Merge tag 'for-5.5/drivers-20191121' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "Here are the main block driver updates for 5.5. Nothing major in here,
  mostly just fixes. This contains:

   - a set of bcache changes via Coly

   - MD changes from Song

   - loop unmap write-zeroes fix (Darrick)

   - spelling fixes (Geert)

   - zoned additions cleanups to null_blk/dm (Ajay)

   - allow null_blk online submit queue changes (Bart)

   - NVMe changes via Keith, nothing major here either"

* tag 'for-5.5/drivers-20191121' of git://git.kernel.dk/linux-block: (56 commits)
  Revert "bcache: fix fifo index swapping condition in journal_pin_cmp()"
  drivers/md/raid5-ppl.c: use the new spelling of RWH_WRITE_LIFE_NOT_SET
  drivers/md/raid5.c: use the new spelling of RWH_WRITE_LIFE_NOT_SET
  bcache: don't export symbols
  bcache: remove the extra cflags for request.o
  bcache: at least try to shrink 1 node in bch_mca_scan()
  bcache: add idle_max_writeback_rate sysfs interface
  bcache: add code comments in bch_btree_leaf_dirty()
  bcache: fix deadlock in bcache_allocator
  bcache: add code comment bch_keylist_pop() and bch_keylist_pop_front()
  bcache: deleted code comments for dead code in bch_data_insert_keys()
  bcache: add more accurate error messages in read_super()
  bcache: fix static checker warning in bcache_device_free()
  bcache: fix a lost wake-up problem caused by mca_cannibalize_lock
  bcache: fix fifo index swapping condition in journal_pin_cmp()
  md/raid10: prevent access of uninitialized resync_pages offset
  md: avoid invalid memory access for array sb->dev_roles
  md/raid1: avoid soft lockup under high load
  null_blk: add zone open, close, and finish support
  dm: add zone open, close and finish support
  ...

23 files changed, 153 insertions, 97 deletions

diff --git a/drivers/md/bcache/Makefile b/drivers/md/bcache/Makefile
index d26b35195825..fd714628da6a 100644
--- a/drivers/md/bcache/Makefile
+++ b/drivers/md/bcache/Makefile
@@ -5,5 +5,3 @@ obj-$(CONFIG_BCACHE)	+= bcache.o
 bcache-y		:= alloc.o bset.o btree.o closure.o debug.o extents.o\
 	io.o journal.o movinggc.o request.o stats.o super.o sysfs.o trace.o\
 	util.o writeback.o
-
-CFLAGS_request.o	+= -Iblock
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 6f776823b9ba..a1df0d95151c 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -377,7 +377,10 @@ retry_invalidate:
 			if (!fifo_full(&ca->free_inc))
 				goto retry_invalidate;
 
-			bch_prio_write(ca);
+			if (bch_prio_write(ca, false) < 0) {
+				ca->invalidate_needs_gc = 1;
+				wake_up_gc(ca->set);
+			}
 		}
 	}
 out:
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 013e35a9e317..9198c1b480d9 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -582,6 +582,7 @@ struct cache_set {
 	 */
 	wait_queue_head_t	btree_cache_wait;
 	struct task_struct	*btree_cache_alloc_lock;
+	spinlock_t		btree_cannibalize_lock;
 
 	/*
 	 * When we free a btree node, we increment the gen of the bucket the
@@ -723,6 +724,7 @@ struct cache_set {
 	unsigned int		gc_always_rewrite:1;
 	unsigned int		shrinker_disabled:1;
 	unsigned int		copy_gc_enabled:1;
+	unsigned int		idle_max_writeback_rate_enabled:1;
 
 #define BUCKET_HASH_BITS	12
 	struct hlist_head	bucket_hash[1 << BUCKET_HASH_BITS];
@@ -977,7 +979,7 @@ bool bch_cached_dev_error(struct cached_dev *dc);
 __printf(2, 3)
 bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...);
 
-void bch_prio_write(struct cache *ca);
+int bch_prio_write(struct cache *ca, bool wait);
 void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent);
 
 extern struct workqueue_struct *bcache_wq;
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 08768796b543..cffcdc9feefb 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -155,6 +155,7 @@ int __bch_keylist_realloc(struct keylist *l, unsigned int u64s)
 	return 0;
 }
 
+/* Pop the top key of keylist by pointing l->top to its previous key */
 struct bkey *bch_keylist_pop(struct keylist *l)
 {
 	struct bkey *k = l->keys;
@@ -168,6 +169,7 @@ struct bkey *bch_keylist_pop(struct keylist *l)
 	return l->top = k;
 }
 
+/* Pop the bottom key of keylist and update l->top_p */
 void bch_keylist_pop_front(struct keylist *l)
 {
 	l->top_p -= bkey_u64s(l->keys);
@@ -309,7 +311,6 @@ void bch_btree_keys_free(struct btree_keys *b)
 	t->tree = NULL;
 	t->data = NULL;
 }
-EXPORT_SYMBOL(bch_btree_keys_free);
 
 int bch_btree_keys_alloc(struct btree_keys *b,
 			 unsigned int page_order,
@@ -342,7 +343,6 @@ err:
 	bch_btree_keys_free(b);
 	return -ENOMEM;
 }
-EXPORT_SYMBOL(bch_btree_keys_alloc);
 
 void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops,
 			 bool *expensive_debug_checks)
@@ -361,7 +361,6 @@ void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops,
 	 * any more.
 	 */
 }
-EXPORT_SYMBOL(bch_btree_keys_init);
 
 /* Binary tree stuff for auxiliary search trees */
 
@@ -678,7 +677,6 @@ void bch_bset_init_next(struct btree_keys *b, struct bset *i, uint64_t magic)
 
 	bch_bset_build_unwritten_tree(b);
 }
-EXPORT_SYMBOL(bch_bset_init_next);
 
 /*
  * Build auxiliary binary tree 'struct bset_tree *t', this tree is used to
@@ -732,7 +730,6 @@ void bch_bset_build_written_tree(struct btree_keys *b)
 	     j = inorder_next(j, t->size))
 		make_bfloat(t, j);
 }
-EXPORT_SYMBOL(bch_bset_build_written_tree);
 
 /* Insert */
 
@@ -780,7 +777,6 @@ fix_right:	do {
 			j = j * 2 + 1;
 		} while (j < t->size);
 }
-EXPORT_SYMBOL(bch_bset_fix_invalidated_key);
 
 static void bch_bset_fix_lookup_table(struct btree_keys *b,
 				      struct bset_tree *t,
@@ -855,7 +851,6 @@ bool bch_bkey_try_merge(struct btree_keys *b, struct bkey *l, struct bkey *r)
 
 	return b->ops->key_merge(b, l, r);
 }
-EXPORT_SYMBOL(bch_bkey_try_merge);
 
 void bch_bset_insert(struct btree_keys *b, struct bkey *where,
 		     struct bkey *insert)
@@ -875,7 +870,6 @@ void bch_bset_insert(struct btree_keys *b, struct bkey *where,
 	bkey_copy(where, insert);
 	bch_bset_fix_lookup_table(b, t, where);
 }
-EXPORT_SYMBOL(bch_bset_insert);
 
 unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 			      struct bkey *replace_key)
@@ -931,7 +925,6 @@ copy:	bkey_copy(m, k);
 merged:
 	return status;
 }
-EXPORT_SYMBOL(bch_btree_insert_key);
 
 /* Lookup */
 
@@ -1077,7 +1070,6 @@ struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
 
 	return i.l;
 }
-EXPORT_SYMBOL(__bch_bset_search);
 
 /* Btree iterator */
 
@@ -1132,7 +1124,6 @@ struct bkey *bch_btree_iter_init(struct btree_keys *b,
 {
 	return __bch_btree_iter_init(b, iter, search, b->set);
 }
-EXPORT_SYMBOL(bch_btree_iter_init);
 
 static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
 						 btree_iter_cmp_fn *cmp)
@@ -1165,7 +1156,6 @@ struct bkey *bch_btree_iter_next(struct btree_iter *iter)
 	return __bch_btree_iter_next(iter, btree_iter_cmp);
 
 }
-EXPORT_SYMBOL(bch_btree_iter_next);
 
 struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
 					struct btree_keys *b, ptr_filter_fn fn)
@@ -1196,7 +1186,6 @@ int bch_bset_sort_state_init(struct bset_sort_state *state,
 
 	return mempool_init_page_pool(&state->pool, 1, page_order);
 }
-EXPORT_SYMBOL(bch_bset_sort_state_init);
 
 static void btree_mergesort(struct btree_keys *b, struct bset *out,
 			    struct btree_iter *iter,
@@ -1313,7 +1302,6 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
 
 	EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize);
 }
-EXPORT_SYMBOL(bch_btree_sort_partial);
 
 void bch_btree_sort_and_fix_extents(struct btree_keys *b,
 				    struct btree_iter *iter,
@@ -1366,7 +1354,6 @@ void bch_btree_sort_lazy(struct btree_keys *b, struct bset_sort_state *state)
 out:
 	bch_bset_build_written_tree(b);
 }
-EXPORT_SYMBOL(bch_btree_sort_lazy);
 
 void bch_btree_keys_stats(struct btree_keys *b, struct bset_stats *stats)
 {
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index ba434d9ac720..14d6c33b0957 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -543,6 +543,11 @@ static void bch_btree_leaf_dirty(struct btree *b, atomic_t *journal_ref)
 
 	set_btree_node_dirty(b);
 
+	/*
+	 * w->journal is always the oldest journal pin of all bkeys
+	 * in the leaf node, to make sure the oldest jset seq won't
+	 * be increased before this btree node is flushed.
+	 */
 	if (journal_ref) {
 		if (w->journal &&
 		    journal_pin_cmp(b->c, w->journal, journal_ref)) {
@@ -723,6 +728,8 @@ static unsigned long bch_mca_scan(struct shrinker *shrink,
 	 * IO can always make forward progress:
 	 */
 	nr /= c->btree_pages;
+	if (nr == 0)
+		nr = 1;
 	nr = min_t(unsigned long, nr, mca_can_free(c));
 
 	i = 0;
@@ -884,15 +891,17 @@ out:
 
 static int mca_cannibalize_lock(struct cache_set *c, struct btree_op *op)
 {
-	struct task_struct *old;
-
-	old = cmpxchg(&c->btree_cache_alloc_lock, NULL, current);
-	if (old && old != current) {
+	spin_lock(&c->btree_cannibalize_lock);
+	if (likely(c->btree_cache_alloc_lock == NULL)) {
+		c->btree_cache_alloc_lock = current;
+	} else if (c->btree_cache_alloc_lock != current) {
 		if (op)
 			prepare_to_wait(&c->btree_cache_wait, &op->wait,
 					TASK_UNINTERRUPTIBLE);
+		spin_unlock(&c->btree_cannibalize_lock);
 		return -EINTR;
 	}
+	spin_unlock(&c->btree_cannibalize_lock);
 
 	return 0;
 }
@@ -927,10 +936,12 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op,
  */
 static void bch_cannibalize_unlock(struct cache_set *c)
 {
+	spin_lock(&c->btree_cannibalize_lock);
 	if (c->btree_cache_alloc_lock == current) {
 		c->btree_cache_alloc_lock = NULL;
 		wake_up(&c->btree_cache_wait);
 	}
+	spin_unlock(&c->btree_cannibalize_lock);
 }
 
 static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op,
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index c12cd809ab19..0164a1fe94a9 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -45,7 +45,6 @@ void closure_sub(struct closure *cl, int v)
 {
 	closure_put_after_sub(cl, atomic_sub_return(v, &cl->remaining));
 }
-EXPORT_SYMBOL(closure_sub);
 
 /*
  * closure_put - decrement a closure's refcount
@@ -54,7 +53,6 @@ void closure_put(struct closure *cl)
 {
 	closure_put_after_sub(cl, atomic_dec_return(&cl->remaining));
 }
-EXPORT_SYMBOL(closure_put);
 
 /*
  * closure_wake_up - wake up all closures on a wait list, without memory barrier
@@ -76,7 +74,6 @@ void __closure_wake_up(struct closure_waitlist *wait_list)
 		closure_sub(cl, CLOSURE_WAITING + 1);
 	}
 }
-EXPORT_SYMBOL(__closure_wake_up);
 
 /**
  * closure_wait - add a closure to a waitlist
@@ -96,7 +93,6 @@ bool closure_wait(struct closure_waitlist *waitlist, struct closure *cl)
 
 	return true;
 }
-EXPORT_SYMBOL(closure_wait);
 
 struct closure_syncer {
 	struct task_struct	*task;
@@ -131,7 +127,6 @@ void __sched __closure_sync(struct closure *cl)
 
 	__set_current_state(TASK_RUNNING);
 }
-EXPORT_SYMBOL(__closure_sync);
 
 #ifdef CONFIG_BCACHE_CLOSURES_DEBUG
 
@@ -149,7 +144,6 @@ void closure_debug_create(struct closure *cl)
 	list_add(&cl->all, &closure_list);
 	spin_unlock_irqrestore(&closure_list_lock, flags);
 }
-EXPORT_SYMBOL(closure_debug_create);
 
 void closure_debug_destroy(struct closure *cl)
 {
@@ -162,7 +156,6 @@ void closure_debug_destroy(struct closure *cl)
 	list_del(&cl->all);
 	spin_unlock_irqrestore(&closure_list_lock, flags);
 }
-EXPORT_SYMBOL(closure_debug_destroy);
 
 static struct dentry *closure_debug;
 
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 41adcd1546f1..73478a91a342 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -62,18 +62,6 @@ static void bch_data_insert_keys(struct closure *cl)
 	struct bkey *replace_key = op->replace ? &op->replace_key : NULL;
 	int ret;
 
-	/*
-	 * If we're looping, might already be waiting on
-	 * another journal write - can't wait on more than one journal write at
-	 * a time
-	 *
-	 * XXX: this looks wrong
-	 */
-#if 0
-	while (atomic_read(&s->cl.remaining) & CLOSURE_WAITING)
-		closure_sync(&s->cl);
-#endif
-
 	if (!op->replace)
 		journal_ref = bch_journal(op->c, &op->insert_keys,
 					  op->flush_journal ? cl : NULL);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 20ed838e9413..77e9869345e7 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -92,10 +92,11 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 	pr_debug("read sb version %llu, flags %llu, seq %llu, journal size %u",
 		 sb->version, sb->flags, sb->seq, sb->keys);
 
-	err = "Not a bcache superblock";
+	err = "Not a bcache superblock (bad offset)";
 	if (sb->offset != SB_SECTOR)
 		goto err;
 
+	err = "Not a bcache superblock (bad magic)";
 	if (memcmp(sb->magic, bcache_magic, 16))
 		goto err;
 
@@ -529,12 +530,29 @@ static void prio_io(struct cache *ca, uint64_t bucket, int op,
 	closure_sync(cl);
 }
 
-void bch_prio_write(struct cache *ca)
+int bch_prio_write(struct cache *ca, bool wait)
 {
 	int i;
 	struct bucket *b;
 	struct closure cl;
 
+	pr_debug("free_prio=%zu, free_none=%zu, free_inc=%zu",
+		 fifo_used(&ca->free[RESERVE_PRIO]),
+		 fifo_used(&ca->free[RESERVE_NONE]),
+		 fifo_used(&ca->free_inc));
+
+	/*
+	 * Pre-check if there are enough free buckets. In the non-blocking
+	 * scenario it's better to fail early rather than starting to allocate
+	 * buckets and do a cleanup later in case of failure.
+	 */
+	if (!wait) {
+		size_t avail = fifo_used(&ca->free[RESERVE_PRIO]) +
+			       fifo_used(&ca->free[RESERVE_NONE]);
+		if (prio_buckets(ca) > avail)
+			return -ENOMEM;
+	}
+
 	closure_init_stack(&cl);
 
 	lockdep_assert_held(&ca->set->bucket_lock);
@@ -544,9 +562,6 @@ void bch_prio_write(struct cache *ca)
 	atomic_long_add(ca->sb.bucket_size * prio_buckets(ca),
 			&ca->meta_sectors_written);
 
-	//pr_debug("free %zu, free_inc %zu, unused %zu", fifo_used(&ca->free),
-	//	 fifo_used(&ca->free_inc), fifo_used(&ca->unused));
-
 	for (i = prio_buckets(ca) - 1; i >= 0; --i) {
 		long bucket;
 		struct prio_set *p = ca->disk_buckets;
@@ -564,7 +579,7 @@ void bch_prio_write(struct cache *ca)
 		p->magic	= pset_magic(&ca->sb);
 		p->csum		= bch_crc64(&p->magic, bucket_bytes(ca) - 8);
 
-		bucket = bch_bucket_alloc(ca, RESERVE_PRIO, true);
+		bucket = bch_bucket_alloc(ca, RESERVE_PRIO, wait);
 		BUG_ON(bucket == -1);
 
 		mutex_unlock(&ca->set->bucket_lock);
@@ -593,6 +608,7 @@ void bch_prio_write(struct cache *ca)
 
 		ca->prio_last_buckets[i] = ca->prio_buckets[i];
 	}
+	return 0;
 }
 
 static void prio_read(struct cache *ca, uint64_t bucket)
@@ -761,20 +777,28 @@ static inline int idx_to_first_minor(int idx)
 
 static void bcache_device_free(struct bcache_device *d)
 {
+	struct gendisk *disk = d->disk;
+
 	lockdep_assert_held(&bch_register_lock);
 
-	pr_info("%s stopped", d->disk->disk_name);
+	if (disk)
+		pr_info("%s stopped", disk->disk_name);
+	else
+		pr_err("bcache device (NULL gendisk) stopped");
 
 	if (d->c)
 		bcache_device_detach(d);
-	if (d->disk && d->disk->flags & GENHD_FL_UP)
-		del_gendisk(d->disk);
-	if (d->disk && d->disk->queue)
-		blk_cleanup_queue(d->disk->queue);
-	if (d->disk) {
+
+	if (disk) {
+		if (disk->flags & GENHD_FL_UP)
+			del_gendisk(disk);
+
+		if (disk->queue)
+			blk_cleanup_queue(disk->queue);
+
 		ida_simple_remove(&bcache_device_idx,
-				  first_minor_to_idx(d->disk->first_minor));
-		put_disk(d->disk);
+				  first_minor_to_idx(disk->first_minor));
+		put_disk(disk);
 	}
 
 	bioset_exit(&d->bio_split);
@@ -1769,6 +1793,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	sema_init(&c->sb_write_mutex, 1);
 	mutex_init(&c->bucket_lock);
 	init_waitqueue_head(&c->btree_cache_wait);
+	spin_lock_init(&c->btree_cannibalize_lock);
 	init_waitqueue_head(&c->bucket_wait);
 	init_waitqueue_head(&c->gc_wait);
 	sema_init(&c->uuid_write_mutex, 1);
@@ -1809,6 +1834,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	c->congested_read_threshold_us	= 2000;
 	c->congested_write_threshold_us	= 20000;
 	c->error_limit	= DEFAULT_IO_ERROR_LIMIT;
+	c->idle_max_writeback_rate_enabled = 1;
 	WARN_ON(test_and_clear_bit(CACHE_SET_IO_DISABLE, &c->flags));
 
 	return c;
@@ -1954,7 +1980,7 @@ static int run_cache_set(struct cache_set *c)
 
 		mutex_lock(&c->bucket_lock);
 		for_each_cache(ca, c, i)
-			bch_prio_write(ca);
+			bch_prio_write(ca, true);
 		mutex_unlock(&c->bucket_lock);
 
 		err = "cannot allocate new UUID bucket";
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 627dcea0f5b6..733e2ddf3c78 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -134,6 +134,7 @@ rw_attribute(expensive_debug_checks);
 rw_attribute(cache_replacement_policy);
 rw_attribute(btree_shrinker_disabled);
 rw_attribute(copy_gc_enabled);
+rw_attribute(idle_max_writeback_rate);
 rw_attribute(gc_after_writeback);
 rw_attribute(size);
 
@@ -747,6 +748,8 @@ SHOW(__bch_cache_set)
 	sysfs_printf(gc_always_rewrite,		"%i", c->gc_always_rewrite);
 	sysfs_printf(btree_shrinker_disabled,	"%i", c->shrinker_disabled);
 	sysfs_printf(copy_gc_enabled,		"%i", c->copy_gc_enabled);
+	sysfs_printf(idle_max_writeback_rate,	"%i",
+		     c->idle_max_writeback_rate_enabled);
 	sysfs_printf(gc_after_writeback,	"%i", c->gc_after_writeback);
 	sysfs_printf(io_disable,		"%i",
 		     test_bit(CACHE_SET_IO_DISABLE, &c->flags));
@@ -864,6 +867,9 @@ STORE(__bch_cache_set)
 	sysfs_strtoul_bool(gc_always_rewrite,	c->gc_always_rewrite);
 	sysfs_strtoul_bool(btree_shrinker_disabled, c->shrinker_disabled);
 	sysfs_strtoul_bool(copy_gc_enabled,	c->copy_gc_enabled);
+	sysfs_strtoul_bool(idle_max_writeback_rate,
+			   c->idle_max_writeback_rate_enabled);
+
 	/*
 	 * write gc_after_writeback here may overwrite an already set
 	 * BCH_DO_AUTO_GC, it doesn't matter because this flag will be
@@ -954,6 +960,7 @@ static struct attribute *bch_cache_set_internal_files[] = {
 	&sysfs_gc_always_rewrite,
 	&sysfs_btree_shrinker_disabled,
 	&sysfs_copy_gc_enabled,
+	&sysfs_idle_max_writeback_rate,
 	&sysfs_gc_after_writeback,
 	&sysfs_io_disable,
 	&sysfs_cutoff_writeback,
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index d60268fe49e1..4a40f9eadeaf 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -122,6 +122,10 @@ static void __update_writeback_rate(struct cached_dev *dc)
 static bool set_at_max_writeback_rate(struct cache_set *c,
 				       struct cached_dev *dc)
 {
+	/* Don't sst max writeback rate if it is disabled */
+	if (!c->idle_max_writeback_rate_enabled)
+		return false;
+
 	/* Don't set max writeback rate if gc is running */
 	if (!c->gc_mark_valid)
 		return false;
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 2900fbde89b3..76587e9af0ef 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -280,7 +280,7 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio)
 	struct flakey_c *fc = ti->private;
 
 	bio_set_dev(bio, fc->dev->bdev);
-	if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET)
+	if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio)))
 		bio->bi_iter.bi_sector =
 			flakey_map_sector(ti, bio->bi_iter.bi_sector);
 }
@@ -322,8 +322,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
 	pb->bio_submitted = false;
 
-	/* Do not fail reset zone */
-	if (bio_op(bio) == REQ_OP_ZONE_RESET)
+	if (op_is_zone_mgmt(bio_op(bio)))
 		goto map_bio;
 
 	/* Are we alive ? */
@@ -384,7 +383,7 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio,
 	struct flakey_c *fc = ti->private;
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
 
-	if (bio_op(bio) == REQ_OP_ZONE_RESET)
+	if (op_is_zone_mgmt(bio_op(bio)))
 		return DM_ENDIO_DONE;
 
 	if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index ecefe6703736..97acafd48c85 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -90,7 +90,7 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio)
 	struct linear_c *lc = ti->private;
 
 	bio_set_dev(bio, lc->dev->bdev);
-	if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET)
+	if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio)))
 		bio->bi_iter.bi_sector =
 			linear_map_sector(ti, bio->bi_iter.bi_sector);
 }
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1a5e328c443a..bc143c1b2333 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1174,7 +1174,8 @@ static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
- * allowed for all bio types except REQ_PREFLUSH and REQ_OP_ZONE_RESET.
+ * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_RESET,
+ * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE and REQ_OP_ZONE_FINISH.
  *
  * dm_accept_partial_bio informs the dm that the target only wants to process
  * additional n_sectors sectors of the bio and the rest of the data should be
@@ -1627,7 +1628,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 		ci.sector_count = 0;
 		error = __send_empty_flush(&ci);
 		/* dec_pending submits any data associated with flush */
-	} else if (bio_op(bio) == REQ_OP_ZONE_RESET) {
+	} else if (op_is_zone_mgmt(bio_op(bio))) {
 		ci.bio = bio;
 		ci.sector_count = 0;
 		error = __split_and_process_non_flush(&ci);
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index b092c7b5282f..3ad18246fcb3 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -2139,6 +2139,7 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 		memcpy(page_address(store.sb_page),
 		       page_address(bitmap->storage.sb_page),
 		       sizeof(bitmap_super_t));
+	spin_lock_irq(&bitmap->counts.lock);
 	md_bitmap_file_unmap(&bitmap->storage);
 	bitmap->storage = store;
 
@@ -2154,7 +2155,6 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 	blocks = min(old_counts.chunks << old_counts.chunkshift,
 		     chunks << chunkshift);
 
-	spin_lock_irq(&bitmap->counts.lock);
 	/* For cluster raid, need to pre-allocate bitmap */
 	if (mddev_is_clustered(bitmap->mddev)) {
 		unsigned long page;
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index c766c559d36d..26c75c0199fa 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -244,10 +244,9 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 	sector_t start_sector, end_sector, data_offset;
 	sector_t bio_sector = bio->bi_iter.bi_sector;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	tmp_dev = which_dev(mddev, bio_sector);
 	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c
index 6780938d2991..152f9e65a226 100644
--- a/drivers/md/md-multipath.c
+++ b/drivers/md/md-multipath.c
@@ -104,10 +104,9 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
 	struct multipath_bh * mp_bh;
 	struct multipath_info *multipath;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	mp_bh = mempool_alloc(&conf->pool, GFP_NOIO);
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 1be7abeb24fd..805b33e27496 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -550,7 +550,13 @@ static void md_submit_flush_data(struct work_struct *ws)
 	}
 }
 
-void md_flush_request(struct mddev *mddev, struct bio *bio)
+/*
+ * Manages consolidation of flushes and submitting any flushes needed for
+ * a bio with REQ_PREFLUSH.  Returns true if the bio is finished or is
+ * being finished in another context.  Returns false if the flushing is
+ * complete but still needs the I/O portion of the bio to be processed.
+ */
+bool md_flush_request(struct mddev *mddev, struct bio *bio)
 {
 	ktime_t start = ktime_get_boottime();
 	spin_lock_irq(&mddev->lock);
@@ -575,9 +581,10 @@ void md_flush_request(struct mddev *mddev, struct bio *bio)
 			bio_endio(bio);
 		else {
 			bio->bi_opf &= ~REQ_PREFLUSH;
-			mddev->pers->make_request(mddev, bio);
+			return false;
 		}
 	}
+	return true;
 }
 EXPORT_SYMBOL(md_flush_request);
 
@@ -1098,6 +1105,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
 	mdp_super_t *sb;
 	int ret;
+	bool spare_disk = true;
 
 	/*
 	 * Calculate the position of the superblock (512byte sectors),
@@ -1148,8 +1156,18 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 	else
 		rdev->desc_nr = sb->this_disk.number;
 
+	/* not spare disk, or LEVEL_MULTIPATH */
+	if (sb->level == LEVEL_MULTIPATH ||
+		(rdev->desc_nr >= 0 &&
+		 sb->disks[rdev->desc_nr].state &
+		 ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE))))
+		spare_disk = false;
+
 	if (!refdev) {
-		ret = 1;
+		if (!spare_disk)
+			ret = 1;
+		else
+			ret = 0;
 	} else {
 		__u64 ev1, ev2;
 		mdp_super_t *refsb = page_address(refdev->sb_page);
@@ -1165,7 +1183,8 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 		}
 		ev1 = md_event(sb);
 		ev2 = md_event(refsb);
-		if (ev1 > ev2)
+
+		if (!spare_disk && ev1 > ev2)
 			ret = 1;
 		else
 			ret = 0;
@@ -1525,6 +1544,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	sector_t sectors;
 	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
 	int bmask;
+	bool spare_disk = true;
 
 	/*
 	 * Calculate the position of the superblock in 512byte sectors.
@@ -1658,8 +1678,19 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	    sb->level != 0)
 		return -EINVAL;
 
+	/* not spare disk, or LEVEL_MULTIPATH */
+	if (sb->level == cpu_to_le32(LEVEL_MULTIPATH) ||
+		(rdev->desc_nr >= 0 &&
+		rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
+		(le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX ||
+		 le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL)))
+		spare_disk = false;
+
 	if (!refdev) {
-		ret = 1;
+		if (!spare_disk)
+			ret = 1;
+		else
+			ret = 0;
 	} else {
 		__u64 ev1, ev2;
 		struct mdp_superblock_1 *refsb = page_address(refdev->sb_page);
@@ -1676,7 +1707,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 		ev1 = le64_to_cpu(sb->events);
 		ev2 = le64_to_cpu(refsb->events);
 
-		if (ev1 > ev2)
+		if (!spare_disk && ev1 > ev2)
 			ret = 1;
 		else
 			ret = 0;
@@ -3597,7 +3628,7 @@ abort_free:
  * Check a full RAID array for plausibility
  */
 
-static void analyze_sbs(struct mddev *mddev)
+static int analyze_sbs(struct mddev *mddev)
 {
 	int i;
 	struct md_rdev *rdev, *freshest, *tmp;
@@ -3618,6 +3649,12 @@ static void analyze_sbs(struct mddev *mddev)
 			md_kick_rdev_from_array(rdev);
 		}
 
+	/* Cannot find a valid fresh disk */
+	if (!freshest) {
+		pr_warn("md: cannot find a valid disk\n");
+		return -EINVAL;
+	}
+
 	super_types[mddev->major_version].
 		validate_super(mddev, freshest);
 
@@ -3652,6 +3689,8 @@ static void analyze_sbs(struct mddev *mddev)
 			clear_bit(In_sync, &rdev->flags);
 		}
 	}
+
+	return 0;
 }
 
 /* Read a fixed-point number.
@@ -5570,7 +5609,9 @@ int md_run(struct mddev *mddev)
 	if (!mddev->raid_disks) {
 		if (!mddev->persistent)
 			return -EINVAL;
-		analyze_sbs(mddev);
+		err = analyze_sbs(mddev);
+		if (err)
+			return -EINVAL;
 	}
 
 	if (mddev->level != LEVEL_NONE)
diff --git a/drivers/md/md.h b/drivers/md/md.h
index c5e3ff398b59..5f86f8adb0a4 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -550,7 +550,7 @@ struct md_personality
 	int level;
 	struct list_head list;
 	struct module *owner;
-	bool (*make_request)(struct mddev *mddev, struct bio *bio);
+	bool __must_check (*make_request)(struct mddev *mddev, struct bio *bio);
 	/*
 	 * start up works that do NOT require md_thread. tasks that
 	 * requires md_thread should go into start()
@@ -703,7 +703,7 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_finish_reshape(struct mddev *mddev);
 
 extern int mddev_congested(struct mddev *mddev, int bits);
-extern void md_flush_request(struct mddev *mddev, struct bio *bio);
+extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 			   sector_t sector, int size, struct page *page);
 extern int md_super_wait(struct mddev *mddev);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 1e772287b1c8..b7c20979bd19 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -575,10 +575,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 	unsigned chunk_sects;
 	unsigned sectors;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) {
 		raid0_handle_discard(mddev, bio);
@@ -615,7 +614,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 		tmp_dev = map_sector(mddev, zone, sector, &sector);
 		break;
 	default:
-		WARN("md/raid0:%s: Invalid layout\n", mdname(mddev));
+		WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev));
 		bio_io_error(bio);
 		return true;
 	}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 0466ee2453b4..a409ab6f30bc 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -819,6 +819,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio)
 		else
 			generic_make_request(bio);
 		bio = next;
+		cond_resched();
 	}
 }
 
@@ -1567,10 +1568,9 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 {
 	sector_t sectors;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	/*
 	 * There is a limit to the maximum size, but
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 299c7b1c9718..ec136e44aef7 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -191,7 +191,7 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
 
 out_free_pages:
 	while (--j >= 0)
-		resync_free_pages(&rps[j * 2]);
+		resync_free_pages(&rps[j]);
 
 	j = 0;
 out_free_bio:
@@ -1525,10 +1525,9 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 	int chunk_sects = chunk_mask + 1;
 	int sectors = bio_sectors(bio);
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	if (!md_write_start(mddev, bio))
 		return false;
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index 18a4064a61a8..cab5b1352892 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -1404,7 +1404,7 @@ int ppl_init_log(struct r5conf *conf)
 	atomic64_set(&ppl_conf->seq, 0);
 	INIT_LIST_HEAD(&ppl_conf->no_mem_stripes);
 	spin_lock_init(&ppl_conf->no_mem_stripes_lock);
-	ppl_conf->write_hint = RWF_WRITE_LIFE_NOT_SET;
+	ppl_conf->write_hint = RWH_WRITE_LIFE_NOT_SET;
 
 	if (!mddev->external) {
 		ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid));
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 223e97ab27e6..f0fc538bfe59 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1134,7 +1134,7 @@ again:
 			bi->bi_iter.bi_size = STRIPE_SIZE;
 			bi->bi_write_hint = sh->dev[i].write_hint;
 			if (!rrdev)
-				sh->dev[i].write_hint = RWF_WRITE_LIFE_NOT_SET;
+				sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET;
 			/*
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
@@ -1187,7 +1187,7 @@ again:
 			rbi->bi_io_vec[0].bv_offset = 0;
 			rbi->bi_iter.bi_size = STRIPE_SIZE;
 			rbi->bi_write_hint = sh->dev[i].write_hint;
-			sh->dev[i].write_hint = RWF_WRITE_LIFE_NOT_SET;
+			sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET;
 			/*
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
@@ -5592,8 +5592,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 		if (ret == 0)
 			return true;
 		if (ret == -ENODEV) {
-			md_flush_request(mddev, bi);
-			return true;
+			if (md_flush_request(mddev, bi))
+				return true;
 		}
 		/* ret == -EAGAIN, fallback */
 		/*