diff --git a/Makefile b/Makefile
index 3d94974..6ff6f2d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 37
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc5-stor3
 NAME = Flesh-Eating Bats with Fangs
 
 # *DOCUMENTATION*
diff --git a/block/blk-map.c b/block/blk-map.c
index 5d5dbe4..e663ac2 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -201,12 +201,13 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	for (i = 0; i < iov_count; i++) {
 		unsigned long uaddr = (unsigned long)iov[i].iov_base;
 
+		if (!iov[i].iov_len)
+			return -EINVAL;
+
 		if (uaddr & queue_dma_alignment(q)) {
 			unaligned = 1;
 			break;
 		}
-		if (!iov[i].iov_len)
-			return -EINVAL;
 	}
 
 	if (unaligned || (q->dma_pad_mask & len) || map_data)
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 77b7c26..74bc4a7 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -21,7 +21,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 		return 0;
 
 	fbio = bio;
-	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
+	cluster = blk_queue_cluster(q);
 	seg_size = 0;
 	nr_phys_segs = 0;
 	for_each_bio(bio) {
@@ -87,7 +87,7 @@ EXPORT_SYMBOL(blk_recount_segments);
 static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 				   struct bio *nxt)
 {
-	if (!test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
+	if (!blk_queue_cluster(q))
 		return 0;
 
 	if (bio->bi_seg_back_size + nxt->bi_seg_front_size >
@@ -123,7 +123,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	int nsegs, cluster;
 
 	nsegs = 0;
-	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
+	cluster = blk_queue_cluster(q);
 
 	/*
 	 * for each bio in rq
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 701859f..e55f5fc 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -126,7 +126,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->alignment_offset = 0;
 	lim->io_opt = 0;
 	lim->misaligned = 0;
-	lim->no_cluster = 0;
+	lim->cluster = 1;
 }
 EXPORT_SYMBOL(blk_set_default_limits);
 
@@ -464,15 +464,6 @@ EXPORT_SYMBOL(blk_queue_io_opt);
 void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 {
 	blk_stack_limits(&t->limits, &b->limits, 0);
-
-	if (!t->queue_lock)
-		WARN_ON_ONCE(1);
-	else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) {
-		unsigned long flags;
-		spin_lock_irqsave(t->queue_lock, flags);
-		queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
-		spin_unlock_irqrestore(t->queue_lock, flags);
-	}
 }
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
@@ -545,7 +536,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->io_min = max(t->io_min, b->io_min);
 	t->io_opt = lcm(t->io_opt, b->io_opt);
 
-	t->no_cluster |= b->no_cluster;
+	t->cluster &= b->cluster;
 	t->discard_zeroes_data &= b->discard_zeroes_data;
 
 	/* Physical block size a multiple of the logical block size? */
@@ -641,7 +632,6 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 		       sector_t offset)
 {
 	struct request_queue *t = disk->queue;
-	struct request_queue *b = bdev_get_queue(bdev);
 
 	if (bdev_stack_limits(&t->limits, bdev, offset >> 9) < 0) {
 		char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE];
@@ -652,17 +642,6 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 		printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n",
 		       top, bottom);
 	}
-
-	if (!t->queue_lock)
-		WARN_ON_ONCE(1);
-	else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(t->queue_lock, flags);
-		if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags))
-			queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
-		spin_unlock_irqrestore(t->queue_lock, flags);
-	}
 }
 EXPORT_SYMBOL(disk_stack_limits);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 013457f..41fb691 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -119,7 +119,7 @@ static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *
 
 static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page)
 {
-	if (test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
+	if (blk_queue_cluster(q))
 		return queue_var_show(queue_max_segment_size(q), (page));
 
 	return queue_var_show(PAGE_CACHE_SIZE, (page));
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 004be80..381b09b 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -355,6 +355,12 @@ throtl_start_new_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw)
 			tg->slice_end[rw], jiffies);
 }
 
+static inline void throtl_set_slice_end(struct throtl_data *td,
+		struct throtl_grp *tg, bool rw, unsigned long jiffy_end)
+{
+	tg->slice_end[rw] = roundup(jiffy_end, throtl_slice);
+}
+
 static inline void throtl_extend_slice(struct throtl_data *td,
 		struct throtl_grp *tg, bool rw, unsigned long jiffy_end)
 {
@@ -391,6 +397,16 @@ throtl_trim_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw)
 	if (throtl_slice_used(td, tg, rw))
 		return;
 
+	/*
+	 * A bio has been dispatched. Also adjust slice_end. It might happen
+	 * that initially cgroup limit was very low resulting in high
+	 * slice_end, but later limit was bumped up and bio was dispached
+	 * sooner, then we need to reduce slice_end. A high bogus slice_end
+	 * is bad because it does not allow new slice to start.
+	 */
+
+	throtl_set_slice_end(td, tg, rw, jiffies + throtl_slice);
+
 	time_elapsed = jiffies - tg->slice_start[rw];
 
 	nr_slices = time_elapsed / throtl_slice;
@@ -709,26 +725,21 @@ static void throtl_process_limit_change(struct throtl_data *td)
 	struct throtl_grp *tg;
 	struct hlist_node *pos, *n;
 
-	/*
-	 * Make sure atomic_inc() effects from
-	 * throtl_update_blkio_group_read_bps(), group of functions are
-	 * visible.
-	 * Is this required or smp_mb__after_atomic_inc() was suffcient
-	 * after the atomic_inc().
-	 */
-	smp_rmb();
 	if (!atomic_read(&td->limits_changed))
 		return;
 
 	throtl_log(td, "limit changed =%d", atomic_read(&td->limits_changed));
 
-	hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) {
-		/*
-		 * Do I need an smp_rmb() here to make sure tg->limits_changed
-		 * update is visible. I am relying on smp_rmb() at the
-		 * beginning of function and not putting a new one here.
-		 */
+	/*
+	 * Make sure updates from throtl_update_blkio_group_read_bps() group
+	 * of functions to tg->limits_changed are visible. We do not
+	 * want update td->limits_changed to be visible but update to
+	 * tg->limits_changed not being visible yet on this cpu. Hence
+	 * the read barrier.
+	 */
+	smp_rmb();
 
+	hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) {
 		if (throtl_tg_on_rr(tg) && tg->limits_changed) {
 			throtl_log_tg(td, tg, "limit change rbps=%llu wbps=%llu"
 				" riops=%u wiops=%u", tg->bps[READ],
diff --git a/block/bsg.c b/block/bsg.c
index f20d6a7..0c8b64a 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -250,6 +250,14 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
 	int ret, rw;
 	unsigned int dxfer_len;
 	void *dxferp = NULL;
+	struct bsg_class_device *bcd = &q->bsg_dev;
+
+	/* if the LLD has been removed then the bsg_unregister_queue will
+	 * eventually be called and the class_dev was freed, so we can no
+	 * longer use this request_queue. Return no such address.
+	 */
+	if (!bcd->class_dev)
+		return ERR_PTR(-ENXIO);
 
 	dprintk("map hdr %llx/%u %llx/%u\n", (unsigned long long) hdr->dout_xferp,
 		hdr->dout_xfer_len, (unsigned long long) hdr->din_xferp,
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 11ec911..a1c6fa8 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -90,6 +90,14 @@ config SATA_INIC162X
 	help
 	  This option enables support for Initio 162x Serial ATA.
 
+config SATA_ACARD_AHCI
+	tristate "ACard AHCI variant (ATP 8620)"
+	depends on PCI
+	help
+	  This option enables support for Acard.
+
+	  If unsure, say N.
+
 config SATA_SIL24
 	tristate "Silicon Image 3124/3132 SATA support"
 	depends on PCI
diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile
index c501af5..3ef3bdb 100644
--- a/drivers/ata/Makefile
+++ b/drivers/ata/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_ATA)		+= libata.o
 
 # non-SFF interface
 obj-$(CONFIG_SATA_AHCI)		+= ahci.o libahci.o
+obj-$(CONFIG_SATA_ACARD_AHCI)	+= acard-ahci.o libahci.o
 obj-$(CONFIG_SATA_AHCI_PLATFORM) += ahci_platform.o libahci.o
 obj-$(CONFIG_SATA_FSL)		+= sata_fsl.o
 obj-$(CONFIG_SATA_INIC162X)	+= sata_inic162x.o
diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c
new file mode 100644
index 0000000..339c210
--- /dev/null
+++ b/drivers/ata/acard-ahci.c
@@ -0,0 +1,528 @@
+
+/*
+ *  acard-ahci.c - ACard AHCI SATA support
+ *
+ *  Maintained by:  Jeff Garzik <jgarzik@pobox.com>
+ *		    Please ALWAYS copy linux-ide@vger.kernel.org
+ *		    on emails.
+ *
+ *  Copyright 2010 Red Hat, 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
+ *  the Free Software Foundation; either version 2, or (at your option)
+ *  any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; see the file COPYING.  If not, write to
+ *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ *
+ * libata documentation is available via 'make {ps|pdf}docs',
+ * as Documentation/DocBook/libata.*
+ *
+ * AHCI hardware documentation:
+ * http://www.intel.com/technology/serialata/pdf/rev1_0.pdf
+ * http://www.intel.com/technology/serialata/pdf/rev1_1.pdf
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/blkdev.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/dma-mapping.h>
+#include <linux/device.h>
+#include <linux/dmi.h>
+#include <linux/gfp.h>
+#include <scsi/scsi_host.h>
+#include <scsi/scsi_cmnd.h>
+#include <linux/libata.h>
+#include "ahci.h"
+
+#define DRV_NAME	"acard-ahci"
+#define DRV_VERSION	"1.0"
+
+/*
+  Received FIS structure limited to 80h.
+*/
+
+#define ACARD_AHCI_RX_FIS_SZ 128
+
+enum {
+	AHCI_PCI_BAR		= 5,
+};
+
+enum board_ids {
+	board_acard_ahci,
+};
+
+struct acard_sg {
+	__le32			addr;
+	__le32			addr_hi;
+	__le32			reserved;
+	__le32			size;	 /* bit 31 (EOT) max==0x10000 (64k) */
+};
+
+static void acard_ahci_qc_prep(struct ata_queued_cmd *qc);
+static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc);
+static int acard_ahci_port_start(struct ata_port *ap);
+static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
+
+#ifdef CONFIG_PM
+static int acard_ahci_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg);
+static int acard_ahci_pci_device_resume(struct pci_dev *pdev);
+#endif
+
+static struct scsi_host_template acard_ahci_sht = {
+	AHCI_SHT("acard-ahci"),
+};
+
+static struct ata_port_operations acard_ops = {
+	.inherits		= &ahci_ops,
+	.qc_prep		= acard_ahci_qc_prep,
+	.qc_fill_rtf		= acard_ahci_qc_fill_rtf,
+	.port_start             = acard_ahci_port_start,
+};
+
+#define AHCI_HFLAGS(flags)	.private_data	= (void *)(flags)
+
+static const struct ata_port_info acard_ahci_port_info[] = {
+	[board_acard_ahci] =
+	{
+		AHCI_HFLAGS	(AHCI_HFLAG_NO_NCQ),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &acard_ops,
+	},
+};
+
+static const struct pci_device_id acard_ahci_pci_tbl[] = {
+	/* ACard */
+	{ PCI_VDEVICE(ARTOP, 0x000d), board_acard_ahci }, /* ATP8620 */
+
+	{ }    /* terminate list */
+};
+
+static struct pci_driver acard_ahci_pci_driver = {
+	.name			= DRV_NAME,
+	.id_table		= acard_ahci_pci_tbl,
+	.probe			= acard_ahci_init_one,
+	.remove			= ata_pci_remove_one,
+#ifdef CONFIG_PM
+	.suspend		= acard_ahci_pci_device_suspend,
+	.resume			= acard_ahci_pci_device_resume,
+#endif
+};
+
+#ifdef CONFIG_PM
+static int acard_ahci_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg)
+{
+	struct ata_host *host = dev_get_drvdata(&pdev->dev);
+	struct ahci_host_priv *hpriv = host->private_data;
+	void __iomem *mmio = hpriv->mmio;
+	u32 ctl;
+
+	if (mesg.event & PM_EVENT_SUSPEND &&
+	    hpriv->flags & AHCI_HFLAG_NO_SUSPEND) {
+		dev_printk(KERN_ERR, &pdev->dev,
+			   "BIOS update required for suspend/resume\n");
+		return -EIO;
+	}
+
+	if (mesg.event & PM_EVENT_SLEEP) {
+		/* AHCI spec rev1.1 section 8.3.3:
+		 * Software must disable interrupts prior to requesting a
+		 * transition of the HBA to D3 state.
+		 */
+		ctl = readl(mmio + HOST_CTL);
+		ctl &= ~HOST_IRQ_EN;
+		writel(ctl, mmio + HOST_CTL);
+		readl(mmio + HOST_CTL); /* flush */
+	}
+
+	return ata_pci_device_suspend(pdev, mesg);
+}
+
+static int acard_ahci_pci_device_resume(struct pci_dev *pdev)
+{
+	struct ata_host *host = dev_get_drvdata(&pdev->dev);
+	int rc;
+
+	rc = ata_pci_device_do_resume(pdev);
+	if (rc)
+		return rc;
+
+	if (pdev->dev.power.power_state.event == PM_EVENT_SUSPEND) {
+		rc = ahci_reset_controller(host);
+		if (rc)
+			return rc;
+
+		ahci_init_controller(host);
+	}
+
+	ata_host_resume(host);
+
+	return 0;
+}
+#endif
+
+static int acard_ahci_configure_dma_masks(struct pci_dev *pdev, int using_dac)
+{
+	int rc;
+
+	if (using_dac &&
+	    !pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+		rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+		if (rc) {
+			rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+			if (rc) {
+				dev_printk(KERN_ERR, &pdev->dev,
+					   "64-bit DMA enable failed\n");
+				return rc;
+			}
+		}
+	} else {
+		rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		if (rc) {
+			dev_printk(KERN_ERR, &pdev->dev,
+				   "32-bit DMA enable failed\n");
+			return rc;
+		}
+		rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+		if (rc) {
+			dev_printk(KERN_ERR, &pdev->dev,
+				   "32-bit consistent DMA enable failed\n");
+			return rc;
+		}
+	}
+	return 0;
+}
+
+static void acard_ahci_pci_print_info(struct ata_host *host)
+{
+	struct pci_dev *pdev = to_pci_dev(host->dev);
+	u16 cc;
+	const char *scc_s;
+
+	pci_read_config_word(pdev, 0x0a, &cc);
+	if (cc == PCI_CLASS_STORAGE_IDE)
+		scc_s = "IDE";
+	else if (cc == PCI_CLASS_STORAGE_SATA)
+		scc_s = "SATA";
+	else if (cc == PCI_CLASS_STORAGE_RAID)
+		scc_s = "RAID";
+	else
+		scc_s = "unknown";
+
+	ahci_print_info(host, scc_s);
+}
+
+static unsigned int acard_ahci_fill_sg(struct ata_queued_cmd *qc, void *cmd_tbl)
+{
+	struct scatterlist *sg;
+	struct acard_sg *acard_sg = cmd_tbl + AHCI_CMD_TBL_HDR_SZ;
+	unsigned int si, last_si = 0;
+
+	VPRINTK("ENTER\n");
+
+	/*
+	 * Next, the S/G list.
+	 */
+	for_each_sg(qc->sg, sg, qc->n_elem, si) {
+		dma_addr_t addr = sg_dma_address(sg);
+		u32 sg_len = sg_dma_len(sg);
+
+		/*
+		 * ACard note:
+		 * We must set an end-of-table (EOT) bit,
+		 * and the segment cannot exceed 64k (0x10000)
+		 */
+		acard_sg[si].addr = cpu_to_le32(addr & 0xffffffff);
+		acard_sg[si].addr_hi = cpu_to_le32((addr >> 16) >> 16);
+		acard_sg[si].size = cpu_to_le32(sg_len);
+		last_si = si;
+	}
+
+	acard_sg[last_si].size |= cpu_to_le32(1 << 31);	/* set EOT */
+
+	return si;
+}
+
+static void acard_ahci_qc_prep(struct ata_queued_cmd *qc)
+{
+	struct ata_port *ap = qc->ap;
+	struct ahci_port_priv *pp = ap->private_data;
+	int is_atapi = ata_is_atapi(qc->tf.protocol);
+	void *cmd_tbl;
+	u32 opts;
+	const u32 cmd_fis_len = 5; /* five dwords */
+	unsigned int n_elem;
+
+	/*
+	 * Fill in command table information.  First, the header,
+	 * a SATA Register - Host to Device command FIS.
+	 */
+	cmd_tbl = pp->cmd_tbl + qc->tag * AHCI_CMD_TBL_SZ;
+
+	ata_tf_to_fis(&qc->tf, qc->dev->link->pmp, 1, cmd_tbl);
+	if (is_atapi) {
+		memset(cmd_tbl + AHCI_CMD_TBL_CDB, 0, 32);
+		memcpy(cmd_tbl + AHCI_CMD_TBL_CDB, qc->cdb, qc->dev->cdb_len);
+	}
+
+	n_elem = 0;
+	if (qc->flags & ATA_QCFLAG_DMAMAP)
+		n_elem = acard_ahci_fill_sg(qc, cmd_tbl);
+
+	/*
+	 * Fill in command slot information.
+	 *
+	 * ACard note: prd table length not filled in
+	 */
+	opts = cmd_fis_len | (qc->dev->link->pmp << 12);
+	if (qc->tf.flags & ATA_TFLAG_WRITE)
+		opts |= AHCI_CMD_WRITE;
+	if (is_atapi)
+		opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH;
+
+	ahci_fill_cmd_slot(pp, qc->tag, opts);
+}
+
+static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc)
+{
+	struct ahci_port_priv *pp = qc->ap->private_data;
+	u8 *rx_fis = pp->rx_fis;
+
+	if (pp->fbs_enabled)
+		rx_fis += qc->dev->link->pmp * ACARD_AHCI_RX_FIS_SZ;
+
+	/*
+	 * After a successful execution of an ATA PIO data-in command,
+	 * the device doesn't send D2H Reg FIS to update the TF and
+	 * the host should take TF and E_Status from the preceding PIO
+	 * Setup FIS.
+	 */
+	if (qc->tf.protocol == ATA_PROT_PIO && qc->dma_dir == DMA_FROM_DEVICE &&
+	    !(qc->flags & ATA_QCFLAG_FAILED)) {
+		ata_tf_from_fis(rx_fis + RX_FIS_PIO_SETUP, &qc->result_tf);
+		qc->result_tf.command = (rx_fis + RX_FIS_PIO_SETUP)[15];
+	} else
+		ata_tf_from_fis(rx_fis + RX_FIS_D2H_REG, &qc->result_tf);
+
+	return true;
+}
+
+static int acard_ahci_port_start(struct ata_port *ap)
+{
+	struct ahci_host_priv *hpriv = ap->host->private_data;
+	struct device *dev = ap->host->dev;
+	struct ahci_port_priv *pp;
+	void *mem;
+	dma_addr_t mem_dma;
+	size_t dma_sz, rx_fis_sz;
+
+	pp = devm_kzalloc(dev, sizeof(*pp), GFP_KERNEL);
+	if (!pp)
+		return -ENOMEM;
+
+	/* check FBS capability */
+	if ((hpriv->cap & HOST_CAP_FBS) && sata_pmp_supported(ap)) {
+		void __iomem *port_mmio = ahci_port_base(ap);
+		u32 cmd = readl(port_mmio + PORT_CMD);
+		if (cmd & PORT_CMD_FBSCP)
+			pp->fbs_supported = true;
+		else if (hpriv->flags & AHCI_HFLAG_YES_FBS) {
+			dev_printk(KERN_INFO, dev,
+				   "port %d can do FBS, forcing FBSCP\n",
+				   ap->port_no);
+			pp->fbs_supported = true;
+		} else
+			dev_printk(KERN_WARNING, dev,
+				   "port %d is not capable of FBS\n",
+				   ap->port_no);
+	}
+
+	if (pp->fbs_supported) {
+		dma_sz = AHCI_PORT_PRIV_FBS_DMA_SZ;
+		rx_fis_sz = ACARD_AHCI_RX_FIS_SZ * 16;
+	} else {
+		dma_sz = AHCI_PORT_PRIV_DMA_SZ;
+		rx_fis_sz = ACARD_AHCI_RX_FIS_SZ;
+	}
+
+	mem = dmam_alloc_coherent(dev, dma_sz, &mem_dma, GFP_KERNEL);
+	if (!mem)
+		return -ENOMEM;
+	memset(mem, 0, dma_sz);
+
+	/*
+	 * First item in chunk of DMA memory: 32-slot command table,
+	 * 32 bytes each in size
+	 */
+	pp->cmd_slot = mem;
+	pp->cmd_slot_dma = mem_dma;
+
+	mem += AHCI_CMD_SLOT_SZ;
+	mem_dma += AHCI_CMD_SLOT_SZ;
+
+	/*
+	 * Second item: Received-FIS area
+	 */
+	pp->rx_fis = mem;
+	pp->rx_fis_dma = mem_dma;
+
+	mem += rx_fis_sz;
+	mem_dma += rx_fis_sz;
+
+	/*
+	 * Third item: data area for storing a single command
+	 * and its scatter-gather table
+	 */
+	pp->cmd_tbl = mem;
+	pp->cmd_tbl_dma = mem_dma;
+
+	/*
+	 * Save off initial list of interrupts to be enabled.
+	 * This could be changed later
+	 */
+	pp->intr_mask = DEF_PORT_IRQ;
+
+	ap->private_data = pp;
+
+	/* engage engines, captain */
+	return ahci_port_resume(ap);
+}
+
+static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	static int printed_version;
+	unsigned int board_id = ent->driver_data;
+	struct ata_port_info pi = acard_ahci_port_info[board_id];
+	const struct ata_port_info *ppi[] = { &pi, NULL };
+	struct device *dev = &pdev->dev;
+	struct ahci_host_priv *hpriv;
+	struct ata_host *host;
+	int n_ports, i, rc;
+
+	VPRINTK("ENTER\n");
+
+	WARN_ON(ATA_MAX_QUEUE > AHCI_MAX_CMDS);
+
+	if (!printed_version++)
+		dev_printk(KERN_DEBUG, &pdev->dev, "version " DRV_VERSION "\n");
+
+	/* acquire resources */
+	rc = pcim_enable_device(pdev);
+	if (rc)
+		return rc;
+
+	/* AHCI controllers often implement SFF compatible interface.
+	 * Grab all PCI BARs just in case.
+	 */
+	rc = pcim_iomap_regions_request_all(pdev, 1 << AHCI_PCI_BAR, DRV_NAME);
+	if (rc == -EBUSY)
+		pcim_pin_device(pdev);
+	if (rc)
+		return rc;
+
+	hpriv = devm_kzalloc(dev, sizeof(*hpriv), GFP_KERNEL);
+	if (!hpriv)
+		return -ENOMEM;
+	hpriv->flags |= (unsigned long)pi.private_data;
+
+	if (!(hpriv->flags & AHCI_HFLAG_NO_MSI))
+		pci_enable_msi(pdev);
+
+	hpriv->mmio = pcim_iomap_table(pdev)[AHCI_PCI_BAR];
+
+	/* save initial config */
+	ahci_save_initial_config(&pdev->dev, hpriv, 0, 0);
+
+	/* prepare host */
+	if (hpriv->cap & HOST_CAP_NCQ)
+		pi.flags |= ATA_FLAG_NCQ;
+
+	if (hpriv->cap & HOST_CAP_PMP)
+		pi.flags |= ATA_FLAG_PMP;
+
+	ahci_set_em_messages(hpriv, &pi);
+
+	/* CAP.NP sometimes indicate the index of the last enabled
+	 * port, at other times, that of the last possible port, so
+	 * determining the maximum port number requires looking at
+	 * both CAP.NP and port_map.
+	 */
+	n_ports = max(ahci_nr_ports(hpriv->cap), fls(hpriv->port_map));
+
+	host = ata_host_alloc_pinfo(&pdev->dev, ppi, n_ports);
+	if (!host)
+		return -ENOMEM;
+	host->private_data = hpriv;
+
+	if (!(hpriv->cap & HOST_CAP_SSS) || ahci_ignore_sss)
+		host->flags |= ATA_HOST_PARALLEL_SCAN;
+	else
+		printk(KERN_INFO "ahci: SSS flag set, parallel bus scan disabled\n");
+
+	for (i = 0; i < host->n_ports; i++) {
+		struct ata_port *ap = host->ports[i];
+
+		ata_port_pbar_desc(ap, AHCI_PCI_BAR, -1, "abar");
+		ata_port_pbar_desc(ap, AHCI_PCI_BAR,
+				   0x100 + ap->port_no * 0x80, "port");
+
+		/* set initial link pm policy */
+		/*
+		ap->pm_policy = NOT_AVAILABLE;
+		*/
+		/* disabled/not-implemented port */
+		if (!(hpriv->port_map & (1 << i)))
+			ap->ops = &ata_dummy_port_ops;
+	}
+
+	/* initialize adapter */
+	rc = acard_ahci_configure_dma_masks(pdev, hpriv->cap & HOST_CAP_64);
+	if (rc)
+		return rc;
+
+	rc = ahci_reset_controller(host);
+	if (rc)
+		return rc;
+
+	ahci_init_controller(host);
+	acard_ahci_pci_print_info(host);
+
+	pci_set_master(pdev);
+	return ata_host_activate(host, pdev->irq, ahci_interrupt, IRQF_SHARED,
+				 &acard_ahci_sht);
+}
+
+static int __init acard_ahci_init(void)
+{
+	return pci_register_driver(&acard_ahci_pci_driver);
+}
+
+static void __exit acard_ahci_exit(void)
+{
+	pci_unregister_driver(&acard_ahci_pci_driver);
+}
+
+MODULE_AUTHOR("Jeff Garzik");
+MODULE_DESCRIPTION("ACard AHCI SATA low-level driver");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(pci, acard_ahci_pci_tbl);
+MODULE_VERSION(DRV_VERSION);
+
+module_init(acard_ahci_init);
+module_exit(acard_ahci_exit);
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 329cbbb..3e606c3 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -311,6 +311,8 @@ extern struct device_attribute *ahci_sdev_attrs[];
 
 extern struct ata_port_operations ahci_ops;
 
+void ahci_fill_cmd_slot(struct ahci_port_priv *pp, unsigned int tag,
+			u32 opts);
 void ahci_save_initial_config(struct device *dev,
 			      struct ahci_host_priv *hpriv,
 			      unsigned int force_port_map,
@@ -326,6 +328,7 @@ int ahci_stop_engine(struct ata_port *ap);
 void ahci_start_engine(struct ata_port *ap);
 int ahci_check_ready(struct ata_link *link);
 int ahci_kick_engine(struct ata_port *ap);
+int ahci_port_resume(struct ata_port *ap);
 void ahci_set_em_messages(struct ahci_host_priv *hpriv,
 			  struct ata_port_info *pi);
 int ahci_reset_em(struct ata_host *host);
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index ebc08d6..26d4523 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -87,10 +87,7 @@ static int ahci_hardreset(struct ata_link *link, unsigned int *class,
 static void ahci_postreset(struct ata_link *link, unsigned int *class);
 static void ahci_error_handler(struct ata_port *ap);
 static void ahci_post_internal_cmd(struct ata_queued_cmd *qc);
-static int ahci_port_resume(struct ata_port *ap);
 static void ahci_dev_config(struct ata_device *dev);
-static void ahci_fill_cmd_slot(struct ahci_port_priv *pp, unsigned int tag,
-			       u32 opts);
 #ifdef CONFIG_PM
 static int ahci_port_suspend(struct ata_port *ap, pm_message_t mesg);
 #endif
@@ -1133,8 +1130,8 @@ static unsigned int ahci_dev_classify(struct ata_port *ap)
 	return ata_dev_classify(&tf);
 }
 
-static void ahci_fill_cmd_slot(struct ahci_port_priv *pp, unsigned int tag,
-			       u32 opts)
+void ahci_fill_cmd_slot(struct ahci_port_priv *pp, unsigned int tag,
+			u32 opts)
 {
 	dma_addr_t cmd_tbl_dma;
 
@@ -1145,6 +1142,7 @@ static void ahci_fill_cmd_slot(struct ahci_port_priv *pp, unsigned int tag,
 	pp->cmd_slot[tag].tbl_addr = cpu_to_le32(cmd_tbl_dma & 0xffffffff);
 	pp->cmd_slot[tag].tbl_addr_hi = cpu_to_le32((cmd_tbl_dma >> 16) >> 16);
 }
+EXPORT_SYMBOL_GPL(ahci_fill_cmd_slot);
 
 int ahci_kick_engine(struct ata_port *ap)
 {
@@ -1918,7 +1916,7 @@ static void ahci_pmp_detach(struct ata_port *ap)
 	writel(pp->intr_mask, port_mmio + PORT_IRQ_MASK);
 }
 
-static int ahci_port_resume(struct ata_port *ap)
+int ahci_port_resume(struct ata_port *ap)
 {
 	ahci_power_up(ap);
 	ahci_start_port(ap);
@@ -1930,6 +1928,7 @@ static int ahci_port_resume(struct ata_port *ap)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ahci_port_resume);
 
 #ifdef CONFIG_PM
 static int ahci_port_suspend(struct ata_port *ap, pm_message_t mesg)
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 66aa4be..5defc74 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -346,12 +346,11 @@ struct device_attribute *ata_common_sdev_attrs[] = {
 };
 EXPORT_SYMBOL_GPL(ata_common_sdev_attrs);
 
-static void ata_scsi_invalid_field(struct scsi_cmnd *cmd,
-				   void (*done)(struct scsi_cmnd *))
+static void ata_scsi_invalid_field(struct scsi_cmnd *cmd)
 {
 	ata_scsi_set_sense(cmd, ILLEGAL_REQUEST, 0x24, 0x0);
 	/* "Invalid field in cbd" */
-	done(cmd);
+	cmd->scsi_done(cmd);
 }
 
 /**
@@ -719,7 +718,6 @@ EXPORT_SYMBOL_GPL(ata_scsi_ioctl);
  *	ata_scsi_qc_new - acquire new ata_queued_cmd reference
  *	@dev: ATA device to which the new command is attached
  *	@cmd: SCSI command that originated this ATA command
- *	@done: SCSI command completion function
  *
  *	Obtain a reference to an unused ata_queued_cmd structure,
  *	which is the basic libata structure representing a single
@@ -736,21 +734,20 @@ EXPORT_SYMBOL_GPL(ata_scsi_ioctl);
  *	Command allocated, or %NULL if none available.
  */
 static struct ata_queued_cmd *ata_scsi_qc_new(struct ata_device *dev,
-					      struct scsi_cmnd *cmd,
-					      void (*done)(struct scsi_cmnd *))
+					      struct scsi_cmnd *cmd)
 {
 	struct ata_queued_cmd *qc;
 
 	qc = ata_qc_new_init(dev);
 	if (qc) {
 		qc->scsicmd = cmd;
-		qc->scsidone = done;
+		qc->scsidone = cmd->scsi_done;
 
 		qc->sg = scsi_sglist(cmd);
 		qc->n_elem = scsi_sg_count(cmd);
 	} else {
 		cmd->result = (DID_OK << 16) | (QUEUE_FULL << 1);
-		done(cmd);
+		cmd->scsi_done(cmd);
 	}
 
 	return qc;
@@ -1735,7 +1732,6 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc)
  *	ata_scsi_translate - Translate then issue SCSI command to ATA device
  *	@dev: ATA device to which the command is addressed
  *	@cmd: SCSI command to execute
- *	@done: SCSI command completion function
  *	@xlat_func: Actor which translates @cmd to an ATA taskfile
  *
  *	Our ->queuecommand() function has decided that the SCSI
@@ -1759,7 +1755,6 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc)
  *	needs to be deferred.
  */
 static int ata_scsi_translate(struct ata_device *dev, struct scsi_cmnd *cmd,
-			      void (*done)(struct scsi_cmnd *),
 			      ata_xlat_func_t xlat_func)
 {
 	struct ata_port *ap = dev->link->ap;
@@ -1768,7 +1763,7 @@ static int ata_scsi_translate(struct ata_device *dev, struct scsi_cmnd *cmd,
 
 	VPRINTK("ENTER\n");
 
-	qc = ata_scsi_qc_new(dev, cmd, done);
+	qc = ata_scsi_qc_new(dev, cmd);
 	if (!qc)
 		goto err_mem;
 
@@ -1804,14 +1799,14 @@ static int ata_scsi_translate(struct ata_device *dev, struct scsi_cmnd *cmd,
 
 early_finish:
 	ata_qc_free(qc);
-	qc->scsidone(cmd);
+	cmd->scsi_done(cmd);
 	DPRINTK("EXIT - early finish (good or error)\n");
 	return 0;
 
 err_did:
 	ata_qc_free(qc);
 	cmd->result = (DID_ERROR << 16);
-	qc->scsidone(cmd);
+	cmd->scsi_done(cmd);
 err_mem:
 	DPRINTK("EXIT - internal\n");
 	return 0;
@@ -3116,7 +3111,6 @@ static inline void ata_scsi_dump_cdb(struct ata_port *ap,
 }
 
 static inline int __ata_scsi_queuecmd(struct scsi_cmnd *scmd,
-				      void (*done)(struct scsi_cmnd *),
 				      struct ata_device *dev)
 {
 	u8 scsi_op = scmd->cmnd[0];
@@ -3150,9 +3144,9 @@ static inline int __ata_scsi_queuecmd(struct scsi_cmnd *scmd,
 	}
 
 	if (xlat_func)
-		rc = ata_scsi_translate(dev, scmd, done, xlat_func);
+		rc = ata_scsi_translate(dev, scmd, xlat_func);
 	else
-		ata_scsi_simulate(dev, scmd, done);
+		ata_scsi_simulate(dev, scmd);
 
 	return rc;
 
@@ -3160,7 +3154,7 @@ static inline int __ata_scsi_queuecmd(struct scsi_cmnd *scmd,
 	DPRINTK("bad CDB len=%u, scsi_op=0x%02x, max=%u\n",
 		scmd->cmd_len, scsi_op, dev->cdb_len);
 	scmd->result = DID_ERROR << 16;
-	done(scmd);
+	scmd->scsi_done(scmd);
 	return 0;
 }
 
@@ -3199,7 +3193,7 @@ int ata_scsi_queuecmd(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
 
 	dev = ata_scsi_find_dev(ap, scsidev);
 	if (likely(dev))
-		rc = __ata_scsi_queuecmd(cmd, cmd->scsi_done, dev);
+		rc = __ata_scsi_queuecmd(cmd, dev);
 	else {
 		cmd->result = (DID_BAD_TARGET << 16);
 		cmd->scsi_done(cmd);
@@ -3214,7 +3208,6 @@ int ata_scsi_queuecmd(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
  *	ata_scsi_simulate - simulate SCSI command on ATA device
  *	@dev: the target device
  *	@cmd: SCSI command being sent to device.
- *	@done: SCSI command completion function.
  *
  *	Interprets and directly executes a select list of SCSI commands
  *	that can be handled internally.
@@ -3223,8 +3216,7 @@ int ata_scsi_queuecmd(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
  *	spin_lock_irqsave(host lock)
  */
 
-void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd,
-		      void (*done)(struct scsi_cmnd *))
+void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd)
 {
 	struct ata_scsi_args args;
 	const u8 *scsicmd = cmd->cmnd;
@@ -3233,17 +3225,17 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd,
 	args.dev = dev;
 	args.id = dev->id;
 	args.cmd = cmd;
-	args.done = done;
+	args.done = cmd->scsi_done;
 
 	switch(scsicmd[0]) {
 	/* TODO: worth improving? */
 	case FORMAT_UNIT:
-		ata_scsi_invalid_field(cmd, done);
+		ata_scsi_invalid_field(cmd);
 		break;
 
 	case INQUIRY:
 		if (scsicmd[1] & 2)	           /* is CmdDt set?  */
-			ata_scsi_invalid_field(cmd, done);
+			ata_scsi_invalid_field(cmd);
 		else if ((scsicmd[1] & 1) == 0)    /* is EVPD clear? */
 			ata_scsi_rbuf_fill(&args, ata_scsiop_inq_std);
 		else switch (scsicmd[2]) {
@@ -3269,7 +3261,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd,
 			ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b2);
 			break;
 		default:
-			ata_scsi_invalid_field(cmd, done);
+			ata_scsi_invalid_field(cmd);
 			break;
 		}
 		break;
@@ -3281,7 +3273,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd,
 
 	case MODE_SELECT:	/* unconditionally return */
 	case MODE_SELECT_10:	/* bad-field-in-cdb */
-		ata_scsi_invalid_field(cmd, done);
+		ata_scsi_invalid_field(cmd);
 		break;
 
 	case READ_CAPACITY:
@@ -3292,7 +3284,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd,
 		if ((scsicmd[1] & 0x1f) == SAI_READ_CAPACITY_16)
 			ata_scsi_rbuf_fill(&args, ata_scsiop_read_cap);
 		else
-			ata_scsi_invalid_field(cmd, done);
+			ata_scsi_invalid_field(cmd);
 		break;
 
 	case REPORT_LUNS:
@@ -3302,7 +3294,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd,
 	case REQUEST_SENSE:
 		ata_scsi_set_sense(cmd, 0, 0, 0);
 		cmd->result = (DRIVER_SENSE << 24);
-		done(cmd);
+		cmd->scsi_done(cmd);
 		break;
 
 	/* if we reach this, then writeback caching is disabled,
@@ -3324,14 +3316,14 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd,
 		if ((tmp8 == 0x4) && (!scsicmd[3]) && (!scsicmd[4]))
 			ata_scsi_rbuf_fill(&args, ata_scsiop_noop);
 		else
-			ata_scsi_invalid_field(cmd, done);
+			ata_scsi_invalid_field(cmd);
 		break;
 
 	/* all other commands */
 	default:
 		ata_scsi_set_sense(cmd, ILLEGAL_REQUEST, 0x20, 0x0);
 		/* "Invalid command operation code" */
-		done(cmd);
+		cmd->scsi_done(cmd);
 		break;
 	}
 }
@@ -3858,7 +3850,6 @@ EXPORT_SYMBOL_GPL(ata_sas_slave_configure);
 /**
  *	ata_sas_queuecmd - Issue SCSI cdb to libata-managed device
  *	@cmd: SCSI command to be sent
- *	@done: Completion function, called when command is complete
  *	@ap:	ATA port to which the command is being sent
  *
  *	RETURNS:
@@ -3866,18 +3857,17 @@ EXPORT_SYMBOL_GPL(ata_sas_slave_configure);
  *	0 otherwise.
  */
 
-int ata_sas_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *),
-		     struct ata_port *ap)
+int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap)
 {
 	int rc = 0;
 
 	ata_scsi_dump_cdb(ap, cmd);
 
 	if (likely(ata_dev_enabled(ap->link.device)))
-		rc = __ata_scsi_queuecmd(cmd, done, ap->link.device);
+		rc = __ata_scsi_queuecmd(cmd, ap->link.device);
 	else {
 		cmd->result = (DID_BAD_TARGET << 16);
-		done(cmd);
+		cmd->scsi_done(cmd);
 	}
 	return rc;
 }
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 89d8a7c..24487d4 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -3627,17 +3627,19 @@ static void drbdd(struct drbd_conf *mdev)
 		}
 
 		shs = drbd_cmd_handler[cmd].pkt_size - sizeof(union p_header);
-		rv = drbd_recv(mdev, &header->h80.payload, shs);
-		if (unlikely(rv != shs)) {
-			dev_err(DEV, "short read while reading sub header: rv=%d\n", rv);
-			goto err_out;
-		}
-
 		if (packet_size - shs > 0 && !drbd_cmd_handler[cmd].expect_payload) {
 			dev_err(DEV, "No payload expected %s l:%d\n", cmdname(cmd), packet_size);
 			goto err_out;
 		}
 
+		if (shs) {
+			rv = drbd_recv(mdev, &header->h80.payload, shs);
+			if (unlikely(rv != shs)) {
+				dev_err(DEV, "short read while reading sub header: rv=%d\n", rv);
+				goto err_out;
+			}
+		}
+
 		rv = drbd_cmd_handler[cmd].function(mdev, cmd, packet_size - shs);
 
 		if (unlikely(!rv)) {
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index 181ea03..ab2bd09 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -339,7 +339,8 @@ static inline int _req_mod(struct drbd_request *req, enum drbd_req_event what)
 }
 
 /* completion of master bio is outside of spinlock.
- * If you need it irqsave, do it your self! */
+ * If you need it irqsave, do it your self!
+ * Which means: don't use from bio endio callback. */
 static inline int req_mod(struct drbd_request *req,
 		enum drbd_req_event what)
 {
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 47d223c..34f224b 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -193,8 +193,10 @@ void drbd_endio_sec(struct bio *bio, int error)
  */
 void drbd_endio_pri(struct bio *bio, int error)
 {
+	unsigned long flags;
 	struct drbd_request *req = bio->bi_private;
 	struct drbd_conf *mdev = req->mdev;
+	struct bio_and_error m;
 	enum drbd_req_event what;
 	int uptodate = bio_flagged(bio, BIO_UPTODATE);
 
@@ -220,7 +222,13 @@ void drbd_endio_pri(struct bio *bio, int error)
 	bio_put(req->private_bio);
 	req->private_bio = ERR_PTR(error);
 
-	req_mod(req, what);
+	/* not req_mod(), we need irqsave here! */
+	spin_lock_irqsave(&mdev->req_lock, flags);
+	__req_mod(req, what, &m);
+	spin_unlock_irqrestore(&mdev->req_lock, flags);
+
+	if (m.bio)
+		complete_master_bio(mdev, &m);
 }
 
 int w_read_retry_remote(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 90267f8..e2da191 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1131,11 +1131,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	 */
 	q->limits = *limits;
 
-	if (limits->no_cluster)
-		queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q);
-	else
-		queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, q);
-
 	if (!dm_table_supports_discards(t))
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
 	else
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 84c46a1..52694d2 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4296,9 +4296,6 @@ static int md_alloc(dev_t dev, char *name)
 		goto abort;
 	mddev->queue->queuedata = mddev;
 
-	/* Can be unlocked because the queue is new: no concurrency */
-	queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, mddev->queue);
-
 	blk_queue_make_request(mddev->queue, md_make_request);
 
 	disk = alloc_disk(1 << shift);
diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c
index d37c733..0bcd580 100644
--- a/drivers/s390/scsi/zfcp_erp.c
+++ b/drivers/s390/scsi/zfcp_erp.c
@@ -156,6 +156,8 @@ static int zfcp_erp_required_act(int want, struct zfcp_adapter *adapter,
 		if (!(a_status & ZFCP_STATUS_COMMON_RUNNING) ||
 		      a_status & ZFCP_STATUS_COMMON_ERP_FAILED)
 			return 0;
+		if (p_status & ZFCP_STATUS_COMMON_NOESC)
+			return need;
 		if (!(a_status & ZFCP_STATUS_COMMON_UNBLOCKED))
 			need = ZFCP_ERP_ACTION_REOPEN_ADAPTER;
 		/* fall through */
@@ -188,6 +190,9 @@ static struct zfcp_erp_action *zfcp_erp_setup_act(int need, u32 act_status,
 		atomic_set_mask(ZFCP_STATUS_COMMON_ERP_INUSE,
 				&zfcp_sdev->status);
 		erp_action = &zfcp_sdev->erp_action;
+		memset(erp_action, 0, sizeof(struct zfcp_erp_action));
+		erp_action->port = port;
+		erp_action->sdev = sdev;
 		if (!(atomic_read(&zfcp_sdev->status) &
 		      ZFCP_STATUS_COMMON_RUNNING))
 			act_status |= ZFCP_STATUS_ERP_CLOSE_ONLY;
@@ -200,6 +205,8 @@ static struct zfcp_erp_action *zfcp_erp_setup_act(int need, u32 act_status,
 		zfcp_erp_action_dismiss_port(port);
 		atomic_set_mask(ZFCP_STATUS_COMMON_ERP_INUSE, &port->status);
 		erp_action = &port->erp_action;
+		memset(erp_action, 0, sizeof(struct zfcp_erp_action));
+		erp_action->port = port;
 		if (!(atomic_read(&port->status) & ZFCP_STATUS_COMMON_RUNNING))
 			act_status |= ZFCP_STATUS_ERP_CLOSE_ONLY;
 		break;
@@ -209,6 +216,7 @@ static struct zfcp_erp_action *zfcp_erp_setup_act(int need, u32 act_status,
 		zfcp_erp_action_dismiss_adapter(adapter);
 		atomic_set_mask(ZFCP_STATUS_COMMON_ERP_INUSE, &adapter->status);
 		erp_action = &adapter->erp_action;
+		memset(erp_action, 0, sizeof(struct zfcp_erp_action));
 		if (!(atomic_read(&adapter->status) &
 		      ZFCP_STATUS_COMMON_RUNNING))
 			act_status |= ZFCP_STATUS_ERP_CLOSE_ONLY;
@@ -218,10 +226,7 @@ static struct zfcp_erp_action *zfcp_erp_setup_act(int need, u32 act_status,
 		return NULL;
 	}
 
-	memset(erp_action, 0, sizeof(struct zfcp_erp_action));
 	erp_action->adapter = adapter;
-	erp_action->port = port;
-	erp_action->sdev = sdev;
 	erp_action->action = need;
 	erp_action->status = act_status;
 
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index be03174..2eb7dd5 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -851,7 +851,7 @@ struct zfcp_fsf_req *zfcp_fsf_abort_fcp_cmnd(struct scsi_cmnd *scmnd)
 
 	zfcp_qdio_set_sbale_last(qdio, &req->qdio_req);
 
-	req->data = zfcp_sdev;
+	req->data = sdev;
 	req->handler = zfcp_fsf_abort_fcp_command_handler;
 	req->qtcb->header.lun_handle = zfcp_sdev->lun_handle;
 	req->qtcb->header.port_handle = zfcp_sdev->port->handle;
@@ -2069,8 +2069,6 @@ static void zfcp_fsf_fcp_cmnd_handler(struct zfcp_fsf_req *req)
 	struct fcp_resp_with_ext *fcp_rsp;
 	unsigned long flags;
 
-	zfcp_fsf_fcp_handler_common(req);
-
 	read_lock_irqsave(&req->adapter->abort_lock, flags);
 
 	scpnt = req->data;
@@ -2079,6 +2077,8 @@ static void zfcp_fsf_fcp_cmnd_handler(struct zfcp_fsf_req *req)
 		return;
 	}
 
+	zfcp_fsf_fcp_handler_common(req);
+
 	if (unlikely(req->status & ZFCP_STATUS_FSFREQ_ERROR)) {
 		set_host_byte(scpnt, DID_TRANSPORT_DISRUPTED);
 		goto skip_fsfstatus;
@@ -2170,12 +2170,13 @@ int zfcp_fsf_fcp_cmnd(struct scsi_cmnd *scsi_cmnd)
 	struct zfcp_adapter *adapter = zfcp_sdev->port->adapter;
 	struct zfcp_qdio *qdio = adapter->qdio;
 	struct fsf_qtcb_bottom_io *io;
+	unsigned long flags;
 
 	if (unlikely(!(atomic_read(&zfcp_sdev->status) &
 		       ZFCP_STATUS_COMMON_UNBLOCKED)))
 		return -EBUSY;
 
-	spin_lock(&qdio->req_q_lock);
+	spin_lock_irqsave(&qdio->req_q_lock, flags);
 	if (atomic_read(&qdio->req_q_free) <= 0) {
 		atomic_inc(&qdio->req_q_full);
 		goto out;
@@ -2239,7 +2240,7 @@ failed_scsi_cmnd:
 	zfcp_fsf_req_free(req);
 	scsi_cmnd->host_scribble = NULL;
 out:
-	spin_unlock(&qdio->req_q_lock);
+	spin_unlock_irqrestore(&qdio->req_q_lock, flags);
 	return retval;
 }
 
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index 6bd2dbc..63529ed 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -76,8 +76,8 @@ static void zfcp_scsi_command_fail(struct scsi_cmnd *scpnt, int result)
 	scpnt->scsi_done(scpnt);
 }
 
-static int zfcp_scsi_queuecommand_lck(struct scsi_cmnd *scpnt,
-				  void (*done) (struct scsi_cmnd *))
+static
+int zfcp_scsi_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scpnt)
 {
 	struct zfcp_scsi_dev *zfcp_sdev = sdev_to_zfcp(scpnt->device);
 	struct zfcp_adapter *adapter = zfcp_sdev->port->adapter;
@@ -87,7 +87,6 @@ static int zfcp_scsi_queuecommand_lck(struct scsi_cmnd *scpnt,
 	/* reset the status for this request */
 	scpnt->result = 0;
 	scpnt->host_scribble = NULL;
-	scpnt->scsi_done = done;
 
 	scsi_result = fc_remote_port_chkready(rport);
 	if (unlikely(scsi_result)) {
@@ -127,8 +126,6 @@ static int zfcp_scsi_queuecommand_lck(struct scsi_cmnd *scpnt,
 	return ret;
 }
 
-static DEF_SCSI_QCMD(zfcp_scsi_queuecommand)
-
 static int zfcp_scsi_slave_alloc(struct scsi_device *sdev)
 {
 	struct fc_rport *rport = starget_to_rport(scsi_target(sdev));
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index b2fb2b2..a6dea08 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -90,11 +90,7 @@ static const struct pci_device_id hpsa_pci_device_id[] = {
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x3252},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x3253},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x3254},
-#define PCI_DEVICE_ID_HP_CISSF 0x333f
-	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSF,     0x103C, 0x333F},
-	{PCI_VENDOR_ID_HP,     PCI_ANY_ID,             PCI_ANY_ID, PCI_ANY_ID,
-		PCI_CLASS_STORAGE_RAID << 8, 0xffff << 8, 0},
-	{PCI_VENDOR_ID_COMPAQ,     PCI_ANY_ID,             PCI_ANY_ID, PCI_ANY_ID,
+	{PCI_VENDOR_ID_HP,     PCI_ANY_ID,	PCI_ANY_ID, PCI_ANY_ID,
 		PCI_CLASS_STORAGE_RAID << 8, 0xffff << 8, 0},
 	{0,}
 };
@@ -113,8 +109,6 @@ static struct board_type products[] = {
 	{0x3249103C, "Smart Array P812", &SA5_access},
 	{0x324a103C, "Smart Array P712m", &SA5_access},
 	{0x324b103C, "Smart Array P711m", &SA5_access},
-	{0x3233103C, "StorageWorks P1210m", &SA5_access},
-	{0x333F103C, "StorageWorks P1210m", &SA5_access},
 	{0x3250103C, "Smart Array", &SA5_access},
 	{0x3250113C, "Smart Array", &SA5_access},
 	{0x3250123C, "Smart Array", &SA5_access},
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index de2e09e..d3c5905 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -5748,7 +5748,7 @@ static int ipr_queuecommand_lck(struct scsi_cmnd *scsi_cmd,
 	}
 
 	if (ipr_is_gata(res) && res->sata_port)
-		return ata_sas_queuecmd(scsi_cmd, done, res->sata_port->ap);
+		return ata_sas_queuecmd(scsi_cmd, res->sata_port->ap);
 
 	ipr_cmd = ipr_get_free_ipr_cmnd(ioa_cfg);
 	ioarcb = &ipr_cmd->ioarcb;
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 29251fa..5815cbe 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -211,8 +211,7 @@ static int sas_queuecommand_lck(struct scsi_cmnd *cmd,
 			unsigned long flags;
 
 			spin_lock_irqsave(dev->sata_dev.ap->lock, flags);
-			res = ata_sas_queuecmd(cmd, scsi_done,
-					       dev->sata_dev.ap);
+			res = ata_sas_queuecmd(cmd, dev->sata_dev.ap);
 			spin_unlock_irqrestore(dev->sata_dev.ap->lock, flags);
 			goto out;
 		}
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index 0433ea6..b37c8a3 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -951,8 +951,8 @@ static int _osd_req_finalize_cdb_cont(struct osd_request *or, const u8 *cap_key)
 	/* create a bio for continuation segment */
 	bio = bio_map_kern(req_q, or->cdb_cont.buff, or->cdb_cont.total_bytes,
 			   GFP_KERNEL);
-	if (unlikely(!bio))
-		return -ENOMEM;
+	if (IS_ERR(bio))
+		return PTR_ERR(bio);
 
 	bio->bi_rw |= REQ_WRITE;
 
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index 5e76a62..300d59f 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -62,6 +62,7 @@
 static unsigned int pmcraid_debug_log;
 static unsigned int pmcraid_disable_aen;
 static unsigned int pmcraid_log_level = IOASC_LOG_LEVEL_MUST;
+static unsigned int pmcraid_enable_msix;
 
 /*
  * Data structures to support multiple adapters by the LLD.
@@ -4691,7 +4692,8 @@ pmcraid_register_interrupt_handler(struct pmcraid_instance *pinstance)
 	int rc;
 	struct pci_dev *pdev = pinstance->pdev;
 
-	if (pci_find_capability(pdev, PCI_CAP_ID_MSIX)) {
+	if ((pmcraid_enable_msix) &&
+		(pci_find_capability(pdev, PCI_CAP_ID_MSIX))) {
 		int num_hrrq = PMCRAID_NUM_MSIX_VECTORS;
 		struct msix_entry entries[PMCRAID_NUM_MSIX_VECTORS];
 		int i;
diff --git a/drivers/scsi/pmcraid.h b/drivers/scsi/pmcraid.h
index 1134279..4db210d 100644
--- a/drivers/scsi/pmcraid.h
+++ b/drivers/scsi/pmcraid.h
@@ -42,7 +42,7 @@
  */
 #define PMCRAID_DRIVER_NAME		"PMC MaxRAID"
 #define PMCRAID_DEVFILE			"pmcsas"
-#define PMCRAID_DRIVER_VERSION		"2.0.3"
+#define PMCRAID_DRIVER_VERSION		"1.0.3"
 #define PMCRAID_DRIVER_DATE		__DATE__
 
 #define PMCRAID_FW_VERSION_1		0x002
@@ -333,11 +333,9 @@ struct pmcraid_config_table_entry {
 	__u8  lun[PMCRAID_LUN_LEN];
 } __attribute__((packed, aligned(4)));
 
-/* extended configuration table sizes are of 64 bytes in size */
-#define PMCRAID_CFGTE_EXT_SIZE	32
+/* extended configuration table sizes are also of 32 bytes in size */
 struct pmcraid_config_table_entry_ext {
 	struct pmcraid_config_table_entry cfgte;
-	__u8  cfgte_ext[PMCRAID_CFGTE_EXT_SIZE];
 };
 
 /* resource types (config_table_entry.resource_type values) */
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 3a22eff..9ce539d 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2409,7 +2409,6 @@ struct qla_hw_data {
 		uint32_t	enable_target_reset	:1;
 		uint32_t	enable_lip_full_login	:1;
 		uint32_t	enable_led_scheme	:1;
-		uint32_t	inta_enabled		:1;
 		uint32_t	msi_enabled		:1;
 		uint32_t	msix_enabled		:1;
 		uint32_t	disable_serdes		:1;
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 5f94430..4c1ba62 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -1061,6 +1061,7 @@ qla24xx_build_scsi_crc_2_iocbs(srb_t *sp, struct cmd_type_crc_2 *cmd_pkt,
 		fcp_cmnd->additional_cdb_len |= 2;
 
 	int_to_scsilun(sp->cmd->device->lun, &fcp_cmnd->lun);
+	host_to_fcp_swap((uint8_t *)&fcp_cmnd->lun, sizeof(fcp_cmnd->lun));
 	memcpy(fcp_cmnd->cdb, cmd->cmnd, cmd->cmd_len);
 	cmd_pkt->fcp_cmnd_dseg_len = cpu_to_le16(fcp_cmnd_len);
 	cmd_pkt->fcp_cmnd_dseg_address[0] = cpu_to_le32(
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 1f06ddd..7f77898 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -2491,14 +2491,15 @@ skip_msix:
 skip_msi:
 
 	ret = request_irq(ha->pdev->irq, ha->isp_ops->intr_handler,
-	    IRQF_SHARED, QLA2XXX_DRIVER_NAME, rsp);
+	    ha->flags.msi_enabled ? 0 : IRQF_SHARED,
+	    QLA2XXX_DRIVER_NAME, rsp);
 	if (ret) {
 		qla_printk(KERN_WARNING, ha,
 		    "Failed to reserve interrupt %d already in use.\n",
 		    ha->pdev->irq);
 		goto fail;
 	}
-	ha->flags.inta_enabled = 1;
+
 clear_risc_ints:
 
 	/*
diff --git a/drivers/scsi/qla2xxx/qla_nx.c b/drivers/scsi/qla2xxx/qla_nx.c
index 8d9edfb..ae2acac 100644
--- a/drivers/scsi/qla2xxx/qla_nx.c
+++ b/drivers/scsi/qla2xxx/qla_nx.c
@@ -2749,6 +2749,7 @@ sufficient_dsds:
 			goto queuing_error_fcp_cmnd;
 
 		int_to_scsilun(sp->cmd->device->lun, &cmd_pkt->lun);
+		host_to_fcp_swap((uint8_t *)&cmd_pkt->lun, sizeof(cmd_pkt->lun));
 
 		/* build FCP_CMND IU */
 		memset(ctx->fcp_cmnd, 0, sizeof(struct fcp_cmnd));
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 1644eab..2c0876c 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -829,7 +829,7 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 {
 	scsi_qla_host_t *vha = shost_priv(cmd->device->host);
 	srb_t *sp;
-	int ret;
+	int ret = SUCCESS;
 	unsigned int id, lun;
 	unsigned long flags;
 	int wait = 0;
@@ -2064,6 +2064,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		ha->init_cb_size = sizeof(struct mid_init_cb_81xx);
 		ha->gid_list_info_size = 8;
 		ha->optrom_size = OPTROM_SIZE_82XX;
+		ha->nvram_npiv_size = QLA_MAX_VPORTS_QLA25XX;
 		ha->isp_ops = &qla82xx_isp_ops;
 		ha->flash_conf_off = FARX_ACCESS_FLASH_CONF;
 		ha->flash_data_off = FARX_ACCESS_FLASH_DATA;
diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h
index 8edbccb..cf0075a 100644
--- a/drivers/scsi/qla2xxx/qla_version.h
+++ b/drivers/scsi/qla2xxx/qla_version.h
@@ -7,9 +7,9 @@
 /*
  * Driver version
  */
-#define QLA2XXX_VERSION      "8.03.04-k0"
+#define QLA2XXX_VERSION      "8.03.05-k0"
 
 #define QLA_DRIVER_MAJOR_VER	8
 #define QLA_DRIVER_MINOR_VER	3
-#define QLA_DRIVER_PATCH_VER	4
+#define QLA_DRIVER_PATCH_VER	5
 #define QLA_DRIVER_BETA_VER	0
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 4677129..cf78738 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -615,7 +615,7 @@ static int scsi_try_bus_device_reset(struct scsi_cmnd *scmd)
 	return rtn;
 }
 
-static int __scsi_try_to_abort_cmd(struct scsi_cmnd *scmd)
+static int scsi_try_to_abort_cmd(struct scsi_cmnd *scmd)
 {
 	if (!scmd->device->host->hostt->eh_abort_handler)
 		return FAILED;
@@ -623,31 +623,9 @@ static int __scsi_try_to_abort_cmd(struct scsi_cmnd *scmd)
 	return scmd->device->host->hostt->eh_abort_handler(scmd);
 }
 
-/**
- * scsi_try_to_abort_cmd - Ask host to abort a running command.
- * @scmd:	SCSI cmd to abort from Lower Level.
- *
- * Notes:
- *    This function will not return until the user's completion function
- *    has been called.  there is no timeout on this operation.  if the
- *    author of the low-level driver wishes this operation to be timed,
- *    they can provide this facility themselves.  helper functions in
- *    scsi_error.c can be supplied to make this easier to do.
- */
-static int scsi_try_to_abort_cmd(struct scsi_cmnd *scmd)
-{
-	/*
-	 * scsi_done was called just after the command timed out and before
-	 * we had a chance to process it. (db)
-	 */
-	if (scmd->serial_number == 0)
-		return SUCCESS;
-	return __scsi_try_to_abort_cmd(scmd);
-}
-
 static void scsi_abort_eh_cmnd(struct scsi_cmnd *scmd)
 {
-	if (__scsi_try_to_abort_cmd(scmd) != SUCCESS)
+	if (scsi_try_to_abort_cmd(scmd) != SUCCESS)
 		if (scsi_try_bus_device_reset(scmd) != SUCCESS)
 			if (scsi_try_target_reset(scmd) != SUCCESS)
 				if (scsi_try_bus_reset(scmd) != SUCCESS)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index eafeeda..4a38422 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1403,11 +1403,6 @@ static void scsi_softirq_done(struct request *rq)
 
 	INIT_LIST_HEAD(&cmd->eh_entry);
 
-	/*
-	 * Set the serial numbers back to zero
-	 */
-	cmd->serial_number = 0;
-
 	atomic_inc(&cmd->device->iodone_cnt);
 	if (cmd->result)
 		atomic_inc(&cmd->device->ioerr_cnt);
@@ -1642,9 +1637,8 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost,
 
 	blk_queue_max_segment_size(q, dma_get_max_seg_size(dev));
 
-	/* New queue, no concurrency on queue_flags */
 	if (!shost->use_clustering)
-		queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q);
+		q->limits.cluster = 0;
 
 	/*
 	 * set a reasonable default alignment on word boundaries: the
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index aae86fd..95aeeeb 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -250,7 +250,7 @@ struct queue_limits {
 
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
-	unsigned char		no_cluster;
+	unsigned char		cluster;
 	signed char		discard_zeroes_data;
 };
 
@@ -380,7 +380,6 @@ struct request_queue
 #endif
 };
 
-#define QUEUE_FLAG_CLUSTER	0	/* cluster several segments into 1 */
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
 #define QUEUE_FLAG_STOPPED	2	/* queue is stopped */
 #define	QUEUE_FLAG_SYNCFULL	3	/* read queue has been filled */
@@ -403,7 +402,6 @@ struct request_queue
 #define QUEUE_FLAG_SECDISCARD  19	/* supports SECDISCARD */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
-				 (1 << QUEUE_FLAG_CLUSTER) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
 				 (1 << QUEUE_FLAG_SAME_COMP)	|	\
 				 (1 << QUEUE_FLAG_ADD_RANDOM))
@@ -510,6 +508,11 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 
 #define rq_data_dir(rq)		((rq)->cmd_flags & 1)
 
+static inline unsigned int blk_queue_cluster(struct request_queue *q)
+{
+	return q->limits.cluster;
+}
+
 /*
  * We regard a request as sync, if either a read or a sync write
  */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index d947b12..c9c5d7a 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -996,8 +996,7 @@ extern int ata_sas_port_init(struct ata_port *);
 extern int ata_sas_port_start(struct ata_port *ap);
 extern void ata_sas_port_stop(struct ata_port *ap);
 extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *);
-extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *),
-			    struct ata_port *ap);
+extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap);
 extern int sata_scr_valid(struct ata_link *link);
 extern int sata_scr_read(struct ata_link *link, int reg, u32 *val);
 extern int sata_scr_write(struct ata_link *link, int reg, u32 val);
@@ -1040,8 +1039,7 @@ extern unsigned int ata_do_dev_read_id(struct ata_device *dev,
 					struct ata_taskfile *tf, u16 *id);
 extern void ata_qc_complete(struct ata_queued_cmd *qc);
 extern int ata_qc_complete_multiple(struct ata_port *ap, u32 qc_active);
-extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd,
-			      void (*done)(struct scsi_cmnd *));
+extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd);
 extern int ata_std_bios_param(struct scsi_device *sdev,
 			      struct block_device *bdev,
 			      sector_t capacity, int geom[]);