = lpfc_get_scsi_buf(phba, rdata->pnode);
+	lpfc_cmd = lpfc_get_scsi_buf(phba, pnode);
 	if (lpfc_cmd == NULL)
 		return FAILED;
 	lpfc_cmd->timeout = phba->cfg_task_mgmt_tmo;
 	lpfc_cmd->rdata = rdata;
+	lpfc_cmd->pCmd = cmnd;
 
 	status = lpfc_scsi_prep_task_mgmt_cmd(vport, lpfc_cmd, lun_id,
 					   task_mgmt_cmd);
@@ -5171,7 +5175,7 @@ lpfc_device_reset_handler(struct scsi_cmnd *cmnd)
 	fc_host_post_vendor_event(shost, fc_get_event_number(),
 		sizeof(scsi_event), (char *)&scsi_event, LPFC_NL_VENDOR_ID);
 
-	status = lpfc_send_taskmgmt(vport, rdata, tgt_id, lun_id,
+	status = lpfc_send_taskmgmt(vport, cmnd, tgt_id, lun_id,
 						FCP_LUN_RESET);
 
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_FCP,
@@ -5249,7 +5253,7 @@ lpfc_target_reset_handler(struct scsi_cmnd *cmnd)
 	fc_host_post_vendor_event(shost, fc_get_event_number(),
 		sizeof(scsi_event), (char *)&scsi_event, LPFC_NL_VENDOR_ID);
 
-	status = lpfc_send_taskmgmt(vport, rdata, tgt_id, lun_id,
+	status = lpfc_send_taskmgmt(vport, cmnd, tgt_id, lun_id,
 					FCP_TARGET_RESET);
 
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_FCP,
@@ -5328,7 +5332,7 @@ lpfc_bus_reset_handler(struct scsi_cmnd *cmnd)
 		if (!match)
 			continue;
 
-		status = lpfc_send_taskmgmt(vport, ndlp->rport->dd_data,
+		status = lpfc_send_taskmgmt(vport, cmnd,
 					i, 0, FCP_TARGET_RESET);
 
 		if (status != SUCCESS) {
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index c5326055beee..4faa7672fc1d 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -47,6 +47,7 @@
 #include "lpfc_compat.h"
 #include "lpfc_debugfs.h"
 #include "lpfc_vport.h"
+#include "lpfc_version.h"
 
 /* There are only four IOCB completion types. */
 typedef enum _lpfc_iocb_type {
@@ -1323,18 +1324,20 @@ lpfc_sli_ringtxcmpl_put(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 {
 	lockdep_assert_held(&phba->hbalock);
 
-	BUG_ON(!piocb || !piocb->vport);
+	BUG_ON(!piocb);
 
 	list_add_tail(&piocb->list, &pring->txcmplq);
 	piocb->iocb_flag |= LPFC_IO_ON_TXCMPLQ;
 
 	if ((unlikely(pring->ringno == LPFC_ELS_RING)) &&
 	   (piocb->iocb.ulpCommand != CMD_ABORT_XRI_CN) &&
-	   (piocb->iocb.ulpCommand != CMD_CLOSE_XRI_CN) &&
-	    (!(piocb->vport->load_flag & FC_UNLOADING)))
-		mod_timer(&piocb->vport->els_tmofunc,
-			  jiffies +
-			  msecs_to_jiffies(1000 * (phba->fc_ratov << 1)));
+	   (piocb->iocb.ulpCommand != CMD_CLOSE_XRI_CN)) {
+		BUG_ON(!piocb->vport);
+		if (!(piocb->vport->load_flag & FC_UNLOADING))
+			mod_timer(&piocb->vport->els_tmofunc,
+				  jiffies +
+				  msecs_to_jiffies(1000 * (phba->fc_ratov << 1)));
+	}
 
 	return 0;
 }
@@ -2676,15 +2679,16 @@ lpfc_sli_iocbq_lookup(struct lpfc_hba *phba,
 
 	if (iotag != 0 && iotag <= phba->sli.last_iotag) {
 		cmd_iocb = phba->sli.iocbq_lookup[iotag];
-		list_del_init(&cmd_iocb->list);
 		if (cmd_iocb->iocb_flag & LPFC_IO_ON_TXCMPLQ) {
+			/* remove from txcmpl queue list */
+			list_del_init(&cmd_iocb->list);
 			cmd_iocb->iocb_flag &= ~LPFC_IO_ON_TXCMPLQ;
+			return cmd_iocb;
 		}
-		return cmd_iocb;
 	}
 
 	lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
-			"0317 iotag x%x is out off "
+			"0317 iotag x%x is out of "
 			"range: max iotag x%x wd0 x%x\n",
 			iotag, phba->sli.last_iotag,
 			*(((uint32_t *) &prspiocb->iocb) + 7));
@@ -2719,8 +2723,9 @@ lpfc_sli_iocbq_lookup_by_tag(struct lpfc_hba *phba,
 			return cmd_iocb;
 		}
 	}
+
 	lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
-			"0372 iotag x%x is out off range: max iotag (x%x)\n",
+			"0372 iotag x%x is out of range: max iotag (x%x)\n",
 			iotag, phba->sli.last_iotag);
 	return NULL;
 }
@@ -6289,6 +6294,25 @@ lpfc_sli4_repost_els_sgl_list(struct lpfc_hba *phba)
 	return 0;
 }
 
+void
+lpfc_set_host_data(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox)
+{
+	uint32_t len;
+
+	len = sizeof(struct lpfc_mbx_set_host_data) -
+		sizeof(struct lpfc_sli4_cfg_mhdr);
+	lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_COMMON,
+			 LPFC_MBOX_OPCODE_SET_HOST_DATA, len,
+			 LPFC_SLI4_MBX_EMBED);
+
+	mbox->u.mqe.un.set_host_data.param_id = LPFC_SET_HOST_OS_DRIVER_VERSION;
+	mbox->u.mqe.un.set_host_data.param_len = 8;
+	snprintf(mbox->u.mqe.un.set_host_data.data,
+		 LPFC_HOST_OS_DRIVER_VERSION_SIZE,
+		 "Linux %s v"LPFC_DRIVER_VERSION,
+		 (phba->hba_flag & HBA_FCOE_MODE) ? "FCoE" : "FC");
+}
+
 /**
  * lpfc_sli4_hba_setup - SLI4 device intialization PCI function
  * @phba: Pointer to HBA context object.
@@ -6540,6 +6564,15 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 		goto out_free_mbox;
 	}
 
+	lpfc_set_host_data(phba, mboxq);
+
+	rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
+	if (rc) {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_MBOX | LOG_SLI,
+				"2134 Failed to set host os driver version %x",
+				rc);
+	}
+
 	/* Read the port's service parameters. */
 	rc = lpfc_read_sparam(phba, mboxq, vport->vpi);
 	if (rc) {
@@ -11779,6 +11812,8 @@ lpfc_sli4_els_wcqe_to_rspiocbq(struct lpfc_hba *phba,
 	/* Look up the ELS command IOCB and create pseudo response IOCB */
 	cmdiocbq = lpfc_sli_iocbq_lookup_by_tag(phba, pring,
 				bf_get(lpfc_wcqe_c_request_tag, wcqe));
+	/* Put the iocb back on the txcmplq */
+	lpfc_sli_ringtxcmpl_put(phba, pring, cmdiocbq);
 	spin_unlock_irqrestore(&pring->ring_lock, iflags);
 
 	if (unlikely(!cmdiocbq)) {
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index c9bf20eb7223..50bfc43ebcb0 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -18,7 +18,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "11.2.0.0."
+#define LPFC_DRIVER_VERSION "11.2.0.2"
 #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 a590089b9397..ccb68d12692c 100644
--- a/drivers/scsi/mac_scsi.c
+++ b/drivers/scsi/mac_scsi.c
@@ -28,17 +28,15 @@
 
 /* Definitions for the core NCR5380 driver. */
 
-#define NCR5380_implementation_fields   unsigned char *pdma_base; \
-                                        int pdma_residual
+#define NCR5380_implementation_fields   int pdma_residual
 
-#define NCR5380_read(reg)               macscsi_read(instance, reg)
-#define NCR5380_write(reg, value)       macscsi_write(instance, reg, value)
+#define NCR5380_read(reg)           in_8(hostdata->io + ((reg) << 4))
+#define NCR5380_write(reg, value)   out_8(hostdata->io + ((reg) << 4), value)
 
-#define NCR5380_dma_xfer_len(instance, cmd, phase) \
-        macscsi_dma_xfer_len(instance, cmd)
+#define NCR5380_dma_xfer_len            macscsi_dma_xfer_len
 #define NCR5380_dma_recv_setup          macscsi_pread
 #define NCR5380_dma_send_setup          macscsi_pwrite
-#define NCR5380_dma_residual(instance)  (hostdata->pdma_residual)
+#define NCR5380_dma_residual            macscsi_dma_residual
 
 #define NCR5380_intr                    macscsi_intr
 #define NCR5380_queue_command           macscsi_queue_command
@@ -61,20 +59,6 @@ module_param(setup_hostid, int, 0);
 static int setup_toshiba_delay = -1;
 module_param(setup_toshiba_delay, int, 0);
 
-/*
- * NCR 5380 register access functions
- */
-
-static inline char macscsi_read(struct Scsi_Host *instance, int reg)
-{
-	return in_8(instance->base + (reg << 4));
-}
-
-static inline void macscsi_write(struct Scsi_Host *instance, int reg, int value)
-{
-	out_8(instance->base + (reg << 4), value);
-}
-
 #ifndef MODULE
 static int __init mac_scsi_setup(char *str)
 {
@@ -167,16 +151,15 @@ __asm__ __volatile__					\
      : "0"(s), "1"(d), "2"(n)				\
      : "d0")
 
-static int macscsi_pread(struct Scsi_Host *instance,
-                         unsigned char *dst, int len)
+static inline int macscsi_pread(struct NCR5380_hostdata *hostdata,
+                                unsigned char *dst, int len)
 {
-	struct NCR5380_hostdata *hostdata = shost_priv(instance);
-	unsigned char *s = hostdata->pdma_base + (INPUT_DATA_REG << 4);
+	unsigned char *s = hostdata->pdma_io + (INPUT_DATA_REG << 4);
 	unsigned char *d = dst;
 	int n = len;
 	int transferred;
 
-	while (!NCR5380_poll_politely(instance, BUS_AND_STATUS_REG,
+	while (!NCR5380_poll_politely(hostdata, BUS_AND_STATUS_REG,
 	                              BASR_DRQ | BASR_PHASE_MATCH,
 	                              BASR_DRQ | BASR_PHASE_MATCH, HZ / 64)) {
 		CP_IO_TO_MEM(s, d, n);
@@ -189,23 +172,23 @@ static int macscsi_pread(struct Scsi_Host *instance,
 			return 0;
 
 		/* Target changed phase early? */
-		if (NCR5380_poll_politely2(instance, STATUS_REG, SR_REQ, SR_REQ,
+		if (NCR5380_poll_politely2(hostdata, STATUS_REG, SR_REQ, SR_REQ,
 		                           BUS_AND_STATUS_REG, BASR_ACK, BASR_ACK, HZ / 64) < 0)
 			scmd_printk(KERN_ERR, hostdata->connected,
 			            "%s: !REQ and !ACK\n", __func__);
 		if (!(NCR5380_read(BUS_AND_STATUS_REG) & BASR_PHASE_MATCH))
 			return 0;
 
-		dsprintk(NDEBUG_PSEUDO_DMA, instance,
+		dsprintk(NDEBUG_PSEUDO_DMA, hostdata->host,
 		         "%s: bus error (%d/%d)\n", __func__, transferred, len);
-		NCR5380_dprint(NDEBUG_PSEUDO_DMA, instance);
+		NCR5380_dprint(NDEBUG_PSEUDO_DMA, hostdata->host);
 		d = dst + transferred;
 		n = len - transferred;
 	}
 
 	scmd_printk(KERN_ERR, hostdata->connected,
 	            "%s: phase mismatch or !DRQ\n", __func__);
-	NCR5380_dprint(NDEBUG_PSEUDO_DMA, instance);
+	NCR5380_dprint(NDEBUG_PSEUDO_DMA, hostdata->host);
 	return -1;
 }
 
@@ -270,16 +253,15 @@ __asm__ __volatile__					\
      : "0"(s), "1"(d), "2"(n)				\
      : "d0")
 
-static int macscsi_pwrite(struct Scsi_Host *instance,
-                          unsigned char *src, int len)
+static inline int macscsi_pwrite(struct NCR5380_hostdata *hostdata,
+                                 unsigned char *src, int len)
 {
-	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	unsigned char *s = src;
-	unsigned char *d = hostdata->pdma_base + (OUTPUT_DATA_REG << 4);
+	unsigned char *d = hostdata->pdma_io + (OUTPUT_DATA_REG << 4);
 	int n = len;
 	int transferred;
 
-	while (!NCR5380_poll_politely(instance, BUS_AND_STATUS_REG,
+	while (!NCR5380_poll_politely(hostdata, BUS_AND_STATUS_REG,
 	                              BASR_DRQ | BASR_PHASE_MATCH,
 	                              BASR_DRQ | BASR_PHASE_MATCH, HZ / 64)) {
 		CP_MEM_TO_IO(s, d, n);
@@ -288,7 +270,7 @@ static int macscsi_pwrite(struct Scsi_Host *instance,
 		hostdata->pdma_residual = len - transferred;
 
 		/* Target changed phase early? */
-		if (NCR5380_poll_politely2(instance, STATUS_REG, SR_REQ, SR_REQ,
+		if (NCR5380_poll_politely2(hostdata, STATUS_REG, SR_REQ, SR_REQ,
 		                           BUS_AND_STATUS_REG, BASR_ACK, BASR_ACK, HZ / 64) < 0)
 			scmd_printk(KERN_ERR, hostdata->connected,
 			            "%s: !REQ and !ACK\n", __func__);
@@ -297,7 +279,7 @@ static int macscsi_pwrite(struct Scsi_Host *instance,
 
 		/* No bus error. */
 		if (n == 0) {
-			if (NCR5380_poll_politely(instance, TARGET_COMMAND_REG,
+			if (NCR5380_poll_politely(hostdata, TARGET_COMMAND_REG,
 			                          TCR_LAST_BYTE_SENT,
 			                          TCR_LAST_BYTE_SENT, HZ / 64) < 0)
 				scmd_printk(KERN_ERR, hostdata->connected,
@@ -305,25 +287,23 @@ static int macscsi_pwrite(struct Scsi_Host *instance,
 			return 0;
 		}
 
-		dsprintk(NDEBUG_PSEUDO_DMA, instance,
+		dsprintk(NDEBUG_PSEUDO_DMA, hostdata->host,
 		         "%s: bus error (%d/%d)\n", __func__, transferred, len);
-		NCR5380_dprint(NDEBUG_PSEUDO_DMA, instance);
+		NCR5380_dprint(NDEBUG_PSEUDO_DMA, hostdata->host);
 		s = src + transferred;
 		n = len - transferred;
 	}
 
 	scmd_printk(KERN_ERR, hostdata->connected,
 	            "%s: phase mismatch or !DRQ\n", __func__);
-	NCR5380_dprint(NDEBUG_PSEUDO_DMA, instance);
+	NCR5380_dprint(NDEBUG_PSEUDO_DMA, hostdata->host);
 
 	return -1;
 }
 
-static int macscsi_dma_xfer_len(struct Scsi_Host *instance,
+static int macscsi_dma_xfer_len(struct NCR5380_hostdata *hostdata,
                                 struct scsi_cmnd *cmd)
 {
-	struct NCR5380_hostdata *hostdata = shost_priv(instance);
-
 	if (hostdata->flags & FLAG_NO_PSEUDO_DMA ||
 	    cmd->SCp.this_residual < 16)
 		return 0;
@@ -331,6 +311,11 @@ static int macscsi_dma_xfer_len(struct Scsi_Host *instance,
 	return cmd->SCp.this_residual;
 }
 
+static int macscsi_dma_residual(struct NCR5380_hostdata *hostdata)
+{
+	return hostdata->pdma_residual;
+}
+
 #include "NCR5380.c"
 
 #define DRV_MODULE_NAME         "mac_scsi"
@@ -356,6 +341,7 @@ static struct scsi_host_template mac_scsi_template = {
 static int __init mac_scsi_probe(struct platform_device *pdev)
 {
 	struct Scsi_Host *instance;
+	struct NCR5380_hostdata *hostdata;
 	int error;
 	int host_flags = 0;
 	struct resource *irq, *pio_mem, *pdma_mem = NULL;
@@ -388,17 +374,18 @@ static int __init mac_scsi_probe(struct platform_device *pdev)
 	if (!instance)
 		return -ENOMEM;
 
-	instance->base = pio_mem->start;
 	if (irq)
 		instance->irq = irq->start;
 	else
 		instance->irq = NO_IRQ;
 
-	if (pdma_mem && setup_use_pdma) {
-		struct NCR5380_hostdata *hostdata = shost_priv(instance);
+	hostdata = shost_priv(instance);
+	hostdata->base = pio_mem->start;
+	hostdata->io = (void *)pio_mem->start;
 
-		hostdata->pdma_base = (unsigned char *)pdma_mem->start;
-	} else
+	if (pdma_mem && setup_use_pdma)
+		hostdata->pdma_io = (void *)pdma_mem->start;
+	else
 		host_flags |= FLAG_NO_PSEUDO_DMA;
 
 	host_flags |= setup_toshiba_delay > 0 ? FLAG_TOSHIBA_DELAY : 0;
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 9d05302a3bcd..3c63c292cb92 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -34,7 +34,7 @@
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/blkdev.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
diff --git a/drivers/scsi/megaraid/megaraid_mm.h b/drivers/scsi/megaraid/megaraid_mm.h
index 55b425c0a654..a30e725f2d5c 100644
--- a/drivers/scsi/megaraid/megaraid_mm.h
+++ b/drivers/scsi/megaraid/megaraid_mm.h
@@ -17,7 +17,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/fs.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index 3aaea713bf37..fdd519c1dd57 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -35,8 +35,8 @@
 /*
  * MegaRAID SAS Driver meta data
  */
-#define MEGASAS_VERSION				"06.811.02.00-rc1"
-#define MEGASAS_RELDATE				"April 12, 2016"
+#define MEGASAS_VERSION				"06.812.07.00-rc1"
+#define MEGASAS_RELDATE				"August 22, 2016"
 
 /*
  * Device IDs
@@ -1429,6 +1429,8 @@ enum FW_BOOT_CONTEXT {
 #define MR_MAX_REPLY_QUEUES_EXT_OFFSET_SHIFT    14
 #define MR_MAX_MSIX_REG_ARRAY                   16
 #define MR_RDPQ_MODE_OFFSET			0X00800000
+#define MR_CAN_HANDLE_SYNC_CACHE_OFFSET		0X01000000
+
 /*
 * register set for both 1068 and 1078 controllers
 * structure extended for 1078 registers
@@ -2118,7 +2120,6 @@ struct megasas_instance {
 	u32 ctrl_context_pages;
 	struct megasas_ctrl_info *ctrl_info;
 	unsigned int msix_vectors;
-	struct msix_entry msixentry[MEGASAS_MAX_MSIX_QUEUES];
 	struct megasas_irq_context irq_context[MEGASAS_MAX_MSIX_QUEUES];
 	u64 map_id;
 	u64 pd_seq_map_id;
@@ -2140,6 +2141,7 @@ struct megasas_instance {
 	u8 is_imr;
 	u8 is_rdpq;
 	bool dev_handle;
+	bool fw_sync_cache_support;
 };
 struct MR_LD_VF_MAP {
 	u32 size;
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index d8b1fbd4c8aa..d5cf15eb8c5e 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -42,7 +42,7 @@
 #include <linux/delay.h>
 #include <linux/uio.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fs.h>
 #include <linux/compat.h>
 #include <linux/blkdev.h>
@@ -1700,11 +1700,8 @@ megasas_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 		goto out_done;
 	}
 
-	/*
-	 * FW takes care of flush cache on its own for Virtual Disk.
-	 * No need to send it down for VD. For JBOD send SYNCHRONIZE_CACHE to FW.
-	 */
-	if ((scmd->cmnd[0] == SYNCHRONIZE_CACHE) && MEGASAS_IS_LOGICAL(scmd)) {
+	if ((scmd->cmnd[0] == SYNCHRONIZE_CACHE) && MEGASAS_IS_LOGICAL(scmd) &&
+		(!instance->fw_sync_cache_support)) {
 		scmd->result = DID_OK << 16;
 		goto out_done;
 	}
@@ -4840,7 +4837,7 @@ fail_alloc_cmds:
 }
 
 /*
- * megasas_setup_irqs_msix -		register legacy interrupts.
+ * megasas_setup_irqs_ioapic -		register legacy interrupts.
  * @instance:				Adapter soft state
  *
  * Do not enable interrupt, only setup ISRs.
@@ -4855,8 +4852,9 @@ megasas_setup_irqs_ioapic(struct megasas_instance *instance)
 	pdev = instance->pdev;
 	instance->irq_context[0].instance = instance;
 	instance->irq_context[0].MSIxIndex = 0;
-	if (request_irq(pdev->irq, instance->instancet->service_isr,
-		IRQF_SHARED, "megasas", &instance->irq_context[0])) {
+	if (request_irq(pci_irq_vector(pdev, 0),
+			instance->instancet->service_isr, IRQF_SHARED,
+			"megasas", &instance->irq_context[0])) {
 		dev_err(&instance->pdev->dev,
 				"Failed to register IRQ from %s %d\n",
 				__func__, __LINE__);
@@ -4877,28 +4875,23 @@ megasas_setup_irqs_ioapic(struct megasas_instance *instance)
 static int
 megasas_setup_irqs_msix(struct megasas_instance *instance, u8 is_probe)
 {
-	int i, j, cpu;
+	int i, j;
 	struct pci_dev *pdev;
 
 	pdev = instance->pdev;
 
 	/* Try MSI-x */
-	cpu = cpumask_first(cpu_online_mask);
 	for (i = 0; i < instance->msix_vectors; i++) {
 		instance->irq_context[i].instance = instance;
 		instance->irq_context[i].MSIxIndex = i;
-		if (request_irq(instance->msixentry[i].vector,
+		if (request_irq(pci_irq_vector(pdev, i),
 			instance->instancet->service_isr, 0, "megasas",
 			&instance->irq_context[i])) {
 			dev_err(&instance->pdev->dev,
 				"Failed to register IRQ for vector %d.\n", i);
-			for (j = 0; j < i; j++) {
-				if (smp_affinity_enable)
-					irq_set_affinity_hint(
-						instance->msixentry[j].vector, NULL);
-				free_irq(instance->msixentry[j].vector,
-					&instance->irq_context[j]);
-			}
+			for (j = 0; j < i; j++)
+				free_irq(pci_irq_vector(pdev, j),
+					 &instance->irq_context[j]);
 			/* Retry irq register for IO_APIC*/
 			instance->msix_vectors = 0;
 			if (is_probe)
@@ -4906,14 +4899,6 @@ megasas_setup_irqs_msix(struct megasas_instance *instance, u8 is_probe)
 			else
 				return -1;
 		}
-		if (smp_affinity_enable) {
-			if (irq_set_affinity_hint(instance->msixentry[i].vector,
-				get_cpu_mask(cpu)))
-				dev_err(&instance->pdev->dev,
-					"Failed to set affinity hint"
-					" for cpu %d\n", cpu);
-			cpu = cpumask_next(cpu, cpu_online_mask);
-		}
 	}
 	return 0;
 }
@@ -4930,14 +4915,12 @@ megasas_destroy_irqs(struct megasas_instance *instance) {
 
 	if (instance->msix_vectors)
 		for (i = 0; i < instance->msix_vectors; i++) {
-			if (smp_affinity_enable)
-				irq_set_affinity_hint(
-					instance->msixentry[i].vector, NULL);
-			free_irq(instance->msixentry[i].vector,
+			free_irq(pci_irq_vector(instance->pdev, i),
 				 &instance->irq_context[i]);
 		}
 	else
-		free_irq(instance->pdev->irq, &instance->irq_context[0]);
+		free_irq(pci_irq_vector(instance->pdev, 0),
+			 &instance->irq_context[0]);
 }
 
 /**
@@ -5095,6 +5078,8 @@ static int megasas_init_fw(struct megasas_instance *instance)
 	msix_enable = (instance->instancet->read_fw_status_reg(reg_set) &
 		       0x4000000) >> 0x1a;
 	if (msix_enable && !msix_disable) {
+		int irq_flags = PCI_IRQ_MSIX;
+
 		scratch_pad_2 = readl
 			(&instance->reg_set->outbound_scratch_pad_2);
 		/* Check max MSI-X vectors */
@@ -5131,15 +5116,18 @@ static int megasas_init_fw(struct megasas_instance *instance)
 		/* Don't bother allocating more MSI-X vectors than cpus */
 		instance->msix_vectors = min(instance->msix_vectors,
 					     (unsigned int)num_online_cpus());
-		for (i = 0; i < instance->msix_vectors; i++)
-			instance->msixentry[i].entry = i;
-		i = pci_enable_msix_range(instance->pdev, instance->msixentry,
-					  1, instance->msix_vectors);
+		if (smp_affinity_enable)
+			irq_flags |= PCI_IRQ_AFFINITY;
+		i = pci_alloc_irq_vectors(instance->pdev, 1,
+					  instance->msix_vectors, irq_flags);
 		if (i > 0)
 			instance->msix_vectors = i;
 		else
 			instance->msix_vectors = 0;
 	}
+	i = pci_alloc_irq_vectors(instance->pdev, 1, 1, PCI_IRQ_LEGACY);
+	if (i < 0)
+		goto fail_setup_irqs;
 
 	dev_info(&instance->pdev->dev,
 		"firmware supports msix\t: (%d)", fw_msix_count);
@@ -5152,11 +5140,6 @@ static int megasas_init_fw(struct megasas_instance *instance)
 	tasklet_init(&instance->isr_tasklet, instance->instancet->tasklet,
 		(unsigned long)instance);
 
-	if (instance->msix_vectors ?
-		megasas_setup_irqs_msix(instance, 1) :
-		megasas_setup_irqs_ioapic(instance))
-		goto fail_setup_irqs;
-
 	instance->ctrl_info = kzalloc(sizeof(struct megasas_ctrl_info),
 				GFP_KERNEL);
 	if (instance->ctrl_info == NULL)
@@ -5172,6 +5155,10 @@ static int megasas_init_fw(struct megasas_instance *instance)
 	if (instance->instancet->init_adapter(instance))
 		goto fail_init_adapter;
 
+	if (instance->msix_vectors ?
+		megasas_setup_irqs_msix(instance, 1) :
+		megasas_setup_irqs_ioapic(instance))
+		goto fail_init_adapter;
 
 	instance->instancet->enable_intr(instance);
 
@@ -5315,7 +5302,7 @@ fail_init_adapter:
 	megasas_destroy_irqs(instance);
 fail_setup_irqs:
 	if (instance->msix_vectors)
-		pci_disable_msix(instance->pdev);
+		pci_free_irq_vectors(instance->pdev);
 	instance->msix_vectors = 0;
 fail_ready_state:
 	kfree(instance->ctrl_info);
@@ -5584,7 +5571,6 @@ static int megasas_io_attach(struct megasas_instance *instance)
 	/*
 	 * Export parameters required by SCSI mid-layer
 	 */
-	host->irq = instance->pdev->irq;
 	host->unique_id = instance->unique_id;
 	host->can_queue = instance->max_scsi_cmds;
 	host->this_id = instance->init_id;
@@ -5947,7 +5933,7 @@ fail_io_attach:
 	else
 		megasas_release_mfi(instance);
 	if (instance->msix_vectors)
-		pci_disable_msix(instance->pdev);
+		pci_free_irq_vectors(instance->pdev);
 fail_init_mfi:
 fail_alloc_dma_buf:
 	if (instance->evt_detail)
@@ -6105,7 +6091,7 @@ megasas_suspend(struct pci_dev *pdev, pm_message_t state)
 	megasas_destroy_irqs(instance);
 
 	if (instance->msix_vectors)
-		pci_disable_msix(instance->pdev);
+		pci_free_irq_vectors(instance->pdev);
 
 	pci_save_state(pdev);
 	pci_disable_device(pdev);
@@ -6125,6 +6111,7 @@ megasas_resume(struct pci_dev *pdev)
 	int rval;
 	struct Scsi_Host *host;
 	struct megasas_instance *instance;
+	int irq_flags = PCI_IRQ_LEGACY;
 
 	instance = pci_get_drvdata(pdev);
 	host = instance->host;
@@ -6160,9 +6147,15 @@ megasas_resume(struct pci_dev *pdev)
 		goto fail_ready_state;
 
 	/* Now re-enable MSI-X */
-	if (instance->msix_vectors &&
-	    pci_enable_msix_exact(instance->pdev, instance->msixentry,
-				  instance->msix_vectors))
+	if (instance->msix_vectors) {
+		irq_flags = PCI_IRQ_MSIX;
+		if (smp_affinity_enable)
+			irq_flags |= PCI_IRQ_AFFINITY;
+	}
+	rval = pci_alloc_irq_vectors(instance->pdev, 1,
+				     instance->msix_vectors ?
+				     instance->msix_vectors : 1, irq_flags);
+	if (rval < 0)
 		goto fail_reenable_msix;
 
 	if (instance->ctrl_context) {
@@ -6245,6 +6238,34 @@ fail_reenable_msix:
 #define megasas_resume	NULL
 #endif
 
+static inline int
+megasas_wait_for_adapter_operational(struct megasas_instance *instance)
+{
+	int wait_time = MEGASAS_RESET_WAIT_TIME * 2;
+	int i;
+
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR)
+		return 1;
+
+	for (i = 0; i < wait_time; i++) {
+		if (atomic_read(&instance->adprecovery)	== MEGASAS_HBA_OPERATIONAL)
+			break;
+
+		if (!(i % MEGASAS_RESET_NOTICE_INTERVAL))
+			dev_notice(&instance->pdev->dev, "waiting for controller reset to finish\n");
+
+		msleep(1000);
+	}
+
+	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
+		dev_info(&instance->pdev->dev, "%s timed out while waiting for HBA to recover.\n",
+			__func__);
+		return 1;
+	}
+
+	return 0;
+}
+
 /**
  * megasas_detach_one -	PCI hot"un"plug entry point
  * @pdev:		PCI device structure
@@ -6269,9 +6290,14 @@ static void megasas_detach_one(struct pci_dev *pdev)
 	if (instance->fw_crash_state != UNAVAILABLE)
 		megasas_free_host_crash_buffer(instance);
 	scsi_remove_host(instance->host);
+
+	if (megasas_wait_for_adapter_operational(instance))
+		goto skip_firing_dcmds;
+
 	megasas_flush_cache(instance);
 	megasas_shutdown_controller(instance, MR_DCMD_CTRL_SHUTDOWN);
 
+skip_firing_dcmds:
 	/* cancel the delayed work if this work still in queue*/
 	if (instance->ev != NULL) {
 		struct megasas_aen_event *ev = instance->ev;
@@ -6302,7 +6328,7 @@ static void megasas_detach_one(struct pci_dev *pdev)
 	megasas_destroy_irqs(instance);
 
 	if (instance->msix_vectors)
-		pci_disable_msix(instance->pdev);
+		pci_free_irq_vectors(instance->pdev);
 
 	if (instance->ctrl_context) {
 		megasas_release_fusion(instance);
@@ -6385,13 +6411,19 @@ static void megasas_shutdown(struct pci_dev *pdev)
 	struct megasas_instance *instance = pci_get_drvdata(pdev);
 
 	instance->unload = 1;
+
+	if (megasas_wait_for_adapter_operational(instance))
+		goto skip_firing_dcmds;
+
 	megasas_flush_cache(instance);
 	megasas_shutdown_controller(instance, MR_DCMD_CTRL_SHUTDOWN);
+
+skip_firing_dcmds:
 	instance->instancet->disable_intr(instance);
 	megasas_destroy_irqs(instance);
 
 	if (instance->msix_vectors)
-		pci_disable_msix(instance->pdev);
+		pci_free_irq_vectors(instance->pdev);
 }
 
 /**
@@ -6752,8 +6784,7 @@ static int megasas_mgmt_ioctl_fw(struct file *file, unsigned long arg)
 	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
 		spin_unlock_irqrestore(&instance->hba_lock, flags);
 
-		dev_err(&instance->pdev->dev, "timed out while"
-			"waiting for HBA to recover\n");
+		dev_err(&instance->pdev->dev, "timed out while waiting for HBA to recover\n");
 		error = -ENODEV;
 		goto out_up;
 	}
@@ -6821,8 +6852,7 @@ static int megasas_mgmt_ioctl_aen(struct file *file, unsigned long arg)
 	spin_lock_irqsave(&instance->hba_lock, flags);
 	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
 		spin_unlock_irqrestore(&instance->hba_lock, flags);
-		dev_err(&instance->pdev->dev, "timed out while waiting"
-				"for HBA to recover\n");
+		dev_err(&instance->pdev->dev, "timed out while waiting for HBA to recover\n");
 		return -ENODEV;
 	}
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
diff --git a/drivers/scsi/megaraid/megaraid_sas_fp.c b/drivers/scsi/megaraid/megaraid_sas_fp.c
index e413113c86ac..f237d0003df3 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fp.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fp.c
@@ -782,7 +782,8 @@ static u8 mr_spanset_get_phy_params(struct megasas_instance *instance, u32 ld,
 			(raid->regTypeReqOnRead != REGION_TYPE_UNUSED))))
 			pRAID_Context->regLockFlags = REGION_TYPE_EXCLUSIVE;
 		else if (raid->level == 1) {
-			pd = MR_ArPdGet(arRef, physArm + 1, map);
+			physArm = physArm + 1;
+			pd = MR_ArPdGet(arRef, physArm, map);
 			if (pd != MR_PD_INVALID)
 				*pDevHandle = MR_PdDevHandleGet(pd, map);
 		}
@@ -879,7 +880,8 @@ u8 MR_GetPhyParams(struct megasas_instance *instance, u32 ld, u64 stripRow,
 			pRAID_Context->regLockFlags = REGION_TYPE_EXCLUSIVE;
 		else if (raid->level == 1) {
 			/* Get alternate Pd. */
-			pd = MR_ArPdGet(arRef, physArm + 1, map);
+			physArm = physArm + 1;
+			pd = MR_ArPdGet(arRef, physArm, map);
 			if (pd != MR_PD_INVALID)
 				/* Get dev handle from Pd */
 				*pDevHandle = MR_PdDevHandleGet(pd, map);
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 52d8bbf7feb5..24778ba4b6e8 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -748,6 +748,11 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 		goto fail_fw_init;
 	}
 
+	instance->fw_sync_cache_support = (scratch_pad_2 &
+		MR_CAN_HANDLE_SYNC_CACHE_OFFSET) ? 1 : 0;
+	dev_info(&instance->pdev->dev, "FW supports sync cache\t: %s\n",
+		 instance->fw_sync_cache_support ? "Yes" : "No");
+
 	IOCInitMessage =
 	  dma_alloc_coherent(&instance->pdev->dev,
 			     sizeof(struct MPI2_IOC_INIT_REQUEST),
@@ -2000,6 +2005,8 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 		io_request->DevHandle = pd_sync->seq[pd_index].devHandle;
 		pRAID_Context->regLockFlags |=
 			(MR_RL_FLAGS_SEQ_NUM_ENABLE|MR_RL_FLAGS_GRANT_DESTINATION_CUDA);
+		pRAID_Context->Type = MPI2_TYPE_CUDA;
+		pRAID_Context->nseg = 0x1;
 	} else if (fusion->fast_path_io) {
 		pRAID_Context->VirtualDiskTgtId = cpu_to_le16(device_id);
 		pRAID_Context->configSeqNum = 0;
@@ -2035,12 +2042,10 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 		pRAID_Context->timeoutValue =
 			cpu_to_le16((os_timeout_value > timeout_limit) ?
 			timeout_limit : os_timeout_value);
-		if (fusion->adapter_type == INVADER_SERIES) {
-			pRAID_Context->Type = MPI2_TYPE_CUDA;
-			pRAID_Context->nseg = 0x1;
+		if (fusion->adapter_type == INVADER_SERIES)
 			io_request->IoFlags |=
 				cpu_to_le16(MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH);
-		}
+
 		cmd->request_desc->SCSIIO.RequestFlags =
 			(MPI2_REQ_DESCRIPT_FLAGS_FP_IO <<
 				MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
@@ -2463,12 +2468,15 @@ irqreturn_t megasas_isr_fusion(int irq, void *devp)
 			/* Start collecting crash, if DMA bit is done */
 			if ((fw_state == MFI_STATE_FAULT) && dma_state)
 				schedule_work(&instance->crash_init);
-			else if (fw_state == MFI_STATE_FAULT)
-				schedule_work(&instance->work_init);
+			else if (fw_state == MFI_STATE_FAULT) {
+				if (instance->unload == 0)
+					schedule_work(&instance->work_init);
+			}
 		} else if (fw_state == MFI_STATE_FAULT) {
 			dev_warn(&instance->pdev->dev, "Iop2SysDoorbellInt"
 			       "for scsi%d\n", instance->host->host_no);
-			schedule_work(&instance->work_init);
+			if (instance->unload == 0)
+				schedule_work(&instance->work_init);
 		}
 	}
 
@@ -2823,6 +2831,7 @@ int megasas_wait_for_outstanding_fusion(struct megasas_instance *instance,
 		dev_err(&instance->pdev->dev, "pending commands remain after waiting, "
 		       "will reset adapter scsi%d.\n",
 		       instance->host->host_no);
+		*convert = 1;
 		retval = 1;
 	}
 out:
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h b/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h
index 95356a82ee99..fa61baf7c74d 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h
@@ -478,6 +478,13 @@ typedef struct _MPI2_CONFIG_REPLY {
 #define MPI26_MFGPAGE_DEVID_SAS3324_3               (0x00C2)
 #define MPI26_MFGPAGE_DEVID_SAS3324_4               (0x00C3)
 
+#define MPI26_MFGPAGE_DEVID_SAS3516                 (0x00AA)
+#define MPI26_MFGPAGE_DEVID_SAS3516_1               (0x00AB)
+#define MPI26_MFGPAGE_DEVID_SAS3416                 (0x00AC)
+#define MPI26_MFGPAGE_DEVID_SAS3508                 (0x00AD)
+#define MPI26_MFGPAGE_DEVID_SAS3508_1               (0x00AE)
+#define MPI26_MFGPAGE_DEVID_SAS3408                 (0x00AF)
+
 /*Manufacturing Page 0 */
 
 typedef struct _MPI2_CONFIG_PAGE_MAN_0 {
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index a1a5ceb42ce6..f00ef88a378a 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -849,7 +849,7 @@ _base_async_event(struct MPT3SAS_ADAPTER *ioc, u8 msix_index, u32 reply)
 	ack_request->EventContext = mpi_reply->EventContext;
 	ack_request->VF_ID = 0;  /* TODO */
 	ack_request->VP_ID = 0;
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 
  out:
 
@@ -1078,7 +1078,7 @@ _base_interrupt(int irq, void *bus_id)
 	 * new reply host index value in ReplyPostIndex Field and msix_index
 	 * value in MSIxIndex field.
 	 */
-	if (ioc->msix96_vector)
+	if (ioc->combined_reply_queue)
 		writel(reply_q->reply_post_host_index | ((msix_index  & 7) <<
 			MPI2_RPHI_MSIX_INDEX_SHIFT),
 			ioc->replyPostRegisterIndex[msix_index/8]);
@@ -1959,7 +1959,7 @@ _base_enable_msix(struct MPT3SAS_ADAPTER *ioc)
 {
 	struct msix_entry *entries, *a;
 	int r;
-	int i;
+	int i, local_max_msix_vectors;
 	u8 try_msix = 0;
 
 	if (msix_disable == -1 || msix_disable == 0)
@@ -1979,13 +1979,15 @@ _base_enable_msix(struct MPT3SAS_ADAPTER *ioc)
 	  ioc->cpu_count, max_msix_vectors);
 
 	if (!ioc->rdpq_array_enable && max_msix_vectors == -1)
-		max_msix_vectors = 8;
+		local_max_msix_vectors = 8;
+	else
+		local_max_msix_vectors = max_msix_vectors;
 
-	if (max_msix_vectors > 0) {
-		ioc->reply_queue_count = min_t(int, max_msix_vectors,
+	if (local_max_msix_vectors > 0) {
+		ioc->reply_queue_count = min_t(int, local_max_msix_vectors,
 			ioc->reply_queue_count);
 		ioc->msix_vector_count = ioc->reply_queue_count;
-	} else if (max_msix_vectors == 0)
+	} else if (local_max_msix_vectors == 0)
 		goto try_ioapic;
 
 	if (ioc->msix_vector_count < ioc->cpu_count)
@@ -2050,7 +2052,7 @@ mpt3sas_base_unmap_resources(struct MPT3SAS_ADAPTER *ioc)
 	_base_free_irq(ioc);
 	_base_disable_msix(ioc);
 
-	if (ioc->msix96_vector) {
+	if (ioc->combined_reply_queue) {
 		kfree(ioc->replyPostRegisterIndex);
 		ioc->replyPostRegisterIndex = NULL;
 	}
@@ -2160,7 +2162,7 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
 	/* Use the Combined reply queue feature only for SAS3 C0 & higher
 	 * revision HBAs and also only when reply queue count is greater than 8
 	 */
-	if (ioc->msix96_vector && ioc->reply_queue_count > 8) {
+	if (ioc->combined_reply_queue && ioc->reply_queue_count > 8) {
 		/* Determine the Supplemental Reply Post Host Index Registers
 		 * Addresse. Supplemental Reply Post Host Index Registers
 		 * starts at offset MPI25_SUP_REPLY_POST_HOST_INDEX_OFFSET and
@@ -2168,7 +2170,7 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
 		 * MPT3_SUP_REPLY_POST_HOST_INDEX_REG_OFFSET from previous one.
 		 */
 		ioc->replyPostRegisterIndex = kcalloc(
-		     MPT3_SUP_REPLY_POST_HOST_INDEX_REG_COUNT,
+		     ioc->combined_reply_index_count,
 		     sizeof(resource_size_t *), GFP_KERNEL);
 		if (!ioc->replyPostRegisterIndex) {
 			dfailprintk(ioc, printk(MPT3SAS_FMT
@@ -2178,14 +2180,14 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
 			goto out_fail;
 		}
 
-		for (i = 0; i < MPT3_SUP_REPLY_POST_HOST_INDEX_REG_COUNT; i++) {
+		for (i = 0; i < ioc->combined_reply_index_count; i++) {
 			ioc->replyPostRegisterIndex[i] = (resource_size_t *)
 			     ((u8 *)&ioc->chip->Doorbell +
 			     MPI25_SUP_REPLY_POST_HOST_INDEX_OFFSET +
 			     (i * MPT3_SUP_REPLY_POST_HOST_INDEX_REG_OFFSET));
 		}
 	} else
-		ioc->msix96_vector = 0;
+		ioc->combined_reply_queue = 0;
 
 	if (ioc->is_warpdrive) {
 		ioc->reply_post_host_index[0] = (resource_size_t __iomem *)
@@ -2462,15 +2464,15 @@ _base_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock)
 #endif
 
 /**
- * mpt3sas_base_put_smid_scsi_io - send SCSI_IO request to firmware
+ * _base_put_smid_scsi_io - send SCSI_IO request to firmware
  * @ioc: per adapter object
  * @smid: system request message index
  * @handle: device handle
  *
  * Return nothing.
  */
-void
-mpt3sas_base_put_smid_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid, u16 handle)
+static void
+_base_put_smid_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid, u16 handle)
 {
 	Mpi2RequestDescriptorUnion_t descriptor;
 	u64 *request = (u64 *)&descriptor;
@@ -2486,15 +2488,15 @@ mpt3sas_base_put_smid_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid, u16 handle)
 }
 
 /**
- * mpt3sas_base_put_smid_fast_path - send fast path request to firmware
+ * _base_put_smid_fast_path - send fast path request to firmware
  * @ioc: per adapter object
  * @smid: system request message index
  * @handle: device handle
  *
  * Return nothing.
  */
-void
-mpt3sas_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
+static void
+_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	u16 handle)
 {
 	Mpi2RequestDescriptorUnion_t descriptor;
@@ -2511,14 +2513,14 @@ mpt3sas_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 }
 
 /**
- * mpt3sas_base_put_smid_hi_priority - send Task Managment request to firmware
+ * _base_put_smid_hi_priority - send Task Management request to firmware
  * @ioc: per adapter object
  * @smid: system request message index
  * @msix_task: msix_task will be same as msix of IO incase of task abort else 0.
  * Return nothing.
  */
-void
-mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid,
+static void
+_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	u16 msix_task)
 {
 	Mpi2RequestDescriptorUnion_t descriptor;
@@ -2535,14 +2537,14 @@ mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 }
 
 /**
- * mpt3sas_base_put_smid_default - Default, primarily used for config pages
+ * _base_put_smid_default - Default, primarily used for config pages
  * @ioc: per adapter object
  * @smid: system request message index
  *
  * Return nothing.
  */
-void
-mpt3sas_base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid)
+static void
+_base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 {
 	Mpi2RequestDescriptorUnion_t descriptor;
 	u64 *request = (u64 *)&descriptor;
@@ -2557,6 +2559,95 @@ mpt3sas_base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 }
 
 /**
+* _base_put_smid_scsi_io_atomic - send SCSI_IO request to firmware using
+*   Atomic Request Descriptor
+* @ioc: per adapter object
+* @smid: system request message index
+* @handle: device handle, unused in this function, for function type match
+*
+* Return nothing.
+*/
+static void
+_base_put_smid_scsi_io_atomic(struct MPT3SAS_ADAPTER *ioc, u16 smid,
+	u16 handle)
+{
+	Mpi26AtomicRequestDescriptor_t descriptor;
+	u32 *request = (u32 *)&descriptor;
+
+	descriptor.RequestFlags = MPI2_REQ_DESCRIPT_FLAGS_SCSI_IO;
+	descriptor.MSIxIndex = _base_get_msix_index(ioc);
+	descriptor.SMID = cpu_to_le16(smid);
+
+	writel(cpu_to_le32(*request), &ioc->chip->AtomicRequestDescriptorPost);
+}
+
+/**
+ * _base_put_smid_fast_path_atomic - send fast path request to firmware
+ * using Atomic Request Descriptor
+ * @ioc: per adapter object
+ * @smid: system request message index
+ * @handle: device handle, unused in this function, for function type match
+ * Return nothing
+ */
+static void
+_base_put_smid_fast_path_atomic(struct MPT3SAS_ADAPTER *ioc, u16 smid,
+	u16 handle)
+{
+	Mpi26AtomicRequestDescriptor_t descriptor;
+	u32 *request = (u32 *)&descriptor;
+
+	descriptor.RequestFlags = MPI25_REQ_DESCRIPT_FLAGS_FAST_PATH_SCSI_IO;
+	descriptor.MSIxIndex = _base_get_msix_index(ioc);
+	descriptor.SMID = cpu_to_le16(smid);
+
+	writel(cpu_to_le32(*request), &ioc->chip->AtomicRequestDescriptorPost);
+}
+
+/**
+ * _base_put_smid_hi_priority_atomic - send Task Management request to
+ * firmware using Atomic Request Descriptor
+ * @ioc: per adapter object
+ * @smid: system request message index
+ * @msix_task: msix_task will be same as msix of IO incase of task abort else 0
+ *
+ * Return nothing.
+ */
+static void
+_base_put_smid_hi_priority_atomic(struct MPT3SAS_ADAPTER *ioc, u16 smid,
+	u16 msix_task)
+{
+	Mpi26AtomicRequestDescriptor_t descriptor;
+	u32 *request = (u32 *)&descriptor;
+
+	descriptor.RequestFlags = MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY;
+	descriptor.MSIxIndex = msix_task;
+	descriptor.SMID = cpu_to_le16(smid);
+
+	writel(cpu_to_le32(*request), &ioc->chip->AtomicRequestDescriptorPost);
+}
+
+/**
+ * _base_put_smid_default - Default, primarily used for config pages
+ * use Atomic Request Descriptor
+ * @ioc: per adapter object
+ * @smid: system request message index
+ *
+ * Return nothing.
+ */
+static void
+_base_put_smid_default_atomic(struct MPT3SAS_ADAPTER *ioc, u16 smid)
+{
+	Mpi26AtomicRequestDescriptor_t descriptor;
+	u32 *request = (u32 *)&descriptor;
+
+	descriptor.RequestFlags = MPI2_REQ_DESCRIPT_FLAGS_DEFAULT_TYPE;
+	descriptor.MSIxIndex = _base_get_msix_index(ioc);
+	descriptor.SMID = cpu_to_le16(smid);
+
+	writel(cpu_to_le32(*request), &ioc->chip->AtomicRequestDescriptorPost);
+}
+
+/**
  * _base_display_OEMs_branding - Display branding string
  * @ioc: per adapter object
  *
@@ -4070,7 +4161,7 @@ mpt3sas_base_sas_iounit_control(struct MPT3SAS_ADAPTER *ioc,
 	    mpi_request->Operation == MPI2_SAS_OP_PHY_LINK_RESET)
 		ioc->ioc_link_reset_in_progress = 1;
 	init_completion(&ioc->base_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->base_cmds.done,
 	    msecs_to_jiffies(10000));
 	if ((mpi_request->Operation == MPI2_SAS_OP_PHY_HARD_RESET ||
@@ -4170,7 +4261,7 @@ mpt3sas_base_scsi_enclosure_processor(struct MPT3SAS_ADAPTER *ioc,
 	ioc->base_cmds.smid = smid;
 	memcpy(request, mpi_request, sizeof(Mpi2SepReply_t));
 	init_completion(&ioc->base_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->base_cmds.done,
 	    msecs_to_jiffies(10000));
 	if (!(ioc->base_cmds.status & MPT3_CMD_COMPLETE)) {
@@ -4355,6 +4446,8 @@ _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc)
 	if ((facts->IOCCapabilities &
 	      MPI2_IOCFACTS_CAPABILITY_RDPQ_ARRAY_CAPABLE))
 		ioc->rdpq_array_capable = 1;
+	if (facts->IOCCapabilities & MPI26_IOCFACTS_CAPABILITY_ATOMIC_REQ)
+		ioc->atomic_desc_capable = 1;
 	facts->FWVersion.Word = le32_to_cpu(mpi_reply.FWVersion.Word);
 	facts->IOCRequestFrameSize =
 	    le16_to_cpu(mpi_reply.IOCRequestFrameSize);
@@ -4582,7 +4675,7 @@ _base_send_port_enable(struct MPT3SAS_ADAPTER *ioc)
 	mpi_request->Function = MPI2_FUNCTION_PORT_ENABLE;
 
 	init_completion(&ioc->port_enable_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->port_enable_cmds.done, 300*HZ);
 	if (!(ioc->port_enable_cmds.status & MPT3_CMD_COMPLETE)) {
 		pr_err(MPT3SAS_FMT "%s: timeout\n",
@@ -4645,7 +4738,7 @@ mpt3sas_port_enable(struct MPT3SAS_ADAPTER *ioc)
 	memset(mpi_request, 0, sizeof(Mpi2PortEnableRequest_t));
 	mpi_request->Function = MPI2_FUNCTION_PORT_ENABLE;
 
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	return 0;
 }
 
@@ -4764,7 +4857,7 @@ _base_event_notification(struct MPT3SAS_ADAPTER *ioc)
 		mpi_request->EventMasks[i] =
 		    cpu_to_le32(ioc->event_masks[i]);
 	init_completion(&ioc->base_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->base_cmds.done, 30*HZ);
 	if (!(ioc->base_cmds.status & MPT3_CMD_COMPLETE)) {
 		pr_err(MPT3SAS_FMT "%s: timeout\n",
@@ -5138,7 +5231,7 @@ _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc)
 
 	/* initialize reply post host index */
 	list_for_each_entry(reply_q, &ioc->reply_queue_list, list) {
-		if (ioc->msix96_vector)
+		if (ioc->combined_reply_queue)
 			writel((reply_q->msix_index & 7)<<
 			   MPI2_RPHI_MSIX_INDEX_SHIFT,
 			   ioc->replyPostRegisterIndex[reply_q->msix_index/8]);
@@ -5280,9 +5373,23 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 		ioc->build_sg = &_base_build_sg_ieee;
 		ioc->build_zero_len_sge = &_base_build_zero_len_sge_ieee;
 		ioc->sge_size_ieee = sizeof(Mpi2IeeeSgeSimple64_t);
+
 		break;
 	}
 
+	if (ioc->atomic_desc_capable) {
+		ioc->put_smid_default = &_base_put_smid_default_atomic;
+		ioc->put_smid_scsi_io = &_base_put_smid_scsi_io_atomic;
+		ioc->put_smid_fast_path = &_base_put_smid_fast_path_atomic;
+		ioc->put_smid_hi_priority = &_base_put_smid_hi_priority_atomic;
+	} else {
+		ioc->put_smid_default = &_base_put_smid_default;
+		ioc->put_smid_scsi_io = &_base_put_smid_scsi_io;
+		ioc->put_smid_fast_path = &_base_put_smid_fast_path;
+		ioc->put_smid_hi_priority = &_base_put_smid_hi_priority;
+	}
+
+
 	/*
 	 * These function pointers for other requests that don't
 	 * the require IEEE scatter gather elements.
@@ -5332,6 +5439,21 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 		goto out_free_resources;
 	}
 
+	/* allocate memory for pending OS device add list */
+	ioc->pend_os_device_add_sz = (ioc->facts.MaxDevHandle / 8);
+	if (ioc->facts.MaxDevHandle % 8)
+		ioc->pend_os_device_add_sz++;
+	ioc->pend_os_device_add = kzalloc(ioc->pend_os_device_add_sz,
+	    GFP_KERNEL);
+	if (!ioc->pend_os_device_add)
+		goto out_free_resources;
+
+	ioc->device_remove_in_progress_sz = ioc->pend_os_device_add_sz;
+	ioc->device_remove_in_progress =
+		kzalloc(ioc->device_remove_in_progress_sz, GFP_KERNEL);
+	if (!ioc->device_remove_in_progress)
+		goto out_free_resources;
+
 	ioc->fwfault_debug = mpt3sas_fwfault_debug;
 
 	/* base internal command bits */
@@ -5414,6 +5536,8 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 		kfree(ioc->reply_post_host_index);
 	kfree(ioc->pd_handles);
 	kfree(ioc->blocking_handles);
+	kfree(ioc->device_remove_in_progress);
+	kfree(ioc->pend_os_device_add);
 	kfree(ioc->tm_cmds.reply);
 	kfree(ioc->transport_cmds.reply);
 	kfree(ioc->scsih_cmds.reply);
@@ -5455,6 +5579,8 @@ mpt3sas_base_detach(struct MPT3SAS_ADAPTER *ioc)
 		kfree(ioc->reply_post_host_index);
 	kfree(ioc->pd_handles);
 	kfree(ioc->blocking_handles);
+	kfree(ioc->device_remove_in_progress);
+	kfree(ioc->pend_os_device_add);
 	kfree(ioc->pfacts);
 	kfree(ioc->ctl_cmds.reply);
 	kfree(ioc->ctl_cmds.sense);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 3e71bc1b4a80..394fe1338d09 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -73,9 +73,9 @@
 #define MPT3SAS_DRIVER_NAME		"mpt3sas"
 #define MPT3SAS_AUTHOR "Avago Technologies <MPT-FusionLinux.pdl@avagotech.com>"
 #define MPT3SAS_DESCRIPTION	"LSI MPT Fusion SAS 3.0 Device Driver"
-#define MPT3SAS_DRIVER_VERSION		"13.100.00.00"
-#define MPT3SAS_MAJOR_VERSION		13
-#define MPT3SAS_MINOR_VERSION		100
+#define MPT3SAS_DRIVER_VERSION		"14.101.00.00"
+#define MPT3SAS_MAJOR_VERSION		14
+#define MPT3SAS_MINOR_VERSION		101
 #define MPT3SAS_BUILD_VERSION		0
 #define MPT3SAS_RELEASE_VERSION	00
 
@@ -300,8 +300,9 @@
  * There are twelve Supplemental Reply Post Host Index Registers
  * and each register is at offset 0x10 bytes from the previous one.
  */
-#define MPT3_SUP_REPLY_POST_HOST_INDEX_REG_COUNT 12
-#define MPT3_SUP_REPLY_POST_HOST_INDEX_REG_OFFSET (0x10)
+#define MPT3_SUP_REPLY_POST_HOST_INDEX_REG_COUNT_G3	12
+#define MPT3_SUP_REPLY_POST_HOST_INDEX_REG_COUNT_G35	16
+#define MPT3_SUP_REPLY_POST_HOST_INDEX_REG_OFFSET	(0x10)
 
 /* OEM Identifiers */
 #define MFG10_OEM_ID_INVALID                   (0x00000000)
@@ -375,7 +376,6 @@ struct MPT3SAS_TARGET {
  * per device private data
  */
 #define MPT_DEVICE_FLAGS_INIT		0x01
-#define MPT_DEVICE_TLR_ON		0x02
 
 #define MFG_PAGE10_HIDE_SSDS_MASK	(0x00000003)
 #define MFG_PAGE10_HIDE_ALL_DISKS	(0x00)
@@ -402,6 +402,9 @@ struct MPT3SAS_DEVICE {
 	u8	block;
 	u8	tlr_snoop_check;
 	u8	ignore_delay_remove;
+	/* Iopriority Command Handling */
+	u8	ncq_prio_enable;
+
 };
 
 #define MPT3_CMD_NOT_USED	0x8000	/* free */
@@ -736,7 +739,10 @@ typedef void (*MPT_BUILD_SG)(struct MPT3SAS_ADAPTER *ioc, void *psge,
 typedef void (*MPT_BUILD_ZERO_LEN_SGE)(struct MPT3SAS_ADAPTER *ioc,
 		void *paddr);
 
-
+/* To support atomic and non atomic descriptors*/
+typedef void (*PUT_SMID_IO_FP_HIP) (struct MPT3SAS_ADAPTER *ioc, u16 smid,
+	u16 funcdep);
+typedef void (*PUT_SMID_DEFAULT) (struct MPT3SAS_ADAPTER *ioc, u16 smid);
 
 /* IOC Facts and Port Facts converted from little endian to cpu */
 union mpi3_version_union {
@@ -1079,6 +1085,9 @@ struct MPT3SAS_ADAPTER {
 	void		*pd_handles;
 	u16		pd_handles_sz;
 
+	void		*pend_os_device_add;
+	u16		pend_os_device_add_sz;
+
 	/* config page */
 	u16		config_page_sz;
 	void		*config_page;
@@ -1156,7 +1165,8 @@ struct MPT3SAS_ADAPTER {
 	u8		reply_queue_count;
 	struct list_head reply_queue_list;
 
-	u8		msix96_vector;
+	u8		combined_reply_queue;
+	u8		combined_reply_index_count;
 	/* reply post register index */
 	resource_size_t	**replyPostRegisterIndex;
 
@@ -1187,6 +1197,15 @@ struct MPT3SAS_ADAPTER {
 	struct SL_WH_EVENT_TRIGGERS_T diag_trigger_event;
 	struct SL_WH_SCSI_TRIGGERS_T diag_trigger_scsi;
 	struct SL_WH_MPI_TRIGGERS_T diag_trigger_mpi;
+	void		*device_remove_in_progress;
+	u16		device_remove_in_progress_sz;
+	u8		is_gen35_ioc;
+	u8		atomic_desc_capable;
+	PUT_SMID_IO_FP_HIP put_smid_scsi_io;
+	PUT_SMID_IO_FP_HIP put_smid_fast_path;
+	PUT_SMID_IO_FP_HIP put_smid_hi_priority;
+	PUT_SMID_DEFAULT put_smid_default;
+
 };
 
 typedef u8 (*MPT_CALLBACK)(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -1232,13 +1251,6 @@ u16 mpt3sas_base_get_smid_scsiio(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx,
 
 u16 mpt3sas_base_get_smid(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx);
 void mpt3sas_base_free_smid(struct MPT3SAS_ADAPTER *ioc, u16 smid);
-void mpt3sas_base_put_smid_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid,
-	u16 handle);
-void mpt3sas_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
-	u16 handle);
-void mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc,
-	u16 smid, u16 msix_task);
-void mpt3sas_base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid);
 void mpt3sas_base_initialize_callback_handler(void);
 u8 mpt3sas_base_register_callback_handler(MPT_CALLBACK cb_func);
 void mpt3sas_base_release_callback_handler(u8 cb_idx);
@@ -1449,4 +1461,7 @@ mpt3sas_setup_direct_io(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
 	struct _raid_device *raid_device, Mpi2SCSIIORequest_t *mpi_request,
 	u16 smid);
 
+/* NCQ Prio Handling Check */
+bool scsih_ncq_prio_supp(struct scsi_device *sdev);
+
 #endif /* MPT3SAS_BASE_H_INCLUDED */
diff --git a/drivers/scsi/mpt3sas/mpt3sas_config.c b/drivers/scsi/mpt3sas/mpt3sas_config.c
index cebfd734fd76..dd6270125614 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_config.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_config.c
@@ -384,7 +384,7 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t
 	memcpy(config_request, mpi_request, sizeof(Mpi2ConfigRequest_t));
 	_config_display_some_debug(ioc, smid, "config_request", NULL);
 	init_completion(&ioc->config_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->config_cmds.done, timeout*HZ);
 	if (!(ioc->config_cmds.status & MPT3_CMD_COMPLETE)) {
 		pr_err(MPT3SAS_FMT "%s: timeout\n",
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 26cdc127ac89..95f0f24bac05 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -654,6 +654,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 	size_t data_in_sz = 0;
 	long ret;
 	u16 wait_state_count;
+	u16 device_handle = MPT3SAS_INVALID_DEVICE_HANDLE;
 
 	issue_reset = 0;
 
@@ -738,10 +739,13 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 	data_in_sz = karg.data_in_size;
 
 	if (mpi_request->Function == MPI2_FUNCTION_SCSI_IO_REQUEST ||
-	    mpi_request->Function == MPI2_FUNCTION_RAID_SCSI_IO_PASSTHROUGH) {
-		if (!le16_to_cpu(mpi_request->FunctionDependent1) ||
-		    le16_to_cpu(mpi_request->FunctionDependent1) >
-		    ioc->facts.MaxDevHandle) {
+	    mpi_request->Function == MPI2_FUNCTION_RAID_SCSI_IO_PASSTHROUGH ||
+	    mpi_request->Function == MPI2_FUNCTION_SCSI_TASK_MGMT ||
+	    mpi_request->Function == MPI2_FUNCTION_SATA_PASSTHROUGH) {
+
+		device_handle = le16_to_cpu(mpi_request->FunctionDependent1);
+		if (!device_handle || (device_handle >
+		    ioc->facts.MaxDevHandle)) {
 			ret = -EINVAL;
 			mpt3sas_base_free_smid(ioc, smid);
 			goto out;
@@ -797,14 +801,20 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 		scsiio_request->SenseBufferLowAddress =
 		    mpt3sas_base_get_sense_buffer_dma(ioc, smid);
 		memset(ioc->ctl_cmds.sense, 0, SCSI_SENSE_BUFFERSIZE);
+		if (test_bit(device_handle, ioc->device_remove_in_progress)) {
+			dtmprintk(ioc, pr_info(MPT3SAS_FMT
+				"handle(0x%04x) :ioctl failed due to device removal in progress\n",
+				ioc->name, device_handle));
+			mpt3sas_base_free_smid(ioc, smid);
+			ret = -EINVAL;
+			goto out;
+		}
 		ioc->build_sg(ioc, psge, data_out_dma, data_out_sz,
 		    data_in_dma, data_in_sz);
-
 		if (mpi_request->Function == MPI2_FUNCTION_SCSI_IO_REQUEST)
-			mpt3sas_base_put_smid_scsi_io(ioc, smid,
-			    le16_to_cpu(mpi_request->FunctionDependent1));
+			ioc->put_smid_scsi_io(ioc, smid, device_handle);
 		else
-			mpt3sas_base_put_smid_default(ioc, smid);
+			ioc->put_smid_default(ioc, smid);
 		break;
 	}
 	case MPI2_FUNCTION_SCSI_TASK_MGMT:
@@ -827,11 +837,19 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 			}
 		}
 
+		if (test_bit(device_handle, ioc->device_remove_in_progress)) {
+			dtmprintk(ioc, pr_info(MPT3SAS_FMT
+				"handle(0x%04x) :ioctl failed due to device removal in progress\n",
+				ioc->name, device_handle));
+			mpt3sas_base_free_smid(ioc, smid);
+			ret = -EINVAL;
+			goto out;
+		}
 		mpt3sas_scsih_set_tm_flag(ioc, le16_to_cpu(
 		    tm_request->DevHandle));
 		ioc->build_sg_mpi(ioc, psge, data_out_dma, data_out_sz,
 		    data_in_dma, data_in_sz);
-		mpt3sas_base_put_smid_hi_priority(ioc, smid, 0);
+		ioc->put_smid_hi_priority(ioc, smid, 0);
 		break;
 	}
 	case MPI2_FUNCTION_SMP_PASSTHROUGH:
@@ -862,16 +880,30 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 		}
 		ioc->build_sg(ioc, psge, data_out_dma, data_out_sz, data_in_dma,
 		    data_in_sz);
-		mpt3sas_base_put_smid_default(ioc, smid);
+		ioc->put_smid_default(ioc, smid);
 		break;
 	}
 	case MPI2_FUNCTION_SATA_PASSTHROUGH:
+	{
+		if (test_bit(device_handle, ioc->device_remove_in_progress)) {
+			dtmprintk(ioc, pr_info(MPT3SAS_FMT
+				"handle(0x%04x) :ioctl failed due to device removal in progress\n",
+				ioc->name, device_handle));
+			mpt3sas_base_free_smid(ioc, smid);
+			ret = -EINVAL;
+			goto out;
+		}
+		ioc->build_sg(ioc, psge, data_out_dma, data_out_sz, data_in_dma,
+		    data_in_sz);
+		ioc->put_smid_default(ioc, smid);
+		break;
+	}
 	case MPI2_FUNCTION_FW_DOWNLOAD:
 	case MPI2_FUNCTION_FW_UPLOAD:
 	{
 		ioc->build_sg(ioc, psge, data_out_dma, data_out_sz, data_in_dma,
 		    data_in_sz);
-		mpt3sas_base_put_smid_default(ioc, smid);
+		ioc->put_smid_default(ioc, smid);
 		break;
 	}
 	case MPI2_FUNCTION_TOOLBOX:
@@ -886,7 +918,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 			ioc->build_sg_mpi(ioc, psge, data_out_dma, data_out_sz,
 				data_in_dma, data_in_sz);
 		}
-		mpt3sas_base_put_smid_default(ioc, smid);
+		ioc->put_smid_default(ioc, smid);
 		break;
 	}
 	case MPI2_FUNCTION_SAS_IO_UNIT_CONTROL:
@@ -905,7 +937,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 	default:
 		ioc->build_sg_mpi(ioc, psge, data_out_dma, data_out_sz,
 		    data_in_dma, data_in_sz);
-		mpt3sas_base_put_smid_default(ioc, smid);
+		ioc->put_smid_default(ioc, smid);
 		break;
 	}
 
@@ -1064,7 +1096,10 @@ _ctl_getiocinfo(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 		break;
 	case MPI25_VERSION:
 	case MPI26_VERSION:
-		karg.adapter_type = MPT3_IOCTL_INTERFACE_SAS3;
+		if (ioc->is_gen35_ioc)
+			karg.adapter_type = MPT3_IOCTL_INTERFACE_SAS35;
+		else
+			karg.adapter_type = MPT3_IOCTL_INTERFACE_SAS3;
 		strcat(karg.driver_version, MPT3SAS_DRIVER_VERSION);
 		break;
 	}
@@ -1491,7 +1526,7 @@ _ctl_diag_register_2(struct MPT3SAS_ADAPTER *ioc,
 			cpu_to_le32(ioc->product_specific[buffer_type][i]);
 
 	init_completion(&ioc->ctl_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->ctl_cmds.done,
 	    MPT3_IOCTL_DEFAULT_TIMEOUT*HZ);
 
@@ -1838,7 +1873,7 @@ mpt3sas_send_diag_release(struct MPT3SAS_ADAPTER *ioc, u8 buffer_type,
 	mpi_request->VP_ID = 0;
 
 	init_completion(&ioc->ctl_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->ctl_cmds.done,
 	    MPT3_IOCTL_DEFAULT_TIMEOUT*HZ);
 
@@ -2105,7 +2140,7 @@ _ctl_diag_read_buffer(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 	mpi_request->VP_ID = 0;
 
 	init_completion(&ioc->ctl_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->ctl_cmds.done,
 	    MPT3_IOCTL_DEFAULT_TIMEOUT*HZ);
 
@@ -3290,8 +3325,6 @@ static DEVICE_ATTR(diag_trigger_mpi, S_IRUGO | S_IWUSR,
 
 /*********** diagnostic trigger suppport *** END ****************************/
 
-
-
 /*****************************************/
 
 struct device_attribute *mpt3sas_host_attrs[] = {
@@ -3367,9 +3400,50 @@ _ctl_device_handle_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR(sas_device_handle, S_IRUGO, _ctl_device_handle_show, NULL);
 
+/**
+ * _ctl_device_ncq_io_prio_show - send prioritized io commands to device
+ * @dev - pointer to embedded device
+ * @buf - the buffer returned
+ *
+ * A sysfs 'read/write' sdev attribute, only works with SATA
+ */
+static ssize_t
+_ctl_device_ncq_prio_enable_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct scsi_device *sdev = to_scsi_device(dev);
+	struct MPT3SAS_DEVICE *sas_device_priv_data = sdev->hostdata;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			sas_device_priv_data->ncq_prio_enable);
+}
+
+static ssize_t
+_ctl_device_ncq_prio_enable_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct scsi_device *sdev = to_scsi_device(dev);
+	struct MPT3SAS_DEVICE *sas_device_priv_data = sdev->hostdata;
+	bool ncq_prio_enable = 0;
+
+	if (kstrtobool(buf, &ncq_prio_enable))
+		return -EINVAL;
+
+	if (!scsih_ncq_prio_supp(sdev))
+		return -EINVAL;
+
+	sas_device_priv_data->ncq_prio_enable = ncq_prio_enable;
+	return strlen(buf);
+}
+static DEVICE_ATTR(sas_ncq_prio_enable, S_IRUGO | S_IWUSR,
+		   _ctl_device_ncq_prio_enable_show,
+		   _ctl_device_ncq_prio_enable_store);
+
 struct device_attribute *mpt3sas_dev_attrs[] = {
 	&dev_attr_sas_address,
 	&dev_attr_sas_device_handle,
+	&dev_attr_sas_ncq_prio_enable,
 	NULL,
 };
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.h b/drivers/scsi/mpt3sas/mpt3sas_ctl.h
index 89408356d252..f3e17a8c1b07 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.h
@@ -143,6 +143,7 @@ struct mpt3_ioctl_pci_info {
 #define MPT2_IOCTL_INTERFACE_SAS2	(0x04)
 #define MPT2_IOCTL_INTERFACE_SAS2_SSS6200	(0x05)
 #define MPT3_IOCTL_INTERFACE_SAS3	(0x06)
+#define MPT3_IOCTL_INTERFACE_SAS35	(0x07)
 #define MPT2_IOCTL_VERSION_LENGTH	(32)
 
 /**
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 8aa769a2d919..b5c966e319d3 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -423,7 +423,7 @@ _scsih_get_sas_address(struct MPT3SAS_ADAPTER *ioc, u16 handle,
 		return 0;
 	}
 
-	/* we hit this becuase the given parent handle doesn't exist */
+	/* we hit this because the given parent handle doesn't exist */
 	if (ioc_status == MPI2_IOCSTATUS_CONFIG_INVALID_PAGE)
 		return -ENXIO;
 
@@ -788,6 +788,11 @@ _scsih_sas_device_add(struct MPT3SAS_ADAPTER *ioc,
 	list_add_tail(&sas_device->list, &ioc->sas_device_list);
 	spin_unlock_irqrestore(&ioc->sas_device_lock, flags);
 
+	if (ioc->hide_drives) {
+		clear_bit(sas_device->handle, ioc->pend_os_device_add);
+		return;
+	}
+
 	if (!mpt3sas_transport_port_add(ioc, sas_device->handle,
 	     sas_device->sas_address_parent)) {
 		_scsih_sas_device_remove(ioc, sas_device);
@@ -803,7 +808,8 @@ _scsih_sas_device_add(struct MPT3SAS_ADAPTER *ioc,
 			    sas_device->sas_address_parent);
 			_scsih_sas_device_remove(ioc, sas_device);
 		}
-	}
+	} else
+		clear_bit(sas_device->handle, ioc->pend_os_device_add);
 }
 
 /**
@@ -1517,7 +1523,7 @@ _scsih_display_sata_capabilities(struct MPT3SAS_ADAPTER *ioc,
 /*
  * raid transport support -
  * Enabled for SLES11 and newer, in older kernels the driver will panic when
- * unloading the driver followed by a load - I beleive that the subroutine
+ * unloading the driver followed by a load - I believe that the subroutine
  * raid_class_release() is not cleaning up properly.
  */
 
@@ -2279,7 +2285,7 @@ mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, uint channel,
 		msix_task = scsi_lookup->msix_io;
 	else
 		msix_task = 0;
-	mpt3sas_base_put_smid_hi_priority(ioc, smid, msix_task);
+	ioc->put_smid_hi_priority(ioc, smid, msix_task);
 	wait_for_completion_timeout(&ioc->tm_cmds.done, timeout*HZ);
 	if (!(ioc->tm_cmds.status & MPT3_CMD_COMPLETE)) {
 		pr_err(MPT3SAS_FMT "%s: timeout\n",
@@ -2837,7 +2843,7 @@ _scsih_internal_device_block(struct scsi_device *sdev,
 	if (r == -EINVAL)
 		sdev_printk(KERN_WARNING, sdev,
 		    "device_block failed with return(%d) for handle(0x%04x)\n",
-		    sas_device_priv_data->sas_target->handle, r);
+		    r, sas_device_priv_data->sas_target->handle);
 }
 
 /**
@@ -2867,20 +2873,20 @@ _scsih_internal_device_unblock(struct scsi_device *sdev,
 		sdev_printk(KERN_WARNING, sdev,
 		    "device_unblock failed with return(%d) for handle(0x%04x) "
 		    "performing a block followed by an unblock\n",
-		    sas_device_priv_data->sas_target->handle, r);
+		    r, sas_device_priv_data->sas_target->handle);
 		sas_device_priv_data->block = 1;
 		r = scsi_internal_device_block(sdev);
 		if (r)
 			sdev_printk(KERN_WARNING, sdev, "retried device_block "
 			    "failed with return(%d) for handle(0x%04x)\n",
-			    sas_device_priv_data->sas_target->handle, r);
+			    r, sas_device_priv_data->sas_target->handle);
 
 		sas_device_priv_data->block = 0;
 		r = scsi_internal_device_unblock(sdev, SDEV_RUNNING);
 		if (r)
 			sdev_printk(KERN_WARNING, sdev, "retried device_unblock"
 			    " failed with return(%d) for handle(0x%04x)\n",
-			    sas_device_priv_data->sas_target->handle, r);
+			    r, sas_device_priv_data->sas_target->handle);
 	}
 }
 
@@ -2942,7 +2948,7 @@ _scsih_ublock_io_device(struct MPT3SAS_ADAPTER *ioc, u64 sas_address)
  * @ioc: per adapter object
  * @handle: device handle
  *
- * During device pull we need to appropiately set the sdev state.
+ * During device pull we need to appropriately set the sdev state.
  */
 static void
 _scsih_block_io_all_device(struct MPT3SAS_ADAPTER *ioc)
@@ -2971,7 +2977,7 @@ _scsih_block_io_all_device(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  * @handle: device handle
  *
- * During device pull we need to appropiately set the sdev state.
+ * During device pull we need to appropriately set the sdev state.
  */
 static void
 _scsih_block_io_device(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -3138,6 +3144,8 @@ _scsih_tm_tr_send(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	if (test_bit(handle, ioc->pd_handles))
 		return;
 
+	clear_bit(handle, ioc->pend_os_device_add);
+
 	spin_lock_irqsave(&ioc->sas_device_lock, flags);
 	sas_device = __mpt3sas_get_sdev_by_handle(ioc, handle);
 	if (sas_device && sas_device->starget &&
@@ -3192,7 +3200,8 @@ _scsih_tm_tr_send(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	mpi_request->Function = MPI2_FUNCTION_SCSI_TASK_MGMT;
 	mpi_request->DevHandle = cpu_to_le16(handle);
 	mpi_request->TaskType = MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET;
-	mpt3sas_base_put_smid_hi_priority(ioc, smid, 0);
+	set_bit(handle, ioc->device_remove_in_progress);
+	ioc->put_smid_hi_priority(ioc, smid, 0);
 	mpt3sas_trigger_master(ioc, MASTER_TRIGGER_DEVICE_REMOVAL);
 
 out:
@@ -3291,7 +3300,7 @@ _scsih_tm_tr_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
 	mpi_request->Function = MPI2_FUNCTION_SAS_IO_UNIT_CONTROL;
 	mpi_request->Operation = MPI2_SAS_OP_REMOVE_DEVICE;
 	mpi_request->DevHandle = mpi_request_tm->DevHandle;
-	mpt3sas_base_put_smid_default(ioc, smid_sas_ctrl);
+	ioc->put_smid_default(ioc, smid_sas_ctrl);
 
 	return _scsih_check_for_pending_tm(ioc, smid);
 }
@@ -3326,6 +3335,11 @@ _scsih_sas_control_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 		ioc->name, le16_to_cpu(mpi_reply->DevHandle), smid,
 		le16_to_cpu(mpi_reply->IOCStatus),
 		le32_to_cpu(mpi_reply->IOCLogInfo)));
+		if (le16_to_cpu(mpi_reply->IOCStatus) ==
+		     MPI2_IOCSTATUS_SUCCESS) {
+			clear_bit(le16_to_cpu(mpi_reply->DevHandle),
+			    ioc->device_remove_in_progress);
+		}
 	} else {
 		pr_err(MPT3SAS_FMT "mpi_reply not valid at %s:%d/%s()!\n",
 		    ioc->name, __FILE__, __LINE__, __func__);
@@ -3381,7 +3395,7 @@ _scsih_tm_tr_volume_send(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	mpi_request->Function = MPI2_FUNCTION_SCSI_TASK_MGMT;
 	mpi_request->DevHandle = cpu_to_le16(handle);
 	mpi_request->TaskType = MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET;
-	mpt3sas_base_put_smid_hi_priority(ioc, smid, 0);
+	ioc->put_smid_hi_priority(ioc, smid, 0);
 }
 
 /**
@@ -3473,7 +3487,7 @@ _scsih_issue_delayed_event_ack(struct MPT3SAS_ADAPTER *ioc, u16 smid, u16 event,
 	ack_request->EventContext = event_context;
 	ack_request->VF_ID = 0;  /* TODO */
 	ack_request->VP_ID = 0;
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 }
 
 /**
@@ -3530,7 +3544,7 @@ _scsih_issue_delayed_sas_io_unit_ctrl(struct MPT3SAS_ADAPTER *ioc,
 	mpi_request->Function = MPI2_FUNCTION_SAS_IO_UNIT_CONTROL;
 	mpi_request->Operation = MPI2_SAS_OP_REMOVE_DEVICE;
 	mpi_request->DevHandle = handle;
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 }
 
 /**
@@ -3885,6 +3899,11 @@ _scsih_temp_threshold_events(struct MPT3SAS_ADAPTER *ioc,
 	}
 }
 
+static inline bool ata_12_16_cmd(struct scsi_cmnd *scmd)
+{
+	return (scmd->cmnd[0] == ATA_12 || scmd->cmnd[0] == ATA_16);
+}
+
 /**
  * _scsih_flush_running_cmds - completing outstanding commands.
  * @ioc: per adapter object
@@ -3906,6 +3925,9 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc)
 		if (!scmd)
 			continue;
 		count++;
+		if (ata_12_16_cmd(scmd))
+			scsi_internal_device_unblock(scmd->device,
+							SDEV_RUNNING);
 		mpt3sas_base_free_smid(ioc, smid);
 		scsi_dma_unmap(scmd);
 		if (ioc->pci_error_recovery)
@@ -3922,7 +3944,7 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc)
  * _scsih_setup_eedp - setup MPI request for EEDP transfer
  * @ioc: per adapter object
  * @scmd: pointer to scsi command object
- * @mpi_request: pointer to the SCSI_IO reqest message frame
+ * @mpi_request: pointer to the SCSI_IO request message frame
  *
  * Supporting protection 1 and 3.
  *
@@ -3975,6 +3997,9 @@ _scsih_setup_eedp(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
 
 	mpi_request_3v->EEDPBlockSize =
 	    cpu_to_le16(scmd->device->sector_size);
+
+	if (ioc->is_gen35_ioc)
+		eedp_flags |= MPI25_SCSIIO_EEDPFLAGS_APPTAG_DISABLE_MODE;
 	mpi_request->EEDPFlags = cpu_to_le16(eedp_flags);
 }
 
@@ -4010,8 +4035,6 @@ _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status)
 	    SAM_STAT_CHECK_CONDITION;
 }
 
-
-
 /**
  * scsih_qcmd - main scsi request entry point
  * @scmd: pointer to scsi command object
@@ -4030,6 +4053,8 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 	struct MPT3SAS_DEVICE *sas_device_priv_data;
 	struct MPT3SAS_TARGET *sas_target_priv_data;
 	struct _raid_device *raid_device;
+	struct request *rq = scmd->request;
+	int class;
 	Mpi2SCSIIORequest_t *mpi_request;
 	u32 mpi_control;
 	u16 smid;
@@ -4038,6 +4063,13 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 	if (ioc->logging_level & MPT_DEBUG_SCSI)
 		scsi_print_command(scmd);
 
+	/*
+	 * Lock the device for any subsequent command until command is
+	 * done.
+	 */
+	if (ata_12_16_cmd(scmd))
+		scsi_internal_device_block(scmd->device);
+
 	sas_device_priv_data = scmd->device->hostdata;
 	if (!sas_device_priv_data || !sas_device_priv_data->sas_target) {
 		scmd->result = DID_NO_CONNECT << 16;
@@ -4071,7 +4103,7 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 		scmd->result = DID_NO_CONNECT << 16;
 		scmd->scsi_done(scmd);
 		return 0;
-	/* device busy with task managment */
+	/* device busy with task management */
 	} else if (sas_target_priv_data->tm_busy ||
 	    sas_device_priv_data->block)
 		return SCSI_MLQUEUE_DEVICE_BUSY;
@@ -4085,7 +4117,12 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 
 	/* set tags */
 	mpi_control |= MPI2_SCSIIO_CONTROL_SIMPLEQ;
-
+	/* NCQ Prio supported, make sure control indicated high priority */
+	if (sas_device_priv_data->ncq_prio_enable) {
+		class = IOPRIO_PRIO_CLASS(req_get_ioprio(rq));
+		if (class == IOPRIO_CLASS_RT)
+			mpi_control |= 1 << MPI2_SCSIIO_CONTROL_CMDPRI_SHIFT;
+	}
 	/* Make sure Device is not raid volume.
 	 * We do not expose raid functionality to upper layer for warpdrive.
 	 */
@@ -4141,12 +4178,12 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 		if (sas_target_priv_data->flags & MPT_TARGET_FASTPATH_IO) {
 			mpi_request->IoFlags = cpu_to_le16(scmd->cmd_len |
 			    MPI25_SCSIIO_IOFLAGS_FAST_PATH);
-			mpt3sas_base_put_smid_fast_path(ioc, smid, handle);
+			ioc->put_smid_fast_path(ioc, smid, handle);
 		} else
-			mpt3sas_base_put_smid_scsi_io(ioc, smid,
+			ioc->put_smid_scsi_io(ioc, smid,
 			    le16_to_cpu(mpi_request->DevHandle));
 	} else
-		mpt3sas_base_put_smid_default(ioc, smid);
+		ioc->put_smid_default(ioc, smid);
 	return 0;
 
  out:
@@ -4613,6 +4650,9 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	if (scmd == NULL)
 		return 1;
 
+	if (ata_12_16_cmd(scmd))
+		scsi_internal_device_unblock(scmd->device, SDEV_RUNNING);
+
 	mpi_request = mpt3sas_base_get_msg_frame(ioc, smid);
 
 	if (mpi_reply == NULL) {
@@ -4642,7 +4682,7 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 		memcpy(mpi_request->CDB.CDB32, scmd->cmnd, scmd->cmd_len);
 		mpi_request->DevHandle =
 		    cpu_to_le16(sas_device_priv_data->sas_target->handle);
-		mpt3sas_base_put_smid_scsi_io(ioc, smid,
+		ioc->put_smid_scsi_io(ioc, smid,
 		    sas_device_priv_data->sas_target->handle);
 		return 0;
 	}
@@ -5367,10 +5407,10 @@ _scsih_check_device(struct MPT3SAS_ADAPTER *ioc,
 			sas_device->handle, handle);
 		sas_target_priv_data->handle = handle;
 		sas_device->handle = handle;
-		if (sas_device_pg0.Flags &
+		if (le16_to_cpu(sas_device_pg0.Flags) &
 		     MPI2_SAS_DEVICE0_FLAGS_ENCL_LEVEL_VALID) {
 			sas_device->enclosure_level =
-				le16_to_cpu(sas_device_pg0.EnclosureLevel);
+				sas_device_pg0.EnclosureLevel;
 			memcpy(sas_device->connector_name,
 				sas_device_pg0.ConnectorName, 4);
 			sas_device->connector_name[4] = '\0';
@@ -5449,6 +5489,7 @@ _scsih_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle, u8 phy_num,
 	device_info = le32_to_cpu(sas_device_pg0.DeviceInfo);
 	if (!(_scsih_is_end_device(device_info)))
 		return -1;
+	set_bit(handle, ioc->pend_os_device_add);
 	sas_address = le64_to_cpu(sas_device_pg0.SASAddress);
 
 	/* check if device is present */
@@ -5467,6 +5508,7 @@ _scsih_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle, u8 phy_num,
 	sas_device = mpt3sas_get_sdev_by_addr(ioc,
 					sas_address);
 	if (sas_device) {
+		clear_bit(handle, ioc->pend_os_device_add);
 		sas_device_put(sas_device);
 		return -1;
 	}
@@ -5497,9 +5539,10 @@ _scsih_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle, u8 phy_num,
 	sas_device->fast_path = (le16_to_cpu(sas_device_pg0.Flags) &
 	    MPI25_SAS_DEVICE0_FLAGS_FAST_PATH_CAPABLE) ? 1 : 0;
 
-	if (sas_device_pg0.Flags & MPI2_SAS_DEVICE0_FLAGS_ENCL_LEVEL_VALID) {
+	if (le16_to_cpu(sas_device_pg0.Flags)
+		& MPI2_SAS_DEVICE0_FLAGS_ENCL_LEVEL_VALID) {
 		sas_device->enclosure_level =
-			le16_to_cpu(sas_device_pg0.EnclosureLevel);
+			sas_device_pg0.EnclosureLevel;
 		memcpy(sas_device->connector_name,
 			sas_device_pg0.ConnectorName, 4);
 		sas_device->connector_name[4] = '\0';
@@ -5790,6 +5833,9 @@ _scsih_sas_topology_change_event(struct MPT3SAS_ADAPTER *ioc,
 			_scsih_check_device(ioc, sas_address, handle,
 			    phy_number, link_rate);
 
+			if (!test_bit(handle, ioc->pend_os_device_add))
+				break;
+
 
 		case MPI2_EVENT_SAS_TOPO_RC_TARG_ADDED:
 
@@ -6251,7 +6297,7 @@ _scsih_ir_fastpath(struct MPT3SAS_ADAPTER *ioc, u16 handle, u8 phys_disk_num)
 	    handle, phys_disk_num));
 
 	init_completion(&ioc->scsih_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->scsih_cmds.done, 10*HZ);
 
 	if (!(ioc->scsih_cmds.status & MPT3_CMD_COMPLETE)) {
@@ -6304,7 +6350,7 @@ _scsih_reprobe_lun(struct scsi_device *sdev, void *no_uld_attach)
 {
 	sdev->no_uld_attach = no_uld_attach ? 1 : 0;
 	sdev_printk(KERN_INFO, sdev, "%s raid component\n",
-	    sdev->no_uld_attach ? "hidding" : "exposing");
+	    sdev->no_uld_attach ? "hiding" : "exposing");
 	WARN_ON(scsi_device_reprobe(sdev));
 }
 
@@ -7034,7 +7080,7 @@ Mpi2SasDevicePage0_t *sas_device_pg0)
 			if (sas_device_pg0->Flags &
 			      MPI2_SAS_DEVICE0_FLAGS_ENCL_LEVEL_VALID) {
 				sas_device->enclosure_level =
-				   le16_to_cpu(sas_device_pg0->EnclosureLevel);
+				   sas_device_pg0->EnclosureLevel;
 				memcpy(&sas_device->connector_name[0],
 					&sas_device_pg0->ConnectorName[0], 4);
 			} else {
@@ -7096,6 +7142,7 @@ _scsih_search_responding_sas_devices(struct MPT3SAS_ADAPTER *ioc)
 		sas_device_pg0.SASAddress =
 				le64_to_cpu(sas_device_pg0.SASAddress);
 		sas_device_pg0.Slot = le16_to_cpu(sas_device_pg0.Slot);
+		sas_device_pg0.Flags = le16_to_cpu(sas_device_pg0.Flags);
 		_scsih_mark_responding_sas_device(ioc, &sas_device_pg0);
 	}
 
@@ -7707,6 +7754,9 @@ mpt3sas_scsih_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase)
 			complete(&ioc->tm_cmds.done);
 		}
 
+		memset(ioc->pend_os_device_add, 0, ioc->pend_os_device_add_sz);
+		memset(ioc->device_remove_in_progress, 0,
+		       ioc->device_remove_in_progress_sz);
 		_scsih_fw_event_cleanup_queue(ioc);
 		_scsih_flush_running_cmds(ioc);
 		break;
@@ -8097,7 +8147,7 @@ _scsih_ir_shutdown(struct MPT3SAS_ADAPTER *ioc)
 	if (!ioc->hide_ir_msg)
 		pr_info(MPT3SAS_FMT "IR shutdown (sending)\n", ioc->name);
 	init_completion(&ioc->scsih_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->scsih_cmds.done, 10*HZ);
 
 	if (!(ioc->scsih_cmds.status & MPT3_CMD_COMPLETE)) {
@@ -8638,6 +8688,12 @@ _scsih_determine_hba_mpi_version(struct pci_dev *pdev)
 	case MPI26_MFGPAGE_DEVID_SAS3324_2:
 	case MPI26_MFGPAGE_DEVID_SAS3324_3:
 	case MPI26_MFGPAGE_DEVID_SAS3324_4:
+	case MPI26_MFGPAGE_DEVID_SAS3508:
+	case MPI26_MFGPAGE_DEVID_SAS3508_1:
+	case MPI26_MFGPAGE_DEVID_SAS3408:
+	case MPI26_MFGPAGE_DEVID_SAS3516:
+	case MPI26_MFGPAGE_DEVID_SAS3516_1:
+	case MPI26_MFGPAGE_DEVID_SAS3416:
 		return MPI26_VERSION;
 	}
 	return 0;
@@ -8706,10 +8762,29 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		ioc->hba_mpi_version_belonged = hba_mpi_version;
 		ioc->id = mpt3_ids++;
 		sprintf(ioc->driver_name, "%s", MPT3SAS_DRIVER_NAME);
+		switch (pdev->device) {
+		case MPI26_MFGPAGE_DEVID_SAS3508:
+		case MPI26_MFGPAGE_DEVID_SAS3508_1:
+		case MPI26_MFGPAGE_DEVID_SAS3408:
+		case MPI26_MFGPAGE_DEVID_SAS3516:
+		case MPI26_MFGPAGE_DEVID_SAS3516_1:
+		case MPI26_MFGPAGE_DEVID_SAS3416:
+			ioc->is_gen35_ioc = 1;
+			break;
+		default:
+			ioc->is_gen35_ioc = 0;
+		}
 		if ((ioc->hba_mpi_version_belonged == MPI25_VERSION &&
 			pdev->revision >= SAS3_PCI_DEVICE_C0_REVISION) ||
-			(ioc->hba_mpi_version_belonged == MPI26_VERSION))
-			ioc->msix96_vector = 1;
+			(ioc->hba_mpi_version_belonged == MPI26_VERSION)) {
+			ioc->combined_reply_queue = 1;
+			if (ioc->is_gen35_ioc)
+				ioc->combined_reply_index_count =
+				 MPT3_SUP_REPLY_POST_HOST_INDEX_REG_COUNT_G35;
+			else
+				ioc->combined_reply_index_count =
+				 MPT3_SUP_REPLY_POST_HOST_INDEX_REG_COUNT_G3;
+		}
 		break;
 	default:
 		return -ENODEV;
@@ -9031,6 +9106,31 @@ scsih_pci_mmio_enabled(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
+/**
+ * scsih__ncq_prio_supp - Check for NCQ command priority support
+ * @sdev: scsi device struct
+ *
+ * This is called when a user indicates they would like to enable
+ * ncq command priorities. This works only on SATA devices.
+ */
+bool scsih_ncq_prio_supp(struct scsi_device *sdev)
+{
+	unsigned char *buf;
+	bool ncq_prio_supp = false;
+
+	if (!scsi_device_supports_vpd(sdev))
+		return ncq_prio_supp;
+
+	buf = kmalloc(SCSI_VPD_PG_LEN, GFP_KERNEL);
+	if (!buf)
+		return ncq_prio_supp;
+
+	if (!scsi_get_vpd_page(sdev, 0x89, buf, SCSI_VPD_PG_LEN))
+		ncq_prio_supp = (buf[213] >> 4) & 1;
+
+	kfree(buf);
+	return ncq_prio_supp;
+}
 /*
  * The pci device ids are defined in mpi/mpi2_cnfg.h.
  */
@@ -9112,6 +9212,19 @@ static const struct pci_device_id mpt3sas_pci_table[] = {
 		PCI_ANY_ID, PCI_ANY_ID },
 	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3324_4,
 		PCI_ANY_ID, PCI_ANY_ID },
+	/* Ventura, Crusader, Harpoon & Tomcat ~ 3516, 3416, 3508 & 3408*/
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3508,
+		PCI_ANY_ID, PCI_ANY_ID },
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3508_1,
+		PCI_ANY_ID, PCI_ANY_ID },
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3408,
+		PCI_ANY_ID, PCI_ANY_ID },
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3516,
+		PCI_ANY_ID, PCI_ANY_ID },
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3516_1,
+		PCI_ANY_ID, PCI_ANY_ID },
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3416,
+		PCI_ANY_ID, PCI_ANY_ID },
 	{0}     /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(pci, mpt3sas_pci_table);
@@ -9152,7 +9265,7 @@ scsih_init(void)
 	 /* queuecommand callback hander */
 	scsi_io_cb_idx = mpt3sas_base_register_callback_handler(_scsih_io_done);
 
-	/* task managment callback handler */
+	/* task management callback handler */
 	tm_cb_idx = mpt3sas_base_register_callback_handler(_scsih_tm_done);
 
 	/* base internal commands callback handler */
diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c
index b74faf1a69b2..7f1d5785bc30 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_transport.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c
@@ -392,7 +392,7 @@ _transport_expander_report_manufacture(struct MPT3SAS_ADAPTER *ioc,
 		"report_manufacture - send to sas_addr(0x%016llx)\n",
 		ioc->name, (unsigned long long)sas_address));
 	init_completion(&ioc->transport_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->transport_cmds.done, 10*HZ);
 
 	if (!(ioc->transport_cmds.status & MPT3_CMD_COMPLETE)) {
@@ -1198,7 +1198,7 @@ _transport_get_expander_phy_error_log(struct MPT3SAS_ADAPTER *ioc,
 		ioc->name, (unsigned long long)phy->identify.sas_address,
 		phy->number));
 	init_completion(&ioc->transport_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->transport_cmds.done, 10*HZ);
 
 	if (!(ioc->transport_cmds.status & MPT3_CMD_COMPLETE)) {
@@ -1514,7 +1514,7 @@ _transport_expander_phy_control(struct MPT3SAS_ADAPTER *ioc,
 		ioc->name, (unsigned long long)phy->identify.sas_address,
 		phy->number, phy_operation));
 	init_completion(&ioc->transport_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->transport_cmds.done, 10*HZ);
 
 	if (!(ioc->transport_cmds.status & MPT3_CMD_COMPLETE)) {
@@ -2032,7 +2032,7 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 		"%s - sending smp request\n", ioc->name, __func__));
 
 	init_completion(&ioc->transport_cmds.done);
-	mpt3sas_base_put_smid_default(ioc, smid);
+	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->transport_cmds.done, 10*HZ);
 
 	if (!(ioc->transport_cmds.status & MPT3_CMD_COMPLETE)) {
diff --git a/drivers/scsi/mvsas/mv_94xx.c b/drivers/scsi/mvsas/mv_94xx.c
index 4c57d9abce7b..7de5d8d75480 100644
--- a/drivers/scsi/mvsas/mv_94xx.c
+++ b/drivers/scsi/mvsas/mv_94xx.c
@@ -668,7 +668,7 @@ static void mvs_94xx_command_active(struct mvs_info *mvi, u32 slot_idx)
 {
 	u32 tmp;
 	tmp = mvs_cr32(mvi, MVS_COMMAND_ACTIVE+(slot_idx >> 3));
-	if (tmp && 1 << (slot_idx % 32)) {
+	if (tmp & 1 << (slot_idx % 32)) {
 		mv_printk("command active %08X,  slot [%x].\n", tmp, slot_idx);
 		mvs_cw32(mvi, MVS_COMMAND_ACTIVE + (slot_idx >> 3),
 			1 << (slot_idx % 32));
diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c
index 86eb19902bac..c7cc8035eacb 100644
--- a/drivers/scsi/mvsas/mv_sas.c
+++ b/drivers/scsi/mvsas/mv_sas.c
@@ -791,8 +791,10 @@ static int mvs_task_prep(struct sas_task *task, struct mvs_info *mvi, int is_tmf
 	slot->slot_tag = tag;
 
 	slot->buf = pci_pool_alloc(mvi->dma_pool, GFP_ATOMIC, &slot->buf_dma);
-	if (!slot->buf)
+	if (!slot->buf) {
+		rc = -ENOMEM;
 		goto err_out_tag;
+	}
 	memset(slot->buf, 0, MVS_SLOT_BUF_SZ);
 
 	tei.task = task;
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index 2f2a9910e30e..ef99f62831fb 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -1595,7 +1595,7 @@ static int _init_blk_request(struct osd_request *or,
 	}
 
 	or->request = req;
-	req->cmd_flags |= REQ_QUIET;
+	req->rq_flags |= RQF_QUIET;
 
 	req->timeout = or->timeout;
 	req->retries = or->retries;
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index 5033223f6287..e8196c55b633 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -52,7 +52,7 @@ static const char * osst_version = "0.99.4";
 #include <linux/delay.h>
 #include <linux/jiffies.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/dma.h>
 
 /* The driver prints some debugging information on the console if DEBUG
@@ -368,7 +368,7 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd,
 		return DRIVER_ERROR << 24;
 
 	blk_rq_set_block_pc(req);
-	req->cmd_flags |= REQ_QUIET;
+	req->rq_flags |= RQF_QUIET;
 
 	SRpnt->bio = NULL;
 
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index 68a5c347fae9..337982cf3d63 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -1368,13 +1368,8 @@ static struct genl_multicast_group pmcraid_mcgrps[] = {
 	{ .name = "events", /* not really used - see ID discussion below */ },
 };
 
-static struct genl_family pmcraid_event_family = {
-	/*
-	 * Due to prior multicast group abuse (the code having assumed that
-	 * the family ID can be used as a multicast group ID) we need to
-	 * statically allocate a family (and thus group) ID.
-	 */
-	.id = GENL_ID_PMCRAID,
+static struct genl_family pmcraid_event_family __ro_after_init = {
+	.module = THIS_MODULE,
 	.name = "pmcraid",
 	.version = 1,
 	.maxattr = PMCRAID_AEN_ATTR_MAX,
@@ -1389,7 +1384,7 @@ static struct genl_family pmcraid_event_family = {
  *	0 if the pmcraid_event_family is successfully registered
  *	with netlink generic, non-zero otherwise
  */
-static int pmcraid_netlink_init(void)
+static int __init pmcraid_netlink_init(void)
 {
 	int result;
 
@@ -3792,11 +3787,11 @@ static long pmcraid_ioctl_passthrough(
 						      direction);
 		if (rc) {
 			pmcraid_err("couldn't build passthrough ioadls\n");
-			goto out_free_buffer;
+			goto out_free_cmd;
 		}
 	} else if (request_size < 0) {
 		rc = -EINVAL;
-		goto out_free_buffer;
+		goto out_free_cmd;
 	}
 
 	/* If data is being written into the device, copy the data from user
@@ -3913,6 +3908,8 @@ out_handle_response:
 
 out_free_sglist:
 	pmcraid_release_passthrough_ioadls(cmd, request_size, direction);
+
+out_free_cmd:
 	pmcraid_return_cmd(cmd);
 
 out_free_buffer:
@@ -6023,8 +6020,10 @@ static int __init pmcraid_init(void)
 
 	error = pmcraid_netlink_init();
 
-	if (error)
+	if (error) {
+		class_destroy(pmcraid_class);
 		goto out_unreg_chrdev;
+	}
 
 	error = pci_register_driver(&pmcraid_driver);
 
diff --git a/drivers/scsi/qedi/Kconfig b/drivers/scsi/qedi/Kconfig
new file mode 100644
index 000000000000..23ca8a274586
--- /dev/null
+++ b/drivers/scsi/qedi/Kconfig
@@ -0,0 +1,10 @@
+config QEDI
+	tristate "QLogic QEDI 25/40/100Gb iSCSI Initiator Driver Support"
+	depends on PCI && SCSI
+	depends on QED
+	select SCSI_ISCSI_ATTRS
+	select QED_LL2
+	select QED_ISCSI
+	---help---
+	This driver supports iSCSI offload for the QLogic FastLinQ
+	41000 Series Converged Network Adapters.
diff --git a/drivers/scsi/qedi/Makefile b/drivers/scsi/qedi/Makefile
new file mode 100644
index 000000000000..2b3e16b24299
--- /dev/null
+++ b/drivers/scsi/qedi/Makefile
@@ -0,0 +1,5 @@
+obj-$(CONFIG_QEDI) := qedi.o
+qedi-y := qedi_main.o qedi_iscsi.o qedi_fw.o qedi_sysfs.o \
+	    qedi_dbg.o
+
+qedi-$(CONFIG_DEBUG_FS) += qedi_debugfs.o
diff --git a/drivers/scsi/qedi/qedi.h b/drivers/scsi/qedi/qedi.h
new file mode 100644
index 000000000000..5ca3e8c28a3f
--- /dev/null
+++ b/drivers/scsi/qedi/qedi.h
@@ -0,0 +1,364 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#ifndef _QEDI_H_
+#define _QEDI_H_
+
+#define __PREVENT_QED_HSI__
+
+#include <scsi/scsi_transport_iscsi.h>
+#include <scsi/libiscsi.h>
+#include <scsi/scsi_host.h>
+#include <linux/uio_driver.h>
+
+#include "qedi_hsi.h"
+#include <linux/qed/qed_if.h>
+#include "qedi_dbg.h"
+#include <linux/qed/qed_iscsi_if.h>
+#include <linux/qed/qed_ll2_if.h>
+#include "qedi_version.h"
+
+#define QEDI_MODULE_NAME		"qedi"
+
+struct qedi_endpoint;
+
+/*
+ * PCI function probe defines
+ */
+#define QEDI_MODE_NORMAL	0
+#define QEDI_MODE_RECOVERY	1
+
+#define ISCSI_WQE_SET_PTU_INVALIDATE	1
+#define QEDI_MAX_ISCSI_TASK		4096
+#define QEDI_MAX_TASK_NUM		0x0FFF
+#define QEDI_MAX_ISCSI_CONNS_PER_HBA	1024
+#define QEDI_ISCSI_MAX_BDS_PER_CMD	256	/* Firmware max BDs is 256 */
+#define MAX_OUSTANDING_TASKS_PER_CON	1024
+
+#define QEDI_MAX_BD_LEN		0xffff
+#define QEDI_BD_SPLIT_SZ	0x1000
+#define QEDI_PAGE_SIZE		4096
+#define QEDI_FAST_SGE_COUNT	4
+/* MAX Length for cached SGL */
+#define MAX_SGLEN_FOR_CACHESGL	((1U << 16) - 1)
+
+#define MAX_NUM_MSIX_PF         8
+#define MIN_NUM_CPUS_MSIX(x)	min((x)->msix_count, num_online_cpus())
+
+#define QEDI_LOCAL_PORT_MIN     60000
+#define QEDI_LOCAL_PORT_MAX     61024
+#define QEDI_LOCAL_PORT_RANGE   (QEDI_LOCAL_PORT_MAX - QEDI_LOCAL_PORT_MIN)
+#define QEDI_LOCAL_PORT_INVALID	0xffff
+#define TX_RX_RING		16
+#define RX_RING			(TX_RX_RING - 1)
+#define LL2_SINGLE_BUF_SIZE	0x400
+#define QEDI_PAGE_SIZE		4096
+#define QEDI_PAGE_ALIGN(addr)	ALIGN(addr, QEDI_PAGE_SIZE)
+#define QEDI_PAGE_MASK		(~((QEDI_PAGE_SIZE) - 1))
+
+#define QEDI_PAGE_SIZE		4096
+#define QEDI_PATH_HANDLE	0xFE0000000UL
+
+struct qedi_uio_ctrl {
+	/* meta data */
+	u32 uio_hsi_version;
+
+	/* user writes */
+	u32 host_tx_prod;
+	u32 host_rx_cons;
+	u32 host_rx_bd_cons;
+	u32 host_tx_pkt_len;
+	u32 host_rx_cons_cnt;
+
+	/* driver writes */
+	u32 hw_tx_cons;
+	u32 hw_rx_prod;
+	u32 hw_rx_bd_prod;
+	u32 hw_rx_prod_cnt;
+
+	/* other */
+	u8 mac_addr[6];
+	u8 reserve[2];
+};
+
+struct qedi_rx_bd {
+	u32 rx_pkt_index;
+	u32 rx_pkt_len;
+	u16 vlan_id;
+};
+
+#define QEDI_RX_DESC_CNT	(QEDI_PAGE_SIZE / sizeof(struct qedi_rx_bd))
+#define QEDI_MAX_RX_DESC_CNT	(QEDI_RX_DESC_CNT - 1)
+#define QEDI_NUM_RX_BD		(QEDI_RX_DESC_CNT * 1)
+#define QEDI_MAX_RX_BD		(QEDI_NUM_RX_BD - 1)
+
+#define QEDI_NEXT_RX_IDX(x)	((((x) & (QEDI_MAX_RX_DESC_CNT)) ==	\
+				  (QEDI_MAX_RX_DESC_CNT - 1)) ?		\
+				 (x) + 2 : (x) + 1)
+
+struct qedi_uio_dev {
+	struct uio_info		qedi_uinfo;
+	u32			uio_dev;
+	struct list_head	list;
+
+	u32			ll2_ring_size;
+	void			*ll2_ring;
+
+	u32			ll2_buf_size;
+	void			*ll2_buf;
+
+	void			*rx_pkt;
+	void			*tx_pkt;
+
+	struct qedi_ctx		*qedi;
+	struct pci_dev		*pdev;
+	void			*uctrl;
+};
+
+/* List to maintain the skb pointers */
+struct skb_work_list {
+	struct list_head list;
+	struct sk_buff *skb;
+	u16 vlan_id;
+};
+
+/* Queue sizes in number of elements */
+#define QEDI_SQ_SIZE		MAX_OUSTANDING_TASKS_PER_CON
+#define QEDI_CQ_SIZE		2048
+#define QEDI_CMDQ_SIZE		QEDI_MAX_ISCSI_TASK
+#define QEDI_PROTO_CQ_PROD_IDX	0
+
+struct qedi_glbl_q_params {
+	u64 hw_p_cq;	/* Completion queue PBL */
+	u64 hw_p_rq;	/* Request queue PBL */
+	u64 hw_p_cmdq;	/* Command queue PBL */
+};
+
+struct global_queue {
+	union iscsi_cqe *cq;
+	dma_addr_t cq_dma;
+	u32 cq_mem_size;
+	u32 cq_cons_idx; /* Completion queue consumer index */
+
+	void *cq_pbl;
+	dma_addr_t cq_pbl_dma;
+	u32 cq_pbl_size;
+
+};
+
+struct qedi_fastpath {
+	struct qed_sb_info	*sb_info;
+	u16			sb_id;
+#define QEDI_NAME_SIZE		16
+	char			name[QEDI_NAME_SIZE];
+	struct qedi_ctx         *qedi;
+};
+
+/* Used to pass fastpath information needed to process CQEs */
+struct qedi_io_work {
+	struct list_head list;
+	struct iscsi_cqe_solicited cqe;
+	u16	que_idx;
+};
+
+/**
+ * struct iscsi_cid_queue - Per adapter iscsi cid queue
+ *
+ * @cid_que_base:           queue base memory
+ * @cid_que:                queue memory pointer
+ * @cid_q_prod_idx:         produce index
+ * @cid_q_cons_idx:         consumer index
+ * @cid_q_max_idx:          max index. used to detect wrap around condition
+ * @cid_free_cnt:           queue size
+ * @conn_cid_tbl:           iscsi cid to conn structure mapping table
+ *
+ * Per adapter iSCSI CID Queue
+ */
+struct iscsi_cid_queue {
+	void *cid_que_base;
+	u32 *cid_que;
+	u32 cid_q_prod_idx;
+	u32 cid_q_cons_idx;
+	u32 cid_q_max_idx;
+	u32 cid_free_cnt;
+	struct qedi_conn **conn_cid_tbl;
+};
+
+struct qedi_portid_tbl {
+	spinlock_t      lock;	/* Port id lock */
+	u16             start;
+	u16             max;
+	u16             next;
+	unsigned long   *table;
+};
+
+struct qedi_itt_map {
+	__le32	itt;
+	struct qedi_cmd *p_cmd;
+};
+
+/* I/O tracing entry */
+#define QEDI_IO_TRACE_SIZE             2048
+struct qedi_io_log {
+#define QEDI_IO_TRACE_REQ              0
+#define QEDI_IO_TRACE_RSP              1
+	u8 direction;
+	u16 task_id;
+	u32 cid;
+	u32 port_id;	/* Remote port fabric ID */
+	int lun;
+	u8 op;		/* SCSI CDB */
+	u8 lba[4];
+	unsigned int bufflen;	/* SCSI buffer length */
+	unsigned int sg_count;	/* Number of SG elements */
+	u8 fast_sgs;		/* number of fast sgls */
+	u8 slow_sgs;		/* number of slow sgls */
+	u8 cached_sgs;		/* number of cached sgls */
+	int result;		/* Result passed back to mid-layer */
+	unsigned long jiffies;	/* Time stamp when I/O logged */
+	int refcount;		/* Reference count for task id */
+	unsigned int blk_req_cpu; /* CPU that the task is queued on by
+				   * blk layer
+				   */
+	unsigned int req_cpu;	/* CPU that the task is queued on */
+	unsigned int intr_cpu;	/* Interrupt CPU that the task is received on */
+	unsigned int blk_rsp_cpu;/* CPU that task is actually processed and
+				  * returned to blk layer
+				  */
+	bool cached_sge;
+	bool slow_sge;
+	bool fast_sge;
+};
+
+/* Number of entries in BDQ */
+#define QEDI_BDQ_NUM		256
+#define QEDI_BDQ_BUF_SIZE	256
+
+/* DMA coherent buffers for BDQ */
+struct qedi_bdq_buf {
+	void *buf_addr;
+	dma_addr_t buf_dma;
+};
+
+/* Main port level struct */
+struct qedi_ctx {
+	struct qedi_dbg_ctx dbg_ctx;
+	struct Scsi_Host *shost;
+	struct pci_dev *pdev;
+	struct qed_dev *cdev;
+	struct qed_dev_iscsi_info dev_info;
+	struct qed_int_info int_info;
+	struct qedi_glbl_q_params *p_cpuq;
+	struct global_queue **global_queues;
+	/* uio declaration */
+	struct qedi_uio_dev *udev;
+	struct list_head ll2_skb_list;
+	spinlock_t ll2_lock;	/* Light L2 lock */
+	spinlock_t hba_lock;	/* per port lock */
+	struct task_struct *ll2_recv_thread;
+	unsigned long flags;
+#define UIO_DEV_OPENED		1
+#define QEDI_IOTHREAD_WAKE	2
+#define QEDI_IN_RECOVERY	5
+#define QEDI_IN_OFFLINE		6
+
+	u8 mac[ETH_ALEN];
+	u32 src_ip[4];
+	u8 ip_type;
+
+	/* Physical address of above array */
+	dma_addr_t hw_p_cpuq;
+
+	struct qedi_bdq_buf bdq[QEDI_BDQ_NUM];
+	void *bdq_pbl;
+	dma_addr_t bdq_pbl_dma;
+	size_t bdq_pbl_mem_size;
+	void *bdq_pbl_list;
+	dma_addr_t bdq_pbl_list_dma;
+	u8 bdq_pbl_list_num_entries;
+	void __iomem *bdq_primary_prod;
+	void __iomem *bdq_secondary_prod;
+	u16 bdq_prod_idx;
+	u16 rq_num_entries;
+
+	u32 msix_count;
+	u32 max_sqes;
+	u8 num_queues;
+	u32 max_active_conns;
+
+	struct iscsi_cid_queue cid_que;
+	struct qedi_endpoint **ep_tbl;
+	struct qedi_portid_tbl lcl_port_tbl;
+
+	/* Rx fast path intr context */
+	struct qed_sb_info	*sb_array;
+	struct qedi_fastpath	*fp_array;
+	struct qed_iscsi_tid	tasks;
+
+#define QEDI_LINK_DOWN		0
+#define QEDI_LINK_UP		1
+	atomic_t link_state;
+
+#define QEDI_RESERVE_TASK_ID	0
+#define MAX_ISCSI_TASK_ENTRIES	4096
+#define QEDI_INVALID_TASK_ID	(MAX_ISCSI_TASK_ENTRIES + 1)
+	unsigned long task_idx_map[MAX_ISCSI_TASK_ENTRIES / BITS_PER_LONG];
+	struct qedi_itt_map *itt_map;
+	u16 tid_reuse_count[QEDI_MAX_ISCSI_TASK];
+	struct qed_pf_params pf_params;
+
+	struct workqueue_struct *tmf_thread;
+	struct workqueue_struct *offload_thread;
+
+	u16 ll2_mtu;
+
+	struct workqueue_struct *dpc_wq;
+
+	spinlock_t task_idx_lock;	/* To protect gbl context */
+	s32 last_tidx_alloc;
+	s32 last_tidx_clear;
+
+	struct qedi_io_log io_trace_buf[QEDI_IO_TRACE_SIZE];
+	spinlock_t io_trace_lock;	/* prtect trace Log buf */
+	u16 io_trace_idx;
+	unsigned int intr_cpu;
+	u32 cached_sgls;
+	bool use_cached_sge;
+	u32 slow_sgls;
+	bool use_slow_sge;
+	u32 fast_sgls;
+	bool use_fast_sge;
+
+	atomic_t num_offloads;
+};
+
+struct qedi_work {
+	struct list_head list;
+	struct qedi_ctx *qedi;
+	union iscsi_cqe cqe;
+	u16     que_idx;
+	bool is_solicited;
+};
+
+struct qedi_percpu_s {
+	struct task_struct *iothread;
+	struct list_head work_list;
+	spinlock_t p_work_lock;		/* Per cpu worker lock */
+};
+
+static inline void *qedi_get_task_mem(struct qed_iscsi_tid *info, u32 tid)
+{
+	return (info->blocks[tid / info->num_tids_per_block] +
+		(tid % info->num_tids_per_block) * info->size);
+}
+
+#define QEDI_U64_HI(val) ((u32)(((u64)(val)) >> 32))
+#define QEDI_U64_LO(val) ((u32)(((u64)(val)) & 0xffffffff))
+
+#endif /* _QEDI_H_ */
diff --git a/drivers/scsi/qedi/qedi_dbg.c b/drivers/scsi/qedi/qedi_dbg.c
new file mode 100644
index 000000000000..2bdedb9c39bc
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_dbg.c
@@ -0,0 +1,143 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include "qedi_dbg.h"
+#include <linux/vmalloc.h>
+
+void
+qedi_dbg_err(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+	     const char *fmt, ...)
+{
+	va_list va;
+	struct va_format vaf;
+	char nfunc[32];
+
+	memset(nfunc, 0, sizeof(nfunc));
+	memcpy(nfunc, func, sizeof(nfunc) - 1);
+
+	va_start(va, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &va;
+
+	if (likely(qedi) && likely(qedi->pdev))
+		pr_err("[%s]:[%s:%d]:%d: %pV", dev_name(&qedi->pdev->dev),
+		       nfunc, line, qedi->host_no, &vaf);
+	else
+		pr_err("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
+
+	va_end(va);
+}
+
+void
+qedi_dbg_warn(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+	      const char *fmt, ...)
+{
+	va_list va;
+	struct va_format vaf;
+	char nfunc[32];
+
+	memset(nfunc, 0, sizeof(nfunc));
+	memcpy(nfunc, func, sizeof(nfunc) - 1);
+
+	va_start(va, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &va;
+
+	if (!(qedi_dbg_log & QEDI_LOG_WARN))
+		return;
+
+	if (likely(qedi) && likely(qedi->pdev))
+		pr_warn("[%s]:[%s:%d]:%d: %pV", dev_name(&qedi->pdev->dev),
+			nfunc, line, qedi->host_no, &vaf);
+	else
+		pr_warn("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
+
+	va_end(va);
+}
+
+void
+qedi_dbg_notice(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+		const char *fmt, ...)
+{
+	va_list va;
+	struct va_format vaf;
+	char nfunc[32];
+
+	memset(nfunc, 0, sizeof(nfunc));
+	memcpy(nfunc, func, sizeof(nfunc) - 1);
+
+	va_start(va, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &va;
+
+	if (!(qedi_dbg_log & QEDI_LOG_NOTICE))
+		return;
+
+	if (likely(qedi) && likely(qedi->pdev))
+		pr_notice("[%s]:[%s:%d]:%d: %pV",
+			  dev_name(&qedi->pdev->dev), nfunc, line,
+			  qedi->host_no, &vaf);
+	else
+		pr_notice("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
+
+	va_end(va);
+}
+
+void
+qedi_dbg_info(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+	      u32 level, const char *fmt, ...)
+{
+	va_list va;
+	struct va_format vaf;
+	char nfunc[32];
+
+	memset(nfunc, 0, sizeof(nfunc));
+	memcpy(nfunc, func, sizeof(nfunc) - 1);
+
+	va_start(va, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &va;
+
+	if (!(qedi_dbg_log & level))
+		return;
+
+	if (likely(qedi) && likely(qedi->pdev))
+		pr_info("[%s]:[%s:%d]:%d: %pV", dev_name(&qedi->pdev->dev),
+			nfunc, line, qedi->host_no, &vaf);
+	else
+		pr_info("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
+
+	va_end(va);
+}
+
+int
+qedi_create_sysfs_attr(struct Scsi_Host *shost, struct sysfs_bin_attrs *iter)
+{
+	int ret = 0;
+
+	for (; iter->name; iter++) {
+		ret = sysfs_create_bin_file(&shost->shost_gendev.kobj,
+					    iter->attr);
+		if (ret)
+			pr_err("Unable to create sysfs %s attr, err(%d).\n",
+			       iter->name, ret);
+	}
+	return ret;
+}
+
+void
+qedi_remove_sysfs_attr(struct Scsi_Host *shost, struct sysfs_bin_attrs *iter)
+{
+	for (; iter->name; iter++)
+		sysfs_remove_bin_file(&shost->shost_gendev.kobj, iter->attr);
+}
diff --git a/drivers/scsi/qedi/qedi_dbg.h b/drivers/scsi/qedi/qedi_dbg.h
new file mode 100644
index 000000000000..c55572badfb0
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_dbg.h
@@ -0,0 +1,144 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#ifndef _QEDI_DBG_H_
+#define _QEDI_DBG_H_
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <linux/string.h>
+#include <linux/version.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <scsi/scsi_transport.h>
+#include <scsi/scsi_transport_iscsi.h>
+#include <linux/fs.h>
+
+#define __PREVENT_QED_HSI__
+#include <linux/qed/common_hsi.h>
+#include <linux/qed/qed_if.h>
+
+extern uint qedi_dbg_log;
+
+/* Debug print level definitions */
+#define QEDI_LOG_DEFAULT	0x1		/* Set default logging mask */
+#define QEDI_LOG_INFO		0x2		/* Informational logs,
+						 * MAC address, WWPN, WWNN
+						 */
+#define QEDI_LOG_DISC		0x4		/* Init, discovery, rport */
+#define QEDI_LOG_LL2		0x8		/* LL2, VLAN logs */
+#define QEDI_LOG_CONN		0x10		/* Connection setup, cleanup */
+#define QEDI_LOG_EVT		0x20		/* Events, link, mtu */
+#define QEDI_LOG_TIMER		0x40		/* Timer events */
+#define QEDI_LOG_MP_REQ		0x80		/* Middle Path (MP) logs */
+#define QEDI_LOG_SCSI_TM	0x100		/* SCSI Aborts, Task Mgmt */
+#define QEDI_LOG_UNSOL		0x200		/* unsolicited event logs */
+#define QEDI_LOG_IO		0x400		/* scsi cmd, completion */
+#define QEDI_LOG_MQ		0x800		/* Multi Queue logs */
+#define QEDI_LOG_BSG		0x1000		/* BSG logs */
+#define QEDI_LOG_DEBUGFS	0x2000		/* debugFS logs */
+#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_UIO		0x40000		/* iSCSI UIO logs */
+#define QEDI_LOG_TID		0x80000         /* FW TID context acquire,
+						 * free
+						 */
+#define QEDI_TRACK_TID		0x100000        /* Track TID state. To be
+						 * enabled only at module load
+						 * and not run-time.
+						 */
+#define QEDI_TRACK_CMD_LIST    0x300000        /* Track active cmd list nodes,
+						* done with reference to TID,
+						* hence TRACK_TID also enabled.
+						*/
+#define QEDI_LOG_NOTICE		0x40000000	/* Notice logs */
+#define QEDI_LOG_WARN		0x80000000	/* Warning logs */
+
+/* Debug context structure */
+struct qedi_dbg_ctx {
+	unsigned int host_no;
+	struct pci_dev *pdev;
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *bdf_dentry;
+#endif
+};
+
+#define QEDI_ERR(pdev, fmt, ...)	\
+		qedi_dbg_err(pdev, __func__, __LINE__, fmt, ## __VA_ARGS__)
+#define QEDI_WARN(pdev, fmt, ...)	\
+		qedi_dbg_warn(pdev, __func__, __LINE__, fmt, ## __VA_ARGS__)
+#define QEDI_NOTICE(pdev, fmt, ...)	\
+		qedi_dbg_notice(pdev, __func__, __LINE__, fmt, ## __VA_ARGS__)
+#define QEDI_INFO(pdev, level, fmt, ...)	\
+		qedi_dbg_info(pdev, __func__, __LINE__, level, fmt,	\
+			      ## __VA_ARGS__)
+
+void qedi_dbg_err(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+		  const char *fmt, ...);
+void qedi_dbg_warn(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+		   const char *fmt, ...);
+void qedi_dbg_notice(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+		     const char *fmt, ...);
+void qedi_dbg_info(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+		   u32 info, const char *fmt, ...);
+
+struct Scsi_Host;
+
+struct sysfs_bin_attrs {
+	char *name;
+	struct bin_attribute *attr;
+};
+
+int qedi_create_sysfs_attr(struct Scsi_Host *shost,
+			   struct sysfs_bin_attrs *iter);
+void qedi_remove_sysfs_attr(struct Scsi_Host *shost,
+			    struct sysfs_bin_attrs *iter);
+
+#ifdef CONFIG_DEBUG_FS
+/* DebugFS related code */
+struct qedi_list_of_funcs {
+	char *oper_str;
+	ssize_t (*oper_func)(struct qedi_dbg_ctx *qedi);
+};
+
+struct qedi_debugfs_ops {
+	char *name;
+	struct qedi_list_of_funcs *qedi_funcs;
+};
+
+#define qedi_dbg_fileops(drv, ops) \
+{ \
+	.owner  = THIS_MODULE, \
+	.open   = simple_open, \
+	.read   = drv##_dbg_##ops##_cmd_read, \
+	.write  = drv##_dbg_##ops##_cmd_write \
+}
+
+/* Used for debugfs sequential files */
+#define qedi_dbg_fileops_seq(drv, ops) \
+{ \
+	.owner = THIS_MODULE, \
+	.open = drv##_dbg_##ops##_open, \
+	.read = seq_read, \
+	.llseek = seq_lseek, \
+	.release = single_release, \
+}
+
+void qedi_dbg_host_init(struct qedi_dbg_ctx *qedi,
+			struct qedi_debugfs_ops *dops,
+			const struct file_operations *fops);
+void qedi_dbg_host_exit(struct qedi_dbg_ctx *qedi);
+void qedi_dbg_init(char *drv_name);
+void qedi_dbg_exit(void);
+#endif /* CONFIG_DEBUG_FS */
+
+#endif /* _QEDI_DBG_H_ */
diff --git a/drivers/scsi/qedi/qedi_debugfs.c b/drivers/scsi/qedi/qedi_debugfs.c
new file mode 100644
index 000000000000..955936274241
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_debugfs.c
@@ -0,0 +1,244 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include "qedi.h"
+#include "qedi_dbg.h"
+
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/module.h>
+
+int do_not_recover;
+static struct dentry *qedi_dbg_root;
+
+void
+qedi_dbg_host_init(struct qedi_dbg_ctx *qedi,
+		   struct qedi_debugfs_ops *dops,
+		   const struct file_operations *fops)
+{
+	char host_dirname[32];
+	struct dentry *file_dentry = NULL;
+
+	sprintf(host_dirname, "host%u", qedi->host_no);
+	qedi->bdf_dentry = debugfs_create_dir(host_dirname, qedi_dbg_root);
+	if (!qedi->bdf_dentry)
+		return;
+
+	while (dops) {
+		if (!(dops->name))
+			break;
+
+		file_dentry = debugfs_create_file(dops->name, 0600,
+						  qedi->bdf_dentry, qedi,
+						  fops);
+		if (!file_dentry) {
+			QEDI_INFO(qedi, QEDI_LOG_DEBUGFS,
+				  "Debugfs entry %s creation failed\n",
+				  dops->name);
+			debugfs_remove_recursive(qedi->bdf_dentry);
+			return;
+		}
+		dops++;
+		fops++;
+	}
+}
+
+void
+qedi_dbg_host_exit(struct qedi_dbg_ctx *qedi)
+{
+	debugfs_remove_recursive(qedi->bdf_dentry);
+	qedi->bdf_dentry = NULL;
+}
+
+void
+qedi_dbg_init(char *drv_name)
+{
+	qedi_dbg_root = debugfs_create_dir(drv_name, NULL);
+	if (!qedi_dbg_root)
+		QEDI_INFO(NULL, QEDI_LOG_DEBUGFS, "Init of debugfs failed\n");
+}
+
+void
+qedi_dbg_exit(void)
+{
+	debugfs_remove_recursive(qedi_dbg_root);
+	qedi_dbg_root = NULL;
+}
+
+static ssize_t
+qedi_dbg_do_not_recover_enable(struct qedi_dbg_ctx *qedi_dbg)
+{
+	if (!do_not_recover)
+		do_not_recover = 1;
+
+	QEDI_INFO(qedi_dbg, QEDI_LOG_DEBUGFS, "do_not_recover=%d\n",
+		  do_not_recover);
+	return 0;
+}
+
+static ssize_t
+qedi_dbg_do_not_recover_disable(struct qedi_dbg_ctx *qedi_dbg)
+{
+	if (do_not_recover)
+		do_not_recover = 0;
+
+	QEDI_INFO(qedi_dbg, QEDI_LOG_DEBUGFS, "do_not_recover=%d\n",
+		  do_not_recover);
+	return 0;
+}
+
+static struct qedi_list_of_funcs qedi_dbg_do_not_recover_ops[] = {
+	{ "enable", qedi_dbg_do_not_recover_enable },
+	{ "disable", qedi_dbg_do_not_recover_disable },
+	{ NULL, NULL }
+};
+
+struct qedi_debugfs_ops qedi_debugfs_ops[] = {
+	{ "gbl_ctx", NULL },
+	{ "do_not_recover", qedi_dbg_do_not_recover_ops},
+	{ "io_trace", NULL },
+	{ NULL, NULL }
+};
+
+static ssize_t
+qedi_dbg_do_not_recover_cmd_write(struct file *filp, const char __user *buffer,
+				  size_t count, loff_t *ppos)
+{
+	size_t cnt = 0;
+	struct qedi_dbg_ctx *qedi_dbg =
+			(struct qedi_dbg_ctx *)filp->private_data;
+	struct qedi_list_of_funcs *lof = qedi_dbg_do_not_recover_ops;
+
+	if (*ppos)
+		return 0;
+
+	while (lof) {
+		if (!(lof->oper_str))
+			break;
+
+		if (!strncmp(lof->oper_str, buffer, strlen(lof->oper_str))) {
+			cnt = lof->oper_func(qedi_dbg);
+			break;
+		}
+
+		lof++;
+	}
+	return (count - cnt);
+}
+
+static ssize_t
+qedi_dbg_do_not_recover_cmd_read(struct file *filp, char __user *buffer,
+				 size_t count, loff_t *ppos)
+{
+	size_t cnt = 0;
+
+	if (*ppos)
+		return 0;
+
+	cnt = sprintf(buffer, "do_not_recover=%d\n", do_not_recover);
+	cnt = min_t(int, count, cnt - *ppos);
+	*ppos += cnt;
+	return cnt;
+}
+
+static int
+qedi_gbl_ctx_show(struct seq_file *s, void *unused)
+{
+	struct qedi_fastpath *fp = NULL;
+	struct qed_sb_info *sb_info = NULL;
+	struct status_block *sb = NULL;
+	struct global_queue *que = NULL;
+	int id;
+	u16 prod_idx;
+	struct qedi_ctx *qedi = s->private;
+	unsigned long flags;
+
+	seq_puts(s, " DUMP CQ CONTEXT:\n");
+
+	for (id = 0; id < MIN_NUM_CPUS_MSIX(qedi); id++) {
+		spin_lock_irqsave(&qedi->hba_lock, flags);
+		seq_printf(s, "=========FAST CQ PATH [%d] ==========\n", id);
+		fp = &qedi->fp_array[id];
+		sb_info = fp->sb_info;
+		sb = sb_info->sb_virt;
+		prod_idx = (sb->pi_array[QEDI_PROTO_CQ_PROD_IDX] &
+			    STATUS_BLOCK_PROD_INDEX_MASK);
+		seq_printf(s, "SB PROD IDX: %d\n", prod_idx);
+		que = qedi->global_queues[fp->sb_id];
+		seq_printf(s, "DRV CONS IDX: %d\n", que->cq_cons_idx);
+		seq_printf(s, "CQ complete host memory: %d\n", fp->sb_id);
+		seq_puts(s, "=========== END ==================\n\n\n");
+		spin_unlock_irqrestore(&qedi->hba_lock, flags);
+	}
+	return 0;
+}
+
+static int
+qedi_dbg_gbl_ctx_open(struct inode *inode, struct file *file)
+{
+	struct qedi_dbg_ctx *qedi_dbg = inode->i_private;
+	struct qedi_ctx *qedi = container_of(qedi_dbg, struct qedi_ctx,
+					     dbg_ctx);
+
+	return single_open(file, qedi_gbl_ctx_show, qedi);
+}
+
+static int
+qedi_io_trace_show(struct seq_file *s, void *unused)
+{
+	int id, idx = 0;
+	struct qedi_ctx *qedi = s->private;
+	struct qedi_io_log *io_log;
+	unsigned long flags;
+
+	seq_puts(s, " DUMP IO LOGS:\n");
+	spin_lock_irqsave(&qedi->io_trace_lock, flags);
+	idx = qedi->io_trace_idx;
+	for (id = 0; id < QEDI_IO_TRACE_SIZE; id++) {
+		io_log = &qedi->io_trace_buf[idx];
+		seq_printf(s, "iodir-%d:", io_log->direction);
+		seq_printf(s, "tid-0x%x:", io_log->task_id);
+		seq_printf(s, "cid-0x%x:", io_log->cid);
+		seq_printf(s, "lun-%d:", io_log->lun);
+		seq_printf(s, "op-0x%02x:", io_log->op);
+		seq_printf(s, "0x%02x%02x%02x%02x:", io_log->lba[0],
+			   io_log->lba[1], io_log->lba[2], io_log->lba[3]);
+		seq_printf(s, "buflen-%d:", io_log->bufflen);
+		seq_printf(s, "sgcnt-%d:", io_log->sg_count);
+		seq_printf(s, "res-0x%08x:", io_log->result);
+		seq_printf(s, "jif-%lu:", io_log->jiffies);
+		seq_printf(s, "blk_req_cpu-%d:", io_log->blk_req_cpu);
+		seq_printf(s, "req_cpu-%d:", io_log->req_cpu);
+		seq_printf(s, "intr_cpu-%d:", io_log->intr_cpu);
+		seq_printf(s, "blk_rsp_cpu-%d\n", io_log->blk_rsp_cpu);
+
+		idx++;
+		if (idx == QEDI_IO_TRACE_SIZE)
+			idx = 0;
+	}
+	spin_unlock_irqrestore(&qedi->io_trace_lock, flags);
+	return 0;
+}
+
+static int
+qedi_dbg_io_trace_open(struct inode *inode, struct file *file)
+{
+	struct qedi_dbg_ctx *qedi_dbg = inode->i_private;
+	struct qedi_ctx *qedi = container_of(qedi_dbg, struct qedi_ctx,
+					     dbg_ctx);
+
+	return single_open(file, qedi_io_trace_show, qedi);
+}
+
+const struct file_operations qedi_dbg_fops[] = {
+	qedi_dbg_fileops_seq(qedi, gbl_ctx),
+	qedi_dbg_fileops(qedi, do_not_recover),
+	qedi_dbg_fileops_seq(qedi, io_trace),
+	{ NULL, NULL },
+};
diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c
new file mode 100644
index 000000000000..b1d3904ae8fd
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_fw.c
@@ -0,0 +1,2378 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include <linux/blkdev.h>
+#include <scsi/scsi_tcq.h>
+#include <linux/delay.h>
+
+#include "qedi.h"
+#include "qedi_iscsi.h"
+#include "qedi_gbl.h"
+
+static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
+			       struct iscsi_task *mtask);
+
+void qedi_iscsi_unmap_sg_list(struct qedi_cmd *cmd)
+{
+	struct scsi_cmnd *sc = cmd->scsi_cmd;
+
+	if (cmd->io_tbl.sge_valid && sc) {
+		cmd->io_tbl.sge_valid = 0;
+		scsi_dma_unmap(sc);
+	}
+}
+
+static void qedi_process_logout_resp(struct qedi_ctx *qedi,
+				     union iscsi_cqe *cqe,
+				     struct iscsi_task *task,
+				     struct qedi_conn *qedi_conn)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_logout_rsp *resp_hdr;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_logout_response_hdr *cqe_logout_response;
+	struct qedi_cmd *cmd;
+
+	cmd = (struct qedi_cmd *)task->dd_data;
+	cqe_logout_response = &cqe->cqe_common.iscsi_hdr.logout_response;
+	spin_lock(&session->back_lock);
+	resp_hdr = (struct iscsi_logout_rsp *)&qedi_conn->gen_pdu.resp_hdr;
+	memset(resp_hdr, 0, sizeof(struct iscsi_hdr));
+	resp_hdr->opcode = cqe_logout_response->opcode;
+	resp_hdr->flags = cqe_logout_response->flags;
+	resp_hdr->hlength = 0;
+
+	resp_hdr->itt = build_itt(cqe->cqe_solicited.itid, conn->session->age);
+	resp_hdr->statsn = cpu_to_be32(cqe_logout_response->stat_sn);
+	resp_hdr->exp_cmdsn = cpu_to_be32(cqe_logout_response->exp_cmd_sn);
+	resp_hdr->max_cmdsn = cpu_to_be32(cqe_logout_response->max_cmd_sn);
+
+	resp_hdr->t2wait = cpu_to_be32(cqe_logout_response->time2wait);
+	resp_hdr->t2retain = cpu_to_be32(cqe_logout_response->time2retain);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+		  "Freeing tid=0x%x for cid=0x%x\n",
+		  cmd->task_id, qedi_conn->iscsi_conn_id);
+
+	if (likely(cmd->io_cmd_in_list)) {
+		cmd->io_cmd_in_list = false;
+		list_del_init(&cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+	} else {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "Active cmd list node already deleted, tid=0x%x, cid=0x%x, io_cmd_node=%p\n",
+			  cmd->task_id, qedi_conn->iscsi_conn_id,
+			  &cmd->io_cmd);
+	}
+
+	cmd->state = RESPONSE_RECEIVED;
+	qedi_clear_task_idx(qedi, cmd->task_id);
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)resp_hdr, NULL, 0);
+
+	spin_unlock(&session->back_lock);
+}
+
+static void qedi_process_text_resp(struct qedi_ctx *qedi,
+				   union iscsi_cqe *cqe,
+				   struct iscsi_task *task,
+				   struct qedi_conn *qedi_conn)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_task_context *task_ctx;
+	struct iscsi_text_rsp *resp_hdr_ptr;
+	struct iscsi_text_response_hdr *cqe_text_response;
+	struct qedi_cmd *cmd;
+	int pld_len;
+	u32 *tmp;
+
+	cmd = (struct qedi_cmd *)task->dd_data;
+	task_ctx = qedi_get_task_mem(&qedi->tasks, cmd->task_id);
+
+	cqe_text_response = &cqe->cqe_common.iscsi_hdr.text_response;
+	spin_lock(&session->back_lock);
+	resp_hdr_ptr =  (struct iscsi_text_rsp *)&qedi_conn->gen_pdu.resp_hdr;
+	memset(resp_hdr_ptr, 0, sizeof(struct iscsi_hdr));
+	resp_hdr_ptr->opcode = cqe_text_response->opcode;
+	resp_hdr_ptr->flags = cqe_text_response->flags;
+	resp_hdr_ptr->hlength = 0;
+
+	hton24(resp_hdr_ptr->dlength,
+	       (cqe_text_response->hdr_second_dword &
+		ISCSI_TEXT_RESPONSE_HDR_DATA_SEG_LEN_MASK));
+	tmp = (u32 *)resp_hdr_ptr->dlength;
+
+	resp_hdr_ptr->itt = build_itt(cqe->cqe_solicited.itid,
+				      conn->session->age);
+	resp_hdr_ptr->ttt = cqe_text_response->ttt;
+	resp_hdr_ptr->statsn = cpu_to_be32(cqe_text_response->stat_sn);
+	resp_hdr_ptr->exp_cmdsn = cpu_to_be32(cqe_text_response->exp_cmd_sn);
+	resp_hdr_ptr->max_cmdsn = cpu_to_be32(cqe_text_response->max_cmd_sn);
+
+	pld_len = cqe_text_response->hdr_second_dword &
+		  ISCSI_TEXT_RESPONSE_HDR_DATA_SEG_LEN_MASK;
+	qedi_conn->gen_pdu.resp_wr_ptr = qedi_conn->gen_pdu.resp_buf + pld_len;
+
+	memset(task_ctx, '\0', sizeof(*task_ctx));
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+		  "Freeing tid=0x%x for cid=0x%x\n",
+		  cmd->task_id, qedi_conn->iscsi_conn_id);
+
+	if (likely(cmd->io_cmd_in_list)) {
+		cmd->io_cmd_in_list = false;
+		list_del_init(&cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+	} else {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "Active cmd list node already deleted, tid=0x%x, cid=0x%x, io_cmd_node=%p\n",
+			  cmd->task_id, qedi_conn->iscsi_conn_id,
+			  &cmd->io_cmd);
+	}
+
+	cmd->state = RESPONSE_RECEIVED;
+	qedi_clear_task_idx(qedi, cmd->task_id);
+
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)resp_hdr_ptr,
+			     qedi_conn->gen_pdu.resp_buf,
+			     (qedi_conn->gen_pdu.resp_wr_ptr -
+			      qedi_conn->gen_pdu.resp_buf));
+	spin_unlock(&session->back_lock);
+}
+
+static void qedi_tmf_resp_work(struct work_struct *work)
+{
+	struct qedi_cmd *qedi_cmd =
+				container_of(work, struct qedi_cmd, tmf_work);
+	struct qedi_conn *qedi_conn = qedi_cmd->conn;
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_tm_rsp *resp_hdr_ptr;
+	struct iscsi_cls_session *cls_sess;
+	int rval = 0;
+
+	set_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+	resp_hdr_ptr =  (struct iscsi_tm_rsp *)qedi_cmd->tmf_resp_buf;
+	cls_sess = iscsi_conn_to_session(qedi_conn->cls_conn);
+
+	iscsi_block_session(session->cls_session);
+	rval = qedi_cleanup_all_io(qedi, qedi_conn, qedi_cmd->task, true);
+	if (rval) {
+		clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+		qedi_clear_task_idx(qedi, qedi_cmd->task_id);
+		iscsi_unblock_session(session->cls_session);
+		return;
+	}
+
+	iscsi_unblock_session(session->cls_session);
+	qedi_clear_task_idx(qedi, qedi_cmd->task_id);
+
+	spin_lock(&session->back_lock);
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)resp_hdr_ptr, NULL, 0);
+	spin_unlock(&session->back_lock);
+	kfree(resp_hdr_ptr);
+	clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+}
+
+static void qedi_process_tmf_resp(struct qedi_ctx *qedi,
+				  union iscsi_cqe *cqe,
+				  struct iscsi_task *task,
+				  struct qedi_conn *qedi_conn)
+
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_tmf_response_hdr *cqe_tmp_response;
+	struct iscsi_tm_rsp *resp_hdr_ptr;
+	struct iscsi_tm *tmf_hdr;
+	struct qedi_cmd *qedi_cmd = NULL;
+	u32 *tmp;
+
+	cqe_tmp_response = &cqe->cqe_common.iscsi_hdr.tmf_response;
+
+	qedi_cmd = task->dd_data;
+	qedi_cmd->tmf_resp_buf = kzalloc(sizeof(*resp_hdr_ptr), GFP_KERNEL);
+	if (!qedi_cmd->tmf_resp_buf) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Failed to allocate resp buf, cid=0x%x\n",
+			  qedi_conn->iscsi_conn_id);
+		return;
+	}
+
+	spin_lock(&session->back_lock);
+	resp_hdr_ptr =  (struct iscsi_tm_rsp *)qedi_cmd->tmf_resp_buf;
+	memset(resp_hdr_ptr, 0, sizeof(struct iscsi_tm_rsp));
+
+	/* Fill up the header */
+	resp_hdr_ptr->opcode = cqe_tmp_response->opcode;
+	resp_hdr_ptr->flags = cqe_tmp_response->hdr_flags;
+	resp_hdr_ptr->response = cqe_tmp_response->hdr_response;
+	resp_hdr_ptr->hlength = 0;
+
+	hton24(resp_hdr_ptr->dlength,
+	       (cqe_tmp_response->hdr_second_dword &
+		ISCSI_TMF_RESPONSE_HDR_DATA_SEG_LEN_MASK));
+	tmp = (u32 *)resp_hdr_ptr->dlength;
+	resp_hdr_ptr->itt = build_itt(cqe->cqe_solicited.itid,
+				      conn->session->age);
+	resp_hdr_ptr->statsn = cpu_to_be32(cqe_tmp_response->stat_sn);
+	resp_hdr_ptr->exp_cmdsn  = cpu_to_be32(cqe_tmp_response->exp_cmd_sn);
+	resp_hdr_ptr->max_cmdsn = cpu_to_be32(cqe_tmp_response->max_cmd_sn);
+
+	tmf_hdr = (struct iscsi_tm *)qedi_cmd->task->hdr;
+
+	if (likely(qedi_cmd->io_cmd_in_list)) {
+		qedi_cmd->io_cmd_in_list = false;
+		list_del_init(&qedi_cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+	}
+
+	if (((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+	      ISCSI_TM_FUNC_LOGICAL_UNIT_RESET) ||
+	    ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+	      ISCSI_TM_FUNC_TARGET_WARM_RESET) ||
+	    ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+	      ISCSI_TM_FUNC_TARGET_COLD_RESET)) {
+		INIT_WORK(&qedi_cmd->tmf_work, qedi_tmf_resp_work);
+		queue_work(qedi->tmf_thread, &qedi_cmd->tmf_work);
+		goto unblock_sess;
+	}
+
+	qedi_clear_task_idx(qedi, qedi_cmd->task_id);
+
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)resp_hdr_ptr, NULL, 0);
+	kfree(resp_hdr_ptr);
+
+unblock_sess:
+	spin_unlock(&session->back_lock);
+}
+
+static void qedi_process_login_resp(struct qedi_ctx *qedi,
+				    union iscsi_cqe *cqe,
+				    struct iscsi_task *task,
+				    struct qedi_conn *qedi_conn)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_task_context *task_ctx;
+	struct iscsi_login_rsp *resp_hdr_ptr;
+	struct iscsi_login_response_hdr *cqe_login_response;
+	struct qedi_cmd *cmd;
+	int pld_len;
+	u32 *tmp;
+
+	cmd = (struct qedi_cmd *)task->dd_data;
+
+	cqe_login_response = &cqe->cqe_common.iscsi_hdr.login_response;
+	task_ctx = qedi_get_task_mem(&qedi->tasks, cmd->task_id);
+
+	spin_lock(&session->back_lock);
+	resp_hdr_ptr =  (struct iscsi_login_rsp *)&qedi_conn->gen_pdu.resp_hdr;
+	memset(resp_hdr_ptr, 0, sizeof(struct iscsi_login_rsp));
+	resp_hdr_ptr->opcode = cqe_login_response->opcode;
+	resp_hdr_ptr->flags = cqe_login_response->flags_attr;
+	resp_hdr_ptr->hlength = 0;
+
+	hton24(resp_hdr_ptr->dlength,
+	       (cqe_login_response->hdr_second_dword &
+		ISCSI_LOGIN_RESPONSE_HDR_DATA_SEG_LEN_MASK));
+	tmp = (u32 *)resp_hdr_ptr->dlength;
+	resp_hdr_ptr->itt = build_itt(cqe->cqe_solicited.itid,
+				      conn->session->age);
+	resp_hdr_ptr->tsih = cqe_login_response->tsih;
+	resp_hdr_ptr->statsn = cpu_to_be32(cqe_login_response->stat_sn);
+	resp_hdr_ptr->exp_cmdsn = cpu_to_be32(cqe_login_response->exp_cmd_sn);
+	resp_hdr_ptr->max_cmdsn = cpu_to_be32(cqe_login_response->max_cmd_sn);
+	resp_hdr_ptr->status_class = cqe_login_response->status_class;
+	resp_hdr_ptr->status_detail = cqe_login_response->status_detail;
+	pld_len = cqe_login_response->hdr_second_dword &
+		  ISCSI_LOGIN_RESPONSE_HDR_DATA_SEG_LEN_MASK;
+	qedi_conn->gen_pdu.resp_wr_ptr = qedi_conn->gen_pdu.resp_buf + pld_len;
+
+	if (likely(cmd->io_cmd_in_list)) {
+		cmd->io_cmd_in_list = false;
+		list_del_init(&cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+	}
+
+	memset(task_ctx, '\0', sizeof(*task_ctx));
+
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)resp_hdr_ptr,
+			     qedi_conn->gen_pdu.resp_buf,
+			     (qedi_conn->gen_pdu.resp_wr_ptr -
+			     qedi_conn->gen_pdu.resp_buf));
+
+	spin_unlock(&session->back_lock);
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+		  "Freeing tid=0x%x for cid=0x%x\n",
+		  cmd->task_id, qedi_conn->iscsi_conn_id);
+	cmd->state = RESPONSE_RECEIVED;
+	qedi_clear_task_idx(qedi, cmd->task_id);
+}
+
+static void qedi_get_rq_bdq_buf(struct qedi_ctx *qedi,
+				struct iscsi_cqe_unsolicited *cqe,
+				char *ptr, int len)
+{
+	u16 idx = 0;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "pld_len [%d], bdq_prod_idx [%d], idx [%d]\n",
+		  len, qedi->bdq_prod_idx,
+		  (qedi->bdq_prod_idx % qedi->rq_num_entries));
+
+	/* Obtain buffer address from rqe_opaque */
+	idx = cqe->rqe_opaque.lo;
+	if ((idx < 0) || (idx > (QEDI_BDQ_NUM - 1))) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "wrong idx %d returned by FW, dropping the unsolicited pkt\n",
+			  idx);
+		return;
+	}
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "rqe_opaque.lo [0x%p], rqe_opaque.hi [0x%p], idx [%d]\n",
+		  cqe->rqe_opaque.lo, cqe->rqe_opaque.hi, idx);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "unsol_cqe_type = %d\n", cqe->unsol_cqe_type);
+	switch (cqe->unsol_cqe_type) {
+	case ISCSI_CQE_UNSOLICITED_SINGLE:
+	case ISCSI_CQE_UNSOLICITED_FIRST:
+		if (len)
+			memcpy(ptr, (void *)qedi->bdq[idx].buf_addr, len);
+		break;
+	case ISCSI_CQE_UNSOLICITED_MIDDLE:
+	case ISCSI_CQE_UNSOLICITED_LAST:
+		break;
+	default:
+		break;
+	}
+}
+
+static void qedi_put_rq_bdq_buf(struct qedi_ctx *qedi,
+				struct iscsi_cqe_unsolicited *cqe,
+				int count)
+{
+	u16 tmp;
+	u16 idx = 0;
+	struct scsi_bd *pbl;
+
+	/* Obtain buffer address from rqe_opaque */
+	idx = cqe->rqe_opaque.lo;
+	if ((idx < 0) || (idx > (QEDI_BDQ_NUM - 1))) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "wrong idx %d returned by FW, dropping the unsolicited pkt\n",
+			  idx);
+		return;
+	}
+
+	pbl = (struct scsi_bd *)qedi->bdq_pbl;
+	pbl += (qedi->bdq_prod_idx % qedi->rq_num_entries);
+	pbl->address.hi = cpu_to_le32(QEDI_U64_HI(qedi->bdq[idx].buf_dma));
+	pbl->address.lo = cpu_to_le32(QEDI_U64_LO(qedi->bdq[idx].buf_dma));
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "pbl [0x%p] pbl->address hi [0x%llx] lo [0x%llx] idx [%d]\n",
+		  pbl, pbl->address.hi, pbl->address.lo, idx);
+	pbl->opaque.hi = 0;
+	pbl->opaque.lo = cpu_to_le32(QEDI_U64_LO(idx));
+
+	/* Increment producer to let f/w know we've handled the frame */
+	qedi->bdq_prod_idx += count;
+
+	writew(qedi->bdq_prod_idx, qedi->bdq_primary_prod);
+	tmp = readw(qedi->bdq_primary_prod);
+
+	writew(qedi->bdq_prod_idx, qedi->bdq_secondary_prod);
+	tmp = readw(qedi->bdq_secondary_prod);
+}
+
+static void qedi_unsol_pdu_adjust_bdq(struct qedi_ctx *qedi,
+				      struct iscsi_cqe_unsolicited *cqe,
+				      u32 pdu_len, u32 num_bdqs,
+				      char *bdq_data)
+{
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "num_bdqs [%d]\n", num_bdqs);
+
+	qedi_get_rq_bdq_buf(qedi, cqe, bdq_data, pdu_len);
+	qedi_put_rq_bdq_buf(qedi, cqe, (num_bdqs + 1));
+}
+
+static int qedi_process_nopin_mesg(struct qedi_ctx *qedi,
+				   union iscsi_cqe *cqe,
+				   struct iscsi_task *task,
+				   struct qedi_conn *qedi_conn, u16 que_idx)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_nop_in_hdr *cqe_nop_in;
+	struct iscsi_nopin *hdr;
+	struct qedi_cmd *cmd;
+	int tgt_async_nop = 0;
+	u32 lun[2];
+	u32 pdu_len, num_bdqs;
+	char bdq_data[QEDI_BDQ_BUF_SIZE];
+	unsigned long flags;
+
+	spin_lock_bh(&session->back_lock);
+	cqe_nop_in = &cqe->cqe_common.iscsi_hdr.nop_in;
+
+	pdu_len = cqe_nop_in->hdr_second_dword &
+		  ISCSI_NOP_IN_HDR_DATA_SEG_LEN_MASK;
+	num_bdqs = pdu_len / QEDI_BDQ_BUF_SIZE;
+
+	hdr = (struct iscsi_nopin *)&qedi_conn->gen_pdu.resp_hdr;
+	memset(hdr, 0, sizeof(struct iscsi_hdr));
+	hdr->opcode = cqe_nop_in->opcode;
+	hdr->max_cmdsn = cpu_to_be32(cqe_nop_in->max_cmd_sn);
+	hdr->exp_cmdsn = cpu_to_be32(cqe_nop_in->exp_cmd_sn);
+	hdr->statsn = cpu_to_be32(cqe_nop_in->stat_sn);
+	hdr->ttt = cpu_to_be32(cqe_nop_in->ttt);
+
+	if (cqe->cqe_common.cqe_type == ISCSI_CQE_TYPE_UNSOLICITED) {
+		spin_lock_irqsave(&qedi->hba_lock, flags);
+		qedi_unsol_pdu_adjust_bdq(qedi, &cqe->cqe_unsolicited,
+					  pdu_len, num_bdqs, bdq_data);
+		hdr->itt = RESERVED_ITT;
+		tgt_async_nop = 1;
+		spin_unlock_irqrestore(&qedi->hba_lock, flags);
+		goto done;
+	}
+
+	/* Response to one of our nop-outs */
+	if (task) {
+		cmd = task->dd_data;
+		hdr->flags = ISCSI_FLAG_CMD_FINAL;
+		hdr->itt = build_itt(cqe->cqe_solicited.itid,
+				     conn->session->age);
+		lun[0] = 0xffffffff;
+		lun[1] = 0xffffffff;
+		memcpy(&hdr->lun, lun, sizeof(struct scsi_lun));
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+			  "Freeing tid=0x%x for cid=0x%x\n",
+			  cmd->task_id, qedi_conn->iscsi_conn_id);
+		cmd->state = RESPONSE_RECEIVED;
+		spin_lock(&qedi_conn->list_lock);
+		if (likely(cmd->io_cmd_in_list)) {
+			cmd->io_cmd_in_list = false;
+			list_del_init(&cmd->io_cmd);
+			qedi_conn->active_cmd_count--;
+		}
+
+		spin_unlock(&qedi_conn->list_lock);
+		qedi_clear_task_idx(qedi, cmd->task_id);
+	}
+
+done:
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)hdr, bdq_data, pdu_len);
+
+	spin_unlock_bh(&session->back_lock);
+	return tgt_async_nop;
+}
+
+static void qedi_process_async_mesg(struct qedi_ctx *qedi,
+				    union iscsi_cqe *cqe,
+				    struct iscsi_task *task,
+				    struct qedi_conn *qedi_conn,
+				    u16 que_idx)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_async_msg_hdr *cqe_async_msg;
+	struct iscsi_async *resp_hdr;
+	u32 lun[2];
+	u32 pdu_len, num_bdqs;
+	char bdq_data[QEDI_BDQ_BUF_SIZE];
+	unsigned long flags;
+
+	spin_lock_bh(&session->back_lock);
+
+	cqe_async_msg = &cqe->cqe_common.iscsi_hdr.async_msg;
+	pdu_len = cqe_async_msg->hdr_second_dword &
+		ISCSI_ASYNC_MSG_HDR_DATA_SEG_LEN_MASK;
+	num_bdqs = pdu_len / QEDI_BDQ_BUF_SIZE;
+
+	if (cqe->cqe_common.cqe_type == ISCSI_CQE_TYPE_UNSOLICITED) {
+		spin_lock_irqsave(&qedi->hba_lock, flags);
+		qedi_unsol_pdu_adjust_bdq(qedi, &cqe->cqe_unsolicited,
+					  pdu_len, num_bdqs, bdq_data);
+		spin_unlock_irqrestore(&qedi->hba_lock, flags);
+	}
+
+	resp_hdr = (struct iscsi_async *)&qedi_conn->gen_pdu.resp_hdr;
+	memset(resp_hdr, 0, sizeof(struct iscsi_hdr));
+	resp_hdr->opcode = cqe_async_msg->opcode;
+	resp_hdr->flags = 0x80;
+
+	lun[0] = cpu_to_be32(cqe_async_msg->lun.lo);
+	lun[1] = cpu_to_be32(cqe_async_msg->lun.hi);
+	memcpy(&resp_hdr->lun, lun, sizeof(struct scsi_lun));
+	resp_hdr->exp_cmdsn = cpu_to_be32(cqe_async_msg->exp_cmd_sn);
+	resp_hdr->max_cmdsn = cpu_to_be32(cqe_async_msg->max_cmd_sn);
+	resp_hdr->statsn = cpu_to_be32(cqe_async_msg->stat_sn);
+
+	resp_hdr->async_event = cqe_async_msg->async_event;
+	resp_hdr->async_vcode = cqe_async_msg->async_vcode;
+
+	resp_hdr->param1 = cpu_to_be16(cqe_async_msg->param1_rsrv);
+	resp_hdr->param2 = cpu_to_be16(cqe_async_msg->param2_rsrv);
+	resp_hdr->param3 = cpu_to_be16(cqe_async_msg->param3_rsrv);
+
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)resp_hdr, bdq_data,
+			     pdu_len);
+
+	spin_unlock_bh(&session->back_lock);
+}
+
+static void qedi_process_reject_mesg(struct qedi_ctx *qedi,
+				     union iscsi_cqe *cqe,
+				     struct iscsi_task *task,
+				     struct qedi_conn *qedi_conn,
+				     uint16_t que_idx)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_reject_hdr *cqe_reject;
+	struct iscsi_reject *hdr;
+	u32 pld_len, num_bdqs;
+	unsigned long flags;
+
+	spin_lock_bh(&session->back_lock);
+	cqe_reject = &cqe->cqe_common.iscsi_hdr.reject;
+	pld_len = cqe_reject->hdr_second_dword &
+		  ISCSI_REJECT_HDR_DATA_SEG_LEN_MASK;
+	num_bdqs = pld_len / QEDI_BDQ_BUF_SIZE;
+
+	if (cqe->cqe_common.cqe_type == ISCSI_CQE_TYPE_UNSOLICITED) {
+		spin_lock_irqsave(&qedi->hba_lock, flags);
+		qedi_unsol_pdu_adjust_bdq(qedi, &cqe->cqe_unsolicited,
+					  pld_len, num_bdqs, conn->data);
+		spin_unlock_irqrestore(&qedi->hba_lock, flags);
+	}
+	hdr = (struct iscsi_reject *)&qedi_conn->gen_pdu.resp_hdr;
+	memset(hdr, 0, sizeof(struct iscsi_hdr));
+	hdr->opcode = cqe_reject->opcode;
+	hdr->reason = cqe_reject->hdr_reason;
+	hdr->flags = cqe_reject->hdr_flags;
+	hton24(hdr->dlength, (cqe_reject->hdr_second_dword &
+			      ISCSI_REJECT_HDR_DATA_SEG_LEN_MASK));
+	hdr->max_cmdsn = cpu_to_be32(cqe_reject->max_cmd_sn);
+	hdr->exp_cmdsn = cpu_to_be32(cqe_reject->exp_cmd_sn);
+	hdr->statsn = cpu_to_be32(cqe_reject->stat_sn);
+	hdr->ffffffff = cpu_to_be32(0xffffffff);
+
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)hdr,
+			     conn->data, pld_len);
+	spin_unlock_bh(&session->back_lock);
+}
+
+static void qedi_scsi_completion(struct qedi_ctx *qedi,
+				 union iscsi_cqe *cqe,
+				 struct iscsi_task *task,
+				 struct iscsi_conn *conn)
+{
+	struct scsi_cmnd *sc_cmd;
+	struct qedi_cmd *cmd = task->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_scsi_rsp *hdr;
+	struct iscsi_data_in_hdr *cqe_data_in;
+	int datalen = 0;
+	struct qedi_conn *qedi_conn;
+	u32 iscsi_cid;
+	bool mark_cmd_node_deleted = false;
+	u8 cqe_err_bits = 0;
+
+	iscsi_cid  = cqe->cqe_common.conn_id;
+	qedi_conn = qedi->cid_que.conn_cid_tbl[iscsi_cid];
+
+	cqe_data_in = &cqe->cqe_common.iscsi_hdr.data_in;
+	cqe_err_bits =
+		cqe->cqe_common.error_bitmap.error_bits.cqe_error_status_bits;
+
+	spin_lock_bh(&session->back_lock);
+	/* get the scsi command */
+	sc_cmd = cmd->scsi_cmd;
+
+	if (!sc_cmd) {
+		QEDI_WARN(&qedi->dbg_ctx, "sc_cmd is NULL!\n");
+		goto error;
+	}
+
+	if (!sc_cmd->SCp.ptr) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "SCp.ptr is NULL, returned in another context.\n");
+		goto error;
+	}
+
+	if (!sc_cmd->request) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "sc_cmd->request is NULL, sc_cmd=%p.\n",
+			  sc_cmd);
+		goto error;
+	}
+
+	if (!sc_cmd->request->special) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "request->special is NULL so request not valid, sc_cmd=%p.\n",
+			  sc_cmd);
+		goto error;
+	}
+
+	if (!sc_cmd->request->q) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "request->q is NULL so request is not valid, sc_cmd=%p.\n",
+			  sc_cmd);
+		goto error;
+	}
+
+	qedi_iscsi_unmap_sg_list(cmd);
+
+	hdr = (struct iscsi_scsi_rsp *)task->hdr;
+	hdr->opcode = cqe_data_in->opcode;
+	hdr->max_cmdsn = cpu_to_be32(cqe_data_in->max_cmd_sn);
+	hdr->exp_cmdsn = cpu_to_be32(cqe_data_in->exp_cmd_sn);
+	hdr->itt = build_itt(cqe->cqe_solicited.itid, conn->session->age);
+	hdr->response = cqe_data_in->reserved1;
+	hdr->cmd_status = cqe_data_in->status_rsvd;
+	hdr->flags = cqe_data_in->flags;
+	hdr->residual_count = cpu_to_be32(cqe_data_in->residual_count);
+
+	if (hdr->cmd_status == SAM_STAT_CHECK_CONDITION) {
+		datalen = cqe_data_in->reserved2 &
+			  ISCSI_COMMON_HDR_DATA_SEG_LEN_MASK;
+		memcpy((char *)conn->data, (char *)cmd->sense_buffer, datalen);
+	}
+
+	/* If f/w reports data underrun err then set residual to IO transfer
+	 * length, set Underrun flag and clear Overrun flag explicitly
+	 */
+	if (unlikely(cqe_err_bits &&
+		     GET_FIELD(cqe_err_bits, CQE_ERROR_BITMAP_UNDER_RUN_ERR))) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "Under flow itt=0x%x proto flags=0x%x tid=0x%x cid 0x%x fw resid 0x%x sc dlen 0x%x\n",
+			  hdr->itt, cqe_data_in->flags, cmd->task_id,
+			  qedi_conn->iscsi_conn_id, hdr->residual_count,
+			  scsi_bufflen(sc_cmd));
+		hdr->residual_count = cpu_to_be32(scsi_bufflen(sc_cmd));
+		hdr->flags |= ISCSI_FLAG_CMD_UNDERFLOW;
+		hdr->flags &= (~ISCSI_FLAG_CMD_OVERFLOW);
+	}
+
+	spin_lock(&qedi_conn->list_lock);
+	if (likely(cmd->io_cmd_in_list)) {
+		cmd->io_cmd_in_list = false;
+		list_del_init(&cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+		mark_cmd_node_deleted = true;
+	}
+	spin_unlock(&qedi_conn->list_lock);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+		  "Freeing tid=0x%x for cid=0x%x\n",
+		  cmd->task_id, qedi_conn->iscsi_conn_id);
+	cmd->state = RESPONSE_RECEIVED;
+	if (qedi_io_tracing)
+		qedi_trace_io(qedi, task, cmd->task_id, QEDI_IO_TRACE_RSP);
+
+	qedi_clear_task_idx(qedi, cmd->task_id);
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)hdr,
+			     conn->data, datalen);
+error:
+	spin_unlock_bh(&session->back_lock);
+}
+
+static void qedi_mtask_completion(struct qedi_ctx *qedi,
+				  union iscsi_cqe *cqe,
+				  struct iscsi_task *task,
+				  struct qedi_conn *conn, uint16_t que_idx)
+{
+	struct iscsi_conn *iscsi_conn;
+	u32 hdr_opcode;
+
+	hdr_opcode = cqe->cqe_common.iscsi_hdr.common.hdr_first_byte;
+	iscsi_conn = conn->cls_conn->dd_data;
+
+	switch (hdr_opcode) {
+	case ISCSI_OPCODE_SCSI_RESPONSE:
+	case ISCSI_OPCODE_DATA_IN:
+		qedi_scsi_completion(qedi, cqe, task, iscsi_conn);
+		break;
+	case ISCSI_OPCODE_LOGIN_RESPONSE:
+		qedi_process_login_resp(qedi, cqe, task, conn);
+		break;
+	case ISCSI_OPCODE_TMF_RESPONSE:
+		qedi_process_tmf_resp(qedi, cqe, task, conn);
+		break;
+	case ISCSI_OPCODE_TEXT_RESPONSE:
+		qedi_process_text_resp(qedi, cqe, task, conn);
+		break;
+	case ISCSI_OPCODE_LOGOUT_RESPONSE:
+		qedi_process_logout_resp(qedi, cqe, task, conn);
+		break;
+	case ISCSI_OPCODE_NOP_IN:
+		qedi_process_nopin_mesg(qedi, cqe, task, conn, que_idx);
+		break;
+	default:
+		QEDI_ERR(&qedi->dbg_ctx, "unknown opcode\n");
+	}
+}
+
+static void qedi_process_nopin_local_cmpl(struct qedi_ctx *qedi,
+					  struct iscsi_cqe_solicited *cqe,
+					  struct iscsi_task *task,
+					  struct qedi_conn *qedi_conn)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct qedi_cmd *cmd = task->dd_data;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_UNSOL,
+		  "itid=0x%x, cmd task id=0x%x\n",
+		  cqe->itid, cmd->task_id);
+
+	cmd->state = RESPONSE_RECEIVED;
+	qedi_clear_task_idx(qedi, cmd->task_id);
+
+	spin_lock_bh(&session->back_lock);
+	__iscsi_put_task(task);
+	spin_unlock_bh(&session->back_lock);
+}
+
+static void qedi_process_cmd_cleanup_resp(struct qedi_ctx *qedi,
+					  struct iscsi_cqe_solicited *cqe,
+					  struct iscsi_task *task,
+					  struct iscsi_conn *conn)
+{
+	struct qedi_work_map *work, *work_tmp;
+	u32 proto_itt = cqe->itid;
+	u32 ptmp_itt = 0;
+	itt_t protoitt = 0;
+	int found = 0;
+	struct qedi_cmd *qedi_cmd = NULL;
+	u32 rtid = 0;
+	u32 iscsi_cid;
+	struct qedi_conn *qedi_conn;
+	struct qedi_cmd *cmd_new, *dbg_cmd;
+	struct iscsi_task *mtask;
+	struct iscsi_tm *tmf_hdr = NULL;
+
+	iscsi_cid = cqe->conn_id;
+	qedi_conn = qedi->cid_que.conn_cid_tbl[iscsi_cid];
+
+	/* Based on this itt get the corresponding qedi_cmd */
+	spin_lock_bh(&qedi_conn->tmf_work_lock);
+	list_for_each_entry_safe(work, work_tmp, &qedi_conn->tmf_work_list,
+				 list) {
+		if (work->rtid == proto_itt) {
+			/* We found the command */
+			qedi_cmd = work->qedi_cmd;
+			if (!qedi_cmd->list_tmf_work) {
+				QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+					  "TMF work not found, cqe->tid=0x%x, cid=0x%x\n",
+					  proto_itt, qedi_conn->iscsi_conn_id);
+				WARN_ON(1);
+			}
+			found = 1;
+			mtask = qedi_cmd->task;
+			tmf_hdr = (struct iscsi_tm *)mtask->hdr;
+			rtid = work->rtid;
+
+			list_del_init(&work->list);
+			kfree(work);
+			qedi_cmd->list_tmf_work = NULL;
+		}
+	}
+	spin_unlock_bh(&qedi_conn->tmf_work_lock);
+
+	if (found) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+			  "TMF work, cqe->tid=0x%x, tmf flags=0x%x, cid=0x%x\n",
+			  proto_itt, tmf_hdr->flags, qedi_conn->iscsi_conn_id);
+
+		if ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+		    ISCSI_TM_FUNC_ABORT_TASK) {
+			spin_lock_bh(&conn->session->back_lock);
+
+			protoitt = build_itt(get_itt(tmf_hdr->rtt),
+					     conn->session->age);
+			task = iscsi_itt_to_task(conn, protoitt);
+
+			spin_unlock_bh(&conn->session->back_lock);
+
+			if (!task) {
+				QEDI_NOTICE(&qedi->dbg_ctx,
+					    "IO task completed, tmf rtt=0x%x, cid=0x%x\n",
+					    get_itt(tmf_hdr->rtt),
+					    qedi_conn->iscsi_conn_id);
+				return;
+			}
+
+			dbg_cmd = task->dd_data;
+
+			QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+				  "Abort tmf rtt=0x%x, i/o itt=0x%x, i/o tid=0x%x, cid=0x%x\n",
+				  get_itt(tmf_hdr->rtt), get_itt(task->itt),
+				  dbg_cmd->task_id, qedi_conn->iscsi_conn_id);
+
+			if (qedi_cmd->state == CLEANUP_WAIT_FAILED)
+				qedi_cmd->state = CLEANUP_RECV;
+
+			qedi_clear_task_idx(qedi_conn->qedi, rtid);
+
+			spin_lock(&qedi_conn->list_lock);
+			list_del_init(&dbg_cmd->io_cmd);
+			qedi_conn->active_cmd_count--;
+			spin_unlock(&qedi_conn->list_lock);
+			qedi_cmd->state = CLEANUP_RECV;
+			wake_up_interruptible(&qedi_conn->wait_queue);
+		}
+	} else if (qedi_conn->cmd_cleanup_req > 0) {
+		spin_lock_bh(&conn->session->back_lock);
+		qedi_get_proto_itt(qedi, cqe->itid, &ptmp_itt);
+		protoitt = build_itt(ptmp_itt, conn->session->age);
+		task = iscsi_itt_to_task(conn, protoitt);
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+			  "cleanup io itid=0x%x, protoitt=0x%x, cmd_cleanup_cmpl=%d, cid=0x%x\n",
+			  cqe->itid, protoitt, qedi_conn->cmd_cleanup_cmpl,
+			  qedi_conn->iscsi_conn_id);
+
+		spin_unlock_bh(&conn->session->back_lock);
+		if (!task) {
+			QEDI_NOTICE(&qedi->dbg_ctx,
+				    "task is null, itid=0x%x, cid=0x%x\n",
+				    cqe->itid, qedi_conn->iscsi_conn_id);
+			return;
+		}
+		qedi_conn->cmd_cleanup_cmpl++;
+		wake_up(&qedi_conn->wait_queue);
+		cmd_new = task->dd_data;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+			  "Freeing tid=0x%x for cid=0x%x\n",
+			  cqe->itid, qedi_conn->iscsi_conn_id);
+		qedi_clear_task_idx(qedi_conn->qedi, cqe->itid);
+
+	} else {
+		qedi_get_proto_itt(qedi, cqe->itid, &ptmp_itt);
+		protoitt = build_itt(ptmp_itt, conn->session->age);
+		task = iscsi_itt_to_task(conn, protoitt);
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Delayed or untracked cleanup response, itt=0x%x, tid=0x%x, cid=0x%x, task=%p\n",
+			 protoitt, cqe->itid, qedi_conn->iscsi_conn_id, task);
+		WARN_ON(1);
+	}
+}
+
+void qedi_fp_process_cqes(struct qedi_work *work)
+{
+	struct qedi_ctx *qedi = work->qedi;
+	union iscsi_cqe *cqe = &work->cqe;
+	struct iscsi_task *task = NULL;
+	struct iscsi_nopout *nopout_hdr;
+	struct qedi_conn *q_conn;
+	struct iscsi_conn *conn;
+	struct qedi_cmd *qedi_cmd;
+	u32 comp_type;
+	u32 iscsi_cid;
+	u32 hdr_opcode;
+	u16 que_idx = work->que_idx;
+	u8 cqe_err_bits = 0;
+
+	comp_type = cqe->cqe_common.cqe_type;
+	hdr_opcode = cqe->cqe_common.iscsi_hdr.common.hdr_first_byte;
+	cqe_err_bits =
+		cqe->cqe_common.error_bitmap.error_bits.cqe_error_status_bits;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "fw_cid=0x%x, cqe type=0x%x, opcode=0x%x\n",
+		  cqe->cqe_common.conn_id, comp_type, hdr_opcode);
+
+	if (comp_type >= MAX_ISCSI_CQES_TYPE) {
+		QEDI_WARN(&qedi->dbg_ctx, "Invalid CqE type\n");
+		return;
+	}
+
+	iscsi_cid  = cqe->cqe_common.conn_id;
+	q_conn = qedi->cid_que.conn_cid_tbl[iscsi_cid];
+	if (!q_conn) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Session no longer exists for cid=0x%x!!\n",
+			  iscsi_cid);
+		return;
+	}
+
+	conn = q_conn->cls_conn->dd_data;
+
+	if (unlikely(cqe_err_bits &&
+		     GET_FIELD(cqe_err_bits,
+			       CQE_ERROR_BITMAP_DATA_DIGEST_ERR))) {
+		iscsi_conn_failure(conn, ISCSI_ERR_DATA_DGST);
+		return;
+	}
+
+	switch (comp_type) {
+	case ISCSI_CQE_TYPE_SOLICITED:
+	case ISCSI_CQE_TYPE_SOLICITED_WITH_SENSE:
+		qedi_cmd = container_of(work, struct qedi_cmd, cqe_work);
+		task = qedi_cmd->task;
+		if (!task) {
+			QEDI_WARN(&qedi->dbg_ctx, "task is NULL\n");
+			return;
+		}
+
+		/* Process NOPIN local completion */
+		nopout_hdr = (struct iscsi_nopout *)task->hdr;
+		if ((nopout_hdr->itt == RESERVED_ITT) &&
+		    (cqe->cqe_solicited.itid != (u16)RESERVED_ITT)) {
+			qedi_process_nopin_local_cmpl(qedi, &cqe->cqe_solicited,
+						      task, q_conn);
+		} else {
+			cqe->cqe_solicited.itid =
+					       qedi_get_itt(cqe->cqe_solicited);
+			/* Process other solicited responses */
+			qedi_mtask_completion(qedi, cqe, task, q_conn, que_idx);
+		}
+		break;
+	case ISCSI_CQE_TYPE_UNSOLICITED:
+		switch (hdr_opcode) {
+		case ISCSI_OPCODE_NOP_IN:
+			qedi_process_nopin_mesg(qedi, cqe, task, q_conn,
+						que_idx);
+			break;
+		case ISCSI_OPCODE_ASYNC_MSG:
+			qedi_process_async_mesg(qedi, cqe, task, q_conn,
+						que_idx);
+			break;
+		case ISCSI_OPCODE_REJECT:
+			qedi_process_reject_mesg(qedi, cqe, task, q_conn,
+						 que_idx);
+			break;
+		}
+		goto exit_fp_process;
+	case ISCSI_CQE_TYPE_DUMMY:
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM, "Dummy CqE\n");
+		goto exit_fp_process;
+	case ISCSI_CQE_TYPE_TASK_CLEANUP:
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM, "CleanUp CqE\n");
+		qedi_process_cmd_cleanup_resp(qedi, &cqe->cqe_solicited, task,
+					      conn);
+		goto exit_fp_process;
+	default:
+		QEDI_ERR(&qedi->dbg_ctx, "Error cqe.\n");
+		break;
+	}
+
+exit_fp_process:
+	return;
+}
+
+static void qedi_add_to_sq(struct qedi_conn *qedi_conn, struct iscsi_task *task,
+			   u16 tid, uint16_t ptu_invalidate, int is_cleanup)
+{
+	struct iscsi_wqe *wqe;
+	struct iscsi_wqe_field *cont_field;
+	struct qedi_endpoint *ep;
+	struct scsi_cmnd *sc = task->sc;
+	struct iscsi_login_req *login_hdr;
+	struct qedi_cmd *cmd = task->dd_data;
+
+	login_hdr = (struct iscsi_login_req *)task->hdr;
+	ep = qedi_conn->ep;
+	wqe = &ep->sq[ep->sq_prod_idx];
+
+	memset(wqe, 0, sizeof(*wqe));
+
+	ep->sq_prod_idx++;
+	ep->fw_sq_prod_idx++;
+	if (ep->sq_prod_idx == QEDI_SQ_SIZE)
+		ep->sq_prod_idx = 0;
+
+	if (is_cleanup) {
+		SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
+			  ISCSI_WQE_TYPE_TASK_CLEANUP);
+		wqe->task_id = tid;
+		return;
+	}
+
+	if (ptu_invalidate) {
+		SET_FIELD(wqe->flags, ISCSI_WQE_PTU_INVALIDATE,
+			  ISCSI_WQE_SET_PTU_INVALIDATE);
+	}
+
+	cont_field = &wqe->cont_prevtid_union.cont_field;
+
+	switch (task->hdr->opcode & ISCSI_OPCODE_MASK) {
+	case ISCSI_OP_LOGIN:
+	case ISCSI_OP_TEXT:
+		SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
+			  ISCSI_WQE_TYPE_MIDDLE_PATH);
+		SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES,
+			  1);
+		cont_field->contlen_cdbsize_field = ntoh24(login_hdr->dlength);
+		break;
+	case ISCSI_OP_LOGOUT:
+	case ISCSI_OP_NOOP_OUT:
+	case ISCSI_OP_SCSI_TMFUNC:
+		 SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
+			   ISCSI_WQE_TYPE_NORMAL);
+		break;
+	default:
+		if (!sc)
+			break;
+
+		SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
+			  ISCSI_WQE_TYPE_NORMAL);
+		cont_field->contlen_cdbsize_field =
+				(sc->sc_data_direction == DMA_TO_DEVICE) ?
+				scsi_bufflen(sc) : 0;
+		if (cmd->use_slowpath)
+			SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES, 0);
+		else
+			SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES,
+				  (sc->sc_data_direction ==
+				   DMA_TO_DEVICE) ?
+				  min((u16)QEDI_FAST_SGE_COUNT,
+				      (u16)cmd->io_tbl.sge_valid) : 0);
+		break;
+	}
+
+	wqe->task_id = tid;
+	/* Make sure SQ data is coherent */
+	wmb();
+}
+
+static void qedi_ring_doorbell(struct qedi_conn *qedi_conn)
+{
+	struct iscsi_db_data dbell = { 0 };
+
+	dbell.agg_flags = 0;
+
+	dbell.params |= DB_DEST_XCM << ISCSI_DB_DATA_DEST_SHIFT;
+	dbell.params |= DB_AGG_CMD_SET << ISCSI_DB_DATA_AGG_CMD_SHIFT;
+	dbell.params |=
+		   DQ_XCM_ISCSI_SQ_PROD_CMD << ISCSI_DB_DATA_AGG_VAL_SEL_SHIFT;
+
+	dbell.sq_prod = qedi_conn->ep->fw_sq_prod_idx;
+	writel(*(u32 *)&dbell, qedi_conn->ep->p_doorbell);
+
+	/* Make sure fw write idx is coherent, and include both memory barriers
+	 * as a failsafe as for some architectures the call is the same but on
+	 * others they are two different assembly operations.
+	 */
+	wmb();
+	mmiowb();
+	QEDI_INFO(&qedi_conn->qedi->dbg_ctx, QEDI_LOG_MP_REQ,
+		  "prod_idx=0x%x, fw_prod_idx=0x%x, cid=0x%x\n",
+		  qedi_conn->ep->sq_prod_idx, qedi_conn->ep->fw_sq_prod_idx,
+		  qedi_conn->iscsi_conn_id);
+}
+
+int qedi_send_iscsi_login(struct qedi_conn *qedi_conn,
+			  struct iscsi_task *task)
+{
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_task_context *fw_task_ctx;
+	struct iscsi_login_req *login_hdr;
+	struct iscsi_login_req_hdr *fw_login_req = NULL;
+	struct iscsi_cached_sge_ctx *cached_sge = NULL;
+	struct iscsi_sge *single_sge = NULL;
+	struct iscsi_sge *req_sge = NULL;
+	struct iscsi_sge *resp_sge = NULL;
+	struct qedi_cmd *qedi_cmd;
+	s16 ptu_invalidate = 0;
+	s16 tid = 0;
+
+	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	qedi_cmd = (struct qedi_cmd *)task->dd_data;
+	login_hdr = (struct iscsi_login_req *)task->hdr;
+
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1)
+		return -ENOMEM;
+
+	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+
+	qedi_cmd->task_id = tid;
+
+	/* Ystorm context */
+	fw_login_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.login_req;
+	fw_login_req->opcode = login_hdr->opcode;
+	fw_login_req->version_min = login_hdr->min_version;
+	fw_login_req->version_max = login_hdr->max_version;
+	fw_login_req->flags_attr = login_hdr->flags;
+	fw_login_req->isid_tabc = *((u16 *)login_hdr->isid + 2);
+	fw_login_req->isid_d = *((u32 *)login_hdr->isid);
+	fw_login_req->tsih = login_hdr->tsih;
+	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
+	fw_login_req->itt = qedi_set_itt(tid, get_itt(task->itt));
+	fw_login_req->cid = qedi_conn->iscsi_conn_id;
+	fw_login_req->cmd_sn = be32_to_cpu(login_hdr->cmdsn);
+	fw_login_req->exp_stat_sn = be32_to_cpu(login_hdr->exp_statsn);
+	fw_login_req->exp_stat_sn = 0;
+
+	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
+		ptu_invalidate = 1;
+		qedi->tid_reuse_count[tid] = 0;
+	}
+
+	fw_task_ctx->ystorm_st_context.state.reuse_count =
+						qedi->tid_reuse_count[tid];
+	fw_task_ctx->mstorm_st_context.reuse_count =
+						qedi->tid_reuse_count[tid]++;
+	cached_sge =
+	       &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
+	cached_sge->sge.sge_len = req_sge->sge_len;
+	cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
+	cached_sge->sge.sge_addr.hi =
+			     (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+
+	/* Mstorm context */
+	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
+	fw_task_ctx->mstorm_st_context.task_type = 0x2;
+	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
+	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
+	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
+	single_sge->sge_len = resp_sge->sge_len;
+
+	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+		  ISCSI_MFLAGS_SINGLE_SGE, 1);
+	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+		  ISCSI_MFLAGS_SLOW_IO, 0);
+	fw_task_ctx->mstorm_st_context.sgl_size = 1;
+	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
+
+	/* Ustorm context */
+	fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
+	fw_task_ctx->ustorm_st_context.exp_data_transfer_len =
+						ntoh24(login_hdr->dlength);
+	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
+	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
+	fw_task_ctx->ustorm_st_context.task_type = 0x2;
+	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
+	fw_task_ctx->ustorm_ag_context.exp_data_acked =
+						 ntoh24(login_hdr->dlength);
+	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
+		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
+
+	spin_lock(&qedi_conn->list_lock);
+	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
+	qedi_cmd->io_cmd_in_list = true;
+	qedi_conn->active_cmd_count++;
+	spin_unlock(&qedi_conn->list_lock);
+
+	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
+	qedi_ring_doorbell(qedi_conn);
+	return 0;
+}
+
+int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn,
+			   struct iscsi_task *task)
+{
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_logout_req_hdr *fw_logout_req = NULL;
+	struct iscsi_task_context *fw_task_ctx = NULL;
+	struct iscsi_logout *logout_hdr = NULL;
+	struct qedi_cmd *qedi_cmd = NULL;
+	s16  tid = 0;
+	s16 ptu_invalidate = 0;
+
+	qedi_cmd = (struct qedi_cmd *)task->dd_data;
+	logout_hdr = (struct iscsi_logout *)task->hdr;
+
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1)
+		return -ENOMEM;
+
+	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+
+	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+	qedi_cmd->task_id = tid;
+
+	/* Ystorm context */
+	fw_logout_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.logout_req;
+	fw_logout_req->opcode = ISCSI_OPCODE_LOGOUT_REQUEST;
+	fw_logout_req->reason_code = 0x80 | logout_hdr->flags;
+	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
+	fw_logout_req->itt = qedi_set_itt(tid, get_itt(task->itt));
+	fw_logout_req->exp_stat_sn = be32_to_cpu(logout_hdr->exp_statsn);
+	fw_logout_req->cmd_sn = be32_to_cpu(logout_hdr->cmdsn);
+
+	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
+		ptu_invalidate = 1;
+		qedi->tid_reuse_count[tid] = 0;
+	}
+	fw_task_ctx->ystorm_st_context.state.reuse_count =
+						  qedi->tid_reuse_count[tid];
+	fw_task_ctx->mstorm_st_context.reuse_count =
+						qedi->tid_reuse_count[tid]++;
+	fw_logout_req->cid = qedi_conn->iscsi_conn_id;
+	fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
+
+	/* Mstorm context */
+	fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
+	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
+
+	/* Ustorm context */
+	fw_task_ctx->ustorm_st_context.rem_rcv_len = 0;
+	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0;
+	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
+	fw_task_ctx->ustorm_st_context.task_type =  ISCSI_TASK_TYPE_MIDPATH;
+	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
+
+	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
+		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
+	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+		  ISCSI_REG1_NUM_FAST_SGES, 0);
+
+	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
+	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+
+	spin_lock(&qedi_conn->list_lock);
+	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
+	qedi_cmd->io_cmd_in_list = true;
+	qedi_conn->active_cmd_count++;
+	spin_unlock(&qedi_conn->list_lock);
+
+	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
+	qedi_ring_doorbell(qedi_conn);
+
+	return 0;
+}
+
+int qedi_cleanup_all_io(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn,
+			struct iscsi_task *task, bool in_recovery)
+{
+	int rval;
+	struct iscsi_task *ctask;
+	struct qedi_cmd *cmd, *cmd_tmp;
+	struct iscsi_tm *tmf_hdr;
+	unsigned int lun = 0;
+	bool lun_reset = false;
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+
+	/* From recovery, task is NULL or from tmf resp valid task */
+	if (task) {
+		tmf_hdr = (struct iscsi_tm *)task->hdr;
+
+		if ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+			ISCSI_TM_FUNC_LOGICAL_UNIT_RESET) {
+			lun_reset = true;
+			lun = scsilun_to_int(&tmf_hdr->lun);
+		}
+	}
+
+	qedi_conn->cmd_cleanup_req = 0;
+	qedi_conn->cmd_cleanup_cmpl = 0;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+		  "active_cmd_count=%d, cid=0x%x, in_recovery=%d, lun_reset=%d\n",
+		  qedi_conn->active_cmd_count, qedi_conn->iscsi_conn_id,
+		  in_recovery, lun_reset);
+
+	if (lun_reset)
+		spin_lock_bh(&session->back_lock);
+
+	spin_lock(&qedi_conn->list_lock);
+
+	list_for_each_entry_safe(cmd, cmd_tmp, &qedi_conn->active_cmd_list,
+				 io_cmd) {
+		ctask = cmd->task;
+		if (ctask == task)
+			continue;
+
+		if (lun_reset) {
+			if (cmd->scsi_cmd && cmd->scsi_cmd->device) {
+				QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+					  "tid=0x%x itt=0x%x scsi_cmd_ptr=%p device=%p task_state=%d cmd_state=0%x cid=0x%x\n",
+					  cmd->task_id, get_itt(ctask->itt),
+					  cmd->scsi_cmd, cmd->scsi_cmd->device,
+					  ctask->state, cmd->state,
+					  qedi_conn->iscsi_conn_id);
+				if (cmd->scsi_cmd->device->lun != lun)
+					continue;
+			}
+		}
+		qedi_conn->cmd_cleanup_req++;
+		qedi_iscsi_cleanup_task(ctask, true);
+
+		list_del_init(&cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Deleted active cmd list node io_cmd=%p, cid=0x%x\n",
+			  &cmd->io_cmd, qedi_conn->iscsi_conn_id);
+	}
+
+	spin_unlock(&qedi_conn->list_lock);
+
+	if (lun_reset)
+		spin_unlock_bh(&session->back_lock);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+		  "cmd_cleanup_req=%d, cid=0x%x\n",
+		  qedi_conn->cmd_cleanup_req,
+		  qedi_conn->iscsi_conn_id);
+
+	rval  = wait_event_interruptible_timeout(qedi_conn->wait_queue,
+						 ((qedi_conn->cmd_cleanup_req ==
+						 qedi_conn->cmd_cleanup_cmpl) ||
+						 qedi_conn->ep),
+						 5 * HZ);
+	if (rval) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+			  "i/o cmd_cleanup_req=%d, equal to cmd_cleanup_cmpl=%d, cid=0x%x\n",
+			  qedi_conn->cmd_cleanup_req,
+			  qedi_conn->cmd_cleanup_cmpl,
+			  qedi_conn->iscsi_conn_id);
+
+		return 0;
+	}
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+		  "i/o cmd_cleanup_req=%d, not equal to cmd_cleanup_cmpl=%d, cid=0x%x\n",
+		  qedi_conn->cmd_cleanup_req,
+		  qedi_conn->cmd_cleanup_cmpl,
+		  qedi_conn->iscsi_conn_id);
+
+	iscsi_host_for_each_session(qedi->shost,
+				    qedi_mark_device_missing);
+	qedi_ops->common->drain(qedi->cdev);
+
+	/* Enable IOs for all other sessions except current.*/
+	if (!wait_event_interruptible_timeout(qedi_conn->wait_queue,
+					      (qedi_conn->cmd_cleanup_req ==
+					       qedi_conn->cmd_cleanup_cmpl),
+					      5 * HZ)) {
+		iscsi_host_for_each_session(qedi->shost,
+					    qedi_mark_device_available);
+		return -1;
+	}
+
+	iscsi_host_for_each_session(qedi->shost,
+				    qedi_mark_device_available);
+
+	return 0;
+}
+
+void qedi_clearsq(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn,
+		  struct iscsi_task *task)
+{
+	struct qedi_endpoint *qedi_ep;
+	int rval;
+
+	qedi_ep = qedi_conn->ep;
+	qedi_conn->cmd_cleanup_req = 0;
+	qedi_conn->cmd_cleanup_cmpl = 0;
+
+	if (!qedi_ep) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Cannot proceed, ep already disconnected, cid=0x%x\n",
+			  qedi_conn->iscsi_conn_id);
+		return;
+	}
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+		  "Clearing SQ for cid=0x%x, conn=%p, ep=%p\n",
+		  qedi_conn->iscsi_conn_id, qedi_conn, qedi_ep);
+
+	qedi_ops->clear_sq(qedi->cdev, qedi_ep->handle);
+
+	rval = qedi_cleanup_all_io(qedi, qedi_conn, task, true);
+	if (rval) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "fatal error, need hard reset, cid=0x%x\n",
+			 qedi_conn->iscsi_conn_id);
+		WARN_ON(1);
+	}
+}
+
+static int qedi_wait_for_cleanup_request(struct qedi_ctx *qedi,
+					 struct qedi_conn *qedi_conn,
+					 struct iscsi_task *task,
+					 struct qedi_cmd *qedi_cmd,
+					 struct qedi_work_map *list_work)
+{
+	struct qedi_cmd *cmd = (struct qedi_cmd *)task->dd_data;
+	int wait;
+
+	wait  = wait_event_interruptible_timeout(qedi_conn->wait_queue,
+						 ((qedi_cmd->state ==
+						   CLEANUP_RECV) ||
+						 ((qedi_cmd->type == TYPEIO) &&
+						  (cmd->state ==
+						   RESPONSE_RECEIVED))),
+						 5 * HZ);
+	if (!wait) {
+		qedi_cmd->state = CLEANUP_WAIT_FAILED;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+			  "Cleanup timedout tid=0x%x, issue connection recovery, cid=0x%x\n",
+			  cmd->task_id, qedi_conn->iscsi_conn_id);
+
+		return -1;
+	}
+	return 0;
+}
+
+static void qedi_tmf_work(struct work_struct *work)
+{
+	struct qedi_cmd *qedi_cmd =
+		container_of(work, struct qedi_cmd, tmf_work);
+	struct qedi_conn *qedi_conn = qedi_cmd->conn;
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_cls_session *cls_sess;
+	struct qedi_work_map *list_work = NULL;
+	struct iscsi_task *mtask;
+	struct qedi_cmd *cmd;
+	struct iscsi_task *ctask;
+	struct iscsi_tm *tmf_hdr;
+	s16 rval = 0;
+	s16 tid = 0;
+
+	mtask = qedi_cmd->task;
+	tmf_hdr = (struct iscsi_tm *)mtask->hdr;
+	cls_sess = iscsi_conn_to_session(qedi_conn->cls_conn);
+	set_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+
+	ctask = iscsi_itt_to_task(conn, tmf_hdr->rtt);
+	if (!ctask || !ctask->sc) {
+		QEDI_ERR(&qedi->dbg_ctx, "Task already completed\n");
+		goto abort_ret;
+	}
+
+	cmd = (struct qedi_cmd *)ctask->dd_data;
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+		  "Abort tmf rtt=0x%x, cmd itt=0x%x, cmd tid=0x%x, cid=0x%x\n",
+		  get_itt(tmf_hdr->rtt), get_itt(ctask->itt), cmd->task_id,
+		  qedi_conn->iscsi_conn_id);
+
+	if (do_not_recover) {
+		QEDI_ERR(&qedi->dbg_ctx, "DONT SEND CLEANUP/ABORT %d\n",
+			 do_not_recover);
+		goto abort_ret;
+	}
+
+	list_work = kzalloc(sizeof(*list_work), GFP_ATOMIC);
+	if (!list_work) {
+		QEDI_ERR(&qedi->dbg_ctx, "Memory alloction failed\n");
+		goto abort_ret;
+	}
+
+	qedi_cmd->type = TYPEIO;
+	list_work->qedi_cmd = qedi_cmd;
+	list_work->rtid = cmd->task_id;
+	list_work->state = QEDI_WORK_SCHEDULED;
+	qedi_cmd->list_tmf_work = list_work;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+		  "Queue tmf work=%p, list node=%p, cid=0x%x, tmf flags=0x%x\n",
+		  list_work->ptr_tmf_work, list_work, qedi_conn->iscsi_conn_id,
+		  tmf_hdr->flags);
+
+	spin_lock_bh(&qedi_conn->tmf_work_lock);
+	list_add_tail(&list_work->list, &qedi_conn->tmf_work_list);
+	spin_unlock_bh(&qedi_conn->tmf_work_lock);
+
+	qedi_iscsi_cleanup_task(ctask, false);
+
+	rval = qedi_wait_for_cleanup_request(qedi, qedi_conn, ctask, qedi_cmd,
+					     list_work);
+	if (rval == -1) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "FW cleanup got escalated, cid=0x%x\n",
+			  qedi_conn->iscsi_conn_id);
+		goto ldel_exit;
+	}
+
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1) {
+		QEDI_ERR(&qedi->dbg_ctx, "Invalid tid, cid=0x%x\n",
+			 qedi_conn->iscsi_conn_id);
+		goto ldel_exit;
+	}
+
+	qedi_cmd->task_id = tid;
+	qedi_send_iscsi_tmf(qedi_conn, qedi_cmd->task);
+
+abort_ret:
+	clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+	return;
+
+ldel_exit:
+	spin_lock_bh(&qedi_conn->tmf_work_lock);
+	if (!qedi_cmd->list_tmf_work) {
+		list_del_init(&list_work->list);
+		qedi_cmd->list_tmf_work = NULL;
+		kfree(list_work);
+	}
+	spin_unlock_bh(&qedi_conn->tmf_work_lock);
+
+	spin_lock(&qedi_conn->list_lock);
+	list_del_init(&cmd->io_cmd);
+	qedi_conn->active_cmd_count--;
+	spin_unlock(&qedi_conn->list_lock);
+
+	clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+}
+
+static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
+			       struct iscsi_task *mtask)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_task_context *fw_task_ctx;
+	struct iscsi_tmf_request_hdr *fw_tmf_request;
+	struct iscsi_sge *single_sge;
+	struct qedi_cmd *qedi_cmd;
+	struct qedi_cmd *cmd;
+	struct iscsi_task *ctask;
+	struct iscsi_tm *tmf_hdr;
+	struct iscsi_sge *req_sge;
+	struct iscsi_sge *resp_sge;
+	u32 lun[2];
+	s16 tid = 0, ptu_invalidate = 0;
+
+	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	qedi_cmd = (struct qedi_cmd *)mtask->dd_data;
+	tmf_hdr = (struct iscsi_tm *)mtask->hdr;
+
+	tid = qedi_cmd->task_id;
+	qedi_update_itt_map(qedi, tid, mtask->itt, qedi_cmd);
+
+	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+
+	fw_tmf_request = &fw_task_ctx->ystorm_st_context.pdu_hdr.tmf_request;
+	fw_tmf_request->itt = qedi_set_itt(tid, get_itt(mtask->itt));
+	fw_tmf_request->cmd_sn = be32_to_cpu(tmf_hdr->cmdsn);
+
+	memcpy(lun, &tmf_hdr->lun, sizeof(struct scsi_lun));
+	fw_tmf_request->lun.lo = be32_to_cpu(lun[0]);
+	fw_tmf_request->lun.hi = be32_to_cpu(lun[1]);
+
+	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
+		ptu_invalidate = 1;
+		qedi->tid_reuse_count[tid] = 0;
+	}
+	fw_task_ctx->ystorm_st_context.state.reuse_count =
+						qedi->tid_reuse_count[tid];
+	fw_task_ctx->mstorm_st_context.reuse_count =
+						qedi->tid_reuse_count[tid]++;
+
+	if ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+	     ISCSI_TM_FUNC_ABORT_TASK) {
+		ctask = iscsi_itt_to_task(conn, tmf_hdr->rtt);
+		if (!ctask || !ctask->sc) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Could not get reference task\n");
+			return 0;
+		}
+		cmd = (struct qedi_cmd *)ctask->dd_data;
+		fw_tmf_request->rtt =
+				qedi_set_itt(cmd->task_id,
+					     get_itt(tmf_hdr->rtt));
+	} else {
+		fw_tmf_request->rtt = ISCSI_RESERVED_TAG;
+	}
+
+	fw_tmf_request->opcode = tmf_hdr->opcode;
+	fw_tmf_request->function = tmf_hdr->flags;
+	fw_tmf_request->hdr_second_dword = ntoh24(tmf_hdr->dlength);
+	fw_tmf_request->ref_cmd_sn = be32_to_cpu(tmf_hdr->refcmdsn);
+
+	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
+	fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
+	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
+	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
+	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
+	single_sge->sge_len = resp_sge->sge_len;
+
+	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+		  ISCSI_MFLAGS_SINGLE_SGE, 1);
+	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+		  ISCSI_MFLAGS_SLOW_IO, 0);
+	fw_task_ctx->mstorm_st_context.sgl_size = 1;
+	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
+
+	/* Ustorm context */
+	fw_task_ctx->ustorm_st_context.rem_rcv_len = 0;
+	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0;
+	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
+	fw_task_ctx->ustorm_st_context.task_type =  ISCSI_TASK_TYPE_MIDPATH;
+	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
+
+	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
+		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
+	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+		  ISCSI_REG1_NUM_FAST_SGES, 0);
+
+	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
+	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+	fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
+	fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+		  "Add TMF to SQ, tmf tid=0x%x, itt=0x%x, cid=0x%x\n",
+		  tid,  mtask->itt, qedi_conn->iscsi_conn_id);
+
+	spin_lock(&qedi_conn->list_lock);
+	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
+	qedi_cmd->io_cmd_in_list = true;
+	qedi_conn->active_cmd_count++;
+	spin_unlock(&qedi_conn->list_lock);
+
+	qedi_add_to_sq(qedi_conn, mtask, tid, ptu_invalidate, false);
+	qedi_ring_doorbell(qedi_conn);
+	return 0;
+}
+
+int qedi_iscsi_abort_work(struct qedi_conn *qedi_conn,
+			  struct iscsi_task *mtask)
+{
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_tm *tmf_hdr;
+	struct qedi_cmd *qedi_cmd = (struct qedi_cmd *)mtask->dd_data;
+	s16 tid = 0;
+
+	tmf_hdr = (struct iscsi_tm *)mtask->hdr;
+	qedi_cmd->task = mtask;
+
+	/* If abort task then schedule the work and return */
+	if ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+	    ISCSI_TM_FUNC_ABORT_TASK) {
+		qedi_cmd->state = CLEANUP_WAIT;
+		INIT_WORK(&qedi_cmd->tmf_work, qedi_tmf_work);
+		queue_work(qedi->tmf_thread, &qedi_cmd->tmf_work);
+
+	} else if (((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+		    ISCSI_TM_FUNC_LOGICAL_UNIT_RESET) ||
+		   ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+		    ISCSI_TM_FUNC_TARGET_WARM_RESET) ||
+		   ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+		    ISCSI_TM_FUNC_TARGET_COLD_RESET)) {
+		tid = qedi_get_task_idx(qedi);
+		if (tid == -1) {
+			QEDI_ERR(&qedi->dbg_ctx, "Invalid tid, cid=0x%x\n",
+				 qedi_conn->iscsi_conn_id);
+			return -1;
+		}
+		qedi_cmd->task_id = tid;
+
+		qedi_send_iscsi_tmf(qedi_conn, qedi_cmd->task);
+
+	} else {
+		QEDI_ERR(&qedi->dbg_ctx, "Invalid tmf, cid=0x%x\n",
+			 qedi_conn->iscsi_conn_id);
+		return -1;
+	}
+
+	return 0;
+}
+
+int qedi_send_iscsi_text(struct qedi_conn *qedi_conn,
+			 struct iscsi_task *task)
+{
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_task_context *fw_task_ctx;
+	struct iscsi_text_request_hdr *fw_text_request;
+	struct iscsi_cached_sge_ctx *cached_sge;
+	struct iscsi_sge *single_sge;
+	struct qedi_cmd *qedi_cmd;
+	/* For 6.5 hdr iscsi_hdr */
+	struct iscsi_text *text_hdr;
+	struct iscsi_sge *req_sge;
+	struct iscsi_sge *resp_sge;
+	s16 ptu_invalidate = 0;
+	s16 tid = 0;
+
+	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	qedi_cmd = (struct qedi_cmd *)task->dd_data;
+	text_hdr = (struct iscsi_text *)task->hdr;
+
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1)
+		return -ENOMEM;
+
+	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+
+	qedi_cmd->task_id = tid;
+
+	/* Ystorm context */
+	fw_text_request =
+			&fw_task_ctx->ystorm_st_context.pdu_hdr.text_request;
+	fw_text_request->opcode = text_hdr->opcode;
+	fw_text_request->flags_attr = text_hdr->flags;
+
+	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
+	fw_text_request->itt = qedi_set_itt(tid, get_itt(task->itt));
+	fw_text_request->ttt = text_hdr->ttt;
+	fw_text_request->cmd_sn = be32_to_cpu(text_hdr->cmdsn);
+	fw_text_request->exp_stat_sn = be32_to_cpu(text_hdr->exp_statsn);
+	fw_text_request->hdr_second_dword = ntoh24(text_hdr->dlength);
+
+	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
+		ptu_invalidate = 1;
+		qedi->tid_reuse_count[tid] = 0;
+	}
+	fw_task_ctx->ystorm_st_context.state.reuse_count =
+						     qedi->tid_reuse_count[tid];
+	fw_task_ctx->mstorm_st_context.reuse_count =
+						   qedi->tid_reuse_count[tid]++;
+
+	cached_sge =
+	       &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
+	cached_sge->sge.sge_len = req_sge->sge_len;
+	cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
+	cached_sge->sge.sge_addr.hi =
+			      (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+
+	/* Mstorm context */
+	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
+	fw_task_ctx->mstorm_st_context.task_type = 0x2;
+	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
+	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
+	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
+	single_sge->sge_len = resp_sge->sge_len;
+
+	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+		  ISCSI_MFLAGS_SINGLE_SGE, 1);
+	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+		  ISCSI_MFLAGS_SLOW_IO, 0);
+	fw_task_ctx->mstorm_st_context.sgl_size = 1;
+	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
+
+	/* Ustorm context */
+	fw_task_ctx->ustorm_ag_context.exp_data_acked =
+						      ntoh24(text_hdr->dlength);
+	fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
+	fw_task_ctx->ustorm_st_context.exp_data_transfer_len =
+						      ntoh24(text_hdr->dlength);
+	fw_task_ctx->ustorm_st_context.exp_data_sn =
+					      be32_to_cpu(text_hdr->exp_statsn);
+	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
+	fw_task_ctx->ustorm_st_context.task_type = 0x2;
+	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
+	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+
+	/*  Add command in active command list */
+	spin_lock(&qedi_conn->list_lock);
+	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
+	qedi_cmd->io_cmd_in_list = true;
+	qedi_conn->active_cmd_count++;
+	spin_unlock(&qedi_conn->list_lock);
+
+	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
+	qedi_ring_doorbell(qedi_conn);
+
+	return 0;
+}
+
+int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn,
+			   struct iscsi_task *task,
+			   char *datap, int data_len, int unsol)
+{
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_task_context *fw_task_ctx;
+	struct iscsi_nop_out_hdr *fw_nop_out;
+	struct qedi_cmd *qedi_cmd;
+	/* For 6.5 hdr iscsi_hdr */
+	struct iscsi_nopout *nopout_hdr;
+	struct iscsi_cached_sge_ctx *cached_sge;
+	struct iscsi_sge *single_sge;
+	struct iscsi_sge *req_sge;
+	struct iscsi_sge *resp_sge;
+	u32 lun[2];
+	s16 ptu_invalidate = 0;
+	s16 tid = 0;
+
+	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	qedi_cmd = (struct qedi_cmd *)task->dd_data;
+	nopout_hdr = (struct iscsi_nopout *)task->hdr;
+
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1) {
+		QEDI_WARN(&qedi->dbg_ctx, "Invalid tid\n");
+		return -ENOMEM;
+	}
+
+	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+
+	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+	qedi_cmd->task_id = tid;
+
+	/* Ystorm context */
+	fw_nop_out = &fw_task_ctx->ystorm_st_context.pdu_hdr.nop_out;
+	SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_CONST1, 1);
+	SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_RSRV, 0);
+
+	memcpy(lun, &nopout_hdr->lun, sizeof(struct scsi_lun));
+	fw_nop_out->lun.lo = be32_to_cpu(lun[0]);
+	fw_nop_out->lun.hi = be32_to_cpu(lun[1]);
+
+	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
+
+	if (nopout_hdr->ttt != ISCSI_TTT_ALL_ONES) {
+		fw_nop_out->itt = be32_to_cpu(nopout_hdr->itt);
+		fw_nop_out->ttt = be32_to_cpu(nopout_hdr->ttt);
+		fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
+		fw_task_ctx->ystorm_st_context.state.local_comp = 1;
+		SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
+			  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 1);
+	} else {
+		fw_nop_out->itt = qedi_set_itt(tid, get_itt(task->itt));
+		fw_nop_out->ttt = ISCSI_TTT_ALL_ONES;
+		fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
+
+		spin_lock(&qedi_conn->list_lock);
+		list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
+		qedi_cmd->io_cmd_in_list = true;
+		qedi_conn->active_cmd_count++;
+		spin_unlock(&qedi_conn->list_lock);
+	}
+
+	fw_nop_out->opcode = ISCSI_OPCODE_NOP_OUT;
+	fw_nop_out->cmd_sn = be32_to_cpu(nopout_hdr->cmdsn);
+	fw_nop_out->exp_stat_sn = be32_to_cpu(nopout_hdr->exp_statsn);
+
+	cached_sge =
+	       &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
+	cached_sge->sge.sge_len = req_sge->sge_len;
+	cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
+	cached_sge->sge.sge_addr.hi =
+			(u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+
+	/* Mstorm context */
+	fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
+	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
+
+	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
+	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
+	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
+	single_sge->sge_len = resp_sge->sge_len;
+	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
+
+	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
+		ptu_invalidate = 1;
+		qedi->tid_reuse_count[tid] = 0;
+	}
+	fw_task_ctx->ystorm_st_context.state.reuse_count =
+						qedi->tid_reuse_count[tid];
+	fw_task_ctx->mstorm_st_context.reuse_count =
+						qedi->tid_reuse_count[tid]++;
+	/* Ustorm context */
+	fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
+	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = data_len;
+	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
+	fw_task_ctx->ustorm_st_context.task_type =  ISCSI_TASK_TYPE_MIDPATH;
+	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
+
+	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+		  ISCSI_REG1_NUM_FAST_SGES, 0);
+
+	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
+	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+
+	fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
+	fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
+
+	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
+	qedi_ring_doorbell(qedi_conn);
+	return 0;
+}
+
+static int qedi_split_bd(struct qedi_cmd *cmd, u64 addr, int sg_len,
+			 int bd_index)
+{
+	struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+	int frag_size, sg_frags;
+
+	sg_frags = 0;
+
+	while (sg_len) {
+		if (addr % QEDI_PAGE_SIZE)
+			frag_size =
+				   (QEDI_PAGE_SIZE - (addr % QEDI_PAGE_SIZE));
+		else
+			frag_size = (sg_len > QEDI_BD_SPLIT_SZ) ? 0 :
+				    (sg_len % QEDI_BD_SPLIT_SZ);
+
+		if (frag_size == 0)
+			frag_size = QEDI_BD_SPLIT_SZ;
+
+		bd[bd_index + sg_frags].sge_addr.lo = (addr & 0xffffffff);
+		bd[bd_index + sg_frags].sge_addr.hi = (addr >> 32);
+		bd[bd_index + sg_frags].sge_len = (u16)frag_size;
+		QEDI_INFO(&cmd->conn->qedi->dbg_ctx, QEDI_LOG_IO,
+			  "split sge %d: addr=%llx, len=%x",
+			  (bd_index + sg_frags), addr, frag_size);
+
+		addr += (u64)frag_size;
+		sg_frags++;
+		sg_len -= frag_size;
+	}
+	return sg_frags;
+}
+
+static int qedi_map_scsi_sg(struct qedi_ctx *qedi, struct qedi_cmd *cmd)
+{
+	struct scsi_cmnd *sc = cmd->scsi_cmd;
+	struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+	struct scatterlist *sg;
+	int byte_count = 0;
+	int bd_count = 0;
+	int sg_count;
+	int sg_len;
+	int sg_frags;
+	u64 addr, end_addr;
+	int i;
+
+	WARN_ON(scsi_sg_count(sc) > QEDI_ISCSI_MAX_BDS_PER_CMD);
+
+	sg_count = dma_map_sg(&qedi->pdev->dev, scsi_sglist(sc),
+			      scsi_sg_count(sc), sc->sc_data_direction);
+
+	/*
+	 * New condition to send single SGE as cached-SGL.
+	 * Single SGE with length less than 64K.
+	 */
+	sg = scsi_sglist(sc);
+	if ((sg_count == 1) && (sg_dma_len(sg) <= MAX_SGLEN_FOR_CACHESGL)) {
+		sg_len = sg_dma_len(sg);
+		addr = (u64)sg_dma_address(sg);
+
+		bd[bd_count].sge_addr.lo = (addr & 0xffffffff);
+		bd[bd_count].sge_addr.hi = (addr >> 32);
+		bd[bd_count].sge_len = (u16)sg_len;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO,
+			  "single-cashed-sgl: bd_count:%d addr=%llx, len=%x",
+			  sg_count, addr, sg_len);
+
+		return ++bd_count;
+	}
+
+	scsi_for_each_sg(sc, sg, sg_count, i) {
+		sg_len = sg_dma_len(sg);
+		addr = (u64)sg_dma_address(sg);
+		end_addr = (addr + sg_len);
+
+		/*
+		 * first sg elem in the 'list',
+		 * check if end addr is page-aligned.
+		 */
+		if ((i == 0) && (sg_count > 1) && (end_addr % QEDI_PAGE_SIZE))
+			cmd->use_slowpath = true;
+
+		/*
+		 * last sg elem in the 'list',
+		 * check if start addr is page-aligned.
+		 */
+		else if ((i == (sg_count - 1)) &&
+			 (sg_count > 1) && (addr % QEDI_PAGE_SIZE))
+			cmd->use_slowpath = true;
+
+		/*
+		 * middle sg elements in list,
+		 * check if start and end addr is page-aligned
+		 */
+		else if ((i != 0) && (i != (sg_count - 1)) &&
+			 ((addr % QEDI_PAGE_SIZE) ||
+			 (end_addr % QEDI_PAGE_SIZE)))
+			cmd->use_slowpath = true;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO, "sg[%d] size=0x%x",
+			  i, sg_len);
+
+		if (sg_len > QEDI_BD_SPLIT_SZ) {
+			sg_frags = qedi_split_bd(cmd, addr, sg_len, bd_count);
+		} else {
+			sg_frags = 1;
+			bd[bd_count].sge_addr.lo = addr & 0xffffffff;
+			bd[bd_count].sge_addr.hi = addr >> 32;
+			bd[bd_count].sge_len = sg_len;
+		}
+		byte_count += sg_len;
+		bd_count += sg_frags;
+	}
+
+	if (byte_count != scsi_bufflen(sc))
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "byte_count = %d != scsi_bufflen = %d\n", byte_count,
+			 scsi_bufflen(sc));
+	else
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO, "byte_count = %d\n",
+			  byte_count);
+
+	WARN_ON(byte_count != scsi_bufflen(sc));
+
+	return bd_count;
+}
+
+static void qedi_iscsi_map_sg_list(struct qedi_cmd *cmd)
+{
+	int bd_count;
+	struct scsi_cmnd *sc = cmd->scsi_cmd;
+
+	if (scsi_sg_count(sc)) {
+		bd_count  = qedi_map_scsi_sg(cmd->conn->qedi, cmd);
+		if (bd_count == 0)
+			return;
+	} else {
+		struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+
+		bd[0].sge_addr.lo = 0;
+		bd[0].sge_addr.hi = 0;
+		bd[0].sge_len = 0;
+		bd_count = 0;
+	}
+	cmd->io_tbl.sge_valid = bd_count;
+}
+
+static void qedi_cpy_scsi_cdb(struct scsi_cmnd *sc, u32 *dstp)
+{
+	u32 dword;
+	int lpcnt;
+	u8 *srcp;
+
+	lpcnt = sc->cmd_len / sizeof(dword);
+	srcp = (u8 *)sc->cmnd;
+	while (lpcnt--) {
+		memcpy(&dword, (const void *)srcp, 4);
+		*dstp = cpu_to_be32(dword);
+		srcp += 4;
+		dstp++;
+	}
+	if (sc->cmd_len & 0x3) {
+		dword = (u32)srcp[0] | ((u32)srcp[1] << 8);
+		*dstp = cpu_to_be32(dword);
+	}
+}
+
+void qedi_trace_io(struct qedi_ctx *qedi, struct iscsi_task *task,
+		   u16 tid, int8_t direction)
+{
+	struct qedi_io_log *io_log;
+	struct iscsi_conn *conn = task->conn;
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct scsi_cmnd *sc_cmd = task->sc;
+	unsigned long flags;
+	u8 op;
+
+	spin_lock_irqsave(&qedi->io_trace_lock, flags);
+
+	io_log = &qedi->io_trace_buf[qedi->io_trace_idx];
+	io_log->direction = direction;
+	io_log->task_id = tid;
+	io_log->cid = qedi_conn->iscsi_conn_id;
+	io_log->lun = sc_cmd->device->lun;
+	io_log->op = sc_cmd->cmnd[0];
+	op = sc_cmd->cmnd[0];
+	io_log->lba[0] = sc_cmd->cmnd[2];
+	io_log->lba[1] = sc_cmd->cmnd[3];
+	io_log->lba[2] = sc_cmd->cmnd[4];
+	io_log->lba[3] = sc_cmd->cmnd[5];
+	io_log->bufflen = scsi_bufflen(sc_cmd);
+	io_log->sg_count = scsi_sg_count(sc_cmd);
+	io_log->fast_sgs = qedi->fast_sgls;
+	io_log->cached_sgs = qedi->cached_sgls;
+	io_log->slow_sgs = qedi->slow_sgls;
+	io_log->cached_sge = qedi->use_cached_sge;
+	io_log->slow_sge = qedi->use_slow_sge;
+	io_log->fast_sge = qedi->use_fast_sge;
+	io_log->result = sc_cmd->result;
+	io_log->jiffies = jiffies;
+	io_log->blk_req_cpu = smp_processor_id();
+
+	if (direction == QEDI_IO_TRACE_REQ) {
+		/* For requests we only care about the submission CPU */
+		io_log->req_cpu = smp_processor_id() % qedi->num_queues;
+		io_log->intr_cpu = 0;
+		io_log->blk_rsp_cpu = 0;
+	} else if (direction == QEDI_IO_TRACE_RSP) {
+		io_log->req_cpu = smp_processor_id() % qedi->num_queues;
+		io_log->intr_cpu = qedi->intr_cpu;
+		io_log->blk_rsp_cpu = smp_processor_id();
+	}
+
+	qedi->io_trace_idx++;
+	if (qedi->io_trace_idx == QEDI_IO_TRACE_SIZE)
+		qedi->io_trace_idx = 0;
+
+	qedi->use_cached_sge = false;
+	qedi->use_slow_sge = false;
+	qedi->use_fast_sge = false;
+
+	spin_unlock_irqrestore(&qedi->io_trace_lock, flags);
+}
+
+int qedi_iscsi_send_ioreq(struct iscsi_task *task)
+{
+	struct iscsi_conn *conn = task->conn;
+	struct iscsi_session *session = conn->session;
+	struct Scsi_Host *shost = iscsi_session_to_shost(session->cls_session);
+	struct qedi_ctx *qedi = iscsi_host_priv(shost);
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct qedi_cmd *cmd = task->dd_data;
+	struct scsi_cmnd *sc = task->sc;
+	struct iscsi_task_context *fw_task_ctx;
+	struct iscsi_cached_sge_ctx *cached_sge;
+	struct iscsi_phys_sgl_ctx *phys_sgl;
+	struct iscsi_virt_sgl_ctx *virt_sgl;
+	struct ystorm_iscsi_task_st_ctx *yst_cxt;
+	struct mstorm_iscsi_task_st_ctx *mst_cxt;
+	struct iscsi_sgl *sgl_struct;
+	struct iscsi_sge *single_sge;
+	struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)task->hdr;
+	struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+	enum iscsi_task_type task_type;
+	struct iscsi_cmd_hdr *fw_cmd;
+	u32 lun[2];
+	u32 exp_data;
+	u16 cq_idx = smp_processor_id() % qedi->num_queues;
+	s16 ptu_invalidate = 0;
+	s16 tid = 0;
+	u8 num_fast_sgs;
+
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1)
+		return -ENOMEM;
+
+	qedi_iscsi_map_sg_list(cmd);
+
+	int_to_scsilun(sc->device->lun, (struct scsi_lun *)lun);
+	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+
+	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+	cmd->task_id = tid;
+
+	/* Ystorm context */
+	fw_cmd = &fw_task_ctx->ystorm_st_context.pdu_hdr.cmd;
+	SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_ATTR, ISCSI_ATTR_SIMPLE);
+
+	if (sc->sc_data_direction == DMA_TO_DEVICE) {
+		if (conn->session->initial_r2t_en) {
+			exp_data = min((conn->session->imm_data_en *
+					conn->max_xmit_dlength),
+				       conn->session->first_burst);
+			exp_data = min(exp_data, scsi_bufflen(sc));
+			fw_task_ctx->ustorm_ag_context.exp_data_acked =
+							  cpu_to_le32(exp_data);
+		} else {
+			fw_task_ctx->ustorm_ag_context.exp_data_acked =
+			      min(conn->session->first_burst, scsi_bufflen(sc));
+		}
+
+		SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_WRITE, 1);
+		task_type = ISCSI_TASK_TYPE_INITIATOR_WRITE;
+	} else {
+		if (scsi_bufflen(sc))
+			SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_READ, 1);
+		task_type = ISCSI_TASK_TYPE_INITIATOR_READ;
+	}
+
+	fw_cmd->lun.lo = be32_to_cpu(lun[0]);
+	fw_cmd->lun.hi = be32_to_cpu(lun[1]);
+
+	qedi_update_itt_map(qedi, tid, task->itt, cmd);
+	fw_cmd->itt = qedi_set_itt(tid, get_itt(task->itt));
+	fw_cmd->expected_transfer_length = scsi_bufflen(sc);
+	fw_cmd->cmd_sn = be32_to_cpu(hdr->cmdsn);
+	fw_cmd->opcode = hdr->opcode;
+	qedi_cpy_scsi_cdb(sc, (u32 *)fw_cmd->cdb);
+
+	/* Mstorm context */
+	fw_task_ctx->mstorm_st_context.sense_db.lo = (u32)cmd->sense_buffer_dma;
+	fw_task_ctx->mstorm_st_context.sense_db.hi =
+					(u32)((u64)cmd->sense_buffer_dma >> 32);
+	fw_task_ctx->mstorm_ag_context.task_cid = qedi_conn->iscsi_conn_id;
+	fw_task_ctx->mstorm_st_context.task_type = task_type;
+
+	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
+		ptu_invalidate = 1;
+		qedi->tid_reuse_count[tid] = 0;
+	}
+	fw_task_ctx->ystorm_st_context.state.reuse_count =
+						     qedi->tid_reuse_count[tid];
+	fw_task_ctx->mstorm_st_context.reuse_count =
+						   qedi->tid_reuse_count[tid]++;
+
+	/* Ustorm context */
+	fw_task_ctx->ustorm_st_context.rem_rcv_len = scsi_bufflen(sc);
+	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = scsi_bufflen(sc);
+	fw_task_ctx->ustorm_st_context.exp_data_sn =
+						   be32_to_cpu(hdr->exp_statsn);
+	fw_task_ctx->ustorm_st_context.task_type = task_type;
+	fw_task_ctx->ustorm_st_context.cq_rss_number = cq_idx;
+	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
+
+	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
+		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
+
+	num_fast_sgs = (cmd->io_tbl.sge_valid ?
+			min((u16)QEDI_FAST_SGE_COUNT,
+			    (u16)cmd->io_tbl.sge_valid) : 0);
+	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+		  ISCSI_REG1_NUM_FAST_SGES, num_fast_sgs);
+
+	fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
+	fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO, "Total sge count [%d]\n",
+		  cmd->io_tbl.sge_valid);
+
+	yst_cxt = &fw_task_ctx->ystorm_st_context;
+	mst_cxt = &fw_task_ctx->mstorm_st_context;
+	/* Tx path */
+	if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) {
+		/* not considering  superIO or FastIO */
+		if (cmd->io_tbl.sge_valid == 1) {
+			cached_sge = &yst_cxt->state.sgl_ctx_union.cached_sge;
+			cached_sge->sge.sge_addr.lo = bd[0].sge_addr.lo;
+			cached_sge->sge.sge_addr.hi = bd[0].sge_addr.hi;
+			cached_sge->sge.sge_len = bd[0].sge_len;
+			qedi->cached_sgls++;
+		} else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) {
+			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+				  ISCSI_MFLAGS_SLOW_IO, 1);
+			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+				  ISCSI_REG1_NUM_FAST_SGES, 0);
+			phys_sgl = &yst_cxt->state.sgl_ctx_union.phys_sgl;
+			phys_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma);
+			phys_sgl->sgl_base.hi =
+				     (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
+			phys_sgl->sgl_size = cmd->io_tbl.sge_valid;
+			qedi->slow_sgls++;
+		} else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) {
+			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+				  ISCSI_MFLAGS_SLOW_IO, 0);
+			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+				  ISCSI_REG1_NUM_FAST_SGES,
+				  min((u16)QEDI_FAST_SGE_COUNT,
+				      (u16)cmd->io_tbl.sge_valid));
+			virt_sgl = &yst_cxt->state.sgl_ctx_union.virt_sgl;
+			virt_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma);
+			virt_sgl->sgl_base.hi =
+				      (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
+			virt_sgl->sgl_initial_offset =
+				 (u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1);
+			qedi->fast_sgls++;
+		}
+		fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid;
+		fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc);
+	} else {
+	/* Rx path */
+		if (cmd->io_tbl.sge_valid == 1) {
+			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+				  ISCSI_MFLAGS_SLOW_IO, 0);
+			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+				  ISCSI_MFLAGS_SINGLE_SGE, 1);
+			single_sge = &mst_cxt->sgl_union.single_sge;
+			single_sge->sge_addr.lo = bd[0].sge_addr.lo;
+			single_sge->sge_addr.hi = bd[0].sge_addr.hi;
+			single_sge->sge_len = bd[0].sge_len;
+			qedi->cached_sgls++;
+		} else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) {
+			sgl_struct = &mst_cxt->sgl_union.sgl_struct;
+			sgl_struct->sgl_addr.lo =
+						(u32)(cmd->io_tbl.sge_tbl_dma);
+			sgl_struct->sgl_addr.hi =
+				     (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
+			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+				  ISCSI_MFLAGS_SLOW_IO, 1);
+			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+				  ISCSI_REG1_NUM_FAST_SGES, 0);
+			sgl_struct->updated_sge_size = 0;
+			sgl_struct->updated_sge_offset = 0;
+			qedi->slow_sgls++;
+		} else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) {
+			sgl_struct = &mst_cxt->sgl_union.sgl_struct;
+			sgl_struct->sgl_addr.lo =
+						(u32)(cmd->io_tbl.sge_tbl_dma);
+			sgl_struct->sgl_addr.hi =
+				     (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
+			sgl_struct->byte_offset =
+				(u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1);
+			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+				  ISCSI_MFLAGS_SLOW_IO, 0);
+			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+				  ISCSI_REG1_NUM_FAST_SGES, 0);
+			sgl_struct->updated_sge_size = 0;
+			sgl_struct->updated_sge_offset = 0;
+			qedi->fast_sgls++;
+		}
+		fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid;
+		fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc);
+	}
+
+	if (cmd->io_tbl.sge_valid == 1)
+		/* Singel-SGL */
+		qedi->use_cached_sge = true;
+	else {
+		if (cmd->use_slowpath)
+			qedi->use_slow_sge = true;
+		else
+			qedi->use_fast_sge = true;
+	}
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO,
+		  "%s: %s-SGL: num_sges=0x%x first-sge-lo=0x%x first-sge-hi=0x%x",
+		  (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) ?
+		  "Write " : "Read ", (cmd->io_tbl.sge_valid == 1) ?
+		  "Single" : (cmd->use_slowpath ? "SLOW" : "FAST"),
+		  (u16)cmd->io_tbl.sge_valid, (u32)(cmd->io_tbl.sge_tbl_dma),
+		  (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32));
+
+	/*  Add command in active command list */
+	spin_lock(&qedi_conn->list_lock);
+	list_add_tail(&cmd->io_cmd, &qedi_conn->active_cmd_list);
+	cmd->io_cmd_in_list = true;
+	qedi_conn->active_cmd_count++;
+	spin_unlock(&qedi_conn->list_lock);
+
+	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
+	qedi_ring_doorbell(qedi_conn);
+	if (qedi_io_tracing)
+		qedi_trace_io(qedi, task, tid, QEDI_IO_TRACE_REQ);
+
+	return 0;
+}
+
+int qedi_iscsi_cleanup_task(struct iscsi_task *task, bool mark_cmd_node_deleted)
+{
+	struct iscsi_conn *conn = task->conn;
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct qedi_cmd *cmd = task->dd_data;
+	s16 ptu_invalidate = 0;
+
+	QEDI_INFO(&qedi_conn->qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+		  "issue cleanup tid=0x%x itt=0x%x task_state=%d cmd_state=0%x cid=0x%x\n",
+		  cmd->task_id, get_itt(task->itt), task->state,
+		  cmd->state, qedi_conn->iscsi_conn_id);
+
+	qedi_add_to_sq(qedi_conn, task, cmd->task_id, ptu_invalidate, true);
+	qedi_ring_doorbell(qedi_conn);
+
+	return 0;
+}
diff --git a/drivers/scsi/qedi/qedi_gbl.h b/drivers/scsi/qedi/qedi_gbl.h
new file mode 100644
index 000000000000..8e488de88ece
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_gbl.h
@@ -0,0 +1,73 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#ifndef _QEDI_GBL_H_
+#define _QEDI_GBL_H_
+
+#include "qedi_iscsi.h"
+
+extern uint qedi_io_tracing;
+extern int do_not_recover;
+extern struct scsi_host_template qedi_host_template;
+extern struct iscsi_transport qedi_iscsi_transport;
+extern const struct qed_iscsi_ops *qedi_ops;
+extern struct qedi_debugfs_ops qedi_debugfs_ops;
+extern const struct file_operations qedi_dbg_fops;
+extern struct device_attribute *qedi_shost_attrs[];
+
+int qedi_alloc_sq(struct qedi_ctx *qedi, struct qedi_endpoint *ep);
+void qedi_free_sq(struct qedi_ctx *qedi, struct qedi_endpoint *ep);
+
+int qedi_send_iscsi_login(struct qedi_conn *qedi_conn,
+			  struct iscsi_task *task);
+int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn,
+			   struct iscsi_task *task);
+int qedi_iscsi_abort_work(struct qedi_conn *qedi_conn,
+			  struct iscsi_task *mtask);
+int qedi_send_iscsi_text(struct qedi_conn *qedi_conn,
+			 struct iscsi_task *task);
+int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn,
+			   struct iscsi_task *task,
+			   char *datap, int data_len, int unsol);
+int qedi_iscsi_send_ioreq(struct iscsi_task *task);
+int qedi_get_task_idx(struct qedi_ctx *qedi);
+void qedi_clear_task_idx(struct qedi_ctx *qedi, int idx);
+int qedi_iscsi_cleanup_task(struct iscsi_task *task,
+			    bool mark_cmd_node_deleted);
+void qedi_iscsi_unmap_sg_list(struct qedi_cmd *cmd);
+void qedi_update_itt_map(struct qedi_ctx *qedi, u32 tid, u32 proto_itt,
+			 struct qedi_cmd *qedi_cmd);
+void qedi_get_proto_itt(struct qedi_ctx *qedi, u32 tid, u32 *proto_itt);
+void qedi_get_task_tid(struct qedi_ctx *qedi, u32 itt, int16_t *tid);
+void qedi_process_iscsi_error(struct qedi_endpoint *ep,
+			      struct async_data *data);
+void qedi_start_conn_recovery(struct qedi_ctx *qedi,
+			      struct qedi_conn *qedi_conn);
+struct qedi_conn *qedi_get_conn_from_id(struct qedi_ctx *qedi, u32 iscsi_cid);
+void qedi_process_tcp_error(struct qedi_endpoint *ep, struct async_data *data);
+void qedi_mark_device_missing(struct iscsi_cls_session *cls_session);
+void qedi_mark_device_available(struct iscsi_cls_session *cls_session);
+void qedi_reset_host_mtu(struct qedi_ctx *qedi, u16 mtu);
+int qedi_recover_all_conns(struct qedi_ctx *qedi);
+void qedi_fp_process_cqes(struct qedi_work *work);
+int qedi_cleanup_all_io(struct qedi_ctx *qedi,
+			struct qedi_conn *qedi_conn,
+			struct iscsi_task *task, bool in_recovery);
+void qedi_trace_io(struct qedi_ctx *qedi, struct iscsi_task *task,
+		   u16 tid, int8_t direction);
+int qedi_alloc_id(struct qedi_portid_tbl *id_tbl, u16 id);
+u16 qedi_alloc_new_id(struct qedi_portid_tbl *id_tbl);
+void qedi_free_id(struct qedi_portid_tbl *id_tbl, u16 id);
+int qedi_create_sysfs_ctx_attr(struct qedi_ctx *qedi);
+void qedi_remove_sysfs_ctx_attr(struct qedi_ctx *qedi);
+void qedi_clearsq(struct qedi_ctx *qedi,
+		  struct qedi_conn *qedi_conn,
+		  struct iscsi_task *task);
+
+#endif
diff --git a/drivers/scsi/qedi/qedi_hsi.h b/drivers/scsi/qedi/qedi_hsi.h
new file mode 100644
index 000000000000..8ca44c78f093
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_hsi.h
@@ -0,0 +1,52 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+#ifndef __QEDI_HSI__
+#define __QEDI_HSI__
+/*
+ * Add include to common target
+ */
+#include <linux/qed/common_hsi.h>
+
+/*
+ * Add include to common storage target
+ */
+#include <linux/qed/storage_common.h>
+
+/*
+ * Add include to common TCP target
+ */
+#include <linux/qed/tcp_common.h>
+
+/*
+ * Add include to common iSCSI target for both eCore and protocol driver
+ */
+#include <linux/qed/iscsi_common.h>
+
+/*
+ * iSCSI CMDQ element
+ */
+struct iscsi_cmdqe {
+	__le16 conn_id;
+	u8 invalid_command;
+	u8 cmd_hdr_type;
+	__le32 reserved1[2];
+	__le32 cmd_payload[13];
+};
+
+/*
+ * iSCSI CMD header type
+ */
+enum iscsi_cmd_hdr_type {
+	ISCSI_CMD_HDR_TYPE_BHS_ONLY /* iSCSI BHS with no expected AHS */,
+	ISCSI_CMD_HDR_TYPE_BHS_W_AHS /* iSCSI BHS with expected AHS */,
+	ISCSI_CMD_HDR_TYPE_AHS /* iSCSI AHS */,
+	MAX_ISCSI_CMD_HDR_TYPE
+};
+
+#endif /* __QEDI_HSI__ */
diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c
new file mode 100644
index 000000000000..d6a205433b66
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_iscsi.c
@@ -0,0 +1,1624 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include <linux/blkdev.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <scsi/scsi_tcq.h>
+
+#include "qedi.h"
+#include "qedi_iscsi.h"
+#include "qedi_gbl.h"
+
+int qedi_recover_all_conns(struct qedi_ctx *qedi)
+{
+	struct qedi_conn *qedi_conn;
+	int i;
+
+	for (i = 0; i < qedi->max_active_conns; i++) {
+		qedi_conn = qedi_get_conn_from_id(qedi, i);
+		if (!qedi_conn)
+			continue;
+
+		qedi_start_conn_recovery(qedi, qedi_conn);
+	}
+
+	return SUCCESS;
+}
+
+static int qedi_eh_host_reset(struct scsi_cmnd *cmd)
+{
+	struct Scsi_Host *shost = cmd->device->host;
+	struct qedi_ctx *qedi;
+
+	qedi = iscsi_host_priv(shost);
+
+	return qedi_recover_all_conns(qedi);
+}
+
+struct scsi_host_template qedi_host_template = {
+	.module = THIS_MODULE,
+	.name = "QLogic QEDI 25/40/100Gb iSCSI Initiator Driver",
+	.proc_name = QEDI_MODULE_NAME,
+	.queuecommand = iscsi_queuecommand,
+	.eh_abort_handler = iscsi_eh_abort,
+	.eh_device_reset_handler = iscsi_eh_device_reset,
+	.eh_target_reset_handler = iscsi_eh_recover_target,
+	.eh_host_reset_handler = qedi_eh_host_reset,
+	.target_alloc = iscsi_target_alloc,
+	.change_queue_depth = scsi_change_queue_depth,
+	.can_queue = QEDI_MAX_ISCSI_TASK,
+	.this_id = -1,
+	.sg_tablesize = QEDI_ISCSI_MAX_BDS_PER_CMD,
+	.max_sectors = 0xffff,
+	.cmd_per_lun = 128,
+	.use_clustering = ENABLE_CLUSTERING,
+	.shost_attrs = qedi_shost_attrs,
+};
+
+static void qedi_conn_free_login_resources(struct qedi_ctx *qedi,
+					   struct qedi_conn *qedi_conn)
+{
+	if (qedi_conn->gen_pdu.resp_bd_tbl) {
+		dma_free_coherent(&qedi->pdev->dev, QEDI_PAGE_SIZE,
+				  qedi_conn->gen_pdu.resp_bd_tbl,
+				  qedi_conn->gen_pdu.resp_bd_dma);
+		qedi_conn->gen_pdu.resp_bd_tbl = NULL;
+	}
+
+	if (qedi_conn->gen_pdu.req_bd_tbl) {
+		dma_free_coherent(&qedi->pdev->dev, QEDI_PAGE_SIZE,
+				  qedi_conn->gen_pdu.req_bd_tbl,
+				  qedi_conn->gen_pdu.req_bd_dma);
+		qedi_conn->gen_pdu.req_bd_tbl = NULL;
+	}
+
+	if (qedi_conn->gen_pdu.resp_buf) {
+		dma_free_coherent(&qedi->pdev->dev,
+				  ISCSI_DEF_MAX_RECV_SEG_LEN,
+				  qedi_conn->gen_pdu.resp_buf,
+				  qedi_conn->gen_pdu.resp_dma_addr);
+		qedi_conn->gen_pdu.resp_buf = NULL;
+	}
+
+	if (qedi_conn->gen_pdu.req_buf) {
+		dma_free_coherent(&qedi->pdev->dev,
+				  ISCSI_DEF_MAX_RECV_SEG_LEN,
+				  qedi_conn->gen_pdu.req_buf,
+				  qedi_conn->gen_pdu.req_dma_addr);
+		qedi_conn->gen_pdu.req_buf = NULL;
+	}
+}
+
+static int qedi_conn_alloc_login_resources(struct qedi_ctx *qedi,
+					   struct qedi_conn *qedi_conn)
+{
+	qedi_conn->gen_pdu.req_buf =
+		dma_alloc_coherent(&qedi->pdev->dev,
+				   ISCSI_DEF_MAX_RECV_SEG_LEN,
+				   &qedi_conn->gen_pdu.req_dma_addr,
+				   GFP_KERNEL);
+	if (!qedi_conn->gen_pdu.req_buf)
+		goto login_req_buf_failure;
+
+	qedi_conn->gen_pdu.req_buf_size = 0;
+	qedi_conn->gen_pdu.req_wr_ptr = qedi_conn->gen_pdu.req_buf;
+
+	qedi_conn->gen_pdu.resp_buf =
+		dma_alloc_coherent(&qedi->pdev->dev,
+				   ISCSI_DEF_MAX_RECV_SEG_LEN,
+				   &qedi_conn->gen_pdu.resp_dma_addr,
+				   GFP_KERNEL);
+	if (!qedi_conn->gen_pdu.resp_buf)
+		goto login_resp_buf_failure;
+
+	qedi_conn->gen_pdu.resp_buf_size = ISCSI_DEF_MAX_RECV_SEG_LEN;
+	qedi_conn->gen_pdu.resp_wr_ptr = qedi_conn->gen_pdu.resp_buf;
+
+	qedi_conn->gen_pdu.req_bd_tbl =
+		dma_alloc_coherent(&qedi->pdev->dev, QEDI_PAGE_SIZE,
+				   &qedi_conn->gen_pdu.req_bd_dma, GFP_KERNEL);
+	if (!qedi_conn->gen_pdu.req_bd_tbl)
+		goto login_req_bd_tbl_failure;
+
+	qedi_conn->gen_pdu.resp_bd_tbl =
+		dma_alloc_coherent(&qedi->pdev->dev, QEDI_PAGE_SIZE,
+				   &qedi_conn->gen_pdu.resp_bd_dma,
+				   GFP_KERNEL);
+	if (!qedi_conn->gen_pdu.resp_bd_tbl)
+		goto login_resp_bd_tbl_failure;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SESS,
+		  "Allocation successful, cid=0x%x\n",
+		  qedi_conn->iscsi_conn_id);
+	return 0;
+
+login_resp_bd_tbl_failure:
+	dma_free_coherent(&qedi->pdev->dev, QEDI_PAGE_SIZE,
+			  qedi_conn->gen_pdu.req_bd_tbl,
+			  qedi_conn->gen_pdu.req_bd_dma);
+	qedi_conn->gen_pdu.req_bd_tbl = NULL;
+
+login_req_bd_tbl_failure:
+	dma_free_coherent(&qedi->pdev->dev, ISCSI_DEF_MAX_RECV_SEG_LEN,
+			  qedi_conn->gen_pdu.resp_buf,
+			  qedi_conn->gen_pdu.resp_dma_addr);
+	qedi_conn->gen_pdu.resp_buf = NULL;
+login_resp_buf_failure:
+	dma_free_coherent(&qedi->pdev->dev, ISCSI_DEF_MAX_RECV_SEG_LEN,
+			  qedi_conn->gen_pdu.req_buf,
+			  qedi_conn->gen_pdu.req_dma_addr);
+	qedi_conn->gen_pdu.req_buf = NULL;
+login_req_buf_failure:
+	iscsi_conn_printk(KERN_ERR, qedi_conn->cls_conn->dd_data,
+			  "login resource alloc failed!!\n");
+	return -ENOMEM;
+}
+
+static void qedi_destroy_cmd_pool(struct qedi_ctx *qedi,
+				  struct iscsi_session *session)
+{
+	int i;
+
+	for (i = 0; i < session->cmds_max; i++) {
+		struct iscsi_task *task = session->cmds[i];
+		struct qedi_cmd *cmd = task->dd_data;
+
+		if (cmd->io_tbl.sge_tbl)
+			dma_free_coherent(&qedi->pdev->dev,
+					  QEDI_ISCSI_MAX_BDS_PER_CMD *
+					  sizeof(struct iscsi_sge),
+					  cmd->io_tbl.sge_tbl,
+					  cmd->io_tbl.sge_tbl_dma);
+
+		if (cmd->sense_buffer)
+			dma_free_coherent(&qedi->pdev->dev,
+					  SCSI_SENSE_BUFFERSIZE,
+					  cmd->sense_buffer,
+					  cmd->sense_buffer_dma);
+	}
+}
+
+static int qedi_alloc_sget(struct qedi_ctx *qedi, struct iscsi_session *session,
+			   struct qedi_cmd *cmd)
+{
+	struct qedi_io_bdt *io = &cmd->io_tbl;
+	struct iscsi_sge *sge;
+
+	io->sge_tbl = dma_alloc_coherent(&qedi->pdev->dev,
+					 QEDI_ISCSI_MAX_BDS_PER_CMD *
+					 sizeof(*sge),
+					 &io->sge_tbl_dma, GFP_KERNEL);
+	if (!io->sge_tbl) {
+		iscsi_session_printk(KERN_ERR, session,
+				     "Could not allocate BD table.\n");
+		return -ENOMEM;
+	}
+
+	io->sge_valid = 0;
+	return 0;
+}
+
+static int qedi_setup_cmd_pool(struct qedi_ctx *qedi,
+			       struct iscsi_session *session)
+{
+	int i;
+
+	for (i = 0; i < session->cmds_max; i++) {
+		struct iscsi_task *task = session->cmds[i];
+		struct qedi_cmd *cmd = task->dd_data;
+
+		task->hdr = &cmd->hdr;
+		task->hdr_max = sizeof(struct iscsi_hdr);
+
+		if (qedi_alloc_sget(qedi, session, cmd))
+			goto free_sgets;
+
+		cmd->sense_buffer = dma_alloc_coherent(&qedi->pdev->dev,
+						       SCSI_SENSE_BUFFERSIZE,
+						       &cmd->sense_buffer_dma,
+						       GFP_KERNEL);
+		if (!cmd->sense_buffer)
+			goto free_sgets;
+	}
+
+	return 0;
+
+free_sgets:
+	qedi_destroy_cmd_pool(qedi, session);
+	return -ENOMEM;
+}
+
+static struct iscsi_cls_session *
+qedi_session_create(struct iscsi_endpoint *ep, u16 cmds_max,
+		    u16 qdepth, uint32_t initial_cmdsn)
+{
+	struct Scsi_Host *shost;
+	struct iscsi_cls_session *cls_session;
+	struct qedi_ctx *qedi;
+	struct qedi_endpoint *qedi_ep;
+
+	if (!ep)
+		return NULL;
+
+	qedi_ep = ep->dd_data;
+	shost = qedi_ep->qedi->shost;
+	qedi = iscsi_host_priv(shost);
+
+	if (cmds_max > qedi->max_sqes)
+		cmds_max = qedi->max_sqes;
+	else if (cmds_max < QEDI_SQ_WQES_MIN)
+		cmds_max = QEDI_SQ_WQES_MIN;
+
+	cls_session = iscsi_session_setup(&qedi_iscsi_transport, shost,
+					  cmds_max, 0, sizeof(struct qedi_cmd),
+					  initial_cmdsn, ISCSI_MAX_TARGET);
+	if (!cls_session) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Failed to setup session for ep=%p\n", qedi_ep);
+		return NULL;
+	}
+
+	if (qedi_setup_cmd_pool(qedi, cls_session->dd_data)) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Failed to setup cmd pool for ep=%p\n", qedi_ep);
+		goto session_teardown;
+	}
+
+	return cls_session;
+
+session_teardown:
+	iscsi_session_teardown(cls_session);
+	return NULL;
+}
+
+static void qedi_session_destroy(struct iscsi_cls_session *cls_session)
+{
+	struct iscsi_session *session = cls_session->dd_data;
+	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
+	struct qedi_ctx *qedi = iscsi_host_priv(shost);
+
+	qedi_destroy_cmd_pool(qedi, session);
+	iscsi_session_teardown(cls_session);
+}
+
+static struct iscsi_cls_conn *
+qedi_conn_create(struct iscsi_cls_session *cls_session, uint32_t cid)
+{
+	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
+	struct qedi_ctx *qedi = iscsi_host_priv(shost);
+	struct iscsi_cls_conn *cls_conn;
+	struct qedi_conn *qedi_conn;
+	struct iscsi_conn *conn;
+
+	cls_conn = iscsi_conn_setup(cls_session, sizeof(*qedi_conn),
+				    cid);
+	if (!cls_conn) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "conn_new: iscsi conn setup failed, cid=0x%x, cls_sess=%p!\n",
+			 cid, cls_session);
+		return NULL;
+	}
+
+	conn = cls_conn->dd_data;
+	qedi_conn = conn->dd_data;
+	qedi_conn->cls_conn = cls_conn;
+	qedi_conn->qedi = qedi;
+	qedi_conn->ep = NULL;
+	qedi_conn->active_cmd_count = 0;
+	INIT_LIST_HEAD(&qedi_conn->active_cmd_list);
+	spin_lock_init(&qedi_conn->list_lock);
+
+	if (qedi_conn_alloc_login_resources(qedi, qedi_conn)) {
+		iscsi_conn_printk(KERN_ALERT, conn,
+				  "conn_new: login resc alloc failed, cid=0x%x, cls_sess=%p!!\n",
+				   cid, cls_session);
+		goto free_conn;
+	}
+
+	return cls_conn;
+
+free_conn:
+	iscsi_conn_teardown(cls_conn);
+	return NULL;
+}
+
+void qedi_mark_device_missing(struct iscsi_cls_session *cls_session)
+{
+	iscsi_block_session(cls_session);
+}
+
+void qedi_mark_device_available(struct iscsi_cls_session *cls_session)
+{
+	iscsi_unblock_session(cls_session);
+}
+
+static int qedi_bind_conn_to_iscsi_cid(struct qedi_ctx *qedi,
+				       struct qedi_conn *qedi_conn)
+{
+	u32 iscsi_cid = qedi_conn->iscsi_conn_id;
+
+	if (qedi->cid_que.conn_cid_tbl[iscsi_cid]) {
+		iscsi_conn_printk(KERN_ALERT, qedi_conn->cls_conn->dd_data,
+				  "conn bind - entry #%d not free\n",
+				  iscsi_cid);
+		return -EBUSY;
+	}
+
+	qedi->cid_que.conn_cid_tbl[iscsi_cid] = qedi_conn;
+	return 0;
+}
+
+struct qedi_conn *qedi_get_conn_from_id(struct qedi_ctx *qedi, u32 iscsi_cid)
+{
+	if (!qedi->cid_que.conn_cid_tbl) {
+		QEDI_ERR(&qedi->dbg_ctx, "missing conn<->cid table\n");
+		return NULL;
+
+	} else if (iscsi_cid >= qedi->max_active_conns) {
+		QEDI_ERR(&qedi->dbg_ctx, "wrong cid #%d\n", iscsi_cid);
+		return NULL;
+	}
+	return qedi->cid_que.conn_cid_tbl[iscsi_cid];
+}
+
+static int qedi_conn_bind(struct iscsi_cls_session *cls_session,
+			  struct iscsi_cls_conn *cls_conn,
+			  u64 transport_fd, int is_leading)
+{
+	struct iscsi_conn *conn = cls_conn->dd_data;
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
+	struct qedi_ctx *qedi = iscsi_host_priv(shost);
+	struct qedi_endpoint *qedi_ep;
+	struct iscsi_endpoint *ep;
+
+	ep = iscsi_lookup_endpoint(transport_fd);
+	if (!ep)
+		return -EINVAL;
+
+	qedi_ep = ep->dd_data;
+	if ((qedi_ep->state == EP_STATE_TCP_FIN_RCVD) ||
+	    (qedi_ep->state == EP_STATE_TCP_RST_RCVD))
+		return -EINVAL;
+
+	if (iscsi_conn_bind(cls_session, cls_conn, is_leading))
+		return -EINVAL;
+
+	qedi_ep->conn = qedi_conn;
+	qedi_conn->ep = qedi_ep;
+	qedi_conn->iscsi_conn_id = qedi_ep->iscsi_cid;
+	qedi_conn->fw_cid = qedi_ep->fw_cid;
+	qedi_conn->cmd_cleanup_req = 0;
+	qedi_conn->cmd_cleanup_cmpl = 0;
+
+	if (qedi_bind_conn_to_iscsi_cid(qedi, qedi_conn))
+		return -EINVAL;
+
+	spin_lock_init(&qedi_conn->tmf_work_lock);
+	INIT_LIST_HEAD(&qedi_conn->tmf_work_list);
+	init_waitqueue_head(&qedi_conn->wait_queue);
+	return 0;
+}
+
+static int qedi_iscsi_update_conn(struct qedi_ctx *qedi,
+				  struct qedi_conn *qedi_conn)
+{
+	struct qed_iscsi_params_update *conn_info;
+	struct iscsi_cls_conn *cls_conn = qedi_conn->cls_conn;
+	struct iscsi_conn *conn = cls_conn->dd_data;
+	struct qedi_endpoint *qedi_ep;
+	int rval;
+
+	qedi_ep = qedi_conn->ep;
+
+	conn_info = kzalloc(sizeof(*conn_info), GFP_KERNEL);
+	if (!conn_info) {
+		QEDI_ERR(&qedi->dbg_ctx, "memory alloc failed\n");
+		return -ENOMEM;
+	}
+
+	conn_info->update_flag = 0;
+
+	if (conn->hdrdgst_en)
+		SET_FIELD(conn_info->update_flag,
+			  ISCSI_CONN_UPDATE_RAMROD_PARAMS_HD_EN, true);
+	if (conn->datadgst_en)
+		SET_FIELD(conn_info->update_flag,
+			  ISCSI_CONN_UPDATE_RAMROD_PARAMS_DD_EN, true);
+	if (conn->session->initial_r2t_en)
+		SET_FIELD(conn_info->update_flag,
+			  ISCSI_CONN_UPDATE_RAMROD_PARAMS_INITIAL_R2T,
+			  true);
+	if (conn->session->imm_data_en)
+		SET_FIELD(conn_info->update_flag,
+			  ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA,
+			  true);
+
+	conn_info->max_seq_size = conn->session->max_burst;
+	conn_info->max_recv_pdu_length = conn->max_recv_dlength;
+	conn_info->max_send_pdu_length = conn->max_xmit_dlength;
+	conn_info->first_seq_length = conn->session->first_burst;
+	conn_info->exp_stat_sn = conn->exp_statsn;
+
+	rval = qedi_ops->update_conn(qedi->cdev, qedi_ep->handle,
+				     conn_info);
+	if (rval) {
+		rval = -ENXIO;
+		QEDI_ERR(&qedi->dbg_ctx, "Could not update connection\n");
+		goto update_conn_err;
+	}
+
+	kfree(conn_info);
+	rval = 0;
+
+update_conn_err:
+	return rval;
+}
+
+static u16 qedi_calc_mss(u16 pmtu, u8 is_ipv6, u8 tcp_ts_en, u8 vlan_en)
+{
+	u16 mss = 0;
+	u16 hdrs = TCP_HDR_LEN;
+
+	if (is_ipv6)
+		hdrs += IPV6_HDR_LEN;
+	else
+		hdrs += IPV4_HDR_LEN;
+
+	if (vlan_en)
+		hdrs += VLAN_LEN;
+
+	mss = pmtu - hdrs;
+
+	if (tcp_ts_en)
+		mss -= TCP_OPTION_LEN;
+
+	if (!mss)
+		mss = DEF_MSS;
+
+	return mss;
+}
+
+static int qedi_iscsi_offload_conn(struct qedi_endpoint *qedi_ep)
+{
+	struct qedi_ctx *qedi = qedi_ep->qedi;
+	struct qed_iscsi_params_offload *conn_info;
+	int rval;
+	int i;
+
+	conn_info = kzalloc(sizeof(*conn_info), GFP_KERNEL);
+	if (!conn_info) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Failed to allocate memory ep=%p\n", qedi_ep);
+		return -ENOMEM;
+	}
+
+	ether_addr_copy(conn_info->src.mac, qedi_ep->src_mac);
+	ether_addr_copy(conn_info->dst.mac, qedi_ep->dst_mac);
+
+	conn_info->src.ip[0] = ntohl(qedi_ep->src_addr[0]);
+	conn_info->dst.ip[0] = ntohl(qedi_ep->dst_addr[0]);
+
+	if (qedi_ep->ip_type == TCP_IPV4) {
+		conn_info->ip_version = 0;
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "After ntohl: src_addr=%pI4, dst_addr=%pI4\n",
+			  qedi_ep->src_addr, qedi_ep->dst_addr);
+	} else {
+		for (i = 1; i < 4; i++) {
+			conn_info->src.ip[i] = ntohl(qedi_ep->src_addr[i]);
+			conn_info->dst.ip[i] = ntohl(qedi_ep->dst_addr[i]);
+		}
+
+		conn_info->ip_version = 1;
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "After ntohl: src_addr=%pI6, dst_addr=%pI6\n",
+			  qedi_ep->src_addr, qedi_ep->dst_addr);
+	}
+
+	conn_info->src.port = qedi_ep->src_port;
+	conn_info->dst.port = qedi_ep->dst_port;
+
+	conn_info->layer_code = ISCSI_SLOW_PATH_LAYER_CODE;
+	conn_info->sq_pbl_addr = qedi_ep->sq_pbl_dma;
+	conn_info->vlan_id = qedi_ep->vlan_id;
+
+	SET_FIELD(conn_info->tcp_flags, TCP_OFFLOAD_PARAMS_TS_EN, 1);
+	SET_FIELD(conn_info->tcp_flags, TCP_OFFLOAD_PARAMS_DA_EN, 1);
+	SET_FIELD(conn_info->tcp_flags, TCP_OFFLOAD_PARAMS_DA_CNT_EN, 1);
+	SET_FIELD(conn_info->tcp_flags, TCP_OFFLOAD_PARAMS_KA_EN, 1);
+
+	conn_info->default_cq = (qedi_ep->fw_cid % 8);
+
+	conn_info->ka_max_probe_cnt = DEF_KA_MAX_PROBE_COUNT;
+	conn_info->dup_ack_theshold = 3;
+	conn_info->rcv_wnd = 65535;
+	conn_info->cwnd = DEF_MAX_CWND;
+
+	conn_info->ss_thresh = 65535;
+	conn_info->srtt = 300;
+	conn_info->rtt_var = 150;
+	conn_info->flow_label = 0;
+	conn_info->ka_timeout = DEF_KA_TIMEOUT;
+	conn_info->ka_interval = DEF_KA_INTERVAL;
+	conn_info->max_rt_time = DEF_MAX_RT_TIME;
+	conn_info->ttl = DEF_TTL;
+	conn_info->tos_or_tc = DEF_TOS;
+	conn_info->remote_port = qedi_ep->dst_port;
+	conn_info->local_port = qedi_ep->src_port;
+
+	conn_info->mss = qedi_calc_mss(qedi_ep->pmtu,
+				       (qedi_ep->ip_type == TCP_IPV6),
+				       1, (qedi_ep->vlan_id != 0));
+
+	conn_info->rcv_wnd_scale = 4;
+	conn_info->ts_ticks_per_second = 1000;
+	conn_info->da_timeout_value = 200;
+	conn_info->ack_frequency = 2;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+		  "Default cq index [%d], mss [%d]\n",
+		  conn_info->default_cq, conn_info->mss);
+
+	rval = qedi_ops->offload_conn(qedi->cdev, qedi_ep->handle, conn_info);
+	if (rval)
+		QEDI_ERR(&qedi->dbg_ctx, "offload_conn returned %d, ep=%p\n",
+			 rval, qedi_ep);
+
+	kfree(conn_info);
+	return rval;
+}
+
+static int qedi_conn_start(struct iscsi_cls_conn *cls_conn)
+{
+	struct iscsi_conn *conn = cls_conn->dd_data;
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct qedi_ctx *qedi;
+	int rval;
+
+	qedi = qedi_conn->qedi;
+
+	rval = qedi_iscsi_update_conn(qedi, qedi_conn);
+	if (rval) {
+		iscsi_conn_printk(KERN_ALERT, conn,
+				  "conn_start: FW oflload conn failed.\n");
+		rval = -EINVAL;
+		goto start_err;
+	}
+
+	clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+	qedi_conn->abrt_conn = 0;
+
+	rval = iscsi_conn_start(cls_conn);
+	if (rval) {
+		iscsi_conn_printk(KERN_ALERT, conn,
+				  "iscsi_conn_start: FW oflload conn failed!!\n");
+	}
+
+start_err:
+	return rval;
+}
+
+static void qedi_conn_destroy(struct iscsi_cls_conn *cls_conn)
+{
+	struct iscsi_conn *conn = cls_conn->dd_data;
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct Scsi_Host *shost;
+	struct qedi_ctx *qedi;
+
+	shost = iscsi_session_to_shost(iscsi_conn_to_session(cls_conn));
+	qedi = iscsi_host_priv(shost);
+
+	qedi_conn_free_login_resources(qedi, qedi_conn);
+	iscsi_conn_teardown(cls_conn);
+}
+
+static int qedi_ep_get_param(struct iscsi_endpoint *ep,
+			     enum iscsi_param param, char *buf)
+{
+	struct qedi_endpoint *qedi_ep = ep->dd_data;
+	int len;
+
+	if (!qedi_ep)
+		return -ENOTCONN;
+
+	switch (param) {
+	case ISCSI_PARAM_CONN_PORT:
+		len = sprintf(buf, "%hu\n", qedi_ep->dst_port);
+		break;
+	case ISCSI_PARAM_CONN_ADDRESS:
+		if (qedi_ep->ip_type == TCP_IPV4)
+			len = sprintf(buf, "%pI4\n", qedi_ep->dst_addr);
+		else
+			len = sprintf(buf, "%pI6\n", qedi_ep->dst_addr);
+		break;
+	default:
+		return -ENOTCONN;
+	}
+
+	return len;
+}
+
+static int qedi_host_get_param(struct Scsi_Host *shost,
+			       enum iscsi_host_param param, char *buf)
+{
+	struct qedi_ctx *qedi;
+	int len;
+
+	qedi = iscsi_host_priv(shost);
+
+	switch (param) {
+	case ISCSI_HOST_PARAM_HWADDRESS:
+		len = sysfs_format_mac(buf, qedi->mac, 6);
+		break;
+	case ISCSI_HOST_PARAM_NETDEV_NAME:
+		len = sprintf(buf, "host%d\n", shost->host_no);
+		break;
+	case ISCSI_HOST_PARAM_IPADDRESS:
+		if (qedi->ip_type == TCP_IPV4)
+			len = sprintf(buf, "%pI4\n", qedi->src_ip);
+		else
+			len = sprintf(buf, "%pI6\n", qedi->src_ip);
+		break;
+	default:
+		return iscsi_host_get_param(shost, param, buf);
+	}
+
+	return len;
+}
+
+static void qedi_conn_get_stats(struct iscsi_cls_conn *cls_conn,
+				struct iscsi_stats *stats)
+{
+	struct iscsi_conn *conn = cls_conn->dd_data;
+	struct qed_iscsi_stats iscsi_stats;
+	struct Scsi_Host *shost;
+	struct qedi_ctx *qedi;
+
+	shost = iscsi_session_to_shost(iscsi_conn_to_session(cls_conn));
+	qedi = iscsi_host_priv(shost);
+	qedi_ops->get_stats(qedi->cdev, &iscsi_stats);
+
+	conn->txdata_octets = iscsi_stats.iscsi_tx_bytes_cnt;
+	conn->rxdata_octets = iscsi_stats.iscsi_rx_bytes_cnt;
+	conn->dataout_pdus_cnt = (uint32_t)iscsi_stats.iscsi_tx_data_pdu_cnt;
+	conn->datain_pdus_cnt = (uint32_t)iscsi_stats.iscsi_rx_data_pdu_cnt;
+	conn->r2t_pdus_cnt = (uint32_t)iscsi_stats.iscsi_rx_r2t_pdu_cnt;
+
+	stats->txdata_octets = conn->txdata_octets;
+	stats->rxdata_octets = conn->rxdata_octets;
+	stats->scsicmd_pdus = conn->scsicmd_pdus_cnt;
+	stats->dataout_pdus = conn->dataout_pdus_cnt;
+	stats->scsirsp_pdus = conn->scsirsp_pdus_cnt;
+	stats->datain_pdus = conn->datain_pdus_cnt;
+	stats->r2t_pdus = conn->r2t_pdus_cnt;
+	stats->tmfcmd_pdus = conn->tmfcmd_pdus_cnt;
+	stats->tmfrsp_pdus = conn->tmfrsp_pdus_cnt;
+	stats->digest_err = 0;
+	stats->timeout_err = 0;
+	strcpy(stats->custom[0].desc, "eh_abort_cnt");
+	stats->custom[0].value = conn->eh_abort_cnt;
+	stats->custom_length = 1;
+}
+
+static void qedi_iscsi_prep_generic_pdu_bd(struct qedi_conn *qedi_conn)
+{
+	struct iscsi_sge *bd_tbl;
+
+	bd_tbl = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+
+	bd_tbl->sge_addr.hi =
+		(u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+	bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.req_dma_addr;
+	bd_tbl->sge_len = qedi_conn->gen_pdu.req_wr_ptr -
+				qedi_conn->gen_pdu.req_buf;
+	bd_tbl->reserved0 = 0;
+	bd_tbl = (struct iscsi_sge  *)qedi_conn->gen_pdu.resp_bd_tbl;
+	bd_tbl->sge_addr.hi =
+			(u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
+	bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.resp_dma_addr;
+	bd_tbl->sge_len = ISCSI_DEF_MAX_RECV_SEG_LEN;
+	bd_tbl->reserved0 = 0;
+}
+
+static int qedi_iscsi_send_generic_request(struct iscsi_task *task)
+{
+	struct qedi_cmd *cmd = task->dd_data;
+	struct qedi_conn *qedi_conn = cmd->conn;
+	char *buf;
+	int data_len;
+	int rc = 0;
+
+	qedi_iscsi_prep_generic_pdu_bd(qedi_conn);
+	switch (task->hdr->opcode & ISCSI_OPCODE_MASK) {
+	case ISCSI_OP_LOGIN:
+		qedi_send_iscsi_login(qedi_conn, task);
+		break;
+	case ISCSI_OP_NOOP_OUT:
+		data_len = qedi_conn->gen_pdu.req_buf_size;
+		buf = qedi_conn->gen_pdu.req_buf;
+		if (data_len)
+			rc = qedi_send_iscsi_nopout(qedi_conn, task,
+						    buf, data_len, 1);
+		else
+			rc = qedi_send_iscsi_nopout(qedi_conn, task,
+						    NULL, 0, 1);
+		break;
+	case ISCSI_OP_LOGOUT:
+		rc = qedi_send_iscsi_logout(qedi_conn, task);
+		break;
+	case ISCSI_OP_SCSI_TMFUNC:
+		rc = qedi_iscsi_abort_work(qedi_conn, task);
+		break;
+	case ISCSI_OP_TEXT:
+		rc = qedi_send_iscsi_text(qedi_conn, task);
+		break;
+	default:
+		iscsi_conn_printk(KERN_ALERT, qedi_conn->cls_conn->dd_data,
+				  "unsupported op 0x%x\n", task->hdr->opcode);
+	}
+
+	return rc;
+}
+
+static int qedi_mtask_xmit(struct iscsi_conn *conn, struct iscsi_task *task)
+{
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct qedi_cmd *cmd = task->dd_data;
+
+	memset(qedi_conn->gen_pdu.req_buf, 0, ISCSI_DEF_MAX_RECV_SEG_LEN);
+
+	qedi_conn->gen_pdu.req_buf_size = task->data_count;
+
+	if (task->data_count) {
+		memcpy(qedi_conn->gen_pdu.req_buf, task->data,
+		       task->data_count);
+		qedi_conn->gen_pdu.req_wr_ptr =
+			qedi_conn->gen_pdu.req_buf + task->data_count;
+	}
+
+	cmd->conn = conn->dd_data;
+	cmd->scsi_cmd = NULL;
+	return qedi_iscsi_send_generic_request(task);
+}
+
+static int qedi_task_xmit(struct iscsi_task *task)
+{
+	struct iscsi_conn *conn = task->conn;
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct qedi_cmd *cmd = task->dd_data;
+	struct scsi_cmnd *sc = task->sc;
+
+	cmd->state = 0;
+	cmd->task = NULL;
+	cmd->use_slowpath = false;
+	cmd->conn = qedi_conn;
+	cmd->task = task;
+	cmd->io_cmd_in_list = false;
+	INIT_LIST_HEAD(&cmd->io_cmd);
+
+	if (!sc)
+		return qedi_mtask_xmit(conn, task);
+
+	cmd->scsi_cmd = sc;
+	return qedi_iscsi_send_ioreq(task);
+}
+
+static struct iscsi_endpoint *
+qedi_ep_connect(struct Scsi_Host *shost, struct sockaddr *dst_addr,
+		int non_blocking)
+{
+	struct qedi_ctx *qedi;
+	struct iscsi_endpoint *ep;
+	struct qedi_endpoint *qedi_ep;
+	struct sockaddr_in *addr;
+	struct sockaddr_in6 *addr6;
+	struct qed_dev *cdev  =  NULL;
+	struct qedi_uio_dev *udev = NULL;
+	struct iscsi_path path_req;
+	u32 msg_type = ISCSI_KEVENT_IF_DOWN;
+	u32 iscsi_cid = QEDI_CID_RESERVED;
+	u16 len = 0;
+	char *buf = NULL;
+	int ret;
+
+	if (!shost) {
+		ret = -ENXIO;
+		QEDI_ERR(NULL, "shost is NULL\n");
+		return ERR_PTR(ret);
+	}
+
+	if (do_not_recover) {
+		ret = -ENOMEM;
+		return ERR_PTR(ret);
+	}
+
+	qedi = iscsi_host_priv(shost);
+	cdev = qedi->cdev;
+	udev = qedi->udev;
+
+	if (test_bit(QEDI_IN_OFFLINE, &qedi->flags) ||
+	    test_bit(QEDI_IN_RECOVERY, &qedi->flags)) {
+		ret = -ENOMEM;
+		return ERR_PTR(ret);
+	}
+
+	ep = iscsi_create_endpoint(sizeof(struct qedi_endpoint));
+	if (!ep) {
+		QEDI_ERR(&qedi->dbg_ctx, "endpoint create fail\n");
+		ret = -ENOMEM;
+		return ERR_PTR(ret);
+	}
+	qedi_ep = ep->dd_data;
+	memset(qedi_ep, 0, sizeof(struct qedi_endpoint));
+	qedi_ep->state = EP_STATE_IDLE;
+	qedi_ep->iscsi_cid = (u32)-1;
+	qedi_ep->qedi = qedi;
+
+	if (dst_addr->sa_family == AF_INET) {
+		addr = (struct sockaddr_in *)dst_addr;
+		memcpy(qedi_ep->dst_addr, &addr->sin_addr.s_addr,
+		       sizeof(struct in_addr));
+		qedi_ep->dst_port = ntohs(addr->sin_port);
+		qedi_ep->ip_type = TCP_IPV4;
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "dst_addr=%pI4, dst_port=%u\n",
+			  qedi_ep->dst_addr, qedi_ep->dst_port);
+	} else if (dst_addr->sa_family == AF_INET6) {
+		addr6 = (struct sockaddr_in6 *)dst_addr;
+		memcpy(qedi_ep->dst_addr, &addr6->sin6_addr,
+		       sizeof(struct in6_addr));
+		qedi_ep->dst_port = ntohs(addr6->sin6_port);
+		qedi_ep->ip_type = TCP_IPV6;
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "dst_addr=%pI6, dst_port=%u\n",
+			  qedi_ep->dst_addr, qedi_ep->dst_port);
+	} else {
+		QEDI_ERR(&qedi->dbg_ctx, "Invalid endpoint\n");
+	}
+
+	if (atomic_read(&qedi->link_state) != QEDI_LINK_UP) {
+		QEDI_WARN(&qedi->dbg_ctx, "qedi link down\n");
+		ret = -ENXIO;
+		goto ep_conn_exit;
+	}
+
+	ret = qedi_alloc_sq(qedi, qedi_ep);
+	if (ret)
+		goto ep_conn_exit;
+
+	ret = qedi_ops->acquire_conn(qedi->cdev, &qedi_ep->handle,
+				     &qedi_ep->fw_cid, &qedi_ep->p_doorbell);
+
+	if (ret) {
+		QEDI_ERR(&qedi->dbg_ctx, "Could not acquire connection\n");
+		ret = -ENXIO;
+		goto ep_free_sq;
+	}
+
+	iscsi_cid = qedi_ep->handle;
+	qedi_ep->iscsi_cid = iscsi_cid;
+
+	init_waitqueue_head(&qedi_ep->ofld_wait);
+	init_waitqueue_head(&qedi_ep->tcp_ofld_wait);
+	qedi_ep->state = EP_STATE_OFLDCONN_START;
+	qedi->ep_tbl[iscsi_cid] = qedi_ep;
+
+	buf = (char *)&path_req;
+	len = sizeof(path_req);
+	memset(&path_req, 0, len);
+
+	msg_type = ISCSI_KEVENT_PATH_REQ;
+	path_req.handle = (u64)qedi_ep->iscsi_cid;
+	path_req.pmtu = qedi->ll2_mtu;
+	qedi_ep->pmtu = qedi->ll2_mtu;
+	if (qedi_ep->ip_type == TCP_IPV4) {
+		memcpy(&path_req.dst.v4_addr, &qedi_ep->dst_addr,
+		       sizeof(struct in_addr));
+		path_req.ip_addr_len = 4;
+	} else {
+		memcpy(&path_req.dst.v6_addr, &qedi_ep->dst_addr,
+		       sizeof(struct in6_addr));
+		path_req.ip_addr_len = 16;
+	}
+
+	ret = iscsi_offload_mesg(shost, &qedi_iscsi_transport, msg_type, buf,
+				 len);
+	if (ret) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "iscsi_offload_mesg() failed for cid=0x%x ret=%d\n",
+			 iscsi_cid, ret);
+		goto ep_rel_conn;
+	}
+
+	atomic_inc(&qedi->num_offloads);
+	return ep;
+
+ep_rel_conn:
+	qedi->ep_tbl[iscsi_cid] = NULL;
+	ret = qedi_ops->release_conn(qedi->cdev, qedi_ep->handle);
+	if (ret)
+		QEDI_WARN(&qedi->dbg_ctx, "release_conn returned %d\n",
+			  ret);
+ep_free_sq:
+	qedi_free_sq(qedi, qedi_ep);
+ep_conn_exit:
+	iscsi_destroy_endpoint(ep);
+	return ERR_PTR(ret);
+}
+
+static int qedi_ep_poll(struct iscsi_endpoint *ep, int timeout_ms)
+{
+	struct qedi_endpoint *qedi_ep;
+	int ret = 0;
+
+	if (do_not_recover)
+		return 1;
+
+	qedi_ep = ep->dd_data;
+	if (qedi_ep->state == EP_STATE_IDLE ||
+	    qedi_ep->state == EP_STATE_OFLDCONN_FAILED)
+		return -1;
+
+	if (qedi_ep->state == EP_STATE_OFLDCONN_COMPL)
+		ret = 1;
+
+	ret = wait_event_interruptible_timeout(qedi_ep->ofld_wait,
+					       QEDI_OFLD_WAIT_STATE(qedi_ep),
+					       msecs_to_jiffies(timeout_ms));
+
+	if (qedi_ep->state == EP_STATE_OFLDCONN_FAILED)
+		ret = -1;
+
+	if (ret > 0)
+		return 1;
+	else if (!ret)
+		return 0;
+	else
+		return ret;
+}
+
+static void qedi_cleanup_active_cmd_list(struct qedi_conn *qedi_conn)
+{
+	struct qedi_cmd *cmd, *cmd_tmp;
+
+	list_for_each_entry_safe(cmd, cmd_tmp, &qedi_conn->active_cmd_list,
+				 io_cmd) {
+		list_del_init(&cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+	}
+}
+
+static void qedi_ep_disconnect(struct iscsi_endpoint *ep)
+{
+	struct qedi_endpoint *qedi_ep;
+	struct qedi_conn *qedi_conn = NULL;
+	struct iscsi_conn *conn = NULL;
+	struct qedi_ctx *qedi;
+	int ret = 0;
+	int wait_delay = 20 * HZ;
+	int abrt_conn = 0;
+	int count = 10;
+
+	qedi_ep = ep->dd_data;
+	qedi = qedi_ep->qedi;
+
+	flush_work(&qedi_ep->offload_work);
+
+	if (qedi_ep->conn) {
+		qedi_conn = qedi_ep->conn;
+		conn = qedi_conn->cls_conn->dd_data;
+		iscsi_suspend_queue(conn);
+		abrt_conn = qedi_conn->abrt_conn;
+
+		while (count--)	{
+			if (!test_bit(QEDI_CONN_FW_CLEANUP,
+				      &qedi_conn->flags)) {
+				break;
+			}
+			msleep(1000);
+		}
+
+		if (test_bit(QEDI_IN_RECOVERY, &qedi->flags)) {
+			if (do_not_recover) {
+				QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+					  "Do not recover cid=0x%x\n",
+					  qedi_ep->iscsi_cid);
+				goto ep_exit_recover;
+			}
+			QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+				  "Reset recovery cid=0x%x, qedi_ep=%p, state=0x%x\n",
+				  qedi_ep->iscsi_cid, qedi_ep, qedi_ep->state);
+			qedi_cleanup_active_cmd_list(qedi_conn);
+			goto ep_release_conn;
+		}
+	}
+
+	if (do_not_recover)
+		goto ep_exit_recover;
+
+	switch (qedi_ep->state) {
+	case EP_STATE_OFLDCONN_START:
+		goto ep_release_conn;
+	case EP_STATE_OFLDCONN_FAILED:
+			break;
+	case EP_STATE_OFLDCONN_COMPL:
+		if (unlikely(!qedi_conn))
+			break;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "Active cmd count=%d, abrt_conn=%d, ep state=0x%x, cid=0x%x, qedi_conn=%p\n",
+			  qedi_conn->active_cmd_count, abrt_conn,
+			  qedi_ep->state,
+			  qedi_ep->iscsi_cid,
+			  qedi_ep->conn
+			  );
+
+		if (!qedi_conn->active_cmd_count)
+			abrt_conn = 0;
+		else
+			abrt_conn = 1;
+
+		if (abrt_conn)
+			qedi_clearsq(qedi, qedi_conn, NULL);
+		break;
+	default:
+		break;
+	}
+
+	qedi_ep->state = EP_STATE_DISCONN_START;
+	ret = qedi_ops->destroy_conn(qedi->cdev, qedi_ep->handle, abrt_conn);
+	if (ret) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "destroy_conn failed returned %d\n", ret);
+	} else {
+		ret = wait_event_interruptible_timeout(
+					qedi_ep->tcp_ofld_wait,
+					(qedi_ep->state !=
+					 EP_STATE_DISCONN_START),
+					wait_delay);
+		if ((ret <= 0) || (qedi_ep->state == EP_STATE_DISCONN_START)) {
+			QEDI_WARN(&qedi->dbg_ctx,
+				  "Destroy conn timedout or interrupted, ret=%d, delay=%d, cid=0x%x\n",
+				  ret, wait_delay, qedi_ep->iscsi_cid);
+		}
+	}
+
+ep_release_conn:
+	ret = qedi_ops->release_conn(qedi->cdev, qedi_ep->handle);
+	if (ret)
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "release_conn returned %d, cid=0x%x\n",
+			  ret, qedi_ep->iscsi_cid);
+ep_exit_recover:
+	qedi_ep->state = EP_STATE_IDLE;
+	qedi->ep_tbl[qedi_ep->iscsi_cid] = NULL;
+	qedi->cid_que.conn_cid_tbl[qedi_ep->iscsi_cid] = NULL;
+	qedi_free_id(&qedi->lcl_port_tbl, qedi_ep->src_port);
+	qedi_free_sq(qedi, qedi_ep);
+
+	if (qedi_conn)
+		qedi_conn->ep = NULL;
+
+	qedi_ep->conn = NULL;
+	qedi_ep->qedi = NULL;
+	atomic_dec(&qedi->num_offloads);
+
+	iscsi_destroy_endpoint(ep);
+}
+
+static int qedi_data_avail(struct qedi_ctx *qedi, u16 vlanid)
+{
+	struct qed_dev *cdev = qedi->cdev;
+	struct qedi_uio_dev *udev;
+	struct qedi_uio_ctrl *uctrl;
+	struct sk_buff *skb;
+	u32 len;
+	int rc = 0;
+
+	udev = qedi->udev;
+	if (!udev) {
+		QEDI_ERR(&qedi->dbg_ctx, "udev is NULL.\n");
+		return -EINVAL;
+	}
+
+	uctrl = (struct qedi_uio_ctrl *)udev->uctrl;
+	if (!uctrl) {
+		QEDI_ERR(&qedi->dbg_ctx, "uctlr is NULL.\n");
+		return -EINVAL;
+	}
+
+	len = uctrl->host_tx_pkt_len;
+	if (!len) {
+		QEDI_ERR(&qedi->dbg_ctx, "Invalid len %u\n", len);
+		return -EINVAL;
+	}
+
+	skb = alloc_skb(len, GFP_ATOMIC);
+	if (!skb) {
+		QEDI_ERR(&qedi->dbg_ctx, "alloc_skb failed\n");
+		return -EINVAL;
+	}
+
+	skb_put(skb, len);
+	memcpy(skb->data, udev->tx_pkt, len);
+	skb->ip_summed = CHECKSUM_NONE;
+
+	if (vlanid)
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlanid);
+
+	rc = qedi_ops->ll2->start_xmit(cdev, skb);
+	if (rc) {
+		QEDI_ERR(&qedi->dbg_ctx, "ll2 start_xmit returned %d\n",
+			 rc);
+		kfree_skb(skb);
+	}
+
+	uctrl->host_tx_pkt_len = 0;
+	uctrl->hw_tx_cons++;
+
+	return rc;
+}
+
+static void qedi_offload_work(struct work_struct *work)
+{
+	struct qedi_endpoint *qedi_ep =
+		container_of(work, struct qedi_endpoint, offload_work);
+	struct qedi_ctx *qedi;
+	int wait_delay = 20 * HZ;
+	int ret;
+
+	qedi = qedi_ep->qedi;
+
+	ret = qedi_iscsi_offload_conn(qedi_ep);
+	if (ret) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "offload error: iscsi_cid=%u, qedi_ep=%p, ret=%d\n",
+			 qedi_ep->iscsi_cid, qedi_ep, ret);
+		qedi_ep->state = EP_STATE_OFLDCONN_FAILED;
+		return;
+	}
+
+	ret = wait_event_interruptible_timeout(qedi_ep->tcp_ofld_wait,
+					       (qedi_ep->state ==
+					       EP_STATE_OFLDCONN_COMPL),
+					       wait_delay);
+	if ((ret <= 0) || (qedi_ep->state != EP_STATE_OFLDCONN_COMPL)) {
+		qedi_ep->state = EP_STATE_OFLDCONN_FAILED;
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Offload conn TIMEOUT iscsi_cid=%u, qedi_ep=%p\n",
+			 qedi_ep->iscsi_cid, qedi_ep);
+	}
+}
+
+static int qedi_set_path(struct Scsi_Host *shost, struct iscsi_path *path_data)
+{
+	struct qedi_ctx *qedi;
+	struct qedi_endpoint *qedi_ep;
+	int ret = 0;
+	u32 iscsi_cid;
+	u16 port_id = 0;
+
+	if (!shost) {
+		ret = -ENXIO;
+		QEDI_ERR(NULL, "shost is NULL\n");
+		return ret;
+	}
+
+	if (strcmp(shost->hostt->proc_name, "qedi")) {
+		ret = -ENXIO;
+		QEDI_ERR(NULL, "shost %s is invalid\n",
+			 shost->hostt->proc_name);
+		return ret;
+	}
+
+	qedi = iscsi_host_priv(shost);
+	if (path_data->handle == QEDI_PATH_HANDLE) {
+		ret = qedi_data_avail(qedi, path_data->vlan_id);
+		goto set_path_exit;
+	}
+
+	iscsi_cid = (u32)path_data->handle;
+	qedi_ep = qedi->ep_tbl[iscsi_cid];
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "iscsi_cid=0x%x, qedi_ep=%p\n", iscsi_cid, qedi_ep);
+
+	if (!is_valid_ether_addr(&path_data->mac_addr[0])) {
+		QEDI_NOTICE(&qedi->dbg_ctx, "dst mac NOT VALID\n");
+		ret = -EIO;
+		goto set_path_exit;
+	}
+
+	ether_addr_copy(&qedi_ep->src_mac[0], &qedi->mac[0]);
+	ether_addr_copy(&qedi_ep->dst_mac[0], &path_data->mac_addr[0]);
+
+	qedi_ep->vlan_id = path_data->vlan_id;
+	if (path_data->pmtu < DEF_PATH_MTU) {
+		qedi_ep->pmtu = qedi->ll2_mtu;
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "MTU cannot be %u, using default MTU %u\n",
+			   path_data->pmtu, qedi_ep->pmtu);
+	}
+
+	if (path_data->pmtu != qedi->ll2_mtu) {
+		if (path_data->pmtu > JUMBO_MTU) {
+			ret = -EINVAL;
+			QEDI_ERR(NULL, "Invalid MTU %u\n", path_data->pmtu);
+			goto set_path_exit;
+		}
+
+		qedi_reset_host_mtu(qedi, path_data->pmtu);
+		qedi_ep->pmtu = qedi->ll2_mtu;
+	}
+
+	port_id = qedi_ep->src_port;
+	if (port_id >= QEDI_LOCAL_PORT_MIN &&
+	    port_id < QEDI_LOCAL_PORT_MAX) {
+		if (qedi_alloc_id(&qedi->lcl_port_tbl, port_id))
+			port_id = 0;
+	} else {
+		port_id = 0;
+	}
+
+	if (!port_id) {
+		port_id = qedi_alloc_new_id(&qedi->lcl_port_tbl);
+		if (port_id == QEDI_LOCAL_PORT_INVALID) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Failed to allocate port id for iscsi_cid=0x%x\n",
+				 iscsi_cid);
+			ret = -ENOMEM;
+			goto set_path_exit;
+		}
+	}
+
+	qedi_ep->src_port = port_id;
+
+	if (qedi_ep->ip_type == TCP_IPV4) {
+		memcpy(&qedi_ep->src_addr[0], &path_data->src.v4_addr,
+		       sizeof(struct in_addr));
+		memcpy(&qedi->src_ip[0], &path_data->src.v4_addr,
+		       sizeof(struct in_addr));
+		qedi->ip_type = TCP_IPV4;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "src addr:port=%pI4:%u, dst addr:port=%pI4:%u\n",
+			  qedi_ep->src_addr, qedi_ep->src_port,
+			  qedi_ep->dst_addr, qedi_ep->dst_port);
+	} else {
+		memcpy(&qedi_ep->src_addr[0], &path_data->src.v6_addr,
+		       sizeof(struct in6_addr));
+		memcpy(&qedi->src_ip[0], &path_data->src.v6_addr,
+		       sizeof(struct in6_addr));
+		qedi->ip_type = TCP_IPV6;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "src addr:port=%pI6:%u, dst addr:port=%pI6:%u\n",
+			  qedi_ep->src_addr, qedi_ep->src_port,
+			  qedi_ep->dst_addr, qedi_ep->dst_port);
+	}
+
+	INIT_WORK(&qedi_ep->offload_work, qedi_offload_work);
+	queue_work(qedi->offload_thread, &qedi_ep->offload_work);
+
+	ret = 0;
+
+set_path_exit:
+	return ret;
+}
+
+static umode_t qedi_attr_is_visible(int param_type, int param)
+{
+	switch (param_type) {
+	case ISCSI_HOST_PARAM:
+		switch (param) {
+		case ISCSI_HOST_PARAM_NETDEV_NAME:
+		case ISCSI_HOST_PARAM_HWADDRESS:
+		case ISCSI_HOST_PARAM_IPADDRESS:
+			return 0444;
+		default:
+			return 0;
+		}
+	case ISCSI_PARAM:
+		switch (param) {
+		case ISCSI_PARAM_MAX_RECV_DLENGTH:
+		case ISCSI_PARAM_MAX_XMIT_DLENGTH:
+		case ISCSI_PARAM_HDRDGST_EN:
+		case ISCSI_PARAM_DATADGST_EN:
+		case ISCSI_PARAM_CONN_ADDRESS:
+		case ISCSI_PARAM_CONN_PORT:
+		case ISCSI_PARAM_EXP_STATSN:
+		case ISCSI_PARAM_PERSISTENT_ADDRESS:
+		case ISCSI_PARAM_PERSISTENT_PORT:
+		case ISCSI_PARAM_PING_TMO:
+		case ISCSI_PARAM_RECV_TMO:
+		case ISCSI_PARAM_INITIAL_R2T_EN:
+		case ISCSI_PARAM_MAX_R2T:
+		case ISCSI_PARAM_IMM_DATA_EN:
+		case ISCSI_PARAM_FIRST_BURST:
+		case ISCSI_PARAM_MAX_BURST:
+		case ISCSI_PARAM_PDU_INORDER_EN:
+		case ISCSI_PARAM_DATASEQ_INORDER_EN:
+		case ISCSI_PARAM_ERL:
+		case ISCSI_PARAM_TARGET_NAME:
+		case ISCSI_PARAM_TPGT:
+		case ISCSI_PARAM_USERNAME:
+		case ISCSI_PARAM_PASSWORD:
+		case ISCSI_PARAM_USERNAME_IN:
+		case ISCSI_PARAM_PASSWORD_IN:
+		case ISCSI_PARAM_FAST_ABORT:
+		case ISCSI_PARAM_ABORT_TMO:
+		case ISCSI_PARAM_LU_RESET_TMO:
+		case ISCSI_PARAM_TGT_RESET_TMO:
+		case ISCSI_PARAM_IFACE_NAME:
+		case ISCSI_PARAM_INITIATOR_NAME:
+		case ISCSI_PARAM_BOOT_ROOT:
+		case ISCSI_PARAM_BOOT_NIC:
+		case ISCSI_PARAM_BOOT_TARGET:
+			return 0444;
+		default:
+			return 0;
+		}
+	}
+
+	return 0;
+}
+
+static void qedi_cleanup_task(struct iscsi_task *task)
+{
+	if (!task->sc || task->state == ISCSI_TASK_PENDING) {
+		QEDI_INFO(NULL, QEDI_LOG_IO, "Returning ref_cnt=%d\n",
+			  atomic_read(&task->refcount));
+		return;
+	}
+
+	qedi_iscsi_unmap_sg_list(task->dd_data);
+}
+
+struct iscsi_transport qedi_iscsi_transport = {
+	.owner = THIS_MODULE,
+	.name = QEDI_MODULE_NAME,
+	.caps = CAP_RECOVERY_L0 | CAP_HDRDGST | CAP_MULTI_R2T | CAP_DATADGST |
+		CAP_DATA_PATH_OFFLOAD | CAP_TEXT_NEGO,
+	.create_session = qedi_session_create,
+	.destroy_session = qedi_session_destroy,
+	.create_conn = qedi_conn_create,
+	.bind_conn = qedi_conn_bind,
+	.start_conn = qedi_conn_start,
+	.stop_conn = iscsi_conn_stop,
+	.destroy_conn = qedi_conn_destroy,
+	.set_param = iscsi_set_param,
+	.get_ep_param = qedi_ep_get_param,
+	.get_conn_param = iscsi_conn_get_param,
+	.get_session_param = iscsi_session_get_param,
+	.get_host_param = qedi_host_get_param,
+	.send_pdu = iscsi_conn_send_pdu,
+	.get_stats = qedi_conn_get_stats,
+	.xmit_task = qedi_task_xmit,
+	.cleanup_task = qedi_cleanup_task,
+	.session_recovery_timedout = iscsi_session_recovery_timedout,
+	.ep_connect = qedi_ep_connect,
+	.ep_poll = qedi_ep_poll,
+	.ep_disconnect = qedi_ep_disconnect,
+	.set_path = qedi_set_path,
+	.attr_is_visible = qedi_attr_is_visible,
+};
+
+void qedi_start_conn_recovery(struct qedi_ctx *qedi,
+			      struct qedi_conn *qedi_conn)
+{
+	struct iscsi_cls_session *cls_sess;
+	struct iscsi_cls_conn *cls_conn;
+	struct iscsi_conn *conn;
+
+	cls_conn = qedi_conn->cls_conn;
+	conn = cls_conn->dd_data;
+	cls_sess = iscsi_conn_to_session(cls_conn);
+
+	if (iscsi_is_session_online(cls_sess)) {
+		qedi_conn->abrt_conn = 1;
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Failing connection, state=0x%x, cid=0x%x\n",
+			 conn->session->state, qedi_conn->iscsi_conn_id);
+		iscsi_conn_failure(qedi_conn->cls_conn->dd_data,
+				   ISCSI_ERR_CONN_FAILED);
+	}
+}
+
+static const struct {
+	enum iscsi_error_types error_code;
+	char *err_string;
+} qedi_iscsi_error[] = {
+	{ ISCSI_STATUS_NONE,
+	  "tcp_error none"
+	},
+	{ ISCSI_CONN_ERROR_TASK_CID_MISMATCH,
+	  "task cid mismatch"
+	},
+	{ ISCSI_CONN_ERROR_TASK_NOT_VALID,
+	  "invalid task"
+	},
+	{ ISCSI_CONN_ERROR_RQ_RING_IS_FULL,
+	  "rq ring full"
+	},
+	{ ISCSI_CONN_ERROR_CMDQ_RING_IS_FULL,
+	  "cmdq ring full"
+	},
+	{ ISCSI_CONN_ERROR_HQE_CACHING_FAILED,
+	  "sge caching failed"
+	},
+	{ ISCSI_CONN_ERROR_HEADER_DIGEST_ERROR,
+	  "hdr digest error"
+	},
+	{ ISCSI_CONN_ERROR_LOCAL_COMPLETION_ERROR,
+	  "local cmpl error"
+	},
+	{ ISCSI_CONN_ERROR_DATA_OVERRUN,
+	  "invalid task"
+	},
+	{ ISCSI_CONN_ERROR_OUT_OF_SGES_ERROR,
+	  "out of sge error"
+	},
+	{ ISCSI_CONN_ERROR_TCP_SEG_PROC_IP_OPTIONS_ERROR,
+	  "tcp seg ip options error"
+	},
+	{ ISCSI_CONN_ERROR_TCP_IP_FRAGMENT_ERROR,
+	  "tcp ip fragment error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_AHS_LEN,
+	  "AHS len protocol error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_ITT_OUT_OF_RANGE,
+	  "itt out of range error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DATA_SEG_LEN_EXCEEDS_PDU_SIZE,
+	  "data seg more than pdu size"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_INVALID_OPCODE,
+	  "invalid opcode"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_INVALID_OPCODE_BEFORE_UPDATE,
+	  "invalid opcode before update"
+	},
+	{ ISCSI_CONN_ERROR_UNVALID_NOPIN_DSL,
+	  "unexpected opcode"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_R2T_CARRIES_NO_DATA,
+	  "r2t carries no data"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DATA_SN,
+	  "data sn error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DATA_IN_TTT,
+	  "data TTT error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_R2T_TTT,
+	  "r2t TTT error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_R2T_BUFFER_OFFSET,
+	  "buffer offset error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_BUFFER_OFFSET_OOO,
+	  "buffer offset ooo"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_R2T_SN,
+	  "data seg len 0"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DESIRED_DATA_TRNS_LEN_0,
+	  "data xer len error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DESIRED_DATA_TRNS_LEN_1,
+	  "data xer len1 error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DESIRED_DATA_TRNS_LEN_2,
+	  "data xer len2 error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_LUN,
+	  "protocol lun error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_F_BIT_ZERO,
+	  "f bit zero error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_EXP_STAT_SN,
+	  "exp stat sn error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DSL_NOT_ZERO,
+	  "dsl not zero error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_INVALID_DSL,
+	  "invalid dsl"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DATA_SEG_LEN_TOO_BIG,
+	  "data seg len too big"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_OUTSTANDING_R2T_COUNT,
+	  "outstanding r2t count error"
+	},
+	{ ISCSI_CONN_ERROR_SENSE_DATA_LENGTH,
+	  "sense datalen error"
+	},
+};
+
+char *qedi_get_iscsi_error(enum iscsi_error_types err_code)
+{
+	int i;
+	char *msg = NULL;
+
+	for (i = 0; i < ARRAY_SIZE(qedi_iscsi_error); i++) {
+		if (qedi_iscsi_error[i].error_code == err_code) {
+			msg = qedi_iscsi_error[i].err_string;
+			break;
+		}
+	}
+	return msg;
+}
+
+void qedi_process_iscsi_error(struct qedi_endpoint *ep, struct async_data *data)
+{
+	struct qedi_conn *qedi_conn;
+	struct qedi_ctx *qedi;
+	char warn_notice[] = "iscsi_warning";
+	char error_notice[] = "iscsi_error";
+	char unknown_msg[] = "Unknown error";
+	char *message;
+	int need_recovery = 0;
+	u32 err_mask = 0;
+	char *msg;
+
+	if (!ep)
+		return;
+
+	qedi_conn = ep->conn;
+	if (!qedi_conn)
+		return;
+
+	qedi = ep->qedi;
+
+	QEDI_ERR(&qedi->dbg_ctx, "async event iscsi error:0x%x\n",
+		 data->error_code);
+
+	if (err_mask) {
+		need_recovery = 0;
+		message = warn_notice;
+	} else {
+		need_recovery = 1;
+		message = error_notice;
+	}
+
+	msg = qedi_get_iscsi_error(data->error_code);
+	if (!msg) {
+		need_recovery = 0;
+		msg = unknown_msg;
+	}
+
+	iscsi_conn_printk(KERN_ALERT,
+			  qedi_conn->cls_conn->dd_data,
+			  "qedi: %s - %s\n", message, msg);
+
+	if (need_recovery)
+		qedi_start_conn_recovery(qedi_conn->qedi, qedi_conn);
+}
+
+void qedi_process_tcp_error(struct qedi_endpoint *ep, struct async_data *data)
+{
+	struct qedi_conn *qedi_conn;
+
+	if (!ep)
+		return;
+
+	qedi_conn = ep->conn;
+	if (!qedi_conn)
+		return;
+
+	QEDI_ERR(&ep->qedi->dbg_ctx, "async event TCP error:0x%x\n",
+		 data->error_code);
+
+	qedi_start_conn_recovery(qedi_conn->qedi, qedi_conn);
+}
diff --git a/drivers/scsi/qedi/qedi_iscsi.h b/drivers/scsi/qedi/qedi_iscsi.h
new file mode 100644
index 000000000000..d3c06bbddb4e
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_iscsi.h
@@ -0,0 +1,232 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#ifndef _QEDI_ISCSI_H_
+#define _QEDI_ISCSI_H_
+
+#include <linux/socket.h>
+#include <linux/completion.h>
+#include "qedi.h"
+
+#define ISCSI_MAX_SESS_PER_HBA	4096
+
+#define DEF_KA_TIMEOUT		7200000
+#define DEF_KA_INTERVAL		10000
+#define DEF_KA_MAX_PROBE_COUNT	10
+#define DEF_TOS			0
+#define DEF_TTL			0xfe
+#define DEF_SND_SEQ_SCALE	0
+#define DEF_RCV_BUF		0xffff
+#define DEF_SND_BUF		0xffff
+#define DEF_SEED		0
+#define DEF_MAX_RT_TIME		8000
+#define DEF_MAX_DA_COUNT        2
+#define DEF_SWS_TIMER		1000
+#define DEF_MAX_CWND		2
+#define DEF_PATH_MTU		1500
+#define DEF_MSS			1460
+#define DEF_LL2_MTU		1560
+#define JUMBO_MTU		9000
+
+#define MIN_MTU         576 /* rfc 793 */
+#define IPV4_HDR_LEN    20
+#define IPV6_HDR_LEN    40
+#define TCP_HDR_LEN     20
+#define TCP_OPTION_LEN  12
+#define VLAN_LEN         4
+
+enum {
+	EP_STATE_IDLE                   = 0x0,
+	EP_STATE_ACQRCONN_START         = 0x1,
+	EP_STATE_ACQRCONN_COMPL         = 0x2,
+	EP_STATE_OFLDCONN_START         = 0x4,
+	EP_STATE_OFLDCONN_COMPL         = 0x8,
+	EP_STATE_DISCONN_START          = 0x10,
+	EP_STATE_DISCONN_COMPL          = 0x20,
+	EP_STATE_CLEANUP_START          = 0x40,
+	EP_STATE_CLEANUP_CMPL           = 0x80,
+	EP_STATE_TCP_FIN_RCVD           = 0x100,
+	EP_STATE_TCP_RST_RCVD           = 0x200,
+	EP_STATE_LOGOUT_SENT            = 0x400,
+	EP_STATE_LOGOUT_RESP_RCVD       = 0x800,
+	EP_STATE_CLEANUP_FAILED         = 0x1000,
+	EP_STATE_OFLDCONN_FAILED        = 0x2000,
+	EP_STATE_CONNECT_FAILED         = 0x4000,
+	EP_STATE_DISCONN_TIMEDOUT       = 0x8000,
+};
+
+struct qedi_conn;
+
+struct qedi_endpoint {
+	struct qedi_ctx *qedi;
+	u32 dst_addr[4];
+	u32 src_addr[4];
+	u16 src_port;
+	u16 dst_port;
+	u16 vlan_id;
+	u16 pmtu;
+	u8 src_mac[ETH_ALEN];
+	u8 dst_mac[ETH_ALEN];
+	u8 ip_type;
+	int state;
+	wait_queue_head_t ofld_wait;
+	wait_queue_head_t tcp_ofld_wait;
+	u32 iscsi_cid;
+	/* identifier of the connection from qed */
+	u32 handle;
+	u32 fw_cid;
+	void __iomem *p_doorbell;
+
+	/* Send queue management */
+	struct iscsi_wqe *sq;
+	dma_addr_t sq_dma;
+
+	u16 sq_prod_idx;
+	u16 fw_sq_prod_idx;
+	u16 sq_con_idx;
+	u32 sq_mem_size;
+
+	void *sq_pbl;
+	dma_addr_t sq_pbl_dma;
+	u32 sq_pbl_size;
+	struct qedi_conn *conn;
+	struct work_struct offload_work;
+};
+
+#define QEDI_SQ_WQES_MIN	16
+
+struct qedi_io_bdt {
+	struct iscsi_sge *sge_tbl;
+	dma_addr_t sge_tbl_dma;
+	u16 sge_valid;
+};
+
+/**
+ * struct generic_pdu_resc - login pdu resource structure
+ *
+ * @req_buf:            driver buffer used to stage payload associated with
+ *                      the login request
+ * @req_dma_addr:       dma address for iscsi login request payload buffer
+ * @req_buf_size:       actual login request payload length
+ * @req_wr_ptr:         pointer into login request buffer when next data is
+ *                      to be written
+ * @resp_hdr:           iscsi header where iscsi login response header is to
+ *                      be recreated
+ * @resp_buf:           buffer to stage login response payload
+ * @resp_dma_addr:      login response payload buffer dma address
+ * @resp_buf_size:      login response paylod length
+ * @resp_wr_ptr:        pointer into login response buffer when next data is
+ *                      to be written
+ * @req_bd_tbl:         iscsi login request payload BD table
+ * @req_bd_dma:         login request BD table dma address
+ * @resp_bd_tbl:        iscsi login response payload BD table
+ * @resp_bd_dma:        login request BD table dma address
+ *
+ * following structure defines buffer info for generic pdus such as iSCSI Login,
+ *      Logout and NOP
+ */
+struct generic_pdu_resc {
+	char *req_buf;
+	dma_addr_t req_dma_addr;
+	u32 req_buf_size;
+	char *req_wr_ptr;
+	struct iscsi_hdr resp_hdr;
+	char *resp_buf;
+	dma_addr_t resp_dma_addr;
+	u32 resp_buf_size;
+	char *resp_wr_ptr;
+	char *req_bd_tbl;
+	dma_addr_t req_bd_dma;
+	char *resp_bd_tbl;
+	dma_addr_t resp_bd_dma;
+};
+
+struct qedi_conn {
+	struct iscsi_cls_conn *cls_conn;
+	struct qedi_ctx *qedi;
+	struct qedi_endpoint *ep;
+	struct list_head active_cmd_list;
+	spinlock_t list_lock;		/* internal conn lock */
+	u32 active_cmd_count;
+	u32 cmd_cleanup_req;
+	u32 cmd_cleanup_cmpl;
+
+	u32 iscsi_conn_id;
+	int itt;
+	int abrt_conn;
+#define QEDI_CID_RESERVED	0x5AFF
+	u32 fw_cid;
+	/*
+	 * Buffer for login negotiation process
+	 */
+	struct generic_pdu_resc gen_pdu;
+
+	struct list_head tmf_work_list;
+	wait_queue_head_t wait_queue;
+	spinlock_t tmf_work_lock;	/* tmf work lock */
+	unsigned long flags;
+#define QEDI_CONN_FW_CLEANUP	1
+};
+
+struct qedi_cmd {
+	struct list_head io_cmd;
+	bool io_cmd_in_list;
+	struct iscsi_hdr hdr;
+	struct qedi_conn *conn;
+	struct scsi_cmnd *scsi_cmd;
+	struct scatterlist *sg;
+	struct qedi_io_bdt io_tbl;
+	struct iscsi_task_context request;
+	unsigned char *sense_buffer;
+	dma_addr_t sense_buffer_dma;
+	u16 task_id;
+
+	/* field populated for tmf work queue */
+	struct iscsi_task *task;
+	struct work_struct tmf_work;
+	int state;
+#define CLEANUP_WAIT	1
+#define CLEANUP_RECV	2
+#define CLEANUP_WAIT_FAILED	3
+#define CLEANUP_NOT_REQUIRED	4
+#define LUN_RESET_RESPONSE_RECEIVED	5
+#define RESPONSE_RECEIVED	6
+
+	int type;
+#define TYPEIO		1
+#define TYPERESET	2
+
+	struct qedi_work_map *list_tmf_work;
+	/* slowpath management */
+	bool use_slowpath;
+
+	struct iscsi_tm_rsp *tmf_resp_buf;
+	struct qedi_work cqe_work;
+};
+
+struct qedi_work_map {
+	struct list_head list;
+	struct qedi_cmd *qedi_cmd;
+	int rtid;
+
+	int state;
+#define QEDI_WORK_QUEUED	1
+#define QEDI_WORK_SCHEDULED	2
+#define QEDI_WORK_EXIT		3
+
+	struct work_struct *ptr_tmf_work;
+};
+
+#define qedi_set_itt(task_id, itt) ((u32)(((task_id) & 0xffff) | ((itt) << 16)))
+#define qedi_get_itt(cqe) (cqe.iscsi_hdr.cmd.itt >> 16)
+
+#define QEDI_OFLD_WAIT_STATE(q) ((q)->state == EP_STATE_OFLDCONN_FAILED || \
+				(q)->state == EP_STATE_OFLDCONN_COMPL)
+
+#endif /* _QEDI_ISCSI_H_ */
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
new file mode 100644
index 000000000000..5eda21d903e9
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -0,0 +1,2095 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/if_arp.h>
+#include <scsi/iscsi_if.h>
+#include <linux/inet.h>
+#include <net/arp.h>
+#include <linux/list.h>
+#include <linux/kthread.h>
+#include <linux/mm.h>
+#include <linux/if_vlan.h>
+#include <linux/cpu.h>
+
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_device.h>
+#include <scsi/scsi_eh.h>
+#include <scsi/scsi_host.h>
+#include <scsi/scsi.h>
+
+#include "qedi.h"
+#include "qedi_gbl.h"
+#include "qedi_iscsi.h"
+
+static uint qedi_fw_debug;
+module_param(qedi_fw_debug, uint, 0644);
+MODULE_PARM_DESC(qedi_fw_debug, " Firmware debug level 0(default) to 3");
+
+uint qedi_dbg_log = QEDI_LOG_WARN | QEDI_LOG_SCSI_TM;
+module_param(qedi_dbg_log, uint, 0644);
+MODULE_PARM_DESC(qedi_dbg_log, " Default debug level");
+
+uint qedi_io_tracing;
+module_param(qedi_io_tracing, uint, 0644);
+MODULE_PARM_DESC(qedi_io_tracing,
+		 " Enable logging of SCSI requests/completions into trace buffer. (default off).");
+
+const struct qed_iscsi_ops *qedi_ops;
+static struct scsi_transport_template *qedi_scsi_transport;
+static struct pci_driver qedi_pci_driver;
+static DEFINE_PER_CPU(struct qedi_percpu_s, qedi_percpu);
+static LIST_HEAD(qedi_udev_list);
+/* Static function declaration */
+static int qedi_alloc_global_queues(struct qedi_ctx *qedi);
+static void qedi_free_global_queues(struct qedi_ctx *qedi);
+static struct qedi_cmd *qedi_get_cmd_from_tid(struct qedi_ctx *qedi, u32 tid);
+static void qedi_reset_uio_rings(struct qedi_uio_dev *udev);
+static void qedi_ll2_free_skbs(struct qedi_ctx *qedi);
+
+static int qedi_iscsi_event_cb(void *context, u8 fw_event_code, void *fw_handle)
+{
+	struct qedi_ctx *qedi;
+	struct qedi_endpoint *qedi_ep;
+	struct async_data *data;
+	int rval = 0;
+
+	if (!context || !fw_handle) {
+		QEDI_ERR(NULL, "Recv event with ctx NULL\n");
+		return -EINVAL;
+	}
+
+	qedi = (struct qedi_ctx *)context;
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+		  "Recv Event %d fw_handle %p\n", fw_event_code, fw_handle);
+
+	data = (struct async_data *)fw_handle;
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+		  "cid=0x%x tid=0x%x err-code=0x%x fw-dbg-param=0x%x\n",
+		   data->cid, data->itid, data->error_code,
+		   data->fw_debug_param);
+
+	qedi_ep = qedi->ep_tbl[data->cid];
+
+	if (!qedi_ep) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Cannot process event, ep already disconnected, cid=0x%x\n",
+			   data->cid);
+		WARN_ON(1);
+		return -ENODEV;
+	}
+
+	switch (fw_event_code) {
+	case ISCSI_EVENT_TYPE_ASYN_CONNECT_COMPLETE:
+		if (qedi_ep->state == EP_STATE_OFLDCONN_START)
+			qedi_ep->state = EP_STATE_OFLDCONN_COMPL;
+
+		wake_up_interruptible(&qedi_ep->tcp_ofld_wait);
+		break;
+	case ISCSI_EVENT_TYPE_ASYN_TERMINATE_DONE:
+		qedi_ep->state = EP_STATE_DISCONN_COMPL;
+		wake_up_interruptible(&qedi_ep->tcp_ofld_wait);
+		break;
+	case ISCSI_EVENT_TYPE_ISCSI_CONN_ERROR:
+		qedi_process_iscsi_error(qedi_ep, data);
+		break;
+	case ISCSI_EVENT_TYPE_ASYN_ABORT_RCVD:
+	case ISCSI_EVENT_TYPE_ASYN_SYN_RCVD:
+	case ISCSI_EVENT_TYPE_ASYN_MAX_RT_TIME:
+	case ISCSI_EVENT_TYPE_ASYN_MAX_RT_CNT:
+	case ISCSI_EVENT_TYPE_ASYN_MAX_KA_PROBES_CNT:
+	case ISCSI_EVENT_TYPE_ASYN_FIN_WAIT2:
+	case ISCSI_EVENT_TYPE_TCP_CONN_ERROR:
+		qedi_process_tcp_error(qedi_ep, data);
+		break;
+	default:
+		QEDI_ERR(&qedi->dbg_ctx, "Recv Unknown Event %u\n",
+			 fw_event_code);
+	}
+
+	return rval;
+}
+
+static int qedi_uio_open(struct uio_info *uinfo, struct inode *inode)
+{
+	struct qedi_uio_dev *udev = uinfo->priv;
+	struct qedi_ctx *qedi = udev->qedi;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (udev->uio_dev != -1)
+		return -EBUSY;
+
+	rtnl_lock();
+	udev->uio_dev = iminor(inode);
+	qedi_reset_uio_rings(udev);
+	set_bit(UIO_DEV_OPENED, &qedi->flags);
+	rtnl_unlock();
+
+	return 0;
+}
+
+static int qedi_uio_close(struct uio_info *uinfo, struct inode *inode)
+{
+	struct qedi_uio_dev *udev = uinfo->priv;
+	struct qedi_ctx *qedi = udev->qedi;
+
+	udev->uio_dev = -1;
+	clear_bit(UIO_DEV_OPENED, &qedi->flags);
+	qedi_ll2_free_skbs(qedi);
+	return 0;
+}
+
+static void __qedi_free_uio_rings(struct qedi_uio_dev *udev)
+{
+	if (udev->ll2_ring) {
+		free_page((unsigned long)udev->ll2_ring);
+		udev->ll2_ring = NULL;
+	}
+
+	if (udev->ll2_buf) {
+		free_pages((unsigned long)udev->ll2_buf, 2);
+		udev->ll2_buf = NULL;
+	}
+}
+
+static void __qedi_free_uio(struct qedi_uio_dev *udev)
+{
+	uio_unregister_device(&udev->qedi_uinfo);
+
+	__qedi_free_uio_rings(udev);
+
+	pci_dev_put(udev->pdev);
+	kfree(udev->uctrl);
+	kfree(udev);
+}
+
+static void qedi_free_uio(struct qedi_uio_dev *udev)
+{
+	if (!udev)
+		return;
+
+	list_del_init(&udev->list);
+	__qedi_free_uio(udev);
+}
+
+static void qedi_reset_uio_rings(struct qedi_uio_dev *udev)
+{
+	struct qedi_ctx *qedi = NULL;
+	struct qedi_uio_ctrl *uctrl = NULL;
+
+	qedi = udev->qedi;
+	uctrl = udev->uctrl;
+
+	spin_lock_bh(&qedi->ll2_lock);
+	uctrl->host_rx_cons = 0;
+	uctrl->hw_rx_prod = 0;
+	uctrl->hw_rx_bd_prod = 0;
+	uctrl->host_rx_bd_cons = 0;
+
+	memset(udev->ll2_ring, 0, udev->ll2_ring_size);
+	memset(udev->ll2_buf, 0, udev->ll2_buf_size);
+	spin_unlock_bh(&qedi->ll2_lock);
+}
+
+static int __qedi_alloc_uio_rings(struct qedi_uio_dev *udev)
+{
+	int rc = 0;
+
+	if (udev->ll2_ring || udev->ll2_buf)
+		return rc;
+
+	/* Allocating memory for LL2 ring  */
+	udev->ll2_ring_size = QEDI_PAGE_SIZE;
+	udev->ll2_ring = (void *)get_zeroed_page(GFP_KERNEL | __GFP_COMP);
+	if (!udev->ll2_ring) {
+		rc = -ENOMEM;
+		goto exit_alloc_ring;
+	}
+
+	/* Allocating memory for Tx/Rx pkt buffer */
+	udev->ll2_buf_size = TX_RX_RING * LL2_SINGLE_BUF_SIZE;
+	udev->ll2_buf_size = QEDI_PAGE_ALIGN(udev->ll2_buf_size);
+	udev->ll2_buf = (void *)__get_free_pages(GFP_KERNEL | __GFP_COMP |
+						 __GFP_ZERO, 2);
+	if (!udev->ll2_buf) {
+		rc = -ENOMEM;
+		goto exit_alloc_buf;
+	}
+	return rc;
+
+exit_alloc_buf:
+	free_page((unsigned long)udev->ll2_ring);
+	udev->ll2_ring = NULL;
+exit_alloc_ring:
+	return rc;
+}
+
+static int qedi_alloc_uio_rings(struct qedi_ctx *qedi)
+{
+	struct qedi_uio_dev *udev = NULL;
+	struct qedi_uio_ctrl *uctrl = NULL;
+	int rc = 0;
+
+	list_for_each_entry(udev, &qedi_udev_list, list) {
+		if (udev->pdev == qedi->pdev) {
+			udev->qedi = qedi;
+			if (__qedi_alloc_uio_rings(udev)) {
+				udev->qedi = NULL;
+				return -ENOMEM;
+			}
+			qedi->udev = udev;
+			return 0;
+		}
+	}
+
+	udev = kzalloc(sizeof(*udev), GFP_KERNEL);
+	if (!udev) {
+		rc = -ENOMEM;
+		goto err_udev;
+	}
+
+	uctrl = kzalloc(sizeof(*uctrl), GFP_KERNEL);
+	if (!uctrl) {
+		rc = -ENOMEM;
+		goto err_uctrl;
+	}
+
+	udev->uio_dev = -1;
+
+	udev->qedi = qedi;
+	udev->pdev = qedi->pdev;
+	udev->uctrl = uctrl;
+
+	rc = __qedi_alloc_uio_rings(udev);
+	if (rc)
+		goto err_uio_rings;
+
+	list_add(&udev->list, &qedi_udev_list);
+
+	pci_dev_get(udev->pdev);
+	qedi->udev = udev;
+
+	udev->tx_pkt = udev->ll2_buf;
+	udev->rx_pkt = udev->ll2_buf + LL2_SINGLE_BUF_SIZE;
+	return 0;
+
+ err_uio_rings:
+	kfree(uctrl);
+ err_uctrl:
+	kfree(udev);
+ err_udev:
+	return -ENOMEM;
+}
+
+static int qedi_init_uio(struct qedi_ctx *qedi)
+{
+	struct qedi_uio_dev *udev = qedi->udev;
+	struct uio_info *uinfo;
+	int ret = 0;
+
+	if (!udev)
+		return -ENOMEM;
+
+	uinfo = &udev->qedi_uinfo;
+
+	uinfo->mem[0].addr = (unsigned long)udev->uctrl;
+	uinfo->mem[0].size = sizeof(struct qedi_uio_ctrl);
+	uinfo->mem[0].memtype = UIO_MEM_LOGICAL;
+
+	uinfo->mem[1].addr = (unsigned long)udev->ll2_ring;
+	uinfo->mem[1].size = udev->ll2_ring_size;
+	uinfo->mem[1].memtype = UIO_MEM_LOGICAL;
+
+	uinfo->mem[2].addr = (unsigned long)udev->ll2_buf;
+	uinfo->mem[2].size = udev->ll2_buf_size;
+	uinfo->mem[2].memtype = UIO_MEM_LOGICAL;
+
+	uinfo->name = "qedi_uio";
+	uinfo->version = QEDI_MODULE_VERSION;
+	uinfo->irq = UIO_IRQ_CUSTOM;
+
+	uinfo->open = qedi_uio_open;
+	uinfo->release = qedi_uio_close;
+
+	if (udev->uio_dev == -1) {
+		if (!uinfo->priv) {
+			uinfo->priv = udev;
+
+			ret = uio_register_device(&udev->pdev->dev, uinfo);
+			if (ret) {
+				QEDI_ERR(&qedi->dbg_ctx,
+					 "UIO registration failed\n");
+			}
+		}
+	}
+
+	return ret;
+}
+
+static int qedi_alloc_and_init_sb(struct qedi_ctx *qedi,
+				  struct qed_sb_info *sb_info, u16 sb_id)
+{
+	struct status_block *sb_virt;
+	dma_addr_t sb_phys;
+	int ret;
+
+	sb_virt = dma_alloc_coherent(&qedi->pdev->dev,
+				     sizeof(struct status_block), &sb_phys,
+				     GFP_KERNEL);
+	if (!sb_virt) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Status block allocation failed for id = %d.\n",
+			  sb_id);
+		return -ENOMEM;
+	}
+
+	ret = qedi_ops->common->sb_init(qedi->cdev, sb_info, sb_virt, sb_phys,
+				       sb_id, QED_SB_TYPE_STORAGE);
+	if (ret) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Status block initialization failed for id = %d.\n",
+			  sb_id);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void qedi_free_sb(struct qedi_ctx *qedi)
+{
+	struct qed_sb_info *sb_info;
+	int id;
+
+	for (id = 0; id < MIN_NUM_CPUS_MSIX(qedi); id++) {
+		sb_info = &qedi->sb_array[id];
+		if (sb_info->sb_virt)
+			dma_free_coherent(&qedi->pdev->dev,
+					  sizeof(*sb_info->sb_virt),
+					  (void *)sb_info->sb_virt,
+					  sb_info->sb_phys);
+	}
+}
+
+static void qedi_free_fp(struct qedi_ctx *qedi)
+{
+	kfree(qedi->fp_array);
+	kfree(qedi->sb_array);
+}
+
+static void qedi_destroy_fp(struct qedi_ctx *qedi)
+{
+	qedi_free_sb(qedi);
+	qedi_free_fp(qedi);
+}
+
+static int qedi_alloc_fp(struct qedi_ctx *qedi)
+{
+	int ret = 0;
+
+	qedi->fp_array = kcalloc(MIN_NUM_CPUS_MSIX(qedi),
+				 sizeof(struct qedi_fastpath), GFP_KERNEL);
+	if (!qedi->fp_array) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "fastpath fp array allocation failed.\n");
+		return -ENOMEM;
+	}
+
+	qedi->sb_array = kcalloc(MIN_NUM_CPUS_MSIX(qedi),
+				 sizeof(struct qed_sb_info), GFP_KERNEL);
+	if (!qedi->sb_array) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "fastpath sb array allocation failed.\n");
+		ret = -ENOMEM;
+		goto free_fp;
+	}
+
+	return ret;
+
+free_fp:
+	qedi_free_fp(qedi);
+	return ret;
+}
+
+static void qedi_int_fp(struct qedi_ctx *qedi)
+{
+	struct qedi_fastpath *fp;
+	int id;
+
+	memset(qedi->fp_array, 0, MIN_NUM_CPUS_MSIX(qedi) *
+	       sizeof(*qedi->fp_array));
+	memset(qedi->sb_array, 0, MIN_NUM_CPUS_MSIX(qedi) *
+	       sizeof(*qedi->sb_array));
+
+	for (id = 0; id < MIN_NUM_CPUS_MSIX(qedi); id++) {
+		fp = &qedi->fp_array[id];
+		fp->sb_info = &qedi->sb_array[id];
+		fp->sb_id = id;
+		fp->qedi = qedi;
+		snprintf(fp->name, sizeof(fp->name), "%s-fp-%d",
+			 "qedi", id);
+
+		/* fp_array[i] ---- irq cookie
+		 * So init data which is needed in int ctx
+		 */
+	}
+}
+
+static int qedi_prepare_fp(struct qedi_ctx *qedi)
+{
+	struct qedi_fastpath *fp;
+	int id, ret = 0;
+
+	ret = qedi_alloc_fp(qedi);
+	if (ret)
+		goto err;
+
+	qedi_int_fp(qedi);
+
+	for (id = 0; id < MIN_NUM_CPUS_MSIX(qedi); id++) {
+		fp = &qedi->fp_array[id];
+		ret = qedi_alloc_and_init_sb(qedi, fp->sb_info, fp->sb_id);
+		if (ret) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "SB allocation and initialization failed.\n");
+			ret = -EIO;
+			goto err_init;
+		}
+	}
+
+	return 0;
+
+err_init:
+	qedi_free_sb(qedi);
+	qedi_free_fp(qedi);
+err:
+	return ret;
+}
+
+static int qedi_setup_cid_que(struct qedi_ctx *qedi)
+{
+	int i;
+
+	qedi->cid_que.cid_que_base = kmalloc_array(qedi->max_active_conns,
+						   sizeof(u32), GFP_KERNEL);
+	if (!qedi->cid_que.cid_que_base)
+		return -ENOMEM;
+
+	qedi->cid_que.conn_cid_tbl = kmalloc_array(qedi->max_active_conns,
+						   sizeof(struct qedi_conn *),
+						   GFP_KERNEL);
+	if (!qedi->cid_que.conn_cid_tbl) {
+		kfree(qedi->cid_que.cid_que_base);
+		qedi->cid_que.cid_que_base = NULL;
+		return -ENOMEM;
+	}
+
+	qedi->cid_que.cid_que = (u32 *)qedi->cid_que.cid_que_base;
+	qedi->cid_que.cid_q_prod_idx = 0;
+	qedi->cid_que.cid_q_cons_idx = 0;
+	qedi->cid_que.cid_q_max_idx = qedi->max_active_conns;
+	qedi->cid_que.cid_free_cnt = qedi->max_active_conns;
+
+	for (i = 0; i < qedi->max_active_conns; i++) {
+		qedi->cid_que.cid_que[i] = i;
+		qedi->cid_que.conn_cid_tbl[i] = NULL;
+	}
+
+	return 0;
+}
+
+static void qedi_release_cid_que(struct qedi_ctx *qedi)
+{
+	kfree(qedi->cid_que.cid_que_base);
+	qedi->cid_que.cid_que_base = NULL;
+
+	kfree(qedi->cid_que.conn_cid_tbl);
+	qedi->cid_que.conn_cid_tbl = NULL;
+}
+
+static int qedi_init_id_tbl(struct qedi_portid_tbl *id_tbl, u16 size,
+			    u16 start_id, u16 next)
+{
+	id_tbl->start = start_id;
+	id_tbl->max = size;
+	id_tbl->next = next;
+	spin_lock_init(&id_tbl->lock);
+	id_tbl->table = kzalloc(DIV_ROUND_UP(size, 32) * 4, GFP_KERNEL);
+	if (!id_tbl->table)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void qedi_free_id_tbl(struct qedi_portid_tbl *id_tbl)
+{
+	kfree(id_tbl->table);
+	id_tbl->table = NULL;
+}
+
+int qedi_alloc_id(struct qedi_portid_tbl *id_tbl, u16 id)
+{
+	int ret = -1;
+
+	id -= id_tbl->start;
+	if (id >= id_tbl->max)
+		return ret;
+
+	spin_lock(&id_tbl->lock);
+	if (!test_bit(id, id_tbl->table)) {
+		set_bit(id, id_tbl->table);
+		ret = 0;
+	}
+	spin_unlock(&id_tbl->lock);
+	return ret;
+}
+
+u16 qedi_alloc_new_id(struct qedi_portid_tbl *id_tbl)
+{
+	u16 id;
+
+	spin_lock(&id_tbl->lock);
+	id = find_next_zero_bit(id_tbl->table, id_tbl->max, id_tbl->next);
+	if (id >= id_tbl->max) {
+		id = QEDI_LOCAL_PORT_INVALID;
+		if (id_tbl->next != 0) {
+			id = find_first_zero_bit(id_tbl->table, id_tbl->next);
+			if (id >= id_tbl->next)
+				id = QEDI_LOCAL_PORT_INVALID;
+		}
+	}
+
+	if (id < id_tbl->max) {
+		set_bit(id, id_tbl->table);
+		id_tbl->next = (id + 1) & (id_tbl->max - 1);
+		id += id_tbl->start;
+	}
+
+	spin_unlock(&id_tbl->lock);
+
+	return id;
+}
+
+void qedi_free_id(struct qedi_portid_tbl *id_tbl, u16 id)
+{
+	if (id == QEDI_LOCAL_PORT_INVALID)
+		return;
+
+	id -= id_tbl->start;
+	if (id >= id_tbl->max)
+		return;
+
+	clear_bit(id, id_tbl->table);
+}
+
+static void qedi_cm_free_mem(struct qedi_ctx *qedi)
+{
+	kfree(qedi->ep_tbl);
+	qedi->ep_tbl = NULL;
+	qedi_free_id_tbl(&qedi->lcl_port_tbl);
+}
+
+static int qedi_cm_alloc_mem(struct qedi_ctx *qedi)
+{
+	u16 port_id;
+
+	qedi->ep_tbl = kzalloc((qedi->max_active_conns *
+				sizeof(struct qedi_endpoint *)), GFP_KERNEL);
+	if (!qedi->ep_tbl)
+		return -ENOMEM;
+	port_id = prandom_u32() % QEDI_LOCAL_PORT_RANGE;
+	if (qedi_init_id_tbl(&qedi->lcl_port_tbl, QEDI_LOCAL_PORT_RANGE,
+			     QEDI_LOCAL_PORT_MIN, port_id)) {
+		qedi_cm_free_mem(qedi);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static struct qedi_ctx *qedi_host_alloc(struct pci_dev *pdev)
+{
+	struct Scsi_Host *shost;
+	struct qedi_ctx *qedi = NULL;
+
+	shost = iscsi_host_alloc(&qedi_host_template,
+				 sizeof(struct qedi_ctx), 0);
+	if (!shost) {
+		QEDI_ERR(NULL, "Could not allocate shost\n");
+		goto exit_setup_shost;
+	}
+
+	shost->max_id = QEDI_MAX_ISCSI_CONNS_PER_HBA;
+	shost->max_channel = 0;
+	shost->max_lun = ~0;
+	shost->max_cmd_len = 16;
+	shost->transportt = qedi_scsi_transport;
+
+	qedi = iscsi_host_priv(shost);
+	memset(qedi, 0, sizeof(*qedi));
+	qedi->shost = shost;
+	qedi->dbg_ctx.host_no = shost->host_no;
+	qedi->pdev = pdev;
+	qedi->dbg_ctx.pdev = pdev;
+	qedi->max_active_conns = ISCSI_MAX_SESS_PER_HBA;
+	qedi->max_sqes = QEDI_SQ_SIZE;
+
+	if (shost_use_blk_mq(shost))
+		shost->nr_hw_queues = MIN_NUM_CPUS_MSIX(qedi);
+
+	pci_set_drvdata(pdev, qedi);
+
+exit_setup_shost:
+	return qedi;
+}
+
+static int qedi_ll2_rx(void *cookie, struct sk_buff *skb, u32 arg1, u32 arg2)
+{
+	struct qedi_ctx *qedi = (struct qedi_ctx *)cookie;
+	struct qedi_uio_dev *udev;
+	struct qedi_uio_ctrl *uctrl;
+	struct skb_work_list *work;
+	u32 prod;
+
+	if (!qedi) {
+		QEDI_ERR(NULL, "qedi is NULL\n");
+		return -1;
+	}
+
+	if (!test_bit(UIO_DEV_OPENED, &qedi->flags)) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_UIO,
+			  "UIO DEV is not opened\n");
+		kfree_skb(skb);
+		return 0;
+	}
+
+	udev = qedi->udev;
+	uctrl = udev->uctrl;
+
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Could not allocate work so dropping frame.\n");
+		kfree_skb(skb);
+		return 0;
+	}
+
+	INIT_LIST_HEAD(&work->list);
+	work->skb = skb;
+
+	if (skb_vlan_tag_present(skb))
+		work->vlan_id = skb_vlan_tag_get(skb);
+
+	if (work->vlan_id)
+		__vlan_insert_tag(work->skb, htons(ETH_P_8021Q), work->vlan_id);
+
+	spin_lock_bh(&qedi->ll2_lock);
+	list_add_tail(&work->list, &qedi->ll2_skb_list);
+
+	++uctrl->hw_rx_prod_cnt;
+	prod = (uctrl->hw_rx_prod + 1) % RX_RING;
+	if (prod != uctrl->host_rx_cons) {
+		uctrl->hw_rx_prod = prod;
+		spin_unlock_bh(&qedi->ll2_lock);
+		wake_up_process(qedi->ll2_recv_thread);
+		return 0;
+	}
+
+	spin_unlock_bh(&qedi->ll2_lock);
+	return 0;
+}
+
+/* map this skb to iscsiuio mmaped region */
+static int qedi_ll2_process_skb(struct qedi_ctx *qedi, struct sk_buff *skb,
+				u16 vlan_id)
+{
+	struct qedi_uio_dev *udev = NULL;
+	struct qedi_uio_ctrl *uctrl = NULL;
+	struct qedi_rx_bd rxbd;
+	struct qedi_rx_bd *p_rxbd;
+	u32 rx_bd_prod;
+	void *pkt;
+	int len = 0;
+
+	if (!qedi) {
+		QEDI_ERR(NULL, "qedi is NULL\n");
+		return -1;
+	}
+
+	udev = qedi->udev;
+	uctrl = udev->uctrl;
+	pkt = udev->rx_pkt + (uctrl->hw_rx_prod * LL2_SINGLE_BUF_SIZE);
+	len = min_t(u32, skb->len, (u32)LL2_SINGLE_BUF_SIZE);
+	memcpy(pkt, skb->data, len);
+
+	memset(&rxbd, 0, sizeof(rxbd));
+	rxbd.rx_pkt_index = uctrl->hw_rx_prod;
+	rxbd.rx_pkt_len = len;
+	rxbd.vlan_id = vlan_id;
+
+	uctrl->hw_rx_bd_prod = (uctrl->hw_rx_bd_prod + 1) % QEDI_NUM_RX_BD;
+	rx_bd_prod = uctrl->hw_rx_bd_prod;
+	p_rxbd = (struct qedi_rx_bd *)udev->ll2_ring;
+	p_rxbd += rx_bd_prod;
+
+	memcpy(p_rxbd, &rxbd, sizeof(rxbd));
+
+	/* notify the iscsiuio about new packet */
+	uio_event_notify(&udev->qedi_uinfo);
+
+	return 0;
+}
+
+static void qedi_ll2_free_skbs(struct qedi_ctx *qedi)
+{
+	struct skb_work_list *work, *work_tmp;
+
+	spin_lock_bh(&qedi->ll2_lock);
+	list_for_each_entry_safe(work, work_tmp, &qedi->ll2_skb_list, list) {
+		list_del(&work->list);
+		if (work->skb)
+			kfree_skb(work->skb);
+		kfree(work);
+	}
+	spin_unlock_bh(&qedi->ll2_lock);
+}
+
+static int qedi_ll2_recv_thread(void *arg)
+{
+	struct qedi_ctx *qedi = (struct qedi_ctx *)arg;
+	struct skb_work_list *work, *work_tmp;
+
+	set_user_nice(current, -20);
+
+	while (!kthread_should_stop()) {
+		spin_lock_bh(&qedi->ll2_lock);
+		list_for_each_entry_safe(work, work_tmp, &qedi->ll2_skb_list,
+					 list) {
+			list_del(&work->list);
+			qedi_ll2_process_skb(qedi, work->skb, work->vlan_id);
+			kfree_skb(work->skb);
+			kfree(work);
+		}
+		set_current_state(TASK_INTERRUPTIBLE);
+		spin_unlock_bh(&qedi->ll2_lock);
+		schedule();
+	}
+
+	__set_current_state(TASK_RUNNING);
+	return 0;
+}
+
+static int qedi_set_iscsi_pf_param(struct qedi_ctx *qedi)
+{
+	u8 num_sq_pages;
+	u32 log_page_size;
+	int rval = 0;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC, "Min number of MSIX %d\n",
+		  MIN_NUM_CPUS_MSIX(qedi));
+
+	num_sq_pages = (MAX_OUSTANDING_TASKS_PER_CON * 8) / PAGE_SIZE;
+
+	qedi->num_queues = MIN_NUM_CPUS_MSIX(qedi);
+
+	memset(&qedi->pf_params.iscsi_pf_params, 0,
+	       sizeof(qedi->pf_params.iscsi_pf_params));
+
+	qedi->p_cpuq = pci_alloc_consistent(qedi->pdev,
+			qedi->num_queues * sizeof(struct qedi_glbl_q_params),
+			&qedi->hw_p_cpuq);
+	if (!qedi->p_cpuq) {
+		QEDI_ERR(&qedi->dbg_ctx, "pci_alloc_consistent fail\n");
+		rval = -1;
+		goto err_alloc_mem;
+	}
+
+	rval = qedi_alloc_global_queues(qedi);
+	if (rval) {
+		QEDI_ERR(&qedi->dbg_ctx, "Global queue allocation failed.\n");
+		rval = -1;
+		goto err_alloc_mem;
+	}
+
+	qedi->pf_params.iscsi_pf_params.num_cons = QEDI_MAX_ISCSI_CONNS_PER_HBA;
+	qedi->pf_params.iscsi_pf_params.num_tasks = QEDI_MAX_ISCSI_TASK;
+	qedi->pf_params.iscsi_pf_params.half_way_close_timeout = 10;
+	qedi->pf_params.iscsi_pf_params.num_sq_pages_in_ring = num_sq_pages;
+	qedi->pf_params.iscsi_pf_params.num_r2tq_pages_in_ring = num_sq_pages;
+	qedi->pf_params.iscsi_pf_params.num_uhq_pages_in_ring = num_sq_pages;
+	qedi->pf_params.iscsi_pf_params.num_queues = qedi->num_queues;
+	qedi->pf_params.iscsi_pf_params.debug_mode = qedi_fw_debug;
+
+	for (log_page_size = 0 ; log_page_size < 32 ; log_page_size++) {
+		if ((1 << log_page_size) == PAGE_SIZE)
+			break;
+	}
+	qedi->pf_params.iscsi_pf_params.log_page_size = log_page_size;
+
+	qedi->pf_params.iscsi_pf_params.glbl_q_params_addr =
+							   (u64)qedi->hw_p_cpuq;
+
+	/* RQ BDQ initializations.
+	 * rq_num_entries: suggested value for Initiator is 16 (4KB RQ)
+	 * rqe_log_size: 8 for 256B RQE
+	 */
+	qedi->pf_params.iscsi_pf_params.rqe_log_size = 8;
+	/* BDQ address and size */
+	qedi->pf_params.iscsi_pf_params.bdq_pbl_base_addr[BDQ_ID_RQ] =
+							qedi->bdq_pbl_list_dma;
+	qedi->pf_params.iscsi_pf_params.bdq_pbl_num_entries[BDQ_ID_RQ] =
+						qedi->bdq_pbl_list_num_entries;
+	qedi->pf_params.iscsi_pf_params.rq_buffer_size = QEDI_BDQ_BUF_SIZE;
+
+	/* cq_num_entries: num_tasks + rq_num_entries */
+	qedi->pf_params.iscsi_pf_params.cq_num_entries = 2048;
+
+	qedi->pf_params.iscsi_pf_params.gl_rq_pi = QEDI_PROTO_CQ_PROD_IDX;
+	qedi->pf_params.iscsi_pf_params.gl_cmd_pi = 1;
+	qedi->pf_params.iscsi_pf_params.ooo_enable = 1;
+
+err_alloc_mem:
+	return rval;
+}
+
+/* Free DMA coherent memory for array of queue pointers we pass to qed */
+static void qedi_free_iscsi_pf_param(struct qedi_ctx *qedi)
+{
+	size_t size = 0;
+
+	if (qedi->p_cpuq) {
+		size = qedi->num_queues * sizeof(struct qedi_glbl_q_params);
+		pci_free_consistent(qedi->pdev, size, qedi->p_cpuq,
+				    qedi->hw_p_cpuq);
+	}
+
+	qedi_free_global_queues(qedi);
+
+	kfree(qedi->global_queues);
+}
+
+static void qedi_link_update(void *dev, struct qed_link_output *link)
+{
+	struct qedi_ctx *qedi = (struct qedi_ctx *)dev;
+
+	if (link->link_up) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, "Link Up event.\n");
+		atomic_set(&qedi->link_state, QEDI_LINK_UP);
+	} else {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "Link Down event.\n");
+		atomic_set(&qedi->link_state, QEDI_LINK_DOWN);
+	}
+}
+
+static struct qed_iscsi_cb_ops qedi_cb_ops = {
+	{
+		.link_update =		qedi_link_update,
+	}
+};
+
+static int qedi_queue_cqe(struct qedi_ctx *qedi, union iscsi_cqe *cqe,
+			  u16 que_idx, struct qedi_percpu_s *p)
+{
+	struct qedi_work *qedi_work;
+	struct qedi_conn *q_conn;
+	struct iscsi_conn *conn;
+	struct qedi_cmd *qedi_cmd;
+	u32 iscsi_cid;
+	int rc = 0;
+
+	iscsi_cid  = cqe->cqe_common.conn_id;
+	q_conn = qedi->cid_que.conn_cid_tbl[iscsi_cid];
+	if (!q_conn) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Session no longer exists for cid=0x%x!!\n",
+			  iscsi_cid);
+		return -1;
+	}
+	conn = q_conn->cls_conn->dd_data;
+
+	switch (cqe->cqe_common.cqe_type) {
+	case ISCSI_CQE_TYPE_SOLICITED:
+	case ISCSI_CQE_TYPE_SOLICITED_WITH_SENSE:
+		qedi_cmd = qedi_get_cmd_from_tid(qedi, cqe->cqe_solicited.itid);
+		if (!qedi_cmd) {
+			rc = -1;
+			break;
+		}
+		INIT_LIST_HEAD(&qedi_cmd->cqe_work.list);
+		qedi_cmd->cqe_work.qedi = qedi;
+		memcpy(&qedi_cmd->cqe_work.cqe, cqe, sizeof(union iscsi_cqe));
+		qedi_cmd->cqe_work.que_idx = que_idx;
+		qedi_cmd->cqe_work.is_solicited = true;
+		list_add_tail(&qedi_cmd->cqe_work.list, &p->work_list);
+		break;
+	case ISCSI_CQE_TYPE_UNSOLICITED:
+	case ISCSI_CQE_TYPE_DUMMY:
+	case ISCSI_CQE_TYPE_TASK_CLEANUP:
+		qedi_work = kzalloc(sizeof(*qedi_work), GFP_ATOMIC);
+		if (!qedi_work) {
+			rc = -1;
+			break;
+		}
+		INIT_LIST_HEAD(&qedi_work->list);
+		qedi_work->qedi = qedi;
+		memcpy(&qedi_work->cqe, cqe, sizeof(union iscsi_cqe));
+		qedi_work->que_idx = que_idx;
+		qedi_work->is_solicited = false;
+		list_add_tail(&qedi_work->list, &p->work_list);
+		break;
+	default:
+		rc = -1;
+		QEDI_ERR(&qedi->dbg_ctx, "FW Error cqe.\n");
+	}
+	return rc;
+}
+
+static bool qedi_process_completions(struct qedi_fastpath *fp)
+{
+	struct qedi_ctx *qedi = fp->qedi;
+	struct qed_sb_info *sb_info = fp->sb_info;
+	struct status_block *sb = sb_info->sb_virt;
+	struct qedi_percpu_s *p = NULL;
+	struct global_queue *que;
+	u16 prod_idx;
+	unsigned long flags;
+	union iscsi_cqe *cqe;
+	int cpu;
+	int ret;
+
+	/* Get the current firmware producer index */
+	prod_idx = sb->pi_array[QEDI_PROTO_CQ_PROD_IDX];
+
+	if (prod_idx >= QEDI_CQ_SIZE)
+		prod_idx = prod_idx % QEDI_CQ_SIZE;
+
+	que = qedi->global_queues[fp->sb_id];
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO,
+		  "Before: global queue=%p prod_idx=%d cons_idx=%d, sb_id=%d\n",
+		  que, prod_idx, que->cq_cons_idx, fp->sb_id);
+
+	qedi->intr_cpu = fp->sb_id;
+	cpu = smp_processor_id();
+	p = &per_cpu(qedi_percpu, cpu);
+
+	if (unlikely(!p->iothread))
+		WARN_ON(1);
+
+	spin_lock_irqsave(&p->p_work_lock, flags);
+	while (que->cq_cons_idx != prod_idx) {
+		cqe = &que->cq[que->cq_cons_idx];
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO,
+			  "cqe=%p prod_idx=%d cons_idx=%d.\n",
+			  cqe, prod_idx, que->cq_cons_idx);
+
+		ret = qedi_queue_cqe(qedi, cqe, fp->sb_id, p);
+		if (ret)
+			continue;
+
+		que->cq_cons_idx++;
+		if (que->cq_cons_idx == QEDI_CQ_SIZE)
+			que->cq_cons_idx = 0;
+	}
+	wake_up_process(p->iothread);
+	spin_unlock_irqrestore(&p->p_work_lock, flags);
+
+	return true;
+}
+
+static bool qedi_fp_has_work(struct qedi_fastpath *fp)
+{
+	struct qedi_ctx *qedi = fp->qedi;
+	struct global_queue *que;
+	struct qed_sb_info *sb_info = fp->sb_info;
+	struct status_block *sb = sb_info->sb_virt;
+	u16 prod_idx;
+
+	barrier();
+
+	/* Get the current firmware producer index */
+	prod_idx = sb->pi_array[QEDI_PROTO_CQ_PROD_IDX];
+
+	/* Get the pointer to the global CQ this completion is on */
+	que = qedi->global_queues[fp->sb_id];
+
+	/* prod idx wrap around uint16 */
+	if (prod_idx >= QEDI_CQ_SIZE)
+		prod_idx = prod_idx % QEDI_CQ_SIZE;
+
+	return (que->cq_cons_idx != prod_idx);
+}
+
+/* MSI-X fastpath handler code */
+static irqreturn_t qedi_msix_handler(int irq, void *dev_id)
+{
+	struct qedi_fastpath *fp = dev_id;
+	struct qedi_ctx *qedi = fp->qedi;
+	bool wake_io_thread = true;
+
+	qed_sb_ack(fp->sb_info, IGU_INT_DISABLE, 0);
+
+process_again:
+	wake_io_thread = qedi_process_completions(fp);
+	if (wake_io_thread) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC,
+			  "process already running\n");
+	}
+
+	if (qedi_fp_has_work(fp) == 0)
+		qed_sb_update_sb_idx(fp->sb_info);
+
+	/* Check for more work */
+	rmb();
+
+	if (qedi_fp_has_work(fp) == 0)
+		qed_sb_ack(fp->sb_info, IGU_INT_ENABLE, 1);
+	else
+		goto process_again;
+
+	return IRQ_HANDLED;
+}
+
+/* simd handler for MSI/INTa */
+static void qedi_simd_int_handler(void *cookie)
+{
+	/* Cookie is qedi_ctx struct */
+	struct qedi_ctx *qedi = (struct qedi_ctx *)cookie;
+
+	QEDI_WARN(&qedi->dbg_ctx, "qedi=%p.\n", qedi);
+}
+
+#define QEDI_SIMD_HANDLER_NUM		0
+static void qedi_sync_free_irqs(struct qedi_ctx *qedi)
+{
+	int i;
+
+	if (qedi->int_info.msix_cnt) {
+		for (i = 0; i < qedi->int_info.used_cnt; i++) {
+			synchronize_irq(qedi->int_info.msix[i].vector);
+			irq_set_affinity_hint(qedi->int_info.msix[i].vector,
+					      NULL);
+			free_irq(qedi->int_info.msix[i].vector,
+				 &qedi->fp_array[i]);
+		}
+	} else {
+		qedi_ops->common->simd_handler_clean(qedi->cdev,
+						     QEDI_SIMD_HANDLER_NUM);
+	}
+
+	qedi->int_info.used_cnt = 0;
+	qedi_ops->common->set_fp_int(qedi->cdev, 0);
+}
+
+static int qedi_request_msix_irq(struct qedi_ctx *qedi)
+{
+	int i, rc, cpu;
+
+	cpu = cpumask_first(cpu_online_mask);
+	for (i = 0; i < MIN_NUM_CPUS_MSIX(qedi); i++) {
+		rc = request_irq(qedi->int_info.msix[i].vector,
+				 qedi_msix_handler, 0, "qedi",
+				 &qedi->fp_array[i]);
+
+		if (rc) {
+			QEDI_WARN(&qedi->dbg_ctx, "request_irq failed.\n");
+			qedi_sync_free_irqs(qedi);
+			return rc;
+		}
+		qedi->int_info.used_cnt++;
+		rc = irq_set_affinity_hint(qedi->int_info.msix[i].vector,
+					   get_cpu_mask(cpu));
+		cpu = cpumask_next(cpu, cpu_online_mask);
+	}
+
+	return 0;
+}
+
+static int qedi_setup_int(struct qedi_ctx *qedi)
+{
+	int rc = 0;
+
+	rc = qedi_ops->common->set_fp_int(qedi->cdev, num_online_cpus());
+	rc = qedi_ops->common->get_fp_int(qedi->cdev, &qedi->int_info);
+	if (rc)
+		goto exit_setup_int;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC,
+		  "Number of msix_cnt = 0x%x num of cpus = 0x%x\n",
+		   qedi->int_info.msix_cnt, num_online_cpus());
+
+	if (qedi->int_info.msix_cnt) {
+		rc = qedi_request_msix_irq(qedi);
+		goto exit_setup_int;
+	} else {
+		qedi_ops->common->simd_handler_config(qedi->cdev, &qedi,
+						      QEDI_SIMD_HANDLER_NUM,
+						      qedi_simd_int_handler);
+		qedi->int_info.used_cnt = 1;
+	}
+
+exit_setup_int:
+	return rc;
+}
+
+static void qedi_free_bdq(struct qedi_ctx *qedi)
+{
+	int i;
+
+	if (qedi->bdq_pbl_list)
+		dma_free_coherent(&qedi->pdev->dev, PAGE_SIZE,
+				  qedi->bdq_pbl_list, qedi->bdq_pbl_list_dma);
+
+	if (qedi->bdq_pbl)
+		dma_free_coherent(&qedi->pdev->dev, qedi->bdq_pbl_mem_size,
+				  qedi->bdq_pbl, qedi->bdq_pbl_dma);
+
+	for (i = 0; i < QEDI_BDQ_NUM; i++) {
+		if (qedi->bdq[i].buf_addr) {
+			dma_free_coherent(&qedi->pdev->dev, QEDI_BDQ_BUF_SIZE,
+					  qedi->bdq[i].buf_addr,
+					  qedi->bdq[i].buf_dma);
+		}
+	}
+}
+
+static void qedi_free_global_queues(struct qedi_ctx *qedi)
+{
+	int i;
+	struct global_queue **gl = qedi->global_queues;
+
+	for (i = 0; i < qedi->num_queues; i++) {
+		if (!gl[i])
+			continue;
+
+		if (gl[i]->cq)
+			dma_free_coherent(&qedi->pdev->dev, gl[i]->cq_mem_size,
+					  gl[i]->cq, gl[i]->cq_dma);
+		if (gl[i]->cq_pbl)
+			dma_free_coherent(&qedi->pdev->dev, gl[i]->cq_pbl_size,
+					  gl[i]->cq_pbl, gl[i]->cq_pbl_dma);
+
+		kfree(gl[i]);
+	}
+	qedi_free_bdq(qedi);
+}
+
+static int qedi_alloc_bdq(struct qedi_ctx *qedi)
+{
+	int i;
+	struct scsi_bd *pbl;
+	u64 *list;
+	dma_addr_t page;
+
+	/* Alloc dma memory for BDQ buffers */
+	for (i = 0; i < QEDI_BDQ_NUM; i++) {
+		qedi->bdq[i].buf_addr =
+				dma_alloc_coherent(&qedi->pdev->dev,
+						   QEDI_BDQ_BUF_SIZE,
+						   &qedi->bdq[i].buf_dma,
+						   GFP_KERNEL);
+		if (!qedi->bdq[i].buf_addr) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Could not allocate BDQ buffer %d.\n", i);
+			return -ENOMEM;
+		}
+	}
+
+	/* Alloc dma memory for BDQ page buffer list */
+	qedi->bdq_pbl_mem_size = QEDI_BDQ_NUM * sizeof(struct scsi_bd);
+	qedi->bdq_pbl_mem_size = ALIGN(qedi->bdq_pbl_mem_size, PAGE_SIZE);
+	qedi->rq_num_entries = qedi->bdq_pbl_mem_size / sizeof(struct scsi_bd);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN, "rq_num_entries = %d.\n",
+		  qedi->rq_num_entries);
+
+	qedi->bdq_pbl = dma_alloc_coherent(&qedi->pdev->dev,
+					   qedi->bdq_pbl_mem_size,
+					   &qedi->bdq_pbl_dma, GFP_KERNEL);
+	if (!qedi->bdq_pbl) {
+		QEDI_ERR(&qedi->dbg_ctx, "Could not allocate BDQ PBL.\n");
+		return -ENOMEM;
+	}
+
+	/*
+	 * Populate BDQ PBL with physical and virtual address of individual
+	 * BDQ buffers
+	 */
+	pbl = (struct scsi_bd  *)qedi->bdq_pbl;
+	for (i = 0; i < QEDI_BDQ_NUM; i++) {
+		pbl->address.hi =
+				cpu_to_le32(QEDI_U64_HI(qedi->bdq[i].buf_dma));
+		pbl->address.lo =
+				cpu_to_le32(QEDI_U64_LO(qedi->bdq[i].buf_dma));
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "pbl [0x%p] pbl->address hi [0x%llx] lo [0x%llx], idx [%d]\n",
+			  pbl, pbl->address.hi, pbl->address.lo, i);
+		pbl->opaque.hi = 0;
+		pbl->opaque.lo = cpu_to_le32(QEDI_U64_LO(i));
+		pbl++;
+	}
+
+	/* Allocate list of PBL pages */
+	qedi->bdq_pbl_list = dma_alloc_coherent(&qedi->pdev->dev,
+						PAGE_SIZE,
+						&qedi->bdq_pbl_list_dma,
+						GFP_KERNEL);
+	if (!qedi->bdq_pbl_list) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Could not allocate list of PBL pages.\n");
+		return -ENOMEM;
+	}
+	memset(qedi->bdq_pbl_list, 0, PAGE_SIZE);
+
+	/*
+	 * Now populate PBL list with pages that contain pointers to the
+	 * individual buffers.
+	 */
+	qedi->bdq_pbl_list_num_entries = qedi->bdq_pbl_mem_size / PAGE_SIZE;
+	list = (u64 *)qedi->bdq_pbl_list;
+	page = qedi->bdq_pbl_list_dma;
+	for (i = 0; i < qedi->bdq_pbl_list_num_entries; i++) {
+		*list = qedi->bdq_pbl_dma;
+		list++;
+		page += PAGE_SIZE;
+	}
+
+	return 0;
+}
+
+static int qedi_alloc_global_queues(struct qedi_ctx *qedi)
+{
+	u32 *list;
+	int i;
+	int status = 0, rc;
+	u32 *pbl;
+	dma_addr_t page;
+	int num_pages;
+
+	/*
+	 * Number of global queues (CQ / RQ). This should
+	 * be <= number of available MSIX vectors for the PF
+	 */
+	if (!qedi->num_queues) {
+		QEDI_ERR(&qedi->dbg_ctx, "No MSI-X vectors available!\n");
+		return 1;
+	}
+
+	/* Make sure we allocated the PBL that will contain the physical
+	 * addresses of our queues
+	 */
+	if (!qedi->p_cpuq) {
+		status = 1;
+		goto mem_alloc_failure;
+	}
+
+	qedi->global_queues = kzalloc((sizeof(struct global_queue *) *
+				       qedi->num_queues), GFP_KERNEL);
+	if (!qedi->global_queues) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Unable to allocate global queues array ptr memory\n");
+		return -ENOMEM;
+	}
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC,
+		  "qedi->global_queues=%p.\n", qedi->global_queues);
+
+	/* Allocate DMA coherent buffers for BDQ */
+	rc = qedi_alloc_bdq(qedi);
+	if (rc)
+		goto mem_alloc_failure;
+
+	/* Allocate a CQ and an associated PBL for each MSI-X
+	 * vector.
+	 */
+	for (i = 0; i < qedi->num_queues; i++) {
+		qedi->global_queues[i] =
+					kzalloc(sizeof(*qedi->global_queues[0]),
+						GFP_KERNEL);
+		if (!qedi->global_queues[i]) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Unable to allocation global queue %d.\n", i);
+			goto mem_alloc_failure;
+		}
+
+		qedi->global_queues[i]->cq_mem_size =
+		    (QEDI_CQ_SIZE + 8) * sizeof(union iscsi_cqe);
+		qedi->global_queues[i]->cq_mem_size =
+		    (qedi->global_queues[i]->cq_mem_size +
+		    (QEDI_PAGE_SIZE - 1));
+
+		qedi->global_queues[i]->cq_pbl_size =
+		    (qedi->global_queues[i]->cq_mem_size /
+		    QEDI_PAGE_SIZE) * sizeof(void *);
+		qedi->global_queues[i]->cq_pbl_size =
+		    (qedi->global_queues[i]->cq_pbl_size +
+		    (QEDI_PAGE_SIZE - 1));
+
+		qedi->global_queues[i]->cq =
+		    dma_alloc_coherent(&qedi->pdev->dev,
+				       qedi->global_queues[i]->cq_mem_size,
+				       &qedi->global_queues[i]->cq_dma,
+				       GFP_KERNEL);
+
+		if (!qedi->global_queues[i]->cq) {
+			QEDI_WARN(&qedi->dbg_ctx,
+				  "Could not allocate cq.\n");
+			status = -ENOMEM;
+			goto mem_alloc_failure;
+		}
+		memset(qedi->global_queues[i]->cq, 0,
+		       qedi->global_queues[i]->cq_mem_size);
+
+		qedi->global_queues[i]->cq_pbl =
+		    dma_alloc_coherent(&qedi->pdev->dev,
+				       qedi->global_queues[i]->cq_pbl_size,
+				       &qedi->global_queues[i]->cq_pbl_dma,
+				       GFP_KERNEL);
+
+		if (!qedi->global_queues[i]->cq_pbl) {
+			QEDI_WARN(&qedi->dbg_ctx,
+				  "Could not allocate cq PBL.\n");
+			status = -ENOMEM;
+			goto mem_alloc_failure;
+		}
+		memset(qedi->global_queues[i]->cq_pbl, 0,
+		       qedi->global_queues[i]->cq_pbl_size);
+
+		/* Create PBL */
+		num_pages = qedi->global_queues[i]->cq_mem_size /
+		    QEDI_PAGE_SIZE;
+		page = qedi->global_queues[i]->cq_dma;
+		pbl = (u32 *)qedi->global_queues[i]->cq_pbl;
+
+		while (num_pages--) {
+			*pbl = (u32)page;
+			pbl++;
+			*pbl = (u32)((u64)page >> 32);
+			pbl++;
+			page += QEDI_PAGE_SIZE;
+		}
+	}
+
+	list = (u32 *)qedi->p_cpuq;
+
+	/*
+	 * The list is built as follows: CQ#0 PBL pointer, RQ#0 PBL pointer,
+	 * CQ#1 PBL pointer, RQ#1 PBL pointer, etc.  Each PBL pointer points
+	 * to the physical address which contains an array of pointers to the
+	 * physical addresses of the specific queue pages.
+	 */
+	for (i = 0; i < qedi->num_queues; i++) {
+		*list = (u32)qedi->global_queues[i]->cq_pbl_dma;
+		list++;
+		*list = (u32)((u64)qedi->global_queues[i]->cq_pbl_dma >> 32);
+		list++;
+
+		*list = (u32)0;
+		list++;
+		*list = (u32)((u64)0 >> 32);
+		list++;
+	}
+
+	return 0;
+
+mem_alloc_failure:
+	qedi_free_global_queues(qedi);
+	return status;
+}
+
+int qedi_alloc_sq(struct qedi_ctx *qedi, struct qedi_endpoint *ep)
+{
+	int rval = 0;
+	u32 *pbl;
+	dma_addr_t page;
+	int num_pages;
+
+	if (!ep)
+		return -EIO;
+
+	/* Calculate appropriate queue and PBL sizes */
+	ep->sq_mem_size = QEDI_SQ_SIZE * sizeof(struct iscsi_wqe);
+	ep->sq_mem_size += QEDI_PAGE_SIZE - 1;
+
+	ep->sq_pbl_size = (ep->sq_mem_size / QEDI_PAGE_SIZE) * sizeof(void *);
+	ep->sq_pbl_size = ep->sq_pbl_size + QEDI_PAGE_SIZE;
+
+	ep->sq = dma_alloc_coherent(&qedi->pdev->dev, ep->sq_mem_size,
+				    &ep->sq_dma, GFP_KERNEL);
+	if (!ep->sq) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Could not allocate send queue.\n");
+		rval = -ENOMEM;
+		goto out;
+	}
+	memset(ep->sq, 0, ep->sq_mem_size);
+
+	ep->sq_pbl = dma_alloc_coherent(&qedi->pdev->dev, ep->sq_pbl_size,
+					&ep->sq_pbl_dma, GFP_KERNEL);
+	if (!ep->sq_pbl) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Could not allocate send queue PBL.\n");
+		rval = -ENOMEM;
+		goto out_free_sq;
+	}
+	memset(ep->sq_pbl, 0, ep->sq_pbl_size);
+
+	/* Create PBL */
+	num_pages = ep->sq_mem_size / QEDI_PAGE_SIZE;
+	page = ep->sq_dma;
+	pbl = (u32 *)ep->sq_pbl;
+
+	while (num_pages--) {
+		*pbl = (u32)page;
+		pbl++;
+		*pbl = (u32)((u64)page >> 32);
+		pbl++;
+		page += QEDI_PAGE_SIZE;
+	}
+
+	return rval;
+
+out_free_sq:
+	dma_free_coherent(&qedi->pdev->dev, ep->sq_mem_size, ep->sq,
+			  ep->sq_dma);
+out:
+	return rval;
+}
+
+void qedi_free_sq(struct qedi_ctx *qedi, struct qedi_endpoint *ep)
+{
+	if (ep->sq_pbl)
+		dma_free_coherent(&qedi->pdev->dev, ep->sq_pbl_size, ep->sq_pbl,
+				  ep->sq_pbl_dma);
+	if (ep->sq)
+		dma_free_coherent(&qedi->pdev->dev, ep->sq_mem_size, ep->sq,
+				  ep->sq_dma);
+}
+
+int qedi_get_task_idx(struct qedi_ctx *qedi)
+{
+	s16 tmp_idx;
+
+again:
+	tmp_idx = find_first_zero_bit(qedi->task_idx_map,
+				      MAX_ISCSI_TASK_ENTRIES);
+
+	if (tmp_idx >= MAX_ISCSI_TASK_ENTRIES) {
+		QEDI_ERR(&qedi->dbg_ctx, "FW task context pool is full.\n");
+		tmp_idx = -1;
+		goto err_idx;
+	}
+
+	if (test_and_set_bit(tmp_idx, qedi->task_idx_map))
+		goto again;
+
+err_idx:
+	return tmp_idx;
+}
+
+void qedi_clear_task_idx(struct qedi_ctx *qedi, int idx)
+{
+	if (!test_and_clear_bit(idx, qedi->task_idx_map)) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "FW task context, already cleared, tid=0x%x\n", idx);
+		WARN_ON(1);
+	}
+}
+
+void qedi_update_itt_map(struct qedi_ctx *qedi, u32 tid, u32 proto_itt,
+			 struct qedi_cmd *cmd)
+{
+	qedi->itt_map[tid].itt = proto_itt;
+	qedi->itt_map[tid].p_cmd = cmd;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "update itt map tid=0x%x, with proto itt=0x%x\n", tid,
+		  qedi->itt_map[tid].itt);
+}
+
+void qedi_get_task_tid(struct qedi_ctx *qedi, u32 itt, s16 *tid)
+{
+	u16 i;
+
+	for (i = 0; i < MAX_ISCSI_TASK_ENTRIES; i++) {
+		if (qedi->itt_map[i].itt == itt) {
+			*tid = i;
+			QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+				  "Ref itt=0x%x, found at tid=0x%x\n",
+				  itt, *tid);
+			return;
+		}
+	}
+
+	WARN_ON(1);
+}
+
+void qedi_get_proto_itt(struct qedi_ctx *qedi, u32 tid, u32 *proto_itt)
+{
+	*proto_itt = qedi->itt_map[tid].itt;
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "Get itt map tid [0x%x with proto itt[0x%x]",
+		  tid, *proto_itt);
+}
+
+struct qedi_cmd *qedi_get_cmd_from_tid(struct qedi_ctx *qedi, u32 tid)
+{
+	struct qedi_cmd *cmd = NULL;
+
+	if (tid > MAX_ISCSI_TASK_ENTRIES)
+		return NULL;
+
+	cmd = qedi->itt_map[tid].p_cmd;
+	if (cmd->task_id != tid)
+		return NULL;
+
+	qedi->itt_map[tid].p_cmd = NULL;
+
+	return cmd;
+}
+
+static int qedi_alloc_itt(struct qedi_ctx *qedi)
+{
+	qedi->itt_map = kcalloc(MAX_ISCSI_TASK_ENTRIES,
+				sizeof(struct qedi_itt_map), GFP_KERNEL);
+	if (!qedi->itt_map) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Unable to allocate itt map array memory\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void qedi_free_itt(struct qedi_ctx *qedi)
+{
+	kfree(qedi->itt_map);
+}
+
+static struct qed_ll2_cb_ops qedi_ll2_cb_ops = {
+	.rx_cb = qedi_ll2_rx,
+	.tx_cb = NULL,
+};
+
+static int qedi_percpu_io_thread(void *arg)
+{
+	struct qedi_percpu_s *p = arg;
+	struct qedi_work *work, *tmp;
+	unsigned long flags;
+	LIST_HEAD(work_list);
+
+	set_user_nice(current, -20);
+
+	while (!kthread_should_stop()) {
+		spin_lock_irqsave(&p->p_work_lock, flags);
+		while (!list_empty(&p->work_list)) {
+			list_splice_init(&p->work_list, &work_list);
+			spin_unlock_irqrestore(&p->p_work_lock, flags);
+
+			list_for_each_entry_safe(work, tmp, &work_list, list) {
+				list_del_init(&work->list);
+				qedi_fp_process_cqes(work);
+				if (!work->is_solicited)
+					kfree(work);
+			}
+			cond_resched();
+			spin_lock_irqsave(&p->p_work_lock, flags);
+		}
+		set_current_state(TASK_INTERRUPTIBLE);
+		spin_unlock_irqrestore(&p->p_work_lock, flags);
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+
+	return 0;
+}
+
+static int qedi_cpu_online(unsigned int cpu)
+{
+	struct qedi_percpu_s *p = this_cpu_ptr(&qedi_percpu);
+	struct task_struct *thread;
+
+	thread = kthread_create_on_node(qedi_percpu_io_thread, (void *)p,
+					cpu_to_node(cpu),
+					"qedi_thread/%d", cpu);
+	if (IS_ERR(thread))
+		return PTR_ERR(thread);
+
+	kthread_bind(thread, cpu);
+	p->iothread = thread;
+	wake_up_process(thread);
+	return 0;
+}
+
+static int qedi_cpu_offline(unsigned int cpu)
+{
+	struct qedi_percpu_s *p = this_cpu_ptr(&qedi_percpu);
+	struct qedi_work *work, *tmp;
+	struct task_struct *thread;
+
+	spin_lock_bh(&p->p_work_lock);
+	thread = p->iothread;
+	p->iothread = NULL;
+
+	list_for_each_entry_safe(work, tmp, &p->work_list, list) {
+		list_del_init(&work->list);
+		qedi_fp_process_cqes(work);
+		if (!work->is_solicited)
+			kfree(work);
+	}
+
+	spin_unlock_bh(&p->p_work_lock);
+	if (thread)
+		kthread_stop(thread);
+	return 0;
+}
+
+void qedi_reset_host_mtu(struct qedi_ctx *qedi, u16 mtu)
+{
+	struct qed_ll2_params params;
+
+	qedi_recover_all_conns(qedi);
+
+	qedi_ops->ll2->stop(qedi->cdev);
+	qedi_ll2_free_skbs(qedi);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, "old MTU %u, new MTU %u\n",
+		  qedi->ll2_mtu, mtu);
+	memset(&params, 0, sizeof(params));
+	qedi->ll2_mtu = mtu;
+	params.mtu = qedi->ll2_mtu + IPV6_HDR_LEN + TCP_HDR_LEN;
+	params.drop_ttl0_packets = 0;
+	params.rx_vlan_stripping = 1;
+	ether_addr_copy(params.ll2_mac_address, qedi->dev_info.common.hw_mac);
+	qedi_ops->ll2->start(qedi->cdev, &params);
+}
+
+static void __qedi_remove(struct pci_dev *pdev, int mode)
+{
+	struct qedi_ctx *qedi = pci_get_drvdata(pdev);
+
+	if (qedi->tmf_thread) {
+		flush_workqueue(qedi->tmf_thread);
+		destroy_workqueue(qedi->tmf_thread);
+		qedi->tmf_thread = NULL;
+	}
+
+	if (qedi->offload_thread) {
+		flush_workqueue(qedi->offload_thread);
+		destroy_workqueue(qedi->offload_thread);
+		qedi->offload_thread = NULL;
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	qedi_dbg_host_exit(&qedi->dbg_ctx);
+#endif
+	if (!test_bit(QEDI_IN_OFFLINE, &qedi->flags))
+		qedi_ops->common->set_power_state(qedi->cdev, PCI_D0);
+
+	qedi_sync_free_irqs(qedi);
+
+	if (!test_bit(QEDI_IN_OFFLINE, &qedi->flags)) {
+		qedi_ops->stop(qedi->cdev);
+		qedi_ops->ll2->stop(qedi->cdev);
+	}
+
+	if (mode == QEDI_MODE_NORMAL)
+		qedi_free_iscsi_pf_param(qedi);
+
+	if (!test_bit(QEDI_IN_OFFLINE, &qedi->flags)) {
+		qedi_ops->common->slowpath_stop(qedi->cdev);
+		qedi_ops->common->remove(qedi->cdev);
+	}
+
+	qedi_destroy_fp(qedi);
+
+	if (mode == QEDI_MODE_NORMAL) {
+		qedi_release_cid_que(qedi);
+		qedi_cm_free_mem(qedi);
+		qedi_free_uio(qedi->udev);
+		qedi_free_itt(qedi);
+
+		iscsi_host_remove(qedi->shost);
+		iscsi_host_free(qedi->shost);
+
+		if (qedi->ll2_recv_thread) {
+			kthread_stop(qedi->ll2_recv_thread);
+			qedi->ll2_recv_thread = NULL;
+		}
+		qedi_ll2_free_skbs(qedi);
+	}
+}
+
+static int __qedi_probe(struct pci_dev *pdev, int mode)
+{
+	struct qedi_ctx *qedi;
+	struct qed_ll2_params params;
+	u32 dp_module = 0;
+	u8 dp_level = 0;
+	bool is_vf = false;
+	char host_buf[16];
+	struct qed_link_params link_params;
+	struct qed_slowpath_params sp_params;
+	struct qed_probe_params qed_params;
+	void *task_start, *task_end;
+	int rc;
+	u16 tmp;
+
+	if (mode != QEDI_MODE_RECOVERY) {
+		qedi = qedi_host_alloc(pdev);
+		if (!qedi) {
+			rc = -ENOMEM;
+			goto exit_probe;
+		}
+	} else {
+		qedi = pci_get_drvdata(pdev);
+	}
+
+	memset(&qed_params, 0, sizeof(qed_params));
+	qed_params.protocol = QED_PROTOCOL_ISCSI;
+	qed_params.dp_module = dp_module;
+	qed_params.dp_level = dp_level;
+	qed_params.is_vf = is_vf;
+	qedi->cdev = qedi_ops->common->probe(pdev, &qed_params);
+	if (!qedi->cdev) {
+		rc = -ENODEV;
+		QEDI_ERR(&qedi->dbg_ctx, "Cannot initialize hardware\n");
+		goto free_host;
+	}
+
+	qedi->msix_count = MAX_NUM_MSIX_PF;
+	atomic_set(&qedi->link_state, QEDI_LINK_DOWN);
+
+	if (mode != QEDI_MODE_RECOVERY) {
+		rc = qedi_set_iscsi_pf_param(qedi);
+		if (rc) {
+			rc = -ENOMEM;
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Set iSCSI pf param fail\n");
+			goto free_host;
+		}
+	}
+
+	qedi_ops->common->update_pf_params(qedi->cdev, &qedi->pf_params);
+
+	rc = qedi_prepare_fp(qedi);
+	if (rc) {
+		QEDI_ERR(&qedi->dbg_ctx, "Cannot start slowpath.\n");
+		goto free_pf_params;
+	}
+
+	/* Start the Slowpath-process */
+	memset(&sp_params, 0, sizeof(struct qed_slowpath_params));
+	sp_params.int_mode = QED_INT_MODE_MSIX;
+	sp_params.drv_major = QEDI_DRIVER_MAJOR_VER;
+	sp_params.drv_minor = QEDI_DRIVER_MINOR_VER;
+	sp_params.drv_rev = QEDI_DRIVER_REV_VER;
+	sp_params.drv_eng = QEDI_DRIVER_ENG_VER;
+	strlcpy(sp_params.name, "qedi iSCSI", QED_DRV_VER_STR_SIZE);
+	rc = qedi_ops->common->slowpath_start(qedi->cdev, &sp_params);
+	if (rc) {
+		QEDI_ERR(&qedi->dbg_ctx, "Cannot start slowpath\n");
+		goto stop_hw;
+	}
+
+	/* update_pf_params needs to be called before and after slowpath
+	 * start
+	 */
+	qedi_ops->common->update_pf_params(qedi->cdev, &qedi->pf_params);
+
+	qedi_setup_int(qedi);
+	if (rc)
+		goto stop_iscsi_func;
+
+	qedi_ops->common->set_power_state(qedi->cdev, PCI_D0);
+
+	/* Learn information crucial for qedi to progress */
+	rc = qedi_ops->fill_dev_info(qedi->cdev, &qedi->dev_info);
+	if (rc)
+		goto stop_iscsi_func;
+
+	/* Record BDQ producer doorbell addresses */
+	qedi->bdq_primary_prod = qedi->dev_info.primary_dbq_rq_addr;
+	qedi->bdq_secondary_prod = qedi->dev_info.secondary_bdq_rq_addr;
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC,
+		  "BDQ primary_prod=%p secondary_prod=%p.\n",
+		  qedi->bdq_primary_prod,
+		  qedi->bdq_secondary_prod);
+
+	/*
+	 * We need to write the number of BDs in the BDQ we've preallocated so
+	 * the f/w will do a prefetch and we'll get an unsolicited CQE when a
+	 * packet arrives.
+	 */
+	qedi->bdq_prod_idx = QEDI_BDQ_NUM;
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC,
+		  "Writing %d to primary and secondary BDQ doorbell registers.\n",
+		  qedi->bdq_prod_idx);
+	writew(qedi->bdq_prod_idx, qedi->bdq_primary_prod);
+	tmp = readw(qedi->bdq_primary_prod);
+	writew(qedi->bdq_prod_idx, qedi->bdq_secondary_prod);
+	tmp = readw(qedi->bdq_secondary_prod);
+
+	ether_addr_copy(qedi->mac, qedi->dev_info.common.hw_mac);
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC, "MAC address is %pM.\n",
+		  qedi->mac);
+
+	sprintf(host_buf, "host_%d", qedi->shost->host_no);
+	qedi_ops->common->set_id(qedi->cdev, host_buf, QEDI_MODULE_VERSION);
+
+	qedi_ops->register_ops(qedi->cdev, &qedi_cb_ops, qedi);
+
+	memset(&params, 0, sizeof(params));
+	params.mtu = DEF_PATH_MTU + IPV6_HDR_LEN + TCP_HDR_LEN;
+	qedi->ll2_mtu = DEF_PATH_MTU;
+	params.drop_ttl0_packets = 0;
+	params.rx_vlan_stripping = 1;
+	ether_addr_copy(params.ll2_mac_address, qedi->dev_info.common.hw_mac);
+
+	if (mode != QEDI_MODE_RECOVERY) {
+		/* set up rx path */
+		INIT_LIST_HEAD(&qedi->ll2_skb_list);
+		spin_lock_init(&qedi->ll2_lock);
+		/* start qedi context */
+		spin_lock_init(&qedi->hba_lock);
+		spin_lock_init(&qedi->task_idx_lock);
+	}
+	qedi_ops->ll2->register_cb_ops(qedi->cdev, &qedi_ll2_cb_ops, qedi);
+	qedi_ops->ll2->start(qedi->cdev, &params);
+
+	if (mode != QEDI_MODE_RECOVERY) {
+		qedi->ll2_recv_thread = kthread_run(qedi_ll2_recv_thread,
+						    (void *)qedi,
+						    "qedi_ll2_thread");
+	}
+
+	rc = qedi_ops->start(qedi->cdev, &qedi->tasks,
+			     qedi, qedi_iscsi_event_cb);
+	if (rc) {
+		rc = -ENODEV;
+		QEDI_ERR(&qedi->dbg_ctx, "Cannot start iSCSI function\n");
+		goto stop_slowpath;
+	}
+
+	task_start = qedi_get_task_mem(&qedi->tasks, 0);
+	task_end = qedi_get_task_mem(&qedi->tasks, MAX_TID_BLOCKS_ISCSI - 1);
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC,
+		  "Task context start=%p, end=%p block_size=%u.\n",
+		   task_start, task_end, qedi->tasks.size);
+
+	memset(&link_params, 0, sizeof(link_params));
+	link_params.link_up = true;
+	rc = qedi_ops->common->set_link(qedi->cdev, &link_params);
+	if (rc) {
+		QEDI_WARN(&qedi->dbg_ctx, "Link set up failed.\n");
+		atomic_set(&qedi->link_state, QEDI_LINK_DOWN);
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	qedi_dbg_host_init(&qedi->dbg_ctx, &qedi_debugfs_ops,
+			   &qedi_dbg_fops);
+#endif
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+		  "QLogic FastLinQ iSCSI Module qedi %s, FW %d.%d.%d.%d\n",
+		  QEDI_MODULE_VERSION, FW_MAJOR_VERSION, FW_MINOR_VERSION,
+		  FW_REVISION_VERSION, FW_ENGINEERING_VERSION);
+
+	if (mode == QEDI_MODE_NORMAL) {
+		if (iscsi_host_add(qedi->shost, &pdev->dev)) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Could not add iscsi host\n");
+			rc = -ENOMEM;
+			goto remove_host;
+		}
+
+		/* Allocate uio buffers */
+		rc = qedi_alloc_uio_rings(qedi);
+		if (rc) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "UIO alloc ring failed err=%d\n", rc);
+			goto remove_host;
+		}
+
+		rc = qedi_init_uio(qedi);
+		if (rc) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "UIO init failed, err=%d\n", rc);
+			goto free_uio;
+		}
+
+		/* host the array on iscsi_conn */
+		rc = qedi_setup_cid_que(qedi);
+		if (rc) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Could not setup cid que\n");
+			goto free_uio;
+		}
+
+		rc = qedi_cm_alloc_mem(qedi);
+		if (rc) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Could not alloc cm memory\n");
+			goto free_cid_que;
+		}
+
+		rc = qedi_alloc_itt(qedi);
+		if (rc) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Could not alloc itt memory\n");
+			goto free_cid_que;
+		}
+
+		sprintf(host_buf, "host_%d", qedi->shost->host_no);
+		qedi->tmf_thread = create_singlethread_workqueue(host_buf);
+		if (!qedi->tmf_thread) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Unable to start tmf thread!\n");
+			rc = -ENODEV;
+			goto free_cid_que;
+		}
+
+		sprintf(host_buf, "qedi_ofld%d", qedi->shost->host_no);
+		qedi->offload_thread = create_workqueue(host_buf);
+		if (!qedi->offload_thread) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Unable to start offload thread!\n");
+			rc = -ENODEV;
+			goto free_cid_que;
+		}
+
+		/* F/w needs 1st task context memory entry for performance */
+		set_bit(QEDI_RESERVE_TASK_ID, qedi->task_idx_map);
+		atomic_set(&qedi->num_offloads, 0);
+	}
+
+	return 0;
+
+free_cid_que:
+	qedi_release_cid_que(qedi);
+free_uio:
+	qedi_free_uio(qedi->udev);
+remove_host:
+#ifdef CONFIG_DEBUG_FS
+	qedi_dbg_host_exit(&qedi->dbg_ctx);
+#endif
+	iscsi_host_remove(qedi->shost);
+stop_iscsi_func:
+	qedi_ops->stop(qedi->cdev);
+stop_slowpath:
+	qedi_ops->common->slowpath_stop(qedi->cdev);
+stop_hw:
+	qedi_ops->common->remove(qedi->cdev);
+free_pf_params:
+	qedi_free_iscsi_pf_param(qedi);
+free_host:
+	iscsi_host_free(qedi->shost);
+exit_probe:
+	return rc;
+}
+
+static int qedi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	return __qedi_probe(pdev, QEDI_MODE_NORMAL);
+}
+
+static void qedi_remove(struct pci_dev *pdev)
+{
+	__qedi_remove(pdev, QEDI_MODE_NORMAL);
+}
+
+static struct pci_device_id qedi_pci_tbl[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, 0x165E) },
+	{ 0 },
+};
+MODULE_DEVICE_TABLE(pci, qedi_pci_tbl);
+
+static enum cpuhp_state qedi_cpuhp_state;
+
+static struct pci_driver qedi_pci_driver = {
+	.name = QEDI_MODULE_NAME,
+	.id_table = qedi_pci_tbl,
+	.probe = qedi_probe,
+	.remove = qedi_remove,
+};
+
+static int __init qedi_init(void)
+{
+	struct qedi_percpu_s *p;
+	int cpu, rc = 0;
+
+	qedi_ops = qed_get_iscsi_ops();
+	if (!qedi_ops) {
+		QEDI_ERR(NULL, "Failed to get qed iSCSI operations\n");
+		return -EINVAL;
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	qedi_dbg_init("qedi");
+#endif
+
+	qedi_scsi_transport = iscsi_register_transport(&qedi_iscsi_transport);
+	if (!qedi_scsi_transport) {
+		QEDI_ERR(NULL, "Could not register qedi transport");
+		rc = -ENOMEM;
+		goto exit_qedi_init_1;
+	}
+
+	for_each_possible_cpu(cpu) {
+		p = &per_cpu(qedi_percpu, cpu);
+		INIT_LIST_HEAD(&p->work_list);
+		spin_lock_init(&p->p_work_lock);
+		p->iothread = NULL;
+	}
+
+	rc = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "scsi/qedi:online",
+			       qedi_cpu_online, qedi_cpu_offline);
+	if (rc < 0)
+		goto exit_qedi_init_2;
+	qedi_cpuhp_state = rc;
+
+	rc = pci_register_driver(&qedi_pci_driver);
+	if (rc) {
+		QEDI_ERR(NULL, "Failed to register driver\n");
+		goto exit_qedi_hp;
+	}
+
+	return 0;
+
+exit_qedi_hp:
+	cpuhp_remove_state(qedi_cpuhp_state);
+exit_qedi_init_2:
+	iscsi_unregister_transport(&qedi_iscsi_transport);
+exit_qedi_init_1:
+#ifdef CONFIG_DEBUG_FS
+	qedi_dbg_exit();
+#endif
+	qed_put_iscsi_ops();
+	return rc;
+}
+
+static void __exit qedi_cleanup(void)
+{
+	pci_unregister_driver(&qedi_pci_driver);
+	cpuhp_remove_state(qedi_cpuhp_state);
+	iscsi_unregister_transport(&qedi_iscsi_transport);
+
+#ifdef CONFIG_DEBUG_FS
+	qedi_dbg_exit();
+#endif
+	qed_put_iscsi_ops();
+}
+
+MODULE_DESCRIPTION("QLogic FastLinQ 4xxxx iSCSI Module");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("QLogic Corporation");
+MODULE_VERSION(QEDI_MODULE_VERSION);
+module_init(qedi_init);
+module_exit(qedi_cleanup);
diff --git a/drivers/scsi/qedi/qedi_sysfs.c b/drivers/scsi/qedi/qedi_sysfs.c
new file mode 100644
index 000000000000..b10c48bd1428
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_sysfs.c
@@ -0,0 +1,52 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include "qedi.h"
+#include "qedi_gbl.h"
+#include "qedi_iscsi.h"
+#include "qedi_dbg.h"
+
+static inline struct qedi_ctx *qedi_dev_to_hba(struct device *dev)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+
+	return iscsi_host_priv(shost);
+}
+
+static ssize_t qedi_show_port_state(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct qedi_ctx *qedi = qedi_dev_to_hba(dev);
+
+	if (atomic_read(&qedi->link_state) == QEDI_LINK_UP)
+		return sprintf(buf, "Online\n");
+	else
+		return sprintf(buf, "Linkdown\n");
+}
+
+static ssize_t qedi_show_speed(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct qedi_ctx *qedi = qedi_dev_to_hba(dev);
+	struct qed_link_output if_link;
+
+	qedi_ops->common->get_link(qedi->cdev, &if_link);
+
+	return sprintf(buf, "%d Gbit\n", if_link.speed / 1000);
+}
+
+static DEVICE_ATTR(port_state, 0444, qedi_show_port_state, NULL);
+static DEVICE_ATTR(speed, 0444, qedi_show_speed, NULL);
+
+struct device_attribute *qedi_shost_attrs[] = {
+	&dev_attr_port_state,
+	&dev_attr_speed,
+	NULL
+};
diff --git a/drivers/scsi/qedi/qedi_version.h b/drivers/scsi/qedi/qedi_version.h
new file mode 100644
index 000000000000..9543a1b139d4
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_version.h
@@ -0,0 +1,14 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#define QEDI_MODULE_VERSION	"8.10.3.0"
+#define QEDI_DRIVER_MAJOR_VER		8
+#define QEDI_DRIVER_MINOR_VER		10
+#define QEDI_DRIVER_REV_VER		3
+#define QEDI_DRIVER_ENG_VER		0
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index fe7469c901f7..47eb4d545d13 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -1988,9 +1988,9 @@ qla24xx_vport_create(struct fc_vport *fc_vport, bool disable)
 	scsi_qla_host_t *base_vha = shost_priv(fc_vport->shost);
 	scsi_qla_host_t *vha = NULL;
 	struct qla_hw_data *ha = base_vha->hw;
-	uint16_t options = 0;
 	int	cnt;
 	struct req_que *req = ha->req_q_map[0];
+	struct qla_qpair *qpair;
 
 	ret = qla24xx_vport_create_req_sanity_check(fc_vport);
 	if (ret) {
@@ -2075,15 +2075,9 @@ qla24xx_vport_create(struct fc_vport *fc_vport, bool disable)
 	qlt_vport_create(vha, ha);
 	qla24xx_vport_disable(fc_vport, disable);
 
-	if (ha->flags.cpu_affinity_enabled) {
-		req = ha->req_q_map[1];
-		ql_dbg(ql_dbg_multiq, vha, 0xc000,
-		    "Request queue %p attached with "
-		    "VP[%d], cpu affinity =%d\n",
-		    req, vha->vp_idx, ha->flags.cpu_affinity_enabled);
-		goto vport_queue;
-	} else if (ql2xmaxqueues == 1 || !ha->npiv_info)
+	if (!ql2xmqsupport || !ha->npiv_info)
 		goto vport_queue;
+
 	/* Create a request queue in QoS mode for the vport */
 	for (cnt = 0; cnt < ha->nvram_npiv_size; cnt++) {
 		if (memcmp(ha->npiv_info[cnt].port_name, vha->port_name, 8) == 0
@@ -2095,20 +2089,20 @@ qla24xx_vport_create(struct fc_vport *fc_vport, bool disable)
 	}
 
 	if (qos) {
-		ret = qla25xx_create_req_que(ha, options, vha->vp_idx, 0, 0,
-			qos);
-		if (!ret)
+		qpair = qla2xxx_create_qpair(vha, qos, vha->vp_idx);
+		if (!qpair)
 			ql_log(ql_log_warn, vha, 0x7084,
-			    "Can't create request queue for VP[%d]\n",
+			    "Can't create qpair for VP[%d]\n",
 			    vha->vp_idx);
 		else {
 			ql_dbg(ql_dbg_multiq, vha, 0xc001,
-			    "Request Que:%d Q0s: %d) created for VP[%d]\n",
-			    ret, qos, vha->vp_idx);
+			    "Queue pair: %d Qos: %d) created for VP[%d]\n",
+			    qpair->id, qos, vha->vp_idx);
 			ql_dbg(ql_dbg_user, vha, 0x7085,
-			    "Request Que:%d Q0s: %d) created for VP[%d]\n",
-			    ret, qos, vha->vp_idx);
-			req = ha->req_q_map[ret];
+			    "Queue Pair: %d Qos: %d) created for VP[%d]\n",
+			    qpair->id, qos, vha->vp_idx);
+			req = qpair->req;
+			vha->qpair = qpair;
 		}
 	}
 
@@ -2162,10 +2156,10 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)
 	clear_bit(vha->vp_idx, ha->vp_idx_map);
 	mutex_unlock(&ha->vport_lock);
 
-	if (vha->req->id && !ha->flags.cpu_affinity_enabled) {
-		if (qla25xx_delete_req_que(vha, vha->req) != QLA_SUCCESS)
+	if (vha->qpair->vp_idx == vha->vp_idx) {
+		if (qla2xxx_delete_qpair(vha, vha->qpair) != QLA_SUCCESS)
 			ql_log(ql_log_warn, vha, 0x7087,
-			    "Queue delete failed.\n");
+			    "Queue Pair delete failed.\n");
 	}
 
 	ql_log(ql_log_info, vha, 0x7088, "VP[%d] deleted.\n", id);
diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index 643014f82f7d..1bf8061ff803 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -1,4 +1,4 @@
-/*
+	/*
  * QLogic Fibre Channel HBA Driver
  * Copyright (c)  2003-2014 QLogic Corporation
  *
@@ -9,6 +9,7 @@
 #include <linux/kthread.h>
 #include <linux/vmalloc.h>
 #include <linux/delay.h>
+#include <linux/bsg-lib.h>
 
 /* BSG support for ELS/CT pass through */
 void
@@ -16,10 +17,12 @@ qla2x00_bsg_job_done(void *data, void *ptr, int res)
 {
 	srb_t *sp = (srb_t *)ptr;
 	struct scsi_qla_host *vha = (scsi_qla_host_t *)data;
-	struct fc_bsg_job *bsg_job = sp->u.bsg_job;
+	struct bsg_job *bsg_job = sp->u.bsg_job;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
 
-	bsg_job->reply->result = res;
-	bsg_job->job_done(bsg_job);
+	bsg_reply->result = res;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	sp->free(vha, sp);
 }
 
@@ -28,13 +31,15 @@ qla2x00_bsg_sp_free(void *data, void *ptr)
 {
 	srb_t *sp = (srb_t *)ptr;
 	struct scsi_qla_host *vha = sp->fcport->vha;
-	struct fc_bsg_job *bsg_job = sp->u.bsg_job;
+	struct bsg_job *bsg_job = sp->u.bsg_job;
+	struct fc_bsg_request *bsg_request = bsg_job->request;
+
 	struct qla_hw_data *ha = vha->hw;
 	struct qla_mt_iocb_rqst_fx00 *piocb_rqst;
 
 	if (sp->type == SRB_FXIOCB_BCMD) {
 		piocb_rqst = (struct qla_mt_iocb_rqst_fx00 *)
-		    &bsg_job->request->rqst_data.h_vendor.vendor_cmd[1];
+		    &bsg_request->rqst_data.h_vendor.vendor_cmd[1];
 
 		if (piocb_rqst->flags & SRB_FXDISC_REQ_DMA_VALID)
 			dma_unmap_sg(&ha->pdev->dev,
@@ -116,9 +121,11 @@ qla24xx_fcp_prio_cfg_valid(scsi_qla_host_t *vha,
 }
 
 static int
-qla24xx_proc_fcp_prio_cfg_cmd(struct fc_bsg_job *bsg_job)
+qla24xx_proc_fcp_prio_cfg_cmd(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
+	struct fc_bsg_request *bsg_request = bsg_job->request;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	int ret = 0;
@@ -131,7 +138,7 @@ qla24xx_proc_fcp_prio_cfg_cmd(struct fc_bsg_job *bsg_job)
 	}
 
 	/* Get the sub command */
-	oper = bsg_job->request->rqst_data.h_vendor.vendor_cmd[1];
+	oper = bsg_request->rqst_data.h_vendor.vendor_cmd[1];
 
 	/* Only set config is allowed if config memory is not allocated */
 	if (!ha->fcp_prio_cfg && (oper != QLFC_FCP_PRIO_SET_CONFIG)) {
@@ -145,10 +152,10 @@ qla24xx_proc_fcp_prio_cfg_cmd(struct fc_bsg_job *bsg_job)
 			ha->fcp_prio_cfg->attributes &=
 				~FCP_PRIO_ATTR_ENABLE;
 			qla24xx_update_all_fcp_prio(vha);
-			bsg_job->reply->result = DID_OK;
+			bsg_reply->result = DID_OK;
 		} else {
 			ret = -EINVAL;
-			bsg_job->reply->result = (DID_ERROR << 16);
+			bsg_reply->result = (DID_ERROR << 16);
 			goto exit_fcp_prio_cfg;
 		}
 		break;
@@ -160,10 +167,10 @@ qla24xx_proc_fcp_prio_cfg_cmd(struct fc_bsg_job *bsg_job)
 				ha->fcp_prio_cfg->attributes |=
 				    FCP_PRIO_ATTR_ENABLE;
 				qla24xx_update_all_fcp_prio(vha);
-				bsg_job->reply->result = DID_OK;
+				bsg_reply->result = DID_OK;
 			} else {
 				ret = -EINVAL;
-				bsg_job->reply->result = (DID_ERROR << 16);
+				bsg_reply->result = (DID_ERROR << 16);
 				goto exit_fcp_prio_cfg;
 			}
 		}
@@ -173,12 +180,12 @@ qla24xx_proc_fcp_prio_cfg_cmd(struct fc_bsg_job *bsg_job)
 		len = bsg_job->reply_payload.payload_len;
 		if (!len || len > FCP_PRIO_CFG_SIZE) {
 			ret = -EINVAL;
-			bsg_job->reply->result = (DID_ERROR << 16);
+			bsg_reply->result = (DID_ERROR << 16);
 			goto exit_fcp_prio_cfg;
 		}
 
-		bsg_job->reply->result = DID_OK;
-		bsg_job->reply->reply_payload_rcv_len =
+		bsg_reply->result = DID_OK;
+		bsg_reply->reply_payload_rcv_len =
 			sg_copy_from_buffer(
 			bsg_job->reply_payload.sg_list,
 			bsg_job->reply_payload.sg_cnt, ha->fcp_prio_cfg,
@@ -189,7 +196,7 @@ qla24xx_proc_fcp_prio_cfg_cmd(struct fc_bsg_job *bsg_job)
 	case QLFC_FCP_PRIO_SET_CONFIG:
 		len = bsg_job->request_payload.payload_len;
 		if (!len || len > FCP_PRIO_CFG_SIZE) {
-			bsg_job->reply->result = (DID_ERROR << 16);
+			bsg_reply->result = (DID_ERROR << 16);
 			ret = -EINVAL;
 			goto exit_fcp_prio_cfg;
 		}
@@ -200,7 +207,7 @@ qla24xx_proc_fcp_prio_cfg_cmd(struct fc_bsg_job *bsg_job)
 				ql_log(ql_log_warn, vha, 0x7050,
 				    "Unable to allocate memory for fcp prio "
 				    "config data (%x).\n", FCP_PRIO_CFG_SIZE);
-				bsg_job->reply->result = (DID_ERROR << 16);
+				bsg_reply->result = (DID_ERROR << 16);
 				ret = -ENOMEM;
 				goto exit_fcp_prio_cfg;
 			}
@@ -215,7 +222,7 @@ qla24xx_proc_fcp_prio_cfg_cmd(struct fc_bsg_job *bsg_job)
 
 		if (!qla24xx_fcp_prio_cfg_valid(vha,
 		    (struct qla_fcp_prio_cfg *) ha->fcp_prio_cfg, 1)) {
-			bsg_job->reply->result = (DID_ERROR << 16);
+			bsg_reply->result = (DID_ERROR << 16);
 			ret = -EINVAL;
 			/* If buffer was invalidatic int
 			 * fcp_prio_cfg is of no use
@@ -229,7 +236,7 @@ qla24xx_proc_fcp_prio_cfg_cmd(struct fc_bsg_job *bsg_job)
 		if (ha->fcp_prio_cfg->attributes & FCP_PRIO_ATTR_ENABLE)
 			ha->flags.fcp_prio_enabled = 1;
 		qla24xx_update_all_fcp_prio(vha);
-		bsg_job->reply->result = DID_OK;
+		bsg_reply->result = DID_OK;
 		break;
 	default:
 		ret = -EINVAL;
@@ -237,13 +244,15 @@ qla24xx_proc_fcp_prio_cfg_cmd(struct fc_bsg_job *bsg_job)
 	}
 exit_fcp_prio_cfg:
 	if (!ret)
-		bsg_job->job_done(bsg_job);
+		bsg_job_done(bsg_job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	return ret;
 }
 
 static int
-qla2x00_process_els(struct fc_bsg_job *bsg_job)
+qla2x00_process_els(struct bsg_job *bsg_job)
 {
+	struct fc_bsg_request *bsg_request = bsg_job->request;
 	struct fc_rport *rport;
 	fc_port_t *fcport = NULL;
 	struct Scsi_Host *host;
@@ -255,15 +264,15 @@ qla2x00_process_els(struct fc_bsg_job *bsg_job)
 	int rval =  (DRIVER_ERROR << 16);
 	uint16_t nextlid = 0;
 
-	if (bsg_job->request->msgcode == FC_BSG_RPT_ELS) {
-		rport = bsg_job->rport;
+	if (bsg_request->msgcode == FC_BSG_RPT_ELS) {
+		rport = fc_bsg_to_rport(bsg_job);
 		fcport = *(fc_port_t **) rport->dd_data;
 		host = rport_to_shost(rport);
 		vha = shost_priv(host);
 		ha = vha->hw;
 		type = "FC_BSG_RPT_ELS";
 	} else {
-		host = bsg_job->shost;
+		host = fc_bsg_to_shost(bsg_job);
 		vha = shost_priv(host);
 		ha = vha->hw;
 		type = "FC_BSG_HST_ELS_NOLOGIN";
@@ -296,7 +305,7 @@ qla2x00_process_els(struct fc_bsg_job *bsg_job)
 	}
 
 	/* ELS request for rport */
-	if (bsg_job->request->msgcode == FC_BSG_RPT_ELS) {
+	if (bsg_request->msgcode == FC_BSG_RPT_ELS) {
 		/* make sure the rport is logged in,
 		 * if not perform fabric login
 		 */
@@ -322,11 +331,11 @@ qla2x00_process_els(struct fc_bsg_job *bsg_job)
 		/* Initialize all required  fields of fcport */
 		fcport->vha = vha;
 		fcport->d_id.b.al_pa =
-			bsg_job->request->rqst_data.h_els.port_id[0];
+			bsg_request->rqst_data.h_els.port_id[0];
 		fcport->d_id.b.area =
-			bsg_job->request->rqst_data.h_els.port_id[1];
+			bsg_request->rqst_data.h_els.port_id[1];
 		fcport->d_id.b.domain =
-			bsg_job->request->rqst_data.h_els.port_id[2];
+			bsg_request->rqst_data.h_els.port_id[2];
 		fcport->loop_id =
 			(fcport->d_id.b.al_pa == 0xFD) ?
 			NPH_FABRIC_CONTROLLER : NPH_F_PORT;
@@ -366,11 +375,11 @@ qla2x00_process_els(struct fc_bsg_job *bsg_job)
 	}
 
 	sp->type =
-		(bsg_job->request->msgcode == FC_BSG_RPT_ELS ?
-		SRB_ELS_CMD_RPT : SRB_ELS_CMD_HST);
+		(bsg_request->msgcode == FC_BSG_RPT_ELS ?
+		 SRB_ELS_CMD_RPT : SRB_ELS_CMD_HST);
 	sp->name =
-		(bsg_job->request->msgcode == FC_BSG_RPT_ELS ?
-		"bsg_els_rpt" : "bsg_els_hst");
+		(bsg_request->msgcode == FC_BSG_RPT_ELS ?
+		 "bsg_els_rpt" : "bsg_els_hst");
 	sp->u.bsg_job = bsg_job;
 	sp->free = qla2x00_bsg_sp_free;
 	sp->done = qla2x00_bsg_job_done;
@@ -378,7 +387,7 @@ qla2x00_process_els(struct fc_bsg_job *bsg_job)
 	ql_dbg(ql_dbg_user, vha, 0x700a,
 	    "bsg rqst type: %s els type: %x - loop-id=%x "
 	    "portid=%-2x%02x%02x.\n", type,
-	    bsg_job->request->rqst_data.h_els.command_code, fcport->loop_id,
+	    bsg_request->rqst_data.h_els.command_code, fcport->loop_id,
 	    fcport->d_id.b.domain, fcport->d_id.b.area, fcport->d_id.b.al_pa);
 
 	rval = qla2x00_start_sp(sp);
@@ -399,7 +408,7 @@ done_unmap_sg:
 	goto done_free_fcport;
 
 done_free_fcport:
-	if (bsg_job->request->msgcode == FC_BSG_RPT_ELS)
+	if (bsg_request->msgcode == FC_BSG_RPT_ELS)
 		kfree(fcport);
 done:
 	return rval;
@@ -420,10 +429,11 @@ qla24xx_calc_ct_iocbs(uint16_t dsds)
 }
 
 static int
-qla2x00_process_ct(struct fc_bsg_job *bsg_job)
+qla2x00_process_ct(struct bsg_job *bsg_job)
 {
 	srb_t *sp;
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_request *bsg_request = bsg_job->request;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	int rval = (DRIVER_ERROR << 16);
@@ -469,7 +479,7 @@ qla2x00_process_ct(struct fc_bsg_job *bsg_job)
 	}
 
 	loop_id =
-		(bsg_job->request->rqst_data.h_ct.preamble_word1 & 0xFF000000)
+		(bsg_request->rqst_data.h_ct.preamble_word1 & 0xFF000000)
 			>> 24;
 	switch (loop_id) {
 	case 0xFC:
@@ -500,9 +510,9 @@ qla2x00_process_ct(struct fc_bsg_job *bsg_job)
 
 	/* Initialize all required  fields of fcport */
 	fcport->vha = vha;
-	fcport->d_id.b.al_pa = bsg_job->request->rqst_data.h_ct.port_id[0];
-	fcport->d_id.b.area = bsg_job->request->rqst_data.h_ct.port_id[1];
-	fcport->d_id.b.domain = bsg_job->request->rqst_data.h_ct.port_id[2];
+	fcport->d_id.b.al_pa = bsg_request->rqst_data.h_ct.port_id[0];
+	fcport->d_id.b.area = bsg_request->rqst_data.h_ct.port_id[1];
+	fcport->d_id.b.domain = bsg_request->rqst_data.h_ct.port_id[2];
 	fcport->loop_id = loop_id;
 
 	/* Alloc SRB structure */
@@ -524,7 +534,7 @@ qla2x00_process_ct(struct fc_bsg_job *bsg_job)
 	ql_dbg(ql_dbg_user, vha, 0x7016,
 	    "bsg rqst type: %s else type: %x - "
 	    "loop-id=%x portid=%02x%02x%02x.\n", type,
-	    (bsg_job->request->rqst_data.h_ct.preamble_word2 >> 16),
+	    (bsg_request->rqst_data.h_ct.preamble_word2 >> 16),
 	    fcport->loop_id, fcport->d_id.b.domain, fcport->d_id.b.area,
 	    fcport->d_id.b.al_pa);
 
@@ -697,9 +707,11 @@ done_set_internal:
 }
 
 static int
-qla2x00_process_loopback(struct fc_bsg_job *bsg_job)
+qla2x00_process_loopback(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_request *bsg_request = bsg_job->request;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	int rval;
@@ -780,9 +792,9 @@ qla2x00_process_loopback(struct fc_bsg_job *bsg_job)
 	elreq.rcv_dma = rsp_data_dma;
 	elreq.transfer_size = req_data_len;
 
-	elreq.options = bsg_job->request->rqst_data.h_vendor.vendor_cmd[1];
+	elreq.options = bsg_request->rqst_data.h_vendor.vendor_cmd[1];
 	elreq.iteration_count =
-	    bsg_job->request->rqst_data.h_vendor.vendor_cmd[2];
+	    bsg_request->rqst_data.h_vendor.vendor_cmd[2];
 
 	if (atomic_read(&vha->loop_state) == LOOP_READY &&
 	    (ha->current_topology == ISP_CFG_F ||
@@ -896,12 +908,12 @@ qla2x00_process_loopback(struct fc_bsg_job *bsg_job)
 		    "Vendor request %s failed.\n", type);
 
 		rval = 0;
-		bsg_job->reply->result = (DID_ERROR << 16);
-		bsg_job->reply->reply_payload_rcv_len = 0;
+		bsg_reply->result = (DID_ERROR << 16);
+		bsg_reply->reply_payload_rcv_len = 0;
 	} else {
 		ql_dbg(ql_dbg_user, vha, 0x702d,
 		    "Vendor request %s completed.\n", type);
-		bsg_job->reply->result = (DID_OK << 16);
+		bsg_reply->result = (DID_OK << 16);
 		sg_copy_from_buffer(bsg_job->reply_payload.sg_list,
 			bsg_job->reply_payload.sg_cnt, rsp_data,
 			rsp_data_len);
@@ -930,14 +942,17 @@ done_unmap_req_sg:
 	    bsg_job->request_payload.sg_list,
 	    bsg_job->request_payload.sg_cnt, DMA_TO_DEVICE);
 	if (!rval)
-		bsg_job->job_done(bsg_job);
+		bsg_job_done(bsg_job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	return rval;
 }
 
 static int
-qla84xx_reset(struct fc_bsg_job *bsg_job)
+qla84xx_reset(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_request *bsg_request = bsg_job->request;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	int rval = 0;
@@ -948,7 +963,7 @@ qla84xx_reset(struct fc_bsg_job *bsg_job)
 		return -EINVAL;
 	}
 
-	flag = bsg_job->request->rqst_data.h_vendor.vendor_cmd[1];
+	flag = bsg_request->rqst_data.h_vendor.vendor_cmd[1];
 
 	rval = qla84xx_reset_chip(vha, flag == A84_ISSUE_RESET_DIAG_FW);
 
@@ -960,17 +975,20 @@ qla84xx_reset(struct fc_bsg_job *bsg_job)
 	} else {
 		ql_dbg(ql_dbg_user, vha, 0x7031,
 		    "Vendor request 84xx reset completed.\n");
-		bsg_job->reply->result = DID_OK;
-		bsg_job->job_done(bsg_job);
+		bsg_reply->result = DID_OK;
+		bsg_job_done(bsg_job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	}
 
 	return rval;
 }
 
 static int
-qla84xx_updatefw(struct fc_bsg_job *bsg_job)
+qla84xx_updatefw(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_request *bsg_request = bsg_job->request;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	struct verify_chip_entry_84xx *mn = NULL;
@@ -1027,7 +1045,7 @@ qla84xx_updatefw(struct fc_bsg_job *bsg_job)
 		goto done_free_fw_buf;
 	}
 
-	flag = bsg_job->request->rqst_data.h_vendor.vendor_cmd[1];
+	flag = bsg_request->rqst_data.h_vendor.vendor_cmd[1];
 	fw_ver = le32_to_cpu(*((uint32_t *)((uint32_t *)fw_buf + 2)));
 
 	memset(mn, 0, sizeof(struct access_chip_84xx));
@@ -1059,7 +1077,7 @@ qla84xx_updatefw(struct fc_bsg_job *bsg_job)
 		    "Vendor request 84xx updatefw completed.\n");
 
 		bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-		bsg_job->reply->result = DID_OK;
+		bsg_reply->result = DID_OK;
 	}
 
 	dma_pool_free(ha->s_dma_pool, mn, mn_dma);
@@ -1072,14 +1090,17 @@ done_unmap_sg:
 		bsg_job->request_payload.sg_cnt, DMA_TO_DEVICE);
 
 	if (!rval)
-		bsg_job->job_done(bsg_job);
+		bsg_job_done(bsg_job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	return rval;
 }
 
 static int
-qla84xx_mgmt_cmd(struct fc_bsg_job *bsg_job)
+qla84xx_mgmt_cmd(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_request *bsg_request = bsg_job->request;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	struct access_chip_84xx *mn = NULL;
@@ -1107,7 +1128,7 @@ qla84xx_mgmt_cmd(struct fc_bsg_job *bsg_job)
 	memset(mn, 0, sizeof(struct access_chip_84xx));
 	mn->entry_type = ACCESS_CHIP_IOCB_TYPE;
 	mn->entry_count = 1;
-	ql84_mgmt = (void *)bsg_job->request + sizeof(struct fc_bsg_request);
+	ql84_mgmt = (void *)bsg_request + sizeof(struct fc_bsg_request);
 	switch (ql84_mgmt->mgmt.cmd) {
 	case QLA84_MGMT_READ_MEM:
 	case QLA84_MGMT_GET_INFO:
@@ -1239,11 +1260,11 @@ qla84xx_mgmt_cmd(struct fc_bsg_job *bsg_job)
 		    "Vendor request 84xx mgmt completed.\n");
 
 		bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-		bsg_job->reply->result = DID_OK;
+		bsg_reply->result = DID_OK;
 
 		if ((ql84_mgmt->mgmt.cmd == QLA84_MGMT_READ_MEM) ||
 			(ql84_mgmt->mgmt.cmd == QLA84_MGMT_GET_INFO)) {
-			bsg_job->reply->reply_payload_rcv_len =
+			bsg_reply->reply_payload_rcv_len =
 				bsg_job->reply_payload.payload_len;
 
 			sg_copy_from_buffer(bsg_job->reply_payload.sg_list,
@@ -1267,14 +1288,17 @@ exit_mgmt:
 	dma_pool_free(ha->s_dma_pool, mn, mn_dma);
 
 	if (!rval)
-		bsg_job->job_done(bsg_job);
+		bsg_job_done(bsg_job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	return rval;
 }
 
 static int
-qla24xx_iidma(struct fc_bsg_job *bsg_job)
+qla24xx_iidma(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_request *bsg_request = bsg_job->request;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	int rval = 0;
 	struct qla_port_param *port_param = NULL;
@@ -1288,7 +1312,7 @@ qla24xx_iidma(struct fc_bsg_job *bsg_job)
 		return -EINVAL;
 	}
 
-	port_param = (void *)bsg_job->request + sizeof(struct fc_bsg_request);
+	port_param = (void *)bsg_request + sizeof(struct fc_bsg_request);
 	if (port_param->fc_scsi_addr.dest_type != EXT_DEF_TYPE_WWPN) {
 		ql_log(ql_log_warn, vha, 0x7048,
 		    "Invalid destination type.\n");
@@ -1343,24 +1367,26 @@ qla24xx_iidma(struct fc_bsg_job *bsg_job)
 			bsg_job->reply_len = sizeof(struct fc_bsg_reply) +
 				sizeof(struct qla_port_param);
 
-			rsp_ptr = ((uint8_t *)bsg_job->reply) +
+			rsp_ptr = ((uint8_t *)bsg_reply) +
 				sizeof(struct fc_bsg_reply);
 
 			memcpy(rsp_ptr, port_param,
 				sizeof(struct qla_port_param));
 		}
 
-		bsg_job->reply->result = DID_OK;
-		bsg_job->job_done(bsg_job);
+		bsg_reply->result = DID_OK;
+		bsg_job_done(bsg_job, bsg_reply->result,
+			       bsg_reply->reply_payload_rcv_len);
 	}
 
 	return rval;
 }
 
 static int
-qla2x00_optrom_setup(struct fc_bsg_job *bsg_job, scsi_qla_host_t *vha,
+qla2x00_optrom_setup(struct bsg_job *bsg_job, scsi_qla_host_t *vha,
 	uint8_t is_update)
 {
+	struct fc_bsg_request *bsg_request = bsg_job->request;
 	uint32_t start = 0;
 	int valid = 0;
 	struct qla_hw_data *ha = vha->hw;
@@ -1368,7 +1394,7 @@ qla2x00_optrom_setup(struct fc_bsg_job *bsg_job, scsi_qla_host_t *vha,
 	if (unlikely(pci_channel_offline(ha->pdev)))
 		return -EINVAL;
 
-	start = bsg_job->request->rqst_data.h_vendor.vendor_cmd[1];
+	start = bsg_request->rqst_data.h_vendor.vendor_cmd[1];
 	if (start > ha->optrom_size) {
 		ql_log(ql_log_warn, vha, 0x7055,
 		    "start %d > optrom_size %d.\n", start, ha->optrom_size);
@@ -1427,9 +1453,10 @@ qla2x00_optrom_setup(struct fc_bsg_job *bsg_job, scsi_qla_host_t *vha,
 }
 
 static int
-qla2x00_read_optrom(struct fc_bsg_job *bsg_job)
+qla2x00_read_optrom(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	int rval = 0;
@@ -1451,20 +1478,22 @@ qla2x00_read_optrom(struct fc_bsg_job *bsg_job)
 	    bsg_job->reply_payload.sg_cnt, ha->optrom_buffer,
 	    ha->optrom_region_size);
 
-	bsg_job->reply->reply_payload_rcv_len = ha->optrom_region_size;
-	bsg_job->reply->result = DID_OK;
+	bsg_reply->reply_payload_rcv_len = ha->optrom_region_size;
+	bsg_reply->result = DID_OK;
 	vfree(ha->optrom_buffer);
 	ha->optrom_buffer = NULL;
 	ha->optrom_state = QLA_SWAITING;
 	mutex_unlock(&ha->optrom_mutex);
-	bsg_job->job_done(bsg_job);
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	return rval;
 }
 
 static int
-qla2x00_update_optrom(struct fc_bsg_job *bsg_job)
+qla2x00_update_optrom(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	int rval = 0;
@@ -1486,19 +1515,21 @@ qla2x00_update_optrom(struct fc_bsg_job *bsg_job)
 	ha->isp_ops->write_optrom(vha, ha->optrom_buffer,
 	    ha->optrom_region_start, ha->optrom_region_size);
 
-	bsg_job->reply->result = DID_OK;
+	bsg_reply->result = DID_OK;
 	vfree(ha->optrom_buffer);
 	ha->optrom_buffer = NULL;
 	ha->optrom_state = QLA_SWAITING;
 	mutex_unlock(&ha->optrom_mutex);
-	bsg_job->job_done(bsg_job);
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	return rval;
 }
 
 static int
-qla2x00_update_fru_versions(struct fc_bsg_job *bsg_job)
+qla2x00_update_fru_versions(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	int rval = 0;
@@ -1509,7 +1540,7 @@ qla2x00_update_fru_versions(struct fc_bsg_job *bsg_job)
 	dma_addr_t sfp_dma;
 	void *sfp = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &sfp_dma);
 	if (!sfp) {
-		bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+		bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 		    EXT_STATUS_NO_MEMORY;
 		goto done;
 	}
@@ -1525,30 +1556,32 @@ qla2x00_update_fru_versions(struct fc_bsg_job *bsg_job)
 		    image->field_address.device, image->field_address.offset,
 		    sizeof(image->field_info), image->field_address.option);
 		if (rval) {
-			bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+			bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 			    EXT_STATUS_MAILBOX;
 			goto dealloc;
 		}
 		image++;
 	}
 
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] = 0;
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] = 0;
 
 dealloc:
 	dma_pool_free(ha->s_dma_pool, sfp, sfp_dma);
 
 done:
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-	bsg_job->reply->result = DID_OK << 16;
-	bsg_job->job_done(bsg_job);
+	bsg_reply->result = DID_OK << 16;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 
 	return 0;
 }
 
 static int
-qla2x00_read_fru_status(struct fc_bsg_job *bsg_job)
+qla2x00_read_fru_status(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	int rval = 0;
@@ -1557,7 +1590,7 @@ qla2x00_read_fru_status(struct fc_bsg_job *bsg_job)
 	dma_addr_t sfp_dma;
 	uint8_t *sfp = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &sfp_dma);
 	if (!sfp) {
-		bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+		bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 		    EXT_STATUS_NO_MEMORY;
 		goto done;
 	}
@@ -1571,7 +1604,7 @@ qla2x00_read_fru_status(struct fc_bsg_job *bsg_job)
 	sr->status_reg = *sfp;
 
 	if (rval) {
-		bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+		bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 		    EXT_STATUS_MAILBOX;
 		goto dealloc;
 	}
@@ -1579,24 +1612,26 @@ qla2x00_read_fru_status(struct fc_bsg_job *bsg_job)
 	sg_copy_from_buffer(bsg_job->reply_payload.sg_list,
 	    bsg_job->reply_payload.sg_cnt, sr, sizeof(*sr));
 
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] = 0;
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] = 0;
 
 dealloc:
 	dma_pool_free(ha->s_dma_pool, sfp, sfp_dma);
 
 done:
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-	bsg_job->reply->reply_payload_rcv_len = sizeof(*sr);
-	bsg_job->reply->result = DID_OK << 16;
-	bsg_job->job_done(bsg_job);
+	bsg_reply->reply_payload_rcv_len = sizeof(*sr);
+	bsg_reply->result = DID_OK << 16;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 
 	return 0;
 }
 
 static int
-qla2x00_write_fru_status(struct fc_bsg_job *bsg_job)
+qla2x00_write_fru_status(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	int rval = 0;
@@ -1605,7 +1640,7 @@ qla2x00_write_fru_status(struct fc_bsg_job *bsg_job)
 	dma_addr_t sfp_dma;
 	uint8_t *sfp = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &sfp_dma);
 	if (!sfp) {
-		bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+		bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 		    EXT_STATUS_NO_MEMORY;
 		goto done;
 	}
@@ -1619,28 +1654,30 @@ qla2x00_write_fru_status(struct fc_bsg_job *bsg_job)
 	    sizeof(sr->status_reg), sr->field_address.option);
 
 	if (rval) {
-		bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+		bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 		    EXT_STATUS_MAILBOX;
 		goto dealloc;
 	}
 
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] = 0;
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] = 0;
 
 dealloc:
 	dma_pool_free(ha->s_dma_pool, sfp, sfp_dma);
 
 done:
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-	bsg_job->reply->result = DID_OK << 16;
-	bsg_job->job_done(bsg_job);
+	bsg_reply->result = DID_OK << 16;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 
 	return 0;
 }
 
 static int
-qla2x00_write_i2c(struct fc_bsg_job *bsg_job)
+qla2x00_write_i2c(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	int rval = 0;
@@ -1649,7 +1686,7 @@ qla2x00_write_i2c(struct fc_bsg_job *bsg_job)
 	dma_addr_t sfp_dma;
 	uint8_t *sfp = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &sfp_dma);
 	if (!sfp) {
-		bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+		bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 		    EXT_STATUS_NO_MEMORY;
 		goto done;
 	}
@@ -1662,28 +1699,30 @@ qla2x00_write_i2c(struct fc_bsg_job *bsg_job)
 	    i2c->device, i2c->offset, i2c->length, i2c->option);
 
 	if (rval) {
-		bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+		bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 		    EXT_STATUS_MAILBOX;
 		goto dealloc;
 	}
 
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] = 0;
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] = 0;
 
 dealloc:
 	dma_pool_free(ha->s_dma_pool, sfp, sfp_dma);
 
 done:
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-	bsg_job->reply->result = DID_OK << 16;
-	bsg_job->job_done(bsg_job);
+	bsg_reply->result = DID_OK << 16;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 
 	return 0;
 }
 
 static int
-qla2x00_read_i2c(struct fc_bsg_job *bsg_job)
+qla2x00_read_i2c(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	int rval = 0;
@@ -1692,7 +1731,7 @@ qla2x00_read_i2c(struct fc_bsg_job *bsg_job)
 	dma_addr_t sfp_dma;
 	uint8_t *sfp = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &sfp_dma);
 	if (!sfp) {
-		bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+		bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 		    EXT_STATUS_NO_MEMORY;
 		goto done;
 	}
@@ -1704,7 +1743,7 @@ qla2x00_read_i2c(struct fc_bsg_job *bsg_job)
 		i2c->device, i2c->offset, i2c->length, i2c->option);
 
 	if (rval) {
-		bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+		bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 		    EXT_STATUS_MAILBOX;
 		goto dealloc;
 	}
@@ -1713,24 +1752,26 @@ qla2x00_read_i2c(struct fc_bsg_job *bsg_job)
 	sg_copy_from_buffer(bsg_job->reply_payload.sg_list,
 	    bsg_job->reply_payload.sg_cnt, i2c, sizeof(*i2c));
 
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] = 0;
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] = 0;
 
 dealloc:
 	dma_pool_free(ha->s_dma_pool, sfp, sfp_dma);
 
 done:
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-	bsg_job->reply->reply_payload_rcv_len = sizeof(*i2c);
-	bsg_job->reply->result = DID_OK << 16;
-	bsg_job->job_done(bsg_job);
+	bsg_reply->reply_payload_rcv_len = sizeof(*i2c);
+	bsg_reply->result = DID_OK << 16;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 
 	return 0;
 }
 
 static int
-qla24xx_process_bidir_cmd(struct fc_bsg_job *bsg_job)
+qla24xx_process_bidir_cmd(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	uint32_t rval = EXT_STATUS_OK;
@@ -1895,19 +1936,21 @@ done:
 	/* Return an error vendor specific response
 	 * and complete the bsg request
 	 */
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] = rval;
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] = rval;
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-	bsg_job->reply->reply_payload_rcv_len = 0;
-	bsg_job->reply->result = (DID_OK) << 16;
-	bsg_job->job_done(bsg_job);
+	bsg_reply->reply_payload_rcv_len = 0;
+	bsg_reply->result = (DID_OK) << 16;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	/* Always return success, vendor rsp carries correct status */
 	return 0;
 }
 
 static int
-qlafx00_mgmt_cmd(struct fc_bsg_job *bsg_job)
+qlafx00_mgmt_cmd(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_request *bsg_request = bsg_job->request;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	int rval = (DRIVER_ERROR << 16);
@@ -1919,7 +1962,7 @@ qlafx00_mgmt_cmd(struct fc_bsg_job *bsg_job)
 
 	/* Copy the IOCB specific information */
 	piocb_rqst = (struct qla_mt_iocb_rqst_fx00 *)
-	    &bsg_job->request->rqst_data.h_vendor.vendor_cmd[1];
+	    &bsg_request->rqst_data.h_vendor.vendor_cmd[1];
 
 	/* Dump the vendor information */
 	ql_dump_buffer(ql_dbg_user + ql_dbg_verbose , vha, 0x70cf,
@@ -2027,9 +2070,10 @@ done:
 }
 
 static int
-qla26xx_serdes_op(struct fc_bsg_job *bsg_job)
+qla26xx_serdes_op(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	int rval = 0;
 	struct qla_serdes_reg sr;
@@ -2042,13 +2086,13 @@ qla26xx_serdes_op(struct fc_bsg_job *bsg_job)
 	switch (sr.cmd) {
 	case INT_SC_SERDES_WRITE_REG:
 		rval = qla2x00_write_serdes_word(vha, sr.addr, sr.val);
-		bsg_job->reply->reply_payload_rcv_len = 0;
+		bsg_reply->reply_payload_rcv_len = 0;
 		break;
 	case INT_SC_SERDES_READ_REG:
 		rval = qla2x00_read_serdes_word(vha, sr.addr, &sr.val);
 		sg_copy_from_buffer(bsg_job->reply_payload.sg_list,
 		    bsg_job->reply_payload.sg_cnt, &sr, sizeof(sr));
-		bsg_job->reply->reply_payload_rcv_len = sizeof(sr);
+		bsg_reply->reply_payload_rcv_len = sizeof(sr);
 		break;
 	default:
 		ql_dbg(ql_dbg_user, vha, 0x708c,
@@ -2057,19 +2101,21 @@ qla26xx_serdes_op(struct fc_bsg_job *bsg_job)
 		break;
 	}
 
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 	    rval ? EXT_STATUS_MAILBOX : 0;
 
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-	bsg_job->reply->result = DID_OK << 16;
-	bsg_job->job_done(bsg_job);
+	bsg_reply->result = DID_OK << 16;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	return 0;
 }
 
 static int
-qla8044_serdes_op(struct fc_bsg_job *bsg_job)
+qla8044_serdes_op(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	int rval = 0;
 	struct qla_serdes_reg_ex sr;
@@ -2082,13 +2128,13 @@ qla8044_serdes_op(struct fc_bsg_job *bsg_job)
 	switch (sr.cmd) {
 	case INT_SC_SERDES_WRITE_REG:
 		rval = qla8044_write_serdes_word(vha, sr.addr, sr.val);
-		bsg_job->reply->reply_payload_rcv_len = 0;
+		bsg_reply->reply_payload_rcv_len = 0;
 		break;
 	case INT_SC_SERDES_READ_REG:
 		rval = qla8044_read_serdes_word(vha, sr.addr, &sr.val);
 		sg_copy_from_buffer(bsg_job->reply_payload.sg_list,
 		    bsg_job->reply_payload.sg_cnt, &sr, sizeof(sr));
-		bsg_job->reply->reply_payload_rcv_len = sizeof(sr);
+		bsg_reply->reply_payload_rcv_len = sizeof(sr);
 		break;
 	default:
 		ql_dbg(ql_dbg_user, vha, 0x70cf,
@@ -2097,19 +2143,21 @@ qla8044_serdes_op(struct fc_bsg_job *bsg_job)
 		break;
 	}
 
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 	    rval ? EXT_STATUS_MAILBOX : 0;
 
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-	bsg_job->reply->result = DID_OK << 16;
-	bsg_job->job_done(bsg_job);
+	bsg_reply->result = DID_OK << 16;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	return 0;
 }
 
 static int
-qla27xx_get_flash_upd_cap(struct fc_bsg_job *bsg_job)
+qla27xx_get_flash_upd_cap(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	struct qla_flash_update_caps cap;
@@ -2125,21 +2173,23 @@ qla27xx_get_flash_upd_cap(struct fc_bsg_job *bsg_job)
 
 	sg_copy_from_buffer(bsg_job->reply_payload.sg_list,
 	    bsg_job->reply_payload.sg_cnt, &cap, sizeof(cap));
-	bsg_job->reply->reply_payload_rcv_len = sizeof(cap);
+	bsg_reply->reply_payload_rcv_len = sizeof(cap);
 
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 	    EXT_STATUS_OK;
 
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-	bsg_job->reply->result = DID_OK << 16;
-	bsg_job->job_done(bsg_job);
+	bsg_reply->result = DID_OK << 16;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	return 0;
 }
 
 static int
-qla27xx_set_flash_upd_cap(struct fc_bsg_job *bsg_job)
+qla27xx_set_flash_upd_cap(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	uint64_t online_fw_attr = 0;
@@ -2158,32 +2208,34 @@ qla27xx_set_flash_upd_cap(struct fc_bsg_job *bsg_job)
 			 (uint64_t)ha->fw_attributes;
 
 	if (online_fw_attr != cap.capabilities) {
-		bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+		bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 		    EXT_STATUS_INVALID_PARAM;
 		return -EINVAL;
 	}
 
 	if (cap.outage_duration < MAX_LOOP_TIMEOUT)  {
-		bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+		bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 		    EXT_STATUS_INVALID_PARAM;
 		return -EINVAL;
 	}
 
-	bsg_job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 	    EXT_STATUS_OK;
 
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-	bsg_job->reply->result = DID_OK << 16;
-	bsg_job->job_done(bsg_job);
+	bsg_reply->result = DID_OK << 16;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	return 0;
 }
 
 static int
-qla27xx_get_bbcr_data(struct fc_bsg_job *bsg_job)
+qla27xx_get_bbcr_data(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	struct qla_bbcr_data bbcr;
@@ -2227,27 +2279,30 @@ qla27xx_get_bbcr_data(struct fc_bsg_job *bsg_job)
 done:
 	sg_copy_from_buffer(bsg_job->reply_payload.sg_list,
 		bsg_job->reply_payload.sg_cnt, &bbcr, sizeof(bbcr));
-	bsg_job->reply->reply_payload_rcv_len = sizeof(bbcr);
+	bsg_reply->reply_payload_rcv_len = sizeof(bbcr);
 
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] = EXT_STATUS_OK;
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] = EXT_STATUS_OK;
 
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
-	bsg_job->reply->result = DID_OK << 16;
-	bsg_job->job_done(bsg_job);
+	bsg_reply->result = DID_OK << 16;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 	return 0;
 }
 
 static int
-qla2x00_get_priv_stats(struct fc_bsg_job *bsg_job)
+qla2x00_get_priv_stats(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_request *bsg_request = bsg_job->request;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
 	struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
 	struct link_statistics *stats = NULL;
 	dma_addr_t stats_dma;
 	int rval;
-	uint32_t *cmd = bsg_job->request->rqst_data.h_vendor.vendor_cmd;
+	uint32_t *cmd = bsg_request->rqst_data.h_vendor.vendor_cmd;
 	uint options = cmd[0] == QL_VND_GET_PRIV_STATS_EX ? cmd[1] : 0;
 
 	if (test_bit(UNLOADING, &vha->dpc_flags))
@@ -2281,13 +2336,14 @@ qla2x00_get_priv_stats(struct fc_bsg_job *bsg_job)
 			bsg_job->reply_payload.sg_cnt, stats, sizeof(*stats));
 	}
 
-	bsg_job->reply->reply_payload_rcv_len = sizeof(*stats);
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+	bsg_reply->reply_payload_rcv_len = sizeof(*stats);
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 	    rval ? EXT_STATUS_MAILBOX : EXT_STATUS_OK;
 
-	bsg_job->reply_len = sizeof(*bsg_job->reply);
-	bsg_job->reply->result = DID_OK << 16;
-	bsg_job->job_done(bsg_job);
+	bsg_job->reply_len = sizeof(*bsg_reply);
+	bsg_reply->result = DID_OK << 16;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 
 	dma_free_coherent(&ha->pdev->dev, sizeof(*stats),
 		stats, stats_dma);
@@ -2296,9 +2352,10 @@ qla2x00_get_priv_stats(struct fc_bsg_job *bsg_job)
 }
 
 static int
-qla2x00_do_dport_diagnostics(struct fc_bsg_job *bsg_job)
+qla2x00_do_dport_diagnostics(struct bsg_job *bsg_job)
 {
-	struct Scsi_Host *host = bsg_job->shost;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	int rval;
 	struct qla_dport_diag *dd;
@@ -2323,13 +2380,14 @@ qla2x00_do_dport_diagnostics(struct fc_bsg_job *bsg_job)
 		    bsg_job->reply_payload.sg_cnt, dd, sizeof(*dd));
 	}
 
-	bsg_job->reply->reply_payload_rcv_len = sizeof(*dd);
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+	bsg_reply->reply_payload_rcv_len = sizeof(*dd);
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] =
 	    rval ? EXT_STATUS_MAILBOX : EXT_STATUS_OK;
 
-	bsg_job->reply_len = sizeof(*bsg_job->reply);
-	bsg_job->reply->result = DID_OK << 16;
-	bsg_job->job_done(bsg_job);
+	bsg_job->reply_len = sizeof(*bsg_reply);
+	bsg_reply->result = DID_OK << 16;
+	bsg_job_done(bsg_job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
 
 	kfree(dd);
 
@@ -2337,9 +2395,11 @@ qla2x00_do_dport_diagnostics(struct fc_bsg_job *bsg_job)
 }
 
 static int
-qla2x00_process_vendor_specific(struct fc_bsg_job *bsg_job)
+qla2x00_process_vendor_specific(struct bsg_job *bsg_job)
 {
-	switch (bsg_job->request->rqst_data.h_vendor.vendor_cmd[0]) {
+	struct fc_bsg_request *bsg_request = bsg_job->request;
+
+	switch (bsg_request->rqst_data.h_vendor.vendor_cmd[0]) {
 	case QL_VND_LOOPBACK:
 		return qla2x00_process_loopback(bsg_job);
 
@@ -2413,36 +2473,38 @@ qla2x00_process_vendor_specific(struct fc_bsg_job *bsg_job)
 }
 
 int
-qla24xx_bsg_request(struct fc_bsg_job *bsg_job)
+qla24xx_bsg_request(struct bsg_job *bsg_job)
 {
+	struct fc_bsg_request *bsg_request = bsg_job->request;
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
 	int ret = -EINVAL;
 	struct fc_rport *rport;
 	struct Scsi_Host *host;
 	scsi_qla_host_t *vha;
 
 	/* In case no data transferred. */
-	bsg_job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 
-	if (bsg_job->request->msgcode == FC_BSG_RPT_ELS) {
-		rport = bsg_job->rport;
+	if (bsg_request->msgcode == FC_BSG_RPT_ELS) {
+		rport = fc_bsg_to_rport(bsg_job);
 		host = rport_to_shost(rport);
 		vha = shost_priv(host);
 	} else {
-		host = bsg_job->shost;
+		host = fc_bsg_to_shost(bsg_job);
 		vha = shost_priv(host);
 	}
 
 	if (qla2x00_reset_active(vha)) {
 		ql_dbg(ql_dbg_user, vha, 0x709f,
 		    "BSG: ISP abort active/needed -- cmd=%d.\n",
-		    bsg_job->request->msgcode);
+		    bsg_request->msgcode);
 		return -EBUSY;
 	}
 
 	ql_dbg(ql_dbg_user, vha, 0x7000,
-	    "Entered %s msgcode=0x%x.\n", __func__, bsg_job->request->msgcode);
+	    "Entered %s msgcode=0x%x.\n", __func__, bsg_request->msgcode);
 
-	switch (bsg_job->request->msgcode) {
+	switch (bsg_request->msgcode) {
 	case FC_BSG_RPT_ELS:
 	case FC_BSG_HST_ELS_NOLOGIN:
 		ret = qla2x00_process_els(bsg_job);
@@ -2464,9 +2526,10 @@ qla24xx_bsg_request(struct fc_bsg_job *bsg_job)
 }
 
 int
-qla24xx_bsg_timeout(struct fc_bsg_job *bsg_job)
+qla24xx_bsg_timeout(struct bsg_job *bsg_job)
 {
-	scsi_qla_host_t *vha = shost_priv(bsg_job->shost);
+	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+	scsi_qla_host_t *vha = shost_priv(fc_bsg_to_shost(bsg_job));
 	struct qla_hw_data *ha = vha->hw;
 	srb_t *sp;
 	int cnt, que;
@@ -2494,13 +2557,13 @@ qla24xx_bsg_timeout(struct fc_bsg_job *bsg_job)
 						    "mbx abort_command "
 						    "failed.\n");
 						bsg_job->req->errors =
-						bsg_job->reply->result = -EIO;
+						bsg_reply->result = -EIO;
 					} else {
 						ql_dbg(ql_dbg_user, vha, 0x708a,
 						    "mbx abort_command "
 						    "success.\n");
 						bsg_job->req->errors =
-						bsg_job->reply->result = 0;
+						bsg_reply->result = 0;
 					}
 					spin_lock_irqsave(&ha->hardware_lock, flags);
 					goto done;
@@ -2510,7 +2573,7 @@ qla24xx_bsg_timeout(struct fc_bsg_job *bsg_job)
 	}
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 	ql_log(ql_log_info, vha, 0x708b, "SRB not found to abort.\n");
-	bsg_job->req->errors = bsg_job->reply->result = -ENXIO;
+	bsg_job->req->errors = bsg_reply->result = -ENXIO;
 	return 0;
 
 done:
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 45af34ddc432..21d9fb7fc887 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -11,7 +11,7 @@
  * ----------------------------------------------------------------------
  * |             Level            |   Last Value Used  |     Holes	|
  * ----------------------------------------------------------------------
- * | Module Init and Probe        |       0x0191       | 0x0146         |
+ * | Module Init and Probe        |       0x0193       | 0x0146         |
  * |                              |                    | 0x015b-0x0160	|
  * |                              |                    | 0x016e		|
  * | Mailbox commands             |       0x1199       | 0x1193		|
@@ -58,7 +58,7 @@
  * |                              |                    | 0xb13a,0xb142  |
  * |                              |                    | 0xb13c-0xb140  |
  * |                              |                    | 0xb149		|
- * | MultiQ                       |       0xc00c       |		|
+ * | MultiQ                       |       0xc010       |		|
  * | Misc                         |       0xd301       | 0xd031-0xd0ff	|
  * |                              |                    | 0xd101-0xd1fe	|
  * |                              |                    | 0xd214-0xd2fe	|
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 73b12e41d992..f7df01b76714 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -401,9 +401,10 @@ typedef struct srb {
 	uint16_t type;
 	char *name;
 	int iocbs;
+	struct qla_qpair *qpair;
 	union {
 		struct srb_iocb iocb_cmd;
-		struct fc_bsg_job *bsg_job;
+		struct bsg_job *bsg_job;
 		struct srb_cmd scmd;
 	} u;
 	void (*done)(void *, void *, int);
@@ -2719,6 +2720,7 @@ struct isp_operations {
 
 	int (*get_flash_version) (struct scsi_qla_host *, void *);
 	int (*start_scsi) (srb_t *);
+	int (*start_scsi_mq) (srb_t *);
 	int (*abort_isp) (struct scsi_qla_host *);
 	int (*iospace_config)(struct qla_hw_data*);
 	int (*initialize_adapter)(struct scsi_qla_host *);
@@ -2730,8 +2732,10 @@ struct isp_operations {
 #define QLA_MSIX_FW_MODE(m)	(((m) & (BIT_7|BIT_8|BIT_9)) >> 7)
 #define QLA_MSIX_FW_MODE_1(m)	(QLA_MSIX_FW_MODE(m) == 1)
 
-#define QLA_MSIX_DEFAULT	0x00
-#define QLA_MSIX_RSP_Q		0x01
+#define QLA_MSIX_DEFAULT		0x00
+#define QLA_MSIX_RSP_Q			0x01
+#define QLA_ATIO_VECTOR		0x02
+#define QLA_MSIX_QPAIR_MULTIQ_RSP_Q	0x03
 
 #define QLA_MIDX_DEFAULT	0
 #define QLA_MIDX_RSP_Q		1
@@ -2745,9 +2749,11 @@ struct scsi_qla_host;
 
 struct qla_msix_entry {
 	int have_irq;
+	int in_use;
 	uint32_t vector;
 	uint16_t entry;
-	struct rsp_que *rsp;
+	char name[30];
+	void *handle;
 	struct irq_affinity_notify irq_notify;
 	int cpuid;
 };
@@ -2872,7 +2878,6 @@ struct rsp_que {
 	struct qla_msix_entry *msix;
 	struct req_que *req;
 	srb_t *status_srb; /* status continuation entry */
-	struct work_struct q_work;
 
 	dma_addr_t  dma_fx00;
 	response_t *ring_fx00;
@@ -2909,6 +2914,37 @@ struct req_que {
 	uint8_t req_pkt[REQUEST_ENTRY_SIZE];
 };
 
+/*Queue pair data structure */
+struct qla_qpair {
+	spinlock_t qp_lock;
+	atomic_t ref_count;
+	/* distill these fields down to 'online=0/1'
+	 * ha->flags.eeh_busy
+	 * ha->flags.pci_channel_io_perm_failure
+	 * base_vha->loop_state
+	 */
+	uint32_t online:1;
+	/* move vha->flags.difdix_supported here */
+	uint32_t difdix_supported:1;
+	uint32_t delete_in_progress:1;
+
+	uint16_t id;			/* qp number used with FW */
+	uint16_t num_active_cmd;	/* cmds down at firmware */
+	cpumask_t cpu_mask; /* CPU mask for cpu affinity operation */
+	uint16_t vp_idx;		/* vport ID */
+
+	mempool_t *srb_mempool;
+
+	/* to do: New driver: move queues to here instead of pointers */
+	struct req_que *req;
+	struct rsp_que *rsp;
+	struct atio_que *atio;
+	struct qla_msix_entry *msix; /* point to &ha->msix_entries[x] */
+	struct qla_hw_data *hw;
+	struct work_struct q_work;
+	struct list_head qp_list_elem; /* vha->qp_list */
+};
+
 /* Place holder for FW buffer parameters */
 struct qlfc_fw {
 	void *fw_buf;
@@ -3004,7 +3040,6 @@ struct qla_hw_data {
 		uint32_t	chip_reset_done		:1;
 		uint32_t	running_gold_fw		:1;
 		uint32_t	eeh_busy		:1;
-		uint32_t	cpu_affinity_enabled	:1;
 		uint32_t	disable_msix_handshake	:1;
 		uint32_t	fcp_prio_enabled	:1;
 		uint32_t	isp82xx_fw_hung:1;
@@ -3061,10 +3096,15 @@ struct qla_hw_data {
 	uint8_t         mqenable;
 	struct req_que **req_q_map;
 	struct rsp_que **rsp_q_map;
+	struct qla_qpair **queue_pair_map;
 	unsigned long req_qid_map[(QLA_MAX_QUEUES / 8) / sizeof(unsigned long)];
 	unsigned long rsp_qid_map[(QLA_MAX_QUEUES / 8) / sizeof(unsigned long)];
+	unsigned long qpair_qid_map[(QLA_MAX_QUEUES / 8)
+		/ sizeof(unsigned long)];
 	uint8_t 	max_req_queues;
 	uint8_t 	max_rsp_queues;
+	uint8_t		max_qpairs;
+	struct qla_qpair *base_qpair;
 	struct qla_npiv_entry *npiv_info;
 	uint16_t	nvram_npiv_size;
 
@@ -3328,6 +3368,7 @@ struct qla_hw_data {
 
 	struct mutex vport_lock;        /* Virtual port synchronization */
 	spinlock_t vport_slock; /* order is hardware_lock, then vport_slock */
+	struct mutex mq_lock;        /* multi-queue synchronization */
 	struct completion mbx_cmd_comp; /* Serialize mbx access */
 	struct completion mbx_intr_comp;  /* Used for completion notification */
 	struct completion dcbx_comp;	/* For set port config notification */
@@ -3608,6 +3649,7 @@ typedef struct scsi_qla_host {
 
 		uint32_t	fw_tgt_reported:1;
 		uint32_t	bbcr_enable:1;
+		uint32_t	qpairs_available:1;
 	} flags;
 
 	atomic_t	loop_state;
@@ -3646,6 +3688,7 @@ typedef struct scsi_qla_host {
 #define FX00_TARGET_SCAN	24
 #define FX00_CRITEMP_RECOVERY	25
 #define FX00_HOST_INFO_RESEND	26
+#define QPAIR_ONLINE_CHECK_NEEDED	27
 
 	unsigned long	pci_flags;
 #define PFLG_DISCONNECTED	0	/* PCI device removed */
@@ -3704,10 +3747,13 @@ typedef struct scsi_qla_host {
 	/* List of pending PLOGI acks, protected by hw lock */
 	struct list_head	plogi_ack_list;
 
+	struct list_head	qp_list;
+
 	uint32_t	vp_abort_cnt;
 
 	struct fc_vport	*fc_vport;	/* holds fc_vport * for each vport */
 	uint16_t        vp_idx;		/* vport ID */
+	struct qla_qpair *qpair;	/* base qpair */
 
 	unsigned long		vp_flags;
 #define VP_IDX_ACQUIRED		0	/* bit no 0 */
@@ -3763,6 +3809,23 @@ struct qla_tgt_vp_map {
 	scsi_qla_host_t *vha;
 };
 
+struct qla2_sgx {
+	dma_addr_t		dma_addr;	/* OUT */
+	uint32_t		dma_len;	/* OUT */
+
+	uint32_t		tot_bytes;	/* IN */
+	struct scatterlist	*cur_sg;	/* IN */
+
+	/* for book keeping, bzero on initial invocation */
+	uint32_t		bytes_consumed;
+	uint32_t		num_bytes;
+	uint32_t		tot_partial;
+
+	/* for debugging */
+	uint32_t		num_sg;
+	srb_t			*sp;
+};
+
 /*
  * Macros to help code, maintain, etc.
  */
@@ -3775,21 +3838,34 @@ struct qla_tgt_vp_map {
 		(test_bit(ISP_ABORT_NEEDED, &ha->dpc_flags) || \
 			 test_bit(LOOP_RESYNC_NEEDED, &ha->dpc_flags))
 
-#define QLA_VHA_MARK_BUSY(__vha, __bail) do {		     \
-	atomic_inc(&__vha->vref_count);			     \
-	mb();						     \
-	if (__vha->flags.delete_progress) {		     \
-		atomic_dec(&__vha->vref_count);		     \
-		__bail = 1;				     \
-	} else {					     \
-		__bail = 0;				     \
-	}						     \
+#define QLA_VHA_MARK_BUSY(__vha, __bail) do {		\
+	atomic_inc(&__vha->vref_count);			\
+	mb();						\
+	if (__vha->flags.delete_progress) {		\
+		atomic_dec(&__vha->vref_count);		\
+		__bail = 1;				\
+	} else {					\
+		__bail = 0;				\
+	}						\
 } while (0)
 
-#define QLA_VHA_MARK_NOT_BUSY(__vha) do {		     \
-	atomic_dec(&__vha->vref_count);			     \
+#define QLA_VHA_MARK_NOT_BUSY(__vha)			\
+	atomic_dec(&__vha->vref_count);			\
+
+#define QLA_QPAIR_MARK_BUSY(__qpair, __bail) do {	\
+	atomic_inc(&__qpair->ref_count);		\
+	mb();						\
+	if (__qpair->delete_in_progress) {		\
+		atomic_dec(&__qpair->ref_count);	\
+		__bail = 1;				\
+	} else {					\
+	       __bail = 0;				\
+	}						\
 } while (0)
 
+#define QLA_QPAIR_MARK_NOT_BUSY(__qpair)		\
+	atomic_dec(&__qpair->ref_count);		\
+
 /*
  * qla2x00 local function return status codes
  */
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index 6ca00813c71f..afa0116a163b 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -91,12 +91,17 @@ extern int
 qla2x00_alloc_outstanding_cmds(struct qla_hw_data *, struct req_que *);
 extern int qla2x00_init_rings(scsi_qla_host_t *);
 extern uint8_t qla27xx_find_valid_image(struct scsi_qla_host *);
+extern struct qla_qpair *qla2xxx_create_qpair(struct scsi_qla_host *,
+	int, int);
+extern int qla2xxx_delete_qpair(struct scsi_qla_host *, struct qla_qpair *);
 
 /*
  * Global Data in qla_os.c source file.
  */
 extern char qla2x00_version_str[];
 
+extern struct kmem_cache *srb_cachep;
+
 extern int ql2xlogintimeout;
 extern int qlport_down_retry;
 extern int ql2xplogiabsentdevice;
@@ -105,8 +110,7 @@ extern int ql2xfdmienable;
 extern int ql2xallocfwdump;
 extern int ql2xextended_error_logging;
 extern int ql2xiidmaenable;
-extern int ql2xmaxqueues;
-extern int ql2xmultique_tag;
+extern int ql2xmqsupport;
 extern int ql2xfwloadbin;
 extern int ql2xetsenable;
 extern int ql2xshiftctondsd;
@@ -172,6 +176,9 @@ extern int qla2x00_post_uevent_work(struct scsi_qla_host *, u32);
 
 extern int qla2x00_post_uevent_work(struct scsi_qla_host *, u32);
 extern void qla2x00_disable_board_on_pci_error(struct work_struct *);
+extern void qla2x00_sp_compl(void *, void *, int);
+extern void qla2xxx_qpair_sp_free_dma(void *, void *);
+extern void qla2xxx_qpair_sp_compl(void *, void *, int);
 
 /*
  * Global Functions in qla_mid.c source file.
@@ -220,6 +227,8 @@ extern uint16_t qla2x00_calc_iocbs_32(uint16_t);
 extern uint16_t qla2x00_calc_iocbs_64(uint16_t);
 extern void qla2x00_build_scsi_iocbs_32(srb_t *, cmd_entry_t *, uint16_t);
 extern void qla2x00_build_scsi_iocbs_64(srb_t *, cmd_entry_t *, uint16_t);
+extern void qla24xx_build_scsi_iocbs(srb_t *, struct cmd_type_7 *,
+	uint16_t, struct req_que *);
 extern int qla2x00_start_scsi(srb_t *sp);
 extern int qla24xx_start_scsi(srb_t *sp);
 int qla2x00_marker(struct scsi_qla_host *, struct req_que *, struct rsp_que *,
@@ -227,6 +236,7 @@ int qla2x00_marker(struct scsi_qla_host *, struct req_que *, struct rsp_que *,
 extern int qla2x00_start_sp(srb_t *);
 extern int qla24xx_dif_start_scsi(srb_t *);
 extern int qla2x00_start_bidir(srb_t *, struct scsi_qla_host *, uint32_t);
+extern int qla2xxx_dif_start_scsi_mq(srb_t *);
 extern unsigned long qla2x00_get_async_timeout(struct scsi_qla_host *);
 
 extern void *qla2x00_alloc_iocbs(scsi_qla_host_t *, srb_t *);
@@ -237,7 +247,10 @@ extern int qla24xx_walk_and_build_sglist(struct qla_hw_data *, srb_t *,
 	uint32_t *, uint16_t, struct qla_tgt_cmd *);
 extern int qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *, srb_t *,
 	uint32_t *, uint16_t, struct qla_tgt_cmd *);
-
+extern int qla24xx_get_one_block_sg(uint32_t, struct qla2_sgx *, uint32_t *);
+extern int qla24xx_configure_prot_mode(srb_t *, uint16_t *);
+extern int qla24xx_build_scsi_crc_2_iocbs(srb_t *,
+	struct cmd_type_crc_2 *, uint16_t, uint16_t, uint16_t);
 
 /*
  * Global Function Prototypes in qla_mbx.c source file.
@@ -468,6 +481,8 @@ qla2x00_get_sp_from_handle(scsi_qla_host_t *, const char *, struct req_que *,
 extern void
 qla2x00_process_completed_request(struct scsi_qla_host *, struct req_que *,
 	uint32_t);
+extern irqreturn_t
+qla2xxx_msix_rsp_q(int irq, void *dev_id);
 
 /*
  * Global Function Prototypes in qla_sup.c source file.
@@ -603,15 +618,18 @@ extern int qla2x00_dfs_setup(scsi_qla_host_t *);
 extern int qla2x00_dfs_remove(scsi_qla_host_t *);
 
 /* Globa function prototypes for multi-q */
-extern int qla25xx_request_irq(struct rsp_que *);
+extern int qla25xx_request_irq(struct qla_hw_data *, struct qla_qpair *,
+	struct qla_msix_entry *, int);
 extern int qla25xx_init_req_que(struct scsi_qla_host *, struct req_que *);
 extern int qla25xx_init_rsp_que(struct scsi_qla_host *, struct rsp_que *);
 extern int qla25xx_create_req_que(struct qla_hw_data *, uint16_t, uint8_t,
 	uint16_t, int, uint8_t);
 extern int qla25xx_create_rsp_que(struct qla_hw_data *, uint16_t, uint8_t,
-	uint16_t, int);
+	uint16_t, struct qla_qpair *);
+
 extern void qla2x00_init_response_q_entries(struct rsp_que *);
 extern int qla25xx_delete_req_que(struct scsi_qla_host *, struct req_que *);
+extern int qla25xx_delete_rsp_que(struct scsi_qla_host *, struct rsp_que *);
 extern int qla25xx_delete_queues(struct scsi_qla_host *);
 extern uint16_t qla24xx_rd_req_reg(struct qla_hw_data *, uint16_t);
 extern uint16_t qla25xx_rd_req_reg(struct qla_hw_data *, uint16_t);
@@ -733,8 +751,8 @@ extern int qla82xx_read_temperature(scsi_qla_host_t *);
 extern int qla8044_read_temperature(scsi_qla_host_t *);
 
 /* BSG related functions */
-extern int qla24xx_bsg_request(struct fc_bsg_job *);
-extern int qla24xx_bsg_timeout(struct fc_bsg_job *);
+extern int qla24xx_bsg_request(struct bsg_job *);
+extern int qla24xx_bsg_timeout(struct bsg_job *);
 extern int qla84xx_reset_chip(scsi_qla_host_t *, uint16_t);
 extern int qla2x00_issue_iocb_timeout(scsi_qla_host_t *, void *,
 	dma_addr_t, size_t, uint32_t);
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 5b09296b46a3..632d5f30386a 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -1769,8 +1769,7 @@ qla2x00_alloc_outstanding_cmds(struct qla_hw_data *ha, struct req_que *req)
 	if (req->outstanding_cmds)
 		return QLA_SUCCESS;
 
-	if (!IS_FWI2_CAPABLE(ha) || (ha->mqiobase &&
-	    (ql2xmultique_tag || ql2xmaxqueues > 1)))
+	if (!IS_FWI2_CAPABLE(ha))
 		req->num_outstanding_cmds = DEFAULT_OUTSTANDING_COMMANDS;
 	else {
 		if (ha->cur_fw_xcb_count <= ha->cur_fw_iocb_count)
@@ -4248,10 +4247,7 @@ qla2x00_loop_resync(scsi_qla_host_t *vha)
 	struct req_que *req;
 	struct rsp_que *rsp;
 
-	if (vha->hw->flags.cpu_affinity_enabled)
-		req = vha->hw->req_q_map[0];
-	else
-		req = vha->req;
+	req = vha->req;
 	rsp = req->rsp;
 
 	clear_bit(ISP_ABORT_RETRY, &vha->dpc_flags);
@@ -6040,10 +6036,10 @@ qla24xx_configure_vhba(scsi_qla_host_t *vha)
 		return -EINVAL;
 
 	rval = qla2x00_fw_ready(base_vha);
-	if (ha->flags.cpu_affinity_enabled)
-		req = ha->req_q_map[0];
+	if (vha->qpair)
+		req = vha->qpair->req;
 	else
-		req = vha->req;
+		req = ha->req_q_map[0];
 	rsp = req->rsp;
 
 	if (rval == QLA_SUCCESS) {
@@ -6725,3 +6721,162 @@ qla24xx_update_all_fcp_prio(scsi_qla_host_t *vha)
 
 	return ret;
 }
+
+struct qla_qpair *qla2xxx_create_qpair(struct scsi_qla_host *vha, int qos, int vp_idx)
+{
+	int rsp_id = 0;
+	int  req_id = 0;
+	int i;
+	struct qla_hw_data *ha = vha->hw;
+	uint16_t qpair_id = 0;
+	struct qla_qpair *qpair = NULL;
+	struct qla_msix_entry *msix;
+
+	if (!(ha->fw_attributes & BIT_6) || !ha->flags.msix_enabled) {
+		ql_log(ql_log_warn, vha, 0x00181,
+		    "FW/Driver is not multi-queue capable.\n");
+		return NULL;
+	}
+
+	if (ql2xmqsupport) {
+		qpair = kzalloc(sizeof(struct qla_qpair), GFP_KERNEL);
+		if (qpair == NULL) {
+			ql_log(ql_log_warn, vha, 0x0182,
+			    "Failed to allocate memory for queue pair.\n");
+			return NULL;
+		}
+		memset(qpair, 0, sizeof(struct qla_qpair));
+
+		qpair->hw = vha->hw;
+
+		/* Assign available que pair id */
+		mutex_lock(&ha->mq_lock);
+		qpair_id = find_first_zero_bit(ha->qpair_qid_map, ha->max_qpairs);
+		if (qpair_id >= ha->max_qpairs) {
+			mutex_unlock(&ha->mq_lock);
+			ql_log(ql_log_warn, vha, 0x0183,
+			    "No resources to create additional q pair.\n");
+			goto fail_qid_map;
+		}
+		set_bit(qpair_id, ha->qpair_qid_map);
+		ha->queue_pair_map[qpair_id] = qpair;
+		qpair->id = qpair_id;
+		qpair->vp_idx = vp_idx;
+
+		for (i = 0; i < ha->msix_count; i++) {
+			msix = &ha->msix_entries[i];
+			if (msix->in_use)
+				continue;
+			qpair->msix = msix;
+			ql_log(ql_dbg_multiq, vha, 0xc00f,
+			    "Vector %x selected for qpair\n", msix->vector);
+			break;
+		}
+		if (!qpair->msix) {
+			ql_log(ql_log_warn, vha, 0x0184,
+			    "Out of MSI-X vectors!.\n");
+			goto fail_msix;
+		}
+
+		qpair->msix->in_use = 1;
+		list_add_tail(&qpair->qp_list_elem, &vha->qp_list);
+
+		mutex_unlock(&ha->mq_lock);
+
+		/* Create response queue first */
+		rsp_id = qla25xx_create_rsp_que(ha, 0, 0, 0, qpair);
+		if (!rsp_id) {
+			ql_log(ql_log_warn, vha, 0x0185,
+			    "Failed to create response queue.\n");
+			goto fail_rsp;
+		}
+
+		qpair->rsp = ha->rsp_q_map[rsp_id];
+
+		/* Create request queue */
+		req_id = qla25xx_create_req_que(ha, 0, vp_idx, 0, rsp_id, qos);
+		if (!req_id) {
+			ql_log(ql_log_warn, vha, 0x0186,
+			    "Failed to create request queue.\n");
+			goto fail_req;
+		}
+
+		qpair->req = ha->req_q_map[req_id];
+		qpair->rsp->req = qpair->req;
+
+		if (IS_T10_PI_CAPABLE(ha) && ql2xenabledif) {
+			if (ha->fw_attributes & BIT_4)
+				qpair->difdix_supported = 1;
+		}
+
+		qpair->srb_mempool = mempool_create_slab_pool(SRB_MIN_REQ, srb_cachep);
+		if (!qpair->srb_mempool) {
+			ql_log(ql_log_warn, vha, 0x0191,
+			    "Failed to create srb mempool for qpair %d\n",
+			    qpair->id);
+			goto fail_mempool;
+		}
+
+		/* Mark as online */
+		qpair->online = 1;
+
+		if (!vha->flags.qpairs_available)
+			vha->flags.qpairs_available = 1;
+
+		ql_dbg(ql_dbg_multiq, vha, 0xc00d,
+		    "Request/Response queue pair created, id %d\n",
+		    qpair->id);
+		ql_dbg(ql_dbg_init, vha, 0x0187,
+		    "Request/Response queue pair created, id %d\n",
+		    qpair->id);
+	}
+	return qpair;
+
+fail_mempool:
+fail_req:
+	qla25xx_delete_rsp_que(vha, qpair->rsp);
+fail_rsp:
+	mutex_lock(&ha->mq_lock);
+	qpair->msix->in_use = 0;
+	list_del(&qpair->qp_list_elem);
+	if (list_empty(&vha->qp_list))
+		vha->flags.qpairs_available = 0;
+fail_msix:
+	ha->queue_pair_map[qpair_id] = NULL;
+	clear_bit(qpair_id, ha->qpair_qid_map);
+	mutex_unlock(&ha->mq_lock);
+fail_qid_map:
+	kfree(qpair);
+	return NULL;
+}
+
+int qla2xxx_delete_qpair(struct scsi_qla_host *vha, struct qla_qpair *qpair)
+{
+	int ret;
+	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)
+		goto fail;
+	ret = qla25xx_delete_rsp_que(vha, qpair->rsp);
+	if (ret != QLA_SUCCESS)
+		goto fail;
+
+	mutex_lock(&ha->mq_lock);
+	ha->queue_pair_map[qpair->id] = NULL;
+	clear_bit(qpair->id, ha->qpair_qid_map);
+	list_del(&qpair->qp_list_elem);
+	if (list_empty(&vha->qp_list))
+		vha->flags.qpairs_available = 0;
+	mempool_destroy(qpair->srb_mempool);
+	kfree(qpair);
+	mutex_unlock(&ha->mq_lock);
+
+	return QLA_SUCCESS;
+fail:
+	return ret;
+}
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index edc48f3b8230..44e404583c86 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -216,6 +216,36 @@ qla2x00_reset_active(scsi_qla_host_t *vha)
 }
 
 static inline srb_t *
+qla2xxx_get_qpair_sp(struct qla_qpair *qpair, fc_port_t *fcport, gfp_t flag)
+{
+	srb_t *sp = NULL;
+	uint8_t bail;
+
+	QLA_QPAIR_MARK_BUSY(qpair, bail);
+	if (unlikely(bail))
+		return NULL;
+
+	sp = mempool_alloc(qpair->srb_mempool, flag);
+	if (!sp)
+		goto done;
+
+	memset(sp, 0, sizeof(*sp));
+	sp->fcport = fcport;
+	sp->iocbs = 1;
+done:
+	if (!sp)
+		QLA_QPAIR_MARK_NOT_BUSY(qpair);
+	return sp;
+}
+
+static inline void
+qla2xxx_rel_qpair_sp(struct qla_qpair *qpair, srb_t *sp)
+{
+	mempool_free(sp, qpair->srb_mempool);
+	QLA_QPAIR_MARK_NOT_BUSY(qpair);
+}
+
+static inline srb_t *
 qla2x00_get_sp(scsi_qla_host_t *vha, fc_port_t *fcport, gfp_t flag)
 {
 	srb_t *sp = NULL;
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index b41265a75ed5..58e49a3e1de8 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -12,7 +12,6 @@
 
 #include <scsi/scsi_tcq.h>
 
-static void qla25xx_set_que(srb_t *, struct rsp_que **);
 /**
  * qla2x00_get_cmd_direction() - Determine control_flag data direction.
  * @cmd: SCSI command
@@ -143,7 +142,7 @@ qla2x00_prep_cont_type1_iocb(scsi_qla_host_t *vha, struct req_que *req)
 	return (cont_pkt);
 }
 
-static inline int
+inline int
 qla24xx_configure_prot_mode(srb_t *sp, uint16_t *fw_prot_opts)
 {
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
@@ -693,10 +692,11 @@ qla24xx_calc_dsd_lists(uint16_t dsds)
  * @sp: SRB command to process
  * @cmd_pkt: Command type 3 IOCB
  * @tot_dsds: Total number of segments to transfer
+ * @req: pointer to request queue
  */
-static inline void
+inline void
 qla24xx_build_scsi_iocbs(srb_t *sp, struct cmd_type_7 *cmd_pkt,
-    uint16_t tot_dsds)
+	uint16_t tot_dsds, struct req_que *req)
 {
 	uint16_t	avail_dsds;
 	uint32_t	*cur_dsd;
@@ -745,7 +745,7 @@ qla24xx_build_scsi_iocbs(srb_t *sp, struct cmd_type_7 *cmd_pkt,
 			 * Five DSDs are available in the Continuation
 			 * Type 1 IOCB.
 			 */
-			cont_pkt = qla2x00_prep_cont_type1_iocb(vha, vha->req);
+			cont_pkt = qla2x00_prep_cont_type1_iocb(vha, req);
 			cur_dsd = (uint32_t *)cont_pkt->dseg_0_address;
 			avail_dsds = 5;
 		}
@@ -845,24 +845,7 @@ qla24xx_set_t10dif_tags(srb_t *sp, struct fw_dif_context *pkt,
 	}
 }
 
-struct qla2_sgx {
-	dma_addr_t		dma_addr;	/* OUT */
-	uint32_t		dma_len;	/* OUT */
-
-	uint32_t		tot_bytes;	/* IN */
-	struct scatterlist	*cur_sg;	/* IN */
-
-	/* for book keeping, bzero on initial invocation */
-	uint32_t		bytes_consumed;
-	uint32_t		num_bytes;
-	uint32_t		tot_partial;
-
-	/* for debugging */
-	uint32_t		num_sg;
-	srb_t			*sp;
-};
-
-static int
+int
 qla24xx_get_one_block_sg(uint32_t blk_sz, struct qla2_sgx *sgx,
 	uint32_t *partial)
 {
@@ -1207,7 +1190,7 @@ qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *ha, srb_t *sp,
  * @cmd_pkt: Command type 3 IOCB
  * @tot_dsds: Total number of segments to transfer
  */
-static inline int
+inline int
 qla24xx_build_scsi_crc_2_iocbs(srb_t *sp, struct cmd_type_crc_2 *cmd_pkt,
     uint16_t tot_dsds, uint16_t tot_prot_dsds, uint16_t fw_prot_opts)
 {
@@ -1436,8 +1419,8 @@ qla24xx_start_scsi(srb_t *sp)
 	struct qla_hw_data *ha = vha->hw;
 
 	/* Setup device pointers. */
-	qla25xx_set_que(sp, &rsp);
 	req = vha->req;
+	rsp = req->rsp;
 
 	/* So we know we haven't pci_map'ed anything yet */
 	tot_dsds = 0;
@@ -1523,12 +1506,10 @@ qla24xx_start_scsi(srb_t *sp)
 	cmd_pkt->byte_count = cpu_to_le32((uint32_t)scsi_bufflen(cmd));
 
 	/* Build IOCB segments */
-	qla24xx_build_scsi_iocbs(sp, cmd_pkt, tot_dsds);
+	qla24xx_build_scsi_iocbs(sp, cmd_pkt, tot_dsds, req);
 
 	/* Set total data segment count. */
 	cmd_pkt->entry_count = (uint8_t)req_cnt;
-	/* Specify response queue number where completion should happen */
-	cmd_pkt->entry_status = (uint8_t) rsp->id;
 	wmb();
 	/* Adjust ring index. */
 	req->ring_index++;
@@ -1597,9 +1578,8 @@ qla24xx_dif_start_scsi(srb_t *sp)
 	}
 
 	/* Setup device pointers. */
-
-	qla25xx_set_que(sp, &rsp);
 	req = vha->req;
+	rsp = req->rsp;
 
 	/* So we know we haven't pci_map'ed anything yet */
 	tot_dsds = 0;
@@ -1764,18 +1744,365 @@ queuing_error:
 	return QLA_FUNCTION_FAILED;
 }
 
-
-static void qla25xx_set_que(srb_t *sp, struct rsp_que **rsp)
+/**
+ * qla2xxx_start_scsi_mq() - Send a SCSI command to the ISP
+ * @sp: command to send to the ISP
+ *
+ * Returns non-zero if a failure occurred, else zero.
+ */
+static int
+qla2xxx_start_scsi_mq(srb_t *sp)
 {
+	int		nseg;
+	unsigned long   flags;
+	uint32_t	*clr_ptr;
+	uint32_t        index;
+	uint32_t	handle;
+	struct cmd_type_7 *cmd_pkt;
+	uint16_t	cnt;
+	uint16_t	req_cnt;
+	uint16_t	tot_dsds;
+	struct req_que *req = NULL;
+	struct rsp_que *rsp = NULL;
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
-	struct qla_hw_data *ha = sp->fcport->vha->hw;
-	int affinity = cmd->request->cpu;
+	struct scsi_qla_host *vha = sp->fcport->vha;
+	struct qla_hw_data *ha = vha->hw;
+	struct qla_qpair *qpair = sp->qpair;
+
+	/* Setup qpair pointers */
+	rsp = qpair->rsp;
+	req = qpair->req;
+
+	/* So we know we haven't pci_map'ed anything yet */
+	tot_dsds = 0;
+
+	/* Send marker if required */
+	if (vha->marker_needed != 0) {
+		if (qla2x00_marker(vha, req, rsp, 0, 0, MK_SYNC_ALL) !=
+		    QLA_SUCCESS)
+			return QLA_FUNCTION_FAILED;
+		vha->marker_needed = 0;
+	}
+
+	/* Acquire qpair specific lock */
+	spin_lock_irqsave(&qpair->qp_lock, flags);
+
+	/* Check for room in outstanding command list. */
+	handle = req->current_outstanding_cmd;
+	for (index = 1; index < req->num_outstanding_cmds; index++) {
+		handle++;
+		if (handle == req->num_outstanding_cmds)
+			handle = 1;
+		if (!req->outstanding_cmds[handle])
+			break;
+	}
+	if (index == req->num_outstanding_cmds)
+		goto queuing_error;
+
+	/* Map the sg table so we have an accurate count of sg entries needed */
+	if (scsi_sg_count(cmd)) {
+		nseg = dma_map_sg(&ha->pdev->dev, scsi_sglist(cmd),
+		    scsi_sg_count(cmd), cmd->sc_data_direction);
+		if (unlikely(!nseg))
+			goto queuing_error;
+	} else
+		nseg = 0;
+
+	tot_dsds = nseg;
+	req_cnt = qla24xx_calc_iocbs(vha, tot_dsds);
+	if (req->cnt < (req_cnt + 2)) {
+		cnt = IS_SHADOW_REG_CAPABLE(ha) ? *req->out_ptr :
+		    RD_REG_DWORD_RELAXED(req->req_q_out);
+		if (req->ring_index < cnt)
+			req->cnt = cnt - req->ring_index;
+		else
+			req->cnt = req->length -
+				(req->ring_index - cnt);
+		if (req->cnt < (req_cnt + 2))
+			goto queuing_error;
+	}
+
+	/* Build command packet. */
+	req->current_outstanding_cmd = handle;
+	req->outstanding_cmds[handle] = sp;
+	sp->handle = handle;
+	cmd->host_scribble = (unsigned char *)(unsigned long)handle;
+	req->cnt -= req_cnt;
+
+	cmd_pkt = (struct cmd_type_7 *)req->ring_ptr;
+	cmd_pkt->handle = MAKE_HANDLE(req->id, handle);
+
+	/* Zero out remaining portion of packet. */
+	/*    tagged queuing modifier -- default is TSK_SIMPLE (0). */
+	clr_ptr = (uint32_t *)cmd_pkt + 2;
+	memset(clr_ptr, 0, REQUEST_ENTRY_SIZE - 8);
+	cmd_pkt->dseg_count = cpu_to_le16(tot_dsds);
+
+	/* Set NPORT-ID and LUN number*/
+	cmd_pkt->nport_handle = cpu_to_le16(sp->fcport->loop_id);
+	cmd_pkt->port_id[0] = sp->fcport->d_id.b.al_pa;
+	cmd_pkt->port_id[1] = sp->fcport->d_id.b.area;
+	cmd_pkt->port_id[2] = sp->fcport->d_id.b.domain;
+	cmd_pkt->vp_index = sp->fcport->vha->vp_idx;
+
+	int_to_scsilun(cmd->device->lun, &cmd_pkt->lun);
+	host_to_fcp_swap((uint8_t *)&cmd_pkt->lun, sizeof(cmd_pkt->lun));
+
+	cmd_pkt->task = TSK_SIMPLE;
+
+	/* Load SCSI command packet. */
+	memcpy(cmd_pkt->fcp_cdb, cmd->cmnd, cmd->cmd_len);
+	host_to_fcp_swap(cmd_pkt->fcp_cdb, sizeof(cmd_pkt->fcp_cdb));
+
+	cmd_pkt->byte_count = cpu_to_le32((uint32_t)scsi_bufflen(cmd));
+
+	/* Build IOCB segments */
+	qla24xx_build_scsi_iocbs(sp, cmd_pkt, tot_dsds, req);
+
+	/* Set total data segment count. */
+	cmd_pkt->entry_count = (uint8_t)req_cnt;
+	wmb();
+	/* Adjust ring index. */
+	req->ring_index++;
+	if (req->ring_index == req->length) {
+		req->ring_index = 0;
+		req->ring_ptr = req->ring;
+	} else
+		req->ring_ptr++;
+
+	sp->flags |= SRB_DMA_VALID;
+
+	/* Set chip new ring index. */
+	WRT_REG_DWORD(req->req_q_in, req->ring_index);
+
+	/* Manage unprocessed RIO/ZIO commands in response queue. */
+	if (vha->flags.process_response_queue &&
+		rsp->ring_ptr->signature != RESPONSE_PROCESSED)
+		qla24xx_process_response_queue(vha, rsp);
+
+	spin_unlock_irqrestore(&qpair->qp_lock, flags);
+	return QLA_SUCCESS;
+
+queuing_error:
+	if (tot_dsds)
+		scsi_dma_unmap(cmd);
+
+	spin_unlock_irqrestore(&qpair->qp_lock, flags);
+
+	return QLA_FUNCTION_FAILED;
+}
+
+
+/**
+ * qla2xxx_dif_start_scsi_mq() - Send a SCSI command to the ISP
+ * @sp: command to send to the ISP
+ *
+ * Returns non-zero if a failure occurred, else zero.
+ */
+int
+qla2xxx_dif_start_scsi_mq(srb_t *sp)
+{
+	int			nseg;
+	unsigned long		flags;
+	uint32_t		*clr_ptr;
+	uint32_t		index;
+	uint32_t		handle;
+	uint16_t		cnt;
+	uint16_t		req_cnt = 0;
+	uint16_t		tot_dsds;
+	uint16_t		tot_prot_dsds;
+	uint16_t		fw_prot_opts = 0;
+	struct req_que		*req = NULL;
+	struct rsp_que		*rsp = NULL;
+	struct scsi_cmnd	*cmd = GET_CMD_SP(sp);
+	struct scsi_qla_host	*vha = sp->fcport->vha;
+	struct qla_hw_data	*ha = vha->hw;
+	struct cmd_type_crc_2	*cmd_pkt;
+	uint32_t		status = 0;
+	struct qla_qpair	*qpair = sp->qpair;
+
+#define QDSS_GOT_Q_SPACE	BIT_0
+
+	/* Check for host side state */
+	if (!qpair->online) {
+		cmd->result = DID_NO_CONNECT << 16;
+		return QLA_INTERFACE_ERROR;
+	}
+
+	if (!qpair->difdix_supported &&
+		scsi_get_prot_op(cmd) != SCSI_PROT_NORMAL) {
+		cmd->result = DID_NO_CONNECT << 16;
+		return QLA_INTERFACE_ERROR;
+	}
+
+	/* Only process protection or >16 cdb in this routine */
+	if (scsi_get_prot_op(cmd) == SCSI_PROT_NORMAL) {
+		if (cmd->cmd_len <= 16)
+			return qla2xxx_start_scsi_mq(sp);
+	}
+
+	/* Setup qpair pointers */
+	rsp = qpair->rsp;
+	req = qpair->req;
+
+	/* So we know we haven't pci_map'ed anything yet */
+	tot_dsds = 0;
+
+	/* Send marker if required */
+	if (vha->marker_needed != 0) {
+		if (qla2x00_marker(vha, req, rsp, 0, 0, MK_SYNC_ALL) !=
+		    QLA_SUCCESS)
+			return QLA_FUNCTION_FAILED;
+		vha->marker_needed = 0;
+	}
+
+	/* Acquire ring specific lock */
+	spin_lock_irqsave(&qpair->qp_lock, flags);
+
+	/* Check for room in outstanding command list. */
+	handle = req->current_outstanding_cmd;
+	for (index = 1; index < req->num_outstanding_cmds; index++) {
+		handle++;
+		if (handle == req->num_outstanding_cmds)
+			handle = 1;
+		if (!req->outstanding_cmds[handle])
+			break;
+	}
+
+	if (index == req->num_outstanding_cmds)
+		goto queuing_error;
+
+	/* Compute number of required data segments */
+	/* Map the sg table so we have an accurate count of sg entries needed */
+	if (scsi_sg_count(cmd)) {
+		nseg = dma_map_sg(&ha->pdev->dev, scsi_sglist(cmd),
+		    scsi_sg_count(cmd), cmd->sc_data_direction);
+		if (unlikely(!nseg))
+			goto queuing_error;
+		else
+			sp->flags |= SRB_DMA_VALID;
+
+		if ((scsi_get_prot_op(cmd) == SCSI_PROT_READ_INSERT) ||
+		    (scsi_get_prot_op(cmd) == SCSI_PROT_WRITE_STRIP)) {
+			struct qla2_sgx sgx;
+			uint32_t	partial;
+
+			memset(&sgx, 0, sizeof(struct qla2_sgx));
+			sgx.tot_bytes = scsi_bufflen(cmd);
+			sgx.cur_sg = scsi_sglist(cmd);
+			sgx.sp = sp;
+
+			nseg = 0;
+			while (qla24xx_get_one_block_sg(
+			    cmd->device->sector_size, &sgx, &partial))
+				nseg++;
+		}
+	} else
+		nseg = 0;
+
+	/* number of required data segments */
+	tot_dsds = nseg;
+
+	/* Compute number of required protection segments */
+	if (qla24xx_configure_prot_mode(sp, &fw_prot_opts)) {
+		nseg = dma_map_sg(&ha->pdev->dev, scsi_prot_sglist(cmd),
+		    scsi_prot_sg_count(cmd), cmd->sc_data_direction);
+		if (unlikely(!nseg))
+			goto queuing_error;
+		else
+			sp->flags |= SRB_CRC_PROT_DMA_VALID;
+
+		if ((scsi_get_prot_op(cmd) == SCSI_PROT_READ_INSERT) ||
+		    (scsi_get_prot_op(cmd) == SCSI_PROT_WRITE_STRIP)) {
+			nseg = scsi_bufflen(cmd) / cmd->device->sector_size;
+		}
+	} else {
+		nseg = 0;
+	}
+
+	req_cnt = 1;
+	/* Total Data and protection sg segment(s) */
+	tot_prot_dsds = nseg;
+	tot_dsds += nseg;
+	if (req->cnt < (req_cnt + 2)) {
+		cnt = IS_SHADOW_REG_CAPABLE(ha) ? *req->out_ptr :
+		    RD_REG_DWORD_RELAXED(req->req_q_out);
+		if (req->ring_index < cnt)
+			req->cnt = cnt - req->ring_index;
+		else
+			req->cnt = req->length -
+				(req->ring_index - cnt);
+		if (req->cnt < (req_cnt + 2))
+			goto queuing_error;
+	}
+
+	status |= QDSS_GOT_Q_SPACE;
+
+	/* Build header part of command packet (excluding the OPCODE). */
+	req->current_outstanding_cmd = handle;
+	req->outstanding_cmds[handle] = sp;
+	sp->handle = handle;
+	cmd->host_scribble = (unsigned char *)(unsigned long)handle;
+	req->cnt -= req_cnt;
+
+	/* Fill-in common area */
+	cmd_pkt = (struct cmd_type_crc_2 *)req->ring_ptr;
+	cmd_pkt->handle = MAKE_HANDLE(req->id, handle);
+
+	clr_ptr = (uint32_t *)cmd_pkt + 2;
+	memset(clr_ptr, 0, REQUEST_ENTRY_SIZE - 8);
+
+	/* Set NPORT-ID and LUN number*/
+	cmd_pkt->nport_handle = cpu_to_le16(sp->fcport->loop_id);
+	cmd_pkt->port_id[0] = sp->fcport->d_id.b.al_pa;
+	cmd_pkt->port_id[1] = sp->fcport->d_id.b.area;
+	cmd_pkt->port_id[2] = sp->fcport->d_id.b.domain;
 
-	if (ha->flags.cpu_affinity_enabled && affinity >= 0 &&
-		affinity < ha->max_rsp_queues - 1)
-		*rsp = ha->rsp_q_map[affinity + 1];
-	 else
-		*rsp = ha->rsp_q_map[0];
+	int_to_scsilun(cmd->device->lun, &cmd_pkt->lun);
+	host_to_fcp_swap((uint8_t *)&cmd_pkt->lun, sizeof(cmd_pkt->lun));
+
+	/* Total Data and protection segment(s) */
+	cmd_pkt->dseg_count = cpu_to_le16(tot_dsds);
+
+	/* Build IOCB segments and adjust for data protection segments */
+	if (qla24xx_build_scsi_crc_2_iocbs(sp, (struct cmd_type_crc_2 *)
+	    req->ring_ptr, tot_dsds, tot_prot_dsds, fw_prot_opts) !=
+		QLA_SUCCESS)
+		goto queuing_error;
+
+	cmd_pkt->entry_count = (uint8_t)req_cnt;
+	cmd_pkt->timeout = cpu_to_le16(0);
+	wmb();
+
+	/* Adjust ring index. */
+	req->ring_index++;
+	if (req->ring_index == req->length) {
+		req->ring_index = 0;
+		req->ring_ptr = req->ring;
+	} else
+		req->ring_ptr++;
+
+	/* Set chip new ring index. */
+	WRT_REG_DWORD(req->req_q_in, req->ring_index);
+
+	/* Manage unprocessed RIO/ZIO commands in response queue. */
+	if (vha->flags.process_response_queue &&
+	    rsp->ring_ptr->signature != RESPONSE_PROCESSED)
+		qla24xx_process_response_queue(vha, rsp);
+
+	spin_unlock_irqrestore(&qpair->qp_lock, flags);
+
+	return QLA_SUCCESS;
+
+queuing_error:
+	if (status & QDSS_GOT_Q_SPACE) {
+		req->outstanding_cmds[handle] = NULL;
+		req->cnt += req_cnt;
+	}
+	/* Cleanup will be performed by the caller (queuecommand) */
+
+	spin_unlock_irqrestore(&qpair->qp_lock, flags);
+	return QLA_FUNCTION_FAILED;
 }
 
 /* Generic Control-SRB manipulation functions. */
@@ -2197,7 +2524,8 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 static void
 qla24xx_els_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 {
-	struct fc_bsg_job *bsg_job = sp->u.bsg_job;
+	struct bsg_job *bsg_job = sp->u.bsg_job;
+	struct fc_bsg_request *bsg_request = bsg_job->request;
 
         els_iocb->entry_type = ELS_IOCB_TYPE;
         els_iocb->entry_count = 1;
@@ -2212,8 +2540,8 @@ qla24xx_els_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 
 	els_iocb->opcode =
 	    sp->type == SRB_ELS_CMD_RPT ?
-	    bsg_job->request->rqst_data.r_els.els_code :
-	    bsg_job->request->rqst_data.h_els.command_code;
+	    bsg_request->rqst_data.r_els.els_code :
+	    bsg_request->rqst_data.h_els.command_code;
         els_iocb->port_id[0] = sp->fcport->d_id.b.al_pa;
         els_iocb->port_id[1] = sp->fcport->d_id.b.area;
         els_iocb->port_id[2] = sp->fcport->d_id.b.domain;
@@ -2250,7 +2578,7 @@ qla2x00_ct_iocb(srb_t *sp, ms_iocb_entry_t *ct_iocb)
 	uint16_t tot_dsds;
 	scsi_qla_host_t *vha = sp->fcport->vha;
 	struct qla_hw_data *ha = vha->hw;
-	struct fc_bsg_job *bsg_job = sp->u.bsg_job;
+	struct bsg_job *bsg_job = sp->u.bsg_job;
 	int loop_iterartion = 0;
 	int entry_count = 1;
 
@@ -2327,7 +2655,7 @@ qla24xx_ct_iocb(srb_t *sp, struct ct_entry_24xx *ct_iocb)
 	uint16_t tot_dsds;
         scsi_qla_host_t *vha = sp->fcport->vha;
 	struct qla_hw_data *ha = vha->hw;
-	struct fc_bsg_job *bsg_job = sp->u.bsg_job;
+	struct bsg_job *bsg_job = sp->u.bsg_job;
 	int loop_iterartion = 0;
 	int entry_count = 1;
 
@@ -2663,7 +2991,7 @@ sufficient_dsds:
 		cmd_pkt->byte_count = cpu_to_le32((uint32_t)scsi_bufflen(cmd));
 
 		/* Build IOCB segments */
-		qla24xx_build_scsi_iocbs(sp, cmd_pkt, tot_dsds);
+		qla24xx_build_scsi_iocbs(sp, cmd_pkt, tot_dsds, req);
 
 		/* Set total data segment count. */
 		cmd_pkt->entry_count = (uint8_t)req_cnt;
@@ -2833,7 +3161,7 @@ qla25xx_build_bidir_iocb(srb_t *sp, struct scsi_qla_host *vha,
 	struct scatterlist *sg;
 	int index;
 	int entry_count = 1;
-	struct fc_bsg_job *bsg_job = sp->u.bsg_job;
+	struct bsg_job *bsg_job = sp->u.bsg_job;
 
 	/*Update entry type to indicate bidir command */
 	*((uint32_t *)(&cmd_pkt->entry_type)) =
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 068c4e47fac9..5093ca9b02ec 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -9,6 +9,7 @@
 
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/t10-pi.h>
 #include <scsi/scsi_tcq.h>
 #include <scsi/scsi_bsg_fc.h>
 #include <scsi/scsi_eh.h>
@@ -1356,7 +1357,8 @@ qla2x00_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 	const char func[] = "CT_IOCB";
 	const char *type;
 	srb_t *sp;
-	struct fc_bsg_job *bsg_job;
+	struct bsg_job *bsg_job;
+	struct fc_bsg_reply *bsg_reply;
 	uint16_t comp_status;
 	int res;
 
@@ -1365,6 +1367,7 @@ qla2x00_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 		return;
 
 	bsg_job = sp->u.bsg_job;
+	bsg_reply = bsg_job->reply;
 
 	type = "ct pass-through";
 
@@ -1373,32 +1376,32 @@ qla2x00_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 	/* return FC_CTELS_STATUS_OK and leave the decoding of the ELS/CT
 	 * fc payload  to the caller
 	 */
-	bsg_job->reply->reply_data.ctels_reply.status = FC_CTELS_STATUS_OK;
+	bsg_reply->reply_data.ctels_reply.status = FC_CTELS_STATUS_OK;
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
 
 	if (comp_status != CS_COMPLETE) {
 		if (comp_status == CS_DATA_UNDERRUN) {
 			res = DID_OK << 16;
-			bsg_job->reply->reply_payload_rcv_len =
+			bsg_reply->reply_payload_rcv_len =
 			    le16_to_cpu(((sts_entry_t *)pkt)->rsp_info_len);
 
 			ql_log(ql_log_warn, vha, 0x5048,
 			    "CT pass-through-%s error "
 			    "comp_status-status=0x%x total_byte = 0x%x.\n",
 			    type, comp_status,
-			    bsg_job->reply->reply_payload_rcv_len);
+			    bsg_reply->reply_payload_rcv_len);
 		} else {
 			ql_log(ql_log_warn, vha, 0x5049,
 			    "CT pass-through-%s error "
 			    "comp_status-status=0x%x.\n", type, comp_status);
 			res = DID_ERROR << 16;
-			bsg_job->reply->reply_payload_rcv_len = 0;
+			bsg_reply->reply_payload_rcv_len = 0;
 		}
 		ql_dump_buffer(ql_dbg_async + ql_dbg_buffer, vha, 0x5035,
 		    (uint8_t *)pkt, sizeof(*pkt));
 	} else {
 		res = DID_OK << 16;
-		bsg_job->reply->reply_payload_rcv_len =
+		bsg_reply->reply_payload_rcv_len =
 		    bsg_job->reply_payload.payload_len;
 		bsg_job->reply_len = 0;
 	}
@@ -1413,7 +1416,8 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 	const char func[] = "ELS_CT_IOCB";
 	const char *type;
 	srb_t *sp;
-	struct fc_bsg_job *bsg_job;
+	struct bsg_job *bsg_job;
+	struct fc_bsg_reply *bsg_reply;
 	uint16_t comp_status;
 	uint32_t fw_status[3];
 	uint8_t* fw_sts_ptr;
@@ -1423,6 +1427,7 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 	if (!sp)
 		return;
 	bsg_job = sp->u.bsg_job;
+	bsg_reply = bsg_job->reply;
 
 	type = NULL;
 	switch (sp->type) {
@@ -1452,13 +1457,13 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 	/* return FC_CTELS_STATUS_OK and leave the decoding of the ELS/CT
 	 * fc payload  to the caller
 	 */
-	bsg_job->reply->reply_data.ctels_reply.status = FC_CTELS_STATUS_OK;
+	bsg_reply->reply_data.ctels_reply.status = FC_CTELS_STATUS_OK;
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply) + sizeof(fw_status);
 
 	if (comp_status != CS_COMPLETE) {
 		if (comp_status == CS_DATA_UNDERRUN) {
 			res = DID_OK << 16;
-			bsg_job->reply->reply_payload_rcv_len =
+			bsg_reply->reply_payload_rcv_len =
 			    le16_to_cpu(((struct els_sts_entry_24xx *)pkt)->total_byte_count);
 
 			ql_dbg(ql_dbg_user, vha, 0x503f,
@@ -1480,7 +1485,7 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 			    le16_to_cpu(((struct els_sts_entry_24xx *)
 				    pkt)->error_subcode_2));
 			res = DID_ERROR << 16;
-			bsg_job->reply->reply_payload_rcv_len = 0;
+			bsg_reply->reply_payload_rcv_len = 0;
 			fw_sts_ptr = ((uint8_t*)bsg_job->req->sense) + sizeof(struct fc_bsg_reply);
 			memcpy( fw_sts_ptr, fw_status, sizeof(fw_status));
 		}
@@ -1489,7 +1494,7 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 	}
 	else {
 		res =  DID_OK << 16;
-		bsg_job->reply->reply_payload_rcv_len = bsg_job->reply_payload.payload_len;
+		bsg_reply->reply_payload_rcv_len = bsg_job->reply_payload.payload_len;
 		bsg_job->reply_len = 0;
 	}
 
@@ -1904,7 +1909,9 @@ qla25xx_process_bidir_status_iocb(scsi_qla_host_t *vha, void *pkt,
 	uint16_t	scsi_status;
 	uint16_t thread_id;
 	uint32_t rval = EXT_STATUS_OK;
-	struct fc_bsg_job *bsg_job = NULL;
+	struct bsg_job *bsg_job = NULL;
+	struct fc_bsg_request *bsg_request;
+	struct fc_bsg_reply *bsg_reply;
 	sts_entry_t *sts;
 	struct sts_entry_24xx *sts24;
 	sts = (sts_entry_t *) pkt;
@@ -1919,11 +1926,7 @@ qla25xx_process_bidir_status_iocb(scsi_qla_host_t *vha, void *pkt,
 	}
 
 	sp = req->outstanding_cmds[index];
-	if (sp) {
-		/* Free outstanding command slot. */
-		req->outstanding_cmds[index] = NULL;
-		bsg_job = sp->u.bsg_job;
-	} else {
+	if (!sp) {
 		ql_log(ql_log_warn, vha, 0x70b0,
 		    "Req:%d: Invalid ISP SCSI completion handle(0x%x)\n",
 		    req->id, index);
@@ -1932,6 +1935,12 @@ qla25xx_process_bidir_status_iocb(scsi_qla_host_t *vha, void *pkt,
 		return;
 	}
 
+	/* Free outstanding command slot. */
+	req->outstanding_cmds[index] = NULL;
+	bsg_job = sp->u.bsg_job;
+	bsg_request = bsg_job->request;
+	bsg_reply = bsg_job->reply;
+
 	if (IS_FWI2_CAPABLE(ha)) {
 		comp_status = le16_to_cpu(sts24->comp_status);
 		scsi_status = le16_to_cpu(sts24->scsi_status) & SS_MASK;
@@ -1940,14 +1949,14 @@ qla25xx_process_bidir_status_iocb(scsi_qla_host_t *vha, void *pkt,
 		scsi_status = le16_to_cpu(sts->scsi_status) & SS_MASK;
 	}
 
-	thread_id = bsg_job->request->rqst_data.h_vendor.vendor_cmd[1];
+	thread_id = bsg_request->rqst_data.h_vendor.vendor_cmd[1];
 	switch (comp_status) {
 	case CS_COMPLETE:
 		if (scsi_status == 0) {
-			bsg_job->reply->reply_payload_rcv_len =
+			bsg_reply->reply_payload_rcv_len =
 					bsg_job->reply_payload.payload_len;
 			vha->qla_stats.input_bytes +=
-				bsg_job->reply->reply_payload_rcv_len;
+				bsg_reply->reply_payload_rcv_len;
 			vha->qla_stats.input_requests++;
 			rval = EXT_STATUS_OK;
 		}
@@ -2028,11 +2037,11 @@ qla25xx_process_bidir_status_iocb(scsi_qla_host_t *vha, void *pkt,
 		rval = EXT_STATUS_ERR;
 		break;
 	}
-	bsg_job->reply->reply_payload_rcv_len = 0;
+	bsg_reply->reply_payload_rcv_len = 0;
 
 done:
 	/* Return the vendor specific reply to API */
-	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] = rval;
+	bsg_reply->reply_data.vendor_reply.vendor_rsp[0] = rval;
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
 	/* Always return DID_OK, bsg will send the vendor specific response
 	 * in this case only */
@@ -2863,41 +2872,6 @@ out:
 }
 
 static irqreturn_t
-qla25xx_msix_rsp_q(int irq, void *dev_id)
-{
-	struct qla_hw_data *ha;
-	scsi_qla_host_t *vha;
-	struct rsp_que *rsp;
-	struct device_reg_24xx __iomem *reg;
-	unsigned long flags;
-	uint32_t hccr = 0;
-
-	rsp = (struct rsp_que *) dev_id;
-	if (!rsp) {
-		ql_log(ql_log_info, NULL, 0x505b,
-		    "%s: NULL response queue pointer.\n", __func__);
-		return IRQ_NONE;
-	}
-	ha = rsp->hw;
-	vha = pci_get_drvdata(ha->pdev);
-
-	/* Clear the interrupt, if enabled, for this response queue */
-	if (!ha->flags.disable_msix_handshake) {
-		reg = &ha->iobase->isp24;
-		spin_lock_irqsave(&ha->hardware_lock, flags);
-		WRT_REG_DWORD(&reg->hccr, HCCRX_CLR_RISC_INT);
-		hccr = RD_REG_DWORD_RELAXED(&reg->hccr);
-		spin_unlock_irqrestore(&ha->hardware_lock, flags);
-	}
-	if (qla2x00_check_reg32_for_disconnect(vha, hccr))
-		goto out;
-	queue_work_on((int) (rsp->id - 1), ha->wq, &rsp->q_work);
-
-out:
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t
 qla24xx_msix_default(int irq, void *dev_id)
 {
 	scsi_qla_host_t	*vha;
@@ -2993,6 +2967,35 @@ qla24xx_msix_default(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+irqreturn_t
+qla2xxx_msix_rsp_q(int irq, void *dev_id)
+{
+	struct qla_hw_data *ha;
+	struct qla_qpair *qpair;
+	struct device_reg_24xx __iomem *reg;
+	unsigned long flags;
+
+	qpair = dev_id;
+	if (!qpair) {
+		ql_log(ql_log_info, NULL, 0x505b,
+		    "%s: NULL response queue pointer.\n", __func__);
+		return IRQ_NONE;
+	}
+	ha = qpair->hw;
+
+	/* Clear the interrupt, if enabled, for this response queue */
+	if (unlikely(!ha->flags.disable_msix_handshake)) {
+		reg = &ha->iobase->isp24;
+		spin_lock_irqsave(&ha->hardware_lock, flags);
+		WRT_REG_DWORD(&reg->hccr, HCCRX_CLR_RISC_INT);
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+	}
+
+	queue_work(ha->wq, &qpair->q_work);
+
+	return IRQ_HANDLED;
+}
+
 /* Interrupt handling helpers. */
 
 struct qla_init_msix_entry {
@@ -3000,69 +3003,28 @@ struct qla_init_msix_entry {
 	irq_handler_t handler;
 };
 
-static struct qla_init_msix_entry msix_entries[3] = {
+static struct qla_init_msix_entry msix_entries[] = {
 	{ "qla2xxx (default)", qla24xx_msix_default },
 	{ "qla2xxx (rsp_q)", qla24xx_msix_rsp_q },
-	{ "qla2xxx (multiq)", qla25xx_msix_rsp_q },
+	{ "qla2xxx (atio_q)", qla83xx_msix_atio_q },
+	{ "qla2xxx (qpair_multiq)", qla2xxx_msix_rsp_q },
 };
 
-static struct qla_init_msix_entry qla82xx_msix_entries[2] = {
+static struct qla_init_msix_entry qla82xx_msix_entries[] = {
 	{ "qla2xxx (default)", qla82xx_msix_default },
 	{ "qla2xxx (rsp_q)", qla82xx_msix_rsp_q },
 };
 
-static struct qla_init_msix_entry qla83xx_msix_entries[3] = {
-	{ "qla2xxx (default)", qla24xx_msix_default },
-	{ "qla2xxx (rsp_q)", qla24xx_msix_rsp_q },
-	{ "qla2xxx (atio_q)", qla83xx_msix_atio_q },
-};
-
-static void
-qla24xx_disable_msix(struct qla_hw_data *ha)
-{
-	int i;
-	struct qla_msix_entry *qentry;
-	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
-
-	for (i = 0; i < ha->msix_count; i++) {
-		qentry = &ha->msix_entries[i];
-		if (qentry->have_irq) {
-			/* un-register irq cpu affinity notification */
-			irq_set_affinity_notifier(qentry->vector, NULL);
-			free_irq(qentry->vector, qentry->rsp);
-		}
-	}
-	pci_disable_msix(ha->pdev);
-	kfree(ha->msix_entries);
-	ha->msix_entries = NULL;
-	ha->flags.msix_enabled = 0;
-	ql_dbg(ql_dbg_init, vha, 0x0042,
-	    "Disabled the MSI.\n");
-}
-
 static int
 qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 {
 #define MIN_MSIX_COUNT	2
-#define ATIO_VECTOR	2
 	int i, ret;
-	struct msix_entry *entries;
 	struct qla_msix_entry *qentry;
 	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
 
-	entries = kzalloc(sizeof(struct msix_entry) * ha->msix_count,
-			GFP_KERNEL);
-	if (!entries) {
-		ql_log(ql_log_warn, vha, 0x00bc,
-		    "Failed to allocate memory for msix_entry.\n");
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < ha->msix_count; i++)
-		entries[i].entry = i;
-
-	ret = pci_enable_msix_range(ha->pdev,
-				    entries, MIN_MSIX_COUNT, ha->msix_count);
+	ret = pci_alloc_irq_vectors(ha->pdev, MIN_MSIX_COUNT, ha->msix_count,
+				    PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
 	if (ret < 0) {
 		ql_log(ql_log_fatal, vha, 0x00c7,
 		    "MSI-X: Failed to enable support, "
@@ -3072,10 +3034,23 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 	} else if (ret < ha->msix_count) {
 		ql_log(ql_log_warn, vha, 0x00c6,
 		    "MSI-X: Failed to enable support "
-		    "-- %d/%d\n Retry with %d vectors.\n",
-		    ha->msix_count, ret, ret);
+		     "with %d vectors, using %d vectors.\n",
+		    ha->msix_count, ret);
 		ha->msix_count = ret;
-		ha->max_rsp_queues = ha->msix_count - 1;
+		/* Recalculate queue values */
+		if (ha->mqiobase && ql2xmqsupport) {
+			ha->max_req_queues = ha->msix_count - 1;
+
+			/* ATIOQ needs 1 vector. That's 1 less QPair */
+			if (QLA_TGT_MODE_ENABLED())
+				ha->max_req_queues--;
+
+			ha->max_rsp_queues = ha->max_req_queues;
+
+			ha->max_qpairs = ha->max_req_queues - 1;
+			ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0190,
+			    "Adjusted Max no of queues pairs: %d.\n", ha->max_qpairs);
+		}
 	}
 	ha->msix_entries = kzalloc(sizeof(struct qla_msix_entry) *
 				ha->msix_count, GFP_KERNEL);
@@ -3089,20 +3064,23 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 
 	for (i = 0; i < ha->msix_count; i++) {
 		qentry = &ha->msix_entries[i];
-		qentry->vector = entries[i].vector;
-		qentry->entry = entries[i].entry;
+		qentry->vector = pci_irq_vector(ha->pdev, i);
+		qentry->entry = i;
 		qentry->have_irq = 0;
-		qentry->rsp = NULL;
+		qentry->in_use = 0;
+		qentry->handle = NULL;
 		qentry->irq_notify.notify  = qla_irq_affinity_notify;
 		qentry->irq_notify.release = qla_irq_affinity_release;
 		qentry->cpuid = -1;
 	}
 
 	/* Enable MSI-X vectors for the base queue */
-	for (i = 0; i < 2; i++) {
+	for (i = 0; i < (QLA_MSIX_RSP_Q + 1); i++) {
 		qentry = &ha->msix_entries[i];
-		qentry->rsp = rsp;
+		qentry->handle = rsp;
 		rsp->msix = qentry;
+		scnprintf(qentry->name, sizeof(qentry->name),
+		    msix_entries[i].name);
 		if (IS_P3P_TYPE(ha))
 			ret = request_irq(qentry->vector,
 				qla82xx_msix_entries[i].handler,
@@ -3114,6 +3092,7 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 		if (ret)
 			goto msix_register_fail;
 		qentry->have_irq = 1;
+		qentry->in_use = 1;
 
 		/* Register for CPU affinity notification. */
 		irq_set_affinity_notifier(qentry->vector, &qentry->irq_notify);
@@ -3133,12 +3112,15 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 	 * queue.
 	 */
 	if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha)) {
-		qentry = &ha->msix_entries[ATIO_VECTOR];
-		qentry->rsp = rsp;
+		qentry = &ha->msix_entries[QLA_ATIO_VECTOR];
 		rsp->msix = qentry;
+		qentry->handle = rsp;
+		scnprintf(qentry->name, sizeof(qentry->name),
+		    msix_entries[QLA_ATIO_VECTOR].name);
+		qentry->in_use = 1;
 		ret = request_irq(qentry->vector,
-			qla83xx_msix_entries[ATIO_VECTOR].handler,
-			0, qla83xx_msix_entries[ATIO_VECTOR].name, rsp);
+			msix_entries[QLA_ATIO_VECTOR].handler,
+			0, msix_entries[QLA_ATIO_VECTOR].name, rsp);
 		qentry->have_irq = 1;
 	}
 
@@ -3147,7 +3129,7 @@ msix_register_fail:
 		ql_log(ql_log_fatal, vha, 0x00cb,
 		    "MSI-X: unable to register handler -- %x/%d.\n",
 		    qentry->vector, ret);
-		qla24xx_disable_msix(ha);
+		qla2x00_free_irqs(vha);
 		ha->mqenable = 0;
 		goto msix_out;
 	}
@@ -3155,11 +3137,13 @@ msix_register_fail:
 	/* Enable MSI-X vector for response queue update for queue 0 */
 	if (IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
 		if (ha->msixbase && ha->mqiobase &&
-		    (ha->max_rsp_queues > 1 || ha->max_req_queues > 1))
+		    (ha->max_rsp_queues > 1 || ha->max_req_queues > 1 ||
+		     ql2xmqsupport))
 			ha->mqenable = 1;
 	} else
-		if (ha->mqiobase
-		    && (ha->max_rsp_queues > 1 || ha->max_req_queues > 1))
+		if (ha->mqiobase &&
+		    (ha->max_rsp_queues > 1 || ha->max_req_queues > 1 ||
+		     ql2xmqsupport))
 			ha->mqenable = 1;
 	ql_dbg(ql_dbg_multiq, vha, 0xc005,
 	    "mqiobase=%p, max_rsp_queues=%d, max_req_queues=%d.\n",
@@ -3169,7 +3153,6 @@ msix_register_fail:
 	    ha->mqiobase, ha->max_rsp_queues, ha->max_req_queues);
 
 msix_out:
-	kfree(entries);
 	return ret;
 }
 
@@ -3222,7 +3205,7 @@ skip_msix:
 	    !IS_QLA27XX(ha))
 		goto skip_msi;
 
-	ret = pci_enable_msi(ha->pdev);
+	ret = pci_alloc_irq_vectors(ha->pdev, 1, 1, PCI_IRQ_MSI);
 	if (!ret) {
 		ql_dbg(ql_dbg_init, vha, 0x0038,
 		    "MSI: Enabled.\n");
@@ -3267,6 +3250,8 @@ qla2x00_free_irqs(scsi_qla_host_t *vha)
 {
 	struct qla_hw_data *ha = vha->hw;
 	struct rsp_que *rsp;
+	struct qla_msix_entry *qentry;
+	int i;
 
 	/*
 	 * We need to check that ha->rsp_q_map is valid in case we are called
@@ -3276,25 +3261,36 @@ qla2x00_free_irqs(scsi_qla_host_t *vha)
 		return;
 	rsp = ha->rsp_q_map[0];
 
-	if (ha->flags.msix_enabled)
-		qla24xx_disable_msix(ha);
-	else if (ha->flags.msi_enabled) {
-		free_irq(ha->pdev->irq, rsp);
-		pci_disable_msi(ha->pdev);
-	} else
-		free_irq(ha->pdev->irq, rsp);
-}
+	if (ha->flags.msix_enabled) {
+		for (i = 0; i < ha->msix_count; i++) {
+			qentry = &ha->msix_entries[i];
+			if (qentry->have_irq) {
+				irq_set_affinity_notifier(qentry->vector, NULL);
+				free_irq(pci_irq_vector(ha->pdev, i), qentry->handle);
+			}
+		}
+		kfree(ha->msix_entries);
+		ha->msix_entries = NULL;
+		ha->flags.msix_enabled = 0;
+		ql_dbg(ql_dbg_init, vha, 0x0042,
+			"Disabled MSI-X.\n");
+	} else {
+		free_irq(pci_irq_vector(ha->pdev, 0), rsp);
+	}
 
+	pci_free_irq_vectors(ha->pdev);
+}
 
-int qla25xx_request_irq(struct rsp_que *rsp)
+int qla25xx_request_irq(struct qla_hw_data *ha, struct qla_qpair *qpair,
+	struct qla_msix_entry *msix, int vector_type)
 {
-	struct qla_hw_data *ha = rsp->hw;
-	struct qla_init_msix_entry *intr = &msix_entries[2];
-	struct qla_msix_entry *msix = rsp->msix;
+	struct qla_init_msix_entry *intr = &msix_entries[vector_type];
 	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
 	int ret;
 
-	ret = request_irq(msix->vector, intr->handler, 0, intr->name, rsp);
+	scnprintf(msix->name, sizeof(msix->name),
+	    "qla2xxx%lu_qpair%d", vha->host_no, qpair->id);
+	ret = request_irq(msix->vector, intr->handler, 0, msix->name, qpair);
 	if (ret) {
 		ql_log(ql_log_fatal, vha, 0x00e6,
 		    "MSI-X: Unable to register handler -- %x/%d.\n",
@@ -3302,7 +3298,7 @@ int qla25xx_request_irq(struct rsp_que *rsp)
 		return ret;
 	}
 	msix->have_irq = 1;
-	msix->rsp = rsp;
+	msix->handle = qpair;
 	return ret;
 }
 
@@ -3315,11 +3311,12 @@ static void qla_irq_affinity_notify(struct irq_affinity_notify *notify,
 		container_of(notify, struct qla_msix_entry, irq_notify);
 	struct qla_hw_data *ha;
 	struct scsi_qla_host *base_vha;
+	struct rsp_que *rsp = e->handle;
 
 	/* user is recommended to set mask to just 1 cpu */
 	e->cpuid = cpumask_first(mask);
 
-	ha = e->rsp->hw;
+	ha = rsp->hw;
 	base_vha = pci_get_drvdata(ha->pdev);
 
 	ql_dbg(ql_dbg_init, base_vha, 0xffff,
@@ -3343,9 +3340,10 @@ static void qla_irq_affinity_release(struct kref *ref)
 		container_of(ref, struct irq_affinity_notify, kref);
 	struct qla_msix_entry *e =
 		container_of(notify, struct qla_msix_entry, irq_notify);
-	struct scsi_qla_host *base_vha = pci_get_drvdata(e->rsp->hw->pdev);
+	struct rsp_que *rsp = e->handle;
+	struct scsi_qla_host *base_vha = pci_get_drvdata(rsp->hw->pdev);
 
 	ql_dbg(ql_dbg_init, base_vha, 0xffff,
-	    "%s: host%ld: vector %d cpu %d \n", __func__,
+		"%s: host%ld: vector %d cpu %d\n", __func__,
 	    base_vha->host_no, e->vector, e->cpuid);
 }
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 23698c998699..2819ceb96041 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -10,6 +10,43 @@
 #include <linux/delay.h>
 #include <linux/gfp.h>
 
+struct rom_cmd {
+	uint16_t cmd;
+} rom_cmds[] = {
+	{ MBC_LOAD_RAM },
+	{ MBC_EXECUTE_FIRMWARE },
+	{ MBC_READ_RAM_WORD },
+	{ MBC_MAILBOX_REGISTER_TEST },
+	{ MBC_VERIFY_CHECKSUM },
+	{ MBC_GET_FIRMWARE_VERSION },
+	{ MBC_LOAD_RISC_RAM },
+	{ MBC_DUMP_RISC_RAM },
+	{ MBC_LOAD_RISC_RAM_EXTENDED },
+	{ MBC_DUMP_RISC_RAM_EXTENDED },
+	{ MBC_WRITE_RAM_WORD_EXTENDED },
+	{ MBC_READ_RAM_EXTENDED },
+	{ MBC_GET_RESOURCE_COUNTS },
+	{ MBC_SET_FIRMWARE_OPTION },
+	{ MBC_MID_INITIALIZE_FIRMWARE },
+	{ MBC_GET_FIRMWARE_STATE },
+	{ MBC_GET_MEM_OFFLOAD_CNTRL_STAT },
+	{ MBC_GET_RETRY_COUNT },
+	{ MBC_TRACE_CONTROL },
+};
+
+static int is_rom_cmd(uint16_t cmd)
+{
+	int i;
+	struct  rom_cmd *wc;
+
+	for (i = 0; i < ARRAY_SIZE(rom_cmds); i++) {
+		wc = rom_cmds + i;
+		if (wc->cmd == cmd)
+			return 1;
+	}
+
+	return 0;
+}
 
 /*
  * qla2x00_mailbox_command
@@ -92,6 +129,17 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		return QLA_FUNCTION_TIMEOUT;
 	}
 
+	/* check if ISP abort is active and return cmd with timeout */
+	if ((test_bit(ABORT_ISP_ACTIVE, &base_vha->dpc_flags) ||
+	    test_bit(ISP_ABORT_RETRY, &base_vha->dpc_flags) ||
+	    test_bit(ISP_ABORT_NEEDED, &base_vha->dpc_flags)) &&
+	    !is_rom_cmd(mcp->mb[0])) {
+		ql_log(ql_log_info, vha, 0x1005,
+		    "Cmd 0x%x aborted with timeout since ISP Abort is pending\n",
+		    mcp->mb[0]);
+		return QLA_FUNCTION_TIMEOUT;
+	}
+
 	/*
 	 * Wait for active mailbox commands to finish by waiting at most tov
 	 * seconds. This is to serialize actual issuing of mailbox cmds during
@@ -178,6 +226,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 			WRT_REG_WORD(&reg->isp.hccr, HCCR_SET_HOST_INT);
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
+		wait_time = jiffies;
 		if (!wait_for_completion_timeout(&ha->mbx_intr_comp,
 		    mcp->tov * HZ)) {
 			ql_dbg(ql_dbg_mbx, vha, 0x117a,
@@ -186,6 +235,9 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 			clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		}
+		if (time_after(jiffies, wait_time + 5 * HZ))
+			ql_log(ql_log_warn, vha, 0x1015, "cmd=0x%x, waited %d msecs\n",
+			    command, jiffies_to_msecs(jiffies - wait_time));
 	} else {
 		ql_dbg(ql_dbg_mbx, vha, 0x1011,
 		    "Cmd=%x Polling Mode.\n", command);
@@ -1194,12 +1246,17 @@ qla2x00_abort_command(srb_t *sp)
 	fc_port_t	*fcport = sp->fcport;
 	scsi_qla_host_t *vha = fcport->vha;
 	struct qla_hw_data *ha = vha->hw;
-	struct req_que *req = vha->req;
+	struct req_que *req;
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
 
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x103b,
 	    "Entered %s.\n", __func__);
 
+	if (vha->flags.qpairs_available && sp->qpair)
+		req = sp->qpair->req;
+	else
+		req = vha->req;
+
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	for (handle = 1; handle < req->num_outstanding_cmds; handle++) {
 		if (req->outstanding_cmds[handle] == sp)
@@ -2152,10 +2209,10 @@ qla24xx_login_fabric(scsi_qla_host_t *vha, uint16_t loop_id, uint8_t domain,
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1061,
 	    "Entered %s.\n", __func__);
 
-	if (ha->flags.cpu_affinity_enabled)
-		req = ha->req_q_map[0];
+	if (vha->vp_idx && vha->qpair)
+		req = vha->qpair->req;
 	else
-		req = vha->req;
+		req = ha->req_q_map[0];
 
 	lg = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &lg_dma);
 	if (lg == NULL) {
@@ -2435,10 +2492,7 @@ qla24xx_fabric_logout(scsi_qla_host_t *vha, uint16_t loop_id, uint8_t domain,
 	}
 	memset(lg, 0, sizeof(struct logio_entry_24xx));
 
-	if (ql2xmaxqueues > 1)
-		req = ha->req_q_map[0];
-	else
-		req = vha->req;
+	req = vha->req;
 	lg->entry_type = LOGINOUT_PORT_IOCB_TYPE;
 	lg->entry_count = 1;
 	lg->handle = MAKE_HANDLE(req->id, lg->handle);
@@ -2904,6 +2958,9 @@ qla24xx_abort_command(srb_t *sp)
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x108c,
 	    "Entered %s.\n", __func__);
 
+	if (vha->flags.qpairs_available && sp->qpair)
+		req = sp->qpair->req;
+
 	if (ql2xasynctmfenable)
 		return qla24xx_async_abort_command(sp);
 
@@ -2984,6 +3041,7 @@ __qla24xx_issue_tmf(char *name, uint32_t type, struct fc_port *fcport,
 	struct qla_hw_data *ha;
 	struct req_que *req;
 	struct rsp_que *rsp;
+	struct qla_qpair *qpair;
 
 	vha = fcport->vha;
 	ha = vha->hw;
@@ -2992,10 +3050,15 @@ __qla24xx_issue_tmf(char *name, uint32_t type, struct fc_port *fcport,
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1092,
 	    "Entered %s.\n", __func__);
 
-	if (ha->flags.cpu_affinity_enabled)
-		rsp = ha->rsp_q_map[tag + 1];
-	else
+	if (vha->vp_idx && vha->qpair) {
+		/* NPIV port */
+		qpair = vha->qpair;
+		rsp = qpair->rsp;
+		req = qpair->req;
+	} else {
 		rsp = req->rsp;
+	}
+
 	tsk = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &tsk_dma);
 	if (tsk == NULL) {
 		ql_log(ql_log_warn, vha, 0x1093,
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index cf7ba52bae66..c6d6f0d912ff 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -540,9 +540,10 @@ qla25xx_free_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp)
 	uint16_t que_id = rsp->id;
 
 	if (rsp->msix && rsp->msix->have_irq) {
-		free_irq(rsp->msix->vector, rsp);
+		free_irq(rsp->msix->vector, rsp->msix->handle);
 		rsp->msix->have_irq = 0;
-		rsp->msix->rsp = NULL;
+		rsp->msix->in_use = 0;
+		rsp->msix->handle = NULL;
 	}
 	dma_free_coherent(&ha->pdev->dev, (rsp->length + 1) *
 		sizeof(response_t), rsp->ring, rsp->dma);
@@ -573,7 +574,7 @@ qla25xx_delete_req_que(struct scsi_qla_host *vha, struct req_que *req)
 	return ret;
 }
 
-static int
+int
 qla25xx_delete_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp)
 {
 	int ret = -1;
@@ -596,34 +597,42 @@ qla25xx_delete_queues(struct scsi_qla_host *vha)
 	struct req_que *req = NULL;
 	struct rsp_que *rsp = NULL;
 	struct qla_hw_data *ha = vha->hw;
+	struct qla_qpair *qpair, *tqpair;
 
-	/* Delete request queues */
-	for (cnt = 1; cnt < ha->max_req_queues; cnt++) {
-		req = ha->req_q_map[cnt];
-		if (req && test_bit(cnt, ha->req_qid_map)) {
-			ret = qla25xx_delete_req_que(vha, req);
-			if (ret != QLA_SUCCESS) {
-				ql_log(ql_log_warn, vha, 0x00ea,
-				    "Couldn't delete req que %d.\n",
-				    req->id);
-				return ret;
+	if (ql2xmqsupport) {
+		list_for_each_entry_safe(qpair, tqpair, &vha->qp_list,
+		    qp_list_elem)
+			qla2xxx_delete_qpair(vha, qpair);
+	} else {
+		/* Delete request queues */
+		for (cnt = 1; cnt < ha->max_req_queues; cnt++) {
+			req = ha->req_q_map[cnt];
+			if (req && test_bit(cnt, ha->req_qid_map)) {
+				ret = qla25xx_delete_req_que(vha, req);
+				if (ret != QLA_SUCCESS) {
+					ql_log(ql_log_warn, vha, 0x00ea,
+					    "Couldn't delete req que %d.\n",
+					    req->id);
+					return ret;
+				}
 			}
 		}
-	}
 
-	/* Delete response queues */
-	for (cnt = 1; cnt < ha->max_rsp_queues; cnt++) {
-		rsp = ha->rsp_q_map[cnt];
-		if (rsp && test_bit(cnt, ha->rsp_qid_map)) {
-			ret = qla25xx_delete_rsp_que(vha, rsp);
-			if (ret != QLA_SUCCESS) {
-				ql_log(ql_log_warn, vha, 0x00eb,
-				    "Couldn't delete rsp que %d.\n",
-				    rsp->id);
-				return ret;
+		/* Delete response queues */
+		for (cnt = 1; cnt < ha->max_rsp_queues; cnt++) {
+			rsp = ha->rsp_q_map[cnt];
+			if (rsp && test_bit(cnt, ha->rsp_qid_map)) {
+				ret = qla25xx_delete_rsp_que(vha, rsp);
+				if (ret != QLA_SUCCESS) {
+					ql_log(ql_log_warn, vha, 0x00eb,
+					    "Couldn't delete rsp que %d.\n",
+					    rsp->id);
+					return ret;
+				}
 			}
 		}
 	}
+
 	return ret;
 }
 
@@ -659,10 +668,10 @@ qla25xx_create_req_que(struct qla_hw_data *ha, uint16_t options,
 	if (ret != QLA_SUCCESS)
 		goto que_failed;
 
-	mutex_lock(&ha->vport_lock);
+	mutex_lock(&ha->mq_lock);
 	que_id = find_first_zero_bit(ha->req_qid_map, ha->max_req_queues);
 	if (que_id >= ha->max_req_queues) {
-		mutex_unlock(&ha->vport_lock);
+		mutex_unlock(&ha->mq_lock);
 		ql_log(ql_log_warn, base_vha, 0x00db,
 		    "No resources to create additional request queue.\n");
 		goto que_failed;
@@ -708,7 +717,7 @@ qla25xx_create_req_que(struct qla_hw_data *ha, uint16_t options,
 	req->req_q_out = &reg->isp25mq.req_q_out;
 	req->max_q_depth = ha->req_q_map[0]->max_q_depth;
 	req->out_ptr = (void *)(req->ring + req->length);
-	mutex_unlock(&ha->vport_lock);
+	mutex_unlock(&ha->mq_lock);
 	ql_dbg(ql_dbg_multiq, base_vha, 0xc004,
 	    "ring_ptr=%p ring_index=%d, "
 	    "cnt=%d id=%d max_q_depth=%d.\n",
@@ -724,9 +733,9 @@ qla25xx_create_req_que(struct qla_hw_data *ha, uint16_t options,
 	if (ret != QLA_SUCCESS) {
 		ql_log(ql_log_fatal, base_vha, 0x00df,
 		    "%s failed.\n", __func__);
-		mutex_lock(&ha->vport_lock);
+		mutex_lock(&ha->mq_lock);
 		clear_bit(que_id, ha->req_qid_map);
-		mutex_unlock(&ha->vport_lock);
+		mutex_unlock(&ha->mq_lock);
 		goto que_failed;
 	}
 
@@ -741,20 +750,20 @@ failed:
 static void qla_do_work(struct work_struct *work)
 {
 	unsigned long flags;
-	struct rsp_que *rsp = container_of(work, struct rsp_que, q_work);
+	struct qla_qpair *qpair = container_of(work, struct qla_qpair, q_work);
 	struct scsi_qla_host *vha;
-	struct qla_hw_data *ha = rsp->hw;
+	struct qla_hw_data *ha = qpair->hw;
 
-	spin_lock_irqsave(&rsp->hw->hardware_lock, flags);
+	spin_lock_irqsave(&qpair->qp_lock, flags);
 	vha = pci_get_drvdata(ha->pdev);
-	qla24xx_process_response_queue(vha, rsp);
-	spin_unlock_irqrestore(&rsp->hw->hardware_lock, flags);
+	qla24xx_process_response_queue(vha, qpair->rsp);
+	spin_unlock_irqrestore(&qpair->qp_lock, flags);
 }
 
 /* create response queue */
 int
 qla25xx_create_rsp_que(struct qla_hw_data *ha, uint16_t options,
-	uint8_t vp_idx, uint16_t rid, int req)
+	uint8_t vp_idx, uint16_t rid, struct qla_qpair *qpair)
 {
 	int ret = 0;
 	struct rsp_que *rsp = NULL;
@@ -779,28 +788,24 @@ qla25xx_create_rsp_que(struct qla_hw_data *ha, uint16_t options,
 		goto que_failed;
 	}
 
-	mutex_lock(&ha->vport_lock);
+	mutex_lock(&ha->mq_lock);
 	que_id = find_first_zero_bit(ha->rsp_qid_map, ha->max_rsp_queues);
 	if (que_id >= ha->max_rsp_queues) {
-		mutex_unlock(&ha->vport_lock);
+		mutex_unlock(&ha->mq_lock);
 		ql_log(ql_log_warn, base_vha, 0x00e2,
 		    "No resources to create additional request queue.\n");
 		goto que_failed;
 	}
 	set_bit(que_id, ha->rsp_qid_map);
 
-	if (ha->flags.msix_enabled)
-		rsp->msix = &ha->msix_entries[que_id + 1];
-	else
-		ql_log(ql_log_warn, base_vha, 0x00e3,
-		    "MSIX not enabled.\n");
+	rsp->msix = qpair->msix;
 
 	ha->rsp_q_map[que_id] = rsp;
 	rsp->rid = rid;
 	rsp->vp_idx = vp_idx;
 	rsp->hw = ha;
 	ql_dbg(ql_dbg_init, base_vha, 0x00e4,
-	    "queue_id=%d rid=%d vp_idx=%d hw=%p.\n",
+	    "rsp queue_id=%d rid=%d vp_idx=%d hw=%p.\n",
 	    que_id, rsp->rid, rsp->vp_idx, rsp->hw);
 	/* Use alternate PCI bus number */
 	if (MSB(rsp->rid))
@@ -812,23 +817,27 @@ qla25xx_create_rsp_que(struct qla_hw_data *ha, uint16_t options,
 	if (!IS_MSIX_NACK_CAPABLE(ha))
 		options |= BIT_6;
 
+	/* Set option to indicate response queue creation */
+	options |= BIT_1;
+
 	rsp->options = options;
 	rsp->id = que_id;
 	reg = ISP_QUE_REG(ha, que_id);
 	rsp->rsp_q_in = &reg->isp25mq.rsp_q_in;
 	rsp->rsp_q_out = &reg->isp25mq.rsp_q_out;
 	rsp->in_ptr = (void *)(rsp->ring + rsp->length);
-	mutex_unlock(&ha->vport_lock);
+	mutex_unlock(&ha->mq_lock);
 	ql_dbg(ql_dbg_multiq, base_vha, 0xc00b,
-	    "options=%x id=%d rsp_q_in=%p rsp_q_out=%p",
+	    "options=%x id=%d rsp_q_in=%p rsp_q_out=%p\n",
 	    rsp->options, rsp->id, rsp->rsp_q_in,
 	    rsp->rsp_q_out);
 	ql_dbg(ql_dbg_init, base_vha, 0x00e5,
-	    "options=%x id=%d rsp_q_in=%p rsp_q_out=%p",
+	    "options=%x id=%d rsp_q_in=%p rsp_q_out=%p\n",
 	    rsp->options, rsp->id, rsp->rsp_q_in,
 	    rsp->rsp_q_out);
 
-	ret = qla25xx_request_irq(rsp);
+	ret = qla25xx_request_irq(ha, qpair, qpair->msix,
+	    QLA_MSIX_QPAIR_MULTIQ_RSP_Q);
 	if (ret)
 		goto que_failed;
 
@@ -836,19 +845,16 @@ qla25xx_create_rsp_que(struct qla_hw_data *ha, uint16_t options,
 	if (ret != QLA_SUCCESS) {
 		ql_log(ql_log_fatal, base_vha, 0x00e7,
 		    "%s failed.\n", __func__);
-		mutex_lock(&ha->vport_lock);
+		mutex_lock(&ha->mq_lock);
 		clear_bit(que_id, ha->rsp_qid_map);
-		mutex_unlock(&ha->vport_lock);
+		mutex_unlock(&ha->mq_lock);
 		goto que_failed;
 	}
-	if (req >= 0)
-		rsp->req = ha->req_q_map[req];
-	else
-		rsp->req = NULL;
+	rsp->req = NULL;
 
 	qla2x00_init_response_q_entries(rsp);
-	if (rsp->hw->wq)
-		INIT_WORK(&rsp->q_work, qla_do_work);
+	if (qpair->hw->wq)
+		INIT_WORK(&qpair->q_work, qla_do_work);
 	return rsp->id;
 
 que_failed:
diff --git a/drivers/scsi/qla2xxx/qla_mr.c b/drivers/scsi/qla2xxx/qla_mr.c
index 15dff7099955..02f1de18bc2b 100644
--- a/drivers/scsi/qla2xxx/qla_mr.c
+++ b/drivers/scsi/qla2xxx/qla_mr.c
@@ -10,6 +10,7 @@
 #include <linux/pci.h>
 #include <linux/ratelimit.h>
 #include <linux/vmalloc.h>
+#include <linux/bsg-lib.h>
 #include <scsi/scsi_tcq.h>
 #include <linux/utsname.h>
 
@@ -2206,7 +2207,8 @@ qlafx00_ioctl_iosb_entry(scsi_qla_host_t *vha, struct req_que *req,
 {
 	const char func[] = "IOSB_IOCB";
 	srb_t *sp;
-	struct fc_bsg_job *bsg_job;
+	struct bsg_job *bsg_job;
+	struct fc_bsg_reply *bsg_reply;
 	struct srb_iocb *iocb_job;
 	int res;
 	struct qla_mt_iocb_rsp_fx00 fstatus;
@@ -2226,6 +2228,7 @@ qlafx00_ioctl_iosb_entry(scsi_qla_host_t *vha, struct req_que *req,
 			    pkt->dataword_r;
 	} else {
 		bsg_job = sp->u.bsg_job;
+		bsg_reply = bsg_job->reply;
 
 		memset(&fstatus, 0, sizeof(struct qla_mt_iocb_rsp_fx00));
 
@@ -2257,8 +2260,8 @@ qlafx00_ioctl_iosb_entry(scsi_qla_host_t *vha, struct req_que *req,
 		    sp->fcport->vha, 0x5074,
 		    (uint8_t *)fw_sts_ptr, sizeof(struct qla_mt_iocb_rsp_fx00));
 
-		res = bsg_job->reply->result = DID_OK << 16;
-		bsg_job->reply->reply_payload_rcv_len =
+		res = bsg_reply->result = DID_OK << 16;
+		bsg_reply->reply_payload_rcv_len =
 		    bsg_job->reply_payload.payload_len;
 	}
 	sp->done(vha, sp, res);
@@ -3252,7 +3255,8 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb)
 {
 	struct srb_iocb *fxio = &sp->u.iocb_cmd;
 	struct qla_mt_iocb_rqst_fx00 *piocb_rqst;
-	struct fc_bsg_job *bsg_job;
+	struct bsg_job *bsg_job;
+	struct fc_bsg_request *bsg_request;
 	struct fxdisc_entry_fx00 fx_iocb;
 	uint8_t entry_cnt = 1;
 
@@ -3301,8 +3305,9 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb)
 	} else {
 		struct scatterlist *sg;
 		bsg_job = sp->u.bsg_job;
+		bsg_request = bsg_job->request;
 		piocb_rqst = (struct qla_mt_iocb_rqst_fx00 *)
-			&bsg_job->request->rqst_data.h_vendor.vendor_cmd[1];
+			&bsg_request->rqst_data.h_vendor.vendor_cmd[1];
 
 		fx_iocb.func_num = piocb_rqst->func_type;
 		fx_iocb.adapid = piocb_rqst->adapid;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 567fa080e261..8521cfe302e9 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -13,6 +13,7 @@
 #include <linux/mutex.h>
 #include <linux/kobject.h>
 #include <linux/slab.h>
+#include <linux/blk-mq-pci.h>
 #include <scsi/scsi_tcq.h>
 #include <scsi/scsicam.h>
 #include <scsi/scsi_transport.h>
@@ -30,7 +31,7 @@ static int apidev_major;
 /*
  * SRB allocation cache
  */
-static struct kmem_cache *srb_cachep;
+struct kmem_cache *srb_cachep;
 
 /*
  * CT6 CTX allocation cache
@@ -143,19 +144,12 @@ MODULE_PARM_DESC(ql2xiidmaenable,
 		"Enables iIDMA settings "
 		"Default is 1 - perform iIDMA. 0 - no iIDMA.");
 
-int ql2xmaxqueues = 1;
-module_param(ql2xmaxqueues, int, S_IRUGO);
-MODULE_PARM_DESC(ql2xmaxqueues,
-		"Enables MQ settings "
-		"Default is 1 for single queue. Set it to number "
-		"of queues in MQ mode.");
-
-int ql2xmultique_tag;
-module_param(ql2xmultique_tag, int, S_IRUGO);
-MODULE_PARM_DESC(ql2xmultique_tag,
-		"Enables CPU affinity settings for the driver "
-		"Default is 0 for no affinity of request and response IO. "
-		"Set it to 1 to turn on the cpu affinity.");
+int ql2xmqsupport = 1;
+module_param(ql2xmqsupport, int, S_IRUGO);
+MODULE_PARM_DESC(ql2xmqsupport,
+		"Enable on demand multiple queue pairs support "
+		"Default is 1 for supported. "
+		"Set it to 0 to turn off mq qpair support.");
 
 int ql2xfwloadbin;
 module_param(ql2xfwloadbin, int, S_IRUGO|S_IWUSR);
@@ -261,6 +255,7 @@ static int qla2xxx_eh_host_reset(struct scsi_cmnd *);
 static void qla2x00_clear_drv_active(struct qla_hw_data *);
 static void qla2x00_free_device(scsi_qla_host_t *);
 static void qla83xx_disable_laser(scsi_qla_host_t *vha);
+static int qla2xxx_map_queues(struct Scsi_Host *shost);
 
 struct scsi_host_template qla2xxx_driver_template = {
 	.module			= THIS_MODULE,
@@ -280,6 +275,7 @@ struct scsi_host_template qla2xxx_driver_template = {
 	.scan_finished		= qla2xxx_scan_finished,
 	.scan_start		= qla2xxx_scan_start,
 	.change_queue_depth	= scsi_change_queue_depth,
+	.map_queues             = qla2xxx_map_queues,
 	.this_id		= -1,
 	.cmd_per_lun		= 3,
 	.use_clustering		= ENABLE_CLUSTERING,
@@ -339,6 +335,8 @@ static int qla2x00_mem_alloc(struct qla_hw_data *, uint16_t, uint16_t,
 	struct req_que **, struct rsp_que **);
 static void qla2x00_free_fw_dump(struct qla_hw_data *);
 static void qla2x00_mem_free(struct qla_hw_data *);
+int qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd,
+	struct qla_qpair *qpair);
 
 /* -------------------------------------------------------------------------- */
 static int qla2x00_alloc_queues(struct qla_hw_data *ha, struct req_que *req,
@@ -360,6 +358,25 @@ static int qla2x00_alloc_queues(struct qla_hw_data *ha, struct req_que *req,
 		    "Unable to allocate memory for response queue ptrs.\n");
 		goto fail_rsp_map;
 	}
+
+	if (ql2xmqsupport && ha->max_qpairs) {
+		ha->queue_pair_map = kcalloc(ha->max_qpairs, sizeof(struct qla_qpair *),
+			GFP_KERNEL);
+		if (!ha->queue_pair_map) {
+			ql_log(ql_log_fatal, vha, 0x0180,
+			    "Unable to allocate memory for queue pair ptrs.\n");
+			goto fail_qpair_map;
+		}
+		ha->base_qpair = kzalloc(sizeof(struct qla_qpair), GFP_KERNEL);
+		if (ha->base_qpair == NULL) {
+			ql_log(ql_log_warn, vha, 0x0182,
+			    "Failed to allocate base queue pair memory.\n");
+			goto fail_base_qpair;
+		}
+		ha->base_qpair->req = req;
+		ha->base_qpair->rsp = rsp;
+	}
+
 	/*
 	 * Make sure we record at least the request and response queue zero in
 	 * case we need to free them if part of the probe fails.
@@ -370,6 +387,11 @@ static int qla2x00_alloc_queues(struct qla_hw_data *ha, struct req_que *req,
 	set_bit(0, ha->req_qid_map);
 	return 1;
 
+fail_base_qpair:
+	kfree(ha->queue_pair_map);
+fail_qpair_map:
+	kfree(ha->rsp_q_map);
+	ha->rsp_q_map = NULL;
 fail_rsp_map:
 	kfree(ha->req_q_map);
 	ha->req_q_map = NULL;
@@ -417,82 +439,43 @@ static void qla2x00_free_queues(struct qla_hw_data *ha)
 	struct req_que *req;
 	struct rsp_que *rsp;
 	int cnt;
+	unsigned long flags;
 
+	spin_lock_irqsave(&ha->hardware_lock, flags);
 	for (cnt = 0; cnt < ha->max_req_queues; cnt++) {
 		if (!test_bit(cnt, ha->req_qid_map))
 			continue;
 
 		req = ha->req_q_map[cnt];
+		clear_bit(cnt, ha->req_qid_map);
+		ha->req_q_map[cnt] = NULL;
+
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		qla2x00_free_req_que(ha, req);
+		spin_lock_irqsave(&ha->hardware_lock, flags);
 	}
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 	kfree(ha->req_q_map);
 	ha->req_q_map = NULL;
 
+
+	spin_lock_irqsave(&ha->hardware_lock, flags);
 	for (cnt = 0; cnt < ha->max_rsp_queues; cnt++) {
 		if (!test_bit(cnt, ha->rsp_qid_map))
 			continue;
 
 		rsp = ha->rsp_q_map[cnt];
+		clear_bit(cnt, ha->req_qid_map);
+		ha->rsp_q_map[cnt] =  NULL;
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		qla2x00_free_rsp_que(ha, rsp);
+		spin_lock_irqsave(&ha->hardware_lock, flags);
 	}
-	kfree(ha->rsp_q_map);
-	ha->rsp_q_map = NULL;
-}
-
-static int qla25xx_setup_mode(struct scsi_qla_host *vha)
-{
-	uint16_t options = 0;
-	int ques, req, ret;
-	struct qla_hw_data *ha = vha->hw;
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
-	if (!(ha->fw_attributes & BIT_6)) {
-		ql_log(ql_log_warn, vha, 0x00d8,
-		    "Firmware is not multi-queue capable.\n");
-		goto fail;
-	}
-	if (ql2xmultique_tag) {
-		/* create a request queue for IO */
-		options |= BIT_7;
-		req = qla25xx_create_req_que(ha, options, 0, 0, -1,
-			QLA_DEFAULT_QUE_QOS);
-		if (!req) {
-			ql_log(ql_log_warn, vha, 0x00e0,
-			    "Failed to create request queue.\n");
-			goto fail;
-		}
-		ha->wq = alloc_workqueue("qla2xxx_wq", WQ_MEM_RECLAIM, 1);
-		vha->req = ha->req_q_map[req];
-		options |= BIT_1;
-		for (ques = 1; ques < ha->max_rsp_queues; ques++) {
-			ret = qla25xx_create_rsp_que(ha, options, 0, 0, req);
-			if (!ret) {
-				ql_log(ql_log_warn, vha, 0x00e8,
-				    "Failed to create response queue.\n");
-				goto fail2;
-			}
-		}
-		ha->flags.cpu_affinity_enabled = 1;
-		ql_dbg(ql_dbg_multiq, vha, 0xc007,
-		    "CPU affinity mode enabled, "
-		    "no. of response queues:%d no. of request queues:%d.\n",
-		    ha->max_rsp_queues, ha->max_req_queues);
-		ql_dbg(ql_dbg_init, vha, 0x00e9,
-		    "CPU affinity mode enabled, "
-		    "no. of response queues:%d no. of request queues:%d.\n",
-		    ha->max_rsp_queues, ha->max_req_queues);
-	}
-	return 0;
-fail2:
-	qla25xx_delete_queues(vha);
-	destroy_workqueue(ha->wq);
-	ha->wq = NULL;
-	vha->req = ha->req_q_map[0];
-fail:
-	ha->mqenable = 0;
-	kfree(ha->req_q_map);
 	kfree(ha->rsp_q_map);
-	ha->max_req_queues = ha->max_rsp_queues = 1;
-	return 1;
+	ha->rsp_q_map = NULL;
 }
 
 static char *
@@ -669,7 +652,7 @@ qla2x00_sp_free_dma(void *vha, void *ptr)
 	qla2x00_rel_sp(sp->fcport->vha, sp);
 }
 
-static void
+void
 qla2x00_sp_compl(void *data, void *ptr, int res)
 {
 	struct qla_hw_data *ha = (struct qla_hw_data *)data;
@@ -693,6 +676,75 @@ qla2x00_sp_compl(void *data, void *ptr, int res)
 	cmd->scsi_done(cmd);
 }
 
+void
+qla2xxx_qpair_sp_free_dma(void *vha, void *ptr)
+{
+	srb_t *sp = (srb_t *)ptr;
+	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
+	struct qla_hw_data *ha = sp->fcport->vha->hw;
+	void *ctx = GET_CMD_CTX_SP(sp);
+
+	if (sp->flags & SRB_DMA_VALID) {
+		scsi_dma_unmap(cmd);
+		sp->flags &= ~SRB_DMA_VALID;
+	}
+
+	if (sp->flags & SRB_CRC_PROT_DMA_VALID) {
+		dma_unmap_sg(&ha->pdev->dev, scsi_prot_sglist(cmd),
+		    scsi_prot_sg_count(cmd), cmd->sc_data_direction);
+		sp->flags &= ~SRB_CRC_PROT_DMA_VALID;
+	}
+
+	if (sp->flags & SRB_CRC_CTX_DSD_VALID) {
+		/* List assured to be having elements */
+		qla2x00_clean_dsd_pool(ha, sp, NULL);
+		sp->flags &= ~SRB_CRC_CTX_DSD_VALID;
+	}
+
+	if (sp->flags & SRB_CRC_CTX_DMA_VALID) {
+		dma_pool_free(ha->dl_dma_pool, ctx,
+		    ((struct crc_context *)ctx)->crc_ctx_dma);
+		sp->flags &= ~SRB_CRC_CTX_DMA_VALID;
+	}
+
+	if (sp->flags & SRB_FCP_CMND_DMA_VALID) {
+		struct ct6_dsd *ctx1 = (struct ct6_dsd *)ctx;
+
+		dma_pool_free(ha->fcp_cmnd_dma_pool, ctx1->fcp_cmnd,
+		    ctx1->fcp_cmnd_dma);
+		list_splice(&ctx1->dsd_list, &ha->gbl_dsd_list);
+		ha->gbl_dsd_inuse -= ctx1->dsd_use_cnt;
+		ha->gbl_dsd_avail += ctx1->dsd_use_cnt;
+		mempool_free(ctx1, ha->ctx_mempool);
+	}
+
+	CMD_SP(cmd) = NULL;
+	qla2xxx_rel_qpair_sp(sp->qpair, sp);
+}
+
+void
+qla2xxx_qpair_sp_compl(void *data, void *ptr, int res)
+{
+	srb_t *sp = (srb_t *)ptr;
+	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
+
+	cmd->result = res;
+
+	if (atomic_read(&sp->ref_count) == 0) {
+		ql_dbg(ql_dbg_io, sp->fcport->vha, 0x3079,
+		    "SP reference-count to ZERO -- sp=%p cmd=%p.\n",
+		    sp, GET_CMD_SP(sp));
+		if (ql2xextended_error_logging & ql_dbg_io)
+			WARN_ON(atomic_read(&sp->ref_count) == 0);
+		return;
+	}
+	if (!atomic_dec_and_test(&sp->ref_count))
+		return;
+
+	qla2xxx_qpair_sp_free_dma(sp->fcport->vha, sp);
+	cmd->scsi_done(cmd);
+}
+
 /* If we are SP1 here, we need to still take and release the host_lock as SP1
  * does not have the changes necessary to avoid taking host->host_lock.
  */
@@ -706,12 +758,28 @@ qla2xxx_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
 	srb_t *sp;
 	int rval;
+	struct qla_qpair *qpair = NULL;
+	uint32_t tag;
+	uint16_t hwq;
 
 	if (unlikely(test_bit(UNLOADING, &base_vha->dpc_flags))) {
 		cmd->result = DID_NO_CONNECT << 16;
 		goto qc24_fail_command;
 	}
 
+	if (ha->mqenable) {
+		if (shost_use_blk_mq(vha->host)) {
+			tag = blk_mq_unique_tag(cmd->request);
+			hwq = blk_mq_unique_tag_to_hwq(tag);
+			qpair = ha->queue_pair_map[hwq];
+		} else if (vha->vp_idx && vha->qpair) {
+			qpair = vha->qpair;
+		}
+
+		if (qpair)
+			return qla2xxx_mqueuecommand(host, cmd, qpair);
+	}
+
 	if (ha->flags.eeh_busy) {
 		if (ha->flags.pci_channel_io_perm_failure) {
 			ql_dbg(ql_dbg_aer, vha, 0x9010,
@@ -808,6 +876,95 @@ qc24_fail_command:
 	return 0;
 }
 
+/* For MQ supported I/O */
+int
+qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd,
+    struct qla_qpair *qpair)
+{
+	scsi_qla_host_t *vha = shost_priv(host);
+	fc_port_t *fcport = (struct fc_port *) cmd->device->hostdata;
+	struct fc_rport *rport = starget_to_rport(scsi_target(cmd->device));
+	struct qla_hw_data *ha = vha->hw;
+	struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
+	srb_t *sp;
+	int rval;
+
+	rval = fc_remote_port_chkready(rport);
+	if (rval) {
+		cmd->result = rval;
+		ql_dbg(ql_dbg_io + ql_dbg_verbose, vha, 0x3076,
+		    "fc_remote_port_chkready failed for cmd=%p, rval=0x%x.\n",
+		    cmd, rval);
+		goto qc24_fail_command;
+	}
+
+	if (!fcport) {
+		cmd->result = DID_NO_CONNECT << 16;
+		goto qc24_fail_command;
+	}
+
+	if (atomic_read(&fcport->state) != FCS_ONLINE) {
+		if (atomic_read(&fcport->state) == FCS_DEVICE_DEAD ||
+			atomic_read(&base_vha->loop_state) == LOOP_DEAD) {
+			ql_dbg(ql_dbg_io, vha, 0x3077,
+			    "Returning DNC, fcport_state=%d loop_state=%d.\n",
+			    atomic_read(&fcport->state),
+			    atomic_read(&base_vha->loop_state));
+			cmd->result = DID_NO_CONNECT << 16;
+			goto qc24_fail_command;
+		}
+		goto qc24_target_busy;
+	}
+
+	/*
+	 * Return target busy if we've received a non-zero retry_delay_timer
+	 * in a FCP_RSP.
+	 */
+	if (fcport->retry_delay_timestamp == 0) {
+		/* retry delay not set */
+	} else if (time_after(jiffies, fcport->retry_delay_timestamp))
+		fcport->retry_delay_timestamp = 0;
+	else
+		goto qc24_target_busy;
+
+	sp = qla2xxx_get_qpair_sp(qpair, fcport, GFP_ATOMIC);
+	if (!sp)
+		goto qc24_host_busy;
+
+	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_host_busy_free_sp;
+	}
+
+	return 0;
+
+qc24_host_busy_free_sp:
+	qla2xxx_qpair_sp_free_dma(vha, sp);
+
+qc24_host_busy:
+	return SCSI_MLQUEUE_HOST_BUSY;
+
+qc24_target_busy:
+	return SCSI_MLQUEUE_TARGET_BUSY;
+
+qc24_fail_command:
+	cmd->scsi_done(cmd);
+
+	return 0;
+}
+
 /*
  * qla2x00_eh_wait_on_command
  *    Waits for the command to be returned by the Firmware for some
@@ -1456,15 +1613,20 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res)
 		for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) {
 			sp = req->outstanding_cmds[cnt];
 			if (sp) {
-				/* Get a reference to the sp and drop the lock.
-				 * The reference ensures this sp->done() call
-				 * - and not the call in qla2xxx_eh_abort() -
-				 * ends the SCSI command (with result 'res').
+				/* Don't abort commands in adapter during EEH
+				 * recovery as it's not accessible/responding.
 				 */
-				sp_get(sp);
-				spin_unlock_irqrestore(&ha->hardware_lock, flags);
-				qla2xxx_eh_abort(GET_CMD_SP(sp));
-				spin_lock_irqsave(&ha->hardware_lock, flags);
+				if (!ha->flags.eeh_busy) {
+					/* Get a reference to the sp and drop the lock.
+					 * The reference ensures this sp->done() call
+					 * - and not the call in qla2xxx_eh_abort() -
+					 * ends the SCSI command (with result 'res').
+					 */
+					sp_get(sp);
+					spin_unlock_irqrestore(&ha->hardware_lock, flags);
+					qla2xxx_eh_abort(GET_CMD_SP(sp));
+					spin_lock_irqsave(&ha->hardware_lock, flags);
+				}
 				req->outstanding_cmds[cnt] = NULL;
 				sp->done(vha, sp, res);
 			}
@@ -1596,7 +1758,6 @@ qla2x00_iospace_config(struct qla_hw_data *ha)
 {
 	resource_size_t pio;
 	uint16_t msix;
-	int cpus;
 
 	if (pci_request_selected_regions(ha->pdev, ha->bars,
 	    QLA2XXX_DRIVER_NAME)) {
@@ -1653,9 +1814,7 @@ skip_pio:
 
 	/* Determine queue resources */
 	ha->max_req_queues = ha->max_rsp_queues = 1;
-	if ((ql2xmaxqueues <= 1 && !ql2xmultique_tag) ||
-		(ql2xmaxqueues > 1 && ql2xmultique_tag) ||
-		(!IS_QLA25XX(ha) && !IS_QLA81XX(ha)))
+	if (!ql2xmqsupport || (!IS_QLA25XX(ha) && !IS_QLA81XX(ha)))
 		goto mqiobase_exit;
 
 	ha->mqiobase = ioremap(pci_resource_start(ha->pdev, 3),
@@ -1665,26 +1824,18 @@ skip_pio:
 		    "MQIO Base=%p.\n", ha->mqiobase);
 		/* Read MSIX vector size of the board */
 		pci_read_config_word(ha->pdev, QLA_PCI_MSIX_CONTROL, &msix);
-		ha->msix_count = msix;
+		ha->msix_count = msix + 1;
 		/* Max queues are bounded by available msix vectors */
-		/* queue 0 uses two msix vectors */
-		if (ql2xmultique_tag) {
-			cpus = num_online_cpus();
-			ha->max_rsp_queues = (ha->msix_count - 1 > cpus) ?
-				(cpus + 1) : (ha->msix_count - 1);
-			ha->max_req_queues = 2;
-		} else if (ql2xmaxqueues > 1) {
-			ha->max_req_queues = ql2xmaxqueues > QLA_MQ_SIZE ?
-			    QLA_MQ_SIZE : ql2xmaxqueues;
-			ql_dbg_pci(ql_dbg_multiq, ha->pdev, 0xc008,
-			    "QoS mode set, max no of request queues:%d.\n",
-			    ha->max_req_queues);
-			ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0019,
-			    "QoS mode set, max no of request queues:%d.\n",
-			    ha->max_req_queues);
-		}
+		/* MB interrupt uses 1 vector */
+		ha->max_req_queues = ha->msix_count - 1;
+		ha->max_rsp_queues = ha->max_req_queues;
+		/* Queue pairs is the max value minus the base queue pair */
+		ha->max_qpairs = ha->max_rsp_queues - 1;
+		ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0188,
+		    "Max no of queues pairs: %d.\n", ha->max_qpairs);
+
 		ql_log_pci(ql_log_info, ha->pdev, 0x001a,
-		    "MSI-X vector count: %d.\n", msix);
+		    "MSI-X vector count: %d.\n", ha->msix_count);
 	} else
 		ql_log_pci(ql_log_info, ha->pdev, 0x001b,
 		    "BAR 3 not enabled.\n");
@@ -1704,7 +1855,6 @@ static int
 qla83xx_iospace_config(struct qla_hw_data *ha)
 {
 	uint16_t msix;
-	int cpus;
 
 	if (pci_request_selected_regions(ha->pdev, ha->bars,
 	    QLA2XXX_DRIVER_NAME)) {
@@ -1756,32 +1906,36 @@ qla83xx_iospace_config(struct qla_hw_data *ha)
 		/* Read MSIX vector size of the board */
 		pci_read_config_word(ha->pdev,
 		    QLA_83XX_PCI_MSIX_CONTROL, &msix);
-		ha->msix_count = msix;
-		/* Max queues are bounded by available msix vectors */
-		/* queue 0 uses two msix vectors */
-		if (ql2xmultique_tag) {
-			cpus = num_online_cpus();
-			ha->max_rsp_queues = (ha->msix_count - 1 > cpus) ?
-				(cpus + 1) : (ha->msix_count - 1);
-			ha->max_req_queues = 2;
-		} else if (ql2xmaxqueues > 1) {
-			ha->max_req_queues = ql2xmaxqueues > QLA_MQ_SIZE ?
-						QLA_MQ_SIZE : ql2xmaxqueues;
-			ql_dbg_pci(ql_dbg_multiq, ha->pdev, 0xc00c,
-			    "QoS mode set, max no of request queues:%d.\n",
-			    ha->max_req_queues);
-			ql_dbg_pci(ql_dbg_init, ha->pdev, 0x011b,
-			    "QoS mode set, max no of request queues:%d.\n",
-			    ha->max_req_queues);
+		ha->msix_count = msix + 1;
+		/*
+		 * By default, driver uses at least two msix vectors
+		 * (default & rspq)
+		 */
+		if (ql2xmqsupport) {
+			/* MB interrupt uses 1 vector */
+			ha->max_req_queues = ha->msix_count - 1;
+			ha->max_rsp_queues = ha->max_req_queues;
+
+			/* ATIOQ needs 1 vector. That's 1 less QPair */
+			if (QLA_TGT_MODE_ENABLED())
+				ha->max_req_queues--;
+
+			/* Queue pairs is the max value minus
+			 * the base queue pair */
+			ha->max_qpairs = ha->max_req_queues - 1;
+			ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0190,
+			    "Max no of queues pairs: %d.\n", ha->max_qpairs);
 		}
 		ql_log_pci(ql_log_info, ha->pdev, 0x011c,
-		    "MSI-X vector count: %d.\n", msix);
+		    "MSI-X vector count: %d.\n", ha->msix_count);
 	} else
 		ql_log_pci(ql_log_info, ha->pdev, 0x011e,
 		    "BAR 1 not enabled.\n");
 
 mqiobase_exit:
 	ha->msix_count = ha->max_rsp_queues + 1;
+	if (QLA_TGT_MODE_ENABLED())
+		ha->msix_count++;
 
 	qlt_83xx_iospace_config(ha);
 
@@ -1826,6 +1980,7 @@ static struct isp_operations qla2100_isp_ops = {
 	.write_optrom		= qla2x00_write_optrom_data,
 	.get_flash_version	= qla2x00_get_flash_version,
 	.start_scsi		= qla2x00_start_scsi,
+	.start_scsi_mq          = NULL,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config     	= qla2x00_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -1864,6 +2019,7 @@ static struct isp_operations qla2300_isp_ops = {
 	.write_optrom		= qla2x00_write_optrom_data,
 	.get_flash_version	= qla2x00_get_flash_version,
 	.start_scsi		= qla2x00_start_scsi,
+	.start_scsi_mq          = NULL,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config		= qla2x00_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -1902,6 +2058,7 @@ static struct isp_operations qla24xx_isp_ops = {
 	.write_optrom		= qla24xx_write_optrom_data,
 	.get_flash_version	= qla24xx_get_flash_version,
 	.start_scsi		= qla24xx_start_scsi,
+	.start_scsi_mq          = NULL,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config		= qla2x00_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -1940,6 +2097,7 @@ static struct isp_operations qla25xx_isp_ops = {
 	.write_optrom		= qla24xx_write_optrom_data,
 	.get_flash_version	= qla24xx_get_flash_version,
 	.start_scsi		= qla24xx_dif_start_scsi,
+	.start_scsi_mq          = qla2xxx_dif_start_scsi_mq,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config		= qla2x00_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -1978,6 +2136,7 @@ static struct isp_operations qla81xx_isp_ops = {
 	.write_optrom		= qla24xx_write_optrom_data,
 	.get_flash_version	= qla24xx_get_flash_version,
 	.start_scsi		= qla24xx_dif_start_scsi,
+	.start_scsi_mq          = qla2xxx_dif_start_scsi_mq,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config		= qla2x00_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -2016,6 +2175,7 @@ static struct isp_operations qla82xx_isp_ops = {
 	.write_optrom		= qla82xx_write_optrom_data,
 	.get_flash_version	= qla82xx_get_flash_version,
 	.start_scsi             = qla82xx_start_scsi,
+	.start_scsi_mq          = NULL,
 	.abort_isp		= qla82xx_abort_isp,
 	.iospace_config     	= qla82xx_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -2054,6 +2214,7 @@ static struct isp_operations qla8044_isp_ops = {
 	.write_optrom		= qla8044_write_optrom_data,
 	.get_flash_version	= qla82xx_get_flash_version,
 	.start_scsi             = qla82xx_start_scsi,
+	.start_scsi_mq          = NULL,
 	.abort_isp		= qla8044_abort_isp,
 	.iospace_config		= qla82xx_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -2092,6 +2253,7 @@ static struct isp_operations qla83xx_isp_ops = {
 	.write_optrom		= qla24xx_write_optrom_data,
 	.get_flash_version	= qla24xx_get_flash_version,
 	.start_scsi		= qla24xx_dif_start_scsi,
+	.start_scsi_mq          = qla2xxx_dif_start_scsi_mq,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config		= qla83xx_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -2130,6 +2292,7 @@ static struct isp_operations qlafx00_isp_ops = {
 	.write_optrom		= qla24xx_write_optrom_data,
 	.get_flash_version	= qla24xx_get_flash_version,
 	.start_scsi		= qlafx00_start_scsi,
+	.start_scsi_mq          = NULL,
 	.abort_isp		= qlafx00_abort_isp,
 	.iospace_config		= qlafx00_iospace_config,
 	.initialize_adapter	= qlafx00_initialize_adapter,
@@ -2168,6 +2331,7 @@ static struct isp_operations qla27xx_isp_ops = {
 	.write_optrom		= qla24xx_write_optrom_data,
 	.get_flash_version	= qla24xx_get_flash_version,
 	.start_scsi		= qla24xx_dif_start_scsi,
+	.start_scsi_mq          = qla2xxx_dif_start_scsi_mq,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config		= qla83xx_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -2382,6 +2546,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	uint16_t req_length = 0, rsp_length = 0;
 	struct req_que *req = NULL;
 	struct rsp_que *rsp = NULL;
+	int i;
+
 	bars = pci_select_bars(pdev, IORESOURCE_MEM | IORESOURCE_IO);
 	sht = &qla2xxx_driver_template;
 	if (pdev->device == PCI_DEVICE_ID_QLOGIC_ISP2422 ||
@@ -2645,6 +2811,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    "Found an ISP%04X irq %d iobase 0x%p.\n",
 	    pdev->device, pdev->irq, ha->iobase);
 	mutex_init(&ha->vport_lock);
+	mutex_init(&ha->mq_lock);
 	init_completion(&ha->mbx_cmd_comp);
 	complete(&ha->mbx_cmd_comp);
 	init_completion(&ha->mbx_intr_comp);
@@ -2732,7 +2899,11 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    host->max_cmd_len, host->max_channel, host->max_lun,
 	    host->transportt, sht->vendor_id);
 
-que_init:
+	/* Set up the irqs */
+	ret = qla2x00_request_irqs(ha, rsp);
+	if (ret)
+		goto probe_init_failed;
+
 	/* Alloc arrays of request and response ring ptrs */
 	if (!qla2x00_alloc_queues(ha, req, rsp)) {
 		ql_log(ql_log_fatal, base_vha, 0x003d,
@@ -2741,12 +2912,17 @@ que_init:
 		goto probe_init_failed;
 	}
 
-	qlt_probe_one_stage1(base_vha, ha);
+	if (ha->mqenable && shost_use_blk_mq(host)) {
+		/* number of hardware queues supported by blk/scsi-mq*/
+		host->nr_hw_queues = ha->max_qpairs;
 
-	/* Set up the irqs */
-	ret = qla2x00_request_irqs(ha, rsp);
-	if (ret)
-		goto probe_init_failed;
+		ql_dbg(ql_dbg_init, base_vha, 0x0192,
+			"blk/scsi-mq enabled, HW queues = %d.\n", host->nr_hw_queues);
+	} else
+		ql_dbg(ql_dbg_init, base_vha, 0x0193,
+			"blk/scsi-mq disabled.\n");
+
+	qlt_probe_one_stage1(base_vha, ha);
 
 	pci_save_state(pdev);
 
@@ -2837,11 +3013,12 @@ que_init:
 	    host->can_queue, base_vha->req,
 	    base_vha->mgmt_svr_loop_id, host->sg_tablesize);
 
-	if (ha->mqenable) {
-		if (qla25xx_setup_mode(base_vha)) {
-			ql_log(ql_log_warn, base_vha, 0x00ec,
-			    "Failed to create queues, falling back to single queue mode.\n");
-			goto que_init;
+	if (ha->mqenable && qla_ini_mode_enabled(base_vha)) {
+		ha->wq = alloc_workqueue("qla2xxx_wq", WQ_MEM_RECLAIM, 1);
+		/* Create start of day qpairs for Block MQ */
+		if (shost_use_blk_mq(host)) {
+			for (i = 0; i < ha->max_qpairs; i++)
+				qla2xxx_create_qpair(base_vha, 5, 0);
 		}
 	}
 
@@ -3110,13 +3287,6 @@ qla2x00_delete_all_vps(struct qla_hw_data *ha, scsi_qla_host_t *base_vha)
 static void
 qla2x00_destroy_deferred_work(struct qla_hw_data *ha)
 {
-	/* Flush the work queue and remove it */
-	if (ha->wq) {
-		flush_workqueue(ha->wq);
-		destroy_workqueue(ha->wq);
-		ha->wq = NULL;
-	}
-
 	/* Cancel all work and destroy DPC workqueues */
 	if (ha->dpc_lp_wq) {
 		cancel_work_sync(&ha->idc_aen);
@@ -3312,9 +3482,17 @@ qla2x00_free_device(scsi_qla_host_t *vha)
 		ha->isp_ops->disable_intrs(ha);
 	}
 
+	qla2x00_free_fcports(vha);
+
 	qla2x00_free_irqs(vha);
 
-	qla2x00_free_fcports(vha);
+	/* Flush the work queue and remove it */
+	if (ha->wq) {
+		flush_workqueue(ha->wq);
+		destroy_workqueue(ha->wq);
+		ha->wq = NULL;
+	}
+
 
 	qla2x00_mem_free(ha);
 
@@ -4029,6 +4207,7 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht,
 	INIT_LIST_HEAD(&vha->qla_sess_op_cmd_list);
 	INIT_LIST_HEAD(&vha->logo_list);
 	INIT_LIST_HEAD(&vha->plogi_ack_list);
+	INIT_LIST_HEAD(&vha->qp_list);
 
 	spin_lock_init(&vha->work_lock);
 	spin_lock_init(&vha->cmd_list_lock);
@@ -5033,8 +5212,8 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work)
 
 	base_vha->flags.init_done = 0;
 	qla25xx_delete_queues(base_vha);
-	qla2x00_free_irqs(base_vha);
 	qla2x00_free_fcports(base_vha);
+	qla2x00_free_irqs(base_vha);
 	qla2x00_mem_free(ha);
 	qla82xx_md_free(base_vha);
 	qla2x00_free_queues(ha);
@@ -5068,6 +5247,8 @@ qla2x00_do_dpc(void *data)
 {
 	scsi_qla_host_t *base_vha;
 	struct qla_hw_data *ha;
+	uint32_t online;
+	struct qla_qpair *qpair;
 
 	ha = (struct qla_hw_data *)data;
 	base_vha = pci_get_drvdata(ha->pdev);
@@ -5329,6 +5510,22 @@ intr_on_check:
 				ha->isp_ops->beacon_blink(base_vha);
 		}
 
+		/* qpair online check */
+		if (test_and_clear_bit(QPAIR_ONLINE_CHECK_NEEDED,
+		    &base_vha->dpc_flags)) {
+			if (ha->flags.eeh_busy ||
+			    ha->flags.pci_channel_io_perm_failure)
+				online = 0;
+			else
+				online = 1;
+
+			mutex_lock(&ha->mq_lock);
+			list_for_each_entry(qpair, &base_vha->qp_list,
+			    qp_list_elem)
+			qpair->online = online;
+			mutex_unlock(&ha->mq_lock);
+		}
+
 		if (!IS_QLAFX00(ha))
 			qla2x00_do_dpc_all_vps(base_vha);
 
@@ -5671,6 +5868,10 @@ qla2xxx_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
 	switch (state) {
 	case pci_channel_io_normal:
 		ha->flags.eeh_busy = 0;
+		if (ql2xmqsupport) {
+			set_bit(QPAIR_ONLINE_CHECK_NEEDED, &vha->dpc_flags);
+			qla2xxx_wake_dpc(vha);
+		}
 		return PCI_ERS_RESULT_CAN_RECOVER;
 	case pci_channel_io_frozen:
 		ha->flags.eeh_busy = 1;
@@ -5684,10 +5885,18 @@ qla2xxx_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
 		pci_disable_device(pdev);
 		/* Return back all IOs */
 		qla2x00_abort_all_cmds(vha, DID_RESET << 16);
+		if (ql2xmqsupport) {
+			set_bit(QPAIR_ONLINE_CHECK_NEEDED, &vha->dpc_flags);
+			qla2xxx_wake_dpc(vha);
+		}
 		return PCI_ERS_RESULT_NEED_RESET;
 	case pci_channel_io_perm_failure:
 		ha->flags.pci_channel_io_perm_failure = 1;
 		qla2x00_abort_all_cmds(vha, DID_NO_CONNECT << 16);
+		if (ql2xmqsupport) {
+			set_bit(QPAIR_ONLINE_CHECK_NEEDED, &vha->dpc_flags);
+			qla2xxx_wake_dpc(vha);
+		}
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 	return PCI_ERS_RESULT_NEED_RESET;
@@ -5955,6 +6164,13 @@ qla83xx_disable_laser(scsi_qla_host_t *vha)
 	qla83xx_wr_reg(vha, reg, data);
 }
 
+static int qla2xxx_map_queues(struct Scsi_Host *shost)
+{
+	scsi_qla_host_t *vha = (scsi_qla_host_t *)shost->hostdata;
+
+	return blk_mq_pci_map_queues(&shost->tag_set, vha->hw->pdev);
+}
+
 static const struct pci_error_handlers qla2xxx_err_handler = {
 	.error_detected = qla2xxx_pci_error_detected,
 	.mmio_enabled = qla2xxx_pci_mmio_enabled,
diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c
index 9f6012b78e56..b4336e0cd85f 100644
--- a/drivers/scsi/qla2xxx/qla_sup.c
+++ b/drivers/scsi/qla2xxx/qla_sup.c
@@ -9,7 +9,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * NVRAM support routines
diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h
index a7cfc270bd08..aeebefb1e9f8 100644
--- a/drivers/scsi/qla4xxx/ql4_def.h
+++ b/drivers/scsi/qla4xxx/ql4_def.h
@@ -409,18 +409,9 @@ struct qla4_8xxx_legacy_intr_set {
 
 /* MSI-X Support */
 
-#define QLA_MSIX_DEFAULT	0x00
-#define QLA_MSIX_RSP_Q		0x01
-
+#define QLA_MSIX_DEFAULT	0
+#define QLA_MSIX_RSP_Q		1
 #define QLA_MSIX_ENTRIES	2
-#define QLA_MIDX_DEFAULT	0
-#define QLA_MIDX_RSP_Q		1
-
-struct ql4_msix_entry {
-	int have_irq;
-	uint16_t msix_vector;
-	uint16_t msix_entry;
-};
 
 /*
  * ISP Operations
@@ -572,9 +563,6 @@ struct scsi_qla_host {
 #define AF_IRQ_ATTACHED			10 /* 0x00000400 */
 #define AF_DISABLE_ACB_COMPLETE		11 /* 0x00000800 */
 #define AF_HA_REMOVAL			12 /* 0x00001000 */
-#define AF_INTx_ENABLED			15 /* 0x00008000 */
-#define AF_MSI_ENABLED			16 /* 0x00010000 */
-#define AF_MSIX_ENABLED			17 /* 0x00020000 */
 #define AF_MBOX_COMMAND_NOPOLL		18 /* 0x00040000 */
 #define AF_FW_RECOVERY			19 /* 0x00080000 */
 #define AF_EEH_BUSY			20 /* 0x00100000 */
@@ -762,8 +750,6 @@ struct scsi_qla_host {
 	struct isp_operations *isp_ops;
 	struct ql82xx_hw_data hw;
 
-	struct ql4_msix_entry msix_entries[QLA_MSIX_ENTRIES];
-
 	uint32_t nx_dev_init_timeout;
 	uint32_t nx_reset_timeout;
 	void *fw_dump;
diff --git a/drivers/scsi/qla4xxx/ql4_glbl.h b/drivers/scsi/qla4xxx/ql4_glbl.h
index 2559144f5475..bce96a58f14e 100644
--- a/drivers/scsi/qla4xxx/ql4_glbl.h
+++ b/drivers/scsi/qla4xxx/ql4_glbl.h
@@ -134,7 +134,6 @@ int qla4_8xxx_get_flash_info(struct scsi_qla_host *ha);
 void qla4_82xx_enable_intrs(struct scsi_qla_host *ha);
 void qla4_82xx_disable_intrs(struct scsi_qla_host *ha);
 int qla4_8xxx_enable_msix(struct scsi_qla_host *ha);
-void qla4_8xxx_disable_msix(struct scsi_qla_host *ha);
 irqreturn_t qla4_8xxx_msi_handler(int irq, void *dev_id);
 irqreturn_t qla4_8xxx_default_intr_handler(int irq, void *dev_id);
 irqreturn_t qla4_8xxx_msix_rsp_q(int irq, void *dev_id);
diff --git a/drivers/scsi/qla4xxx/ql4_isr.c b/drivers/scsi/qla4xxx/ql4_isr.c
index 4f9c0f2be89d..d2cd33d8d67f 100644
--- a/drivers/scsi/qla4xxx/ql4_isr.c
+++ b/drivers/scsi/qla4xxx/ql4_isr.c
@@ -1107,7 +1107,7 @@ static void qla4_82xx_spurious_interrupt(struct scsi_qla_host *ha,
 	DEBUG2(ql4_printk(KERN_INFO, ha, "Spurious Interrupt\n"));
 	if (is_qla8022(ha)) {
 		writel(0, &ha->qla4_82xx_reg->host_int);
-		if (test_bit(AF_INTx_ENABLED, &ha->flags))
+		if (!ha->pdev->msi_enabled && !ha->pdev->msix_enabled)
 			qla4_82xx_wr_32(ha, ha->nx_legacy_intr.tgt_mask_reg,
 			    0xfbff);
 	}
@@ -1564,19 +1564,18 @@ int qla4xxx_request_irqs(struct scsi_qla_host *ha)
 
 try_msi:
 	/* Trying MSI */
-	ret = pci_enable_msi(ha->pdev);
-	if (!ret) {
+	ret = pci_alloc_irq_vectors(ha->pdev, 1, 1, PCI_IRQ_MSI);
+	if (ret > 0) {
 		ret = request_irq(ha->pdev->irq, qla4_8xxx_msi_handler,
 			0, DRIVER_NAME, ha);
 		if (!ret) {
 			DEBUG2(ql4_printk(KERN_INFO, ha, "MSI: Enabled.\n"));
-			set_bit(AF_MSI_ENABLED, &ha->flags);
 			goto irq_attached;
 		} else {
 			ql4_printk(KERN_WARNING, ha,
 			    "MSI: Failed to reserve interrupt %d "
 			    "already in use.\n", ha->pdev->irq);
-			pci_disable_msi(ha->pdev);
+			pci_free_irq_vectors(ha->pdev);
 		}
 	}
 
@@ -1592,7 +1591,6 @@ try_intx:
 	    IRQF_SHARED, DRIVER_NAME, ha);
 	if (!ret) {
 		DEBUG2(ql4_printk(KERN_INFO, ha, "INTx: Enabled.\n"));
-		set_bit(AF_INTx_ENABLED, &ha->flags);
 		goto irq_attached;
 
 	} else {
@@ -1614,14 +1612,11 @@ irq_not_attached:
 
 void qla4xxx_free_irqs(struct scsi_qla_host *ha)
 {
-	if (test_and_clear_bit(AF_IRQ_ATTACHED, &ha->flags)) {
-		if (test_bit(AF_MSIX_ENABLED, &ha->flags)) {
-			qla4_8xxx_disable_msix(ha);
-		} else if (test_and_clear_bit(AF_MSI_ENABLED, &ha->flags)) {
-			free_irq(ha->pdev->irq, ha);
-			pci_disable_msi(ha->pdev);
-		} else if (test_and_clear_bit(AF_INTx_ENABLED, &ha->flags)) {
-			free_irq(ha->pdev->irq, ha);
-		}
-	}
+	if (!test_and_clear_bit(AF_IRQ_ATTACHED, &ha->flags))
+		return;
+
+	if (ha->pdev->msix_enabled)
+		free_irq(pci_irq_vector(ha->pdev, 1), ha);
+	free_irq(pci_irq_vector(ha->pdev, 0), ha);
+	pci_free_irq_vectors(ha->pdev);
 }
diff --git a/drivers/scsi/qla4xxx/ql4_mbx.c b/drivers/scsi/qla4xxx/ql4_mbx.c
index c291fdff1b33..1da04f323d38 100644
--- a/drivers/scsi/qla4xxx/ql4_mbx.c
+++ b/drivers/scsi/qla4xxx/ql4_mbx.c
@@ -2032,10 +2032,7 @@ int qla4xxx_set_param_ddbentry(struct scsi_qla_host *ha,
 	ptid = (uint16_t *)&fw_ddb_entry->isid[1];
 	*ptid = cpu_to_le16((uint16_t)ddb_entry->sess->target_id);
 
-	DEBUG2(ql4_printk(KERN_INFO, ha, "ISID [%02x%02x%02x%02x%02x%02x]\n",
-			  fw_ddb_entry->isid[5], fw_ddb_entry->isid[4],
-			  fw_ddb_entry->isid[3], fw_ddb_entry->isid[2],
-			  fw_ddb_entry->isid[1], fw_ddb_entry->isid[0]));
+	DEBUG2(ql4_printk(KERN_INFO, ha, "ISID [%pmR]\n", fw_ddb_entry->isid));
 
 	iscsi_opts = le16_to_cpu(fw_ddb_entry->iscsi_options);
 	memset(fw_ddb_entry->iscsi_alias, 0, sizeof(fw_ddb_entry->iscsi_alias));
diff --git a/drivers/scsi/qla4xxx/ql4_nx.c b/drivers/scsi/qla4xxx/ql4_nx.c
index 06ddd13cb7cc..e91abb327745 100644
--- a/drivers/scsi/qla4xxx/ql4_nx.c
+++ b/drivers/scsi/qla4xxx/ql4_nx.c
@@ -3945,7 +3945,7 @@ void qla4_82xx_process_mbox_intr(struct scsi_qla_host *ha, int out_count)
 		ha->isp_ops->interrupt_service_routine(ha, intr_status);
 
 		if (test_bit(AF_INTERRUPTS_ON, &ha->flags) &&
-		    test_bit(AF_INTx_ENABLED, &ha->flags))
+		    (!ha->pdev->msi_enabled && !ha->pdev->msix_enabled))
 			qla4_82xx_wr_32(ha, ha->nx_legacy_intr.tgt_mask_reg,
 					0xfbff);
 	}
@@ -4094,12 +4094,8 @@ int qla4_8xxx_get_sys_info(struct scsi_qla_host *ha)
 	ha->phy_port_num = sys_info->port_num;
 	ha->iscsi_pci_func_cnt = sys_info->iscsi_pci_func_cnt;
 
-	DEBUG2(printk("scsi%ld: %s: "
-	    "mac %02x:%02x:%02x:%02x:%02x:%02x "
-	    "serial %s\n", ha->host_no, __func__,
-	    ha->my_mac[0], ha->my_mac[1], ha->my_mac[2],
-	    ha->my_mac[3], ha->my_mac[4], ha->my_mac[5],
-	    ha->serial_number));
+	DEBUG2(printk("scsi%ld: %s: mac %pM serial %s\n",
+	    ha->host_no, __func__, ha->my_mac, ha->serial_number));
 
 	status = QLA_SUCCESS;
 
@@ -4178,78 +4174,37 @@ qla4_82xx_disable_intrs(struct scsi_qla_host *ha)
 	spin_unlock_irq(&ha->hardware_lock);
 }
 
-struct ql4_init_msix_entry {
-	uint16_t entry;
-	uint16_t index;
-	const char *name;
-	irq_handler_t handler;
-};
-
-static struct ql4_init_msix_entry qla4_8xxx_msix_entries[QLA_MSIX_ENTRIES] = {
-	{ QLA_MSIX_DEFAULT, QLA_MIDX_DEFAULT,
-	    "qla4xxx (default)",
-	    (irq_handler_t)qla4_8xxx_default_intr_handler },
-	{ QLA_MSIX_RSP_Q, QLA_MIDX_RSP_Q,
-	    "qla4xxx (rsp_q)", (irq_handler_t)qla4_8xxx_msix_rsp_q },
-};
-
-void
-qla4_8xxx_disable_msix(struct scsi_qla_host *ha)
-{
-	int i;
-	struct ql4_msix_entry *qentry;
-
-	for (i = 0; i < QLA_MSIX_ENTRIES; i++) {
-		qentry = &ha->msix_entries[qla4_8xxx_msix_entries[i].index];
-		if (qentry->have_irq) {
-			free_irq(qentry->msix_vector, ha);
-			DEBUG2(ql4_printk(KERN_INFO, ha, "%s: %s\n",
-				__func__, qla4_8xxx_msix_entries[i].name));
-		}
-	}
-	pci_disable_msix(ha->pdev);
-	clear_bit(AF_MSIX_ENABLED, &ha->flags);
-}
-
 int
 qla4_8xxx_enable_msix(struct scsi_qla_host *ha)
 {
-	int i, ret;
-	struct msix_entry entries[QLA_MSIX_ENTRIES];
-	struct ql4_msix_entry *qentry;
-
-	for (i = 0; i < QLA_MSIX_ENTRIES; i++)
-		entries[i].entry = qla4_8xxx_msix_entries[i].entry;
+	int ret;
 
-	ret = pci_enable_msix_exact(ha->pdev, entries, ARRAY_SIZE(entries));
-	if (ret) {
+	ret = pci_alloc_irq_vectors(ha->pdev, QLA_MSIX_ENTRIES,
+			QLA_MSIX_ENTRIES, PCI_IRQ_MSIX);
+	if (ret < 0) {
 		ql4_printk(KERN_WARNING, ha,
 		    "MSI-X: Failed to enable support -- %d/%d\n",
 		    QLA_MSIX_ENTRIES, ret);
-		goto msix_out;
-	}
-	set_bit(AF_MSIX_ENABLED, &ha->flags);
-
-	for (i = 0; i < QLA_MSIX_ENTRIES; i++) {
-		qentry = &ha->msix_entries[qla4_8xxx_msix_entries[i].index];
-		qentry->msix_vector = entries[i].vector;
-		qentry->msix_entry = entries[i].entry;
-		qentry->have_irq = 0;
-		ret = request_irq(qentry->msix_vector,
-		    qla4_8xxx_msix_entries[i].handler, 0,
-		    qla4_8xxx_msix_entries[i].name, ha);
-		if (ret) {
-			ql4_printk(KERN_WARNING, ha,
-			    "MSI-X: Unable to register handler -- %x/%d.\n",
-			    qla4_8xxx_msix_entries[i].index, ret);
-			qla4_8xxx_disable_msix(ha);
-			goto msix_out;
-		}
-		qentry->have_irq = 1;
-		DEBUG2(ql4_printk(KERN_INFO, ha, "%s: %s\n",
-			__func__, qla4_8xxx_msix_entries[i].name));
+		return ret;
 	}
-msix_out:
+
+	ret = request_irq(pci_irq_vector(ha->pdev, 0),
+			qla4_8xxx_default_intr_handler, 0, "qla4xxx (default)",
+			ha);
+	if (ret)
+		goto out_free_vectors;
+
+	ret = request_irq(pci_irq_vector(ha->pdev, 1),
+			qla4_8xxx_msix_rsp_q, 0, "qla4xxx (rsp_q)", ha);
+	if (ret)
+		goto out_free_default_irq;
+
+	return 0;
+
+out_free_default_irq:
+	free_irq(pci_irq_vector(ha->pdev, 0), ha);
+out_free_vectors:
+	pci_free_irq_vectors(ha->pdev);
 	return ret;
 }
 
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 01c3610a60cf..9fbb33fc90c7 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -6304,13 +6304,9 @@ static int qla4xxx_compare_tuple_ddb(struct scsi_qla_host *ha,
 	 * ISID would not match firmware generated ISID.
 	 */
 	if (is_isid_compare) {
-		DEBUG2(ql4_printk(KERN_INFO, ha, "%s: old ISID [%02x%02x%02x"
-			"%02x%02x%02x] New ISID [%02x%02x%02x%02x%02x%02x]\n",
-			__func__, old_tddb->isid[5], old_tddb->isid[4],
-			old_tddb->isid[3], old_tddb->isid[2], old_tddb->isid[1],
-			old_tddb->isid[0], new_tddb->isid[5], new_tddb->isid[4],
-			new_tddb->isid[3], new_tddb->isid[2], new_tddb->isid[1],
-			new_tddb->isid[0]));
+		DEBUG2(ql4_printk(KERN_INFO, ha,
+			"%s: old ISID [%pmR] New ISID [%pmR]\n",
+			__func__, old_tddb->isid, new_tddb->isid));
 
 		if (memcmp(&old_tddb->isid[0], &new_tddb->isid[0],
 			   sizeof(old_tddb->isid)))
@@ -7925,10 +7921,7 @@ qla4xxx_sysfs_ddb_get_param(struct iscsi_bus_flash_session *fnode_sess,
 		rc = sprintf(buf, "%u\n", fnode_conn->keepalive_timeout);
 		break;
 	case ISCSI_FLASHNODE_ISID:
-		rc = sprintf(buf, "%02x%02x%02x%02x%02x%02x\n",
-			     fnode_sess->isid[0], fnode_sess->isid[1],
-			     fnode_sess->isid[2], fnode_sess->isid[3],
-			     fnode_sess->isid[4], fnode_sess->isid[5]);
+		rc = sprintf(buf, "%pm\n", fnode_sess->isid);
 		break;
 	case ISCSI_FLASHNODE_TSID:
 		rc = sprintf(buf, "%u\n", fnode_sess->tsid);
diff --git a/drivers/scsi/qlogicpti.h b/drivers/scsi/qlogicpti.h
index 4377e87ee79c..892a0b058b99 100644
--- a/drivers/scsi/qlogicpti.h
+++ b/drivers/scsi/qlogicpti.h
@@ -356,8 +356,8 @@ struct qlogicpti {
 
 	/* The rest of the elements are unimportant for performance. */
 	struct qlogicpti         *next;
-	__u32                     res_dvma;             /* Ptr to RESPONSE bufs (DVMA)*/
-	__u32                     req_dvma;             /* Ptr to REQUEST bufs (DVMA) */
+	dma_addr_t                res_dvma;             /* Ptr to RESPONSE bufs (DVMA)*/
+	dma_addr_t                req_dvma;             /* Ptr to REQUEST bufs (DVMA) */
 	u_char	                  fware_majrev, fware_minrev, fware_micrev;
 	struct Scsi_Host         *qhost;
 	int                       qpti_id;
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 1deb6adc411f..75455d4dab68 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -621,6 +621,9 @@ int scsi_change_queue_depth(struct scsi_device *sdev, int depth)
 		wmb();
 	}
 
+	if (sdev->request_queue)
+		blk_set_queue_depth(sdev->request_queue, depth);
+
 	return sdev->queue_depth;
 }
 EXPORT_SYMBOL(scsi_change_queue_depth);
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index cf04a364fd8b..03051e12a072 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -4085,7 +4085,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 			jiffies_to_timespec(delta_jiff, &ts);
 			kt = ktime_set(ts.tv_sec, ts.tv_nsec);
 		} else
-			kt = ktime_set(0, sdebug_ndelay);
+			kt = sdebug_ndelay;
 		if (NULL == sd_dp) {
 			sd_dp = kzalloc(sizeof(*sd_dp), GFP_ATOMIC);
 			if (NULL == sd_dp)
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index 246456925335..28fea83ae2fe 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -220,8 +220,6 @@ static struct {
 	{"NAKAMICH", "MJ-5.16S", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"NEC", "PD-1 ODX654P", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"NEC", "iStorage", NULL, BLIST_REPORTLUN2},
-	{"NETAPP", "LUN C-Mode", NULL, BLIST_SYNC_ALUA},
-	{"NETAPP", "INF-01-00", NULL, BLIST_SYNC_ALUA},
 	{"NRC", "MBR-7", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"NRC", "MBR-7.4", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"PIONEER", "CD-ROM DRM-600", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 106a6adbd6f1..996e134d79fa 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1988,7 +1988,7 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
 
 	req->cmd_len = COMMAND_SIZE(req->cmd[0]);
 
-	req->cmd_flags |= REQ_QUIET;
+	req->rq_flags |= RQF_QUIET;
 	req->timeout = 10 * HZ;
 	req->retries = 5;
 
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index c4f7b56fa6f6..8b8c814df5c7 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -12,7 +12,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/string.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 2cca9cffc63f..c35b6de4ca64 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -86,10 +86,8 @@ scsi_set_blocked(struct scsi_cmnd *cmd, int reason)
 static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd)
 {
 	struct scsi_device *sdev = cmd->device;
-	struct request_queue *q = cmd->request->q;
 
-	blk_mq_requeue_request(cmd->request);
-	blk_mq_kick_requeue_list(q);
+	blk_mq_requeue_request(cmd->request, true);
 	put_device(&sdev->sdev_gendev);
 }
 
@@ -163,26 +161,11 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
 {
 	__scsi_queue_insert(cmd, reason, 1);
 }
-/**
- * scsi_execute - insert request and wait for the result
- * @sdev:	scsi device
- * @cmd:	scsi command
- * @data_direction: data direction
- * @buffer:	data buffer
- * @bufflen:	len of buffer
- * @sense:	optional sense buffer
- * @timeout:	request timeout in seconds
- * @retries:	number of times to retry request
- * @flags:	or into request flags;
- * @resid:	optional residual length
- *
- * returns the req->errors value which is the scsi_cmnd result
- * field.
- */
-int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
+
+static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		 int data_direction, void *buffer, unsigned bufflen,
 		 unsigned char *sense, int timeout, int retries, u64 flags,
-		 int *resid)
+		 req_flags_t rq_flags, int *resid)
 {
 	struct request *req;
 	int write = (data_direction == DMA_TO_DEVICE);
@@ -203,7 +186,8 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	req->sense_len = 0;
 	req->retries = retries;
 	req->timeout = timeout;
-	req->cmd_flags |= flags | REQ_QUIET | REQ_PREEMPT;
+	req->cmd_flags |= flags;
+	req->rq_flags |= rq_flags | RQF_QUIET | RQF_PREEMPT;
 
 	/*
 	 * head injection *required* here otherwise quiesce won't work
@@ -227,12 +211,37 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 
 	return ret;
 }
+
+/**
+ * scsi_execute - insert request and wait for the result
+ * @sdev:	scsi device
+ * @cmd:	scsi command
+ * @data_direction: data direction
+ * @buffer:	data buffer
+ * @bufflen:	len of buffer
+ * @sense:	optional sense buffer
+ * @timeout:	request timeout in seconds
+ * @retries:	number of times to retry request
+ * @flags:	or into request flags;
+ * @resid:	optional residual length
+ *
+ * returns the req->errors value which is the scsi_cmnd result
+ * field.
+ */
+int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
+		 int data_direction, void *buffer, unsigned bufflen,
+		 unsigned char *sense, int timeout, int retries, u64 flags,
+		 int *resid)
+{
+	return __scsi_execute(sdev, cmd, data_direction, buffer, bufflen, sense,
+			timeout, retries, flags, 0, resid);
+}
 EXPORT_SYMBOL(scsi_execute);
 
 int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd,
 		     int data_direction, void *buffer, unsigned bufflen,
 		     struct scsi_sense_hdr *sshdr, int timeout, int retries,
-		     int *resid, u64 flags)
+		     int *resid, u64 flags, req_flags_t rq_flags)
 {
 	char *sense = NULL;
 	int result;
@@ -242,8 +251,8 @@ int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd,
 		if (!sense)
 			return DRIVER_ERROR << 24;
 	}
-	result = scsi_execute(sdev, cmd, data_direction, buffer, bufflen,
-			      sense, timeout, retries, flags, resid);
+	result = __scsi_execute(sdev, cmd, data_direction, buffer, bufflen,
+			      sense, timeout, retries, flags, rq_flags, resid);
 	if (sshdr)
 		scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, sshdr);
 
@@ -813,7 +822,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		 */
 		if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d))
 			;
-		else if (!(req->cmd_flags & REQ_QUIET))
+		else if (!(req->rq_flags & RQF_QUIET))
 			scsi_print_sense(cmd);
 		result = 0;
 		/* BLOCK_PC may have set error */
@@ -943,7 +952,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	switch (action) {
 	case ACTION_FAIL:
 		/* Give up and fail the remainder of the request */
-		if (!(req->cmd_flags & REQ_QUIET)) {
+		if (!(req->rq_flags & RQF_QUIET)) {
 			static DEFINE_RATELIMIT_STATE(_rs,
 					DEFAULT_RATELIMIT_INTERVAL,
 					DEFAULT_RATELIMIT_BURST);
@@ -972,7 +981,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		 * A new command will be prepared and issued.
 		 */
 		if (q->mq_ops) {
-			cmd->request->cmd_flags &= ~REQ_DONTPREP;
+			cmd->request->rq_flags &= ~RQF_DONTPREP;
 			scsi_mq_uninit_cmd(cmd);
 			scsi_mq_requeue_cmd(cmd);
 		} else {
@@ -998,8 +1007,8 @@ static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb)
 	/*
 	 * If sg table allocation fails, requeue request later.
 	 */
-	if (unlikely(sg_alloc_table_chained(&sdb->table, req->nr_phys_segments,
-					sdb->table.sgl)))
+	if (unlikely(sg_alloc_table_chained(&sdb->table,
+			blk_rq_nr_phys_segments(req), sdb->table.sgl)))
 		return BLKPREP_DEFER;
 
 	/* 
@@ -1031,7 +1040,7 @@ int scsi_init_io(struct scsi_cmnd *cmd)
 	bool is_mq = (rq->mq_ctx != NULL);
 	int error;
 
-	BUG_ON(!rq->nr_phys_segments);
+	BUG_ON(!blk_rq_nr_phys_segments(rq));
 
 	error = scsi_init_sgtable(rq, &cmd->sdb);
 	if (error)
@@ -1234,7 +1243,7 @@ scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
 			/*
 			 * If the devices is blocked we defer normal commands.
 			 */
-			if (!(req->cmd_flags & REQ_PREEMPT))
+			if (!(req->rq_flags & RQF_PREEMPT))
 				ret = BLKPREP_DEFER;
 			break;
 		default:
@@ -1243,7 +1252,7 @@ scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
 			 * special commands.  In particular any user initiated
 			 * command is not allowed.
 			 */
-			if (!(req->cmd_flags & REQ_PREEMPT))
+			if (!(req->rq_flags & RQF_PREEMPT))
 				ret = BLKPREP_KILL;
 			break;
 		}
@@ -1279,7 +1288,7 @@ scsi_prep_return(struct request_queue *q, struct request *req, int ret)
 			blk_delay_queue(q, SCSI_QUEUE_DELAY);
 		break;
 	default:
-		req->cmd_flags |= REQ_DONTPREP;
+		req->rq_flags |= RQF_DONTPREP;
 	}
 
 	return ret;
@@ -1736,7 +1745,7 @@ static void scsi_request_fn(struct request_queue *q)
 		 * we add the dev to the starved list so it eventually gets
 		 * a run when a tag is freed.
 		 */
-		if (blk_queue_tagged(q) && !(req->cmd_flags & REQ_QUEUED)) {
+		if (blk_queue_tagged(q) && !(req->rq_flags & RQF_QUEUED)) {
 			spin_lock_irq(shost->host_lock);
 			if (list_empty(&sdev->starved_entry))
 				list_add_tail(&sdev->starved_entry,
@@ -1801,7 +1810,7 @@ static inline int prep_to_mq(int ret)
 {
 	switch (ret) {
 	case BLKPREP_OK:
-		return 0;
+		return BLK_MQ_RQ_QUEUE_OK;
 	case BLKPREP_DEFER:
 		return BLK_MQ_RQ_QUEUE_BUSY;
 	default:
@@ -1888,7 +1897,7 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 	int reason;
 
 	ret = prep_to_mq(scsi_prep_state_check(sdev, req));
-	if (ret)
+	if (ret != BLK_MQ_RQ_QUEUE_OK)
 		goto out;
 
 	ret = BLK_MQ_RQ_QUEUE_BUSY;
@@ -1903,11 +1912,11 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 		goto out_dec_target_busy;
 
 
-	if (!(req->cmd_flags & REQ_DONTPREP)) {
+	if (!(req->rq_flags & RQF_DONTPREP)) {
 		ret = prep_to_mq(scsi_mq_prep_fn(req));
-		if (ret)
+		if (ret != BLK_MQ_RQ_QUEUE_OK)
 			goto out_dec_host_busy;
-		req->cmd_flags |= REQ_DONTPREP;
+		req->rq_flags |= RQF_DONTPREP;
 	} else {
 		blk_mq_start_request(req);
 	}
@@ -1941,7 +1950,6 @@ out_put_device:
 out:
 	switch (ret) {
 	case BLK_MQ_RQ_QUEUE_BUSY:
-		blk_mq_stop_hw_queue(hctx);
 		if (atomic_read(&sdev->device_busy) == 0 &&
 		    !scsi_device_blocked(sdev))
 			blk_mq_delay_queue(hctx, SCSI_QUEUE_DELAY);
@@ -1952,7 +1960,7 @@ out:
 		 * we hit an error, as we will never see this command
 		 * again.
 		 */
-		if (req->cmd_flags & REQ_DONTPREP)
+		if (req->rq_flags & RQF_DONTPREP)
 			scsi_mq_uninit_cmd(cmd);
 		break;
 	default:
@@ -1990,6 +1998,15 @@ static void scsi_exit_request(void *data, struct request *rq,
 	kfree(cmd->sense_buffer);
 }
 
+static int scsi_map_queues(struct blk_mq_tag_set *set)
+{
+	struct Scsi_Host *shost = container_of(set, struct Scsi_Host, tag_set);
+
+	if (shost->hostt->map_queues)
+		return shost->hostt->map_queues(shost);
+	return blk_mq_map_queues(set);
+}
+
 static u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost)
 {
 	struct device *host_dev;
@@ -2082,6 +2099,7 @@ static struct blk_mq_ops scsi_mq_ops = {
 	.timeout	= scsi_timeout,
 	.init_request	= scsi_init_request,
 	.exit_request	= scsi_exit_request,
+	.map_queues	= scsi_map_queues,
 };
 
 struct request_queue *scsi_mq_alloc_queue(struct scsi_device *sdev)
@@ -2724,6 +2742,39 @@ void sdev_evt_send_simple(struct scsi_device *sdev,
 EXPORT_SYMBOL_GPL(sdev_evt_send_simple);
 
 /**
+ * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn()
+ * @sdev: SCSI device to count the number of scsi_request_fn() callers for.
+ */
+static int scsi_request_fn_active(struct scsi_device *sdev)
+{
+	struct request_queue *q = sdev->request_queue;
+	int request_fn_active;
+
+	WARN_ON_ONCE(sdev->host->use_blk_mq);
+
+	spin_lock_irq(q->queue_lock);
+	request_fn_active = q->request_fn_active;
+	spin_unlock_irq(q->queue_lock);
+
+	return request_fn_active;
+}
+
+/**
+ * scsi_wait_for_queuecommand() - wait for ongoing queuecommand() calls
+ * @sdev: SCSI device pointer.
+ *
+ * Wait until the ongoing shost->hostt->queuecommand() calls that are
+ * invoked from scsi_request_fn() have finished.
+ */
+static void scsi_wait_for_queuecommand(struct scsi_device *sdev)
+{
+	WARN_ON_ONCE(sdev->host->use_blk_mq);
+
+	while (scsi_request_fn_active(sdev))
+		msleep(20);
+}
+
+/**
  *	scsi_device_quiesce - Block user issued commands.
  *	@sdev:	scsi device to quiesce.
  *
@@ -2807,8 +2858,7 @@ EXPORT_SYMBOL(scsi_target_resume);
  * @sdev:	device to block
  *
  * Block request made by scsi lld's to temporarily stop all
- * scsi commands on the specified device.  Called from interrupt
- * or normal process context.
+ * scsi commands on the specified device. May sleep.
  *
  * Returns zero if successful or error if not
  *
@@ -2817,6 +2867,10 @@ EXPORT_SYMBOL(scsi_target_resume);
  *	(which must be a legal transition).  When the device is in this
  *	state, all commands are deferred until the scsi lld reenables
  *	the device with scsi_device_unblock or device_block_tmo fires.
+ *
+ * To do: avoid that scsi_send_eh_cmnd() calls queuecommand() after
+ * scsi_internal_device_block() has blocked a SCSI device and also
+ * remove the rport mutex lock and unlock calls from srp_queuecommand().
  */
 int
 scsi_internal_device_block(struct scsi_device *sdev)
@@ -2844,6 +2898,7 @@ scsi_internal_device_block(struct scsi_device *sdev)
 		spin_lock_irqsave(q->queue_lock, flags);
 		blk_stop_queue(q);
 		spin_unlock_irqrestore(q->queue_lock, flags);
+		scsi_wait_for_queuecommand(sdev);
 	}
 
 	return 0;
diff --git a/drivers/scsi/scsi_proc.c b/drivers/scsi/scsi_proc.c
index 7a74b82e8973..480a597b3877 100644
--- a/drivers/scsi/scsi_proc.c
+++ b/drivers/scsi/scsi_proc.c
@@ -26,7 +26,7 @@
 #include <linux/seq_file.h>
 #include <linux/mutex.h>
 #include <linux/gfp.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_device.h>
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 07349270535d..82dfe07b1d47 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -1204,10 +1204,6 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev)
 	struct request_queue *rq = sdev->request_queue;
 	struct scsi_target *starget = sdev->sdev_target;
 
-	error = scsi_device_set_state(sdev, SDEV_RUNNING);
-	if (error)
-		return error;
-
 	error = scsi_target_add(starget);
 	if (error)
 		return error;
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index 0f3a3869524b..03577bde6ac5 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -30,6 +30,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/kernel.h>
+#include <linux/bsg-lib.h>
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport.h>
@@ -2592,7 +2593,7 @@ fc_rport_final_delete(struct work_struct *work)
 
 
 /**
- * fc_rport_create - allocates and creates a remote FC port.
+ * fc_remote_port_create - allocates and creates a remote FC port.
  * @shost:	scsi host the remote port is connected to.
  * @channel:	Channel on shost port connected to.
  * @ids:	The world wide names, fc address, and FC4 port
@@ -2605,8 +2606,8 @@ fc_rport_final_delete(struct work_struct *work)
  *	This routine assumes no locks are held on entry.
  */
 static struct fc_rport *
-fc_rport_create(struct Scsi_Host *shost, int channel,
-	struct fc_rport_identifiers  *ids)
+fc_remote_port_create(struct Scsi_Host *shost, int channel,
+		      struct fc_rport_identifiers  *ids)
 {
 	struct fc_host_attrs *fc_host = shost_to_fc_host(shost);
 	struct fc_internal *fci = to_fc_internal(shost->transportt);
@@ -2914,7 +2915,7 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel,
 	spin_unlock_irqrestore(shost->host_lock, flags);
 
 	/* No consistent binding found - create new remote port entry */
-	rport = fc_rport_create(shost, channel, ids);
+	rport = fc_remote_port_create(shost, channel, ids);
 
 	return rport;
 }
@@ -3554,81 +3555,6 @@ fc_vport_sched_delete(struct work_struct *work)
  * BSG support
  */
 
-
-/**
- * fc_destroy_bsgjob - routine to teardown/delete a fc bsg job
- * @job:	fc_bsg_job that is to be torn down
- */
-static void
-fc_destroy_bsgjob(struct fc_bsg_job *job)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&job->job_lock, flags);
-	if (job->ref_cnt) {
-		spin_unlock_irqrestore(&job->job_lock, flags);
-		return;
-	}
-	spin_unlock_irqrestore(&job->job_lock, flags);
-
-	put_device(job->dev);	/* release reference for the request */
-
-	kfree(job->request_payload.sg_list);
-	kfree(job->reply_payload.sg_list);
-	kfree(job);
-}
-
-/**
- * fc_bsg_jobdone - completion routine for bsg requests that the LLD has
- *                  completed
- * @job:	fc_bsg_job that is complete
- */
-static void
-fc_bsg_jobdone(struct fc_bsg_job *job)
-{
-	struct request *req = job->req;
-	struct request *rsp = req->next_rq;
-	int err;
-
-	err = job->req->errors = job->reply->result;
-
-	if (err < 0)
-		/* we're only returning the result field in the reply */
-		job->req->sense_len = sizeof(uint32_t);
-	else
-		job->req->sense_len = job->reply_len;
-
-	/* we assume all request payload was transferred, residual == 0 */
-	req->resid_len = 0;
-
-	if (rsp) {
-		WARN_ON(job->reply->reply_payload_rcv_len > rsp->resid_len);
-
-		/* set reply (bidi) residual */
-		rsp->resid_len -= min(job->reply->reply_payload_rcv_len,
-				      rsp->resid_len);
-	}
-	blk_complete_request(req);
-}
-
-/**
- * fc_bsg_softirq_done - softirq done routine for destroying the bsg requests
- * @rq:        BSG request that holds the job to be destroyed
- */
-static void fc_bsg_softirq_done(struct request *rq)
-{
-	struct fc_bsg_job *job = rq->special;
-	unsigned long flags;
-
-	spin_lock_irqsave(&job->job_lock, flags);
-	job->state_flags |= FC_RQST_STATE_DONE;
-	job->ref_cnt--;
-	spin_unlock_irqrestore(&job->job_lock, flags);
-
-	blk_end_request_all(rq, rq->errors);
-	fc_destroy_bsgjob(job);
-}
-
 /**
  * fc_bsg_job_timeout - handler for when a bsg request timesout
  * @req:	request that timed out
@@ -3636,27 +3562,22 @@ static void fc_bsg_softirq_done(struct request *rq)
 static enum blk_eh_timer_return
 fc_bsg_job_timeout(struct request *req)
 {
-	struct fc_bsg_job *job = (void *) req->special;
-	struct Scsi_Host *shost = job->shost;
+	struct bsg_job *job = (void *) req->special;
+	struct Scsi_Host *shost = fc_bsg_to_shost(job);
+	struct fc_rport *rport = fc_bsg_to_rport(job);
 	struct fc_internal *i = to_fc_internal(shost->transportt);
-	unsigned long flags;
-	int err = 0, done = 0;
+	int err = 0, inflight = 0;
 
-	if (job->rport && job->rport->port_state == FC_PORTSTATE_BLOCKED)
+	if (rport && rport->port_state == FC_PORTSTATE_BLOCKED)
 		return BLK_EH_RESET_TIMER;
 
-	spin_lock_irqsave(&job->job_lock, flags);
-	if (job->state_flags & FC_RQST_STATE_DONE)
-		done = 1;
-	else
-		job->ref_cnt++;
-	spin_unlock_irqrestore(&job->job_lock, flags);
+	inflight = bsg_job_get(job);
 
-	if (!done && i->f->bsg_timeout) {
+	if (inflight && i->f->bsg_timeout) {
 		/* call LLDD to abort the i/o as it has timed out */
 		err = i->f->bsg_timeout(job);
 		if (err == -EAGAIN) {
-			job->ref_cnt--;
+			bsg_job_put(job);
 			return BLK_EH_RESET_TIMER;
 		} else if (err)
 			printk(KERN_ERR "ERROR: FC BSG request timeout - LLD "
@@ -3664,126 +3585,33 @@ fc_bsg_job_timeout(struct request *req)
 	}
 
 	/* the blk_end_sync_io() doesn't check the error */
-	if (done)
+	if (!inflight)
 		return BLK_EH_NOT_HANDLED;
 	else
 		return BLK_EH_HANDLED;
 }
 
-static int
-fc_bsg_map_buffer(struct fc_bsg_buffer *buf, struct request *req)
-{
-	size_t sz = (sizeof(struct scatterlist) * req->nr_phys_segments);
-
-	BUG_ON(!req->nr_phys_segments);
-
-	buf->sg_list = kzalloc(sz, GFP_KERNEL);
-	if (!buf->sg_list)
-		return -ENOMEM;
-	sg_init_table(buf->sg_list, req->nr_phys_segments);
-	buf->sg_cnt = blk_rq_map_sg(req->q, req, buf->sg_list);
-	buf->payload_len = blk_rq_bytes(req);
-	return 0;
-}
-
-
-/**
- * fc_req_to_bsgjob - Allocate/create the fc_bsg_job structure for the
- *                   bsg request
- * @shost:	SCSI Host corresponding to the bsg object
- * @rport:	(optional) FC Remote Port corresponding to the bsg object
- * @req:	BSG request that needs a job structure
- */
-static int
-fc_req_to_bsgjob(struct Scsi_Host *shost, struct fc_rport *rport,
-	struct request *req)
-{
-	struct fc_internal *i = to_fc_internal(shost->transportt);
-	struct request *rsp = req->next_rq;
-	struct fc_bsg_job *job;
-	int ret;
-
-	BUG_ON(req->special);
-
-	job = kzalloc(sizeof(struct fc_bsg_job) + i->f->dd_bsg_size,
-			GFP_KERNEL);
-	if (!job)
-		return -ENOMEM;
-
-	/*
-	 * Note: this is a bit silly.
-	 * The request gets formatted as a SGIO v4 ioctl request, which
-	 * then gets reformatted as a blk request, which then gets
-	 * reformatted as a fc bsg request. And on completion, we have
-	 * to wrap return results such that SGIO v4 thinks it was a scsi
-	 * status.  I hope this was all worth it.
-	 */
-
-	req->special = job;
-	job->shost = shost;
-	job->rport = rport;
-	job->req = req;
-	if (i->f->dd_bsg_size)
-		job->dd_data = (void *)&job[1];
-	spin_lock_init(&job->job_lock);
-	job->request = (struct fc_bsg_request *)req->cmd;
-	job->request_len = req->cmd_len;
-	job->reply = req->sense;
-	job->reply_len = SCSI_SENSE_BUFFERSIZE;	/* Size of sense buffer
-						 * allocated */
-	if (req->bio) {
-		ret = fc_bsg_map_buffer(&job->request_payload, req);
-		if (ret)
-			goto failjob_rls_job;
-	}
-	if (rsp && rsp->bio) {
-		ret = fc_bsg_map_buffer(&job->reply_payload, rsp);
-		if (ret)
-			goto failjob_rls_rqst_payload;
-	}
-	job->job_done = fc_bsg_jobdone;
-	if (rport)
-		job->dev = &rport->dev;
-	else
-		job->dev = &shost->shost_gendev;
-	get_device(job->dev);		/* take a reference for the request */
-
-	job->ref_cnt = 1;
-
-	return 0;
-
-
-failjob_rls_rqst_payload:
-	kfree(job->request_payload.sg_list);
-failjob_rls_job:
-	kfree(job);
-	return -ENOMEM;
-}
-
-
-enum fc_dispatch_result {
-	FC_DISPATCH_BREAK,	/* on return, q is locked, break from q loop */
-	FC_DISPATCH_LOCKED,	/* on return, q is locked, continue on */
-	FC_DISPATCH_UNLOCKED,	/* on return, q is unlocked, continue on */
-};
-
-
 /**
  * fc_bsg_host_dispatch - process fc host bsg requests and dispatch to LLDD
- * @q:		fc host request queue
  * @shost:	scsi host rport attached to
  * @job:	bsg job to be processed
  */
-static enum fc_dispatch_result
-fc_bsg_host_dispatch(struct request_queue *q, struct Scsi_Host *shost,
-			 struct fc_bsg_job *job)
+static int fc_bsg_host_dispatch(struct Scsi_Host *shost, struct bsg_job *job)
 {
 	struct fc_internal *i = to_fc_internal(shost->transportt);
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	int cmdlen = sizeof(uint32_t);	/* start with length of msgcode */
 	int ret;
 
+	/* check if we really have all the request data needed */
+	if (job->request_len < cmdlen) {
+		ret = -ENOMSG;
+		goto fail_host_msg;
+	}
+
 	/* Validate the host command */
-	switch (job->request->msgcode) {
+	switch (bsg_request->msgcode) {
 	case FC_BSG_HST_ADD_RPORT:
 		cmdlen += sizeof(struct fc_bsg_host_add_rport);
 		break;
@@ -3815,7 +3643,7 @@ fc_bsg_host_dispatch(struct request_queue *q, struct Scsi_Host *shost,
 	case FC_BSG_HST_VENDOR:
 		cmdlen += sizeof(struct fc_bsg_host_vendor);
 		if ((shost->hostt->vendor_id == 0L) ||
-		    (job->request->rqst_data.h_vendor.vendor_id !=
+		    (bsg_request->rqst_data.h_vendor.vendor_id !=
 			shost->hostt->vendor_id)) {
 			ret = -ESRCH;
 			goto fail_host_msg;
@@ -3827,24 +3655,19 @@ fc_bsg_host_dispatch(struct request_queue *q, struct Scsi_Host *shost,
 		goto fail_host_msg;
 	}
 
-	/* check if we really have all the request data needed */
-	if (job->request_len < cmdlen) {
-		ret = -ENOMSG;
-		goto fail_host_msg;
-	}
-
 	ret = i->f->bsg_request(job);
 	if (!ret)
-		return FC_DISPATCH_UNLOCKED;
+		return 0;
 
 fail_host_msg:
 	/* return the errno failure code as the only status */
 	BUG_ON(job->reply_len < sizeof(uint32_t));
-	job->reply->reply_payload_rcv_len = 0;
-	job->reply->result = ret;
+	bsg_reply->reply_payload_rcv_len = 0;
+	bsg_reply->result = ret;
 	job->reply_len = sizeof(uint32_t);
-	fc_bsg_jobdone(job);
-	return FC_DISPATCH_UNLOCKED;
+	bsg_job_done(job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
+	return 0;
 }
 
 
@@ -3855,34 +3678,38 @@ fail_host_msg:
 static void
 fc_bsg_goose_queue(struct fc_rport *rport)
 {
-	if (!rport->rqst_q)
+	struct request_queue *q = rport->rqst_q;
+	unsigned long flags;
+
+	if (!q)
 		return;
 
-	/*
-	 * This get/put dance makes no sense
-	 */
-	get_device(&rport->dev);
-	blk_run_queue_async(rport->rqst_q);
-	put_device(&rport->dev);
+	spin_lock_irqsave(q->queue_lock, flags);
+	blk_run_queue_async(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
 /**
  * fc_bsg_rport_dispatch - process rport bsg requests and dispatch to LLDD
- * @q:		rport request queue
  * @shost:	scsi host rport attached to
- * @rport:	rport request destined to
  * @job:	bsg job to be processed
  */
-static enum fc_dispatch_result
-fc_bsg_rport_dispatch(struct request_queue *q, struct Scsi_Host *shost,
-			 struct fc_rport *rport, struct fc_bsg_job *job)
+static int fc_bsg_rport_dispatch(struct Scsi_Host *shost, struct bsg_job *job)
 {
 	struct fc_internal *i = to_fc_internal(shost->transportt);
+	struct fc_bsg_request *bsg_request = job->request;
+	struct fc_bsg_reply *bsg_reply = job->reply;
 	int cmdlen = sizeof(uint32_t);	/* start with length of msgcode */
 	int ret;
 
+	/* check if we really have all the request data needed */
+	if (job->request_len < cmdlen) {
+		ret = -ENOMSG;
+		goto fail_rport_msg;
+	}
+
 	/* Validate the rport command */
-	switch (job->request->msgcode) {
+	switch (bsg_request->msgcode) {
 	case FC_BSG_RPT_ELS:
 		cmdlen += sizeof(struct fc_bsg_rport_els);
 		goto check_bidi;
@@ -3902,133 +3729,31 @@ check_bidi:
 		goto fail_rport_msg;
 	}
 
-	/* check if we really have all the request data needed */
-	if (job->request_len < cmdlen) {
-		ret = -ENOMSG;
-		goto fail_rport_msg;
-	}
-
 	ret = i->f->bsg_request(job);
 	if (!ret)
-		return FC_DISPATCH_UNLOCKED;
+		return 0;
 
 fail_rport_msg:
 	/* return the errno failure code as the only status */
 	BUG_ON(job->reply_len < sizeof(uint32_t));
-	job->reply->reply_payload_rcv_len = 0;
-	job->reply->result = ret;
+	bsg_reply->reply_payload_rcv_len = 0;
+	bsg_reply->result = ret;
 	job->reply_len = sizeof(uint32_t);
-	fc_bsg_jobdone(job);
-	return FC_DISPATCH_UNLOCKED;
-}
-
-
-/**
- * fc_bsg_request_handler - generic handler for bsg requests
- * @q:		request queue to manage
- * @shost:	Scsi_Host related to the bsg object
- * @rport:	FC remote port related to the bsg object (optional)
- * @dev:	device structure for bsg object
- */
-static void
-fc_bsg_request_handler(struct request_queue *q, struct Scsi_Host *shost,
-		       struct fc_rport *rport, struct device *dev)
-{
-	struct request *req;
-	struct fc_bsg_job *job;
-	enum fc_dispatch_result ret;
-
-	if (!get_device(dev))
-		return;
-
-	while (1) {
-		if (rport && (rport->port_state == FC_PORTSTATE_BLOCKED) &&
-		    !(rport->flags & FC_RPORT_FAST_FAIL_TIMEDOUT))
-			break;
-
-		req = blk_fetch_request(q);
-		if (!req)
-			break;
-
-		if (rport && (rport->port_state != FC_PORTSTATE_ONLINE)) {
-			req->errors = -ENXIO;
-			spin_unlock_irq(q->queue_lock);
-			blk_end_request_all(req, -ENXIO);
-			spin_lock_irq(q->queue_lock);
-			continue;
-		}
-
-		spin_unlock_irq(q->queue_lock);
-
-		ret = fc_req_to_bsgjob(shost, rport, req);
-		if (ret) {
-			req->errors = ret;
-			blk_end_request_all(req, ret);
-			spin_lock_irq(q->queue_lock);
-			continue;
-		}
-
-		job = req->special;
-
-		/* check if we have the msgcode value at least */
-		if (job->request_len < sizeof(uint32_t)) {
-			BUG_ON(job->reply_len < sizeof(uint32_t));
-			job->reply->reply_payload_rcv_len = 0;
-			job->reply->result = -ENOMSG;
-			job->reply_len = sizeof(uint32_t);
-			fc_bsg_jobdone(job);
-			spin_lock_irq(q->queue_lock);
-			continue;
-		}
-
-		/* the dispatch routines will unlock the queue_lock */
-		if (rport)
-			ret = fc_bsg_rport_dispatch(q, shost, rport, job);
-		else
-			ret = fc_bsg_host_dispatch(q, shost, job);
-
-		/* did dispatcher hit state that can't process any more */
-		if (ret == FC_DISPATCH_BREAK)
-			break;
-
-		/* did dispatcher had released the lock */
-		if (ret == FC_DISPATCH_UNLOCKED)
-			spin_lock_irq(q->queue_lock);
-	}
-
-	spin_unlock_irq(q->queue_lock);
-	put_device(dev);
-	spin_lock_irq(q->queue_lock);
-}
-
-
-/**
- * fc_bsg_host_handler - handler for bsg requests for a fc host
- * @q:		fc host request queue
- */
-static void
-fc_bsg_host_handler(struct request_queue *q)
-{
-	struct Scsi_Host *shost = q->queuedata;
-
-	fc_bsg_request_handler(q, shost, NULL, &shost->shost_gendev);
+	bsg_job_done(job, bsg_reply->result,
+		       bsg_reply->reply_payload_rcv_len);
+	return 0;
 }
 
-
-/**
- * fc_bsg_rport_handler - handler for bsg requests for a fc rport
- * @q:		rport request queue
- */
-static void
-fc_bsg_rport_handler(struct request_queue *q)
+static int fc_bsg_dispatch(struct bsg_job *job)
 {
-	struct fc_rport *rport = q->queuedata;
-	struct Scsi_Host *shost = rport_to_shost(rport);
+	struct Scsi_Host *shost = fc_bsg_to_shost(job);
 
-	fc_bsg_request_handler(q, shost, rport, &rport->dev);
+	if (scsi_is_fc_rport(job->dev))
+		return fc_bsg_rport_dispatch(shost, job);
+	else
+		return fc_bsg_host_dispatch(shost, job);
 }
 
-
 /**
  * fc_bsg_hostadd - Create and add the bsg hooks so we can receive requests
  * @shost:	shost for fc_host
@@ -4051,33 +3776,42 @@ fc_bsg_hostadd(struct Scsi_Host *shost, struct fc_host_attrs *fc_host)
 	snprintf(bsg_name, sizeof(bsg_name),
 		 "fc_host%d", shost->host_no);
 
-	q = __scsi_alloc_queue(shost, fc_bsg_host_handler);
+	q = __scsi_alloc_queue(shost, bsg_request_fn);
 	if (!q) {
-		printk(KERN_ERR "fc_host%d: bsg interface failed to "
-				"initialize - no request queue\n",
-				 shost->host_no);
+		dev_err(dev,
+			"fc_host%d: bsg interface failed to initialize - no request queue\n",
+			shost->host_no);
 		return -ENOMEM;
 	}
 
-	q->queuedata = shost;
-	queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q);
-	blk_queue_softirq_done(q, fc_bsg_softirq_done);
-	blk_queue_rq_timed_out(q, fc_bsg_job_timeout);
-	blk_queue_rq_timeout(q, FC_DEFAULT_BSG_TIMEOUT);
-
-	err = bsg_register_queue(q, dev, bsg_name, NULL);
+	err = bsg_setup_queue(dev, q, bsg_name, fc_bsg_dispatch,
+				 i->f->dd_bsg_size);
 	if (err) {
-		printk(KERN_ERR "fc_host%d: bsg interface failed to "
-				"initialize - register queue\n",
-				shost->host_no);
+		dev_err(dev,
+			"fc_host%d: bsg interface failed to initialize - setup queue\n",
+			shost->host_no);
 		blk_cleanup_queue(q);
 		return err;
 	}
-
+	blk_queue_rq_timed_out(q, fc_bsg_job_timeout);
+	blk_queue_rq_timeout(q, FC_DEFAULT_BSG_TIMEOUT);
 	fc_host->rqst_q = q;
 	return 0;
 }
 
+static int fc_bsg_rport_prep(struct request_queue *q, struct request *req)
+{
+	struct fc_rport *rport = dev_to_rport(q->queuedata);
+
+	if (rport->port_state == FC_PORTSTATE_BLOCKED &&
+	    !(rport->flags & FC_RPORT_FAST_FAIL_TIMEDOUT))
+		return BLKPREP_DEFER;
+
+	if (rport->port_state != FC_PORTSTATE_ONLINE)
+		return BLKPREP_KILL;
+
+	return BLKPREP_OK;
+}
 
 /**
  * fc_bsg_rportadd - Create and add the bsg hooks so we can receive requests
@@ -4097,29 +3831,22 @@ fc_bsg_rportadd(struct Scsi_Host *shost, struct fc_rport *rport)
 	if (!i->f->bsg_request)
 		return -ENOTSUPP;
 
-	q = __scsi_alloc_queue(shost, fc_bsg_rport_handler);
+	q = __scsi_alloc_queue(shost, bsg_request_fn);
 	if (!q) {
-		printk(KERN_ERR "%s: bsg interface failed to "
-				"initialize - no request queue\n",
-				 dev->kobj.name);
+		dev_err(dev, "bsg interface failed to initialize - no request queue\n");
 		return -ENOMEM;
 	}
 
-	q->queuedata = rport;
-	queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q);
-	blk_queue_softirq_done(q, fc_bsg_softirq_done);
-	blk_queue_rq_timed_out(q, fc_bsg_job_timeout);
-	blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);
-
-	err = bsg_register_queue(q, dev, NULL, NULL);
+	err = bsg_setup_queue(dev, q, NULL, fc_bsg_dispatch, i->f->dd_bsg_size);
 	if (err) {
-		printk(KERN_ERR "%s: bsg interface failed to "
-				"initialize - register queue\n",
-				 dev->kobj.name);
+		dev_err(dev, "failed to setup bsg queue\n");
 		blk_cleanup_queue(q);
 		return err;
 	}
 
+	blk_queue_prep_rq(q, fc_bsg_rport_prep);
+	blk_queue_rq_timed_out(q, fc_bsg_job_timeout);
+	blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);
 	rport->rqst_q = q;
 	return 0;
 }
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index e3cd3ece4412..b87a78673f65 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -24,7 +24,6 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/delay.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -115,21 +114,12 @@ static DECLARE_TRANSPORT_CLASS(srp_host_class, "srp_host", srp_host_setup,
 static DECLARE_TRANSPORT_CLASS(srp_rport_class, "srp_remote_ports",
 			       NULL, NULL, NULL);
 
-#define SRP_PID(p) \
-	(p)->port_id[0], (p)->port_id[1], (p)->port_id[2], (p)->port_id[3], \
-	(p)->port_id[4], (p)->port_id[5], (p)->port_id[6], (p)->port_id[7], \
-	(p)->port_id[8], (p)->port_id[9], (p)->port_id[10], (p)->port_id[11], \
-	(p)->port_id[12], (p)->port_id[13], (p)->port_id[14], (p)->port_id[15]
-
-#define SRP_PID_FMT "%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x:" \
-	"%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x"
-
 static ssize_t
 show_srp_rport_id(struct device *dev, struct device_attribute *attr,
 		  char *buf)
 {
 	struct srp_rport *rport = transport_class_to_srp_rport(dev);
-	return sprintf(buf, SRP_PID_FMT "\n", SRP_PID(rport));
+	return sprintf(buf, "%16phC\n", rport->port_id);
 }
 
 static DEVICE_ATTR(port_id, S_IRUGO, show_srp_rport_id, NULL);
@@ -402,36 +392,6 @@ static void srp_reconnect_work(struct work_struct *work)
 	}
 }
 
-/**
- * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn()
- * @shost: SCSI host for which to count the number of scsi_request_fn() callers.
- *
- * To do: add support for scsi-mq in this function.
- */
-static int scsi_request_fn_active(struct Scsi_Host *shost)
-{
-	struct scsi_device *sdev;
-	struct request_queue *q;
-	int request_fn_active = 0;
-
-	shost_for_each_device(sdev, shost) {
-		q = sdev->request_queue;
-
-		spin_lock_irq(q->queue_lock);
-		request_fn_active += q->request_fn_active;
-		spin_unlock_irq(q->queue_lock);
-	}
-
-	return request_fn_active;
-}
-
-/* Wait until ongoing shost->hostt->queuecommand() calls have finished. */
-static void srp_wait_for_queuecommand(struct Scsi_Host *shost)
-{
-	while (scsi_request_fn_active(shost))
-		msleep(20);
-}
-
 static void __rport_fail_io_fast(struct srp_rport *rport)
 {
 	struct Scsi_Host *shost = rport_to_shost(rport);
@@ -441,14 +401,17 @@ static void __rport_fail_io_fast(struct srp_rport *rport)
 
 	if (srp_rport_set_state(rport, SRP_RPORT_FAIL_FAST))
 		return;
+	/*
+	 * Call scsi_target_block() to wait for ongoing shost->queuecommand()
+	 * calls before invoking i->f->terminate_rport_io().
+	 */
+	scsi_target_block(rport->dev.parent);
 	scsi_target_unblock(rport->dev.parent, SDEV_TRANSPORT_OFFLINE);
 
 	/* Involve the LLD if possible to terminate all I/O on the rport. */
 	i = to_srp_internal(shost->transportt);
-	if (i->f->terminate_rport_io) {
-		srp_wait_for_queuecommand(shost);
+	if (i->f->terminate_rport_io)
 		i->f->terminate_rport_io(rport);
-	}
 }
 
 /**
@@ -576,7 +539,6 @@ int srp_reconnect_rport(struct srp_rport *rport)
 	if (res)
 		goto out;
 	scsi_target_block(&shost->shost_gendev);
-	srp_wait_for_queuecommand(shost);
 	res = rport->state != SRP_RPORT_LOST ? i->f->reconnect(rport) : -ENODEV;
 	pr_debug("%s (state %d): transport.reconnect() returned %d\n",
 		 dev_name(&shost->shost_gendev), rport->state, res);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 51e56296f465..b1933041da39 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -53,7 +53,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/pr.h>
 #include <linux/t10-pi.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unaligned.h>
 
 #include <scsi/scsi.h>
@@ -93,6 +93,7 @@ MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK15_MAJOR);
 MODULE_ALIAS_SCSI_DEVICE(TYPE_DISK);
 MODULE_ALIAS_SCSI_DEVICE(TYPE_MOD);
 MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC);
+MODULE_ALIAS_SCSI_DEVICE(TYPE_ZBC);
 
 #if !defined(CONFIG_DEBUG_BLOCK_EXT_DEVT)
 #define SD_MINORS	16
@@ -163,7 +164,7 @@ cache_type_store(struct device *dev, struct device_attribute *attr,
 	static const char temp[] = "temporary ";
 	int len;
 
-	if (sdp->type != TYPE_DISK)
+	if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC)
 		/* no cache control on RBC devices; theoretically they
 		 * can do it, but there's probably so many exceptions
 		 * it's not worth the risk */
@@ -262,7 +263,7 @@ allow_restart_store(struct device *dev, struct device_attribute *attr,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
-	if (sdp->type != TYPE_DISK)
+	if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC)
 		return -EINVAL;
 
 	sdp->allow_restart = simple_strtoul(buf, NULL, 10);
@@ -392,6 +393,11 @@ provisioning_mode_store(struct device *dev, struct device_attribute *attr,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
+	if (sd_is_zoned(sdkp)) {
+		sd_config_discard(sdkp, SD_LBP_DISABLE);
+		return count;
+	}
+
 	if (sdp->type != TYPE_DISK)
 		return -EINVAL;
 
@@ -459,7 +465,7 @@ max_write_same_blocks_store(struct device *dev, struct device_attribute *attr,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
-	if (sdp->type != TYPE_DISK)
+	if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC)
 		return -EINVAL;
 
 	err = kstrtoul(buf, 10, &max);
@@ -710,7 +716,6 @@ static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd)
 	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
 	sector_t sector = blk_rq_pos(rq);
 	unsigned int nr_sectors = blk_rq_sectors(rq);
-	unsigned int nr_bytes = blk_rq_bytes(rq);
 	unsigned int len;
 	int ret;
 	char *buf;
@@ -766,24 +771,19 @@ static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd)
 		goto out;
 	}
 
-	rq->completion_data = page;
 	rq->timeout = SD_TIMEOUT;
 
 	cmd->transfersize = len;
 	cmd->allowed = SD_MAX_RETRIES;
 
-	/*
-	 * Initially __data_len is set to the amount of data that needs to be
-	 * transferred to the target. This amount depends on whether WRITE SAME
-	 * or UNMAP is being used. After the scatterlist has been mapped by
-	 * scsi_init_io() we set __data_len to the size of the area to be
-	 * discarded on disk. This allows us to report completion on the full
-	 * amount of blocks described by the request.
-	 */
-	blk_add_request_payload(rq, page, 0, len);
-	ret = scsi_init_io(cmd);
-	rq->__data_len = nr_bytes;
+	rq->special_vec.bv_page = page;
+	rq->special_vec.bv_offset = 0;
+	rq->special_vec.bv_len = len;
+
+	rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
+	rq->resid_len = len;
 
+	ret = scsi_init_io(cmd);
 out:
 	if (ret != BLKPREP_OK)
 		__free_page(page);
@@ -844,6 +844,12 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 
 	BUG_ON(bio_offset(bio) || bio_iovec(bio).bv_len != sdp->sector_size);
 
+	if (sd_is_zoned(sdkp)) {
+		ret = sd_zbc_setup_write_cmnd(cmd);
+		if (ret != BLKPREP_OK)
+			return ret;
+	}
+
 	sector >>= ilog2(sdp->sector_size) - 9;
 	nr_sectors >>= ilog2(sdp->sector_size) - 9;
 
@@ -901,19 +907,25 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 	struct request *rq = SCpnt->request;
 	struct scsi_device *sdp = SCpnt->device;
 	struct gendisk *disk = rq->rq_disk;
-	struct scsi_disk *sdkp;
+	struct scsi_disk *sdkp = scsi_disk(disk);
 	sector_t block = blk_rq_pos(rq);
 	sector_t threshold;
 	unsigned int this_count = blk_rq_sectors(rq);
 	unsigned int dif, dix;
+	bool zoned_write = sd_is_zoned(sdkp) && rq_data_dir(rq) == WRITE;
 	int ret;
 	unsigned char protect;
 
+	if (zoned_write) {
+		ret = sd_zbc_setup_write_cmnd(SCpnt);
+		if (ret != BLKPREP_OK)
+			return ret;
+	}
+
 	ret = scsi_init_io(SCpnt);
 	if (ret != BLKPREP_OK)
 		goto out;
 	SCpnt = rq->special;
-	sdkp = scsi_disk(disk);
 
 	/* from here on until we're complete, any goto out
 	 * is used for a killable error condition */
@@ -1013,8 +1025,7 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 	} else if (rq_data_dir(rq) == READ) {
 		SCpnt->cmnd[0] = READ_6;
 	} else {
-		scmd_printk(KERN_ERR, SCpnt, "Unknown command %llu,%llx\n",
-			    req_op(rq), (unsigned long long) rq->cmd_flags);
+		scmd_printk(KERN_ERR, SCpnt, "Unknown command %d\n", req_op(rq));
 		goto out;
 	}
 
@@ -1132,6 +1143,9 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 	 */
 	ret = BLKPREP_OK;
  out:
+	if (zoned_write && ret != BLKPREP_OK)
+		sd_zbc_cancel_write_cmnd(SCpnt);
+
 	return ret;
 }
 
@@ -1149,6 +1163,10 @@ static int sd_init_command(struct scsi_cmnd *cmd)
 	case REQ_OP_READ:
 	case REQ_OP_WRITE:
 		return sd_setup_read_write_cmnd(cmd);
+	case REQ_OP_ZONE_REPORT:
+		return sd_zbc_setup_report_cmnd(cmd);
+	case REQ_OP_ZONE_RESET:
+		return sd_zbc_setup_reset_cmnd(cmd);
 	default:
 		BUG();
 	}
@@ -1158,8 +1176,8 @@ static void sd_uninit_command(struct scsi_cmnd *SCpnt)
 {
 	struct request *rq = SCpnt->request;
 
-	if (req_op(rq) == REQ_OP_DISCARD)
-		__free_page(rq->completion_data);
+	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
+		__free_page(rq->special_vec.bv_page);
 
 	if (SCpnt->cmnd != rq->cmd) {
 		mempool_free(SCpnt->cmnd, sd_cdb_pool);
@@ -1495,7 +1513,7 @@ static int sd_sync_cache(struct scsi_disk *sdkp)
 		 */
 		res = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0,
 					     &sshdr, timeout, SD_MAX_RETRIES,
-					     NULL, REQ_PM);
+					     NULL, 0, RQF_PM);
 		if (res == 0)
 			break;
 	}
@@ -1780,7 +1798,10 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 	unsigned char op = SCpnt->cmnd[0];
 	unsigned char unmap = SCpnt->cmnd[1] & 8;
 
-	if (req_op(req) == REQ_OP_DISCARD || req_op(req) == REQ_OP_WRITE_SAME) {
+	switch (req_op(req)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_WRITE_SAME:
+	case REQ_OP_ZONE_RESET:
 		if (!result) {
 			good_bytes = blk_rq_bytes(req);
 			scsi_set_resid(SCpnt, 0);
@@ -1788,6 +1809,17 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 			good_bytes = 0;
 			scsi_set_resid(SCpnt, blk_rq_bytes(req));
 		}
+		break;
+	case REQ_OP_ZONE_REPORT:
+		if (!result) {
+			good_bytes = scsi_bufflen(SCpnt)
+				- scsi_get_resid(SCpnt);
+			scsi_set_resid(SCpnt, 0);
+		} else {
+			good_bytes = 0;
+			scsi_set_resid(SCpnt, blk_rq_bytes(req));
+		}
+		break;
 	}
 
 	if (result) {
@@ -1840,7 +1872,7 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 
 					good_bytes = 0;
 					req->__data_len = blk_rq_bytes(req);
-					req->cmd_flags |= REQ_QUIET;
+					req->rq_flags |= RQF_QUIET;
 				}
 			}
 		}
@@ -1848,7 +1880,11 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 	default:
 		break;
 	}
+
  out:
+	if (sd_is_zoned(sdkp))
+		sd_zbc_complete(SCpnt, good_bytes, &sshdr);
+
 	SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, SCpnt,
 					   "sd_done: completed %d of %d bytes\n",
 					   good_bytes, scsi_bufflen(SCpnt)));
@@ -1983,7 +2019,6 @@ sd_spinup_disk(struct scsi_disk *sdkp)
 	}
 }
 
-
 /*
  * Determine whether disk supports Data Integrity Field.
  */
@@ -2133,6 +2168,9 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
 	/* Logical blocks per physical block exponent */
 	sdkp->physical_block_size = (1 << (buffer[13] & 0xf)) * sector_size;
 
+	/* RC basis */
+	sdkp->rc_basis = (buffer[12] >> 4) & 0x3;
+
 	/* Lowest aligned logical block */
 	alignment = ((buffer[14] & 0x3f) << 8 | buffer[15]) * sector_size;
 	blk_queue_alignment_offset(sdp->request_queue, alignment);
@@ -2242,7 +2280,6 @@ sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer)
 {
 	int sector_size;
 	struct scsi_device *sdp = sdkp->device;
-	sector_t old_capacity = sdkp->capacity;
 
 	if (sd_try_rc16_first(sdp)) {
 		sector_size = read_capacity_16(sdkp, sdp, buffer);
@@ -2323,35 +2360,44 @@ got_data:
 		sector_size = 512;
 	}
 	blk_queue_logical_block_size(sdp->request_queue, sector_size);
+	blk_queue_physical_block_size(sdp->request_queue,
+				      sdkp->physical_block_size);
+	sdkp->device->sector_size = sector_size;
 
-	{
-		char cap_str_2[10], cap_str_10[10];
+	if (sdkp->capacity > 0xffffffff)
+		sdp->use_16_for_rw = 1;
 
-		string_get_size(sdkp->capacity, sector_size,
-				STRING_UNITS_2, cap_str_2, sizeof(cap_str_2));
-		string_get_size(sdkp->capacity, sector_size,
-				STRING_UNITS_10, cap_str_10,
-				sizeof(cap_str_10));
+}
 
-		if (sdkp->first_scan || old_capacity != sdkp->capacity) {
-			sd_printk(KERN_NOTICE, sdkp,
-				  "%llu %d-byte logical blocks: (%s/%s)\n",
-				  (unsigned long long)sdkp->capacity,
-				  sector_size, cap_str_10, cap_str_2);
+/*
+ * Print disk capacity
+ */
+static void
+sd_print_capacity(struct scsi_disk *sdkp,
+		  sector_t old_capacity)
+{
+	int sector_size = sdkp->device->sector_size;
+	char cap_str_2[10], cap_str_10[10];
 
-			if (sdkp->physical_block_size != sector_size)
-				sd_printk(KERN_NOTICE, sdkp,
-					  "%u-byte physical blocks\n",
-					  sdkp->physical_block_size);
-		}
-	}
+	string_get_size(sdkp->capacity, sector_size,
+			STRING_UNITS_2, cap_str_2, sizeof(cap_str_2));
+	string_get_size(sdkp->capacity, sector_size,
+			STRING_UNITS_10, cap_str_10,
+			sizeof(cap_str_10));
 
-	if (sdkp->capacity > 0xffffffff)
-		sdp->use_16_for_rw = 1;
+	if (sdkp->first_scan || old_capacity != sdkp->capacity) {
+		sd_printk(KERN_NOTICE, sdkp,
+			  "%llu %d-byte logical blocks: (%s/%s)\n",
+			  (unsigned long long)sdkp->capacity,
+			  sector_size, cap_str_10, cap_str_2);
 
-	blk_queue_physical_block_size(sdp->request_queue,
-				      sdkp->physical_block_size);
-	sdkp->device->sector_size = sector_size;
+		if (sdkp->physical_block_size != sector_size)
+			sd_printk(KERN_NOTICE, sdkp,
+				  "%u-byte physical blocks\n",
+				  sdkp->physical_block_size);
+
+		sd_zbc_print_zones(sdkp);
+	}
 }
 
 /* called with buffer of length 512 */
@@ -2419,9 +2465,7 @@ sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer)
 		if (sdkp->first_scan || old_wp != sdkp->write_prot) {
 			sd_printk(KERN_NOTICE, sdkp, "Write Protect is %s\n",
 				  sdkp->write_prot ? "on" : "off");
-			sd_printk(KERN_DEBUG, sdkp,
-				  "Mode Sense: %02x %02x %02x %02x\n",
-				  buffer[0], buffer[1], buffer[2], buffer[3]);
+			sd_printk(KERN_DEBUG, sdkp, "Mode Sense: %4ph\n", buffer);
 		}
 	}
 }
@@ -2613,7 +2657,7 @@ static void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer)
 	struct scsi_mode_data data;
 	struct scsi_sense_hdr sshdr;
 
-	if (sdp->type != TYPE_DISK)
+	if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC)
 		return;
 
 	if (sdkp->protection_type == 0)
@@ -2720,6 +2764,7 @@ static void sd_read_block_limits(struct scsi_disk *sdkp)
  */
 static void sd_read_block_characteristics(struct scsi_disk *sdkp)
 {
+	struct request_queue *q = sdkp->disk->queue;
 	unsigned char *buffer;
 	u16 rot;
 	const int vpd_len = 64;
@@ -2734,10 +2779,21 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp)
 	rot = get_unaligned_be16(&buffer[4]);
 
 	if (rot == 1) {
-		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, sdkp->disk->queue);
-		queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, sdkp->disk->queue);
+		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
+		queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q);
 	}
 
+	sdkp->zoned = (buffer[8] >> 4) & 3;
+	if (sdkp->zoned == 1)
+		q->limits.zoned = BLK_ZONED_HA;
+	else if (sdkp->device->type == TYPE_ZBC)
+		q->limits.zoned = BLK_ZONED_HM;
+	else
+		q->limits.zoned = BLK_ZONED_NONE;
+	if (blk_queue_is_zoned(q) && sdkp->first_scan)
+		sd_printk(KERN_NOTICE, sdkp, "Host-%s zoned block device\n",
+		      q->limits.zoned == BLK_ZONED_HM ? "managed" : "aware");
+
  out:
 	kfree(buffer);
 }
@@ -2809,6 +2865,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	struct scsi_disk *sdkp = scsi_disk(disk);
 	struct scsi_device *sdp = sdkp->device;
 	struct request_queue *q = sdkp->disk->queue;
+	sector_t old_capacity = sdkp->capacity;
 	unsigned char *buffer;
 	unsigned int dev_max, rw_max;
 
@@ -2842,8 +2899,11 @@ static int sd_revalidate_disk(struct gendisk *disk)
 			sd_read_block_provisioning(sdkp);
 			sd_read_block_limits(sdkp);
 			sd_read_block_characteristics(sdkp);
+			sd_zbc_read_zones(sdkp, buffer);
 		}
 
+		sd_print_capacity(sdkp, old_capacity);
+
 		sd_read_write_protect_flag(sdkp, buffer);
 		sd_read_cache_type(sdkp, buffer);
 		sd_read_app_tag_own(sdkp, buffer);
@@ -3041,9 +3101,16 @@ static int sd_probe(struct device *dev)
 
 	scsi_autopm_get_device(sdp);
 	error = -ENODEV;
-	if (sdp->type != TYPE_DISK && sdp->type != TYPE_MOD && sdp->type != TYPE_RBC)
+	if (sdp->type != TYPE_DISK &&
+	    sdp->type != TYPE_ZBC &&
+	    sdp->type != TYPE_MOD &&
+	    sdp->type != TYPE_RBC)
 		goto out;
 
+#ifndef CONFIG_BLK_DEV_ZONED
+	if (sdp->type == TYPE_ZBC)
+		goto out;
+#endif
 	SCSI_LOG_HLQUEUE(3, sdev_printk(KERN_INFO, sdp,
 					"sd_probe\n"));
 
@@ -3147,6 +3214,8 @@ static int sd_remove(struct device *dev)
 	del_gendisk(sdkp->disk);
 	sd_shutdown(dev);
 
+	sd_zbc_remove(sdkp);
+
 	blk_register_region(devt, SD_MINORS, NULL,
 			    sd_default_probe, NULL, NULL);
 
@@ -3200,7 +3269,7 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start)
 		return -ENODEV;
 
 	res = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0, &sshdr,
-			       SD_TIMEOUT, SD_MAX_RETRIES, NULL, REQ_PM);
+			       SD_TIMEOUT, SD_MAX_RETRIES, NULL, 0, RQF_PM);
 	if (res) {
 		sd_print_result(sdkp, "Start/Stop Unit failed", res);
 		if (driver_byte(res) & DRIVER_SENSE)
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index c8d986368da9..4dac35e96a75 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -64,6 +64,15 @@ struct scsi_disk {
 	struct scsi_device *device;
 	struct device	dev;
 	struct gendisk	*disk;
+#ifdef CONFIG_BLK_DEV_ZONED
+	unsigned int	nr_zones;
+	unsigned int	zone_blocks;
+	unsigned int	zone_shift;
+	unsigned long	*zones_wlock;
+	unsigned int	zones_optimal_open;
+	unsigned int	zones_optimal_nonseq;
+	unsigned int	zones_max_open;
+#endif
 	atomic_t	openers;
 	sector_t	capacity;	/* size in logical blocks */
 	u32		max_xfer_blocks;
@@ -94,6 +103,9 @@ struct scsi_disk {
 	unsigned	lbpvpd : 1;
 	unsigned	ws10 : 1;
 	unsigned	ws16 : 1;
+	unsigned	rc_basis: 2;
+	unsigned	zoned: 2;
+	unsigned	urswrz : 1;
 };
 #define to_scsi_disk(obj) container_of(obj,struct scsi_disk,dev)
 
@@ -156,6 +168,11 @@ static inline unsigned int logical_to_bytes(struct scsi_device *sdev, sector_t b
 	return blocks * sdev->sector_size;
 }
 
+static inline sector_t sectors_to_logical(struct scsi_device *sdev, sector_t sector)
+{
+	return sector >> (ilog2(sdev->sector_size) - 9);
+}
+
 /*
  * Look up the DIX operation based on whether the command is read or
  * write and whether dix and dif are enabled.
@@ -239,4 +256,57 @@ static inline void sd_dif_complete(struct scsi_cmnd *cmd, unsigned int a)
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
+static inline int sd_is_zoned(struct scsi_disk *sdkp)
+{
+	return sdkp->zoned == 1 || sdkp->device->type == TYPE_ZBC;
+}
+
+#ifdef CONFIG_BLK_DEV_ZONED
+
+extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer);
+extern void sd_zbc_remove(struct scsi_disk *sdkp);
+extern void sd_zbc_print_zones(struct scsi_disk *sdkp);
+extern int sd_zbc_setup_write_cmnd(struct scsi_cmnd *cmd);
+extern void sd_zbc_cancel_write_cmnd(struct scsi_cmnd *cmd);
+extern int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd);
+extern int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd);
+extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
+			    struct scsi_sense_hdr *sshdr);
+
+#else /* CONFIG_BLK_DEV_ZONED */
+
+static inline int sd_zbc_read_zones(struct scsi_disk *sdkp,
+				    unsigned char *buf)
+{
+	return 0;
+}
+
+static inline void sd_zbc_remove(struct scsi_disk *sdkp) {}
+
+static inline void sd_zbc_print_zones(struct scsi_disk *sdkp) {}
+
+static inline int sd_zbc_setup_write_cmnd(struct scsi_cmnd *cmd)
+{
+	/* Let the drive fail requests */
+	return BLKPREP_OK;
+}
+
+static inline void sd_zbc_cancel_write_cmnd(struct scsi_cmnd *cmd) {}
+
+static inline int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd)
+{
+	return BLKPREP_INVALID;
+}
+
+static inline int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd)
+{
+	return BLKPREP_INVALID;
+}
+
+static inline void sd_zbc_complete(struct scsi_cmnd *cmd,
+				   unsigned int good_bytes,
+				   struct scsi_sense_hdr *sshdr) {}
+
+#endif /* CONFIG_BLK_DEV_ZONED */
+
 #endif /* _SCSI_DISK_H */
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
new file mode 100644
index 000000000000..92620c8ea8ad
--- /dev/null
+++ b/drivers/scsi/sd_zbc.c
@@ -0,0 +1,648 @@
+/*
+ * SCSI Zoned Block commands
+ *
+ * Copyright (C) 2014-2015 SUSE Linux GmbH
+ * Written by: Hannes Reinecke <hare@suse.de>
+ * Modified by: Damien Le Moal <damien.lemoal@hgst.com>
+ * Modified by: Shaun Tancheff <shaun.tancheff@seagate.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
+ * USA.
+ *
+ */
+
+#include <linux/blkdev.h>
+
+#include <asm/unaligned.h>
+
+#include <scsi/scsi.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_dbg.h>
+#include <scsi/scsi_device.h>
+#include <scsi/scsi_driver.h>
+#include <scsi/scsi_host.h>
+#include <scsi/scsi_eh.h>
+
+#include "sd.h"
+#include "scsi_priv.h"
+
+enum zbc_zone_type {
+	ZBC_ZONE_TYPE_CONV = 0x1,
+	ZBC_ZONE_TYPE_SEQWRITE_REQ,
+	ZBC_ZONE_TYPE_SEQWRITE_PREF,
+	ZBC_ZONE_TYPE_RESERVED,
+};
+
+enum zbc_zone_cond {
+	ZBC_ZONE_COND_NO_WP,
+	ZBC_ZONE_COND_EMPTY,
+	ZBC_ZONE_COND_IMP_OPEN,
+	ZBC_ZONE_COND_EXP_OPEN,
+	ZBC_ZONE_COND_CLOSED,
+	ZBC_ZONE_COND_READONLY = 0xd,
+	ZBC_ZONE_COND_FULL,
+	ZBC_ZONE_COND_OFFLINE,
+};
+
+/**
+ * Convert a zone descriptor to a zone struct.
+ */
+static void sd_zbc_parse_report(struct scsi_disk *sdkp,
+				u8 *buf,
+				struct blk_zone *zone)
+{
+	struct scsi_device *sdp = sdkp->device;
+
+	memset(zone, 0, sizeof(struct blk_zone));
+
+	zone->type = buf[0] & 0x0f;
+	zone->cond = (buf[1] >> 4) & 0xf;
+	if (buf[1] & 0x01)
+		zone->reset = 1;
+	if (buf[1] & 0x02)
+		zone->non_seq = 1;
+
+	zone->len = logical_to_sectors(sdp, get_unaligned_be64(&buf[8]));
+	zone->start = logical_to_sectors(sdp, get_unaligned_be64(&buf[16]));
+	zone->wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24]));
+	if (zone->type != ZBC_ZONE_TYPE_CONV &&
+	    zone->cond == ZBC_ZONE_COND_FULL)
+		zone->wp = zone->start + zone->len;
+}
+
+/**
+ * Issue a REPORT ZONES scsi command.
+ */
+static int sd_zbc_report_zones(struct scsi_disk *sdkp, unsigned char *buf,
+			       unsigned int buflen, sector_t lba)
+{
+	struct scsi_device *sdp = sdkp->device;
+	const int timeout = sdp->request_queue->rq_timeout;
+	struct scsi_sense_hdr sshdr;
+	unsigned char cmd[16];
+	unsigned int rep_len;
+	int result;
+
+	memset(cmd, 0, 16);
+	cmd[0] = ZBC_IN;
+	cmd[1] = ZI_REPORT_ZONES;
+	put_unaligned_be64(lba, &cmd[2]);
+	put_unaligned_be32(buflen, &cmd[10]);
+	memset(buf, 0, buflen);
+
+	result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE,
+				  buf, buflen, &sshdr,
+				  timeout, SD_MAX_RETRIES, NULL);
+	if (result) {
+		sd_printk(KERN_ERR, sdkp,
+			  "REPORT ZONES lba %llu failed with %d/%d\n",
+			  (unsigned long long)lba,
+			  host_byte(result), driver_byte(result));
+		return -EIO;
+	}
+
+	rep_len = get_unaligned_be32(&buf[0]);
+	if (rep_len < 64) {
+		sd_printk(KERN_ERR, sdkp,
+			  "REPORT ZONES report invalid length %u\n",
+			  rep_len);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd)
+{
+	struct request *rq = cmd->request;
+	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	sector_t lba, sector = blk_rq_pos(rq);
+	unsigned int nr_bytes = blk_rq_bytes(rq);
+	int ret;
+
+	WARN_ON(nr_bytes == 0);
+
+	if (!sd_is_zoned(sdkp))
+		/* Not a zoned device */
+		return BLKPREP_KILL;
+
+	ret = scsi_init_io(cmd);
+	if (ret != BLKPREP_OK)
+		return ret;
+
+	cmd->cmd_len = 16;
+	memset(cmd->cmnd, 0, cmd->cmd_len);
+	cmd->cmnd[0] = ZBC_IN;
+	cmd->cmnd[1] = ZI_REPORT_ZONES;
+	lba = sectors_to_logical(sdkp->device, sector);
+	put_unaligned_be64(lba, &cmd->cmnd[2]);
+	put_unaligned_be32(nr_bytes, &cmd->cmnd[10]);
+	/* Do partial report for speeding things up */
+	cmd->cmnd[14] = ZBC_REPORT_ZONE_PARTIAL;
+
+	cmd->sc_data_direction = DMA_FROM_DEVICE;
+	cmd->sdb.length = nr_bytes;
+	cmd->transfersize = sdkp->device->sector_size;
+	cmd->allowed = 0;
+
+	/*
+	 * Report may return less bytes than requested. Make sure
+	 * to report completion on the entire initial request.
+	 */
+	rq->__data_len = nr_bytes;
+
+	return BLKPREP_OK;
+}
+
+static void sd_zbc_report_zones_complete(struct scsi_cmnd *scmd,
+					 unsigned int good_bytes)
+{
+	struct request *rq = scmd->request;
+	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	struct sg_mapping_iter miter;
+	struct blk_zone_report_hdr hdr;
+	struct blk_zone zone;
+	unsigned int offset, bytes = 0;
+	unsigned long flags;
+	u8 *buf;
+
+	if (good_bytes < 64)
+		return;
+
+	memset(&hdr, 0, sizeof(struct blk_zone_report_hdr));
+
+	sg_miter_start(&miter, scsi_sglist(scmd), scsi_sg_count(scmd),
+		       SG_MITER_TO_SG | SG_MITER_ATOMIC);
+
+	local_irq_save(flags);
+	while (sg_miter_next(&miter) && bytes < good_bytes) {
+
+		buf = miter.addr;
+		offset = 0;
+
+		if (bytes == 0) {
+			/* Set the report header */
+			hdr.nr_zones = min_t(unsigned int,
+					 (good_bytes - 64) / 64,
+					 get_unaligned_be32(&buf[0]) / 64);
+			memcpy(buf, &hdr, sizeof(struct blk_zone_report_hdr));
+			offset += 64;
+			bytes += 64;
+		}
+
+		/* Parse zone descriptors */
+		while (offset < miter.length && hdr.nr_zones) {
+			WARN_ON(offset > miter.length);
+			buf = miter.addr + offset;
+			sd_zbc_parse_report(sdkp, buf, &zone);
+			memcpy(buf, &zone, sizeof(struct blk_zone));
+			offset += 64;
+			bytes += 64;
+			hdr.nr_zones--;
+		}
+
+		if (!hdr.nr_zones)
+			break;
+
+	}
+	sg_miter_stop(&miter);
+	local_irq_restore(flags);
+}
+
+static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp)
+{
+	return logical_to_sectors(sdkp->device, sdkp->zone_blocks);
+}
+
+static inline unsigned int sd_zbc_zone_no(struct scsi_disk *sdkp,
+					  sector_t sector)
+{
+	return sectors_to_logical(sdkp->device, sector) >> sdkp->zone_shift;
+}
+
+int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd)
+{
+	struct request *rq = cmd->request;
+	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	sector_t sector = blk_rq_pos(rq);
+	sector_t block = sectors_to_logical(sdkp->device, sector);
+	unsigned int zno = block >> sdkp->zone_shift;
+
+	if (!sd_is_zoned(sdkp))
+		/* Not a zoned device */
+		return BLKPREP_KILL;
+
+	if (sdkp->device->changed)
+		return BLKPREP_KILL;
+
+	if (sector & (sd_zbc_zone_sectors(sdkp) - 1))
+		/* Unaligned request */
+		return BLKPREP_KILL;
+
+	/* Do not allow concurrent reset and writes */
+	if (sdkp->zones_wlock &&
+	    test_and_set_bit(zno, sdkp->zones_wlock))
+		return BLKPREP_DEFER;
+
+	cmd->cmd_len = 16;
+	memset(cmd->cmnd, 0, cmd->cmd_len);
+	cmd->cmnd[0] = ZBC_OUT;
+	cmd->cmnd[1] = ZO_RESET_WRITE_POINTER;
+	put_unaligned_be64(block, &cmd->cmnd[2]);
+
+	rq->timeout = SD_TIMEOUT;
+	cmd->sc_data_direction = DMA_NONE;
+	cmd->transfersize = 0;
+	cmd->allowed = 0;
+
+	return BLKPREP_OK;
+}
+
+int sd_zbc_setup_write_cmnd(struct scsi_cmnd *cmd)
+{
+	struct request *rq = cmd->request;
+	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	sector_t sector = blk_rq_pos(rq);
+	sector_t zone_sectors = sd_zbc_zone_sectors(sdkp);
+	unsigned int zno = sd_zbc_zone_no(sdkp, sector);
+
+	/*
+	 * Note: Checks of the alignment of the write command on
+	 * logical blocks is done in sd.c
+	 */
+
+	/* Do not allow zone boundaries crossing on host-managed drives */
+	if (blk_queue_zoned_model(sdkp->disk->queue) == BLK_ZONED_HM &&
+	    (sector & (zone_sectors - 1)) + blk_rq_sectors(rq) > zone_sectors)
+		return BLKPREP_KILL;
+
+	/*
+	 * Do not issue more than one write at a time per
+	 * zone. This solves write ordering problems due to
+	 * the unlocking of the request queue in the dispatch
+	 * path in the non scsi-mq case. For scsi-mq, this
+	 * also avoids potential write reordering when multiple
+	 * threads running on different CPUs write to the same
+	 * zone (with a synchronized sequential pattern).
+	 */
+	if (sdkp->zones_wlock &&
+	    test_and_set_bit(zno, sdkp->zones_wlock))
+		return BLKPREP_DEFER;
+
+	return BLKPREP_OK;
+}
+
+static void sd_zbc_unlock_zone(struct request *rq)
+{
+	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+
+	if (sdkp->zones_wlock) {
+		unsigned int zno = sd_zbc_zone_no(sdkp, blk_rq_pos(rq));
+		WARN_ON_ONCE(!test_bit(zno, sdkp->zones_wlock));
+		clear_bit_unlock(zno, sdkp->zones_wlock);
+		smp_mb__after_atomic();
+	}
+}
+
+void sd_zbc_cancel_write_cmnd(struct scsi_cmnd *cmd)
+{
+	sd_zbc_unlock_zone(cmd->request);
+}
+
+void sd_zbc_complete(struct scsi_cmnd *cmd,
+		     unsigned int good_bytes,
+		     struct scsi_sense_hdr *sshdr)
+{
+	int result = cmd->result;
+	struct request *rq = cmd->request;
+
+	switch (req_op(rq)) {
+	case REQ_OP_WRITE:
+	case REQ_OP_WRITE_SAME:
+	case REQ_OP_ZONE_RESET:
+
+		/* Unlock the zone */
+		sd_zbc_unlock_zone(rq);
+
+		if (!result ||
+		    sshdr->sense_key != ILLEGAL_REQUEST)
+			break;
+
+		switch (sshdr->asc) {
+		case 0x24:
+			/*
+			 * INVALID FIELD IN CDB error: For a zone reset,
+			 * this means that a reset of a conventional
+			 * zone was attempted. Nothing to worry about in
+			 * this case, so be quiet about the error.
+			 */
+			if (req_op(rq) == REQ_OP_ZONE_RESET)
+				rq->rq_flags |= RQF_QUIET;
+			break;
+		case 0x21:
+			/*
+			 * INVALID ADDRESS FOR WRITE error: It is unlikely that
+			 * retrying write requests failed with any kind of
+			 * alignement error will result in success. So don't.
+			 */
+			cmd->allowed = 0;
+			break;
+		}
+
+		break;
+
+	case REQ_OP_ZONE_REPORT:
+
+		if (!result)
+			sd_zbc_report_zones_complete(cmd, good_bytes);
+		break;
+
+	}
+}
+
+/**
+ * Read zoned block device characteristics (VPD page B6).
+ */
+static int sd_zbc_read_zoned_characteristics(struct scsi_disk *sdkp,
+					     unsigned char *buf)
+{
+
+	if (scsi_get_vpd_page(sdkp->device, 0xb6, buf, 64)) {
+		sd_printk(KERN_NOTICE, sdkp,
+			  "Unconstrained-read check failed\n");
+		return -ENODEV;
+	}
+
+	if (sdkp->device->type != TYPE_ZBC) {
+		/* Host-aware */
+		sdkp->urswrz = 1;
+		sdkp->zones_optimal_open = get_unaligned_be64(&buf[8]);
+		sdkp->zones_optimal_nonseq = get_unaligned_be64(&buf[12]);
+		sdkp->zones_max_open = 0;
+	} else {
+		/* Host-managed */
+		sdkp->urswrz = buf[4] & 1;
+		sdkp->zones_optimal_open = 0;
+		sdkp->zones_optimal_nonseq = 0;
+		sdkp->zones_max_open = get_unaligned_be64(&buf[16]);
+	}
+
+	return 0;
+}
+
+/**
+ * Check reported capacity.
+ */
+static int sd_zbc_check_capacity(struct scsi_disk *sdkp,
+				 unsigned char *buf)
+{
+	sector_t lba;
+	int ret;
+
+	if (sdkp->rc_basis != 0)
+		return 0;
+
+	/* Do a report zone to get the maximum LBA to check capacity */
+	ret = sd_zbc_report_zones(sdkp, buf, SD_BUF_SIZE, 0);
+	if (ret)
+		return ret;
+
+	/* The max_lba field is the capacity of this device */
+	lba = get_unaligned_be64(&buf[8]);
+	if (lba + 1 == sdkp->capacity)
+		return 0;
+
+	if (sdkp->first_scan)
+		sd_printk(KERN_WARNING, sdkp,
+			  "Changing capacity from %llu to max LBA+1 %llu\n",
+			  (unsigned long long)sdkp->capacity,
+			  (unsigned long long)lba + 1);
+	sdkp->capacity = lba + 1;
+
+	return 0;
+}
+
+#define SD_ZBC_BUF_SIZE 131072
+
+static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
+{
+	u64 zone_blocks;
+	sector_t block = 0;
+	unsigned char *buf;
+	unsigned char *rec;
+	unsigned int buf_len;
+	unsigned int list_length;
+	int ret;
+	u8 same;
+
+	sdkp->zone_blocks = 0;
+
+	/* Get a buffer */
+	buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	/* Do a report zone to get the same field */
+	ret = sd_zbc_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, 0);
+	if (ret) {
+		zone_blocks = 0;
+		goto out;
+	}
+
+	same = buf[4] & 0x0f;
+	if (same > 0) {
+		rec = &buf[64];
+		zone_blocks = get_unaligned_be64(&rec[8]);
+		goto out;
+	}
+
+	/*
+	 * Check the size of all zones: all zones must be of
+	 * equal size, except the last zone which can be smaller
+	 * than other zones.
+	 */
+	do {
+
+		/* Parse REPORT ZONES header */
+		list_length = get_unaligned_be32(&buf[0]) + 64;
+		rec = buf + 64;
+		if (list_length < SD_ZBC_BUF_SIZE)
+			buf_len = list_length;
+		else
+			buf_len = SD_ZBC_BUF_SIZE;
+
+		/* Parse zone descriptors */
+		while (rec < buf + buf_len) {
+			zone_blocks = get_unaligned_be64(&rec[8]);
+			if (sdkp->zone_blocks == 0) {
+				sdkp->zone_blocks = zone_blocks;
+			} else if (zone_blocks != sdkp->zone_blocks &&
+				   (block + zone_blocks < sdkp->capacity
+				    || zone_blocks > sdkp->zone_blocks)) {
+				zone_blocks = 0;
+				goto out;
+			}
+			block += zone_blocks;
+			rec += 64;
+		}
+
+		if (block < sdkp->capacity) {
+			ret = sd_zbc_report_zones(sdkp, buf,
+						  SD_ZBC_BUF_SIZE, block);
+			if (ret)
+				return ret;
+		}
+
+	} while (block < sdkp->capacity);
+
+	zone_blocks = sdkp->zone_blocks;
+
+out:
+	kfree(buf);
+
+	if (!zone_blocks) {
+		if (sdkp->first_scan)
+			sd_printk(KERN_NOTICE, sdkp,
+				  "Devices with non constant zone "
+				  "size are not supported\n");
+		return -ENODEV;
+	}
+
+	if (!is_power_of_2(zone_blocks)) {
+		if (sdkp->first_scan)
+			sd_printk(KERN_NOTICE, sdkp,
+				  "Devices with non power of 2 zone "
+				  "size are not supported\n");
+		return -ENODEV;
+	}
+
+	if (logical_to_sectors(sdkp->device, zone_blocks) > UINT_MAX) {
+		if (sdkp->first_scan)
+			sd_printk(KERN_NOTICE, sdkp,
+				  "Zone size too large\n");
+		return -ENODEV;
+	}
+
+	sdkp->zone_blocks = zone_blocks;
+
+	return 0;
+}
+
+static int sd_zbc_setup(struct scsi_disk *sdkp)
+{
+
+	/* chunk_sectors indicates the zone size */
+	blk_queue_chunk_sectors(sdkp->disk->queue,
+			logical_to_sectors(sdkp->device, sdkp->zone_blocks));
+	sdkp->zone_shift = ilog2(sdkp->zone_blocks);
+	sdkp->nr_zones = sdkp->capacity >> sdkp->zone_shift;
+	if (sdkp->capacity & (sdkp->zone_blocks - 1))
+		sdkp->nr_zones++;
+
+	if (!sdkp->zones_wlock) {
+		sdkp->zones_wlock = kcalloc(BITS_TO_LONGS(sdkp->nr_zones),
+					    sizeof(unsigned long),
+					    GFP_KERNEL);
+		if (!sdkp->zones_wlock)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int sd_zbc_read_zones(struct scsi_disk *sdkp,
+		      unsigned char *buf)
+{
+	sector_t capacity;
+	int ret = 0;
+
+	if (!sd_is_zoned(sdkp))
+		/*
+		 * Device managed or normal SCSI disk,
+		 * no special handling required
+		 */
+		return 0;
+
+
+	/* Get zoned block device characteristics */
+	ret = sd_zbc_read_zoned_characteristics(sdkp, buf);
+	if (ret)
+		goto err;
+
+	/*
+	 * Check for unconstrained reads: host-managed devices with
+	 * constrained reads (drives failing read after write pointer)
+	 * are not supported.
+	 */
+	if (!sdkp->urswrz) {
+		if (sdkp->first_scan)
+			sd_printk(KERN_NOTICE, sdkp,
+			  "constrained reads devices are not supported\n");
+		ret = -ENODEV;
+		goto err;
+	}
+
+	/* Check capacity */
+	ret = sd_zbc_check_capacity(sdkp, buf);
+	if (ret)
+		goto err;
+	capacity = logical_to_sectors(sdkp->device, sdkp->capacity);
+
+	/*
+	 * Check zone size: only devices with a constant zone size (except
+	 * an eventual last runt zone) that is a power of 2 are supported.
+	 */
+	ret = sd_zbc_check_zone_size(sdkp);
+	if (ret)
+		goto err;
+
+	/* The drive satisfies the kernel restrictions: set it up */
+	ret = sd_zbc_setup(sdkp);
+	if (ret)
+		goto err;
+
+	/* READ16/WRITE16 is mandatory for ZBC disks */
+	sdkp->device->use_16_for_rw = 1;
+	sdkp->device->use_10_for_rw = 0;
+
+	return 0;
+
+err:
+	sdkp->capacity = 0;
+
+	return ret;
+}
+
+void sd_zbc_remove(struct scsi_disk *sdkp)
+{
+	kfree(sdkp->zones_wlock);
+	sdkp->zones_wlock = NULL;
+}
+
+void sd_zbc_print_zones(struct scsi_disk *sdkp)
+{
+	if (!sd_is_zoned(sdkp) || !sdkp->capacity)
+		return;
+
+	if (sdkp->capacity & (sdkp->zone_blocks - 1))
+		sd_printk(KERN_NOTICE, sdkp,
+			  "%u zones of %u logical blocks + 1 runt zone\n",
+			  sdkp->nr_zones - 1,
+			  sdkp->zone_blocks);
+	else
+		sd_printk(KERN_NOTICE, sdkp,
+			  "%u zones of %u logical blocks\n",
+			  sdkp->nr_zones,
+			  sdkp->zone_blocks);
+}
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 070332eb41f3..dbe5b4b95df0 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -581,6 +581,9 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	sg_io_hdr_t *hp;
 	unsigned char cmnd[SG_MAX_CDB_SIZE];
 
+	if (unlikely(segment_eq(get_fs(), KERNEL_DS)))
+		return -EINVAL;
+
 	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
 		return -ENXIO;
 	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
diff --git a/drivers/scsi/smartpqi/smartpqi.h b/drivers/scsi/smartpqi/smartpqi.h
index 07b6444d3e0a..b673825f46b5 100644
--- a/drivers/scsi/smartpqi/smartpqi.h
+++ b/drivers/scsi/smartpqi/smartpqi.h
@@ -929,8 +929,6 @@ struct pqi_ctrl_info {
 	int		max_msix_vectors;
 	int		num_msix_vectors_enabled;
 	int		num_msix_vectors_initialized;
-	u32		msix_vectors[PQI_MAX_MSIX_VECTORS];
-	void		*intr_data[PQI_MAX_MSIX_VECTORS];
 	int		event_irq;
 	struct Scsi_Host *scsi_host;
 
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index a535b2661f38..8702d9cf8040 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -25,6 +25,7 @@
 #include <linux/rtc.h>
 #include <linux/bcd.h>
 #include <linux/cciss_ioctl.h>
+#include <linux/blk-mq-pci.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
@@ -2887,19 +2888,19 @@ static irqreturn_t pqi_irq_handler(int irq, void *data)
 
 static int pqi_request_irqs(struct pqi_ctrl_info *ctrl_info)
 {
+	struct pci_dev *pdev = ctrl_info->pci_dev;
 	int i;
 	int rc;
 
-	ctrl_info->event_irq = ctrl_info->msix_vectors[0];
+	ctrl_info->event_irq = pci_irq_vector(pdev, 0);
 
 	for (i = 0; i < ctrl_info->num_msix_vectors_enabled; i++) {
-		rc = request_irq(ctrl_info->msix_vectors[i],
-			pqi_irq_handler, 0,
-			DRIVER_NAME_SHORT, ctrl_info->intr_data[i]);
+		rc = request_irq(pci_irq_vector(pdev, i), pqi_irq_handler, 0,
+			DRIVER_NAME_SHORT, &ctrl_info->queue_groups[i]);
 		if (rc) {
-			dev_err(&ctrl_info->pci_dev->dev,
+			dev_err(&pdev->dev,
 				"irq %u init failed with error %d\n",
-				ctrl_info->msix_vectors[i], rc);
+				pci_irq_vector(pdev, i), rc);
 			return rc;
 		}
 		ctrl_info->num_msix_vectors_initialized++;
@@ -2908,72 +2909,23 @@ static int pqi_request_irqs(struct pqi_ctrl_info *ctrl_info)
 	return 0;
 }
 
-static void pqi_free_irqs(struct pqi_ctrl_info *ctrl_info)
-{
-	int i;
-
-	for (i = 0; i < ctrl_info->num_msix_vectors_initialized; i++)
-		free_irq(ctrl_info->msix_vectors[i],
-			ctrl_info->intr_data[i]);
-}
-
 static int pqi_enable_msix_interrupts(struct pqi_ctrl_info *ctrl_info)
 {
-	unsigned int i;
-	int max_vectors;
-	int num_vectors_enabled;
-	struct msix_entry msix_entries[PQI_MAX_MSIX_VECTORS];
-
-	max_vectors = ctrl_info->num_queue_groups;
-
-	for (i = 0; i < max_vectors; i++)
-		msix_entries[i].entry = i;
-
-	num_vectors_enabled = pci_enable_msix_range(ctrl_info->pci_dev,
-		msix_entries, PQI_MIN_MSIX_VECTORS, max_vectors);
+	int ret;
 
-	if (num_vectors_enabled < 0) {
+	ret = pci_alloc_irq_vectors(ctrl_info->pci_dev,
+			PQI_MIN_MSIX_VECTORS, ctrl_info->num_queue_groups,
+			PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
+	if (ret < 0) {
 		dev_err(&ctrl_info->pci_dev->dev,
-			"MSI-X init failed with error %d\n",
-			num_vectors_enabled);
-		return num_vectors_enabled;
-	}
-
-	ctrl_info->num_msix_vectors_enabled = num_vectors_enabled;
-	for (i = 0; i < num_vectors_enabled; i++) {
-		ctrl_info->msix_vectors[i] = msix_entries[i].vector;
-		ctrl_info->intr_data[i] = &ctrl_info->queue_groups[i];
+			"MSI-X init failed with error %d\n", ret);
+		return ret;
 	}
 
+	ctrl_info->num_msix_vectors_enabled = ret;
 	return 0;
 }
 
-static void pqi_irq_set_affinity_hint(struct pqi_ctrl_info *ctrl_info)
-{
-	int i;
-	int rc;
-	int cpu;
-
-	cpu = cpumask_first(cpu_online_mask);
-	for (i = 0; i < ctrl_info->num_msix_vectors_initialized; i++) {
-		rc = irq_set_affinity_hint(ctrl_info->msix_vectors[i],
-			get_cpu_mask(cpu));
-		if (rc)
-			dev_err(&ctrl_info->pci_dev->dev,
-				"error %d setting affinity hint for irq vector %u\n",
-				rc, ctrl_info->msix_vectors[i]);
-		cpu = cpumask_next(cpu, cpu_online_mask);
-	}
-}
-
-static void pqi_irq_unset_affinity_hint(struct pqi_ctrl_info *ctrl_info)
-{
-	int i;
-
-	for (i = 0; i < ctrl_info->num_msix_vectors_initialized; i++)
-		irq_set_affinity_hint(ctrl_info->msix_vectors[i], NULL);
-}
-
 static int pqi_alloc_operational_queues(struct pqi_ctrl_info *ctrl_info)
 {
 	unsigned int i;
@@ -4743,6 +4695,13 @@ static int pqi_slave_configure(struct scsi_device *sdev)
 	return 0;
 }
 
+static int pqi_map_queues(struct Scsi_Host *shost)
+{
+	struct pqi_ctrl_info *ctrl_info = shost_to_hba(shost);
+
+	return blk_mq_pci_map_queues(&shost->tag_set, ctrl_info->pci_dev);
+}
+
 static int pqi_getpciinfo_ioctl(struct pqi_ctrl_info *ctrl_info,
 	void __user *arg)
 {
@@ -5130,6 +5089,7 @@ static struct scsi_host_template pqi_driver_template = {
 	.ioctl = pqi_ioctl,
 	.slave_alloc = pqi_slave_alloc,
 	.slave_configure = pqi_slave_configure,
+	.map_queues = pqi_map_queues,
 	.sdev_attrs = pqi_sdev_attrs,
 	.shost_attrs = pqi_shost_attrs,
 };
@@ -5159,7 +5119,7 @@ static int pqi_register_scsi(struct pqi_ctrl_info *ctrl_info)
 	shost->cmd_per_lun = shost->can_queue;
 	shost->sg_tablesize = ctrl_info->sg_tablesize;
 	shost->transportt = pqi_sas_transport_template;
-	shost->irq = ctrl_info->msix_vectors[0];
+	shost->irq = pci_irq_vector(ctrl_info->pci_dev, 0);
 	shost->unique_id = shost->irq;
 	shost->nr_hw_queues = ctrl_info->num_queue_groups;
 	shost->hostdata[0] = (unsigned long)ctrl_info;
@@ -5409,8 +5369,6 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
 	if (rc)
 		return rc;
 
-	pqi_irq_set_affinity_hint(ctrl_info);
-
 	rc = pqi_create_queues(ctrl_info);
 	if (rc)
 		return rc;
@@ -5557,10 +5515,14 @@ static inline void pqi_free_ctrl_info(struct pqi_ctrl_info *ctrl_info)
 
 static void pqi_free_interrupts(struct pqi_ctrl_info *ctrl_info)
 {
-	pqi_irq_unset_affinity_hint(ctrl_info);
-	pqi_free_irqs(ctrl_info);
-	if (ctrl_info->num_msix_vectors_enabled)
-		pci_disable_msix(ctrl_info->pci_dev);
+	int i;
+
+	for (i = 0; i < ctrl_info->num_msix_vectors_initialized; i++) {
+		free_irq(pci_irq_vector(ctrl_info->pci_dev, i),
+				&ctrl_info->queue_groups[i]);
+	}
+
+	pci_free_irq_vectors(ctrl_info->pci_dev);
 }
 
 static void pqi_free_ctrl_resources(struct pqi_ctrl_info *ctrl_info)
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index bed2bbd6b923..94352e4df831 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -46,7 +46,7 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_dbg.h>
diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
index 03054c0e7689..dfffdf63e44c 100644
--- a/drivers/scsi/sr_ioctl.c
+++ b/drivers/scsi/sr_ioctl.c
@@ -10,7 +10,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_dbg.h>
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 618422ea3a41..5f35b863e1a7 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -41,7 +41,7 @@ static const char *verstr = "20160209";
 #include <linux/delay.h>
 #include <linux/mutex.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/dma.h>
 
 #include <scsi/scsi.h>
@@ -546,7 +546,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
 		return DRIVER_ERROR << 24;
 
 	blk_rq_set_block_pc(req);
-	req->cmd_flags |= REQ_QUIET;
+	req->rq_flags |= RQF_QUIET;
 
 	mdata->null_mapped = 1;
 
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 8ccfc9ea874b..05526b71541b 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1495,9 +1495,9 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	if (sg_count) {
 		if (sg_count > MAX_PAGE_BUFFER_COUNT) {
 
-			payload_sz = (sg_count * sizeof(void *) +
+			payload_sz = (sg_count * sizeof(u64) +
 				      sizeof(struct vmbus_packet_mpb_array));
-			payload = kmalloc(payload_sz, GFP_ATOMIC);
+			payload = kzalloc(payload_sz, GFP_ATOMIC);
 			if (!payload)
 				return SCSI_MLQUEUE_DEVICE_BUSY;
 		}
diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c
index 3c4c07038948..88db6992420e 100644
--- a/drivers/scsi/sun3_scsi.c
+++ b/drivers/scsi/sun3_scsi.c
@@ -43,20 +43,18 @@
 
 #define NCR5380_implementation_fields   /* none */
 
-#define NCR5380_read(reg)               sun3scsi_read(reg)
-#define NCR5380_write(reg, value)       sun3scsi_write(reg, value)
+#define NCR5380_read(reg)               in_8(hostdata->io + (reg))
+#define NCR5380_write(reg, value)       out_8(hostdata->io + (reg), value)
 
 #define NCR5380_queue_command           sun3scsi_queue_command
 #define NCR5380_bus_reset               sun3scsi_bus_reset
 #define NCR5380_abort                   sun3scsi_abort
 #define NCR5380_info                    sun3scsi_info
 
-#define NCR5380_dma_recv_setup(instance, data, count) (count)
-#define NCR5380_dma_send_setup(instance, data, count) (count)
-#define NCR5380_dma_residual(instance) \
-        sun3scsi_dma_residual(instance)
-#define NCR5380_dma_xfer_len(instance, cmd, phase) \
-        sun3scsi_dma_xfer_len(cmd->SCp.this_residual, cmd)
+#define NCR5380_dma_xfer_len            sun3scsi_dma_xfer_len
+#define NCR5380_dma_recv_setup          sun3scsi_dma_count
+#define NCR5380_dma_send_setup          sun3scsi_dma_count
+#define NCR5380_dma_residual            sun3scsi_dma_residual
 
 #define NCR5380_acquire_dma_irq(instance)    (1)
 #define NCR5380_release_dma_irq(instance)
@@ -82,7 +80,6 @@ module_param(setup_hostid, int, 0);
 #define SUN3_DVMA_BUFSIZE 0xe000
 
 static struct scsi_cmnd *sun3_dma_setup_done;
-static unsigned char *sun3_scsi_regp;
 static volatile struct sun3_dma_regs *dregs;
 static struct sun3_udc_regs *udc_regs;
 static unsigned char *sun3_dma_orig_addr;
@@ -90,20 +87,6 @@ static unsigned long sun3_dma_orig_count;
 static int sun3_dma_active;
 static unsigned long last_residual;
 
-/*
- * NCR 5380 register access functions
- */
-
-static inline unsigned char sun3scsi_read(int reg)
-{
-	return in_8(sun3_scsi_regp + reg);
-}
-
-static inline void sun3scsi_write(int reg, int value)
-{
-	out_8(sun3_scsi_regp + reg, value);
-}
-
 #ifndef SUN3_SCSI_VME
 /* dma controller register access functions */
 
@@ -158,8 +141,8 @@ static irqreturn_t scsi_sun3_intr(int irq, void *dev)
 }
 
 /* sun3scsi_dma_setup() -- initialize the dma controller for a read/write */
-static unsigned long sun3scsi_dma_setup(struct Scsi_Host *instance,
-                                void *data, unsigned long count, int write_flag)
+static int sun3scsi_dma_setup(struct NCR5380_hostdata *hostdata,
+                              unsigned char *data, int count, int write_flag)
 {
 	void *addr;
 
@@ -211,9 +194,10 @@ static unsigned long sun3scsi_dma_setup(struct Scsi_Host *instance,
 	dregs->csr |= CSR_FIFO;
 	
 	if(dregs->fifo_count != count) { 
-		shost_printk(KERN_ERR, instance, "FIFO mismatch %04x not %04x\n",
+		shost_printk(KERN_ERR, hostdata->host,
+		             "FIFO mismatch %04x not %04x\n",
 		             dregs->fifo_count, (unsigned int) count);
-		NCR5380_dprint(NDEBUG_DMA, instance);
+		NCR5380_dprint(NDEBUG_DMA, hostdata->host);
 	}
 
 	/* setup udc */
@@ -248,14 +232,34 @@ static unsigned long sun3scsi_dma_setup(struct Scsi_Host *instance,
 
 }
 
-static inline unsigned long sun3scsi_dma_residual(struct Scsi_Host *instance)
+static int sun3scsi_dma_count(struct NCR5380_hostdata *hostdata,
+                              unsigned char *data, int count)
+{
+	return count;
+}
+
+static inline int sun3scsi_dma_recv_setup(struct NCR5380_hostdata *hostdata,
+                                          unsigned char *data, int count)
+{
+	return sun3scsi_dma_setup(hostdata, data, count, 0);
+}
+
+static inline int sun3scsi_dma_send_setup(struct NCR5380_hostdata *hostdata,
+                                          unsigned char *data, int count)
+{
+	return sun3scsi_dma_setup(hostdata, data, count, 1);
+}
+
+static int sun3scsi_dma_residual(struct NCR5380_hostdata *hostdata)
 {
 	return last_residual;
 }
 
-static inline unsigned long sun3scsi_dma_xfer_len(unsigned long wanted_len,
-                                                  struct scsi_cmnd *cmd)
+static int sun3scsi_dma_xfer_len(struct NCR5380_hostdata *hostdata,
+                                 struct scsi_cmnd *cmd)
 {
+	int wanted_len = cmd->SCp.this_residual;
+
 	if (wanted_len < DMA_MIN_SIZE || cmd->request->cmd_type != REQ_TYPE_FS)
 		return 0;
 
@@ -428,9 +432,10 @@ static struct scsi_host_template sun3_scsi_template = {
 static int __init sun3_scsi_probe(struct platform_device *pdev)
 {
 	struct Scsi_Host *instance;
+	struct NCR5380_hostdata *hostdata;
 	int error;
 	struct resource *irq, *mem;
-	unsigned char *ioaddr;
+	void __iomem *ioaddr;
 	int host_flags = 0;
 #ifdef SUN3_SCSI_VME
 	int i;
@@ -493,8 +498,6 @@ static int __init sun3_scsi_probe(struct platform_device *pdev)
 	}
 #endif
 
-	sun3_scsi_regp = ioaddr;
-
 	instance = scsi_host_alloc(&sun3_scsi_template,
 	                           sizeof(struct NCR5380_hostdata));
 	if (!instance) {
@@ -502,9 +505,12 @@ static int __init sun3_scsi_probe(struct platform_device *pdev)
 		goto fail_alloc;
 	}
 
-	instance->io_port = (unsigned long)ioaddr;
 	instance->irq = irq->start;
 
+	hostdata = shost_priv(instance);
+	hostdata->base = mem->start;
+	hostdata->io = ioaddr;
+
 	error = NCR5380_init(instance, host_flags);
 	if (error)
 		goto fail_init;
@@ -552,13 +558,15 @@ fail_init:
 fail_alloc:
 	if (udc_regs)
 		dvma_free(udc_regs);
-	iounmap(sun3_scsi_regp);
+	iounmap(ioaddr);
 	return error;
 }
 
 static int __exit sun3_scsi_remove(struct platform_device *pdev)
 {
 	struct Scsi_Host *instance = platform_get_drvdata(pdev);
+	struct NCR5380_hostdata *hostdata = shost_priv(instance);
+	void __iomem *ioaddr = hostdata->io;
 
 	scsi_remove_host(instance);
 	free_irq(instance->irq, instance);
@@ -566,7 +574,7 @@ static int __exit sun3_scsi_remove(struct platform_device *pdev)
 	scsi_host_put(instance);
 	if (udc_regs)
 		dvma_free(udc_regs);
-	iounmap(sun3_scsi_regp);
+	iounmap(ioaddr);
 	return 0;
 }
 
diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c
index 3aedf73f1131..abe617372661 100644
--- a/drivers/scsi/ufs/ufs-qcom.c
+++ b/drivers/scsi/ufs/ufs-qcom.c
@@ -23,6 +23,7 @@
 #include "unipro.h"
 #include "ufs-qcom.h"
 #include "ufshci.h"
+#include "ufs_quirks.h"
 #define UFS_QCOM_DEFAULT_DBG_PRINT_EN	\
 	(UFS_QCOM_DBG_PRINT_REGS_EN | UFS_QCOM_DBG_PRINT_TEST_BUS_EN)
 
@@ -1031,6 +1032,34 @@ out:
 	return ret;
 }
 
+static int ufs_qcom_quirk_host_pa_saveconfigtime(struct ufs_hba *hba)
+{
+	int err;
+	u32 pa_vs_config_reg1;
+
+	err = ufshcd_dme_get(hba, UIC_ARG_MIB(PA_VS_CONFIG_REG1),
+			     &pa_vs_config_reg1);
+	if (err)
+		goto out;
+
+	/* Allow extension of MSB bits of PA_SaveConfigTime attribute */
+	err = ufshcd_dme_set(hba, UIC_ARG_MIB(PA_VS_CONFIG_REG1),
+			    (pa_vs_config_reg1 | (1 << 12)));
+
+out:
+	return err;
+}
+
+static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba)
+{
+	int err = 0;
+
+	if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME)
+		err = ufs_qcom_quirk_host_pa_saveconfigtime(hba);
+
+	return err;
+}
+
 static u32 ufs_qcom_get_ufs_hci_version(struct ufs_hba *hba)
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
@@ -1094,10 +1123,12 @@ static void ufs_qcom_set_caps(struct ufs_hba *hba)
  * ufs_qcom_setup_clocks - enables/disable clocks
  * @hba: host controller instance
  * @on: If true, enable clocks else disable them.
+ * @status: PRE_CHANGE or POST_CHANGE notify
  *
  * Returns 0 on success, non-zero on failure.
  */
-static int ufs_qcom_setup_clocks(struct ufs_hba *hba, bool on)
+static int ufs_qcom_setup_clocks(struct ufs_hba *hba, bool on,
+				 enum ufs_notify_change_status status)
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
 	int err;
@@ -1111,18 +1142,9 @@ static int ufs_qcom_setup_clocks(struct ufs_hba *hba, bool on)
 	if (!host)
 		return 0;
 
-	if (on) {
-		err = ufs_qcom_phy_enable_iface_clk(host->generic_phy);
-		if (err)
-			goto out;
+	if (on && (status == POST_CHANGE)) {
+		phy_power_on(host->generic_phy);
 
-		err = ufs_qcom_phy_enable_ref_clk(host->generic_phy);
-		if (err) {
-			dev_err(hba->dev, "%s enable phy ref clock failed, err=%d\n",
-				__func__, err);
-			ufs_qcom_phy_disable_iface_clk(host->generic_phy);
-			goto out;
-		}
 		/* enable the device ref clock for HS mode*/
 		if (ufshcd_is_hs_mode(&hba->pwr_info))
 			ufs_qcom_dev_ref_clk_ctrl(host, true);
@@ -1130,14 +1152,15 @@ static int ufs_qcom_setup_clocks(struct ufs_hba *hba, bool on)
 		if (vote == host->bus_vote.min_bw_vote)
 			ufs_qcom_update_bus_bw_vote(host);
 
-	} else {
-
-		/* M-PHY RMMI interface clocks can be turned off */
-		ufs_qcom_phy_disable_iface_clk(host->generic_phy);
-		if (!ufs_qcom_is_link_active(hba))
+	} else if (!on && (status == PRE_CHANGE)) {
+		if (!ufs_qcom_is_link_active(hba)) {
 			/* disable device ref_clk */
 			ufs_qcom_dev_ref_clk_ctrl(host, false);
 
+			/* powering off PHY during aggressive clk gating */
+			phy_power_off(host->generic_phy);
+		}
+
 		vote = host->bus_vote.min_bw_vote;
 	}
 
@@ -1146,7 +1169,6 @@ static int ufs_qcom_setup_clocks(struct ufs_hba *hba, bool on)
 		dev_err(hba->dev, "%s: set bus vote failed %d\n",
 				__func__, err);
 
-out:
 	return err;
 }
 
@@ -1201,15 +1223,24 @@ static int ufs_qcom_init(struct ufs_hba *hba)
 	 */
 	host->generic_phy = devm_phy_get(dev, "ufsphy");
 
-	if (IS_ERR(host->generic_phy)) {
+	if (host->generic_phy == ERR_PTR(-EPROBE_DEFER)) {
+		/*
+		 * UFS driver might be probed before the phy driver does.
+		 * In that case we would like to return EPROBE_DEFER code.
+		 */
+		err = -EPROBE_DEFER;
+		dev_warn(dev, "%s: required phy device. hasn't probed yet. err = %d\n",
+			__func__, err);
+		goto out_variant_clear;
+	} else if (IS_ERR(host->generic_phy)) {
 		err = PTR_ERR(host->generic_phy);
 		dev_err(dev, "%s: PHY get failed %d\n", __func__, err);
-		goto out;
+		goto out_variant_clear;
 	}
 
 	err = ufs_qcom_bus_register(host);
 	if (err)
-		goto out_host_free;
+		goto out_variant_clear;
 
 	ufs_qcom_get_controller_revision(hba, &host->hw_ver.major,
 		&host->hw_ver.minor, &host->hw_ver.step);
@@ -1254,7 +1285,7 @@ static int ufs_qcom_init(struct ufs_hba *hba)
 	ufs_qcom_set_caps(hba);
 	ufs_qcom_advertise_quirks(hba);
 
-	ufs_qcom_setup_clocks(hba, true);
+	ufs_qcom_setup_clocks(hba, true, POST_CHANGE);
 
 	if (hba->dev->id < MAX_UFS_QCOM_HOSTS)
 		ufs_qcom_hosts[hba->dev->id] = host;
@@ -1274,8 +1305,7 @@ out_disable_phy:
 	phy_power_off(host->generic_phy);
 out_unregister_bus:
 	phy_exit(host->generic_phy);
-out_host_free:
-	devm_kfree(dev, host);
+out_variant_clear:
 	ufshcd_set_variant(hba, NULL);
 out:
 	return err;
@@ -1287,6 +1317,7 @@ static void ufs_qcom_exit(struct ufs_hba *hba)
 
 	ufs_qcom_disable_lane_clks(host);
 	phy_power_off(host->generic_phy);
+	phy_exit(host->generic_phy);
 }
 
 static int ufs_qcom_set_dme_vs_core_clk_ctrl_clear_div(struct ufs_hba *hba,
@@ -1439,7 +1470,8 @@ static void ufs_qcom_print_hw_debug_reg_all(struct ufs_hba *hba,
 	reg = ufs_qcom_get_debug_reg_offset(host, UFS_UFS_DBG_RD_PRDT_RAM);
 	print_fn(hba, reg, 64, "UFS_UFS_DBG_RD_PRDT_RAM ", priv);
 
-	ufshcd_writel(hba, (reg & ~UFS_BIT(17)), REG_UFS_CFG1);
+	/* clear bit 17 - UTP_DBG_RAMS_EN */
+	ufshcd_rmwl(hba, UFS_BIT(17), 0, REG_UFS_CFG1);
 
 	reg = ufs_qcom_get_debug_reg_offset(host, UFS_DBG_RD_REG_UAWM);
 	print_fn(hba, reg, 4, "UFS_DBG_RD_REG_UAWM ", priv);
@@ -1616,6 +1648,7 @@ static struct ufs_hba_variant_ops ufs_hba_qcom_vops = {
 	.hce_enable_notify      = ufs_qcom_hce_enable_notify,
 	.link_startup_notify    = ufs_qcom_link_startup_notify,
 	.pwr_change_notify	= ufs_qcom_pwr_change_notify,
+	.apply_dev_quirks	= ufs_qcom_apply_dev_quirks,
 	.suspend		= ufs_qcom_suspend,
 	.resume			= ufs_qcom_resume,
 	.dbg_register_dump	= ufs_qcom_dump_dbg_regs,
diff --git a/drivers/scsi/ufs/ufs-qcom.h b/drivers/scsi/ufs/ufs-qcom.h
index a19307a57ce2..fe517cd7dac3 100644
--- a/drivers/scsi/ufs/ufs-qcom.h
+++ b/drivers/scsi/ufs/ufs-qcom.h
@@ -142,6 +142,7 @@ enum ufs_qcom_phy_init_type {
 	 UFS_QCOM_DBG_PRINT_TEST_BUS_EN)
 
 /* QUniPro Vendor specific attributes */
+#define PA_VS_CONFIG_REG1	0x9000
 #define DME_VS_CORE_CLK_CTRL	0xD002
 /* bit and mask definitions for DME_VS_CORE_CLK_CTRL attribute */
 #define DME_VS_CORE_CLK_CTRL_CORE_CLK_DIV_EN_BIT		BIT(8)
diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h
index 845b874e2977..8e6709a3fb6b 100644
--- a/drivers/scsi/ufs/ufs.h
+++ b/drivers/scsi/ufs/ufs.h
@@ -46,6 +46,7 @@
 #define QUERY_DESC_HDR_SIZE       2
 #define QUERY_OSF_SIZE            (GENERAL_UPIU_REQUEST_SIZE - \
 					(sizeof(struct utp_upiu_header)))
+#define RESPONSE_UPIU_SENSE_DATA_LENGTH	18
 
 #define UPIU_HEADER_DWORD(byte3, byte2, byte1, byte0)\
 			cpu_to_be32((byte3 << 24) | (byte2 << 16) |\
@@ -162,7 +163,7 @@ enum desc_header_offset {
 };
 
 enum ufs_desc_max_size {
-	QUERY_DESC_DEVICE_MAX_SIZE		= 0x1F,
+	QUERY_DESC_DEVICE_MAX_SIZE		= 0x40,
 	QUERY_DESC_CONFIGURAION_MAX_SIZE	= 0x90,
 	QUERY_DESC_UNIT_MAX_SIZE		= 0x23,
 	QUERY_DESC_INTERCONNECT_MAX_SIZE	= 0x06,
@@ -416,7 +417,7 @@ struct utp_cmd_rsp {
 	__be32 residual_transfer_count;
 	__be32 reserved[4];
 	__be16 sense_data_len;
-	u8 sense_data[18];
+	u8 sense_data[RESPONSE_UPIU_SENSE_DATA_LENGTH];
 };
 
 /**
diff --git a/drivers/scsi/ufs/ufs_quirks.h b/drivers/scsi/ufs/ufs_quirks.h
index 22f881e9253a..08b799d4efcc 100644
--- a/drivers/scsi/ufs/ufs_quirks.h
+++ b/drivers/scsi/ufs/ufs_quirks.h
@@ -128,26 +128,23 @@ struct ufs_dev_fix {
  */
 #define UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM	(1 << 6)
 
+/*
+ * Some UFS devices require host PA_TACTIVATE to be lower than device
+ * PA_TACTIVATE, enabling this quirk ensure this.
+ */
+#define UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE	(1 << 7)
+
+/*
+ * The max. value PA_SaveConfigTime is 250 (10us) but this is not enough for
+ * some vendors.
+ * Gear switch from PWM to HS may fail even with this max. PA_SaveConfigTime.
+ * Gear switch can be issued by host controller as an error recovery and any
+ * software delay will not help on this case so we need to increase
+ * PA_SaveConfigTime to >32us as per vendor recommendation.
+ */
+#define UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME	(1 << 8)
+
 struct ufs_hba;
 void ufs_advertise_fixup_device(struct ufs_hba *hba);
 
-static struct ufs_dev_fix ufs_fixups[] = {
-	/* UFS cards deviations table */
-	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
-		UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM),
-	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL, UFS_DEVICE_NO_VCCQ),
-	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
-		UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS),
-	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
-		UFS_DEVICE_NO_FASTAUTO),
-	UFS_FIX(UFS_VENDOR_TOSHIBA, UFS_ANY_MODEL,
-		UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM),
-	UFS_FIX(UFS_VENDOR_TOSHIBA, "THGLF2G9C8KBADG",
-		UFS_DEVICE_QUIRK_PA_TACTIVATE),
-	UFS_FIX(UFS_VENDOR_TOSHIBA, "THGLF2G9D8KBADG",
-		UFS_DEVICE_QUIRK_PA_TACTIVATE),
-	UFS_FIX(UFS_VENDOR_SKHYNIX, UFS_ANY_MODEL, UFS_DEVICE_NO_VCCQ),
-
-	END_FIX
-};
 #endif /* UFS_QUIRKS_H_ */
diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c
index d15eaa466c59..52b546fb509b 100644
--- a/drivers/scsi/ufs/ufshcd-pci.c
+++ b/drivers/scsi/ufs/ufshcd-pci.c
@@ -104,6 +104,7 @@ static void ufshcd_pci_remove(struct pci_dev *pdev)
 	pm_runtime_forbid(&pdev->dev);
 	pm_runtime_get_noresume(&pdev->dev);
 	ufshcd_remove(hba);
+	ufshcd_dealloc_host(hba);
 }
 
 /**
@@ -147,6 +148,7 @@ ufshcd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	err = ufshcd_init(hba, mmio_base, pdev->irq);
 	if (err) {
 		dev_err(&pdev->dev, "Initialization failed\n");
+		ufshcd_dealloc_host(hba);
 		return err;
 	}
 
diff --git a/drivers/scsi/ufs/ufshcd-pltfrm.c b/drivers/scsi/ufs/ufshcd-pltfrm.c
index db53f38da864..a72a4ba78125 100644
--- a/drivers/scsi/ufs/ufshcd-pltfrm.c
+++ b/drivers/scsi/ufs/ufshcd-pltfrm.c
@@ -163,7 +163,7 @@ static int ufshcd_populate_vreg(struct device *dev, const char *name,
 	if (ret) {
 		dev_err(dev, "%s: unable to find %s err %d\n",
 				__func__, prop_name, ret);
-		goto out_free;
+		goto out;
 	}
 
 	vreg->min_uA = 0;
@@ -185,9 +185,6 @@ static int ufshcd_populate_vreg(struct device *dev, const char *name,
 
 	goto out;
 
-out_free:
-	devm_kfree(dev, vreg);
-	vreg = NULL;
 out:
 	if (!ret)
 		*out_vreg = vreg;
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 05c745663c10..20e5e5fb048c 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -45,6 +45,8 @@
 #include "ufs_quirks.h"
 #include "unipro.h"
 
+#define UFSHCD_REQ_SENSE_SIZE	18
+
 #define UFSHCD_ENABLE_INTRS	(UTP_TRANSFER_REQ_COMPL |\
 				 UTP_TASK_REQ_COMPL |\
 				 UFSHCD_ERROR_MASK)
@@ -57,15 +59,9 @@
 #define NOP_OUT_TIMEOUT    30 /* msecs */
 
 /* Query request retries */
-#define QUERY_REQ_RETRIES 10
+#define QUERY_REQ_RETRIES 3
 /* Query request timeout */
-#define QUERY_REQ_TIMEOUT 30 /* msec */
-/*
- * Query request timeout for fDeviceInit flag
- * fDeviceInit query response time for some devices is too large that default
- * QUERY_REQ_TIMEOUT may not be enough for such devices.
- */
-#define QUERY_FDEVICEINIT_REQ_TIMEOUT 600 /* msec */
+#define QUERY_REQ_TIMEOUT 1500 /* 1.5 seconds */
 
 /* Task management command timeout */
 #define TM_CMD_TIMEOUT	100 /* msecs */
@@ -123,6 +119,7 @@ enum {
 	UFSHCD_STATE_RESET,
 	UFSHCD_STATE_ERROR,
 	UFSHCD_STATE_OPERATIONAL,
+	UFSHCD_STATE_EH_SCHEDULED,
 };
 
 /* UFSHCD error handling flags */
@@ -188,6 +185,30 @@ ufs_get_pm_lvl_to_link_pwr_state(enum ufs_pm_level lvl)
 	return ufs_pm_lvl_states[lvl].link_state;
 }
 
+static struct ufs_dev_fix ufs_fixups[] = {
+	/* UFS cards deviations table */
+	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
+		UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM),
+	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL, UFS_DEVICE_NO_VCCQ),
+	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
+		UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS),
+	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
+		UFS_DEVICE_NO_FASTAUTO),
+	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
+		UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE),
+	UFS_FIX(UFS_VENDOR_TOSHIBA, UFS_ANY_MODEL,
+		UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM),
+	UFS_FIX(UFS_VENDOR_TOSHIBA, "THGLF2G9C8KBADG",
+		UFS_DEVICE_QUIRK_PA_TACTIVATE),
+	UFS_FIX(UFS_VENDOR_TOSHIBA, "THGLF2G9D8KBADG",
+		UFS_DEVICE_QUIRK_PA_TACTIVATE),
+	UFS_FIX(UFS_VENDOR_SKHYNIX, UFS_ANY_MODEL, UFS_DEVICE_NO_VCCQ),
+	UFS_FIX(UFS_VENDOR_SKHYNIX, UFS_ANY_MODEL,
+		UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME),
+
+	END_FIX
+};
+
 static void ufshcd_tmc_handler(struct ufs_hba *hba);
 static void ufshcd_async_scan(void *data, async_cookie_t cookie);
 static int ufshcd_reset_and_restore(struct ufs_hba *hba);
@@ -291,10 +312,24 @@ int ufshcd_wait_for_register(struct ufs_hba *hba, u32 reg, u32 mask,
  */
 static inline u32 ufshcd_get_intr_mask(struct ufs_hba *hba)
 {
-	if (hba->ufs_version == UFSHCI_VERSION_10)
-		return INTERRUPT_MASK_ALL_VER_10;
-	else
-		return INTERRUPT_MASK_ALL_VER_11;
+	u32 intr_mask = 0;
+
+	switch (hba->ufs_version) {
+	case UFSHCI_VERSION_10:
+		intr_mask = INTERRUPT_MASK_ALL_VER_10;
+		break;
+	/* allow fall through */
+	case UFSHCI_VERSION_11:
+	case UFSHCI_VERSION_20:
+		intr_mask = INTERRUPT_MASK_ALL_VER_11;
+		break;
+	/* allow fall through */
+	case UFSHCI_VERSION_21:
+	default:
+		intr_mask = INTERRUPT_MASK_ALL_VER_21;
+	}
+
+	return intr_mask;
 }
 
 /**
@@ -598,6 +633,20 @@ static bool ufshcd_is_unipro_pa_params_tuning_req(struct ufs_hba *hba)
 		return false;
 }
 
+static void ufshcd_suspend_clkscaling(struct ufs_hba *hba)
+{
+	if (ufshcd_is_clkscaling_enabled(hba)) {
+		devfreq_suspend_device(hba->devfreq);
+		hba->clk_scaling.window_start_t = 0;
+	}
+}
+
+static void ufshcd_resume_clkscaling(struct ufs_hba *hba)
+{
+	if (ufshcd_is_clkscaling_enabled(hba))
+		devfreq_resume_device(hba->devfreq);
+}
+
 static void ufshcd_ungate_work(struct work_struct *work)
 {
 	int ret;
@@ -631,8 +680,7 @@ static void ufshcd_ungate_work(struct work_struct *work)
 		hba->clk_gating.is_suspended = false;
 	}
 unblock_reqs:
-	if (ufshcd_is_clkscaling_enabled(hba))
-		devfreq_resume_device(hba->devfreq);
+	ufshcd_resume_clkscaling(hba);
 	scsi_unblock_requests(hba->host);
 }
 
@@ -660,6 +708,21 @@ int ufshcd_hold(struct ufs_hba *hba, bool async)
 start:
 	switch (hba->clk_gating.state) {
 	case CLKS_ON:
+		/*
+		 * Wait for the ungate work to complete if in progress.
+		 * Though the clocks may be in ON state, the link could
+		 * still be in hibner8 state if hibern8 is allowed
+		 * during clock gating.
+		 * Make sure we exit hibern8 state also in addition to
+		 * clocks being ON.
+		 */
+		if (ufshcd_can_hibern8_during_gating(hba) &&
+		    ufshcd_is_link_hibern8(hba)) {
+			spin_unlock_irqrestore(hba->host->host_lock, flags);
+			flush_work(&hba->clk_gating.ungate_work);
+			spin_lock_irqsave(hba->host->host_lock, flags);
+			goto start;
+		}
 		break;
 	case REQ_CLKS_OFF:
 		if (cancel_delayed_work(&hba->clk_gating.gate_work)) {
@@ -709,7 +772,14 @@ static void ufshcd_gate_work(struct work_struct *work)
 	unsigned long flags;
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
-	if (hba->clk_gating.is_suspended) {
+	/*
+	 * In case you are here to cancel this work the gating state
+	 * would be marked as REQ_CLKS_ON. In this case save time by
+	 * skipping the gating work and exit after changing the clock
+	 * state to CLKS_ON.
+	 */
+	if (hba->clk_gating.is_suspended ||
+		(hba->clk_gating.state == REQ_CLKS_ON)) {
 		hba->clk_gating.state = CLKS_ON;
 		goto rel_lock;
 	}
@@ -731,10 +801,7 @@ static void ufshcd_gate_work(struct work_struct *work)
 		ufshcd_set_link_hibern8(hba);
 	}
 
-	if (ufshcd_is_clkscaling_enabled(hba)) {
-		devfreq_suspend_device(hba->devfreq);
-		hba->clk_scaling.window_start_t = 0;
-	}
+	ufshcd_suspend_clkscaling(hba);
 
 	if (!ufshcd_is_link_active(hba))
 		ufshcd_setup_clocks(hba, false);
@@ -863,7 +930,7 @@ static void ufshcd_clk_scaling_update_busy(struct ufs_hba *hba)
 	if (!hba->outstanding_reqs && scaling->is_busy_started) {
 		scaling->tot_busy_t += ktime_to_us(ktime_sub(ktime_get(),
 					scaling->busy_start_t));
-		scaling->busy_start_t = ktime_set(0, 0);
+		scaling->busy_start_t = 0;
 		scaling->is_busy_started = false;
 	}
 }
@@ -878,6 +945,8 @@ void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag)
 	ufshcd_clk_scaling_start_busy(hba);
 	__set_bit(task_tag, &hba->outstanding_reqs);
 	ufshcd_writel(hba, 1 << task_tag, REG_UTP_TRANSFER_REQ_DOOR_BELL);
+	/* Make sure that doorbell is committed immediately */
+	wmb();
 }
 
 /**
@@ -889,10 +958,14 @@ static inline void ufshcd_copy_sense_data(struct ufshcd_lrb *lrbp)
 	int len;
 	if (lrbp->sense_buffer &&
 	    ufshcd_get_rsp_upiu_data_seg_len(lrbp->ucd_rsp_ptr)) {
+		int len_to_copy;
+
 		len = be16_to_cpu(lrbp->ucd_rsp_ptr->sr.sense_data_len);
+		len_to_copy = min_t(int, RESPONSE_UPIU_SENSE_DATA_LENGTH, len);
+
 		memcpy(lrbp->sense_buffer,
 			lrbp->ucd_rsp_ptr->sr.sense_data,
-			min_t(int, len, SCSI_SENSE_BUFFERSIZE));
+			min_t(int, len_to_copy, UFSHCD_REQ_SENSE_SIZE));
 	}
 }
 
@@ -1088,7 +1161,7 @@ ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
  *
  * Returns 0 in case of success, non-zero value in case of failure
  */
-static int ufshcd_map_sg(struct ufshcd_lrb *lrbp)
+static int ufshcd_map_sg(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 {
 	struct ufshcd_sg_entry *prd_table;
 	struct scatterlist *sg;
@@ -1102,8 +1175,13 @@ static int ufshcd_map_sg(struct ufshcd_lrb *lrbp)
 		return sg_segments;
 
 	if (sg_segments) {
-		lrbp->utr_descriptor_ptr->prd_table_length =
-					cpu_to_le16((u16) (sg_segments));
+		if (hba->quirks & UFSHCD_QUIRK_PRDT_BYTE_GRAN)
+			lrbp->utr_descriptor_ptr->prd_table_length =
+				cpu_to_le16((u16)(sg_segments *
+					sizeof(struct ufshcd_sg_entry)));
+		else
+			lrbp->utr_descriptor_ptr->prd_table_length =
+				cpu_to_le16((u16) (sg_segments));
 
 		prd_table = (struct ufshcd_sg_entry *)lrbp->ucd_prdt_ptr;
 
@@ -1410,6 +1488,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	switch (hba->ufshcd_state) {
 	case UFSHCD_STATE_OPERATIONAL:
 		break;
+	case UFSHCD_STATE_EH_SCHEDULED:
 	case UFSHCD_STATE_RESET:
 		err = SCSI_MLQUEUE_HOST_BUSY;
 		goto out_unlock;
@@ -1457,7 +1536,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 
 	WARN_ON(lrbp->cmd);
 	lrbp->cmd = cmd;
-	lrbp->sense_bufflen = SCSI_SENSE_BUFFERSIZE;
+	lrbp->sense_bufflen = UFSHCD_REQ_SENSE_SIZE;
 	lrbp->sense_buffer = cmd->sense_buffer;
 	lrbp->task_tag = tag;
 	lrbp->lun = ufshcd_scsi_to_upiu_lun(cmd->device->lun);
@@ -1465,15 +1544,18 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 
 	ufshcd_comp_scsi_upiu(hba, lrbp);
 
-	err = ufshcd_map_sg(lrbp);
+	err = ufshcd_map_sg(hba, lrbp);
 	if (err) {
 		lrbp->cmd = NULL;
 		clear_bit_unlock(tag, &hba->lrb_in_use);
 		goto out;
 	}
+	/* Make sure descriptors are ready before ringing the doorbell */
+	wmb();
 
 	/* issue command to the controller */
 	spin_lock_irqsave(hba->host->host_lock, flags);
+	ufshcd_vops_setup_xfer_req(hba, tag, (lrbp->cmd ? true : false));
 	ufshcd_send_command(hba, tag);
 out_unlock:
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
@@ -1581,6 +1663,8 @@ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
 	time_left = wait_for_completion_timeout(hba->dev_cmd.complete,
 			msecs_to_jiffies(max_timeout));
 
+	/* Make sure descriptors are ready before ringing the doorbell */
+	wmb();
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	hba->dev_cmd.complete = NULL;
 	if (likely(time_left)) {
@@ -1683,6 +1767,7 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
 	/* Make sure descriptors are ready before ringing the doorbell */
 	wmb();
 	spin_lock_irqsave(hba->host->host_lock, flags);
+	ufshcd_vops_setup_xfer_req(hba, tag, (lrbp->cmd ? true : false));
 	ufshcd_send_command(hba, tag);
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
@@ -1789,9 +1874,6 @@ int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
 		goto out_unlock;
 	}
 
-	if (idn == QUERY_FLAG_IDN_FDEVICEINIT)
-		timeout = QUERY_FDEVICEINIT_REQ_TIMEOUT;
-
 	err = ufshcd_exec_dev_cmd(hba, DEV_CMD_TYPE_QUERY, timeout);
 
 	if (err) {
@@ -1861,8 +1943,8 @@ static int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode,
 	err = ufshcd_exec_dev_cmd(hba, DEV_CMD_TYPE_QUERY, QUERY_REQ_TIMEOUT);
 
 	if (err) {
-		dev_err(hba->dev, "%s: opcode 0x%.2x for idn %d failed, err = %d\n",
-				__func__, opcode, idn, err);
+		dev_err(hba->dev, "%s: opcode 0x%.2x for idn %d failed, index %d, err = %d\n",
+				__func__, opcode, idn, index, err);
 		goto out_unlock;
 	}
 
@@ -1961,8 +2043,8 @@ static int __ufshcd_query_descriptor(struct ufs_hba *hba,
 	err = ufshcd_exec_dev_cmd(hba, DEV_CMD_TYPE_QUERY, QUERY_REQ_TIMEOUT);
 
 	if (err) {
-		dev_err(hba->dev, "%s: opcode 0x%.2x for idn %d failed, err = %d\n",
-				__func__, opcode, idn, err);
+		dev_err(hba->dev, "%s: opcode 0x%.2x for idn %d failed, index %d, err = %d\n",
+				__func__, opcode, idn, index, err);
 		goto out_unlock;
 	}
 
@@ -2055,18 +2137,41 @@ static int ufshcd_read_desc_param(struct ufs_hba *hba,
 					desc_id, desc_index, 0, desc_buf,
 					&buff_len);
 
-	if (ret || (buff_len < ufs_query_desc_max_size[desc_id]) ||
-	    (desc_buf[QUERY_DESC_LENGTH_OFFSET] !=
-	     ufs_query_desc_max_size[desc_id])
-	    || (desc_buf[QUERY_DESC_DESC_TYPE_OFFSET] != desc_id)) {
-		dev_err(hba->dev, "%s: Failed reading descriptor. desc_id %d param_offset %d buff_len %d ret %d",
-			__func__, desc_id, param_offset, buff_len, ret);
-		if (!ret)
-			ret = -EINVAL;
+	if (ret) {
+		dev_err(hba->dev, "%s: Failed reading descriptor. desc_id %d, desc_index %d, param_offset %d, ret %d",
+			__func__, desc_id, desc_index, param_offset, ret);
 
 		goto out;
 	}
 
+	/* Sanity check */
+	if (desc_buf[QUERY_DESC_DESC_TYPE_OFFSET] != desc_id) {
+		dev_err(hba->dev, "%s: invalid desc_id %d in descriptor header",
+			__func__, desc_buf[QUERY_DESC_DESC_TYPE_OFFSET]);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * While reading variable size descriptors (like string descriptor),
+	 * some UFS devices may report the "LENGTH" (field in "Transaction
+	 * Specific fields" of Query Response UPIU) same as what was requested
+	 * in Query Request UPIU instead of reporting the actual size of the
+	 * variable size descriptor.
+	 * Although it's safe to ignore the "LENGTH" field for variable size
+	 * descriptors as we can always derive the length of the descriptor from
+	 * the descriptor header fields. Hence this change impose the length
+	 * match check only for fixed size descriptors (for which we always
+	 * request the correct size as part of Query Request UPIU).
+	 */
+	if ((desc_id != QUERY_DESC_IDN_STRING) &&
+	    (buff_len != desc_buf[QUERY_DESC_LENGTH_OFFSET])) {
+		dev_err(hba->dev, "%s: desc_buf length mismatch: buff_len %d, buff_len(desc_header) %d",
+			__func__, buff_len, desc_buf[QUERY_DESC_LENGTH_OFFSET]);
+		ret = -EINVAL;
+		goto out;
+	}
+
 	if (is_kmalloc)
 		memcpy(param_read_buf, &desc_buf[param_offset], param_size);
 out:
@@ -2088,7 +2193,18 @@ static inline int ufshcd_read_power_desc(struct ufs_hba *hba,
 					 u8 *buf,
 					 u32 size)
 {
-	return ufshcd_read_desc(hba, QUERY_DESC_IDN_POWER, 0, buf, size);
+	int err = 0;
+	int retries;
+
+	for (retries = QUERY_REQ_RETRIES; retries > 0; retries--) {
+		/* Read descriptor*/
+		err = ufshcd_read_desc(hba, QUERY_DESC_IDN_POWER, 0, buf, size);
+		if (!err)
+			break;
+		dev_dbg(hba->dev, "%s: error %d retrying\n", __func__, err);
+	}
+
+	return err;
 }
 
 int ufshcd_read_device_desc(struct ufs_hba *hba, u8 *buf, u32 size)
@@ -2320,12 +2436,21 @@ static void ufshcd_host_memory_configure(struct ufs_hba *hba)
 				cpu_to_le32(upper_32_bits(cmd_desc_element_addr));
 
 		/* Response upiu and prdt offset should be in double words */
-		utrdlp[i].response_upiu_offset =
+		if (hba->quirks & UFSHCD_QUIRK_PRDT_BYTE_GRAN) {
+			utrdlp[i].response_upiu_offset =
+				cpu_to_le16(response_offset);
+			utrdlp[i].prd_table_offset =
+				cpu_to_le16(prdt_offset);
+			utrdlp[i].response_upiu_length =
+				cpu_to_le16(ALIGNED_UPIU_SIZE);
+		} else {
+			utrdlp[i].response_upiu_offset =
 				cpu_to_le16((response_offset >> 2));
-		utrdlp[i].prd_table_offset =
+			utrdlp[i].prd_table_offset =
 				cpu_to_le16((prdt_offset >> 2));
-		utrdlp[i].response_upiu_length =
+			utrdlp[i].response_upiu_length =
 				cpu_to_le16(ALIGNED_UPIU_SIZE >> 2);
+		}
 
 		hba->lrb[i].utr_descriptor_ptr = (utrdlp + i);
 		hba->lrb[i].ucd_req_ptr =
@@ -2429,10 +2554,10 @@ int ufshcd_dme_set_attr(struct ufs_hba *hba, u32 attr_sel,
 				set, UIC_GET_ATTR_ID(attr_sel), mib_val, ret);
 	} while (ret && peer && --retries);
 
-	if (!retries)
+	if (ret)
 		dev_err(hba->dev, "%s: attr-id 0x%x val 0x%x failed %d retries\n",
-				set, UIC_GET_ATTR_ID(attr_sel), mib_val,
-				retries);
+			set, UIC_GET_ATTR_ID(attr_sel), mib_val,
+			UFS_UIC_COMMAND_RETRIES - retries);
 
 	return ret;
 }
@@ -2496,9 +2621,10 @@ int ufshcd_dme_get_attr(struct ufs_hba *hba, u32 attr_sel,
 				get, UIC_GET_ATTR_ID(attr_sel), ret);
 	} while (ret && peer && --retries);
 
-	if (!retries)
+	if (ret)
 		dev_err(hba->dev, "%s: attr-id 0x%x failed %d retries\n",
-				get, UIC_GET_ATTR_ID(attr_sel), retries);
+			get, UIC_GET_ATTR_ID(attr_sel),
+			UFS_UIC_COMMAND_RETRIES - retries);
 
 	if (mib_val && !ret)
 		*mib_val = uic_cmd.argument3;
@@ -2651,6 +2777,8 @@ static int __ufshcd_uic_hibern8_enter(struct ufs_hba *hba)
 	int ret;
 	struct uic_command uic_cmd = {0};
 
+	ufshcd_vops_hibern8_notify(hba, UIC_CMD_DME_HIBER_ENTER, PRE_CHANGE);
+
 	uic_cmd.command = UIC_CMD_DME_HIBER_ENTER;
 	ret = ufshcd_uic_pwr_ctrl(hba, &uic_cmd);
 
@@ -2664,7 +2792,9 @@ static int __ufshcd_uic_hibern8_enter(struct ufs_hba *hba)
 		 */
 		if (ufshcd_link_recovery(hba))
 			ret = -ENOLINK;
-	}
+	} else
+		ufshcd_vops_hibern8_notify(hba, UIC_CMD_DME_HIBER_ENTER,
+								POST_CHANGE);
 
 	return ret;
 }
@@ -2687,13 +2817,17 @@ static int ufshcd_uic_hibern8_exit(struct ufs_hba *hba)
 	struct uic_command uic_cmd = {0};
 	int ret;
 
+	ufshcd_vops_hibern8_notify(hba, UIC_CMD_DME_HIBER_EXIT, PRE_CHANGE);
+
 	uic_cmd.command = UIC_CMD_DME_HIBER_EXIT;
 	ret = ufshcd_uic_pwr_ctrl(hba, &uic_cmd);
 	if (ret) {
 		dev_err(hba->dev, "%s: hibern8 exit failed. ret = %d\n",
 			__func__, ret);
 		ret = ufshcd_link_recovery(hba);
-	}
+	} else
+		ufshcd_vops_hibern8_notify(hba, UIC_CMD_DME_HIBER_EXIT,
+								POST_CHANGE);
 
 	return ret;
 }
@@ -2725,8 +2859,8 @@ static int ufshcd_get_max_pwr_mode(struct ufs_hba *hba)
 	if (hba->max_pwr_info.is_valid)
 		return 0;
 
-	pwr_info->pwr_tx = FASTAUTO_MODE;
-	pwr_info->pwr_rx = FASTAUTO_MODE;
+	pwr_info->pwr_tx = FAST_MODE;
+	pwr_info->pwr_rx = FAST_MODE;
 	pwr_info->hs_rate = PA_HS_MODE_B;
 
 	/* Get the connected lane count */
@@ -2757,7 +2891,7 @@ static int ufshcd_get_max_pwr_mode(struct ufs_hba *hba)
 				__func__, pwr_info->gear_rx);
 			return -EINVAL;
 		}
-		pwr_info->pwr_rx = SLOWAUTO_MODE;
+		pwr_info->pwr_rx = SLOW_MODE;
 	}
 
 	ufshcd_dme_peer_get(hba, UIC_ARG_MIB(PA_MAXRXHSGEAR),
@@ -2770,7 +2904,7 @@ static int ufshcd_get_max_pwr_mode(struct ufs_hba *hba)
 				__func__, pwr_info->gear_tx);
 			return -EINVAL;
 		}
-		pwr_info->pwr_tx = SLOWAUTO_MODE;
+		pwr_info->pwr_tx = SLOW_MODE;
 	}
 
 	hba->max_pwr_info.is_valid = true;
@@ -3090,7 +3224,16 @@ static int ufshcd_link_startup(struct ufs_hba *hba)
 {
 	int ret;
 	int retries = DME_LINKSTARTUP_RETRIES;
+	bool link_startup_again = false;
+
+	/*
+	 * If UFS device isn't active then we will have to issue link startup
+	 * 2 times to make sure the device state move to active.
+	 */
+	if (!ufshcd_is_ufs_dev_active(hba))
+		link_startup_again = true;
 
+link_startup:
 	do {
 		ufshcd_vops_link_startup_notify(hba, PRE_CHANGE);
 
@@ -3116,6 +3259,12 @@ static int ufshcd_link_startup(struct ufs_hba *hba)
 		/* failed to get the link up... retire */
 		goto out;
 
+	if (link_startup_again) {
+		link_startup_again = false;
+		retries = DME_LINKSTARTUP_RETRIES;
+		goto link_startup;
+	}
+
 	if (hba->quirks & UFSHCD_QUIRK_BROKEN_LCC) {
 		ret = ufshcd_disable_device_tx_lcc(hba);
 		if (ret)
@@ -3181,16 +3330,24 @@ static void ufshcd_set_queue_depth(struct scsi_device *sdev)
 {
 	int ret = 0;
 	u8 lun_qdepth;
+	int retries;
 	struct ufs_hba *hba;
 
 	hba = shost_priv(sdev->host);
 
 	lun_qdepth = hba->nutrs;
-	ret = ufshcd_read_unit_desc_param(hba,
-					  ufshcd_scsi_to_upiu_lun(sdev->lun),
-					  UNIT_DESC_PARAM_LU_Q_DEPTH,
-					  &lun_qdepth,
-					  sizeof(lun_qdepth));
+	for (retries = QUERY_REQ_RETRIES; retries > 0; retries--) {
+		/* Read descriptor*/
+		ret = ufshcd_read_unit_desc_param(hba,
+				  ufshcd_scsi_to_upiu_lun(sdev->lun),
+				  UNIT_DESC_PARAM_LU_Q_DEPTH,
+				  &lun_qdepth,
+				  sizeof(lun_qdepth));
+		if (!ret || ret == -ENOTSUPP)
+			break;
+
+		dev_dbg(hba->dev, "%s: error %d retrying\n", __func__, ret);
+	}
 
 	/* Some WLUN doesn't support unit descriptor */
 	if (ret == -EOPNOTSUPP)
@@ -4097,6 +4254,17 @@ static void ufshcd_update_uic_error(struct ufs_hba *hba)
 {
 	u32 reg;
 
+	/* 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))
+		/*
+		 * 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__);
+
 	/* PA_INIT_ERROR is fatal and needs UIC reset */
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_DATA_LINK_LAYER);
 	if (reg & UIC_DATA_LINK_LAYER_ERROR_PA_INIT)
@@ -4158,7 +4326,7 @@ static void ufshcd_check_errors(struct ufs_hba *hba)
 			/* block commands from scsi mid-layer */
 			scsi_block_requests(hba->host);
 
-			hba->ufshcd_state = UFSHCD_STATE_ERROR;
+			hba->ufshcd_state = UFSHCD_STATE_EH_SCHEDULED;
 			schedule_work(&hba->eh_work);
 		}
 	}
@@ -4311,6 +4479,8 @@ static int ufshcd_issue_tm_cmd(struct ufs_hba *hba, int lun_id, int task_id,
 	task_req_upiup->input_param1 = cpu_to_be32(lun_id);
 	task_req_upiup->input_param2 = cpu_to_be32(task_id);
 
+	ufshcd_vops_setup_task_mgmt(hba, free_slot, tm_function);
+
 	/* send command to the controller */
 	__set_bit(free_slot, &hba->outstanding_tasks);
 
@@ -4318,6 +4488,8 @@ static int ufshcd_issue_tm_cmd(struct ufs_hba *hba, int lun_id, int task_id,
 	wmb();
 
 	ufshcd_writel(hba, 1 << free_slot, REG_UTP_TASK_REQ_DOOR_BELL);
+	/* Make sure that doorbell is committed immediately */
+	wmb();
 
 	spin_unlock_irqrestore(host->host_lock, flags);
 
@@ -4722,6 +4894,24 @@ out:
 	return icc_level;
 }
 
+static int ufshcd_set_icc_levels_attr(struct ufs_hba *hba, u32 icc_level)
+{
+	int ret = 0;
+	int retries;
+
+	for (retries = QUERY_REQ_RETRIES; retries > 0; retries--) {
+		/* write attribute */
+		ret = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR,
+			QUERY_ATTR_IDN_ACTIVE_ICC_LVL, 0, 0, &icc_level);
+		if (!ret)
+			break;
+
+		dev_dbg(hba->dev, "%s: failed with error %d\n", __func__, ret);
+	}
+
+	return ret;
+}
+
 static void ufshcd_init_icc_levels(struct ufs_hba *hba)
 {
 	int ret;
@@ -4742,9 +4932,8 @@ static void ufshcd_init_icc_levels(struct ufs_hba *hba)
 	dev_dbg(hba->dev, "%s: setting icc_level 0x%x",
 			__func__, hba->init_prefetch_data.icc_level);
 
-	ret = ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_WRITE_ATTR,
-		QUERY_ATTR_IDN_ACTIVE_ICC_LVL, 0, 0,
-		&hba->init_prefetch_data.icc_level);
+	ret = ufshcd_set_icc_levels_attr(hba,
+				 hba->init_prefetch_data.icc_level);
 
 	if (ret)
 		dev_err(hba->dev,
@@ -4965,6 +5154,76 @@ out:
 	return ret;
 }
 
+/**
+ * ufshcd_quirk_tune_host_pa_tactivate - Ensures that host PA_TACTIVATE is
+ * less than device PA_TACTIVATE time.
+ * @hba: per-adapter instance
+ *
+ * Some UFS devices require host PA_TACTIVATE to be lower than device
+ * PA_TACTIVATE, we need to enable UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE quirk
+ * for such devices.
+ *
+ * Returns zero on success, non-zero error value on failure.
+ */
+static int ufshcd_quirk_tune_host_pa_tactivate(struct ufs_hba *hba)
+{
+	int ret = 0;
+	u32 granularity, peer_granularity;
+	u32 pa_tactivate, peer_pa_tactivate;
+	u32 pa_tactivate_us, peer_pa_tactivate_us;
+	u8 gran_to_us_table[] = {1, 4, 8, 16, 32, 100};
+
+	ret = ufshcd_dme_get(hba, UIC_ARG_MIB(PA_GRANULARITY),
+				  &granularity);
+	if (ret)
+		goto out;
+
+	ret = ufshcd_dme_peer_get(hba, UIC_ARG_MIB(PA_GRANULARITY),
+				  &peer_granularity);
+	if (ret)
+		goto out;
+
+	if ((granularity < PA_GRANULARITY_MIN_VAL) ||
+	    (granularity > PA_GRANULARITY_MAX_VAL)) {
+		dev_err(hba->dev, "%s: invalid host PA_GRANULARITY %d",
+			__func__, granularity);
+		return -EINVAL;
+	}
+
+	if ((peer_granularity < PA_GRANULARITY_MIN_VAL) ||
+	    (peer_granularity > PA_GRANULARITY_MAX_VAL)) {
+		dev_err(hba->dev, "%s: invalid device PA_GRANULARITY %d",
+			__func__, peer_granularity);
+		return -EINVAL;
+	}
+
+	ret = ufshcd_dme_get(hba, UIC_ARG_MIB(PA_TACTIVATE), &pa_tactivate);
+	if (ret)
+		goto out;
+
+	ret = ufshcd_dme_peer_get(hba, UIC_ARG_MIB(PA_TACTIVATE),
+				  &peer_pa_tactivate);
+	if (ret)
+		goto out;
+
+	pa_tactivate_us = pa_tactivate * gran_to_us_table[granularity - 1];
+	peer_pa_tactivate_us = peer_pa_tactivate *
+			     gran_to_us_table[peer_granularity - 1];
+
+	if (pa_tactivate_us > peer_pa_tactivate_us) {
+		u32 new_peer_pa_tactivate;
+
+		new_peer_pa_tactivate = pa_tactivate_us /
+				      gran_to_us_table[peer_granularity - 1];
+		new_peer_pa_tactivate++;
+		ret = ufshcd_dme_peer_set(hba, UIC_ARG_MIB(PA_TACTIVATE),
+					  new_peer_pa_tactivate);
+	}
+
+out:
+	return ret;
+}
+
 static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
 {
 	if (ufshcd_is_unipro_pa_params_tuning_req(hba)) {
@@ -4975,6 +5234,11 @@ static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
 	if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_TACTIVATE)
 		/* set 1ms timeout for PA_TACTIVATE */
 		ufshcd_dme_set(hba, UIC_ARG_MIB(PA_TACTIVATE), 10);
+
+	if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE)
+		ufshcd_quirk_tune_host_pa_tactivate(hba);
+
+	ufshcd_vops_apply_dev_quirks(hba);
 }
 
 /**
@@ -5027,9 +5291,11 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 			__func__);
 	} else {
 		ret = ufshcd_config_pwr_mode(hba, &hba->max_pwr_info.info);
-		if (ret)
+		if (ret) {
 			dev_err(hba->dev, "%s: Failed setting power mode, err = %d\n",
 					__func__, ret);
+			goto out;
+		}
 	}
 
 	/* set the state as operational after switching to desired gear */
@@ -5062,8 +5328,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 		hba->is_init_prefetch = true;
 
 	/* Resume devfreq after UFS device is detected */
-	if (ufshcd_is_clkscaling_enabled(hba))
-		devfreq_resume_device(hba->devfreq);
+	ufshcd_resume_clkscaling(hba);
 
 out:
 	/*
@@ -5389,6 +5654,10 @@ static int __ufshcd_setup_clocks(struct ufs_hba *hba, bool on,
 	if (!head || list_empty(head))
 		goto out;
 
+	ret = ufshcd_vops_setup_clocks(hba, on, PRE_CHANGE);
+	if (ret)
+		return ret;
+
 	list_for_each_entry(clki, head, list) {
 		if (!IS_ERR_OR_NULL(clki->clk)) {
 			if (skip_ref_clk && !strcmp(clki->name, "ref_clk"))
@@ -5410,7 +5679,10 @@ static int __ufshcd_setup_clocks(struct ufs_hba *hba, bool on,
 		}
 	}
 
-	ret = ufshcd_vops_setup_clocks(hba, on);
+	ret = ufshcd_vops_setup_clocks(hba, on, POST_CHANGE);
+	if (ret)
+		return ret;
+
 out:
 	if (ret) {
 		list_for_each_entry(clki, head, list) {
@@ -5500,8 +5772,6 @@ static void ufshcd_variant_hba_exit(struct ufs_hba *hba)
 	if (!hba->vops)
 		return;
 
-	ufshcd_vops_setup_clocks(hba, false);
-
 	ufshcd_vops_setup_regulators(hba, false);
 
 	ufshcd_vops_exit(hba);
@@ -5564,6 +5834,7 @@ static void ufshcd_hba_exit(struct ufs_hba *hba)
 	if (hba->is_powered) {
 		ufshcd_variant_hba_exit(hba);
 		ufshcd_setup_vreg(hba, false);
+		ufshcd_suspend_clkscaling(hba);
 		ufshcd_setup_clocks(hba, false);
 		ufshcd_setup_hba_vreg(hba, false);
 		hba->is_powered = false;
@@ -5577,20 +5848,20 @@ ufshcd_send_request_sense(struct ufs_hba *hba, struct scsi_device *sdp)
 				0,
 				0,
 				0,
-				SCSI_SENSE_BUFFERSIZE,
+				UFSHCD_REQ_SENSE_SIZE,
 				0};
 	char *buffer;
 	int ret;
 
-	buffer = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
+	buffer = kzalloc(UFSHCD_REQ_SENSE_SIZE, GFP_KERNEL);
 	if (!buffer) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
 	ret = scsi_execute_req_flags(sdp, cmd, DMA_FROM_DEVICE, buffer,
-				SCSI_SENSE_BUFFERSIZE, NULL,
-				msecs_to_jiffies(1000), 3, NULL, REQ_PM);
+				UFSHCD_REQ_SENSE_SIZE, NULL,
+				msecs_to_jiffies(1000), 3, NULL, 0, RQF_PM);
 	if (ret)
 		pr_err("%s: failed with err %d\n", __func__, ret);
 
@@ -5652,11 +5923,11 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 
 	/*
 	 * Current function would be generally called from the power management
-	 * callbacks hence set the REQ_PM flag so that it doesn't resume the
+	 * callbacks hence set the RQF_PM flag so that it doesn't resume the
 	 * already suspended childs.
 	 */
 	ret = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0, &sshdr,
-				     START_STOP_TIMEOUT, 0, NULL, REQ_PM);
+				     START_STOP_TIMEOUT, 0, NULL, 0, RQF_PM);
 	if (ret) {
 		sdev_printk(KERN_WARNING, sdp,
 			    "START_STOP failed for power mode: %d, result %x\n",
@@ -5766,7 +6037,6 @@ static int ufshcd_vreg_set_hpm(struct ufs_hba *hba)
 	    !hba->dev_info.is_lu_power_on_wp) {
 		ret = ufshcd_setup_vreg(hba, true);
 	} else if (!ufshcd_is_ufs_dev_active(hba)) {
-		ret = ufshcd_toggle_vreg(hba->dev, hba->vreg_info.vcc, true);
 		if (!ret && !ufshcd_is_link_active(hba)) {
 			ret = ufshcd_config_vreg_hpm(hba, hba->vreg_info.vccq);
 			if (ret)
@@ -5775,6 +6045,7 @@ static int ufshcd_vreg_set_hpm(struct ufs_hba *hba)
 			if (ret)
 				goto vccq_lpm;
 		}
+		ret = ufshcd_toggle_vreg(hba->dev, hba->vreg_info.vcc, true);
 	}
 	goto out;
 
@@ -5839,6 +6110,8 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 	ufshcd_hold(hba, false);
 	hba->clk_gating.is_suspended = true;
 
+	ufshcd_suspend_clkscaling(hba);
+
 	if (req_dev_pwr_mode == UFS_ACTIVE_PWR_MODE &&
 			req_link_state == UIC_LINK_ACTIVE_STATE) {
 		goto disable_clks;
@@ -5846,12 +6119,12 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 
 	if ((req_dev_pwr_mode == hba->curr_dev_pwr_mode) &&
 	    (req_link_state == hba->uic_link_state))
-		goto out;
+		goto enable_gating;
 
 	/* UFS device & link must be active before we enter in this function */
 	if (!ufshcd_is_ufs_dev_active(hba) || !ufshcd_is_link_active(hba)) {
 		ret = -EINVAL;
-		goto out;
+		goto enable_gating;
 	}
 
 	if (ufshcd_is_runtime_pm(pm_op)) {
@@ -5888,15 +6161,6 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 
 disable_clks:
 	/*
-	 * The clock scaling needs access to controller registers. Hence, Wait
-	 * for pending clock scaling work to be done before clocks are
-	 * turned off.
-	 */
-	if (ufshcd_is_clkscaling_enabled(hba)) {
-		devfreq_suspend_device(hba->devfreq);
-		hba->clk_scaling.window_start_t = 0;
-	}
-	/*
 	 * Call vendor specific suspend callback. As these callbacks may access
 	 * vendor specific host controller register space call them before the
 	 * host clocks are ON.
@@ -5905,10 +6169,6 @@ disable_clks:
 	if (ret)
 		goto set_link_active;
 
-	ret = ufshcd_vops_setup_clocks(hba, false);
-	if (ret)
-		goto vops_resume;
-
 	if (!ufshcd_is_link_active(hba))
 		ufshcd_setup_clocks(hba, false);
 	else
@@ -5925,9 +6185,8 @@ disable_clks:
 	ufshcd_hba_vreg_set_lpm(hba);
 	goto out;
 
-vops_resume:
-	ufshcd_vops_resume(hba, pm_op);
 set_link_active:
+	ufshcd_resume_clkscaling(hba);
 	ufshcd_vreg_set_hpm(hba);
 	if (ufshcd_is_link_hibern8(hba) && !ufshcd_uic_hibern8_exit(hba))
 		ufshcd_set_link_active(hba);
@@ -5937,6 +6196,7 @@ set_dev_active:
 	if (!ufshcd_set_dev_pwr_mode(hba, UFS_ACTIVE_PWR_MODE))
 		ufshcd_disable_auto_bkops(hba);
 enable_gating:
+	ufshcd_resume_clkscaling(hba);
 	hba->clk_gating.is_suspended = false;
 	ufshcd_release(hba);
 out:
@@ -6015,8 +6275,7 @@ static int ufshcd_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 	ufshcd_urgent_bkops(hba);
 	hba->clk_gating.is_suspended = false;
 
-	if (ufshcd_is_clkscaling_enabled(hba))
-		devfreq_resume_device(hba->devfreq);
+	ufshcd_resume_clkscaling(hba);
 
 	/* Schedule clock gating in case of no access to UFS device yet */
 	ufshcd_release(hba);
@@ -6030,6 +6289,7 @@ disable_vreg:
 	ufshcd_vreg_set_lpm(hba);
 disable_irq_and_vops_clks:
 	ufshcd_disable_irq(hba);
+	ufshcd_suspend_clkscaling(hba);
 	ufshcd_setup_clocks(hba, false);
 out:
 	hba->pm_op_in_progress = 0;
@@ -6052,16 +6312,13 @@ int ufshcd_system_suspend(struct ufs_hba *hba)
 	if (!hba || !hba->is_powered)
 		return 0;
 
-	if (pm_runtime_suspended(hba->dev)) {
-		if (hba->rpm_lvl == hba->spm_lvl)
-			/*
-			 * There is possibility that device may still be in
-			 * active state during the runtime suspend.
-			 */
-			if ((ufs_get_pm_lvl_to_dev_pwr_mode(hba->spm_lvl) ==
-			    hba->curr_dev_pwr_mode) && !hba->auto_bkops_enabled)
-				goto out;
+	if ((ufs_get_pm_lvl_to_dev_pwr_mode(hba->spm_lvl) ==
+	     hba->curr_dev_pwr_mode) &&
+	    (ufs_get_pm_lvl_to_link_pwr_state(hba->spm_lvl) ==
+	     hba->uic_link_state))
+		goto out;
 
+	if (pm_runtime_suspended(hba->dev)) {
 		/*
 		 * UFS device and/or UFS link low power states during runtime
 		 * suspend seems to be different than what is expected during
@@ -6092,7 +6349,10 @@ EXPORT_SYMBOL(ufshcd_system_suspend);
 
 int ufshcd_system_resume(struct ufs_hba *hba)
 {
-	if (!hba || !hba->is_powered || pm_runtime_suspended(hba->dev))
+	if (!hba)
+		return -EINVAL;
+
+	if (!hba->is_powered || pm_runtime_suspended(hba->dev))
 		/*
 		 * Let the runtime resume take care of resuming
 		 * if runtime suspended.
@@ -6113,7 +6373,10 @@ EXPORT_SYMBOL(ufshcd_system_resume);
  */
 int ufshcd_runtime_suspend(struct ufs_hba *hba)
 {
-	if (!hba || !hba->is_powered)
+	if (!hba)
+		return -EINVAL;
+
+	if (!hba->is_powered)
 		return 0;
 
 	return ufshcd_suspend(hba, UFS_RUNTIME_PM);
@@ -6143,10 +6406,13 @@ EXPORT_SYMBOL(ufshcd_runtime_suspend);
  */
 int ufshcd_runtime_resume(struct ufs_hba *hba)
 {
-	if (!hba || !hba->is_powered)
+	if (!hba)
+		return -EINVAL;
+
+	if (!hba->is_powered)
 		return 0;
-	else
-		return ufshcd_resume(hba, UFS_RUNTIME_PM);
+
+	return ufshcd_resume(hba, UFS_RUNTIME_PM);
 }
 EXPORT_SYMBOL(ufshcd_runtime_resume);
 
@@ -6198,11 +6464,7 @@ void ufshcd_remove(struct ufs_hba *hba)
 	ufshcd_disable_intr(hba, hba->intr_mask);
 	ufshcd_hba_stop(hba, true);
 
-	scsi_host_put(hba->host);
-
 	ufshcd_exit_clk_gating(hba);
-	if (ufshcd_is_clkscaling_enabled(hba))
-		devfreq_remove_device(hba->devfreq);
 	ufshcd_hba_exit(hba);
 }
 EXPORT_SYMBOL_GPL(ufshcd_remove);
@@ -6324,15 +6586,47 @@ static int ufshcd_devfreq_target(struct device *dev,
 {
 	int err = 0;
 	struct ufs_hba *hba = dev_get_drvdata(dev);
+	bool release_clk_hold = false;
+	unsigned long irq_flags;
 
 	if (!ufshcd_is_clkscaling_enabled(hba))
 		return -EINVAL;
 
+	spin_lock_irqsave(hba->host->host_lock, irq_flags);
+	if (ufshcd_eh_in_progress(hba)) {
+		spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
+		return 0;
+	}
+
+	if (ufshcd_is_clkgating_allowed(hba) &&
+	    (hba->clk_gating.state != CLKS_ON)) {
+		if (cancel_delayed_work(&hba->clk_gating.gate_work)) {
+			/* hold the vote until the scaling work is completed */
+			hba->clk_gating.active_reqs++;
+			release_clk_hold = true;
+			hba->clk_gating.state = CLKS_ON;
+		} else {
+			/*
+			 * Clock gating work seems to be running in parallel
+			 * hence skip scaling work to avoid deadlock between
+			 * current scaling work and gating work.
+			 */
+			spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
+			return 0;
+		}
+	}
+	spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
+
 	if (*freq == UINT_MAX)
 		err = ufshcd_scale_clks(hba, true);
 	else if (*freq == 0)
 		err = ufshcd_scale_clks(hba, false);
 
+	spin_lock_irqsave(hba->host->host_lock, irq_flags);
+	if (release_clk_hold)
+		__ufshcd_release(hba);
+	spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
+
 	return err;
 }
 
@@ -6367,7 +6661,7 @@ start_window:
 		scaling->busy_start_t = ktime_get();
 		scaling->is_busy_started = true;
 	} else {
-		scaling->busy_start_t = ktime_set(0, 0);
+		scaling->busy_start_t = 0;
 		scaling->is_busy_started = false;
 	}
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
@@ -6413,6 +6707,13 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	/* Get UFS version supported by the controller */
 	hba->ufs_version = ufshcd_get_ufs_version(hba);
 
+	if ((hba->ufs_version != UFSHCI_VERSION_10) &&
+	    (hba->ufs_version != UFSHCI_VERSION_11) &&
+	    (hba->ufs_version != UFSHCI_VERSION_20) &&
+	    (hba->ufs_version != UFSHCI_VERSION_21))
+		dev_err(hba->dev, "invalid UFS version 0x%x\n",
+			hba->ufs_version);
+
 	/* Get Interrupt bit mask per version */
 	hba->intr_mask = ufshcd_get_intr_mask(hba);
 
@@ -6498,7 +6799,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	}
 
 	if (ufshcd_is_clkscaling_enabled(hba)) {
-		hba->devfreq = devfreq_add_device(dev, &ufs_devfreq_profile,
+		hba->devfreq = devm_devfreq_add_device(dev, &ufs_devfreq_profile,
 						   "simple_ondemand", NULL);
 		if (IS_ERR(hba->devfreq)) {
 			dev_err(hba->dev, "Unable to register with devfreq %ld\n",
@@ -6507,18 +6808,19 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 			goto out_remove_scsi_host;
 		}
 		/* Suspend devfreq until the UFS device is detected */
-		devfreq_suspend_device(hba->devfreq);
-		hba->clk_scaling.window_start_t = 0;
+		ufshcd_suspend_clkscaling(hba);
 	}
 
 	/* Hold auto suspend until async scan completes */
 	pm_runtime_get_sync(dev);
 
 	/*
-	 * The device-initialize-sequence hasn't been invoked yet.
-	 * Set the device to power-off state
+	 * We are assuming that device wasn't put in sleep/power-down
+	 * state exclusively during the boot stage before kernel.
+	 * This assumption helps avoid doing link startup twice during
+	 * ufshcd_probe_hba().
 	 */
-	ufshcd_set_ufs_dev_poweroff(hba);
+	ufshcd_set_ufs_dev_active(hba);
 
 	async_schedule(ufshcd_async_scan, hba);
 
@@ -6530,7 +6832,6 @@ exit_gating:
 	ufshcd_exit_clk_gating(hba);
 out_disable:
 	hba->is_irq_enabled = false;
-	scsi_host_put(host);
 	ufshcd_hba_exit(hba);
 out_error:
 	return err;
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 430bef111293..08cd26ed2382 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -261,6 +261,12 @@ struct ufs_pwr_mode_info {
  * @pwr_change_notify: called before and after a power mode change
  *			is carried out to allow vendor spesific capabilities
  *			to be set.
+ * @setup_xfer_req: called before any transfer request is issued
+ *                  to set some things
+ * @setup_task_mgmt: called before any task management request is issued
+ *                  to set some things
+ * @hibern8_notify: called around hibern8 enter/exit
+ * @apply_dev_quirks: called to apply device specific quirks
  * @suspend: called during host controller PM callback
  * @resume: called during host controller PM callback
  * @dbg_register_dump: used to dump controller debug information
@@ -273,7 +279,8 @@ struct ufs_hba_variant_ops {
 	u32	(*get_ufs_hci_version)(struct ufs_hba *);
 	int	(*clk_scale_notify)(struct ufs_hba *, bool,
 				    enum ufs_notify_change_status);
-	int	(*setup_clocks)(struct ufs_hba *, bool);
+	int	(*setup_clocks)(struct ufs_hba *, bool,
+				enum ufs_notify_change_status);
 	int     (*setup_regulators)(struct ufs_hba *, bool);
 	int	(*hce_enable_notify)(struct ufs_hba *,
 				     enum ufs_notify_change_status);
@@ -283,6 +290,11 @@ struct ufs_hba_variant_ops {
 					enum ufs_notify_change_status status,
 					struct ufs_pa_layer_attr *,
 					struct ufs_pa_layer_attr *);
+	void	(*setup_xfer_req)(struct ufs_hba *, int, bool);
+	void	(*setup_task_mgmt)(struct ufs_hba *, int, u8);
+	void    (*hibern8_notify)(struct ufs_hba *, enum uic_cmd_dme,
+					enum ufs_notify_change_status);
+	int	(*apply_dev_quirks)(struct ufs_hba *);
 	int     (*suspend)(struct ufs_hba *, enum ufs_pm_op);
 	int     (*resume)(struct ufs_hba *, enum ufs_pm_op);
 	void	(*dbg_register_dump)(struct ufs_hba *hba);
@@ -474,6 +486,12 @@ struct ufs_hba {
 	 */
 	#define UFSHCD_QUIRK_BROKEN_UFS_HCI_VERSION		UFS_BIT(5)
 
+	/*
+	 * This quirk needs to be enabled if the host contoller regards
+	 * resolution of the values of PRDTO and PRDTL in UTRD as byte.
+	 */
+	#define UFSHCD_QUIRK_PRDT_BYTE_GRAN			UFS_BIT(7)
+
 	unsigned int quirks;	/* Deviations from standard UFSHCI spec. */
 
 	/* Device deviations from standard UFS device spec. */
@@ -755,10 +773,11 @@ static inline int ufshcd_vops_clk_scale_notify(struct ufs_hba *hba,
 	return 0;
 }
 
-static inline int ufshcd_vops_setup_clocks(struct ufs_hba *hba, bool on)
+static inline int ufshcd_vops_setup_clocks(struct ufs_hba *hba, bool on,
+					enum ufs_notify_change_status status)
 {
 	if (hba->vops && hba->vops->setup_clocks)
-		return hba->vops->setup_clocks(hba, on);
+		return hba->vops->setup_clocks(hba, on, status);
 	return 0;
 }
 
@@ -799,6 +818,35 @@ static inline int ufshcd_vops_pwr_change_notify(struct ufs_hba *hba,
 	return -ENOTSUPP;
 }
 
+static inline void ufshcd_vops_setup_xfer_req(struct ufs_hba *hba, int tag,
+					bool is_scsi_cmd)
+{
+	if (hba->vops && hba->vops->setup_xfer_req)
+		return hba->vops->setup_xfer_req(hba, tag, is_scsi_cmd);
+}
+
+static inline void ufshcd_vops_setup_task_mgmt(struct ufs_hba *hba,
+					int tag, u8 tm_function)
+{
+	if (hba->vops && hba->vops->setup_task_mgmt)
+		return hba->vops->setup_task_mgmt(hba, tag, tm_function);
+}
+
+static inline void ufshcd_vops_hibern8_notify(struct ufs_hba *hba,
+					enum uic_cmd_dme cmd,
+					enum ufs_notify_change_status status)
+{
+	if (hba->vops && hba->vops->hibern8_notify)
+		return hba->vops->hibern8_notify(hba, cmd, status);
+}
+
+static inline int ufshcd_vops_apply_dev_quirks(struct ufs_hba *hba)
+{
+	if (hba->vops && hba->vops->apply_dev_quirks)
+		return hba->vops->apply_dev_quirks(hba);
+	return 0;
+}
+
 static inline int ufshcd_vops_suspend(struct ufs_hba *hba, enum ufs_pm_op op)
 {
 	if (hba->vops && hba->vops->suspend)
diff --git a/drivers/scsi/ufs/ufshci.h b/drivers/scsi/ufs/ufshci.h
index 9599741ff606..8c5190e2e1c9 100644
--- a/drivers/scsi/ufs/ufshci.h
+++ b/drivers/scsi/ufs/ufshci.h
@@ -72,6 +72,10 @@ enum {
 	REG_UIC_COMMAND_ARG_1			= 0x94,
 	REG_UIC_COMMAND_ARG_2			= 0x98,
 	REG_UIC_COMMAND_ARG_3			= 0x9C,
+	REG_UFS_CCAP				= 0x100,
+	REG_UFS_CRYPTOCAP			= 0x104,
+
+	UFSHCI_CRYPTO_REG_SPACE_SIZE		= 0x400,
 };
 
 /* Controller capability masks */
@@ -83,6 +87,8 @@ enum {
 	MASK_UIC_DME_TEST_MODE_SUPPORT		= 0x04000000,
 };
 
+#define UFS_MASK(mask, offset)		((mask) << (offset))
+
 /* UFS Version 08h */
 #define MINOR_VERSION_NUM_MASK		UFS_MASK(0xFFFF, 0)
 #define MAJOR_VERSION_NUM_MASK		UFS_MASK(0xFFFF, 16)
@@ -166,6 +172,7 @@ enum {
 /* UECPA - Host UIC Error Code PHY Adapter Layer 38h */
 #define UIC_PHY_ADAPTER_LAYER_ERROR			UFS_BIT(31)
 #define UIC_PHY_ADAPTER_LAYER_ERROR_CODE_MASK		0x1F
+#define UIC_PHY_ADAPTER_LAYER_LANE_ERR_MASK		0xF
 
 /* UECDL - Host UIC Error Code Data Link Layer 3Ch */
 #define UIC_DATA_LINK_LAYER_ERROR		UFS_BIT(31)
@@ -272,6 +279,9 @@ enum {
 
 	/* Interrupt disable mask for UFSHCI v1.1 */
 	INTERRUPT_MASK_ALL_VER_11	= 0x31FFF,
+
+	/* Interrupt disable mask for UFSHCI v2.1 */
+	INTERRUPT_MASK_ALL_VER_21	= 0x71FFF,
 };
 
 /*
diff --git a/drivers/scsi/ufs/unipro.h b/drivers/scsi/ufs/unipro.h
index eff8b5675575..23129d7b2678 100644
--- a/drivers/scsi/ufs/unipro.h
+++ b/drivers/scsi/ufs/unipro.h
@@ -123,6 +123,7 @@
 #define PA_MAXRXHSGEAR		0x1587
 #define PA_RXHSUNTERMCAP	0x15A5
 #define PA_RXLSTERMCAP		0x15A6
+#define PA_GRANULARITY		0x15AA
 #define PA_PACPREQTIMEOUT	0x1590
 #define PA_PACPREQEOBTIMEOUT	0x1591
 #define PA_HIBERN8TIME		0x15A7
@@ -158,6 +159,9 @@
 #define VS_DEBUGOMC		0xD09E
 #define VS_POWERSTATE		0xD083
 
+#define PA_GRANULARITY_MIN_VAL	1
+#define PA_GRANULARITY_MAX_VAL	6
+
 /* PHY Adapter Protocol Constants */
 #define PA_MAXDATALANES	4
 
diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c
index 9dc8687bf048..9aa1fe1fc939 100644
--- a/drivers/scsi/xen-scsifront.c
+++ b/drivers/scsi/xen-scsifront.c
@@ -79,10 +79,13 @@
 struct vscsifrnt_shadow {
 	/* command between backend and frontend */
 	unsigned char act;
+	uint8_t nr_segments;
 	uint16_t rqid;
+	uint16_t ref_rqid;
 
 	unsigned int nr_grants;		/* number of grants in gref[] */
 	struct scsiif_request_segment *sg;	/* scatter/gather elements */
+	struct scsiif_request_segment seg[VSCSIIF_SG_TABLESIZE];
 
 	/* Do reset or abort function. */
 	wait_queue_head_t wq_reset;	/* reset work queue           */
@@ -172,68 +175,90 @@ static void scsifront_put_rqid(struct vscsifrnt_info *info, uint32_t id)
 		scsifront_wake_up(info);
 }
 
-static struct vscsiif_request *scsifront_pre_req(struct vscsifrnt_info *info)
+static int scsifront_do_request(struct vscsifrnt_info *info,
+				struct vscsifrnt_shadow *shadow)
 {
 	struct vscsiif_front_ring *ring = &(info->ring);
 	struct vscsiif_request *ring_req;
+	struct scsi_cmnd *sc = shadow->sc;
 	uint32_t id;
+	int i, notify;
+
+	if (RING_FULL(&info->ring))
+		return -EBUSY;
 
 	id = scsifront_get_rqid(info);	/* use id in response */
 	if (id >= VSCSIIF_MAX_REQS)
-		return NULL;
+		return -EBUSY;
 
-	ring_req = RING_GET_REQUEST(&(info->ring), ring->req_prod_pvt);
+	info->shadow[id] = shadow;
+	shadow->rqid = id;
 
+	ring_req = RING_GET_REQUEST(&(info->ring), ring->req_prod_pvt);
 	ring->req_prod_pvt++;
 
-	ring_req->rqid = (uint16_t)id;
+	ring_req->rqid        = id;
+	ring_req->act         = shadow->act;
+	ring_req->ref_rqid    = shadow->ref_rqid;
+	ring_req->nr_segments = shadow->nr_segments;
 
-	return ring_req;
-}
+	ring_req->id      = sc->device->id;
+	ring_req->lun     = sc->device->lun;
+	ring_req->channel = sc->device->channel;
+	ring_req->cmd_len = sc->cmd_len;
 
-static void scsifront_do_request(struct vscsifrnt_info *info)
-{
-	struct vscsiif_front_ring *ring = &(info->ring);
-	int notify;
+	BUG_ON(sc->cmd_len > VSCSIIF_MAX_COMMAND_SIZE);
+
+	memcpy(ring_req->cmnd, sc->cmnd, sc->cmd_len);
+
+	ring_req->sc_data_direction   = (uint8_t)sc->sc_data_direction;
+	ring_req->timeout_per_command = sc->request->timeout / HZ;
+
+	for (i = 0; i < (shadow->nr_segments & ~VSCSIIF_SG_GRANT); i++)
+		ring_req->seg[i] = shadow->seg[i];
 
 	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(ring, notify);
 	if (notify)
 		notify_remote_via_irq(info->irq);
+
+	return 0;
 }
 
-static void scsifront_gnttab_done(struct vscsifrnt_info *info, uint32_t id)
+static void scsifront_gnttab_done(struct vscsifrnt_info *info,
+				  struct vscsifrnt_shadow *shadow)
 {
-	struct vscsifrnt_shadow *s = info->shadow[id];
 	int i;
 
-	if (s->sc->sc_data_direction == DMA_NONE)
+	if (shadow->sc->sc_data_direction == DMA_NONE)
 		return;
 
-	for (i = 0; i < s->nr_grants; i++) {
-		if (unlikely(gnttab_query_foreign_access(s->gref[i]) != 0)) {
+	for (i = 0; i < shadow->nr_grants; i++) {
+		if (unlikely(gnttab_query_foreign_access(shadow->gref[i]))) {
 			shost_printk(KERN_ALERT, info->host, KBUILD_MODNAME
 				     "grant still in use by backend\n");
 			BUG();
 		}
-		gnttab_end_foreign_access(s->gref[i], 0, 0UL);
+		gnttab_end_foreign_access(shadow->gref[i], 0, 0UL);
 	}
 
-	kfree(s->sg);
+	kfree(shadow->sg);
 }
 
 static void scsifront_cdb_cmd_done(struct vscsifrnt_info *info,
 				   struct vscsiif_response *ring_rsp)
 {
+	struct vscsifrnt_shadow *shadow;
 	struct scsi_cmnd *sc;
 	uint32_t id;
 	uint8_t sense_len;
 
 	id = ring_rsp->rqid;
-	sc = info->shadow[id]->sc;
+	shadow = info->shadow[id];
+	sc = shadow->sc;
 
 	BUG_ON(sc == NULL);
 
-	scsifront_gnttab_done(info, id);
+	scsifront_gnttab_done(info, shadow);
 	scsifront_put_rqid(info, id);
 
 	sc->result = ring_rsp->rslt;
@@ -366,7 +391,6 @@ static void scsifront_finish_all(struct vscsifrnt_info *info)
 
 static int map_data_for_request(struct vscsifrnt_info *info,
 				struct scsi_cmnd *sc,
-				struct vscsiif_request *ring_req,
 				struct vscsifrnt_shadow *shadow)
 {
 	grant_ref_t gref_head;
@@ -379,7 +403,6 @@ static int map_data_for_request(struct vscsifrnt_info *info,
 	struct scatterlist *sg;
 	struct scsiif_request_segment *seg;
 
-	ring_req->nr_segments = 0;
 	if (sc->sc_data_direction == DMA_NONE || !data_len)
 		return 0;
 
@@ -398,7 +421,7 @@ static int map_data_for_request(struct vscsifrnt_info *info,
 		if (!shadow->sg)
 			return -ENOMEM;
 	}
-	seg = shadow->sg ? : ring_req->seg;
+	seg = shadow->sg ? : shadow->seg;
 
 	err = gnttab_alloc_grant_references(seg_grants + data_grants,
 					    &gref_head);
@@ -423,9 +446,9 @@ static int map_data_for_request(struct vscsifrnt_info *info,
 				info->dev->otherend_id,
 				xen_page_to_gfn(page), 1);
 			shadow->gref[ref_cnt] = ref;
-			ring_req->seg[ref_cnt].gref   = ref;
-			ring_req->seg[ref_cnt].offset = (uint16_t)off;
-			ring_req->seg[ref_cnt].length = (uint16_t)bytes;
+			shadow->seg[ref_cnt].gref   = ref;
+			shadow->seg[ref_cnt].offset = (uint16_t)off;
+			shadow->seg[ref_cnt].length = (uint16_t)bytes;
 
 			page++;
 			len -= bytes;
@@ -473,44 +496,14 @@ static int map_data_for_request(struct vscsifrnt_info *info,
 	}
 
 	if (seg_grants)
-		ring_req->nr_segments = VSCSIIF_SG_GRANT | seg_grants;
+		shadow->nr_segments = VSCSIIF_SG_GRANT | seg_grants;
 	else
-		ring_req->nr_segments = (uint8_t)ref_cnt;
+		shadow->nr_segments = (uint8_t)ref_cnt;
 	shadow->nr_grants = ref_cnt;
 
 	return 0;
 }
 
-static struct vscsiif_request *scsifront_command2ring(
-		struct vscsifrnt_info *info, struct scsi_cmnd *sc,
-		struct vscsifrnt_shadow *shadow)
-{
-	struct vscsiif_request *ring_req;
-
-	memset(shadow, 0, sizeof(*shadow));
-
-	ring_req = scsifront_pre_req(info);
-	if (!ring_req)
-		return NULL;
-
-	info->shadow[ring_req->rqid] = shadow;
-	shadow->rqid = ring_req->rqid;
-
-	ring_req->id      = sc->device->id;
-	ring_req->lun     = sc->device->lun;
-	ring_req->channel = sc->device->channel;
-	ring_req->cmd_len = sc->cmd_len;
-
-	BUG_ON(sc->cmd_len > VSCSIIF_MAX_COMMAND_SIZE);
-
-	memcpy(ring_req->cmnd, sc->cmnd, sc->cmd_len);
-
-	ring_req->sc_data_direction   = (uint8_t)sc->sc_data_direction;
-	ring_req->timeout_per_command = sc->request->timeout / HZ;
-
-	return ring_req;
-}
-
 static int scsifront_enter(struct vscsifrnt_info *info)
 {
 	if (info->pause)
@@ -536,36 +529,25 @@ static int scsifront_queuecommand(struct Scsi_Host *shost,
 				  struct scsi_cmnd *sc)
 {
 	struct vscsifrnt_info *info = shost_priv(shost);
-	struct vscsiif_request *ring_req;
 	struct vscsifrnt_shadow *shadow = scsi_cmd_priv(sc);
 	unsigned long flags;
 	int err;
-	uint16_t rqid;
+
+	sc->result = 0;
+	memset(shadow, 0, sizeof(*shadow));
+
+	shadow->sc  = sc;
+	shadow->act = VSCSIIF_ACT_SCSI_CDB;
 
 	spin_lock_irqsave(shost->host_lock, flags);
 	if (scsifront_enter(info)) {
 		spin_unlock_irqrestore(shost->host_lock, flags);
 		return SCSI_MLQUEUE_HOST_BUSY;
 	}
-	if (RING_FULL(&info->ring))
-		goto busy;
-
-	ring_req = scsifront_command2ring(info, sc, shadow);
-	if (!ring_req)
-		goto busy;
-
-	sc->result = 0;
-
-	rqid = ring_req->rqid;
-	ring_req->act = VSCSIIF_ACT_SCSI_CDB;
 
-	shadow->sc  = sc;
-	shadow->act = VSCSIIF_ACT_SCSI_CDB;
-
-	err = map_data_for_request(info, sc, ring_req, shadow);
+	err = map_data_for_request(info, sc, shadow);
 	if (err < 0) {
 		pr_debug("%s: err %d\n", __func__, err);
-		scsifront_put_rqid(info, rqid);
 		scsifront_return(info);
 		spin_unlock_irqrestore(shost->host_lock, flags);
 		if (err == -ENOMEM)
@@ -575,7 +557,11 @@ static int scsifront_queuecommand(struct Scsi_Host *shost,
 		return 0;
 	}
 
-	scsifront_do_request(info);
+	if (scsifront_do_request(info, shadow)) {
+		scsifront_gnttab_done(info, shadow);
+		goto busy;
+	}
+
 	scsifront_return(info);
 	spin_unlock_irqrestore(shost->host_lock, flags);
 
@@ -598,26 +584,30 @@ static int scsifront_action_handler(struct scsi_cmnd *sc, uint8_t act)
 	struct Scsi_Host *host = sc->device->host;
 	struct vscsifrnt_info *info = shost_priv(host);
 	struct vscsifrnt_shadow *shadow, *s = scsi_cmd_priv(sc);
-	struct vscsiif_request *ring_req;
 	int err = 0;
 
-	shadow = kmalloc(sizeof(*shadow), GFP_NOIO);
+	shadow = kzalloc(sizeof(*shadow), GFP_NOIO);
 	if (!shadow)
 		return FAILED;
 
+	shadow->act = act;
+	shadow->rslt_reset = RSLT_RESET_WAITING;
+	shadow->sc = sc;
+	shadow->ref_rqid = s->rqid;
+	init_waitqueue_head(&shadow->wq_reset);
+
 	spin_lock_irq(host->host_lock);
 
 	for (;;) {
-		if (!RING_FULL(&info->ring)) {
-			ring_req = scsifront_command2ring(info, sc, shadow);
-			if (ring_req)
-				break;
-		}
-		if (err || info->pause) {
-			spin_unlock_irq(host->host_lock);
-			kfree(shadow);
-			return FAILED;
-		}
+		if (scsifront_enter(info))
+			goto fail;
+
+		if (!scsifront_do_request(info, shadow))
+			break;
+
+		scsifront_return(info);
+		if (err)
+			goto fail;
 		info->wait_ring_available = 1;
 		spin_unlock_irq(host->host_lock);
 		err = wait_event_interruptible(info->wq_sync,
@@ -625,22 +615,6 @@ static int scsifront_action_handler(struct scsi_cmnd *sc, uint8_t act)
 		spin_lock_irq(host->host_lock);
 	}
 
-	if (scsifront_enter(info)) {
-		spin_unlock_irq(host->host_lock);
-		return FAILED;
-	}
-
-	ring_req->act = act;
-	ring_req->ref_rqid = s->rqid;
-
-	shadow->act = act;
-	shadow->rslt_reset = RSLT_RESET_WAITING;
-	init_waitqueue_head(&shadow->wq_reset);
-
-	ring_req->nr_segments = 0;
-
-	scsifront_do_request(info);
-
 	spin_unlock_irq(host->host_lock);
 	err = wait_event_interruptible(shadow->wq_reset, shadow->wait_reset);
 	spin_lock_irq(host->host_lock);
@@ -659,6 +633,11 @@ static int scsifront_action_handler(struct scsi_cmnd *sc, uint8_t act)
 	scsifront_return(info);
 	spin_unlock_irq(host->host_lock);
 	return err;
+
+fail:
+	spin_unlock_irq(host->host_lock);
+	kfree(shadow);
+	return FAILED;
 }
 
 static int scsifront_eh_abort_handler(struct scsi_cmnd *sc)
@@ -1060,13 +1039,9 @@ static void scsifront_read_backend_params(struct xenbus_device *dev,
 					  struct vscsifrnt_info *info)
 {
 	unsigned int sg_grant, nr_segs;
-	int ret;
 	struct Scsi_Host *host = info->host;
 
-	ret = xenbus_scanf(XBT_NIL, dev->otherend, "feature-sg-grant", "%u",
-			   &sg_grant);
-	if (ret != 1)
-		sg_grant = 0;
+	sg_grant = xenbus_read_unsigned(dev->otherend, "feature-sg-grant", 0);
 	nr_segs = min_t(unsigned int, sg_grant, SG_ALL);
 	nr_segs = max_t(unsigned int, nr_segs, VSCSIIF_SG_TABLESIZE);
 	nr_segs = min_t(unsigned int, nr_segs,
author	Mauro Carvalho Chehab <mchehab@s-opensource.com>	2016-12-26 19:11:35 +0300
committer	Mauro Carvalho Chehab <mchehab@s-opensource.com>	2016-12-26 19:11:35 +0300
commit	bd361f5de2b338218c276d17a510701a16075deb (patch)
tree	e0d60ab13fd29d7a56131c9364c9b53baba4940a /drivers/scsi
parent	c739c0a7c3c2472d7562b8f802cdce44d2597c8b (diff)
parent	7ce7d89f48834cefece7804d38fc5d85382edf77 (diff)
download	linux-bd361f5de2b338218c276d17a510701a16075deb.tar.xz