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

Pull SCSI updates from James Bottomley:
 "This is mostly updates of the usual suspects: lpfc, qla2xxx, bnx2fc,
  qedf, hpsa, hisi_sas, smartpqi, cxlflash, aacraid, csiostor along with
  a host of minor and miscellaneous changes"

* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (276 commits)
  qla2xxx: Fix NVMe entry_type for iocb packet on BE system
  scsi: qla2xxx: avoid unused-function warning
  scsi: snic: fix a couple of spelling mistakes/typos
  scsi: qla2xxx: fix a bunch of typos and spelling mistakes
  scsi: lpfc: don't double count abort errors
  scsi: lpfc: spin_lock_irq() is not nestable
  scsi: hisi_sas: optimise DMA slot memory
  scsi: ibmvfc: constify dev_pm_ops structures.
  scsi: ibmvscsi: constify dev_pm_ops structures.
  scsi: cxlflash: Update debug prints in reset handlers
  scsi: cxlflash: Update send_tmf() parameters
  scsi: cxlflash: Avoid double free of character device
  scsi: Add STARGET_CREATED_REMOVE state to scsi_target_state
  scsi: ses: do not add a device to an enclosure if enclosure_add_links() fails.
  scsi: ufs: flush eh_work when eh_work scheduled.
  scsi: qla2xxx: Protect access to qpair members with qpair->qp_lock
  scsi: sun_esp: fix device reference leaks
  scsi: fnic: changing queue command to return result DID_IMM_RETRY when rport is init
  scsi: fnic: correct speed display and add support for 25,40 and 100G
  scsi: fnic: added timestamp reporting in fnic debug stats
  ...

Documentation/ioctl/ioctl-number.txt

@@ -326,7 +326,7 @@ Code  Seq#(hex)	Include File		Comments
 0xB5	00-0F	uapi/linux/rpmsg.h	<mailto:linux-remoteproc@vger.kernel.org>
 0xC0	00-0F	linux/usb/iowarrior.h
 0xCA	00-0F	uapi/misc/cxl.h
-0xCA	80-8F	uapi/scsi/cxlflash_ioctl.h
+0xCA	80-BF	uapi/scsi/cxlflash_ioctl.h
 0xCB	00-1F	CBM serial IEC bus	in development:
 					<mailto:michael.klein@puffin.lb.shuttle.de>
 0xCD	01	linux/reiserfs_fs.h

Documentation/powerpc/cxlflash.txt

@@ -124,8 +124,8 @@ Block library API
     http://github.com/open-power/capiflash
 
 
-CXL Flash Driver IOCTLs
-=======================
+CXL Flash Driver LUN IOCTLs
+===========================
 
     Users, such as the block library, that wish to interface with a flash
     device (LUN) via user space access need to use the services provided
@@ -257,6 +257,12 @@ DK_CXLFLASH_VLUN_RESIZE
     operating in the virtual mode and used to program a LUN translation
     table that the AFU references when provided with a resource handle.
 
+    This ioctl can return -EAGAIN if an AFU sync operation takes too long.
+    In addition to returning a failure to user, cxlflash will also schedule
+    an asynchronous AFU reset. Should the user choose to retry the operation,
+    it is expected to succeed. If this ioctl fails with -EAGAIN, the user
+    can either retry the operation or treat it as a failure.
+
 DK_CXLFLASH_RELEASE
 -------------------
     This ioctl is responsible for releasing a previously obtained
@@ -309,6 +315,12 @@ DK_CXLFLASH_VLUN_CLONE
     clone. This is to avoid a stale entry in the file descriptor table of the
     child process.
 
+    This ioctl can return -EAGAIN if an AFU sync operation takes too long.
+    In addition to returning a failure to user, cxlflash will also schedule
+    an asynchronous AFU reset. Should the user choose to retry the operation,
+    it is expected to succeed. If this ioctl fails with -EAGAIN, the user
+    can either retry the operation or treat it as a failure.
+
 DK_CXLFLASH_VERIFY
 ------------------
     This ioctl is used to detect various changes such as the capacity of
@@ -355,3 +367,63 @@ DK_CXLFLASH_MANAGE_LUN
     exclusive user space access (superpipe). In case a LUN is visible
     across multiple ports and adapters, this ioctl is used to uniquely
     identify each LUN by its World Wide Node Name (WWNN).
+
+
+CXL Flash Driver Host IOCTLs
+============================
+
+    Each host adapter instance that is supported by the cxlflash driver
+    has a special character device associated with it to enable a set of
+    host management function. These character devices are hosted in a
+    class dedicated for cxlflash and can be accessed via /dev/cxlflash/*.
+
+    Applications can be written to perform various functions using the
+    host ioctl APIs below.
+
+    The structure definitions for these IOCTLs are available in:
+    uapi/scsi/cxlflash_ioctl.h
+
+HT_CXLFLASH_LUN_PROVISION
+-------------------------
+    This ioctl is used to create and delete persistent LUNs on cxlflash
+    devices that lack an external LUN management interface. It is only
+    valid when used with AFUs that support the LUN provision capability.
+
+    When sufficient space is available, LUNs can be created by specifying
+    the target port to host the LUN and a desired size in 4K blocks. Upon
+    success, the LUN ID and WWID of the created LUN will be returned and
+    the SCSI bus can be scanned to detect the change in LUN topology. Note
+    that partial allocations are not supported. Should a creation fail due
+    to a space issue, the target port can be queried for its current LUN
+    geometry.
+
+    To remove a LUN, the device must first be disassociated from the Linux
+    SCSI subsystem. The LUN deletion can then be initiated by specifying a
+    target port and LUN ID. Upon success, the LUN geometry associated with
+    the port will be updated to reflect new number of provisioned LUNs and
+    available capacity.
+
+    To query the LUN geometry of a port, the target port is specified and
+    upon success, the following information is presented:
+
+        - Maximum number of provisioned LUNs allowed for the port
+        - Current number of provisioned LUNs for the port
+        - Maximum total capacity of provisioned LUNs for the port (4K blocks)
+        - Current total capacity of provisioned LUNs for the port (4K blocks)
+
+    With this information, the number of available LUNs and capacity can be
+    can be calculated.
+
+HT_CXLFLASH_AFU_DEBUG
+---------------------
+    This ioctl is used to debug AFUs by supporting a command pass-through
+    interface. It is only valid when used with AFUs that support the AFU
+    debug capability.
+
+    With exception of buffer management, AFU debug commands are opaque to
+    cxlflash and treated as pass-through. For debug commands that do require
+    data transfer, the user supplies an adequately sized data buffer and must
+    specify the data transfer direction with respect to the host. There is a
+    maximum transfer size of 256K imposed. Note that partial read completions
+    are not supported - when errors are experienced with a host read data
+    transfer, the data buffer is not copied back to the user.

drivers/hv/channel_mgmt.c

@@ -332,7 +332,6 @@ static struct vmbus_channel *alloc_channel(void)
 	if (!channel)
 		return NULL;
 
-	spin_lock_init(&channel->inbound_lock);
 	spin_lock_init(&channel->lock);
 
 	INIT_LIST_HEAD(&channel->sc_list);

drivers/misc/enclosure.c

@@ -375,6 +375,7 @@ int enclosure_add_device(struct enclosure_device *edev, int component,
 			 struct device *dev)
 {
 	struct enclosure_component *cdev;
+	int err;
 
 	if (!edev || component >= edev->components)
 		return -EINVAL;
@@ -384,12 +385,17 @@ int enclosure_add_device(struct enclosure_device *edev, int component,
 	if (cdev->dev == dev)
 		return -EEXIST;
 
-	if (cdev->dev)
+	if (cdev->dev) {
 		enclosure_remove_links(cdev);
-
-	put_device(cdev->dev);
+		put_device(cdev->dev);
+	}
 	cdev->dev = get_device(dev);
-	return enclosure_add_links(cdev);
+	err = enclosure_add_links(cdev);
+	if (err) {
+		put_device(cdev->dev);
+		cdev->dev = NULL;
+	}
+	return err;
 }
 EXPORT_SYMBOL_GPL(enclosure_add_device);
 

drivers/scsi/53c700.c

@@ -296,8 +296,8 @@ NCR_700_detect(struct scsi_host_template *tpnt,
 	if(tpnt->sdev_attrs == NULL)
 		tpnt->sdev_attrs = NCR_700_dev_attrs;
 
-	memory = dma_alloc_noncoherent(hostdata->dev, TOTAL_MEM_SIZE,
-				       &pScript, GFP_KERNEL);
+	memory = dma_alloc_attrs(hostdata->dev, TOTAL_MEM_SIZE, &pScript,
+				 GFP_KERNEL, DMA_ATTR_NON_CONSISTENT);
 	if(memory == NULL) {
 		printk(KERN_ERR "53c700: Failed to allocate memory for driver, detaching\n");
 		return NULL;
@@ -410,8 +410,8 @@ NCR_700_release(struct Scsi_Host *host)
 	struct NCR_700_Host_Parameters *hostdata = 
 		(struct NCR_700_Host_Parameters *)host->hostdata[0];
 
-	dma_free_noncoherent(hostdata->dev, TOTAL_MEM_SIZE,
-			       hostdata->script, hostdata->pScript);
+	dma_free_attrs(hostdata->dev, TOTAL_MEM_SIZE, hostdata->script,
+		       hostdata->pScript, DMA_ATTR_NON_CONSISTENT);
 	return 1;
 }
 

drivers/scsi/Kconfig

@@ -47,17 +47,6 @@ config SCSI_NETLINK
 	default	n
 	depends on NET
 
-config SCSI_MQ_DEFAULT
-	bool "SCSI: use blk-mq I/O path by default"
-	depends on SCSI
-	---help---
-	  This option enables the new blk-mq based I/O path for SCSI
-	  devices by default.  With the option the scsi_mod.use_blk_mq
-	  module/boot option defaults to Y, without it to N, but it can
-	  still be overridden either way.
-
-	  If unsure say N.
-
 config SCSI_PROC_FS
 	bool "legacy /proc/scsi/ support"
 	depends on SCSI && PROC_FS

drivers/scsi/aacraid/aachba.c

@@ -2071,20 +2071,15 @@ int aac_get_adapter_info(struct aac_dev* dev)
 		expose_physicals = 0;
 	}
 
-	if(dev->dac_support != 0) {
-		if (!pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(64)) &&
-			!pci_set_consistent_dma_mask(dev->pdev, DMA_BIT_MASK(64))) {
+	if (dev->dac_support) {
+		if (!pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(64))) {
 			if (!dev->in_reset)
-				printk(KERN_INFO"%s%d: 64 Bit DAC enabled\n",
-					dev->name, dev->id);
-		} else if (!pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(32)) &&
-			!pci_set_consistent_dma_mask(dev->pdev, DMA_BIT_MASK(32))) {
-			printk(KERN_INFO"%s%d: DMA mask set failed, 64 Bit DAC disabled\n",
-				dev->name, dev->id);
+				dev_info(&dev->pdev->dev, "64 Bit DAC enabled\n");
+		} else if (!pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(32))) {
+			dev_info(&dev->pdev->dev, "DMA mask set failed, 64 Bit DAC disabled\n");
 			dev->dac_support = 0;
 		} else {
-			printk(KERN_WARNING"%s%d: No suitable DMA available.\n",
-				dev->name, dev->id);
+			dev_info(&dev->pdev->dev, "No suitable DMA available\n");
 			rcode = -ENOMEM;
 		}
 	}

drivers/scsi/aacraid/aacraid.h

@@ -97,7 +97,7 @@ enum {
 #define	PMC_GLOBAL_INT_BIT0		0x00000001
 
 #ifndef AAC_DRIVER_BUILD
-# define AAC_DRIVER_BUILD 50792
+# define AAC_DRIVER_BUILD 50834
 # define AAC_DRIVER_BRANCH "-custom"
 #endif
 #define MAXIMUM_NUM_CONTAINERS	32
@@ -415,6 +415,7 @@ struct aac_ciss_identify_pd {
  * These macros convert from physical channels to virtual channels
  */
 #define CONTAINER_CHANNEL		(0)
+#define NATIVE_CHANNEL			(1)
 #define CONTAINER_TO_CHANNEL(cont)	(CONTAINER_CHANNEL)
 #define CONTAINER_TO_ID(cont)		(cont)
 #define CONTAINER_TO_LUN(cont)		(0)
@@ -423,7 +424,6 @@ struct aac_ciss_identify_pd {
 #define PMC_DEVICE_S6	0x28b
 #define PMC_DEVICE_S7	0x28c
 #define PMC_DEVICE_S8	0x28d
-#define PMC_DEVICE_S9	0x28f
 
 #define aac_phys_to_logical(x)  ((x)+1)
 #define aac_logical_to_phys(x)  ((x)?(x)-1:0)
@@ -2377,6 +2377,7 @@ struct revision
 #define SOFT_RESET_TIME			60
 
 
+
 struct aac_common
 {
 	/*
@@ -2487,7 +2488,9 @@ struct aac_hba_info {
 #define IOP_RESET_FW_FIB_DUMP		0x00000034
 #define IOP_RESET			0x00001000
 #define IOP_RESET_ALWAYS		0x00001001
-#define RE_INIT_ADAPTER			0x000000ee
+#define RE_INIT_ADAPTER		0x000000ee
+
+#define IOP_SRC_RESET_MASK		0x00000100
 
 /*
  *	Adapter Status Register
@@ -2512,6 +2515,7 @@ struct aac_hba_info {
 
 #define	SELF_TEST_FAILED		0x00000004
 #define	MONITOR_PANIC			0x00000020
+#define	KERNEL_BOOTING			0x00000040
 #define	KERNEL_UP_AND_RUNNING		0x00000080
 #define	KERNEL_PANIC			0x00000100
 #define	FLASH_UPD_PENDING		0x00002000
@@ -2684,6 +2688,18 @@ int aac_probe_container(struct aac_dev *dev, int cid);
 int _aac_rx_init(struct aac_dev *dev);
 int aac_rx_select_comm(struct aac_dev *dev, int comm);
 int aac_rx_deliver_producer(struct fib * fib);
+
+static inline int aac_is_src(struct aac_dev *dev)
+{
+	u16 device = dev->pdev->device;
+
+	if (device == PMC_DEVICE_S6 ||
+		device == PMC_DEVICE_S7 ||
+		device == PMC_DEVICE_S8)
+		return 1;
+	return 0;
+}
+
 char * get_container_type(unsigned type);
 extern int numacb;
 extern char aac_driver_version[];

drivers/scsi/aacraid/commctrl.c

@@ -668,7 +668,7 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 				goto cleanup;
 			}
 
-			p = kmalloc(sg_count[i], GFP_KERNEL|__GFP_DMA);
+			p = kmalloc(sg_count[i], GFP_KERNEL);
 			if (!p) {
 				rcode = -ENOMEM;
 				goto cleanup;
@@ -732,8 +732,8 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 					rcode = -EINVAL;
 					goto cleanup;
 				}
-				/* Does this really need to be GFP_DMA? */
-				p = kmalloc(sg_count[i], GFP_KERNEL|__GFP_DMA);
+
+				p = kmalloc(sg_count[i], GFP_KERNEL);
 				if(!p) {
 					dprintk((KERN_DEBUG"aacraid: Could not allocate SG buffer - size = %d buffer number %d of %d\n",
 					  sg_count[i], i, upsg->count));
@@ -788,8 +788,8 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 					rcode = -EINVAL;
 					goto cleanup;
 				}
-				/* Does this really need to be GFP_DMA? */
-				p = kmalloc(sg_count[i], GFP_KERNEL|__GFP_DMA);
+
+				p = kmalloc(sg_count[i], GFP_KERNEL);
 				if(!p) {
 					dprintk((KERN_DEBUG "aacraid: Could not allocate SG buffer - size = %d buffer number %d of %d\n",
 						sg_count[i], i, usg->count));
@@ -845,8 +845,7 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 					rcode = -EINVAL;
 					goto cleanup;
 				}
-				/* Does this really need to be GFP_DMA? */
-				p = kmalloc(sg_count[i], GFP_KERNEL|__GFP_DMA);
+				p = kmalloc(sg_count[i], GFP_KERNEL|GFP_DMA32);
 				if (!p) {
 					dprintk((KERN_DEBUG"aacraid: Could not allocate SG buffer - size = %d buffer number %d of %d\n",
 						sg_count[i], i, usg->count));
@@ -887,7 +886,7 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 					rcode = -EINVAL;
 					goto cleanup;
 				}
-				p = kmalloc(sg_count[i], GFP_KERNEL);
+				p = kmalloc(sg_count[i], GFP_KERNEL|GFP_DMA32);
 				if (!p) {
 					dprintk((KERN_DEBUG"aacraid: Could not allocate SG buffer - size = %d buffer number %d of %d\n",
 					  sg_count[i], i, upsg->count));
@@ -950,12 +949,15 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 			&((struct aac_native_hba *)srbfib->hw_fib_va)->resp.err;
 		struct aac_srb_reply reply;
 
+		memset(&reply, 0, sizeof(reply));
 		reply.status = ST_OK;
 		if (srbfib->flags & FIB_CONTEXT_FLAG_FASTRESP) {
 			/* fast response */
 			reply.srb_status = SRB_STATUS_SUCCESS;
 			reply.scsi_status = 0;
 			reply.data_xfer_length = byte_count;
+			reply.sense_data_size = 0;
+			memset(reply.sense_data, 0, AAC_SENSE_BUFFERSIZE);
 		} else {
 			reply.srb_status = err->service_response;
 			reply.scsi_status = err->status;
@@ -1019,6 +1021,7 @@ static int aac_get_hba_info(struct aac_dev *dev, void __user *arg)
 {
 	struct aac_hba_info hbainfo;
 
+	memset(&hbainfo, 0, sizeof(hbainfo));
 	hbainfo.adapter_number		= (u8) dev->id;
 	hbainfo.system_io_bus_number	= dev->pdev->bus->number;
 	hbainfo.device_number		= (dev->pdev->devfn >> 3);

drivers/scsi/aacraid/comminit.c

@@ -53,11 +53,8 @@ static inline int aac_is_msix_mode(struct aac_dev *dev)
 {
 	u32 status = 0;
 
-	if (dev->pdev->device == PMC_DEVICE_S6 ||
-		dev->pdev->device == PMC_DEVICE_S7 ||
-		dev->pdev->device == PMC_DEVICE_S8) {
+	if (aac_is_src(dev))
 		status = src_readl(dev, MUnit.OMR);
-	}
 	return (status & AAC_INT_MODE_MSIX);
 }
 
@@ -325,9 +322,7 @@ int aac_send_shutdown(struct aac_dev * dev)
 	/* FIB should be freed only after getting the response from the F/W */
 	if (status != -ERESTARTSYS)
 		aac_fib_free(fibctx);
-	if ((dev->pdev->device == PMC_DEVICE_S7 ||
-	     dev->pdev->device == PMC_DEVICE_S8 ||
-	     dev->pdev->device == PMC_DEVICE_S9) &&
+	if (aac_is_src(dev) &&
 	     dev->msi_enabled)
 		aac_set_intx_mode(dev);
 	return status;
@@ -583,9 +578,7 @@ struct aac_dev *aac_init_adapter(struct aac_dev *dev)
 		dev->max_fib_size = status[1] & 0xFFE0;
 		host->sg_tablesize = status[2] >> 16;
 		dev->sg_tablesize = status[2] & 0xFFFF;
-		if (dev->pdev->device == PMC_DEVICE_S7 ||
-		    dev->pdev->device == PMC_DEVICE_S8 ||
-		    dev->pdev->device == PMC_DEVICE_S9) {
+		if (aac_is_src(dev)) {
 			if (host->can_queue > (status[3] >> 16) -
 					AAC_NUM_MGT_FIB)
 				host->can_queue = (status[3] >> 16) -
@@ -604,10 +597,7 @@ struct aac_dev *aac_init_adapter(struct aac_dev *dev)
 			pr_warn("numacb=%d ignored\n", numacb);
 	}
 
-	if (dev->pdev->device == PMC_DEVICE_S6 ||
-	    dev->pdev->device == PMC_DEVICE_S7 ||
-	    dev->pdev->device == PMC_DEVICE_S8 ||
-	    dev->pdev->device == PMC_DEVICE_S9)
+	if (aac_is_src(dev))
 		aac_define_int_mode(dev);
 	/*
 	 *	Ok now init the communication subsystem

drivers/scsi/aacraid/commsup.c

@@ -803,11 +803,11 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback,
 		if (aac_check_eeh_failure(dev))
 			return -EFAULT;
 
-		/* Only set for first known interruptable command */
-		if (down_interruptible(&fibptr->event_wait)) {
+		fibptr->flags |= FIB_CONTEXT_FLAG_WAIT;
+		if (down_interruptible(&fibptr->event_wait))
 			fibptr->done = 2;
-			up(&fibptr->event_wait);
-		}
+		fibptr->flags &= ~(FIB_CONTEXT_FLAG_WAIT);
+
 		spin_lock_irqsave(&fibptr->event_lock, flags);
 		if ((fibptr->done == 0) || (fibptr->done == 2)) {
 			fibptr->done = 2; /* Tell interrupt we aborted */
@@ -1513,6 +1513,8 @@ static int _aac_reset_adapter(struct aac_dev *aac, int forced, u8 reset_type)
 	struct scsi_cmnd *command_list;
 	int jafo = 0;
 	int bled;
+	u64 dmamask;
+	int num_of_fibs = 0;
 
 	/*
 	 * Assumptions:
@@ -1546,10 +1548,20 @@ static int _aac_reset_adapter(struct aac_dev *aac, int forced, u8 reset_type)
 	/*
 	 *	Loop through the fibs, close the synchronous FIBS
 	 */
-	for (retval = 1, index = 0; index < (aac->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB); index++) {
+	retval = 1;
+	num_of_fibs = aac->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB;
+	for (index = 0; index <  num_of_fibs; index++) {
+
 		struct fib *fib = &aac->fibs[index];
-		if (!(fib->hw_fib_va->header.XferState & cpu_to_le32(NoResponseExpected | Async)) &&
-		  (fib->hw_fib_va->header.XferState & cpu_to_le32(ResponseExpected))) {
+		__le32 XferState = fib->hw_fib_va->header.XferState;
+		bool is_response_expected = false;
+
+		if (!(XferState & cpu_to_le32(NoResponseExpected | Async)) &&
+		   (XferState & cpu_to_le32(ResponseExpected)))
+			is_response_expected = true;
+
+		if (is_response_expected
+		  || fib->flags & FIB_CONTEXT_FLAG_WAIT) {
 			unsigned long flagv;
 			spin_lock_irqsave(&fib->event_lock, flagv);
 			up(&fib->event_wait);
@@ -1580,21 +1592,27 @@ static int _aac_reset_adapter(struct aac_dev *aac, int forced, u8 reset_type)
 	aac_free_irq(aac);
 	kfree(aac->fsa_dev);
 	aac->fsa_dev = NULL;
+
+	dmamask = DMA_BIT_MASK(32);
 	quirks = aac_get_driver_ident(index)->quirks;
-	if (quirks & AAC_QUIRK_31BIT) {
-		if (((retval = pci_set_dma_mask(aac->pdev, DMA_BIT_MASK(31)))) ||
-		  ((retval = pci_set_consistent_dma_mask(aac->pdev, DMA_BIT_MASK(31)))))
-			goto out;
-	} else {
-		if (((retval = pci_set_dma_mask(aac->pdev, DMA_BIT_MASK(32)))) ||
-		  ((retval = pci_set_consistent_dma_mask(aac->pdev, DMA_BIT_MASK(32)))))
-			goto out;
+	if (quirks & AAC_QUIRK_31BIT)
+		retval = pci_set_dma_mask(aac->pdev, dmamask);
+	else if (!(quirks & AAC_QUIRK_SRC))
+		retval = pci_set_dma_mask(aac->pdev, dmamask);
+	else
+		retval = pci_set_consistent_dma_mask(aac->pdev, dmamask);
+
+	if (quirks & AAC_QUIRK_31BIT && !retval) {
+		dmamask = DMA_BIT_MASK(31);
+		retval = pci_set_consistent_dma_mask(aac->pdev, dmamask);
 	}
+
+	if (retval)
+		goto out;
+
 	if ((retval = (*(aac_get_driver_ident(index)->init))(aac)))
 		goto out;
-	if (quirks & AAC_QUIRK_31BIT)
-		if ((retval = pci_set_dma_mask(aac->pdev, DMA_BIT_MASK(32))))
-			goto out;
+
 	if (jafo) {
 		aac->thread = kthread_run(aac_command_thread, aac, "%s",
 					  aac->name);
@@ -1768,8 +1786,6 @@ int aac_check_health(struct aac_dev * aac)
 	int BlinkLED;
 	unsigned long time_now, flagv = 0;
 	struct list_head * entry;
-	struct Scsi_Host * host;
-	int bled;
 
 	/* Extending the scope of fib_lock slightly to protect aac->in_reset */
 	if (spin_trylock_irqsave(&aac->fib_lock, flagv) == 0)
@@ -1881,19 +1897,6 @@ int aac_check_health(struct aac_dev * aac)
 
 	printk(KERN_ERR "%s: Host adapter BLINK LED 0x%x\n", aac->name, BlinkLED);
 
-	if (!aac_check_reset || ((aac_check_reset == 1) &&
-		(aac->supplement_adapter_info.supported_options2 &
-			AAC_OPTION_IGNORE_RESET)))
-		goto out;
-	host = aac->scsi_host_ptr;
-	if (aac->thread->pid != current->pid)
-		spin_lock_irqsave(host->host_lock, flagv);
-	bled = aac_check_reset != 1 ? 1 : 0;
-	_aac_reset_adapter(aac, bled, IOP_HWSOFT_RESET);
-	if (aac->thread->pid != current->pid)
-		spin_unlock_irqrestore(host->host_lock, flagv);
-	return BlinkLED;
-
 out:
 	aac->in_reset = 0;
 	return BlinkLED;
@@ -2483,7 +2486,7 @@ int aac_command_thread(void *data)
 		if ((time_before(next_check_jiffies,next_jiffies))
 		 && ((difference = next_check_jiffies - jiffies) <= 0)) {
 			next_check_jiffies = next_jiffies;
-			if (aac_check_health(dev) == 0) {
+			if (aac_adapter_check_health(dev) == 0) {
 				difference = ((long)(unsigned)check_interval)
 					   * HZ;
 				next_check_jiffies = jiffies + difference;
@@ -2496,7 +2499,7 @@ int aac_command_thread(void *data)
 			int ret;
 
 			/* Don't even try to talk to adapter if its sick */
-			ret = aac_check_health(dev);
+			ret = aac_adapter_check_health(dev);
 			if (ret || !dev->queues)
 				break;
 			next_check_jiffies = jiffies
@@ -2588,10 +2591,7 @@ void aac_free_irq(struct aac_dev *dev)
 	int cpu;
 
 	cpu = cpumask_first(cpu_online_mask);
-	if (dev->pdev->device == PMC_DEVICE_S6 ||
-	    dev->pdev->device == PMC_DEVICE_S7 ||
-	    dev->pdev->device == PMC_DEVICE_S8 ||
-	    dev->pdev->device == PMC_DEVICE_S9) {
+	if (aac_is_src(dev)) {
 		if (dev->max_msix > 1) {
 			for (i = 0; i < dev->max_msix; i++)
 				free_irq(pci_irq_vector(dev->pdev, i),

drivers/scsi/aacraid/linit.c

@@ -405,17 +405,23 @@ static int aac_slave_configure(struct scsi_device *sdev)
 	int chn, tid;
 	unsigned int depth = 0;
 	unsigned int set_timeout = 0;
+	bool set_qd_dev_type = false;
+	u8 devtype = 0;
 
 	chn = aac_logical_to_phys(sdev_channel(sdev));
 	tid = sdev_id(sdev);
-	if (chn < AAC_MAX_BUSES && tid < AAC_MAX_TARGETS &&
-		aac->hba_map[chn][tid].devtype == AAC_DEVTYPE_NATIVE_RAW) {
-		depth = aac->hba_map[chn][tid].qd_limit;
+	if (chn < AAC_MAX_BUSES && tid < AAC_MAX_TARGETS && aac->sa_firmware) {
+		devtype = aac->hba_map[chn][tid].devtype;
+
+		if (devtype == AAC_DEVTYPE_NATIVE_RAW)
+			depth = aac->hba_map[chn][tid].qd_limit;
+		else if (devtype == AAC_DEVTYPE_ARC_RAW)
+			set_qd_dev_type = true;
+
 		set_timeout = 1;
 		goto common_config;
 	}
 
-
 	if (aac->jbod && (sdev->type == TYPE_DISK))
 		sdev->removable = 1;
 
@@ -466,9 +472,26 @@ static int aac_slave_configure(struct scsi_device *sdev)
 			++num_lsu;
 
 		depth = (host->can_queue - num_one) / num_lsu;
+
+		if (sdev_channel(sdev) != NATIVE_CHANNEL)
+			goto common_config;
+
+		set_qd_dev_type = true;
+
 	}
 
 common_config:
+
+	/*
+	 * Check if SATA drive
+	 */
+	if (set_qd_dev_type) {
+		if (strncmp(sdev->vendor, "ATA", 3) == 0)
+			depth = 32;
+		else
+			depth = 64;
+	}
+
 	/*
 	 * Firmware has an individual device recovery time typically
 	 * of 35 seconds, give us a margin.
@@ -601,6 +624,56 @@ static int aac_ioctl(struct scsi_device *sdev, int cmd, void __user * arg)
 	return aac_do_ioctl(dev, cmd, arg);
 }
 
+static int get_num_of_incomplete_fibs(struct aac_dev *aac)
+{
+
+	unsigned long flags;
+	struct scsi_device *sdev = NULL;
+	struct Scsi_Host *shost = aac->scsi_host_ptr;
+	struct scsi_cmnd *scmnd = NULL;
+	struct device *ctrl_dev;
+
+	int mlcnt  = 0;
+	int llcnt  = 0;
+	int ehcnt  = 0;
+	int fwcnt  = 0;
+	int krlcnt = 0;
+
+	__shost_for_each_device(sdev, shost) {
+		spin_lock_irqsave(&sdev->list_lock, flags);
+		list_for_each_entry(scmnd, &sdev->cmd_list, list) {
+			switch (scmnd->SCp.phase) {
+			case AAC_OWNER_FIRMWARE:
+				fwcnt++;
+				break;
+			case AAC_OWNER_ERROR_HANDLER:
+				ehcnt++;
+				break;
+			case AAC_OWNER_LOWLEVEL:
+				llcnt++;
+				break;
+			case AAC_OWNER_MIDLEVEL:
+				mlcnt++;
+				break;
+			default:
+				krlcnt++;
+				break;
+			}
+		}
+		spin_unlock_irqrestore(&sdev->list_lock, flags);
+	}
+
+	ctrl_dev = &aac->pdev->dev;
+
+	dev_info(ctrl_dev, "outstanding cmd: midlevel-%d\n", mlcnt);
+	dev_info(ctrl_dev, "outstanding cmd: lowlevel-%d\n", llcnt);
+	dev_info(ctrl_dev, "outstanding cmd: error handler-%d\n", ehcnt);
+	dev_info(ctrl_dev, "outstanding cmd: firmware-%d\n", fwcnt);
+	dev_info(ctrl_dev, "outstanding cmd: kernel-%d\n", krlcnt);
+
+	return mlcnt + llcnt + ehcnt + fwcnt;
+}
+
 static int aac_eh_abort(struct scsi_cmnd* cmd)
 {
 	struct scsi_device * dev = cmd->device;
@@ -661,8 +734,8 @@ static int aac_eh_abort(struct scsi_cmnd* cmd)
 				  (fib_callback) aac_hba_callback,
 				  (void *) cmd);
 
-		/* Wait up to 2 minutes for completion */
-		for (count = 0; count < 120; ++count) {
+		/* Wait up to 15 secs for completion */
+		for (count = 0; count < 15; ++count) {
 			if (cmd->SCp.sent_command) {
 				ret = SUCCESS;
 				break;
@@ -754,6 +827,12 @@ static int aac_eh_reset(struct scsi_cmnd* cmd)
 	int count;
 	u32 bus, cid;
 	int ret = FAILED;
+	int status = 0;
+	__le32 supported_options2 = 0;
+	bool is_mu_reset;
+	bool is_ignore_reset;
+	bool is_doorbell_reset;
+
 
 	bus = aac_logical_to_phys(scmd_channel(cmd));
 	cid = scmd_id(cmd);
@@ -817,8 +896,8 @@ static int aac_eh_reset(struct scsi_cmnd* cmd)
 				  (fib_callback) aac_hba_callback,
 				  (void *) cmd);
 
-		/* Wait up to 2 minutes for completion */
-		for (count = 0; count < 120; ++count) {
+		/* Wait up to 15 seconds for completion */
+		for (count = 0; count < 15; ++count) {
 			if (cmd->SCp.sent_command) {
 				ret = SUCCESS;
 				break;
@@ -826,12 +905,10 @@ static int aac_eh_reset(struct scsi_cmnd* cmd)
 			msleep(1000);
 		}
 
-		if (ret != SUCCESS)
-			pr_err("%s: Host adapter reset request timed out\n",
-			AAC_DRIVERNAME);
+		if (ret == SUCCESS)
+			goto out;
+
 	} else {
-		struct scsi_cmnd *command;
-		unsigned long flags;
 
 		/* Mark the assoc. FIB to not complete, eh handler does this */
 		for (count = 0;
@@ -846,68 +923,42 @@ static int aac_eh_reset(struct scsi_cmnd* cmd)
 				cmd->SCp.phase = AAC_OWNER_ERROR_HANDLER;
 			}
 		}
+	}
 
-		pr_err("%s: Host adapter reset request. SCSI hang ?\n",
-					AAC_DRIVERNAME);
-
-		count = aac_check_health(aac);
-		if (count)
-			return count;
-		/*
-		 * Wait for all commands to complete to this specific
-		 * target (block maximum 60 seconds).
-		 */
-		for (count = 60; count; --count) {
-			int active = aac->in_reset;
-
-			if (active == 0)
-			__shost_for_each_device(dev, host) {
-				spin_lock_irqsave(&dev->list_lock, flags);
-				list_for_each_entry(command, &dev->cmd_list,
-					list) {
-					if ((command != cmd) &&
-					(command->SCp.phase ==
-					AAC_OWNER_FIRMWARE)) {
-						active++;
-						break;
-					}
-				}
-				spin_unlock_irqrestore(&dev->list_lock, flags);
-				if (active)
-					break;
+	pr_err("%s: Host adapter reset request. SCSI hang ?\n", AAC_DRIVERNAME);
 
-			}
-			/*
-			 * We can exit If all the commands are complete
-			 */
-			if (active == 0)
-				return SUCCESS;
-			ssleep(1);
-		}
-		pr_err("%s: SCSI bus appears hung\n", AAC_DRIVERNAME);
+	/*
+	 * Check the health of the controller
+	 */
+	status = aac_adapter_check_health(aac);
+	if (status)
+		dev_err(&aac->pdev->dev, "Adapter health - %d\n", status);
 
-		/*
-		 * This adapter needs a blind reset, only do so for
-		 * Adapters that support a register, instead of a commanded,
-		 * reset.
-		 */
-		if (((aac->supplement_adapter_info.supported_options2 &
-			  AAC_OPTION_MU_RESET) ||
-			  (aac->supplement_adapter_info.supported_options2 &
-			  AAC_OPTION_DOORBELL_RESET)) &&
-			  aac_check_reset &&
-			  ((aac_check_reset != 1) ||
-			   !(aac->supplement_adapter_info.supported_options2 &
-			    AAC_OPTION_IGNORE_RESET))) {
-			/* Bypass wait for command quiesce */
-			aac_reset_adapter(aac, 2, IOP_HWSOFT_RESET);
-		}
-		ret = SUCCESS;
-	}
+	count = get_num_of_incomplete_fibs(aac);
+	if (count == 0)
+		return SUCCESS;
+
+	/*
+	 * Check if reset is supported by the firmware
+	 */
+	supported_options2 = aac->supplement_adapter_info.supported_options2;
+	is_mu_reset = supported_options2 & AAC_OPTION_MU_RESET;
+	is_doorbell_reset = supported_options2 & AAC_OPTION_DOORBELL_RESET;
+	is_ignore_reset = supported_options2 & AAC_OPTION_IGNORE_RESET;
 	/*
-	 * Cause an immediate retry of the command with a ten second delay
-	 * after successful tur
+	 * This adapter needs a blind reset, only do so for
+	 * Adapters that support a register, instead of a commanded,
+	 * reset.
 	 */
+	if ((is_mu_reset || is_doorbell_reset)
+	 && aac_check_reset
+	 && (aac_check_reset != -1 || !is_ignore_reset)) {
+		/* Bypass wait for command quiesce */
+		aac_reset_adapter(aac, 2, IOP_HWSOFT_RESET);
+	}
+	ret = SUCCESS;
+
+out:
 	return ret;
 }
 
@@ -1365,10 +1416,7 @@ static void __aac_shutdown(struct aac_dev * aac)
 		kthread_stop(aac->thread);
 	}
 	aac_adapter_disable_int(aac);
-	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_is_src(aac)) {
 		if (aac->max_msix > 1) {
 			for (i = 0; i < aac->max_msix; i++) {
 				free_irq(pci_irq_vector(aac->pdev, i),
@@ -1403,6 +1451,7 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	int error = -ENODEV;
 	int unique_id = 0;
 	u64 dmamask;
+	int mask_bits = 0;
 	extern int aac_sync_mode;
 
 	/*
@@ -1426,18 +1475,32 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto out;
 	error = -ENODEV;
 
+	if (!(aac_drivers[index].quirks & AAC_QUIRK_SRC)) {
+		error = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		if (error) {
+			dev_err(&pdev->dev, "PCI 32 BIT dma mask set failed");
+			goto out_disable_pdev;
+		}
+	}
+
 	/*
 	 * If the quirk31 bit is set, the adapter needs adapter
 	 * to driver communication memory to be allocated below 2gig
 	 */
-	if (aac_drivers[index].quirks & AAC_QUIRK_31BIT)
+	if (aac_drivers[index].quirks & AAC_QUIRK_31BIT) {
 		dmamask = DMA_BIT_MASK(31);
-	else
+		mask_bits = 31;
+	} else {
 		dmamask = DMA_BIT_MASK(32);
+		mask_bits = 32;
+	}
 
-	if (pci_set_dma_mask(pdev, dmamask) ||
-			pci_set_consistent_dma_mask(pdev, dmamask))
+	error = pci_set_consistent_dma_mask(pdev, dmamask);
+	if (error) {
+		dev_err(&pdev->dev, "PCI %d B consistent dma mask set failed\n"
+				, mask_bits);
 		goto out_disable_pdev;
+	}
 
 	pci_set_master(pdev);
 
@@ -1501,15 +1564,6 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto out_deinit;
 	}
 
-	/*
-	 * If we had set a smaller DMA mask earlier, set it to 4gig
-	 * now since the adapter can dma data to at least a 4gig
-	 * address space.
-	 */
-	if (aac_drivers[index].quirks & AAC_QUIRK_31BIT)
-		if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))
-			goto out_deinit;
-
 	aac->maximum_num_channels = aac_drivers[index].channels;
 	error = aac_get_adapter_info(aac);
 	if (error < 0)
@@ -1627,9 +1681,7 @@ static int aac_acquire_resources(struct aac_dev *dev)
 	aac_adapter_enable_int(dev);
 
 
-	if ((dev->pdev->device == PMC_DEVICE_S7 ||
-	     dev->pdev->device == PMC_DEVICE_S8 ||
-	     dev->pdev->device == PMC_DEVICE_S9))
+	if (aac_is_src(dev))
 		aac_define_int_mode(dev);
 
 	if (dev->msi_enabled)

drivers/scsi/aacraid/src.c

@@ -694,33 +694,52 @@ static void aac_dump_fw_fib_iop_reset(struct aac_dev *dev)
 			0, 0, 0,  0, 0, 0, NULL, NULL, NULL, NULL, NULL);
 }
 
-static void aac_send_iop_reset(struct aac_dev *dev, int bled)
+static bool aac_is_ctrl_up_and_running(struct aac_dev *dev)
 {
-	u32 var, reset_mask;
+	bool ctrl_up = true;
+	unsigned long status, start;
+	bool is_up = false;
 
-	aac_dump_fw_fib_iop_reset(dev);
+	start = jiffies;
+	do {
+		schedule();
+		status = src_readl(dev, MUnit.OMR);
 
-	bled = aac_adapter_sync_cmd(dev, IOP_RESET_ALWAYS,
-				    0, 0, 0, 0, 0, 0, &var,
-				    &reset_mask, NULL, NULL, NULL);
+		if (status == 0xffffffff)
+			status = 0;
 
-	if ((bled || var != 0x00000001) && !dev->doorbell_mask)
-		bled = -EINVAL;
-	else if (dev->doorbell_mask) {
-		reset_mask = dev->doorbell_mask;
-		bled = 0;
-		var = 0x00000001;
-	}
+		if (status & KERNEL_BOOTING) {
+			start = jiffies;
+			continue;
+		}
+
+		if (time_after(jiffies, start+HZ*SOFT_RESET_TIME)) {
+			ctrl_up = false;
+			break;
+		}
+
+		is_up = status & KERNEL_UP_AND_RUNNING;
+
+	} while (!is_up);
+
+	return ctrl_up;
+}
+
+static void aac_notify_fw_of_iop_reset(struct aac_dev *dev)
+{
+	aac_adapter_sync_cmd(dev, IOP_RESET_ALWAYS, 0, 0, 0, 0, 0, 0, NULL,
+						NULL, NULL, NULL, NULL);
+}
+
+static void aac_send_iop_reset(struct aac_dev *dev)
+{
+	aac_dump_fw_fib_iop_reset(dev);
+
+	aac_notify_fw_of_iop_reset(dev);
 
 	aac_set_intx_mode(dev);
 
-	if (!bled && (dev->supplement_adapter_info.supported_options2 &
-	    AAC_OPTION_DOORBELL_RESET)) {
-		src_writel(dev, MUnit.IDR, reset_mask);
-	} else {
-		src_writel(dev, MUnit.IDR, 0x100);
-	}
-	msleep(30000);
+	src_writel(dev, MUnit.IDR, IOP_SRC_RESET_MASK);
 }
 
 static void aac_send_hardware_soft_reset(struct aac_dev *dev)
@@ -735,14 +754,14 @@ static void aac_send_hardware_soft_reset(struct aac_dev *dev)
 
 static int aac_src_restart_adapter(struct aac_dev *dev, int bled, u8 reset_type)
 {
-	unsigned long status, start;
+	bool is_ctrl_up;
+	int ret = 0;
 
 	if (bled < 0)
 		goto invalid_out;
 
 	if (bled)
-		pr_err("%s%d: adapter kernel panic'd %x.\n",
-				dev->name, dev->id, bled);
+		dev_err(&dev->pdev->dev, "adapter kernel panic'd %x.\n", bled);
 
 	/*
 	 * When there is a BlinkLED, IOP_RESET has not effect
@@ -752,48 +771,55 @@ static int aac_src_restart_adapter(struct aac_dev *dev, int bled, u8 reset_type)
 
 	dev->a_ops.adapter_enable_int = aac_src_disable_interrupt;
 
-	switch (reset_type) {
-	case IOP_HWSOFT_RESET:
-		aac_send_iop_reset(dev, bled);
+	dev_err(&dev->pdev->dev, "Controller reset type is %d\n", reset_type);
+
+	if (reset_type & HW_IOP_RESET) {
+		dev_info(&dev->pdev->dev, "Issuing IOP reset\n");
+		aac_send_iop_reset(dev);
+
 		/*
-		 * Check to see if KERNEL_UP_AND_RUNNING
-		 * Wait for the adapter to be up and running.
-		 * If !KERNEL_UP_AND_RUNNING issue HW Soft Reset
+		 * Creates a delay or wait till up and running comes thru
 		 */
-		status = src_readl(dev, MUnit.OMR);
-		if (dev->sa_firmware
-		 && !(status & KERNEL_UP_AND_RUNNING)) {
-			start = jiffies;
-			do {
-				status = src_readl(dev, MUnit.OMR);
-				if (time_after(jiffies,
-				 start+HZ*SOFT_RESET_TIME)) {
-					aac_send_hardware_soft_reset(dev);
-					start = jiffies;
-				}
-			} while (!(status & KERNEL_UP_AND_RUNNING));
+		is_ctrl_up = aac_is_ctrl_up_and_running(dev);
+		if (!is_ctrl_up)
+			dev_err(&dev->pdev->dev, "IOP reset failed\n");
+		else {
+			dev_info(&dev->pdev->dev, "IOP reset succeded\n");
+			goto set_startup;
 		}
-		break;
-	case HW_SOFT_RESET:
-		if (dev->sa_firmware) {
-			aac_send_hardware_soft_reset(dev);
-			aac_set_intx_mode(dev);
-		}
-		break;
-	default:
-		aac_send_iop_reset(dev, bled);
-		break;
 	}
 
-invalid_out:
+	if (!dev->sa_firmware) {
+		dev_err(&dev->pdev->dev, "ARC Reset attempt failed\n");
+		ret = -ENODEV;
+		goto out;
+	}
 
-	if (src_readl(dev, MUnit.OMR) & KERNEL_PANIC)
-		return -ENODEV;
+	if (reset_type & HW_SOFT_RESET) {
+		dev_info(&dev->pdev->dev, "Issuing SOFT reset\n");
+		aac_send_hardware_soft_reset(dev);
+		dev->msi_enabled = 0;
 
+		is_ctrl_up = aac_is_ctrl_up_and_running(dev);
+		if (!is_ctrl_up) {
+			dev_err(&dev->pdev->dev, "SOFT reset failed\n");
+			ret = -ENODEV;
+			goto out;
+		} else
+			dev_info(&dev->pdev->dev, "SOFT reset succeded\n");
+	}
+
+set_startup:
 	if (startup_timeout < 300)
 		startup_timeout = 300;
 
-	return 0;
+out:
+	return ret;
+
+invalid_out:
+	if (src_readl(dev, MUnit.OMR) & KERNEL_PANIC)
+		ret = -ENODEV;
+goto out;
 }
 
 /**

drivers/scsi/atari_scsi.c

@@ -776,7 +776,7 @@ static int __init atari_scsi_probe(struct platform_device *pdev)
 	 * from/to alternative Ram.
 	 */
 	if (ATARIHW_PRESENT(ST_SCSI) && !ATARIHW_PRESENT(EXTD_DMA) &&
-	    m68k_num_memory > 1) {
+	    m68k_realnum_memory > 1) {
 		atari_dma_buffer = atari_stram_alloc(STRAM_BUFFER_SIZE, "SCSI");
 		if (!atari_dma_buffer) {
 			pr_err(PFX "can't allocate ST-RAM double buffer\n");

drivers/scsi/bnx2fc/57xx_hsi_bnx2fc.h

@@ -3,7 +3,8 @@
  * session resources such as connection id and qp resources.
  *
  * Copyright (c) 2008-2013 Broadcom Corporation
- * Copyright (c) 2014-2015 QLogic Corporation
+ * Copyright (c) 2014-2016 QLogic Corporation
+ * Copyright (c) 2016-2017 Cavium Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

drivers/scsi/bnx2fc/bnx2fc.h

@@ -1,7 +1,8 @@
 /* bnx2fc.h: QLogic Linux FCoE offload driver.
  *
  * Copyright (c) 2008-2013 Broadcom Corporation
- * Copyright (c) 2014-2015 QLogic Corporation
+ * Copyright (c) 2014-2016 QLogic Corporation
+ * Copyright (c) 2016-2017 Cavium Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -65,7 +66,7 @@
 #include "bnx2fc_constants.h"
 
 #define BNX2FC_NAME		"bnx2fc"
-#define BNX2FC_VERSION		"2.10.3"
+#define BNX2FC_VERSION		"2.11.8"
 
 #define PFX			"bnx2fc: "
 

drivers/scsi/bnx2fc/bnx2fc_constants.h

@@ -3,7 +3,8 @@
  * session resources such as connection id and qp resources.
  *
  * Copyright (c) 2008-2013 Broadcom Corporation
- * Copyright (c) 2014-2015 QLogic Corporation
+ * Copyright (c) 2014-2016 QLogic Corporation
+ * Copyright (c) 2016-2017 Cavium Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

drivers/scsi/bnx2fc/bnx2fc_debug.c

@@ -3,7 +3,8 @@
  * session resources such as connection id and qp resources.
  *
  * Copyright (c) 2008-2013 Broadcom Corporation
- * Copyright (c) 2014-2015 QLogic Corporation
+ * Copyright (c) 2014-2016 QLogic Corporation
+ * Copyright (c) 2016-2017 Cavium Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

drivers/scsi/bnx2fc/bnx2fc_debug.h

@@ -3,7 +3,8 @@
  * session resources such as connection id and qp resources.
  *
  * Copyright (c) 2008-2013 Broadcom Corporation
- * Copyright (c) 2014-2015 QLogic Corporation
+ * Copyright (c) 2014-2016 QLogic Corporation
+ * Copyright (c) 2016-2017 Cavium Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

drivers/scsi/bnx2fc/bnx2fc_els.c

@@ -4,7 +4,8 @@
  * and responses.
  *
  * Copyright (c) 2008-2013 Broadcom Corporation
- * Copyright (c) 2014-2015 QLogic Corporation
+ * Copyright (c) 2014-2016 QLogic Corporation
+ * Copyright (c) 2016-2017 Cavium Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -61,13 +62,20 @@ int bnx2fc_send_rrq(struct bnx2fc_cmd *aborted_io_req)
 
 	struct fc_els_rrq rrq;
 	struct bnx2fc_rport *tgt = aborted_io_req->tgt;
-	struct fc_lport *lport = tgt->rdata->local_port;
+	struct fc_lport *lport = NULL;
 	struct bnx2fc_els_cb_arg *cb_arg = NULL;
-	u32 sid = tgt->sid;
-	u32 r_a_tov = lport->r_a_tov;
+	u32 sid = 0;
+	u32 r_a_tov = 0;
 	unsigned long start = jiffies;
 	int rc;
 
+	if (!test_bit(BNX2FC_FLAG_SESSION_READY, &tgt->flags))
+		return -EINVAL;
+
+	lport = tgt->rdata->local_port;
+	sid = tgt->sid;
+	r_a_tov = lport->r_a_tov;
+
 	BNX2FC_ELS_DBG("Sending RRQ orig_xid = 0x%x\n",
 		   aborted_io_req->xid);
 	memset(&rrq, 0, sizeof(rrq));

drivers/scsi/bnx2fc/bnx2fc_fcoe.c

@@ -4,7 +4,8 @@
  * FIP/FCoE packets, listen to link events etc.
  *
  * Copyright (c) 2008-2013 Broadcom Corporation
- * Copyright (c) 2014-2015 QLogic Corporation
+ * Copyright (c) 2014-2016 QLogic Corporation
+ * Copyright (c) 2016-2017 Cavium Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -522,10 +523,12 @@ static void bnx2fc_recv_frame(struct sk_buff *skb)
 	struct fcoe_crc_eof crc_eof;
 	struct fc_frame *fp;
 	struct fc_lport *vn_port;
-	struct fcoe_port *port;
+	struct fcoe_port *port, *phys_port;
 	u8 *mac = NULL;
 	u8 *dest_mac = NULL;
 	struct fcoe_hdr *hp;
+	struct bnx2fc_interface *interface;
+	struct fcoe_ctlr *ctlr;
 
 	fr = fcoe_dev_from_skb(skb);
 	lport = fr->fr_dev;
@@ -561,8 +564,19 @@ static void bnx2fc_recv_frame(struct sk_buff *skb)
 		return;
 	}
 
+	phys_port = lport_priv(lport);
+	interface = phys_port->priv;
+	ctlr = bnx2fc_to_ctlr(interface);
+
 	fh = fc_frame_header_get(fp);
 
+	if (ntoh24(&dest_mac[3]) != ntoh24(fh->fh_d_id)) {
+		BNX2FC_HBA_DBG(lport, "FC frame d_id mismatch with MAC %pM.\n",
+		    dest_mac);
+		kfree_skb(skb);
+		return;
+	}
+
 	vn_port = fc_vport_id_lookup(lport, ntoh24(fh->fh_d_id));
 	if (vn_port) {
 		port = lport_priv(vn_port);
@@ -572,6 +586,14 @@ static void bnx2fc_recv_frame(struct sk_buff *skb)
 			return;
 		}
 	}
+	if (ctlr->state) {
+		if (!ether_addr_equal(mac, ctlr->dest_addr)) {
+			BNX2FC_HBA_DBG(lport, "Wrong source address: mac:%pM dest_addr:%pM.\n",
+			    mac, ctlr->dest_addr);
+			kfree_skb(skb);
+			return;
+		}
+	}
 	if (fh->fh_r_ctl == FC_RCTL_DD_SOL_DATA &&
 	    fh->fh_type == FC_TYPE_FCP) {
 		/* Drop FCP data. We dont this in L2 path */
@@ -597,6 +619,18 @@ static void bnx2fc_recv_frame(struct sk_buff *skb)
 		return;
 	}
 
+	/*
+	 * If the destination ID from the frame header does not match what we
+	 * have on record for lport and the search for a NPIV port came up
+	 * empty then this is not addressed to our port so simply drop it.
+	 */
+	if (lport->port_id != ntoh24(fh->fh_d_id) && !vn_port) {
+		BNX2FC_HBA_DBG(lport, "Dropping frame due to destination mismatch: lport->port_id=%x fh->d_id=%x.\n",
+		    lport->port_id, ntoh24(fh->fh_d_id));
+		kfree_skb(skb);
+		return;
+	}
+
 	stats = per_cpu_ptr(lport->stats, smp_processor_id());
 	stats->RxFrames++;
 	stats->RxWords += fr_len / FCOE_WORD_TO_BYTE;
@@ -2105,6 +2139,9 @@ static uint bnx2fc_npiv_create_vports(struct fc_lport *lport,
 {
 	struct fc_vport_identifiers vpid;
 	uint i, created = 0;
+	u64 wwnn = 0;
+	char wwpn_str[32];
+	char wwnn_str[32];
 
 	if (npiv_tbl->count > MAX_NPIV_ENTRIES) {
 		BNX2FC_HBA_DBG(lport, "Exceeded count max of npiv table\n");
@@ -2123,11 +2160,23 @@ static uint bnx2fc_npiv_create_vports(struct fc_lport *lport,
 	vpid.disable = false;
 
 	for (i = 0; i < npiv_tbl->count; i++) {
-		vpid.node_name = wwn_to_u64(npiv_tbl->wwnn[i]);
+		wwnn = wwn_to_u64(npiv_tbl->wwnn[i]);
+		if (wwnn == 0) {
+			/*
+			 * If we get a 0 element from for the WWNN then assume
+			 * the WWNN should be the same as the physical port.
+			 */
+			wwnn = lport->wwnn;
+		}
+		vpid.node_name = wwnn;
 		vpid.port_name = wwn_to_u64(npiv_tbl->wwpn[i]);
 		scnprintf(vpid.symbolic_name, sizeof(vpid.symbolic_name),
 		    "NPIV[%u]:%016llx-%016llx",
 		    created, vpid.port_name, vpid.node_name);
+		fcoe_wwn_to_str(vpid.node_name, wwnn_str, sizeof(wwnn_str));
+		fcoe_wwn_to_str(vpid.port_name, wwpn_str, sizeof(wwpn_str));
+		BNX2FC_HBA_DBG(lport, "Creating vport %s:%s.\n", wwnn_str,
+		    wwpn_str);
 		if (fc_vport_create(lport->host, 0, &vpid))
 			created++;
 		else
@@ -2524,6 +2573,11 @@ static void bnx2fc_ulp_exit(struct cnic_dev *dev)
 	bnx2fc_hba_destroy(hba);
 }
 
+static void bnx2fc_rport_terminate_io(struct fc_rport *rport)
+{
+	/* This is a no-op */
+}
+
 /**
  * bnx2fc_fcoe_reset - Resets the fcoe
  *
@@ -2860,7 +2914,7 @@ static struct fc_function_template bnx2fc_transport_function = {
 
 	.issue_fc_host_lip = bnx2fc_fcoe_reset,
 
-	.terminate_rport_io = fc_rport_terminate_io,
+	.terminate_rport_io = bnx2fc_rport_terminate_io,
 
 	.vport_create = bnx2fc_vport_create,
 	.vport_delete = bnx2fc_vport_destroy,

drivers/scsi/bnx2fc/bnx2fc_hwi.c

@@ -3,7 +3,8 @@
  * with 57712 FCoE firmware.
  *
  * Copyright (c) 2008-2013 Broadcom Corporation
- * Copyright (c) 2014-2015 QLogic Corporation
+ * Copyright (c) 2014-2016 QLogic Corporation
+ * Copyright (c) 2016-2017 Cavium Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

drivers/scsi/bnx2fc/bnx2fc_io.c

@@ -2,7 +2,8 @@
  * IO manager and SCSI IO processing.
  *
  * Copyright (c) 2008-2013 Broadcom Corporation
- * Copyright (c) 2014-2015 QLogic Corporation
+ * Copyright (c) 2014-2016 QLogic Corporation
+ * Copyright (c) 2016-2017 Cavium Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -1166,16 +1167,11 @@ int bnx2fc_eh_abort(struct scsi_cmnd *sc_cmd)
 		printk(KERN_ERR PFX "eh_abort: io_req (xid = 0x%x) "
 				"not on active_q\n", io_req->xid);
 		/*
-		 * This condition can happen only due to the FW bug,
-		 * where we do not receive cleanup response from
-		 * the FW. Handle this case gracefully by erroring
-		 * back the IO request to SCSI-ml
+		 * The IO is still with the FW.
+		 * Return failure and let SCSI-ml retry eh_abort.
 		 */
-		bnx2fc_scsi_done(io_req, DID_ABORT);
-
-		kref_put(&io_req->refcount, bnx2fc_cmd_release);
 		spin_unlock_bh(&tgt->tgt_lock);
-		return SUCCESS;
+		return FAILED;
 	}
 
 	/*

drivers/scsi/bnx2fc/bnx2fc_tgt.c

@@ -3,7 +3,8 @@
  * session resources such as connection id and qp resources.
  *
  * Copyright (c) 2008-2013 Broadcom Corporation
- * Copyright (c) 2014-2015 QLogic Corporation
+ * Copyright (c) 2014-2016 QLogic Corporation
+ * Copyright (c) 2016-2017 Cavium Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

drivers/scsi/bnx2i/bnx2i_iscsi.c

@@ -1909,7 +1909,8 @@ static struct iscsi_endpoint *bnx2i_ep_connect(struct Scsi_Host *shost,
 
 	bnx2i_ep_active_list_add(hba, bnx2i_ep);
 
-	if (bnx2i_map_ep_dbell_regs(bnx2i_ep))
+	rc = bnx2i_map_ep_dbell_regs(bnx2i_ep);
+	if (rc)
 		goto del_active_ep;
 
 	mutex_unlock(&hba->net_dev_lock);

drivers/scsi/csiostor/csio_hw.c

@@ -794,18 +794,24 @@ csio_hw_dev_ready(struct csio_hw *hw)
 {
 	uint32_t reg;
 	int cnt = 6;
+	int src_pf;
 
 	while (((reg = csio_rd_reg32(hw, PL_WHOAMI_A)) == 0xFFFFFFFF) &&
 	       (--cnt != 0))
 		mdelay(100);
 
-	if ((cnt == 0) && (((int32_t)(SOURCEPF_G(reg)) < 0) ||
-			   (SOURCEPF_G(reg) >= CSIO_MAX_PFN))) {
+	if (csio_is_t5(hw->pdev->device & CSIO_HW_CHIP_MASK))
+		src_pf = SOURCEPF_G(reg);
+	else
+		src_pf = T6_SOURCEPF_G(reg);
+
+	if ((cnt == 0) && (((int32_t)(src_pf) < 0) ||
+			   (src_pf >= CSIO_MAX_PFN))) {
 		csio_err(hw, "PL_WHOAMI returned 0x%x, cnt:%d\n", reg, cnt);
 		return -EIO;
 	}
 
-	hw->pfn = SOURCEPF_G(reg);
+	hw->pfn = src_pf;
 
 	return 0;
 }
@@ -1581,10 +1587,16 @@ csio_hw_flash_config(struct csio_hw *hw, u32 *fw_cfg_param, char *path)
 	unsigned int mtype = 0, maddr = 0;
 	uint32_t *cfg_data;
 	int value_to_add = 0;
+	const char *fw_cfg_file;
+
+	if (csio_is_t5(pci_dev->device & CSIO_HW_CHIP_MASK))
+		fw_cfg_file = FW_CFG_NAME_T5;
+	else
+		fw_cfg_file = FW_CFG_NAME_T6;
 
-	if (request_firmware(&cf, FW_CFG_NAME_T5, dev) < 0) {
+	if (request_firmware(&cf, fw_cfg_file, dev) < 0) {
 		csio_err(hw, "could not find config file %s, err: %d\n",
-			 FW_CFG_NAME_T5, ret);
+			 fw_cfg_file, ret);
 		return -ENOENT;
 	}
 
@@ -1623,9 +1635,8 @@ csio_hw_flash_config(struct csio_hw *hw, u32 *fw_cfg_param, char *path)
 		ret = csio_memory_write(hw, mtype, maddr + size, 4, &last.word);
 	}
 	if (ret == 0) {
-		csio_info(hw, "config file upgraded to %s\n",
-			  FW_CFG_NAME_T5);
-		snprintf(path, 64, "%s%s", "/lib/firmware/", FW_CFG_NAME_T5);
+		csio_info(hw, "config file upgraded to %s\n", fw_cfg_file);
+		snprintf(path, 64, "%s%s", "/lib/firmware/", fw_cfg_file);
 	}
 
 leave:
@@ -1886,6 +1897,19 @@ static struct fw_info fw_info_array[] = {
 			.intfver_iscsi = FW_INTFVER(T5, ISCSI),
 			.intfver_fcoe = FW_INTFVER(T5, FCOE),
 		},
+	}, {
+		.chip = CHELSIO_T6,
+		.fs_name = FW_CFG_NAME_T6,
+		.fw_mod_name = FW_FNAME_T6,
+		.fw_hdr = {
+			.chip = FW_HDR_CHIP_T6,
+			.fw_ver = __cpu_to_be32(FW_VERSION(T6)),
+			.intfver_nic = FW_INTFVER(T6, NIC),
+			.intfver_vnic = FW_INTFVER(T6, VNIC),
+			.intfver_ri = FW_INTFVER(T6, RI),
+			.intfver_iscsi = FW_INTFVER(T6, ISCSI),
+			.intfver_fcoe = FW_INTFVER(T6, FCOE),
+		},
 	}
 };
 
@@ -2002,6 +2026,7 @@ csio_hw_flash_fw(struct csio_hw *hw, int *reset)
 	struct device *dev = &pci_dev->dev ;
 	const u8 *fw_data = NULL;
 	unsigned int fw_size = 0;
+	const char *fw_bin_file;
 
 	/* This is the firmware whose headers the driver was compiled
 	 * against
@@ -2014,9 +2039,14 @@ csio_hw_flash_fw(struct csio_hw *hw, int *reset)
 		return -EINVAL;
 	}
 
-	if (request_firmware(&fw, FW_FNAME_T5, dev) < 0) {
+	if (csio_is_t5(pci_dev->device & CSIO_HW_CHIP_MASK))
+		fw_bin_file = FW_FNAME_T5;
+	else
+		fw_bin_file = FW_FNAME_T6;
+
+	if (request_firmware(&fw, fw_bin_file, dev) < 0) {
 		csio_err(hw, "could not find firmware image %s, err: %d\n",
-			 FW_FNAME_T5, ret);
+			 fw_bin_file, ret);
 	} else {
 		fw_data = fw->data;
 		fw_size = fw->size;
@@ -2038,6 +2068,17 @@ csio_hw_flash_fw(struct csio_hw *hw, int *reset)
 	return ret;
 }
 
+static int csio_hw_check_fwver(struct csio_hw *hw)
+{
+	if (csio_is_t6(hw->pdev->device & CSIO_HW_CHIP_MASK) &&
+	    (hw->fwrev < CSIO_MIN_T6_FW)) {
+		csio_hw_print_fw_version(hw, "T6 unsupported fw");
+		return -1;
+	}
+
+	return 0;
+}
+
 /*
  * csio_hw_configure - Configure HW
  * @hw - HW module
@@ -2105,6 +2146,10 @@ csio_hw_configure(struct csio_hw *hw)
 		if (rv != 0)
 			goto out;
 
+		rv = csio_hw_check_fwver(hw);
+		if (rv < 0)
+			goto out;
+
 		/* If the firmware doesn't support Configuration Files,
 		 * return an error.
 		 */
@@ -2132,6 +2177,10 @@ csio_hw_configure(struct csio_hw *hw)
 		}
 
 	} else {
+		rv = csio_hw_check_fwver(hw);
+		if (rv < 0)
+			goto out;
+
 		if (hw->fw_state == CSIO_DEV_STATE_INIT) {
 
 			hw->flags |= CSIO_HWF_USING_SOFT_PARAMS;
@@ -2241,9 +2290,14 @@ static void
 csio_hw_intr_enable(struct csio_hw *hw)
 {
 	uint16_t vec = (uint16_t)csio_get_mb_intr_idx(csio_hw_to_mbm(hw));
-	uint32_t pf = SOURCEPF_G(csio_rd_reg32(hw, PL_WHOAMI_A));
+	u32 pf = 0;
 	uint32_t pl = csio_rd_reg32(hw, PL_INT_ENABLE_A);
 
+	if (csio_is_t5(hw->pdev->device & CSIO_HW_CHIP_MASK))
+		pf = SOURCEPF_G(csio_rd_reg32(hw, PL_WHOAMI_A));
+	else
+		pf = T6_SOURCEPF_G(csio_rd_reg32(hw, PL_WHOAMI_A));
+
 	/*
 	 * Set aivec for MSI/MSIX. PCIE_PF_CFG.INTXType is set up
 	 * by FW, so do nothing for INTX.
@@ -2293,7 +2347,12 @@ csio_hw_intr_enable(struct csio_hw *hw)
 void
 csio_hw_intr_disable(struct csio_hw *hw)
 {
-	uint32_t pf = SOURCEPF_G(csio_rd_reg32(hw, PL_WHOAMI_A));
+	u32 pf = 0;
+
+	if (csio_is_t5(hw->pdev->device & CSIO_HW_CHIP_MASK))
+		pf = SOURCEPF_G(csio_rd_reg32(hw, PL_WHOAMI_A));
+	else
+		pf = T6_SOURCEPF_G(csio_rd_reg32(hw, PL_WHOAMI_A));
 
 	if (!(hw->flags & CSIO_HWF_HW_INTR_ENABLED))
 		return;
@@ -2918,6 +2977,8 @@ static void csio_cplsw_intr_handler(struct csio_hw *hw)
  */
 static void csio_le_intr_handler(struct csio_hw *hw)
 {
+	enum chip_type chip = CHELSIO_CHIP_VERSION(hw->chip_id);
+
 	static struct intr_info le_intr_info[] = {
 		{ LIPMISS_F, "LE LIP miss", -1, 0 },
 		{ LIP0_F, "LE 0 LIP error", -1, 0 },
@@ -2927,7 +2988,18 @@ static void csio_le_intr_handler(struct csio_hw *hw)
 		{ 0, NULL, 0, 0 }
 	};
 
-	if (csio_handle_intr_status(hw, LE_DB_INT_CAUSE_A, le_intr_info))
+	static struct intr_info t6_le_intr_info[] = {
+		{ T6_LIPMISS_F, "LE LIP miss", -1, 0 },
+		{ T6_LIP0_F, "LE 0 LIP error", -1, 0 },
+		{ TCAMINTPERR_F, "LE parity error", -1, 1 },
+		{ T6_UNKNOWNCMD_F, "LE unknown command", -1, 1 },
+		{ SSRAMINTPERR_F, "LE request queue parity error", -1, 1 },
+		{ 0, NULL, 0, 0 }
+	};
+
+	if (csio_handle_intr_status(hw, LE_DB_INT_CAUSE_A,
+				    (chip == CHELSIO_T5) ?
+				    le_intr_info : t6_le_intr_info))
 		csio_hw_fatal_err(hw);
 }
 

drivers/scsi/csiostor/csio_hw.h

@@ -71,6 +71,7 @@
 #define CSIO_MAX_CMD_PER_LUN	32
 #define CSIO_MAX_DDP_BUF_SIZE	(1024 * 1024)
 #define CSIO_MAX_SECTOR_SIZE	128
+#define CSIO_MIN_T6_FW		0x01102D00  /* FW 1.16.45.0 */
 
 /* Interrupts */
 #define CSIO_EXTRA_MSI_IQS	2	/* Extra iqs for INTX/MSI mode

drivers/scsi/csiostor/csio_hw_chip.h

@@ -39,11 +39,15 @@
 /* Define MACRO values */
 #define CSIO_HW_T5				0x5000
 #define CSIO_T5_FCOE_ASIC			0x5600
+#define CSIO_HW_T6				0x6000
+#define CSIO_T6_FCOE_ASIC			0x6600
 #define CSIO_HW_CHIP_MASK			0xF000
 
 #define T5_REGMAP_SIZE				(332 * 1024)
 #define FW_FNAME_T5				"cxgb4/t5fw.bin"
 #define FW_CFG_NAME_T5				"cxgb4/t5-config.txt"
+#define FW_FNAME_T6				"cxgb4/t6fw.bin"
+#define FW_CFG_NAME_T6				"cxgb4/t6-config.txt"
 
 #define CHELSIO_CHIP_CODE(version, revision) (((version) << 4) | (revision))
 #define CHELSIO_CHIP_FPGA          0x100
@@ -51,12 +55,17 @@
 #define CHELSIO_CHIP_RELEASE(code) ((code) & 0xf)
 
 #define CHELSIO_T5		0x5
+#define CHELSIO_T6		0x6
 
 enum chip_type {
 	T5_A0 = CHELSIO_CHIP_CODE(CHELSIO_T5, 0),
 	T5_A1 = CHELSIO_CHIP_CODE(CHELSIO_T5, 1),
 	T5_FIRST_REV	= T5_A0,
 	T5_LAST_REV	= T5_A1,
+
+	T6_A0 = CHELSIO_CHIP_CODE(CHELSIO_T6, 0),
+	T6_FIRST_REV    = T6_A0,
+	T6_LAST_REV     = T6_A0,
 };
 
 static inline int csio_is_t5(uint16_t chip)
@@ -64,6 +73,11 @@ static inline int csio_is_t5(uint16_t chip)
 	return (chip == CSIO_HW_T5);
 }
 
+static inline int csio_is_t6(uint16_t chip)
+{
+	return (chip == CSIO_HW_T6);
+}
+
 /* Define MACRO DEFINITIONS */
 #define CSIO_DEVICE(devid, idx)						\
 	{ PCI_VENDOR_ID_CHELSIO, (devid), PCI_ANY_ID, PCI_ANY_ID, 0, 0, (idx) }

drivers/scsi/csiostor/csio_hw_t5.c

@@ -71,27 +71,6 @@ csio_t5_set_mem_win(struct csio_hw *hw, uint32_t win)
 static void
 csio_t5_pcie_intr_handler(struct csio_hw *hw)
 {
-	static struct intr_info sysbus_intr_info[] = {
-		{ RNPP_F, "RXNP array parity error", -1, 1 },
-		{ RPCP_F, "RXPC array parity error", -1, 1 },
-		{ RCIP_F, "RXCIF array parity error", -1, 1 },
-		{ RCCP_F, "Rx completions control array parity error", -1, 1 },
-		{ RFTP_F, "RXFT array parity error", -1, 1 },
-		{ 0, NULL, 0, 0 }
-	};
-	static struct intr_info pcie_port_intr_info[] = {
-		{ TPCP_F, "TXPC array parity error", -1, 1 },
-		{ TNPP_F, "TXNP array parity error", -1, 1 },
-		{ TFTP_F, "TXFT array parity error", -1, 1 },
-		{ TCAP_F, "TXCA array parity error", -1, 1 },
-		{ TCIP_F, "TXCIF array parity error", -1, 1 },
-		{ RCAP_F, "RXCA array parity error", -1, 1 },
-		{ OTDD_F, "outbound request TLP discarded", -1, 1 },
-		{ RDPE_F, "Rx data parity error", -1, 1 },
-		{ TDUE_F, "Tx uncorrectable data error", -1, 1 },
-		{ 0, NULL, 0, 0 }
-	};
-
 	static struct intr_info pcie_intr_info[] = {
 		{ MSTGRPPERR_F, "Master Response Read Queue parity error",
 		-1, 1 },
@@ -133,13 +112,7 @@ csio_t5_pcie_intr_handler(struct csio_hw *hw)
 	};
 
 	int fat;
-	fat = csio_handle_intr_status(hw,
-				      PCIE_CORE_UTL_SYSTEM_BUS_AGENT_STATUS_A,
-				      sysbus_intr_info) +
-	      csio_handle_intr_status(hw,
-				      PCIE_CORE_UTL_PCI_EXPRESS_PORT_STATUS_A,
-				      pcie_port_intr_info) +
-	      csio_handle_intr_status(hw, PCIE_INT_CAUSE_A, pcie_intr_info);
+	fat = csio_handle_intr_status(hw, PCIE_INT_CAUSE_A, pcie_intr_info);
 	if (fat)
 		csio_hw_fatal_err(hw);
 }

drivers/scsi/csiostor/csio_init.c

@@ -952,8 +952,9 @@ static int csio_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	struct csio_hw *hw;
 	struct csio_lnode *ln;
 
-	/* probe only T5 cards */
-	if (!csio_is_t5((pdev->device & CSIO_HW_CHIP_MASK)))
+	/* probe only T5 and T6 cards */
+	if (!csio_is_t5((pdev->device & CSIO_HW_CHIP_MASK)) &&
+	    !csio_is_t6((pdev->device & CSIO_HW_CHIP_MASK)))
 		return -ENODEV;
 
 	rv = csio_pci_init(pdev, &bars);
@@ -1253,3 +1254,4 @@ MODULE_LICENSE(CSIO_DRV_LICENSE);
 MODULE_DEVICE_TABLE(pci, csio_pci_tbl);
 MODULE_VERSION(CSIO_DRV_VERSION);
 MODULE_FIRMWARE(FW_FNAME_T5);
+MODULE_FIRMWARE(FW_FNAME_T6);

drivers/scsi/csiostor/csio_init.h

@@ -50,7 +50,7 @@
 #define CSIO_DRV_AUTHOR			"Chelsio Communications"
 #define CSIO_DRV_LICENSE		"Dual BSD/GPL"
 #define CSIO_DRV_DESC			"Chelsio FCoE driver"
-#define CSIO_DRV_VERSION		"1.0.0"
+#define CSIO_DRV_VERSION		"1.0.0-ko"
 
 extern struct fc_function_template csio_fc_transport_funcs;
 extern struct fc_function_template csio_fc_transport_vport_funcs;

drivers/scsi/csiostor/csio_lnode.c

@@ -238,14 +238,23 @@ csio_osname(uint8_t *buf, size_t buf_len)
 }
 
 static inline void
-csio_append_attrib(uint8_t **ptr, uint16_t type, uint8_t *val, uint16_t len)
+csio_append_attrib(uint8_t **ptr, uint16_t type, void *val, size_t val_len)
 {
+	uint16_t len;
 	struct fc_fdmi_attr_entry *ae = (struct fc_fdmi_attr_entry *)*ptr;
+
+	if (WARN_ON(val_len > U16_MAX))
+		return;
+
+	len = val_len;
+
 	ae->type = htons(type);
 	len += 4;		/* includes attribute type and length */
 	len = (len + 3) & ~3;	/* should be multiple of 4 bytes */
 	ae->len = htons(len);
-	memcpy(ae->value, val, len);
+	memcpy(ae->value, val, val_len);
+	if (len > val_len)
+		memset(ae->value + val_len, 0, len - val_len);
 	*ptr += len;
 }
 
@@ -335,7 +344,7 @@ csio_ln_fdmi_rhba_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req)
 	numattrs++;
 	val = htonl(FC_PORTSPEED_1GBIT | FC_PORTSPEED_10GBIT);
 	csio_append_attrib(&pld, FC_FDMI_PORT_ATTR_SUPPORTEDSPEED,
-			   (uint8_t *)&val,
+			   &val,
 			   FC_FDMI_PORT_ATTR_SUPPORTEDSPEED_LEN);
 	numattrs++;
 
@@ -346,23 +355,22 @@ csio_ln_fdmi_rhba_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req)
 	else
 		val = htonl(CSIO_HBA_PORTSPEED_UNKNOWN);
 	csio_append_attrib(&pld, FC_FDMI_PORT_ATTR_CURRENTPORTSPEED,
-			   (uint8_t *)&val,
-			   FC_FDMI_PORT_ATTR_CURRENTPORTSPEED_LEN);
+			   &val, FC_FDMI_PORT_ATTR_CURRENTPORTSPEED_LEN);
 	numattrs++;
 
 	mfs = ln->ln_sparm.csp.sp_bb_data;
 	csio_append_attrib(&pld, FC_FDMI_PORT_ATTR_MAXFRAMESIZE,
-			   (uint8_t *)&mfs, FC_FDMI_PORT_ATTR_MAXFRAMESIZE_LEN);
+			   &mfs, sizeof(mfs));
 	numattrs++;
 
 	strcpy(buf, "csiostor");
 	csio_append_attrib(&pld, FC_FDMI_PORT_ATTR_OSDEVICENAME, buf,
-			   (uint16_t)strlen(buf));
+			   strlen(buf));
 	numattrs++;
 
 	if (!csio_hostname(buf, sizeof(buf))) {
 		csio_append_attrib(&pld, FC_FDMI_PORT_ATTR_HOSTNAME,
-				   buf, (uint16_t)strlen(buf));
+				   buf, strlen(buf));
 		numattrs++;
 	}
 	attrib_blk->numattrs = htonl(numattrs);
@@ -444,33 +452,32 @@ csio_ln_fdmi_dprt_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req)
 
 	strcpy(buf, "Chelsio Communications");
 	csio_append_attrib(&pld, FC_FDMI_HBA_ATTR_MANUFACTURER, buf,
-			   (uint16_t)strlen(buf));
+			   strlen(buf));
 	numattrs++;
 	csio_append_attrib(&pld, FC_FDMI_HBA_ATTR_SERIALNUMBER,
-			   hw->vpd.sn, (uint16_t)sizeof(hw->vpd.sn));
+			   hw->vpd.sn, sizeof(hw->vpd.sn));
 	numattrs++;
 	csio_append_attrib(&pld, FC_FDMI_HBA_ATTR_MODEL, hw->vpd.id,
-			   (uint16_t)sizeof(hw->vpd.id));
+			   sizeof(hw->vpd.id));
 	numattrs++;
 	csio_append_attrib(&pld, FC_FDMI_HBA_ATTR_MODELDESCRIPTION,
-			   hw->model_desc, (uint16_t)strlen(hw->model_desc));
+			   hw->model_desc, strlen(hw->model_desc));
 	numattrs++;
 	csio_append_attrib(&pld, FC_FDMI_HBA_ATTR_HARDWAREVERSION,
-			   hw->hw_ver, (uint16_t)sizeof(hw->hw_ver));
+			   hw->hw_ver, sizeof(hw->hw_ver));
 	numattrs++;
 	csio_append_attrib(&pld, FC_FDMI_HBA_ATTR_FIRMWAREVERSION,
-			   hw->fwrev_str, (uint16_t)strlen(hw->fwrev_str));
+			   hw->fwrev_str, strlen(hw->fwrev_str));
 	numattrs++;
 
 	if (!csio_osname(buf, sizeof(buf))) {
 		csio_append_attrib(&pld, FC_FDMI_HBA_ATTR_OSNAMEVERSION,
-				   buf, (uint16_t)strlen(buf));
+				   buf, strlen(buf));
 		numattrs++;
 	}
 
 	csio_append_attrib(&pld, FC_FDMI_HBA_ATTR_MAXCTPAYLOAD,
-			   (uint8_t *)&maxpayload,
-			   FC_FDMI_HBA_ATTR_MAXCTPAYLOAD_LEN);
+			   &maxpayload, FC_FDMI_HBA_ATTR_MAXCTPAYLOAD_LEN);
 	len = (uint32_t)(pld - (uint8_t *)cmd);
 	numattrs++;
 	attrib_blk->numattrs = htonl(numattrs);
@@ -1794,6 +1801,8 @@ csio_ln_mgmt_submit_req(struct csio_ioreq *io_req,
 	struct csio_mgmtm *mgmtm = csio_hw_to_mgmtm(hw);
 	int rv;
 
+	BUG_ON(pld_len > pld->len);
+
 	io_req->io_cbfn = io_cbfn;	/* Upper layer callback handler */
 	io_req->fw_handle = (uintptr_t) (io_req);
 	io_req->eq_idx = mgmtm->eq_idx;

drivers/scsi/csiostor/csio_wr.c

@@ -480,12 +480,14 @@ csio_wr_iq_create(struct csio_hw *hw, void *priv, int iq_idx,
 
 	flq_idx = csio_q_iq_flq_idx(hw, iq_idx);
 	if (flq_idx != -1) {
+		enum chip_type chip = CHELSIO_CHIP_VERSION(hw->chip_id);
 		struct csio_q *flq = hw->wrm.q_arr[flq_idx];
 
 		iqp.fl0paden	= 1;
 		iqp.fl0packen	= flq->un.fl.packen ? 1 : 0;
 		iqp.fl0fbmin	= X_FETCHBURSTMIN_64B;
-		iqp.fl0fbmax	= X_FETCHBURSTMAX_512B;
+		iqp.fl0fbmax	= ((chip == CHELSIO_T5) ?
+				  X_FETCHBURSTMAX_512B : X_FETCHBURSTMAX_256B);
 		iqp.fl0size	= csio_q_size(hw, flq_idx) / CSIO_QCREDIT_SZ;
 		iqp.fl0addr	= csio_q_pstart(hw, flq_idx);
 	}

drivers/scsi/cxgbi/cxgb4i/cxgb4i.c

@@ -1608,6 +1608,7 @@ static int init_act_open(struct cxgbi_sock *csk)
 	struct neighbour *n = NULL;
 	void *daddr;
 	unsigned int step;
+	unsigned int rxq_idx;
 	unsigned int size, size6;
 	unsigned int linkspeed;
 	unsigned int rcv_winf, snd_winf;
@@ -1686,7 +1687,9 @@ static int init_act_open(struct cxgbi_sock *csk)
 	step = lldi->ntxq / lldi->nchan;
 	csk->txq_idx = cxgb4_port_idx(ndev) * step;
 	step = lldi->nrxq / lldi->nchan;
-	csk->rss_qid = lldi->rxq_ids[cxgb4_port_idx(ndev) * step];
+	rxq_idx = (cxgb4_port_idx(ndev) * step) + (cdev->rxq_idx_cntr % step);
+	cdev->rxq_idx_cntr++;
+	csk->rss_qid = lldi->rxq_ids[rxq_idx];
 	linkspeed = ((struct port_info *)netdev_priv(ndev))->link_cfg.speed;
 	csk->snd_win = cxgb4i_snd_win;
 	csk->rcv_win = cxgb4i_rcv_win;

drivers/scsi/cxgbi/libcxgbi.h

@@ -477,6 +477,7 @@ struct cxgbi_device {
 	unsigned int skb_rx_extra;	/* for msg coalesced mode */
 	unsigned int tx_max_size;
 	unsigned int rx_max_size;
+	unsigned int rxq_idx_cntr;
 	struct cxgbi_ports_map pmap;
 
 	void (*dev_ddp_cleanup)(struct cxgbi_device *);

drivers/scsi/cxlflash/common.h

@@ -15,6 +15,8 @@
 #ifndef _CXLFLASH_COMMON_H
 #define _CXLFLASH_COMMON_H
 
+#include <linux/async.h>
+#include <linux/cdev.h>
 #include <linux/irq_poll.h>
 #include <linux/list.h>
 #include <linux/rwsem.h>
@@ -85,7 +87,8 @@ enum cxlflash_init_state {
 	INIT_STATE_NONE,
 	INIT_STATE_PCI,
 	INIT_STATE_AFU,
-	INIT_STATE_SCSI
+	INIT_STATE_SCSI,
+	INIT_STATE_CDEV
 };
 
 enum cxlflash_state {
@@ -115,6 +118,8 @@ struct cxlflash_cfg {
 	struct pci_device_id *dev_id;
 	struct Scsi_Host *host;
 	int num_fc_ports;
+	struct cdev cdev;
+	struct device *chardev;
 
 	ulong cxlflash_regs_pci;
 
@@ -142,8 +147,10 @@ struct cxlflash_cfg {
 	wait_queue_head_t tmf_waitq;
 	spinlock_t tmf_slock;
 	bool tmf_active;
+	bool ws_unmap;		/* Write-same unmap supported */
 	wait_queue_head_t reset_waitq;
 	enum cxlflash_state state;
+	async_cookie_t async_reset_cookie;
 };
 
 struct afu_cmd {
@@ -155,7 +162,10 @@ struct afu_cmd {
 	struct list_head queue;
 	u32 hwq_index;
 
-	u8 cmd_tmf:1;
+	u8 cmd_tmf:1,
+	   cmd_aborted:1;
+
+	struct list_head list;	/* Pending commands link */
 
 	/* As per the SISLITE spec the IOARCB EA has to be 16-byte aligned.
 	 * However for performance reasons the IOARCB/IOASA should be
@@ -168,12 +178,20 @@ 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_afuci(struct scsi_cmnd *sc)
+{
+	struct afu_cmd *afuc = sc_to_afuc(sc);
+
+	INIT_LIST_HEAD(&afuc->queue);
+	return afuc;
+}
+
 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;
+	return sc_to_afuci(sc);
 }
 
 struct hwq {
@@ -191,9 +209,10 @@ struct hwq {
 	struct sisl_ctrl_map __iomem *ctrl_map;		/* MC control map */
 	ctx_hndl_t ctx_hndl;	/* master's context handle */
 	u32 index;		/* Index of this hwq */
+	struct list_head pending_cmds;	/* Commands pending completion */
 
 	atomic_t hsq_credits;
-	spinlock_t hsq_slock;
+	spinlock_t hsq_slock;	/* Hardware send queue lock */
 	struct sisl_ioarcb *hsq_start;
 	struct sisl_ioarcb *hsq_end;
 	struct sisl_ioarcb *hsq_curr;
@@ -204,7 +223,6 @@ struct hwq {
 	bool toggle;
 
 	s64 room;
-	spinlock_t rrin_slock; /* Lock to rrin queuing and cmd_room updates */
 
 	struct irq_poll irqpoll;
 } __aligned(cache_line_size());
@@ -212,7 +230,7 @@ struct hwq {
 struct afu {
 	struct hwq hwqs[CXLFLASH_MAX_HWQS];
 	int (*send_cmd)(struct afu *, struct afu_cmd *);
-	void (*context_reset)(struct afu_cmd *);
+	int (*context_reset)(struct hwq *);
 
 	/* AFU HW */
 	struct cxlflash_afu_map __iomem *afu_map;	/* entire MMIO map */
@@ -245,21 +263,31 @@ static inline bool afu_is_irqpoll_enabled(struct afu *afu)
 	return !!afu->irqpoll_weight;
 }
 
-static inline bool afu_is_cmd_mode(struct afu *afu, u64 cmd_mode)
+static inline bool afu_has_cap(struct afu *afu, u64 cap)
 {
 	u64 afu_cap = afu->interface_version >> SISL_INTVER_CAP_SHIFT;
 
-	return afu_cap & cmd_mode;
+	return afu_cap & cap;
+}
+
+static inline bool afu_is_afu_debug(struct afu *afu)
+{
+	return afu_has_cap(afu, SISL_INTVER_CAP_AFU_DEBUG);
+}
+
+static inline bool afu_is_lun_provision(struct afu *afu)
+{
+	return afu_has_cap(afu, SISL_INTVER_CAP_LUN_PROVISION);
 }
 
 static inline bool afu_is_sq_cmd_mode(struct afu *afu)
 {
-	return afu_is_cmd_mode(afu, SISL_INTVER_CAP_SQ_CMD_MODE);
+	return afu_has_cap(afu, SISL_INTVER_CAP_SQ_CMD_MODE);
 }
 
 static inline bool afu_is_ioarrin_cmd_mode(struct afu *afu)
 {
-	return afu_is_cmd_mode(afu, SISL_INTVER_CAP_IOARRIN_CMD_MODE);
+	return afu_has_cap(afu, SISL_INTVER_CAP_IOARRIN_CMD_MODE);
 }
 
 static inline u64 lun_to_lunid(u64 lun)

drivers/scsi/cxlflash/main.c

@@ -34,6 +34,10 @@ MODULE_AUTHOR("Manoj N. Kumar <manoj@linux.vnet.ibm.com>");
 MODULE_AUTHOR("Matthew R. Ochs <mrochs@linux.vnet.ibm.com>");
 MODULE_LICENSE("GPL");
 
+static struct class *cxlflash_class;
+static u32 cxlflash_major;
+static DECLARE_BITMAP(cxlflash_minor, CXLFLASH_MAX_ADAPTERS);
+
 /**
  * process_cmd_err() - command error handler
  * @cmd:	AFU command that experienced the error.
@@ -151,9 +155,10 @@ static void process_cmd_err(struct afu_cmd *cmd, struct scsi_cmnd *scp)
  * cmd_complete() - command completion handler
  * @cmd:	AFU command that has completed.
  *
- * 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
- * (cmd->scp populated) commands.
+ * For SCSI commands this routine prepares and submits commands that have
+ * either completed or timed out to the SCSI stack. For internal commands
+ * (TMF or AFU), this routine simply notifies the originator that the
+ * command has completed.
  */
 static void cmd_complete(struct afu_cmd *cmd)
 {
@@ -162,7 +167,11 @@ static void cmd_complete(struct afu_cmd *cmd)
 	struct afu *afu = cmd->parent;
 	struct cxlflash_cfg *cfg = afu->parent;
 	struct device *dev = &cfg->dev->dev;
-	bool cmd_is_tmf;
+	struct hwq *hwq = get_hwq(afu, cmd->hwq_index);
+
+	spin_lock_irqsave(&hwq->hsq_slock, lock_flags);
+	list_del(&cmd->list);
+	spin_unlock_irqrestore(&hwq->hsq_slock, lock_flags);
 
 	if (cmd->scp) {
 		scp = cmd->scp;
@@ -171,73 +180,124 @@ static void cmd_complete(struct afu_cmd *cmd)
 		else
 			scp->result = (DID_OK << 16);
 
-		cmd_is_tmf = cmd->cmd_tmf;
-
 		dev_dbg_ratelimited(dev, "%s:scp=%p result=%08x ioasc=%08x\n",
 				    __func__, scp, scp->result, cmd->sa.ioasc);
-
 		scp->scsi_done(scp);
-
-		if (cmd_is_tmf) {
-			spin_lock_irqsave(&cfg->tmf_slock, lock_flags);
-			cfg->tmf_active = false;
-			wake_up_all_locked(&cfg->tmf_waitq);
-			spin_unlock_irqrestore(&cfg->tmf_slock, lock_flags);
-		}
+	} else if (cmd->cmd_tmf) {
+		spin_lock_irqsave(&cfg->tmf_slock, lock_flags);
+		cfg->tmf_active = false;
+		wake_up_all_locked(&cfg->tmf_waitq);
+		spin_unlock_irqrestore(&cfg->tmf_slock, lock_flags);
 	} else
 		complete(&cmd->cevent);
 }
 
 /**
- * context_reset() - reset command owner context via specified register
- * @cmd:	AFU command that timed out.
+ * flush_pending_cmds() - flush all pending commands on this hardware queue
+ * @hwq:	Hardware queue to flush.
+ *
+ * The hardware send queue lock associated with this hardware queue must be
+ * held when calling this routine.
+ */
+static void flush_pending_cmds(struct hwq *hwq)
+{
+	struct cxlflash_cfg *cfg = hwq->afu->parent;
+	struct afu_cmd *cmd, *tmp;
+	struct scsi_cmnd *scp;
+	ulong lock_flags;
+
+	list_for_each_entry_safe(cmd, tmp, &hwq->pending_cmds, list) {
+		/* Bypass command when on a doneq, cmd_complete() will handle */
+		if (!list_empty(&cmd->queue))
+			continue;
+
+		list_del(&cmd->list);
+
+		if (cmd->scp) {
+			scp = cmd->scp;
+			scp->result = (DID_IMM_RETRY << 16);
+			scp->scsi_done(scp);
+		} else {
+			cmd->cmd_aborted = true;
+
+			if (cmd->cmd_tmf) {
+				spin_lock_irqsave(&cfg->tmf_slock, lock_flags);
+				cfg->tmf_active = false;
+				wake_up_all_locked(&cfg->tmf_waitq);
+				spin_unlock_irqrestore(&cfg->tmf_slock,
+						       lock_flags);
+			} else
+				complete(&cmd->cevent);
+		}
+	}
+}
+
+/**
+ * context_reset() - reset context via specified register
+ * @hwq:	Hardware queue owning the context to be reset.
  * @reset_reg:	MMIO register to perform reset.
+ *
+ * When the reset is successful, the SISLite specification guarantees that
+ * the AFU has aborted all currently pending I/O. Accordingly, these commands
+ * must be flushed.
+ *
+ * Return: 0 on success, -errno on failure
  */
-static void context_reset(struct afu_cmd *cmd, __be64 __iomem *reset_reg)
+static int context_reset(struct hwq *hwq, __be64 __iomem *reset_reg)
 {
-	int nretry = 0;
-	u64 rrin = 0x1;
-	struct afu *afu = cmd->parent;
-	struct cxlflash_cfg *cfg = afu->parent;
+	struct cxlflash_cfg *cfg = hwq->afu->parent;
 	struct device *dev = &cfg->dev->dev;
+	int rc = -ETIMEDOUT;
+	int nretry = 0;
+	u64 val = 0x1;
+	ulong lock_flags;
 
-	dev_dbg(dev, "%s: cmd=%p\n", __func__, cmd);
+	dev_dbg(dev, "%s: hwq=%p\n", __func__, hwq);
+
+	spin_lock_irqsave(&hwq->hsq_slock, lock_flags);
 
-	writeq_be(rrin, reset_reg);
+	writeq_be(val, reset_reg);
 	do {
-		rrin = readq_be(reset_reg);
-		if (rrin != 0x1)
+		val = readq_be(reset_reg);
+		if ((val & 0x1) == 0x0) {
+			rc = 0;
 			break;
+		}
+
 		/* Double delay each time */
 		udelay(1 << nretry);
 	} while (nretry++ < MC_ROOM_RETRY_CNT);
 
-	dev_dbg(dev, "%s: returning rrin=%016llx nretry=%d\n",
-		__func__, rrin, nretry);
+	if (!rc)
+		flush_pending_cmds(hwq);
+
+	spin_unlock_irqrestore(&hwq->hsq_slock, lock_flags);
+
+	dev_dbg(dev, "%s: returning rc=%d, val=%016llx nretry=%d\n",
+		__func__, rc, val, nretry);
+	return rc;
 }
 
 /**
- * context_reset_ioarrin() - reset command owner context via IOARRIN register
- * @cmd:	AFU command that timed out.
+ * context_reset_ioarrin() - reset context via IOARRIN register
+ * @hwq:	Hardware queue owning the context to be reset.
+ *
+ * Return: 0 on success, -errno on failure
  */
-static void context_reset_ioarrin(struct afu_cmd *cmd)
+static int context_reset_ioarrin(struct hwq *hwq)
 {
-	struct afu *afu = cmd->parent;
-	struct hwq *hwq = get_hwq(afu, cmd->hwq_index);
-
-	context_reset(cmd, &hwq->host_map->ioarrin);
+	return context_reset(hwq, &hwq->host_map->ioarrin);
 }
 
 /**
- * context_reset_sq() - reset command owner context w/ SQ Context Reset register
- * @cmd:	AFU command that timed out.
+ * context_reset_sq() - reset context via SQ_CONTEXT_RESET register
+ * @hwq:	Hardware queue owning the context to be reset.
+ *
+ * Return: 0 on success, -errno on failure
  */
-static void context_reset_sq(struct afu_cmd *cmd)
+static int context_reset_sq(struct hwq *hwq)
 {
-	struct afu *afu = cmd->parent;
-	struct hwq *hwq = get_hwq(afu, cmd->hwq_index);
-
-	context_reset(cmd, &hwq->host_map->sq_ctx_reset);
+	return context_reset(hwq, &hwq->host_map->sq_ctx_reset);
 }
 
 /**
@@ -261,7 +321,7 @@ static int send_cmd_ioarrin(struct afu *afu, struct afu_cmd *cmd)
 	 * To avoid the performance penalty of MMIO, spread the update of
 	 * 'room' over multiple commands.
 	 */
-	spin_lock_irqsave(&hwq->rrin_slock, lock_flags);
+	spin_lock_irqsave(&hwq->hsq_slock, lock_flags);
 	if (--hwq->room < 0) {
 		room = readq_be(&hwq->host_map->cmd_room);
 		if (room <= 0) {
@@ -275,9 +335,10 @@ static int send_cmd_ioarrin(struct afu *afu, struct afu_cmd *cmd)
 		hwq->room = room - 1;
 	}
 
+	list_add(&cmd->list, &hwq->pending_cmds);
 	writeq_be((u64)&cmd->rcb, &hwq->host_map->ioarrin);
 out:
-	spin_unlock_irqrestore(&hwq->rrin_slock, lock_flags);
+	spin_unlock_irqrestore(&hwq->hsq_slock, lock_flags);
 	dev_dbg(dev, "%s: cmd=%p len=%u ea=%016llx rc=%d\n", __func__,
 		cmd, cmd->rcb.data_len, cmd->rcb.data_ea, rc);
 	return rc;
@@ -315,6 +376,8 @@ static int send_cmd_sq(struct afu *afu, struct afu_cmd *cmd)
 		hwq->hsq_curr++;
 	else
 		hwq->hsq_curr = hwq->hsq_start;
+
+	list_add(&cmd->list, &hwq->pending_cmds);
 	writeq_be((u64)hwq->hsq_curr, &hwq->host_map->sq_tail);
 
 	spin_unlock_irqrestore(&hwq->hsq_slock, lock_flags);
@@ -332,8 +395,7 @@ out:
  * @afu:	AFU associated with the host.
  * @cmd:	AFU command that was sent.
  *
- * Return:
- *	0 on success, -1 on timeout/error
+ * Return: 0 on success, -errno on failure
  */
 static int wait_resp(struct afu *afu, struct afu_cmd *cmd)
 {
@@ -343,15 +405,16 @@ static int wait_resp(struct afu *afu, struct afu_cmd *cmd)
 	ulong timeout = msecs_to_jiffies(cmd->rcb.timeout * 2 * 1000);
 
 	timeout = wait_for_completion_timeout(&cmd->cevent, timeout);
-	if (!timeout) {
-		afu->context_reset(cmd);
-		rc = -1;
-	}
+	if (!timeout)
+		rc = -ETIMEDOUT;
+
+	if (cmd->cmd_aborted)
+		rc = -EAGAIN;
 
 	if (unlikely(cmd->sa.ioasc != 0)) {
 		dev_err(dev, "%s: cmd %02x failed, ioasc=%08x\n",
 			__func__, cmd->rcb.cdb[0], cmd->sa.ioasc);
-		rc = -1;
+		rc = -EIO;
 	}
 
 	return rc;
@@ -396,25 +459,35 @@ static u32 cmd_to_target_hwq(struct Scsi_Host *host, struct scsi_cmnd *scp,
 
 /**
  * send_tmf() - sends a Task Management Function (TMF)
- * @afu:	AFU to checkout from.
- * @scp:	SCSI command from stack.
+ * @cfg:	Internal structure associated with the host.
+ * @sdev:	SCSI device destined for TMF.
  * @tmfcmd:	TMF command to send.
  *
  * Return:
- *	0 on success, SCSI_MLQUEUE_HOST_BUSY on failure
+ *	0 on success, SCSI_MLQUEUE_HOST_BUSY or -errno on failure
  */
-static int send_tmf(struct afu *afu, struct scsi_cmnd *scp, u64 tmfcmd)
+static int send_tmf(struct cxlflash_cfg *cfg, struct scsi_device *sdev,
+		    u64 tmfcmd)
 {
-	struct Scsi_Host *host = scp->device->host;
-	struct cxlflash_cfg *cfg = shost_priv(host);
-	struct afu_cmd *cmd = sc_to_afucz(scp);
+	struct afu *afu = cfg->afu;
+	struct afu_cmd *cmd = NULL;
 	struct device *dev = &cfg->dev->dev;
-	int hwq_index = cmd_to_target_hwq(host, scp, afu);
-	struct hwq *hwq = get_hwq(afu, hwq_index);
+	struct hwq *hwq = get_hwq(afu, PRIMARY_HWQ);
+	char *buf = NULL;
 	ulong lock_flags;
 	int rc = 0;
 	ulong to;
 
+	buf = kzalloc(sizeof(*cmd) + __alignof__(*cmd) - 1, GFP_KERNEL);
+	if (unlikely(!buf)) {
+		dev_err(dev, "%s: no memory for command\n", __func__);
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	cmd = (struct afu_cmd *)PTR_ALIGN(buf, __alignof__(*cmd));
+	INIT_LIST_HEAD(&cmd->queue);
+
 	/* When Task Management Function is active do not send another */
 	spin_lock_irqsave(&cfg->tmf_slock, lock_flags);
 	if (cfg->tmf_active)
@@ -424,15 +497,14 @@ static int send_tmf(struct afu *afu, struct scsi_cmnd *scp, u64 tmfcmd)
 	cfg->tmf_active = true;
 	spin_unlock_irqrestore(&cfg->tmf_slock, lock_flags);
 
-	cmd->scp = scp;
 	cmd->parent = afu;
 	cmd->cmd_tmf = true;
-	cmd->hwq_index = hwq_index;
+	cmd->hwq_index = hwq->index;
 
 	cmd->rcb.ctx_id = hwq->ctx_hndl;
 	cmd->rcb.msi = SISL_MSI_RRQ_UPDATED;
-	cmd->rcb.port_sel = CHAN2PORTMASK(scp->device->channel);
-	cmd->rcb.lun_id = lun_to_lunid(scp->device->lun);
+	cmd->rcb.port_sel = CHAN2PORTMASK(sdev->channel);
+	cmd->rcb.lun_id = lun_to_lunid(sdev->lun);
 	cmd->rcb.req_flags = (SISL_REQ_FLAGS_PORT_LUN_ID |
 			      SISL_REQ_FLAGS_SUP_UNDERRUN |
 			      SISL_REQ_FLAGS_TMF_CMD);
@@ -453,12 +525,20 @@ static int send_tmf(struct afu *afu, struct scsi_cmnd *scp, u64 tmfcmd)
 						       cfg->tmf_slock,
 						       to);
 	if (!to) {
-		cfg->tmf_active = false;
 		dev_err(dev, "%s: TMF timed out\n", __func__);
-		rc = -1;
-	}
+		rc = -ETIMEDOUT;
+	} else if (cmd->cmd_aborted) {
+		dev_err(dev, "%s: TMF aborted\n", __func__);
+		rc = -EAGAIN;
+	} else if (cmd->sa.ioasc) {
+		dev_err(dev, "%s: TMF failed ioasc=%08x\n",
+			__func__, cmd->sa.ioasc);
+		rc = -EIO;
+	}
+	cfg->tmf_active = false;
 	spin_unlock_irqrestore(&cfg->tmf_slock, lock_flags);
 out:
+	kfree(buf);
 	return rc;
 }
 
@@ -485,7 +565,7 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 	struct cxlflash_cfg *cfg = shost_priv(host);
 	struct afu *afu = cfg->afu;
 	struct device *dev = &cfg->dev->dev;
-	struct afu_cmd *cmd = sc_to_afucz(scp);
+	struct afu_cmd *cmd = sc_to_afuci(scp);
 	struct scatterlist *sg = scsi_sglist(scp);
 	int hwq_index = cmd_to_target_hwq(host, scp, afu);
 	struct hwq *hwq = get_hwq(afu, hwq_index);
@@ -584,6 +664,20 @@ static void free_mem(struct cxlflash_cfg *cfg)
 	}
 }
 
+/**
+ * cxlflash_reset_sync() - synchronizing point for asynchronous resets
+ * @cfg:	Internal structure associated with the host.
+ */
+static void cxlflash_reset_sync(struct cxlflash_cfg *cfg)
+{
+	if (cfg->async_reset_cookie == 0)
+		return;
+
+	/* Wait until all async calls prior to this cookie have completed */
+	async_synchronize_cookie(cfg->async_reset_cookie + 1);
+	cfg->async_reset_cookie = 0;
+}
+
 /**
  * stop_afu() - stops the AFU command timers and unmaps the MMIO space
  * @cfg:	Internal structure associated with the host.
@@ -600,6 +694,8 @@ static void stop_afu(struct cxlflash_cfg *cfg)
 	int i;
 
 	cancel_work_sync(&cfg->work_q);
+	if (!current_is_async())
+		cxlflash_reset_sync(cfg);
 
 	if (likely(afu)) {
 		while (atomic_read(&afu->cmds_active))
@@ -677,6 +773,7 @@ static void term_mc(struct cxlflash_cfg *cfg, u32 index)
 	struct afu *afu = cfg->afu;
 	struct device *dev = &cfg->dev->dev;
 	struct hwq *hwq;
+	ulong lock_flags;
 
 	if (!afu) {
 		dev_err(dev, "%s: returning with NULL afu\n", __func__);
@@ -694,6 +791,10 @@ static void term_mc(struct cxlflash_cfg *cfg, u32 index)
 	if (index != PRIMARY_HWQ)
 		WARN_ON(cxl_release_context(hwq->ctx));
 	hwq->ctx = NULL;
+
+	spin_lock_irqsave(&hwq->hsq_slock, lock_flags);
+	flush_pending_cmds(hwq);
+	spin_unlock_irqrestore(&hwq->hsq_slock, lock_flags);
 }
 
 /**
@@ -787,6 +888,46 @@ static void notify_shutdown(struct cxlflash_cfg *cfg, bool wait)
 	}
 }
 
+/**
+ * cxlflash_get_minor() - gets the first available minor number
+ *
+ * Return: Unique minor number that can be used to create the character device.
+ */
+static int cxlflash_get_minor(void)
+{
+	int minor;
+	long bit;
+
+	bit = find_first_zero_bit(cxlflash_minor, CXLFLASH_MAX_ADAPTERS);
+	if (bit >= CXLFLASH_MAX_ADAPTERS)
+		return -1;
+
+	minor = bit & MINORMASK;
+	set_bit(minor, cxlflash_minor);
+	return minor;
+}
+
+/**
+ * cxlflash_put_minor() - releases the minor number
+ * @minor:	Minor number that is no longer needed.
+ */
+static void cxlflash_put_minor(int minor)
+{
+	clear_bit(minor, cxlflash_minor);
+}
+
+/**
+ * cxlflash_release_chrdev() - release the character device for the host
+ * @cfg:	Internal structure associated with the host.
+ */
+static void cxlflash_release_chrdev(struct cxlflash_cfg *cfg)
+{
+	device_unregister(cfg->chardev);
+	cfg->chardev = NULL;
+	cdev_del(&cfg->cdev);
+	cxlflash_put_minor(MINOR(cfg->cdev.dev));
+}
+
 /**
  * cxlflash_remove() - PCI entry point to tear down host
  * @pdev:	PCI device associated with the host.
@@ -822,6 +963,8 @@ static void cxlflash_remove(struct pci_dev *pdev)
 	cxlflash_stop_term_user_contexts(cfg);
 
 	switch (cfg->init_state) {
+	case INIT_STATE_CDEV:
+		cxlflash_release_chrdev(cfg);
 	case INIT_STATE_SCSI:
 		cxlflash_term_local_luns(cfg);
 		scsi_remove_host(cfg->host);
@@ -1690,6 +1833,18 @@ static int init_global(struct cxlflash_cfg *cfg)
 			SISL_CTX_CAP_AFU_CMD | SISL_CTX_CAP_GSCSI_CMD),
 			&hwq->ctrl_map->ctx_cap);
 	}
+
+	/*
+	 * Determine write-same unmap support for host by evaluating the unmap
+	 * sector support bit of the context control register associated with
+	 * the primary hardware queue. Note that while this status is reflected
+	 * in a context register, the outcome can be assumed to be host-wide.
+	 */
+	hwq = get_hwq(afu, PRIMARY_HWQ);
+	reg = readq_be(&hwq->host_map->ctx_ctrl);
+	if (reg & SISL_CTX_CTRL_UNMAP_SECTOR)
+		cfg->ws_unmap = true;
+
 	/* Initialize heartbeat */
 	afu->hb = readq_be(&afu->afu_map->global.regs.afu_hb);
 out:
@@ -1722,7 +1877,10 @@ static int start_afu(struct cxlflash_cfg *cfg)
 		hwq->hrrq_end = &hwq->rrq_entry[NUM_RRQ_ENTRY - 1];
 		hwq->hrrq_curr = hwq->hrrq_start;
 		hwq->toggle = 1;
+
+		/* Initialize spin locks */
 		spin_lock_init(&hwq->hrrq_slock);
+		spin_lock_init(&hwq->hsq_slock);
 
 		/* Initialize SQ */
 		if (afu_is_sq_cmd_mode(afu)) {
@@ -1731,7 +1889,6 @@ static int start_afu(struct cxlflash_cfg *cfg)
 			hwq->hsq_end = &hwq->sq[NUM_SQ_ENTRY - 1];
 			hwq->hsq_curr = hwq->hsq_start;
 
-			spin_lock_init(&hwq->hsq_slock);
 			atomic_set(&hwq->hsq_credits, NUM_SQ_ENTRY - 1);
 		}
 
@@ -1821,6 +1978,7 @@ static int init_mc(struct cxlflash_cfg *cfg, u32 index)
 
 	hwq->afu = cfg->afu;
 	hwq->index = index;
+	INIT_LIST_HEAD(&hwq->pending_cmds);
 
 	if (index == PRIMARY_HWQ)
 		ctx = cxl_get_context(cfg->dev);
@@ -1984,7 +2142,6 @@ static int init_afu(struct cxlflash_cfg *cfg)
 	for (i = 0; i < afu->num_hwqs; i++) {
 		hwq = get_hwq(afu, i);
 
-		spin_lock_init(&hwq->rrin_slock);
 		hwq->room = readq_be(&hwq->host_map->cmd_room);
 	}
 
@@ -2003,29 +2160,107 @@ err1:
 }
 
 /**
- * cxlflash_afu_sync() - builds and sends an AFU sync command
+ * afu_reset() - resets the AFU
+ * @cfg:	Internal structure associated with the host.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int afu_reset(struct cxlflash_cfg *cfg)
+{
+	struct device *dev = &cfg->dev->dev;
+	int rc = 0;
+
+	/* Stop the context before the reset. Since the context is
+	 * no longer available restart it after the reset is complete
+	 */
+	term_afu(cfg);
+
+	rc = init_afu(cfg);
+
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
+	return rc;
+}
+
+/**
+ * drain_ioctls() - wait until all currently executing ioctls have completed
+ * @cfg:	Internal structure associated with the host.
+ *
+ * Obtain write access to read/write semaphore that wraps ioctl
+ * handling to 'drain' ioctls currently executing.
+ */
+static void drain_ioctls(struct cxlflash_cfg *cfg)
+{
+	down_write(&cfg->ioctl_rwsem);
+	up_write(&cfg->ioctl_rwsem);
+}
+
+/**
+ * cxlflash_async_reset_host() - asynchronous host reset handler
+ * @data:	Private data provided while scheduling reset.
+ * @cookie:	Cookie that can be used for checkpointing.
+ */
+static void cxlflash_async_reset_host(void *data, async_cookie_t cookie)
+{
+	struct cxlflash_cfg *cfg = data;
+	struct device *dev = &cfg->dev->dev;
+	int rc = 0;
+
+	if (cfg->state != STATE_RESET) {
+		dev_dbg(dev, "%s: Not performing a reset, state=%d\n",
+			__func__, cfg->state);
+		goto out;
+	}
+
+	drain_ioctls(cfg);
+	cxlflash_mark_contexts_error(cfg);
+	rc = afu_reset(cfg);
+	if (rc)
+		cfg->state = STATE_FAILTERM;
+	else
+		cfg->state = STATE_NORMAL;
+	wake_up_all(&cfg->reset_waitq);
+
+out:
+	scsi_unblock_requests(cfg->host);
+}
+
+/**
+ * cxlflash_schedule_async_reset() - schedule an asynchronous host reset
+ * @cfg:	Internal structure associated with the host.
+ */
+static void cxlflash_schedule_async_reset(struct cxlflash_cfg *cfg)
+{
+	struct device *dev = &cfg->dev->dev;
+
+	if (cfg->state != STATE_NORMAL) {
+		dev_dbg(dev, "%s: Not performing reset state=%d\n",
+			__func__, cfg->state);
+		return;
+	}
+
+	cfg->state = STATE_RESET;
+	scsi_block_requests(cfg->host);
+	cfg->async_reset_cookie = async_schedule(cxlflash_async_reset_host,
+						 cfg);
+}
+
+/**
+ * send_afu_cmd() - builds and sends an internal AFU command
  * @afu:	AFU associated with the host.
- * @ctx_hndl_u:	Identifies context requesting sync.
- * @res_hndl_u:	Identifies resource requesting sync.
- * @mode:	Type of sync to issue (lightweight, heavyweight, global).
+ * @rcb:	Pre-populated IOARCB describing command to send.
  *
- * The AFU can only take 1 sync command at a time. This routine enforces this
- * limitation by using a mutex to provide exclusive access to the AFU during
- * the sync. This design point requires calling threads to not be on interrupt
- * context due to the possibility of sleeping during concurrent sync operations.
+ * The AFU can only take one internal AFU command at a time. This limitation is
+ * enforced by using a mutex to provide exclusive access to the AFU during the
+ * operation. This design point requires calling threads to not be on interrupt
+ * context due to the possibility of sleeping during concurrent AFU operations.
  *
- * AFU sync operations are only necessary and allowed when the device is
- * operating normally. When not operating normally, sync requests can occur as
- * part of cleaning up resources associated with an adapter prior to removal.
- * In this scenario, these requests are simply ignored (safe due to the AFU
- * going away).
+ * The command status is optionally passed back to the caller when the caller
+ * populates the IOASA field of the IOARCB with a pointer to an IOASA structure.
  *
  * Return:
- *	0 on success
- *	-1 on failure
+ *	0 on success, -errno on failure
  */
-int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t ctx_hndl_u,
-		      res_hndl_t res_hndl_u, u8 mode)
+static int send_afu_cmd(struct afu *afu, struct sisl_ioarcb *rcb)
 {
 	struct cxlflash_cfg *cfg = afu->parent;
 	struct device *dev = &cfg->dev->dev;
@@ -2033,6 +2268,7 @@ int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t ctx_hndl_u,
 	struct hwq *hwq = get_hwq(afu, PRIMARY_HWQ);
 	char *buf = NULL;
 	int rc = 0;
+	int nretry = 0;
 	static DEFINE_MUTEX(sync_active);
 
 	if (cfg->state != STATE_NORMAL) {
@@ -2043,39 +2279,52 @@ int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t ctx_hndl_u,
 
 	mutex_lock(&sync_active);
 	atomic_inc(&afu->cmds_active);
-	buf = kzalloc(sizeof(*cmd) + __alignof__(*cmd) - 1, GFP_KERNEL);
+	buf = kmalloc(sizeof(*cmd) + __alignof__(*cmd) - 1, GFP_KERNEL);
 	if (unlikely(!buf)) {
 		dev_err(dev, "%s: no memory for command\n", __func__);
-		rc = -1;
+		rc = -ENOMEM;
 		goto out;
 	}
 
 	cmd = (struct afu_cmd *)PTR_ALIGN(buf, __alignof__(*cmd));
+
+retry:
+	memset(cmd, 0, sizeof(*cmd));
+	memcpy(&cmd->rcb, rcb, sizeof(*rcb));
+	INIT_LIST_HEAD(&cmd->queue);
 	init_completion(&cmd->cevent);
 	cmd->parent = afu;
 	cmd->hwq_index = hwq->index;
-
-	dev_dbg(dev, "%s: afu=%p cmd=%p %d\n", __func__, afu, cmd, ctx_hndl_u);
-
-	cmd->rcb.req_flags = SISL_REQ_FLAGS_AFU_CMD;
 	cmd->rcb.ctx_id = hwq->ctx_hndl;
-	cmd->rcb.msi = SISL_MSI_RRQ_UPDATED;
-	cmd->rcb.timeout = MC_AFU_SYNC_TIMEOUT;
-
-	cmd->rcb.cdb[0] = 0xC0;	/* AFU Sync */
-	cmd->rcb.cdb[1] = mode;
 
-	/* The cdb is aligned, no unaligned accessors required */
-	*((__be16 *)&cmd->rcb.cdb[2]) = cpu_to_be16(ctx_hndl_u);
-	*((__be32 *)&cmd->rcb.cdb[4]) = cpu_to_be32(res_hndl_u);
+	dev_dbg(dev, "%s: afu=%p cmd=%p type=%02x nretry=%d\n",
+		__func__, afu, cmd, cmd->rcb.cdb[0], nretry);
 
 	rc = afu->send_cmd(afu, cmd);
-	if (unlikely(rc))
+	if (unlikely(rc)) {
+		rc = -ENOBUFS;
 		goto out;
+	}
 
 	rc = wait_resp(afu, cmd);
-	if (unlikely(rc))
-		rc = -1;
+	switch (rc) {
+	case -ETIMEDOUT:
+		rc = afu->context_reset(hwq);
+		if (rc) {
+			cxlflash_schedule_async_reset(cfg);
+			break;
+		}
+		/* fall through to retry */
+	case -EAGAIN:
+		if (++nretry < 2)
+			goto retry;
+		/* fall through to exit */
+	default:
+		break;
+	}
+
+	if (rcb->ioasa)
+		*rcb->ioasa = cmd->sa;
 out:
 	atomic_dec(&afu->cmds_active);
 	mutex_unlock(&sync_active);
@@ -2085,38 +2334,88 @@ out:
 }
 
 /**
- * afu_reset() - resets the AFU
- * @cfg:	Internal structure associated with the host.
+ * cxlflash_afu_sync() - builds and sends an AFU sync command
+ * @afu:	AFU associated with the host.
+ * @ctx:	Identifies context requesting sync.
+ * @res:	Identifies resource requesting sync.
+ * @mode:	Type of sync to issue (lightweight, heavyweight, global).
  *
- * Return: 0 on success, -errno on failure
+ * AFU sync operations are only necessary and allowed when the device is
+ * operating normally. When not operating normally, sync requests can occur as
+ * part of cleaning up resources associated with an adapter prior to removal.
+ * In this scenario, these requests are simply ignored (safe due to the AFU
+ * going away).
+ *
+ * Return:
+ *	0 on success, -errno on failure
  */
-static int afu_reset(struct cxlflash_cfg *cfg)
+int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t ctx, res_hndl_t res, u8 mode)
 {
+	struct cxlflash_cfg *cfg = afu->parent;
 	struct device *dev = &cfg->dev->dev;
-	int rc = 0;
+	struct sisl_ioarcb rcb = { 0 };
 
-	/* Stop the context before the reset. Since the context is
-	 * no longer available restart it after the reset is complete
-	 */
-	term_afu(cfg);
+	dev_dbg(dev, "%s: afu=%p ctx=%u res=%u mode=%u\n",
+		__func__, afu, ctx, res, mode);
 
-	rc = init_afu(cfg);
+	rcb.req_flags = SISL_REQ_FLAGS_AFU_CMD;
+	rcb.msi = SISL_MSI_RRQ_UPDATED;
+	rcb.timeout = MC_AFU_SYNC_TIMEOUT;
 
-	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
-	return rc;
+	rcb.cdb[0] = SISL_AFU_CMD_SYNC;
+	rcb.cdb[1] = mode;
+	put_unaligned_be16(ctx, &rcb.cdb[2]);
+	put_unaligned_be32(res, &rcb.cdb[4]);
+
+	return send_afu_cmd(afu, &rcb);
 }
 
 /**
- * drain_ioctls() - wait until all currently executing ioctls have completed
- * @cfg:	Internal structure associated with the host.
+ * cxlflash_eh_abort_handler() - abort a SCSI command
+ * @scp:	SCSI command to abort.
  *
- * Obtain write access to read/write semaphore that wraps ioctl
- * handling to 'drain' ioctls currently executing.
+ * CXL Flash devices do not support a single command abort. Reset the context
+ * as per SISLite specification. Flush any pending commands in the hardware
+ * queue before the reset.
+ *
+ * Return: SUCCESS/FAILED as defined in scsi/scsi.h
  */
-static void drain_ioctls(struct cxlflash_cfg *cfg)
+static int cxlflash_eh_abort_handler(struct scsi_cmnd *scp)
 {
-	down_write(&cfg->ioctl_rwsem);
-	up_write(&cfg->ioctl_rwsem);
+	int rc = FAILED;
+	struct Scsi_Host *host = scp->device->host;
+	struct cxlflash_cfg *cfg = shost_priv(host);
+	struct afu_cmd *cmd = sc_to_afuc(scp);
+	struct device *dev = &cfg->dev->dev;
+	struct afu *afu = cfg->afu;
+	struct hwq *hwq = get_hwq(afu, cmd->hwq_index);
+
+	dev_dbg(dev, "%s: (scp=%p) %d/%d/%d/%llu "
+		"cdb=(%08x-%08x-%08x-%08x)\n", __func__, scp, host->host_no,
+		scp->device->channel, scp->device->id, scp->device->lun,
+		get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
+
+	/* When the state is not normal, another reset/reload is in progress.
+	 * Return failed and the mid-layer will invoke host reset handler.
+	 */
+	if (cfg->state != STATE_NORMAL) {
+		dev_dbg(dev, "%s: Invalid state for abort, state=%d\n",
+			__func__, cfg->state);
+		goto out;
+	}
+
+	rc = afu->context_reset(hwq);
+	if (unlikely(rc))
+		goto out;
+
+	rc = SUCCESS;
+
+out:
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
+	return rc;
 }
 
 /**
@@ -2130,24 +2429,18 @@ static void drain_ioctls(struct cxlflash_cfg *cfg)
 static int cxlflash_eh_device_reset_handler(struct scsi_cmnd *scp)
 {
 	int rc = SUCCESS;
-	struct Scsi_Host *host = scp->device->host;
+	struct scsi_device *sdev = scp->device;
+	struct Scsi_Host *host = sdev->host;
 	struct cxlflash_cfg *cfg = shost_priv(host);
 	struct device *dev = &cfg->dev->dev;
-	struct afu *afu = cfg->afu;
 	int rcr = 0;
 
-	dev_dbg(dev, "%s: (scp=%p) %d/%d/%d/%llu "
-		"cdb=(%08x-%08x-%08x-%08x)\n", __func__, scp, host->host_no,
-		scp->device->channel, scp->device->id, scp->device->lun,
-		get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
-		get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
-		get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
-		get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
-
+	dev_dbg(dev, "%s: %d/%d/%d/%llu\n", __func__,
+		host->host_no, sdev->channel, sdev->id, sdev->lun);
 retry:
 	switch (cfg->state) {
 	case STATE_NORMAL:
-		rcr = send_tmf(afu, scp, TMF_LUN_RESET);
+		rcr = send_tmf(cfg, sdev, TMF_LUN_RESET);
 		if (unlikely(rcr))
 			rc = FAILED;
 		break;
@@ -2184,13 +2477,7 @@ static int cxlflash_eh_host_reset_handler(struct scsi_cmnd *scp)
 	struct cxlflash_cfg *cfg = shost_priv(host);
 	struct device *dev = &cfg->dev->dev;
 
-	dev_dbg(dev, "%s: (scp=%p) %d/%d/%d/%llu "
-		"cdb=(%08x-%08x-%08x-%08x)\n", __func__, scp, host->host_no,
-		scp->device->channel, scp->device->id, scp->device->lun,
-		get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
-		get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
-		get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
-		get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
+	dev_dbg(dev, "%s: %d\n", __func__, host->host_no);
 
 	switch (cfg->state) {
 	case STATE_NORMAL:
@@ -2427,7 +2714,14 @@ static ssize_t lun_mode_store(struct device *dev,
 static ssize_t ioctl_version_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
-	return scnprintf(buf, PAGE_SIZE, "%u\n", DK_CXLFLASH_VERSION_0);
+	ssize_t bytes = 0;
+
+	bytes = scnprintf(buf, PAGE_SIZE,
+			  "disk: %u\n", DK_CXLFLASH_VERSION_0);
+	bytes += scnprintf(buf + bytes, PAGE_SIZE - bytes,
+			   "host: %u\n", HT_CXLFLASH_VERSION_0);
+
+	return bytes;
 }
 
 /**
@@ -2833,6 +3127,7 @@ static struct scsi_host_template driver_template = {
 	.ioctl = cxlflash_ioctl,
 	.proc_name = CXLFLASH_NAME,
 	.queuecommand = cxlflash_queuecommand,
+	.eh_abort_handler = cxlflash_eh_abort_handler,
 	.eh_device_reset_handler = cxlflash_eh_device_reset_handler,
 	.eh_host_reset_handler = cxlflash_eh_host_reset_handler,
 	.change_queue_depth = cxlflash_change_queue_depth,
@@ -2922,6 +3217,397 @@ static void cxlflash_worker_thread(struct work_struct *work)
 		scsi_scan_host(cfg->host);
 }
 
+/**
+ * cxlflash_chr_open() - character device open handler
+ * @inode:	Device inode associated with this character device.
+ * @file:	File pointer for this device.
+ *
+ * Only users with admin privileges are allowed to open the character device.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int cxlflash_chr_open(struct inode *inode, struct file *file)
+{
+	struct cxlflash_cfg *cfg;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	cfg = container_of(inode->i_cdev, struct cxlflash_cfg, cdev);
+	file->private_data = cfg;
+
+	return 0;
+}
+
+/**
+ * decode_hioctl() - translates encoded host ioctl to easily identifiable string
+ * @cmd:        The host ioctl command to decode.
+ *
+ * Return: A string identifying the decoded host ioctl.
+ */
+static char *decode_hioctl(int cmd)
+{
+	switch (cmd) {
+	case HT_CXLFLASH_LUN_PROVISION:
+		return __stringify_1(HT_CXLFLASH_LUN_PROVISION);
+	}
+
+	return "UNKNOWN";
+}
+
+/**
+ * cxlflash_lun_provision() - host LUN provisioning handler
+ * @cfg:	Internal structure associated with the host.
+ * @arg:	Kernel copy of userspace ioctl data structure.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int cxlflash_lun_provision(struct cxlflash_cfg *cfg,
+				  struct ht_cxlflash_lun_provision *lunprov)
+{
+	struct afu *afu = cfg->afu;
+	struct device *dev = &cfg->dev->dev;
+	struct sisl_ioarcb rcb;
+	struct sisl_ioasa asa;
+	__be64 __iomem *fc_port_regs;
+	u16 port = lunprov->port;
+	u16 scmd = lunprov->hdr.subcmd;
+	u16 type;
+	u64 reg;
+	u64 size;
+	u64 lun_id;
+	int rc = 0;
+
+	if (!afu_is_lun_provision(afu)) {
+		rc = -ENOTSUPP;
+		goto out;
+	}
+
+	if (port >= cfg->num_fc_ports) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	switch (scmd) {
+	case HT_CXLFLASH_LUN_PROVISION_SUBCMD_CREATE_LUN:
+		type = SISL_AFU_LUN_PROVISION_CREATE;
+		size = lunprov->size;
+		lun_id = 0;
+		break;
+	case HT_CXLFLASH_LUN_PROVISION_SUBCMD_DELETE_LUN:
+		type = SISL_AFU_LUN_PROVISION_DELETE;
+		size = 0;
+		lun_id = lunprov->lun_id;
+		break;
+	case HT_CXLFLASH_LUN_PROVISION_SUBCMD_QUERY_PORT:
+		fc_port_regs = get_fc_port_regs(cfg, port);
+
+		reg = readq_be(&fc_port_regs[FC_MAX_NUM_LUNS / 8]);
+		lunprov->max_num_luns = reg;
+		reg = readq_be(&fc_port_regs[FC_CUR_NUM_LUNS / 8]);
+		lunprov->cur_num_luns = reg;
+		reg = readq_be(&fc_port_regs[FC_MAX_CAP_PORT / 8]);
+		lunprov->max_cap_port = reg;
+		reg = readq_be(&fc_port_regs[FC_CUR_CAP_PORT / 8]);
+		lunprov->cur_cap_port = reg;
+
+		goto out;
+	default:
+		rc = -EINVAL;
+		goto out;
+	}
+
+	memset(&rcb, 0, sizeof(rcb));
+	memset(&asa, 0, sizeof(asa));
+	rcb.req_flags = SISL_REQ_FLAGS_AFU_CMD;
+	rcb.lun_id = lun_id;
+	rcb.msi = SISL_MSI_RRQ_UPDATED;
+	rcb.timeout = MC_LUN_PROV_TIMEOUT;
+	rcb.ioasa = &asa;
+
+	rcb.cdb[0] = SISL_AFU_CMD_LUN_PROVISION;
+	rcb.cdb[1] = type;
+	rcb.cdb[2] = port;
+	put_unaligned_be64(size, &rcb.cdb[8]);
+
+	rc = send_afu_cmd(afu, &rcb);
+	if (rc) {
+		dev_err(dev, "%s: send_afu_cmd failed rc=%d asc=%08x afux=%x\n",
+			__func__, rc, asa.ioasc, asa.afu_extra);
+		goto out;
+	}
+
+	if (scmd == HT_CXLFLASH_LUN_PROVISION_SUBCMD_CREATE_LUN) {
+		lunprov->lun_id = (u64)asa.lunid_hi << 32 | asa.lunid_lo;
+		memcpy(lunprov->wwid, asa.wwid, sizeof(lunprov->wwid));
+	}
+out:
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
+	return rc;
+}
+
+/**
+ * cxlflash_afu_debug() - host AFU debug handler
+ * @cfg:	Internal structure associated with the host.
+ * @arg:	Kernel copy of userspace ioctl data structure.
+ *
+ * For debug requests requiring a data buffer, always provide an aligned
+ * (cache line) buffer to the AFU to appease any alignment requirements.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int cxlflash_afu_debug(struct cxlflash_cfg *cfg,
+			      struct ht_cxlflash_afu_debug *afu_dbg)
+{
+	struct afu *afu = cfg->afu;
+	struct device *dev = &cfg->dev->dev;
+	struct sisl_ioarcb rcb;
+	struct sisl_ioasa asa;
+	char *buf = NULL;
+	char *kbuf = NULL;
+	void __user *ubuf = (__force void __user *)afu_dbg->data_ea;
+	u16 req_flags = SISL_REQ_FLAGS_AFU_CMD;
+	u32 ulen = afu_dbg->data_len;
+	bool is_write = afu_dbg->hdr.flags & HT_CXLFLASH_HOST_WRITE;
+	int rc = 0;
+
+	if (!afu_is_afu_debug(afu)) {
+		rc = -ENOTSUPP;
+		goto out;
+	}
+
+	if (ulen) {
+		req_flags |= SISL_REQ_FLAGS_SUP_UNDERRUN;
+
+		if (ulen > HT_CXLFLASH_AFU_DEBUG_MAX_DATA_LEN) {
+			rc = -EINVAL;
+			goto out;
+		}
+
+		if (unlikely(!access_ok(is_write ? VERIFY_READ : VERIFY_WRITE,
+					ubuf, ulen))) {
+			rc = -EFAULT;
+			goto out;
+		}
+
+		buf = kmalloc(ulen + cache_line_size() - 1, GFP_KERNEL);
+		if (unlikely(!buf)) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
+		kbuf = PTR_ALIGN(buf, cache_line_size());
+
+		if (is_write) {
+			req_flags |= SISL_REQ_FLAGS_HOST_WRITE;
+
+			rc = copy_from_user(kbuf, ubuf, ulen);
+			if (unlikely(rc))
+				goto out;
+		}
+	}
+
+	memset(&rcb, 0, sizeof(rcb));
+	memset(&asa, 0, sizeof(asa));
+
+	rcb.req_flags = req_flags;
+	rcb.msi = SISL_MSI_RRQ_UPDATED;
+	rcb.timeout = MC_AFU_DEBUG_TIMEOUT;
+	rcb.ioasa = &asa;
+
+	if (ulen) {
+		rcb.data_len = ulen;
+		rcb.data_ea = (uintptr_t)kbuf;
+	}
+
+	rcb.cdb[0] = SISL_AFU_CMD_DEBUG;
+	memcpy(&rcb.cdb[4], afu_dbg->afu_subcmd,
+	       HT_CXLFLASH_AFU_DEBUG_SUBCMD_LEN);
+
+	rc = send_afu_cmd(afu, &rcb);
+	if (rc) {
+		dev_err(dev, "%s: send_afu_cmd failed rc=%d asc=%08x afux=%x\n",
+			__func__, rc, asa.ioasc, asa.afu_extra);
+		goto out;
+	}
+
+	if (ulen && !is_write)
+		rc = copy_to_user(ubuf, kbuf, ulen);
+out:
+	kfree(buf);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
+	return rc;
+}
+
+/**
+ * cxlflash_chr_ioctl() - character device IOCTL handler
+ * @file:	File pointer for this device.
+ * @cmd:	IOCTL command.
+ * @arg:	Userspace ioctl data structure.
+ *
+ * A read/write semaphore is used to implement a 'drain' of currently
+ * running ioctls. The read semaphore is taken at the beginning of each
+ * ioctl thread and released upon concluding execution. Additionally the
+ * semaphore should be released and then reacquired in any ioctl execution
+ * path which will wait for an event to occur that is outside the scope of
+ * the ioctl (i.e. an adapter reset). To drain the ioctls currently running,
+ * a thread simply needs to acquire the write semaphore.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static long cxlflash_chr_ioctl(struct file *file, unsigned int cmd,
+			       unsigned long arg)
+{
+	typedef int (*hioctl) (struct cxlflash_cfg *, void *);
+
+	struct cxlflash_cfg *cfg = file->private_data;
+	struct device *dev = &cfg->dev->dev;
+	char buf[sizeof(union cxlflash_ht_ioctls)];
+	void __user *uarg = (void __user *)arg;
+	struct ht_cxlflash_hdr *hdr;
+	size_t size = 0;
+	bool known_ioctl = false;
+	int idx = 0;
+	int rc = 0;
+	hioctl do_ioctl = NULL;
+
+	static const struct {
+		size_t size;
+		hioctl ioctl;
+	} ioctl_tbl[] = {	/* NOTE: order matters here */
+	{ sizeof(struct ht_cxlflash_lun_provision),
+		(hioctl)cxlflash_lun_provision },
+	{ sizeof(struct ht_cxlflash_afu_debug),
+		(hioctl)cxlflash_afu_debug },
+	};
+
+	/* Hold read semaphore so we can drain if needed */
+	down_read(&cfg->ioctl_rwsem);
+
+	dev_dbg(dev, "%s: cmd=%u idx=%d tbl_size=%lu\n",
+		__func__, cmd, idx, sizeof(ioctl_tbl));
+
+	switch (cmd) {
+	case HT_CXLFLASH_LUN_PROVISION:
+	case HT_CXLFLASH_AFU_DEBUG:
+		known_ioctl = true;
+		idx = _IOC_NR(HT_CXLFLASH_LUN_PROVISION) - _IOC_NR(cmd);
+		size = ioctl_tbl[idx].size;
+		do_ioctl = ioctl_tbl[idx].ioctl;
+
+		if (likely(do_ioctl))
+			break;
+
+		/* fall through */
+	default:
+		rc = -EINVAL;
+		goto out;
+	}
+
+	if (unlikely(copy_from_user(&buf, uarg, size))) {
+		dev_err(dev, "%s: copy_from_user() fail "
+			"size=%lu cmd=%d (%s) uarg=%p\n",
+			__func__, size, cmd, decode_hioctl(cmd), uarg);
+		rc = -EFAULT;
+		goto out;
+	}
+
+	hdr = (struct ht_cxlflash_hdr *)&buf;
+	if (hdr->version != HT_CXLFLASH_VERSION_0) {
+		dev_dbg(dev, "%s: Version %u not supported for %s\n",
+			__func__, hdr->version, decode_hioctl(cmd));
+		rc = -EINVAL;
+		goto out;
+	}
+
+	if (hdr->rsvd[0] || hdr->rsvd[1] || hdr->return_flags) {
+		dev_dbg(dev, "%s: Reserved/rflags populated\n", __func__);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	rc = do_ioctl(cfg, (void *)&buf);
+	if (likely(!rc))
+		if (unlikely(copy_to_user(uarg, &buf, size))) {
+			dev_err(dev, "%s: copy_to_user() fail "
+				"size=%lu cmd=%d (%s) uarg=%p\n",
+				__func__, size, cmd, decode_hioctl(cmd), uarg);
+			rc = -EFAULT;
+		}
+
+	/* fall through to exit */
+
+out:
+	up_read(&cfg->ioctl_rwsem);
+	if (unlikely(rc && known_ioctl))
+		dev_err(dev, "%s: ioctl %s (%08X) returned rc=%d\n",
+			__func__, decode_hioctl(cmd), cmd, rc);
+	else
+		dev_dbg(dev, "%s: ioctl %s (%08X) returned rc=%d\n",
+			__func__, decode_hioctl(cmd), cmd, rc);
+	return rc;
+}
+
+/*
+ * Character device file operations
+ */
+static const struct file_operations cxlflash_chr_fops = {
+	.owner          = THIS_MODULE,
+	.open           = cxlflash_chr_open,
+	.unlocked_ioctl	= cxlflash_chr_ioctl,
+	.compat_ioctl	= cxlflash_chr_ioctl,
+};
+
+/**
+ * init_chrdev() - initialize the character device for the host
+ * @cfg:	Internal structure associated with the host.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int init_chrdev(struct cxlflash_cfg *cfg)
+{
+	struct device *dev = &cfg->dev->dev;
+	struct device *char_dev;
+	dev_t devno;
+	int minor;
+	int rc = 0;
+
+	minor = cxlflash_get_minor();
+	if (unlikely(minor < 0)) {
+		dev_err(dev, "%s: Exhausted allowed adapters\n", __func__);
+		rc = -ENOSPC;
+		goto out;
+	}
+
+	devno = MKDEV(cxlflash_major, minor);
+	cdev_init(&cfg->cdev, &cxlflash_chr_fops);
+
+	rc = cdev_add(&cfg->cdev, devno, 1);
+	if (rc) {
+		dev_err(dev, "%s: cdev_add failed rc=%d\n", __func__, rc);
+		goto err1;
+	}
+
+	char_dev = device_create(cxlflash_class, NULL, devno,
+				 NULL, "cxlflash%d", minor);
+	if (IS_ERR(char_dev)) {
+		rc = PTR_ERR(char_dev);
+		dev_err(dev, "%s: device_create failed rc=%d\n",
+			__func__, rc);
+		goto err2;
+	}
+
+	cfg->chardev = char_dev;
+out:
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
+	return rc;
+err2:
+	cdev_del(&cfg->cdev);
+err1:
+	cxlflash_put_minor(minor);
+	goto out;
+}
+
 /**
  * cxlflash_probe() - PCI entry point to add host
  * @pdev:	PCI device associated with the host.
@@ -3032,6 +3718,13 @@ static int cxlflash_probe(struct pci_dev *pdev,
 	}
 	cfg->init_state = INIT_STATE_SCSI;
 
+	rc = init_chrdev(cfg);
+	if (rc) {
+		dev_err(dev, "%s: init_chrdev failed rc=%d\n", __func__, rc);
+		goto out_remove;
+	}
+	cfg->init_state = INIT_STATE_CDEV;
+
 	if (wq_has_sleeper(&cfg->reset_waitq)) {
 		cfg->state = STATE_PROBED;
 		wake_up_all(&cfg->reset_waitq);
@@ -3134,6 +3827,63 @@ static void cxlflash_pci_resume(struct pci_dev *pdev)
 	scsi_unblock_requests(cfg->host);
 }
 
+/**
+ * cxlflash_devnode() - provides devtmpfs for devices in the cxlflash class
+ * @dev:	Character device.
+ * @mode:	Mode that can be used to verify access.
+ *
+ * Return: Allocated string describing the devtmpfs structure.
+ */
+static char *cxlflash_devnode(struct device *dev, umode_t *mode)
+{
+	return kasprintf(GFP_KERNEL, "cxlflash/%s", dev_name(dev));
+}
+
+/**
+ * cxlflash_class_init() - create character device class
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int cxlflash_class_init(void)
+{
+	dev_t devno;
+	int rc = 0;
+
+	rc = alloc_chrdev_region(&devno, 0, CXLFLASH_MAX_ADAPTERS, "cxlflash");
+	if (unlikely(rc)) {
+		pr_err("%s: alloc_chrdev_region failed rc=%d\n", __func__, rc);
+		goto out;
+	}
+
+	cxlflash_major = MAJOR(devno);
+
+	cxlflash_class = class_create(THIS_MODULE, "cxlflash");
+	if (IS_ERR(cxlflash_class)) {
+		rc = PTR_ERR(cxlflash_class);
+		pr_err("%s: class_create failed rc=%d\n", __func__, rc);
+		goto err;
+	}
+
+	cxlflash_class->devnode = cxlflash_devnode;
+out:
+	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	return rc;
+err:
+	unregister_chrdev_region(devno, CXLFLASH_MAX_ADAPTERS);
+	goto out;
+}
+
+/**
+ * cxlflash_class_exit() - destroy character device class
+ */
+static void cxlflash_class_exit(void)
+{
+	dev_t devno = MKDEV(cxlflash_major, 0);
+
+	class_destroy(cxlflash_class);
+	unregister_chrdev_region(devno, CXLFLASH_MAX_ADAPTERS);
+}
+
 static const struct pci_error_handlers cxlflash_err_handler = {
 	.error_detected = cxlflash_pci_error_detected,
 	.slot_reset = cxlflash_pci_slot_reset,
@@ -3159,10 +3909,23 @@ static struct pci_driver cxlflash_driver = {
  */
 static int __init init_cxlflash(void)
 {
+	int rc;
+
 	check_sizes();
 	cxlflash_list_init();
+	rc = cxlflash_class_init();
+	if (unlikely(rc))
+		goto out;
 
-	return pci_register_driver(&cxlflash_driver);
+	rc = pci_register_driver(&cxlflash_driver);
+	if (unlikely(rc))
+		goto err;
+out:
+	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	return rc;
+err:
+	cxlflash_class_exit();
+	goto out;
 }
 
 /**
@@ -3174,6 +3937,7 @@ static void __exit exit_cxlflash(void)
 	cxlflash_free_errpage();
 
 	pci_unregister_driver(&cxlflash_driver);
+	cxlflash_class_exit();
 }
 
 module_init(init_cxlflash);

drivers/scsi/cxlflash/main.h

@@ -22,6 +22,7 @@
 
 #define CXLFLASH_NAME		"cxlflash"
 #define CXLFLASH_ADAPTER_NAME	"IBM POWER CXL Flash Adapter"
+#define CXLFLASH_MAX_ADAPTERS	32
 
 #define PCI_DEVICE_ID_IBM_CORSA		0x04F0
 #define PCI_DEVICE_ID_IBM_FLASH_GT	0x0600
@@ -40,6 +41,10 @@
 /* FC defines */
 #define FC_MTIP_CMDCONFIG 0x010
 #define FC_MTIP_STATUS 0x018
+#define FC_MAX_NUM_LUNS 0x080 /* Max LUNs host can provision for port */
+#define FC_CUR_NUM_LUNS 0x088 /* Cur number LUNs provisioned for port */
+#define FC_MAX_CAP_PORT 0x090 /* Max capacity all LUNs for port (4K blocks) */
+#define FC_CUR_CAP_PORT 0x098 /* Cur capacity all LUNs for port (4K blocks) */
 
 #define FC_PNAME 0x300
 #define FC_CONFIG 0x320
@@ -62,6 +67,8 @@
 
 /* AFU command timeout values */
 #define MC_AFU_SYNC_TIMEOUT	5	/* 5 secs */
+#define MC_LUN_PROV_TIMEOUT	5	/* 5 secs */
+#define MC_AFU_DEBUG_TIMEOUT	5	/* 5 secs */
 
 /* AFU command room retry limit */
 #define MC_ROOM_RETRY_CNT	10

drivers/scsi/cxlflash/sislite.h

@@ -72,6 +72,13 @@ struct sisl_ioarcb {
 	u16 timeout;		/* in units specified by req_flags */
 	u32 rsvd1;
 	u8 cdb[16];		/* must be in big endian */
+#define SISL_AFU_CMD_SYNC		0xC0	/* AFU sync command */
+#define SISL_AFU_CMD_LUN_PROVISION	0xD0	/* AFU LUN provision command */
+#define SISL_AFU_CMD_DEBUG		0xE0	/* AFU debug command */
+
+#define SISL_AFU_LUN_PROVISION_CREATE	0x00	/* LUN provision create type */
+#define SISL_AFU_LUN_PROVISION_DELETE	0x01	/* LUN provision delete type */
+
 	union {
 		u64 reserved;			/* Reserved for IOARRIN mode */
 		struct sisl_ioasa *ioasa;	/* IOASA EA for SQ Mode */
@@ -156,6 +163,7 @@ struct sisl_rc {
 };
 
 #define SISL_SENSE_DATA_LEN     20	/* Sense data length         */
+#define SISL_WWID_DATA_LEN	16	/* WWID data length          */
 
 /*
  * IOASA: 64 bytes & must follow IOARCB, min 16 byte alignment required,
@@ -167,7 +175,12 @@ struct sisl_ioasa {
 		u32 ioasc;
 #define SISL_IOASC_GOOD_COMPLETION        0x00000000U
 	};
-	u32 resid;
+
+	union {
+		u32 resid;
+		u32 lunid_hi;
+	};
+
 	u8 port;
 	u8 afu_extra;
 	/* when afu_rc=0x04, 0x14, 0x31 (_xxx_DMA_ERR):
@@ -190,7 +203,14 @@ struct sisl_ioasa {
 
 	u8 scsi_extra;
 	u8 fc_extra;
-	u8 sense_data[SISL_SENSE_DATA_LEN];
+
+	union {
+		u8 sense_data[SISL_SENSE_DATA_LEN];
+		struct {
+			u32 lunid_lo;
+			u8 wwid[SISL_WWID_DATA_LEN];
+		};
+	};
 
 	/* These fields are defined by the SISlite architecture for the
 	 * host to use as they see fit for their implementation.
@@ -263,6 +283,7 @@ struct sisl_host_map {
 	__be64 rrq_end;		/* write sequence: start followed by end */
 	__be64 cmd_room;
 	__be64 ctx_ctrl;	/* least significant byte or b56:63 is LISN# */
+#define SISL_CTX_CTRL_UNMAP_SECTOR	0x8000000000000000ULL /* b0 */
 	__be64 mbox_w;		/* restricted use */
 	__be64 sq_start;	/* Submission Queue (R/W): write sequence and */
 	__be64 sq_end;		/* inclusion semantics are the same as RRQ    */
@@ -392,6 +413,8 @@ struct sisl_global_regs {
 #define SISL_INTVER_CAP_SQ_CMD_MODE		0x400000000000ULL
 #define SISL_INTVER_CAP_RESERVED_CMD_MODE_A	0x200000000000ULL
 #define SISL_INTVER_CAP_RESERVED_CMD_MODE_B	0x100000000000ULL
+#define SISL_INTVER_CAP_LUN_PROVISION		0x080000000000ULL
+#define SISL_INTVER_CAP_AFU_DEBUG		0x040000000000ULL
 };
 
 #define CXLFLASH_NUM_FC_PORTS_PER_BANK	2	/* fixed # of ports per bank */

drivers/scsi/cxlflash/superpipe.c

@@ -56,6 +56,19 @@ static void marshal_det_to_rele(struct dk_cxlflash_detach *detach,
 	release->context_id = detach->context_id;
 }
 
+/**
+ * marshal_udir_to_rele() - translate udirect to release structure
+ * @udirect:	Source structure from which to translate/copy.
+ * @release:	Destination structure for the translate/copy.
+ */
+static void marshal_udir_to_rele(struct dk_cxlflash_udirect *udirect,
+				 struct dk_cxlflash_release *release)
+{
+	release->hdr = udirect->hdr;
+	release->context_id = udirect->context_id;
+	release->rsrc_handle = udirect->rsrc_handle;
+}
+
 /**
  * cxlflash_free_errpage() - frees resources associated with global error page
  */
@@ -622,6 +635,7 @@ int _cxlflash_disk_release(struct scsi_device *sdev,
 	res_hndl_t rhndl = release->rsrc_handle;
 
 	int rc = 0;
+	int rcr = 0;
 	u64 ctxid = DECODE_CTXID(release->context_id),
 	    rctxid = release->context_id;
 
@@ -686,8 +700,12 @@ int _cxlflash_disk_release(struct scsi_device *sdev,
 		rhte_f1->dw = 0;
 		dma_wmb(); /* Make RHT entry bottom-half clearing visible */
 
-		if (!ctxi->err_recovery_active)
-			cxlflash_afu_sync(afu, ctxid, rhndl, AFU_HW_SYNC);
+		if (!ctxi->err_recovery_active) {
+			rcr = cxlflash_afu_sync(afu, ctxid, rhndl, AFU_HW_SYNC);
+			if (unlikely(rcr))
+				dev_dbg(dev, "%s: AFU sync failed rc=%d\n",
+					__func__, rcr);
+		}
 		break;
 	default:
 		WARN(1, "Unsupported LUN mode!");
@@ -1929,6 +1947,7 @@ static int cxlflash_disk_direct_open(struct scsi_device *sdev, void *arg)
 	struct afu *afu = cfg->afu;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
+	struct dk_cxlflash_release rel = { { 0 }, 0 };
 
 	struct dk_cxlflash_udirect *pphys = (struct dk_cxlflash_udirect *)arg;
 
@@ -1970,13 +1989,18 @@ static int cxlflash_disk_direct_open(struct scsi_device *sdev, void *arg)
 	rsrc_handle = (rhte - ctxi->rht_start);
 
 	rht_format1(rhte, lli->lun_id[sdev->channel], ctxi->rht_perms, port);
-	cxlflash_afu_sync(afu, ctxid, rsrc_handle, AFU_LW_SYNC);
 
 	last_lba = gli->max_lba;
 	pphys->hdr.return_flags = 0;
 	pphys->last_lba = last_lba;
 	pphys->rsrc_handle = rsrc_handle;
 
+	rc = cxlflash_afu_sync(afu, ctxid, rsrc_handle, AFU_LW_SYNC);
+	if (unlikely(rc)) {
+		dev_dbg(dev, "%s: AFU sync failed rc=%d\n", __func__, rc);
+		goto err2;
+	}
+
 out:
 	if (likely(ctxi))
 		put_context(ctxi);
@@ -1984,6 +2008,10 @@ out:
 		__func__, rsrc_handle, rc, last_lba);
 	return rc;
 
+err2:
+	marshal_udir_to_rele(pphys, &rel);
+	_cxlflash_disk_release(sdev, ctxi, &rel);
+	goto out;
 err1:
 	cxlflash_lun_detach(gli);
 	goto out;

drivers/scsi/cxlflash/vlun.c

@@ -446,6 +446,7 @@ static int write_same16(struct scsi_device *sdev,
 	while (left > 0) {
 
 		scsi_cmd[0] = WRITE_SAME_16;
+		scsi_cmd[1] = cfg->ws_unmap ? 0x8 : 0;
 		put_unaligned_be64(offset, &scsi_cmd[2]);
 		put_unaligned_be32(ws_limit < left ? ws_limit : left,
 				   &scsi_cmd[10]);
@@ -594,7 +595,9 @@ static int grow_lxt(struct afu *afu,
 	rhte->lxt_cnt = my_new_size;
 	dma_wmb(); /* Make RHT entry's LXT table size update visible */
 
-	cxlflash_afu_sync(afu, ctxid, rhndl, AFU_LW_SYNC);
+	rc = cxlflash_afu_sync(afu, ctxid, rhndl, AFU_LW_SYNC);
+	if (unlikely(rc))
+		rc = -EAGAIN;
 
 	/* free old lxt if reallocated */
 	if (lxt != lxt_old)
@@ -673,8 +676,11 @@ static int shrink_lxt(struct afu *afu,
 	rhte->lxt_start = lxt;
 	dma_wmb(); /* Make RHT entry's LXT table update visible */
 
-	if (needs_sync)
-		cxlflash_afu_sync(afu, ctxid, rhndl, AFU_HW_SYNC);
+	if (needs_sync) {
+		rc = cxlflash_afu_sync(afu, ctxid, rhndl, AFU_HW_SYNC);
+		if (unlikely(rc))
+			rc = -EAGAIN;
+	}
 
 	if (needs_ws) {
 		/*
@@ -792,6 +798,21 @@ int _cxlflash_vlun_resize(struct scsi_device *sdev,
 		rc = grow_lxt(afu, sdev, ctxid, rhndl, rhte, &new_size);
 	else if (new_size < rhte->lxt_cnt)
 		rc = shrink_lxt(afu, sdev, rhndl, rhte, ctxi, &new_size);
+	else {
+		/*
+		 * Rare case where there is already sufficient space, just
+		 * need to perform a translation sync with the AFU. This
+		 * scenario likely follows a previous sync failure during
+		 * a resize operation. Accordingly, perform the heavyweight
+		 * form of translation sync as it is unknown which type of
+		 * resize failed previously.
+		 */
+		rc = cxlflash_afu_sync(afu, ctxid, rhndl, AFU_HW_SYNC);
+		if (unlikely(rc)) {
+			rc = -EAGAIN;
+			goto out;
+		}
+	}
 
 	resize->hdr.return_flags = 0;
 	resize->last_lba = (new_size * MC_CHUNK_SIZE * gli->blk_len);
@@ -1084,10 +1105,13 @@ static int clone_lxt(struct afu *afu,
 {
 	struct cxlflash_cfg *cfg = afu->parent;
 	struct device *dev = &cfg->dev->dev;
-	struct sisl_lxt_entry *lxt;
+	struct sisl_lxt_entry *lxt = NULL;
+	bool locked = false;
 	u32 ngrps;
 	u64 aun;		/* chunk# allocated by block allocator */
-	int i, j;
+	int j;
+	int i = 0;
+	int rc = 0;
 
 	ngrps = LXT_NUM_GROUPS(rhte_src->lxt_cnt);
 
@@ -1095,33 +1119,29 @@ static int clone_lxt(struct afu *afu,
 		/* allocate new LXTs for clone */
 		lxt = kzalloc((sizeof(*lxt) * LXT_GROUP_SIZE * ngrps),
 				GFP_KERNEL);
-		if (unlikely(!lxt))
-			return -ENOMEM;
+		if (unlikely(!lxt)) {
+			rc = -ENOMEM;
+			goto out;
+		}
 
 		/* copy over */
 		memcpy(lxt, rhte_src->lxt_start,
 		       (sizeof(*lxt) * rhte_src->lxt_cnt));
 
-		/* clone the LBAs in block allocator via ref_cnt */
+		/* clone the LBAs in block allocator via ref_cnt, note that the
+		 * block allocator mutex must be held until it is established
+		 * that this routine will complete without the need for a
+		 * cleanup.
+		 */
 		mutex_lock(&blka->mutex);
+		locked = true;
 		for (i = 0; i < rhte_src->lxt_cnt; i++) {
 			aun = (lxt[i].rlba_base >> MC_CHUNK_SHIFT);
 			if (ba_clone(&blka->ba_lun, aun) == -1ULL) {
-				/* free the clones already made */
-				for (j = 0; j < i; j++) {
-					aun = (lxt[j].rlba_base >>
-					       MC_CHUNK_SHIFT);
-					ba_free(&blka->ba_lun, aun);
-				}
-
-				mutex_unlock(&blka->mutex);
-				kfree(lxt);
-				return -EIO;
+				rc = -EIO;
+				goto err;
 			}
 		}
-		mutex_unlock(&blka->mutex);
-	} else {
-		lxt = NULL;
 	}
 
 	/*
@@ -1136,10 +1156,31 @@ static int clone_lxt(struct afu *afu,
 	rhte->lxt_cnt = rhte_src->lxt_cnt;
 	dma_wmb(); /* Make RHT entry's LXT table size update visible */
 
-	cxlflash_afu_sync(afu, ctxid, rhndl, AFU_LW_SYNC);
+	rc = cxlflash_afu_sync(afu, ctxid, rhndl, AFU_LW_SYNC);
+	if (unlikely(rc)) {
+		rc = -EAGAIN;
+		goto err2;
+	}
 
-	dev_dbg(dev, "%s: returning\n", __func__);
-	return 0;
+out:
+	if (locked)
+		mutex_unlock(&blka->mutex);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
+	return rc;
+err2:
+	/* Reset the RHTE */
+	rhte->lxt_cnt = 0;
+	dma_wmb();
+	rhte->lxt_start = NULL;
+	dma_wmb();
+err:
+	/* free the clones already made */
+	for (j = 0; j < i; j++) {
+		aun = (lxt[j].rlba_base >> MC_CHUNK_SHIFT);
+		ba_free(&blka->ba_lun, aun);
+	}
+	kfree(lxt);
+	goto out;
 }
 
 /**

drivers/scsi/device_handler/scsi_dh_alua.c

@@ -57,7 +57,6 @@
 /* device handler flags */
 #define ALUA_OPTIMIZE_STPG		0x01
 #define ALUA_RTPG_EXT_HDR_UNSUPP	0x02
-#define ALUA_SYNC_STPG			0x04
 /* State machine flags */
 #define ALUA_PG_RUN_RTPG		0x10
 #define ALUA_PG_RUN_STPG		0x20
@@ -70,7 +69,6 @@ MODULE_PARM_DESC(optimize_stpg, "Allow use of a non-optimized path, rather than
 static LIST_HEAD(port_group_list);
 static DEFINE_SPINLOCK(port_group_lock);
 static struct workqueue_struct *kaluad_wq;
-static struct workqueue_struct *kaluad_sync_wq;
 
 struct alua_port_group {
 	struct kref		kref;
@@ -380,8 +378,6 @@ static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h,
 	}
 
 	spin_lock_irqsave(&pg->lock, flags);
-	if (sdev->synchronous_alua)
-		pg->flags |= ALUA_SYNC_STPG;
 	if (pg_updated)
 		list_add_rcu(&h->node, &pg->dh_list);
 	spin_unlock_irqrestore(&pg->lock, flags);
@@ -785,7 +781,6 @@ static void alua_rtpg_work(struct work_struct *work)
 	int err = SCSI_DH_OK;
 	struct alua_queue_data *qdata, *tmp;
 	unsigned long flags;
-	struct workqueue_struct *alua_wq = kaluad_wq;
 
 	spin_lock_irqsave(&pg->lock, flags);
 	sdev = pg->rtpg_sdev;
@@ -796,8 +791,6 @@ static void alua_rtpg_work(struct work_struct *work)
 		kref_put(&pg->kref, release_port_group);
 		return;
 	}
-	if (pg->flags & ALUA_SYNC_STPG)
-		alua_wq = kaluad_sync_wq;
 	pg->flags |= ALUA_PG_RUNNING;
 	if (pg->flags & ALUA_PG_RUN_RTPG) {
 		int state = pg->state;
@@ -810,7 +803,7 @@ static void alua_rtpg_work(struct work_struct *work)
 				pg->flags &= ~ALUA_PG_RUNNING;
 				pg->flags |= ALUA_PG_RUN_RTPG;
 				spin_unlock_irqrestore(&pg->lock, flags);
-				queue_delayed_work(alua_wq, &pg->rtpg_work,
+				queue_delayed_work(kaluad_wq, &pg->rtpg_work,
 						   pg->interval * HZ);
 				return;
 			}
@@ -822,7 +815,7 @@ static void alua_rtpg_work(struct work_struct *work)
 			pg->flags &= ~ALUA_PG_RUNNING;
 			pg->flags |= ALUA_PG_RUN_RTPG;
 			spin_unlock_irqrestore(&pg->lock, flags);
-			queue_delayed_work(alua_wq, &pg->rtpg_work,
+			queue_delayed_work(kaluad_wq, &pg->rtpg_work,
 					   pg->interval * HZ);
 			return;
 		}
@@ -839,7 +832,7 @@ static void alua_rtpg_work(struct work_struct *work)
 			pg->interval = 0;
 			pg->flags &= ~ALUA_PG_RUNNING;
 			spin_unlock_irqrestore(&pg->lock, flags);
-			queue_delayed_work(alua_wq, &pg->rtpg_work,
+			queue_delayed_work(kaluad_wq, &pg->rtpg_work,
 					   pg->interval * HZ);
 			return;
 		}
@@ -874,8 +867,6 @@ static bool alua_rtpg_queue(struct alua_port_group *pg,
 {
 	int start_queue = 0;
 	unsigned long flags;
-	struct workqueue_struct *alua_wq = kaluad_wq;
-
 	if (WARN_ON_ONCE(!pg) || scsi_device_get(sdev))
 		return false;
 
@@ -900,12 +891,10 @@ static bool alua_rtpg_queue(struct alua_port_group *pg,
 		}
 	}
 
-	if (pg->flags & ALUA_SYNC_STPG)
-		alua_wq = kaluad_sync_wq;
 	spin_unlock_irqrestore(&pg->lock, flags);
 
 	if (start_queue) {
-		if (queue_delayed_work(alua_wq, &pg->rtpg_work,
+		if (queue_delayed_work(kaluad_wq, &pg->rtpg_work,
 				msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS)))
 			sdev = NULL;
 		else
@@ -1166,16 +1155,11 @@ static int __init alua_init(void)
 		/* Temporary failure, bypass */
 		return SCSI_DH_DEV_TEMP_BUSY;
 	}
-	kaluad_sync_wq = create_workqueue("kaluad_sync");
-	if (!kaluad_sync_wq) {
-		destroy_workqueue(kaluad_wq);
-		return SCSI_DH_DEV_TEMP_BUSY;
-	}
+
 	r = scsi_register_device_handler(&alua_dh);
 	if (r != 0) {
 		printk(KERN_ERR "%s: Failed to register scsi device handler",
 			ALUA_DH_NAME);
-		destroy_workqueue(kaluad_sync_wq);
 		destroy_workqueue(kaluad_wq);
 	}
 	return r;
@@ -1184,7 +1168,6 @@ static int __init alua_init(void)
 static void __exit alua_exit(void)
 {
 	scsi_unregister_device_handler(&alua_dh);
-	destroy_workqueue(kaluad_sync_wq);
 	destroy_workqueue(kaluad_wq);
 }
 

drivers/scsi/esas2r/esas2r.h

@@ -945,8 +945,8 @@ struct esas2r_adapter {
 	struct list_head vrq_mds_head;
 	struct esas2r_mem_desc *vrq_mds;
 	int num_vrqs;
-	struct semaphore fm_api_semaphore;
-	struct semaphore fs_api_semaphore;
+	struct mutex fm_api_mutex;
+	struct mutex fs_api_mutex;
 	struct semaphore nvram_semaphore;
 	struct atto_ioctl *local_atto_ioctl;
 	u8 fw_coredump_buff[ESAS2R_FWCOREDUMP_SZ];

drivers/scsi/esas2r/esas2r_init.c

@@ -327,8 +327,8 @@ int esas2r_init_adapter(struct Scsi_Host *host, struct pci_dev *pcid,
 	esas2r_debug("new adapter %p, name %s", a, a->name);
 	spin_lock_init(&a->request_lock);
 	spin_lock_init(&a->fw_event_lock);
-	sema_init(&a->fm_api_semaphore, 1);
-	sema_init(&a->fs_api_semaphore, 1);
+	mutex_init(&a->fm_api_mutex);
+	mutex_init(&a->fs_api_mutex);
 	sema_init(&a->nvram_semaphore, 1);
 
 	esas2r_fw_event_off(a);

drivers/scsi/esas2r/esas2r_ioctl.c

@@ -110,7 +110,7 @@ static void do_fm_api(struct esas2r_adapter *a, struct esas2r_flash_img *fi)
 {
 	struct esas2r_request *rq;
 
-	if (down_interruptible(&a->fm_api_semaphore)) {
+	if (mutex_lock_interruptible(&a->fm_api_mutex)) {
 		fi->status = FI_STAT_BUSY;
 		return;
 	}
@@ -173,7 +173,7 @@ all_done:
 free_req:
 	esas2r_free_request(a, (struct esas2r_request *)rq);
 free_sem:
-	up(&a->fm_api_semaphore);
+	mutex_unlock(&a->fm_api_mutex);
 	return;
 
 }
@@ -1962,7 +1962,7 @@ int esas2r_read_fs(struct esas2r_adapter *a, char *buf, long off, int count)
 			(struct esas2r_ioctl_fs *)a->fs_api_buffer;
 
 		/* If another flash request is already in progress, return. */
-		if (down_interruptible(&a->fs_api_semaphore)) {
+		if (mutex_lock_interruptible(&a->fs_api_mutex)) {
 busy:
 			fs->status = ATTO_STS_OUT_OF_RSRC;
 			return -EBUSY;
@@ -1978,7 +1978,7 @@ busy:
 		rq = esas2r_alloc_request(a);
 		if (rq == NULL) {
 			esas2r_debug("esas2r_read_fs: out of requests");
-			up(&a->fs_api_semaphore);
+			mutex_unlock(&a->fs_api_mutex);
 			goto busy;
 		}
 
@@ -2006,7 +2006,7 @@ busy:
 		;
 dont_wait:
 		/* Free the request and keep going */
-		up(&a->fs_api_semaphore);
+		mutex_unlock(&a->fs_api_mutex);
 		esas2r_free_request(a, (struct esas2r_request *)rq);
 
 		/* Pick up possible error code from above */

drivers/scsi/fcoe/fcoe.c

@@ -519,7 +519,7 @@ static void fcoe_interface_cleanup(struct fcoe_interface *fcoe)
  * @skb:      The receive skb
  * @netdev:   The associated net device
  * @ptype:    The packet_type structure which was used to register this handler
- * @orig_dev: The original net_device the the skb was received on.
+ * @orig_dev: The original net_device the skb was received on.
  *	      (in case dev is a bond)
  *
  * Returns: 0 for success
@@ -542,7 +542,7 @@ static int fcoe_fip_recv(struct sk_buff *skb, struct net_device *netdev,
  * @skb:      The receive skb
  * @netdev:   The associated net device
  * @ptype:    The packet_type structure which was used to register this handler
- * @orig_dev: The original net_device the the skb was received on.
+ * @orig_dev: The original net_device the skb was received on.
  *	      (in case dev is a bond)
  *
  * Returns: 0 for success
@@ -2258,7 +2258,7 @@ static int _fcoe_create(struct net_device *netdev, enum fip_mode fip_mode,
 		fcoe_interface_cleanup(fcoe);
 		mutex_unlock(&fcoe_config_mutex);
 		fcoe_ctlr_device_delete(ctlr_dev);
-		goto out;
+		return rc;
 	}
 
 	/* Make this the "master" N_Port */
@@ -2299,7 +2299,7 @@ static int _fcoe_create(struct net_device *netdev, enum fip_mode fip_mode,
 out_nodev:
 	rtnl_unlock();
 	mutex_unlock(&fcoe_config_mutex);
-out:
+
 	return rc;
 }
 
@@ -2590,7 +2590,7 @@ module_exit(fcoe_exit);
  * fcoe_flogi_resp() - FCoE specific FLOGI and FDISC response handler
  * @seq: active sequence in the FLOGI or FDISC exchange
  * @fp: response frame, or error encoded in a pointer (timeout)
- * @arg: pointer the the fcoe_ctlr structure
+ * @arg: pointer to the fcoe_ctlr structure
  *
  * This handles MAC address management for FCoE, then passes control on to
  * the libfc FLOGI response handler.
@@ -2619,7 +2619,7 @@ done:
  * fcoe_logo_resp() - FCoE specific LOGO response handler
  * @seq: active sequence in the LOGO exchange
  * @fp: response frame, or error encoded in a pointer (timeout)
- * @arg: pointer the the fcoe_ctlr structure
+ * @arg: pointer to the fcoe_ctlr structure
  *
  * This handles MAC address management for FCoE, then passes control on to
  * the libfc LOGO response handler.

drivers/scsi/fnic/fnic_debugfs.c

@@ -632,6 +632,7 @@ static ssize_t fnic_reset_stats_write(struct file *file,
 			sizeof(struct io_path_stats) - sizeof(u64));
 		memset(fw_stats_p+1, 0,
 			sizeof(struct fw_stats) - sizeof(u64));
+		getnstimeofday(&stats->stats_timestamps.last_reset_time);
 	}
 
 	(*ppos)++;

drivers/scsi/fnic/fnic_fcs.c

@@ -65,6 +65,30 @@ void fnic_handle_link(struct work_struct *work)
 	fnic->link_status = vnic_dev_link_status(fnic->vdev);
 	fnic->link_down_cnt = vnic_dev_link_down_cnt(fnic->vdev);
 
+	switch (vnic_dev_port_speed(fnic->vdev)) {
+	case DCEM_PORTSPEED_10G:
+		fc_host_speed(fnic->lport->host)   = FC_PORTSPEED_10GBIT;
+		fnic->lport->link_supported_speeds = FC_PORTSPEED_10GBIT;
+		break;
+	case DCEM_PORTSPEED_25G:
+		fc_host_speed(fnic->lport->host)   = FC_PORTSPEED_25GBIT;
+		fnic->lport->link_supported_speeds = FC_PORTSPEED_25GBIT;
+		break;
+	case DCEM_PORTSPEED_40G:
+	case DCEM_PORTSPEED_4x10G:
+		fc_host_speed(fnic->lport->host)   = FC_PORTSPEED_40GBIT;
+		fnic->lport->link_supported_speeds = FC_PORTSPEED_40GBIT;
+		break;
+	case DCEM_PORTSPEED_100G:
+		fc_host_speed(fnic->lport->host)   = FC_PORTSPEED_100GBIT;
+		fnic->lport->link_supported_speeds = FC_PORTSPEED_100GBIT;
+		break;
+	default:
+		fc_host_speed(fnic->lport->host)   = FC_PORTSPEED_UNKNOWN;
+		fnic->lport->link_supported_speeds = FC_PORTSPEED_UNKNOWN;
+		break;
+	}
+
 	if (old_link_status == fnic->link_status) {
 		if (!fnic->link_status) {
 			/* DOWN -> DOWN */

drivers/scsi/fnic/fnic_io.h

@@ -66,4 +66,13 @@ struct fnic_io_req {
 	struct completion *dr_done; /* completion for device reset */
 };
 
+enum fnic_port_speeds {
+	DCEM_PORTSPEED_NONE = 0,
+	DCEM_PORTSPEED_1G    = 1000,
+	DCEM_PORTSPEED_10G   = 10000,
+	DCEM_PORTSPEED_40G   = 40000,
+	DCEM_PORTSPEED_4x10G = 41000,
+	DCEM_PORTSPEED_25G   = 25000,
+	DCEM_PORTSPEED_100G  = 100000,
+};
 #endif /* _FNIC_IO_H_ */

drivers/scsi/fnic/fnic_main.c

@@ -176,11 +176,21 @@ static void fnic_get_host_speed(struct Scsi_Host *shost)
 
 	/* Add in other values as they get defined in fw */
 	switch (port_speed) {
-	case 10000:
+	case DCEM_PORTSPEED_10G:
 		fc_host_speed(shost) = FC_PORTSPEED_10GBIT;
 		break;
+	case DCEM_PORTSPEED_25G:
+		fc_host_speed(shost) = FC_PORTSPEED_25GBIT;
+		break;
+	case DCEM_PORTSPEED_40G:
+	case DCEM_PORTSPEED_4x10G:
+		fc_host_speed(shost) = FC_PORTSPEED_40GBIT;
+		break;
+	case DCEM_PORTSPEED_100G:
+		fc_host_speed(shost) = FC_PORTSPEED_100GBIT;
+		break;
 	default:
-		fc_host_speed(shost) = FC_PORTSPEED_10GBIT;
+		fc_host_speed(shost) = FC_PORTSPEED_UNKNOWN;
 		break;
 	}
 }

drivers/scsi/fnic/fnic_scsi.c

@@ -466,15 +466,27 @@ static int fnic_queuecommand_lck(struct scsi_cmnd *sc, void (*done)(struct scsi_
 	}
 
 	rp = rport->dd_data;
-	if (!rp || rp->rp_state != RPORT_ST_READY) {
+	if (!rp || rp->rp_state == RPORT_ST_DELETE) {
 		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
-				"returning DID_NO_CONNECT for IO as rport is removed\n");
+			"rport 0x%x removed, returning DID_NO_CONNECT\n",
+			rport->port_id);
+
 		atomic64_inc(&fnic_stats->misc_stats.rport_not_ready);
 		sc->result = DID_NO_CONNECT<<16;
 		done(sc);
 		return 0;
 	}
 
+	if (rp->rp_state != RPORT_ST_READY) {
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+			"rport 0x%x in state 0x%x, returning DID_IMM_RETRY\n",
+			rport->port_id, rp->rp_state);
+
+		sc->result = DID_IMM_RETRY << 16;
+		done(sc);
+		return 0;
+	}
+
 	if (lp->state != LPORT_ST_READY || !(lp->link_up))
 		return SCSI_MLQUEUE_HOST_BUSY;
 
@@ -633,6 +645,7 @@ static int fnic_fcpio_fw_reset_cmpl_handler(struct fnic *fnic,
 
 	atomic64_set(&fnic->fnic_stats.fw_stats.active_fw_reqs, 0);
 	atomic64_set(&fnic->fnic_stats.io_stats.active_ios, 0);
+	atomic64_set(&fnic->io_cmpl_skip, 0);
 
 	spin_lock_irqsave(&fnic->fnic_lock, flags);
 

drivers/scsi/fnic/fnic_stats.h

@@ -16,6 +16,12 @@
  */
 #ifndef _FNIC_STATS_H_
 #define _FNIC_STATS_H_
+
+struct stats_timestamps {
+	struct timespec last_reset_time;
+	struct timespec last_read_time;
+};
+
 struct io_path_stats {
 	atomic64_t active_ios;
 	atomic64_t max_active_ios;
@@ -110,6 +116,7 @@ struct misc_stats {
 };
 
 struct fnic_stats {
+	struct stats_timestamps stats_timestamps;
 	struct io_path_stats io_stats;
 	struct abort_stats abts_stats;
 	struct terminate_stats term_stats;

drivers/scsi/fnic/fnic_trace.c

@@ -219,7 +219,31 @@ int fnic_get_stats_data(struct stats_debug_info *debug,
 	int buf_size = debug->buf_size;
 	struct timespec val1, val2;
 
+	getnstimeofday(&val1);
 	len = snprintf(debug->debug_buffer + len, buf_size - len,
+		"------------------------------------------\n"
+		 "\t\tTime\n"
+		"------------------------------------------\n");
+
+	len += snprintf(debug->debug_buffer + len, buf_size - len,
+		"Current time :          [%ld:%ld]\n"
+		"Last stats reset time:  [%ld:%ld]\n"
+		"Last stats read time:   [%ld:%ld]\n"
+		"delta since last reset: [%ld:%ld]\n"
+		"delta since last read:  [%ld:%ld]\n",
+	val1.tv_sec, val1.tv_nsec,
+	stats->stats_timestamps.last_reset_time.tv_sec,
+	stats->stats_timestamps.last_reset_time.tv_nsec,
+	stats->stats_timestamps.last_read_time.tv_sec,
+	stats->stats_timestamps.last_read_time.tv_nsec,
+	timespec_sub(val1, stats->stats_timestamps.last_reset_time).tv_sec,
+	timespec_sub(val1, stats->stats_timestamps.last_reset_time).tv_nsec,
+	timespec_sub(val1, stats->stats_timestamps.last_read_time).tv_sec,
+	timespec_sub(val1, stats->stats_timestamps.last_read_time).tv_nsec);
+
+	stats->stats_timestamps.last_read_time = val1;
+
+	len += snprintf(debug->debug_buffer + len, buf_size - len,
 		  "------------------------------------------\n"
 		  "\t\tIO Statistics\n"
 		  "------------------------------------------\n");

drivers/scsi/hisi_sas/Kconfig

@@ -6,4 +6,12 @@ config SCSI_HISI_SAS
 	select BLK_DEV_INTEGRITY
 	depends on ATA
 	help
-		This driver supports HiSilicon's SAS HBA
+		This driver supports HiSilicon's SAS HBA, including support based
+		on platform device
+
+config SCSI_HISI_SAS_PCI
+	tristate "HiSilicon SAS on PCI bus"
+	depends on SCSI_HISI_SAS
+	depends on PCI
+	help
+		This driver supports HiSilicon's SAS HBA based on PCI device

drivers/scsi/hisi_sas/Makefile

@@ -1,2 +1,3 @@
 obj-$(CONFIG_SCSI_HISI_SAS)		+= hisi_sas_main.o
 obj-$(CONFIG_SCSI_HISI_SAS)		+= hisi_sas_v1_hw.o hisi_sas_v2_hw.o
+obj-$(CONFIG_SCSI_HISI_SAS_PCI)		+= hisi_sas_v3_hw.o

drivers/scsi/hisi_sas/hisi_sas.h

@@ -18,6 +18,7 @@
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
+#include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/property.h>
 #include <linux/regmap.h>
@@ -33,10 +34,24 @@
 #define HISI_SAS_MAX_DEVICES HISI_SAS_MAX_ITCT_ENTRIES
 #define HISI_SAS_RESET_BIT	0
 
-#define HISI_SAS_STATUS_BUF_SZ \
-		(sizeof(struct hisi_sas_err_record) + 1024)
-#define HISI_SAS_COMMAND_TABLE_SZ \
-		(((sizeof(union hisi_sas_command_table)+3)/4)*4)
+#define HISI_SAS_STATUS_BUF_SZ (sizeof(struct hisi_sas_status_buffer))
+#define HISI_SAS_COMMAND_TABLE_SZ (sizeof(union hisi_sas_command_table))
+
+#define hisi_sas_status_buf_addr(buf) \
+	(buf + offsetof(struct hisi_sas_slot_buf_table, status_buffer))
+#define hisi_sas_status_buf_addr_mem(slot) hisi_sas_status_buf_addr(slot->buf)
+#define hisi_sas_status_buf_addr_dma(slot) \
+	hisi_sas_status_buf_addr(slot->buf_dma)
+
+#define hisi_sas_cmd_hdr_addr(buf) \
+	(buf + offsetof(struct hisi_sas_slot_buf_table, command_header))
+#define hisi_sas_cmd_hdr_addr_mem(slot) hisi_sas_cmd_hdr_addr(slot->buf)
+#define hisi_sas_cmd_hdr_addr_dma(slot) hisi_sas_cmd_hdr_addr(slot->buf_dma)
+
+#define hisi_sas_sge_addr(buf) \
+	(buf + offsetof(struct hisi_sas_slot_buf_table, sge_page))
+#define hisi_sas_sge_addr_mem(slot) hisi_sas_sge_addr(slot->buf)
+#define hisi_sas_sge_addr_dma(slot) hisi_sas_sge_addr(slot->buf_dma)
 
 #define HISI_SAS_MAX_SSP_RESP_SZ (sizeof(struct ssp_frame_hdr) + 1024)
 #define HISI_SAS_MAX_SMP_RESP_SZ 1028
@@ -46,6 +61,12 @@
 	((type == SAS_EDGE_EXPANDER_DEVICE) || \
 	(type == SAS_FANOUT_EXPANDER_DEVICE))
 
+#define HISI_SAS_SATA_PROTOCOL_NONDATA		0x1
+#define HISI_SAS_SATA_PROTOCOL_PIO			0x2
+#define HISI_SAS_SATA_PROTOCOL_DMA			0x4
+#define HISI_SAS_SATA_PROTOCOL_FPDMA		0x8
+#define HISI_SAS_SATA_PROTOCOL_ATAPI		0x10
+
 struct hisi_hba;
 
 enum {
@@ -78,11 +99,11 @@ struct hisi_sas_phy {
 	struct work_struct	phyup_ws;
 	u64		port_id; /* from hw */
 	u64		dev_sas_addr;
-	u64		phy_type;
 	u64		frame_rcvd_size;
 	u8		frame_rcvd[32];
 	u8		phy_attached;
 	u8		reserved[3];
+	u32		phy_type;
 	enum sas_linkrate	minimum_linkrate;
 	enum sas_linkrate	maximum_linkrate;
 };
@@ -102,20 +123,23 @@ struct hisi_sas_cq {
 
 struct hisi_sas_dq {
 	struct hisi_hba *hisi_hba;
+	struct hisi_sas_slot	*slot_prep;
+	spinlock_t lock;
 	int	wr_point;
 	int	id;
 };
 
 struct hisi_sas_device {
-	enum sas_device_type	dev_type;
 	struct hisi_hba		*hisi_hba;
 	struct domain_device	*sas_device;
+	struct hisi_sas_dq	*dq;
+	struct list_head	list;
 	u64 attached_phy;
-	u64 device_id;
 	atomic64_t running_req;
-	struct list_head	list;
-	u8 dev_status;
+	enum sas_device_type	dev_type;
+	int device_id;
 	int sata_idx;
+	u8 dev_status;
 };
 
 struct hisi_sas_slot {
@@ -129,14 +153,10 @@ struct hisi_sas_slot {
 	int	cmplt_queue_slot;
 	int	idx;
 	int	abort;
+	void	*buf;
+	dma_addr_t buf_dma;
 	void	*cmd_hdr;
 	dma_addr_t cmd_hdr_dma;
-	void	*status_buffer;
-	dma_addr_t status_buffer_dma;
-	void *command_table;
-	dma_addr_t command_table_dma;
-	struct hisi_sas_sge_page *sge_page;
-	dma_addr_t sge_page_dma;
 	struct work_struct abort_slot;
 	struct timer_list internal_abort_timer;
 };
@@ -154,9 +174,8 @@ 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, u32 dev_id,
-			int *q, int *s);
-	void (*start_delivery)(struct hisi_hba *hisi_hba);
+	int (*get_free_slot)(struct hisi_hba *hisi_hba, struct hisi_sas_dq *dq);
+	void (*start_delivery)(struct hisi_sas_dq *dq);
 	int (*prep_ssp)(struct hisi_hba *hisi_hba,
 			struct hisi_sas_slot *slot, int is_tmf,
 			struct hisi_sas_tmf_task *tmf);
@@ -179,6 +198,8 @@ struct hisi_sas_hw {
 	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);
+	void (*dereg_device)(struct hisi_hba *hisi_hba,
+				struct domain_device *device);
 	int (*soft_reset)(struct hisi_hba *hisi_hba);
 	int max_command_entries;
 	int complete_hdr_size;
@@ -188,7 +209,10 @@ struct hisi_hba {
 	/* This must be the first element, used by SHOST_TO_SAS_HA */
 	struct sas_ha_struct *p;
 
-	struct platform_device *pdev;
+	struct platform_device *platform_dev;
+	struct pci_dev *pci_dev;
+	struct device *dev;
+
 	void __iomem *regs;
 	struct regmap *ctrl;
 	u32 ctrl_reset_reg;
@@ -217,12 +241,9 @@ struct hisi_hba {
 	struct hisi_sas_port port[HISI_SAS_MAX_PHYS];
 
 	int	queue_count;
-	struct hisi_sas_slot	*slot_prep;
 
-	struct dma_pool *sge_page_pool;
+	struct dma_pool *buffer_pool;
 	struct hisi_sas_device	devices[HISI_SAS_MAX_DEVICES];
-	struct dma_pool *command_table_pool;
-	struct dma_pool *status_buffer_pool;
 	struct hisi_sas_cmd_hdr	*cmd_hdr[HISI_SAS_MAX_QUEUES];
 	dma_addr_t cmd_hdr_dma[HISI_SAS_MAX_QUEUES];
 	void *complete_hdr[HISI_SAS_MAX_QUEUES];
@@ -334,7 +355,7 @@ struct hisi_sas_command_table_stp {
 #define HISI_SAS_SGE_PAGE_CNT SG_CHUNK_SIZE
 struct hisi_sas_sge_page {
 	struct hisi_sas_sge sge[HISI_SAS_SGE_PAGE_CNT];
-};
+}  __aligned(16);
 
 struct hisi_sas_command_table_ssp {
 	struct ssp_frame_hdr hdr;
@@ -353,9 +374,31 @@ union hisi_sas_command_table {
 	struct hisi_sas_command_table_ssp ssp;
 	struct hisi_sas_command_table_smp smp;
 	struct hisi_sas_command_table_stp stp;
+}  __aligned(16);
+
+struct hisi_sas_status_buffer {
+	struct hisi_sas_err_record err;
+	u8	iu[1024];
+}  __aligned(16);
+
+struct hisi_sas_slot_buf_table {
+	struct hisi_sas_status_buffer status_buffer;
+	union hisi_sas_command_table command_header;
+	struct hisi_sas_sge_page sge_page;
 };
 
+extern struct scsi_transport_template *hisi_sas_stt;
+extern struct scsi_host_template *hisi_sas_sht;
+
+extern void hisi_sas_init_add(struct hisi_hba *hisi_hba);
+extern int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost);
+extern void hisi_sas_free(struct hisi_hba *hisi_hba);
+extern u8 hisi_sas_get_ata_protocol(u8 cmd, int direction);
 extern struct hisi_sas_port *to_hisi_sas_port(struct asd_sas_port *sas_port);
+extern void hisi_sas_sata_done(struct sas_task *task,
+			    struct hisi_sas_slot *slot);
+extern int hisi_sas_get_ncq_tag(struct sas_task *task, u32 *tag);
+extern int hisi_sas_get_fw_info(struct hisi_hba *hisi_hba);
 extern int hisi_sas_probe(struct platform_device *pdev,
 			  const struct hisi_sas_hw *ops);
 extern int hisi_sas_remove(struct platform_device *pdev);

drivers/scsi/hisi_sas/hisi_sas_main.c

@@ -23,6 +23,97 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 			     int abort_flag, int tag);
 static int hisi_sas_softreset_ata_disk(struct domain_device *device);
 
+u8 hisi_sas_get_ata_protocol(u8 cmd, int direction)
+{
+	switch (cmd) {
+	case ATA_CMD_FPDMA_WRITE:
+	case ATA_CMD_FPDMA_READ:
+	case ATA_CMD_FPDMA_RECV:
+	case ATA_CMD_FPDMA_SEND:
+	case ATA_CMD_NCQ_NON_DATA:
+	return HISI_SAS_SATA_PROTOCOL_FPDMA;
+
+	case ATA_CMD_DOWNLOAD_MICRO:
+	case ATA_CMD_ID_ATA:
+	case ATA_CMD_PMP_READ:
+	case ATA_CMD_READ_LOG_EXT:
+	case ATA_CMD_PIO_READ:
+	case ATA_CMD_PIO_READ_EXT:
+	case ATA_CMD_PMP_WRITE:
+	case ATA_CMD_WRITE_LOG_EXT:
+	case ATA_CMD_PIO_WRITE:
+	case ATA_CMD_PIO_WRITE_EXT:
+	return HISI_SAS_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 HISI_SAS_SATA_PROTOCOL_DMA;
+
+	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:
+	case ATA_CMD_VERIFY_EXT:
+	case ATA_CMD_SET_FEATURES:
+	case ATA_CMD_STANDBY:
+	case ATA_CMD_STANDBYNOW1:
+	return HISI_SAS_SATA_PROTOCOL_NONDATA;
+	default:
+		if (direction == DMA_NONE)
+			return HISI_SAS_SATA_PROTOCOL_NONDATA;
+		return HISI_SAS_SATA_PROTOCOL_PIO;
+	}
+}
+EXPORT_SYMBOL_GPL(hisi_sas_get_ata_protocol);
+
+void hisi_sas_sata_done(struct sas_task *task,
+			    struct hisi_sas_slot *slot)
+{
+	struct task_status_struct *ts = &task->task_status;
+	struct ata_task_resp *resp = (struct ata_task_resp *)ts->buf;
+	struct hisi_sas_status_buffer *status_buf =
+			hisi_sas_status_buf_addr_mem(slot);
+	u8 *iu = &status_buf->iu[0];
+	struct dev_to_host_fis *d2h =  (struct dev_to_host_fis *)iu;
+
+	resp->frame_len = sizeof(struct dev_to_host_fis);
+	memcpy(&resp->ending_fis[0], d2h, sizeof(struct dev_to_host_fis));
+
+	ts->buf_valid_size = sizeof(*resp);
+}
+EXPORT_SYMBOL_GPL(hisi_sas_sata_done);
+
+int hisi_sas_get_ncq_tag(struct sas_task *task, u32 *tag)
+{
+	struct ata_queued_cmd *qc = task->uldd_task;
+
+	if (qc) {
+		if (qc->tf.command == ATA_CMD_FPDMA_WRITE ||
+			qc->tf.command == ATA_CMD_FPDMA_READ) {
+			*tag = qc->tag;
+			return 1;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hisi_sas_get_ncq_tag);
+
 static struct hisi_hba *dev_to_hisi_hba(struct domain_device *device)
 {
 	return device->port->ha->lldd_ha;
@@ -79,7 +170,7 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 {
 
 	if (task) {
-		struct device *dev = &hisi_hba->pdev->dev;
+		struct device *dev = hisi_hba->dev;
 		struct domain_device *device = task->dev;
 		struct hisi_sas_device *sas_dev = device->lldd_dev;
 
@@ -94,17 +185,9 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 			atomic64_dec(&sas_dev->running_req);
 	}
 
-	if (slot->command_table)
-		dma_pool_free(hisi_hba->command_table_pool,
-			      slot->command_table, slot->command_table_dma);
-
-	if (slot->status_buffer)
-		dma_pool_free(hisi_hba->status_buffer_pool,
-			      slot->status_buffer, slot->status_buffer_dma);
+	if (slot->buf)
+		dma_pool_free(hisi_hba->buffer_pool, slot->buf, slot->buf_dma);
 
-	if (slot->sge_page)
-		dma_pool_free(hisi_hba->sge_page_pool, slot->sge_page,
-			      slot->sge_page_dma);
 
 	list_del_init(&slot->entry);
 	slot->task = NULL;
@@ -156,7 +239,7 @@ static void hisi_sas_slot_abort(struct work_struct *work)
 	struct scsi_cmnd *cmnd = task->uldd_task;
 	struct hisi_sas_tmf_task tmf_task;
 	struct scsi_lun lun;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	int tag = abort_slot->idx;
 	unsigned long flags;
 
@@ -179,17 +262,18 @@ out:
 		task->task_done(task);
 }
 
-static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
-			      int is_tmf, struct hisi_sas_tmf_task *tmf,
-			      int *pass)
+static int hisi_sas_task_prep(struct sas_task *task, struct hisi_sas_dq
+		*dq, int is_tmf, struct hisi_sas_tmf_task *tmf,
+		int *pass)
 {
+	struct hisi_hba *hisi_hba = dq->hisi_hba;
 	struct domain_device *device = task->dev;
 	struct hisi_sas_device *sas_dev = device->lldd_dev;
 	struct hisi_sas_port *port;
 	struct hisi_sas_slot *slot;
 	struct hisi_sas_cmd_hdr	*cmd_hdr_base;
 	struct asd_sas_port *sas_port = device->port;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	int dlvry_queue_slot, dlvry_queue, n_elem = 0, rc, slot_idx;
 	unsigned long flags;
 
@@ -209,7 +293,7 @@ static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
 
 	if (DEV_IS_GONE(sas_dev)) {
 		if (sas_dev)
-			dev_info(dev, "task prep: device %llu not ready\n",
+			dev_info(dev, "task prep: device %d not ready\n",
 				 sas_dev->device_id);
 		else
 			dev_info(dev, "task prep: device %016llx not ready\n",
@@ -240,18 +324,24 @@ static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
 	} else
 		n_elem = task->num_scatter;
 
+	spin_lock_irqsave(&hisi_hba->lock, flags);
 	if (hisi_hba->hw->slot_index_alloc)
 		rc = hisi_hba->hw->slot_index_alloc(hisi_hba, &slot_idx,
 						    device);
 	else
 		rc = hisi_sas_slot_index_alloc(hisi_hba, &slot_idx);
-	if (rc)
+	if (rc) {
+		spin_unlock_irqrestore(&hisi_hba->lock, flags);
 		goto err_out;
-	rc = hisi_hba->hw->get_free_slot(hisi_hba, sas_dev->device_id,
-					&dlvry_queue, &dlvry_queue_slot);
+	}
+	spin_unlock_irqrestore(&hisi_hba->lock, flags);
+
+	rc = hisi_hba->hw->get_free_slot(hisi_hba, dq);
 	if (rc)
 		goto err_out_tag;
 
+	dlvry_queue = dq->id;
+	dlvry_queue_slot = dq->wr_point;
 	slot = &hisi_hba->slot_info[slot_idx];
 	memset(slot, 0, sizeof(struct hisi_sas_slot));
 
@@ -266,24 +356,15 @@ static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
 	task->lldd_task = slot;
 	INIT_WORK(&slot->abort_slot, hisi_sas_slot_abort);
 
-	slot->status_buffer = dma_pool_alloc(hisi_hba->status_buffer_pool,
-					     GFP_ATOMIC,
-					     &slot->status_buffer_dma);
-	if (!slot->status_buffer) {
+	slot->buf = dma_pool_alloc(hisi_hba->buffer_pool,
+				   GFP_ATOMIC, &slot->buf_dma);
+	if (!slot->buf) {
 		rc = -ENOMEM;
 		goto err_out_slot_buf;
 	}
-	memset(slot->status_buffer, 0, HISI_SAS_STATUS_BUF_SZ);
-
-	slot->command_table = dma_pool_alloc(hisi_hba->command_table_pool,
-					     GFP_ATOMIC,
-					     &slot->command_table_dma);
-	if (!slot->command_table) {
-		rc = -ENOMEM;
-		goto err_out_status_buf;
-	}
-	memset(slot->command_table, 0, HISI_SAS_COMMAND_TABLE_SZ);
 	memset(slot->cmd_hdr, 0, sizeof(struct hisi_sas_cmd_hdr));
+	memset(hisi_sas_cmd_hdr_addr_mem(slot), 0, HISI_SAS_COMMAND_TABLE_SZ);
+	memset(hisi_sas_status_buf_addr_mem(slot), 0, HISI_SAS_STATUS_BUF_SZ);
 
 	switch (task->task_proto) {
 	case SAS_PROTOCOL_SMP:
@@ -306,9 +387,7 @@ static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
 
 	if (rc) {
 		dev_err(dev, "task prep: rc = 0x%x\n", rc);
-		if (slot->sge_page)
-			goto err_out_sge;
-		goto err_out_command_table;
+		goto err_out_buf;
 	}
 
 	list_add_tail(&slot->entry, &sas_dev->list);
@@ -316,26 +395,22 @@ static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
 	task->task_state_flags |= SAS_TASK_AT_INITIATOR;
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
 
-	hisi_hba->slot_prep = slot;
+	dq->slot_prep = slot;
 
 	atomic64_inc(&sas_dev->running_req);
 	++(*pass);
 
 	return 0;
 
-err_out_sge:
-	dma_pool_free(hisi_hba->sge_page_pool, slot->sge_page,
-		slot->sge_page_dma);
-err_out_command_table:
-	dma_pool_free(hisi_hba->command_table_pool, slot->command_table,
-		slot->command_table_dma);
-err_out_status_buf:
-	dma_pool_free(hisi_hba->status_buffer_pool, slot->status_buffer,
-		slot->status_buffer_dma);
+err_out_buf:
+	dma_pool_free(hisi_hba->buffer_pool, slot->buf,
+		slot->buf_dma);
 err_out_slot_buf:
 	/* Nothing to be done */
 err_out_tag:
+	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot_idx);
+	spin_unlock_irqrestore(&hisi_hba->lock, flags);
 err_out:
 	dev_err(dev, "task prep: failed[%d]!\n", rc);
 	if (!sas_protocol_ata(task->task_proto))
@@ -353,20 +428,23 @@ static int hisi_sas_task_exec(struct sas_task *task, gfp_t gfp_flags,
 	u32 pass = 0;
 	unsigned long flags;
 	struct hisi_hba *hisi_hba = dev_to_hisi_hba(task->dev);
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
+	struct domain_device *device = task->dev;
+	struct hisi_sas_device *sas_dev = device->lldd_dev;
+	struct hisi_sas_dq *dq = sas_dev->dq;
 
 	if (unlikely(test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags)))
 		return -EINVAL;
 
 	/* protect task_prep and start_delivery sequence */
-	spin_lock_irqsave(&hisi_hba->lock, flags);
-	rc = hisi_sas_task_prep(task, hisi_hba, is_tmf, tmf, &pass);
+	spin_lock_irqsave(&dq->lock, flags);
+	rc = hisi_sas_task_prep(task, dq, is_tmf, tmf, &pass);
 	if (rc)
 		dev_err(dev, "task exec: failed[%d]!\n", rc);
 
 	if (likely(pass))
-		hisi_hba->hw->start_delivery(hisi_hba);
-	spin_unlock_irqrestore(&hisi_hba->lock, flags);
+		hisi_hba->hw->start_delivery(dq);
+	spin_unlock_irqrestore(&dq->lock, flags);
 
 	return rc;
 }
@@ -421,12 +499,16 @@ static struct hisi_sas_device *hisi_sas_alloc_dev(struct domain_device *device)
 	spin_lock(&hisi_hba->lock);
 	for (i = 0; i < HISI_SAS_MAX_DEVICES; i++) {
 		if (hisi_hba->devices[i].dev_type == SAS_PHY_UNUSED) {
+			int queue = i % hisi_hba->queue_count;
+			struct hisi_sas_dq *dq = &hisi_hba->dq[queue];
+
 			hisi_hba->devices[i].device_id = i;
 			sas_dev = &hisi_hba->devices[i];
 			sas_dev->dev_status = HISI_SAS_DEV_NORMAL;
 			sas_dev->dev_type = device->dev_type;
 			sas_dev->hisi_hba = hisi_hba;
 			sas_dev->sas_device = device;
+			sas_dev->dq = dq;
 			INIT_LIST_HEAD(&hisi_hba->devices[i].list);
 			break;
 		}
@@ -441,7 +523,7 @@ static int hisi_sas_dev_found(struct domain_device *device)
 	struct hisi_hba *hisi_hba = dev_to_hisi_hba(device);
 	struct domain_device *parent_dev = device->parent;
 	struct hisi_sas_device *sas_dev;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 
 	if (hisi_hba->hw->alloc_dev)
 		sas_dev = hisi_hba->hw->alloc_dev(device);
@@ -622,19 +704,28 @@ static void hisi_sas_release_tasks(struct hisi_hba *hisi_hba)
 	}
 }
 
+static void hisi_sas_dereg_device(struct hisi_hba *hisi_hba,
+				struct domain_device *device)
+{
+	if (hisi_hba->hw->dereg_device)
+		hisi_hba->hw->dereg_device(hisi_hba, device);
+}
+
 static void hisi_sas_dev_gone(struct domain_device *device)
 {
 	struct hisi_sas_device *sas_dev = device->lldd_dev;
 	struct hisi_hba *hisi_hba = dev_to_hisi_hba(device);
-	struct device *dev = &hisi_hba->pdev->dev;
-	u64 dev_id = sas_dev->device_id;
+	struct device *dev = hisi_hba->dev;
+	int dev_id = sas_dev->device_id;
 
-	dev_info(dev, "found dev[%lld:%x] is gone\n",
+	dev_info(dev, "found dev[%d:%x] is gone\n",
 		 sas_dev->device_id, sas_dev->dev_type);
 
 	hisi_sas_internal_task_abort(hisi_hba, device,
 				     HISI_SAS_INT_ABT_DEV, 0);
 
+	hisi_sas_dereg_device(hisi_hba, device);
+
 	hisi_hba->hw->free_device(hisi_hba, sas_dev);
 	device->lldd_dev = NULL;
 	memset(sas_dev, 0, sizeof(*sas_dev));
@@ -691,8 +782,13 @@ static void hisi_sas_task_done(struct sas_task *task)
 static void hisi_sas_tmf_timedout(unsigned long data)
 {
 	struct sas_task *task = (struct sas_task *)data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&task->task_state_lock, flags);
+	if (!(task->task_state_flags & SAS_TASK_STATE_DONE))
+		task->task_state_flags |= SAS_TASK_STATE_ABORTED;
+	spin_unlock_irqrestore(&task->task_state_lock, flags);
 
-	task->task_state_flags |= SAS_TASK_STATE_ABORTED;
 	complete(&task->slow_task->completion);
 }
 
@@ -704,7 +800,7 @@ static int hisi_sas_exec_internal_tmf_task(struct domain_device *device,
 {
 	struct hisi_sas_device *sas_dev = device->lldd_dev;
 	struct hisi_hba *hisi_hba = sas_dev->hisi_hba;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	struct sas_task *task;
 	int res, retry;
 
@@ -821,7 +917,7 @@ static int hisi_sas_softreset_ata_disk(struct domain_device *device)
 	struct ata_link *link;
 	int rc = TMF_RESP_FUNC_FAILED;
 	struct hisi_hba *hisi_hba = dev_to_hisi_hba(device);
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	int s = sizeof(struct host_to_dev_fis);
 	unsigned long flags;
 
@@ -879,7 +975,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 		return -1;
 
 	if (!test_and_set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags)) {
-		struct device *dev = &hisi_hba->pdev->dev;
+		struct device *dev = hisi_hba->dev;
 		struct sas_ha_struct *sas_ha = &hisi_hba->sha;
 		unsigned long flags;
 
@@ -912,7 +1008,7 @@ static int hisi_sas_abort_task(struct sas_task *task)
 	struct domain_device *device = task->dev;
 	struct hisi_sas_device *sas_dev = device->lldd_dev;
 	struct hisi_hba *hisi_hba = dev_to_hisi_hba(task->dev);
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	int rc = TMF_RESP_FUNC_FAILED;
 	unsigned long flags;
 
@@ -961,9 +1057,10 @@ static int hisi_sas_abort_task(struct sas_task *task)
 		if (task->dev->dev_type == SAS_SATA_DEV) {
 			hisi_sas_internal_task_abort(hisi_hba, device,
 						     HISI_SAS_INT_ABT_DEV, 0);
+			hisi_sas_dereg_device(hisi_hba, device);
 			rc = hisi_sas_softreset_ata_disk(device);
 		}
-	} else if (task->task_proto & SAS_PROTOCOL_SMP) {
+	} else if (task->lldd_task && task->task_proto & SAS_PROTOCOL_SMP) {
 		/* SMP */
 		struct hisi_sas_slot *slot = task->lldd_task;
 		u32 tag = slot->idx;
@@ -1027,6 +1124,10 @@ static int hisi_sas_I_T_nexus_reset(struct domain_device *device)
 		return TMF_RESP_FUNC_FAILED;
 	sas_dev->dev_status = HISI_SAS_DEV_NORMAL;
 
+	hisi_sas_internal_task_abort(hisi_hba, device,
+					HISI_SAS_INT_ABT_DEV, 0);
+	hisi_sas_dereg_device(hisi_hba, device);
+
 	rc = hisi_sas_debug_I_T_nexus_reset(device);
 
 	if (rc == TMF_RESP_FUNC_COMPLETE) {
@@ -1041,7 +1142,7 @@ static int hisi_sas_lu_reset(struct domain_device *device, u8 *lun)
 {
 	struct hisi_sas_device *sas_dev = device->lldd_dev;
 	struct hisi_hba *hisi_hba = dev_to_hisi_hba(device);
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	unsigned long flags;
 	int rc = TMF_RESP_FUNC_FAILED;
 
@@ -1054,6 +1155,7 @@ static int hisi_sas_lu_reset(struct domain_device *device, u8 *lun)
 						  HISI_SAS_INT_ABT_DEV, 0);
 		if (rc == TMF_RESP_FUNC_FAILED)
 			goto out;
+		hisi_sas_dereg_device(hisi_hba, device);
 
 		phy = sas_get_local_phy(device);
 
@@ -1077,7 +1179,7 @@ static int hisi_sas_lu_reset(struct domain_device *device, u8 *lun)
 	}
 out:
 	if (rc != TMF_RESP_FUNC_COMPLETE)
-		dev_err(dev, "lu_reset: for device[%llx]:rc= %d\n",
+		dev_err(dev, "lu_reset: for device[%d]:rc= %d\n",
 			     sas_dev->device_id, rc);
 	return rc;
 }
@@ -1124,19 +1226,20 @@ static int hisi_sas_query_task(struct sas_task *task)
 }
 
 static int
-hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, u64 device_id,
+hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 				  struct sas_task *task, int abort_flag,
 				  int task_tag)
 {
 	struct domain_device *device = task->dev;
 	struct hisi_sas_device *sas_dev = device->lldd_dev;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	struct hisi_sas_port *port;
 	struct hisi_sas_slot *slot;
 	struct asd_sas_port *sas_port = device->port;
 	struct hisi_sas_cmd_hdr *cmd_hdr_base;
+	struct hisi_sas_dq *dq = sas_dev->dq;
 	int dlvry_queue_slot, dlvry_queue, n_elem = 0, rc, slot_idx;
-	unsigned long flags;
+	unsigned long flags, flags_dq;
 
 	if (unlikely(test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags)))
 		return -EINVAL;
@@ -1147,14 +1250,22 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, u64 device_id,
 	port = to_hisi_sas_port(sas_port);
 
 	/* simply get a slot and send abort command */
+	spin_lock_irqsave(&hisi_hba->lock, flags);
 	rc = hisi_sas_slot_index_alloc(hisi_hba, &slot_idx);
-	if (rc)
+	if (rc) {
+		spin_unlock_irqrestore(&hisi_hba->lock, flags);
 		goto err_out;
-	rc = hisi_hba->hw->get_free_slot(hisi_hba, sas_dev->device_id,
-					&dlvry_queue, &dlvry_queue_slot);
+	}
+	spin_unlock_irqrestore(&hisi_hba->lock, flags);
+
+	spin_lock_irqsave(&dq->lock, flags_dq);
+	rc = hisi_hba->hw->get_free_slot(hisi_hba, dq);
 	if (rc)
 		goto err_out_tag;
 
+	dlvry_queue = dq->id;
+	dlvry_queue_slot = dq->wr_point;
+
 	slot = &hisi_hba->slot_info[slot_idx];
 	memset(slot, 0, sizeof(struct hisi_sas_slot));
 
@@ -1181,17 +1292,21 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, u64 device_id,
 	task->task_state_flags |= SAS_TASK_AT_INITIATOR;
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
 
-	hisi_hba->slot_prep = slot;
+	dq->slot_prep = slot;
 
 	atomic64_inc(&sas_dev->running_req);
 
-	/* send abort command to our chip */
-	hisi_hba->hw->start_delivery(hisi_hba);
+	/* send abort command to the chip */
+	hisi_hba->hw->start_delivery(dq);
+	spin_unlock_irqrestore(&dq->lock, flags_dq);
 
 	return 0;
 
 err_out_tag:
+	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot_idx);
+	spin_unlock_irqrestore(&hisi_hba->lock, flags);
+	spin_unlock_irqrestore(&dq->lock, flags_dq);
 err_out:
 	dev_err(dev, "internal abort task prep: failed[%d]!\n", rc);
 
@@ -1214,9 +1329,8 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 {
 	struct sas_task *task;
 	struct hisi_sas_device *sas_dev = device->lldd_dev;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	int res;
-	unsigned long flags;
 
 	if (!hisi_hba->hw->prep_abort)
 		return -EOPNOTSUPP;
@@ -1233,11 +1347,8 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 	task->slow_task->timer.expires = jiffies + msecs_to_jiffies(110);
 	add_timer(&task->slow_task->timer);
 
-	/* Lock as we are alloc'ing a slot, which cannot be interrupted */
-	spin_lock_irqsave(&hisi_hba->lock, flags);
 	res = hisi_sas_internal_abort_task_exec(hisi_hba, sas_dev->device_id,
 						task, abort_flag, tag);
-	spin_unlock_irqrestore(&hisi_hba->lock, flags);
 	if (res) {
 		del_timer(&task->slow_task->timer);
 		dev_err(dev, "internal task abort: executing internal task failed: %d\n",
@@ -1247,6 +1358,17 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 	wait_for_completion(&task->slow_task->completion);
 	res = TMF_RESP_FUNC_FAILED;
 
+	/* Internal abort timed out */
+	if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) {
+		if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
+			struct hisi_sas_slot *slot = task->lldd_task;
+
+			if (slot)
+				slot->task = NULL;
+			dev_err(dev, "internal task abort: timeout.\n");
+		}
+	}
+
 	if (task->task_status.resp == SAS_TASK_COMPLETE &&
 		task->task_status.stat == TMF_RESP_FUNC_COMPLETE) {
 		res = TMF_RESP_FUNC_COMPLETE;
@@ -1259,13 +1381,6 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 		goto exit;
 	}
 
-	/* Internal abort timed out */
-	if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) {
-		if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
-			dev_err(dev, "internal task abort: timeout.\n");
-		}
-	}
-
 exit:
 	dev_dbg(dev, "internal task abort: task to dev %016llx task=%p "
 		"resp: 0x%x sts 0x%x\n",
@@ -1353,9 +1468,10 @@ void hisi_sas_rescan_topology(struct hisi_hba *hisi_hba, u32 old_state,
 }
 EXPORT_SYMBOL_GPL(hisi_sas_rescan_topology);
 
-static struct scsi_transport_template *hisi_sas_stt;
+struct scsi_transport_template *hisi_sas_stt;
+EXPORT_SYMBOL_GPL(hisi_sas_stt);
 
-static struct scsi_host_template hisi_sas_sht = {
+static struct scsi_host_template _hisi_sas_sht = {
 	.module			= THIS_MODULE,
 	.name			= DRV_NAME,
 	.queuecommand		= sas_queuecommand,
@@ -1375,6 +1491,8 @@ static struct scsi_host_template hisi_sas_sht = {
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
 };
+struct scsi_host_template *hisi_sas_sht = &_hisi_sas_sht;
+EXPORT_SYMBOL_GPL(hisi_sas_sht);
 
 static struct sas_domain_function_template hisi_sas_transport_ops = {
 	.lldd_dev_found		= hisi_sas_dev_found,
@@ -1422,10 +1540,9 @@ void hisi_sas_init_mem(struct hisi_hba *hisi_hba)
 }
 EXPORT_SYMBOL_GPL(hisi_sas_init_mem);
 
-static int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
+int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 {
-	struct platform_device *pdev = hisi_hba->pdev;
-	struct device *dev = &pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
 
 	spin_lock_init(&hisi_hba->lock);
@@ -1468,16 +1585,9 @@ static int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 			goto err_out;
 	}
 
-	s = HISI_SAS_STATUS_BUF_SZ;
-	hisi_hba->status_buffer_pool = dma_pool_create("status_buffer",
-						       dev, s, 16, 0);
-	if (!hisi_hba->status_buffer_pool)
-		goto err_out;
-
-	s = HISI_SAS_COMMAND_TABLE_SZ;
-	hisi_hba->command_table_pool = dma_pool_create("command_table",
-						       dev, s, 16, 0);
-	if (!hisi_hba->command_table_pool)
+	s = sizeof(struct hisi_sas_slot_buf_table);
+	hisi_hba->buffer_pool = dma_pool_create("dma_buffer", dev, s, 16, 0);
+	if (!hisi_hba->buffer_pool)
 		goto err_out;
 
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
@@ -1512,11 +1622,6 @@ static int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 	if (!hisi_hba->slot_index_tags)
 		goto err_out;
 
-	hisi_hba->sge_page_pool = dma_pool_create("status_sge", dev,
-				sizeof(struct hisi_sas_sge_page), 16, 0);
-	if (!hisi_hba->sge_page_pool)
-		goto err_out;
-
 	s = sizeof(struct hisi_sas_initial_fis) * HISI_SAS_MAX_PHYS;
 	hisi_hba->initial_fis = dma_alloc_coherent(dev, s,
 				&hisi_hba->initial_fis_dma, GFP_KERNEL);
@@ -1542,10 +1647,11 @@ static int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 err_out:
 	return -ENOMEM;
 }
+EXPORT_SYMBOL_GPL(hisi_sas_alloc);
 
-static void hisi_sas_free(struct hisi_hba *hisi_hba)
+void hisi_sas_free(struct hisi_hba *hisi_hba)
 {
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
 
 	for (i = 0; i < hisi_hba->queue_count; i++) {
@@ -1562,9 +1668,7 @@ static void hisi_sas_free(struct hisi_hba *hisi_hba)
 					  hisi_hba->complete_hdr_dma[i]);
 	}
 
-	dma_pool_destroy(hisi_hba->status_buffer_pool);
-	dma_pool_destroy(hisi_hba->command_table_pool);
-	dma_pool_destroy(hisi_hba->sge_page_pool);
+	dma_pool_destroy(hisi_hba->buffer_pool);
 
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
 	if (hisi_hba->itct)
@@ -1598,6 +1702,7 @@ static void hisi_sas_free(struct hisi_hba *hisi_hba)
 	if (hisi_hba->wq)
 		destroy_workqueue(hisi_hba->wq);
 }
+EXPORT_SYMBOL_GPL(hisi_sas_free);
 
 static void hisi_sas_rst_work_handler(struct work_struct *work)
 {
@@ -1607,65 +1712,99 @@ static void hisi_sas_rst_work_handler(struct work_struct *work)
 	hisi_sas_controller_reset(hisi_hba);
 }
 
-static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
-					      const struct hisi_sas_hw *hw)
+int hisi_sas_get_fw_info(struct hisi_hba *hisi_hba)
 {
-	struct resource *res;
-	struct Scsi_Host *shost;
-	struct hisi_hba *hisi_hba;
-	struct device *dev = &pdev->dev;
-	struct device_node *np = pdev->dev.of_node;
+	struct device *dev = hisi_hba->dev;
+	struct platform_device *pdev = hisi_hba->platform_dev;
+	struct device_node *np = pdev ? pdev->dev.of_node : NULL;
 	struct clk *refclk;
 
-	shost = scsi_host_alloc(&hisi_sas_sht, sizeof(*hisi_hba));
-	if (!shost) {
-		dev_err(dev, "scsi host alloc failed\n");
-		return NULL;
-	}
-	hisi_hba = shost_priv(shost);
-
-	INIT_WORK(&hisi_hba->rst_work, hisi_sas_rst_work_handler);
-	hisi_hba->hw = hw;
-	hisi_hba->pdev = pdev;
-	hisi_hba->shost = shost;
-	SHOST_TO_SAS_HA(shost) = &hisi_hba->sha;
-
-	init_timer(&hisi_hba->timer);
-
 	if (device_property_read_u8_array(dev, "sas-addr", hisi_hba->sas_addr,
-					  SAS_ADDR_SIZE))
-		goto err_out;
+					  SAS_ADDR_SIZE)) {
+		dev_err(dev, "could not get property sas-addr\n");
+		return -ENOENT;
+	}
 
 	if (np) {
+		/*
+		 * These properties are only required for platform device-based
+		 * controller with DT firmware.
+		 */
 		hisi_hba->ctrl = syscon_regmap_lookup_by_phandle(np,
 					"hisilicon,sas-syscon");
-		if (IS_ERR(hisi_hba->ctrl))
-			goto err_out;
+		if (IS_ERR(hisi_hba->ctrl)) {
+			dev_err(dev, "could not get syscon\n");
+			return -ENOENT;
+		}
 
 		if (device_property_read_u32(dev, "ctrl-reset-reg",
-					     &hisi_hba->ctrl_reset_reg))
-			goto err_out;
+					     &hisi_hba->ctrl_reset_reg)) {
+			dev_err(dev,
+				"could not get property ctrl-reset-reg\n");
+			return -ENOENT;
+		}
 
 		if (device_property_read_u32(dev, "ctrl-reset-sts-reg",
-					     &hisi_hba->ctrl_reset_sts_reg))
-			goto err_out;
+					     &hisi_hba->ctrl_reset_sts_reg)) {
+			dev_err(dev,
+				"could not get property ctrl-reset-sts-reg\n");
+			return -ENOENT;
+		}
 
 		if (device_property_read_u32(dev, "ctrl-clock-ena-reg",
-					     &hisi_hba->ctrl_clock_ena_reg))
-			goto err_out;
+					     &hisi_hba->ctrl_clock_ena_reg)) {
+			dev_err(dev,
+				"could not get property ctrl-clock-ena-reg\n");
+			return -ENOENT;
+		}
 	}
 
-	refclk = devm_clk_get(&pdev->dev, NULL);
+	refclk = devm_clk_get(dev, NULL);
 	if (IS_ERR(refclk))
 		dev_dbg(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;
+	if (device_property_read_u32(dev, "phy-count", &hisi_hba->n_phy)) {
+		dev_err(dev, "could not get property phy-count\n");
+		return -ENOENT;
+	}
 
 	if (device_property_read_u32(dev, "queue-count",
-				     &hisi_hba->queue_count))
+				     &hisi_hba->queue_count)) {
+		dev_err(dev, "could not get property queue-count\n");
+		return -ENOENT;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hisi_sas_get_fw_info);
+
+static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
+					      const struct hisi_sas_hw *hw)
+{
+	struct resource *res;
+	struct Scsi_Host *shost;
+	struct hisi_hba *hisi_hba;
+	struct device *dev = &pdev->dev;
+
+	shost = scsi_host_alloc(hisi_sas_sht, sizeof(*hisi_hba));
+	if (!shost) {
+		dev_err(dev, "scsi host alloc failed\n");
+		return NULL;
+	}
+	hisi_hba = shost_priv(shost);
+
+	INIT_WORK(&hisi_hba->rst_work, hisi_sas_rst_work_handler);
+	hisi_hba->hw = hw;
+	hisi_hba->dev = dev;
+	hisi_hba->platform_dev = pdev;
+	hisi_hba->shost = shost;
+	SHOST_TO_SAS_HA(shost) = &hisi_hba->sha;
+
+	init_timer(&hisi_hba->timer);
+
+	if (hisi_sas_get_fw_info(hisi_hba) < 0)
 		goto err_out;
 
 	if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)) &&
@@ -1691,7 +1830,7 @@ err_out:
 	return NULL;
 }
 
-static void hisi_sas_init_add(struct hisi_hba *hisi_hba)
+void hisi_sas_init_add(struct hisi_hba *hisi_hba)
 {
 	int i;
 
@@ -1700,6 +1839,7 @@ static void hisi_sas_init_add(struct hisi_hba *hisi_hba)
 		       hisi_hba->sas_addr,
 		       SAS_ADDR_SIZE);
 }
+EXPORT_SYMBOL_GPL(hisi_sas_init_add);
 
 int hisi_sas_probe(struct platform_device *pdev,
 			 const struct hisi_sas_hw *hw)
@@ -1743,7 +1883,7 @@ int hisi_sas_probe(struct platform_device *pdev,
 	shost->cmd_per_lun = hisi_hba->hw->max_command_entries;
 
 	sha->sas_ha_name = DRV_NAME;
-	sha->dev = &hisi_hba->pdev->dev;
+	sha->dev = hisi_hba->dev;
 	sha->lldd_module = THIS_MODULE;
 	sha->sas_addr = &hisi_hba->sas_addr[0];
 	sha->num_phys = hisi_hba->n_phy;

drivers/scsi/hisi_sas/hisi_sas_v1_hw.c

@@ -505,7 +505,7 @@ static void setup_itct_v1_hw(struct hisi_hba *hisi_hba,
 			     struct hisi_sas_device *sas_dev)
 {
 	struct domain_device *device = sas_dev->sas_device;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	u64 qw0, device_id = sas_dev->device_id;
 	struct hisi_sas_itct *itct = &hisi_hba->itct[device_id];
 	struct asd_sas_port *sas_port = device->port;
@@ -571,7 +571,7 @@ static int reset_hw_v1_hw(struct hisi_hba *hisi_hba)
 	int i;
 	unsigned long end_time;
 	u32 val;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 
 	for (i = 0; i < hisi_hba->n_phy; i++) {
 		u32 phy_ctrl = hisi_sas_phy_read32(hisi_hba, i, PHY_CTRL);
@@ -756,7 +756,7 @@ static void init_reg_v1_hw(struct hisi_hba *hisi_hba)
 
 static int hw_init_v1_hw(struct hisi_hba *hisi_hba)
 {
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	int rc;
 
 	rc = reset_hw_v1_hw(hisi_hba);
@@ -900,22 +900,17 @@ static int get_wideport_bitmap_v1_hw(struct hisi_hba *hisi_hba, int port_id)
 	return bitmap;
 }
 
-/**
- * This function allocates across all queues to load balance.
- * Slots are allocated from queues in a round-robin fashion.
- *
+/*
  * 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, u32 dev_id,
-				int *q, int *s)
+static int
+get_free_slot_v1_hw(struct hisi_hba *hisi_hba, struct hisi_sas_dq *dq)
 {
-	struct device *dev = &hisi_hba->pdev->dev;
-	struct hisi_sas_dq *dq;
+	struct device *dev = hisi_hba->dev;
+	int queue = dq->id;
 	u32 r, w;
-	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));
@@ -924,16 +919,14 @@ static int get_free_slot_v1_hw(struct hisi_hba *hisi_hba, u32 dev_id,
 		return -EAGAIN;
 	}
 
-	*q = queue;
-	*s = w;
 	return 0;
 }
 
-static void start_delivery_v1_hw(struct hisi_hba *hisi_hba)
+static void start_delivery_v1_hw(struct hisi_sas_dq *dq)
 {
-	int dlvry_queue = hisi_hba->slot_prep->dlvry_queue;
-	int dlvry_queue_slot = hisi_hba->slot_prep->dlvry_queue_slot;
-	struct hisi_sas_dq *dq = &hisi_hba->dq[dlvry_queue];
+	struct hisi_hba *hisi_hba = dq->hisi_hba;
+	int dlvry_queue = dq->slot_prep->dlvry_queue;
+	int dlvry_queue_slot = dq->slot_prep->dlvry_queue_slot;
 
 	dq->wr_point = ++dlvry_queue_slot % HISI_SAS_QUEUE_SLOTS;
 	hisi_sas_write32(hisi_hba, DLVRY_Q_0_WR_PTR + (dlvry_queue * 0x14),
@@ -946,7 +939,8 @@ static int prep_prd_sge_v1_hw(struct hisi_hba *hisi_hba,
 			      struct scatterlist *scatter,
 			      int n_elem)
 {
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct hisi_sas_sge_page *sge_page = hisi_sas_sge_addr_mem(slot);
+	struct device *dev = hisi_hba->dev;
 	struct scatterlist *sg;
 	int i;
 
@@ -956,13 +950,8 @@ static int prep_prd_sge_v1_hw(struct hisi_hba *hisi_hba,
 		return -EINVAL;
 	}
 
-	slot->sge_page = dma_pool_alloc(hisi_hba->sge_page_pool, GFP_ATOMIC,
-					&slot->sge_page_dma);
-	if (!slot->sge_page)
-		return -ENOMEM;
-
 	for_each_sg(scatter, sg, n_elem, i) {
-		struct hisi_sas_sge *entry = &slot->sge_page->sge[i];
+		struct hisi_sas_sge *entry = &sge_page->sge[i];
 
 		entry->addr = cpu_to_le64(sg_dma_address(sg));
 		entry->page_ctrl_0 = entry->page_ctrl_1 = 0;
@@ -970,7 +959,7 @@ static int prep_prd_sge_v1_hw(struct hisi_hba *hisi_hba,
 		entry->data_off = 0;
 	}
 
-	hdr->prd_table_addr = cpu_to_le64(slot->sge_page_dma);
+	hdr->prd_table_addr = cpu_to_le64(hisi_sas_sge_addr_dma(slot));
 
 	hdr->sg_len = cpu_to_le32(n_elem << CMD_HDR_DATA_SGL_LEN_OFF);
 
@@ -983,7 +972,7 @@ static int prep_smp_v1_hw(struct hisi_hba *hisi_hba,
 	struct sas_task *task = slot->task;
 	struct hisi_sas_cmd_hdr *hdr = slot->cmd_hdr;
 	struct domain_device *device = task->dev;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	struct hisi_sas_port *port = slot->port;
 	struct scatterlist *sg_req, *sg_resp;
 	struct hisi_sas_device *sas_dev = device->lldd_dev;
@@ -1033,7 +1022,7 @@ static int prep_smp_v1_hw(struct hisi_hba *hisi_hba,
 	hdr->transfer_tags = cpu_to_le32(slot->idx << CMD_HDR_IPTT_OFF);
 
 	hdr->cmd_table_addr = cpu_to_le64(req_dma_addr);
-	hdr->sts_buffer_addr = cpu_to_le64(slot->status_buffer_dma);
+	hdr->sts_buffer_addr = cpu_to_le64(hisi_sas_status_buf_addr_dma(slot));
 
 	return 0;
 
@@ -1114,10 +1103,11 @@ static int prep_ssp_v1_hw(struct hisi_hba *hisi_hba,
 	}
 
 	hdr->data_transfer_len = cpu_to_le32(task->total_xfer_len);
-	hdr->cmd_table_addr = cpu_to_le64(slot->command_table_dma);
-	hdr->sts_buffer_addr = cpu_to_le64(slot->status_buffer_dma);
+	hdr->cmd_table_addr = cpu_to_le64(hisi_sas_cmd_hdr_addr_dma(slot));
+	hdr->sts_buffer_addr = cpu_to_le64(hisi_sas_status_buf_addr_dma(slot));
 
-	buf_cmd = slot->command_table + sizeof(struct ssp_frame_hdr);
+	buf_cmd = hisi_sas_cmd_hdr_addr_mem(slot) +
+		sizeof(struct ssp_frame_hdr);
 	if (task->ssp_task.enable_first_burst) {
 		fburst = (1 << 7);
 		dw2 |= 1 << CMD_HDR_FIRST_BURST_OFF;
@@ -1154,8 +1144,9 @@ static void slot_err_v1_hw(struct hisi_hba *hisi_hba,
 			   struct hisi_sas_slot *slot)
 {
 	struct task_status_struct *ts = &task->task_status;
-	struct hisi_sas_err_record_v1 *err_record = slot->status_buffer;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct hisi_sas_err_record_v1 *err_record =
+			hisi_sas_status_buf_addr_mem(slot);
+	struct device *dev = hisi_hba->dev;
 
 	switch (task->task_proto) {
 	case SAS_PROTOCOL_SSP:
@@ -1281,7 +1272,7 @@ static int slot_complete_v1_hw(struct hisi_hba *hisi_hba,
 {
 	struct sas_task *task = slot->task;
 	struct hisi_sas_device *sas_dev;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	struct task_status_struct *ts;
 	struct domain_device *device;
 	enum exec_status sts;
@@ -1371,8 +1362,11 @@ static int slot_complete_v1_hw(struct hisi_hba *hisi_hba,
 	switch (task->task_proto) {
 	case SAS_PROTOCOL_SSP:
 	{
-		struct ssp_response_iu *iu = slot->status_buffer +
-			sizeof(struct hisi_sas_err_record);
+		struct hisi_sas_status_buffer *status_buffer =
+				hisi_sas_status_buf_addr_mem(slot);
+		struct ssp_response_iu *iu = (struct ssp_response_iu *)
+				&status_buffer->iu[0];
+
 		sas_ssp_task_response(dev, task, iu);
 		break;
 	}
@@ -1389,7 +1383,7 @@ static int slot_complete_v1_hw(struct hisi_hba *hisi_hba,
 		dma_unmap_sg(dev, &task->smp_task.smp_req, 1,
 			     DMA_TO_DEVICE);
 		memcpy(to + sg_resp->offset,
-		       slot->status_buffer +
+		       hisi_sas_status_buf_addr_mem(slot) +
 		       sizeof(struct hisi_sas_err_record),
 		       sg_dma_len(sg_resp));
 		kunmap_atomic(to);
@@ -1430,7 +1424,7 @@ static irqreturn_t int_phyup_v1_hw(int irq_no, void *p)
 {
 	struct hisi_sas_phy *phy = p;
 	struct hisi_hba *hisi_hba = phy->hisi_hba;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
 	int i, phy_no = sas_phy->id;
 	u32 irq_value, context, port_id, link_rate;
@@ -1511,7 +1505,7 @@ static irqreturn_t int_bcast_v1_hw(int irq, void *p)
 	struct hisi_hba *hisi_hba = phy->hisi_hba;
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
 	struct sas_ha_struct *sha = &hisi_hba->sha;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	int phy_no = sas_phy->id;
 	u32 irq_value;
 	irqreturn_t res = IRQ_HANDLED;
@@ -1538,7 +1532,7 @@ static irqreturn_t int_abnormal_v1_hw(int irq, void *p)
 {
 	struct hisi_sas_phy *phy = p;
 	struct hisi_hba *hisi_hba = phy->hisi_hba;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
 	u32 irq_value, irq_mask_old;
 	int phy_no = sas_phy->id;
@@ -1641,7 +1635,7 @@ static irqreturn_t cq_interrupt_v1_hw(int irq, void *p)
 static irqreturn_t fatal_ecc_int_v1_hw(int irq, void *p)
 {
 	struct hisi_hba *hisi_hba = p;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	u32 ecc_int = hisi_sas_read32(hisi_hba, SAS_ECC_INTR);
 
 	if (ecc_int & SAS_ECC_INTR_DQ_ECC1B_MSK) {
@@ -1700,7 +1694,7 @@ static irqreturn_t fatal_ecc_int_v1_hw(int irq, void *p)
 static irqreturn_t fatal_axi_int_v1_hw(int irq, void *p)
 {
 	struct hisi_hba *hisi_hba = p;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	u32 axi_int = hisi_sas_read32(hisi_hba, ENT_INT_SRC2);
 	u32 axi_info = hisi_sas_read32(hisi_hba, HGC_AXI_FIFO_ERR_INFO);
 
@@ -1738,7 +1732,7 @@ static irq_handler_t fatal_interrupts[HISI_SAS_MAX_QUEUES] = {
 
 static int interrupt_init_v1_hw(struct hisi_hba *hisi_hba)
 {
-	struct platform_device *pdev = hisi_hba->pdev;
+	struct platform_device *pdev = hisi_hba->platform_dev;
 	struct device *dev = &pdev->dev;
 	int i, j, irq, rc, idx;
 

drivers/scsi/hisi_sas/hisi_sas_v2_hw.c

@@ -554,12 +554,6 @@ enum {
 #define DIR_TO_DEVICE 2
 #define DIR_RESERVED 3
 
-#define SATA_PROTOCOL_NONDATA		0x1
-#define SATA_PROTOCOL_PIO		0x2
-#define SATA_PROTOCOL_DMA		0x4
-#define SATA_PROTOCOL_FPDMA		0x8
-#define SATA_PROTOCOL_ATAPI		0x10
-
 #define ERR_ON_TX_PHASE(err_phase) (err_phase == 0x2 || \
 		err_phase == 0x4 || err_phase == 0x8 ||\
 		err_phase == 0x6 || err_phase == 0xa)
@@ -659,7 +653,7 @@ slot_index_alloc_quirk_v2_hw(struct hisi_hba *hisi_hba, int *slot_idx,
 static bool sata_index_alloc_v2_hw(struct hisi_hba *hisi_hba, int *idx)
 {
 	unsigned int index;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	void *bitmap = hisi_hba->sata_dev_bitmap;
 
 	index = find_first_zero_bit(bitmap, HISI_MAX_SATA_SUPPORT_V2_HW);
@@ -695,6 +689,9 @@ hisi_sas_device *alloc_dev_quirk_v2_hw(struct domain_device *device)
 		if (sata_dev && (i & 1))
 			continue;
 		if (hisi_hba->devices[i].dev_type == SAS_PHY_UNUSED) {
+			int queue = i % hisi_hba->queue_count;
+			struct hisi_sas_dq *dq = &hisi_hba->dq[queue];
+
 			hisi_hba->devices[i].device_id = i;
 			sas_dev = &hisi_hba->devices[i];
 			sas_dev->dev_status = HISI_SAS_DEV_NORMAL;
@@ -702,6 +699,7 @@ hisi_sas_device *alloc_dev_quirk_v2_hw(struct domain_device *device)
 			sas_dev->hisi_hba = hisi_hba;
 			sas_dev->sas_device = device;
 			sas_dev->sata_idx = sata_idx;
+			sas_dev->dq = dq;
 			INIT_LIST_HEAD(&hisi_hba->devices[i].list);
 			break;
 		}
@@ -756,7 +754,7 @@ static void setup_itct_v2_hw(struct hisi_hba *hisi_hba,
 			     struct hisi_sas_device *sas_dev)
 {
 	struct domain_device *device = sas_dev->sas_device;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	u64 qw0, device_id = sas_dev->device_id;
 	struct hisi_sas_itct *itct = &hisi_hba->itct[device_id];
 	struct domain_device *parent_dev = device->parent;
@@ -809,7 +807,7 @@ static void free_device_v2_hw(struct hisi_hba *hisi_hba,
 			      struct hisi_sas_device *sas_dev)
 {
 	u64 dev_id = sas_dev->device_id;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	struct hisi_sas_itct *itct = &hisi_hba->itct[dev_id];
 	u32 reg_val = hisi_sas_read32(hisi_hba, ENT_INT_SRC3);
 	int i;
@@ -853,7 +851,7 @@ static int reset_hw_v2_hw(struct hisi_hba *hisi_hba)
 	int i, reset_val;
 	u32 val;
 	unsigned long end_time;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 
 	/* The mask needs to be set depending on the number of phys */
 	if (hisi_hba->n_phy == 9)
@@ -989,7 +987,7 @@ static void phys_try_accept_stp_links_v2_hw(struct hisi_hba *hisi_hba)
 
 static void init_reg_v2_hw(struct hisi_hba *hisi_hba)
 {
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	int i;
 
 	/* Global registers init */
@@ -1170,7 +1168,7 @@ static void set_link_timer_quirk(struct hisi_hba *hisi_hba)
 
 static int hw_init_v2_hw(struct hisi_hba *hisi_hba)
 {
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	int rc;
 
 	rc = reset_hw_v2_hw(hisi_hba);
@@ -1219,7 +1217,7 @@ static bool tx_fifo_is_empty_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
 static bool axi_bus_is_idle_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
 {
 	int i, max_loop = 1000;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	u32 status, axi_status, dfx_val, dfx_tx_val;
 
 	for (i = 0; i < max_loop; i++) {
@@ -1245,7 +1243,7 @@ static bool axi_bus_is_idle_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
 static bool wait_io_done_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
 {
 	int i, max_loop = 1000;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	u32 status, tx_dfx0;
 
 	for (i = 0; i < max_loop; i++) {
@@ -1283,7 +1281,7 @@ static bool allowed_disable_phy_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
 static void disable_phy_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
 {
 	u32 cfg, axi_val, dfx0_val, txid_auto;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 
 	/* Close axi bus. */
 	axi_val = hisi_sas_read32(hisi_hba, AXI_MASTER_CFG_BASE +
@@ -1454,22 +1452,17 @@ static int get_wideport_bitmap_v2_hw(struct hisi_hba *hisi_hba, int port_id)
 	return bitmap;
 }
 
-/**
- * This function allocates across all queues to load balance.
- * Slots are allocated from queues in a round-robin fashion.
- *
+/*
  * 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, u32 dev_id,
-				int *q, int *s)
+static int
+get_free_slot_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_dq *dq)
 {
-	struct device *dev = &hisi_hba->pdev->dev;
-	struct hisi_sas_dq *dq;
+	struct device *dev = hisi_hba->dev;
+	int queue = dq->id;
 	u32 r, w;
-	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));
@@ -1479,16 +1472,14 @@ static int get_free_slot_v2_hw(struct hisi_hba *hisi_hba, u32 dev_id,
 		return -EAGAIN;
 	}
 
-	*q = queue;
-	*s = w;
 	return 0;
 }
 
-static void start_delivery_v2_hw(struct hisi_hba *hisi_hba)
+static void start_delivery_v2_hw(struct hisi_sas_dq *dq)
 {
-	int dlvry_queue = hisi_hba->slot_prep->dlvry_queue;
-	int dlvry_queue_slot = hisi_hba->slot_prep->dlvry_queue_slot;
-	struct hisi_sas_dq *dq = &hisi_hba->dq[dlvry_queue];
+	struct hisi_hba *hisi_hba = dq->hisi_hba;
+	int dlvry_queue = dq->slot_prep->dlvry_queue;
+	int dlvry_queue_slot = dq->slot_prep->dlvry_queue_slot;
 
 	dq->wr_point = ++dlvry_queue_slot % HISI_SAS_QUEUE_SLOTS;
 	hisi_sas_write32(hisi_hba, DLVRY_Q_0_WR_PTR + (dlvry_queue * 0x14),
@@ -1501,7 +1492,8 @@ static int prep_prd_sge_v2_hw(struct hisi_hba *hisi_hba,
 			      struct scatterlist *scatter,
 			      int n_elem)
 {
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct hisi_sas_sge_page *sge_page = hisi_sas_sge_addr_mem(slot);
+	struct device *dev = hisi_hba->dev;
 	struct scatterlist *sg;
 	int i;
 
@@ -1511,13 +1503,8 @@ static int prep_prd_sge_v2_hw(struct hisi_hba *hisi_hba,
 		return -EINVAL;
 	}
 
-	slot->sge_page = dma_pool_alloc(hisi_hba->sge_page_pool, GFP_ATOMIC,
-					&slot->sge_page_dma);
-	if (!slot->sge_page)
-		return -ENOMEM;
-
 	for_each_sg(scatter, sg, n_elem, i) {
-		struct hisi_sas_sge *entry = &slot->sge_page->sge[i];
+		struct hisi_sas_sge *entry = &sge_page->sge[i];
 
 		entry->addr = cpu_to_le64(sg_dma_address(sg));
 		entry->page_ctrl_0 = entry->page_ctrl_1 = 0;
@@ -1525,7 +1512,7 @@ static int prep_prd_sge_v2_hw(struct hisi_hba *hisi_hba,
 		entry->data_off = 0;
 	}
 
-	hdr->prd_table_addr = cpu_to_le64(slot->sge_page_dma);
+	hdr->prd_table_addr = cpu_to_le64(hisi_sas_sge_addr_dma(slot));
 
 	hdr->sg_len = cpu_to_le32(n_elem << CMD_HDR_DATA_SGL_LEN_OFF);
 
@@ -1538,7 +1525,7 @@ static int prep_smp_v2_hw(struct hisi_hba *hisi_hba,
 	struct sas_task *task = slot->task;
 	struct hisi_sas_cmd_hdr *hdr = slot->cmd_hdr;
 	struct domain_device *device = task->dev;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	struct hisi_sas_port *port = slot->port;
 	struct scatterlist *sg_req, *sg_resp;
 	struct hisi_sas_device *sas_dev = device->lldd_dev;
@@ -1589,7 +1576,7 @@ static int prep_smp_v2_hw(struct hisi_hba *hisi_hba,
 	hdr->transfer_tags = cpu_to_le32(slot->idx << CMD_HDR_IPTT_OFF);
 
 	hdr->cmd_table_addr = cpu_to_le64(req_dma_addr);
-	hdr->sts_buffer_addr = cpu_to_le64(slot->status_buffer_dma);
+	hdr->sts_buffer_addr = cpu_to_le64(hisi_sas_status_buf_addr_dma(slot));
 
 	return 0;
 
@@ -1663,10 +1650,11 @@ static int prep_ssp_v2_hw(struct hisi_hba *hisi_hba,
 	}
 
 	hdr->data_transfer_len = cpu_to_le32(task->total_xfer_len);
-	hdr->cmd_table_addr = cpu_to_le64(slot->command_table_dma);
-	hdr->sts_buffer_addr = cpu_to_le64(slot->status_buffer_dma);
+	hdr->cmd_table_addr = cpu_to_le64(hisi_sas_cmd_hdr_addr_dma(slot));
+	hdr->sts_buffer_addr = cpu_to_le64(hisi_sas_status_buf_addr_dma(slot));
 
-	buf_cmd = slot->command_table + sizeof(struct ssp_frame_hdr);
+	buf_cmd = hisi_sas_cmd_hdr_addr_mem(slot) +
+		sizeof(struct ssp_frame_hdr);
 
 	memcpy(buf_cmd, &task->ssp_task.LUN, 8);
 	if (!is_tmf) {
@@ -1692,20 +1680,6 @@ static int prep_ssp_v2_hw(struct hisi_hba *hisi_hba,
 	return 0;
 }
 
-static void sata_done_v2_hw(struct hisi_hba *hisi_hba, struct sas_task *task,
-			    struct hisi_sas_slot *slot)
-{
-	struct task_status_struct *ts = &task->task_status;
-	struct ata_task_resp *resp = (struct ata_task_resp *)ts->buf;
-	struct dev_to_host_fis *d2h = slot->status_buffer +
-				      sizeof(struct hisi_sas_err_record);
-
-	resp->frame_len = sizeof(struct dev_to_host_fis);
-	memcpy(&resp->ending_fis[0], d2h, sizeof(struct dev_to_host_fis));
-
-	ts->buf_valid_size = sizeof(*resp);
-}
-
 #define TRANS_TX_ERR	0
 #define TRANS_RX_ERR	1
 #define DMA_TX_ERR		2
@@ -1907,7 +1881,8 @@ static void slot_err_v2_hw(struct hisi_hba *hisi_hba,
 			   int err_phase)
 {
 	struct task_status_struct *ts = &task->task_status;
-	struct hisi_sas_err_record_v2 *err_record = slot->status_buffer;
+	struct hisi_sas_err_record_v2 *err_record =
+			hisi_sas_status_buf_addr_mem(slot);
 	u32 trans_tx_fail_type = cpu_to_le32(err_record->trans_tx_fail_type);
 	u32 trans_rx_fail_type = cpu_to_le32(err_record->trans_rx_fail_type);
 	u16 dma_tx_err_type = cpu_to_le16(err_record->dma_tx_err_type);
@@ -2198,7 +2173,7 @@ static void slot_err_v2_hw(struct hisi_hba *hisi_hba,
 			break;
 		}
 		}
-		sata_done_v2_hw(hisi_hba, task, slot);
+		hisi_sas_sata_done(task, slot);
 	}
 		break;
 	default:
@@ -2211,7 +2186,7 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot)
 {
 	struct sas_task *task = slot->task;
 	struct hisi_sas_device *sas_dev;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	struct task_status_struct *ts;
 	struct domain_device *device;
 	enum exec_status sts;
@@ -2296,8 +2271,10 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot)
 	switch (task->task_proto) {
 	case SAS_PROTOCOL_SSP:
 	{
-		struct ssp_response_iu *iu = slot->status_buffer +
-			sizeof(struct hisi_sas_err_record);
+		struct hisi_sas_status_buffer *status_buffer =
+				hisi_sas_status_buf_addr_mem(slot);
+		struct ssp_response_iu *iu = (struct ssp_response_iu *)
+				&status_buffer->iu[0];
 
 		sas_ssp_task_response(dev, task, iu);
 		break;
@@ -2315,7 +2292,7 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot)
 		dma_unmap_sg(dev, &task->smp_task.smp_req, 1,
 			     DMA_TO_DEVICE);
 		memcpy(to + sg_resp->offset,
-		       slot->status_buffer +
+		       hisi_sas_status_buf_addr_mem(slot) +
 		       sizeof(struct hisi_sas_err_record),
 		       sg_dma_len(sg_resp));
 		kunmap_atomic(to);
@@ -2326,7 +2303,7 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot)
 	case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP:
 	{
 		ts->stat = SAM_STAT_GOOD;
-		sata_done_v2_hw(hisi_hba, task, slot);
+		hisi_sas_sata_done(task, slot);
 		break;
 	}
 	default:
@@ -2344,7 +2321,9 @@ out:
 	spin_lock_irqsave(&task->task_state_lock, flags);
 	task->task_state_flags |= SAS_TASK_STATE_DONE;
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
+	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_task_free(hisi_hba, task, slot);
+	spin_unlock_irqrestore(&hisi_hba->lock, flags);
 	sts = ts->stat;
 
 	if (task->task_done)
@@ -2353,78 +2332,6 @@ out:
 	return sts;
 }
 
-static u8 get_ata_protocol(u8 cmd, int direction)
-{
-	switch (cmd) {
-	case ATA_CMD_FPDMA_WRITE:
-	case ATA_CMD_FPDMA_READ:
-	case ATA_CMD_FPDMA_RECV:
-	case ATA_CMD_FPDMA_SEND:
-	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:
-	case ATA_CMD_PIO_READ:
-	case ATA_CMD_PIO_READ_EXT:
-	case ATA_CMD_PMP_WRITE:
-	case ATA_CMD_WRITE_LOG_EXT:
-	case ATA_CMD_PIO_WRITE:
-	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_CHK_POWER:
-	case ATA_CMD_DEV_RESET:
-	case ATA_CMD_EDD:
-	case ATA_CMD_FLUSH:
-	case ATA_CMD_FLUSH_EXT:
-	case ATA_CMD_VERIFY:
-	case ATA_CMD_VERIFY_EXT:
-	case ATA_CMD_SET_FEATURES:
-	case ATA_CMD_STANDBY:
-	case ATA_CMD_STANDBYNOW1:
-	return SATA_PROTOCOL_NONDATA;
-	default:
-		if (direction == DMA_NONE)
-			return SATA_PROTOCOL_NONDATA;
-		return SATA_PROTOCOL_PIO;
-	}
-}
-
-static int get_ncq_tag_v2_hw(struct sas_task *task, u32 *tag)
-{
-	struct ata_queued_cmd *qc = task->uldd_task;
-
-	if (qc) {
-		if (qc->tf.command == ATA_CMD_FPDMA_WRITE ||
-			qc->tf.command == ATA_CMD_FPDMA_READ) {
-			*tag = qc->tag;
-			return 1;
-		}
-	}
-	return 0;
-}
-
 static int prep_ata_v2_hw(struct hisi_hba *hisi_hba,
 			  struct hisi_sas_slot *slot)
 {
@@ -2465,13 +2372,14 @@ static int prep_ata_v2_hw(struct hisi_hba *hisi_hba,
 			(task->ata_task.fis.control & ATA_SRST))
 		dw1 |= 1 << CMD_HDR_RESET_OFF;
 
-	dw1 |= (get_ata_protocol(task->ata_task.fis.command, task->data_dir))
+	dw1 |= (hisi_sas_get_ata_protocol(
+		task->ata_task.fis.command, task->data_dir))
 		<< CMD_HDR_FRAME_TYPE_OFF;
 	dw1 |= sas_dev->device_id << CMD_HDR_DEV_ID_OFF;
 	hdr->dw1 = cpu_to_le32(dw1);
 
 	/* dw2 */
-	if (task->ata_task.use_ncq && get_ncq_tag_v2_hw(task, &hdr_tag)) {
+	if (task->ata_task.use_ncq && hisi_sas_get_ncq_tag(task, &hdr_tag)) {
 		task->ata_task.fis.sector_count |= (u8) (hdr_tag << 3);
 		dw2 |= hdr_tag << CMD_HDR_NCQ_TAG_OFF;
 	}
@@ -2490,12 +2398,11 @@ static int prep_ata_v2_hw(struct hisi_hba *hisi_hba,
 			return rc;
 	}
 
-
 	hdr->data_transfer_len = cpu_to_le32(task->total_xfer_len);
-	hdr->cmd_table_addr = cpu_to_le64(slot->command_table_dma);
-	hdr->sts_buffer_addr = cpu_to_le64(slot->status_buffer_dma);
+	hdr->cmd_table_addr = cpu_to_le64(hisi_sas_cmd_hdr_addr_dma(slot));
+	hdr->sts_buffer_addr = cpu_to_le64(hisi_sas_status_buf_addr_dma(slot));
 
-	buf_cmd = slot->command_table;
+	buf_cmd = hisi_sas_cmd_hdr_addr_mem(slot);
 
 	if (likely(!task->ata_task.device_control_reg_update))
 		task->ata_task.fis.flags |= 0x80; /* C=1: update ATA cmd reg */
@@ -2578,7 +2485,7 @@ static int phy_up_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
 	u32 port_id, link_rate, hard_phy_linkrate;
 	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	u32 *frame_rcvd = (u32 *)sas_phy->frame_rcvd;
 	struct sas_identify_frame *id = (struct sas_identify_frame *)frame_rcvd;
 
@@ -2765,7 +2672,7 @@ static void phy_bcast_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
 static irqreturn_t int_chnl_int_v2_hw(int irq_no, void *p)
 {
 	struct hisi_hba *hisi_hba = p;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	u32 ent_msk, ent_tmp, irq_msk;
 	int phy_no = 0;
 
@@ -2825,7 +2732,7 @@ static irqreturn_t int_chnl_int_v2_hw(int irq_no, void *p)
 static void
 one_bit_ecc_error_process_v2_hw(struct hisi_hba *hisi_hba, u32 irq_value)
 {
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	u32 reg_val;
 
 	if (irq_value & BIT(SAS_ECC_INTR_DQE_ECC_1B_OFF)) {
@@ -2914,7 +2821,7 @@ 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;
+	struct device *dev = hisi_hba->dev;
 
 	if (irq_value & BIT(SAS_ECC_INTR_DQE_ECC_MB_OFF)) {
 		reg_val = hisi_sas_read32(hisi_hba, HGC_DQE_ECC_ADDR);
@@ -3064,7 +2971,7 @@ 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;
+	struct device *dev = hisi_hba->dev;
 
 	irq_msk = hisi_sas_read32(hisi_hba, ENT_INT_SRC_MSK3);
 	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK3, irq_msk | 0xfffffffe);
@@ -3162,13 +3069,14 @@ static void cq_tasklet_v2_hw(unsigned long val)
 	struct hisi_sas_complete_v2_hdr *complete_queue;
 	u32 rd_point = cq->rd_point, wr_point, dev_id;
 	int queue = cq->id;
+	struct hisi_sas_dq *dq = &hisi_hba->dq[queue];
 
 	if (unlikely(hisi_hba->reject_stp_links_msk))
 		phys_try_accept_stp_links_v2_hw(hisi_hba);
 
 	complete_queue = hisi_hba->complete_hdr[queue];
 
-	spin_lock(&hisi_hba->lock);
+	spin_lock(&dq->lock);
 	wr_point = hisi_sas_read32(hisi_hba, COMPL_Q_0_WR_PTR +
 				   (0x14 * queue));
 
@@ -3218,7 +3126,7 @@ static void cq_tasklet_v2_hw(unsigned long val)
 	/* update rd_point */
 	cq->rd_point = rd_point;
 	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
-	spin_unlock(&hisi_hba->lock);
+	spin_unlock(&dq->lock);
 }
 
 static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)
@@ -3239,7 +3147,7 @@ static irqreturn_t sata_int_v2_hw(int irq_no, void *p)
 	struct hisi_sas_phy *phy = p;
 	struct hisi_hba *hisi_hba = phy->hisi_hba;
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	struct	hisi_sas_initial_fis *initial_fis;
 	struct dev_to_host_fis *fis;
 	u32 ent_tmp, ent_msk, ent_int, port_id, link_rate, hard_phy_linkrate;
@@ -3341,7 +3249,7 @@ static irq_handler_t fatal_interrupts[HISI_SAS_FATAL_INT_NR] = {
  */
 static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 {
-	struct platform_device *pdev = hisi_hba->pdev;
+	struct platform_device *pdev = hisi_hba->platform_dev;
 	struct device *dev = &pdev->dev;
 	int i, irq, rc, irq_map[128];
 
@@ -3455,7 +3363,7 @@ static int hisi_sas_v2_init(struct hisi_hba *hisi_hba)
 
 static void interrupt_disable_v2_hw(struct hisi_hba *hisi_hba)
 {
-	struct platform_device *pdev = hisi_hba->pdev;
+	struct platform_device *pdev = hisi_hba->platform_dev;
 	int i;
 
 	for (i = 0; i < hisi_hba->queue_count; i++)
@@ -3477,7 +3385,7 @@ static void interrupt_disable_v2_hw(struct hisi_hba *hisi_hba)
 
 static int soft_reset_v2_hw(struct hisi_hba *hisi_hba)
 {
-	struct device *dev = &hisi_hba->pdev->dev;
+	struct device *dev = hisi_hba->dev;
 	u32 old_state, state;
 	int rc, cnt;
 	int phy_no;

drivers/scsi/hisi_sas/hisi_sas_v3_hw.c

@@ -0,0 +1,1846 @@
+/*
+ * Copyright (c) 2017 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#include "hisi_sas.h"
+#define DRV_NAME "hisi_sas_v3_hw"
+
+/* global registers need init*/
+#define DLVRY_QUEUE_ENABLE		0x0
+#define IOST_BASE_ADDR_LO		0x8
+#define IOST_BASE_ADDR_HI		0xc
+#define ITCT_BASE_ADDR_LO		0x10
+#define ITCT_BASE_ADDR_HI		0x14
+#define IO_BROKEN_MSG_ADDR_LO		0x18
+#define IO_BROKEN_MSG_ADDR_HI		0x1c
+#define PHY_CONTEXT			0x20
+#define PHY_STATE			0x24
+#define PHY_PORT_NUM_MA			0x28
+#define PHY_CONN_RATE			0x30
+#define AXI_AHB_CLK_CFG			0x3c
+#define ITCT_CLR			0x44
+#define ITCT_CLR_EN_OFF			16
+#define ITCT_CLR_EN_MSK			(0x1 << ITCT_CLR_EN_OFF)
+#define ITCT_DEV_OFF			0
+#define ITCT_DEV_MSK			(0x7ff << ITCT_DEV_OFF)
+#define AXI_USER1			0x48
+#define AXI_USER2			0x4c
+#define IO_SATA_BROKEN_MSG_ADDR_LO	0x58
+#define IO_SATA_BROKEN_MSG_ADDR_HI	0x5c
+#define SATA_INITI_D2H_STORE_ADDR_LO	0x60
+#define SATA_INITI_D2H_STORE_ADDR_HI	0x64
+#define CFG_MAX_TAG			0x68
+#define HGC_SAS_TX_OPEN_FAIL_RETRY_CTRL	0x84
+#define HGC_SAS_TXFAIL_RETRY_CTRL	0x88
+#define HGC_GET_ITV_TIME		0x90
+#define DEVICE_MSG_WORK_MODE		0x94
+#define OPENA_WT_CONTI_TIME		0x9c
+#define I_T_NEXUS_LOSS_TIME		0xa0
+#define MAX_CON_TIME_LIMIT_TIME		0xa4
+#define BUS_INACTIVE_LIMIT_TIME		0xa8
+#define REJECT_TO_OPEN_LIMIT_TIME	0xac
+#define CFG_AGING_TIME			0xbc
+#define HGC_DFX_CFG2			0xc0
+#define CFG_ABT_SET_QUERY_IPTT	0xd4
+#define CFG_SET_ABORTED_IPTT_OFF	0
+#define CFG_SET_ABORTED_IPTT_MSK	(0xfff << CFG_SET_ABORTED_IPTT_OFF)
+#define CFG_SET_ABORTED_EN_OFF	12
+#define CFG_ABT_SET_IPTT_DONE	0xd8
+#define CFG_ABT_SET_IPTT_DONE_OFF	0
+#define HGC_IOMB_PROC1_STATUS	0x104
+#define CFG_1US_TIMER_TRSH		0xcc
+#define CHNL_INT_STATUS			0x148
+#define INT_COAL_EN			0x19c
+#define OQ_INT_COAL_TIME		0x1a0
+#define OQ_INT_COAL_CNT			0x1a4
+#define ENT_INT_COAL_TIME		0x1a8
+#define ENT_INT_COAL_CNT		0x1ac
+#define OQ_INT_SRC			0x1b0
+#define OQ_INT_SRC_MSK			0x1b4
+#define ENT_INT_SRC1			0x1b8
+#define ENT_INT_SRC1_D2H_FIS_CH0_OFF	0
+#define ENT_INT_SRC1_D2H_FIS_CH0_MSK	(0x1 << ENT_INT_SRC1_D2H_FIS_CH0_OFF)
+#define ENT_INT_SRC1_D2H_FIS_CH1_OFF	8
+#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 CHNL_PHYUPDOWN_INT_MSK		0x1d0
+#define CHNL_ENT_INT_MSK			0x1d4
+#define HGC_COM_INT_MSK				0x1d8
+#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_MSK		0x1ec
+#define HGC_ERR_STAT_EN			0x238
+#define DLVRY_Q_0_BASE_ADDR_LO		0x260
+#define DLVRY_Q_0_BASE_ADDR_HI		0x264
+#define DLVRY_Q_0_DEPTH			0x268
+#define DLVRY_Q_0_WR_PTR		0x26c
+#define DLVRY_Q_0_RD_PTR		0x270
+#define HYPER_STREAM_ID_EN_CFG		0xc80
+#define OQ0_INT_SRC_MSK			0xc90
+#define COMPL_Q_0_BASE_ADDR_LO		0x4e0
+#define COMPL_Q_0_BASE_ADDR_HI		0x4e4
+#define COMPL_Q_0_DEPTH			0x4e8
+#define COMPL_Q_0_WR_PTR		0x4ec
+#define COMPL_Q_0_RD_PTR		0x4f0
+#define AWQOS_AWCACHE_CFG	0xc84
+#define ARQOS_ARCACHE_CFG	0xc88
+
+/* phy registers requiring init */
+#define PORT_BASE			(0x2000)
+#define PHY_CFG				(PORT_BASE + 0x0)
+#define HARD_PHY_LINKRATE		(PORT_BASE + 0x4)
+#define PHY_CFG_ENA_OFF			0
+#define PHY_CFG_ENA_MSK			(0x1 << PHY_CFG_ENA_OFF)
+#define PHY_CFG_DC_OPT_OFF		2
+#define PHY_CFG_DC_OPT_MSK		(0x1 << PHY_CFG_DC_OPT_OFF)
+#define PROG_PHY_LINK_RATE		(PORT_BASE + 0x8)
+#define PHY_CTRL			(PORT_BASE + 0x14)
+#define PHY_CTRL_RESET_OFF		0
+#define PHY_CTRL_RESET_MSK		(0x1 << PHY_CTRL_RESET_OFF)
+#define SL_CFG				(PORT_BASE + 0x84)
+#define SL_CONTROL			(PORT_BASE + 0x94)
+#define SL_CONTROL_NOTIFY_EN_OFF	0
+#define SL_CONTROL_NOTIFY_EN_MSK	(0x1 << SL_CONTROL_NOTIFY_EN_OFF)
+#define SL_CTA_OFF		17
+#define SL_CTA_MSK		(0x1 << SL_CTA_OFF)
+#define TX_ID_DWORD0			(PORT_BASE + 0x9c)
+#define TX_ID_DWORD1			(PORT_BASE + 0xa0)
+#define TX_ID_DWORD2			(PORT_BASE + 0xa4)
+#define TX_ID_DWORD3			(PORT_BASE + 0xa8)
+#define TX_ID_DWORD4			(PORT_BASE + 0xaC)
+#define TX_ID_DWORD5			(PORT_BASE + 0xb0)
+#define TX_ID_DWORD6			(PORT_BASE + 0xb4)
+#define TXID_AUTO				(PORT_BASE + 0xb8)
+#define CT3_OFF		1
+#define CT3_MSK		(0x1 << CT3_OFF)
+#define TX_HARDRST_OFF          2
+#define TX_HARDRST_MSK          (0x1 << TX_HARDRST_OFF)
+#define RX_IDAF_DWORD0			(PORT_BASE + 0xc4)
+#define RXOP_CHECK_CFG_H		(PORT_BASE + 0xfc)
+#define SAS_SSP_CON_TIMER_CFG		(PORT_BASE + 0x134)
+#define SAS_SMP_CON_TIMER_CFG		(PORT_BASE + 0x138)
+#define SAS_STP_CON_TIMER_CFG		(PORT_BASE + 0x13c)
+#define CHL_INT0			(PORT_BASE + 0x1b4)
+#define CHL_INT0_HOTPLUG_TOUT_OFF	0
+#define CHL_INT0_HOTPLUG_TOUT_MSK	(0x1 << CHL_INT0_HOTPLUG_TOUT_OFF)
+#define CHL_INT0_SL_RX_BCST_ACK_OFF	1
+#define CHL_INT0_SL_RX_BCST_ACK_MSK	(0x1 << CHL_INT0_SL_RX_BCST_ACK_OFF)
+#define CHL_INT0_SL_PHY_ENABLE_OFF	2
+#define CHL_INT0_SL_PHY_ENABLE_MSK	(0x1 << CHL_INT0_SL_PHY_ENABLE_OFF)
+#define CHL_INT0_NOT_RDY_OFF		4
+#define CHL_INT0_NOT_RDY_MSK		(0x1 << CHL_INT0_NOT_RDY_OFF)
+#define CHL_INT0_PHY_RDY_OFF		5
+#define CHL_INT0_PHY_RDY_MSK		(0x1 << CHL_INT0_PHY_RDY_OFF)
+#define CHL_INT1			(PORT_BASE + 0x1b8)
+#define CHL_INT1_DMAC_TX_ECC_ERR_OFF	15
+#define CHL_INT1_DMAC_TX_ECC_ERR_MSK	(0x1 << CHL_INT1_DMAC_TX_ECC_ERR_OFF)
+#define CHL_INT1_DMAC_RX_ECC_ERR_OFF	17
+#define CHL_INT1_DMAC_RX_ECC_ERR_MSK	(0x1 << CHL_INT1_DMAC_RX_ECC_ERR_OFF)
+#define CHL_INT2			(PORT_BASE + 0x1bc)
+#define CHL_INT0_MSK			(PORT_BASE + 0x1c0)
+#define CHL_INT1_MSK			(PORT_BASE + 0x1c4)
+#define CHL_INT2_MSK			(PORT_BASE + 0x1c8)
+#define CHL_INT_COAL_EN			(PORT_BASE + 0x1d0)
+#define PHY_CTRL_RDY_MSK		(PORT_BASE + 0x2b0)
+#define PHYCTRL_NOT_RDY_MSK		(PORT_BASE + 0x2b4)
+#define PHYCTRL_DWS_RESET_MSK		(PORT_BASE + 0x2b8)
+#define PHYCTRL_PHY_ENA_MSK		(PORT_BASE + 0x2bc)
+#define SL_RX_BCAST_CHK_MSK		(PORT_BASE + 0x2c0)
+#define PHYCTRL_OOB_RESTART_MSK		(PORT_BASE + 0x2c4)
+
+/* HW dma structures */
+/* Delivery queue header */
+/* dw0 */
+#define CMD_HDR_ABORT_FLAG_OFF		0
+#define CMD_HDR_ABORT_FLAG_MSK		(0x3 << CMD_HDR_ABORT_FLAG_OFF)
+#define CMD_HDR_ABORT_DEVICE_TYPE_OFF	2
+#define CMD_HDR_ABORT_DEVICE_TYPE_MSK	(0x1 << CMD_HDR_ABORT_DEVICE_TYPE_OFF)
+#define CMD_HDR_RESP_REPORT_OFF		5
+#define CMD_HDR_RESP_REPORT_MSK		(0x1 << CMD_HDR_RESP_REPORT_OFF)
+#define CMD_HDR_TLR_CTRL_OFF		6
+#define CMD_HDR_TLR_CTRL_MSK		(0x3 << CMD_HDR_TLR_CTRL_OFF)
+#define CMD_HDR_PORT_OFF		18
+#define CMD_HDR_PORT_MSK		(0xf << CMD_HDR_PORT_OFF)
+#define CMD_HDR_PRIORITY_OFF		27
+#define CMD_HDR_PRIORITY_MSK		(0x1 << CMD_HDR_PRIORITY_OFF)
+#define CMD_HDR_CMD_OFF			29
+#define CMD_HDR_CMD_MSK			(0x7 << CMD_HDR_CMD_OFF)
+/* dw1 */
+#define CMD_HDR_UNCON_CMD_OFF	3
+#define CMD_HDR_DIR_OFF			5
+#define CMD_HDR_DIR_MSK			(0x3 << CMD_HDR_DIR_OFF)
+#define CMD_HDR_RESET_OFF		7
+#define CMD_HDR_RESET_MSK		(0x1 << CMD_HDR_RESET_OFF)
+#define CMD_HDR_VDTL_OFF		10
+#define CMD_HDR_VDTL_MSK		(0x1 << CMD_HDR_VDTL_OFF)
+#define CMD_HDR_FRAME_TYPE_OFF		11
+#define CMD_HDR_FRAME_TYPE_MSK		(0x1f << CMD_HDR_FRAME_TYPE_OFF)
+#define CMD_HDR_DEV_ID_OFF		16
+#define CMD_HDR_DEV_ID_MSK		(0xffff << CMD_HDR_DEV_ID_OFF)
+/* dw2 */
+#define CMD_HDR_CFL_OFF			0
+#define CMD_HDR_CFL_MSK			(0x1ff << CMD_HDR_CFL_OFF)
+#define CMD_HDR_NCQ_TAG_OFF		10
+#define CMD_HDR_NCQ_TAG_MSK		(0x1f << CMD_HDR_NCQ_TAG_OFF)
+#define CMD_HDR_MRFL_OFF		15
+#define CMD_HDR_MRFL_MSK		(0x1ff << CMD_HDR_MRFL_OFF)
+#define CMD_HDR_SG_MOD_OFF		24
+#define CMD_HDR_SG_MOD_MSK		(0x3 << CMD_HDR_SG_MOD_OFF)
+/* dw3 */
+#define CMD_HDR_IPTT_OFF		0
+#define CMD_HDR_IPTT_MSK		(0xffff << CMD_HDR_IPTT_OFF)
+/* dw6 */
+#define CMD_HDR_DIF_SGL_LEN_OFF		0
+#define CMD_HDR_DIF_SGL_LEN_MSK		(0xffff << CMD_HDR_DIF_SGL_LEN_OFF)
+#define CMD_HDR_DATA_SGL_LEN_OFF	16
+#define CMD_HDR_DATA_SGL_LEN_MSK	(0xffff << CMD_HDR_DATA_SGL_LEN_OFF)
+/* dw7 */
+#define CMD_HDR_ADDR_MODE_SEL_OFF		15
+#define CMD_HDR_ADDR_MODE_SEL_MSK		(1 << CMD_HDR_ADDR_MODE_SEL_OFF)
+#define CMD_HDR_ABORT_IPTT_OFF		16
+#define CMD_HDR_ABORT_IPTT_MSK		(0xffff << CMD_HDR_ABORT_IPTT_OFF)
+
+/* Completion header */
+/* dw0 */
+#define CMPLT_HDR_CMPLT_OFF		0
+#define CMPLT_HDR_CMPLT_MSK		(0x3 << CMPLT_HDR_CMPLT_OFF)
+#define CMPLT_HDR_ERROR_PHASE_OFF   2
+#define CMPLT_HDR_ERROR_PHASE_MSK   (0xff << CMPLT_HDR_ERROR_PHASE_OFF)
+#define CMPLT_HDR_RSPNS_XFRD_OFF	10
+#define CMPLT_HDR_RSPNS_XFRD_MSK	(0x1 << CMPLT_HDR_RSPNS_XFRD_OFF)
+#define CMPLT_HDR_ERX_OFF		12
+#define CMPLT_HDR_ERX_MSK		(0x1 << CMPLT_HDR_ERX_OFF)
+#define CMPLT_HDR_ABORT_STAT_OFF	13
+#define CMPLT_HDR_ABORT_STAT_MSK	(0x7 << CMPLT_HDR_ABORT_STAT_OFF)
+/* abort_stat */
+#define STAT_IO_NOT_VALID		0x1
+#define STAT_IO_NO_DEVICE		0x2
+#define STAT_IO_COMPLETE		0x3
+#define STAT_IO_ABORTED			0x4
+/* dw1 */
+#define CMPLT_HDR_IPTT_OFF		0
+#define CMPLT_HDR_IPTT_MSK		(0xffff << CMPLT_HDR_IPTT_OFF)
+#define CMPLT_HDR_DEV_ID_OFF		16
+#define CMPLT_HDR_DEV_ID_MSK		(0xffff << CMPLT_HDR_DEV_ID_OFF)
+/* dw3 */
+#define CMPLT_HDR_IO_IN_TARGET_OFF	17
+#define CMPLT_HDR_IO_IN_TARGET_MSK	(0x1 << CMPLT_HDR_IO_IN_TARGET_OFF)
+
+/* ITCT header */
+/* qw0 */
+#define ITCT_HDR_DEV_TYPE_OFF		0
+#define ITCT_HDR_DEV_TYPE_MSK		(0x3 << ITCT_HDR_DEV_TYPE_OFF)
+#define ITCT_HDR_VALID_OFF		2
+#define ITCT_HDR_VALID_MSK		(0x1 << ITCT_HDR_VALID_OFF)
+#define ITCT_HDR_MCR_OFF		5
+#define ITCT_HDR_MCR_MSK		(0xf << ITCT_HDR_MCR_OFF)
+#define ITCT_HDR_VLN_OFF		9
+#define ITCT_HDR_VLN_MSK		(0xf << ITCT_HDR_VLN_OFF)
+#define ITCT_HDR_SMP_TIMEOUT_OFF	16
+#define ITCT_HDR_AWT_CONTINUE_OFF	25
+#define ITCT_HDR_PORT_ID_OFF		28
+#define ITCT_HDR_PORT_ID_MSK		(0xf << ITCT_HDR_PORT_ID_OFF)
+/* qw2 */
+#define ITCT_HDR_INLT_OFF		0
+#define ITCT_HDR_INLT_MSK		(0xffffULL << ITCT_HDR_INLT_OFF)
+#define ITCT_HDR_RTOLT_OFF		48
+#define ITCT_HDR_RTOLT_MSK		(0xffffULL << ITCT_HDR_RTOLT_OFF)
+
+struct hisi_sas_complete_v3_hdr {
+	__le32 dw0;
+	__le32 dw1;
+	__le32 act;
+	__le32 dw3;
+};
+
+struct hisi_sas_err_record_v3 {
+	/* dw0 */
+	__le32 trans_tx_fail_type;
+
+	/* dw1 */
+	__le32 trans_rx_fail_type;
+
+	/* dw2 */
+	__le16 dma_tx_err_type;
+	__le16 sipc_rx_err_type;
+
+	/* dw3 */
+	__le32 dma_rx_err_type;
+};
+
+#define RX_DATA_LEN_UNDERFLOW_OFF	6
+#define RX_DATA_LEN_UNDERFLOW_MSK	(1 << RX_DATA_LEN_UNDERFLOW_OFF)
+
+#define HISI_SAS_COMMAND_ENTRIES_V3_HW 4096
+#define HISI_SAS_MSI_COUNT_V3_HW 32
+
+enum {
+	HISI_SAS_PHY_PHY_UPDOWN,
+	HISI_SAS_PHY_CHNL_INT,
+	HISI_SAS_PHY_INT_NR
+};
+
+#define DIR_NO_DATA 0
+#define DIR_TO_INI 1
+#define DIR_TO_DEVICE 2
+#define DIR_RESERVED 3
+
+#define CMD_IS_UNCONSTRAINT(cmd) \
+	((cmd == ATA_CMD_READ_LOG_EXT) || \
+	(cmd == ATA_CMD_READ_LOG_DMA_EXT) || \
+	(cmd == ATA_CMD_DEV_RESET))
+
+static u32 hisi_sas_read32(struct hisi_hba *hisi_hba, u32 off)
+{
+	void __iomem *regs = hisi_hba->regs + off;
+
+	return readl(regs);
+}
+
+static u32 hisi_sas_read32_relaxed(struct hisi_hba *hisi_hba, u32 off)
+{
+	void __iomem *regs = hisi_hba->regs + off;
+
+	return readl_relaxed(regs);
+}
+
+static void hisi_sas_write32(struct hisi_hba *hisi_hba, u32 off, u32 val)
+{
+	void __iomem *regs = hisi_hba->regs + off;
+
+	writel(val, regs);
+}
+
+static void hisi_sas_phy_write32(struct hisi_hba *hisi_hba, int phy_no,
+				 u32 off, u32 val)
+{
+	void __iomem *regs = hisi_hba->regs + (0x400 * phy_no) + off;
+
+	writel(val, regs);
+}
+
+static u32 hisi_sas_phy_read32(struct hisi_hba *hisi_hba,
+				      int phy_no, u32 off)
+{
+	void __iomem *regs = hisi_hba->regs + (0x400 * phy_no) + off;
+
+	return readl(regs);
+}
+
+static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
+{
+	int i;
+
+	/* Global registers init */
+	hisi_sas_write32(hisi_hba, DLVRY_QUEUE_ENABLE,
+			 (u32)((1ULL << hisi_hba->queue_count) - 1));
+	hisi_sas_write32(hisi_hba, AXI_USER1, 0x0);
+	hisi_sas_write32(hisi_hba, AXI_USER2, 0x40000060);
+	hisi_sas_write32(hisi_hba, HGC_SAS_TXFAIL_RETRY_CTRL, 0x108);
+	hisi_sas_write32(hisi_hba, CFG_1US_TIMER_TRSH, 0xd);
+	hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x1);
+	hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0x1);
+	hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT, 0x1);
+	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 0xffff);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC1, 0xffffffff);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC2, 0xffffffff);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC3, 0xffffffff);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK1, 0xfefefefe);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK2, 0xfefefefe);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK3, 0xffffffff);
+	hisi_sas_write32(hisi_hba, CHNL_PHYUPDOWN_INT_MSK, 0x0);
+	hisi_sas_write32(hisi_hba, CHNL_ENT_INT_MSK, 0x0);
+	hisi_sas_write32(hisi_hba, HGC_COM_INT_MSK, 0x0);
+	hisi_sas_write32(hisi_hba, SAS_ECC_INTR_MSK, 0xfff00c30);
+	hisi_sas_write32(hisi_hba, AWQOS_AWCACHE_CFG, 0xf0f0);
+	hisi_sas_write32(hisi_hba, ARQOS_ARCACHE_CFG, 0xf0f0);
+	for (i = 0; i < hisi_hba->queue_count; i++)
+		hisi_sas_write32(hisi_hba, OQ0_INT_SRC_MSK+0x4*i, 0);
+
+	hisi_sas_write32(hisi_hba, AXI_AHB_CLK_CFG, 1);
+	hisi_sas_write32(hisi_hba, HYPER_STREAM_ID_EN_CFG, 1);
+	hisi_sas_write32(hisi_hba, CFG_MAX_TAG, 0xfff07fff);
+
+	for (i = 0; i < hisi_hba->n_phy; i++) {
+		hisi_sas_phy_write32(hisi_hba, i, PROG_PHY_LINK_RATE, 0x801);
+		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, 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);
+		hisi_sas_phy_write32(hisi_hba, i, SL_CFG, 0x83f801fc);
+		hisi_sas_phy_write32(hisi_hba, i, PHY_CTRL_RDY_MSK, 0x0);
+		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_NOT_RDY_MSK, 0x0);
+		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_DWS_RESET_MSK, 0x0);
+		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_PHY_ENA_MSK, 0x0);
+		hisi_sas_phy_write32(hisi_hba, i, SL_RX_BCAST_CHK_MSK, 0x0);
+		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_OOB_RESTART_MSK, 0x0);
+		hisi_sas_phy_write32(hisi_hba, i, PHY_CTRL, 0x199b4fa);
+		hisi_sas_phy_write32(hisi_hba, i, SAS_SSP_CON_TIMER_CFG,
+				     0xa0064);
+		hisi_sas_phy_write32(hisi_hba, i, SAS_STP_CON_TIMER_CFG,
+				     0xa0064);
+	}
+	for (i = 0; i < hisi_hba->queue_count; i++) {
+		/* Delivery queue */
+		hisi_sas_write32(hisi_hba,
+				 DLVRY_Q_0_BASE_ADDR_HI + (i * 0x14),
+				 upper_32_bits(hisi_hba->cmd_hdr_dma[i]));
+
+		hisi_sas_write32(hisi_hba, DLVRY_Q_0_BASE_ADDR_LO + (i * 0x14),
+				 lower_32_bits(hisi_hba->cmd_hdr_dma[i]));
+
+		hisi_sas_write32(hisi_hba, DLVRY_Q_0_DEPTH + (i * 0x14),
+				 HISI_SAS_QUEUE_SLOTS);
+
+		/* Completion queue */
+		hisi_sas_write32(hisi_hba, COMPL_Q_0_BASE_ADDR_HI + (i * 0x14),
+				 upper_32_bits(hisi_hba->complete_hdr_dma[i]));
+
+		hisi_sas_write32(hisi_hba, COMPL_Q_0_BASE_ADDR_LO + (i * 0x14),
+				 lower_32_bits(hisi_hba->complete_hdr_dma[i]));
+
+		hisi_sas_write32(hisi_hba, COMPL_Q_0_DEPTH + (i * 0x14),
+				 HISI_SAS_QUEUE_SLOTS);
+	}
+
+	/* itct */
+	hisi_sas_write32(hisi_hba, ITCT_BASE_ADDR_LO,
+			 lower_32_bits(hisi_hba->itct_dma));
+
+	hisi_sas_write32(hisi_hba, ITCT_BASE_ADDR_HI,
+			 upper_32_bits(hisi_hba->itct_dma));
+
+	/* iost */
+	hisi_sas_write32(hisi_hba, IOST_BASE_ADDR_LO,
+			 lower_32_bits(hisi_hba->iost_dma));
+
+	hisi_sas_write32(hisi_hba, IOST_BASE_ADDR_HI,
+			 upper_32_bits(hisi_hba->iost_dma));
+
+	/* breakpoint */
+	hisi_sas_write32(hisi_hba, IO_BROKEN_MSG_ADDR_LO,
+			 lower_32_bits(hisi_hba->breakpoint_dma));
+
+	hisi_sas_write32(hisi_hba, IO_BROKEN_MSG_ADDR_HI,
+			 upper_32_bits(hisi_hba->breakpoint_dma));
+
+	/* SATA broken msg */
+	hisi_sas_write32(hisi_hba, IO_SATA_BROKEN_MSG_ADDR_LO,
+			 lower_32_bits(hisi_hba->sata_breakpoint_dma));
+
+	hisi_sas_write32(hisi_hba, IO_SATA_BROKEN_MSG_ADDR_HI,
+			 upper_32_bits(hisi_hba->sata_breakpoint_dma));
+
+	/* SATA initial fis */
+	hisi_sas_write32(hisi_hba, SATA_INITI_D2H_STORE_ADDR_LO,
+			 lower_32_bits(hisi_hba->initial_fis_dma));
+
+	hisi_sas_write32(hisi_hba, SATA_INITI_D2H_STORE_ADDR_HI,
+			 upper_32_bits(hisi_hba->initial_fis_dma));
+}
+
+static void config_phy_opt_mode_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	u32 cfg = hisi_sas_phy_read32(hisi_hba, phy_no, PHY_CFG);
+
+	cfg &= ~PHY_CFG_DC_OPT_MSK;
+	cfg |= 1 << PHY_CFG_DC_OPT_OFF;
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
+}
+
+static void config_id_frame_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	struct sas_identify_frame identify_frame;
+	u32 *identify_buffer;
+
+	memset(&identify_frame, 0, sizeof(identify_frame));
+	identify_frame.dev_type = SAS_END_DEVICE;
+	identify_frame.frame_type = 0;
+	identify_frame._un1 = 1;
+	identify_frame.initiator_bits = SAS_PROTOCOL_ALL;
+	identify_frame.target_bits = SAS_PROTOCOL_NONE;
+	memcpy(&identify_frame._un4_11[0], hisi_hba->sas_addr, SAS_ADDR_SIZE);
+	memcpy(&identify_frame.sas_addr[0], hisi_hba->sas_addr,	SAS_ADDR_SIZE);
+	identify_frame.phy_id = phy_no;
+	identify_buffer = (u32 *)(&identify_frame);
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, TX_ID_DWORD0,
+			__swab32(identify_buffer[0]));
+	hisi_sas_phy_write32(hisi_hba, phy_no, TX_ID_DWORD1,
+			__swab32(identify_buffer[1]));
+	hisi_sas_phy_write32(hisi_hba, phy_no, TX_ID_DWORD2,
+			__swab32(identify_buffer[2]));
+	hisi_sas_phy_write32(hisi_hba, phy_no, TX_ID_DWORD3,
+			__swab32(identify_buffer[3]));
+	hisi_sas_phy_write32(hisi_hba, phy_no, TX_ID_DWORD4,
+			__swab32(identify_buffer[4]));
+	hisi_sas_phy_write32(hisi_hba, phy_no, TX_ID_DWORD5,
+			__swab32(identify_buffer[5]));
+}
+
+static void setup_itct_v3_hw(struct hisi_hba *hisi_hba,
+			     struct hisi_sas_device *sas_dev)
+{
+	struct domain_device *device = sas_dev->sas_device;
+	struct device *dev = hisi_hba->dev;
+	u64 qw0, device_id = sas_dev->device_id;
+	struct hisi_sas_itct *itct = &hisi_hba->itct[device_id];
+	struct domain_device *parent_dev = device->parent;
+	struct asd_sas_port *sas_port = device->port;
+	struct hisi_sas_port *port = to_hisi_sas_port(sas_port);
+
+	memset(itct, 0, sizeof(*itct));
+
+	/* qw0 */
+	qw0 = 0;
+	switch (sas_dev->dev_type) {
+	case SAS_END_DEVICE:
+	case SAS_EDGE_EXPANDER_DEVICE:
+	case SAS_FANOUT_EXPANDER_DEVICE:
+		qw0 = HISI_SAS_DEV_TYPE_SSP << ITCT_HDR_DEV_TYPE_OFF;
+		break;
+	case SAS_SATA_DEV:
+	case SAS_SATA_PENDING:
+		if (parent_dev && DEV_IS_EXPANDER(parent_dev->dev_type))
+			qw0 = HISI_SAS_DEV_TYPE_STP << ITCT_HDR_DEV_TYPE_OFF;
+		else
+			qw0 = HISI_SAS_DEV_TYPE_SATA << ITCT_HDR_DEV_TYPE_OFF;
+		break;
+	default:
+		dev_warn(dev, "setup itct: unsupported dev type (%d)\n",
+			 sas_dev->dev_type);
+	}
+
+	qw0 |= ((1 << ITCT_HDR_VALID_OFF) |
+		(device->linkrate << ITCT_HDR_MCR_OFF) |
+		(1 << ITCT_HDR_VLN_OFF) |
+		(0xfa << ITCT_HDR_SMP_TIMEOUT_OFF) |
+		(1 << ITCT_HDR_AWT_CONTINUE_OFF) |
+		(port->id << ITCT_HDR_PORT_ID_OFF));
+	itct->qw0 = cpu_to_le64(qw0);
+
+	/* qw1 */
+	memcpy(&itct->sas_addr, device->sas_addr, SAS_ADDR_SIZE);
+	itct->sas_addr = __swab64(itct->sas_addr);
+
+	/* qw2 */
+	if (!dev_is_sata(device))
+		itct->qw2 = cpu_to_le64((5000ULL << ITCT_HDR_INLT_OFF) |
+					(0x1ULL << ITCT_HDR_RTOLT_OFF));
+}
+
+static void free_device_v3_hw(struct hisi_hba *hisi_hba,
+			      struct hisi_sas_device *sas_dev)
+{
+	u64 dev_id = sas_dev->device_id;
+	struct device *dev = hisi_hba->dev;
+	struct hisi_sas_itct *itct = &hisi_hba->itct[dev_id];
+	u32 reg_val = hisi_sas_read32(hisi_hba, ENT_INT_SRC3);
+
+	/* clear the itct interrupt state */
+	if (ENT_INT_SRC3_ITC_INT_MSK & reg_val)
+		hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
+				 ENT_INT_SRC3_ITC_INT_MSK);
+
+	/* clear the itct table*/
+	reg_val = hisi_sas_read32(hisi_hba, ITCT_CLR);
+	reg_val |= ITCT_CLR_EN_MSK | (dev_id & ITCT_DEV_MSK);
+	hisi_sas_write32(hisi_hba, ITCT_CLR, reg_val);
+
+	udelay(10);
+	reg_val = hisi_sas_read32(hisi_hba, ENT_INT_SRC3);
+	if (ENT_INT_SRC3_ITC_INT_MSK & reg_val) {
+		dev_dbg(dev, "got clear ITCT done interrupt\n");
+
+		/* invalid the itct state*/
+		memset(itct, 0, sizeof(struct hisi_sas_itct));
+		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);
+		dev_dbg(dev, "clear ITCT ok\n");
+	}
+}
+
+static void dereg_device_v3_hw(struct hisi_hba *hisi_hba,
+				struct domain_device *device)
+{
+	struct hisi_sas_slot *slot, *slot2;
+	struct hisi_sas_device *sas_dev = device->lldd_dev;
+	u32 cfg_abt_set_query_iptt;
+
+	cfg_abt_set_query_iptt = hisi_sas_read32(hisi_hba,
+		CFG_ABT_SET_QUERY_IPTT);
+	list_for_each_entry_safe(slot, slot2, &sas_dev->list, entry) {
+		cfg_abt_set_query_iptt &= ~CFG_SET_ABORTED_IPTT_MSK;
+		cfg_abt_set_query_iptt |= (1 << CFG_SET_ABORTED_EN_OFF) |
+			(slot->idx << CFG_SET_ABORTED_IPTT_OFF);
+		hisi_sas_write32(hisi_hba, CFG_ABT_SET_QUERY_IPTT,
+			cfg_abt_set_query_iptt);
+	}
+	cfg_abt_set_query_iptt &= ~(1 << CFG_SET_ABORTED_EN_OFF);
+	hisi_sas_write32(hisi_hba, CFG_ABT_SET_QUERY_IPTT,
+		cfg_abt_set_query_iptt);
+	hisi_sas_write32(hisi_hba, CFG_ABT_SET_IPTT_DONE,
+					1 << CFG_ABT_SET_IPTT_DONE_OFF);
+}
+
+static int hw_init_v3_hw(struct hisi_hba *hisi_hba)
+{
+	init_reg_v3_hw(hisi_hba);
+
+	return 0;
+}
+
+static void enable_phy_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	u32 cfg = hisi_sas_phy_read32(hisi_hba, phy_no, PHY_CFG);
+
+	cfg |= PHY_CFG_ENA_MSK;
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
+}
+
+static void disable_phy_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	u32 cfg = hisi_sas_phy_read32(hisi_hba, phy_no, PHY_CFG);
+
+	cfg &= ~PHY_CFG_ENA_MSK;
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
+}
+
+static void start_phy_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	config_id_frame_v3_hw(hisi_hba, phy_no);
+	config_phy_opt_mode_v3_hw(hisi_hba, phy_no);
+	enable_phy_v3_hw(hisi_hba, phy_no);
+}
+
+static void stop_phy_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	disable_phy_v3_hw(hisi_hba, phy_no);
+}
+
+static void start_phys_v3_hw(struct hisi_hba *hisi_hba)
+{
+	int i;
+
+	for (i = 0; i < hisi_hba->n_phy; i++)
+		start_phy_v3_hw(hisi_hba, i);
+}
+
+static void phy_hard_reset_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+	u32 txid_auto;
+
+	stop_phy_v3_hw(hisi_hba, phy_no);
+	if (phy->identify.device_type == SAS_END_DEVICE) {
+		txid_auto = hisi_sas_phy_read32(hisi_hba, phy_no, TXID_AUTO);
+		hisi_sas_phy_write32(hisi_hba, phy_no, TXID_AUTO,
+					txid_auto | TX_HARDRST_MSK);
+	}
+	msleep(100);
+	start_phy_v3_hw(hisi_hba, phy_no);
+}
+
+enum sas_linkrate phy_get_max_linkrate_v3_hw(void)
+{
+	return SAS_LINK_RATE_12_0_GBPS;
+}
+
+static void phys_init_v3_hw(struct hisi_hba *hisi_hba)
+{
+	start_phys_v3_hw(hisi_hba);
+}
+
+static void sl_notify_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	u32 sl_control;
+
+	sl_control = hisi_sas_phy_read32(hisi_hba, phy_no, SL_CONTROL);
+	sl_control |= SL_CONTROL_NOTIFY_EN_MSK;
+	hisi_sas_phy_write32(hisi_hba, phy_no, SL_CONTROL, sl_control);
+	msleep(1);
+	sl_control = hisi_sas_phy_read32(hisi_hba, phy_no, SL_CONTROL);
+	sl_control &= ~SL_CONTROL_NOTIFY_EN_MSK;
+	hisi_sas_phy_write32(hisi_hba, phy_no, SL_CONTROL, sl_control);
+}
+
+static int get_wideport_bitmap_v3_hw(struct hisi_hba *hisi_hba, int port_id)
+{
+	int i, bitmap = 0;
+	u32 phy_port_num_ma = hisi_sas_read32(hisi_hba, PHY_PORT_NUM_MA);
+
+	for (i = 0; i < hisi_hba->n_phy; i++)
+		if (((phy_port_num_ma >> (i * 4)) & 0xf) == port_id)
+			bitmap |= 1 << i;
+
+	return bitmap;
+}
+
+/**
+ * The callpath to this function and upto writing the write
+ * queue pointer should be safe from interruption.
+ */
+static int
+get_free_slot_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_dq *dq)
+{
+	struct device *dev = hisi_hba->dev;
+	int queue = dq->id;
+	u32 r, w;
+
+	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;
+	}
+
+	return 0;
+}
+
+static void start_delivery_v3_hw(struct hisi_sas_dq *dq)
+{
+	struct hisi_hba *hisi_hba = dq->hisi_hba;
+	int dlvry_queue = dq->slot_prep->dlvry_queue;
+	int dlvry_queue_slot = dq->slot_prep->dlvry_queue_slot;
+
+	dq->wr_point = ++dlvry_queue_slot % HISI_SAS_QUEUE_SLOTS;
+	hisi_sas_write32(hisi_hba, DLVRY_Q_0_WR_PTR + (dlvry_queue * 0x14),
+			 dq->wr_point);
+}
+
+static int prep_prd_sge_v3_hw(struct hisi_hba *hisi_hba,
+			      struct hisi_sas_slot *slot,
+			      struct hisi_sas_cmd_hdr *hdr,
+			      struct scatterlist *scatter,
+			      int n_elem)
+{
+	struct hisi_sas_sge_page *sge_page = hisi_sas_sge_addr_mem(slot);
+	struct device *dev = hisi_hba->dev;
+	struct scatterlist *sg;
+	int i;
+
+	if (n_elem > HISI_SAS_SGE_PAGE_CNT) {
+		dev_err(dev, "prd err: n_elem(%d) > HISI_SAS_SGE_PAGE_CNT",
+			n_elem);
+		return -EINVAL;
+	}
+
+	for_each_sg(scatter, sg, n_elem, i) {
+		struct hisi_sas_sge *entry = &sge_page->sge[i];
+
+		entry->addr = cpu_to_le64(sg_dma_address(sg));
+		entry->page_ctrl_0 = entry->page_ctrl_1 = 0;
+		entry->data_len = cpu_to_le32(sg_dma_len(sg));
+		entry->data_off = 0;
+	}
+
+	hdr->prd_table_addr = cpu_to_le64(hisi_sas_sge_addr_dma(slot));
+
+	hdr->sg_len = cpu_to_le32(n_elem << CMD_HDR_DATA_SGL_LEN_OFF);
+
+	return 0;
+}
+
+static int prep_ssp_v3_hw(struct hisi_hba *hisi_hba,
+			  struct hisi_sas_slot *slot, int is_tmf,
+			  struct hisi_sas_tmf_task *tmf)
+{
+	struct sas_task *task = slot->task;
+	struct hisi_sas_cmd_hdr *hdr = slot->cmd_hdr;
+	struct domain_device *device = task->dev;
+	struct hisi_sas_device *sas_dev = device->lldd_dev;
+	struct hisi_sas_port *port = slot->port;
+	struct sas_ssp_task *ssp_task = &task->ssp_task;
+	struct scsi_cmnd *scsi_cmnd = ssp_task->cmd;
+	int has_data = 0, rc, priority = is_tmf;
+	u8 *buf_cmd;
+	u32 dw1 = 0, dw2 = 0;
+
+	hdr->dw0 = cpu_to_le32((1 << CMD_HDR_RESP_REPORT_OFF) |
+			       (2 << CMD_HDR_TLR_CTRL_OFF) |
+			       (port->id << CMD_HDR_PORT_OFF) |
+			       (priority << CMD_HDR_PRIORITY_OFF) |
+			       (1 << CMD_HDR_CMD_OFF)); /* ssp */
+
+	dw1 = 1 << CMD_HDR_VDTL_OFF;
+	if (is_tmf) {
+		dw1 |= 2 << CMD_HDR_FRAME_TYPE_OFF;
+		dw1 |= DIR_NO_DATA << CMD_HDR_DIR_OFF;
+	} else {
+		dw1 |= 1 << CMD_HDR_FRAME_TYPE_OFF;
+		switch (scsi_cmnd->sc_data_direction) {
+		case DMA_TO_DEVICE:
+			has_data = 1;
+			dw1 |= DIR_TO_DEVICE << CMD_HDR_DIR_OFF;
+			break;
+		case DMA_FROM_DEVICE:
+			has_data = 1;
+			dw1 |= DIR_TO_INI << CMD_HDR_DIR_OFF;
+			break;
+		default:
+			dw1 &= ~CMD_HDR_DIR_MSK;
+		}
+	}
+
+	/* map itct entry */
+	dw1 |= sas_dev->device_id << CMD_HDR_DEV_ID_OFF;
+	hdr->dw1 = cpu_to_le32(dw1);
+
+	dw2 = (((sizeof(struct ssp_command_iu) + sizeof(struct ssp_frame_hdr)
+	      + 3) / 4) << CMD_HDR_CFL_OFF) |
+	      ((HISI_SAS_MAX_SSP_RESP_SZ / 4) << CMD_HDR_MRFL_OFF) |
+	      (2 << CMD_HDR_SG_MOD_OFF);
+	hdr->dw2 = cpu_to_le32(dw2);
+	hdr->transfer_tags = cpu_to_le32(slot->idx);
+
+	if (has_data) {
+		rc = prep_prd_sge_v3_hw(hisi_hba, slot, hdr, task->scatter,
+					slot->n_elem);
+		if (rc)
+			return rc;
+	}
+
+	hdr->data_transfer_len = cpu_to_le32(task->total_xfer_len);
+	hdr->cmd_table_addr = cpu_to_le64(hisi_sas_cmd_hdr_addr_dma(slot));
+	hdr->sts_buffer_addr = cpu_to_le64(hisi_sas_status_buf_addr_dma(slot));
+
+	buf_cmd = hisi_sas_cmd_hdr_addr_mem(slot) +
+		sizeof(struct ssp_frame_hdr);
+
+	memcpy(buf_cmd, &task->ssp_task.LUN, 8);
+	if (!is_tmf) {
+		buf_cmd[9] = ssp_task->task_attr | (ssp_task->task_prio << 3);
+		memcpy(buf_cmd + 12, scsi_cmnd->cmnd, scsi_cmnd->cmd_len);
+	} else {
+		buf_cmd[10] = tmf->tmf;
+		switch (tmf->tmf) {
+		case TMF_ABORT_TASK:
+		case TMF_QUERY_TASK:
+			buf_cmd[12] =
+				(tmf->tag_of_task_to_be_managed >> 8) & 0xff;
+			buf_cmd[13] =
+				tmf->tag_of_task_to_be_managed & 0xff;
+			break;
+		default:
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int prep_smp_v3_hw(struct hisi_hba *hisi_hba,
+			  struct hisi_sas_slot *slot)
+{
+	struct sas_task *task = slot->task;
+	struct hisi_sas_cmd_hdr *hdr = slot->cmd_hdr;
+	struct domain_device *device = task->dev;
+	struct device *dev = hisi_hba->dev;
+	struct hisi_sas_port *port = slot->port;
+	struct scatterlist *sg_req, *sg_resp;
+	struct hisi_sas_device *sas_dev = device->lldd_dev;
+	dma_addr_t req_dma_addr;
+	unsigned int req_len, resp_len;
+	int elem, rc;
+
+	/*
+	 * DMA-map SMP request, response buffers
+	 */
+	/* req */
+	sg_req = &task->smp_task.smp_req;
+	elem = dma_map_sg(dev, sg_req, 1, DMA_TO_DEVICE);
+	if (!elem)
+		return -ENOMEM;
+	req_len = sg_dma_len(sg_req);
+	req_dma_addr = sg_dma_address(sg_req);
+
+	/* resp */
+	sg_resp = &task->smp_task.smp_resp;
+	elem = dma_map_sg(dev, sg_resp, 1, DMA_FROM_DEVICE);
+	if (!elem) {
+		rc = -ENOMEM;
+		goto err_out_req;
+	}
+	resp_len = sg_dma_len(sg_resp);
+	if ((req_len & 0x3) || (resp_len & 0x3)) {
+		rc = -EINVAL;
+		goto err_out_resp;
+	}
+
+	/* create header */
+	/* dw0 */
+	hdr->dw0 = cpu_to_le32((port->id << CMD_HDR_PORT_OFF) |
+			       (1 << CMD_HDR_PRIORITY_OFF) | /* high pri */
+			       (2 << CMD_HDR_CMD_OFF)); /* smp */
+
+	/* map itct entry */
+	hdr->dw1 = cpu_to_le32((sas_dev->device_id << CMD_HDR_DEV_ID_OFF) |
+			       (1 << CMD_HDR_FRAME_TYPE_OFF) |
+			       (DIR_NO_DATA << CMD_HDR_DIR_OFF));
+
+	/* dw2 */
+	hdr->dw2 = cpu_to_le32((((req_len - 4) / 4) << CMD_HDR_CFL_OFF) |
+			       (HISI_SAS_MAX_SMP_RESP_SZ / 4 <<
+			       CMD_HDR_MRFL_OFF));
+
+	hdr->transfer_tags = cpu_to_le32(slot->idx << CMD_HDR_IPTT_OFF);
+
+	hdr->cmd_table_addr = cpu_to_le64(req_dma_addr);
+	hdr->sts_buffer_addr = cpu_to_le64(hisi_sas_status_buf_addr_dma(slot));
+
+	return 0;
+
+err_out_resp:
+	dma_unmap_sg(dev, &slot->task->smp_task.smp_resp, 1,
+		     DMA_FROM_DEVICE);
+err_out_req:
+	dma_unmap_sg(dev, &slot->task->smp_task.smp_req, 1,
+		     DMA_TO_DEVICE);
+	return rc;
+}
+
+static int get_ncq_tag_v3_hw(struct sas_task *task, u32 *tag)
+{
+	struct ata_queued_cmd *qc = task->uldd_task;
+
+	if (qc) {
+		if (qc->tf.command == ATA_CMD_FPDMA_WRITE ||
+			qc->tf.command == ATA_CMD_FPDMA_READ) {
+			*tag = qc->tag;
+			return 1;
+		}
+	}
+	return 0;
+}
+
+static int prep_ata_v3_hw(struct hisi_hba *hisi_hba,
+			  struct hisi_sas_slot *slot)
+{
+	struct sas_task *task = slot->task;
+	struct domain_device *device = task->dev;
+	struct domain_device *parent_dev = device->parent;
+	struct hisi_sas_device *sas_dev = device->lldd_dev;
+	struct hisi_sas_cmd_hdr *hdr = slot->cmd_hdr;
+	struct asd_sas_port *sas_port = device->port;
+	struct hisi_sas_port *port = to_hisi_sas_port(sas_port);
+	u8 *buf_cmd;
+	int has_data = 0, rc = 0, hdr_tag = 0;
+	u32 dw1 = 0, dw2 = 0;
+
+	hdr->dw0 = cpu_to_le32(port->id << CMD_HDR_PORT_OFF);
+	if (parent_dev && DEV_IS_EXPANDER(parent_dev->dev_type))
+		hdr->dw0 |= cpu_to_le32(3 << CMD_HDR_CMD_OFF);
+	else
+		hdr->dw0 |= cpu_to_le32(4 << CMD_HDR_CMD_OFF);
+
+	switch (task->data_dir) {
+	case DMA_TO_DEVICE:
+		has_data = 1;
+		dw1 |= DIR_TO_DEVICE << CMD_HDR_DIR_OFF;
+		break;
+	case DMA_FROM_DEVICE:
+		has_data = 1;
+		dw1 |= DIR_TO_INI << CMD_HDR_DIR_OFF;
+		break;
+	default:
+		dw1 &= ~CMD_HDR_DIR_MSK;
+	}
+
+	if ((task->ata_task.fis.command == ATA_CMD_DEV_RESET) &&
+			(task->ata_task.fis.control & ATA_SRST))
+		dw1 |= 1 << CMD_HDR_RESET_OFF;
+
+	dw1 |= (hisi_sas_get_ata_protocol(
+		task->ata_task.fis.command, task->data_dir))
+		<< CMD_HDR_FRAME_TYPE_OFF;
+	dw1 |= sas_dev->device_id << CMD_HDR_DEV_ID_OFF;
+
+	if (CMD_IS_UNCONSTRAINT(task->ata_task.fis.command))
+		dw1 |= 1 << CMD_HDR_UNCON_CMD_OFF;
+
+	hdr->dw1 = cpu_to_le32(dw1);
+
+	/* dw2 */
+	if (task->ata_task.use_ncq && get_ncq_tag_v3_hw(task, &hdr_tag)) {
+		task->ata_task.fis.sector_count |= (u8) (hdr_tag << 3);
+		dw2 |= hdr_tag << CMD_HDR_NCQ_TAG_OFF;
+	}
+
+	dw2 |= (HISI_SAS_MAX_STP_RESP_SZ / 4) << CMD_HDR_CFL_OFF |
+			2 << CMD_HDR_SG_MOD_OFF;
+	hdr->dw2 = cpu_to_le32(dw2);
+
+	/* dw3 */
+	hdr->transfer_tags = cpu_to_le32(slot->idx);
+
+	if (has_data) {
+		rc = prep_prd_sge_v3_hw(hisi_hba, slot, hdr, task->scatter,
+					slot->n_elem);
+		if (rc)
+			return rc;
+	}
+
+	hdr->data_transfer_len = cpu_to_le32(task->total_xfer_len);
+	hdr->cmd_table_addr = cpu_to_le64(hisi_sas_cmd_hdr_addr_dma(slot));
+	hdr->sts_buffer_addr = cpu_to_le64(hisi_sas_status_buf_addr_dma(slot));
+
+	buf_cmd = hisi_sas_cmd_hdr_addr_mem(slot);
+
+	if (likely(!task->ata_task.device_control_reg_update))
+		task->ata_task.fis.flags |= 0x80; /* C=1: update ATA cmd reg */
+	/* fill in command FIS */
+	memcpy(buf_cmd, &task->ata_task.fis, sizeof(struct host_to_dev_fis));
+
+	return 0;
+}
+
+static int prep_abort_v3_hw(struct hisi_hba *hisi_hba,
+		struct hisi_sas_slot *slot,
+		int device_id, int abort_flag, int tag_to_abort)
+{
+	struct sas_task *task = slot->task;
+	struct domain_device *dev = task->dev;
+	struct hisi_sas_cmd_hdr *hdr = slot->cmd_hdr;
+	struct hisi_sas_port *port = slot->port;
+
+	/* dw0 */
+	hdr->dw0 = cpu_to_le32((5 << CMD_HDR_CMD_OFF) | /*abort*/
+			       (port->id << CMD_HDR_PORT_OFF) |
+				   ((dev_is_sata(dev) ? 1:0)
+					<< CMD_HDR_ABORT_DEVICE_TYPE_OFF) |
+					(abort_flag
+					 << CMD_HDR_ABORT_FLAG_OFF));
+
+	/* dw1 */
+	hdr->dw1 = cpu_to_le32(device_id
+			<< CMD_HDR_DEV_ID_OFF);
+
+	/* dw7 */
+	hdr->dw7 = cpu_to_le32(tag_to_abort << CMD_HDR_ABORT_IPTT_OFF);
+	hdr->transfer_tags = cpu_to_le32(slot->idx);
+
+	return 0;
+}
+
+static int phy_up_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
+{
+	int i, res = 0;
+	u32 context, port_id, link_rate, hard_phy_linkrate;
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+	struct asd_sas_phy *sas_phy = &phy->sas_phy;
+	struct device *dev = hisi_hba->dev;
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHYCTRL_PHY_ENA_MSK, 1);
+
+	port_id = hisi_sas_read32(hisi_hba, PHY_PORT_NUM_MA);
+	port_id = (port_id >> (4 * phy_no)) & 0xf;
+	link_rate = hisi_sas_read32(hisi_hba, PHY_CONN_RATE);
+	link_rate = (link_rate >> (phy_no * 4)) & 0xf;
+
+	if (port_id == 0xf) {
+		dev_err(dev, "phyup: phy%d invalid portid\n", phy_no);
+		res = IRQ_NONE;
+		goto end;
+	}
+	sas_phy->linkrate = link_rate;
+	hard_phy_linkrate = hisi_sas_phy_read32(hisi_hba, phy_no,
+						HARD_PHY_LINKRATE);
+	phy->maximum_linkrate = hard_phy_linkrate & 0xf;
+	phy->minimum_linkrate = (hard_phy_linkrate >> 4) & 0xf;
+	phy->phy_type &= ~(PORT_TYPE_SAS | PORT_TYPE_SATA);
+
+	/* Check for SATA dev */
+	context = hisi_sas_read32(hisi_hba, PHY_CONTEXT);
+	if (context & (1 << phy_no)) {
+		struct hisi_sas_initial_fis *initial_fis;
+		struct dev_to_host_fis *fis;
+		u8 attached_sas_addr[SAS_ADDR_SIZE] = {0};
+
+		dev_info(dev, "phyup: phy%d link_rate=%d\n", phy_no, link_rate);
+		initial_fis = &hisi_hba->initial_fis[phy_no];
+		fis = &initial_fis->fis;
+		sas_phy->oob_mode = SATA_OOB_MODE;
+		attached_sas_addr[0] = 0x50;
+		attached_sas_addr[7] = phy_no;
+		memcpy(sas_phy->attached_sas_addr,
+		       attached_sas_addr,
+		       SAS_ADDR_SIZE);
+		memcpy(sas_phy->frame_rcvd, fis,
+		       sizeof(struct dev_to_host_fis));
+		phy->phy_type |= PORT_TYPE_SATA;
+		phy->identify.device_type = SAS_SATA_DEV;
+		phy->frame_rcvd_size = sizeof(struct dev_to_host_fis);
+		phy->identify.target_port_protocols = SAS_PROTOCOL_SATA;
+	} else {
+		u32 *frame_rcvd = (u32 *)sas_phy->frame_rcvd;
+		struct sas_identify_frame *id =
+			(struct sas_identify_frame *)frame_rcvd;
+
+		dev_info(dev, "phyup: phy%d link_rate=%d\n", phy_no, link_rate);
+		for (i = 0; i < 6; i++) {
+			u32 idaf = hisi_sas_phy_read32(hisi_hba, phy_no,
+					       RX_IDAF_DWORD0 + (i * 4));
+			frame_rcvd[i] = __swab32(idaf);
+		}
+		sas_phy->oob_mode = SAS_OOB_MODE;
+		memcpy(sas_phy->attached_sas_addr,
+		       &id->sas_addr,
+		       SAS_ADDR_SIZE);
+		phy->phy_type |= PORT_TYPE_SAS;
+		phy->identify.device_type = id->dev_type;
+		phy->frame_rcvd_size = sizeof(struct sas_identify_frame);
+		if (phy->identify.device_type == SAS_END_DEVICE)
+			phy->identify.target_port_protocols =
+				SAS_PROTOCOL_SSP;
+		else if (phy->identify.device_type != SAS_PHY_UNUSED)
+			phy->identify.target_port_protocols =
+				SAS_PROTOCOL_SMP;
+	}
+
+	phy->port_id = port_id;
+	phy->phy_attached = 1;
+	queue_work(hisi_hba->wq, &phy->phyup_ws);
+
+end:
+	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
+			     CHL_INT0_SL_PHY_ENABLE_MSK);
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHYCTRL_PHY_ENA_MSK, 0);
+
+	return res;
+}
+
+static int phy_down_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
+{
+	int res = 0;
+	u32 phy_state, sl_ctrl, txid_auto;
+	struct device *dev = hisi_hba->dev;
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHYCTRL_NOT_RDY_MSK, 1);
+
+	phy_state = hisi_sas_read32(hisi_hba, PHY_STATE);
+	dev_info(dev, "phydown: phy%d phy_state=0x%x\n", phy_no, phy_state);
+	hisi_sas_phy_down(hisi_hba, phy_no, (phy_state & 1 << phy_no) ? 1 : 0);
+
+	sl_ctrl = hisi_sas_phy_read32(hisi_hba, phy_no, SL_CONTROL);
+	hisi_sas_phy_write32(hisi_hba, phy_no, SL_CONTROL,
+						sl_ctrl&(~SL_CTA_MSK));
+
+	txid_auto = hisi_sas_phy_read32(hisi_hba, phy_no, TXID_AUTO);
+	hisi_sas_phy_write32(hisi_hba, phy_no, TXID_AUTO,
+						txid_auto | CT3_MSK);
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0, CHL_INT0_NOT_RDY_MSK);
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHYCTRL_NOT_RDY_MSK, 0);
+
+	return res;
+}
+
+static void phy_bcast_v3_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;
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
+	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);
+}
+
+static irqreturn_t int_phy_up_down_bcast_v3_hw(int irq_no, void *p)
+{
+	struct hisi_hba *hisi_hba = p;
+	u32 irq_msk;
+	int phy_no = 0;
+	irqreturn_t res = IRQ_NONE;
+
+	irq_msk = hisi_sas_read32(hisi_hba, CHNL_INT_STATUS)
+				& 0x11111111;
+	while (irq_msk) {
+		if (irq_msk  & 1) {
+			u32 irq_value = hisi_sas_phy_read32(hisi_hba, phy_no,
+							    CHL_INT0);
+			u32 phy_state = hisi_sas_read32(hisi_hba, PHY_STATE);
+			int rdy = phy_state & (1 << phy_no);
+
+			if (rdy) {
+				if (irq_value & CHL_INT0_SL_PHY_ENABLE_MSK)
+					/* phy up */
+					if (phy_up_v3_hw(phy_no, hisi_hba)
+							== IRQ_HANDLED)
+						res = IRQ_HANDLED;
+				if (irq_value & CHL_INT0_SL_RX_BCST_ACK_MSK)
+					/* phy bcast */
+					phy_bcast_v3_hw(phy_no, hisi_hba);
+			} else {
+				if (irq_value & CHL_INT0_NOT_RDY_MSK)
+					/* phy down */
+					if (phy_down_v3_hw(phy_no, hisi_hba)
+							== IRQ_HANDLED)
+						res = IRQ_HANDLED;
+			}
+		}
+		irq_msk >>= 4;
+		phy_no++;
+	}
+
+	return res;
+}
+
+static irqreturn_t int_chnl_int_v3_hw(int irq_no, void *p)
+{
+	struct hisi_hba *hisi_hba = p;
+	struct device *dev = hisi_hba->dev;
+	u32 ent_msk, ent_tmp, irq_msk;
+	int phy_no = 0;
+
+	ent_msk = hisi_sas_read32(hisi_hba, ENT_INT_SRC_MSK3);
+	ent_tmp = ent_msk;
+	ent_msk |= ENT_INT_SRC_MSK3_ENT95_MSK_MSK;
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK3, ent_msk);
+
+	irq_msk = hisi_sas_read32(hisi_hba, CHNL_INT_STATUS)
+				& 0xeeeeeeee;
+
+	while (irq_msk) {
+		u32 irq_value0 = hisi_sas_phy_read32(hisi_hba, phy_no,
+						     CHL_INT0);
+		u32 irq_value1 = hisi_sas_phy_read32(hisi_hba, phy_no,
+						     CHL_INT1);
+		u32 irq_value2 = hisi_sas_phy_read32(hisi_hba, phy_no,
+						     CHL_INT2);
+
+		if ((irq_msk & (4 << (phy_no * 4))) &&
+						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);
+
+			hisi_sas_phy_write32(hisi_hba, phy_no,
+					     CHL_INT1, irq_value1);
+		}
+
+		if (irq_msk & (8 << (phy_no * 4)) && irq_value2)
+			hisi_sas_phy_write32(hisi_hba, phy_no,
+					     CHL_INT2, irq_value2);
+
+
+		if (irq_msk & (2 << (phy_no * 4)) && irq_value0) {
+			hisi_sas_phy_write32(hisi_hba, phy_no,
+					CHL_INT0, irq_value0
+					& (~CHL_INT0_HOTPLUG_TOUT_MSK)
+					& (~CHL_INT0_SL_PHY_ENABLE_MSK)
+					& (~CHL_INT0_NOT_RDY_MSK));
+		}
+		irq_msk &= ~(0xe << (phy_no * 4));
+		phy_no++;
+	}
+
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK3, ent_tmp);
+
+	return IRQ_HANDLED;
+}
+
+static void
+slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task,
+	       struct hisi_sas_slot *slot)
+{
+	struct task_status_struct *ts = &task->task_status;
+	struct hisi_sas_complete_v3_hdr *complete_queue =
+			hisi_hba->complete_hdr[slot->cmplt_queue];
+	struct hisi_sas_complete_v3_hdr *complete_hdr =
+			&complete_queue[slot->cmplt_queue_slot];
+	struct hisi_sas_err_record_v3 *record =
+			hisi_sas_status_buf_addr_mem(slot);
+	u32 dma_rx_err_type = record->dma_rx_err_type;
+	u32 trans_tx_fail_type = record->trans_tx_fail_type;
+
+	switch (task->task_proto) {
+	case SAS_PROTOCOL_SSP:
+		if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) {
+			ts->residual = trans_tx_fail_type;
+			ts->stat = SAS_DATA_UNDERRUN;
+		} else if (complete_hdr->dw3 & CMPLT_HDR_IO_IN_TARGET_MSK) {
+			ts->stat = SAS_QUEUE_FULL;
+			slot->abort = 1;
+		} else {
+			ts->stat = SAS_OPEN_REJECT;
+			ts->open_rej_reason = SAS_OREJ_RSVD_RETRY;
+		}
+		break;
+	case SAS_PROTOCOL_SATA:
+	case SAS_PROTOCOL_STP:
+	case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP:
+		if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) {
+			ts->residual = trans_tx_fail_type;
+			ts->stat = SAS_DATA_UNDERRUN;
+		} else if (complete_hdr->dw3 & CMPLT_HDR_IO_IN_TARGET_MSK) {
+			ts->stat = SAS_PHY_DOWN;
+			slot->abort = 1;
+		} else {
+			ts->stat = SAS_OPEN_REJECT;
+			ts->open_rej_reason = SAS_OREJ_RSVD_RETRY;
+		}
+		hisi_sas_sata_done(task, slot);
+		break;
+	case SAS_PROTOCOL_SMP:
+		ts->stat = SAM_STAT_CHECK_CONDITION;
+		break;
+	default:
+		break;
+	}
+}
+
+static int
+slot_complete_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot)
+{
+	struct sas_task *task = slot->task;
+	struct hisi_sas_device *sas_dev;
+	struct device *dev = hisi_hba->dev;
+	struct task_status_struct *ts;
+	struct domain_device *device;
+	enum exec_status sts;
+	struct hisi_sas_complete_v3_hdr *complete_queue =
+			hisi_hba->complete_hdr[slot->cmplt_queue];
+	struct hisi_sas_complete_v3_hdr *complete_hdr =
+			&complete_queue[slot->cmplt_queue_slot];
+	int aborted;
+	unsigned long flags;
+
+	if (unlikely(!task || !task->lldd_task || !task->dev))
+		return -EINVAL;
+
+	ts = &task->task_status;
+	device = task->dev;
+	sas_dev = device->lldd_dev;
+
+	spin_lock_irqsave(&task->task_state_lock, flags);
+	aborted = task->task_state_flags & SAS_TASK_STATE_ABORTED;
+	task->task_state_flags &=
+		~(SAS_TASK_STATE_PENDING | SAS_TASK_AT_INITIATOR);
+	spin_unlock_irqrestore(&task->task_state_lock, flags);
+
+	memset(ts, 0, sizeof(*ts));
+	ts->resp = SAS_TASK_COMPLETE;
+	if (unlikely(aborted)) {
+		ts->stat = SAS_ABORTED_TASK;
+		hisi_sas_slot_task_free(hisi_hba, task, slot);
+		return -1;
+	}
+
+	if (unlikely(!sas_dev)) {
+		dev_dbg(dev, "slot complete: port has not device\n");
+		ts->stat = SAS_PHY_DOWN;
+		goto out;
+	}
+
+	/*
+	 * Use SAS+TMF status codes
+	 */
+	switch ((complete_hdr->dw0 & CMPLT_HDR_ABORT_STAT_MSK)
+			>> CMPLT_HDR_ABORT_STAT_OFF) {
+	case STAT_IO_ABORTED:
+		/* this IO has been aborted by abort command */
+		ts->stat = SAS_ABORTED_TASK;
+		goto out;
+	case STAT_IO_COMPLETE:
+		/* internal abort command complete */
+		ts->stat = TMF_RESP_FUNC_SUCC;
+		goto out;
+	case STAT_IO_NO_DEVICE:
+		ts->stat = TMF_RESP_FUNC_COMPLETE;
+		goto out;
+	case STAT_IO_NOT_VALID:
+		/*
+		 * abort single IO, the controller can't find the IO
+		 */
+		ts->stat = TMF_RESP_FUNC_FAILED;
+		goto out;
+	default:
+		break;
+	}
+
+	/* check for erroneous completion */
+	if ((complete_hdr->dw0 & CMPLT_HDR_CMPLT_MSK) == 0x3) {
+		slot_err_v3_hw(hisi_hba, task, slot);
+		if (unlikely(slot->abort))
+			return ts->stat;
+		goto out;
+	}
+
+	switch (task->task_proto) {
+	case SAS_PROTOCOL_SSP: {
+		struct ssp_response_iu *iu =
+			hisi_sas_status_buf_addr_mem(slot) +
+			sizeof(struct hisi_sas_err_record);
+
+		sas_ssp_task_response(dev, task, iu);
+		break;
+	}
+	case SAS_PROTOCOL_SMP: {
+		struct scatterlist *sg_resp = &task->smp_task.smp_resp;
+		void *to;
+
+		ts->stat = SAM_STAT_GOOD;
+		to = kmap_atomic(sg_page(sg_resp));
+
+		dma_unmap_sg(dev, &task->smp_task.smp_resp, 1,
+			     DMA_FROM_DEVICE);
+		dma_unmap_sg(dev, &task->smp_task.smp_req, 1,
+			     DMA_TO_DEVICE);
+		memcpy(to + sg_resp->offset,
+			hisi_sas_status_buf_addr_mem(slot) +
+		       sizeof(struct hisi_sas_err_record),
+		       sg_dma_len(sg_resp));
+		kunmap_atomic(to);
+		break;
+	}
+	case SAS_PROTOCOL_SATA:
+	case SAS_PROTOCOL_STP:
+	case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP:
+		ts->stat = SAM_STAT_GOOD;
+		hisi_sas_sata_done(task, slot);
+		break;
+	default:
+		ts->stat = SAM_STAT_CHECK_CONDITION;
+		break;
+	}
+
+	if (!slot->port->port_attached) {
+		dev_err(dev, "slot complete: port %d has removed\n",
+			slot->port->sas_port.id);
+		ts->stat = SAS_PHY_DOWN;
+	}
+
+out:
+	spin_lock_irqsave(&task->task_state_lock, flags);
+	task->task_state_flags |= SAS_TASK_STATE_DONE;
+	spin_unlock_irqrestore(&task->task_state_lock, flags);
+	spin_lock_irqsave(&hisi_hba->lock, flags);
+	hisi_sas_slot_task_free(hisi_hba, task, slot);
+	spin_unlock_irqrestore(&hisi_hba->lock, flags);
+	sts = ts->stat;
+
+	if (task->task_done)
+		task->task_done(task);
+
+	return sts;
+}
+
+static void cq_tasklet_v3_hw(unsigned long val)
+{
+	struct hisi_sas_cq *cq = (struct hisi_sas_cq *)val;
+	struct hisi_hba *hisi_hba = cq->hisi_hba;
+	struct hisi_sas_slot *slot;
+	struct hisi_sas_itct *itct;
+	struct hisi_sas_complete_v3_hdr *complete_queue;
+	u32 rd_point = cq->rd_point, wr_point, dev_id;
+	int queue = cq->id;
+	struct hisi_sas_dq *dq = &hisi_hba->dq[queue];
+
+	complete_queue = hisi_hba->complete_hdr[queue];
+
+	spin_lock(&dq->lock);
+	wr_point = hisi_sas_read32(hisi_hba, COMPL_Q_0_WR_PTR +
+				   (0x14 * queue));
+
+	while (rd_point != wr_point) {
+		struct hisi_sas_complete_v3_hdr *complete_hdr;
+		int iptt;
+
+		complete_hdr = &complete_queue[rd_point];
+
+		/* Check for NCQ completion */
+		if (complete_hdr->act) {
+			u32 act_tmp = complete_hdr->act;
+			int ncq_tag_count = ffs(act_tmp);
+
+			dev_id = (complete_hdr->dw1 & CMPLT_HDR_DEV_ID_MSK) >>
+				 CMPLT_HDR_DEV_ID_OFF;
+			itct = &hisi_hba->itct[dev_id];
+
+			/* The NCQ tags are held in the itct header */
+			while (ncq_tag_count) {
+				__le64 *ncq_tag = &itct->qw4_15[0];
+
+				ncq_tag_count -= 1;
+				iptt = (ncq_tag[ncq_tag_count / 5]
+					>> (ncq_tag_count % 5) * 12) & 0xfff;
+
+				slot = &hisi_hba->slot_info[iptt];
+				slot->cmplt_queue_slot = rd_point;
+				slot->cmplt_queue = queue;
+				slot_complete_v3_hw(hisi_hba, slot);
+
+				act_tmp &= ~(1 << ncq_tag_count);
+				ncq_tag_count = ffs(act_tmp);
+			}
+		} else {
+			iptt = (complete_hdr->dw1) & CMPLT_HDR_IPTT_MSK;
+			slot = &hisi_hba->slot_info[iptt];
+			slot->cmplt_queue_slot = rd_point;
+			slot->cmplt_queue = queue;
+			slot_complete_v3_hw(hisi_hba, slot);
+		}
+
+		if (++rd_point >= HISI_SAS_QUEUE_SLOTS)
+			rd_point = 0;
+	}
+
+	/* update rd_point */
+	cq->rd_point = rd_point;
+	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
+	spin_unlock(&dq->lock);
+}
+
+static irqreturn_t cq_interrupt_v3_hw(int irq_no, void *p)
+{
+	struct hisi_sas_cq *cq = p;
+	struct hisi_hba *hisi_hba = cq->hisi_hba;
+	int queue = cq->id;
+
+	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 1 << queue);
+
+	tasklet_schedule(&cq->tasklet);
+
+	return IRQ_HANDLED;
+}
+
+static int interrupt_init_v3_hw(struct hisi_hba *hisi_hba)
+{
+	struct device *dev = hisi_hba->dev;
+	struct pci_dev *pdev = hisi_hba->pci_dev;
+	int vectors, rc;
+	int i, k;
+	int max_msi = HISI_SAS_MSI_COUNT_V3_HW;
+
+	vectors = pci_alloc_irq_vectors(hisi_hba->pci_dev, 1,
+					max_msi, PCI_IRQ_MSI);
+	if (vectors < max_msi) {
+		dev_err(dev, "could not allocate all msi (%d)\n", vectors);
+		return -ENOENT;
+	}
+
+	rc = devm_request_irq(dev, pci_irq_vector(pdev, 1),
+			      int_phy_up_down_bcast_v3_hw, 0,
+			      DRV_NAME " phy", hisi_hba);
+	if (rc) {
+		dev_err(dev, "could not request phy interrupt, rc=%d\n", rc);
+		rc = -ENOENT;
+		goto free_irq_vectors;
+	}
+
+	rc = devm_request_irq(dev, pci_irq_vector(pdev, 2),
+			      int_chnl_int_v3_hw, 0,
+			      DRV_NAME " channel", hisi_hba);
+	if (rc) {
+		dev_err(dev, "could not request chnl interrupt, rc=%d\n", rc);
+		rc = -ENOENT;
+		goto free_phy_irq;
+	}
+
+	/* Init tasklets for cq only */
+	for (i = 0; i < hisi_hba->queue_count; i++) {
+		struct hisi_sas_cq *cq = &hisi_hba->cq[i];
+		struct tasklet_struct *t = &cq->tasklet;
+
+		rc = devm_request_irq(dev, pci_irq_vector(pdev, i+16),
+					  cq_interrupt_v3_hw, 0,
+					  DRV_NAME " cq", cq);
+		if (rc) {
+			dev_err(dev,
+				"could not request cq%d interrupt, rc=%d\n",
+				i, rc);
+			rc = -ENOENT;
+			goto free_cq_irqs;
+		}
+
+		tasklet_init(t, cq_tasklet_v3_hw, (unsigned long)cq);
+	}
+
+	return 0;
+
+free_cq_irqs:
+	for (k = 0; k < i; k++) {
+		struct hisi_sas_cq *cq = &hisi_hba->cq[k];
+
+		free_irq(pci_irq_vector(pdev, k+16), cq);
+	}
+	free_irq(pci_irq_vector(pdev, 2), hisi_hba);
+free_phy_irq:
+	free_irq(pci_irq_vector(pdev, 1), hisi_hba);
+free_irq_vectors:
+	pci_free_irq_vectors(pdev);
+	return rc;
+}
+
+static int hisi_sas_v3_init(struct hisi_hba *hisi_hba)
+{
+	int rc;
+
+	rc = hw_init_v3_hw(hisi_hba);
+	if (rc)
+		return rc;
+
+	rc = interrupt_init_v3_hw(hisi_hba);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static const struct hisi_sas_hw hisi_sas_v3_hw = {
+	.hw_init = hisi_sas_v3_init,
+	.setup_itct = setup_itct_v3_hw,
+	.max_command_entries = HISI_SAS_COMMAND_ENTRIES_V3_HW,
+	.get_wideport_bitmap = get_wideport_bitmap_v3_hw,
+	.complete_hdr_size = sizeof(struct hisi_sas_complete_v3_hdr),
+	.free_device = free_device_v3_hw,
+	.sl_notify = sl_notify_v3_hw,
+	.prep_ssp = prep_ssp_v3_hw,
+	.prep_smp = prep_smp_v3_hw,
+	.prep_stp = prep_ata_v3_hw,
+	.prep_abort = prep_abort_v3_hw,
+	.get_free_slot = get_free_slot_v3_hw,
+	.start_delivery = start_delivery_v3_hw,
+	.slot_complete = slot_complete_v3_hw,
+	.phys_init = phys_init_v3_hw,
+	.phy_enable = enable_phy_v3_hw,
+	.phy_disable = disable_phy_v3_hw,
+	.phy_hard_reset = phy_hard_reset_v3_hw,
+	.phy_get_max_linkrate = phy_get_max_linkrate_v3_hw,
+	.dereg_device = dereg_device_v3_hw,
+};
+
+static struct Scsi_Host *
+hisi_sas_shost_alloc_pci(struct pci_dev *pdev)
+{
+	struct Scsi_Host *shost;
+	struct hisi_hba *hisi_hba;
+	struct device *dev = &pdev->dev;
+
+	shost = scsi_host_alloc(hisi_sas_sht, sizeof(*hisi_hba));
+	if (!shost)
+		goto err_out;
+	hisi_hba = shost_priv(shost);
+
+	hisi_hba->hw = &hisi_sas_v3_hw;
+	hisi_hba->pci_dev = pdev;
+	hisi_hba->dev = dev;
+	hisi_hba->shost = shost;
+	SHOST_TO_SAS_HA(shost) = &hisi_hba->sha;
+
+	init_timer(&hisi_hba->timer);
+
+	if (hisi_sas_get_fw_info(hisi_hba) < 0)
+		goto err_out;
+
+	if (hisi_sas_alloc(hisi_hba, shost)) {
+		hisi_sas_free(hisi_hba);
+		goto err_out;
+	}
+
+	return shost;
+err_out:
+	dev_err(dev, "shost alloc failed\n");
+	return NULL;
+}
+
+static int
+hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct Scsi_Host *shost;
+	struct hisi_hba *hisi_hba;
+	struct device *dev = &pdev->dev;
+	struct asd_sas_phy **arr_phy;
+	struct asd_sas_port **arr_port;
+	struct sas_ha_struct *sha;
+	int rc, phy_nr, port_nr, i;
+
+	rc = pci_enable_device(pdev);
+	if (rc)
+		goto err_out;
+
+	pci_set_master(pdev);
+
+	rc = pci_request_regions(pdev, DRV_NAME);
+	if (rc)
+		goto err_out_disable_device;
+
+	if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) ||
+	    (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0)) {
+		if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) ||
+		   (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)) != 0)) {
+			dev_err(dev, "No usable DMA addressing method\n");
+			rc = -EIO;
+			goto err_out_regions;
+		}
+	}
+
+	shost = hisi_sas_shost_alloc_pci(pdev);
+	if (!shost) {
+		rc = -ENOMEM;
+		goto err_out_regions;
+	}
+
+	sha = SHOST_TO_SAS_HA(shost);
+	hisi_hba = shost_priv(shost);
+	dev_set_drvdata(dev, sha);
+
+	hisi_hba->regs = pcim_iomap(pdev, 5, 0);
+	if (!hisi_hba->regs) {
+		dev_err(dev, "cannot map register.\n");
+		rc = -ENOMEM;
+		goto err_out_ha;
+	}
+
+	phy_nr = port_nr = hisi_hba->n_phy;
+
+	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) {
+		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;
+	shost->max_id = HISI_SAS_MAX_DEVICES;
+	shost->max_lun = ~0;
+	shost->max_channel = 1;
+	shost->max_cmd_len = 16;
+	shost->sg_tablesize = min_t(u16, SG_ALL, HISI_SAS_SGE_PAGE_CNT);
+	shost->can_queue = hisi_hba->hw->max_command_entries;
+	shost->cmd_per_lun = hisi_hba->hw->max_command_entries;
+
+	sha->sas_ha_name = DRV_NAME;
+	sha->dev = dev;
+	sha->lldd_module = THIS_MODULE;
+	sha->sas_addr = &hisi_hba->sas_addr[0];
+	sha->num_phys = hisi_hba->n_phy;
+	sha->core.shost = hisi_hba->shost;
+
+	for (i = 0; i < hisi_hba->n_phy; i++) {
+		sha->sas_phy[i] = &hisi_hba->phy[i].sas_phy;
+		sha->sas_port[i] = &hisi_hba->port[i].sas_port;
+	}
+
+	hisi_sas_init_add(hisi_hba);
+
+	rc = scsi_add_host(shost, dev);
+	if (rc)
+		goto err_out_ha;
+
+	rc = sas_register_ha(sha);
+	if (rc)
+		goto err_out_register_ha;
+
+	rc = hisi_hba->hw->hw_init(hisi_hba);
+	if (rc)
+		goto err_out_register_ha;
+
+	scsi_scan_host(shost);
+
+	return 0;
+
+err_out_register_ha:
+	scsi_remove_host(shost);
+err_out_ha:
+	kfree(shost);
+err_out_regions:
+	pci_release_regions(pdev);
+err_out_disable_device:
+	pci_disable_device(pdev);
+err_out:
+	return rc;
+}
+
+static void
+hisi_sas_v3_destroy_irqs(struct pci_dev *pdev, struct hisi_hba *hisi_hba)
+{
+	int i;
+
+	free_irq(pci_irq_vector(pdev, 1), hisi_hba);
+	free_irq(pci_irq_vector(pdev, 2), hisi_hba);
+	for (i = 0; i < hisi_hba->queue_count; i++) {
+		struct hisi_sas_cq *cq = &hisi_hba->cq[i];
+
+		free_irq(pci_irq_vector(pdev, i+16), cq);
+	}
+	pci_free_irq_vectors(pdev);
+}
+
+static void hisi_sas_v3_remove(struct pci_dev *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct sas_ha_struct *sha = dev_get_drvdata(dev);
+	struct hisi_hba *hisi_hba = sha->lldd_ha;
+
+	sas_unregister_ha(sha);
+	sas_remove_host(sha->core.shost);
+
+	hisi_sas_free(hisi_hba);
+	hisi_sas_v3_destroy_irqs(pdev, hisi_hba);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+}
+
+enum {
+	/* instances of the controller */
+	hip08,
+};
+
+static const struct pci_device_id sas_v3_pci_table[] = {
+	{ PCI_VDEVICE(HUAWEI, 0xa230), hip08 },
+	{}
+};
+
+static struct pci_driver sas_v3_pci_driver = {
+	.name		= DRV_NAME,
+	.id_table	= sas_v3_pci_table,
+	.probe		= hisi_sas_v3_probe,
+	.remove		= hisi_sas_v3_remove,
+};
+
+module_pci_driver(sas_v3_pci_driver);
+
+MODULE_VERSION(DRV_VERSION);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("John Garry <john.garry@huawei.com>");
+MODULE_DESCRIPTION("HISILICON SAS controller v3 hw driver based on pci device");
+MODULE_ALIAS("platform:" DRV_NAME);

drivers/scsi/hpsa.c

@@ -60,7 +60,7 @@
  * HPSA_DRIVER_VERSION must be 3 byte values (0-255) separated by '.'
  * with an optional trailing '-' followed by a byte value (0-255).
  */
-#define HPSA_DRIVER_VERSION "3.4.18-0"
+#define HPSA_DRIVER_VERSION "3.4.20-0"
 #define DRIVER_NAME "HP HPSA Driver (v " HPSA_DRIVER_VERSION ")"
 #define HPSA "hpsa"
 
@@ -258,7 +258,6 @@ static int hpsa_scan_finished(struct Scsi_Host *sh,
 static int hpsa_change_queue_depth(struct scsi_device *sdev, int qdepth);
 
 static int hpsa_eh_device_reset_handler(struct scsi_cmnd *scsicmd);
-static int hpsa_eh_abort_handler(struct scsi_cmnd *scsicmd);
 static int hpsa_slave_alloc(struct scsi_device *sdev);
 static int hpsa_slave_configure(struct scsi_device *sdev);
 static void hpsa_slave_destroy(struct scsi_device *sdev);
@@ -326,7 +325,7 @@ static inline bool hpsa_is_cmd_idle(struct CommandList *c)
 
 static inline bool hpsa_is_pending_event(struct CommandList *c)
 {
-	return c->abort_pending || c->reset_pending;
+	return c->reset_pending;
 }
 
 /* extract sense key, asc, and ascq from sense data.  -1 means invalid. */
@@ -581,12 +580,6 @@ static u32 soft_unresettable_controller[] = {
 	0x409D0E11, /* Smart Array 6400 EM */
 };
 
-static u32 needs_abort_tags_swizzled[] = {
-	0x323D103C, /* Smart Array P700m */
-	0x324a103C, /* Smart Array P712m */
-	0x324b103C, /* SmartArray P711m */
-};
-
 static int board_id_in_array(u32 a[], int nelems, u32 board_id)
 {
 	int i;
@@ -615,12 +608,6 @@ static int ctlr_is_resettable(u32 board_id)
 		ctlr_is_soft_resettable(board_id);
 }
 
-static int ctlr_needs_abort_tags_swizzled(u32 board_id)
-{
-	return board_id_in_array(needs_abort_tags_swizzled,
-			ARRAY_SIZE(needs_abort_tags_swizzled), board_id);
-}
-
 static ssize_t host_show_resettable(struct device *dev,
 	struct device_attribute *attr, char *buf)
 {
@@ -928,8 +915,8 @@ static struct device_attribute *hpsa_shost_attrs[] = {
 	NULL,
 };
 
-#define HPSA_NRESERVED_CMDS	(HPSA_CMDS_RESERVED_FOR_ABORTS + \
-		HPSA_CMDS_RESERVED_FOR_DRIVER + HPSA_MAX_CONCURRENT_PASSTHRUS)
+#define HPSA_NRESERVED_CMDS	(HPSA_CMDS_RESERVED_FOR_DRIVER +\
+				 HPSA_MAX_CONCURRENT_PASSTHRUS)
 
 static struct scsi_host_template hpsa_driver_template = {
 	.module			= THIS_MODULE,
@@ -941,7 +928,6 @@ static struct scsi_host_template hpsa_driver_template = {
 	.change_queue_depth	= hpsa_change_queue_depth,
 	.this_id		= -1,
 	.use_clustering		= ENABLE_CLUSTERING,
-	.eh_abort_handler	= hpsa_eh_abort_handler,
 	.eh_device_reset_handler = hpsa_eh_device_reset_handler,
 	.ioctl			= hpsa_ioctl,
 	.slave_alloc		= hpsa_slave_alloc,
@@ -1110,6 +1096,7 @@ static int is_firmware_flash_cmd(u8 *cdb)
  */
 #define HEARTBEAT_SAMPLE_INTERVAL_DURING_FLASH (240 * HZ)
 #define HEARTBEAT_SAMPLE_INTERVAL (30 * HZ)
+#define HPSA_EVENT_MONITOR_INTERVAL (15 * HZ)
 static void dial_down_lockup_detection_during_fw_flash(struct ctlr_info *h,
 		struct CommandList *c)
 {
@@ -1859,10 +1846,13 @@ static void adjust_hpsa_scsi_table(struct ctlr_info *h,
 	 * A reset can cause a device status to change
 	 * re-schedule the scan to see what happened.
 	 */
+	spin_lock_irqsave(&h->reset_lock, flags);
 	if (h->reset_in_progress) {
 		h->drv_req_rescan = 1;
+		spin_unlock_irqrestore(&h->reset_lock, flags);
 		return;
 	}
+	spin_unlock_irqrestore(&h->reset_lock, flags);
 
 	added = kzalloc(sizeof(*added) * HPSA_MAX_DEVICES, GFP_KERNEL);
 	removed = kzalloc(sizeof(*removed) * HPSA_MAX_DEVICES, GFP_KERNEL);
@@ -2066,10 +2056,13 @@ static int hpsa_slave_configure(struct scsi_device *sdev)
 	sd = sdev->hostdata;
 	sdev->no_uld_attach = !sd || !sd->expose_device;
 
-	if (sd)
-		queue_depth = sd->queue_depth != 0 ?
-			sd->queue_depth : sdev->host->can_queue;
-	else
+	if (sd) {
+		if (sd->external)
+			queue_depth = EXTERNAL_QD;
+		else
+			queue_depth = sd->queue_depth != 0 ?
+					sd->queue_depth : sdev->host->can_queue;
+	} else
 		queue_depth = sdev->host->can_queue;
 
 	scsi_change_queue_depth(sdev, queue_depth);
@@ -2354,26 +2347,12 @@ static void hpsa_cmd_resolve_events(struct ctlr_info *h,
 	bool do_wake = false;
 
 	/*
-	 * Prevent the following race in the abort handler:
-	 *
-	 * 1. LLD is requested to abort a SCSI command
-	 * 2. The SCSI command completes
-	 * 3. The struct CommandList associated with step 2 is made available
-	 * 4. New I/O request to LLD to another LUN re-uses struct CommandList
-	 * 5. Abort handler follows scsi_cmnd->host_scribble and
-	 *    finds struct CommandList and tries to aborts it
-	 * Now we have aborted the wrong command.
-	 *
-	 * Reset c->scsi_cmd here so that the abort or reset handler will know
+	 * Reset c->scsi_cmd here so that the reset handler will know
 	 * this command has completed.  Then, check to see if the handler is
 	 * waiting for this command, and, if so, wake it.
 	 */
 	c->scsi_cmd = SCSI_CMD_IDLE;
 	mb();	/* Declare command idle before checking for pending events. */
-	if (c->abort_pending) {
-		do_wake = true;
-		c->abort_pending = false;
-	}
 	if (c->reset_pending) {
 		unsigned long flags;
 		struct hpsa_scsi_dev_t *dev;
@@ -2416,20 +2395,6 @@ static void hpsa_retry_cmd(struct ctlr_info *h, struct CommandList *c)
 	queue_work_on(raw_smp_processor_id(), h->resubmit_wq, &c->work);
 }
 
-static void hpsa_set_scsi_cmd_aborted(struct scsi_cmnd *cmd)
-{
-	cmd->result = DID_ABORT << 16;
-}
-
-static void hpsa_cmd_abort_and_free(struct ctlr_info *h, struct CommandList *c,
-				    struct scsi_cmnd *cmd)
-{
-	hpsa_set_scsi_cmd_aborted(cmd);
-	dev_warn(&h->pdev->dev, "CDB %16phN was aborted with status 0x%x\n",
-			 c->Request.CDB, c->err_info->ScsiStatus);
-	hpsa_cmd_resolve_and_free(h, c);
-}
-
 static void process_ioaccel2_completion(struct ctlr_info *h,
 		struct CommandList *c, struct scsi_cmnd *cmd,
 		struct hpsa_scsi_dev_t *dev)
@@ -2554,12 +2519,9 @@ static void complete_scsi_command(struct CommandList *cp)
 		return hpsa_cmd_free_and_done(h, cp, cmd);
 	}
 
-	if ((unlikely(hpsa_is_pending_event(cp)))) {
+	if ((unlikely(hpsa_is_pending_event(cp))))
 		if (cp->reset_pending)
 			return hpsa_cmd_free_and_done(h, cp, cmd);
-		if (cp->abort_pending)
-			return hpsa_cmd_abort_and_free(h, cp, cmd);
-	}
 
 	if (cp->cmd_type == CMD_IOACCEL2)
 		return process_ioaccel2_completion(h, cp, cmd, dev);
@@ -2679,8 +2641,8 @@ static void complete_scsi_command(struct CommandList *cp)
 			cp->Request.CDB);
 		break;
 	case CMD_ABORTED:
-		/* Return now to avoid calling scsi_done(). */
-		return hpsa_cmd_abort_and_free(h, cp, cmd);
+		cmd->result = DID_ABORT << 16;
+		break;
 	case CMD_ABORT_FAILED:
 		cmd->result = DID_ERROR << 16;
 		dev_warn(&h->pdev->dev, "CDB %16phN : abort failed\n",
@@ -3090,7 +3052,7 @@ 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);
+		rc = wait_for_device_to_become_ready(h, scsi3addr, 0);
 
 	mutex_unlock(&h->reset_mutex);
 	return rc;
@@ -3165,7 +3127,7 @@ static void hpsa_debug_map_buff(struct ctlr_info *h, int rc,
 			le16_to_cpu(map_buff->layout_map_count));
 	dev_info(&h->pdev->dev, "flags = 0x%x\n",
 			le16_to_cpu(map_buff->flags));
-	dev_info(&h->pdev->dev, "encrypytion = %s\n",
+	dev_info(&h->pdev->dev, "encryption = %s\n",
 			le16_to_cpu(map_buff->flags) &
 			RAID_MAP_FLAG_ENCRYPT_ON ?  "ON" : "OFF");
 	dev_info(&h->pdev->dev, "dekindex = %u\n",
@@ -3353,6 +3315,11 @@ static void hpsa_get_enclosure_info(struct ctlr_info *h,
 
 	bmic_device_index = GET_BMIC_DRIVE_NUMBER(&rle->lunid[0]);
 
+	if (encl_dev->target == -1 || encl_dev->lun == -1) {
+		rc = IO_OK;
+		goto out;
+	}
+
 	if (bmic_device_index == 0xFF00 || MASKED_DEVICE(&rle->lunid[0])) {
 		rc = IO_OK;
 		goto out;
@@ -3781,53 +3748,6 @@ static unsigned char hpsa_volume_offline(struct ctlr_info *h,
 	return HPSA_LV_OK;
 }
 
-/*
- * Find out if a logical device supports aborts by simply trying one.
- * Smart Array may claim not to support aborts on logical drives, but
- * if a MSA2000 * is connected, the drives on that will be presented
- * by the Smart Array as logical drives, and aborts may be sent to
- * those devices successfully.  So the simplest way to find out is
- * to simply try an abort and see how the device responds.
- */
-static int hpsa_device_supports_aborts(struct ctlr_info *h,
-					unsigned char *scsi3addr)
-{
-	struct CommandList *c;
-	struct ErrorInfo *ei;
-	int rc = 0;
-
-	u64 tag = (u64) -1; /* bogus tag */
-
-	/* Assume that physical devices support aborts */
-	if (!is_logical_dev_addr_mode(scsi3addr))
-		return 1;
-
-	c = cmd_alloc(h);
-
-	(void) fill_cmd(c, HPSA_ABORT_MSG, h, &tag, 0, 0, scsi3addr, TYPE_MSG);
-	(void) hpsa_scsi_do_simple_cmd(h, c, DEFAULT_REPLY_QUEUE,
-					DEFAULT_TIMEOUT);
-	/* no unmap needed here because no data xfer. */
-	ei = c->err_info;
-	switch (ei->CommandStatus) {
-	case CMD_INVALID:
-		rc = 0;
-		break;
-	case CMD_UNABORTABLE:
-	case CMD_ABORT_FAILED:
-		rc = 1;
-		break;
-	case CMD_TMF_STATUS:
-		rc = hpsa_evaluate_tmf_status(h, c);
-		break;
-	default:
-		rc = 0;
-		break;
-	}
-	cmd_free(h, c);
-	return rc;
-}
-
 static int hpsa_update_device_info(struct ctlr_info *h,
 	unsigned char scsi3addr[], struct hpsa_scsi_dev_t *this_device,
 	unsigned char *is_OBDR_device)
@@ -3907,6 +3827,9 @@ static int hpsa_update_device_info(struct ctlr_info *h,
 		this_device->queue_depth = h->nr_cmds;
 	}
 
+	if (this_device->external)
+		this_device->queue_depth = EXTERNAL_QD;
+
 	if (is_OBDR_device) {
 		/* See if this is a One-Button-Disaster-Recovery device
 		 * by looking for "$DR-10" at offset 43 in inquiry data.
@@ -3924,31 +3847,6 @@ bail_out:
 	return rc;
 }
 
-static void hpsa_update_device_supports_aborts(struct ctlr_info *h,
-			struct hpsa_scsi_dev_t *dev, u8 *scsi3addr)
-{
-	unsigned long flags;
-	int rc, entry;
-	/*
-	 * See if this device supports aborts.  If we already know
-	 * the device, we already know if it supports aborts, otherwise
-	 * we have to find out if it supports aborts by trying one.
-	 */
-	spin_lock_irqsave(&h->devlock, flags);
-	rc = hpsa_scsi_find_entry(dev, h->dev, h->ndevices, &entry);
-	if ((rc == DEVICE_SAME || rc == DEVICE_UPDATED) &&
-		entry >= 0 && entry < h->ndevices) {
-		dev->supports_aborts = h->dev[entry]->supports_aborts;
-		spin_unlock_irqrestore(&h->devlock, flags);
-	} else {
-		spin_unlock_irqrestore(&h->devlock, flags);
-		dev->supports_aborts =
-				hpsa_device_supports_aborts(h, scsi3addr);
-		if (dev->supports_aborts < 0)
-			dev->supports_aborts = 0;
-	}
-}
-
 /*
  * Helper function to assign bus, target, lun mapping of devices.
  * Logical drive target and lun are assigned at this time, but
@@ -3986,35 +3884,6 @@ static void figure_bus_target_lun(struct ctlr_info *h,
 				0, lunid & 0x3fff);
 }
 
-
-/*
- * Get address of physical disk used for an ioaccel2 mode command:
- *	1. Extract ioaccel2 handle from the command.
- *	2. Find a matching ioaccel2 handle from list of physical disks.
- *	3. Return:
- *		1 and set scsi3addr to address of matching physical
- *		0 if no matching physical disk was found.
- */
-static int hpsa_get_pdisk_of_ioaccel2(struct ctlr_info *h,
-	struct CommandList *ioaccel2_cmd_to_abort, unsigned char *scsi3addr)
-{
-	struct io_accel2_cmd *c2 =
-			&h->ioaccel2_cmd_pool[ioaccel2_cmd_to_abort->cmdindex];
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&h->devlock, flags);
-	for (i = 0; i < h->ndevices; i++)
-		if (h->dev[i]->ioaccel_handle == le32_to_cpu(c2->scsi_nexus)) {
-			memcpy(scsi3addr, h->dev[i]->scsi3addr,
-				sizeof(h->dev[i]->scsi3addr));
-			spin_unlock_irqrestore(&h->devlock, flags);
-			return 1;
-		}
-	spin_unlock_irqrestore(&h->devlock, flags);
-	return 0;
-}
-
 static int  figure_external_status(struct ctlr_info *h, int raid_ctlr_position,
 	int i, int nphysicals, int nlocal_logicals)
 {
@@ -4115,14 +3984,6 @@ static void hpsa_get_ioaccel_drive_info(struct ctlr_info *h,
 	int rc;
 	struct ext_report_lun_entry *rle;
 
-	/*
-	 * external targets don't support BMIC
-	 */
-	if (dev->external) {
-		dev->queue_depth = 7;
-		return;
-	}
-
 	rle = &rlep->LUN[rle_index];
 
 	dev->ioaccel_handle = rle->ioaccel_handle;
@@ -4387,7 +4248,6 @@ static void hpsa_update_scsi_devices(struct ctlr_info *h)
 		}
 
 		figure_bus_target_lun(h, lunaddrbytes, tmpdevice);
-		hpsa_update_device_supports_aborts(h, tmpdevice, lunaddrbytes);
 		this_device = currentsd[ncurrent];
 
 		/* Turn on discovery_polling if there are ext target devices.
@@ -4584,7 +4444,55 @@ sglist_finished:
 	return 0;
 }
 
-#define IO_ACCEL_INELIGIBLE (1)
+#define BUFLEN 128
+static inline void warn_zero_length_transfer(struct ctlr_info *h,
+						u8 *cdb, int cdb_len,
+						const char *func)
+{
+	char buf[BUFLEN];
+	int outlen;
+	int i;
+
+	outlen = scnprintf(buf, BUFLEN,
+				"%s: Blocking zero-length request: CDB:", func);
+	for (i = 0; i < cdb_len; i++)
+		outlen += scnprintf(buf+outlen, BUFLEN - outlen,
+					"%02hhx", cdb[i]);
+	dev_warn(&h->pdev->dev, "%s\n", buf);
+}
+
+#define IO_ACCEL_INELIGIBLE 1
+/* zero-length transfers trigger hardware errors. */
+static bool is_zero_length_transfer(u8 *cdb)
+{
+	u32 block_cnt;
+
+	/* Block zero-length transfer sizes on certain commands. */
+	switch (cdb[0]) {
+	case READ_10:
+	case WRITE_10:
+	case VERIFY:		/* 0x2F */
+	case WRITE_VERIFY:	/* 0x2E */
+		block_cnt = get_unaligned_be16(&cdb[7]);
+		break;
+	case READ_12:
+	case WRITE_12:
+	case VERIFY_12: /* 0xAF */
+	case WRITE_VERIFY_12:	/* 0xAE */
+		block_cnt = get_unaligned_be32(&cdb[6]);
+		break;
+	case READ_16:
+	case WRITE_16:
+	case VERIFY_16:		/* 0x8F */
+		block_cnt = get_unaligned_be32(&cdb[10]);
+		break;
+	default:
+		return false;
+	}
+
+	return block_cnt == 0;
+}
+
 static int fixup_ioaccel_cdb(u8 *cdb, int *cdb_len)
 {
 	int is_write = 0;
@@ -4651,6 +4559,12 @@ static int hpsa_scsi_ioaccel1_queue_command(struct ctlr_info *h,
 
 	BUG_ON(cmd->cmd_len > IOACCEL1_IOFLAGS_CDBLEN_MAX);
 
+	if (is_zero_length_transfer(cdb)) {
+		warn_zero_length_transfer(h, cdb, cdb_len, __func__);
+		atomic_dec(&phys_disk->ioaccel_cmds_out);
+		return IO_ACCEL_INELIGIBLE;
+	}
+
 	if (fixup_ioaccel_cdb(cdb, &cdb_len)) {
 		atomic_dec(&phys_disk->ioaccel_cmds_out);
 		return IO_ACCEL_INELIGIBLE;
@@ -4815,6 +4729,12 @@ static int hpsa_scsi_ioaccel2_queue_command(struct ctlr_info *h,
 
 	BUG_ON(scsi_sg_count(cmd) > h->maxsgentries);
 
+	if (is_zero_length_transfer(cdb)) {
+		warn_zero_length_transfer(h, cdb, cdb_len, __func__);
+		atomic_dec(&phys_disk->ioaccel_cmds_out);
+		return IO_ACCEL_INELIGIBLE;
+	}
+
 	if (fixup_ioaccel_cdb(cdb, &cdb_len)) {
 		atomic_dec(&phys_disk->ioaccel_cmds_out);
 		return IO_ACCEL_INELIGIBLE;
@@ -5460,9 +5380,7 @@ static void hpsa_command_resubmit_worker(struct work_struct *work)
 		return hpsa_cmd_free_and_done(c->h, c, cmd);
 	}
 	if (c->reset_pending)
-		return hpsa_cmd_resolve_and_free(c->h, c);
-	if (c->abort_pending)
-		return hpsa_cmd_abort_and_free(c->h, c, cmd);
+		return hpsa_cmd_free_and_done(c->h, c, cmd);
 	if (c->cmd_type == CMD_IOACCEL2) {
 		struct ctlr_info *h = c->h;
 		struct io_accel2_cmd *c2 = &h->ioaccel2_cmd_pool[c->cmdindex];
@@ -5613,10 +5531,14 @@ static void hpsa_scan_start(struct Scsi_Host *sh)
 	/*
 	 * Do the scan after a reset completion
 	 */
+	spin_lock_irqsave(&h->reset_lock, flags);
 	if (h->reset_in_progress) {
 		h->drv_req_rescan = 1;
+		spin_unlock_irqrestore(&h->reset_lock, flags);
+		hpsa_scan_complete(h);
 		return;
 	}
+	spin_unlock_irqrestore(&h->reset_lock, flags);
 
 	hpsa_update_scsi_devices(h);
 
@@ -5828,24 +5750,37 @@ static int wait_for_device_to_become_ready(struct ctlr_info *h,
  */
 static int hpsa_eh_device_reset_handler(struct scsi_cmnd *scsicmd)
 {
-	int rc;
+	int rc = SUCCESS;
 	struct ctlr_info *h;
 	struct hpsa_scsi_dev_t *dev;
 	u8 reset_type;
 	char msg[48];
+	unsigned long flags;
 
 	/* find the controller to which the command to be aborted was sent */
 	h = sdev_to_hba(scsicmd->device);
 	if (h == NULL) /* paranoia */
 		return FAILED;
 
-	if (lockup_detected(h))
-		return FAILED;
+	spin_lock_irqsave(&h->reset_lock, flags);
+	h->reset_in_progress = 1;
+	spin_unlock_irqrestore(&h->reset_lock, flags);
+
+	if (lockup_detected(h)) {
+		rc = FAILED;
+		goto return_reset_status;
+	}
 
 	dev = scsicmd->device->hostdata;
 	if (!dev) {
 		dev_err(&h->pdev->dev, "%s: device lookup failed\n", __func__);
-		return FAILED;
+		rc = FAILED;
+		goto return_reset_status;
+	}
+
+	if (dev->devtype == TYPE_ENCLOSURE) {
+		rc = SUCCESS;
+		goto return_reset_status;
 	}
 
 	/* if controller locked up, we can guarantee command won't complete */
@@ -5854,7 +5789,8 @@ static int hpsa_eh_device_reset_handler(struct scsi_cmnd *scsicmd)
 			 "cmd %d RESET FAILED, lockup detected",
 			 hpsa_get_cmd_index(scsicmd));
 		hpsa_show_dev_msg(KERN_WARNING, h, dev, msg);
-		return FAILED;
+		rc = FAILED;
+		goto return_reset_status;
 	}
 
 	/* this reset request might be the result of a lockup; check */
@@ -5863,12 +5799,15 @@ static int hpsa_eh_device_reset_handler(struct scsi_cmnd *scsicmd)
 			 "cmd %d RESET FAILED, new lockup detected",
 			 hpsa_get_cmd_index(scsicmd));
 		hpsa_show_dev_msg(KERN_WARNING, h, dev, msg);
-		return FAILED;
+		rc = FAILED;
+		goto return_reset_status;
 	}
 
 	/* Do not attempt on controller */
-	if (is_hba_lunid(dev->scsi3addr))
-		return SUCCESS;
+	if (is_hba_lunid(dev->scsi3addr)) {
+		rc = SUCCESS;
+		goto return_reset_status;
+	}
 
 	if (is_logical_dev_addr_mode(dev->scsi3addr))
 		reset_type = HPSA_DEVICE_RESET_MSG;
@@ -5879,446 +5818,26 @@ static int hpsa_eh_device_reset_handler(struct scsi_cmnd *scsicmd)
 		reset_type == HPSA_DEVICE_RESET_MSG ? "logical " : "physical ");
 	hpsa_show_dev_msg(KERN_WARNING, h, dev, msg);
 
-	h->reset_in_progress = 1;
-
 	/* send a reset to the SCSI LUN which the command was sent to */
 	rc = hpsa_do_reset(h, dev, dev->scsi3addr, reset_type,
 			   DEFAULT_REPLY_QUEUE);
+	if (rc == 0)
+		rc = SUCCESS;
+	else
+		rc = FAILED;
+
 	sprintf(msg, "reset %s %s",
 		reset_type == HPSA_DEVICE_RESET_MSG ? "logical " : "physical ",
-		rc == 0 ? "completed successfully" : "failed");
+		rc == SUCCESS ? "completed successfully" : "failed");
 	hpsa_show_dev_msg(KERN_WARNING, h, dev, msg);
-	h->reset_in_progress = 0;
-	return rc == 0 ? SUCCESS : FAILED;
-}
-
-static void swizzle_abort_tag(u8 *tag)
-{
-	u8 original_tag[8];
-
-	memcpy(original_tag, tag, 8);
-	tag[0] = original_tag[3];
-	tag[1] = original_tag[2];
-	tag[2] = original_tag[1];
-	tag[3] = original_tag[0];
-	tag[4] = original_tag[7];
-	tag[5] = original_tag[6];
-	tag[6] = original_tag[5];
-	tag[7] = original_tag[4];
-}
-
-static void hpsa_get_tag(struct ctlr_info *h,
-	struct CommandList *c, __le32 *taglower, __le32 *tagupper)
-{
-	u64 tag;
-	if (c->cmd_type == CMD_IOACCEL1) {
-		struct io_accel1_cmd *cm1 = (struct io_accel1_cmd *)
-			&h->ioaccel_cmd_pool[c->cmdindex];
-		tag = le64_to_cpu(cm1->tag);
-		*tagupper = cpu_to_le32(tag >> 32);
-		*taglower = cpu_to_le32(tag);
-		return;
-	}
-	if (c->cmd_type == CMD_IOACCEL2) {
-		struct io_accel2_cmd *cm2 = (struct io_accel2_cmd *)
-			&h->ioaccel2_cmd_pool[c->cmdindex];
-		/* upper tag not used in ioaccel2 mode */
-		memset(tagupper, 0, sizeof(*tagupper));
-		*taglower = cm2->Tag;
-		return;
-	}
-	tag = le64_to_cpu(c->Header.tag);
-	*tagupper = cpu_to_le32(tag >> 32);
-	*taglower = cpu_to_le32(tag);
-}
-
-static int hpsa_send_abort(struct ctlr_info *h, unsigned char *scsi3addr,
-	struct CommandList *abort, int reply_queue)
-{
-	int rc = IO_OK;
-	struct CommandList *c;
-	struct ErrorInfo *ei;
-	__le32 tagupper, taglower;
-
-	c = cmd_alloc(h);
-
-	/* fill_cmd can't fail here, no buffer to map */
-	(void) fill_cmd(c, HPSA_ABORT_MSG, h, &abort->Header.tag,
-		0, 0, scsi3addr, TYPE_MSG);
-	if (h->needs_abort_tags_swizzled)
-		swizzle_abort_tag(&c->Request.CDB[4]);
-	(void) hpsa_scsi_do_simple_cmd(h, c, reply_queue, DEFAULT_TIMEOUT);
-	hpsa_get_tag(h, abort, &taglower, &tagupper);
-	dev_dbg(&h->pdev->dev, "%s: Tag:0x%08x:%08x: do_simple_cmd(abort) completed.\n",
-		__func__, tagupper, taglower);
-	/* no unmap needed here because no data xfer. */
-
-	ei = c->err_info;
-	switch (ei->CommandStatus) {
-	case CMD_SUCCESS:
-		break;
-	case CMD_TMF_STATUS:
-		rc = hpsa_evaluate_tmf_status(h, c);
-		break;
-	case CMD_UNABORTABLE: /* Very common, don't make noise. */
-		rc = -1;
-		break;
-	default:
-		dev_dbg(&h->pdev->dev, "%s: Tag:0x%08x:%08x: interpreting error.\n",
-			__func__, tagupper, taglower);
-		hpsa_scsi_interpret_error(h, c);
-		rc = -1;
-		break;
-	}
-	cmd_free(h, c);
-	dev_dbg(&h->pdev->dev, "%s: Tag:0x%08x:%08x: Finished.\n",
-		__func__, tagupper, taglower);
-	return rc;
-}
-
-static void setup_ioaccel2_abort_cmd(struct CommandList *c, struct ctlr_info *h,
-	struct CommandList *command_to_abort, int reply_queue)
-{
-	struct io_accel2_cmd *c2 = &h->ioaccel2_cmd_pool[c->cmdindex];
-	struct hpsa_tmf_struct *ac = (struct hpsa_tmf_struct *) c2;
-	struct io_accel2_cmd *c2a =
-		&h->ioaccel2_cmd_pool[command_to_abort->cmdindex];
-	struct scsi_cmnd *scmd = command_to_abort->scsi_cmd;
-	struct hpsa_scsi_dev_t *dev = scmd->device->hostdata;
 
-	if (!dev)
-		return;
-
-	/*
-	 * We're overlaying struct hpsa_tmf_struct on top of something which
-	 * was allocated as a struct io_accel2_cmd, so we better be sure it
-	 * actually fits, and doesn't overrun the error info space.
-	 */
-	BUILD_BUG_ON(sizeof(struct hpsa_tmf_struct) >
-			sizeof(struct io_accel2_cmd));
-	BUG_ON(offsetof(struct io_accel2_cmd, error_data) <
-			offsetof(struct hpsa_tmf_struct, error_len) +
-				sizeof(ac->error_len));
-
-	c->cmd_type = IOACCEL2_TMF;
-	c->scsi_cmd = SCSI_CMD_BUSY;
-
-	/* Adjust the DMA address to point to the accelerated command buffer */
-	c->busaddr = (u32) h->ioaccel2_cmd_pool_dhandle +
-				(c->cmdindex * sizeof(struct io_accel2_cmd));
-	BUG_ON(c->busaddr & 0x0000007F);
-
-	memset(ac, 0, sizeof(*c2)); /* yes this is correct */
-	ac->iu_type = IOACCEL2_IU_TMF_TYPE;
-	ac->reply_queue = reply_queue;
-	ac->tmf = IOACCEL2_TMF_ABORT;
-	ac->it_nexus = cpu_to_le32(dev->ioaccel_handle);
-	memset(ac->lun_id, 0, sizeof(ac->lun_id));
-	ac->tag = cpu_to_le64(c->cmdindex << DIRECT_LOOKUP_SHIFT);
-	ac->abort_tag = cpu_to_le64(le32_to_cpu(c2a->Tag));
-	ac->error_ptr = cpu_to_le64(c->busaddr +
-			offsetof(struct io_accel2_cmd, error_data));
-	ac->error_len = cpu_to_le32(sizeof(c2->error_data));
-}
-
-/* ioaccel2 path firmware cannot handle abort task requests.
- * Change abort requests to physical target reset, and send to the
- * address of the physical disk used for the ioaccel 2 command.
- * Return 0 on success (IO_OK)
- *	 -1 on failure
- */
-
-static int hpsa_send_reset_as_abort_ioaccel2(struct ctlr_info *h,
-	unsigned char *scsi3addr, struct CommandList *abort, int reply_queue)
-{
-	int rc = IO_OK;
-	struct scsi_cmnd *scmd; /* scsi command within request being aborted */
-	struct hpsa_scsi_dev_t *dev; /* device to which scsi cmd was sent */
-	unsigned char phys_scsi3addr[8]; /* addr of phys disk with volume */
-	unsigned char *psa = &phys_scsi3addr[0];
-
-	/* Get a pointer to the hpsa logical device. */
-	scmd = abort->scsi_cmd;
-	dev = (struct hpsa_scsi_dev_t *)(scmd->device->hostdata);
-	if (dev == NULL) {
-		dev_warn(&h->pdev->dev,
-			"Cannot abort: no device pointer for command.\n");
-			return -1; /* not abortable */
-	}
-
-	if (h->raid_offload_debug > 0)
-		dev_info(&h->pdev->dev,
-			"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);
-
-	if (!dev->offload_enabled) {
-		dev_warn(&h->pdev->dev,
-			"Can't abort: device is not operating in HP SSD Smart Path mode.\n");
-		return -1; /* not abortable */
-	}
-
-	/* Incoming scsi3addr is logical addr. We need physical disk addr. */
-	if (!hpsa_get_pdisk_of_ioaccel2(h, abort, psa)) {
-		dev_warn(&h->pdev->dev, "Can't abort: Failed lookup of physical address.\n");
-		return -1; /* not abortable */
-	}
-
-	/* send the reset */
-	if (h->raid_offload_debug > 0)
-		dev_info(&h->pdev->dev,
-			"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%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%8phN\n",
-			psa);
-		return -1;  /* failed to recover */
-	}
-
-	/* device recovered */
-	dev_info(&h->pdev->dev,
-		"Reset as abort: Device recovered from reset: scsi3addr 0x%8phN\n",
-		psa);
-
-	return rc; /* success */
-}
-
-static int hpsa_send_abort_ioaccel2(struct ctlr_info *h,
-	struct CommandList *abort, int reply_queue)
-{
-	int rc = IO_OK;
-	struct CommandList *c;
-	__le32 taglower, tagupper;
-	struct hpsa_scsi_dev_t *dev;
-	struct io_accel2_cmd *c2;
-
-	dev = abort->scsi_cmd->device->hostdata;
-	if (!dev)
-		return -1;
-
-	if (!dev->offload_enabled && !dev->hba_ioaccel_enabled)
-		return -1;
-
-	c = cmd_alloc(h);
-	setup_ioaccel2_abort_cmd(c, h, abort, reply_queue);
-	c2 = &h->ioaccel2_cmd_pool[c->cmdindex];
-	(void) hpsa_scsi_do_simple_cmd(h, c, reply_queue, DEFAULT_TIMEOUT);
-	hpsa_get_tag(h, abort, &taglower, &tagupper);
-	dev_dbg(&h->pdev->dev,
-		"%s: Tag:0x%08x:%08x: do_simple_cmd(ioaccel2 abort) completed.\n",
-		__func__, tagupper, taglower);
-	/* no unmap needed here because no data xfer. */
-
-	dev_dbg(&h->pdev->dev,
-		"%s: Tag:0x%08x:%08x: abort service response = 0x%02x.\n",
-		__func__, tagupper, taglower, c2->error_data.serv_response);
-	switch (c2->error_data.serv_response) {
-	case IOACCEL2_SERV_RESPONSE_TMF_COMPLETE:
-	case IOACCEL2_SERV_RESPONSE_TMF_SUCCESS:
-		rc = 0;
-		break;
-	case IOACCEL2_SERV_RESPONSE_TMF_REJECTED:
-	case IOACCEL2_SERV_RESPONSE_FAILURE:
-	case IOACCEL2_SERV_RESPONSE_TMF_WRONG_LUN:
-		rc = -1;
-		break;
-	default:
-		dev_warn(&h->pdev->dev,
-			"%s: Tag:0x%08x:%08x: unknown abort service response 0x%02x\n",
-			__func__, tagupper, taglower,
-			c2->error_data.serv_response);
-		rc = -1;
-	}
-	cmd_free(h, c);
-	dev_dbg(&h->pdev->dev, "%s: Tag:0x%08x:%08x: Finished.\n", __func__,
-		tagupper, taglower);
+return_reset_status:
+	spin_lock_irqsave(&h->reset_lock, flags);
+	h->reset_in_progress = 0;
+	spin_unlock_irqrestore(&h->reset_lock, flags);
 	return rc;
 }
 
-static int hpsa_send_abort_both_ways(struct ctlr_info *h,
-	struct hpsa_scsi_dev_t *dev, struct CommandList *abort, int reply_queue)
-{
-	/*
-	 * ioccelerator mode 2 commands should be aborted via the
-	 * accelerated path, since RAID path is unaware of these commands,
-	 * but not all underlying firmware can handle abort TMF.
-	 * Change abort to physical device reset when abort TMF is unsupported.
-	 */
-	if (abort->cmd_type == CMD_IOACCEL2) {
-		if ((HPSATMF_IOACCEL_ENABLED & h->TMFSupportFlags) ||
-			dev->physical_device)
-			return hpsa_send_abort_ioaccel2(h, abort,
-						reply_queue);
-		else
-			return hpsa_send_reset_as_abort_ioaccel2(h,
-							dev->scsi3addr,
-							abort, reply_queue);
-	}
-	return hpsa_send_abort(h, dev->scsi3addr, abort, reply_queue);
-}
-
-/* Find out which reply queue a command was meant to return on */
-static int hpsa_extract_reply_queue(struct ctlr_info *h,
-					struct CommandList *c)
-{
-	if (c->cmd_type == CMD_IOACCEL2)
-		return h->ioaccel2_cmd_pool[c->cmdindex].reply_queue;
-	return c->Header.ReplyQueue;
-}
-
-/*
- * Limit concurrency of abort commands to prevent
- * over-subscription of commands
- */
-static inline int wait_for_available_abort_cmd(struct ctlr_info *h)
-{
-#define ABORT_CMD_WAIT_MSECS 5000
-	return !wait_event_timeout(h->abort_cmd_wait_queue,
-			atomic_dec_if_positive(&h->abort_cmds_available) >= 0,
-			msecs_to_jiffies(ABORT_CMD_WAIT_MSECS));
-}
-
-/* Send an abort for the specified command.
- *	If the device and controller support it,
- *		send a task abort request.
- */
-static int hpsa_eh_abort_handler(struct scsi_cmnd *sc)
-{
-
-	int rc;
-	struct ctlr_info *h;
-	struct hpsa_scsi_dev_t *dev;
-	struct CommandList *abort; /* pointer to command to be aborted */
-	struct scsi_cmnd *as;	/* ptr to scsi cmd inside aborted command. */
-	char msg[256];		/* For debug messaging. */
-	int ml = 0;
-	__le32 tagupper, taglower;
-	int refcount, reply_queue;
-
-	if (sc == NULL)
-		return FAILED;
-
-	if (sc->device == NULL)
-		return FAILED;
-
-	/* Find the controller of the command to be aborted */
-	h = sdev_to_hba(sc->device);
-	if (h == NULL)
-		return FAILED;
-
-	/* Find the device of the command to be aborted */
-	dev = sc->device->hostdata;
-	if (!dev) {
-		dev_err(&h->pdev->dev, "%s FAILED, Device lookup failed.\n",
-				msg);
-		return FAILED;
-	}
-
-	/* If controller locked up, we can guarantee command won't complete */
-	if (lockup_detected(h)) {
-		hpsa_show_dev_msg(KERN_WARNING, h, dev,
-					"ABORT FAILED, lockup detected");
-		return FAILED;
-	}
-
-	/* This is a good time to check if controller lockup has occurred */
-	if (detect_controller_lockup(h)) {
-		hpsa_show_dev_msg(KERN_WARNING, h, dev,
-					"ABORT FAILED, new lockup detected");
-		return FAILED;
-	}
-
-	/* Check that controller supports some kind of task abort */
-	if (!(HPSATMF_PHYS_TASK_ABORT & h->TMFSupportFlags) &&
-		!(HPSATMF_LOG_TASK_ABORT & h->TMFSupportFlags))
-		return FAILED;
-
-	memset(msg, 0, sizeof(msg));
-	ml += sprintf(msg+ml, "scsi %d:%d:%d:%llu %s %p",
-		h->scsi_host->host_no, sc->device->channel,
-		sc->device->id, sc->device->lun,
-		"Aborting command", sc);
-
-	/* Get SCSI command to be aborted */
-	abort = (struct CommandList *) sc->host_scribble;
-	if (abort == NULL) {
-		/* This can happen if the command already completed. */
-		return SUCCESS;
-	}
-	refcount = atomic_inc_return(&abort->refcount);
-	if (refcount == 1) { /* Command is done already. */
-		cmd_free(h, abort);
-		return SUCCESS;
-	}
-
-	/* Don't bother trying the abort if we know it won't work. */
-	if (abort->cmd_type != CMD_IOACCEL2 &&
-		abort->cmd_type != CMD_IOACCEL1 && !dev->supports_aborts) {
-		cmd_free(h, abort);
-		return FAILED;
-	}
-
-	/*
-	 * Check that we're aborting the right command.
-	 * It's possible the CommandList already completed and got re-used.
-	 */
-	if (abort->scsi_cmd != sc) {
-		cmd_free(h, abort);
-		return SUCCESS;
-	}
-
-	abort->abort_pending = true;
-	hpsa_get_tag(h, abort, &taglower, &tagupper);
-	reply_queue = hpsa_extract_reply_queue(h, abort);
-	ml += sprintf(msg+ml, "Tag:0x%08x:%08x ", tagupper, taglower);
-	as  = abort->scsi_cmd;
-	if (as != NULL)
-		ml += sprintf(msg+ml,
-			"CDBLen: %d CDB: 0x%02x%02x... SN: 0x%lx ",
-			as->cmd_len, as->cmnd[0], as->cmnd[1],
-			as->serial_number);
-	dev_warn(&h->pdev->dev, "%s BEING SENT\n", msg);
-	hpsa_show_dev_msg(KERN_WARNING, h, dev, "Aborting command");
-
-	/*
-	 * Command is in flight, or possibly already completed
-	 * by the firmware (but not to the scsi mid layer) but we can't
-	 * distinguish which.  Send the abort down.
-	 */
-	if (wait_for_available_abort_cmd(h)) {
-		dev_warn(&h->pdev->dev,
-			"%s FAILED, timeout waiting for an abort command to become available.\n",
-			msg);
-		cmd_free(h, abort);
-		return FAILED;
-	}
-	rc = hpsa_send_abort_both_ways(h, dev, abort, reply_queue);
-	atomic_inc(&h->abort_cmds_available);
-	wake_up_all(&h->abort_cmd_wait_queue);
-	if (rc != 0) {
-		dev_warn(&h->pdev->dev, "%s SENT, FAILED\n", msg);
-		hpsa_show_dev_msg(KERN_WARNING, h, dev,
-				"FAILED to abort command");
-		cmd_free(h, abort);
-		return FAILED;
-	}
-	dev_info(&h->pdev->dev, "%s SENT, SUCCESS\n", msg);
-	wait_event(h->event_sync_wait_queue,
-		   abort->scsi_cmd != sc || lockup_detected(h));
-	cmd_free(h, abort);
-	return !lockup_detected(h) ? SUCCESS : FAILED;
-}
-
 /*
  * For operations with an associated SCSI command, a command block is allocated
  * at init, and managed by cmd_tagged_alloc() and cmd_tagged_free() using the
@@ -6364,9 +5883,7 @@ static void cmd_tagged_free(struct ctlr_info *h, struct CommandList *c)
 {
 	/*
 	 * Release our reference to the block.  We don't need to do anything
-	 * else to free it, because it is accessed by index.  (There's no point
-	 * in checking the result of the decrement, since we cannot guarantee
-	 * that there isn't a concurrent abort which is also accessing it.)
+	 * else to free it, because it is accessed by index.
 	 */
 	(void)atomic_dec(&c->refcount);
 }
@@ -6905,7 +6422,6 @@ static int fill_cmd(struct CommandList *c, u8 cmd, struct ctlr_info *h,
 	int cmd_type)
 {
 	int pci_dir = XFER_NONE;
-	u64 tag; /* for commands to be aborted */
 
 	c->cmd_type = CMD_IOCTL_PEND;
 	c->scsi_cmd = SCSI_CMD_BUSY;
@@ -7089,27 +6605,6 @@ static int fill_cmd(struct CommandList *c, u8 cmd, struct ctlr_info *h,
 			c->Request.CDB[6] = 0x00;
 			c->Request.CDB[7] = 0x00;
 			break;
-		case  HPSA_ABORT_MSG:
-			memcpy(&tag, buff, sizeof(tag));
-			dev_dbg(&h->pdev->dev,
-				"Abort Tag:0x%016llx using rqst Tag:0x%016llx",
-				tag, c->Header.tag);
-			c->Request.CDBLen = 16;
-			c->Request.type_attr_dir =
-					TYPE_ATTR_DIR(cmd_type,
-						ATTR_SIMPLE, XFER_WRITE);
-			c->Request.Timeout = 0; /* Don't time out */
-			c->Request.CDB[0] = HPSA_TASK_MANAGEMENT;
-			c->Request.CDB[1] = HPSA_TMF_ABORT_TASK;
-			c->Request.CDB[2] = 0x00; /* reserved */
-			c->Request.CDB[3] = 0x00; /* reserved */
-			/* Tag to abort goes in CDB[4]-CDB[11] */
-			memcpy(&c->Request.CDB[4], &tag, sizeof(tag));
-			c->Request.CDB[12] = 0x00; /* reserved */
-			c->Request.CDB[13] = 0x00; /* reserved */
-			c->Request.CDB[14] = 0x00; /* reserved */
-			c->Request.CDB[15] = 0x00; /* reserved */
-		break;
 		default:
 			dev_warn(&h->pdev->dev, "unknown message type %d\n",
 				cmd);
@@ -8067,9 +7562,6 @@ static int hpsa_pci_init(struct ctlr_info *h)
 	h->product_name = products[prod_index].product_name;
 	h->access = *(products[prod_index].access);
 
-	h->needs_abort_tags_swizzled =
-		ctlr_needs_abort_tags_swizzled(h->board_id);
-
 	pci_disable_link_state(h->pdev, PCIE_LINK_STATE_L0S |
 			       PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_CLKPM);
 
@@ -8627,41 +8119,79 @@ out:
 	return rc;
 }
 
-static void hpsa_rescan_ctlr_worker(struct work_struct *work)
+static void hpsa_perform_rescan(struct ctlr_info *h)
 {
+	struct Scsi_Host *sh = NULL;
 	unsigned long flags;
-	struct ctlr_info *h = container_of(to_delayed_work(work),
-					struct ctlr_info, rescan_ctlr_work);
-
-
-	if (h->remove_in_progress)
-		return;
 
 	/*
 	 * Do the scan after the reset
 	 */
+	spin_lock_irqsave(&h->reset_lock, flags);
 	if (h->reset_in_progress) {
 		h->drv_req_rescan = 1;
+		spin_unlock_irqrestore(&h->reset_lock, flags);
 		return;
 	}
+	spin_unlock_irqrestore(&h->reset_lock, flags);
+
+	sh = scsi_host_get(h->scsi_host);
+	if (sh != NULL) {
+		hpsa_scan_start(sh);
+		scsi_host_put(sh);
+		h->drv_req_rescan = 0;
+	}
+}
+
+/*
+ * watch for controller events
+ */
+static void hpsa_event_monitor_worker(struct work_struct *work)
+{
+	struct ctlr_info *h = container_of(to_delayed_work(work),
+					struct ctlr_info, event_monitor_work);
+	unsigned long flags;
+
+	spin_lock_irqsave(&h->lock, flags);
+	if (h->remove_in_progress) {
+		spin_unlock_irqrestore(&h->lock, flags);
+		return;
+	}
+	spin_unlock_irqrestore(&h->lock, flags);
 
-	if (hpsa_ctlr_needs_rescan(h) || hpsa_offline_devices_ready(h)) {
-		scsi_host_get(h->scsi_host);
+	if (hpsa_ctlr_needs_rescan(h)) {
 		hpsa_ack_ctlr_events(h);
-		hpsa_scan_start(h->scsi_host);
-		scsi_host_put(h->scsi_host);
+		hpsa_perform_rescan(h);
+	}
+
+	spin_lock_irqsave(&h->lock, flags);
+	if (!h->remove_in_progress)
+		schedule_delayed_work(&h->event_monitor_work,
+					HPSA_EVENT_MONITOR_INTERVAL);
+	spin_unlock_irqrestore(&h->lock, flags);
+}
+
+static void hpsa_rescan_ctlr_worker(struct work_struct *work)
+{
+	unsigned long flags;
+	struct ctlr_info *h = container_of(to_delayed_work(work),
+					struct ctlr_info, rescan_ctlr_work);
+
+	spin_lock_irqsave(&h->lock, flags);
+	if (h->remove_in_progress) {
+		spin_unlock_irqrestore(&h->lock, flags);
+		return;
+	}
+	spin_unlock_irqrestore(&h->lock, flags);
+
+	if (h->drv_req_rescan || hpsa_offline_devices_ready(h)) {
+		hpsa_perform_rescan(h);
 	} else if (h->discovery_polling) {
 		hpsa_disable_rld_caching(h);
 		if (hpsa_luns_changed(h)) {
-			struct Scsi_Host *sh = NULL;
-
 			dev_info(&h->pdev->dev,
 				"driver discovery polling rescan.\n");
-			sh = scsi_host_get(h->scsi_host);
-			if (sh != NULL) {
-				hpsa_scan_start(sh);
-				scsi_host_put(sh);
-			}
+			hpsa_perform_rescan(h);
 		}
 	}
 	spin_lock_irqsave(&h->lock, flags);
@@ -8750,8 +8280,8 @@ reinit_after_soft_reset:
 	spin_lock_init(&h->lock);
 	spin_lock_init(&h->offline_device_lock);
 	spin_lock_init(&h->scan_lock);
+	spin_lock_init(&h->reset_lock);
 	atomic_set(&h->passthru_cmds_avail, HPSA_MAX_CONCURRENT_PASSTHRUS);
-	atomic_set(&h->abort_cmds_available, HPSA_CMDS_RESERVED_FOR_ABORTS);
 
 	/* Allocate and clear per-cpu variable lockup_detected */
 	h->lockup_detected = alloc_percpu(u32);
@@ -8803,7 +8333,6 @@ reinit_after_soft_reset:
 	if (rc)
 		goto clean5;	/* cmd, irq, shost, pci, lu, aer/h */
 	init_waitqueue_head(&h->scan_wait_queue);
-	init_waitqueue_head(&h->abort_cmd_wait_queue);
 	init_waitqueue_head(&h->event_sync_wait_queue);
 	mutex_init(&h->reset_mutex);
 	h->scan_finished = 1; /* no scan currently in progress */
@@ -8926,6 +8455,9 @@ reinit_after_soft_reset:
 	INIT_DELAYED_WORK(&h->rescan_ctlr_work, hpsa_rescan_ctlr_worker);
 	queue_delayed_work(h->rescan_ctlr_wq, &h->rescan_ctlr_work,
 				h->heartbeat_sample_interval);
+	INIT_DELAYED_WORK(&h->event_monitor_work, hpsa_event_monitor_worker);
+	schedule_delayed_work(&h->event_monitor_work,
+				HPSA_EVENT_MONITOR_INTERVAL);
 	return 0;
 
 clean7: /* perf, sg, cmd, irq, shost, pci, lu, aer/h */
@@ -9094,6 +8626,7 @@ static void hpsa_remove_one(struct pci_dev *pdev)
 	spin_unlock_irqrestore(&h->lock, flags);
 	cancel_delayed_work_sync(&h->monitor_ctlr_work);
 	cancel_delayed_work_sync(&h->rescan_ctlr_work);
+	cancel_delayed_work_sync(&h->event_monitor_work);
 	destroy_workqueue(h->rescan_ctlr_wq);
 	destroy_workqueue(h->resubmit_wq);
 

drivers/scsi/hpsa.h

@@ -57,6 +57,7 @@ struct hpsa_sas_phy {
 	bool added_to_port;
 };
 
+#define EXTERNAL_QD 7
 struct hpsa_scsi_dev_t {
 	unsigned int devtype;
 	int bus, target, lun;		/* as presented to the OS */
@@ -244,6 +245,7 @@ struct ctlr_info {
 	u32 __percpu *lockup_detected;
 	struct delayed_work monitor_ctlr_work;
 	struct delayed_work rescan_ctlr_work;
+	struct delayed_work event_monitor_work;
 	int remove_in_progress;
 	/* Address of h->q[x] is passed to intr handler to know which queue */
 	u8 q[MAX_REPLY_QUEUES];
@@ -296,11 +298,11 @@ struct ctlr_info {
 	struct workqueue_struct *resubmit_wq;
 	struct workqueue_struct *rescan_ctlr_wq;
 	atomic_t abort_cmds_available;
-	wait_queue_head_t abort_cmd_wait_queue;
 	wait_queue_head_t event_sync_wait_queue;
 	struct mutex reset_mutex;
 	u8 reset_in_progress;
 	struct hpsa_sas_node *sas_host;
+	spinlock_t reset_lock;
 };
 
 struct offline_device_entry {

drivers/scsi/hpsa_cmd.h

@@ -809,10 +809,7 @@ struct bmic_identify_physical_device {
 	u8     max_temperature_degreesC;
 	u8     logical_blocks_per_phys_block_exp; /* phyblocksize = 512*2^exp */
 	__le16 current_queue_depth_limit;
-	u8     switch_name[10];
-	__le16 switch_port;
-	u8     alternate_paths_switch_name[40];
-	u8     alternate_paths_switch_port[8];
+	u8     reserved_switch_stuff[60];
 	__le16 power_on_hours; /* valid only if gas gauge supported */
 	__le16 percent_endurance_used; /* valid only if gas gauge supported. */
 #define BMIC_PHYS_DRIVE_SSD_WEAROUT(idphydrv) \
@@ -828,11 +825,22 @@ struct bmic_identify_physical_device {
 	(idphydrv->smart_carrier_authentication == 0x01)
 	u8     smart_carrier_app_fw_version;
 	u8     smart_carrier_bootloader_fw_version;
+	u8     sanitize_support_flags;
+	u8     drive_key_flags;
 	u8     encryption_key_name[64];
 	__le32 misc_drive_flags;
 	__le16 dek_index;
-	u8     padding[112];
-};
+	__le16 hba_drive_encryption_flags;
+	__le16 max_overwrite_time;
+	__le16 max_block_erase_time;
+	__le16 max_crypto_erase_time;
+	u8     device_connector_info[5];
+	u8     connector_name[8][8];
+	u8     page_83_id[16];
+	u8     max_link_rate[256];
+	u8     neg_phys_link_rate[256];
+	u8     box_conn_name[8];
+} __attribute((aligned(512)));
 
 struct bmic_sense_subsystem_info {
 	u8	primary_slot_number;

drivers/scsi/hptiop.c

@@ -800,7 +800,7 @@ static void hptiop_host_request_callback_itl(struct hptiop_hba *hba, u32 _tag)
 	hptiop_finish_scsi_req(hba, tag, req);
 }
 
-void hptiop_iop_request_callback_itl(struct hptiop_hba *hba, u32 tag)
+static void hptiop_iop_request_callback_itl(struct hptiop_hba *hba, u32 tag)
 {
 	struct hpt_iop_request_header __iomem *req;
 	struct hpt_iop_request_ioctl_command __iomem *p;

drivers/scsi/ibmvscsi/ibmvfc.c

@@ -4935,7 +4935,7 @@ static struct vio_device_id ibmvfc_device_table[] = {
 };
 MODULE_DEVICE_TABLE(vio, ibmvfc_device_table);
 
-static struct dev_pm_ops ibmvfc_pm_ops = {
+static const struct dev_pm_ops ibmvfc_pm_ops = {
 	.resume = ibmvfc_resume
 };
 

drivers/scsi/ibmvscsi/ibmvscsi.c

@@ -2336,7 +2336,7 @@ static struct vio_device_id ibmvscsi_device_table[] = {
 };
 MODULE_DEVICE_TABLE(vio, ibmvscsi_device_table);
 
-static struct dev_pm_ops ibmvscsi_pm_ops = {
+static const struct dev_pm_ops ibmvscsi_pm_ops = {
 	.resume = ibmvscsi_resume
 };
 

drivers/scsi/libiscsi.c

@@ -2556,7 +2556,7 @@ iscsi_pool_init(struct iscsi_pool *q, int max, void ***items, int item_size)
 	 * the array. */
 	if (items)
 		num_arrays++;
-	q->pool = kzalloc(num_arrays * max * sizeof(void*), GFP_KERNEL);
+	q->pool = kvzalloc(num_arrays * max * sizeof(void*), GFP_KERNEL);
 	if (q->pool == NULL)
 		return -ENOMEM;
 
@@ -2590,7 +2590,7 @@ void iscsi_pool_free(struct iscsi_pool *q)
 
 	for (i = 0; i < q->max; i++)
 		kfree(q->pool[i]);
-	kfree(q->pool);
+	kvfree(q->pool);
 }
 EXPORT_SYMBOL_GPL(iscsi_pool_free);
 

drivers/scsi/libsas/sas_event.c

@@ -27,30 +27,38 @@
 #include "sas_internal.h"
 #include "sas_dump.h"
 
-void sas_queue_work(struct sas_ha_struct *ha, struct sas_work *sw)
+int sas_queue_work(struct sas_ha_struct *ha, struct sas_work *sw)
 {
+	int rc = 0;
+
 	if (!test_bit(SAS_HA_REGISTERED, &ha->state))
-		return;
+		return 0;
 
 	if (test_bit(SAS_HA_DRAINING, &ha->state)) {
 		/* add it to the defer list, if not already pending */
 		if (list_empty(&sw->drain_node))
 			list_add(&sw->drain_node, &ha->defer_q);
 	} else
-		scsi_queue_work(ha->core.shost, &sw->work);
+		rc = scsi_queue_work(ha->core.shost, &sw->work);
+
+	return rc;
 }
 
-static void sas_queue_event(int event, unsigned long *pending,
+static int sas_queue_event(int event, unsigned long *pending,
 			    struct sas_work *work,
 			    struct sas_ha_struct *ha)
 {
+	int rc = 0;
+
 	if (!test_and_set_bit(event, pending)) {
 		unsigned long flags;
 
 		spin_lock_irqsave(&ha->lock, flags);
-		sas_queue_work(ha, work);
+		rc = sas_queue_work(ha, work);
 		spin_unlock_irqrestore(&ha->lock, flags);
 	}
+
+	return rc;
 }
 
 
@@ -116,32 +124,32 @@ void sas_enable_revalidation(struct sas_ha_struct *ha)
 	mutex_unlock(&ha->disco_mutex);
 }
 
-static void notify_ha_event(struct sas_ha_struct *sas_ha, enum ha_event event)
+static int notify_ha_event(struct sas_ha_struct *sas_ha, enum ha_event event)
 {
 	BUG_ON(event >= HA_NUM_EVENTS);
 
-	sas_queue_event(event, &sas_ha->pending,
-			&sas_ha->ha_events[event].work, sas_ha);
+	return sas_queue_event(event, &sas_ha->pending,
+			       &sas_ha->ha_events[event].work, sas_ha);
 }
 
-static void notify_port_event(struct asd_sas_phy *phy, enum port_event event)
+static int notify_port_event(struct asd_sas_phy *phy, enum port_event event)
 {
 	struct sas_ha_struct *ha = phy->ha;
 
 	BUG_ON(event >= PORT_NUM_EVENTS);
 
-	sas_queue_event(event, &phy->port_events_pending,
-			&phy->port_events[event].work, ha);
+	return sas_queue_event(event, &phy->port_events_pending,
+			       &phy->port_events[event].work, ha);
 }
 
-void sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event)
+int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event)
 {
 	struct sas_ha_struct *ha = phy->ha;
 
 	BUG_ON(event >= PHY_NUM_EVENTS);
 
-	sas_queue_event(event, &phy->phy_events_pending,
-			&phy->phy_events[event].work, ha);
+	return sas_queue_event(event, &phy->phy_events_pending,
+			       &phy->phy_events[event].work, ha);
 }
 
 int sas_init_events(struct sas_ha_struct *sas_ha)

drivers/scsi/libsas/sas_internal.h

@@ -76,7 +76,7 @@ void sas_porte_broadcast_rcvd(struct work_struct *work);
 void sas_porte_link_reset_err(struct work_struct *work);
 void sas_porte_timer_event(struct work_struct *work);
 void sas_porte_hard_reset(struct work_struct *work);
-void sas_queue_work(struct sas_ha_struct *ha, struct sas_work *sw);
+int sas_queue_work(struct sas_ha_struct *ha, struct sas_work *sw);
 
 int sas_notify_lldd_dev_found(struct domain_device *);
 void sas_notify_lldd_dev_gone(struct domain_device *);
@@ -85,7 +85,7 @@ int sas_smp_phy_control(struct domain_device *dev, int phy_id,
 			enum phy_func phy_func, struct sas_phy_linkrates *);
 int sas_smp_get_phy_events(struct sas_phy *phy);
 
-void sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event);
+int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event);
 void sas_device_set_phy(struct domain_device *dev, struct sas_port *port);
 struct domain_device *sas_find_dev_by_rphy(struct sas_rphy *rphy);
 struct domain_device *sas_ex_to_ata(struct domain_device *ex_dev, int phy_id);

drivers/scsi/lpfc/lpfc.h

@@ -756,6 +756,7 @@ struct lpfc_hba {
 	uint8_t  nvmet_support;	/* driver supports NVMET */
 #define LPFC_NVMET_MAX_PORTS	32
 	uint8_t  mds_diags_support;
+	uint32_t initial_imax;
 
 	/* HBA Config Parameters */
 	uint32_t cfg_ack0;
@@ -777,6 +778,7 @@ struct lpfc_hba {
 	uint32_t cfg_poll_tmo;
 	uint32_t cfg_task_mgmt_tmo;
 	uint32_t cfg_use_msi;
+	uint32_t cfg_auto_imax;
 	uint32_t cfg_fcp_imax;
 	uint32_t cfg_fcp_cpu_map;
 	uint32_t cfg_fcp_io_channel;
@@ -913,16 +915,16 @@ struct lpfc_hba {
 	/*
 	 * stat  counters
 	 */
-	uint64_t fc4ScsiInputRequests;
-	uint64_t fc4ScsiOutputRequests;
-	uint64_t fc4ScsiControlRequests;
-	uint64_t fc4ScsiIoCmpls;
-	uint64_t fc4NvmeInputRequests;
-	uint64_t fc4NvmeOutputRequests;
-	uint64_t fc4NvmeControlRequests;
-	uint64_t fc4NvmeIoCmpls;
-	uint64_t fc4NvmeLsRequests;
-	uint64_t fc4NvmeLsCmpls;
+	atomic_t fc4ScsiInputRequests;
+	atomic_t fc4ScsiOutputRequests;
+	atomic_t fc4ScsiControlRequests;
+	atomic_t fc4ScsiIoCmpls;
+	atomic_t fc4NvmeInputRequests;
+	atomic_t fc4NvmeOutputRequests;
+	atomic_t fc4NvmeControlRequests;
+	atomic_t fc4NvmeIoCmpls;
+	atomic_t fc4NvmeLsRequests;
+	atomic_t fc4NvmeLsCmpls;
 
 	uint64_t bg_guard_err_cnt;
 	uint64_t bg_apptag_err_cnt;
@@ -1050,6 +1052,7 @@ struct lpfc_hba {
 
 	uint8_t temp_sensor_support;
 	/* Fields used for heart beat. */
+	unsigned long last_eqdelay_time;
 	unsigned long last_completion_time;
 	unsigned long skipped_hb;
 	struct timer_list hb_tmofunc;

drivers/scsi/lpfc/lpfc_attr.c

@@ -148,9 +148,9 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 	struct lpfc_hba   *phba = vport->phba;
 	struct lpfc_nvmet_tgtport *tgtp;
 	struct nvme_fc_local_port *localport;
-	struct lpfc_nvme_lport *lport;
-	struct lpfc_nvme_rport *rport;
+	struct lpfc_nodelist *ndlp;
 	struct nvme_fc_remote_port *nrport;
+	uint64_t data1, data2, data3, tot;
 	char *statep;
 	int len = 0;
 
@@ -171,7 +171,7 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 		else
 			statep = "INIT";
 		len += snprintf(buf + len, PAGE_SIZE - len,
-				"NVME Target: Enabled  State %s\n",
+				"NVME Target Enabled  State %s\n",
 				statep);
 		len += snprintf(buf + len, PAGE_SIZE - len,
 				"%s%d WWPN x%llx WWNN x%llx DID x%06x\n",
@@ -245,11 +245,21 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 				atomic_read(&tgtp->xmt_abort_rsp),
 				atomic_read(&tgtp->xmt_abort_rsp_error));
 
+		spin_lock(&phba->sli4_hba.nvmet_ctx_get_lock);
+		spin_lock(&phba->sli4_hba.nvmet_ctx_put_lock);
+		tot = phba->sli4_hba.nvmet_xri_cnt -
+			(phba->sli4_hba.nvmet_ctx_get_cnt +
+			phba->sli4_hba.nvmet_ctx_put_cnt);
+		spin_unlock(&phba->sli4_hba.nvmet_ctx_put_lock);
+		spin_unlock(&phba->sli4_hba.nvmet_ctx_get_lock);
+
 		len += snprintf(buf + len, PAGE_SIZE - len,
-				"IO_CTX: %08x outstanding %08x total %x",
-				phba->sli4_hba.nvmet_ctx_cnt,
+				"IO_CTX: %08x  WAIT: cur %08x tot %08x\n"
+				"CTX Outstanding %08llx\n",
+				phba->sli4_hba.nvmet_xri_cnt,
 				phba->sli4_hba.nvmet_io_wait_cnt,
-				phba->sli4_hba.nvmet_io_wait_total);
+				phba->sli4_hba.nvmet_io_wait_total,
+				tot);
 
 		len +=  snprintf(buf+len, PAGE_SIZE-len, "\n");
 		return len;
@@ -265,7 +275,6 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 	len = snprintf(buf, PAGE_SIZE, "NVME Initiator Enabled\n");
 
 	spin_lock_irq(shost->host_lock);
-	lport = (struct lpfc_nvme_lport *)localport->private;
 
 	/* Port state is only one of two values for now. */
 	if (localport->port_id)
@@ -281,9 +290,12 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 			wwn_to_u64(vport->fc_nodename.u.wwn),
 			localport->port_id, statep);
 
-	list_for_each_entry(rport, &lport->rport_list, list) {
+	list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
+		if (!ndlp->nrport)
+			continue;
+
 		/* local short-hand pointer. */
-		nrport = rport->remoteport;
+		nrport = ndlp->nrport->remoteport;
 
 		/* Port state is only one of two values for now. */
 		switch (nrport->port_state) {
@@ -311,25 +323,23 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 		len += snprintf(buf + len, PAGE_SIZE - len, "DID x%06x ",
 				nrport->port_id);
 
-		switch (nrport->port_role) {
-		case FC_PORT_ROLE_NVME_INITIATOR:
+		/* An NVME rport can have multiple roles. */
+		if (nrport->port_role & FC_PORT_ROLE_NVME_INITIATOR)
 			len +=  snprintf(buf + len, PAGE_SIZE - len,
 					 "INITIATOR ");
-			break;
-		case FC_PORT_ROLE_NVME_TARGET:
+		if (nrport->port_role & FC_PORT_ROLE_NVME_TARGET)
 			len +=  snprintf(buf + len, PAGE_SIZE - len,
 					 "TARGET ");
-			break;
-		case FC_PORT_ROLE_NVME_DISCOVERY:
+		if (nrport->port_role & FC_PORT_ROLE_NVME_DISCOVERY)
 			len +=  snprintf(buf + len, PAGE_SIZE - len,
-					 "DISCOVERY ");
-			break;
-		default:
+					 "DISCSRVC ");
+		if (nrport->port_role & ~(FC_PORT_ROLE_NVME_INITIATOR |
+					  FC_PORT_ROLE_NVME_TARGET |
+					  FC_PORT_ROLE_NVME_DISCOVERY))
 			len +=  snprintf(buf + len, PAGE_SIZE - len,
-					 "UNKNOWN_ROLE x%x",
+					 "UNKNOWN ROLE x%x",
 					 nrport->port_role);
-			break;
-		}
+
 		len +=  snprintf(buf + len, PAGE_SIZE - len, "%s  ", statep);
 		/* Terminate the string. */
 		len +=  snprintf(buf + len, PAGE_SIZE - len, "\n");
@@ -338,19 +348,21 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 
 	len += snprintf(buf + len, PAGE_SIZE - len, "\nNVME Statistics\n");
 	len += snprintf(buf+len, PAGE_SIZE-len,
-			"LS: Xmt %016llx Cmpl %016llx\n",
-			phba->fc4NvmeLsRequests,
-			phba->fc4NvmeLsCmpls);
-
+			"LS: Xmt %016x Cmpl %016x\n",
+			atomic_read(&phba->fc4NvmeLsRequests),
+			atomic_read(&phba->fc4NvmeLsCmpls));
+
+	tot = atomic_read(&phba->fc4NvmeIoCmpls);
+	data1 = atomic_read(&phba->fc4NvmeInputRequests);
+	data2 = atomic_read(&phba->fc4NvmeOutputRequests);
+	data3 = atomic_read(&phba->fc4NvmeControlRequests);
 	len += snprintf(buf+len, PAGE_SIZE-len,
 			"FCP: Rd %016llx Wr %016llx IO %016llx\n",
-			phba->fc4NvmeInputRequests,
-			phba->fc4NvmeOutputRequests,
-			phba->fc4NvmeControlRequests);
+			data1, data2, data3);
 
 	len += snprintf(buf+len, PAGE_SIZE-len,
-			"    Cmpl %016llx\n", phba->fc4NvmeIoCmpls);
-
+			"    Cmpl %016llx Outstanding %016llx\n",
+			tot, (data1 + data2 + data3) - tot);
 	return len;
 }
 
@@ -1342,6 +1354,8 @@ lpfc_board_mode_store(struct device *dev, struct device_attribute *attr,
 			goto board_mode_out;
 		}
 		wait_for_completion(&online_compl);
+		if (status)
+			status = -EIO;
 	} else if (strncmp(buf, "offline", sizeof("offline") - 1) == 0)
 		status = lpfc_do_offline(phba, LPFC_EVT_OFFLINE);
 	else if (strncmp(buf, "warm", sizeof("warm") - 1) == 0)
@@ -3198,9 +3212,12 @@ lpfc_update_rport_devloss_tmo(struct lpfc_vport *vport)
 
 	shost = lpfc_shost_from_vport(vport);
 	spin_lock_irq(shost->host_lock);
-	list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp)
-		if (NLP_CHK_NODE_ACT(ndlp) && ndlp->rport)
+	list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
+		if (!NLP_CHK_NODE_ACT(ndlp))
+			continue;
+		if (ndlp->rport)
 			ndlp->rport->dev_loss_tmo = vport->cfg_devloss_tmo;
+	}
 	spin_unlock_irq(shost->host_lock);
 }
 
@@ -4467,9 +4484,11 @@ lpfc_fcp_imax_store(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 
 	phba->cfg_fcp_imax = (uint32_t)val;
+	phba->initial_imax = phba->cfg_fcp_imax;
 
 	for (i = 0; i < phba->io_channel_irqs; i += LPFC_MAX_EQ_DELAY_EQID_CNT)
-		lpfc_modify_hba_eq_delay(phba, i);
+		lpfc_modify_hba_eq_delay(phba, i, LPFC_MAX_EQ_DELAY_EQID_CNT,
+					 val);
 
 	return strlen(buf);
 }
@@ -4524,6 +4543,16 @@ lpfc_fcp_imax_init(struct lpfc_hba *phba, int val)
 static DEVICE_ATTR(lpfc_fcp_imax, S_IRUGO | S_IWUSR,
 		   lpfc_fcp_imax_show, lpfc_fcp_imax_store);
 
+/*
+ * lpfc_auto_imax: Controls Auto-interrupt coalescing values support.
+ *       0       No auto_imax support
+ *       1       auto imax on
+ * Auto imax will change the value of fcp_imax on a per EQ basis, using
+ * the EQ Delay Multiplier, depending on the activity for that EQ.
+ * Value range [0,1]. Default value is 1.
+ */
+LPFC_ATTR_RW(auto_imax, 1, 0, 1, "Enable Auto imax");
+
 /**
  * lpfc_state_show - Display current driver CPU affinity
  * @dev: class converted to a Scsi_host structure.
@@ -5150,6 +5179,7 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_task_mgmt_tmo,
 	&dev_attr_lpfc_use_msi,
 	&dev_attr_lpfc_nvme_oas,
+	&dev_attr_lpfc_auto_imax,
 	&dev_attr_lpfc_fcp_imax,
 	&dev_attr_lpfc_fcp_cpu_map,
 	&dev_attr_lpfc_fcp_io_channel,
@@ -6168,6 +6198,7 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	lpfc_enable_SmartSAN_init(phba, lpfc_enable_SmartSAN);
 	lpfc_use_msi_init(phba, lpfc_use_msi);
 	lpfc_nvme_oas_init(phba, lpfc_nvme_oas);
+	lpfc_auto_imax_init(phba, lpfc_auto_imax);
 	lpfc_fcp_imax_init(phba, lpfc_fcp_imax);
 	lpfc_fcp_cpu_map_init(phba, lpfc_fcp_cpu_map);
 	lpfc_enable_hba_reset_init(phba, lpfc_enable_hba_reset);
@@ -6212,6 +6243,10 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 			phba->cfg_enable_fc4_type |= LPFC_ENABLE_FCP;
 	}
 
+	if (phba->cfg_auto_imax && !phba->cfg_fcp_imax)
+		phba->cfg_auto_imax = 0;
+	phba->initial_imax = phba->cfg_fcp_imax;
+
 	/* A value of 0 means use the number of CPUs found in the system */
 	if (phba->cfg_fcp_io_channel == 0)
 		phba->cfg_fcp_io_channel = phba->sli4_hba.num_present_cpu;

drivers/scsi/lpfc/lpfc_ct.c

@@ -503,26 +503,23 @@ lpfc_prep_node_fc4type(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
 				Did, vport->fc_flag, vport->fc_rscn_id_cnt);
 
 			/*
-			 * This NPortID was previously a FCP target,
+			 * This NPortID was previously a FCP/NVMe target,
 			 * Don't even bother to send GFF_ID.
 			 */
 			ndlp = lpfc_findnode_did(vport, Did);
-			if (ndlp && NLP_CHK_NODE_ACT(ndlp))
-				ndlp->nlp_fc4_type = fc4_type;
-
-			if (ndlp && NLP_CHK_NODE_ACT(ndlp)) {
-				ndlp->nlp_fc4_type = fc4_type;
-
-				if (ndlp->nlp_type & NLP_FCP_TARGET)
-					lpfc_setup_disc_node(vport, Did);
-
-				else if (lpfc_ns_cmd(vport, SLI_CTNS_GFF_ID,
-							0, Did) == 0)
-					vport->num_disc_nodes++;
-
-				else
-					lpfc_setup_disc_node(vport, Did);
-			}
+			if (ndlp && NLP_CHK_NODE_ACT(ndlp) &&
+			    (ndlp->nlp_type &
+			    (NLP_FCP_TARGET | NLP_NVME_TARGET))) {
+				if (fc4_type == FC_TYPE_FCP)
+					ndlp->nlp_fc4_type |= NLP_FC4_FCP;
+				if (fc4_type == FC_TYPE_NVME)
+					ndlp->nlp_fc4_type |= NLP_FC4_NVME;
+				lpfc_setup_disc_node(vport, Did);
+			} else if (lpfc_ns_cmd(vport, SLI_CTNS_GFF_ID,
+				   0, Did) == 0)
+				vport->num_disc_nodes++;
+			else
+				lpfc_setup_disc_node(vport, Did);
 		} else {
 			lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_CT,
 				"Skip2 GID_FTrsp: did:x%x flg:x%x cnt:%d",

drivers/scsi/lpfc/lpfc_debugfs.c

@@ -323,7 +323,7 @@ lpfc_debugfs_hbqinfo_data(struct lpfc_hba *phba, char *buf, int size)
 	raw_index = phba->hbq_get[i];
 	getidx = le32_to_cpu(raw_index);
 	len +=  snprintf(buf+len, size-len,
-		"entrys:%d bufcnt:%d Put:%d nPut:%d localGet:%d hbaGet:%d\n",
+		"entries:%d bufcnt:%d Put:%d nPut:%d localGet:%d hbaGet:%d\n",
 		hbqs->entry_count, hbqs->buffer_count, hbqs->hbqPutIdx,
 		hbqs->next_hbqPutIdx, hbqs->local_hbqGetIdx, getidx);
 
@@ -550,8 +550,6 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 	struct lpfc_nodelist *ndlp;
 	unsigned char *statep;
 	struct nvme_fc_local_port *localport;
-	struct lpfc_nvme_lport *lport;
-	struct lpfc_nvme_rport *rport;
 	struct lpfc_nvmet_tgtport *tgtp;
 	struct nvme_fc_remote_port *nrport;
 
@@ -623,6 +621,13 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 				ndlp->nlp_sid);
 		if (ndlp->nlp_type & NLP_FCP_INITIATOR)
 			len += snprintf(buf+len, size-len, "FCP_INITIATOR ");
+		if (ndlp->nlp_type & NLP_NVME_TARGET)
+			len += snprintf(buf + len,
+					size - len, "NVME_TGT sid:%d ",
+					NLP_NO_SID);
+		if (ndlp->nlp_type & NLP_NVME_INITIATOR)
+			len += snprintf(buf + len,
+					size - len, "NVME_INITIATOR ");
 		len += snprintf(buf+len, size-len, "usgmap:%x ",
 			ndlp->nlp_usg_map);
 		len += snprintf(buf+len, size-len, "refcnt:%x",
@@ -660,7 +665,6 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 		goto out_exit;
 
 	spin_lock_irq(shost->host_lock);
-	lport = (struct lpfc_nvme_lport *)localport->private;
 
 	/* Port state is only one of two values for now. */
 	if (localport->port_id)
@@ -673,9 +677,12 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 			localport->port_id, statep);
 
 	len += snprintf(buf + len, size - len, "\tRport List:\n");
-	list_for_each_entry(rport, &lport->rport_list, list) {
+	list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
 		/* local short-hand pointer. */
-		nrport = rport->remoteport;
+		if (!ndlp->nrport)
+			continue;
+
+		nrport = ndlp->nrport->remoteport;
 
 		/* Port state is only one of two values for now. */
 		switch (nrport->port_state) {
@@ -698,26 +705,23 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 				nrport->port_name);
 		len += snprintf(buf + len, size - len, "WWNN x%llx ",
 				nrport->node_name);
-		switch (nrport->port_role) {
-		case FC_PORT_ROLE_NVME_INITIATOR:
+
+		/* An NVME rport can have multiple roles. */
+		if (nrport->port_role & FC_PORT_ROLE_NVME_INITIATOR)
 			len +=  snprintf(buf + len, size - len,
-					 "NVME INITIATOR ");
-			break;
-		case FC_PORT_ROLE_NVME_TARGET:
+					 "INITIATOR ");
+		if (nrport->port_role & FC_PORT_ROLE_NVME_TARGET)
 			len +=  snprintf(buf + len, size - len,
-					 "NVME TARGET ");
-			break;
-		case FC_PORT_ROLE_NVME_DISCOVERY:
+					 "TARGET ");
+		if (nrport->port_role & FC_PORT_ROLE_NVME_DISCOVERY)
 			len +=  snprintf(buf + len, size - len,
-					 "NVME DISCOVERY ");
-			break;
-		default:
+					 "DISCSRVC ");
+		if (nrport->port_role & ~(FC_PORT_ROLE_NVME_INITIATOR |
+					  FC_PORT_ROLE_NVME_TARGET |
+					  FC_PORT_ROLE_NVME_DISCOVERY))
 			len +=  snprintf(buf + len, size - len,
 					 "UNKNOWN ROLE x%x",
 					 nrport->port_role);
-			break;
-		}
-
 		/* Terminate the string. */
 		len +=  snprintf(buf + len, size - len, "\n");
 	}
@@ -746,6 +750,7 @@ lpfc_debugfs_nvmestat_data(struct lpfc_vport *vport, char *buf, int size)
 	struct lpfc_hba   *phba = vport->phba;
 	struct lpfc_nvmet_tgtport *tgtp;
 	struct lpfc_nvmet_rcv_ctx *ctxp, *next_ctxp;
+	uint64_t tot, data1, data2, data3;
 	int len = 0;
 	int cnt;
 
@@ -843,11 +848,21 @@ lpfc_debugfs_nvmestat_data(struct lpfc_vport *vport, char *buf, int size)
 			spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
 		}
 
+		spin_lock(&phba->sli4_hba.nvmet_ctx_get_lock);
+		spin_lock(&phba->sli4_hba.nvmet_ctx_put_lock);
+		tot = phba->sli4_hba.nvmet_xri_cnt -
+			(phba->sli4_hba.nvmet_ctx_get_cnt +
+			phba->sli4_hba.nvmet_ctx_put_cnt);
+		spin_unlock(&phba->sli4_hba.nvmet_ctx_put_lock);
+		spin_unlock(&phba->sli4_hba.nvmet_ctx_get_lock);
+
 		len += snprintf(buf + len, size - len,
-				"IO_CTX: %08x  outstanding %08x total %08x\n",
-				phba->sli4_hba.nvmet_ctx_cnt,
+				"IO_CTX: %08x  WAIT: cur %08x tot %08x\n"
+				"CTX Outstanding %08llx\n",
+				phba->sli4_hba.nvmet_xri_cnt,
 				phba->sli4_hba.nvmet_io_wait_cnt,
-				phba->sli4_hba.nvmet_io_wait_total);
+				phba->sli4_hba.nvmet_io_wait_total,
+				tot);
 	} else {
 		if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
 			return len;
@@ -856,18 +871,22 @@ lpfc_debugfs_nvmestat_data(struct lpfc_vport *vport, char *buf, int size)
 				"\nNVME Lport Statistics\n");
 
 		len += snprintf(buf + len, size - len,
-				"LS: Xmt %016llx Cmpl %016llx\n",
-				phba->fc4NvmeLsRequests,
-				phba->fc4NvmeLsCmpls);
+				"LS: Xmt %016x Cmpl %016x\n",
+				atomic_read(&phba->fc4NvmeLsRequests),
+				atomic_read(&phba->fc4NvmeLsCmpls));
+
+		tot = atomic_read(&phba->fc4NvmeIoCmpls);
+		data1 = atomic_read(&phba->fc4NvmeInputRequests);
+		data2 = atomic_read(&phba->fc4NvmeOutputRequests);
+		data3 = atomic_read(&phba->fc4NvmeControlRequests);
 
 		len += snprintf(buf + len, size - len,
 				"FCP: Rd %016llx Wr %016llx IO %016llx\n",
-				phba->fc4NvmeInputRequests,
-				phba->fc4NvmeOutputRequests,
-				phba->fc4NvmeControlRequests);
+				data1, data2, data3);
 
 		len += snprintf(buf + len, size - len,
-				"    Cmpl %016llx\n", phba->fc4NvmeIoCmpls);
+				"    Cmpl %016llx Outstanding %016llx\n",
+				tot, (data1 + data2 + data3) - tot);
 	}
 
 	return len;
@@ -3229,9 +3248,9 @@ __lpfc_idiag_print_eq(struct lpfc_queue *qp, char *eqtype,
 
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
 			"\n%s EQ info: EQ-STAT[max:x%x noE:x%x "
-			"bs:x%x proc:x%llx]\n",
+			"bs:x%x proc:x%llx eqd %d]\n",
 			eqtype, qp->q_cnt_1, qp->q_cnt_2, qp->q_cnt_3,
-			(unsigned long long)qp->q_cnt_4);
+			(unsigned long long)qp->q_cnt_4, qp->q_mode);
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
 			"EQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
 			"HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]",

drivers/scsi/lpfc/lpfc_els.c

@@ -2168,6 +2168,19 @@ lpfc_issue_els_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 				 ndlp->nlp_fc4_type, ndlp->nlp_DID);
 		return 1;
 	}
+
+	/* SLI3 ports don't support NVME.  If this rport is a strict NVME
+	 * FC4 type, implicitly LOGO.
+	 */
+	if (phba->sli_rev == LPFC_SLI_REV3 &&
+	    ndlp->nlp_fc4_type == NLP_FC4_NVME) {
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY,
+				 "3088 Rport fc4 type 0x%x not supported by SLI3 adapter\n",
+				 ndlp->nlp_type);
+		lpfc_disc_state_machine(vport, ndlp, NULL, NLP_EVT_DEVICE_RM);
+		return 1;
+	}
+
 	elsiocb = lpfc_prep_els_iocb(vport, 1, cmdsize, retry, ndlp,
 				     ndlp->nlp_DID, elscmd);
 	if (!elsiocb)
@@ -2268,7 +2281,8 @@ lpfc_issue_els_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* The driver supports 2 FC4 types.  Make sure
 	 * a PRLI is issued for all types before exiting.
 	 */
-	if (local_nlp_type & (NLP_FC4_FCP | NLP_FC4_NVME))
+	if (phba->sli_rev == LPFC_SLI_REV4 &&
+	    local_nlp_type & (NLP_FC4_FCP | NLP_FC4_NVME))
 		goto send_next_prli;
 
 	return 0;
@@ -3332,6 +3346,19 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		 */
 		switch (stat.un.b.lsRjtRsnCode) {
 		case LSRJT_UNABLE_TPC:
+			/* The driver has a VALID PLOGI but the rport has
+			 * rejected the PRLI - can't do it now.  Delay
+			 * for 1 second and try again - don't care about
+			 * the explanation.
+			 */
+			if (cmd == ELS_CMD_PRLI || cmd == ELS_CMD_NVMEPRLI) {
+				delay = 1000;
+				maxretry = lpfc_max_els_tries + 1;
+				retry = 1;
+				break;
+			}
+
+			/* Legacy bug fix code for targets with PLOGI delays. */
 			if (stat.un.b.lsRjtRsnCodeExp ==
 			    LSEXP_CMD_IN_PROGRESS) {
 				if (cmd == ELS_CMD_PLOGI) {
@@ -3350,9 +3377,7 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 				retry = 1;
 				break;
 			}
-			if ((cmd == ELS_CMD_PLOGI) ||
-			    (cmd == ELS_CMD_PRLI) ||
-			    (cmd == ELS_CMD_NVMEPRLI)) {
+			if (cmd == ELS_CMD_PLOGI) {
 				delay = 1000;
 				maxretry = lpfc_max_els_tries + 1;
 				retry = 1;
@@ -5678,27 +5703,13 @@ lpfc_els_rcv_lcb(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 		rjt_err = LSRJT_CMD_UNSUPPORTED;
 		goto rjt;
 	}
-	if (beacon->lcb_frequency == 0) {
-		rjt_err = LSRJT_CMD_UNSUPPORTED;
-		goto rjt;
-	}
-	if ((beacon->lcb_type != LPFC_LCB_GREEN) &&
-	    (beacon->lcb_type != LPFC_LCB_AMBER)) {
-		rjt_err = LSRJT_CMD_UNSUPPORTED;
-		goto rjt;
-	}
-	if ((beacon->lcb_sub_command != LPFC_LCB_ON) &&
-	    (beacon->lcb_sub_command != LPFC_LCB_OFF)) {
-		rjt_err = LSRJT_CMD_UNSUPPORTED;
-		goto rjt;
-	}
-	if ((beacon->lcb_sub_command == LPFC_LCB_ON) &&
-	    (beacon->lcb_type != LPFC_LCB_GREEN) &&
-	    (beacon->lcb_type != LPFC_LCB_AMBER)) {
+	if (beacon->lcb_sub_command != LPFC_LCB_ON &&
+	    beacon->lcb_sub_command != LPFC_LCB_OFF) {
 		rjt_err = LSRJT_CMD_UNSUPPORTED;
 		goto rjt;
 	}
-	if (be16_to_cpu(beacon->lcb_duration) != 0) {
+	if (beacon->lcb_sub_command == LPFC_LCB_ON &&
+	    be16_to_cpu(beacon->lcb_duration) != 0) {
 		rjt_err = LSRJT_CMD_UNSUPPORTED;
 		goto rjt;
 	}

drivers/scsi/lpfc/lpfc_hbadisc.c

@@ -4167,14 +4167,14 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			lpfc_unregister_remote_port(ndlp);
 		}
 
-		/* Notify the NVME transport of this rport's loss on the
-		 * Initiator.  For NVME Target, should upcall transport
-		 * in the else clause when API available.
-		 */
 		if (ndlp->nlp_fc4_type & NLP_FC4_NVME) {
 			vport->phba->nport_event_cnt++;
 			if (vport->phba->nvmet_support == 0)
+				/* Start devloss */
 				lpfc_nvme_unregister_port(vport, ndlp);
+			else
+				/* NVMET has no upcall. */
+				lpfc_nlp_put(ndlp);
 		}
 	}
 
@@ -4182,8 +4182,10 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	if (new_state ==  NLP_STE_MAPPED_NODE ||
 	    new_state == NLP_STE_UNMAPPED_NODE) {
-		if ((ndlp->nlp_fc4_type & NLP_FC4_FCP) ||
-		    (ndlp->nlp_DID == Fabric_DID)) {
+		if (ndlp->nlp_fc4_type & NLP_FC4_FCP ||
+		    ndlp->nlp_DID == Fabric_DID ||
+		    ndlp->nlp_DID == NameServer_DID ||
+		    ndlp->nlp_DID == FDMI_DID) {
 			vport->phba->nport_event_cnt++;
 			/*
 			 * Tell the fc transport about the port, if we haven't
@@ -4192,7 +4194,8 @@ lpfc_nlp_state_cleanup(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			lpfc_register_remote_port(vport, ndlp);
 		}
 		/* Notify the NVME transport of this new rport. */
-		if (ndlp->nlp_fc4_type & NLP_FC4_NVME) {
+		if (vport->phba->sli_rev >= LPFC_SLI_REV4 &&
+		    ndlp->nlp_fc4_type & NLP_FC4_NVME) {
 			if (vport->phba->nvmet_support == 0) {
 				/* Register this rport with the transport.
 				 * Initiators take the NDLP ref count in

drivers/scsi/lpfc/lpfc_hw4.h

@@ -197,6 +197,7 @@ struct lpfc_sli_intf {
 
 /* Delay Multiplier constant */
 #define LPFC_DMULT_CONST       651042
+#define LPFC_DMULT_MAX         1023
 
 /* Configuration of Interrupts / sec for entire HBA port */
 #define LPFC_MIN_IMAX          5000
@@ -657,6 +658,15 @@ struct lpfc_register {
 #define LPFC_CTL_PORT_ER1_OFFSET	0x40C
 #define LPFC_CTL_PORT_ER2_OFFSET	0x410
 
+#define LPFC_CTL_PORT_EQ_DELAY_OFFSET	0x418
+#define lpfc_sliport_eqdelay_delay_SHIFT 16
+#define lpfc_sliport_eqdelay_delay_MASK	0xffff
+#define lpfc_sliport_eqdelay_delay_WORD	word0
+#define lpfc_sliport_eqdelay_id_SHIFT	0
+#define lpfc_sliport_eqdelay_id_MASK	0xfff
+#define lpfc_sliport_eqdelay_id_WORD	word0
+#define LPFC_SEC_TO_USEC		1000000
+
 /* The following Registers apply to SLI4 if_type 0 UCNAs. They typically
  * reside in BAR 2.
  */
@@ -3258,6 +3268,10 @@ struct lpfc_sli4_parameters {
 #define cfg_xib_SHIFT				4
 #define cfg_xib_MASK				0x00000001
 #define cfg_xib_WORD				word19
+#define cfg_eqdr_SHIFT				8
+#define cfg_eqdr_MASK				0x00000001
+#define cfg_eqdr_WORD				word19
+#define LPFC_NODELAY_MAX_IO		32
 };
 
 #define LPFC_SET_UE_RECOVERY		0x10

drivers/scsi/lpfc/lpfc_init.c

@@ -1249,6 +1249,12 @@ lpfc_hb_timeout_handler(struct lpfc_hba *phba)
 	int retval, i;
 	struct lpfc_sli *psli = &phba->sli;
 	LIST_HEAD(completions);
+	struct lpfc_queue *qp;
+	unsigned long time_elapsed;
+	uint32_t tick_cqe, max_cqe, val;
+	uint64_t tot, data1, data2, data3;
+	struct lpfc_register reg_data;
+	void __iomem *eqdreg = phba->sli4_hba.u.if_type2.EQDregaddr;
 
 	vports = lpfc_create_vport_work_array(phba);
 	if (vports != NULL)
@@ -1263,6 +1269,98 @@ lpfc_hb_timeout_handler(struct lpfc_hba *phba)
 		(phba->pport->fc_flag & FC_OFFLINE_MODE))
 		return;
 
+	if (phba->cfg_auto_imax) {
+		if (!phba->last_eqdelay_time) {
+			phba->last_eqdelay_time = jiffies;
+			goto skip_eqdelay;
+		}
+		time_elapsed = jiffies - phba->last_eqdelay_time;
+		phba->last_eqdelay_time = jiffies;
+
+		tot = 0xffff;
+		/* Check outstanding IO count */
+		if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
+			if (phba->nvmet_support) {
+				spin_lock(&phba->sli4_hba.nvmet_ctx_get_lock);
+				spin_lock(&phba->sli4_hba.nvmet_ctx_put_lock);
+				tot = phba->sli4_hba.nvmet_xri_cnt -
+					(phba->sli4_hba.nvmet_ctx_get_cnt +
+					phba->sli4_hba.nvmet_ctx_put_cnt);
+				spin_unlock(&phba->sli4_hba.nvmet_ctx_put_lock);
+				spin_unlock(&phba->sli4_hba.nvmet_ctx_get_lock);
+			} else {
+				tot = atomic_read(&phba->fc4NvmeIoCmpls);
+				data1 = atomic_read(
+					&phba->fc4NvmeInputRequests);
+				data2 = atomic_read(
+					&phba->fc4NvmeOutputRequests);
+				data3 = atomic_read(
+					&phba->fc4NvmeControlRequests);
+				tot =  (data1 + data2 + data3) - tot;
+			}
+		}
+
+		/* Interrupts per sec per EQ */
+		val = phba->cfg_fcp_imax / phba->io_channel_irqs;
+		tick_cqe = val / CONFIG_HZ; /* Per tick per EQ */
+
+		/* Assume 1 CQE/ISR, calc max CQEs allowed for time duration */
+		max_cqe = time_elapsed * tick_cqe;
+
+		for (i = 0; i < phba->io_channel_irqs; i++) {
+			/* Fast-path EQ */
+			qp = phba->sli4_hba.hba_eq[i];
+			if (!qp)
+				continue;
+
+			/* Use no EQ delay if we don't have many outstanding
+			 * IOs, or if we are only processing 1 CQE/ISR or less.
+			 * Otherwise, assume we can process up to lpfc_fcp_imax
+			 * interrupts per HBA.
+			 */
+			if (tot < LPFC_NODELAY_MAX_IO ||
+			    qp->EQ_cqe_cnt <= max_cqe)
+				val = 0;
+			else
+				val = phba->cfg_fcp_imax;
+
+			if (phba->sli.sli_flag & LPFC_SLI_USE_EQDR) {
+				/* Use EQ Delay Register method */
+
+				/* Convert for EQ Delay register */
+				if (val) {
+					/* First, interrupts per sec per EQ */
+					val = phba->cfg_fcp_imax /
+						phba->io_channel_irqs;
+
+					/* us delay between each interrupt */
+					val = LPFC_SEC_TO_USEC / val;
+				}
+				if (val != qp->q_mode) {
+					reg_data.word0 = 0;
+					bf_set(lpfc_sliport_eqdelay_id,
+					       &reg_data, qp->queue_id);
+					bf_set(lpfc_sliport_eqdelay_delay,
+					       &reg_data, val);
+					writel(reg_data.word0, eqdreg);
+				}
+			} else {
+				/* Use mbox command method */
+				if (val != qp->q_mode)
+					lpfc_modify_hba_eq_delay(phba, i,
+								 1, val);
+			}
+
+			/*
+			 * val is cfg_fcp_imax or 0 for mbox delay or us delay
+			 * between interrupts for EQDR.
+			 */
+			qp->q_mode = val;
+			qp->EQ_cqe_cnt = 0;
+		}
+	}
+
+skip_eqdelay:
 	spin_lock_irq(&phba->pport->work_port_lock);
 
 	if (time_after(phba->last_completion_time +
@@ -2707,13 +2805,6 @@ lpfc_cleanup(struct lpfc_vport *vport)
 			lpfc_disc_state_machine(vport, ndlp, NULL,
 					NLP_EVT_DEVICE_RECOVERY);
 
-		if (ndlp->nlp_fc4_type & NLP_FC4_NVME) {
-			/* Remove the NVME transport reference now and
-			 * continue to remove the node.
-			 */
-			lpfc_nlp_put(ndlp);
-		}
-
 		lpfc_disc_state_machine(vport, ndlp, NULL,
 					     NLP_EVT_DEVICE_RM);
 	}
@@ -3392,7 +3483,6 @@ lpfc_sli4_nvmet_sgl_update(struct lpfc_hba *phba)
 
 	/* For NVMET, ALL remaining XRIs are dedicated for IO processing */
 	nvmet_xri_cnt = phba->sli4_hba.max_cfg_param.max_xri - els_xri_cnt;
-
 	if (nvmet_xri_cnt > phba->sli4_hba.nvmet_xri_cnt) {
 		/* els xri-sgl expanded */
 		xri_cnt = nvmet_xri_cnt - phba->sli4_hba.nvmet_xri_cnt;
@@ -3596,14 +3686,6 @@ lpfc_get_wwpn(struct lpfc_hba *phba)
 	LPFC_MBOXQ_t *mboxq;
 	MAILBOX_t *mb;
 
-	if (phba->sli_rev < LPFC_SLI_REV4) {
-		/* Reset the port first */
-		lpfc_sli_brdrestart(phba);
-		rc = lpfc_sli_chipset_init(phba);
-		if (rc)
-			return (uint64_t)-1;
-	}
-
 	mboxq = (LPFC_MBOXQ_t *) mempool_alloc(phba->mbox_mem_pool,
 						GFP_KERNEL);
 	if (!mboxq)
@@ -3757,8 +3839,19 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev)
 	int i;
 	uint64_t wwn;
 	bool use_no_reset_hba = false;
+	int rc;
 
-	wwn = lpfc_get_wwpn(phba);
+	if (lpfc_no_hba_reset_cnt) {
+		if (phba->sli_rev < LPFC_SLI_REV4 &&
+		    dev == &phba->pcidev->dev) {
+			/* Reset the port first */
+			lpfc_sli_brdrestart(phba);
+			rc = lpfc_sli_chipset_init(phba);
+			if (rc)
+				return NULL;
+		}
+		wwn = lpfc_get_wwpn(phba);
+	}
 
 	for (i = 0; i < lpfc_no_hba_reset_cnt; i++) {
 		if (wwn == lpfc_no_hba_reset[i]) {
@@ -5837,7 +5930,8 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		spin_lock_init(&phba->sli4_hba.abts_nvme_buf_list_lock);
 		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvme_buf_list);
 		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
-		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_ctx_list);
+		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_ctx_get_list);
+		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_ctx_put_list);
 		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_io_wait_list);
 
 		/* Fast-path XRI aborted CQ Event work queue list */
@@ -5846,7 +5940,8 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 
 	/* This abort list used by worker thread */
 	spin_lock_init(&phba->sli4_hba.sgl_list_lock);
-	spin_lock_init(&phba->sli4_hba.nvmet_io_lock);
+	spin_lock_init(&phba->sli4_hba.nvmet_ctx_get_lock);
+	spin_lock_init(&phba->sli4_hba.nvmet_ctx_put_lock);
 	spin_lock_init(&phba->sli4_hba.nvmet_io_wait_lock);
 
 	/*
@@ -6731,6 +6826,16 @@ lpfc_create_shost(struct lpfc_hba *phba)
 	phba->fc_arbtov = FF_DEF_ARBTOV;
 
 	atomic_set(&phba->sdev_cnt, 0);
+	atomic_set(&phba->fc4ScsiInputRequests, 0);
+	atomic_set(&phba->fc4ScsiOutputRequests, 0);
+	atomic_set(&phba->fc4ScsiControlRequests, 0);
+	atomic_set(&phba->fc4ScsiIoCmpls, 0);
+	atomic_set(&phba->fc4NvmeInputRequests, 0);
+	atomic_set(&phba->fc4NvmeOutputRequests, 0);
+	atomic_set(&phba->fc4NvmeControlRequests, 0);
+	atomic_set(&phba->fc4NvmeIoCmpls, 0);
+	atomic_set(&phba->fc4NvmeLsRequests, 0);
+	atomic_set(&phba->fc4NvmeLsCmpls, 0);
 	vport = lpfc_create_port(phba, phba->brd_no, &phba->pcidev->dev);
 	if (!vport)
 		return -ENODEV;
@@ -7247,6 +7352,9 @@ lpfc_sli4_bar0_register_memmap(struct lpfc_hba *phba, uint32_t if_type)
 			phba->sli4_hba.conf_regs_memmap_p + LPFC_SLI_INTF;
 		break;
 	case LPFC_SLI_INTF_IF_TYPE_2:
+		phba->sli4_hba.u.if_type2.EQDregaddr =
+			phba->sli4_hba.conf_regs_memmap_p +
+						LPFC_CTL_PORT_EQ_DELAY_OFFSET;
 		phba->sli4_hba.u.if_type2.ERR1regaddr =
 			phba->sli4_hba.conf_regs_memmap_p +
 						LPFC_CTL_PORT_ER1_OFFSET;
@@ -8773,7 +8881,8 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 	}
 
 	for (qidx = 0; qidx < io_channel; qidx += LPFC_MAX_EQ_DELAY_EQID_CNT)
-		lpfc_modify_hba_eq_delay(phba, qidx);
+		lpfc_modify_hba_eq_delay(phba, qidx, LPFC_MAX_EQ_DELAY_EQID_CNT,
+					 phba->cfg_fcp_imax);
 
 	return 0;
 
@@ -9655,6 +9764,7 @@ static int
 lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 {
 	int vectors, rc, index;
+	char *name;
 
 	/* Set up MSI-X multi-message vectors */
 	vectors = phba->io_channel_irqs;
@@ -9673,9 +9783,9 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 
 	/* Assign MSI-X vectors to interrupt handlers */
 	for (index = 0; index < vectors; index++) {
-		memset(&phba->sli4_hba.handler_name[index], 0, 16);
-		snprintf((char *)&phba->sli4_hba.handler_name[index],
-			 LPFC_SLI4_HANDLER_NAME_SZ,
+		name = phba->sli4_hba.hba_eq_hdl[index].handler_name;
+		memset(name, 0, LPFC_SLI4_HANDLER_NAME_SZ);
+		snprintf(name, LPFC_SLI4_HANDLER_NAME_SZ,
 			 LPFC_DRIVER_HANDLER_NAME"%d", index);
 
 		phba->sli4_hba.hba_eq_hdl[index].idx = index;
@@ -9684,12 +9794,12 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba)
 		if (phba->cfg_fof && (index == (vectors - 1)))
 			rc = request_irq(pci_irq_vector(phba->pcidev, index),
 				 &lpfc_sli4_fof_intr_handler, 0,
-				 (char *)&phba->sli4_hba.handler_name[index],
+				 name,
 				 &phba->sli4_hba.hba_eq_hdl[index]);
 		else
 			rc = request_irq(pci_irq_vector(phba->pcidev, index),
 				 &lpfc_sli4_hba_intr_handler, 0,
-				 (char *)&phba->sli4_hba.handler_name[index],
+				 name,
 				 &phba->sli4_hba.hba_eq_hdl[index]);
 		if (rc) {
 			lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
@@ -10241,6 +10351,9 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 	if (bf_get(cfg_xib, mbx_sli4_parameters) && phba->cfg_suppress_rsp)
 		phba->sli.sli_flag |= LPFC_SLI_SUPPRESS_RSP;
 
+	if (bf_get(cfg_eqdr, mbx_sli4_parameters))
+		phba->sli.sli_flag |= LPFC_SLI_USE_EQDR;
+
 	/* Make sure that sge_supp_len can be handled by the driver */
 	if (sli4_params->sge_supp_len > LPFC_MAX_SGE_SIZE)
 		sli4_params->sge_supp_len = LPFC_MAX_SGE_SIZE;

drivers/scsi/lpfc/lpfc_nvme.c

@@ -186,13 +186,12 @@ lpfc_nvme_remoteport_delete(struct nvme_fc_remote_port *remoteport)
 
 	/* Remove this rport from the lport's list - memory is owned by the
 	 * transport. Remove the ndlp reference for the NVME transport before
-	 * calling state machine to remove the node, this is devloss = 0
-	 * semantics.
+	 * calling state machine to remove the node.
 	 */
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
 			"6146 remoteport delete complete %p\n",
 			remoteport);
-	list_del(&rport->list);
+	ndlp->nrport = NULL;
 	lpfc_nlp_put(ndlp);
 
  rport_err:
@@ -212,7 +211,7 @@ lpfc_nvme_cmpl_gen_req(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	struct lpfc_dmabuf *buf_ptr;
 	struct lpfc_nodelist *ndlp;
 
-	vport->phba->fc4NvmeLsCmpls++;
+	atomic_inc(&vport->phba->fc4NvmeLsCmpls);
 
 	pnvme_lsreq = (struct nvmefc_ls_req *)cmdwqe->context2;
 	status = bf_get(lpfc_wcqe_c_status, wcqe) & LPFC_IOCB_STATUS_MASK;
@@ -479,7 +478,7 @@ lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport,
 			 pnvme_lsreq->rsplen, &pnvme_lsreq->rqstdma,
 			 &pnvme_lsreq->rspdma);
 
-	vport->phba->fc4NvmeLsRequests++;
+	atomic_inc(&vport->phba->fc4NvmeLsRequests);
 
 	/* Hardcode the wait to 30 seconds.  Connections are failing otherwise.
 	 * This code allows it all to work.
@@ -774,7 +773,7 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 				 wcqe);
 		return;
 	}
-	phba->fc4NvmeIoCmpls++;
+	atomic_inc(&phba->fc4NvmeIoCmpls);
 
 	nCmd = lpfc_ncmd->nvmeCmd;
 	rport = lpfc_ncmd->nrport;
@@ -999,7 +998,7 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
 			bf_set(wqe_cmd_type, &wqe->generic.wqe_com,
 			       NVME_WRITE_CMD);
 
-			phba->fc4NvmeOutputRequests++;
+			atomic_inc(&phba->fc4NvmeOutputRequests);
 		} else {
 			/* Word 7 */
 			bf_set(wqe_cmnd, &wqe->generic.wqe_com,
@@ -1020,7 +1019,7 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
 			bf_set(wqe_cmd_type, &wqe->generic.wqe_com,
 			       NVME_READ_CMD);
 
-			phba->fc4NvmeInputRequests++;
+			atomic_inc(&phba->fc4NvmeInputRequests);
 		}
 	} else {
 		/* Word 4 */
@@ -1041,7 +1040,7 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
 		/* Word 11 */
 		bf_set(wqe_cmd_type, &wqe->generic.wqe_com, NVME_READ_CMD);
 
-		phba->fc4NvmeControlRequests++;
+		atomic_inc(&phba->fc4NvmeControlRequests);
 	}
 	/*
 	 * Finish initializing those WQE fields that are independent
@@ -1362,6 +1361,13 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 	return 0;
 
  out_free_nvme_buf:
+	if (lpfc_ncmd->nvmeCmd->sg_cnt) {
+		if (lpfc_ncmd->nvmeCmd->io_dir == NVMEFC_FCP_WRITE)
+			atomic_dec(&phba->fc4NvmeOutputRequests);
+		else
+			atomic_dec(&phba->fc4NvmeInputRequests);
+	} else
+		atomic_dec(&phba->fc4NvmeControlRequests);
 	lpfc_release_nvme_buf(phba, lpfc_ncmd);
  out_fail:
 	return ret;
@@ -1421,7 +1427,6 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 	struct lpfc_nvme_lport *lport;
 	struct lpfc_vport *vport;
 	struct lpfc_hba *phba;
-	struct lpfc_nodelist *ndlp;
 	struct lpfc_nvme_rport *rport;
 	struct lpfc_nvme_buf *lpfc_nbuf;
 	struct lpfc_iocbq *abts_buf;
@@ -1443,38 +1448,6 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 			 pnvme_rport->port_id,
 			 pnvme_fcreq);
 
-	/*
-	 * Catch race where our node has transitioned, but the
-	 * transport is still transitioning.
-	 */
-	ndlp = rport->ndlp;
-	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) {
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_ABTS,
-				 "6054 rport %p, ndlp %p, DID x%06x ndlp "
-				 " not ready.\n",
-				 rport, ndlp, pnvme_rport->port_id);
-
-		ndlp = lpfc_findnode_did(vport, pnvme_rport->port_id);
-		if (!ndlp) {
-			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
-					 "6055 Could not find node for "
-					 "DID %x\n",
-					 pnvme_rport->port_id);
-			return;
-		}
-	}
-
-	/* The remote node has to be ready to send an abort. */
-	if ((ndlp->nlp_state != NLP_STE_MAPPED_NODE) &&
-	    !(ndlp->nlp_type & NLP_NVME_TARGET)) {
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
-				 "6048 rport %p, DID x%06x not ready for "
-				 "IO. State x%x, Type x%x\n",
-				 rport, pnvme_rport->port_id,
-				 ndlp->nlp_state, ndlp->nlp_type);
-		return;
-	}
-
 	/* If the hba is getting reset, this flag is set.  It is
 	 * cleared when the reset is complete and rings reestablished.
 	 */
@@ -1535,7 +1508,7 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
 
 	lpfc_nvmeio_data(phba, "NVME FCP ABORT: xri x%x idx %d to %06x\n",
 			 nvmereq_wqe->sli4_xritag,
-			 nvmereq_wqe->hba_wqidx, ndlp->nlp_DID);
+			 nvmereq_wqe->hba_wqidx, pnvme_rport->port_id);
 
 	/* Outstanding abort is in progress */
 	if (nvmereq_wqe->iocb_flag & LPFC_DRIVER_ABORTED) {
@@ -2208,7 +2181,6 @@ lpfc_nvme_create_localport(struct lpfc_vport *vport)
 		lport = (struct lpfc_nvme_lport *)localport->private;
 		vport->localport = localport;
 		lport->vport = vport;
-		INIT_LIST_HEAD(&lport->rport_list);
 		vport->nvmei_support = 1;
 		len  = lpfc_new_nvme_buf(vport, phba->sli4_hba.nvme_xri_max);
 		vport->phba->total_nvme_bufs += len;
@@ -2233,7 +2205,6 @@ lpfc_nvme_destroy_localport(struct lpfc_vport *vport)
 #if (IS_ENABLED(CONFIG_NVME_FC))
 	struct nvme_fc_local_port *localport;
 	struct lpfc_nvme_lport *lport;
-	struct lpfc_nvme_rport *rport = NULL, *rport_next = NULL;
 	int ret;
 
 	if (vport->nvmei_support == 0)
@@ -2246,19 +2217,6 @@ lpfc_nvme_destroy_localport(struct lpfc_vport *vport)
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME,
 			 "6011 Destroying NVME localport %p\n",
 			 localport);
-	list_for_each_entry_safe(rport, rport_next, &lport->rport_list, list) {
-		/* The last node ref has to get released now before the rport
-		 * private memory area is released by the transport.
-		 */
-		list_del(&rport->list);
-
-		init_completion(&rport->rport_unreg_done);
-		ret = nvme_fc_unregister_remoteport(rport->remoteport);
-		if (ret)
-			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
-					 "6008 rport fail destroy %x\n", ret);
-		wait_for_completion_timeout(&rport->rport_unreg_done, 5);
-	}
 
 	/* lport's rport list is clear.  Unregister
 	 * lport and release resources.
@@ -2340,99 +2298,68 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	localport = vport->localport;
 	lport = (struct lpfc_nvme_lport *)localport->private;
 
-	if (ndlp->nlp_type & (NLP_NVME_TARGET | NLP_NVME_INITIATOR)) {
-
-		/* The driver isn't expecting the rport wwn to change
-		 * but it might get a different DID on a different
-		 * fabric.
+	/* NVME rports are not preserved across devloss.
+	 * Just register this instance.  Note, rpinfo->dev_loss_tmo
+	 * is left 0 to indicate accept transport defaults.  The
+	 * driver communicates port role capabilities consistent
+	 * with the PRLI response data.
+	 */
+	memset(&rpinfo, 0, sizeof(struct nvme_fc_port_info));
+	rpinfo.port_id = ndlp->nlp_DID;
+	if (ndlp->nlp_type & NLP_NVME_TARGET)
+		rpinfo.port_role |= FC_PORT_ROLE_NVME_TARGET;
+	if (ndlp->nlp_type & NLP_NVME_INITIATOR)
+		rpinfo.port_role |= FC_PORT_ROLE_NVME_INITIATOR;
+
+	if (ndlp->nlp_type & NLP_NVME_DISCOVERY)
+		rpinfo.port_role |= FC_PORT_ROLE_NVME_DISCOVERY;
+
+	rpinfo.port_name = wwn_to_u64(ndlp->nlp_portname.u.wwn);
+	rpinfo.node_name = wwn_to_u64(ndlp->nlp_nodename.u.wwn);
+	ret = nvme_fc_register_remoteport(localport, &rpinfo, &remote_port);
+	if (!ret) {
+		/* If the ndlp already has an nrport, this is just
+		 * a resume of the existing rport.  Else this is a
+		 * new rport.
 		 */
-		list_for_each_entry(rport, &lport->rport_list, list) {
-			if (rport->remoteport->port_name !=
-			    wwn_to_u64(ndlp->nlp_portname.u.wwn))
-				continue;
-			lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NVME_DISC,
-					 "6035 lport %p, found matching rport "
-					 "at wwpn 0x%llx, Data: x%x x%x x%x "
-					 "x%06x\n",
-					 lport,
-					 rport->remoteport->port_name,
-					 rport->remoteport->port_id,
-					 rport->remoteport->port_role,
+		rport = remote_port->private;
+		if (ndlp->nrport == rport) {
+			lpfc_printf_vlog(ndlp->vport, KERN_INFO,
+					 LOG_NVME_DISC,
+					 "6014 Rebinding lport to "
+					 "rport wwpn 0x%llx, "
+					 "Data: x%x x%x x%x x%06x\n",
+					 remote_port->port_name,
+					 remote_port->port_id,
+					 remote_port->port_role,
 					 ndlp->nlp_type,
 					 ndlp->nlp_DID);
-			remote_port = rport->remoteport;
-			if ((remote_port->port_id == 0) &&
-			    (remote_port->port_role ==
-			     FC_PORT_ROLE_NVME_DISCOVERY)) {
-				remote_port->port_id = ndlp->nlp_DID;
-				remote_port->port_role &=
-					~FC_PORT_ROLE_NVME_DISCOVERY;
-				if (ndlp->nlp_type & NLP_NVME_TARGET)
-					remote_port->port_role |=
-						FC_PORT_ROLE_NVME_TARGET;
-				if (ndlp->nlp_type & NLP_NVME_INITIATOR)
-					remote_port->port_role |=
-						FC_PORT_ROLE_NVME_INITIATOR;
-
-				lpfc_printf_vlog(ndlp->vport, KERN_INFO,
-						 LOG_NVME_DISC,
-						 "6014 Rebinding lport to "
-						 "rport wwpn 0x%llx, "
-						 "Data: x%x x%x x%x x%06x\n",
-						 remote_port->port_name,
-						 remote_port->port_id,
-						 remote_port->port_role,
-						 ndlp->nlp_type,
-						 ndlp->nlp_DID);
-			}
-			return 0;
-		}
-
-		/* NVME rports are not preserved across devloss.
-		 * Just register this instance.
-		 */
-		rpinfo.port_id = ndlp->nlp_DID;
-		rpinfo.port_role = 0;
-		if (ndlp->nlp_type & NLP_NVME_TARGET)
-			rpinfo.port_role |= FC_PORT_ROLE_NVME_TARGET;
-		if (ndlp->nlp_type & NLP_NVME_INITIATOR)
-			rpinfo.port_role |= FC_PORT_ROLE_NVME_INITIATOR;
-		rpinfo.port_name = wwn_to_u64(ndlp->nlp_portname.u.wwn);
-		rpinfo.node_name = wwn_to_u64(ndlp->nlp_nodename.u.wwn);
-		ret = nvme_fc_register_remoteport(localport, &rpinfo,
-						  &remote_port);
-		if (!ret) {
-			rport = remote_port->private;
+		} else {
+			/* New rport. */
 			rport->remoteport = remote_port;
 			rport->lport = lport;
 			rport->ndlp = lpfc_nlp_get(ndlp);
 			if (!rport->ndlp)
 				return -1;
 			ndlp->nrport = rport;
-			INIT_LIST_HEAD(&rport->list);
-			list_add_tail(&rport->list, &lport->rport_list);
 			lpfc_printf_vlog(vport, KERN_INFO,
 					 LOG_NVME_DISC | LOG_NODE,
-					 "6022 Binding new rport to lport %p "
-					 "Rport WWNN 0x%llx, Rport WWPN 0x%llx "
-					 "DID x%06x Role x%x\n",
+					 "6022 Binding new rport to "
+					 "lport %p Rport WWNN 0x%llx, "
+					 "Rport WWPN 0x%llx DID "
+					 "x%06x Role x%x\n",
 					 lport,
 					 rpinfo.node_name, rpinfo.port_name,
 					 rpinfo.port_id, rpinfo.port_role);
-		} else {
-			lpfc_printf_vlog(vport, KERN_ERR,
-					 LOG_NVME_DISC | LOG_NODE,
-					 "6031 RemotePort Registration failed "
-					 "err: %d, DID x%06x\n",
-					 ret, ndlp->nlp_DID);
 		}
 	} else {
-		ret = -EINVAL;
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
-				 "6027 Unknown nlp_type x%x on DID x%06x "
-				 "ndlp %p.  Not Registering nvme rport\n",
-				 ndlp->nlp_type, ndlp->nlp_DID, ndlp);
+		lpfc_printf_vlog(vport, KERN_ERR,
+				 LOG_NVME_DISC | LOG_NODE,
+				 "6031 RemotePort Registration failed "
+				 "err: %d, DID x%06x\n",
+				 ret, ndlp->nlp_DID);
 	}
+
 	return ret;
 #else
 	return 0;
@@ -2460,7 +2387,6 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	struct lpfc_nvme_lport *lport;
 	struct lpfc_nvme_rport *rport;
 	struct nvme_fc_remote_port *remoteport;
-	unsigned long wait_tmo;
 
 	localport = vport->localport;
 
@@ -2491,6 +2417,10 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	 */
 	if (ndlp->nlp_type & (NLP_NVME_TARGET | NLP_NVME_INITIATOR)) {
 		init_completion(&rport->rport_unreg_done);
+
+		/* No concern about the role change on the nvme remoteport.
+		 * The transport will update it.
+		 */
 		ret = nvme_fc_unregister_remoteport(remoteport);
 		if (ret != 0) {
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
@@ -2499,17 +2429,6 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 					 ret, remoteport->port_state);
 		}
 
-		/* Wait for the driver's delete completion routine to finish
-		 * before proceeding.  This guarantees the transport and driver
-		 * have completed the unreg process.
-		 */
-		wait_tmo = msecs_to_jiffies(5000);
-		ret = wait_for_completion_timeout(&rport->rport_unreg_done,
-						  wait_tmo);
-		if (ret == 0) {
-			lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
-					 "6169 Unreg nvme wait timeout\n");
-		}
 	}
 	return;
 

drivers/scsi/lpfc/lpfc_nvme.h

@@ -35,13 +35,11 @@ struct lpfc_nvme_qhandle {
 /* Declare nvme-based local and remote port definitions. */
 struct lpfc_nvme_lport {
 	struct lpfc_vport *vport;
-	struct list_head rport_list;
 	struct completion lport_unreg_done;
 	/* Add sttats counters here */
 };
 
 struct lpfc_nvme_rport {
-	struct list_head list;
 	struct lpfc_nvme_lport *lport;
 	struct nvme_fc_remote_port *remoteport;
 	struct lpfc_nodelist *ndlp;

drivers/scsi/lpfc/lpfc_nvmet.c

@@ -112,6 +112,15 @@ lpfc_nvmet_xmt_ls_rsp_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 
 	status = bf_get(lpfc_wcqe_c_status, wcqe);
 	result = wcqe->parameter;
+	ctxp = cmdwqe->context2;
+
+	if (ctxp->state != LPFC_NVMET_STE_LS_RSP || ctxp->entry_cnt != 2) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6410 NVMET LS cmpl state mismatch IO x%x: "
+				"%d %d\n",
+				ctxp->oxid, ctxp->state, ctxp->entry_cnt);
+	}
+
 	if (!phba->targetport)
 		goto out;
 
@@ -123,15 +132,14 @@ lpfc_nvmet_xmt_ls_rsp_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 		atomic_inc(&tgtp->xmt_ls_rsp_cmpl);
 
 out:
-	ctxp = cmdwqe->context2;
 	rsp = &ctxp->ctx.ls_req;
 
 	lpfc_nvmeio_data(phba, "NVMET LS  CMPL: xri x%x stat x%x result x%x\n",
 			 ctxp->oxid, status, result);
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_DISC,
-			"6038 %s: Entrypoint: ctx %p status %x/%x\n", __func__,
-			ctxp, status, result);
+			"6038 NVMET LS rsp cmpl: %d %d oxid x%x\n",
+			status, result, ctxp->oxid);
 
 	lpfc_nlp_put(cmdwqe->context1);
 	cmdwqe->context2 = NULL;
@@ -162,7 +170,6 @@ lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba, struct lpfc_nvmet_ctxbuf *ctx_buf)
 	struct lpfc_nvmet_tgtport *tgtp;
 	struct fc_frame_header *fc_hdr;
 	struct rqb_dmabuf *nvmebuf;
-	struct lpfc_dmabuf *hbufp;
 	uint32_t *payload;
 	uint32_t size, oxid, sid, rc;
 	unsigned long iflag;
@@ -173,11 +180,16 @@ lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba, struct lpfc_nvmet_ctxbuf *ctx_buf)
 		ctxp->txrdy = NULL;
 		ctxp->txrdy_phys = 0;
 	}
+
+	if (ctxp->state == LPFC_NVMET_STE_FREE) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6411 NVMET free, already free IO x%x: %d %d\n",
+				ctxp->oxid, ctxp->state, ctxp->entry_cnt);
+	}
 	ctxp->state = LPFC_NVMET_STE_FREE;
 
 	spin_lock_irqsave(&phba->sli4_hba.nvmet_io_wait_lock, iflag);
 	if (phba->sli4_hba.nvmet_io_wait_cnt) {
-		hbufp = &nvmebuf->hbuf;
 		list_remove_head(&phba->sli4_hba.lpfc_nvmet_io_wait_list,
 				 nvmebuf, struct rqb_dmabuf,
 				 hbuf.list);
@@ -193,7 +205,6 @@ lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba, struct lpfc_nvmet_ctxbuf *ctx_buf)
 		sid = sli4_sid_from_fc_hdr(fc_hdr);
 
 		ctxp = (struct lpfc_nvmet_rcv_ctx *)ctx_buf->context;
-		memset(ctxp, 0, sizeof(ctxp->ctx));
 		ctxp->wqeq = NULL;
 		ctxp->txrdy = NULL;
 		ctxp->offset = 0;
@@ -256,11 +267,11 @@ lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba, struct lpfc_nvmet_ctxbuf *ctx_buf)
 	}
 	spin_unlock_irqrestore(&phba->sli4_hba.nvmet_io_wait_lock, iflag);
 
-	spin_lock_irqsave(&phba->sli4_hba.nvmet_io_lock, iflag);
+	spin_lock_irqsave(&phba->sli4_hba.nvmet_ctx_put_lock, iflag);
 	list_add_tail(&ctx_buf->list,
-		      &phba->sli4_hba.lpfc_nvmet_ctx_list);
-	phba->sli4_hba.nvmet_ctx_cnt++;
-	spin_unlock_irqrestore(&phba->sli4_hba.nvmet_io_lock, iflag);
+		      &phba->sli4_hba.lpfc_nvmet_ctx_put_list);
+	phba->sli4_hba.nvmet_ctx_put_cnt++;
+	spin_unlock_irqrestore(&phba->sli4_hba.nvmet_ctx_put_lock, iflag);
 #endif
 }
 
@@ -580,8 +591,17 @@ lpfc_nvmet_xmt_ls_rsp(struct nvmet_fc_target_port *tgtport,
 	int rc;
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_DISC,
-			"6023 %s: Entrypoint ctx %p %p\n", __func__,
-			ctxp, tgtport);
+			"6023 NVMET LS rsp oxid x%x\n", ctxp->oxid);
+
+	if ((ctxp->state != LPFC_NVMET_STE_LS_RCV) ||
+	    (ctxp->entry_cnt != 1)) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6412 NVMET LS rsp state mismatch "
+				"oxid x%x: %d %d\n",
+				ctxp->oxid, ctxp->state, ctxp->entry_cnt);
+	}
+	ctxp->state = LPFC_NVMET_STE_LS_RSP;
+	ctxp->entry_cnt++;
 
 	nvmewqeq = lpfc_nvmet_prep_ls_wqe(phba, ctxp, rsp->rspdma,
 				      rsp->rsplen);
@@ -751,15 +771,14 @@ lpfc_nvmet_xmt_fcp_abort(struct nvmet_fc_target_port *tgtport,
 	unsigned long flags;
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
-			"6103 Abort op: oxri x%x flg x%x cnt %d\n",
-			ctxp->oxid, ctxp->flag, ctxp->entry_cnt);
+			"6103 NVMET Abort op: oxri x%x flg x%x ste %d\n",
+			ctxp->oxid, ctxp->flag, ctxp->state);
 
-	lpfc_nvmeio_data(phba, "NVMET FCP ABRT: "
-			 "xri x%x flg x%x cnt x%x\n",
-			 ctxp->oxid, ctxp->flag, ctxp->entry_cnt);
+	lpfc_nvmeio_data(phba, "NVMET FCP ABRT: xri x%x flg x%x ste x%x\n",
+			 ctxp->oxid, ctxp->flag, ctxp->state);
 
 	atomic_inc(&lpfc_nvmep->xmt_fcp_abort);
-	ctxp->entry_cnt++;
+
 	spin_lock_irqsave(&ctxp->ctxlock, flags);
 
 	/* Since iaab/iaar are NOT set, we need to check
@@ -770,12 +789,17 @@ lpfc_nvmet_xmt_fcp_abort(struct nvmet_fc_target_port *tgtport,
 		return;
 	}
 	ctxp->flag |= LPFC_NVMET_ABORT_OP;
-	if (ctxp->flag & LPFC_NVMET_IO_INP)
-		lpfc_nvmet_sol_fcp_issue_abort(phba, ctxp, ctxp->sid,
-					       ctxp->oxid);
-	else
+
+	/* An state of LPFC_NVMET_STE_RCV means we have just received
+	 * the NVME command and have not started processing it.
+	 * (by issuing any IO WQEs on this exchange yet)
+	 */
+	if (ctxp->state == LPFC_NVMET_STE_RCV)
 		lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, ctxp->sid,
 						 ctxp->oxid);
+	else
+		lpfc_nvmet_sol_fcp_issue_abort(phba, ctxp, ctxp->sid,
+					       ctxp->oxid);
 	spin_unlock_irqrestore(&ctxp->ctxlock, flags);
 }
 
@@ -790,6 +814,13 @@ lpfc_nvmet_xmt_fcp_release(struct nvmet_fc_target_port *tgtport,
 	unsigned long flags;
 	bool aborting = false;
 
+	if (ctxp->state != LPFC_NVMET_STE_DONE &&
+	    ctxp->state != LPFC_NVMET_STE_ABORT) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6413 NVMET release bad state %d %d oxid x%x\n",
+				ctxp->state, ctxp->entry_cnt, ctxp->oxid);
+	}
+
 	spin_lock_irqsave(&ctxp->ctxlock, flags);
 	if ((ctxp->flag & LPFC_NVMET_ABORT_OP) ||
 	    (ctxp->flag & LPFC_NVMET_XBUSY)) {
@@ -828,37 +859,55 @@ static struct nvmet_fc_target_template lpfc_tgttemplate = {
 	.target_priv_sz = sizeof(struct lpfc_nvmet_tgtport),
 };
 
-void
+static void
 lpfc_nvmet_cleanup_io_context(struct lpfc_hba *phba)
 {
 	struct lpfc_nvmet_ctxbuf *ctx_buf, *next_ctx_buf;
 	unsigned long flags;
 
-	list_for_each_entry_safe(
-		ctx_buf, next_ctx_buf,
-		&phba->sli4_hba.lpfc_nvmet_ctx_list, list) {
-		spin_lock_irqsave(
-			&phba->sli4_hba.abts_nvme_buf_list_lock, flags);
+	spin_lock_irqsave(&phba->sli4_hba.nvmet_ctx_get_lock, flags);
+	spin_lock(&phba->sli4_hba.nvmet_ctx_put_lock);
+	list_for_each_entry_safe(ctx_buf, next_ctx_buf,
+			&phba->sli4_hba.lpfc_nvmet_ctx_get_list, list) {
+		spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+		list_del_init(&ctx_buf->list);
+		spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+		__lpfc_clear_active_sglq(phba,
+					 ctx_buf->sglq->sli4_lxritag);
+		ctx_buf->sglq->state = SGL_FREED;
+		ctx_buf->sglq->ndlp = NULL;
+
+		spin_lock(&phba->sli4_hba.sgl_list_lock);
+		list_add_tail(&ctx_buf->sglq->list,
+			      &phba->sli4_hba.lpfc_nvmet_sgl_list);
+		spin_unlock(&phba->sli4_hba.sgl_list_lock);
+
+		lpfc_sli_release_iocbq(phba, ctx_buf->iocbq);
+		kfree(ctx_buf->context);
+	}
+	list_for_each_entry_safe(ctx_buf, next_ctx_buf,
+			&phba->sli4_hba.lpfc_nvmet_ctx_put_list, list) {
+		spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
 		list_del_init(&ctx_buf->list);
-		spin_unlock_irqrestore(
-			&phba->sli4_hba.abts_nvme_buf_list_lock, flags);
+		spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
 		__lpfc_clear_active_sglq(phba,
 					 ctx_buf->sglq->sli4_lxritag);
 		ctx_buf->sglq->state = SGL_FREED;
 		ctx_buf->sglq->ndlp = NULL;
 
-		spin_lock_irqsave(&phba->sli4_hba.sgl_list_lock, flags);
+		spin_lock(&phba->sli4_hba.sgl_list_lock);
 		list_add_tail(&ctx_buf->sglq->list,
 			      &phba->sli4_hba.lpfc_nvmet_sgl_list);
-		spin_unlock_irqrestore(&phba->sli4_hba.sgl_list_lock,
-				       flags);
+		spin_unlock(&phba->sli4_hba.sgl_list_lock);
 
 		lpfc_sli_release_iocbq(phba, ctx_buf->iocbq);
 		kfree(ctx_buf->context);
 	}
+	spin_unlock(&phba->sli4_hba.nvmet_ctx_put_lock);
+	spin_unlock_irqrestore(&phba->sli4_hba.nvmet_ctx_get_lock, flags);
 }
 
-int
+static int
 lpfc_nvmet_setup_io_context(struct lpfc_hba *phba)
 {
 	struct lpfc_nvmet_ctxbuf *ctx_buf;
@@ -891,6 +940,7 @@ lpfc_nvmet_setup_io_context(struct lpfc_hba *phba)
 			return -ENOMEM;
 		}
 		ctx_buf->context->ctxbuf = ctx_buf;
+		ctx_buf->context->state = LPFC_NVMET_STE_FREE;
 
 		ctx_buf->iocbq = lpfc_sli_get_iocbq(phba);
 		if (!ctx_buf->iocbq) {
@@ -926,12 +976,12 @@ lpfc_nvmet_setup_io_context(struct lpfc_hba *phba)
 					"6407 Ran out of NVMET XRIs\n");
 			return -ENOMEM;
 		}
-		spin_lock(&phba->sli4_hba.nvmet_io_lock);
+		spin_lock(&phba->sli4_hba.nvmet_ctx_get_lock);
 		list_add_tail(&ctx_buf->list,
-			      &phba->sli4_hba.lpfc_nvmet_ctx_list);
-		spin_unlock(&phba->sli4_hba.nvmet_io_lock);
+			      &phba->sli4_hba.lpfc_nvmet_ctx_get_list);
+		spin_unlock(&phba->sli4_hba.nvmet_ctx_get_lock);
 	}
-	phba->sli4_hba.nvmet_ctx_cnt = phba->sli4_hba.nvmet_xri_cnt;
+	phba->sli4_hba.nvmet_ctx_get_cnt = phba->sli4_hba.nvmet_xri_cnt;
 	return 0;
 }
 
@@ -1103,7 +1153,7 @@ lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba,
 		}
 
 		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
-				"6318 XB aborted %x flg x%x (%x)\n",
+				"6318 XB aborted oxid %x flg x%x (%x)\n",
 				ctxp->oxid, ctxp->flag, released);
 		if (released)
 			lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
@@ -1253,7 +1303,8 @@ dropit:
 	ctxp->oxid = oxid;
 	ctxp->sid = sid;
 	ctxp->wqeq = NULL;
-	ctxp->state = LPFC_NVMET_STE_RCV;
+	ctxp->state = LPFC_NVMET_STE_LS_RCV;
+	ctxp->entry_cnt = 1;
 	ctxp->rqb_buffer = (void *)nvmebuf;
 
 	lpfc_nvmeio_data(phba, "NVMET LS   RCV: xri x%x sz %d from %06x\n",
@@ -1268,8 +1319,8 @@ dropit:
 				 payload, size);
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_DISC,
-			"6037 %s: ctx %p sz %d rc %d: %08x %08x %08x "
-			"%08x %08x %08x\n", __func__, ctxp, size, rc,
+			"6037 NVMET Unsol rcv: sz %d rc %d: %08x %08x %08x "
+			"%08x %08x %08x\n", size, rc,
 			*payload, *(payload+1), *(payload+2),
 			*(payload+3), *(payload+4), *(payload+5));
 
@@ -1337,13 +1388,31 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 		goto dropit;
 	}
 
-	spin_lock_irqsave(&phba->sli4_hba.nvmet_io_lock, iflag);
-	if (phba->sli4_hba.nvmet_ctx_cnt) {
-		list_remove_head(&phba->sli4_hba.lpfc_nvmet_ctx_list,
+	spin_lock_irqsave(&phba->sli4_hba.nvmet_ctx_get_lock, iflag);
+	if (phba->sli4_hba.nvmet_ctx_get_cnt) {
+		list_remove_head(&phba->sli4_hba.lpfc_nvmet_ctx_get_list,
 				 ctx_buf, struct lpfc_nvmet_ctxbuf, list);
-		phba->sli4_hba.nvmet_ctx_cnt--;
+		phba->sli4_hba.nvmet_ctx_get_cnt--;
+	} else {
+		spin_lock(&phba->sli4_hba.nvmet_ctx_put_lock);
+		if (phba->sli4_hba.nvmet_ctx_put_cnt) {
+			list_splice(&phba->sli4_hba.lpfc_nvmet_ctx_put_list,
+				    &phba->sli4_hba.lpfc_nvmet_ctx_get_list);
+			INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_ctx_put_list);
+			phba->sli4_hba.nvmet_ctx_get_cnt =
+				phba->sli4_hba.nvmet_ctx_put_cnt;
+			phba->sli4_hba.nvmet_ctx_put_cnt = 0;
+			spin_unlock(&phba->sli4_hba.nvmet_ctx_put_lock);
+
+			list_remove_head(
+				&phba->sli4_hba.lpfc_nvmet_ctx_get_list,
+				ctx_buf, struct lpfc_nvmet_ctxbuf, list);
+			phba->sli4_hba.nvmet_ctx_get_cnt--;
+		} else {
+			spin_unlock(&phba->sli4_hba.nvmet_ctx_put_lock);
+		}
 	}
-	spin_unlock_irqrestore(&phba->sli4_hba.nvmet_io_lock, iflag);
+	spin_unlock_irqrestore(&phba->sli4_hba.nvmet_ctx_get_lock, iflag);
 
 	fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
 	oxid = be16_to_cpu(fc_hdr->fh_ox_id);
@@ -1383,7 +1452,11 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 	sid = sli4_sid_from_fc_hdr(fc_hdr);
 
 	ctxp = (struct lpfc_nvmet_rcv_ctx *)ctx_buf->context;
-	memset(ctxp, 0, sizeof(ctxp->ctx));
+	if (ctxp->state != LPFC_NVMET_STE_FREE) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6414 NVMET Context corrupt %d %d oxid x%x\n",
+				ctxp->state, ctxp->entry_cnt, ctxp->oxid);
+	}
 	ctxp->wqeq = NULL;
 	ctxp->txrdy = NULL;
 	ctxp->offset = 0;
@@ -1547,9 +1620,9 @@ lpfc_nvmet_prep_ls_wqe(struct lpfc_hba *phba,
 
 	if (!lpfc_is_link_up(phba)) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
-				"6104 lpfc_nvmet_prep_ls_wqe: link err: "
-				"NPORT x%x oxid:x%x\n",
-				ctxp->sid, ctxp->oxid);
+				"6104 NVMET prep LS wqe: link err: "
+				"NPORT x%x oxid:x%x ste %d\n",
+				ctxp->sid, ctxp->oxid, ctxp->state);
 		return NULL;
 	}
 
@@ -1557,9 +1630,9 @@ lpfc_nvmet_prep_ls_wqe(struct lpfc_hba *phba,
 	nvmewqe = lpfc_sli_get_iocbq(phba);
 	if (nvmewqe == NULL) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
-				"6105 lpfc_nvmet_prep_ls_wqe: No WQE: "
-				"NPORT x%x oxid:x%x\n",
-				ctxp->sid, ctxp->oxid);
+				"6105 NVMET prep LS wqe: No WQE: "
+				"NPORT x%x oxid x%x ste %d\n",
+				ctxp->sid, ctxp->oxid, ctxp->state);
 		return NULL;
 	}
 
@@ -1568,9 +1641,9 @@ lpfc_nvmet_prep_ls_wqe(struct lpfc_hba *phba,
 	    ((ndlp->nlp_state != NLP_STE_UNMAPPED_NODE) &&
 	    (ndlp->nlp_state != NLP_STE_MAPPED_NODE))) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
-				"6106 lpfc_nvmet_prep_ls_wqe: No ndlp: "
-				"NPORT x%x oxid:x%x\n",
-				ctxp->sid, ctxp->oxid);
+				"6106 NVMET prep LS wqe: No ndlp: "
+				"NPORT x%x oxid x%x ste %d\n",
+				ctxp->sid, ctxp->oxid, ctxp->state);
 		goto nvme_wqe_free_wqeq_exit;
 	}
 	ctxp->wqeq = nvmewqe;
@@ -1642,9 +1715,9 @@ lpfc_nvmet_prep_ls_wqe(struct lpfc_hba *phba,
 	nvmewqe->drvrTimeout = (phba->fc_ratov * 3) + LPFC_DRVR_TIMEOUT;
 	nvmewqe->iocb_flag |= LPFC_IO_NVME_LS;
 
-	/* Xmit NVME response to remote NPORT <did> */
+	/* Xmit NVMET response to remote NPORT <did> */
 	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_DISC,
-			"6039 Xmit NVME LS response to remote "
+			"6039 Xmit NVMET LS response to remote "
 			"NPORT x%x iotag:x%x oxid:x%x size:x%x\n",
 			ndlp->nlp_DID, nvmewqe->iotag, ctxp->oxid,
 			rspsize);
@@ -1676,9 +1749,9 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 
 	if (!lpfc_is_link_up(phba)) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-				"6107 lpfc_nvmet_prep_fcp_wqe: link err:"
-				"NPORT x%x oxid:x%x\n", ctxp->sid,
-				ctxp->oxid);
+				"6107 NVMET prep FCP wqe: link err:"
+				"NPORT x%x oxid x%x ste %d\n",
+				ctxp->sid, ctxp->oxid, ctxp->state);
 		return NULL;
 	}
 
@@ -1687,17 +1760,18 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 	    ((ndlp->nlp_state != NLP_STE_UNMAPPED_NODE) &&
 	     (ndlp->nlp_state != NLP_STE_MAPPED_NODE))) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-				"6108 lpfc_nvmet_prep_fcp_wqe: no ndlp: "
-				"NPORT x%x oxid:x%x\n",
-				ctxp->sid, ctxp->oxid);
+				"6108 NVMET prep FCP wqe: no ndlp: "
+				"NPORT x%x oxid x%x ste %d\n",
+				ctxp->sid, ctxp->oxid, ctxp->state);
 		return NULL;
 	}
 
 	if (rsp->sg_cnt > phba->cfg_nvme_seg_cnt) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-				"6109 lpfc_nvmet_prep_fcp_wqe: seg cnt err: "
-				"NPORT x%x oxid:x%x cnt %d\n",
-				ctxp->sid, ctxp->oxid, phba->cfg_nvme_seg_cnt);
+				"6109 NVMET prep FCP wqe: seg cnt err: "
+				"NPORT x%x oxid x%x ste %d cnt %d\n",
+				ctxp->sid, ctxp->oxid, ctxp->state,
+				phba->cfg_nvme_seg_cnt);
 		return NULL;
 	}
 
@@ -1708,9 +1782,9 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 		nvmewqe = ctxp->ctxbuf->iocbq;
 		if (nvmewqe == NULL) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-					"6110 lpfc_nvmet_prep_fcp_wqe: No "
-					"WQE: NPORT x%x oxid:x%x\n",
-					ctxp->sid, ctxp->oxid);
+					"6110 NVMET prep FCP wqe: No "
+					"WQE: NPORT x%x oxid x%x ste %d\n",
+					ctxp->sid, ctxp->oxid, ctxp->state);
 			return NULL;
 		}
 		ctxp->wqeq = nvmewqe;
@@ -1722,13 +1796,12 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 	/* Sanity check */
 	if (((ctxp->state == LPFC_NVMET_STE_RCV) &&
 	    (ctxp->entry_cnt == 1)) ||
-	    ((ctxp->state == LPFC_NVMET_STE_DATA) &&
-	    (ctxp->entry_cnt > 1))) {
+	    (ctxp->state == LPFC_NVMET_STE_DATA)) {
 		wqe = (union lpfc_wqe128 *)&nvmewqe->wqe;
 	} else {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-				"6111 Wrong state %s: %d  cnt %d\n",
-				__func__, ctxp->state, ctxp->entry_cnt);
+				"6111 Wrong state NVMET FCP: %d  cnt %d\n",
+				ctxp->state, ctxp->entry_cnt);
 		return NULL;
 	}
 
@@ -1832,7 +1905,6 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 			bf_set(wqe_ar, &wqe->fcp_tsend.wqe_com, 0);
 			bf_set(wqe_irsplen, &wqe->fcp_tsend.wqe_com, 0);
 		}
-		ctxp->state = LPFC_NVMET_STE_DATA;
 		break;
 
 	case NVMET_FCOP_WRITEDATA:
@@ -1923,7 +1995,6 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 		sgl->word2 = cpu_to_le32(sgl->word2);
 		sgl->sge_len = 0;
 		sgl++;
-		ctxp->state = LPFC_NVMET_STE_DATA;
 		atomic_inc(&tgtp->xmt_fcp_write);
 		break;
 
@@ -1980,7 +2051,6 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 		bf_set(wqe_cmd_type, &wqe->fcp_trsp.wqe_com,
 		       FCP_COMMAND_TRSP);
 		bf_set(wqe_sup, &wqe->fcp_tsend.wqe_com, 0);
-		ctxp->state = LPFC_NVMET_STE_RSP;
 
 		if (rsp->rsplen == LPFC_NVMET_SUCCESS_LEN) {
 			/* Good response - all zero's on wire */
@@ -2029,6 +2099,8 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 		sgl++;
 		ctxp->offset += cnt;
 	}
+	ctxp->state = LPFC_NVMET_STE_DATA;
+	ctxp->entry_cnt++;
 	return nvmewqe;
 }
 
@@ -2124,10 +2196,6 @@ lpfc_nvmet_unsol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	status = bf_get(lpfc_wcqe_c_status, wcqe);
 	result = wcqe->parameter;
 
-	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
-	if (ctxp->flag & LPFC_NVMET_ABORT_OP)
-		atomic_inc(&tgtp->xmt_fcp_abort_cmpl);
-
 	if (!ctxp) {
 		/* if context is clear, related io alrady complete */
 		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
@@ -2137,6 +2205,10 @@ lpfc_nvmet_unsol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 		return;
 	}
 
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	if (ctxp->flag & LPFC_NVMET_ABORT_OP)
+		atomic_inc(&tgtp->xmt_fcp_abort_cmpl);
+
 	/* Sanity check */
 	if (ctxp->state != LPFC_NVMET_STE_ABORT) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
@@ -2206,17 +2278,32 @@ lpfc_nvmet_xmt_ls_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	atomic_inc(&tgtp->xmt_ls_abort_cmpl);
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
-			"6083 Abort cmpl: ctx %p WCQE: %08x %08x %08x %08x\n",
+			"6083 Abort cmpl: ctx %p WCQE:%08x %08x %08x %08x\n",
 			ctxp, wcqe->word0, wcqe->total_data_placed,
 			result, wcqe->word3);
 
-	if (ctxp) {
-		cmdwqe->context2 = NULL;
-		cmdwqe->context3 = NULL;
-		lpfc_sli_release_iocbq(phba, cmdwqe);
-		kfree(ctxp);
-	} else
+	if (!ctxp) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
+				"6415 NVMET LS Abort No ctx: WCQE: "
+				 "%08x %08x %08x %08x\n",
+				wcqe->word0, wcqe->total_data_placed,
+				result, wcqe->word3);
+
 		lpfc_sli_release_iocbq(phba, cmdwqe);
+		return;
+	}
+
+	if (ctxp->state != LPFC_NVMET_STE_LS_ABORT) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6416 NVMET LS abort cmpl state mismatch: "
+				"oxid x%x: %d %d\n",
+				ctxp->oxid, ctxp->state, ctxp->entry_cnt);
+	}
+
+	cmdwqe->context2 = NULL;
+	cmdwqe->context3 = NULL;
+	lpfc_sli_release_iocbq(phba, cmdwqe);
+	kfree(ctxp);
 }
 
 static int
@@ -2240,7 +2327,7 @@ lpfc_nvmet_unsol_issue_abort(struct lpfc_hba *phba,
 	    ((ndlp->nlp_state != NLP_STE_UNMAPPED_NODE) &&
 	    (ndlp->nlp_state != NLP_STE_MAPPED_NODE))) {
 		atomic_inc(&tgtp->xmt_abort_rsp_error);
-		lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
 				"6134 Drop ABTS - wrong NDLP state x%x.\n",
 				(ndlp) ? ndlp->nlp_state : NLP_STE_MAX_STATE);
 
@@ -2250,7 +2337,6 @@ lpfc_nvmet_unsol_issue_abort(struct lpfc_hba *phba,
 
 	abts_wqeq = ctxp->wqeq;
 	wqe_abts = &abts_wqeq->wqe;
-	ctxp->state = LPFC_NVMET_STE_ABORT;
 
 	/*
 	 * Since we zero the whole WQE, we need to ensure we set the WQE fields
@@ -2338,7 +2424,7 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	    ((ndlp->nlp_state != NLP_STE_UNMAPPED_NODE) &&
 	    (ndlp->nlp_state != NLP_STE_MAPPED_NODE))) {
 		atomic_inc(&tgtp->xmt_abort_rsp_error);
-		lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
 				"6160 Drop ABORT - wrong NDLP state x%x.\n",
 				(ndlp) ? ndlp->nlp_state : NLP_STE_MAX_STATE);
 
@@ -2351,7 +2437,7 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	ctxp->abort_wqeq = lpfc_sli_get_iocbq(phba);
 	if (!ctxp->abort_wqeq) {
 		atomic_inc(&tgtp->xmt_abort_rsp_error);
-		lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
 				"6161 ABORT failed: No wqeqs: "
 				"xri: x%x\n", ctxp->oxid);
 		/* No failure to an ABTS request. */
@@ -2437,6 +2523,7 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	abts_wqeq->iocb_cmpl = 0;
 	abts_wqeq->iocb_flag |= LPFC_IO_NVME;
 	abts_wqeq->context2 = ctxp;
+	abts_wqeq->vport = phba->pport;
 	rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abts_wqeq);
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 	if (rc == WQE_SUCCESS) {
@@ -2471,6 +2558,15 @@ lpfc_nvmet_unsol_fcp_issue_abort(struct lpfc_hba *phba,
 		ctxp->wqeq->hba_wqidx = 0;
 	}
 
+	if (ctxp->state == LPFC_NVMET_STE_FREE) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6417 NVMET ABORT ctx freed %d %d oxid x%x\n",
+				ctxp->state, ctxp->entry_cnt, ctxp->oxid);
+		rc = WQE_BUSY;
+		goto aerr;
+	}
+	ctxp->state = LPFC_NVMET_STE_ABORT;
+	ctxp->entry_cnt++;
 	rc = lpfc_nvmet_unsol_issue_abort(phba, ctxp, sid, xri);
 	if (rc == 0)
 		goto aerr;
@@ -2487,10 +2583,9 @@ lpfc_nvmet_unsol_fcp_issue_abort(struct lpfc_hba *phba,
 	}
 
 aerr:
-	atomic_inc(&tgtp->xmt_abort_rsp_error);
 	ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
 	atomic_inc(&tgtp->xmt_abort_rsp_error);
-	lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
+	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
 			"6135 Failed to Issue ABTS for oxid x%x. Status x%x\n",
 			ctxp->oxid, rc);
 	return 1;
@@ -2507,12 +2602,24 @@ lpfc_nvmet_unsol_ls_issue_abort(struct lpfc_hba *phba,
 	unsigned long flags;
 	int rc;
 
+	if ((ctxp->state == LPFC_NVMET_STE_LS_RCV && ctxp->entry_cnt == 1) ||
+	    (ctxp->state == LPFC_NVMET_STE_LS_RSP && ctxp->entry_cnt == 2)) {
+		ctxp->state = LPFC_NVMET_STE_LS_ABORT;
+		ctxp->entry_cnt++;
+	} else {
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"6418 NVMET LS abort state mismatch "
+				"IO x%x: %d %d\n",
+				ctxp->oxid, ctxp->state, ctxp->entry_cnt);
+		ctxp->state = LPFC_NVMET_STE_LS_ABORT;
+	}
+
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
 	if (!ctxp->wqeq) {
 		/* Issue ABTS for this WQE based on iotag */
 		ctxp->wqeq = lpfc_sli_get_iocbq(phba);
 		if (!ctxp->wqeq) {
-			lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
+			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
 					"6068 Abort failed: No wqeqs: "
 					"xri: x%x\n", xri);
 			/* No failure to an ABTS request. */
@@ -2523,7 +2630,10 @@ lpfc_nvmet_unsol_ls_issue_abort(struct lpfc_hba *phba,
 	abts_wqeq = ctxp->wqeq;
 	wqe_abts = &abts_wqeq->wqe;
 
-	lpfc_nvmet_unsol_issue_abort(phba, ctxp, sid, xri);
+	if (lpfc_nvmet_unsol_issue_abort(phba, ctxp, sid, xri) == 0) {
+		rc = WQE_BUSY;
+		goto out;
+	}
 
 	spin_lock_irqsave(&phba->hbalock, flags);
 	abts_wqeq->wqe_cmpl = lpfc_nvmet_xmt_ls_abort_cmp;
@@ -2535,13 +2645,13 @@ lpfc_nvmet_unsol_ls_issue_abort(struct lpfc_hba *phba,
 		atomic_inc(&tgtp->xmt_abort_unsol);
 		return 0;
 	}
-
+out:
 	atomic_inc(&tgtp->xmt_abort_rsp_error);
 	abts_wqeq->context2 = NULL;
 	abts_wqeq->context3 = NULL;
 	lpfc_sli_release_iocbq(phba, abts_wqeq);
 	kfree(ctxp);
-	lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
+	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
 			"6056 Failed to Issue ABTS. Status x%x\n", rc);
 	return 0;
 }

drivers/scsi/lpfc/lpfc_nvmet.h

@@ -93,12 +93,14 @@ struct lpfc_nvmet_rcv_ctx {
 	uint16_t cpu;
 	uint16_t state;
 	/* States */
-#define LPFC_NVMET_STE_FREE		0
-#define LPFC_NVMET_STE_RCV		1
-#define LPFC_NVMET_STE_DATA		2
-#define LPFC_NVMET_STE_ABORT		3
-#define LPFC_NVMET_STE_RSP		4
-#define LPFC_NVMET_STE_DONE		5
+#define LPFC_NVMET_STE_LS_RCV		1
+#define LPFC_NVMET_STE_LS_ABORT		2
+#define LPFC_NVMET_STE_LS_RSP		3
+#define LPFC_NVMET_STE_RCV		4
+#define LPFC_NVMET_STE_DATA		5
+#define LPFC_NVMET_STE_ABORT		6
+#define LPFC_NVMET_STE_DONE		7
+#define LPFC_NVMET_STE_FREE		0xff
 	uint16_t flag;
 #define LPFC_NVMET_IO_INP		0x1  /* IO is in progress on exchange */
 #define LPFC_NVMET_ABORT_OP		0x2  /* Abort WQE issued on exchange */

drivers/scsi/lpfc/lpfc_scsi.c

@@ -3931,7 +3931,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 	struct Scsi_Host *shost;
 	uint32_t logit = LOG_FCP;
 
-	phba->fc4ScsiIoCmpls++;
+	atomic_inc(&phba->fc4ScsiIoCmpls);
 
 	/* Sanity check on return of outstanding command */
 	cmd = lpfc_cmd->pCmd;
@@ -4250,19 +4250,19 @@ lpfc_scsi_prep_cmnd(struct lpfc_vport *vport, struct lpfc_scsi_buf *lpfc_cmd,
 						vport->cfg_first_burst_size;
 			}
 			fcp_cmnd->fcpCntl3 = WRITE_DATA;
-			phba->fc4ScsiOutputRequests++;
+			atomic_inc(&phba->fc4ScsiOutputRequests);
 		} else {
 			iocb_cmd->ulpCommand = CMD_FCP_IREAD64_CR;
 			iocb_cmd->ulpPU = PARM_READ_CHECK;
 			fcp_cmnd->fcpCntl3 = READ_DATA;
-			phba->fc4ScsiInputRequests++;
+			atomic_inc(&phba->fc4ScsiInputRequests);
 		}
 	} else {
 		iocb_cmd->ulpCommand = CMD_FCP_ICMND64_CR;
 		iocb_cmd->un.fcpi.fcpi_parm = 0;
 		iocb_cmd->ulpPU = 0;
 		fcp_cmnd->fcpCntl3 = 0;
-		phba->fc4ScsiControlRequests++;
+		atomic_inc(&phba->fc4ScsiControlRequests);
 	}
 	if (phba->sli_rev == 3 &&
 	    !(phba->sli3_options & LPFC_SLI3_BG_ENABLED))
@@ -4640,7 +4640,16 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 				 (uint32_t)
 				 (cmnd->request->timeout / 1000));
 
-
+		switch (lpfc_cmd->fcp_cmnd->fcpCntl3) {
+		case WRITE_DATA:
+			atomic_dec(&phba->fc4ScsiOutputRequests);
+			break;
+		case READ_DATA:
+			atomic_dec(&phba->fc4ScsiInputRequests);
+			break;
+		default:
+			atomic_dec(&phba->fc4ScsiControlRequests);
+		}
 		goto out_host_busy_free_buf;
 	}
 	if (phba->cfg_poll & ENABLE_FCP_RING_POLLING) {

drivers/scsi/lpfc/lpfc_sli.c

@@ -968,6 +968,7 @@ __lpfc_sli_get_els_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
 			list_remove_head(lpfc_els_sgl_list, sglq,
 						struct lpfc_sglq, list);
 			if (sglq == start_sglq) {
+				list_add_tail(&sglq->list, lpfc_els_sgl_list);
 				sglq = NULL;
 				break;
 			} else
@@ -4302,7 +4303,6 @@ lpfc_sli4_brdreset(struct lpfc_hba *phba)
 
 	/* Perform FCoE PCI function reset before freeing queue memory */
 	rc = lpfc_pci_function_reset(phba);
-	lpfc_sli4_queue_destroy(phba);
 
 	/* Restore PCI cmd register */
 	pci_write_config_word(phba->pcidev, PCI_COMMAND, cfg_value);
@@ -4427,6 +4427,7 @@ lpfc_sli_brdrestart_s4(struct lpfc_hba *phba)
 		pci_disable_pcie_error_reporting(phba->pcidev);
 
 	lpfc_hba_down_post(phba);
+	lpfc_sli4_queue_destroy(phba);
 
 	return rc;
 }
@@ -6926,18 +6927,6 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 		cnt = phba->cfg_iocb_cnt * 1024;
 		/* We need 1 iocbq for every SGL, for IO processing */
 		cnt += phba->sli4_hba.nvmet_xri_cnt;
-		/* Initialize and populate the iocb list per host */
-		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-				"2821 initialize iocb list %d total %d\n",
-				phba->cfg_iocb_cnt, cnt);
-		rc = lpfc_init_iocb_list(phba, cnt);
-		if (rc) {
-			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-					"1413 Failed to init iocb list.\n");
-			goto out_destroy_queue;
-		}
-
-		lpfc_nvmet_create_targetport(phba);
 	} else {
 		/* update host scsi xri-sgl sizes and mappings */
 		rc = lpfc_sli4_scsi_sgl_update(phba);
@@ -6958,18 +6947,24 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 		}
 
 		cnt = phba->cfg_iocb_cnt * 1024;
+	}
+
+	if (!phba->sli.iocbq_lookup) {
 		/* Initialize and populate the iocb list per host */
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-				"2820 initialize iocb list %d total %d\n",
+				"2821 initialize iocb list %d total %d\n",
 				phba->cfg_iocb_cnt, cnt);
 		rc = lpfc_init_iocb_list(phba, cnt);
 		if (rc) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-					"6301 Failed to init iocb list.\n");
+					"1413 Failed to init iocb list.\n");
 			goto out_destroy_queue;
 		}
 	}
 
+	if (phba->nvmet_support)
+		lpfc_nvmet_create_targetport(phba);
+
 	if (phba->nvmet_support && phba->cfg_nvmet_mrq) {
 		/* Post initial buffers to all RQs created */
 		for (i = 0; i < phba->cfg_nvmet_mrq; i++) {
@@ -7512,7 +7507,8 @@ lpfc_sli_issue_mbox_s3(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmbox,
 				"(%d):0308 Mbox cmd issue - BUSY Data: "
 				"x%x x%x x%x x%x\n",
 				pmbox->vport ? pmbox->vport->vpi : 0xffffff,
-				mbx->mbxCommand, phba->pport->port_state,
+				mbx->mbxCommand,
+				phba->pport ? phba->pport->port_state : 0xff,
 				psli->sli_flag, flag);
 
 		psli->slistat.mbox_busy++;
@@ -7564,7 +7560,8 @@ lpfc_sli_issue_mbox_s3(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmbox,
 			"(%d):0309 Mailbox cmd x%x issue Data: x%x x%x "
 			"x%x\n",
 			pmbox->vport ? pmbox->vport->vpi : 0,
-			mbx->mbxCommand, phba->pport->port_state,
+			mbx->mbxCommand,
+			phba->pport ? phba->pport->port_state : 0xff,
 			psli->sli_flag, flag);
 
 	if (mbx->mbxCommand != MBX_HEARTBEAT) {
@@ -10950,6 +10947,7 @@ lpfc_sli_abort_iocb(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
 	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_iocbq *iocbq;
 	struct lpfc_iocbq *abtsiocb;
+	struct lpfc_sli_ring *pring_s4;
 	IOCB_t *cmd = NULL;
 	int errcnt = 0, ret_val = 0;
 	int i;
@@ -11003,8 +11001,15 @@ lpfc_sli_abort_iocb(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
 
 		/* Setup callback routine and issue the command. */
 		abtsiocb->iocb_cmpl = lpfc_sli_abort_fcp_cmpl;
-		ret_val = lpfc_sli_issue_iocb(phba, pring->ringno,
-					      abtsiocb, 0);
+		if (phba->sli_rev == LPFC_SLI_REV4) {
+			pring_s4 = lpfc_sli4_calc_ring(phba, iocbq);
+			if (!pring_s4)
+				continue;
+			ret_val = lpfc_sli_issue_iocb(phba, pring_s4->ringno,
+						      abtsiocb, 0);
+		} else
+			ret_val = lpfc_sli_issue_iocb(phba, pring->ringno,
+						      abtsiocb, 0);
 		if (ret_val == IOCB_ERROR) {
 			lpfc_sli_release_iocbq(phba, abtsiocb);
 			errcnt++;
@@ -13256,6 +13261,7 @@ lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	case FC_STATUS_RQ_BUF_LEN_EXCEEDED:
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
 				"6126 Receive Frame Truncated!!\n");
+		/* Drop thru */
 	case FC_STATUS_RQ_SUCCESS:
 		lpfc_sli4_rq_release(hrq, drq);
 		spin_lock_irqsave(&phba->hbalock, iflags);
@@ -13466,6 +13472,7 @@ process_cq:
 	/* Track the max number of CQEs processed in 1 EQ */
 	if (ecount > cq->CQ_max_cqe)
 		cq->CQ_max_cqe = ecount;
+	cq->assoc_qp->EQ_cqe_cnt += ecount;
 
 	/* Catch the no cq entry condition */
 	if (unlikely(ecount == 0))
@@ -13547,6 +13554,9 @@ lpfc_sli4_fof_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe)
 		return;
 	}
 
+	/* Save EQ associated with this CQ */
+	cq->assoc_qp = phba->sli4_hba.fof_eq;
+
 	/* Process all the entries to the OAS CQ */
 	while ((cqe = lpfc_sli4_cq_get(cq))) {
 		workposted |= lpfc_sli4_fp_handle_cqe(phba, cq, cqe);
@@ -13557,6 +13567,7 @@ lpfc_sli4_fof_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe)
 	/* Track the max number of CQEs processed in 1 EQ */
 	if (ecount > cq->CQ_max_cqe)
 		cq->CQ_max_cqe = ecount;
+	cq->assoc_qp->EQ_cqe_cnt += ecount;
 
 	/* Catch the no cq entry condition */
 	if (unlikely(ecount == 0))
@@ -13617,7 +13628,6 @@ lpfc_sli4_fof_intr_handler(int irq, void *dev_id)
 
 	/* Check device state for handling interrupt */
 	if (unlikely(lpfc_intr_state_check(phba))) {
-		eq->EQ_badstate++;
 		/* Check again for link_state with lock held */
 		spin_lock_irqsave(&phba->hbalock, iflag);
 		if (phba->link_state < LPFC_LINK_DOWN)
@@ -13729,7 +13739,6 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 
 	/* Check device state for handling interrupt */
 	if (unlikely(lpfc_intr_state_check(phba))) {
-		fpeq->EQ_badstate++;
 		/* Check again for link_state with lock held */
 		spin_lock_irqsave(&phba->hbalock, iflag);
 		if (phba->link_state < LPFC_LINK_DOWN)
@@ -13988,14 +13997,15 @@ lpfc_dual_chute_pci_bar_map(struct lpfc_hba *phba, uint16_t pci_barset)
  * fails this function will return -ENXIO.
  **/
 int
-lpfc_modify_hba_eq_delay(struct lpfc_hba *phba, uint32_t startq)
+lpfc_modify_hba_eq_delay(struct lpfc_hba *phba, uint32_t startq,
+			 uint32_t numq, uint32_t imax)
 {
 	struct lpfc_mbx_modify_eq_delay *eq_delay;
 	LPFC_MBOXQ_t *mbox;
 	struct lpfc_queue *eq;
 	int cnt, rc, length, status = 0;
 	uint32_t shdr_status, shdr_add_status;
-	uint32_t result;
+	uint32_t result, val;
 	int qidx;
 	union lpfc_sli4_cfg_shdr *shdr;
 	uint16_t dmult;
@@ -14014,22 +14024,45 @@ lpfc_modify_hba_eq_delay(struct lpfc_hba *phba, uint32_t startq)
 	eq_delay = &mbox->u.mqe.un.eq_delay;
 
 	/* Calculate delay multiper from maximum interrupt per second */
-	result = phba->cfg_fcp_imax / phba->io_channel_irqs;
+	result = imax / phba->io_channel_irqs;
 	if (result > LPFC_DMULT_CONST || result == 0)
 		dmult = 0;
 	else
 		dmult = LPFC_DMULT_CONST/result - 1;
+	if (dmult > LPFC_DMULT_MAX)
+		dmult = LPFC_DMULT_MAX;
 
 	cnt = 0;
 	for (qidx = startq; qidx < phba->io_channel_irqs; qidx++) {
 		eq = phba->sli4_hba.hba_eq[qidx];
 		if (!eq)
 			continue;
+		eq->q_mode = imax;
 		eq_delay->u.request.eq[cnt].eq_id = eq->queue_id;
 		eq_delay->u.request.eq[cnt].phase = 0;
 		eq_delay->u.request.eq[cnt].delay_multi = dmult;
 		cnt++;
-		if (cnt >= LPFC_MAX_EQ_DELAY_EQID_CNT)
+
+		/* q_mode is only used for auto_imax */
+		if (phba->sli.sli_flag & LPFC_SLI_USE_EQDR) {
+			/* Use EQ Delay Register method for q_mode */
+
+			/* Convert for EQ Delay register */
+			val =  phba->cfg_fcp_imax;
+			if (val) {
+				/* First, interrupts per sec per EQ */
+				val = phba->cfg_fcp_imax /
+					phba->io_channel_irqs;
+
+				/* us delay between each interrupt */
+				val = LPFC_SEC_TO_USEC / val;
+			}
+			eq->q_mode = val;
+		} else {
+			eq->q_mode = imax;
+		}
+
+		if (cnt >= numq)
 			break;
 	}
 	eq_delay->u.request.num_eq = cnt;
@@ -16126,9 +16159,6 @@ lpfc_sli4_post_scsi_sgl_block(struct lpfc_hba *phba,
 	return rc;
 }
 
-static char *lpfc_rctl_names[] = FC_RCTL_NAMES_INIT;
-static char *lpfc_type_names[] = FC_TYPE_NAMES_INIT;
-
 /**
  * lpfc_fc_frame_check - Check that this frame is a valid frame to handle
  * @phba: pointer to lpfc_hba struct that the frame was received on
@@ -16203,22 +16233,18 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr)
 	}
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_ELS,
-			"2538 Received frame rctl:%s (x%x), type:%s (x%x), "
+			"2538 Received frame rctl:x%x, type:x%x, "
 			"frame Data:%08x %08x %08x %08x %08x %08x %08x\n",
-			(fc_hdr->fh_r_ctl == FC_RCTL_MDS_DIAGS) ? "MDS Diags" :
-			lpfc_rctl_names[fc_hdr->fh_r_ctl], fc_hdr->fh_r_ctl,
-			(fc_hdr->fh_type == FC_TYPE_VENDOR_UNIQUE) ?
-			"Vendor Unique" : lpfc_type_names[fc_hdr->fh_type],
-			fc_hdr->fh_type, be32_to_cpu(header[0]),
-			be32_to_cpu(header[1]), be32_to_cpu(header[2]),
-			be32_to_cpu(header[3]), be32_to_cpu(header[4]),
-			be32_to_cpu(header[5]), be32_to_cpu(header[6]));
+			fc_hdr->fh_r_ctl, fc_hdr->fh_type,
+			be32_to_cpu(header[0]), be32_to_cpu(header[1]),
+			be32_to_cpu(header[2]), be32_to_cpu(header[3]),
+			be32_to_cpu(header[4]), be32_to_cpu(header[5]),
+			be32_to_cpu(header[6]));
 	return 0;
 drop:
 	lpfc_printf_log(phba, KERN_WARNING, LOG_ELS,
-			"2539 Dropped frame rctl:%s type:%s\n",
-			lpfc_rctl_names[fc_hdr->fh_r_ctl],
-			lpfc_type_names[fc_hdr->fh_type]);
+			"2539 Dropped frame rctl:x%x type:x%x\n",
+			fc_hdr->fh_r_ctl, fc_hdr->fh_type);
 	return 1;
 }
 

drivers/scsi/lpfc/lpfc_sli.h

@@ -321,6 +321,7 @@ struct lpfc_sli {
 #define LPFC_MENLO_MAINT          0x1000 /* need for menl fw download */
 #define LPFC_SLI_ASYNC_MBX_BLK    0x2000 /* Async mailbox is blocked */
 #define LPFC_SLI_SUPPRESS_RSP     0x4000 /* Suppress RSP feature is supported */
+#define LPFC_SLI_USE_EQDR         0x8000 /* EQ Delay Register is supported */
 
 	struct lpfc_sli_ring *sli3_ring;
 

drivers/scsi/lpfc/lpfc_sli4.h

@@ -168,7 +168,7 @@ struct lpfc_queue {
 	struct lpfc_sli_ring *pring; /* ptr to io ring associated with q */
 	struct lpfc_rqb *rqbp;	/* ptr to RQ buffers */
 
-	uint16_t sgl_list_cnt;
+	uint32_t q_mode;
 	uint16_t db_format;
 #define LPFC_DB_RING_FORMAT	0x01
 #define LPFC_DB_LIST_FORMAT	0x02
@@ -181,7 +181,7 @@ struct lpfc_queue {
 /* defines for EQ stats */
 #define	EQ_max_eqe		q_cnt_1
 #define	EQ_no_entry		q_cnt_2
-#define	EQ_badstate		q_cnt_3
+#define	EQ_cqe_cnt		q_cnt_3
 #define	EQ_processed		q_cnt_4
 
 /* defines for CQ stats */
@@ -407,8 +407,10 @@ struct lpfc_max_cfg_param {
 
 struct lpfc_hba;
 /* SLI4 HBA multi-fcp queue handler struct */
+#define LPFC_SLI4_HANDLER_NAME_SZ	16
 struct lpfc_hba_eq_hdl {
 	uint32_t idx;
+	char handler_name[LPFC_SLI4_HANDLER_NAME_SZ];
 	struct lpfc_hba *phba;
 	atomic_t hba_eq_in_use;
 	struct cpumask *cpumask;
@@ -480,7 +482,6 @@ struct lpfc_sli4_lnk_info {
 
 #define LPFC_SLI4_HANDLER_CNT		(LPFC_HBA_IO_CHAN_MAX+ \
 					 LPFC_FOF_IO_CHAN_NUM)
-#define LPFC_SLI4_HANDLER_NAME_SZ	16
 
 /* Used for IRQ vector to CPU mapping */
 struct lpfc_vector_map_info {
@@ -522,6 +523,7 @@ struct lpfc_sli4_hba {
 #define SLIPORT_ERR2_REG_FAILURE_CQ		0x4
 #define SLIPORT_ERR2_REG_FAILURE_BUS		0x5
 #define SLIPORT_ERR2_REG_FAILURE_RQ		0x6
+			void __iomem *EQDregaddr;
 		} if_type2;
 	} u;
 
@@ -548,7 +550,6 @@ struct lpfc_sli4_hba {
 	uint32_t ue_to_rp;
 	struct lpfc_register sli_intf;
 	struct lpfc_pc_sli4_params pc_sli4_params;
-	uint8_t handler_name[LPFC_SLI4_HANDLER_CNT][LPFC_SLI4_HANDLER_NAME_SZ];
 	struct lpfc_hba_eq_hdl *hba_eq_hdl; /* HBA per-WQ handle */
 
 	/* Pointers to the constructed SLI4 queues */
@@ -620,7 +621,8 @@ struct lpfc_sli4_hba {
 	uint16_t scsi_xri_start;
 	uint16_t els_xri_cnt;
 	uint16_t nvmet_xri_cnt;
-	uint16_t nvmet_ctx_cnt;
+	uint16_t nvmet_ctx_get_cnt;
+	uint16_t nvmet_ctx_put_cnt;
 	uint16_t nvmet_io_wait_cnt;
 	uint16_t nvmet_io_wait_total;
 	struct list_head lpfc_els_sgl_list;
@@ -629,7 +631,8 @@ struct lpfc_sli4_hba {
 	struct list_head lpfc_abts_nvmet_ctx_list;
 	struct list_head lpfc_abts_scsi_buf_list;
 	struct list_head lpfc_abts_nvme_buf_list;
-	struct list_head lpfc_nvmet_ctx_list;
+	struct list_head lpfc_nvmet_ctx_get_list;
+	struct list_head lpfc_nvmet_ctx_put_list;
 	struct list_head lpfc_nvmet_io_wait_list;
 	struct lpfc_sglq **lpfc_sglq_active_list;
 	struct list_head lpfc_rpi_hdr_list;
@@ -661,7 +664,8 @@ struct lpfc_sli4_hba {
 	spinlock_t abts_nvme_buf_list_lock; /* list of aborted SCSI IOs */
 	spinlock_t abts_scsi_buf_list_lock; /* list of aborted SCSI IOs */
 	spinlock_t sgl_list_lock; /* list of aborted els IOs */
-	spinlock_t nvmet_io_lock;
+	spinlock_t nvmet_ctx_get_lock; /* list of avail XRI contexts */
+	spinlock_t nvmet_ctx_put_lock; /* list of avail XRI contexts */
 	spinlock_t nvmet_io_wait_lock; /* IOs waiting for ctx resources */
 	uint32_t physical_port;
 
@@ -755,7 +759,8 @@ struct lpfc_queue *lpfc_sli4_queue_alloc(struct lpfc_hba *, uint32_t,
 			uint32_t);
 void lpfc_sli4_queue_free(struct lpfc_queue *);
 int lpfc_eq_create(struct lpfc_hba *, struct lpfc_queue *, uint32_t);
-int lpfc_modify_hba_eq_delay(struct lpfc_hba *phba, uint32_t startq);
+int lpfc_modify_hba_eq_delay(struct lpfc_hba *phba, uint32_t startq,
+			     uint32_t numq, uint32_t imax);
 int lpfc_cq_create(struct lpfc_hba *, struct lpfc_queue *,
 			struct lpfc_queue *, uint32_t, uint32_t);
 int lpfc_cq_create_set(struct lpfc_hba *phba, struct lpfc_queue **cqp,

drivers/scsi/lpfc/lpfc_version.h

@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "11.2.0.14"
+#define LPFC_DRIVER_VERSION "11.4.0.1"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */

drivers/scsi/megaraid/megaraid_mm.c

@@ -574,7 +574,7 @@ mraid_mm_attach_buf(mraid_mmadp_t *adp, uioc_t *kioc, int xferlen)
 
 	kioc->pool_index	= right_pool;
 	kioc->free_buf		= 1;
-	kioc->buf_vaddr 	= pci_pool_alloc(pool->handle, GFP_KERNEL,
+	kioc->buf_vaddr		= pci_pool_alloc(pool->handle, GFP_ATOMIC,
 							&kioc->buf_paddr);
 	spin_unlock_irqrestore(&pool->lock, flags);
 

drivers/scsi/mpt3sas/mpt3sas_scsih.c

@@ -2859,7 +2859,7 @@ _scsih_internal_device_block(struct scsi_device *sdev,
 	    sas_device_priv_data->sas_target->handle);
 	sas_device_priv_data->block = 1;
 
-	r = scsi_internal_device_block(sdev, false);
+	r = scsi_internal_device_block_nowait(sdev);
 	if (r == -EINVAL)
 		sdev_printk(KERN_WARNING, sdev,
 		    "device_block failed with return(%d) for handle(0x%04x)\n",
@@ -2883,7 +2883,7 @@ _scsih_internal_device_unblock(struct scsi_device *sdev,
 	sdev_printk(KERN_WARNING, sdev, "device_unblock and setting to running, "
 	    "handle(0x%04x)\n", sas_device_priv_data->sas_target->handle);
 	sas_device_priv_data->block = 0;
-	r = scsi_internal_device_unblock(sdev, SDEV_RUNNING);
+	r = scsi_internal_device_unblock_nowait(sdev, SDEV_RUNNING);
 	if (r == -EINVAL) {
 		/* The device has been set to SDEV_RUNNING by SD layer during
 		 * device addition but the request queue is still stopped by
@@ -2895,14 +2895,14 @@ _scsih_internal_device_unblock(struct scsi_device *sdev,
 		    "performing a block followed by an unblock\n",
 		    r, sas_device_priv_data->sas_target->handle);
 		sas_device_priv_data->block = 1;
-		r = scsi_internal_device_block(sdev, false);
+		r = scsi_internal_device_block_nowait(sdev);
 		if (r)
 			sdev_printk(KERN_WARNING, sdev, "retried device_block "
 			    "failed with return(%d) for handle(0x%04x)\n",
 			    r, sas_device_priv_data->sas_target->handle);
 
 		sas_device_priv_data->block = 0;
-		r = scsi_internal_device_unblock(sdev, SDEV_RUNNING);
+		r = scsi_internal_device_unblock_nowait(sdev, SDEV_RUNNING);
 		if (r)
 			sdev_printk(KERN_WARNING, sdev, "retried device_unblock"
 			    " failed with return(%d) for handle(0x%04x)\n",

drivers/scsi/qedf/drv_fcoe_fw_funcs.c

@@ -1,5 +1,5 @@
 /* QLogic FCoE Offload Driver
- * Copyright (c) 2016 Cavium Inc.
+ * Copyright (c) 2016-2017 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

drivers/scsi/qedf/drv_fcoe_fw_funcs.h

@@ -1,5 +1,5 @@
 /* QLogic FCoE Offload Driver
- * Copyright (c) 2016 Cavium Inc.
+ * Copyright (c) 2016-2017 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

drivers/scsi/qedf/drv_scsi_fw_funcs.c

@@ -1,5 +1,5 @@
 /* QLogic FCoE Offload Driver
- * Copyright (c) 2016 Cavium Inc.
+ * Copyright (c) 2016-2017 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

drivers/scsi/qedf/drv_scsi_fw_funcs.h

@@ -1,5 +1,5 @@
 /* QLogic FCoE Offload Driver
- * Copyright (c) 2016 Cavium Inc.
+ * Copyright (c) 2016-2017 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

drivers/scsi/qedf/qedf.h

@@ -1,6 +1,6 @@
 /*
  *  QLogic FCoE Offload Driver
- *  Copyright (c) 2016 Cavium Inc.
+ *  Copyright (c) 2016-2017 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

drivers/scsi/qedf/qedf_attr.c

@@ -1,6 +1,6 @@
 /*
  *  QLogic FCoE Offload Driver
- *  Copyright (c) 2016 Cavium Inc.
+ *  Copyright (c) 2016-2017 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
@@ -8,6 +8,25 @@
  */
 #include "qedf.h"
 
+inline bool qedf_is_vport(struct qedf_ctx *qedf)
+{
+	return qedf->lport->vport != NULL;
+}
+
+/* Get base qedf for physical port from vport */
+static struct qedf_ctx *qedf_get_base_qedf(struct qedf_ctx *qedf)
+{
+	struct fc_lport *lport;
+	struct fc_lport *base_lport;
+
+	if (!(qedf_is_vport(qedf)))
+		return NULL;
+
+	lport = qedf->lport;
+	base_lport = shost_priv(vport_to_shost(lport->vport));
+	return lport_priv(base_lport);
+}
+
 static ssize_t
 qedf_fcoe_mac_show(struct device *dev,
 	struct device_attribute *attr, char *buf)
@@ -26,34 +45,34 @@ qedf_fcoe_mac_show(struct device *dev,
 	return scnprintf(buf, PAGE_SIZE, "%pM\n", fcoe_mac);
 }
 
+static ssize_t
+qedf_fka_period_show(struct device *dev,
+	struct device_attribute *attr, char *buf)
+{
+	struct fc_lport *lport = shost_priv(class_to_shost(dev));
+	struct qedf_ctx *qedf = lport_priv(lport);
+	int fka_period = -1;
+
+	if (qedf_is_vport(qedf))
+		qedf = qedf_get_base_qedf(qedf);
+
+	if (qedf->ctlr.sel_fcf)
+		fka_period = qedf->ctlr.sel_fcf->fka_period;
+
+	return scnprintf(buf, PAGE_SIZE, "%d\n", fka_period);
+}
+
 static DEVICE_ATTR(fcoe_mac, S_IRUGO, qedf_fcoe_mac_show, NULL);
+static DEVICE_ATTR(fka_period, S_IRUGO, qedf_fka_period_show, NULL);
 
 struct device_attribute *qedf_host_attrs[] = {
 	&dev_attr_fcoe_mac,
+	&dev_attr_fka_period,
 	NULL,
 };
 
 extern const struct qed_fcoe_ops *qed_ops;
 
-inline bool qedf_is_vport(struct qedf_ctx *qedf)
-{
-	return (!(qedf->lport->vport == NULL));
-}
-
-/* Get base qedf for physical port from vport */
-static struct qedf_ctx *qedf_get_base_qedf(struct qedf_ctx *qedf)
-{
-	struct fc_lport *lport;
-	struct fc_lport *base_lport;
-
-	if (!(qedf_is_vport(qedf)))
-		return NULL;
-
-	lport = qedf->lport;
-	base_lport = shost_priv(vport_to_shost(lport->vport));
-	return (struct qedf_ctx *)(lport_priv(base_lport));
-}
-
 void qedf_capture_grc_dump(struct qedf_ctx *qedf)
 {
 	struct qedf_ctx *base_qedf;

drivers/scsi/qedf/qedf_dbg.h

@@ -1,6 +1,6 @@
 /*
  *  QLogic FCoE Offload Driver
- *  Copyright (c) 2016 Cavium Inc.
+ *  Copyright (c) 2016-2017 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

drivers/scsi/qedf/qedf_debugfs.c

@@ -1,6 +1,6 @@
 /*
  *  QLogic FCoE Offload Driver
- *  Copyright (c) 2016 QLogic Corporation
+ *  Copyright (c) 2016-2017 QLogic Corporation
  *
  *  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

drivers/scsi/qedf/qedf_els.c

@@ -1,6 +1,6 @@
 /*
  *  QLogic FCoE Offload Driver
- *  Copyright (c) 2016 Cavium Inc.
+ *  Copyright (c) 2016-2017 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
@@ -44,7 +44,7 @@ static int qedf_initiate_els(struct qedf_rport *fcport, unsigned int op,
 		goto els_err;
 	}
 
-	if (!(test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags))) {
+	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
 		QEDF_ERR(&(qedf->dbg_ctx), "els 0x%x: fcport not ready\n", op);
 		rc = -EINVAL;
 		goto els_err;
@@ -225,7 +225,7 @@ int qedf_send_rrq(struct qedf_ioreq *aborted_io_req)
 	fcport = aborted_io_req->fcport;
 
 	/* Check that fcport is still offloaded */
-	if (!(test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags))) {
+	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
 		QEDF_ERR(NULL, "fcport is no longer offloaded.\n");
 		return -EINVAL;
 	}
@@ -550,7 +550,7 @@ static int qedf_send_srr(struct qedf_ioreq *orig_io_req, u32 offset, u8 r_ctl)
 	fcport = orig_io_req->fcport;
 
 	/* Check that fcport is still offloaded */
-	if (!(test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags))) {
+	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
 		QEDF_ERR(NULL, "fcport is no longer offloaded.\n");
 		return -EINVAL;
 	}

drivers/scsi/qedf/qedf_fip.c

@@ -1,6 +1,6 @@
 /*
  *  QLogic FCoE Offload Driver
- *  Copyright (c) 2016 Cavium Inc.
+ *  Copyright (c) 2016-2017 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
@@ -155,10 +155,9 @@ void qedf_fip_recv(struct qedf_ctx *qedf, struct sk_buff *skb)
 	struct fip_wwn_desc *wp;
 	struct fip_vn_desc *vp;
 	size_t rlen, dlen;
-	uint32_t cvl_port_id;
-	__u8 cvl_mac[ETH_ALEN];
 	u16 op;
 	u8 sub;
+	bool do_reset = false;
 
 	eth_hdr = (struct ethhdr *)skb_mac_header(skb);
 	fiph = (struct fip_header *) ((void *)skb->data + 2 * ETH_ALEN + 2);
@@ -189,8 +188,6 @@ void qedf_fip_recv(struct qedf_ctx *qedf, struct sk_buff *skb)
 			return;
 		}
 
-		cvl_port_id = 0;
-		memset(cvl_mac, 0, ETH_ALEN);
 		/*
 		 * We need to loop through the CVL descriptors to determine
 		 * if we want to reset the fcoe link
@@ -204,7 +201,9 @@ void qedf_fip_recv(struct qedf_ctx *qedf, struct sk_buff *skb)
 				mp = (struct fip_mac_desc *)desc;
 				QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2,
 				    "fd_mac=%pM\n", mp->fd_mac);
-				ether_addr_copy(cvl_mac, mp->fd_mac);
+				if (ether_addr_equal(mp->fd_mac,
+				    qedf->ctlr.sel_fcf->fcf_mac))
+					do_reset = true;
 				break;
 			case FIP_DT_NAME:
 				wp = (struct fip_wwn_desc *)desc;
@@ -216,7 +215,9 @@ void qedf_fip_recv(struct qedf_ctx *qedf, struct sk_buff *skb)
 				vp = (struct fip_vn_desc *)desc;
 				QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2,
 				    "fd_fc_id=%x.\n", ntoh24(vp->fd_fc_id));
-				cvl_port_id = ntoh24(vp->fd_fc_id);
+				if (ntoh24(vp->fd_fc_id) ==
+				    qedf->lport->port_id)
+					do_reset = true;
 				break;
 			default:
 				/* Ignore anything else */
@@ -227,11 +228,8 @@ void qedf_fip_recv(struct qedf_ctx *qedf, struct sk_buff *skb)
 		}
 
 		QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2,
-		    "cvl_port_id=%06x cvl_mac=%pM.\n", cvl_port_id,
-		    cvl_mac);
-		if (cvl_port_id == qedf->lport->port_id &&
-		    ether_addr_equal(cvl_mac,
-		    qedf->ctlr.sel_fcf->fcf_mac)) {
+		    "do_reset=%d.\n", do_reset);
+		if (do_reset) {
 			fcoe_ctlr_link_down(&qedf->ctlr);
 			qedf_wait_for_upload(qedf);
 			fcoe_ctlr_link_up(&qedf->ctlr);

drivers/scsi/qedf/qedf_hsi.h

@@ -1,6 +1,6 @@
 /*
  *  QLogic FCoE Offload Driver
- *  Copyright (c) 2016 Cavium Inc.
+ *  Copyright (c) 2016-2017 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

drivers/scsi/qedf/qedf_io.c

@@ -1,6 +1,6 @@
 /*
  *  QLogic FCoE Offload Driver
- *  Copyright (c) 2016 Cavium Inc.
+ *  Copyright (c) 2016-2017 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
@@ -1041,10 +1041,13 @@ static void qedf_parse_fcp_rsp(struct qedf_ioreq *io_req,
 		fcp_sns_len = SCSI_SENSE_BUFFERSIZE;
 	}
 
-	memset(sc_cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
-	if (fcp_sns_len)
-		memcpy(sc_cmd->sense_buffer, sense_data,
-		    fcp_sns_len);
+	/* The sense buffer can be NULL for TMF commands */
+	if (sc_cmd->sense_buffer) {
+		memset(sc_cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
+		if (fcp_sns_len)
+			memcpy(sc_cmd->sense_buffer, sense_data,
+			    fcp_sns_len);
+	}
 }
 
 static void qedf_unmap_sg_list(struct qedf_ctx *qedf, struct qedf_ioreq *io_req)
@@ -1476,8 +1479,8 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts)
 {
 	struct fc_lport *lport;
 	struct qedf_rport *fcport = io_req->fcport;
-	struct fc_rport_priv *rdata = fcport->rdata;
-	struct qedf_ctx *qedf = fcport->qedf;
+	struct fc_rport_priv *rdata;
+	struct qedf_ctx *qedf;
 	u16 xid;
 	u32 r_a_tov = 0;
 	int rc = 0;
@@ -1485,15 +1488,18 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts)
 	struct fcoe_wqe *sqe;
 	u16 sqe_idx;
 
-	r_a_tov = rdata->r_a_tov;
-	lport = qedf->lport;
-
+	/* Sanity check qedf_rport before dereferencing any pointers */
 	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
-		QEDF_ERR(&(qedf->dbg_ctx), "tgt not offloaded\n");
+		QEDF_ERR(NULL, "tgt not offloaded\n");
 		rc = 1;
 		goto abts_err;
 	}
 
+	rdata = fcport->rdata;
+	r_a_tov = rdata->r_a_tov;
+	qedf = fcport->qedf;
+	lport = qedf->lport;
+
 	if (lport->state != LPORT_ST_READY || !(lport->link_up)) {
 		QEDF_ERR(&(qedf->dbg_ctx), "link is not ready\n");
 		rc = 1;
@@ -1729,6 +1735,13 @@ int qedf_initiate_cleanup(struct qedf_ioreq *io_req,
 		return SUCCESS;
 	}
 
+	/* Sanity check qedf_rport before dereferencing any pointers */
+	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+		QEDF_ERR(NULL, "tgt not offloaded\n");
+		rc = 1;
+		return SUCCESS;
+	}
+
 	qedf = fcport->qedf;
 	if (!qedf) {
 		QEDF_ERR(NULL, "qedf is NULL.\n");
@@ -1837,7 +1850,7 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd,
 		return FAILED;
 	}
 
-	if (!(test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags))) {
+	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
 		QEDF_ERR(&(qedf->dbg_ctx), "fcport not offloaded\n");
 		rc = FAILED;
 		return FAILED;