diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index d2f9033..4873c75 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -128,3 +128,17 @@
 		preferred request size for workloads where sustained
 		throughput is desired.  If no optimal I/O size is
 		reported this file contains 0.
+
+What:		/sys/block/<disk>/queue/nomerges
+Date:		January 2010
+Contact:
+Description:
+		Standard I/O elevator operations include attempts to
+		merge contiguous I/Os. For known random I/O loads these
+		attempts will always fail and result in extra cycles
+		being spent in the kernel. This allows one to turn off
+		this behavior on one of two ways: When set to 1, complex
+		merge checks are disabled, but the simple one-shot merges
+		with the previous I/O request are enabled. When set to 2,
+		all merge tries are disabled. The default value is 0 -
+		which enables all types of merge tries.
diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt
index e164403..f652740 100644
--- a/Documentation/block/queue-sysfs.txt
+++ b/Documentation/block/queue-sysfs.txt
@@ -25,11 +25,11 @@
 
 nomerges (RW)
 -------------
-This enables the user to disable the lookup logic involved with IO merging
-requests in the block layer. Merging may still occur through a direct
-1-hit cache, since that comes for (almost) free. The IO scheduler will not
-waste cycles doing tree/hash lookups for merges if nomerges is 1. Defaults
-to 0, enabling all merges.
+This enables the user to disable the lookup logic involved with IO
+merging requests in the block layer. By default (0) all merges are
+enabled. When set to 1 only simple one-hit merges will be tried. When
+set to 2 no merge algorithms will be tried (including one-hit or more
+complex tree/hash lookups).
 
 nr_requests (RW)
 ----------------
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 5ff5546..c1ff690 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -747,7 +747,7 @@
 	ubd_dev->fd = fd;
 
 	if(ubd_dev->cow.file != NULL){
-		blk_queue_max_sectors(ubd_dev->queue, 8 * sizeof(long));
+		blk_queue_max_hw_sectors(ubd_dev->queue, 8 * sizeof(long));
 
 		err = -ENOMEM;
 		ubd_dev->cow.bitmap = vmalloc(ubd_dev->cow.bitmap_len);
@@ -849,7 +849,7 @@
 	}
 	ubd_dev->queue->queuedata = ubd_dev;
 
-	blk_queue_max_hw_segments(ubd_dev->queue, MAX_SG);
+	blk_queue_max_segments(ubd_dev->queue, MAX_SG);
 	err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, &ubd_gendisk[n]);
 	if(err){
 		*error_out = "Failed to register device";
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index e7dbbaf..c85d74c 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -23,20 +23,6 @@
 struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
 EXPORT_SYMBOL_GPL(blkio_root_cgroup);
 
-bool blkiocg_css_tryget(struct blkio_cgroup *blkcg)
-{
-	if (!css_tryget(&blkcg->css))
-		return false;
-	return true;
-}
-EXPORT_SYMBOL_GPL(blkiocg_css_tryget);
-
-void blkiocg_css_put(struct blkio_cgroup *blkcg)
-{
-	css_put(&blkcg->css);
-}
-EXPORT_SYMBOL_GPL(blkiocg_css_put);
-
 struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
 {
 	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 4d316df..84bf745 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -43,9 +43,6 @@
 	unsigned long sectors;
 };
 
-extern bool blkiocg_css_tryget(struct blkio_cgroup *blkcg);
-extern void blkiocg_css_put(struct blkio_cgroup *blkcg);
-
 typedef void (blkio_unlink_group_fn) (void *key, struct blkio_group *blkg);
 typedef void (blkio_update_group_weight_fn) (struct blkio_group *blkg,
 						unsigned int weight);
diff --git a/block/blk-core.c b/block/blk-core.c
index d1a9a0a..9fe174d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1490,9 +1490,9 @@
 /*
  * We only want one ->make_request_fn to be active at a time,
  * else stack usage with stacked devices could be a problem.
- * So use current->bio_{list,tail} to keep a list of requests
+ * So use current->bio_list to keep a list of requests
  * submited by a make_request_fn function.
- * current->bio_tail is also used as a flag to say if
+ * current->bio_list is also used as a flag to say if
  * generic_make_request is currently active in this task or not.
  * If it is NULL, then no make_request is active.  If it is non-NULL,
  * then a make_request is active, and new requests should be added
@@ -1500,11 +1500,11 @@
  */
 void generic_make_request(struct bio *bio)
 {
-	if (current->bio_tail) {
+	struct bio_list bio_list_on_stack;
+
+	if (current->bio_list) {
 		/* make_request is active */
-		*(current->bio_tail) = bio;
-		bio->bi_next = NULL;
-		current->bio_tail = &bio->bi_next;
+		bio_list_add(current->bio_list, bio);
 		return;
 	}
 	/* following loop may be a bit non-obvious, and so deserves some
@@ -1512,30 +1512,27 @@
 	 * Before entering the loop, bio->bi_next is NULL (as all callers
 	 * ensure that) so we have a list with a single bio.
 	 * We pretend that we have just taken it off a longer list, so
-	 * we assign bio_list to the next (which is NULL) and bio_tail
-	 * to &bio_list, thus initialising the bio_list of new bios to be
+	 * we assign bio_list to a pointer to the bio_list_on_stack,
+	 * thus initialising the bio_list of new bios to be
 	 * added.  __generic_make_request may indeed add some more bios
 	 * through a recursive call to generic_make_request.  If it
 	 * did, we find a non-NULL value in bio_list and re-enter the loop
 	 * from the top.  In this case we really did just take the bio
-	 * of the top of the list (no pretending) and so fixup bio_list and
-	 * bio_tail or bi_next, and call into __generic_make_request again.
+	 * of the top of the list (no pretending) and so remove it from
+	 * bio_list, and call into __generic_make_request again.
 	 *
 	 * The loop was structured like this to make only one call to
 	 * __generic_make_request (which is important as it is large and
 	 * inlined) and to keep the structure simple.
 	 */
 	BUG_ON(bio->bi_next);
+	bio_list_init(&bio_list_on_stack);
+	current->bio_list = &bio_list_on_stack;
 	do {
-		current->bio_list = bio->bi_next;
-		if (bio->bi_next == NULL)
-			current->bio_tail = &current->bio_list;
-		else
-			bio->bi_next = NULL;
 		__generic_make_request(bio);
-		bio = current->bio_list;
+		bio = bio_list_pop(current->bio_list);
 	} while (bio);
-	current->bio_tail = NULL; /* deactivate */
+	current->bio_list = NULL; /* deactivate */
 }
 EXPORT_SYMBOL(generic_make_request);
 
@@ -1617,8 +1614,7 @@
 	 * limitation.
 	 */
 	blk_recalc_rq_segments(rq);
-	if (rq->nr_phys_segments > queue_max_phys_segments(q) ||
-	    rq->nr_phys_segments > queue_max_hw_segments(q)) {
+	if (rq->nr_phys_segments > queue_max_segments(q)) {
 		printk(KERN_ERR "%s: over max segments limit.\n", __func__);
 		return -EIO;
 	}
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 98e6bf6..3f65c8a 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -91,7 +91,7 @@
 		spin_lock_init(&ret->lock);
 		ret->ioprio_changed = 0;
 		ret->ioprio = 0;
-		ret->last_waited = jiffies; /* doesn't matter... */
+		ret->last_waited = 0; /* doesn't matter... */
 		ret->nr_batch_requests = 0; /* because this is 0 */
 		INIT_RADIX_TREE(&ret->radix_root, GFP_ATOMIC | __GFP_HIGH);
 		INIT_HLIST_HEAD(&ret->cic_list);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 99cb5cf..5e7dc99 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -206,8 +206,7 @@
 {
 	int nr_phys_segs = bio_phys_segments(q, bio);
 
-	if (req->nr_phys_segments + nr_phys_segs > queue_max_hw_segments(q) ||
-	    req->nr_phys_segments + nr_phys_segs > queue_max_phys_segments(q)) {
+	if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q)) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -300,10 +299,7 @@
 		total_phys_segments--;
 	}
 
-	if (total_phys_segments > queue_max_phys_segments(q))
-		return 0;
-
-	if (total_phys_segments > queue_max_hw_segments(q))
+	if (total_phys_segments > queue_max_segments(q))
 		return 0;
 
 	/* Merge is OK... */
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 5eeb9e0..31e7a93 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -91,10 +91,9 @@
  */
 void blk_set_default_limits(struct queue_limits *lim)
 {
-	lim->max_phys_segments = MAX_PHYS_SEGMENTS;
-	lim->max_hw_segments = MAX_HW_SEGMENTS;
+	lim->max_segments = BLK_MAX_SEGMENTS;
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
-	lim->max_segment_size = MAX_SEGMENT_SIZE;
+	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
 	lim->max_sectors = BLK_DEF_MAX_SECTORS;
 	lim->max_hw_sectors = INT_MAX;
 	lim->max_discard_sectors = 0;
@@ -154,7 +153,7 @@
 	q->unplug_timer.data = (unsigned long)q;
 
 	blk_set_default_limits(&q->limits);
-	blk_queue_max_sectors(q, SAFE_MAX_SECTORS);
+	blk_queue_max_hw_sectors(q, BLK_SAFE_MAX_SECTORS);
 
 	/*
 	 * If the caller didn't supply a lock, fall back to our embedded
@@ -210,37 +209,32 @@
 EXPORT_SYMBOL(blk_queue_bounce_limit);
 
 /**
- * blk_queue_max_sectors - set max sectors for a request for this queue
+ * blk_queue_max_hw_sectors - set max sectors for a request for this queue
  * @q:  the request queue for the device
- * @max_sectors:  max sectors in the usual 512b unit
+ * @max_hw_sectors:  max hardware sectors in the usual 512b unit
  *
  * Description:
- *    Enables a low level driver to set an upper limit on the size of
- *    received requests.
+ *    Enables a low level driver to set a hard upper limit,
+ *    max_hw_sectors, on the size of requests.  max_hw_sectors is set by
+ *    the device driver based upon the combined capabilities of I/O
+ *    controller and storage device.
+ *
+ *    max_sectors is a soft limit imposed by the block layer for
+ *    filesystem type requests.  This value can be overridden on a
+ *    per-device basis in /sys/block/<device>/queue/max_sectors_kb.
+ *    The soft limit can not exceed max_hw_sectors.
  **/
-void blk_queue_max_sectors(struct request_queue *q, unsigned int max_sectors)
+void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
 {
-	if ((max_sectors << 9) < PAGE_CACHE_SIZE) {
-		max_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
+	if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) {
+		max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
 		printk(KERN_INFO "%s: set to minimum %d\n",
-		       __func__, max_sectors);
+		       __func__, max_hw_sectors);
 	}
 
-	if (BLK_DEF_MAX_SECTORS > max_sectors)
-		q->limits.max_hw_sectors = q->limits.max_sectors = max_sectors;
-	else {
-		q->limits.max_sectors = BLK_DEF_MAX_SECTORS;
-		q->limits.max_hw_sectors = max_sectors;
-	}
-}
-EXPORT_SYMBOL(blk_queue_max_sectors);
-
-void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_sectors)
-{
-	if (BLK_DEF_MAX_SECTORS > max_sectors)
-		q->limits.max_hw_sectors = BLK_DEF_MAX_SECTORS;
-	else
-		q->limits.max_hw_sectors = max_sectors;
+	q->limits.max_hw_sectors = max_hw_sectors;
+	q->limits.max_sectors = min_t(unsigned int, max_hw_sectors,
+				      BLK_DEF_MAX_SECTORS);
 }
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
@@ -257,17 +251,15 @@
 EXPORT_SYMBOL(blk_queue_max_discard_sectors);
 
 /**
- * blk_queue_max_phys_segments - set max phys segments for a request for this queue
+ * blk_queue_max_segments - set max hw segments for a request for this queue
  * @q:  the request queue for the device
  * @max_segments:  max number of segments
  *
  * Description:
  *    Enables a low level driver to set an upper limit on the number of
- *    physical data segments in a request.  This would be the largest sized
- *    scatter list the driver could handle.
+ *    hw data segments in a request.
  **/
-void blk_queue_max_phys_segments(struct request_queue *q,
-				 unsigned short max_segments)
+void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments)
 {
 	if (!max_segments) {
 		max_segments = 1;
@@ -275,33 +267,9 @@
 		       __func__, max_segments);
 	}
 
-	q->limits.max_phys_segments = max_segments;
+	q->limits.max_segments = max_segments;
 }
-EXPORT_SYMBOL(blk_queue_max_phys_segments);
-
-/**
- * blk_queue_max_hw_segments - set max hw segments for a request for this queue
- * @q:  the request queue for the device
- * @max_segments:  max number of segments
- *
- * Description:
- *    Enables a low level driver to set an upper limit on the number of
- *    hw data segments in a request.  This would be the largest number of
- *    address/length pairs the host adapter can actually give at once
- *    to the device.
- **/
-void blk_queue_max_hw_segments(struct request_queue *q,
-			       unsigned short max_segments)
-{
-	if (!max_segments) {
-		max_segments = 1;
-		printk(KERN_INFO "%s: set to minimum %d\n",
-		       __func__, max_segments);
-	}
-
-	q->limits.max_hw_segments = max_segments;
-}
-EXPORT_SYMBOL(blk_queue_max_hw_segments);
+EXPORT_SYMBOL(blk_queue_max_segments);
 
 /**
  * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
@@ -507,7 +475,7 @@
  * blk_stack_limits - adjust queue_limits for stacked devices
  * @t:	the stacking driver limits (top device)
  * @b:  the underlying queue limits (bottom, component device)
- * @offset:  offset to beginning of data within component device
+ * @start:  first data sector within component device
  *
  * Description:
  *    This function is used by stacking drivers like MD and DM to ensure
@@ -525,10 +493,9 @@
  *    the alignment_offset is undefined.
  */
 int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
-		     sector_t offset)
+		     sector_t start)
 {
-	sector_t alignment;
-	unsigned int top, bottom, ret = 0;
+	unsigned int top, bottom, alignment, ret = 0;
 
 	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
 	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
@@ -537,18 +504,14 @@
 	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
 					    b->seg_boundary_mask);
 
-	t->max_phys_segments = min_not_zero(t->max_phys_segments,
-					    b->max_phys_segments);
-
-	t->max_hw_segments = min_not_zero(t->max_hw_segments,
-					  b->max_hw_segments);
+	t->max_segments = min_not_zero(t->max_segments, b->max_segments);
 
 	t->max_segment_size = min_not_zero(t->max_segment_size,
 					   b->max_segment_size);
 
 	t->misaligned |= b->misaligned;
 
-	alignment = queue_limit_alignment_offset(b, offset);
+	alignment = queue_limit_alignment_offset(b, start);
 
 	/* Bottom device has different alignment.  Check that it is
 	 * compatible with the current top alignment.
@@ -611,11 +574,7 @@
 
 	/* Discard alignment and granularity */
 	if (b->discard_granularity) {
-		unsigned int granularity = b->discard_granularity;
-		offset &= granularity - 1;
-
-		alignment = (granularity + b->discard_alignment - offset)
-			& (granularity - 1);
+		alignment = queue_limit_discard_alignment(b, start);
 
 		if (t->discard_granularity != 0 &&
 		    t->discard_alignment != alignment) {
@@ -657,7 +616,7 @@
 
 	start += get_start_sect(bdev);
 
-	return blk_stack_limits(t, &bq->limits, start << 9);
+	return blk_stack_limits(t, &bq->limits, start);
 }
 EXPORT_SYMBOL(bdev_stack_limits);
 
@@ -668,9 +627,8 @@
  * @offset:  offset to beginning of data within component device
  *
  * Description:
- *    Merges the limits for two queues.  Returns 0 if alignment
- *    didn't change.  Returns -1 if adding the bottom device caused
- *    misalignment.
+ *    Merges the limits for a top level gendisk and a bottom level
+ *    block_device.
  */
 void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 		       sector_t offset)
@@ -678,9 +636,7 @@
 	struct request_queue *t = disk->queue;
 	struct request_queue *b = bdev_get_queue(bdev);
 
-	offset += get_start_sect(bdev) << 9;
-
-	if (blk_stack_limits(&t->limits, &b->limits, offset) < 0) {
+	if (bdev_stack_limits(&t->limits, bdev, offset >> 9) < 0) {
 		char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE];
 
 		disk_name(disk, 0, top);
@@ -752,22 +708,19 @@
  * does is adjust the queue so that the buf is always appended
  * silently to the scatterlist.
  *
- * Note: This routine adjusts max_hw_segments to make room for
- * appending the drain buffer.  If you call
- * blk_queue_max_hw_segments() or blk_queue_max_phys_segments() after
- * calling this routine, you must set the limit to one fewer than your
- * device can support otherwise there won't be room for the drain
- * buffer.
+ * Note: This routine adjusts max_hw_segments to make room for appending
+ * the drain buffer.  If you call blk_queue_max_segments() after calling
+ * this routine, you must set the limit to one fewer than your device
+ * can support otherwise there won't be room for the drain buffer.
  */
 int blk_queue_dma_drain(struct request_queue *q,
 			       dma_drain_needed_fn *dma_drain_needed,
 			       void *buf, unsigned int size)
 {
-	if (queue_max_hw_segments(q) < 2 || queue_max_phys_segments(q) < 2)
+	if (queue_max_segments(q) < 2)
 		return -EINVAL;
 	/* make room for appending the drain */
-	blk_queue_max_hw_segments(q, queue_max_hw_segments(q) - 1);
-	blk_queue_max_phys_segments(q, queue_max_phys_segments(q) - 1);
+	blk_queue_max_segments(q, queue_max_segments(q) - 1);
 	q->dma_drain_needed = dma_drain_needed;
 	q->dma_drain_buffer = buf;
 	q->dma_drain_size = size;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 8606c95..e854424 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -189,7 +189,8 @@
 
 static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
 {
-	return queue_var_show(blk_queue_nomerges(q), page);
+	return queue_var_show((blk_queue_nomerges(q) << 1) |
+			       blk_queue_noxmerges(q), page);
 }
 
 static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
@@ -199,10 +200,12 @@
 	ssize_t ret = queue_var_store(&nm, page, count);
 
 	spin_lock_irq(q->queue_lock);
-	if (nm)
+	queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
+	queue_flag_clear(QUEUE_FLAG_NOXMERGES, q);
+	if (nm == 2)
 		queue_flag_set(QUEUE_FLAG_NOMERGES, q);
-	else
-		queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
+	else if (nm)
+		queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
 	spin_unlock_irq(q->queue_lock);
 
 	return ret;
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 023f4e6..dee9d93 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -19,7 +19,7 @@
  * tunables
  */
 /* max queue in one round of service */
-static const int cfq_quantum = 4;
+static const int cfq_quantum = 8;
 static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
 /* maximum backwards seek, in KiB */
 static const int cfq_back_max = 16 * 1024;
@@ -46,8 +46,9 @@
 #define CFQ_HW_QUEUE_MIN	(5)
 #define CFQ_SERVICE_SHIFT       12
 
-#define CFQQ_SEEK_THR		8 * 1024
-#define CFQQ_SEEKY(cfqq)	((cfqq)->seek_mean > CFQQ_SEEK_THR)
+#define CFQQ_SEEK_THR		(sector_t)(8 * 100)
+#define CFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
+#define CFQQ_SEEKY(cfqq)	(hweight32(cfqq->seek_history) > 32/8)
 
 #define RQ_CIC(rq)		\
 	((struct cfq_io_context *) (rq)->elevator_private)
@@ -77,11 +78,12 @@
 	struct rb_root rb;
 	struct rb_node *left;
 	unsigned count;
+	unsigned total_weight;
 	u64 min_vdisktime;
 	struct rb_node *active;
-	unsigned total_weight;
 };
-#define CFQ_RB_ROOT	(struct cfq_rb_root) { RB_ROOT, NULL, 0, 0, }
+#define CFQ_RB_ROOT	(struct cfq_rb_root) { .rb = RB_ROOT, .left = NULL, \
+			.count = 0, .min_vdisktime = 0, }
 
 /*
  * Per process-grouping structure
@@ -115,11 +117,11 @@
 	/* time when queue got scheduled in to dispatch first request. */
 	unsigned long dispatch_start;
 	unsigned int allocated_slice;
+	unsigned int slice_dispatch;
 	/* time when first request from queue completed and slice started. */
 	unsigned long slice_start;
 	unsigned long slice_end;
 	long slice_resid;
-	unsigned int slice_dispatch;
 
 	/* pending metadata requests */
 	int meta_pending;
@@ -130,13 +132,11 @@
 	unsigned short ioprio, org_ioprio;
 	unsigned short ioprio_class, org_ioprio_class;
 
-	unsigned int seek_samples;
-	u64 seek_total;
-	sector_t seek_mean;
-	sector_t last_request_pos;
-
 	pid_t pid;
 
+	u32 seek_history;
+	sector_t last_request_pos;
+
 	struct cfq_rb_root *service_tree;
 	struct cfq_queue *new_cfqq;
 	struct cfq_group *cfqg;
@@ -223,8 +223,8 @@
 
 	unsigned int busy_queues;
 
-	int rq_in_driver[2];
-	int sync_flight;
+	int rq_in_driver;
+	int rq_in_flight[2];
 
 	/*
 	 * queue-depth detection
@@ -417,11 +417,6 @@
 static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *,
 						struct io_context *);
 
-static inline int rq_in_driver(struct cfq_data *cfqd)
-{
-	return cfqd->rq_in_driver[0] + cfqd->rq_in_driver[1];
-}
-
 static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic,
 					    bool is_sync)
 {
@@ -951,10 +946,6 @@
 	struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
 	unsigned int major, minor;
 
-	/* Do we need to take this reference */
-	if (!blkiocg_css_tryget(blkcg))
-		return NULL;;
-
 	cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
 	if (cfqg || !create)
 		goto done;
@@ -985,7 +976,6 @@
 	hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
 
 done:
-	blkiocg_css_put(blkcg);
 	return cfqg;
 }
 
@@ -1420,9 +1410,9 @@
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 
-	cfqd->rq_in_driver[rq_is_sync(rq)]++;
+	cfqd->rq_in_driver++;
 	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
-						rq_in_driver(cfqd));
+						cfqd->rq_in_driver);
 
 	cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
 }
@@ -1430,12 +1420,11 @@
 static void cfq_deactivate_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
-	const int sync = rq_is_sync(rq);
 
-	WARN_ON(!cfqd->rq_in_driver[sync]);
-	cfqd->rq_in_driver[sync]--;
+	WARN_ON(!cfqd->rq_in_driver);
+	cfqd->rq_in_driver--;
 	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
-						rq_in_driver(cfqd));
+						cfqd->rq_in_driver);
 }
 
 static void cfq_remove_request(struct request *rq)
@@ -1673,16 +1662,7 @@
 static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			       struct request *rq, bool for_preempt)
 {
-	sector_t sdist = cfqq->seek_mean;
-
-	if (!sample_valid(cfqq->seek_samples))
-		sdist = CFQQ_SEEK_THR;
-
-	/* if seek_mean is big, using it as close criteria is meaningless */
-	if (sdist > CFQQ_SEEK_THR && !for_preempt)
-		sdist = CFQQ_SEEK_THR;
-
-	return cfq_dist_from_last(cfqd, rq) <= sdist;
+	return cfq_dist_from_last(cfqd, rq) <= CFQQ_SEEK_THR;
 }
 
 static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
@@ -1878,8 +1858,7 @@
 	cfqq->dispatched++;
 	elv_dispatch_sort(q, rq);
 
-	if (cfq_cfqq_sync(cfqq))
-		cfqd->sync_flight++;
+	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++;
 	cfqq->nr_sectors += blk_rq_sectors(rq);
 }
 
@@ -2219,6 +2198,19 @@
 	return dispatched;
 }
 
+static inline bool cfq_slice_used_soon(struct cfq_data *cfqd,
+	struct cfq_queue *cfqq)
+{
+	/* the queue hasn't finished any request, can't estimate */
+	if (cfq_cfqq_slice_new(cfqq))
+		return 1;
+	if (time_after(jiffies + cfqd->cfq_slice_idle * cfqq->dispatched,
+		cfqq->slice_end))
+		return 1;
+
+	return 0;
+}
+
 static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	unsigned int max_dispatch;
@@ -2226,16 +2218,16 @@
 	/*
 	 * Drain async requests before we start sync IO
 	 */
-	if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC])
+	if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_flight[BLK_RW_ASYNC])
 		return false;
 
 	/*
 	 * If this is an async queue and we have sync IO in flight, let it wait
 	 */
-	if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
+	if (cfqd->rq_in_flight[BLK_RW_SYNC] && !cfq_cfqq_sync(cfqq))
 		return false;
 
-	max_dispatch = cfqd->cfq_quantum;
+	max_dispatch = max_t(unsigned int, cfqd->cfq_quantum / 2, 1);
 	if (cfq_class_idle(cfqq))
 		max_dispatch = 1;
 
@@ -2252,13 +2244,22 @@
 		/*
 		 * We have other queues, don't allow more IO from this one
 		 */
-		if (cfqd->busy_queues > 1)
+		if (cfqd->busy_queues > 1 && cfq_slice_used_soon(cfqd, cfqq))
 			return false;
 
 		/*
 		 * Sole queue user, no limit
 		 */
-		max_dispatch = -1;
+		if (cfqd->busy_queues == 1)
+			max_dispatch = -1;
+		else
+			/*
+			 * Normally we start throttling cfqq when cfq_quantum/2
+			 * requests have been dispatched. But we can drive
+			 * deeper queue depths at the beginning of slice
+			 * subjected to upper limit of cfq_quantum.
+			 * */
+			max_dispatch = cfqd->cfq_quantum;
 	}
 
 	/*
@@ -2980,30 +2981,20 @@
 cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		       struct request *rq)
 {
-	sector_t sdist;
-	u64 total;
+	sector_t sdist = 0;
+	sector_t n_sec = blk_rq_sectors(rq);
+	if (cfqq->last_request_pos) {
+		if (cfqq->last_request_pos < blk_rq_pos(rq))
+			sdist = blk_rq_pos(rq) - cfqq->last_request_pos;
+		else
+			sdist = cfqq->last_request_pos - blk_rq_pos(rq);
+	}
 
-	if (!cfqq->last_request_pos)
-		sdist = 0;
-	else if (cfqq->last_request_pos < blk_rq_pos(rq))
-		sdist = blk_rq_pos(rq) - cfqq->last_request_pos;
+	cfqq->seek_history <<= 1;
+	if (blk_queue_nonrot(cfqd->queue))
+		cfqq->seek_history |= (n_sec < CFQQ_SECT_THR_NONROT);
 	else
-		sdist = cfqq->last_request_pos - blk_rq_pos(rq);
-
-	/*
-	 * Don't allow the seek distance to get too large from the
-	 * odd fragment, pagein, etc
-	 */
-	if (cfqq->seek_samples <= 60) /* second&third seek */
-		sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*1024);
-	else
-		sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*64);
-
-	cfqq->seek_samples = (7*cfqq->seek_samples + 256) / 8;
-	cfqq->seek_total = (7*cfqq->seek_total + (u64)256*sdist) / 8;
-	total = cfqq->seek_total + (cfqq->seek_samples/2);
-	do_div(total, cfqq->seek_samples);
-	cfqq->seek_mean = (sector_t)total;
+		cfqq->seek_history |= (sdist > CFQQ_SEEK_THR);
 }
 
 /*
@@ -3028,8 +3019,7 @@
 		cfq_mark_cfqq_deep(cfqq);
 
 	if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
-	    (!cfq_cfqq_deep(cfqq) && sample_valid(cfqq->seek_samples)
-	     && CFQQ_SEEKY(cfqq)))
+	    (!cfq_cfqq_deep(cfqq) && CFQQ_SEEKY(cfqq)))
 		enable_idle = 0;
 	else if (sample_valid(cic->ttime_samples)) {
 		if (cic->ttime_mean > cfqd->cfq_slice_idle)
@@ -3215,14 +3205,14 @@
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
 
-	if (rq_in_driver(cfqd) > cfqd->hw_tag_est_depth)
-		cfqd->hw_tag_est_depth = rq_in_driver(cfqd);
+	if (cfqd->rq_in_driver > cfqd->hw_tag_est_depth)
+		cfqd->hw_tag_est_depth = cfqd->rq_in_driver;
 
 	if (cfqd->hw_tag == 1)
 		return;
 
 	if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
-	    rq_in_driver(cfqd) <= CFQ_HW_QUEUE_MIN)
+	    cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN)
 		return;
 
 	/*
@@ -3232,7 +3222,7 @@
 	 */
 	if (cfqq && cfq_cfqq_idle_window(cfqq) &&
 	    cfqq->dispatched + cfqq->queued[0] + cfqq->queued[1] <
-	    CFQ_HW_QUEUE_MIN && rq_in_driver(cfqd) < CFQ_HW_QUEUE_MIN)
+	    CFQ_HW_QUEUE_MIN && cfqd->rq_in_driver < CFQ_HW_QUEUE_MIN)
 		return;
 
 	if (cfqd->hw_tag_samples++ < 50)
@@ -3285,13 +3275,12 @@
 
 	cfq_update_hw_tag(cfqd);
 
-	WARN_ON(!cfqd->rq_in_driver[sync]);
+	WARN_ON(!cfqd->rq_in_driver);
 	WARN_ON(!cfqq->dispatched);
-	cfqd->rq_in_driver[sync]--;
+	cfqd->rq_in_driver--;
 	cfqq->dispatched--;
 
-	if (cfq_cfqq_sync(cfqq))
-		cfqd->sync_flight--;
+	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;
 
 	if (sync) {
 		RQ_CIC(rq)->last_end_request = now;
@@ -3345,7 +3334,7 @@
 		}
 	}
 
-	if (!rq_in_driver(cfqd))
+	if (!cfqd->rq_in_driver)
 		cfq_schedule_dispatch(cfqd);
 }
 
diff --git a/block/elevator.c b/block/elevator.c
index 9ad5ccc..ee3a883 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -474,6 +474,15 @@
 	int ret;
 
 	/*
+	 * Levels of merges:
+	 * 	nomerges:  No merges at all attempted
+	 * 	noxmerges: Only simple one-hit cache try
+	 * 	merges:	   All merge tries attempted
+	 */
+	if (blk_queue_nomerges(q))
+		return ELEVATOR_NO_MERGE;
+
+	/*
 	 * First try one-hit cache.
 	 */
 	if (q->last_merge) {
@@ -484,7 +493,7 @@
 		}
 	}
 
-	if (blk_queue_nomerges(q))
+	if (blk_queue_noxmerges(q))
 		return ELEVATOR_NO_MERGE;
 
 	/*
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index d096fbc..bea003a 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1097,7 +1097,7 @@
 		dev->flags |= ATA_DFLAG_NO_UNLOAD;
 
 	/* configure max sectors */
-	blk_queue_max_sectors(sdev->request_queue, dev->max_sectors);
+	blk_queue_max_hw_sectors(sdev->request_queue, dev->max_sectors);
 
 	if (dev->class == ATA_DEV_ATAPI) {
 		struct request_queue *q = sdev->request_queue;
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 0c82d33..684fe04 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -772,7 +772,7 @@
 	}
 
 	blk_queue_segment_boundary(sdev->request_queue, segment_boundary);
-	blk_queue_max_hw_segments(sdev->request_queue, sg_tablesize);
+	blk_queue_max_segments(sdev->request_queue, sg_tablesize);
 	ata_port_printk(ap, KERN_INFO,
 		"DMA mask 0x%llX, segment boundary 0x%lX, hw segs %hu\n",
 		(unsigned long long)*ap->host->dev->dma_mask,
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index ce1fa92..459f1bc 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -2534,8 +2534,8 @@
   	blk_queue_bounce_limit(RequestQueue, Controller->BounceBufferLimit);
   	RequestQueue->queuedata = Controller;
   	blk_queue_max_hw_segments(RequestQueue, Controller->DriverScatterGatherLimit);
-	blk_queue_max_phys_segments(RequestQueue, Controller->DriverScatterGatherLimit);
-	blk_queue_max_sectors(RequestQueue, Controller->MaxBlocksPerCommand);
+	blk_queue_max_segments(RequestQueue, Controller->DriverScatterGatherLimit);
+	blk_queue_max_hw_sectors(RequestQueue, Controller->MaxBlocksPerCommand);
 	disk->queue = RequestQueue;
 	sprintf(disk->disk_name, "rd/c%dd%d", Controller->ControllerNumber, n);
 	disk->major = MajorNumber;
@@ -7134,7 +7134,7 @@
 	.MemoryWindowSize =	DAC960_PD_RegisterWindowSize,
 };
 
-static struct pci_device_id DAC960_id_table[] = {
+static const struct pci_device_id DAC960_id_table[] = {
 	{
 		.vendor 	= PCI_VENDOR_ID_MYLEX,
 		.device		= PCI_DEVICE_ID_MYLEX_DAC960_GEM,
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 4f68843..c6ddeac 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -434,7 +434,7 @@
 		goto out_free_dev;
 	blk_queue_make_request(brd->brd_queue, brd_make_request);
 	blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_TAG, NULL);
-	blk_queue_max_sectors(brd->brd_queue, 1024);
+	blk_queue_max_hw_sectors(brd->brd_queue, 1024);
 	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
 
 	disk = brd->brd_disk = alloc_disk(1 << part_shift);
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 9291614..9e3af30 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -257,6 +257,79 @@
 	hlist_del_init(&c->list);
 }
 
+static void cciss_free_sg_chain_blocks(SGDescriptor_struct **cmd_sg_list,
+	int nr_cmds)
+{
+	int i;
+
+	if (!cmd_sg_list)
+		return;
+	for (i = 0; i < nr_cmds; i++) {
+		kfree(cmd_sg_list[i]);
+		cmd_sg_list[i] = NULL;
+	}
+	kfree(cmd_sg_list);
+}
+
+static SGDescriptor_struct **cciss_allocate_sg_chain_blocks(
+	ctlr_info_t *h, int chainsize, int nr_cmds)
+{
+	int j;
+	SGDescriptor_struct **cmd_sg_list;
+
+	if (chainsize <= 0)
+		return NULL;
+
+	cmd_sg_list = kmalloc(sizeof(*cmd_sg_list) * nr_cmds, GFP_KERNEL);
+	if (!cmd_sg_list)
+		return NULL;
+
+	/* Build up chain blocks for each command */
+	for (j = 0; j < nr_cmds; j++) {
+		/* Need a block of chainsized s/g elements. */
+		cmd_sg_list[j] = kmalloc((chainsize *
+			sizeof(*cmd_sg_list[j])), GFP_KERNEL);
+		if (!cmd_sg_list[j]) {
+			dev_err(&h->pdev->dev, "Cannot get memory "
+				"for s/g chains.\n");
+			goto clean;
+		}
+	}
+	return cmd_sg_list;
+clean:
+	cciss_free_sg_chain_blocks(cmd_sg_list, nr_cmds);
+	return NULL;
+}
+
+static void cciss_unmap_sg_chain_block(ctlr_info_t *h, CommandList_struct *c)
+{
+	SGDescriptor_struct *chain_sg;
+	u64bit temp64;
+
+	if (c->Header.SGTotal <= h->max_cmd_sgentries)
+		return;
+
+	chain_sg = &c->SG[h->max_cmd_sgentries - 1];
+	temp64.val32.lower = chain_sg->Addr.lower;
+	temp64.val32.upper = chain_sg->Addr.upper;
+	pci_unmap_single(h->pdev, temp64.val, chain_sg->Len, PCI_DMA_TODEVICE);
+}
+
+static void cciss_map_sg_chain_block(ctlr_info_t *h, CommandList_struct *c,
+	SGDescriptor_struct *chain_block, int len)
+{
+	SGDescriptor_struct *chain_sg;
+	u64bit temp64;
+
+	chain_sg = &c->SG[h->max_cmd_sgentries - 1];
+	chain_sg->Ext = CCISS_SG_CHAIN;
+	chain_sg->Len = len;
+	temp64.val = pci_map_single(h->pdev, chain_block, len,
+				PCI_DMA_TODEVICE);
+	chain_sg->Addr.lower = temp64.val32.lower;
+	chain_sg->Addr.upper = temp64.val32.upper;
+}
+
 #include "cciss_scsi.c"		/* For SCSI tape support */
 
 static const char *raid_label[] = { "0", "4", "1(1+0)", "5", "5+1", "ADG",
@@ -1344,26 +1417,27 @@
 				kfree(buff);
 				return -ENOMEM;
 			}
-			// Fill in the command type
+			/* Fill in the command type */
 			c->cmd_type = CMD_IOCTL_PEND;
-			// Fill in Command Header
-			c->Header.ReplyQueue = 0;	// unused in simple mode
-			if (iocommand.buf_size > 0)	// buffer to fill
+			/* Fill in Command Header */
+			c->Header.ReplyQueue = 0;   /* unused in simple mode */
+			if (iocommand.buf_size > 0) /* buffer to fill */
 			{
 				c->Header.SGList = 1;
 				c->Header.SGTotal = 1;
-			} else	// no buffers to fill
+			} else /* no buffers to fill */
 			{
 				c->Header.SGList = 0;
 				c->Header.SGTotal = 0;
 			}
 			c->Header.LUN = iocommand.LUN_info;
-			c->Header.Tag.lower = c->busaddr;	// use the kernel address the cmd block for tag
+			/* use the kernel address the cmd block for tag */
+			c->Header.Tag.lower = c->busaddr;
 
-			// Fill in Request block
+			/* Fill in Request block */
 			c->Request = iocommand.Request;
 
-			// Fill in the scatter gather information
+			/* Fill in the scatter gather information */
 			if (iocommand.buf_size > 0) {
 				temp64.val = pci_map_single(host->pdev, buff,
 					iocommand.buf_size,
@@ -1371,7 +1445,7 @@
 				c->SG[0].Addr.lower = temp64.val32.lower;
 				c->SG[0].Addr.upper = temp64.val32.upper;
 				c->SG[0].Len = iocommand.buf_size;
-				c->SG[0].Ext = 0;	// we are not chaining
+				c->SG[0].Ext = 0;  /* we are not chaining */
 			}
 			c->waiting = &wait;
 
@@ -1670,14 +1744,9 @@
 	/* unmap the DMA mapping for all the scatter gather elements */
 	for (i = 0; i < cmd->Header.SGList; i++) {
 		if (curr_sg[sg_index].Ext == CCISS_SG_CHAIN) {
-			temp64.val32.lower = cmd->SG[i].Addr.lower;
-			temp64.val32.upper = cmd->SG[i].Addr.upper;
-			pci_dma_sync_single_for_cpu(h->pdev, temp64.val,
-						cmd->SG[i].Len, ddir);
-			pci_unmap_single(h->pdev, temp64.val,
-						cmd->SG[i].Len, ddir);
+			cciss_unmap_sg_chain_block(h, cmd);
 			/* Point to the next block */
-			curr_sg = h->cmd_sg_list[cmd->cmdindex]->sgchain;
+			curr_sg = h->cmd_sg_list[cmd->cmdindex];
 			sg_index = 0;
 		}
 		temp64.val32.lower = curr_sg[sg_index].Addr.lower;
@@ -1796,12 +1865,9 @@
 	blk_queue_bounce_limit(disk->queue, h->pdev->dma_mask);
 
 	/* This is a hardware imposed limit. */
-	blk_queue_max_hw_segments(disk->queue, h->maxsgentries);
+	blk_queue_max_segments(disk->queue, h->maxsgentries);
 
-	/* This is a limit in the driver and could be eliminated. */
-	blk_queue_max_phys_segments(disk->queue, h->maxsgentries);
-
-	blk_queue_max_sectors(disk->queue, h->cciss_max_sectors);
+	blk_queue_max_hw_sectors(disk->queue, h->cciss_max_sectors);
 
 	blk_queue_softirq_done(disk->queue, cciss_softirq_done);
 
@@ -2425,7 +2491,7 @@
 			c->Request.Type.Direction = XFER_READ;
 			c->Request.Timeout = 0;
 			c->Request.CDB[0] = cmd;
-			c->Request.CDB[6] = (size >> 24) & 0xFF;	//MSB
+			c->Request.CDB[6] = (size >> 24) & 0xFF; /* MSB */
 			c->Request.CDB[7] = (size >> 16) & 0xFF;
 			c->Request.CDB[8] = (size >> 8) & 0xFF;
 			c->Request.CDB[9] = size & 0xFF;
@@ -2694,7 +2760,7 @@
 			       "cciss: reading geometry failed, volume "
 			       "does not support reading geometry\n");
 			drv->heads = 255;
-			drv->sectors = 32;	// Sectors per track
+			drv->sectors = 32;	/* Sectors per track */
 			drv->cylinders = total_size + 1;
 			drv->raid_level = RAID_UNKNOWN;
 		} else {
@@ -3082,7 +3148,6 @@
 	SGDescriptor_struct *curr_sg;
 	drive_info_struct *drv;
 	int i, dir;
-	int nseg = 0;
 	int sg_index = 0;
 	int chained = 0;
 
@@ -3112,19 +3177,19 @@
 
 	/* fill in the request */
 	drv = creq->rq_disk->private_data;
-	c->Header.ReplyQueue = 0;	// unused in simple mode
+	c->Header.ReplyQueue = 0;	/* unused in simple mode */
 	/* got command from pool, so use the command block index instead */
 	/* for direct lookups. */
 	/* The first 2 bits are reserved for controller error reporting. */
 	c->Header.Tag.lower = (c->cmdindex << 3);
 	c->Header.Tag.lower |= 0x04;	/* flag for direct lookup. */
 	memcpy(&c->Header.LUN, drv->LunID, sizeof(drv->LunID));
-	c->Request.CDBLen = 10;	// 12 byte commands not in FW yet;
-	c->Request.Type.Type = TYPE_CMD;	// It is a command.
+	c->Request.CDBLen = 10;	/* 12 byte commands not in FW yet; */
+	c->Request.Type.Type = TYPE_CMD;	/* It is a command. */
 	c->Request.Type.Attribute = ATTR_SIMPLE;
 	c->Request.Type.Direction =
 	    (rq_data_dir(creq) == READ) ? XFER_READ : XFER_WRITE;
-	c->Request.Timeout = 0;	// Don't time out
+	c->Request.Timeout = 0;	/* Don't time out */
 	c->Request.CDB[0] =
 	    (rq_data_dir(creq) == READ) ? h->cciss_read : h->cciss_write;
 	start_blk = blk_rq_pos(creq);
@@ -3149,13 +3214,8 @@
 	for (i = 0; i < seg; i++) {
 		if (((sg_index+1) == (h->max_cmd_sgentries)) &&
 			!chained && ((seg - i) > 1)) {
-			nseg = seg - i;
-			curr_sg[sg_index].Len = (nseg) *
-					sizeof(SGDescriptor_struct);
-			curr_sg[sg_index].Ext = CCISS_SG_CHAIN;
-
 			/* Point to next chain block. */
-			curr_sg = h->cmd_sg_list[c->cmdindex]->sgchain;
+			curr_sg = h->cmd_sg_list[c->cmdindex];
 			sg_index = 0;
 			chained = 1;
 		}
@@ -3166,31 +3226,12 @@
 		curr_sg[sg_index].Addr.lower = temp64.val32.lower;
 		curr_sg[sg_index].Addr.upper = temp64.val32.upper;
 		curr_sg[sg_index].Ext = 0;  /* we are not chaining */
-
 		++sg_index;
 	}
-
-	if (chained) {
-		int len;
-		curr_sg = c->SG;
-		sg_index = h->max_cmd_sgentries - 1;
-		len = curr_sg[sg_index].Len;
-		/* Setup pointer to next chain block.
-		 * Fill out last element in current chain
-		 * block with address of next chain block.
-		 */
-		temp64.val = pci_map_single(h->pdev,
-					h->cmd_sg_list[c->cmdindex]->sgchain,
-					len, dir);
-
-		h->cmd_sg_list[c->cmdindex]->sg_chain_dma = temp64.val;
-		curr_sg[sg_index].Addr.lower = temp64.val32.lower;
-		curr_sg[sg_index].Addr.upper = temp64.val32.upper;
-
-		pci_dma_sync_single_for_device(h->pdev,
-				h->cmd_sg_list[c->cmdindex]->sg_chain_dma,
-				len, dir);
-	}
+	if (chained)
+		cciss_map_sg_chain_block(h, c, h->cmd_sg_list[c->cmdindex],
+			(seg - (h->max_cmd_sgentries - 1)) *
+				sizeof(SGDescriptor_struct));
 
 	/* track how many SG entries we are using */
 	if (seg > h->maxSG)
@@ -3209,11 +3250,11 @@
 	if (likely(blk_fs_request(creq))) {
 		if(h->cciss_read == CCISS_READ_10) {
 			c->Request.CDB[1] = 0;
-			c->Request.CDB[2] = (start_blk >> 24) & 0xff;	//MSB
+			c->Request.CDB[2] = (start_blk >> 24) & 0xff; /* MSB */
 			c->Request.CDB[3] = (start_blk >> 16) & 0xff;
 			c->Request.CDB[4] = (start_blk >> 8) & 0xff;
 			c->Request.CDB[5] = start_blk & 0xff;
-			c->Request.CDB[6] = 0;	// (sect >> 24) & 0xff; MSB
+			c->Request.CDB[6] = 0; /* (sect >> 24) & 0xff; MSB */
 			c->Request.CDB[7] = (blk_rq_sectors(creq) >> 8) & 0xff;
 			c->Request.CDB[8] = blk_rq_sectors(creq) & 0xff;
 			c->Request.CDB[9] = c->Request.CDB[11] = c->Request.CDB[12] = 0;
@@ -3222,7 +3263,7 @@
 
 			c->Request.CDBLen = 16;
 			c->Request.CDB[1]= 0;
-			c->Request.CDB[2]= (upper32 >> 24) & 0xff;	//MSB
+			c->Request.CDB[2]= (upper32 >> 24) & 0xff; /* MSB */
 			c->Request.CDB[3]= (upper32 >> 16) & 0xff;
 			c->Request.CDB[4]= (upper32 >>  8) & 0xff;
 			c->Request.CDB[5]= upper32 & 0xff;
@@ -4240,37 +4281,10 @@
 			goto clean4;
 		}
 	}
-	hba[i]->cmd_sg_list = kmalloc(sizeof(struct Cmd_sg_list *) *
-						hba[i]->nr_cmds,
-						GFP_KERNEL);
-	if (!hba[i]->cmd_sg_list) {
-		printk(KERN_ERR "cciss%d: Cannot get memory for "
-			"s/g chaining.\n", i);
+	hba[i]->cmd_sg_list = cciss_allocate_sg_chain_blocks(hba[i],
+		hba[i]->chainsize, hba[i]->nr_cmds);
+	if (!hba[i]->cmd_sg_list && hba[i]->chainsize > 0)
 		goto clean4;
-	}
-	/* Build up chain blocks for each command */
-	if (hba[i]->chainsize > 0) {
-		for (j = 0; j < hba[i]->nr_cmds; j++) {
-			hba[i]->cmd_sg_list[j] =
-					kmalloc(sizeof(struct Cmd_sg_list),
-							GFP_KERNEL);
-			if (!hba[i]->cmd_sg_list[j]) {
-				printk(KERN_ERR "cciss%d: Cannot get memory "
-					"for chain block.\n", i);
-				goto clean4;
-			}
-			/* Need a block of chainsized s/g elements. */
-			hba[i]->cmd_sg_list[j]->sgchain =
-					kmalloc((hba[i]->chainsize *
-						sizeof(SGDescriptor_struct)),
-						GFP_KERNEL);
-			if (!hba[i]->cmd_sg_list[j]->sgchain) {
-				printk(KERN_ERR "cciss%d: Cannot get memory "
-					"for s/g chains\n", i);
-				goto clean4;
-			}
-		}
-	}
 
 	spin_lock_init(&hba[i]->lock);
 
@@ -4329,16 +4343,7 @@
 	for (k = 0; k < hba[i]->nr_cmds; k++)
 		kfree(hba[i]->scatter_list[k]);
 	kfree(hba[i]->scatter_list);
-	/* Only free up extra s/g lists if controller supports them */
-	if (hba[i]->chainsize > 0) {
-		for (j = 0; j < hba[i]->nr_cmds; j++) {
-			if (hba[i]->cmd_sg_list[j]) {
-				kfree(hba[i]->cmd_sg_list[j]->sgchain);
-				kfree(hba[i]->cmd_sg_list[j]);
-			}
-		}
-		kfree(hba[i]->cmd_sg_list);
-	}
+	cciss_free_sg_chain_blocks(hba[i]->cmd_sg_list, hba[i]->nr_cmds);
 	if (hba[i]->cmd_pool)
 		pci_free_consistent(hba[i]->pdev,
 				    hba[i]->nr_cmds * sizeof(CommandList_struct),
@@ -4456,16 +4461,7 @@
 	for (j = 0; j < hba[i]->nr_cmds; j++)
 		kfree(hba[i]->scatter_list[j]);
 	kfree(hba[i]->scatter_list);
-	/* Only free up extra s/g lists if controller supports them */
-	if (hba[i]->chainsize > 0) {
-		for (j = 0; j < hba[i]->nr_cmds; j++) {
-			if (hba[i]->cmd_sg_list[j]) {
-				kfree(hba[i]->cmd_sg_list[j]->sgchain);
-				kfree(hba[i]->cmd_sg_list[j]);
-			}
-		}
-		kfree(hba[i]->cmd_sg_list);
-	}
+	cciss_free_sg_chain_blocks(hba[i]->cmd_sg_list, hba[i]->nr_cmds);
 	/*
 	 * Deliberately omit pci_disable_device(): it does something nasty to
 	 * Smart Array controllers that pci_enable_device does not undo
@@ -4498,7 +4494,7 @@
 	 * boundary. Given that we use pci_alloc_consistent() to allocate an
 	 * array of them, the size must be a multiple of 8 bytes.
 	 */
-	BUILD_BUG_ON(sizeof(CommandList_struct) % 8);
+	BUILD_BUG_ON(sizeof(CommandList_struct) % COMMANDLIST_ALIGNMENT);
 
 	printk(KERN_INFO DRIVER_NAME "\n");
 
diff --git a/drivers/block/cciss.h b/drivers/block/cciss.h
index 1d95db2..c5d4111 100644
--- a/drivers/block/cciss.h
+++ b/drivers/block/cciss.h
@@ -55,18 +55,12 @@
 	char device_initialized;     /* indicates whether dev is initialized */
 } drive_info_struct;
 
-struct Cmd_sg_list {
-	SGDescriptor_struct	*sgchain;
-	dma_addr_t		sg_chain_dma;
-	int			chain_block_size;
-};
-
 struct ctlr_info
 {
 	int	ctlr;
 	char	devname[8];
 	char    *product_name;
-	char	firm_ver[4]; // Firmware version 
+	char	firm_ver[4]; /* Firmware version */
 	struct pci_dev *pdev;
 	__u32	board_id;
 	void __iomem *vaddr;
@@ -89,7 +83,7 @@
 	int	maxsgentries;
 	int	chainsize;
 	int	max_cmd_sgentries;
-	struct Cmd_sg_list **cmd_sg_list;
+	SGDescriptor_struct **cmd_sg_list;
 
 #	define DOORBELL_INT	0
 #	define PERF_MODE_INT	1
@@ -103,7 +97,7 @@
 	BYTE	cciss_write;
 	BYTE	cciss_read_capacity;
 
-	// information about each logical volume
+	/* information about each logical volume */
 	drive_info_struct *drv[CISS_MAX_LUN];
 
 	struct access_method access;
@@ -116,7 +110,7 @@
 	unsigned int maxSG;
 	spinlock_t lock;
 
-	//* pointers to command and error info pool */ 
+	/* pointers to command and error info pool */
 	CommandList_struct 	*cmd_pool;
 	dma_addr_t		cmd_pool_dhandle; 
 	ErrorInfo_struct 	*errinfo_pool;
@@ -134,12 +128,10 @@
 	*/
 	int			next_to_run;
 
-	// Disk structures we need to pass back
+	/* Disk structures we need to pass back */
 	struct gendisk   *gendisk[CISS_MAX_LUN];
 #ifdef CONFIG_CISS_SCSI_TAPE
-	void *scsi_ctlr; /* ptr to structure containing scsi related stuff */
-	/* list of block side commands the scsi error handling sucked up */
-	/* and saved for later processing */
+	struct cciss_scsi_adapter_data_t *scsi_ctlr;
 #endif
 	unsigned char alive;
 	struct list_head scan_list;
@@ -315,4 +307,3 @@
 #define CCISS_LOCK(i)	(&hba[i]->lock)
 
 #endif /* CCISS_H */
-
diff --git a/drivers/block/cciss_cmd.h b/drivers/block/cciss_cmd.h
index 6afa700..e624ff9 100644
--- a/drivers/block/cciss_cmd.h
+++ b/drivers/block/cciss_cmd.h
@@ -1,31 +1,16 @@
 #ifndef CCISS_CMD_H
 #define CCISS_CMD_H
-//###########################################################################
-//DEFINES
-//###########################################################################
+
+#include <linux/cciss_defs.h>
+
+/* DEFINES */
 #define CISS_VERSION "1.00"
 
-//general boundary definitions
-#define SENSEINFOBYTES          32//note that this value may vary between host implementations
+/* general boundary definitions */
 #define MAXSGENTRIES            32
 #define CCISS_SG_CHAIN          0x80000000
 #define MAXREPLYQS              256
 
-//Command Status value
-#define CMD_SUCCESS             0x0000
-#define CMD_TARGET_STATUS       0x0001
-#define CMD_DATA_UNDERRUN       0x0002
-#define CMD_DATA_OVERRUN        0x0003
-#define CMD_INVALID             0x0004
-#define CMD_PROTOCOL_ERR        0x0005
-#define CMD_HARDWARE_ERR        0x0006
-#define CMD_CONNECTION_LOST     0x0007
-#define CMD_ABORTED             0x0008
-#define CMD_ABORT_FAILED        0x0009
-#define CMD_UNSOLICITED_ABORT   0x000A
-#define CMD_TIMEOUT             0x000B
-#define CMD_UNABORTABLE		0x000C
-
 /* Unit Attentions ASC's as defined for the MSA2012sa */
 #define POWER_OR_RESET			0x29
 #define STATE_CHANGED			0x2a
@@ -49,30 +34,13 @@
 #define ASYM_ACCESS_CHANGED		0x06
 #define LUN_CAPACITY_CHANGED		0x09
 
-//transfer direction
-#define XFER_NONE               0x00
-#define XFER_WRITE              0x01
-#define XFER_READ               0x02
-#define XFER_RSVD               0x03
-
-//task attribute
-#define ATTR_UNTAGGED           0x00
-#define ATTR_SIMPLE             0x04
-#define ATTR_HEADOFQUEUE        0x05
-#define ATTR_ORDERED            0x06
-#define ATTR_ACA                0x07
-
-//cdb type
-#define TYPE_CMD				0x00
-#define TYPE_MSG				0x01
-
-//config space register offsets
+/* config space register offsets */
 #define CFG_VENDORID            0x00
 #define CFG_DEVICEID            0x02
 #define CFG_I2OBAR              0x10
 #define CFG_MEM1BAR             0x14
 
-//i2o space register offsets
+/* i2o space register offsets */
 #define I2O_IBDB_SET            0x20
 #define I2O_IBDB_CLEAR          0x70
 #define I2O_INT_STATUS          0x30
@@ -81,7 +49,7 @@
 #define I2O_OBPOST_Q            0x44
 #define I2O_DMA1_CFG		0x214
 
-//Configuration Table
+/* Configuration Table */
 #define CFGTBL_ChangeReq        0x00000001l
 #define CFGTBL_AccCmds          0x00000001l
 
@@ -103,24 +71,17 @@
    __u64	val;
 } u64bit;
 
-// Type defs used in the following structs
-#define BYTE __u8
-#define WORD __u16
-#define HWORD __u16
-#define DWORD __u32
+/* Type defs used in the following structs */
 #define QWORD vals32 
 
-//###########################################################################
-//STRUCTURES
-//###########################################################################
-#define CISS_MAX_LUN	1024
+/* STRUCTURES */
 #define CISS_MAX_PHYS_LUN	1024
-// SCSI-3 Cmmands 
+/* SCSI-3 Cmmands */
 
 #pragma pack(1)	
 
 #define CISS_INQUIRY 0x12
-//Date returned
+/* Date returned */
 typedef struct _InquiryData_struct
 {
   BYTE data_byte[36];
@@ -128,7 +89,7 @@
 
 #define CISS_REPORT_LOG 0xc2    /* Report Logical LUNs */
 #define CISS_REPORT_PHYS 0xc3   /* Report Physical LUNs */
-// Data returned
+/* Data returned */
 typedef struct _ReportLUNdata_struct
 {
   BYTE LUNListLength[4];
@@ -139,8 +100,8 @@
 #define CCISS_READ_CAPACITY 0x25 /* Read Capacity */ 
 typedef struct _ReadCapdata_struct
 {
-  BYTE total_size[4];	// Total size in blocks
-  BYTE block_size[4];	// Size of blocks in bytes
+  BYTE total_size[4];	/* Total size in blocks */
+  BYTE block_size[4];	/* Size of blocks in bytes */
 } ReadCapdata_struct;
 
 #define CCISS_READ_CAPACITY_16 0x9e /* Read Capacity 16 */
@@ -172,52 +133,13 @@
 #define CDB_LEN10	10
 #define CDB_LEN16	16
 
-// BMIC commands 
+/* BMIC commands */
 #define BMIC_READ 0x26
 #define BMIC_WRITE 0x27
 #define BMIC_CACHE_FLUSH 0xc2
-#define CCISS_CACHE_FLUSH 0x01	//C2 was already being used by CCISS
+#define CCISS_CACHE_FLUSH 0x01	/* C2 was already being used by CCISS */
 
-//Command List Structure
-typedef union _SCSI3Addr_struct {
-   struct {
-    BYTE Dev;
-    BYTE Bus:6;
-    BYTE Mode:2;        // b00
-  } PeripDev;
-   struct {
-    BYTE DevLSB;
-    BYTE DevMSB:6;
-    BYTE Mode:2;        // b01
-  } LogDev;
-   struct {
-    BYTE Dev:5;
-    BYTE Bus:3;
-    BYTE Targ:6;
-    BYTE Mode:2;        // b10
-  } LogUnit;
-} SCSI3Addr_struct;
-
-typedef struct _PhysDevAddr_struct {
-  DWORD             TargetId:24;
-  DWORD             Bus:6;
-  DWORD             Mode:2;
-  SCSI3Addr_struct  Target[2]; //2 level target device addr
-} PhysDevAddr_struct;
-  
-typedef struct _LogDevAddr_struct {
-  DWORD            VolId:30;
-  DWORD            Mode:2;
-  BYTE             reserved[4];
-} LogDevAddr_struct;
-
-typedef union _LUNAddr_struct {
-  BYTE               LunAddrBytes[8];
-  SCSI3Addr_struct   SCSI3Lun[4];
-  PhysDevAddr_struct PhysDev;
-  LogDevAddr_struct  LogDev;
-} LUNAddr_struct;
-
+/* Command List Structure */
 #define CTLR_LUNID "\0\0\0\0\0\0\0\0"
 
 typedef struct _CommandListHeader_struct {
@@ -227,16 +149,6 @@
   QWORD             Tag;
   LUNAddr_struct    LUN;
 } CommandListHeader_struct;
-typedef struct _RequestBlock_struct {
-  BYTE   CDBLen;
-  struct {
-    BYTE Type:3;
-    BYTE Attribute:3;
-    BYTE Direction:2;
-  } Type;
-  HWORD  Timeout;
-  BYTE   CDB[16];
-} RequestBlock_struct;
 typedef struct _ErrDescriptor_struct {
   QWORD  Addr;
   DWORD  Len;
@@ -247,28 +159,6 @@
   DWORD  Ext;
 } SGDescriptor_struct;
 
-typedef union _MoreErrInfo_struct{
-  struct {
-    BYTE  Reserved[3];
-    BYTE  Type;
-    DWORD ErrorInfo;
-  }Common_Info;
-  struct{
-    BYTE  Reserved[2];
-    BYTE  offense_size;//size of offending entry
-    BYTE  offense_num; //byte # of offense 0-base
-    DWORD offense_value;
-  }Invalid_Cmd;
-}MoreErrInfo_struct;
-typedef struct _ErrorInfo_struct {
-  BYTE               ScsiStatus;
-  BYTE               SenseLen;
-  HWORD              CommandStatus;
-  DWORD              ResidualCnt;
-  MoreErrInfo_struct MoreErrInfo;
-  BYTE               SenseInfo[SENSEINFOBYTES];
-} ErrorInfo_struct;
-
 /* Command types */
 #define CMD_RWREQ       0x00
 #define CMD_IOCTL_PEND  0x01
@@ -277,10 +167,18 @@
 #define CMD_MSG_TIMEOUT 0x05
 #define CMD_MSG_STALE	0xff
 
-/* This structure needs to be divisible by 8 for new
- * indexing method.
+/* This structure needs to be divisible by COMMANDLIST_ALIGNMENT
+ * because low bits of the address are used to to indicate that
+ * whether the tag contains an index or an address.  PAD_32 and
+ * PAD_64 can be adjusted independently as needed for 32-bit
+ * and 64-bits systems.
  */
-#define PADSIZE (sizeof(long) - 4)
+#define COMMANDLIST_ALIGNMENT (8)
+#define IS_64_BIT ((sizeof(long) - 4)/4)
+#define IS_32_BIT (!IS_64_BIT)
+#define PAD_32 (0)
+#define PAD_64 (4)
+#define PADSIZE (IS_32_BIT * PAD_32 + IS_64_BIT * PAD_64)
 typedef struct _CommandList_struct {
   CommandListHeader_struct Header;
   RequestBlock_struct      Request;
@@ -300,7 +198,7 @@
   char   pad[PADSIZE];
 } CommandList_struct;
 
-//Configuration Table Structure
+/* Configuration Table Structure */
 typedef struct _HostWrite_struct {
   DWORD TransportRequest;
   DWORD Reserved;
@@ -326,4 +224,4 @@
   DWORD            MaxPhysicalDrivesPerLogicalUnit;
 } CfgTable_struct;
 #pragma pack()	 
-#endif // CCISS_CMD_H
+#endif /* CCISS_CMD_H */
diff --git a/drivers/block/cciss_scsi.c b/drivers/block/cciss_scsi.c
index 5d0e46d..e1d0e2c 100644
--- a/drivers/block/cciss_scsi.c
+++ b/drivers/block/cciss_scsi.c
@@ -84,7 +84,6 @@
 	.queuecommand		= cciss_scsi_queue_command,
 	.can_queue		= SCSI_CCISS_CAN_QUEUE,
 	.this_id		= 7,
-	.sg_tablesize		= MAXSGENTRIES,
 	.cmd_per_lun		= 1,
 	.use_clustering		= DISABLE_CLUSTERING,
 	/* Can't have eh_bus_reset_handler or eh_host_reset_handler for cciss */
@@ -93,11 +92,16 @@
 };
 
 #pragma pack(1)
+
+#define SCSI_PAD_32 0
+#define SCSI_PAD_64 0
+
 struct cciss_scsi_cmd_stack_elem_t {
 	CommandList_struct cmd;
 	ErrorInfo_struct Err;
 	__u32 busaddr;
-	__u32 pad;
+	int cmdindex;
+	u8 pad[IS_32_BIT * SCSI_PAD_32 + IS_64_BIT * SCSI_PAD_64];
 };
 
 #pragma pack()
@@ -118,16 +122,15 @@
 struct cciss_scsi_adapter_data_t {
 	struct Scsi_Host *scsi_host;
 	struct cciss_scsi_cmd_stack_t cmd_stack;
+	SGDescriptor_struct **cmd_sg_list;
 	int registered;
 	spinlock_t lock; // to protect ccissscsi[ctlr]; 
 };
 
 #define CPQ_TAPE_LOCK(ctlr, flags) spin_lock_irqsave( \
-	&(((struct cciss_scsi_adapter_data_t *) \
-	hba[ctlr]->scsi_ctlr)->lock), flags);
+	&hba[ctlr]->scsi_ctlr->lock, flags);
 #define CPQ_TAPE_UNLOCK(ctlr, flags) spin_unlock_irqrestore( \
-	&(((struct cciss_scsi_adapter_data_t *) \
-	hba[ctlr]->scsi_ctlr)->lock), flags);
+	&hba[ctlr]->scsi_ctlr->lock, flags);
 
 static CommandList_struct *
 scsi_cmd_alloc(ctlr_info_t *h)
@@ -143,7 +146,7 @@
 	struct cciss_scsi_cmd_stack_t *stk;
 	u64bit temp64;
 
-	sa = (struct cciss_scsi_adapter_data_t *) h->scsi_ctlr;
+	sa = h->scsi_ctlr;
 	stk = &sa->cmd_stack; 
 
 	if (stk->top < 0) 
@@ -154,6 +157,7 @@
 	memset(&c->Err, 0, sizeof(c->Err));
 	/* set physical addr of cmd and addr of scsi parameters */
 	c->cmd.busaddr = c->busaddr; 
+	c->cmd.cmdindex = c->cmdindex;
 	/* (__u32) (stk->cmd_pool_handle + 
 		(sizeof(struct cciss_scsi_cmd_stack_elem_t)*stk->top)); */
 
@@ -182,7 +186,7 @@
 	struct cciss_scsi_adapter_data_t *sa;
 	struct cciss_scsi_cmd_stack_t *stk;
 
-	sa = (struct cciss_scsi_adapter_data_t *) h->scsi_ctlr;
+	sa = h->scsi_ctlr;
 	stk = &sa->cmd_stack; 
 	if (stk->top >= CMD_STACK_SIZE) {
 		printk("cciss: scsi_cmd_free called too many times.\n");
@@ -199,24 +203,31 @@
 	struct cciss_scsi_cmd_stack_t *stk;
 	size_t size;
 
+	sa->cmd_sg_list = cciss_allocate_sg_chain_blocks(hba[ctlr],
+		hba[ctlr]->chainsize, CMD_STACK_SIZE);
+	if (!sa->cmd_sg_list && hba[ctlr]->chainsize > 0)
+		return -ENOMEM;
+
 	stk = &sa->cmd_stack; 
 	size = sizeof(struct cciss_scsi_cmd_stack_elem_t) * CMD_STACK_SIZE;
 
-	// pci_alloc_consistent guarantees 32-bit DMA address will
-	// be used
-
+	/* Check alignment, see cciss_cmd.h near CommandList_struct def. */
+	BUILD_BUG_ON((sizeof(*stk->pool) % COMMANDLIST_ALIGNMENT) != 0);
+	/* pci_alloc_consistent guarantees 32-bit DMA address will be used */
 	stk->pool = (struct cciss_scsi_cmd_stack_elem_t *)
 		pci_alloc_consistent(hba[ctlr]->pdev, size, &stk->cmd_pool_handle);
 
 	if (stk->pool == NULL) {
-		printk("stk->pool is null\n");
-		return -1;
+		cciss_free_sg_chain_blocks(sa->cmd_sg_list, CMD_STACK_SIZE);
+		sa->cmd_sg_list = NULL;
+		return -ENOMEM;
 	}
 
 	for (i=0; i<CMD_STACK_SIZE; i++) {
 		stk->elem[i] = &stk->pool[i];
 		stk->elem[i]->busaddr = (__u32) (stk->cmd_pool_handle + 
 			(sizeof(struct cciss_scsi_cmd_stack_elem_t) * i));
+		stk->elem[i]->cmdindex = i;
 	}
 	stk->top = CMD_STACK_SIZE-1;
 	return 0;
@@ -229,7 +240,7 @@
 	struct cciss_scsi_cmd_stack_t *stk;
 	size_t size;
 
-	sa = (struct cciss_scsi_adapter_data_t *) hba[ctlr]->scsi_ctlr;
+	sa = hba[ctlr]->scsi_ctlr;
 	stk = &sa->cmd_stack; 
 	if (stk->top != CMD_STACK_SIZE-1) {
 		printk( "cciss: %d scsi commands are still outstanding.\n",
@@ -241,6 +252,7 @@
 
 	pci_free_consistent(hba[ctlr]->pdev, size, stk->pool, stk->cmd_pool_handle);
 	stk->pool = NULL;
+	cciss_free_sg_chain_blocks(sa->cmd_sg_list, CMD_STACK_SIZE);
 }
 
 #if 0
@@ -530,8 +542,7 @@
 	CPQ_TAPE_LOCK(ctlr, flags);
 
 	if (hostno != -1)  /* if it's not the first time... */
-		sh = ((struct cciss_scsi_adapter_data_t *)
-			hba[ctlr]->scsi_ctlr)->scsi_host;
+		sh = hba[ctlr]->scsi_ctlr->scsi_host;
 
 	/* find any devices in ccissscsi[] that are not in 
 	   sd[] and remove them from ccissscsi[] */
@@ -702,7 +713,7 @@
 		kfree(shba);
 		shba = NULL;
 	}
-	hba[cntl_num]->scsi_ctlr = (void *) shba;
+	hba[cntl_num]->scsi_ctlr = shba;
 	return;
 }
 
@@ -725,6 +736,8 @@
 	ctlr = hba[cp->ctlr];
 
 	scsi_dma_unmap(cmd);
+	if (cp->Header.SGTotal > ctlr->max_cmd_sgentries)
+		cciss_unmap_sg_chain_block(ctlr, cp);
 
 	cmd->result = (DID_OK << 16); 		/* host byte */
 	cmd->result |= (COMMAND_COMPLETE << 8);	/* msg byte */
@@ -847,9 +860,10 @@
 	sh->io_port = 0;	// good enough?  FIXME, 
 	sh->n_io_port = 0;	// I don't think we use these two...
 	sh->this_id = SELF_SCSI_ID;  
+	sh->sg_tablesize = hba[ctlr]->maxsgentries;
 
 	((struct cciss_scsi_adapter_data_t *) 
-		hba[ctlr]->scsi_ctlr)->scsi_host = (void *) sh;
+		hba[ctlr]->scsi_ctlr)->scsi_host = sh;
 	sh->hostdata[0] = (unsigned long) hba[ctlr];
 	sh->irq = hba[ctlr]->intr[SIMPLE_MODE_INT];
 	sh->unique_id = sh->irq;
@@ -1364,34 +1378,54 @@
    dma mapping  and fills in the scatter gather entries of the 
    cciss command, cp. */
 
-static void
-cciss_scatter_gather(struct pci_dev *pdev, 
-		CommandList_struct *cp,	
-		struct scsi_cmnd *cmd)
+static void cciss_scatter_gather(ctlr_info_t *h, CommandList_struct *cp,
+	struct scsi_cmnd *cmd)
 {
 	unsigned int len;
 	struct scatterlist *sg;
 	__u64 addr64;
-	int use_sg, i;
+	int request_nsgs, i, chained, sg_index;
+	struct cciss_scsi_adapter_data_t *sa = h->scsi_ctlr;
+	SGDescriptor_struct *curr_sg;
 
-	BUG_ON(scsi_sg_count(cmd) > MAXSGENTRIES);
+	BUG_ON(scsi_sg_count(cmd) > h->maxsgentries);
 
-	use_sg = scsi_dma_map(cmd);
-	if (use_sg) {	/* not too many addrs? */
-		scsi_for_each_sg(cmd, sg, use_sg, i) {
+	chained = 0;
+	sg_index = 0;
+	curr_sg = cp->SG;
+	request_nsgs = scsi_dma_map(cmd);
+	if (request_nsgs) {
+		scsi_for_each_sg(cmd, sg, request_nsgs, i) {
+			if (sg_index + 1 == h->max_cmd_sgentries &&
+				!chained && request_nsgs - i > 1) {
+				chained = 1;
+				sg_index = 0;
+				curr_sg = sa->cmd_sg_list[cp->cmdindex];
+			}
 			addr64 = (__u64) sg_dma_address(sg);
 			len  = sg_dma_len(sg);
-			cp->SG[i].Addr.lower =
-				(__u32) (addr64 & (__u64) 0x00000000FFFFFFFF);
-			cp->SG[i].Addr.upper =
-				(__u32) ((addr64 >> 32) & (__u64) 0x00000000FFFFFFFF);
-			cp->SG[i].Len = len;
-			cp->SG[i].Ext = 0;  // we are not chaining
+			curr_sg[sg_index].Addr.lower =
+				(__u32) (addr64 & 0x0FFFFFFFFULL);
+			curr_sg[sg_index].Addr.upper =
+				(__u32) ((addr64 >> 32) & 0x0FFFFFFFFULL);
+			curr_sg[sg_index].Len = len;
+			curr_sg[sg_index].Ext = 0;
+			++sg_index;
 		}
+		if (chained)
+			cciss_map_sg_chain_block(h, cp,
+				sa->cmd_sg_list[cp->cmdindex],
+				(request_nsgs - (h->max_cmd_sgentries - 1)) *
+					sizeof(SGDescriptor_struct));
 	}
-
-	cp->Header.SGList = (__u8) use_sg;   /* no. SGs contig in this cmd */
-	cp->Header.SGTotal = (__u16) use_sg; /* total sgs in this cmd list */
+	/* track how many SG entries we are using */
+	if (request_nsgs > h->maxSG)
+		h->maxSG = request_nsgs;
+	cp->Header.SGTotal = (__u8) request_nsgs + chained;
+	if (request_nsgs > h->max_cmd_sgentries)
+		cp->Header.SGList = h->max_cmd_sgentries;
+	else
+		cp->Header.SGList = cp->Header.SGTotal;
 	return;
 }
 
@@ -1399,7 +1433,7 @@
 static int
 cciss_scsi_queue_command (struct scsi_cmnd *cmd, void (* done)(struct scsi_cmnd *))
 {
-	ctlr_info_t **c;
+	ctlr_info_t *c;
 	int ctlr, rc;
 	unsigned char scsi3addr[8];
 	CommandList_struct *cp;
@@ -1407,8 +1441,8 @@
 
 	// Get the ptr to our adapter structure (hba[i]) out of cmd->host.
 	// We violate cmd->host privacy here.  (Is there another way?)
-	c = (ctlr_info_t **) &cmd->device->host->hostdata[0];	
-	ctlr = (*c)->ctlr;
+	c = (ctlr_info_t *) cmd->device->host->hostdata[0];
+	ctlr = c->ctlr;
 
 	rc = lookup_scsi3addr(ctlr, cmd->device->channel, cmd->device->id, 
 			cmd->device->lun, scsi3addr);
@@ -1431,7 +1465,7 @@
            see what the device thinks of it. */
 
 	spin_lock_irqsave(CCISS_LOCK(ctlr), flags);
-	cp = scsi_cmd_alloc(*c);
+	cp = scsi_cmd_alloc(c);
 	spin_unlock_irqrestore(CCISS_LOCK(ctlr), flags);
 	if (cp == NULL) {			/* trouble... */
 		printk("scsi_cmd_alloc returned NULL!\n");
@@ -1489,15 +1523,14 @@
 		BUG();
 		break;
 	}
-
-	cciss_scatter_gather((*c)->pdev, cp, cmd); // Fill the SG list
+	cciss_scatter_gather(c, cp, cmd);
 
 	/* Put the request on the tail of the request queue */
 
 	spin_lock_irqsave(CCISS_LOCK(ctlr), flags);
-	addQ(&(*c)->reqQ, cp);
-	(*c)->Qdepth++;
-	start_io(*c);
+	addQ(&c->reqQ, cp);
+	c->Qdepth++;
+	start_io(c);
 	spin_unlock_irqrestore(CCISS_LOCK(ctlr), flags);
 
 	/* the cmd'll come back via intr handler in complete_scsi_command()  */
@@ -1514,7 +1547,7 @@
 	/* we are being forcibly unloaded, and may not refuse. */
 
 	spin_lock_irqsave(CCISS_LOCK(ctlr), flags);
-	sa = (struct cciss_scsi_adapter_data_t *) hba[ctlr]->scsi_ctlr;
+	sa = hba[ctlr]->scsi_ctlr;
 	stk = &sa->cmd_stack; 
 
 	/* if we weren't ever actually registered, don't unregister */ 
@@ -1541,7 +1574,7 @@
 	unsigned long flags;
 
 	spin_lock_irqsave(CCISS_LOCK(ctlr), flags);
-	sa = (struct cciss_scsi_adapter_data_t *) hba[ctlr]->scsi_ctlr;
+	sa = hba[ctlr]->scsi_ctlr;
 	stk = &sa->cmd_stack; 
 
 	if (sa->registered) {
@@ -1654,14 +1687,14 @@
 	int rc;
 	CommandList_struct *cmd_in_trouble;
 	unsigned char lunaddr[8];
-	ctlr_info_t **c;
+	ctlr_info_t *c;
 	int ctlr;
 
 	/* find the controller to which the command to be aborted was sent */
-	c = (ctlr_info_t **) &scsicmd->device->host->hostdata[0];	
+	c = (ctlr_info_t *) scsicmd->device->host->hostdata[0];
 	if (c == NULL) /* paranoia */
 		return FAILED;
-	ctlr = (*c)->ctlr;
+	ctlr = c->ctlr;
 	printk(KERN_WARNING "cciss%d: resetting tape drive or medium changer.\n", ctlr);
 	/* find the command that's giving us trouble */
 	cmd_in_trouble = (CommandList_struct *) scsicmd->host_scribble;
@@ -1671,7 +1704,7 @@
 	/* send a reset to the SCSI LUN which the command was sent to */
 	rc = sendcmd_withirq(CCISS_RESET_MSG, ctlr, NULL, 0, 0, lunaddr,
 		TYPE_MSG);
-	if (rc == 0 && wait_for_device_to_become_ready(*c, lunaddr) == 0)
+	if (rc == 0 && wait_for_device_to_become_ready(c, lunaddr) == 0)
 		return SUCCESS;
 	printk(KERN_WARNING "cciss%d: resetting device failed.\n", ctlr);
 	return FAILED;
@@ -1682,14 +1715,14 @@
 	int rc;
 	CommandList_struct *cmd_to_abort;
 	unsigned char lunaddr[8];
-	ctlr_info_t **c;
+	ctlr_info_t *c;
 	int ctlr;
 
 	/* find the controller to which the command to be aborted was sent */
-	c = (ctlr_info_t **) &scsicmd->device->host->hostdata[0];	
+	c = (ctlr_info_t *) scsicmd->device->host->hostdata[0];
 	if (c == NULL) /* paranoia */
 		return FAILED;
-	ctlr = (*c)->ctlr;
+	ctlr = c->ctlr;
 	printk(KERN_WARNING "cciss%d: aborting tardy SCSI cmd\n", ctlr);
 
 	/* find the command to be aborted */
diff --git a/drivers/block/cciss_scsi.h b/drivers/block/cciss_scsi.h
index 7b75024..6d5822f 100644
--- a/drivers/block/cciss_scsi.h
+++ b/drivers/block/cciss_scsi.h
@@ -25,16 +25,16 @@
 
 #include <scsi/scsicam.h> /* possibly irrelevant, since we don't show disks */
 
-		// the scsi id of the adapter...
+		/* the scsi id of the adapter... */
 #define SELF_SCSI_ID 15
-		// 15 is somewhat arbitrary, since the scsi-2 bus
-		// that's presented by the driver to the OS is
-		// fabricated.  The "real" scsi-3 bus the 
-		// hardware presents is fabricated too.
-		// The actual, honest-to-goodness physical
-		// bus that the devices are attached to is not 
-		// addressible natively, and may in fact turn
-		// out to be not scsi at all.
+		/* 15 is somewhat arbitrary, since the scsi-2 bus
+		   that's presented by the driver to the OS is
+		   fabricated.  The "real" scsi-3 bus the
+		   hardware presents is fabricated too.
+		   The actual, honest-to-goodness physical
+		   bus that the devices are attached to is not
+		   addressible natively, and may in fact turn
+		   out to be not scsi at all. */
 
 #define SCSI_CCISS_CAN_QUEUE 2
 
diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c
index 6422651..91d1163 100644
--- a/drivers/block/cpqarray.c
+++ b/drivers/block/cpqarray.c
@@ -448,11 +448,8 @@
 		blk_queue_bounce_limit(q, hba[i]->pci_dev->dma_mask);
 
 	/* This is a hardware imposed limit. */
-	blk_queue_max_hw_segments(q, SG_MAX);
+	blk_queue_max_segments(q, SG_MAX);
 
-	/* This is a driver limit and could be eliminated. */
-	blk_queue_max_phys_segments(q, SG_MAX);
-	
 	init_timer(&hba[i]->timer);
 	hba[i]->timer.expires = jiffies + IDA_TIMER;
 	hba[i]->timer.data = (unsigned long)hba[i];
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 1292e06..4df3b40 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -709,9 +709,8 @@
 
 	max_seg_s = min(queue_max_sectors(b) * queue_logical_block_size(b), max_seg_s);
 
-	blk_queue_max_sectors(q, max_seg_s >> 9);
-	blk_queue_max_phys_segments(q, max_segments ? max_segments : MAX_PHYS_SEGMENTS);
-	blk_queue_max_hw_segments(q, max_segments ? max_segments : MAX_HW_SEGMENTS);
+	blk_queue_max_hw_sectors(q, max_seg_s >> 9);
+	blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS);
 	blk_queue_max_segment_size(q, max_seg_s);
 	blk_queue_logical_block_size(q, 512);
 	blk_queue_segment_boundary(q, PAGE_SIZE-1);
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 3266b4f..b9b1170 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4234,7 +4234,7 @@
 		err = -ENOMEM;
 		goto out_unreg_driver;
 	}
-	blk_queue_max_sectors(floppy_queue, 64);
+	blk_queue_max_hw_sectors(floppy_queue, 64);
 
 	blk_register_region(MKDEV(FLOPPY_MAJOR, 0), 256, THIS_MODULE,
 			    floppy_find, NULL, NULL);
diff --git a/drivers/block/hd.c b/drivers/block/hd.c
index d5cdce0..5116c65 100644
--- a/drivers/block/hd.c
+++ b/drivers/block/hd.c
@@ -719,7 +719,7 @@
 		return -ENOMEM;
 	}
 
-	blk_queue_max_sectors(hd_queue, 255);
+	blk_queue_max_hw_sectors(hd_queue, 255);
 	init_timer(&device_timer);
 	device_timer.function = hd_times_out;
 	blk_queue_logical_block_size(hd_queue, 512);
diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c
index 02b2583..5416c9a 100644
--- a/drivers/block/mg_disk.c
+++ b/drivers/block/mg_disk.c
@@ -980,7 +980,7 @@
 				__func__, __LINE__);
 		goto probe_err_6;
 	}
-	blk_queue_max_sectors(host->breq, MG_MAX_SECTS);
+	blk_queue_max_hw_sectors(host->breq, MG_MAX_SECTS);
 	blk_queue_logical_block_size(host->breq, MG_SECTOR_SIZE);
 
 	init_timer(&host->timer);
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 569e39e..e712cd5 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -906,7 +906,7 @@
 	if (!pd_queue)
 		goto out1;
 
-	blk_queue_max_sectors(pd_queue, cluster);
+	blk_queue_max_hw_sectors(pd_queue, cluster);
 
 	if (register_blkdev(major, name))
 		goto out2;
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index ea54ea3..ddb4f9a 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -956,8 +956,7 @@
 		return -ENOMEM;
 	}
 
-	blk_queue_max_phys_segments(pf_queue, cluster);
-	blk_queue_max_hw_segments(pf_queue, cluster);
+	blk_queue_max_segments(pf_queue, cluster);
 
 	for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
 		struct gendisk *disk = pf->disk;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 68b5957..b72935b 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -569,6 +569,7 @@
 	}
 
 	spin_lock_init(&pkt->lock);
+	bio_list_init(&pkt->orig_bios);
 
 	for (i = 0; i < frames; i++) {
 		struct bio *bio = pkt_bio_alloc(1);
@@ -721,43 +722,6 @@
 }
 
 /*
- * Add a bio to a single linked list defined by its head and tail pointers.
- */
-static void pkt_add_list_last(struct bio *bio, struct bio **list_head, struct bio **list_tail)
-{
-	bio->bi_next = NULL;
-	if (*list_tail) {
-		BUG_ON((*list_head) == NULL);
-		(*list_tail)->bi_next = bio;
-		(*list_tail) = bio;
-	} else {
-		BUG_ON((*list_head) != NULL);
-		(*list_head) = bio;
-		(*list_tail) = bio;
-	}
-}
-
-/*
- * Remove and return the first bio from a single linked list defined by its
- * head and tail pointers.
- */
-static inline struct bio *pkt_get_list_first(struct bio **list_head, struct bio **list_tail)
-{
-	struct bio *bio;
-
-	if (*list_head == NULL)
-		return NULL;
-
-	bio = *list_head;
-	*list_head = bio->bi_next;
-	if (*list_head == NULL)
-		*list_tail = NULL;
-
-	bio->bi_next = NULL;
-	return bio;
-}
-
-/*
  * Send a packet_command to the underlying block device and
  * wait for completion.
  */
@@ -876,13 +840,10 @@
 static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio)
 {
 	spin_lock(&pd->iosched.lock);
-	if (bio_data_dir(bio) == READ) {
-		pkt_add_list_last(bio, &pd->iosched.read_queue,
-				  &pd->iosched.read_queue_tail);
-	} else {
-		pkt_add_list_last(bio, &pd->iosched.write_queue,
-				  &pd->iosched.write_queue_tail);
-	}
+	if (bio_data_dir(bio) == READ)
+		bio_list_add(&pd->iosched.read_queue, bio);
+	else
+		bio_list_add(&pd->iosched.write_queue, bio);
 	spin_unlock(&pd->iosched.lock);
 
 	atomic_set(&pd->iosched.attention, 1);
@@ -917,8 +878,8 @@
 		int reads_queued, writes_queued;
 
 		spin_lock(&pd->iosched.lock);
-		reads_queued = (pd->iosched.read_queue != NULL);
-		writes_queued = (pd->iosched.write_queue != NULL);
+		reads_queued = !bio_list_empty(&pd->iosched.read_queue);
+		writes_queued = !bio_list_empty(&pd->iosched.write_queue);
 		spin_unlock(&pd->iosched.lock);
 
 		if (!reads_queued && !writes_queued)
@@ -927,7 +888,7 @@
 		if (pd->iosched.writing) {
 			int need_write_seek = 1;
 			spin_lock(&pd->iosched.lock);
-			bio = pd->iosched.write_queue;
+			bio = bio_list_peek(&pd->iosched.write_queue);
 			spin_unlock(&pd->iosched.lock);
 			if (bio && (bio->bi_sector == pd->iosched.last_write))
 				need_write_seek = 0;
@@ -950,13 +911,10 @@
 		}
 
 		spin_lock(&pd->iosched.lock);
-		if (pd->iosched.writing) {
-			bio = pkt_get_list_first(&pd->iosched.write_queue,
-						 &pd->iosched.write_queue_tail);
-		} else {
-			bio = pkt_get_list_first(&pd->iosched.read_queue,
-						 &pd->iosched.read_queue_tail);
-		}
+		if (pd->iosched.writing)
+			bio = bio_list_pop(&pd->iosched.write_queue);
+		else
+			bio = bio_list_pop(&pd->iosched.read_queue);
 		spin_unlock(&pd->iosched.lock);
 
 		if (!bio)
@@ -992,14 +950,14 @@
 static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q)
 {
 	if ((pd->settings.size << 9) / CD_FRAMESIZE
-	    <= queue_max_phys_segments(q)) {
+	    <= queue_max_segments(q)) {
 		/*
 		 * The cdrom device can handle one segment/frame
 		 */
 		clear_bit(PACKET_MERGE_SEGS, &pd->flags);
 		return 0;
 	} else if ((pd->settings.size << 9) / PAGE_SIZE
-		   <= queue_max_phys_segments(q)) {
+		   <= queue_max_segments(q)) {
 		/*
 		 * We can handle this case at the expense of some extra memory
 		 * copies during write operations
@@ -1114,7 +1072,7 @@
 	int f;
 	char written[PACKET_MAX_SIZE];
 
-	BUG_ON(!pkt->orig_bios);
+	BUG_ON(bio_list_empty(&pkt->orig_bios));
 
 	atomic_set(&pkt->io_wait, 0);
 	atomic_set(&pkt->io_errors, 0);
@@ -1124,7 +1082,7 @@
 	 */
 	memset(written, 0, sizeof(written));
 	spin_lock(&pkt->lock);
-	for (bio = pkt->orig_bios; bio; bio = bio->bi_next) {
+	bio_list_for_each(bio, &pkt->orig_bios) {
 		int first_frame = (bio->bi_sector - pkt->sector) / (CD_FRAMESIZE >> 9);
 		int num_frames = bio->bi_size / CD_FRAMESIZE;
 		pd->stats.secs_w += num_frames * (CD_FRAMESIZE >> 9);
@@ -1363,7 +1321,7 @@
 			break;
 		pkt_rbtree_erase(pd, node);
 		spin_lock(&pkt->lock);
-		pkt_add_list_last(bio, &pkt->orig_bios, &pkt->orig_bios_tail);
+		bio_list_add(&pkt->orig_bios, bio);
 		pkt->write_size += bio->bi_size / CD_FRAMESIZE;
 		spin_unlock(&pkt->lock);
 	}
@@ -1409,7 +1367,7 @@
 	 */
 	frames_write = 0;
 	spin_lock(&pkt->lock);
-	for (bio = pkt->orig_bios; bio; bio = bio->bi_next) {
+	bio_list_for_each(bio, &pkt->orig_bios) {
 		int segment = bio->bi_idx;
 		int src_offs = 0;
 		int first_frame = (bio->bi_sector - pkt->sector) / (CD_FRAMESIZE >> 9);
@@ -1472,20 +1430,14 @@
 
 static void pkt_finish_packet(struct packet_data *pkt, int uptodate)
 {
-	struct bio *bio, *next;
+	struct bio *bio;
 
 	if (!uptodate)
 		pkt->cache_valid = 0;
 
 	/* Finish all bios corresponding to this packet */
-	bio = pkt->orig_bios;
-	while (bio) {
-		next = bio->bi_next;
-		bio->bi_next = NULL;
+	while ((bio = bio_list_pop(&pkt->orig_bios)))
 		bio_endio(bio, uptodate ? 0 : -EIO);
-		bio = next;
-	}
-	pkt->orig_bios = pkt->orig_bios_tail = NULL;
 }
 
 static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt)
@@ -2360,7 +2312,7 @@
 		 * even if the size is a multiple of the packet size.
 		 */
 		spin_lock_irq(q->queue_lock);
-		blk_queue_max_sectors(q, pd->settings.size);
+		blk_queue_max_hw_sectors(q, pd->settings.size);
 		spin_unlock_irq(q->queue_lock);
 		set_bit(PACKET_WRITABLE, &pd->flags);
 	} else {
@@ -2567,8 +2519,7 @@
 			spin_lock(&pkt->lock);
 			if ((pkt->state == PACKET_WAITING_STATE) ||
 			    (pkt->state == PACKET_READ_WAIT_STATE)) {
-				pkt_add_list_last(bio, &pkt->orig_bios,
-						  &pkt->orig_bios_tail);
+				bio_list_add(&pkt->orig_bios, bio);
 				pkt->write_size += bio->bi_size / CD_FRAMESIZE;
 				if ((pkt->write_size >= pkt->frames) &&
 				    (pkt->state == PACKET_WAITING_STATE)) {
@@ -2662,7 +2613,7 @@
 
 	blk_queue_make_request(q, pkt_make_request);
 	blk_queue_logical_block_size(q, CD_FRAMESIZE);
-	blk_queue_max_sectors(q, PACKET_MAX_SECTORS);
+	blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS);
 	blk_queue_merge_bvec(q, pkt_merge_bvec);
 	q->queuedata = pd;
 }
@@ -2898,6 +2849,8 @@
 
 	spin_lock_init(&pd->lock);
 	spin_lock_init(&pd->iosched.lock);
+	bio_list_init(&pd->iosched.read_queue);
+	bio_list_init(&pd->iosched.write_queue);
 	sprintf(pd->name, DRIVER_NAME"%d", idx);
 	init_waitqueue_head(&pd->wqueue);
 	pd->bio_queue = RB_ROOT;
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 03a130d..bc95469 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -474,7 +474,7 @@
 
 	blk_queue_bounce_limit(queue, BLK_BOUNCE_HIGH);
 
-	blk_queue_max_sectors(queue, dev->bounce_size >> 9);
+	blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9);
 	blk_queue_segment_boundary(queue, -1UL);
 	blk_queue_dma_alignment(queue, dev->blk_size-1);
 	blk_queue_logical_block_size(queue, dev->blk_size);
@@ -482,8 +482,7 @@
 	blk_queue_ordered(queue, QUEUE_ORDERED_DRAIN_FLUSH,
 			  ps3disk_prepare_flush);
 
-	blk_queue_max_phys_segments(queue, -1);
-	blk_queue_max_hw_segments(queue, -1);
+	blk_queue_max_segments(queue, -1);
 	blk_queue_max_segment_size(queue, dev->bounce_size);
 
 	gendisk = alloc_disk(PS3DISK_MINORS);
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index 1fb6c31..e446082 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -751,10 +751,9 @@
 	priv->queue = queue;
 	queue->queuedata = dev;
 	blk_queue_make_request(queue, ps3vram_make_request);
-	blk_queue_max_phys_segments(queue, MAX_PHYS_SEGMENTS);
-	blk_queue_max_hw_segments(queue, MAX_HW_SEGMENTS);
-	blk_queue_max_segment_size(queue, MAX_SEGMENT_SIZE);
-	blk_queue_max_sectors(queue, SAFE_MAX_SECTORS);
+	blk_queue_max_segments(queue, BLK_MAX_SEGMENTS);
+	blk_queue_max_segment_size(queue, BLK_MAX_SEGMENT_SIZE);
+	blk_queue_max_hw_sectors(queue, BLK_SAFE_MAX_SECTORS);
 
 	gendisk = alloc_disk(1);
 	if (!gendisk) {
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 411f064..48e8fee 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -691,9 +691,8 @@
 
 	port->disk = g;
 
-	blk_queue_max_hw_segments(q, port->ring_cookies);
-	blk_queue_max_phys_segments(q, port->ring_cookies);
-	blk_queue_max_sectors(q, port->max_xfer_size);
+	blk_queue_max_segments(q, port->ring_cookies);
+	blk_queue_max_hw_sectors(q, port->max_xfer_size);
 	g->major = vdc_major;
 	g->first_minor = port->vio.vdev->dev_no << PARTITION_SHIFT;
 	strcpy(g->disk_name, port->disk_name);
diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c
index a7c4184..b70f0fc 100644
--- a/drivers/block/sx8.c
+++ b/drivers/block/sx8.c
@@ -409,7 +409,7 @@
 static void carm_remove_one (struct pci_dev *pdev);
 static int carm_bdev_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 
-static struct pci_device_id carm_pci_tbl[] = {
+static const struct pci_device_id carm_pci_tbl[] = {
 	{ PCI_VENDOR_ID_PROMISE, 0x8000, PCI_ANY_ID, PCI_ANY_ID, 0, 0, },
 	{ PCI_VENDOR_ID_PROMISE, 0x8002, PCI_ANY_ID, PCI_ANY_ID, 0, 0, },
 	{ }	/* terminate list */
@@ -1518,8 +1518,7 @@
 			break;
 		}
 		disk->queue = q;
-		blk_queue_max_hw_segments(q, CARM_MAX_REQ_SG);
-		blk_queue_max_phys_segments(q, CARM_MAX_REQ_SG);
+		blk_queue_max_segments(q, CARM_MAX_REQ_SG);
 		blk_queue_segment_boundary(q, CARM_SG_BOUNDARY);
 
 		q->queuedata = port;
diff --git a/drivers/block/ub.c b/drivers/block/ub.c
index c739b20..2e88983 100644
--- a/drivers/block/ub.c
+++ b/drivers/block/ub.c
@@ -393,7 +393,7 @@
 #define ub_usb_ids  usb_storage_usb_ids
 #else
 
-static struct usb_device_id ub_usb_ids[] = {
+static const struct usb_device_id ub_usb_ids[] = {
 	{ USB_INTERFACE_INFO(USB_CLASS_MASS_STORAGE, US_SC_SCSI, US_PR_BULK) },
 	{ }
 };
@@ -2320,10 +2320,9 @@
 	disk->queue = q;
 
 	blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
-	blk_queue_max_hw_segments(q, UB_MAX_REQ_SG);
-	blk_queue_max_phys_segments(q, UB_MAX_REQ_SG);
+	blk_queue_max_segments(q, UB_MAX_REQ_SG);
 	blk_queue_segment_boundary(q, 0xffffffff);	/* Dubious. */
-	blk_queue_max_sectors(q, UB_MAX_SECTORS);
+	blk_queue_max_hw_sectors(q, UB_MAX_SECTORS);
 	blk_queue_logical_block_size(q, lun->capacity.bsize);
 
 	lun->disk = disk;
diff --git a/drivers/block/viodasd.c b/drivers/block/viodasd.c
index 1b3def1..788d938 100644
--- a/drivers/block/viodasd.c
+++ b/drivers/block/viodasd.c
@@ -462,9 +462,8 @@
 	}
 
 	d->disk = g;
-	blk_queue_max_hw_segments(q, VIOMAXBLOCKDMA);
-	blk_queue_max_phys_segments(q, VIOMAXBLOCKDMA);
-	blk_queue_max_sectors(q, VIODASD_MAXSECTORS);
+	blk_queue_max_segments(q, VIOMAXBLOCKDMA);
+	blk_queue_max_hw_sectors(q, VIODASD_MAXSECTORS);
 	g->major = VIODASD_MAJOR;
 	g->first_minor = dev_no << PARTITION_SHIFT;
 	if (dev_no >= 26)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 7eff828..3c64af0 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -435,7 +435,7 @@
 	kfree(vblk);
 }
 
-static struct virtio_device_id id_table[] = {
+static const struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID },
 	{ 0 },
 };
diff --git a/drivers/block/xd.c b/drivers/block/xd.c
index d1fd032..1a325fb 100644
--- a/drivers/block/xd.c
+++ b/drivers/block/xd.c
@@ -242,7 +242,7 @@
 	}
 
 	/* xd_maxsectors depends on controller - so set after detection */
-	blk_queue_max_sectors(xd_queue, xd_maxsectors);
+	blk_queue_max_hw_sectors(xd_queue, xd_maxsectors);
 
 	for (i = 0; i < xd_drives; i++)
 		add_disk(xd_gendisk[i]);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 05a31e5..9c09694 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -346,15 +346,14 @@
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
 	blk_queue_logical_block_size(rq, sector_size);
-	blk_queue_max_sectors(rq, 512);
+	blk_queue_max_hw_sectors(rq, 512);
 
 	/* Each segment in a request is up to an aligned page in size. */
 	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
 	blk_queue_max_segment_size(rq, PAGE_SIZE);
 
 	/* Ensure a merged request will fit in a single I/O ring slot. */
-	blk_queue_max_phys_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
-	blk_queue_max_hw_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
+	blk_queue_max_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
 
 	/* Make sure buffer addresses are sector-aligned. */
 	blk_queue_dma_alignment(rq, 511);
@@ -1050,7 +1049,7 @@
 };
 
 
-static struct xenbus_device_id blkfront_ids[] = {
+static const struct xenbus_device_id blkfront_ids[] = {
 	{ "vbd" },
 	{ "" }
 };
diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c
index e5c5415..e1c95e2 100644
--- a/drivers/block/xsysace.c
+++ b/drivers/block/xsysace.c
@@ -1227,7 +1227,7 @@
 }
 
 /* Match table for of_platform binding */
-static struct of_device_id ace_of_match[] __devinitdata = {
+static const struct of_device_id ace_of_match[] __devinitconst = {
 	{ .compatible = "xlnx,opb-sysace-1.00.b", },
 	{ .compatible = "xlnx,opb-sysace-1.00.c", },
 	{ .compatible = "xlnx,xps-sysace-1.00.a", },
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index e789e6c..03c71f7 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -741,7 +741,7 @@
 {
 	blk_queue_logical_block_size(gd.gdrom_rq, GDROM_HARD_SECTOR);
 	/* using DMA so memory will need to be contiguous */
-	blk_queue_max_hw_segments(gd.gdrom_rq, 1);
+	blk_queue_max_segments(gd.gdrom_rq, 1);
 	/* set a large max size to get most from DMA */
 	blk_queue_max_segment_size(gd.gdrom_rq, 0x40000);
 	gd.disk->queue = gd.gdrom_rq;
diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c
index 57ca69e..cc435be 100644
--- a/drivers/cdrom/viocd.c
+++ b/drivers/cdrom/viocd.c
@@ -616,9 +616,8 @@
 	gendisk->first_minor = deviceno;
 	strncpy(gendisk->disk_name, c->name,
 			sizeof(gendisk->disk_name));
-	blk_queue_max_hw_segments(q, 1);
-	blk_queue_max_phys_segments(q, 1);
-	blk_queue_max_sectors(q, 4096 / 512);
+	blk_queue_max_segments(q, 1);
+	blk_queue_max_hw_sectors(q, 4096 / 512);
 	gendisk->queue = q;
 	gendisk->fops = &viocd_fops;
 	gendisk->flags = GENHD_FL_CD|GENHD_FL_REMOVABLE;
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index d485cdd..70fef40 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -1571,7 +1571,7 @@
 		sdev->start_stop_pwr_cond = 1;
 
 	if (lu->tgt->workarounds & SBP2_WORKAROUND_128K_MAX_TRANS)
-		blk_queue_max_sectors(sdev->request_queue, 128 * 1024 / 512);
+		blk_queue_max_hw_sectors(sdev->request_queue, 128 * 1024 / 512);
 
 	blk_queue_max_segment_size(sdev->request_queue, SBP2_MAX_SEG_SIZE);
 
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 7f87801..3b128dc 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -679,7 +679,7 @@
 		if (max_s > hwif->rqsize)
 			max_s = hwif->rqsize;
 
-		blk_queue_max_sectors(q, max_s);
+		blk_queue_max_hw_sectors(q, max_s);
 	}
 
 	printk(KERN_INFO "%s: max request size: %dKiB\n", drive->name,
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index fefbdfc..efd9076 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -486,7 +486,7 @@
 		drive->atapi_flags |= IDE_AFLAG_ZIP_DRIVE;
 		/* This value will be visible in the /proc/ide/hdx/settings */
 		drive->pc_delay = IDEFLOPPY_PC_DELAY;
-		blk_queue_max_sectors(drive->queue, 64);
+		blk_queue_max_hw_sectors(drive->queue, 64);
 	}
 
 	/*
@@ -494,7 +494,7 @@
 	 * nasty clicking noises without it, so please don't remove this.
 	 */
 	if (strncmp((char *)&id[ATA_ID_PROD], "IOMEGA Clik!", 11) == 0) {
-		blk_queue_max_sectors(drive->queue, 64);
+		blk_queue_max_hw_sectors(drive->queue, 64);
 		drive->atapi_flags |= IDE_AFLAG_CLIK_DRIVE;
 		/* IOMEGA Clik! drives do not support lock/unlock commands */
 		drive->dev_flags &= ~IDE_DFLAG_DOORLOCKING;
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 4d76ba4..f8c1ae6 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -774,7 +774,7 @@
 
 	if (hwif->rqsize < max_sectors)
 		max_sectors = hwif->rqsize;
-	blk_queue_max_sectors(q, max_sectors);
+	blk_queue_max_hw_sectors(q, max_sectors);
 
 #ifdef CONFIG_PCI
 	/* When we have an IOMMU, we may have a problem where pci_map_sg()
@@ -790,8 +790,7 @@
 		max_sg_entries >>= 1;
 #endif /* CONFIG_PCI */
 
-	blk_queue_max_hw_segments(q, max_sg_entries);
-	blk_queue_max_phys_segments(q, max_sg_entries);
+	blk_queue_max_segments(q, max_sg_entries);
 
 	/* assign drive queue */
 	drive->queue = q;
diff --git a/drivers/ieee1394/sbp2.c b/drivers/ieee1394/sbp2.c
index f199896..c88696a 100644
--- a/drivers/ieee1394/sbp2.c
+++ b/drivers/ieee1394/sbp2.c
@@ -2020,7 +2020,7 @@
 	if (lu->workarounds & SBP2_WORKAROUND_POWER_CONDITION)
 		sdev->start_stop_pwr_cond = 1;
 	if (lu->workarounds & SBP2_WORKAROUND_128K_MAX_TRANS)
-		blk_queue_max_sectors(sdev->request_queue, 128 * 1024 / 512);
+		blk_queue_max_hw_sectors(sdev->request_queue, 128 * 1024 / 512);
 
 	blk_queue_max_segment_size(sdev->request_queue, SBP2_MAX_SEG_SIZE);
 	return 0;
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 00435bd..af2d39d 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -177,7 +177,7 @@
 		 */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
 		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
-			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+			blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		conf->array_sectors += rdev->sectors;
 		cnt++;
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 32a662f..4b323f4 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -308,7 +308,7 @@
 		 */
 			if (q->merge_bvec_fn &&
 			    queue_max_sectors(q) > (PAGE_SIZE>>9))
-				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+				blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9);
 
 			conf->working_disks++;
 			mddev->degraded--;
@@ -478,7 +478,7 @@
 		 * a merge_bvec_fn to be involved in multipath */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
 		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
-			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+			blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		if (!test_bit(Faulty, &rdev->flags))
 			conf->working_disks++;
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 77605cd..a1f7147 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -182,7 +182,7 @@
 
 		if (rdev1->bdev->bd_disk->queue->merge_bvec_fn &&
 		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
-			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+			blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		if (!smallest || (rdev1->sectors < smallest->sectors))
 			smallest = rdev1;
@@ -325,7 +325,7 @@
 	}
 	if (md_check_no_bitmap(mddev))
 		return -EINVAL;
-	blk_queue_max_sectors(mddev->queue, mddev->chunk_sectors);
+	blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
 	mddev->queue->queue_lock = &mddev->queue->__queue_lock;
 
 	ret = create_strip_zones(mddev);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 859bd3f..5a06122 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1158,7 +1158,7 @@
 			 */
 			if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
 			    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
-				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+				blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9);
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
@@ -2103,7 +2103,7 @@
 		 */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
 		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
-			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+			blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9);
 	}
 
 	mddev->degraded = 0;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index d119b7b..7584f9a 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1161,7 +1161,7 @@
 			 */
 			if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
 			    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
-				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+				blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9);
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
@@ -2260,7 +2260,7 @@
 		 */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
 		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
-			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+			blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->head_position = 0;
 	}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index ceb24af..509c8f3 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3739,7 +3739,7 @@
 	if ((bi->bi_size>>9) > queue_max_sectors(q))
 		return 0;
 	blk_recount_segments(q, bi);
-	if (bi->bi_phys_segments > queue_max_phys_segments(q))
+	if (bi->bi_phys_segments > queue_max_segments(q))
 		return 0;
 
 	if (q->merge_bvec_fn)
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index bd83fa0a..972b870 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -1226,9 +1226,8 @@
 	blk_queue_prep_rq(msb->queue, mspro_block_prepare_req);
 
 	blk_queue_bounce_limit(msb->queue, limit);
-	blk_queue_max_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES);
-	blk_queue_max_phys_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS);
-	blk_queue_max_hw_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS);
+	blk_queue_max_hw_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES);
+	blk_queue_max_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS);
 	blk_queue_max_segment_size(msb->queue,
 				   MSPRO_BLOCK_MAX_PAGES * msb->page_size);
 
diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c
index e39986a..2658b14 100644
--- a/drivers/message/i2o/i2o_block.c
+++ b/drivers/message/i2o/i2o_block.c
@@ -1065,9 +1065,8 @@
 	queue = gd->queue;
 	queue->queuedata = i2o_blk_dev;
 
-	blk_queue_max_phys_segments(queue, I2O_MAX_PHYS_SEGMENTS);
-	blk_queue_max_sectors(queue, max_sectors);
-	blk_queue_max_hw_segments(queue, i2o_sg_tablesize(c, body_size));
+	blk_queue_max_hw_sectors(queue, max_sectors);
+	blk_queue_max_segments(queue, i2o_sg_tablesize(c, body_size));
 
 	osm_debug("max sectors = %d\n", queue->max_sectors);
 	osm_debug("phys segments = %d\n", queue->max_phys_segments);
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index c5a7a85..381fe03 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -154,9 +154,8 @@
 
 		if (mq->bounce_buf) {
 			blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_ANY);
-			blk_queue_max_sectors(mq->queue, bouncesz / 512);
-			blk_queue_max_phys_segments(mq->queue, bouncesz / 512);
-			blk_queue_max_hw_segments(mq->queue, bouncesz / 512);
+			blk_queue_max_hw_sectors(mq->queue, bouncesz / 512);
+			blk_queue_max_segments(mq->queue, bouncesz / 512);
 			blk_queue_max_segment_size(mq->queue, bouncesz);
 
 			mq->sg = kmalloc(sizeof(struct scatterlist),
@@ -180,10 +179,9 @@
 
 	if (!mq->bounce_buf) {
 		blk_queue_bounce_limit(mq->queue, limit);
-		blk_queue_max_sectors(mq->queue,
+		blk_queue_max_hw_sectors(mq->queue,
 			min(host->max_blk_count, host->max_req_size / 512));
-		blk_queue_max_phys_segments(mq->queue, host->max_phys_segs);
-		blk_queue_max_hw_segments(mq->queue, host->max_hw_segs);
+		blk_queue_max_segments(mq->queue, host->max_hw_segs);
 		blk_queue_max_segment_size(mq->queue, host->max_seg_size);
 
 		mq->sg = kmalloc(sizeof(struct scatterlist) *
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 9ab1ae4..4951aa8 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -2139,9 +2139,8 @@
 
 	blk_queue_logical_block_size(block->request_queue, block->bp_block);
 	max = block->base->discipline->max_blocks << block->s2b_shift;
-	blk_queue_max_sectors(block->request_queue, max);
-	blk_queue_max_phys_segments(block->request_queue, -1L);
-	blk_queue_max_hw_segments(block->request_queue, -1L);
+	blk_queue_max_hw_sectors(block->request_queue, max);
+	blk_queue_max_segments(block->request_queue, -1L);
 	/* with page sized segments we can translate each segement into
 	 * one idaw/tidaw
 	 */
diff --git a/drivers/s390/char/tape_block.c b/drivers/s390/char/tape_block.c
index 8d3d720..097da8c 100644
--- a/drivers/s390/char/tape_block.c
+++ b/drivers/s390/char/tape_block.c
@@ -222,9 +222,8 @@
 		goto cleanup_queue;
 
 	blk_queue_logical_block_size(blkdat->request_queue, TAPEBLOCK_HSEC_SIZE);
-	blk_queue_max_sectors(blkdat->request_queue, TAPEBLOCK_MAX_SEC);
-	blk_queue_max_phys_segments(blkdat->request_queue, -1L);
-	blk_queue_max_hw_segments(blkdat->request_queue, -1L);
+	blk_queue_max_hw_sectors(blkdat->request_queue, TAPEBLOCK_MAX_SEC);
+	blk_queue_max_segments(blkdat->request_queue, -1L);
 	blk_queue_max_segment_size(blkdat->request_queue, -1L);
 	blk_queue_segment_boundary(blkdat->request_queue, -1L);
 
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 87b536a..732f6d3 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -4195,7 +4195,7 @@
 		if (tgt->service_parms.class3_parms[0] & 0x80000000)
 			rport->supported_classes |= FC_COS_CLASS3;
 		if (rport->rqst_q)
-			blk_queue_max_hw_segments(rport->rqst_q, 1);
+			blk_queue_max_segments(rport->rqst_q, 1);
 	} else
 		tgt_dbg(tgt, "rport add failed\n");
 	spin_unlock_irqrestore(vhost->host->host_lock, flags);
@@ -4669,7 +4669,7 @@
 	}
 
 	if (shost_to_fc_host(shost)->rqst_q)
-		blk_queue_max_hw_segments(shost_to_fc_host(shost)->rqst_q, 1);
+		blk_queue_max_segments(shost_to_fc_host(shost)->rqst_q, 1);
 	dev_set_drvdata(dev, vhost);
 	spin_lock(&ibmvfc_driver_lock);
 	list_add_tail(&vhost->queue, &ibmvfc_head);
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 9e52d16..032f0d0 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -3674,7 +3674,7 @@
 		if (ipr_is_vset_device(res)) {
 			blk_queue_rq_timeout(sdev->request_queue,
 					     IPR_VSET_RW_TIMEOUT);
-			blk_queue_max_sectors(sdev->request_queue, IPR_VSET_MAX_SECTORS);
+			blk_queue_max_hw_sectors(sdev->request_queue, IPR_VSET_MAX_SECTORS);
 		}
 		if (ipr_is_vset_device(res) || ipr_is_scsi_disk(res))
 			sdev->allow_restart = 1;
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index b6f1ef9..9b1c143 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -235,7 +235,7 @@
 		scsi_dev->allow_restart = 1;
 		blk_queue_rq_timeout(scsi_dev->request_queue,
 				     PMCRAID_VSET_IO_TIMEOUT);
-		blk_queue_max_sectors(scsi_dev->request_queue,
+		blk_queue_max_hw_sectors(scsi_dev->request_queue,
 				      PMCRAID_VSET_MAX_SECTORS);
 	}
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 5697709..1646fe7 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1630,10 +1630,10 @@
 	/*
 	 * this limit is imposed by hardware restrictions
 	 */
-	blk_queue_max_hw_segments(q, shost->sg_tablesize);
-	blk_queue_max_phys_segments(q, SCSI_MAX_SG_CHAIN_SEGMENTS);
+	blk_queue_max_segments(q, min_t(unsigned short, shost->sg_tablesize,
+					SCSI_MAX_SG_CHAIN_SEGMENTS));
 
-	blk_queue_max_sectors(q, shost->max_sectors);
+	blk_queue_max_hw_sectors(q, shost->max_sectors);
 	blk_queue_bounce_limit(q, scsi_calculate_bounce_limit(shost));
 	blk_queue_segment_boundary(q, shost->dma_boundary);
 	dma_set_seg_boundary(dev, shost->dma_boundary);
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index f697229..4bc8b77 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -879,7 +879,7 @@
 	 * broken RA4x00 Compaq Disk Array
 	 */
 	if (*bflags & BLIST_MAX_512)
-		blk_queue_max_sectors(sdev->request_queue, 512);
+		blk_queue_max_hw_sectors(sdev->request_queue, 512);
 
 	/*
 	 * Some devices may not want to have a start command automatically
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 040f751..c996d98 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -287,8 +287,7 @@
 	if (list_empty(&sdp->sfds)) {	/* no existing opens on this device */
 		sdp->sgdebug = 0;
 		q = sdp->device->request_queue;
-		sdp->sg_tablesize = min(queue_max_hw_segments(q),
-					queue_max_phys_segments(q));
+		sdp->sg_tablesize = queue_max_segments(q);
 	}
 	if ((sfp = sg_add_sfp(sdp, dev)))
 		filp->private_data = sfp;
@@ -1376,8 +1375,7 @@
 	sdp->device = scsidp;
 	INIT_LIST_HEAD(&sdp->sfds);
 	init_waitqueue_head(&sdp->o_excl_wait);
-	sdp->sg_tablesize = min(queue_max_hw_segments(q),
-				queue_max_phys_segments(q));
+	sdp->sg_tablesize = queue_max_segments(q);
 	sdp->index = k;
 	kref_init(&sdp->d_ref);
 
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index d04ea9a..f67d1a1 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -3983,8 +3983,7 @@
 		return -ENODEV;
 	}
 
-	i = min(queue_max_hw_segments(SDp->request_queue),
-		queue_max_phys_segments(SDp->request_queue));
+	i = queue_max_segments(SDp->request_queue);
 	if (st_max_sg_segs < i)
 		i = st_max_sg_segs;
 	buffer = new_tape_buffer((SDp->host)->unchecked_isa_dma, i);
diff --git a/drivers/staging/hv/blkvsc_drv.c b/drivers/staging/hv/blkvsc_drv.c
index 62b2828..45d9081 100644
--- a/drivers/staging/hv/blkvsc_drv.c
+++ b/drivers/staging/hv/blkvsc_drv.c
@@ -363,10 +363,7 @@
 	blkdev->gd->queue = blk_init_queue(blkvsc_request, &blkdev->lock);
 
 	blk_queue_max_segment_size(blkdev->gd->queue, PAGE_SIZE);
-	blk_queue_max_phys_segments(blkdev->gd->queue,
-				    MAX_MULTIPAGE_BUFFER_COUNT);
-	blk_queue_max_hw_segments(blkdev->gd->queue,
-				  MAX_MULTIPAGE_BUFFER_COUNT);
+	blk_queue_max_segments(blkdev->gd->queue, MAX_MULTIPAGE_BUFFER_COUNT);
 	blk_queue_segment_boundary(blkdev->gd->queue, PAGE_SIZE-1);
 	blk_queue_bounce_limit(blkdev->gd->queue, BLK_BOUNCE_ANY);
 	blk_queue_dma_alignment(blkdev->gd->queue, 511);
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index e5e6df3..aadc16b 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -134,14 +134,14 @@
 		if (us->fflags & US_FL_MAX_SECTORS_MIN)
 			max_sectors = PAGE_CACHE_SIZE >> 9;
 		if (queue_max_sectors(sdev->request_queue) > max_sectors)
-			blk_queue_max_sectors(sdev->request_queue,
+			blk_queue_max_hw_sectors(sdev->request_queue,
 					      max_sectors);
 	} else if (sdev->type == TYPE_TAPE) {
 		/* Tapes need much higher max_sector limits, so just
 		 * raise it to the maximum possible (4 GB / 512) and
 		 * let the queue segment size sort out the real limit.
 		 */
-		blk_queue_max_sectors(sdev->request_queue, 0x7FFFFF);
+		blk_queue_max_hw_sectors(sdev->request_queue, 0x7FFFFF);
 	}
 
 	/* Some USB host controllers can't do DMA; they have to use PIO.
@@ -495,7 +495,7 @@
 	unsigned short ms;
 
 	if (sscanf(buf, "%hu", &ms) > 0 && ms <= SCSI_DEFAULT_MAX_SECTORS) {
-		blk_queue_max_sectors(sdev->request_queue, ms);
+		blk_queue_max_hw_sectors(sdev->request_queue, ms);
 		return strlen(buf);
 	}
 	return -EINVAL;	
diff --git a/fs/bio.c b/fs/bio.c
index 88094af..0bda289 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -507,10 +507,8 @@
 	int nr_pages;
 
 	nr_pages = ((queue_max_sectors(q) << 9) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	if (nr_pages > queue_max_phys_segments(q))
-		nr_pages = queue_max_phys_segments(q);
-	if (nr_pages > queue_max_hw_segments(q))
-		nr_pages = queue_max_hw_segments(q);
+	if (nr_pages > queue_max_segments(q))
+		nr_pages = queue_max_segments(q);
 
 	return nr_pages;
 }
@@ -557,7 +555,7 @@
 					.bi_rw = bio->bi_rw,
 				};
 
-				if (q->merge_bvec_fn(q, &bvm, prev) < len) {
+				if (q->merge_bvec_fn(q, &bvm, prev) != prev->bv_len) {
 					prev->bv_len -= len;
 					return 0;
 				}
@@ -575,8 +573,7 @@
 	 * make this too complex.
 	 */
 
-	while (bio->bi_phys_segments >= queue_max_phys_segments(q)
-	       || bio->bi_phys_segments >= queue_max_hw_segments(q)) {
+	while (bio->bi_phys_segments >= queue_max_segments(q)) {
 
 		if (retried_segments)
 			return 0;
@@ -611,7 +608,7 @@
 		 * merge_bvec_fn() returns number of bytes it can accept
 		 * at this offset
 		 */
-		if (q->merge_bvec_fn(q, &bvm, bvec) < len) {
+		if (q->merge_bvec_fn(q, &bvm, bvec) != bvec->bv_len) {
 			bvec->bv_page = NULL;
 			bvec->bv_len = 0;
 			bvec->bv_offset = 0;
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 64bc899..e8865c1 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -412,9 +412,10 @@
 	pdev = part_to_dev(p);
 
 	p->start_sect = start;
-	p->alignment_offset = queue_sector_alignment_offset(disk->queue, start);
-	p->discard_alignment = queue_sector_discard_alignment(disk->queue,
-							      start);
+	p->alignment_offset =
+		queue_limit_alignment_offset(&disk->queue->limits, start);
+	p->discard_alignment =
+		queue_limit_discard_alignment(&disk->queue->limits, start);
 	p->nr_sects = len;
 	p->partno = partno;
 	p->policy = get_disk_ro(disk);
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 756f831..91be0d8 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -43,6 +43,7 @@
 header-y += bpqether.h
 header-y += bsg.h
 header-y += can.h
+header-y += cciss_defs.h
 header-y += cdk.h
 header-y += chio.h
 header-y += coda_psdev.h
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1896e86..ebd22db 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -316,8 +316,7 @@
 	unsigned int		discard_alignment;
 
 	unsigned short		logical_block_size;
-	unsigned short		max_hw_segments;
-	unsigned short		max_phys_segments;
+	unsigned short		max_segments;
 
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
@@ -462,6 +461,7 @@
 #define QUEUE_FLAG_VIRT        QUEUE_FLAG_NONROT /* paravirt device */
 #define QUEUE_FLAG_IO_STAT     15	/* do IO stats */
 #define QUEUE_FLAG_DISCARD     16	/* supports DISCARD */
+#define QUEUE_FLAG_NOXMERGES   17	/* No extended merges */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_CLUSTER) |		\
@@ -587,6 +587,8 @@
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
+#define blk_queue_noxmerges(q)	\
+	test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
 #define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
 #define blk_queue_flushing(q)	((q)->ordseq)
@@ -918,10 +920,27 @@
 extern void blk_cleanup_queue(struct request_queue *);
 extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);
-extern void blk_queue_max_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
-extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short);
-extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short);
+
+/* Temporary compatibility wrapper */
+static inline void blk_queue_max_sectors(struct request_queue *q, unsigned int max)
+{
+	blk_queue_max_hw_sectors(q, max);
+}
+
+extern void blk_queue_max_segments(struct request_queue *, unsigned short);
+
+static inline void blk_queue_max_phys_segments(struct request_queue *q, unsigned short max)
+{
+	blk_queue_max_segments(q, max);
+}
+
+static inline void blk_queue_max_hw_segments(struct request_queue *q, unsigned short max)
+{
+	blk_queue_max_segments(q, max);
+}
+
+
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 extern void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors);
@@ -1014,11 +1033,15 @@
 #define MAX_PHYS_SEGMENTS 128
 #define MAX_HW_SEGMENTS 128
 #define SAFE_MAX_SECTORS 255
-#define BLK_DEF_MAX_SECTORS 1024
-
 #define MAX_SEGMENT_SIZE	65536
 
-#define BLK_SEG_BOUNDARY_MASK	0xFFFFFFFFUL
+enum blk_default_limits {
+	BLK_MAX_SEGMENTS	= 128,
+	BLK_SAFE_MAX_SECTORS	= 255,
+	BLK_DEF_MAX_SECTORS	= 1024,
+	BLK_MAX_SEGMENT_SIZE	= 65536,
+	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
+};
 
 #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
 
@@ -1042,14 +1065,9 @@
 	return q->limits.max_hw_sectors;
 }
 
-static inline unsigned short queue_max_hw_segments(struct request_queue *q)
+static inline unsigned short queue_max_segments(struct request_queue *q)
 {
-	return q->limits.max_hw_segments;
-}
-
-static inline unsigned short queue_max_phys_segments(struct request_queue *q)
-{
-	return q->limits.max_phys_segments;
+	return q->limits.max_segments;
 }
 
 static inline unsigned int queue_max_segment_size(struct request_queue *q)
@@ -1110,18 +1128,13 @@
 	return q->limits.alignment_offset;
 }
 
-static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t offset)
+static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
 {
 	unsigned int granularity = max(lim->physical_block_size, lim->io_min);
+	unsigned int alignment = (sector << 9) & (granularity - 1);
 
-	offset &= granularity - 1;
-	return (granularity + lim->alignment_offset - offset) & (granularity - 1);
-}
-
-static inline int queue_sector_alignment_offset(struct request_queue *q,
-						sector_t sector)
-{
-	return queue_limit_alignment_offset(&q->limits, sector << 9);
+	return (granularity + lim->alignment_offset - alignment)
+		& (granularity - 1);
 }
 
 static inline int bdev_alignment_offset(struct block_device *bdev)
@@ -1145,10 +1158,8 @@
 	return q->limits.discard_alignment;
 }
 
-static inline int queue_sector_discard_alignment(struct request_queue *q,
-						 sector_t sector)
+static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector)
 {
-	struct queue_limits *lim = &q->limits;
 	unsigned int alignment = (sector << 9) & (lim->discard_granularity - 1);
 
 	return (lim->discard_granularity + lim->discard_alignment - alignment)
diff --git a/include/linux/cciss_defs.h b/include/linux/cciss_defs.h
new file mode 100644
index 0000000..316b670
--- /dev/null
+++ b/include/linux/cciss_defs.h
@@ -0,0 +1,130 @@
+#ifndef CCISS_DEFS_H
+#define CCISS_DEFS_H
+
+#include <linux/types.h>
+
+/* general boundary definitions */
+#define SENSEINFOBYTES          32 /* note that this value may vary
+				      between host implementations */
+
+/* Command Status value */
+#define CMD_SUCCESS             0x0000
+#define CMD_TARGET_STATUS       0x0001
+#define CMD_DATA_UNDERRUN       0x0002
+#define CMD_DATA_OVERRUN        0x0003
+#define CMD_INVALID             0x0004
+#define CMD_PROTOCOL_ERR        0x0005
+#define CMD_HARDWARE_ERR        0x0006
+#define CMD_CONNECTION_LOST     0x0007
+#define CMD_ABORTED             0x0008
+#define CMD_ABORT_FAILED        0x0009
+#define CMD_UNSOLICITED_ABORT   0x000A
+#define CMD_TIMEOUT             0x000B
+#define CMD_UNABORTABLE		0x000C
+
+/* transfer direction */
+#define XFER_NONE               0x00
+#define XFER_WRITE              0x01
+#define XFER_READ               0x02
+#define XFER_RSVD               0x03
+
+/* task attribute */
+#define ATTR_UNTAGGED           0x00
+#define ATTR_SIMPLE             0x04
+#define ATTR_HEADOFQUEUE        0x05
+#define ATTR_ORDERED            0x06
+#define ATTR_ACA                0x07
+
+/* cdb type */
+#define TYPE_CMD				0x00
+#define TYPE_MSG				0x01
+
+/* Type defs used in the following structs */
+#define BYTE __u8
+#define WORD __u16
+#define HWORD __u16
+#define DWORD __u32
+
+#define CISS_MAX_LUN	1024
+
+#define LEVEL2LUN   1 /* index into Target(x) structure, due to byte swapping */
+#define LEVEL3LUN   0
+
+#pragma pack(1)
+
+/* Command List Structure */
+typedef union _SCSI3Addr_struct {
+   struct {
+    BYTE Dev;
+    BYTE Bus:6;
+    BYTE Mode:2;        /* b00 */
+  } PeripDev;
+   struct {
+    BYTE DevLSB;
+    BYTE DevMSB:6;
+    BYTE Mode:2;        /* b01 */
+  } LogDev;
+   struct {
+    BYTE Dev:5;
+    BYTE Bus:3;
+    BYTE Targ:6;
+    BYTE Mode:2;        /* b10 */
+  } LogUnit;
+} SCSI3Addr_struct;
+
+typedef struct _PhysDevAddr_struct {
+  DWORD             TargetId:24;
+  DWORD             Bus:6;
+  DWORD             Mode:2;
+  SCSI3Addr_struct  Target[2]; /* 2 level target device addr */
+} PhysDevAddr_struct;
+
+typedef struct _LogDevAddr_struct {
+  DWORD            VolId:30;
+  DWORD            Mode:2;
+  BYTE             reserved[4];
+} LogDevAddr_struct;
+
+typedef union _LUNAddr_struct {
+  BYTE               LunAddrBytes[8];
+  SCSI3Addr_struct   SCSI3Lun[4];
+  PhysDevAddr_struct PhysDev;
+  LogDevAddr_struct  LogDev;
+} LUNAddr_struct;
+
+typedef struct _RequestBlock_struct {
+  BYTE   CDBLen;
+  struct {
+    BYTE Type:3;
+    BYTE Attribute:3;
+    BYTE Direction:2;
+  } Type;
+  HWORD  Timeout;
+  BYTE   CDB[16];
+} RequestBlock_struct;
+
+typedef union _MoreErrInfo_struct{
+  struct {
+    BYTE  Reserved[3];
+    BYTE  Type;
+    DWORD ErrorInfo;
+  } Common_Info;
+  struct{
+    BYTE  Reserved[2];
+    BYTE  offense_size; /* size of offending entry */
+    BYTE  offense_num;  /* byte # of offense 0-base */
+    DWORD offense_value;
+  } Invalid_Cmd;
+} MoreErrInfo_struct;
+typedef struct _ErrorInfo_struct {
+  BYTE               ScsiStatus;
+  BYTE               SenseLen;
+  HWORD              CommandStatus;
+  DWORD              ResidualCnt;
+  MoreErrInfo_struct MoreErrInfo;
+  BYTE               SenseInfo[SENSEINFOBYTES];
+} ErrorInfo_struct;
+
+#pragma pack()
+
+#endif /* CCISS_DEFS_H */
diff --git a/include/linux/cciss_ioctl.h b/include/linux/cciss_ioctl.h
index eb130b4..986493f 100644
--- a/include/linux/cciss_ioctl.h
+++ b/include/linux/cciss_ioctl.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/ioctl.h>
+#include <linux/cciss_defs.h>
 
 #define CCISS_IOC_MAGIC 'B'
 
@@ -36,133 +37,6 @@
 
 #define MAX_KMALLOC_SIZE 128000
 
-#ifndef CCISS_CMD_H
-// This defines are duplicated in cciss_cmd.h in the driver directory 
-
-//general boundary definitions
-#define SENSEINFOBYTES          32//note that this value may vary between host implementations
-
-//Command Status value
-#define CMD_SUCCESS             0x0000
-#define CMD_TARGET_STATUS       0x0001
-#define CMD_DATA_UNDERRUN       0x0002
-#define CMD_DATA_OVERRUN        0x0003
-#define CMD_INVALID             0x0004
-#define CMD_PROTOCOL_ERR        0x0005
-#define CMD_HARDWARE_ERR        0x0006
-#define CMD_CONNECTION_LOST     0x0007
-#define CMD_ABORTED             0x0008
-#define CMD_ABORT_FAILED        0x0009
-#define CMD_UNSOLICITED_ABORT   0x000A
-#define CMD_TIMEOUT             0x000B
-#define CMD_UNABORTABLE		0x000C
-
-//transfer direction
-#define XFER_NONE               0x00
-#define XFER_WRITE              0x01
-#define XFER_READ               0x02
-#define XFER_RSVD               0x03
-
-//task attribute
-#define ATTR_UNTAGGED           0x00
-#define ATTR_SIMPLE             0x04
-#define ATTR_HEADOFQUEUE        0x05
-#define ATTR_ORDERED            0x06
-#define ATTR_ACA                0x07
-
-//cdb type
-#define TYPE_CMD				0x00
-#define TYPE_MSG				0x01
-
-// Type defs used in the following structs
-#define BYTE __u8
-#define WORD __u16
-#define HWORD __u16
-#define DWORD __u32
-
-#define CISS_MAX_LUN	1024
-
-#define LEVEL2LUN   1   // index into Target(x) structure, due to byte swapping
-#define LEVEL3LUN   0
-
-#pragma pack(1)
-
-//Command List Structure
-typedef union _SCSI3Addr_struct {
-   struct {
-    BYTE Dev;
-    BYTE Bus:6;
-    BYTE Mode:2;        // b00
-  } PeripDev;
-   struct {
-    BYTE DevLSB;
-    BYTE DevMSB:6;
-    BYTE Mode:2;        // b01
-  } LogDev;
-   struct {
-    BYTE Dev:5;
-    BYTE Bus:3;
-    BYTE Targ:6;
-    BYTE Mode:2;        // b10
-  } LogUnit;
-} SCSI3Addr_struct;
-
-typedef struct _PhysDevAddr_struct {
-  DWORD             TargetId:24;
-  DWORD             Bus:6;
-  DWORD             Mode:2;
-  SCSI3Addr_struct  Target[2]; //2 level target device addr
-} PhysDevAddr_struct;
-  
-typedef struct _LogDevAddr_struct {
-  DWORD            VolId:30;
-  DWORD            Mode:2;
-  BYTE             reserved[4];
-} LogDevAddr_struct;
-
-typedef union _LUNAddr_struct {
-  BYTE               LunAddrBytes[8];
-  SCSI3Addr_struct   SCSI3Lun[4];
-  PhysDevAddr_struct PhysDev;
-  LogDevAddr_struct  LogDev;
-} LUNAddr_struct;
-
-typedef struct _RequestBlock_struct {
-  BYTE   CDBLen;
-  struct {
-    BYTE Type:3;
-    BYTE Attribute:3;
-    BYTE Direction:2;
-  } Type;
-  HWORD  Timeout;
-  BYTE   CDB[16];
-} RequestBlock_struct;
-
-typedef union _MoreErrInfo_struct{
-  struct {
-    BYTE  Reserved[3];
-    BYTE  Type;
-    DWORD ErrorInfo;
-  }Common_Info;
-  struct{
-    BYTE  Reserved[2];
-    BYTE  offense_size;//size of offending entry
-    BYTE  offense_num; //byte # of offense 0-base
-    DWORD offense_value;
-  }Invalid_Cmd;
-}MoreErrInfo_struct;
-typedef struct _ErrorInfo_struct {
-  BYTE               ScsiStatus;
-  BYTE               SenseLen;
-  HWORD              CommandStatus;
-  DWORD              ResidualCnt;
-  MoreErrInfo_struct MoreErrInfo;
-  BYTE               SenseInfo[SENSEINFOBYTES];
-} ErrorInfo_struct;
-
-#pragma pack()
-#endif /* CCISS_CMD_H */ 
-
 typedef struct _IOCTL_Command_struct {
   LUNAddr_struct	   LUN_info;
   RequestBlock_struct      Request;
diff --git a/include/linux/i2o.h b/include/linux/i2o.h
index 4c4e57d..87018dc 100644
--- a/include/linux/i2o.h
+++ b/include/linux/i2o.h
@@ -385,7 +385,7 @@
 /* defines for max_sectors and max_phys_segments */
 #define I2O_MAX_SECTORS			1024
 #define I2O_MAX_SECTORS_LIMITED		128
-#define I2O_MAX_PHYS_SEGMENTS		MAX_PHYS_SEGMENTS
+#define I2O_MAX_PHYS_SEGMENTS		BLK_MAX_SEGMENTS
 
 /*
  *	Message structures
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 78ef023..1195a80 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -49,8 +49,8 @@
 	/*
 	 * For request batching
 	 */
-	unsigned long last_waited; /* Time last woken after wait for request */
 	int nr_batch_requests;     /* Number of requests left in the batch */
+	unsigned long last_waited; /* Time last woken after wait for request */
 
 	struct radix_tree_root radix_root;
 	struct hlist_head cic_list;
diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h
index 76e5053..721301b 100644
--- a/include/linux/pktcdvd.h
+++ b/include/linux/pktcdvd.h
@@ -163,10 +163,8 @@
 	atomic_t		attention;	/* Set to non-zero when queue processing is needed */
 	int			writing;	/* Non-zero when writing, zero when reading */
 	spinlock_t		lock;		/* Protecting read/write queue manipulations */
-	struct bio		*read_queue;
-	struct bio		*read_queue_tail;
-	struct bio		*write_queue;
-	struct bio		*write_queue_tail;
+	struct bio_list		read_queue;
+	struct bio_list		write_queue;
 	sector_t		last_write;	/* The sector where the last write ended */
 	int			successive_reads;
 };
@@ -206,8 +204,8 @@
 	spinlock_t		lock;		/* Lock protecting state transitions and */
 						/* orig_bios list */
 
-	struct bio		*orig_bios;	/* Original bios passed to pkt_make_request */
-	struct bio		*orig_bios_tail;/* that will be handled by this packet */
+	struct bio_list		orig_bios;	/* Original bios passed to pkt_make_request */
+						/* that will be handled by this packet */
 	int			write_size;	/* Total size of all bios in the orig_bios */
 						/* list, measured in number of frames */
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0eef87b5..4b1753f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -97,7 +97,7 @@
 struct exec_domain;
 struct futex_pi_state;
 struct robust_list_head;
-struct bio;
+struct bio_list;
 struct fs_struct;
 struct bts_context;
 struct perf_event_context;
@@ -1454,7 +1454,7 @@
 	void *journal_info;
 
 /* stacked block device info */
-	struct bio *bio_list, **bio_tail;
+	struct bio_list *bio_list;
 
 /* VM state */
 	struct reclaim_state *reclaim_state;
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index d9d6206..07f945a9 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -540,9 +540,10 @@
 	if (ret)
 		return ret;
 
-	if (copy_to_user(arg, &buts, sizeof(buts)))
+	if (copy_to_user(arg, &buts, sizeof(buts))) {
+		blk_trace_remove(q);
 		return -EFAULT;
-
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(blk_trace_setup);