Merge branch 'for-linus' into for-3.1/core

Conflicts:
	block/blk-throttle.c
	block/cfq-iosched.c

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

3 files changed, 57 insertions, 45 deletions

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index bfb0493..6f9bbd9 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -21,7 +21,7 @@ static void cfq_dtor(struct io_context *ioc)
 	if (!hlist_empty(&ioc->cic_list)) {
 		struct cfq_io_context *cic;
 
-		cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+		cic = hlist_entry(ioc->cic_list.first, struct cfq_io_context,
 								cic_list);
 		cic->dtor(ioc);
 	}
@@ -57,7 +57,7 @@ static void cfq_exit(struct io_context *ioc)
 	if (!hlist_empty(&ioc->cic_list)) {
 		struct cfq_io_context *cic;
 
-		cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+		cic = hlist_entry(ioc->cic_list.first, struct cfq_io_context,
 								cic_list);
 		cic->exit(ioc);
 	}
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 3d403a1..b2e1c75 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -185,7 +185,7 @@ struct cfq_group {
 	int nr_cfqq;
 
 	/*
-	 * Per group busy queus average. Useful for workload slice calc. We
+	 * Per group busy queues average. Useful for workload slice calc. We
 	 * create the array for each prio class but at run time it is used
 	 * only for RT and BE class and slot for IDLE class remains unused.
 	 * This is primarily done to avoid confusion and a gcc warning.
@@ -369,16 +369,16 @@ CFQ_CFQQ_FNS(wait_busy);
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \
 			cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \
-			blkg_path(&(cfqq)->cfqg->blkg), ##args);
+			blkg_path(&(cfqq)->cfqg->blkg), ##args)
 
 #define cfq_log_cfqg(cfqd, cfqg, fmt, args...)				\
 	blk_add_trace_msg((cfqd)->queue, "%s " fmt,			\
-				blkg_path(&(cfqg)->blkg), ##args);      \
+				blkg_path(&(cfqg)->blkg), ##args)       \
 
 #else
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
-#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0);
+#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0)
 #endif
 #define cfq_log(cfqd, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
@@ -2768,11 +2768,14 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
 	smp_wmb();
 	cic->key = cfqd_dead_key(cfqd);
 
+	rcu_read_lock();
 	if (rcu_dereference(ioc->ioc_data) == cic) {
+		rcu_read_unlock();
 		spin_lock(&ioc->lock);
 		rcu_assign_pointer(ioc->ioc_data, NULL);
 		spin_unlock(&ioc->lock);
-	}
+	} else
+		rcu_read_unlock();
 
 	if (cic->cfqq[BLK_RW_ASYNC]) {
 		cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]);
@@ -3079,7 +3082,8 @@ cfq_drop_dead_cic(struct cfq_data *cfqd, struct io_context *ioc,
 
 	spin_lock_irqsave(&ioc->lock, flags);
 
-	BUG_ON(ioc->ioc_data == cic);
+	BUG_ON(rcu_dereference_check(ioc->ioc_data,
+		lockdep_is_held(&ioc->lock)) == cic);
 
 	radix_tree_delete(&ioc->radix_root, cfqd->cic_index);
 	hlist_del_rcu(&cic->cic_list);
@@ -3785,9 +3789,6 @@ new_queue:
 	return 0;
 
 queue_fail:
-	if (cic)
-		put_io_context(cic->ioc);
-
 	cfq_schedule_dispatch(cfqd);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 	cfq_log(cfqd, "set_request fail");
diff --git a/block/genhd.c b/block/genhd.c
index ed3fe82..82d97c3 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1371,6 +1371,7 @@ struct disk_events {
 	struct gendisk		*disk;		/* the associated disk */
 	spinlock_t		lock;
 
+	struct mutex		block_mutex;	/* protects blocking */
 	int			block;		/* event blocking depth */
 	unsigned int		pending;	/* events already sent out */
 	unsigned int		clearing;	/* events being cleared */
@@ -1414,22 +1415,44 @@ static unsigned long disk_events_poll_jiffies(struct gendisk *disk)
 	return msecs_to_jiffies(intv_msecs);
 }
 
-static void __disk_block_events(struct gendisk *disk, bool sync)
+/**
+ * disk_block_events - block and flush disk event checking
+ * @disk: disk to block events for
+ *
+ * On return from this function, it is guaranteed that event checking
+ * isn't in progress and won't happen until unblocked by
+ * disk_unblock_events().  Events blocking is counted and the actual
+ * unblocking happens after the matching number of unblocks are done.
+ *
+ * Note that this intentionally does not block event checking from
+ * disk_clear_events().
+ *
+ * CONTEXT:
+ * Might sleep.
+ */
+void disk_block_events(struct gendisk *disk)
 {
 	struct disk_events *ev = disk->ev;
 	unsigned long flags;
 	bool cancel;
 
+	if (!ev)
+		return;
+
+	/*
+	 * Outer mutex ensures that the first blocker completes canceling
+	 * the event work before further blockers are allowed to finish.
+	 */
+	mutex_lock(&ev->block_mutex);
+
 	spin_lock_irqsave(&ev->lock, flags);
 	cancel = !ev->block++;
 	spin_unlock_irqrestore(&ev->lock, flags);
 
-	if (cancel) {
-		if (sync)
-			cancel_delayed_work_sync(&disk->ev->dwork);
-		else
-			cancel_delayed_work(&disk->ev->dwork);
-	}
+	if (cancel)
+		cancel_delayed_work_sync(&disk->ev->dwork);
+
+	mutex_unlock(&ev->block_mutex);
 }
 
 static void __disk_unblock_events(struct gendisk *disk, bool check_now)
@@ -1461,27 +1484,6 @@ out_unlock:
 }
 
 /**
- * disk_block_events - block and flush disk event checking
- * @disk: disk to block events for
- *
- * On return from this function, it is guaranteed that event checking
- * isn't in progress and won't happen until unblocked by
- * disk_unblock_events().  Events blocking is counted and the actual
- * unblocking happens after the matching number of unblocks are done.
- *
- * Note that this intentionally does not block event checking from
- * disk_clear_events().
- *
- * CONTEXT:
- * Might sleep.
- */
-void disk_block_events(struct gendisk *disk)
-{
-	if (disk->ev)
-		__disk_block_events(disk, true);
-}
-
-/**
  * disk_unblock_events - unblock disk event checking
  * @disk: disk to unblock events for
  *
@@ -1508,10 +1510,18 @@ void disk_unblock_events(struct gendisk *disk)
  */
 void disk_check_events(struct gendisk *disk)
 {
-	if (disk->ev) {
-		__disk_block_events(disk, false);
-		__disk_unblock_events(disk, true);
+	struct disk_events *ev = disk->ev;
+	unsigned long flags;
+
+	if (!ev)
+		return;
+
+	spin_lock_irqsave(&ev->lock, flags);
+	if (!ev->block) {
+		cancel_delayed_work(&ev->dwork);
+		queue_delayed_work(system_nrt_wq, &ev->dwork, 0);
 	}
+	spin_unlock_irqrestore(&ev->lock, flags);
 }
 EXPORT_SYMBOL_GPL(disk_check_events);
 
@@ -1546,7 +1556,7 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
 	spin_unlock_irq(&ev->lock);
 
 	/* uncondtionally schedule event check and wait for it to finish */
-	__disk_block_events(disk, true);
+	disk_block_events(disk);
 	queue_delayed_work(system_nrt_wq, &ev->dwork, 0);
 	flush_delayed_work(&ev->dwork);
 	__disk_unblock_events(disk, false);
@@ -1664,7 +1674,7 @@ static ssize_t disk_events_poll_msecs_store(struct device *dev,
 	if (intv < 0 && intv != -1)
 		return -EINVAL;
 
-	__disk_block_events(disk, true);
+	disk_block_events(disk);
 	disk->ev->poll_msecs = intv;
 	__disk_unblock_events(disk, true);
 
@@ -1750,6 +1760,7 @@ static void disk_add_events(struct gendisk *disk)
 	INIT_LIST_HEAD(&ev->node);
 	ev->disk = disk;
 	spin_lock_init(&ev->lock);
+	mutex_init(&ev->block_mutex);
 	ev->block = 1;
 	ev->poll_msecs = -1;
 	INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn);
@@ -1770,7 +1781,7 @@ static void disk_del_events(struct gendisk *disk)
 	if (!disk->ev)
 		return;
 
-	__disk_block_events(disk, true);
+	disk_block_events(disk);
 
 	mutex_lock(&disk_events_mutex);
 	list_del_init(&disk->ev->node);