diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index f4eace5ea184..40f3cd7eab0f 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -156,7 +156,8 @@ static int read_sb_page(struct mddev *mddev, loff_t offset,
 
 	rdev_for_each(rdev, mddev) {
 		if (! test_bit(In_sync, &rdev->flags)
-		    || test_bit(Faulty, &rdev->flags))
+		    || test_bit(Faulty, &rdev->flags)
+		    || test_bit(Bitmap_sync, &rdev->flags))
 			continue;
 
 		target = offset + index * (PAGE_SIZE/512);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 991f0fe2dcc6..b50eb4ac1b82 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -134,7 +134,9 @@ enum flag_bits {
 	Faulty,			/* device is known to have a fault */
 	In_sync,		/* device is in_sync with rest of array */
 	Bitmap_sync,		/* ..actually, not quite In_sync.  Need a
-				 * bitmap-based recovery to get fully in sync
+				 * bitmap-based recovery to get fully in sync.
+				 * The bit is only meaningful before device
+				 * has been passed to pers->hot_add_disk.
 				 */
 	WriteMostly,		/* Avoid reading if at all possible */
 	AutoDetected,		/* added by auto-detect */
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index 77cce3573aa8..44ad5baf3206 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -1150,7 +1150,7 @@ int ppl_init_log(struct r5conf *conf)
 		goto err;
 	}
 
-	ppl_conf->bs = bioset_create(conf->raid_disks, 0, 0);
+	ppl_conf->bs = bioset_create(conf->raid_disks, 0, BIOSET_NEED_BVECS);
 	if (!ppl_conf->bs) {
 		ret = -ENOMEM;
 		goto err;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2ceb338b094b..aeeb8d6854e2 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7951,12 +7951,10 @@ static void end_reshape(struct r5conf *conf)
 {
 
 	if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
-		struct md_rdev *rdev;
 
 		spin_lock_irq(&conf->device_lock);
 		conf->previous_raid_disks = conf->raid_disks;
-		rdev_for_each(rdev, conf->mddev)
-			rdev->data_offset = rdev->new_data_offset;
+		md_finish_reshape(conf->mddev);
 		smp_wmb();
 		conf->reshape_progress = MaxSector;
 		conf->mddev->reshape_position = MaxSector;
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index c102ef65cb64..db6dc9dc0482 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -323,6 +323,7 @@ enum {
 
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
+	__WQ_ORDERED_EXPLICIT	= 1 << 18, /* internal: alloc_ordered_workqueue() */
 	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
 
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
@@ -422,7 +423,8 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 #define alloc_ordered_workqueue(fmt, flags, args...)			\
-	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
+	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED |		\
+			__WQ_ORDERED_EXPLICIT | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
 	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2d278b9a5469..a44ef675fd3a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3577,6 +3577,13 @@ static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node,
 
 	/* yeap, return possible CPUs in @node that @attrs wants */
 	cpumask_and(cpumask, attrs->cpumask, wq_numa_possible_cpumask[node]);
+
+	if (cpumask_empty(cpumask)) {
+		pr_warn_once("WARNING: workqueue cpumask: online intersect > "
+				"possible intersect\n");
+		return false;
+	}
+
 	return !cpumask_equal(cpumask, attrs->cpumask);
 
 use_dfl:
@@ -3744,8 +3751,12 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
 		return -EINVAL;
 
 	/* creating multiple pwqs breaks ordering guarantee */
-	if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)))
-		return -EINVAL;
+	if (!list_empty(&wq->pwqs)) {
+		if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
+			return -EINVAL;
+
+		wq->flags &= ~__WQ_ORDERED;
+	}
 
 	ctx = apply_wqattrs_prepare(wq, attrs);
 	if (!ctx)
@@ -3929,6 +3940,16 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 	struct workqueue_struct *wq;
 	struct pool_workqueue *pwq;
 
+	/*
+	 * Unbound && max_active == 1 used to imply ordered, which is no
+	 * longer the case on NUMA machines due to per-node pools.  While
+	 * alloc_ordered_workqueue() is the right way to create an ordered
+	 * workqueue, keep the previous behavior to avoid subtle breakages
+	 * on NUMA.
+	 */
+	if ((flags & WQ_UNBOUND) && max_active == 1)
+		flags |= __WQ_ORDERED;
+
 	/* see the comment above the definition of WQ_POWER_EFFICIENT */
 	if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
 		flags |= WQ_UNBOUND;
@@ -4119,13 +4140,14 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 	struct pool_workqueue *pwq;
 
 	/* disallow meddling with max_active for ordered workqueues */
-	if (WARN_ON(wq->flags & __WQ_ORDERED))
+	if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
 		return;
 
 	max_active = wq_clamp_max_active(max_active, wq->flags, wq->name);
 
 	mutex_lock(&wq->mutex);
 
+	wq->flags &= ~__WQ_ORDERED;
 	wq->saved_max_active = max_active;
 
 	for_each_pwq(pwq, wq)
@@ -5253,7 +5275,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
 	 * attributes breaks ordering guarantee.  Disallow exposing ordered
 	 * workqueues.
 	 */
-	if (WARN_ON(wq->flags & __WQ_ORDERED))
+	if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
 		return -EINVAL;
 
 	wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL);