Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into avr32-arch

12 files changed, 312 insertions, 183 deletions

diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 8eba4e4..f7dae57 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -302,7 +302,7 @@ static void bio_end_empty_barrier(struct bio *bio, int err)
  * Description:
  *    Issue a flush for the block device in question. Caller can supply
  *    room for storing the error offset in case of a flush error, if they
- *    wish to.  Caller must run wait_for_completion() on its own.
+ *    wish to.
  */
 int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
 {
diff --git a/block/blk-core.c b/block/blk-core.c
index a824e49..996ed90 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -64,11 +64,12 @@ static struct workqueue_struct *kblockd_workqueue;
 
 static void drive_stat_acct(struct request *rq, int new_io)
 {
+	struct gendisk *disk = rq->rq_disk;
 	struct hd_struct *part;
 	int rw = rq_data_dir(rq);
 	int cpu;
 
-	if (!blk_fs_request(rq) || !rq->rq_disk)
+	if (!blk_fs_request(rq) || !disk || !blk_do_io_stat(disk->queue))
 		return;
 
 	cpu = part_stat_lock();
@@ -599,17 +600,13 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unplug_fn		= generic_unplug_device;
-	q->queue_flags		= (1 << QUEUE_FLAG_CLUSTER |
-				   1 << QUEUE_FLAG_STACKABLE);
+	q->queue_flags		= QUEUE_FLAG_DEFAULT;
 	q->queue_lock		= lock;
 
-	blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK);
-
+	/*
+	 * This also sets hw/phys segments, boundary and size
+	 */
 	blk_queue_make_request(q, __make_request);
-	blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE);
-
-	blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
-	blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
 
 	q->sg_reserved_size = INT_MAX;
 
@@ -735,7 +732,6 @@ static void freed_request(struct request_queue *q, int rw, int priv)
 		__freed_request(q, rw ^ 1);
 }
 
-#define blkdev_free_rq(list) list_entry((list)->next, struct request, queuelist)
 /*
  * Get a free request, queue_lock must be held.
  * Returns NULL on failure, with queue_lock held.
@@ -1066,6 +1062,9 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 
 	elv_completed_request(q, req);
 
+	/* this is a bio leak */
+	WARN_ON(req->bio != NULL);
+
 	/*
 	 * Request may not have originated from ll_rw_blk. if not,
 	 * it didn't come out of our reserved rq pools
@@ -1125,6 +1124,8 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 
 	if (bio_sync(bio))
 		req->cmd_flags |= REQ_RW_SYNC;
+	if (bio_unplug(bio))
+		req->cmd_flags |= REQ_UNPLUG;
 	if (bio_rw_meta(bio))
 		req->cmd_flags |= REQ_RW_META;
 
@@ -1141,6 +1142,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	int el_ret, nr_sectors;
 	const unsigned short prio = bio_prio(bio);
 	const int sync = bio_sync(bio);
+	const int unplug = bio_unplug(bio);
 	int rw_flags;
 
 	nr_sectors = bio_sectors(bio);
@@ -1244,7 +1246,7 @@ get_rq:
 		blk_plug_device(q);
 	add_request(q, req);
 out:
-	if (sync || blk_queue_nonrot(q))
+	if (unplug || blk_queue_nonrot(q))
 		__generic_unplug_device(q);
 	spin_unlock_irq(q->queue_lock);
 	return 0;
@@ -1448,6 +1450,11 @@ static inline void __generic_make_request(struct bio *bio)
 			err = -EOPNOTSUPP;
 			goto end_io;
 		}
+		if (bio_barrier(bio) && bio_has_data(bio) &&
+		    (q->next_ordered == QUEUE_ORDERED_NONE)) {
+			err = -EOPNOTSUPP;
+			goto end_io;
+		}
 
 		ret = q->make_request_fn(q, bio);
 	} while (ret);
@@ -1655,6 +1662,55 @@ void blkdev_dequeue_request(struct request *req)
 }
 EXPORT_SYMBOL(blkdev_dequeue_request);
 
+static void blk_account_io_completion(struct request *req, unsigned int bytes)
+{
+	struct gendisk *disk = req->rq_disk;
+
+	if (!disk || !blk_do_io_stat(disk->queue))
+		return;
+
+	if (blk_fs_request(req)) {
+		const int rw = rq_data_dir(req);
+		struct hd_struct *part;
+		int cpu;
+
+		cpu = part_stat_lock();
+		part = disk_map_sector_rcu(req->rq_disk, req->sector);
+		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
+		part_stat_unlock();
+	}
+}
+
+static void blk_account_io_done(struct request *req)
+{
+	struct gendisk *disk = req->rq_disk;
+
+	if (!disk || !blk_do_io_stat(disk->queue))
+		return;
+
+	/*
+	 * Account IO completion.  bar_rq isn't accounted as a normal
+	 * IO on queueing nor completion.  Accounting the containing
+	 * request is enough.
+	 */
+	if (blk_fs_request(req) && req != &req->q->bar_rq) {
+		unsigned long duration = jiffies - req->start_time;
+		const int rw = rq_data_dir(req);
+		struct hd_struct *part;
+		int cpu;
+
+		cpu = part_stat_lock();
+		part = disk_map_sector_rcu(disk, req->sector);
+
+		part_stat_inc(cpu, part, ios[rw]);
+		part_stat_add(cpu, part, ticks[rw], duration);
+		part_round_stats(cpu, part);
+		part_dec_in_flight(part);
+
+		part_stat_unlock();
+	}
+}
+
 /**
  * __end_that_request_first - end I/O on a request
  * @req:      the request being processed
@@ -1690,16 +1746,7 @@ static int __end_that_request_first(struct request *req, int error,
 				(unsigned long long)req->sector);
 	}
 
-	if (blk_fs_request(req) && req->rq_disk) {
-		const int rw = rq_data_dir(req);
-		struct hd_struct *part;
-		int cpu;
-
-		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, req->sector);
-		part_stat_add(cpu, part, sectors[rw], nr_bytes >> 9);
-		part_stat_unlock();
-	}
+	blk_account_io_completion(req, nr_bytes);
 
 	total_bytes = bio_nbytes = 0;
 	while ((bio = req->bio) != NULL) {
@@ -1779,8 +1826,6 @@ static int __end_that_request_first(struct request *req, int error,
  */
 static void end_that_request_last(struct request *req, int error)
 {
-	struct gendisk *disk = req->rq_disk;
-
 	if (blk_rq_tagged(req))
 		blk_queue_end_tag(req->q, req);
 
@@ -1792,27 +1837,7 @@ static void end_that_request_last(struct request *req, int error)
 
 	blk_delete_timer(req);
 
-	/*
-	 * Account IO completion.  bar_rq isn't accounted as a normal
-	 * IO on queueing nor completion.  Accounting the containing
-	 * request is enough.
-	 */
-	if (disk && blk_fs_request(req) && req != &req->q->bar_rq) {
-		unsigned long duration = jiffies - req->start_time;
-		const int rw = rq_data_dir(req);
-		struct hd_struct *part;
-		int cpu;
-
-		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(disk, req->sector);
-
-		part_stat_inc(cpu, part, ios[rw]);
-		part_stat_add(cpu, part, ticks[rw], duration);
-		part_round_stats(cpu, part);
-		part_dec_in_flight(part);
-
-		part_stat_unlock();
-	}
+	blk_account_io_done(req);
 
 	if (req->end_io)
 		req->end_io(req, error);
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 61a8e2f..91fa8e0 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -309,24 +309,24 @@ static struct kobj_type integrity_ktype = {
 /**
  * blk_integrity_register - Register a gendisk as being integrity-capable
  * @disk:	struct gendisk pointer to make integrity-aware
- * @template:	integrity profile
+ * @template:	optional integrity profile to register
  *
  * Description: When a device needs to advertise itself as being able
  * to send/receive integrity metadata it must use this function to
  * register the capability with the block layer.  The template is a
  * blk_integrity struct with values appropriate for the underlying
- * hardware.  See Documentation/block/data-integrity.txt.
+ * hardware.  If template is NULL the new profile is allocated but
+ * not filled out. See Documentation/block/data-integrity.txt.
  */
 int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 {
 	struct blk_integrity *bi;
 
 	BUG_ON(disk == NULL);
-	BUG_ON(template == NULL);
 
 	if (disk->integrity == NULL) {
 		bi = kmem_cache_alloc(integrity_cachep,
-						GFP_KERNEL | __GFP_ZERO);
+				      GFP_KERNEL | __GFP_ZERO);
 		if (!bi)
 			return -1;
 
@@ -346,13 +346,16 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 		bi = disk->integrity;
 
 	/* Use the provided profile as template */
-	bi->name = template->name;
-	bi->generate_fn = template->generate_fn;
-	bi->verify_fn = template->verify_fn;
-	bi->tuple_size = template->tuple_size;
-	bi->set_tag_fn = template->set_tag_fn;
-	bi->get_tag_fn = template->get_tag_fn;
-	bi->tag_size = template->tag_size;
+	if (template != NULL) {
+		bi->name = template->name;
+		bi->generate_fn = template->generate_fn;
+		bi->verify_fn = template->verify_fn;
+		bi->tuple_size = template->tuple_size;
+		bi->set_tag_fn = template->set_tag_fn;
+		bi->get_tag_fn = template->get_tag_fn;
+		bi->tag_size = template->tag_size;
+	} else
+		bi->name = "unsupported";
 
 	return 0;
 }
diff --git a/block/blk-merge.c b/block/blk-merge.c
index b92f5b0..e39cb24 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -38,72 +38,77 @@ void blk_recalc_rq_sectors(struct request *rq, int nsect)
 	}
 }
 
-void blk_recalc_rq_segments(struct request *rq)
+static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
+					     struct bio *bio)
 {
-	int nr_phys_segs;
 	unsigned int phys_size;
 	struct bio_vec *bv, *bvprv = NULL;
-	int seg_size;
-	int cluster;
-	struct req_iterator iter;
-	int high, highprv = 1;
-	struct request_queue *q = rq->q;
+	int cluster, i, high, highprv = 1;
+	unsigned int seg_size, nr_phys_segs;
+	struct bio *fbio, *bbio;
 
-	if (!rq->bio)
-		return;
+	if (!bio)
+		return 0;
 
+	fbio = bio;
 	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
 	seg_size = 0;
 	phys_size = nr_phys_segs = 0;
-	rq_for_each_segment(bv, rq, iter) {
-		/*
-		 * the trick here is making sure that a high page is never
-		 * considered part of another segment, since that might
-		 * change with the bounce page.
-		 */
-		high = page_to_pfn(bv->bv_page) > q->bounce_pfn;
-		if (high || highprv)
-			goto new_segment;
-		if (cluster) {
-			if (seg_size + bv->bv_len > q->max_segment_size)
-				goto new_segment;
-			if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
-				goto new_segment;
-			if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv))
+	for_each_bio(bio) {
+		bio_for_each_segment(bv, bio, i) {
+			/*
+			 * the trick here is making sure that a high page is
+			 * never considered part of another segment, since that
+			 * might change with the bounce page.
+			 */
+			high = page_to_pfn(bv->bv_page) > q->bounce_pfn;
+			if (high || highprv)
 				goto new_segment;
+			if (cluster) {
+				if (seg_size + bv->bv_len > q->max_segment_size)
+					goto new_segment;
+				if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
+					goto new_segment;
+				if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv))
+					goto new_segment;
+
+				seg_size += bv->bv_len;
+				bvprv = bv;
+				continue;
+			}
+new_segment:
+			if (nr_phys_segs == 1 && seg_size >
+			    fbio->bi_seg_front_size)
+				fbio->bi_seg_front_size = seg_size;
 
-			seg_size += bv->bv_len;
+			nr_phys_segs++;
 			bvprv = bv;
-			continue;
+			seg_size = bv->bv_len;
+			highprv = high;
 		}
-new_segment:
-		if (nr_phys_segs == 1 && seg_size > rq->bio->bi_seg_front_size)
-			rq->bio->bi_seg_front_size = seg_size;
-
-		nr_phys_segs++;
-		bvprv = bv;
-		seg_size = bv->bv_len;
-		highprv = high;
+		bbio = bio;
 	}
 
-	if (nr_phys_segs == 1 && seg_size > rq->bio->bi_seg_front_size)
-		rq->bio->bi_seg_front_size = seg_size;
-	if (seg_size > rq->biotail->bi_seg_back_size)
-		rq->biotail->bi_seg_back_size = seg_size;
+	if (nr_phys_segs == 1 && seg_size > fbio->bi_seg_front_size)
+		fbio->bi_seg_front_size = seg_size;
+	if (seg_size > bbio->bi_seg_back_size)
+		bbio->bi_seg_back_size = seg_size;
+
+	return nr_phys_segs;
+}
 
-	rq->nr_phys_segments = nr_phys_segs;
+void blk_recalc_rq_segments(struct request *rq)
+{
+	rq->nr_phys_segments = __blk_recalc_rq_segments(rq->q, rq->bio);
 }
 
 void blk_recount_segments(struct request_queue *q, struct bio *bio)
 {
-	struct request rq;
 	struct bio *nxt = bio->bi_next;
-	rq.q = q;
-	rq.bio = rq.biotail = bio;
+
 	bio->bi_next = NULL;
-	blk_recalc_rq_segments(&rq);
+	bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio);
 	bio->bi_next = nxt;
-	bio->bi_phys_segments = rq.nr_phys_segments;
 	bio->bi_flags |= (1 << BIO_SEG_VALID);
 }
 EXPORT_SYMBOL(blk_recount_segments);
@@ -398,6 +403,8 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (blk_rq_cpu_valid(next))
 		req->cpu = next->cpu;
 
+	/* owner-ship of bio passed from next to req */
+	next->bio = NULL;
 	__blk_put_request(q, next);
 	return 1;
 }
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index a29cb78..e29ddfc 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -130,6 +130,27 @@ static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
 	return queue_var_show(max_hw_sectors_kb, (page));
 }
 
+static ssize_t queue_nonrot_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(!blk_queue_nonrot(q), page);
+}
+
+static ssize_t queue_nonrot_store(struct request_queue *q, const char *page,
+				  size_t count)
+{
+	unsigned long nm;
+	ssize_t ret = queue_var_store(&nm, page, count);
+
+	spin_lock_irq(q->queue_lock);
+	if (nm)
+		queue_flag_clear(QUEUE_FLAG_NONROT, q);
+	else
+		queue_flag_set(QUEUE_FLAG_NONROT, q);
+	spin_unlock_irq(q->queue_lock);
+
+	return ret;
+}
+
 static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(blk_queue_nomerges(q), page);
@@ -146,8 +167,8 @@ static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
 		queue_flag_set(QUEUE_FLAG_NOMERGES, q);
 	else
 		queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
-
 	spin_unlock_irq(q->queue_lock);
+
 	return ret;
 }
 
@@ -176,6 +197,27 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 	return ret;
 }
 
+static ssize_t queue_iostats_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(blk_queue_io_stat(q), page);
+}
+
+static ssize_t queue_iostats_store(struct request_queue *q, const char *page,
+				   size_t count)
+{
+	unsigned long stats;
+	ssize_t ret = queue_var_store(&stats, page, count);
+
+	spin_lock_irq(q->queue_lock);
+	if (stats)
+		queue_flag_set(QUEUE_FLAG_IO_STAT, q);
+	else
+		queue_flag_clear(QUEUE_FLAG_IO_STAT, q);
+	spin_unlock_irq(q->queue_lock);
+
+	return ret;
+}
+
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -210,6 +252,12 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = {
 	.show = queue_hw_sector_size_show,
 };
 
+static struct queue_sysfs_entry queue_nonrot_entry = {
+	.attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_nonrot_show,
+	.store = queue_nonrot_store,
+};
+
 static struct queue_sysfs_entry queue_nomerges_entry = {
 	.attr = {.name = "nomerges", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_nomerges_show,
@@ -222,6 +270,12 @@ static struct queue_sysfs_entry queue_rq_affinity_entry = {
 	.store = queue_rq_affinity_store,
 };
 
+static struct queue_sysfs_entry queue_iostats_entry = {
+	.attr = {.name = "iostats", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_iostats_show,
+	.store = queue_iostats_store,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -229,8 +283,10 @@ static struct attribute *default_attrs[] = {
 	&queue_max_sectors_entry.attr,
 	&queue_iosched_entry.attr,
 	&queue_hw_sector_size_entry.attr,
+	&queue_nonrot_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
+	&queue_iostats_entry.attr,
 	NULL,
 };
 
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index a095353..bbbdc4b 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -209,12 +209,19 @@ void blk_abort_queue(struct request_queue *q)
 {
 	unsigned long flags;
 	struct request *rq, *tmp;
+	LIST_HEAD(list);
 
 	spin_lock_irqsave(q->queue_lock, flags);
 
 	elv_abort_queue(q);
 
-	list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list)
+	/*
+	 * Splice entries to local list, to avoid deadlocking if entries
+	 * get readded to the timeout list by error handling
+	 */
+	list_splice_init(&q->timeout_list, &list);
+
+	list_for_each_entry_safe(rq, tmp, &list, timeout_list)
 		blk_abort_request(rq);
 
 	spin_unlock_irqrestore(q->queue_lock, flags);
diff --git a/block/blk.h b/block/blk.h
index 6e1ed40..0dce92c 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -108,4 +108,12 @@ static inline int blk_cpu_to_group(int cpu)
 #endif
 }
 
+static inline int blk_do_io_stat(struct request_queue *q)
+{
+	if (q)
+		return blk_queue_io_stat(q);
+
+	return 0;
+}
+
 #endif
diff --git a/block/blktrace.c b/block/blktrace.c
index b0a2cae..7cf9d1f 100644
--- a/block/blktrace.c
+++ b/block/blktrace.c
@@ -142,7 +142,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 
 	what |= ddir_act[rw & WRITE];
 	what |= MASK_TC_BIT(rw, BARRIER);
-	what |= MASK_TC_BIT(rw, SYNC);
+	what |= MASK_TC_BIT(rw, SYNCIO);
 	what |= MASK_TC_BIT(rw, AHEAD);
 	what |= MASK_TC_BIT(rw, META);
 	what |= MASK_TC_BIT(rw, DISCARD);
@@ -187,59 +187,12 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 
 static struct dentry *blk_tree_root;
 static DEFINE_MUTEX(blk_tree_mutex);
-static unsigned int root_users;
-
-static inline void blk_remove_root(void)
-{
-	if (blk_tree_root) {
-		debugfs_remove(blk_tree_root);
-		blk_tree_root = NULL;
-	}
-}
-
-static void blk_remove_tree(struct dentry *dir)
-{
-	mutex_lock(&blk_tree_mutex);
-	debugfs_remove(dir);
-	if (--root_users == 0)
-		blk_remove_root();
-	mutex_unlock(&blk_tree_mutex);
-}
-
-static struct dentry *blk_create_tree(const char *blk_name)
-{
-	struct dentry *dir = NULL;
-	int created = 0;
-
-	mutex_lock(&blk_tree_mutex);
-
-	if (!blk_tree_root) {
-		blk_tree_root = debugfs_create_dir("block", NULL);
-		if (!blk_tree_root)
-			goto err;
-		created = 1;
-	}
-
-	dir = debugfs_create_dir(blk_name, blk_tree_root);
-	if (dir)
-		root_users++;
-	else {
-		/* Delete root only if we created it */
-		if (created)
-			blk_remove_root();
-	}
-
-err:
-	mutex_unlock(&blk_tree_mutex);
-	return dir;
-}
 
 static void blk_trace_cleanup(struct blk_trace *bt)
 {
-	relay_close(bt->rchan);
 	debugfs_remove(bt->msg_file);
 	debugfs_remove(bt->dropped_file);
-	blk_remove_tree(bt->dir);
+	relay_close(bt->rchan);
 	free_percpu(bt->sequence);
 	free_percpu(bt->msg_data);
 	kfree(bt);
@@ -346,7 +299,18 @@ static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
 
 static int blk_remove_buf_file_callback(struct dentry *dentry)
 {
+	struct dentry *parent = dentry->d_parent;
 	debugfs_remove(dentry);
+
+	/*
+	* this will fail for all but the last file, but that is ok. what we
+	* care about is the top level buts->name directory going away, when
+	* the last trace file is gone. Then we don't have to rmdir() that
+	* manually on trace stop, so it nicely solves the issue with
+	* force killing of running traces.
+	*/
+
+	debugfs_remove(parent);
 	return 0;
 }
 
@@ -404,7 +368,15 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 		goto err;
 
 	ret = -ENOENT;
-	dir = blk_create_tree(buts->name);
+
+	if (!blk_tree_root) {
+		blk_tree_root = debugfs_create_dir("block", NULL);
+		if (!blk_tree_root)
+			return -ENOMEM;
+	}
+
+	dir = debugfs_create_dir(buts->name, blk_tree_root);
+
 	if (!dir)
 		goto err;
 
@@ -458,8 +430,6 @@ probe_err:
 	atomic_dec(&blk_probes_ref);
 	mutex_unlock(&blk_probe_mutex);
 err:
-	if (dir)
-		blk_remove_tree(dir);
 	if (bt) {
 		if (bt->msg_file)
 			debugfs_remove(bt->msg_file);
diff --git a/block/bsg.c b/block/bsg.c
index d414bb5..206060e 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -218,9 +218,6 @@ bsg_validate_sgv4_hdr(struct request_queue *q, struct sg_io_v4 *hdr, int *rw)
 
 	if (hdr->guard != 'Q')
 		return -EINVAL;
-	if (hdr->dout_xfer_len > (q->max_sectors << 9) ||
-	    hdr->din_xfer_len > (q->max_sectors << 9))
-		return -EIO;
 
 	switch (hdr->protocol) {
 	case BSG_PROTOCOL_SCSI:
@@ -244,7 +241,8 @@ bsg_validate_sgv4_hdr(struct request_queue *q, struct sg_io_v4 *hdr, int *rw)
  * map sg_io_v4 to a request.
  */
 static struct request *
-bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm)
+bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
+	    u8 *sense)
 {
 	struct request_queue *q = bd->queue;
 	struct request *rq, *next_rq = NULL;
@@ -306,6 +304,10 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm)
 		if (ret)
 			goto out;
 	}
+
+	rq->sense = sense;
+	rq->sense_len = 0;
+
 	return rq;
 out:
 	if (rq->cmd != rq->__cmd)
@@ -348,8 +350,7 @@ static void bsg_rq_end_io(struct request *rq, int uptodate)
 static void bsg_add_command(struct bsg_device *bd, struct request_queue *q,
 			    struct bsg_command *bc, struct request *rq)
 {
-	rq->sense = bc->sense;
-	rq->sense_len = 0;
+	int at_head = (0 == (bc->hdr.flags & BSG_FLAG_Q_AT_TAIL));
 
 	/*
 	 * add bc command to busy queue and submit rq for io
@@ -366,7 +367,7 @@ static void bsg_add_command(struct bsg_device *bd, struct request_queue *q,
 	dprintk("%s: queueing rq %p, bc %p\n", bd->name, rq, bc);
 
 	rq->end_io_data = bc;
-	blk_execute_rq_nowait(q, NULL, rq, 1, bsg_rq_end_io);
+	blk_execute_rq_nowait(q, NULL, rq, at_head, bsg_rq_end_io);
 }
 
 static struct bsg_command *bsg_next_done_cmd(struct bsg_device *bd)
@@ -419,7 +420,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 {
 	int ret = 0;
 
-	dprintk("rq %p bio %p %u\n", rq, bio, rq->errors);
+	dprintk("rq %p bio %p 0x%x\n", rq, bio, rq->errors);
 	/*
 	 * fill in all the output members
 	 */
@@ -635,7 +636,7 @@ static int __bsg_write(struct bsg_device *bd, const char __user *buf,
 		/*
 		 * get a request, fill in the blanks, and add to request queue
 		 */
-		rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm);
+		rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm, bc->sense);
 		if (IS_ERR(rq)) {
 			ret = PTR_ERR(rq);
 			rq = NULL;
@@ -922,18 +923,22 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		struct request *rq;
 		struct bio *bio, *bidi_bio = NULL;
 		struct sg_io_v4 hdr;
+		int at_head;
+		u8 sense[SCSI_SENSE_BUFFERSIZE];
 
 		if (copy_from_user(&hdr, uarg, sizeof(hdr)))
 			return -EFAULT;
 
-		rq = bsg_map_hdr(bd, &hdr, file->f_mode & FMODE_WRITE);
+		rq = bsg_map_hdr(bd, &hdr, file->f_mode & FMODE_WRITE, sense);
 		if (IS_ERR(rq))
 			return PTR_ERR(rq);
 
 		bio = rq->bio;
 		if (rq->next_rq)
 			bidi_bio = rq->next_rq->bio;
-		blk_execute_rq(bd->queue, NULL, rq, 0);
+
+		at_head = (0 == (hdr.flags & BSG_FLAG_Q_AT_TAIL));
+		blk_execute_rq(bd->queue, NULL, rq, at_head);
 		ret = blk_complete_sgv4_hdr_rq(rq, &hdr, bio, bidi_bio);
 
 		if (copy_to_user(uarg, &hdr, sizeof(hdr)))
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index e8525fa..664ebfd 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -84,6 +84,11 @@ struct cfq_data {
 	 */
 	struct cfq_rb_root service_tree;
 	unsigned int busy_queues;
+	/*
+	 * Used to track any pending rt requests so we can pre-empt current
+	 * non-RT cfqq in service when this value is non-zero.
+	 */
+	unsigned int busy_rt_queues;
 
 	int rq_in_driver;
 	int sync_flight;
@@ -562,6 +567,8 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	cfq_mark_cfqq_on_rr(cfqq);
 	cfqd->busy_queues++;
+	if (cfq_class_rt(cfqq))
+		cfqd->busy_rt_queues++;
 
 	cfq_resort_rr_list(cfqd, cfqq);
 }
@@ -581,6 +588,8 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 
 	BUG_ON(!cfqd->busy_queues);
 	cfqd->busy_queues--;
+	if (cfq_class_rt(cfqq))
+		cfqd->busy_rt_queues--;
 }
 
 /*
@@ -1005,6 +1014,20 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 		goto expire;
 
 	/*
+	 * If we have a RT cfqq waiting, then we pre-empt the current non-rt
+	 * cfqq.
+	 */
+	if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues) {
+		/*
+		 * We simulate this as cfqq timed out so that it gets to bank
+		 * the remaining of its time slice.
+		 */
+		cfq_log_cfqq(cfqd, cfqq, "preempt");
+		cfq_slice_expired(cfqd, 1);
+		goto new_queue;
+	}
+
+	/*
 	 * The active queue has requests and isn't expired, allow it to
 	 * dispatch.
 	 */
@@ -1067,6 +1090,13 @@ __cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		if (RB_EMPTY_ROOT(&cfqq->sort_list))
 			break;
 
+		/*
+		 * If there is a non-empty RT cfqq waiting for current
+		 * cfqq's timeslice to complete, pre-empt this cfqq
+		 */
+		if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues)
+			break;
+
 	} while (dispatched < max_dispatch);
 
 	/*
@@ -1801,6 +1831,12 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	if (rq_is_meta(rq) && !cfqq->meta_pending)
 		return 1;
 
+	/*
+	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
+	 */
+	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
+		return 1;
+
 	if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
 		return 0;
 
@@ -1870,7 +1906,8 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		/*
 		 * not the active queue - expire current slice if it is
 		 * idle and has expired it's mean thinktime or this new queue
-		 * has some old slice time left and is of higher priority
+		 * has some old slice time left and is of higher priority or
+		 * this new queue is RT and the current one is BE
 		 */
 		cfq_preempt_queue(cfqd, cfqq);
 		cfq_mark_cfqq_must_dispatch(cfqq);
diff --git a/block/genhd.c b/block/genhd.c
index 397960c..a9ec910 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -256,6 +256,22 @@ void blkdev_show(struct seq_file *seqf, off_t offset)
 }
 #endif /* CONFIG_PROC_FS */
 
+/**
+ * register_blkdev - register a new block device
+ *
+ * @major: the requested major device number [1..255]. If @major=0, try to
+ *         allocate any unused major number.
+ * @name: the name of the new block device as a zero terminated string
+ *
+ * The @name must be unique within the system.
+ *
+ * The return value depends on the @major input parameter.
+ *  - if a major device number was requested in range [1..255] then the
+ *    function returns zero on success, or a negative error code
+ *  - if any unused major number was requested with @major=0 parameter
+ *    then the return value is the allocated major number in range
+ *    [1..255] or a negative error code otherwise
+ */
 int register_blkdev(unsigned int major, const char *name)
 {
 	struct blk_major_name **n, *p;
@@ -1087,6 +1103,14 @@ dev_t blk_lookup_devt(const char *name, int partno)
 		if (strcmp(dev_name(dev), name))
 			continue;
 
+		if (partno < disk->minors) {
+			/* We need to return the right devno, even
+			 * if the partition doesn't exist yet.
+			 */
+			devt = MKDEV(MAJOR(dev->devt),
+				     MINOR(dev->devt) + partno);
+			break;
+		}
 		part = disk_get_part(disk, partno);
 		if (part) {
 			devt = part_devt(part);
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index ee9c67d..626ee27 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -214,21 +214,10 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 	return 0;
 }
 
-/*
- * unmap a request that was previously mapped to this sg_io_hdr. handles
- * both sg and non-sg sg_io_hdr.
- */
-static int blk_unmap_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr)
-{
-	blk_rq_unmap_user(rq->bio);
-	blk_put_request(rq);
-	return 0;
-}
-
 static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 				 struct bio *bio)
 {
-	int r, ret = 0;
+	int ret = 0;
 
 	/*
 	 * fill in all the output members
@@ -253,12 +242,10 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 			ret = -EFAULT;
 	}
 
-	rq->bio = bio;
-	r = blk_unmap_sghdr_rq(rq, hdr);
-	if (ret)
-		r = ret;
+	blk_rq_unmap_user(bio);
+	blk_put_request(rq);
 
-	return r;
+	return ret;
 }
 
 static int sg_io(struct request_queue *q, struct gendisk *bd_disk,