4 files changed, 158 insertions, 79 deletions

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 8b782a63c29..fb95dd2f889 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -36,11 +36,23 @@ static void icq_free_icq_rcu(struct rcu_head *head)
 	kmem_cache_free(icq->__rcu_icq_cache, icq);
 }
 
-/*
- * Exit and free an icq.  Called with both ioc and q locked.
- */
+/* Exit an icq. Called with both ioc and q locked. */
 static void ioc_exit_icq(struct io_cq *icq)
 {
+	struct elevator_type *et = icq->q->elevator->type;
+
+	if (icq->flags & ICQ_EXITED)
+		return;
+
+	if (et->ops.elevator_exit_icq_fn)
+		et->ops.elevator_exit_icq_fn(icq);
+
+	icq->flags |= ICQ_EXITED;
+}
+
+/* Release an icq.  Called with both ioc and q locked. */
+static void ioc_destroy_icq(struct io_cq *icq)
+{
 	struct io_context *ioc = icq->ioc;
 	struct request_queue *q = icq->q;
 	struct elevator_type *et = q->elevator->type;
@@ -60,8 +72,7 @@ static void ioc_exit_icq(struct io_cq *icq)
 	if (rcu_dereference_raw(ioc->icq_hint) == icq)
 		rcu_assign_pointer(ioc->icq_hint, NULL);
 
-	if (et->ops.elevator_exit_icq_fn)
-		et->ops.elevator_exit_icq_fn(icq);
+	ioc_exit_icq(icq);
 
 	/*
 	 * @icq->q might have gone away by the time RCU callback runs
@@ -79,7 +90,6 @@ static void ioc_release_fn(struct work_struct *work)
 {
 	struct io_context *ioc = container_of(work, struct io_context,
 					      release_work);
-	struct request_queue *last_q = NULL;
 	unsigned long flags;
 
 	/*
@@ -93,44 +103,19 @@ static void ioc_release_fn(struct work_struct *work)
 	while (!hlist_empty(&ioc->icq_list)) {
 		struct io_cq *icq = hlist_entry(ioc->icq_list.first,
 						struct io_cq, ioc_node);
-		struct request_queue *this_q = icq->q;
-
-		if (this_q != last_q) {
-			/*
-			 * Need to switch to @this_q.  Once we release
-			 * @ioc->lock, it can go away along with @cic.
-			 * Hold on to it.
-			 */
-			__blk_get_queue(this_q);
-
-			/*
-			 * blk_put_queue() might sleep thanks to kobject
-			 * idiocy.  Always release both locks, put and
-			 * restart.
-			 */
-			if (last_q) {
-				spin_unlock(last_q->queue_lock);
-				spin_unlock_irqrestore(&ioc->lock, flags);
-				blk_put_queue(last_q);
-			} else {
-				spin_unlock_irqrestore(&ioc->lock, flags);
-			}
-
-			last_q = this_q;
-			spin_lock_irqsave(this_q->queue_lock, flags);
-			spin_lock_nested(&ioc->lock, 1);
-			continue;
+		struct request_queue *q = icq->q;
+
+		if (spin_trylock(q->queue_lock)) {
+			ioc_destroy_icq(icq);
+			spin_unlock(q->queue_lock);
+		} else {
+			spin_unlock_irqrestore(&ioc->lock, flags);
+			cpu_relax();
+			spin_lock_irqsave_nested(&ioc->lock, flags, 1);
 		}
-		ioc_exit_icq(icq);
 	}
 
-	if (last_q) {
-		spin_unlock(last_q->queue_lock);
-		spin_unlock_irqrestore(&ioc->lock, flags);
-		blk_put_queue(last_q);
-	} else {
-		spin_unlock_irqrestore(&ioc->lock, flags);
-	}
+	spin_unlock_irqrestore(&ioc->lock, flags);
 
 	kmem_cache_free(iocontext_cachep, ioc);
 }
@@ -145,6 +130,7 @@ static void ioc_release_fn(struct work_struct *work)
 void put_io_context(struct io_context *ioc)
 {
 	unsigned long flags;
+	bool free_ioc = false;
 
 	if (ioc == NULL)
 		return;
@@ -159,8 +145,13 @@ void put_io_context(struct io_context *ioc)
 		spin_lock_irqsave(&ioc->lock, flags);
 		if (!hlist_empty(&ioc->icq_list))
 			schedule_work(&ioc->release_work);
+		else
+			free_ioc = true;
 		spin_unlock_irqrestore(&ioc->lock, flags);
 	}
+
+	if (free_ioc)
+		kmem_cache_free(iocontext_cachep, ioc);
 }
 EXPORT_SYMBOL(put_io_context);
 
@@ -168,13 +159,41 @@ EXPORT_SYMBOL(put_io_context);
 void exit_io_context(struct task_struct *task)
 {
 	struct io_context *ioc;
+	struct io_cq *icq;
+	struct hlist_node *n;
+	unsigned long flags;
 
 	task_lock(task);
 	ioc = task->io_context;
 	task->io_context = NULL;
 	task_unlock(task);
 
-	atomic_dec(&ioc->nr_tasks);
+	if (!atomic_dec_and_test(&ioc->nr_tasks)) {
+		put_io_context(ioc);
+		return;
+	}
+
+	/*
+	 * Need ioc lock to walk icq_list and q lock to exit icq.  Perform
+	 * reverse double locking.  Read comment in ioc_release_fn() for
+	 * explanation on the nested locking annotation.
+	 */
+retry:
+	spin_lock_irqsave_nested(&ioc->lock, flags, 1);
+	hlist_for_each_entry(icq, n, &ioc->icq_list, ioc_node) {
+		if (icq->flags & ICQ_EXITED)
+			continue;
+		if (spin_trylock(icq->q->queue_lock)) {
+			ioc_exit_icq(icq);
+			spin_unlock(icq->q->queue_lock);
+		} else {
+			spin_unlock_irqrestore(&ioc->lock, flags);
+			cpu_relax();
+			goto retry;
+		}
+	}
+	spin_unlock_irqrestore(&ioc->lock, flags);
+
 	put_io_context(ioc);
 }
 
@@ -194,7 +213,7 @@ void ioc_clear_queue(struct request_queue *q)
 		struct io_context *ioc = icq->ioc;
 
 		spin_lock(&ioc->lock);
-		ioc_exit_icq(icq);
+		ioc_destroy_icq(icq);
 		spin_unlock(&ioc->lock);
 	}
 }
@@ -363,13 +382,13 @@ struct io_cq *ioc_create_icq(struct request_queue *q, gfp_t gfp_mask)
 	return icq;
 }
 
-void ioc_set_changed(struct io_context *ioc, int which)
+void ioc_set_icq_flags(struct io_context *ioc, unsigned int flags)
 {
 	struct io_cq *icq;
 	struct hlist_node *n;
 
 	hlist_for_each_entry(icq, n, &ioc->icq_list, ioc_node)
-		set_bit(which, &icq->changed);
+		icq->flags |= flags;
 }
 
 /**
@@ -387,7 +406,7 @@ void ioc_ioprio_changed(struct io_context *ioc, int ioprio)
 
 	spin_lock_irqsave(&ioc->lock, flags);
 	ioc->ioprio = ioprio;
-	ioc_set_changed(ioc, ICQ_IOPRIO_CHANGED);
+	ioc_set_icq_flags(ioc, ICQ_IOPRIO_CHANGED);
 	spin_unlock_irqrestore(&ioc->lock, flags);
 }
 
@@ -404,11 +423,33 @@ void ioc_cgroup_changed(struct io_context *ioc)
 	unsigned long flags;
 
 	spin_lock_irqsave(&ioc->lock, flags);
-	ioc_set_changed(ioc, ICQ_CGROUP_CHANGED);
+	ioc_set_icq_flags(ioc, ICQ_CGROUP_CHANGED);
 	spin_unlock_irqrestore(&ioc->lock, flags);
 }
 EXPORT_SYMBOL(ioc_cgroup_changed);
 
+/**
+ * icq_get_changed - fetch and clear icq changed mask
+ * @icq: icq of interest
+ *
+ * Fetch and clear ICQ_*_CHANGED bits from @icq.  Grabs and releases
+ * @icq->ioc->lock.
+ */
+unsigned icq_get_changed(struct io_cq *icq)
+{
+	unsigned int changed = 0;
+	unsigned long flags;
+
+	if (unlikely(icq->flags & ICQ_CHANGED_MASK)) {
+		spin_lock_irqsave(&icq->ioc->lock, flags);
+		changed = icq->flags & ICQ_CHANGED_MASK;
+		icq->flags &= ~ICQ_CHANGED_MASK;
+		spin_unlock_irqrestore(&icq->ioc->lock, flags);
+	}
+	return changed;
+}
+EXPORT_SYMBOL(icq_get_changed);
+
 static int __init blk_ioc_init(void)
 {
 	iocontext_cachep = kmem_cache_create("blkdev_ioc",
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index d0ba5053366..45729525356 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3470,20 +3470,20 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
 	const int rw = rq_data_dir(rq);
 	const bool is_sync = rq_is_sync(rq);
 	struct cfq_queue *cfqq;
+	unsigned int changed;
 
 	might_sleep_if(gfp_mask & __GFP_WAIT);
 
 	spin_lock_irq(q->queue_lock);
 
 	/* handle changed notifications */
-	if (unlikely(cic->icq.changed)) {
-		if (test_and_clear_bit(ICQ_IOPRIO_CHANGED, &cic->icq.changed))
-			changed_ioprio(cic);
+	changed = icq_get_changed(&cic->icq);
+	if (unlikely(changed & ICQ_IOPRIO_CHANGED))
+		changed_ioprio(cic);
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
-		if (test_and_clear_bit(ICQ_CGROUP_CHANGED, &cic->icq.changed))
-			changed_cgroup(cic);
+	if (unlikely(changed & ICQ_CGROUP_CHANGED))
+		changed_cgroup(cic);
 #endif
-	}
 
 new_queue:
 	cfqq = cic_to_cfqq(cic, is_sync);
diff --git a/block/genhd.c b/block/genhd.c
index 23b4f706332..df9816ede75 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -35,6 +35,7 @@ static DEFINE_IDR(ext_devt_idr);
 
 static struct device_type disk_type;
 
+static void disk_alloc_events(struct gendisk *disk);
 static void disk_add_events(struct gendisk *disk);
 static void disk_del_events(struct gendisk *disk);
 static void disk_release_events(struct gendisk *disk);
@@ -601,6 +602,8 @@ void add_disk(struct gendisk *disk)
 	disk->major = MAJOR(devt);
 	disk->first_minor = MINOR(devt);
 
+	disk_alloc_events(disk);
+
 	/* Register BDI before referencing it from bdev */
 	bdi = &disk->queue->backing_dev_info;
 	bdi_register_dev(bdi, disk_devt(disk));
@@ -1475,9 +1478,9 @@ static void __disk_unblock_events(struct gendisk *disk, bool check_now)
 	intv = disk_events_poll_jiffies(disk);
 	set_timer_slack(&ev->dwork.timer, intv / 4);
 	if (check_now)
-		queue_delayed_work(system_nrt_wq, &ev->dwork, 0);
+		queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, 0);
 	else if (intv)
-		queue_delayed_work(system_nrt_wq, &ev->dwork, intv);
+		queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, intv);
 out_unlock:
 	spin_unlock_irqrestore(&ev->lock, flags);
 }
@@ -1521,7 +1524,7 @@ void disk_flush_events(struct gendisk *disk, unsigned int mask)
 	ev->clearing |= mask;
 	if (!ev->block) {
 		cancel_delayed_work(&ev->dwork);
-		queue_delayed_work(system_nrt_wq, &ev->dwork, 0);
+		queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, 0);
 	}
 	spin_unlock_irq(&ev->lock);
 }
@@ -1558,7 +1561,7 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
 
 	/* uncondtionally schedule event check and wait for it to finish */
 	disk_block_events(disk);
-	queue_delayed_work(system_nrt_wq, &ev->dwork, 0);
+	queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, 0);
 	flush_delayed_work(&ev->dwork);
 	__disk_unblock_events(disk, false);
 
@@ -1595,7 +1598,7 @@ static void disk_events_workfn(struct work_struct *work)
 
 	intv = disk_events_poll_jiffies(disk);
 	if (!ev->block && intv)
-		queue_delayed_work(system_nrt_wq, &ev->dwork, intv);
+		queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, intv);
 
 	spin_unlock_irq(&ev->lock);
 
@@ -1733,9 +1736,9 @@ module_param_cb(events_dfl_poll_msecs, &disk_events_dfl_poll_msecs_param_ops,
 		&disk_events_dfl_poll_msecs, 0644);
 
 /*
- * disk_{add|del|release}_events - initialize and destroy disk_events.
+ * disk_{alloc|add|del|release}_events - initialize and destroy disk_events.
  */
-static void disk_add_events(struct gendisk *disk)
+static void disk_alloc_events(struct gendisk *disk)
 {
 	struct disk_events *ev;
 
@@ -1748,16 +1751,6 @@ static void disk_add_events(struct gendisk *disk)
 		return;
 	}
 
-	if (sysfs_create_files(&disk_to_dev(disk)->kobj,
-			       disk_events_attrs) < 0) {
-		pr_warn("%s: failed to create sysfs files for events\n",
-			disk->disk_name);
-		kfree(ev);
-		return;
-	}
-
-	disk->ev = ev;
-
 	INIT_LIST_HEAD(&ev->node);
 	ev->disk = disk;
 	spin_lock_init(&ev->lock);
@@ -1766,8 +1759,21 @@ static void disk_add_events(struct gendisk *disk)
 	ev->poll_msecs = -1;
 	INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn);
 
+	disk->ev = ev;
+}
+
+static void disk_add_events(struct gendisk *disk)
+{
+	if (!disk->ev)
+		return;
+
+	/* FIXME: error handling */
+	if (sysfs_create_files(&disk_to_dev(disk)->kobj, disk_events_attrs) < 0)
+		pr_warn("%s: failed to create sysfs files for events\n",
+			disk->disk_name);
+
 	mutex_lock(&disk_events_mutex);
-	list_add_tail(&ev->node, &disk_events);
+	list_add_tail(&disk->ev->node, &disk_events);
 	mutex_unlock(&disk_events_mutex);
 
 	/*
diff --git a/block/partition-generic.c b/block/partition-generic.c
index d06ec1c829c..6df5d6928a4 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -389,17 +389,11 @@ static bool disk_unlock_native_capacity(struct gendisk *disk)
 	}
 }
 
-int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
+static int drop_partitions(struct gendisk *disk, struct block_device *bdev)
 {
-	struct parsed_partitions *state = NULL;
 	struct disk_part_iter piter;
 	struct hd_struct *part;
-	int p, highest, res;
-rescan:
-	if (state && !IS_ERR(state)) {
-		kfree(state);
-		state = NULL;
-	}
+	int res;
 
 	if (bdev->bd_part_count)
 		return -EBUSY;
@@ -412,6 +406,24 @@ rescan:
 		delete_partition(disk, part->partno);
 	disk_part_iter_exit(&piter);
 
+	return 0;
+}
+
+int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
+{
+	struct parsed_partitions *state = NULL;
+	struct hd_struct *part;
+	int p, highest, res;
+rescan:
+	if (state && !IS_ERR(state)) {
+		kfree(state);
+		state = NULL;
+	}
+
+	res = drop_partitions(disk, bdev);
+	if (res)
+		return res;
+
 	if (disk->fops->revalidate_disk)
 		disk->fops->revalidate_disk(disk);
 	check_disk_size_change(disk, bdev);
@@ -515,6 +527,26 @@ rescan:
 	return 0;
 }
 
+int invalidate_partitions(struct gendisk *disk, struct block_device *bdev)
+{
+	int res;
+
+	if (!bdev->bd_invalidated)
+		return 0;
+
+	res = drop_partitions(disk, bdev);
+	if (res)
+		return res;
+
+	set_capacity(disk, 0);
+	check_disk_size_change(disk, bdev);
+	bdev->bd_invalidated = 0;
+	/* tell userspace that the media / partition table may have changed */
+	kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
+
+	return 0;
+}
+
 unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;