Merge branch 'for-2.6.38/core' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.38/core' of git://git.kernel.dk/linux-2.6-block: (43 commits)
  block: ensure that completion error gets properly traced
  blktrace: add missing probe argument to block_bio_complete
  block cfq: don't use atomic_t for cfq_group
  block cfq: don't use atomic_t for cfq_queue
  block: trace event block fix unassigned field
  block: add internal hd part table references
  block: fix accounting bug on cross partition merges
  kref: add kref_test_and_get
  bio-integrity: mark kintegrityd_wq highpri and CPU intensive
  block: make kblockd_workqueue smarter
  Revert "sd: implement sd_check_events()"
  block: Clean up exit_io_context() source code.
  Fix compile warnings due to missing removal of a 'ret' variable
  fs/block: type signature of major_to_index(int) to major_to_index(unsigned)
  block: convert !IS_ERR(p) && p to !IS_ERR_NOR_NULL(p)
  cfq-iosched: don't check cfqg in choose_service_tree()
  fs/splice: Pull buf->ops->confirm() from splice_from_pipe actors
  cdrom: export cdrom_check_events()
  sd: implement sd_check_events()
  sr: implement sr_check_events()
  ...

53 files changed, 1323 insertions, 1085 deletions

diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt
index d6da611f8f63..4ed7b5ceeed2 100644
--- a/Documentation/cgroups/blkio-controller.txt
+++ b/Documentation/cgroups/blkio-controller.txt
@@ -89,6 +89,33 @@ Throttling/Upper Limit policy
 
  Limits for writes can be put using blkio.write_bps_device file.
 
+Hierarchical Cgroups
+====================
+- Currently none of the IO control policy supports hierarhical groups. But
+  cgroup interface does allow creation of hierarhical cgroups and internally
+  IO policies treat them as flat hierarchy.
+
+  So this patch will allow creation of cgroup hierarhcy but at the backend
+  everything will be treated as flat. So if somebody created a hierarchy like
+  as follows.
+
+			root
+			/  \
+		     test1 test2
+			|
+		     test3
+
+  CFQ and throttling will practically treat all groups at same level.
+
+				pivot
+			     /  |   \  \
+			root  test1 test2  test3
+
+  Down the line we can implement hierarchical accounting/control support
+  and also introduce a new cgroup file "use_hierarchy" which will control
+  whether cgroup hierarchy is viewed as flat or hierarchical by the policy..
+  This is how memory controller also has implemented the things.
+
 Various user visible config options
 ===================================
 CONFIG_BLK_CGROUP
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index b1febd0f6d2a..455768a3eb9e 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1452,10 +1452,6 @@ blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 		goto done;
 	}
 
-	/* Currently we do not support hierarchy deeper than two level (0,1) */
-	if (parent != cgroup->top_cgroup)
-		return ERR_PTR(-EPERM);
-
 	blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
 	if (!blkcg)
 		return ERR_PTR(-ENOMEM);
diff --git a/block/blk-core.c b/block/blk-core.c
index 4ce953f1b390..2f4002f79a24 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -33,7 +33,7 @@
 
 #include "blk.h"
 
-EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
 
@@ -64,13 +64,27 @@ static void drive_stat_acct(struct request *rq, int new_io)
 		return;
 
 	cpu = part_stat_lock();
-	part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
 
-	if (!new_io)
+	if (!new_io) {
+		part = rq->part;
 		part_stat_inc(cpu, part, merges[rw]);
-	else {
+	} else {
+		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
+		if (!hd_struct_try_get(part)) {
+			/*
+			 * The partition is already being removed,
+			 * the request will be accounted on the disk only
+			 *
+			 * We take a reference on disk->part0 although that
+			 * partition will never be deleted, so we can treat
+			 * it as any other partition.
+			 */
+			part = &rq->rq_disk->part0;
+			hd_struct_get(part);
+		}
 		part_round_stats(cpu, part);
 		part_inc_in_flight(part, rw);
+		rq->part = part;
 	}
 
 	part_stat_unlock();
@@ -128,6 +142,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->ref_count = 1;
 	rq->start_time = jiffies;
 	set_start_time_ns(rq);
+	rq->part = NULL;
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -1329,9 +1344,9 @@ static inline void blk_partition_remap(struct bio *bio)
 		bio->bi_sector += p->start_sect;
 		bio->bi_bdev = bdev->bd_contains;
 
-		trace_block_remap(bdev_get_queue(bio->bi_bdev), bio,
-				    bdev->bd_dev,
-				    bio->bi_sector - p->start_sect);
+		trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), bio,
+				      bdev->bd_dev,
+				      bio->bi_sector - p->start_sect);
 	}
 }
 
@@ -1500,7 +1515,7 @@ static inline void __generic_make_request(struct bio *bio)
 			goto end_io;
 
 		if (old_sector != -1)
-			trace_block_remap(q, bio, old_dev, old_sector);
+			trace_block_bio_remap(q, bio, old_dev, old_sector);
 
 		old_sector = bio->bi_sector;
 		old_dev = bio->bi_bdev->bd_dev;
@@ -1776,7 +1791,7 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+		part = req->part;
 		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
 		part_stat_unlock();
 	}
@@ -1796,13 +1811,14 @@ static void blk_account_io_done(struct request *req)
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+		part = req->part;
 
 		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, rw);
 
+		hd_struct_put(part);
 		part_stat_unlock();
 	}
 }
@@ -2606,7 +2622,9 @@ int __init blk_dev_init(void)
 	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
 			sizeof(((struct request *)0)->cmd_flags));
 
-	kblockd_workqueue = create_workqueue("kblockd");
+	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
+	kblockd_workqueue = alloc_workqueue("kblockd",
+					    WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
 	if (!kblockd_workqueue)
 		panic("Failed to create kblockd\n");
 
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 3c7a339fe381..b791022beef3 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -64,7 +64,7 @@ static void cfq_exit(struct io_context *ioc)
 	rcu_read_unlock();
 }
 
-/* Called by the exitting task */
+/* Called by the exiting task */
 void exit_io_context(struct task_struct *task)
 {
 	struct io_context *ioc;
@@ -74,10 +74,9 @@ void exit_io_context(struct task_struct *task)
 	task->io_context = NULL;
 	task_unlock(task);
 
-	if (atomic_dec_and_test(&ioc->nr_tasks)) {
+	if (atomic_dec_and_test(&ioc->nr_tasks))
 		cfq_exit(ioc);
 
-	}
 	put_io_context(ioc);
 }
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 74bc4a768f32..ea85e20d5e94 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -351,11 +351,12 @@ static void blk_account_io_merge(struct request *req)
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+		part = req->part;
 
 		part_round_stats(cpu, part);
 		part_dec_in_flight(part, rq_data_dir(req));
 
+		hd_struct_put(part);
 		part_stat_unlock();
 	}
 }
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 78ee4b1d4e85..8427697c5437 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -87,7 +87,6 @@ struct cfq_rb_root {
 	unsigned count;
 	unsigned total_weight;
 	u64 min_vdisktime;
-	struct rb_node *active;
 };
 #define CFQ_RB_ROOT	(struct cfq_rb_root) { .rb = RB_ROOT, .left = NULL, \
 			.count = 0, .min_vdisktime = 0, }
@@ -97,7 +96,7 @@ struct cfq_rb_root {
  */
 struct cfq_queue {
 	/* reference count */
-	atomic_t ref;
+	int ref;
 	/* various state flags, see below */
 	unsigned int flags;
 	/* parent cfq_data */
@@ -180,7 +179,6 @@ struct cfq_group {
 	/* group service_tree key */
 	u64 vdisktime;
 	unsigned int weight;
-	bool on_st;
 
 	/* number of cfqq currently on this group */
 	int nr_cfqq;
@@ -209,7 +207,7 @@ struct cfq_group {
 	struct blkio_group blkg;
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 	struct hlist_node cfqd_node;
-	atomic_t ref;
+	int ref;
 #endif
 	/* number of requests that are on the dispatch list or inside driver */
 	int dispatched;
@@ -563,11 +561,6 @@ static void update_min_vdisktime(struct cfq_rb_root *st)
 	u64 vdisktime = st->min_vdisktime;
 	struct cfq_group *cfqg;
 
-	if (st->active) {
-		cfqg = rb_entry_cfqg(st->active);
-		vdisktime = cfqg->vdisktime;
-	}
-
 	if (st->left) {
 		cfqg = rb_entry_cfqg(st->left);
 		vdisktime = min_vdisktime(vdisktime, cfqg->vdisktime);
@@ -646,11 +639,11 @@ cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 static inline bool cfq_slice_used(struct cfq_queue *cfqq)
 {
 	if (cfq_cfqq_slice_new(cfqq))
-		return 0;
+		return false;
 	if (time_before(jiffies, cfqq->slice_end))
-		return 0;
+		return false;
 
-	return 1;
+	return true;
 }
 
 /*
@@ -869,7 +862,7 @@ cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	struct rb_node *n;
 
 	cfqg->nr_cfqq++;
-	if (cfqg->on_st)
+	if (!RB_EMPTY_NODE(&cfqg->rb_node))
 		return;
 
 	/*
@@ -885,7 +878,6 @@ cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		cfqg->vdisktime = st->min_vdisktime;
 
 	__cfq_group_service_tree_add(st, cfqg);
-	cfqg->on_st = true;
 	st->total_weight += cfqg->weight;
 }
 
@@ -894,9 +886,6 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
 
-	if (st->active == &cfqg->rb_node)
-		st->active = NULL;
-
 	BUG_ON(cfqg->nr_cfqq < 1);
 	cfqg->nr_cfqq--;
 
@@ -905,7 +894,6 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		return;
 
 	cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
-	cfqg->on_st = false;
 	st->total_weight -= cfqg->weight;
 	if (!RB_EMPTY_NODE(&cfqg->rb_node))
 		cfq_rb_erase(&cfqg->rb_node, st);
@@ -1026,7 +1014,7 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	 * elevator which will be dropped by either elevator exit
 	 * or cgroup deletion path depending on who is exiting first.
 	 */
-	atomic_set(&cfqg->ref, 1);
+	cfqg->ref = 1;
 
 	/*
 	 * Add group onto cgroup list. It might happen that bdi->dev is
@@ -1071,7 +1059,7 @@ static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
 
 static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg)
 {
-	atomic_inc(&cfqg->ref);
+	cfqg->ref++;
 	return cfqg;
 }
 
@@ -1083,7 +1071,7 @@ static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg)
 
 	cfqq->cfqg = cfqg;
 	/* cfqq reference on cfqg */
-	atomic_inc(&cfqq->cfqg->ref);
+	cfqq->cfqg->ref++;
 }
 
 static void cfq_put_cfqg(struct cfq_group *cfqg)
@@ -1091,11 +1079,12 @@ static void cfq_put_cfqg(struct cfq_group *cfqg)
 	struct cfq_rb_root *st;
 	int i, j;
 
-	BUG_ON(atomic_read(&cfqg->ref) <= 0);
-	if (!atomic_dec_and_test(&cfqg->ref))
+	BUG_ON(cfqg->ref <= 0);
+	cfqg->ref--;
+	if (cfqg->ref)
 		return;
 	for_each_cfqg_st(cfqg, i, j, st)
-		BUG_ON(!RB_EMPTY_ROOT(&st->rb) || st->active != NULL);
+		BUG_ON(!RB_EMPTY_ROOT(&st->rb));
 	kfree(cfqg);
 }
 
@@ -1200,7 +1189,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
 		cfqq->orig_cfqg = cfqq->cfqg;
 		cfqq->cfqg = &cfqd->root_group;
-		atomic_inc(&cfqd->root_group.ref);
+		cfqd->root_group.ref++;
 		group_changed = 1;
 	} else if (!cfqd->cfq_group_isolation
 		   && cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) {
@@ -1687,9 +1676,6 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	if (cfqq == cfqd->active_queue)
 		cfqd->active_queue = NULL;
 
-	if (&cfqq->cfqg->rb_node == cfqd->grp_service_tree.active)
-		cfqd->grp_service_tree.active = NULL;
-
 	if (cfqd->active_cic) {
 		put_io_context(cfqd->active_cic->ioc);
 		cfqd->active_cic = NULL;
@@ -1901,10 +1887,10 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * in their service tree.
 	 */
 	if (service_tree->count == 1 && cfq_cfqq_sync(cfqq))
-		return 1;
+		return true;
 	cfq_log_cfqq(cfqd, cfqq, "Not idling. st->count:%d",
 			service_tree->count);
-	return 0;
+	return false;
 }
 
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
@@ -2040,7 +2026,7 @@ static int cfqq_process_refs(struct cfq_queue *cfqq)
 	int process_refs, io_refs;
 
 	io_refs = cfqq->allocated[READ] + cfqq->allocated[WRITE];
-	process_refs = atomic_read(&cfqq->ref) - io_refs;
+	process_refs = cfqq->ref - io_refs;
 	BUG_ON(process_refs < 0);
 	return process_refs;
 }
@@ -2080,10 +2066,10 @@ static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
 	 */
 	if (new_process_refs >= process_refs) {
 		cfqq->new_cfqq = new_cfqq;
-		atomic_add(process_refs, &new_cfqq->ref);
+		new_cfqq->ref += process_refs;
 	} else {
 		new_cfqq->new_cfqq = cfqq;
-		atomic_add(new_process_refs, &cfqq->ref);
+		cfqq->ref += new_process_refs;
 	}
 }
 
@@ -2116,12 +2102,7 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	unsigned count;
 	struct cfq_rb_root *st;
 	unsigned group_slice;
-
-	if (!cfqg) {
-		cfqd->serving_prio = IDLE_WORKLOAD;
-		cfqd->workload_expires = jiffies + 1;
-		return;
-	}
+	enum wl_prio_t original_prio = cfqd->serving_prio;
 
 	/* Choose next priority. RT > BE > IDLE */
 	if (cfq_group_busy_queues_wl(RT_WORKLOAD, cfqd, cfqg))
@@ -2134,6 +2115,9 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		return;
 	}
 
+	if (original_prio != cfqd->serving_prio)
+		goto new_workload;
+
 	/*
 	 * For RT and BE, we have to choose also the type
 	 * (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload
@@ -2148,6 +2132,7 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	if (count && !time_after(jiffies, cfqd->workload_expires))
 		return;
 
+new_workload:
 	/* otherwise select new workload type */
 	cfqd->serving_type =
 		cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio);
@@ -2199,7 +2184,6 @@ static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
 	if (RB_EMPTY_ROOT(&st->rb))
 		return NULL;
 	cfqg = cfq_rb_first_group(st);
-	st->active = &cfqg->rb_node;
 	update_min_vdisktime(st);
 	return cfqg;
 }
@@ -2293,6 +2277,17 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 		goto keep_queue;
 	}
 
+	/*
+	 * This is a deep seek queue, but the device is much faster than
+	 * the queue can deliver, don't idle
+	 **/
+	if (CFQQ_SEEKY(cfqq) && cfq_cfqq_idle_window(cfqq) &&
+	    (cfq_cfqq_slice_new(cfqq) ||
+	    (cfqq->slice_end - jiffies > jiffies - cfqq->slice_start))) {
+		cfq_clear_cfqq_deep(cfqq);
+		cfq_clear_cfqq_idle_window(cfqq);
+	}
+
 	if (cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
 		cfqq = NULL;
 		goto keep_queue;
@@ -2367,12 +2362,12 @@ static inline bool cfq_slice_used_soon(struct cfq_data *cfqd,
 {
 	/* the queue hasn't finished any request, can't estimate */
 	if (cfq_cfqq_slice_new(cfqq))
-		return 1;
+		return true;
 	if (time_after(jiffies + cfqd->cfq_slice_idle * cfqq->dispatched,
 		cfqq->slice_end))
-		return 1;
+		return true;
 
-	return 0;
+	return false;
 }
 
 static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
@@ -2538,9 +2533,10 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 	struct cfq_data *cfqd = cfqq->cfqd;
 	struct cfq_group *cfqg, *orig_cfqg;
 
-	BUG_ON(atomic_read(&cfqq->ref) <= 0);
+	BUG_ON(cfqq->ref <= 0);
 
-	if (!atomic_dec_and_test(&cfqq->ref))
+	cfqq->ref--;
+	if (cfqq->ref)
 		return;
 
 	cfq_log_cfqq(cfqd, cfqq, "put_queue");
@@ -2843,7 +2839,7 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	RB_CLEAR_NODE(&cfqq->p_node);
 	INIT_LIST_HEAD(&cfqq->fifo);
 
-	atomic_set(&cfqq->ref, 0);
+	cfqq->ref = 0;
 	cfqq->cfqd = cfqd;
 
 	cfq_mark_cfqq_prio_changed(cfqq);
@@ -2979,11 +2975,11 @@ cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct io_context *ioc,
 	 * pin the queue now that it's allocated, scheduler exit will prune it
 	 */
 	if (!is_sync && !(*async_cfqq)) {
-		atomic_inc(&cfqq->ref);
+		cfqq->ref++;
 		*async_cfqq = cfqq;
 	}
 
-	atomic_inc(&cfqq->ref);
+	cfqq->ref++;
 	return cfqq;
 }
 
@@ -3265,6 +3261,10 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
 		return true;
 
+	/* An idle queue should not be idle now for some reason */
+	if (RB_EMPTY_ROOT(&cfqq->sort_list) && !cfq_should_idle(cfqd, cfqq))
+		return true;
+
 	if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
 		return false;
 
@@ -3681,13 +3681,13 @@ new_queue:
 	}
 
 	cfqq->allocated[rw]++;
-	atomic_inc(&cfqq->ref);
-
-	spin_unlock_irqrestore(q->queue_lock, flags);
-
+	cfqq->ref++;
 	rq->elevator_private = cic;
 	rq->elevator_private2 = cfqq;
 	rq->elevator_private3 = cfq_ref_get_cfqg(cfqq->cfqg);
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
 	return 0;
 
 queue_fail:
@@ -3862,6 +3862,10 @@ static void *cfq_init_queue(struct request_queue *q)
 	if (!cfqd)
 		return NULL;
 
+	/*
+	 * Don't need take queue_lock in the routine, since we are
+	 * initializing the ioscheduler, and nobody is using cfqd
+	 */
 	cfqd->cic_index = i;
 
 	/* Init root service tree */
@@ -3881,7 +3885,7 @@ static void *cfq_init_queue(struct request_queue *q)
 	 * Take a reference to root group which we never drop. This is just
 	 * to make sure that cfq_put_cfqg() does not try to kfree root group
 	 */
-	atomic_set(&cfqg->ref, 1);
+	cfqg->ref = 1;
 	rcu_read_lock();
 	cfq_blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg,
 					(void *)cfqd, 0);
@@ -3901,7 +3905,7 @@ static void *cfq_init_queue(struct request_queue *q)
 	 * will not attempt to free it.
 	 */
 	cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0);
-	atomic_inc(&cfqd->oom_cfqq.ref);
+	cfqd->oom_cfqq.ref++;
 	cfq_link_cfqq_cfqg(&cfqd->oom_cfqq, &cfqd->root_group);
 
 	INIT_LIST_HEAD(&cfqd->cic_list);
diff --git a/block/genhd.c b/block/genhd.c
index 5fa2b44a72ff..6a5b772aa201 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -18,6 +18,7 @@
 #include <linux/buffer_head.h>
 #include <linux/mutex.h>
 #include <linux/idr.h>
+#include <linux/log2.h>
 
 #include "blk.h"
 
@@ -35,6 +36,10 @@ static DEFINE_IDR(ext_devt_idr);
 
 static struct device_type disk_type;
 
+static void disk_add_events(struct gendisk *disk);
+static void disk_del_events(struct gendisk *disk);
+static void disk_release_events(struct gendisk *disk);
+
 /**
  * disk_get_part - get partition
  * @disk: disk to look partition from
@@ -239,7 +244,7 @@ static struct blk_major_name {
 } *major_names[BLKDEV_MAJOR_HASH_SIZE];
 
 /* index in the above - for now: assume no multimajor ranges */
-static inline int major_to_index(int major)
+static inline int major_to_index(unsigned major)
 {
 	return major % BLKDEV_MAJOR_HASH_SIZE;
 }
@@ -502,6 +507,64 @@ static int exact_lock(dev_t devt, void *data)
 	return 0;
 }
 
+void register_disk(struct gendisk *disk)
+{
+	struct device *ddev = disk_to_dev(disk);
+	struct block_device *bdev;
+	struct disk_part_iter piter;
+	struct hd_struct *part;
+	int err;
+
+	ddev->parent = disk->driverfs_dev;
+
+	dev_set_name(ddev, disk->disk_name);
+
+	/* delay uevents, until we scanned partition table */
+	dev_set_uevent_suppress(ddev, 1);
+
+	if (device_add(ddev))
+		return;
+	if (!sysfs_deprecated) {
+		err = sysfs_create_link(block_depr, &ddev->kobj,
+					kobject_name(&ddev->kobj));
+		if (err) {
+			device_del(ddev);
+			return;
+		}
+	}
+	disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj);
+	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
+
+	/* No minors to use for partitions */
+	if (!disk_partitionable(disk))
+		goto exit;
+
+	/* No such device (e.g., media were just removed) */
+	if (!get_capacity(disk))
+		goto exit;
+
+	bdev = bdget_disk(disk, 0);
+	if (!bdev)
+		goto exit;
+
+	bdev->bd_invalidated = 1;
+	err = blkdev_get(bdev, FMODE_READ, NULL);
+	if (err < 0)
+		goto exit;
+	blkdev_put(bdev, FMODE_READ);
+
+exit:
+	/* announce disk after possible partitions are created */
+	dev_set_uevent_suppress(ddev, 0);
+	kobject_uevent(&ddev->kobj, KOBJ_ADD);
+
+	/* announce possible partitions */
+	disk_part_iter_init(&piter, disk, 0);
+	while ((part = disk_part_iter_next(&piter)))
+		kobject_uevent(&part_to_dev(part)->kobj, KOBJ_ADD);
+	disk_part_iter_exit(&piter);
+}
+
 /**
  * add_disk - add partitioning information to kernel list
  * @disk: per-device partitioning information
@@ -551,18 +614,48 @@ void add_disk(struct gendisk *disk)
 	retval = sysfs_create_link(&disk_to_dev(disk)->kobj, &bdi->dev->kobj,
 				   "bdi");
 	WARN_ON(retval);
-}
 
+	disk_add_events(disk);
+}
 EXPORT_SYMBOL(add_disk);
-EXPORT_SYMBOL(del_gendisk);	/* in partitions/check.c */
 
-void unlink_gendisk(struct gendisk *disk)
+void del_gendisk(struct gendisk *disk)
 {
+	struct disk_part_iter piter;
+	struct hd_struct *part;
+
+	disk_del_events(disk);
+
+	/* invalidate stuff */
+	disk_part_iter_init(&piter, disk,
+			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
+	while ((part = disk_part_iter_next(&piter))) {
+		invalidate_partition(disk, part->partno);
+		delete_partition(disk, part->partno);
+	}
+	disk_part_iter_exit(&piter);
+
+	invalidate_partition(disk, 0);
+	blk_free_devt(disk_to_dev(disk)->devt);