Merge tag 'for-5.5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "User visible changes:
   - new block group profiles: RAID1 with 3- and 4- copies
       - RAID1 in btrfs has always 2 copies, now add support for 3 and 4
       - this is an incompat feature (named RAID1C34)
       - recommended use of RAID1C3 is replacement of RAID6 profile on
         metadata, this brings a more reliable resiliency against 2
         device loss/damage

   - support for new checksums
       - per-filesystem, set at mkfs time
       - fast hash (crc32c successor): xxhash, 64bit digest
       - strong hashes (both 256bit): sha256 (slower, FIPS), blake2b
         (faster)
       - the blake2b module goes via the crypto tree, btrfs.ko has a
         soft dependency

   - speed up lseek, don't take inode locks unnecessarily, this can
     speed up parallel SEEK_CUR/SEEK_SET/SEEK_END by 80%

   - send:
       - allow clone operations within the same file
       - limit maximum number of sent clone references to avoid slow
         backref walking

   - error message improvements: device scan prints process name and PID

  Core changes:
   - cleanups
       - remove unique workqueue helpers, used to provide a way to avoid
         deadlocks in the workqueue code, now done in a simpler way
       - remove lots of indirect function calls in compression code
       - extent IO tree code moved out of extent_io.c
       - cleanup backup superblock handling at mount time
       - transaction life cycle documentation and cleanups
       - locking code cleanups, annotations and documentation
       - add more cold, const, pure function attributes
       - removal of unused or redundant struct members or variables

   - new tree-checker sanity tests
       - try to detect missing INODE_ITEM, cross-reference checks of
         DIR_ITEM, DIR_INDEX, INODE_REF, and XATTR_* items

   - remove own bio scheduling code (used to avoid checksum submissions
     being stuck behind other IO), replaced by cgroup controller-based
     code to allow better control and avoid priority inversions in cases
     where the custom and cgroup scheduling disagreed

  Fixes:
   - avoid getting stuck during cyclic writebacks

   - fix trimming of ranges crossing block group boundaries

   - fix rename exchange on subvolumes, all involved subvolumes need to
     be recorded in the transaction"

* tag 'for-5.5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (137 commits)
  btrfs: drop bdev argument from submit_extent_page
  btrfs: remove extent_map::bdev
  btrfs: drop bio_set_dev where not needed
  btrfs: get bdev directly from fs_devices in submit_extent_page
  btrfs: record all roots for rename exchange on a subvol
  Btrfs: fix block group remaining RO forever after error during device replace
  btrfs: scrub: Don't check free space before marking a block group RO
  btrfs: change btrfs_fs_devices::rotating to bool
  btrfs: change btrfs_fs_devices::seeding to bool
  btrfs: rename btrfs_block_group_cache
  btrfs: block-group: Reuse the item key from caller of read_one_block_group()
  btrfs: block-group: Refactor btrfs_read_block_groups()
  btrfs: document extent buffer locking
  btrfs: access eb::blocking_writers according to ACCESS_ONCE policies
  btrfs: set blocking_writers directly, no increment or decrement
  btrfs: merge blocking_writers branches in btrfs_tree_read_lock
  btrfs: drop incompat bit for raid1c34 after last block group is gone
  btrfs: add incompat for raid1 with 3, 4 copies
  btrfs: add support for 4-copy replication (raid1c4)
  btrfs: add support for 3-copy replication (raid1c3)
  ...

63 files changed, 2694 insertions, 2546 deletions

diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index 38651fae7f21..75b6d10c9845 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -5,6 +5,8 @@ config BTRFS_FS
 	select CRYPTO
 	select CRYPTO_CRC32C
 	select LIBCRC32C
+	select CRYPTO_XXHASH
+	select CRYPTO_SHA256
 	select ZLIB_INFLATE
 	select ZLIB_DEFLATE
 	select LZO_COMPRESS
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 2e9e13ffbd08..1d32a07bb2d1 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -53,24 +53,12 @@ struct btrfs_workqueue {
 	struct __btrfs_workqueue *high;
 };
 
-static void normal_work_helper(struct btrfs_work *work);
-
-#define BTRFS_WORK_HELPER(name)					\
-noinline_for_stack void btrfs_##name(struct work_struct *arg)		\
-{									\
-	struct btrfs_work *work = container_of(arg, struct btrfs_work,	\
-					       normal_work);		\
-	normal_work_helper(work);					\
-}
-
-struct btrfs_fs_info *
-btrfs_workqueue_owner(const struct __btrfs_workqueue *wq)
+struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq)
 {
 	return wq->fs_info;
 }
 
-struct btrfs_fs_info *
-btrfs_work_owner(const struct btrfs_work *work)
+struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work)
 {
 	return work->wq->fs_info;
 }
@@ -89,29 +77,6 @@ bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq)
 	return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2;
 }
 
-BTRFS_WORK_HELPER(worker_helper);
-BTRFS_WORK_HELPER(delalloc_helper);
-BTRFS_WORK_HELPER(flush_delalloc_helper);
-BTRFS_WORK_HELPER(cache_helper);
-BTRFS_WORK_HELPER(submit_helper);
-BTRFS_WORK_HELPER(fixup_helper);
-BTRFS_WORK_HELPER(endio_helper);
-BTRFS_WORK_HELPER(endio_meta_helper);
-BTRFS_WORK_HELPER(endio_meta_write_helper);
-BTRFS_WORK_HELPER(endio_raid56_helper);
-BTRFS_WORK_HELPER(endio_repair_helper);
-BTRFS_WORK_HELPER(rmw_helper);
-BTRFS_WORK_HELPER(endio_write_helper);
-BTRFS_WORK_HELPER(freespace_write_helper);
-BTRFS_WORK_HELPER(delayed_meta_helper);
-BTRFS_WORK_HELPER(readahead_helper);
-BTRFS_WORK_HELPER(qgroup_rescan_helper);
-BTRFS_WORK_HELPER(extent_refs_helper);
-BTRFS_WORK_HELPER(scrub_helper);
-BTRFS_WORK_HELPER(scrubwrc_helper);
-BTRFS_WORK_HELPER(scrubnc_helper);
-BTRFS_WORK_HELPER(scrubparity_helper);
-
 static struct __btrfs_workqueue *
 __btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name,
 			unsigned int flags, int limit_active, int thresh)
@@ -252,16 +217,16 @@ out:
 	}
 }
 
-static void run_ordered_work(struct __btrfs_workqueue *wq)
+static void run_ordered_work(struct __btrfs_workqueue *wq,
+			     struct btrfs_work *self)
 {
 	struct list_head *list = &wq->ordered_list;
 	struct btrfs_work *work;
 	spinlock_t *lock = &wq->list_lock;
 	unsigned long flags;
+	bool free_self = false;
 
 	while (1) {
-		void *wtag;
-
 		spin_lock_irqsave(lock, flags);
 		if (list_empty(list))
 			break;
@@ -287,22 +252,53 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
 		list_del(&work->ordered_list);
 		spin_unlock_irqrestore(lock, flags);
 
-		/*
-		 * We don't want to call the ordered free functions with the
-		 * lock held though. Save the work as tag for the trace event,
-		 * because the callback could free the structure.
-		 */
-		wtag = work;
-		work->ordered_free(work);
-		trace_btrfs_all_work_done(wq->fs_info, wtag);
+		if (work == self) {
+			/*
+			 * This is the work item that the worker is currently
+			 * executing.
+			 *
+			 * The kernel workqueue code guarantees non-reentrancy
+			 * of work items. I.e., if a work item with the same
+			 * address and work function is queued twice, the second
+			 * execution is blocked until the first one finishes. A
+			 * work item may be freed and recycled with the same
+			 * work function; the workqueue code assumes that the
+			 * original work item cannot depend on the recycled work
+			 * item in that case (see find_worker_executing_work()).
+			 *
+			 * Note that different types of Btrfs work can depend on
+			 * each other, and one type of work on one Btrfs
+			 * filesystem may even depend on the same type of work
+			 * on another Btrfs filesystem via, e.g., a loop device.
+			 * Therefore, we must not allow the current work item to
+			 * be recycled until we are really done, otherwise we
+			 * break the above assumption and can deadlock.
+			 */
+			free_self = true;
+		} else {
+			/*
+			 * We don't want to call the ordered free functions with
+			 * the lock held.
+			 */
+			work->ordered_free(work);
+			/* NB: work must not be dereferenced past this point. */
+			trace_btrfs_all_work_done(wq->fs_info, work);
+		}
 	}
 	spin_unlock_irqrestore(lock, flags);
+
+	if (free_self) {
+		self->ordered_free(self);
+		/* NB: self must not be dereferenced past this point. */
+		trace_btrfs_all_work_done(wq->fs_info, self);
+	}
 }
 
-static void normal_work_helper(struct btrfs_work *work)
+static void btrfs_work_helper(struct work_struct *normal_work)
 {
+	struct btrfs_work *work = container_of(normal_work, struct btrfs_work,
+					       normal_work);
 	struct __btrfs_workqueue *wq;
-	void *wtag;
 	int need_order = 0;
 
 	/*
@@ -316,29 +312,26 @@ static void normal_work_helper(struct btrfs_work *work)
 	if (work->ordered_func)
 		need_order = 1;
 	wq = work->wq;
-	/* Safe for tracepoints in case work gets freed by the callback */
-	wtag = work;
 
 	trace_btrfs_work_sched(work);
 	thresh_exec_hook(wq);
 	work->func(work);
 	if (need_order) {
 		set_bit(WORK_DONE_BIT, &work->flags);
-		run_ordered_work(wq);
+		run_ordered_work(wq, work);
+	} else {
+		/* NB: work must not be dereferenced past this point. */
+		trace_btrfs_all_work_done(wq->fs_info, work);
 	}
-	if (!need_order)
-		trace_btrfs_all_work_done(wq->fs_info, wtag);
 }
 
-void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
-		     btrfs_func_t func,
-		     btrfs_func_t ordered_func,
-		     btrfs_func_t ordered_free)
+void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
+		     btrfs_func_t ordered_func, btrfs_func_t ordered_free)
 {
 	work->func = func;
 	work->ordered_func = ordered_func;
 	work->ordered_free = ordered_free;
-	INIT_WORK(&work->normal_work, uniq_func);
+	INIT_WORK(&work->normal_work, btrfs_work_helper);
 	INIT_LIST_HEAD(&work->ordered_list);
 	work->flags = 0;
 }
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 7861c9feba5f..a4434301d84d 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -29,49 +29,20 @@ struct btrfs_work {
 	unsigned long flags;
 };
 
-#define BTRFS_WORK_HELPER_PROTO(name)					\
-void btrfs_##name(struct work_struct *arg)
-
-BTRFS_WORK_HELPER_PROTO(worker_helper);
-BTRFS_WORK_HELPER_PROTO(delalloc_helper);
-BTRFS_WORK_HELPER_PROTO(flush_delalloc_helper);
-BTRFS_WORK_HELPER_PROTO(cache_helper);
-BTRFS_WORK_HELPER_PROTO(submit_helper);
-BTRFS_WORK_HELPER_PROTO(fixup_helper);
-BTRFS_WORK_HELPER_PROTO(endio_helper);
-BTRFS_WORK_HELPER_PROTO(endio_meta_helper);
-BTRFS_WORK_HELPER_PROTO(endio_meta_write_helper);
-BTRFS_WORK_HELPER_PROTO(endio_raid56_helper);
-BTRFS_WORK_HELPER_PROTO(endio_repair_helper);
-BTRFS_WORK_HELPER_PROTO(rmw_helper);
-BTRFS_WORK_HELPER_PROTO(endio_write_helper);
-BTRFS_WORK_HELPER_PROTO(freespace_write_helper);
-BTRFS_WORK_HELPER_PROTO(delayed_meta_helper);
-BTRFS_WORK_HELPER_PROTO(readahead_helper);
-BTRFS_WORK_HELPER_PROTO(qgroup_rescan_helper);
-BTRFS_WORK_HELPER_PROTO(extent_refs_helper);
-BTRFS_WORK_HELPER_PROTO(scrub_helper);
-BTRFS_WORK_HELPER_PROTO(scrubwrc_helper);
-BTRFS_WORK_HELPER_PROTO(scrubnc_helper);
-BTRFS_WORK_HELPER_PROTO(scrubparity_helper);
-
-
 struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
 					      const char *name,
 					      unsigned int flags,
 					      int limit_active,
 					      int thresh);
-void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper,
-		     btrfs_func_t func,
-		     btrfs_func_t ordered_func,
-		     btrfs_func_t ordered_free);
+void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
+		     btrfs_func_t ordered_func, btrfs_func_t ordered_free);
 void btrfs_queue_work(struct btrfs_workqueue *wq,
 		      struct btrfs_work *work);
 void btrfs_destroy_workqueue(struct btrfs_workqueue *wq);
 void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max);
 void btrfs_set_work_high_priority(struct btrfs_work *work);
-struct btrfs_fs_info *btrfs_work_owner(const struct btrfs_work *work);
-struct btrfs_fs_info *btrfs_workqueue_owner(const struct __btrfs_workqueue *wq);
+struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work);
+struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq);
 bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq);
 
 #endif
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 670700cb1110..6934a5b8708f 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -120,12 +120,12 @@ u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags)
 	return get_alloc_profile(fs_info, orig_flags);
 }
 
-void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_get_block_group(struct btrfs_block_group *cache)
 {
 	atomic_inc(&cache->count);
 }
 
-void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_put_block_group(struct btrfs_block_group *cache)
 {
 	if (atomic_dec_and_test(&cache->count)) {
 		WARN_ON(cache->pinned > 0);
@@ -149,22 +149,21 @@ void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
  * This adds the block group to the fs_info rb tree for the block group cache
  */
 static int btrfs_add_block_group_cache(struct btrfs_fs_info *info,
-				struct btrfs_block_group_cache *block_group)
+				       struct btrfs_block_group *block_group)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 
 	spin_lock(&info->block_group_cache_lock);
 	p = &info->block_group_cache_tree.rb_node;
 
 	while (*p) {
 		parent = *p;
-		cache = rb_entry(parent, struct btrfs_block_group_cache,
-				 cache_node);
-		if (block_group->key.objectid < cache->key.objectid) {
+		cache = rb_entry(parent, struct btrfs_block_group, cache_node);
+		if (block_group->start < cache->start) {
 			p = &(*p)->rb_left;
-		} else if (block_group->key.objectid > cache->key.objectid) {
+		} else if (block_group->start > cache->start) {
 			p = &(*p)->rb_right;
 		} else {
 			spin_unlock(&info->block_group_cache_lock);
@@ -176,8 +175,8 @@ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info,
 	rb_insert_color(&block_group->cache_node,
 			&info->block_group_cache_tree);
 
-	if (info->first_logical_byte > block_group->key.objectid)
-		info->first_logical_byte = block_group->key.objectid;
+	if (info->first_logical_byte > block_group->start)
+		info->first_logical_byte = block_group->start;
 
 	spin_unlock(&info->block_group_cache_lock);
 
@@ -188,10 +187,10 @@ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info,
  * This will return the block group at or after bytenr if contains is 0, else
  * it will return the block group that contains the bytenr
  */
-static struct btrfs_block_group_cache *block_group_cache_tree_search(
+static struct btrfs_block_group *block_group_cache_tree_search(
 		struct btrfs_fs_info *info, u64 bytenr, int contains)
 {
-	struct btrfs_block_group_cache *cache, *ret = NULL;
+	struct btrfs_block_group *cache, *ret = NULL;
 	struct rb_node *n;
 	u64 end, start;
 
@@ -199,13 +198,12 @@ static struct btrfs_block_group_cache *block_group_cache_tree_search(
 	n = info->block_group_cache_tree.rb_node;
 
 	while (n) {
-		cache = rb_entry(n, struct btrfs_block_group_cache,
-				 cache_node);
-		end = cache->key.objectid + cache->key.offset - 1;
-		start = cache->key.objectid;
+		cache = rb_entry(n, struct btrfs_block_group, cache_node);
+		end = cache->start + cache->length - 1;
+		start = cache->start;
 
 		if (bytenr < start) {
-			if (!contains && (!ret || start < ret->key.objectid))
+			if (!contains && (!ret || start < ret->start))
 				ret = cache;
 			n = n->rb_left;
 		} else if (bytenr > start) {
@@ -221,8 +219,8 @@ static struct btrfs_block_group_cache *block_group_cache_tree_search(
 	}
 	if (ret) {
 		btrfs_get_block_group(ret);
-		if (bytenr == 0 && info->first_logical_byte > ret->key.objectid)
-			info->first_logical_byte = ret->key.objectid;
+		if (bytenr == 0 && info->first_logical_byte > ret->start)
+			info->first_logical_byte = ret->start;
 	}
 	spin_unlock(&info->block_group_cache_lock);
 
@@ -232,7 +230,7 @@ static struct btrfs_block_group_cache *block_group_cache_tree_search(
 /*
  * Return the block group that starts at or after bytenr
  */
-struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
+struct btrfs_block_group *btrfs_lookup_first_block_group(
 		struct btrfs_fs_info *info, u64 bytenr)
 {
 	return block_group_cache_tree_search(info, bytenr, 0);
@@ -241,14 +239,14 @@ struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
 /*
  * Return the block group that contains the given bytenr
  */
-struct btrfs_block_group_cache *btrfs_lookup_block_group(
+struct btrfs_block_group *btrfs_lookup_block_group(
 		struct btrfs_fs_info *info, u64 bytenr)
 {
 	return block_group_cache_tree_search(info, bytenr, 1);
 }
 
-struct btrfs_block_group_cache *btrfs_next_block_group(
-		struct btrfs_block_group_cache *cache)
+struct btrfs_block_group *btrfs_next_block_group(
+		struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct rb_node *node;
@@ -257,7 +255,7 @@ struct btrfs_block_group_cache *btrfs_next_block_group(
 
 	/* If our block group was removed, we need a full search. */
 	if (RB_EMPTY_NODE(&cache->cache_node)) {
-		const u64 next_bytenr = cache->key.objectid + cache->key.offset;
+		const u64 next_bytenr = cache->start + cache->length;
 
 		spin_unlock(&fs_info->block_group_cache_lock);
 		btrfs_put_block_group(cache);
@@ -266,8 +264,7 @@ struct btrfs_block_group_cache *btrfs_next_block_group(
 	node = rb_next(&cache->cache_node);
 	btrfs_put_block_group(cache);
 	if (node) {
-		cache = rb_entry(node, struct btrfs_block_group_cache,
-				 cache_node);
+		cache = rb_entry(node, struct btrfs_block_group, cache_node);
 		btrfs_get_block_group(cache);
 	} else
 		cache = NULL;
@@ -277,7 +274,7 @@ struct btrfs_block_group_cache *btrfs_next_block_group(
 
 bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
 {
-	struct btrfs_block_group_cache *bg;
+	struct btrfs_block_group *bg;
 	bool ret = true;
 
 	bg = btrfs_lookup_block_group(fs_info, bytenr);
@@ -300,7 +297,7 @@ bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
 
 void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
 {
-	struct btrfs_block_group_cache *bg;
+	struct btrfs_block_group *bg;
 
 	bg = btrfs_lookup_block_group(fs_info, bytenr);
 	ASSERT(bg);
@@ -314,7 +311,7 @@ void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
 	btrfs_put_block_group(bg);
 }
 
-void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg)
+void btrfs_wait_nocow_writers(struct btrfs_block_group *bg)
 {
 	wait_var_event(&bg->nocow_writers, !atomic_read(&bg->nocow_writers));
 }
@@ -322,7 +319,7 @@ void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg)
 void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
 					const u64 start)
 {
-	struct btrfs_block_group_cache *bg;
+	struct btrfs_block_group *bg;
 
 	bg = btrfs_lookup_block_group(fs_info, start);
 	ASSERT(bg);
@@ -331,7 +328,7 @@ void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
 	btrfs_put_block_group(bg);
 }
 
-void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
+void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg)
 {
 	struct btrfs_space_info *space_info = bg->space_info;
 
@@ -357,7 +354,7 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
 }
 
 struct btrfs_caching_control *btrfs_get_caching_control(
-		struct btrfs_block_group_cache *cache)
+		struct btrfs_block_group *cache)
 {
 	struct btrfs_caching_control *ctl;
 
@@ -392,7 +389,7 @@ void btrfs_put_caching_control(struct btrfs_caching_control *ctl)
  * Callers of this must check if cache->cached == BTRFS_CACHE_ERROR before using
  * any of the information in this block group.
  */
-void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
+void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 					   u64 num_bytes)
 {
 	struct btrfs_caching_control *caching_ctl;
@@ -401,13 +398,13 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache
 	if (!caching_ctl)
 		return;
 
-	wait_event(caching_ctl->wait, btrfs_block_group_cache_done(cache) ||
+	wait_event(caching_ctl->wait, btrfs_block_group_done(cache) ||
 		   (cache->free_space_ctl->free_space >= num_bytes));
 
 	btrfs_put_caching_control(caching_ctl);
 }
 
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
+int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache)
 {
 	struct btrfs_caching_control *caching_ctl;
 	int ret = 0;
@@ -416,7 +413,7 @@ int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
 	if (!caching_ctl)
 		return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0;
 
-	wait_event(caching_ctl->wait, btrfs_block_group_cache_done(cache));
+	wait_event(caching_ctl->wait, btrfs_block_group_done(cache));
 	if (cache->cached == BTRFS_CACHE_ERROR)
 		ret = -EIO;
 	btrfs_put_caching_control(caching_ctl);
@@ -424,11 +421,11 @@ int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
 }
 
 #ifdef CONFIG_BTRFS_DEBUG
-static void fragment_free_space(struct btrfs_block_group_cache *block_group)
+static void fragment_free_space(struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
-	u64 start = block_group->key.objectid;
-	u64 len = block_group->key.offset;
+	u64 start = block_group->start;
+	u64 len = block_group->length;
 	u64 chunk = block_group->flags & BTRFS_BLOCK_GROUP_METADATA ?
 		fs_info->nodesize : fs_info->sectorsize;
 	u64 step = chunk << 1;
@@ -450,8 +447,7 @@ static void fragment_free_space(struct btrfs_block_group_cache *block_group)
  * used yet since their free space will be released as soon as the transaction
  * commits.
  */
-u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
-		       u64 start, u64 end)
+u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end)
 {
 	struct btrfs_fs_info *info = block_group->fs_info;
 	u64 extent_start, extent_end, size, total_added = 0;
@@ -491,7 +487,7 @@ u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
 
 static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
 {
-	struct btrfs_block_group_cache *block_group = caching_ctl->block_group;
+	struct btrfs_block_group *block_group = caching_ctl->block_group;
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct btrfs_root *extent_root = fs_info->extent_root;
 	struct btrfs_path *path;
@@ -507,7 +503,7 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
 	if (!path)
 		return -ENOMEM;
 
-	last = max_t(u64, block_group->key.objectid, BTRFS_SUPER_INFO_OFFSET);
+	last = max_t(u64, block_group->start, BTRFS_SUPER_INFO_OFFSET);
 
 #ifdef CONFIG_BTRFS_DEBUG
 	/*
@@ -587,13 +583,12 @@ next:
 			goto next;
 		}
 
-		if (key.objectid < block_group->key.objectid) {
+		if (key.objectid < block_group->start) {
 			path->slots[0]++;
 			continue;
 		}
 
-		if (key.objectid >= block_group->key.objectid +
-		    block_group->key.offset)
+		if (key.objectid >= block_group->start + block_group->length)
 			break;
 
 		if (key.type == BTRFS_EXTENT_ITEM_KEY ||
@@ -617,8 +612,7 @@ next:
 	ret = 0;
 
 	total_found += add_new_free_space(block_group, last,
-					  block_group->key.objectid +
-					  block_group->key.offset);
+				block_group->start + block_group->length);
 	caching_ctl->progress = (u64)-1;
 
 out:
@@ -628,7 +622,7 @@ out:
 
 static noinline void caching_thread(struct btrfs_work *work)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_caching_control *caching_ctl;
 	int ret;
@@ -656,8 +650,7 @@ static noinline void caching_thread(struct btrfs_work *work)
 
 		spin_lock(&block_group->space_info->lock);
 		spin_lock(&block_group->lock);
-		bytes_used = block_group->key.offset -
-			btrfs_block_group_used(&block_group->item);
+		bytes_used = block_group->length - block_group->used;
 		block_group->space_info->bytes_used += bytes_used >> 1;
 		spin_unlock(&block_group->lock);
 		spin_unlock(&block_group->space_info->lock);
@@ -677,8 +670,7 @@ static noinline void caching_thread(struct btrfs_work *work)
 	btrfs_put_block_group(block_group);
 }
 
-int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
-			    int load_cache_only)
+int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only)
 {
 	DEFINE_WAIT(wait);
 	struct btrfs_fs_info *fs_info = cache->fs_info;
@@ -693,10 +685,9 @@ int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
 	mutex_init(&caching_ctl->mutex);
 	init_waitqueue_head(&caching_ctl->wait);
 	caching_ctl->block_group = cache;
-	caching_ctl->progress = cache->key.objectid;
+	caching_ctl->progress = cache->start;
 	refcount_set(&caching_ctl->count, 1);
-	btrfs_init_work(&caching_ctl->work, btrfs_cache_helper,
-			caching_thread, NULL, NULL);
+	btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
 
 	spin_lock(&cache->lock);
 	/*
@@ -763,8 +754,7 @@ int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
 
 			spin_lock(&cache->space_info->lock);
 			spin_lock(&cache->lock);
-			bytes_used = cache->key.offset -
-				btrfs_block_group_used(&cache->item);
+			bytes_used = cache->length - cache->used;
 			cache->space_info->bytes_used += bytes_used >> 1;
 			spin_unlock(&cache->lock);
 			spin_unlock(&cache->space_info->lock);
@@ -833,27 +823,36 @@ static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
  *
  * - RAID56 - in case there's neither RAID5 nor RAID6 profile block group
  *            in the whole filesystem
+ *
+ * - RAID1C34 - same as above for RAID1C3 and RAID1C4 block groups
  */
 static void clear_incompat_bg_bits(struct btrfs_fs_info *fs_info, u64 flags)
 {
-	if (flags & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+	bool found_raid56 = false;
+	bool found_raid1c34 = false;
+
+	if ((flags & BTRFS_BLOCK_GROUP_RAID56_MASK) ||
+	    (flags & BTRFS_BLOCK_GROUP_RAID1C3) ||
+	    (flags & BTRFS_BLOCK_GROUP_RAID1C4)) {
 		struct list_head *head = &fs_info->space_info;
 		struct btrfs_space_info *sinfo;
 
 		list_for_each_entry_rcu(sinfo, head, list) {
-			bool found = false;
-
 			down_read(&sinfo->groups_sem);
 			if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID5]))
-				found = true;
+				found_raid56 = true;
 			if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID6]))
-				found = true;
+				found_raid56 = true;
+			if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID1C3]))
+				found_raid1c34 = true;
+			if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID1C4]))
+				found_raid1c34 = true;
 			up_read(&sinfo->groups_sem);
-
-			if (found)
-				return;
 		}
-		btrfs_clear_fs_incompat(fs_info, RAID56);
+		if (found_raid56)
+			btrfs_clear_fs_incompat(fs_info, RAID56);
+		if (found_raid1c34)
+			btrfs_clear_fs_incompat(fs_info, RAID1C34);
 	}
 }
 
@@ -863,7 +862,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_path *path;
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_free_cluster *cluster;
 	struct btrfs_root *tree_root = fs_info->tree_root;
 	struct btrfs_key key;
@@ -886,10 +885,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 * remove it.
 	 */
 	btrfs_free_excluded_extents(block_group);
-	btrfs_free_ref_tree_range(fs_info, block_group->key.objectid,
-				  block_group->key.offset);
+	btrfs_free_ref_tree_range(fs_info, block_group->start,
+				  block_group->length);
 
-	memcpy(&key, &block_group->key, sizeof(key));
 	index = btrfs_bg_flags_to_raid_index(block_group->flags);
 	factor = btrfs_bg_type_to_factor(block_group->flags);
 
@@ -967,8 +965,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	}
 
 	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
-	key.offset = block_group->key.objectid;
 	key.type = 0;
+	key.offset = block_group->start;
 
 	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
 	if (ret < 0)
@@ -987,7 +985,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		 &fs_info->block_group_cache_tree);
 	RB_CLEAR_NODE(&block_group->cache_node);
 
-	if (fs_info->first_logical_byte == block_group->key.objectid)
+	if (fs_info->first_logical_byte == block_group->start)
 		fs_info->first_logical_byte = (u64)-1;
 	spin_unlock(&fs_info->block_group_cache_lock);
 
@@ -1048,19 +1046,21 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	if (btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
 		WARN_ON(block_group->space_info->total_bytes
-			< block_group->key.offset);
+			< block_group->length);
 		WARN_ON(block_group->space_info->bytes_readonly
-			< block_group->key.offset);
+			< block_group->length);
 		WARN_ON(block_group->space_info->disk_total
-			< block_group->key.offset * factor);
+			< block_group->length * factor);
 	}
-	block_group->space_info->total_bytes -= block_group->key.offset;
-	block_group->space_info->bytes_readonly -= block_group->key.offset;
-	block_group->space_info->disk_total -= block_group->key.offset * factor;
+	block_group->space_info->total_bytes -= block_group->length;
+	block_group->space_info->bytes_readonly -= block_group->length;
+	block_group->space_info->disk_total -= block_group->length * factor;
 
 	spin_unlock(&block_group->space_info->lock);
 
-	memcpy(&key, &block_group->key, sizeof(key));
+	key.objectid = block_group->start;
+	key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+	key.offset = block_group->length;
 
 	mutex_lock(&fs_info->chunk_mutex);
 	spin_lock(&block_group->lock);
@@ -1180,7 +1180,7 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
  * data in this block group. That check should be done by relocation routine,
  * not this function.
  */
-static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
+static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
 {
 	struct btrfs_space_info *sinfo = cache->space_info;
 	u64 num_bytes;
@@ -1209,8 +1209,8 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
 		goto out;
 	}
 
-	num_bytes = cache->key.offset - cache->reserved - cache->pinned -
-		    cache->bytes_super - btrfs_block_group_used(&cache->item);
+	num_bytes = cache->length - cache->reserved - cache->pinned -
+		    cache->bytes_super - cache->used;
 	sinfo_used = btrfs_space_info_used(sinfo, true);
 
 	/*
@@ -1231,8 +1231,7 @@ out:
 	spin_unlock(&sinfo->lock);
 	if (ret == -ENOSPC && btrfs_test_opt(cache->fs_info, ENOSPC_DEBUG)) {
 		btrfs_info(cache->fs_info,
-			"unable to make block group %llu ro",
-			cache->key.objectid);
+			"unable to make block group %llu ro", cache->start);
 		btrfs_info(cache->fs_info,
 			"sinfo_used=%llu bg_num_bytes=%llu min_allocable=%llu",
 			sinfo_used, num_bytes, min_allocable_bytes);
@@ -1247,7 +1246,7 @@ out:
  */
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_space_info *space_info;
 	struct btrfs_trans_handle *trans;
 	int ret = 0;
@@ -1261,7 +1260,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		int trimming;
 
 		block_group = list_first_entry(&fs_info->unused_bgs,
-					       struct btrfs_block_group_cache,
+					       struct btrfs_block_group,
 					       bg_list);
 		list_del_init(&block_group->bg_list);
 
@@ -1279,8 +1278,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		down_write(&space_info->groups_sem);
 		spin_lock(&block_group->lock);
 		if (block_group->reserved || block_group->pinned ||
-		    btrfs_block_group_used(&block_group->item) ||
-		    block_group->ro ||
+		    block_group->used || block_group->ro ||
 		    list_is_singular(&block_group->list)) {
 			/*
 			 * We want to bail if we made new allocations or have
@@ -1308,7 +1306,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * properly if we fail to join the transaction.
 		 */
 		trans = btrfs_start_trans_remove_block_group(fs_info,
-						     block_group->key.objectid);
+						     block_group->start);
 		if (IS_ERR(trans)) {
 			btrfs_dec_block_group_ro(block_group);
 			ret = PTR_ERR(trans);
@@ -1319,8 +1317,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * We could have pending pinned extents for this block group,
 		 * just delete them, we don't care about them anymore.
 		 */
-		start = block_group->key.objectid;
-		end = start + block_group->key.offset - 1;
+		start = block_group->start;
+		end = start + block_group->length - 1;
 		/*
 		 * Hold the unused_bg_unpin_mutex lock to avoid racing with
 		 * btrfs_finish_extent_commit(). If we are at transaction N,
@@ -1375,7 +1373,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * Btrfs_remove_chunk will abort the transaction if things go
 		 * horribly wrong.
 		 */
-		ret = btrfs_remove_chunk(trans, block_group->key.objectid);
+		ret = btrfs_remove_chunk(trans, block_group->start);
 
 		if (ret) {
 			if (trimming)
@@ -1410,7 +1408,7 @@ next:
 	spin_unlock(&fs_info->unused_bgs_lock);
 }
 
-void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg)
+void btrfs_mark_bg_unused(struct btrfs_block_group *bg)
 {
 	struct btrfs_fs_info *fs_info = bg->fs_info;
 
@@ -1478,7 +1476,7 @@ static int find_first_block_group(struct btrfs_fs_info *fs_info,
 				read_extent_buffer(leaf, &bg,
 					btrfs_item_ptr_offset(leaf, slot),
 					sizeof(bg));
-				flags = btrfs_block_group_flags(&bg) &
+				flags = btrfs_stack_block_group_flags(&bg) &
 					BTRFS_BLOCK_GROUP_TYPE_MASK;
 
 				if (flags != (em->map_lookup->type &
@@ -1518,7 +1516,7 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 	write_sequnlock(&fs_info->profiles_lock);
 }
 
-static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
+static int exclude_super_stripes(struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	u64 bytenr;
@@ -1526,10 +1524,10 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
 	int stripe_len;
 	int i, nr, ret;
 
-	if (cache->key.objectid < BTRFS_SUPER_INFO_OFFSET) {
-		stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->key.objectid;
+	if (cache->start < BTRFS_SUPER_INFO_OFFSET) {
+		stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->start;
 		cache->bytes_super += stripe_len;
-		ret = btrfs_add_excluded_extent(fs_info, cache->key.objectid,
+		ret = btrfs_add_excluded_extent(fs_info, cache->start,
 						stripe_len);
 		if (ret)
 			return ret;
@@ -1537,7 +1535,7 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
 
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
 		bytenr = btrfs_sb_offset(i);
-		ret = btrfs_rmap_block(fs_info, cache->key.objectid,
+		ret = btrfs_rmap_block(fs_info, cache->start,
 				       bytenr, &logical, &nr, &stripe_len);
 		if (ret)
 			return ret;
@@ -1545,21 +1543,19 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
 		while (nr--) {
 			u64 start, len;
 
-			if (logical[nr] > cache->key.objectid +
-			    cache->key.offset)
+			if (logical[nr] > cache->start + cache->length)
 				continue;
 
-			if (logical[nr] + stripe_len <= cache->key.objectid)
+			if (logical[nr] + stripe_len <= cache->start)
 				continue;
 
 			start = logical[nr];
-			if (start < cache->key.objectid) {
-				start = cache->key.objectid;
+			if (start < cache->start) {
+				start = cache->start;
 				len = (logical[nr] + stripe_len) - start;
 			} else {
 				len = min_t(u64, stripe_len,
-					    cache->key.objectid +
-					    cache->key.offset - start);
+					    cache->start + cache->length - start);
 			}
 
 			cache->bytes_super += len;
@@ -1575,7 +1571,7 @@ static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
 	return 0;
 }
 
-static void link_block_group(struct btrfs_block_group_cache *cache)
+static void link_block_group(struct btrfs_block_group *cache)
 {
 	struct btrfs_space_info *space_info = cache->space_info;
 	int index = btrfs_bg_flags_to_raid_index(cache->flags);
@@ -1591,10 +1587,10 @@ static void link_block_group(struct btrfs_block_group_cache *cache)
 		btrfs_sysfs_add_block_group_type(cache);
 }
 
-static struct btrfs_block_group_cache *btrfs_create_block_group_cache(
+static struct btrfs_block_group *btrfs_create_block_group_cache(
 		struct btrfs_fs_info *fs_info, u64 start, u64 size)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 
 	cache = kzalloc(sizeof(*cache), GFP_NOFS);
 	if (!cache)
@@ -1607,9 +1603,8 @@ static struct btrfs_block_group_cache *btrfs_create_block_group_cache(
 		return NULL;
 	}
 
-	cache->key.objectid = start;
-	cache->key.offset = size;
-	cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+	cache->start = start;
+	cache->length = size;
 
 	cache->fs_info = fs_info;
 	cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start);
@@ -1640,7 +1635,7 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
 {
 	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
 	struct extent_map *em;
-	struct btrfs_block_group_cache *bg;
+	struct btrfs_block_group *bg;
 	u64 start = 0;
 	int ret = 0;
 
@@ -1665,15 +1660,14 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
 			free_extent_map(em);
 			break;
 		}
-		if (bg->key.objectid != em->start ||
-		    bg->key.offset != em->len ||
+		if (bg->start != em->start || bg->length != em->len ||
 		    (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) !=
 		    (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
 			btrfs_err(fs_info,
 "chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx",
 				em->start, em->len,
 				em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
-				bg->key.objectid, bg->key.offset,
+				bg->start, bg->length,
 				bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
 			ret = -EUCLEAN;
 			free_extent_map(em);
@@ -1687,22 +1681,117 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
 	return ret;
 }
 
+static int read_one_block_group(struct btrfs_fs_info *info,
+				struct btrfs_path *path,
+				const struct btrfs_key *key,
+				int need_clear)
+{
+	struct extent_buffer *leaf = path->nodes[0];
+	struct btrfs_block_group *cache;
+	struct btrfs_space_info *space_info;
+	struct btrfs_block_group_item bgi;
+	const bool mixed = btrfs_fs_incompat(info, MIXED_GROUPS);
+	int slot = path->slots[0];
+	int ret;
+
+	ASSERT(key->type == BTRFS_BLOCK_GROUP_ITEM_KEY);
+
+	cache = btrfs_create_block_group_cache(info, key->objectid, key->offset);
+	if (!cache)
+		return -ENOMEM;
+
+	if (need_clear) {
+		/*
+		 * When we mount with old space cache, we need to
+		 * set BTRFS_DC_CLEAR and set dirty flag.
+		 *
+		 * a) Setting 'BTRFS_DC_CLEAR' makes sure that we
+		 *    truncate the old free space cache inode and
+		 *    setup a new one.
+		 * b) Setting 'dirty flag' makes sure that we flush
+		 *    the new space cache info onto disk.
+		 */
+		if (btrfs_test_opt(info, SPACE_CACHE))
+			cache->disk_cache_state = BTRFS_DC_CLEAR;
+	}
+	read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
+			   sizeof(bgi));
+	cache->used = btrfs_stack_block_group_used(&bgi);
+	cache->flags = btrfs_stack_block_group_flags(&bgi);
+	if (!mixed && ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) &&
+	    (cache->flags & BTRFS_BLOCK_GROUP_DATA))) {
+			btrfs_err(info,
+"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups",
+				  cache->start);
+			ret = -EINVAL;
+			goto error;
+	}
+
+	/*
+	 * We need to exclude the super stripes now so that the space info has
+	 * super bytes accounted for, otherwise we'll think we have more space
+	 * than we actually do.
+	 */
+	ret = exclude_super_stripes(cache);
+	if (ret) {
+		/* We may have excluded something, so call this just in case. */
+		btrfs_free_excluded_extents(cache);
+		goto error;
+	}
+
+	/*
+	 * Check for two cases, either we are full, and therefore don't need
+	 * to bother with the caching work since we won't find any space, or we
+	 * are empty, and we can just add all the space in and be done with it.
+	 * This saves us _a_lot_ of time, particularly in the full case.
+	 */
+	if (key->offset == cache->used) {
+		cache->last_byte_to_unpin = (u64)-1;
+		cache->cached = BTRFS_CACHE_FINISHED;
+		btrfs_free_excluded_extents(cache);
+	} else if (cache->used == 0) {
+		cache->last_byte_to_unpin = (u64)-1;
+		cache->cached = BTRFS_CACHE_FINISHED;
+		add_new_free_space(cache, key->objectid,
+				   key->objectid + key->offset);
+		btrfs_free_excluded_extents(cache);
+	}
+
+	ret = btrfs_add_block_group_cache(info, cache);
+	if (ret) {
+		btrfs_remove_free_space_cache(cache);
+		goto error;
+	}
+	trace_btrfs_add_block_group(info, cache, 0);
+	btrfs_update_space_info(info, cache->flags, key->offset,
+				cache->used, cache->bytes_super, &space_info);
+
+	cache->space_info = space_info;
+
+	link_block_group(cache);
+
+	set_avail_alloc_bits(info, cache->flags);
+	if (btrfs_chunk_readonly(info, cache->start)) {
+		inc_block_group_ro(cache, 1);
+	} else if (cache->used == 0) {
+		ASSERT(list_empty(&cache->bg_list));
+		btrfs_mark_bg_unused(cache);
+	}
+	return 0;
+error:
+	btrfs_put_block_group(cache);
+	return ret;
+}
+
 int btrfs_read_block_groups(struct btrfs_fs_info *info)
 {
 	struct btrfs_path *path;
 	int ret;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	struct btrfs_space_info *space_info;
 	struct btrfs_key key;
-	struct btrfs_key found_key;
-	struct extent_buffer *leaf;
 	int need_clear = 0;
 	u64 cache_gen;
-	u64 feature;
-	int mixed;
-
-	feature = btrfs_super_incompat_flags(info->super_copy);
-	mixed = !!(feature & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS);
 
 	key.objectid = 0;
 	key.offset = 0;
@@ -1726,108 +1815,13 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		if (ret != 0)
 			goto error;
 
-		leaf = path->nodes[0];
-		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-
-		cache = btrfs_create_block_group_cache(info, found_key.objectid,
-						       found_key.offset);
-		if (!cache) {
-			ret = -ENOMEM;
-			goto error;
-		}
-
-		if (need_clear) {
-			/*
-			 * When we mount with old space cache, we need to
-			 * set BTRFS_DC_CLEAR and set dirty flag.
-			 *
-			 * a) Setting 'BTRFS_DC_CLEAR' makes sure that we
-			 *    truncate the old free space cache inode and
-			 *    setup a new one.
-			 * b) Setting 'dirty flag' makes sure that we flush
-			 *    the new space cache info onto disk.
-			 */
-			if (btrfs_test_opt(info, SPACE_CACHE))
-				cache->disk_cache_state = BTRFS_DC_CLEAR;
-		}
-
-		read_extent_buffer(leaf, &cache->item,
-				   btrfs_item_ptr_offset(leaf, path->slots[0]),
-				   sizeof(cache->item));
-		cache->flags = btrfs_block_group_flags(&cache->item);
-		if (!mixed &&
-		    ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) &&
-		    (cache->flags & BTRFS_BLOCK_GROUP_DATA))) {
-			btrfs_err(info,
-"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups",
-				  cache->key.objectid);
-			btrfs_put_block_group(cache);
-			ret = -EINVAL;
+		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+		ret = read_one_block_group(info, path, &key, need_clear);
+		if (ret < 0)
 			goto error;
-		}
-
-		key.objectid = found_key.objectid + found_key.offset;
+		key.objectid += key.offset;
+		key.offset = 0;
 		btrfs_release_path(path);
-
-		/*
-		 * We need to exclude the super stripes now so that the space
-		 * info has super bytes accounted for, otherwise we'll think
-		 * we have more space than we actually do.
-		 */
-		ret = exclude_super_stripes(cache);
-		if (ret) {
-			/*
-			 * We may have excluded something, so call this just in
-			 * case.
-			 */
-			btrfs_free_excluded_extents(cache);
-			btrfs_put_block_group(cache);
-			goto error;
-		}
-
-		/*
-		 * Check for two cases, either we are full, and therefore
-		 * don't need to bother with the caching work since we won't
-		 * find any space, or we are empty, and we can just add all
-		 * the space in and be done with it.  This saves us _a_lot_ of
-		 * time, particularly in the full case.
-		 */
-		if (found_key.offset == btrfs_block_group_used(&cache->item)) {
-			cache->last_byte_to_unpin = (u64)-1;
-			cache->cached = BTRFS_CACHE_FINISHED;
-			btrfs_free_excluded_extents(cache);
-		} else if (btrfs_block_group_used(&cache->item) == 0) {
-			cache->last_byte_to_unpin = (u64)-1;
-			cache->cached = BTRFS_CACHE_FINISHED;
-			add_new_free_space(cache, found_key.objectid,
-					   found_key.objectid +
-					   found_key.offset);
-			btrfs_free_excluded_extents(cache);
-		}
-
-		ret = btrfs_add_block_group_cache(info, cache);
-		if (ret) {
-			btrfs_remove_free_space_cache(cache);
-			btrfs_put_block_group(cache);
-			goto error;
-		}
-
-		trace_btrfs_add_block_group(info, cache, 0);
-		btrfs_update_space_info(info, cache->flags, found_key.offset,
-					btrfs_block_group_used(&cache->item),
-					cache->bytes_super, &space_info);
-
-		cache->space_info = space_info;
-
-		link_block_group(cache);
-
-		set_avail_alloc_bits(info, cache->flags);
-		if (btrfs_chunk_readonly(info, cache->key.objectid)) {
-			inc_block_group_ro(cache, 1);
-		} else if (btrfs_block_group_used(&cache->item) == 0) {
-			ASSERT(list_empty(&cache->bg_list));
-			btrfs_mark_bg_unused(cache);
-		}
 	}
 
 	list_for_each_entry_rcu(space_info, &info->space_info, list) {
@@ -1861,7 +1855,7 @@ error:
 void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_root *extent_root = fs_info->extent_root;
 	struct btrfs_block_group_item item;
 	struct btrfs_key key;
@@ -1872,14 +1866,19 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
 
 	while (!list_empty(&trans->new_bgs)) {
 		block_group = list_first_entry(&trans->new_bgs,
-					       struct btrfs_block_group_cache,
+					       struct btrfs_block_group,
 					       bg_list);
 		if (ret)
 			goto next;
 
 		spin_lock(&block_group->lock);
-		memcpy(&item, &block_group->item, sizeof(item));
-		memcpy(&key, &block_group->key, sizeof(key));
+		btrfs_set_stack_block_group_used(&item, block_group->used);
+		btrfs_set_stack_block_group_chunk_objectid(&item,
+				BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+		btrfs_set_stack_block_group_flags(&item, block_group->flags);
+		key.objectid = block_group->start;
+		key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+		key.offset = block_group->length;
 		spin_unlock(&block_group->lock);
 
 		ret = btrfs_insert_item(trans, extent_root, &key, &item,
@@ -1902,7 +1901,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 			   u64 type, u64 chunk_offset, u64 size)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	int ret;
 
 	btrfs_set_log_full_commit(trans);
@@ -1911,11 +1910,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 	if (!cache)
 		return -ENOMEM;
 
-	btrfs_set_block_group_used(&cache->item, bytes_used);
-	btrfs_set_block_group_chunk_objectid(&cache->item,
-					     BTRFS_FIRST_CHUNK_TREE_OBJECTID);
-	btrfs_set_block_group_flags(&cache->item, type);
-
+	cache->used = bytes_used;
 	cache->flags = type;
 	cache->last_byte_to_unpin = (u64)-1;
 	cache->cached = BTRFS_CACHE_FINISHED;
@@ -2022,8 +2017,17 @@ static u64 update_block_group_flags(struct btrfs_fs_info *fs_info, u64 flags)
 	return flags;
 }
 
-int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache)
-
+/*
+ * Mark one block group RO, can be called several times for the same block
+ * group.
+ *
+ * @cache:		the destination block group
+ * @do_chunk_alloc:	whether need to do chunk pre-allocation, this is to
+ * 			ensure we still have some free space after marking this
+ * 			block group RO.
+ */
+int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
+			     bool do_chunk_alloc)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_trans_handle *trans;
@@ -2053,25 +2057,29 @@ again:
 		goto again;
 	}
 
-	/*
-	 * if we are changing raid levels, try to allocate a corresponding
-	 * block group with the new raid level.
-	 */
-	alloc_flags = update_block_group_flags(fs_info, cache->flags);
-	if (alloc_flags != cache->flags) {
-		ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
+	if (do_chunk_alloc) {
 		/*
-		 * ENOSPC is allowed here, we may have enough space
-		 * already allocated at the new raid level to
-		 * carry on
+		 * If we are changing raid levels, try to allocate a
+		 * corresponding block group with the new raid level.
 		 */
-		if (ret == -ENOSPC)
-			ret = 0;
-		if (ret < 0)
-			goto out;
+		alloc_flags = update_block_group_flags(fs_info, cache->flags);
+		if (alloc_flags != cache->flags) {
+			ret = btrfs_chunk_alloc(trans, alloc_flags,
+						CHUNK_ALLOC_FORCE);
+			/*
+			 * ENOSPC is allowed here, we may have enough space
+			 * already allocated at the new raid level to carry on
+			 */
+			if (ret == -ENOSPC)
+				ret = 0;
+			if (ret < 0)
+				goto out;
+		}
 	}
 
-	ret = inc_block_group_ro(cache, 0);
+	ret = inc_block_group_ro(cache, !do_chunk_alloc);
+	if (!do_chunk_alloc)
+		goto unlock_out;
 	if (!ret)
 		goto out;
 	alloc_flags = btrfs_get_alloc_profile(fs_info, cache->space_info->flags);
@@ -2086,13 +2094,14 @@ out:
 		check_system_chunk(trans, alloc_flags);
 		mutex_unlock(&fs_info->chunk_mutex);
 	}
+unlock_out:
 	mutex_unlock(&fs_info->ro_block_group_mutex);
 
 	btrfs_end_transaction(trans);
 	return ret;
 }
 
-void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache)
+void btrfs_dec_block_group_ro(struct btrfs_block_group *cache)
 {
 	struct btrfs_space_info *sinfo = cache->space_info;
 	u64 num_bytes;
@@ -2102,9 +2111,8 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache)
 	spin_lock(&sinfo->lock);
 	spin_lock(&cache->lock);
 	if (!--cache->ro) {
-		num_bytes = cache->key.offset - cache->reserved -
-			    cache->pinned - cache->bytes_super -
-			    btrfs_block_group_used(&cache->item);
+		num_bytes = cache->length - cache->reserved -
+			    cache->pinned - cache->bytes_super - cache->used;
 		sinfo->bytes_readonly -= num_bytes;
 		list_del_init(&cache->ro_list);
 	}
@@ -2114,15 +2122,21 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache)
 
 static int write_one_cache_group(struct btrfs_trans_handle *trans,
 				 struct btrfs_path *path,
-				 struct btrfs_block_group_cache *cache)
+				 struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
 	struct btrfs_root *extent_root = fs_info->extent_root;
 	unsigned long bi;
 	struct extent_buffer *leaf;
+	struct btrfs_block_group_item bgi;
+	struct btrfs_key key;
+
+	key.objectid = cache->start;
+	key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+	key.offset = cache->length;
 
-	ret = btrfs_search_slot(trans, extent_root, &cache->key, path, 0, 1);
+	ret = btrfs_search_slot(trans, extent_root, &key, path, 0, 1);
 	if (ret) {
 		if (ret > 0)
 			ret = -ENOENT;
@@ -2131,7 +2145,11 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
 
 	leaf = path->nodes[0];
 	bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
-	write_extent_buffer(leaf, &cache->item, bi, sizeof(cache->item));
+	btrfs_set_stack_block_group_used(&bgi, cache->used);
+	btrfs_set_stack_block_group_chunk_objectid(&bgi,
+			BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+	btrfs_set_stack_block_group_flags(&bgi, cache->flags);
+	write_extent_buffer(leaf, &bgi, bi, sizeof(bgi));
 	btrfs_mark_buffer_dirty(leaf);
 fail:
 	btrfs_release_path(path);
@@ -2139,7 +2157,7 @@ fail:
 
 }
 
-static int cache_save_setup(struct btrfs_block_group_cache *block_group,
+static int cache_save_setup(struct btrfs_block_group *block_group,
 			    struct btrfs_trans_handle *trans,
 			    struct btrfs_path *path)
 {
@@ -2157,7 +2175,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 	 * If this block group is smaller than 100 megs don't bother caching the
 	 * block group.
 	 */
-	if (block_group->key.offset < (100 * SZ_1M)) {
+	if (block_group->length < (100 * SZ_1M)) {
 		spin_lock(&block_group->lock);
 		block_group->disk_cache_state = BTRFS_DC_WRITTEN;
 		spin_unlock(&block_group->lock);
@@ -2258,7 +2276,7 @@ again:
 	 * taking up quite a bit since it's not folded into the other space
 	 * cache.
 	 */
-	num_pages = div_u64(block_group->key.offset, SZ_256M);
+	num_pages = div_u64(block_group->length, SZ_256M);
 	if (!num_pages)
 		num_pages = 1;
 
@@ -2303,7 +2321,7 @@ out:
 int btrfs_setup_space_cache(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_group_cache *cache, *tmp;
+	struct btrfs_block_group *cache, *tmp;
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_path *path;
 
@@ -2341,7 +2359,7 @@ int btrfs_setup_space_cache(struct btrfs_trans_handle *trans)
 int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	int ret = 0;
 	int should_put;
@@ -2378,8 +2396,7 @@ again:
 	while (!list_empty(&dirty)) {
 		bool drop_reserve = true;
 
-		cache = list_first_entry(&dirty,
-					 struct btrfs_block_group_cache,
+		cache = list_first_entry(&dirty, struct btrfs_block_group,
 					 dirty_list);
 		/*
 		 * This can happen if something re-dirties a block group that
@@ -2504,7 +2521,7 @@ again:
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	int ret = 0;
 	int should_put;
@@ -2534,7 +2551,7 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
 	spin_lock(&cur_trans->dirty_bgs_lock);
 	while (!list_empty(&cur_trans->dirty_bgs)) {
 		cache = list_first_entry(&cur_trans->dirty_bgs,
-					 struct btrfs_block_group_cache,
+					 struct btrfs_block_group,
 					 dirty_list);
 
 		/*
@@ -2616,7 +2633,7 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
 	 * to use it without any locking
 	 */
 	while (!list_empty(io)) {
-		cache = list_first_entry(io, struct btrfs_block_group_cache,
+		cache = list_first_entry(io, struct btrfs_block_group,
 					 io_list);
 		list_del_init(&cache->io_list);
 		btrfs_wait_cache_io(trans, cache, path);
@@ -2631,7 +2648,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 			     u64 bytenr, u64 num_bytes, int alloc)
 {
 	struct btrfs_fs_info *info = trans->fs_info;
-	struct btrfs_block_group_cache *cache = NULL;
+	struct btrfs_block_group *cache = NULL;
 	u64 total = num_bytes;
 	u64 old_val;
 	u64 byte_in_group;
@@ -2662,11 +2679,11 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 		 * is because we need the unpinning stage to actually add the
 		 * space back to the block group, otherwise we will leak space.
 		 */
-		if (!alloc && cache->cached == BTRFS_CACHE_NO)
+		if (!alloc && !btrfs_block_group_done(cache))
 			btrfs_cache_block_group(cache, 1);
 
-		byte_in_group = bytenr - cache->key.objectid;
-		WARN_ON(byte_in_group > cache->key.offset);
+		byte_in_group = bytenr - cache->start;
+		WARN_ON(byte_in_group > cache->length);
 
 		spin_lock(&cache->space_info->lock);
 		spin_lock(&cache->lock);
@@ -2675,11 +2692,11 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 		    cache->disk_cache_state < BTRFS_DC_CLEAR)
 			cache->disk_cache_state = BTRFS_DC_CLEAR;
 
-		old_val = btrfs_block_group_used(&cache->item);
-		num_bytes = min(total, cache->key.offset - byte_in_group);
+		old_val = cache->used;
+		num_bytes = min(total, cache->length - byte_in_group);
 		if (alloc) {
 			old_val += num_bytes;
-			btrfs_set_block_group_used(&cache->item, old_val);
+			cache->used = old_val;
 			cache->reserved -= num_bytes;
 			cache->space_info->bytes_reserved -= num_bytes;
 			cache->space_info->bytes_used += num_bytes;
@@ -2688,7 +2705,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 			spin_unlock(&cache->space_info->lock);
 		} else {
 			old_val -= num_bytes;
-			btrfs_set_block_group_used(&cache->item, old_val);
+			cache->used = old_val;
 			cache->pinned += num_bytes;
 			btrfs_space_info_update_bytes_pinned(info,
 					cache->space_info, num_bytes);
@@ -2746,7 +2763,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
  * reservation and the block group has become read only we cannot make the
  * reservation and return -EAGAIN, otherwise this function always succeeds.
  */
-int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
 			     u64 ram_bytes, u64 num_bytes, int delalloc)
 {
 	struct btrfs_space_info *space_info = cache->space_info;
@@ -2782,7 +2799,7 @@ int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
  * A and before transaction A commits you free that leaf, you call this with
  * reserve set to 0 in order to clear the reservation.
  */
-void btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
 			       u64 num_bytes, int delalloc)
 {
 	struct btrfs_space_info *space_info = cache->space_info;
@@ -2988,9 +3005,7 @@ static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type)
 }
 
 /*
- * If @is_allocation is true, reserve space in the system space info necessary
- * for allocating a chunk, otherwise if it's false, reserve space necessary for
- * removing a chunk.
+ * Reserve space in the system space for allocating or removing a chunk
  */
 void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
 {
@@ -3047,7 +3062,7 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
 
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	u64 last = 0;
 
 	while (1) {
@@ -3075,7 +3090,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
 		spin_unlock(&block_group->lock);
 		ASSERT(block_group->io_ctl.inode == NULL);
 		iput(inode);
-		last = block_group->key.objectid + block_group->key.offset;
+		last = block_group->start + block_group->length;
 		btrfs_put_block_group(block_group);
 	}
 }
@@ -3087,7 +3102,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
  */
 int btrfs_free_block_groups(struct btrfs_fs_info *info)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_space_info *space_info;
 	struct btrfs_caching_control *caching_ctl;
 	struct rb_node *n;
@@ -3104,7 +3119,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 	spin_lock(&info->unused_bgs_lock);
 	while (!list_empty(&info->unused_bgs)) {
 		block_group = list_first_entry(&info->unused_bgs,
-					       struct btrfs_block_group_cache,
+					       struct btrfs_block_group,
 					       bg_list);
 		list_del_init(&block_group->bg_list);
 		btrfs_put_block_group(block_group);
@@ -3113,7 +3128,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 
 	spin_lock(&info->block_group_cache_lock);
 	while ((n = rb_last(&info->block_group_cache_tree)) != NULL) {
-		block_group = rb_entry(n, struct btrfs_block_group_cache,
+		block_group = rb_entry(n, struct btrfs_block_group,
 				       cache_node);
 		rb_erase(&block_group->cache_node,
 			 &info->block_group_cache_tree);
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index c391800388dd..9b409676c4b2 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -34,7 +34,7 @@ struct btrfs_caching_control {
 	struct mutex mutex;
 	wait_queue_head_t wait;
 	struct btrfs_work work;
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	u64 progress;
 	refcount_t count;
 };
@@ -42,14 +42,15 @@ struct btrfs_caching_control {
 /* Once caching_thread() finds this much free space, it will wake up waiters. */
 #define CACHING_CTL_WAKE_UP SZ_2M
 
-struct btrfs_block_group_cache {
-	struct btrfs_key key;
-	struct btrfs_block_group_item item;
+struct btrfs_block_group {
 	struct btrfs_fs_info *fs_info;
 	struct inode *inode;
 	spinlock_t lock;
+	u64 start;
+	u64 length;
 	u64 pinned;
 	u64 reserved;
+	u64 used;
 	u64 delalloc_bytes;
 	u64 bytes_super;
 	u64 flags;
@@ -159,7 +160,7 @@ struct btrfs_block_group_cache {
 
 #ifdef CONFIG_BTRFS_DEBUG
 static inline int btrfs_should_fragment_free_space(
-		struct btrfs_block_group_cache *block_group)
+		struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 
@@ -170,29 +171,29 @@ static inline int btrfs_should_fragment_free_space(
 }
 #endif
 
-struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
+struct btrfs_block_group *btrfs_lookup_first_block_group(
 		struct btrfs_fs_info *info, u64 bytenr);
-struct btrfs_block_group_cache *btrfs_lookup_block_group(
+struct btrfs_block_group *btrfs_lookup_block_group(
 		struct btrfs_fs_info *info, u64 bytenr);
-struct btrfs_block_group_cache *btrfs_next_block_group(
-		struct btrfs_block_group_cache *cache);
-void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
-void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
+struct btrfs_block_group *btrfs_next_block_group(
+		struct btrfs_block_group *cache);
+void btrfs_get_block_group(struct btrfs_block_group *cache);
+void btrfs_put_block_group(struct btrfs_block_group *cache);
 void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
 					const u64 start);
-void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg);
+void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg);
 bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
 void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
-void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg);
-void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
+void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
+void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 				           u64 num_bytes);
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache);
-int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
+int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache);
+int btrfs_cache_block_group(struct btrfs_block_group *cache,
 			    int load_cache_only);
 void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
 struct btrfs_caching_control *btrfs_get_caching_control(
-		struct btrfs_block_group_cache *cache);
-u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
+		struct btrfs_block_group *cache);
+u64 add_new_free_space(struct btrfs_block_group *block_group,
 		       u64 start, u64 end);
 struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 				struct btrfs_fs_info *fs_info,
@@ -200,21 +201,22 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 			     u64 group_start, struct extent_map *em);
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
-void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg);
+void btrfs_mark_bg_unused(struct btrfs_block_group *bg);
 int btrfs_read_block_groups(struct btrfs_fs_info *info);
 int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 			   u64 type, u64 chunk_offset, u64 size);
 void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
-int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache);
-void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache);
+int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
+			     bool do_chunk_alloc);
+void btrfs_dec_block_group_ro(struct btrfs_block_group *cache);
 int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans);
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans);
 int btrfs_setup_space_cache(struct btrfs_trans_handle *trans);
 int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 			     u64 bytenr, u64 num_bytes, int alloc);
-int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
 			     u64 ram_bytes, u64 num_bytes, int delalloc);
-void btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
 			       u64 num_bytes, int delalloc);
 int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 		      enum btrfs_chunk_alloc_enum force);
@@ -239,8 +241,7 @@ static inline u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
 	return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
 }
 
-static inline int btrfs_block_group_cache_done(
-		struct btrfs_block_group_cache *cache)
+static inline int btrfs_block_group_done(struct btrfs_block_group *cache)
 {
 	smp_mb();
 	return cache->cached == BTRFS_CACHE_FINISHED ||
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index f853835c409c..4e12a477d32e 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -63,9 +63,6 @@ struct btrfs_inode {
 	/* held while logging the inode in tree-log.c */
 	struct mutex log_mutex;
 
-	/* held while doing delalloc reservations */
-	struct mutex delalloc_mutex;
-
 	/* used to order data wrt metadata */
 	struct btrfs_ordered_inode_tree ordered_tree;
 
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b05b361e2062..ee834ef7beb4 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -29,6 +29,41 @@
 #include "extent_io.h"
 #include "extent_map.h"
 
+int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
+		u64 start, struct page **pages, unsigned long *out_pages,
+		unsigned long *total_in, unsigned long *total_out);
+int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
+int zlib_decompress(struct list_head *ws, unsigned char *data_in,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		size_t destlen);
+struct list_head *zlib_alloc_workspace(unsigned int level);
+void zlib_free_workspace(struct list_head *ws);
+struct list_head *zlib_get_workspace(unsigned int level);
+
+int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
+		u64 start, struct page **pages, unsigned long *out_pages,
+		unsigned long *total_in, unsigned long *total_out);
+int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
+int lzo_decompress(struct list_head *ws, unsigned char *data_in,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		size_t destlen);
+struct list_head *lzo_alloc_workspace(unsigned int level);
+void lzo_free_workspace(struct list_head *ws);
+
+int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
+		u64 start, struct page **pages, unsigned long *out_pages,
+		unsigned long *total_in, unsigned long *total_out);
+int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
+int zstd_decompress(struct list_head *ws, unsigned char *data_in,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		size_t destlen);
+void zstd_init_workspace_manager(void);
+void zstd_cleanup_workspace_manager(void);
+struct list_head *zstd_alloc_workspace(unsigned int level);
+void zstd_free_workspace(struct list_head *ws);
+struct list_head *zstd_get_workspace(unsigned int level);
+void zstd_put_workspace(struct list_head *ws);
+
 static const char* const btrfs_compress_types[] = { "", "zlib", "lzo", "zstd" };
 
 const char* btrfs_compress_type2str(enum btrfs_compression_type type)
@@ -39,6 +74,8 @@ const char* btrfs_compress_type2str(enum btrfs_compression_type type)
 	case BTRFS_COMPRESS_ZSTD:
 	case BTRFS_COMPRESS_NONE:
 		return btrfs_compress_types[type];
+	default:
+		break;
 	}
 
 	return NULL;
@@ -60,6 +97,70 @@ bool btrfs_compress_is_valid_type(const char *str, size_t len)
 	return false;
 }
 
+static int compression_compress_pages(int type, struct list_head *ws,
+               struct address_space *mapping, u64 start, struct page **pages,
+               unsigned long *out_pages, unsigned long *total_in,
+               unsigned long *total_out)
+{
+	switch (type) {
+	case BTRFS_COMPRESS_ZLIB:
+		return zlib_compress_pages(ws, mapping, start, pages,
+				out_pages, total_in, total_out);
+	case BTRFS_COMPRESS_LZO:
+		return lzo_compress_pages(ws, mapping, start, pages,
+				out_pages, total_in, total_out);
+	case BTRFS_COMPRESS_ZSTD:
+		return zstd_compress_pages(ws, mapping, start, pages,
+				out_pages, total_in, total_out);
+	case BTRFS_COMPRESS_NONE:
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here. As a sane fallback, return what the
+		 * callers will understand as 'no compression happened'.
+		 */
+		return -E2BIG;
+	}
+}
+
+static int compression_decompress_bio(int type, struct list_head *ws,
+		struct compressed_bio *cb)
+{
+	switch (type) {
+	case BTRFS_COMPRESS_ZLIB: return zlib_decompress_bio(ws, cb);
+	case BTRFS_COMPRESS_LZO:  return lzo_decompress_bio(ws, cb);
+	case BTRFS_COMPRESS_ZSTD: return zstd_decompress_bio(ws, cb);
+	case BTRFS_COMPRESS_NONE:
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here.
+		 */
+		BUG();
+	}
+}
+
+static int compression_decompress(int type, struct list_head *ws,
+               unsigned char *data_in, struct page *dest_page,
+               unsigned long start_byte, size_t srclen, size_t destlen)
+{
+	switch (type) {
+	case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_page,
+						start_byte, srclen, destlen);
+	case BTRFS_COMPRESS_LZO:  return lzo_decompress(ws, data_in, dest_page,
+						start_byte, srclen, destlen);
+	case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_page,
+						start_byte, srclen, destlen);
+	case BTRFS_COMPRESS_NONE:
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here.
+		 */
+		BUG();
+	}
+}
+
 static int btrfs_decompress_bio(struct compressed_bio *cb);
 
 static inline int compressed_bio_size(struct btrfs_fs_info *fs_info,
@@ -311,7 +412,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				 unsigned long compressed_len,
 				 struct page **compressed_pages,
 				 unsigned long nr_pages,
-				 unsigned int write_flags)
+				 unsigned int write_flags,
+				 struct cgroup_subsys_state *blkcg_css)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct bio *bio = NULL;
@@ -320,7 +422,6 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	int pg_index = 0;
 	struct page *page;
 	u64 first_byte = disk_start;
-	struct block_device *bdev;
 	blk_status_t ret;
 	int skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
@@ -339,13 +440,15 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	cb->orig_bio = NULL;
 	cb->nr_pages = nr_pages;
 
-	bdev = fs_info->fs_devices->latest_bdev;
-
 	bio = btrfs_bio_alloc(first_byte);
-	bio_set_dev(bio, bdev);
 	bio->bi_opf = REQ_OP_WRITE | write_flags;
 	bio->bi_private = cb;
 	bio->bi_end_io = end_compressed_bio_write;
+
+	if (blkcg_css) {
+		bio->bi_opf |= REQ_CGROUP_PUNT;
+		bio_associate_blkg_from_css(bio, blkcg_css);
+	}
 	refcount_set(&cb->pending_bios, 1);
 
 	/* create and submit bios for the compressed pages */
@@ -378,14 +481,13 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				BUG_ON(ret); /* -ENOMEM */
 			}
 
-			ret = btrfs_map_bio(fs_info, bio, 0, 1);
+			ret = btrfs_map_bio(fs_info, bio, 0);
 			if (ret) {
 				bio->bi_status = ret;
 				bio_endio(bio);
 			}
 
 			bio = btrfs_bio_alloc(first_byte);
-			bio_set_dev(bio, bdev);
 			bio->bi_opf = REQ_OP_WRITE | write_flags;
 			bio->bi_private = cb;
 			bio->bi_end_io = end_compressed_bio_write;
@@ -409,7 +511,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		BUG_ON(ret); /* -ENOMEM */
 	}
 
-	ret = btrfs_map_bio(fs_info, bio, 0, 1);
+	ret = btrfs_map_bio(fs_info, bio, 0);
 	if (ret) {
 		bio->bi_status = ret;
 		bio_endio(bio);
@@ -553,7 +655,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	unsigned long nr_pages;
 	unsigned long pg_index;
 	struct page *page;
-	struct block_device *bdev;
 	struct bio *comp_bio;
 	u64 cur_disk_byte = (u64)bio->bi_iter.bi_sector << 9;
 	u64 em_len;
@@ -604,8 +705,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	if (!cb->compressed_pages)
 		goto fail1;
 
-	bdev = fs_info->fs_devices->latest_bdev;
-
 	for (pg_index = 0; pg_index < nr_pages; pg_index++) {
 		cb->compressed_pages[pg_index] = alloc_page(GFP_NOFS |
 							      __GFP_HIGHMEM);
@@ -624,7 +723,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	cb->len = bio->bi_iter.bi_size;
 
 	comp_bio = btrfs_bio_alloc(cur_disk_byte);
-	bio_set_dev(comp_bio, bdev);
 	comp_bio->bi_opf = REQ_OP_READ;
 	comp_bio->bi_private = cb;
 	comp_bio->bi_end_io = end_compressed_bio_read;
@@ -668,14 +766,13 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 						  fs_info->sectorsize);
 			sums += csum_size * nr_sectors;
 
-			ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0);
+			ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);
 			if (ret) {
 				comp_bio->bi_status = ret;
 				bio_endio(comp_bio);
 			}
 
 			comp_bio = btrfs_bio_alloc(cur_disk_byte);
-			bio_set_dev(comp_bio, bdev);
 			comp_bio->bi_opf = REQ_OP_READ;
 			comp_bio->bi_private = cb;
 			comp_bio->bi_end_io = end_compressed_bio_read;
@@ -693,7 +790,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		BUG_ON(ret); /* -ENOMEM */
 	}
 
-	ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0);
+	ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);
 	if (ret) {
 		comp_bio->bi_status = ret;
 		bio_endio(comp_bio);
@@ -764,26 +861,6 @@ struct heuristic_ws {
 
 static struct workspace_manager heuristic_wsm;
 
-static void heuristic_init_workspace_manager(void)
-{
-	btrfs_init_workspace_manager(&heuristic_wsm, &btrfs_heuristic_compress);
-}
-
-static void heuristic_cleanup_workspace_manager(void)
-{
-	btrfs_cleanup_workspace_manager(&heuristic_wsm);
-}
-
-static struct list_head *heuristic_get_workspace(unsigned int level)
-{
-	return btrfs_get_workspace(&heuristic_wsm, level);
-}
-
-static void heuristic_put_workspace(struct list_head *ws)
-{
-	btrfs_put_workspace(&heuristic_wsm, ws);
-}
-
 static void free_heuristic_ws(struct list_head *ws)
 {
 	struct heuristic_ws *workspace;
@@ -824,12 +901,7 @@ fail:
 }
 
 const struct btrfs_compress_op btrfs_heuristic_compress = {
-	.init_workspace_manager = heuristic_init_workspace_manager,
-	.cleanup_workspace_manager = heuristic_cleanup_workspace_manager,
-	.get_workspace = heuristic_get_workspace,
-	.put_workspace = heuristic_put_workspace,
-	.alloc_workspace = alloc_heuristic_ws,
-	.free_workspace = free_heuristic_ws,
+	.workspace_manager = &heuristic_wsm,
 };
 
 static const struct btrfs_compress_op * const btrfs_compress_op[] = {
@@ -840,13 +912,44 @@ static const struct btrfs_compress_op * const btrfs_compress_op[] = {
 	&btrfs_zstd_compress,
 };
 
-void btrfs_init_workspace_manager(struct workspace_manager *wsm,
-				  const struct btrfs_compress_op *ops)
+static struct list_head *alloc_workspace(int type, unsigned int level)
 {
-	struct list_head *workspace;
+	switch (type) {
+	case BTRFS_COMPRESS_NONE: return alloc_heuristic_ws(level);
+	case BTRFS_COMPRESS_ZLIB: return zlib_alloc_workspace(level);
+	case BTRFS_COMPRESS_LZO:  return lzo_alloc_workspace(level);
+	case BTRFS_COMPRESS_ZSTD: return zstd_alloc_workspace(level);
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here.
+		 */
+		BUG();
+	}
+}
 
-	wsm->ops = ops;
+static void free_workspace(int type, struct list_head *ws)
+{
+	switch (type) {
+	case BTRFS_COMPRESS_NONE: return free_heuristic_ws(ws);
+	case BTRFS_COMPRESS_ZLIB: return zlib_free_workspace(ws);
+	case BTRFS_COMPRESS_LZO:  return lzo_free_workspace(ws);
+	case BTRFS_COMPRESS_ZSTD: return zstd_free_workspace(ws);
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here.
+		 */
+		BUG();
+	}
+}
+
+static void btrfs_init_workspace_manager(int type)
+{
+	struct workspace_manager *wsm;
+	struct list_head *workspace;
 
+	wsm = btrfs_compress_op[type]->workspace_manager;
 	INIT_LIST_HEAD(&wsm->idle_ws);
 	spin_lock_init(&wsm->ws_lock);
 	atomic_set(&wsm->total_ws, 0);
@@ -856,7 +959,7 @@ void btrfs_init_workspace_manager(struct workspace_manager *wsm,
 	 * Preallocate one workspace for each compression type so we can
 	 * guarantee forward progress in the worst case
 	 */
-	workspace = wsm->ops->alloc_workspace(0);
+	workspace = alloc_workspace(type, 0);
 	if (IS_ERR(workspace)) {
 		pr_warn(
 	"BTRFS: cannot preallocate compression workspace, will try later\n");
@@ -867,14 +970,16 @@ void btrfs_init_workspace_manager(struct workspace_manager *wsm,
 	}
 }
 
-void btrfs_cleanup_workspace_manager(struct workspace_manager *wsman)
+static void btrfs_cleanup_workspace_manager(int type)
 {
+	struct workspace_manager *wsman;
 	struct list_head *ws;
 
+	wsman = btrfs_compress_op[type]->workspace_manager;
 	while (!list_empty(&wsman->idle_ws)) {
 		ws = wsman->idle_ws.next;
 		list_del(ws);
-		wsman->ops->free_workspace(ws);
+		free_workspace(type, ws);
 		atomic_dec(&wsman->total_ws);
 	}
 }
@@ -885,9 +990,9 @@ void btrfs_cleanup_workspace_manager(struct workspace_manager *wsman)
  * Preallocation makes a forward progress guarantees and we do not return
  * errors.
  */
-struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
-				      unsigned int level)
+struct list_head *btrfs_get_workspace(int type, unsigned int level)
 {
+	struct workspace_manager *wsm;
 	struct list_head *workspace;
 	int cpus = num_online_cpus();
 	unsigned nofs_flag;
@@ -897,6 +1002,7 @@ struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
 	wait_queue_head_t *ws_wait;
 	int *free_ws;
 
+	wsm = btrfs_compress_op[type]->workspace_manager;
 	idle_ws	 = &wsm->idle_ws;
 	ws_lock	 = &wsm->ws_lock;
 	total_ws = &wsm->total_ws;
@@ -932,7 +1038,7 @@ again:
 	 * context of btrfs_compress_bio/btrfs_compress_pages
 	 */
 	nofs_flag = memalloc_nofs_save();
-	workspace = wsm->ops->alloc_workspace(level);
+	workspace = alloc_workspace(type, level);
 	memalloc_nofs_restore(nofs_flag);
 
 	if (IS_ERR(workspace)) {
@@ -965,21 +1071,34 @@ again:
 
 static struct list_head *get_workspace(int type, int level)
 {
-	return btrfs_compress_op[type]->get_workspace(level);
+	switch (type) {
+	case BTRFS_COMPRESS_NONE: return btrfs_get_workspace(type, level);
+	case BTRFS_COMPRESS_ZLIB: return zlib_get_workspace(level);
+	case BTRFS_COMPRESS_LZO:  return btrfs_get_workspace(type, level);
+	case BTRFS_COMPRESS_ZSTD: return zstd_get_workspace(level);
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here.
+		 */
+		BUG();
+	}
 }
 
 /*
  * put a workspace struct back on the list or free it if we have enough
  * idle ones sitting around
  */
-void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws)
+void btrfs_put_workspace(int type, struct list_head *ws)
 {
+	struct workspace_manager *wsm;
 	struct list_head *idle_ws;
 	spinlock_t *ws_lock;
 	atomic_t *total_ws;
 	wait_queue_head_t *ws_wait;
 	int *free_ws;
 
+	wsm = btrfs_compress_op[type]->workspace_manager;
 	idle_ws	 = &wsm->idle_ws;
 	ws_lock	 = &wsm->ws_lock;
 	total_ws = &wsm->total_ws;
@@ -995,7 +1114,7 @@ void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws)
 	}
 	spin_unlock(ws_lock);
 
-	wsm->ops->free_workspace(ws);
+	free_workspace(type, ws);
 	atomic_dec(total_ws);
 wake:
 	cond_wake_up(ws_wait);
@@ -1003,7 +1122,18 @@ wake:
 
 static void put_workspace(int type, struct list_head *ws)
 {
-	return btrfs_compress_op[type]->put_workspace(ws);
+	switch (type) {
+	case BTRFS_COMPRESS_NONE: return btrfs_put_workspace(type, ws);
+	case BTRFS_COMPRESS_ZLIB: return btrfs_put_workspace(type, ws);
+	case BTRFS_COMPRESS_LZO:  return btrfs_put_workspace(type, ws);
+	case BTRFS_COMPRESS_ZSTD: return zstd_put_workspace(ws);
+	default:
+		/*
+		 * This can't happen, the type is validated several times
+		 * before we get here.
+		 */
+		BUG();
+	}
 }
 
 /*
@@ -1042,10 +1172,8 @@ int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
 
 	level = btrfs_compress_set_level(type, level);
 	workspace = get_workspace(type, level);
-	ret = btrfs_compress_op[type]->compress_pages(workspace, mapping,
-						      start, pages,
-						      out_pages,
-						      total_in, total_out);
+	ret = compression_compress_pages(type, workspace, mapping, start, pages,
+					 out_pages, total_in, total_out);
 	put_workspace(type, workspace);
 	return ret;
 }
@@ -1071,7 +1199,7 @@ static int btrfs_decompress_bio(struct compressed_bio *cb)
 	int type = cb->compress_type;
 
 	workspace = get_workspace(type, 0);
-	ret = btrfs_compress_op[type]->decompress_bio(workspace, cb);
+	ret = compression_decompress_bio(type, workspace, cb);
 	put_workspace(type, workspace);
 
 	return ret;
@@ -1089,9 +1217,8 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 	int ret;
 
 	workspace = get_workspace(type, 0);
-	ret = btrfs_compress_op[type]->decompress(workspace, data_in,
-						  dest_page, start_byte,
-						  srclen, destlen);
+	ret = compression_decompress(type, workspace, data_in, dest_page,
+				     start_byte, srclen, destlen);
 	put_workspace(type, workspace);
 
 	return ret;
@@ -1099,18 +1226,18 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 
 void __init btrfs_init_compress(void)
 {
-	int i;
-
-	for (i = 0; i < BTRFS_NR_WORKSPACE_MANAGERS; i++)
-		btrfs_compress_op[i]->init_workspace_manager();
+	btrfs_init_workspace_manager(BTRFS_COMPRESS_NONE);
+	btrfs_init_workspace_manager(BTRFS_COMPRESS_ZLIB);
+	btrfs_init_workspace_manager(BTRFS_COMPRESS_LZO);
+	zstd_init_workspace_manager();
 }
 
 void __cold btrfs_exit_compress(void)
 {
-	int i;
-
-	for (i = 0; i < BTRFS_NR_WORKSPACE_MANAGERS; i++)
-		btrfs_compress_op[i]->cleanup_workspace_manager();
+	btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_NONE);
+	btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_ZLIB);
+	btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_LZO);
+	zstd_cleanup_workspace_manager();
 }
 
 /*
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 4cb8be9ff88b..d253f7aa8ed5 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -93,7 +93,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				  unsigned long compressed_len,
 				  struct page **compressed_pages,
 				  unsigned long nr_pages,
-				  unsigned int write_flags);
+				  unsigned int write_flags,
+				  struct cgroup_subsys_state *blkcg_css);
 blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags);
 
@@ -104,11 +105,10 @@ enum btrfs_compression_type {
 	BTRFS_COMPRESS_ZLIB  = 1,
 	BTRFS_COMPRESS_LZO   = 2,
 	BTRFS_COMPRESS_ZSTD  = 3,
-	BTRFS_COMPRESS_TYPES = 3,
+	BTRFS_NR_COMPRESS_TYPES = 4,
 };
 
 struct workspace_manager {
-	const struct btrfs_compress_op *ops;
 	struct list_head idle_ws;
 	spinlock_t ws_lock;
 	/* Number of free workspaces */
@@ -119,50 +119,18 @@ struct workspace_manager {
 	wait_queue_head_t ws_wait;
 };
 
-void btrfs_init_workspace_manager(struct workspace_manager *wsm,
-				  const struct btrfs_compress_op *ops);
-struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
-				      unsigned int level);
-void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws);
-void btrfs_cleanup_workspace_manager(struct workspace_manager *wsm);
+struct list_head *btrfs_get_workspace(int type, unsigned int level);
+void btrfs_put_workspace(int type, struct list_head *ws);
 
 struct btrfs_compress_op {
-	void (*init_workspace_manager)(void);
-
-	void (*cleanup_workspace_manager)(void);
-
-	struct list_head *(*get_workspace)(unsigned int level);
-
-	void (*put_workspace)(struct list_head *ws);
-
-	struct list_head *(*alloc_workspace)(unsigned int level);
-
-	void (*free_workspace)(struct list_head *workspace);
-
-	int (*compress_pages)(struct list_head *workspace,
-			      struct address_space *mapping,
-			      u64 start,
-			      struct page **pages,
-			      unsigned long *out_pages,
-			      unsigned long *total_in,
-			      unsigned long *total_out);
-
-	int (*decompress_bio)(struct list_head *workspace,
-				struct compressed_bio *cb);
-
-	int (*decompress)(struct list_head *workspace,
-			  unsigned char *data_in,
-			  struct page *dest_page,
-			  unsigned long start_byte,
-			  size_t srclen, size_t destlen);
-
+	struct workspace_manager *workspace_manager;
 	/* Maximum level supported by the compression algorithm */
 	unsigned int max_level;
 	unsigned int default_level;
 };
 
 /* The heuristic workspaces are managed via the 0th workspace manager */
-#define BTRFS_NR_WORKSPACE_MANAGERS	(BTRFS_COMPRESS_TYPES + 1)
+#define BTRFS_NR_WORKSPACE_MANAGERS	BTRFS_NR_COMPRESS_TYPES
 
 extern const struct btrfs_compress_op btrfs_heuristic_compress;
 extern const struct btrfs_compress_op btrfs_zlib_compress;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index e59cde204b2f..5b6e86aaf2e1 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -32,8 +32,13 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
 static const struct btrfs_csums {
 	u16		size;
 	const char	*name;
+	const char	*driver;
 } btrfs_csums[] = {
 	[BTRFS_CSUM_TYPE_CRC32] = { .size = 4, .name = "crc32c" },
+	[BTRFS_CSUM_TYPE_XXHASH] = { .size = 8, .name = "xxhash64" },
+	[BTRFS_CSUM_TYPE_SHA256] = { .size = 32, .name = "sha256" },
+	[BTRFS_CSUM_TYPE_BLAKE2] = { .size = 32, .name = "blake2b",
+				     .driver = "blake2b-256" },
 };
 
 int btrfs_super_csum_size(const struct btrfs_super_block *s)
@@ -51,34 +56,25 @@ const char *btrfs_super_csum_name(u16 csum_type)
 	return btrfs_csums[csum_type].name;
 }
 
-struct btrfs_path *btrfs_alloc_path(void)
+/*
+ * Return driver name if defined, otherwise the name that's also a valid driver
+ * name
+ */
+const char *btrfs_super_csum_driver(u16 csum_type)
 {
-	return kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
+	/* csum type is validated at mount time */
+	return btrfs_csums[csum_type].driver ?:
+		btrfs_csums[csum_type].name;
 }
 
-/*
- * set all locked nodes in the path to blocking locks.  This should
- * be done before scheduling
- */
-noinline void btrfs_set_path_blocking(struct btrfs_path *p)
+size_t __const btrfs_get_num_csums(void)
 {
-	int i;
-	for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
-		if (!p->nodes[i] || !p->locks[i])
-			continue;
-		/*
-		 * If we currently have a spinning reader or writer lock this
-		 * will bump the count of blocking holders and drop the
-		 * spinlock.
-		 */
-		if (p->locks[i] == BTRFS_READ_LOCK) {
-			btrfs_set_lock_blocking_read(p->nodes[i]);
-			p->locks[i] = BTRFS_READ_LOCK_BLOCKING;
-		} else if (p->locks[i] == BTRFS_WRITE_LOCK) {
-			btrfs_set_lock_blocking_write(p->nodes[i]);
-			p->locks[i] = BTRFS_WRITE_LOCK_BLOCKING;
-		}
-	}
+	return ARRAY_SIZE(btrfs_csums);
+}
+
+struct btrfs_path *btrfs_alloc_path(void)
+{
+	return kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
 }
 
 /* this also releases the path */
@@ -1125,7 +1121,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 		    btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
 			parent_start = buf->start;
 
-		extent_buffer_get(cow);
+		atomic_inc(&cow->refs);
 		ret = tree_mod_log_insert_root(root->node, cow, 1);
 		BUG_ON(ret < 0);
 		rcu_assign_pointer(root->node, cow);
@@ -1563,7 +1559,7 @@ static int comp_keys(const struct btrfs_disk_key *disk,
 /*
  * same as comp_keys only with two btrfs_key's
  */
-int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2)
+int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2)
 {
 	if (k1->objectid > k2->objectid)
 		return 1;
@@ -2036,7 +2032,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 	/* update the path */
 	if (left) {
 		if (btrfs_header_nritems(left) > orig_slot) {
-			extent_buffer_get(left);
+			atomic_inc(&left->refs);
 			/* left was locked after cow */
 			path->nodes[level] = left;
 			path->slots[level + 1] -= 1;
@@ -2379,32 +2375,6 @@ static noinline void unlock_up(struct btrfs_path *path, int level,
 }
 
 /*
- * This releases any locks held in the path starting at level and
- * going all the way up to the root.
- *
- * btrfs_search_slot will keep the lock held on higher nodes in a few
- * corner cases, such as COW of the block at slot zero in the node.  This
- * ignores those rules, and it should only be called when there are no
- * more updates to be done higher up in the tree.
- */
-noinline void btrfs_unlock_up_safe(struct btrfs_path *path, int level)
-{
-	int i;
-
-	if (path->keep_locks)
-		return;
-
-	for (i = level; i < BTRFS_MAX_LEVEL; i++) {
-		if (!path->nodes[i])
-			continue;
-		if (!path->locks[i])
-			continue;
-		btrfs_tree_unlock_rw(path->nodes[i], path->locks[i]);
-		path->locks[i] = 0;
-	}
-}
-
-/*
  * helper function for btrfs_search_slot.  The goal is to find a block
  * in cache without setting the path to blocking.  If we find the block
  * we return zero and the path is unchanged.
@@ -2652,7 +2622,7 @@ static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root,
 
 		} else {
 			b = root->commit_root;
-			extent_buffer_get(b);
+			atomic_inc(&b->refs);
 		}
 		level = btrfs_header_level(b);
 		/*
@@ -2785,12 +2755,10 @@ again:
 	}
 
 	while (b) {
+		int dec = 0;
+
 		level = btrfs_header_level(b);
 
-		/*
-		 * setup the path here so we can release it under lock
-		 * contention with the cow code
-		 */
 		if (cow) {
 			bool last_level = (level == (BTRFS_MAX_LEVEL - 1));
 
@@ -2861,73 +2829,7 @@ cow_done:
 		if (ret < 0)
 			goto done;
 
-		if (level != 0) {
-			int dec = 0;
-			if (ret && slot > 0) {
-				dec = 1;
-				slot -= 1;
-			}
-			p->slots[level] = slot;
-			err = setup_nodes_for_search(trans, root, p, b, level,
-					     ins_len, &write_lock_level);
-			if (err == -EAGAIN)
-				goto again;
-			if (err) {
-				ret = err;
-				goto done;
-			}
-			b = p->nodes[level];
-			slot = p->slots[level];
-
-			/*
-			 * slot 0 is special, if we change the key
-			 * we have to update the parent pointer
-			 * which means we must have a write lock
-			 * on the parent
-			 */
-			if (slot == 0 && ins_len &&
-			    write_lock_level < level + 1) {
-				write_lock_level = level + 1;
-				btrfs_release_path(p);
-				goto again;
-			}
-
-			unlock_up(p, level, lowest_unlock,
-				  min_write_lock_level, &write_lock_level);
-
-			if (level == lowest_level) {
-				if (dec)
-					p->slots[level]++;
-				goto done;
-			}
-
-			err = read_block_for_search(root, p, &b, level,
-						    slot, key);
-			if (err == -EAGAIN)
-				goto again;
-			if (err) {
-				ret = err;
-				goto done;
-			}
-
-			if (!p->skip_locking) {
-				level = btrfs_header_level(b);
-				if (level <= write_lock_level) {
-					if (!btrfs_try_tree_write_lock(b)) {
-						btrfs_set_path_blocking(p);
-						btrfs_tree_lock(b);
-					}
-					p->locks[level] = BTRFS_WRITE_LOCK;
-				} else {
-					if (!btrfs_tree_read_lock_atomic(b)) {
-						btrfs_set_path_blocking(p);
-						btrfs_tree_read_lock(b);
-					}
-					p->locks[level] = BTRFS_READ_LOCK;
-				}
-				p->nodes[level] = b;
-			}
-		} else {
+		if (level == 0) {
 			p->slots[level] = slot;
 			if (ins_len > 0 &&
 			    btrfs_leaf_free_space(b) < ins_len) {
@@ -2952,6 +2854,67 @@ cow_done:
 					  min_write_lock_level, NULL);
 			goto done;
 		}
+		if (ret && slot > 0) {
+			dec = 1;
+			slot--;
+		}
+		p->slots[level] = slot;
+		err = setup_nodes_for_search(trans, root, p, b, level, ins_len,
+					     &write_lock_level);
+		if (err == -EAGAIN)
+			goto again;
+		if (err) {
+			ret = err;
+			goto done;
+		}
+		b = p->nodes[level];
+		slot = p->slots[level];
+
+		/*
+		 * Slot 0 is special, if we change the key we have to update
+		 * the parent pointer which means we must have a write lock on
+		 * the parent
+		 */
+		if (slot == 0 && ins_len && write_lock_level < level + 1) {
+			write_lock_level = level + 1;
+			btrfs_release_path(p);
+			goto again;
+		}
+
+		unlock_up(p, level, lowest_unlock, min_write_lock_level,
+			  &write_lock_level);
+
+		if (level == lowest_level) {
+			if (dec)
+				p->slots[level]++;
+			goto done;
+		}
+
+		err = read_block_for_search(root, p, &b, level, slot, key);
+		if (err == -EAGAIN)
+			goto again;
+		if (err) {
+			ret = err;
+			goto done;
+		}
+
+		if (!p->skip_locking) {
+			level = btrfs_header_level(b);
+			if (level <= write_lock_level) {
+				if (!btrfs_try_tree_write_lock(b)) {
+					btrfs_set_path_blocking(p);
+					btrfs_tree_lock(b);
+				}
+				p->locks[level] = BTRFS_WRITE_LOCK;
+			} else {
+				if (!btrfs_tree_read_lock_atomic(b)) {
+					btrfs_set_path_blocking(p);
+					btrfs_tree_read_lock(b);
+				}
+				p->locks[level] = BTRFS_READ_LOCK;
+			}
+			p->nodes[level] = b;
+		}
 	}
 	ret = 1;
 done:
@@ -3008,6 +2971,8 @@ again:
 	p->locks[level] = BTRFS_READ_LOCK;
 
 	while (b) {
+		int dec = 0;
+
 		level = btrfs_header_level(b);
 		p->nodes[level] = b;
 
@@ -3028,47 +2993,45 @@ again:
 		if (ret < 0)
 			goto done;
 
-		if (level != 0) {
-			int dec = 0;
-			if (ret && slot > 0) {
-				dec = 1;
-				slot -= 1;
-			}
+		if (level == 0) {
 			p->slots[level] = slot;
 			unlock_up(p, level, lowest_unlock, 0, NULL);
+			goto done;
+		}
 
-			if (level == lowest_level) {
-				if (dec)
-					p->slots[level]++;
-				goto done;
-			}
+		if (ret && slot > 0) {
+			dec = 1;
+			slot--;
+		}
+		p->slots[level] = slot;
+		unlock_up(p, level, lowest_unlock, 0, NULL);
 
-			err = read_block_for_search(root, p, &b, level,
-						    slot, key);
-			if (err == -EAGAIN)
-				goto again;
-			if (err) {
-				ret = err;
-				goto done;
-			}
+		if (level == lowest_level) {
+			if (dec)
+				p->slots[level]++;
+			goto done;
+		}
 
-			level = btrfs_header_level(b);
-			if (!btrfs_tree_read_lock_atomic(b)) {
-				btrfs_set_path_blocking(p);
-				btrfs_tree_read_lock(b);
-			}
-			b = tree_mod_log_rewind(fs_info, p, b, time_seq);
-			if (!b) {
-				ret = -ENOMEM;
-				goto done;
-			}
-			p->locks[level] = BTRFS_READ_LOCK;
-			p->nodes[level] = b;
-		} else {
-			p->slots[level] = slot;
-			unlock_up(p, level, lowest_unlock, 0, NULL);
+		err = read_block_for_search(root, p, &b, level, slot, key);
+		if (err == -EAGAIN)
+			goto again;
+		if (err) {
+			ret = err;
+			goto done;
+		}
+
+		level = btrfs_header_level(b);
+		if (!btrfs_tree_read_lock_atomic(b)) {
+			btrfs_set_path_blocking(p);
+			btrfs_tree_read_lock(b);
+		}
+		b = tree_mod_log_rewind(fs_info, p, b, time_seq);
+		if (!b) {
+			ret = -ENOMEM;
 			goto done;
 		}
+		p->locks[level] = BTRFS_READ_LOCK;
+		p->nodes[level] = b;
 	}
 	ret = 1;
 done:
@@ -3433,7 +3396,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 	free_extent_buffer(old);
 
 	add_root_to_dirty_list(root);
-	extent_buffer_get(c);
+	atomic_inc(&c->refs);
 	path->nodes[level] = c;
 	path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
 	path->slots[level] = 0;
@@ -4966,7 +4929,7 @@ static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans,
 
 	root_sub_used(root, leaf->len);
 
-	extent_buffer_get(leaf);
+	atomic_inc(&leaf->refs);
 	btrfs_free_tree_block(trans, root, leaf, 0, 1);
 	free_extent_buffer_stale(leaf);
 }
@@ -5047,7 +5010,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			 * for possible call to del_ptr below
 			 */
 			slot = path->slots[1];
-			extent_buffer_get(leaf);
+			atomic_inc(&leaf->refs);
 
 			btrfs_set_path_blocking(path);
 			wret = push_leaf_left(trans, root, path, 1, 1,
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index fe2b8765d9e6..b2e8fd8a8e59 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -28,6 +28,7 @@
 #include <linux/dynamic_debug.h>
 #include <linux/refcount.h>
 #include <linux/crc32c.h>
+#include "extent-io-tree.h"
 #include "extent_io.h"
 #include "extent_map.h"
 #include "async-thread.h"
@@ -38,7 +39,7 @@ struct btrfs_transaction;
 struct btrfs_pending_snapshot;
 struct btrfs_delayed_ref_root;
 struct btrfs_space_info;
-struct btrfs_block_group_cache;
+struct btrfs_block_group;
 extern struct kmem_cache *btrfs_trans_handle_cachep;
 extern struct kmem_cache *btrfs_bit_radix_cachep;
 extern struct kmem_cache *btrfs_path_cachep;
@@ -56,9 +57,9 @@ struct btrfs_ref;
  * filesystem data as well that can be used to read data in order to repair
  * read errors on other disks.
  *
- * Current value is derived from RAID1 with 2 copies.
+ * Current value is derived from RAID1C4 with 4 copies.
  */
-#define BTRFS_MAX_MIRRORS (2 + 1)
+#define BTRFS_MAX_MIRRORS (4 + 1)
 
 #define BTRFS_MAX_LEVEL 8
 
@@ -291,7 +292,8 @@ struct btrfs_super_block {
 	 BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF |		\
 	 BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA |	\
 	 BTRFS_FEATURE_INCOMPAT_NO_HOLES	|	\
-	 BTRFS_FEATURE_INCOMPAT_METADATA_UUID)
+	 BTRFS_FEATURE_INCOMPAT_METADATA_UUID	|	\
+	 BTRFS_FEATURE_INCOMPAT_RAID1C34)
 
 #define BTRFS_FEATURE_INCOMPAT_SAFE_SET			\
 	(BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
@@ -413,7 +415,7 @@ struct btrfs_free_cluster {
 	/* We did a full search and couldn't create a cluster */
 	bool fragmented;
 
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	/*
 	 * when a cluster is allocated from a block group, we put the
 	 * cluster onto a list in the block group so that it can
@@ -476,8 +478,8 @@ struct btrfs_swapfile_pin {
 	void *ptr;
 	struct inode *inode;
 	/*
-	 * If true, ptr points to a struct btrfs_block_group_cache. Otherwise,
-	 * ptr points to a struct btrfs_device.
+	 * If true, ptr points to a struct btrfs_block_group. Otherwise, ptr
+	 * points to a struct btrfs_device.
 	 */
 	bool is_block_group;
 };
@@ -722,7 +724,6 @@ struct btrfs_fs_info {
 	struct btrfs_workqueue *endio_meta_write_workers;
 	struct btrfs_workqueue *endio_write_workers;
 	struct btrfs_workqueue *endio_freespace_worker;
-	struct btrfs_workqueue *submit_workers;
 	struct btrfs_workqueue *caching_workers;
 	struct btrfs_workqueue *readahead_workers;
 
@@ -1519,18 +1520,18 @@ static inline u64 btrfs_stripe_devid_nr(struct extent_buffer *eb,
 }
 
 /* struct btrfs_block_group_item */
-BTRFS_SETGET_STACK_FUNCS(block_group_used, struct btrfs_block_group_item,
+BTRFS_SETGET_STACK_FUNCS(stack_block_group_used, struct btrfs_block_group_item,
 			 used, 64);
-BTRFS_SETGET_FUNCS(disk_block_group_used, struct btrfs_block_group_item,
+BTRFS_SETGET_FUNCS(block_group_used, struct btrfs_block_group_item,
 			 used, 64);
-BTRFS_SETGET_STACK_FUNCS(block_group_chunk_objectid,
+BTRFS_SETGET_STACK_FUNCS(stack_block_group_chunk_objectid,
 			struct btrfs_block_group_item, chunk_objectid, 64);
 
-BTRFS_SETGET_FUNCS(disk_block_group_chunk_objectid,
+BTRFS_SETGET_FUNCS(block_group_chunk_objectid,
 		   struct btrfs_block_group_item, chunk_objectid, 64);
-BTRFS_SETGET_FUNCS(disk_block_group_flags,
+BTRFS_SETGET_FUNCS(block_group_flags,
 		   struct btrfs_block_group_item, flags, 64);
-BTRFS_SETGET_STACK_FUNCS(block_group_flags,
+BTRFS_SETGET_STACK_FUNCS(stack_block_group_flags,
 			struct btrfs_block_group_item, flags, 64);
 
 /* struct btrfs_free_space_info */
@@ -2163,6 +2164,9 @@ BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block,
 
 int btrfs_super_csum_size(const struct btrfs_super_block *s);
 const char *btrfs_super_csum_name(u16 csum_type);
+const char *btrfs_super_csum_driver(u16 csum_type);
+size_t __const btrfs_get_num_csums(void);
+
 
 /*
  * The leaf data grows from end-to-front in the node.
@@ -2397,7 +2401,7 @@ static inline u64 btrfs_calc_metadata_size(struct btrfs_fs_info *fs_info,
 
 int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info,
 			      u64 start, u64 num_bytes);
-void btrfs_free_excluded_extents(struct btrfs_block_group_cache *cache);
+void btrfs_free_excluded_extents(struct btrfs_block_group *cache);
 int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			   unsigned long count);
 void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
@@ -2453,8 +2457,8 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 struct btrfs_ref *generic_ref);
 
 int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr);
-void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache);
-void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache);
+void btrfs_get_block_group_trimming(struct btrfs_block_group *cache);
+void btrfs_put_block_group_trimming(struct btrfs_block_group *cache);
 void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
 
 enum btrfs_reserve_flush_enum {
@@ -2507,7 +2511,7 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
 		     int level, int *slot);
-int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
+int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
 int btrfs_previous_item(struct btrfs_root *root,
 			struct btrfs_path *path, u64 min_objectid,
 			int type);
@@ -2567,8 +2571,6 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 void btrfs_release_path(struct btrfs_path *p);
 struct btrfs_path *btrfs_alloc_path(void);
 void btrfs_free_path(struct btrfs_path *p);
-void btrfs_set_path_blocking(struct btrfs_path *p);
-void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
 
 int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		   struct btrfs_path *path, int slot, int nr);
@@ -2870,10 +2872,9 @@ int btrfs_drop_inode(struct inode *inode);
 int __init btrfs_init_cachep(void);
 void __cold btrfs_destroy_cachep(void);
 struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
-			      struct btrfs_root *root, int *new,
-			      struct btrfs_path *path);
+			      struct btrfs_root *root, struct btrfs_path *path);
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
-			 struct btrfs_root *root, int *was_new);
+			 struct btrfs_root *root);
 struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 				    struct page *page, size_t pg_offset,
 				    u64 start, u64 end, int create);
@@ -2909,7 +2910,7 @@ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int btrfs_ioctl_get_supported_features(void __user *arg);
 void btrfs_sync_inode_flags_to_i_flags(struct inode *inode);
-int btrfs_is_empty_uuid(u8 *uuid);
+int __pure btrfs_is_empty_uuid(u8 *uuid);
 int btrfs_defrag_file(struct inode *inode, struct file *file,
 		      struct btrfs_ioctl_defrag_range_args *range,
 		      u64 newer_than, unsigned long max_pages);
@@ -3143,7 +3144,7 @@ __cold
 void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
 		     unsigned int line, int errno, const char *fmt, ...);
 
-const char *btrfs_decode_error(int errno);
+const char * __attribute_const__ btrfs_decode_error(int errno);
 
 __cold
 void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index db9f2c58eb4a..4cdac4d834f5 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -307,7 +307,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	unsigned nr_extents;
 	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
 	int ret = 0;
-	bool delalloc_lock = true;
 
 	/*
 	 * If we are a free space inode we need to not flush since we will be in
@@ -320,7 +319,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	 */
 	if (btrfs_is_free_space_inode(inode)) {
 		flush = BTRFS_RESERVE_NO_FLUSH;
-		delalloc_lock = false;
 	} else {
 		if (current->journal_info)
 			flush = BTRFS_RESERVE_FLUSH_LIMIT;
@@ -329,9 +327,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 			schedule_timeout(1);
 	}
 
-	if (delalloc_lock)
-		mutex_lock(&inode->delalloc_mutex);
-
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
 
 	/*
@@ -348,10 +343,12 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 				&qgroup_reserve);
 	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true);
 	if (ret)
-		goto out_fail;
+		return ret;
 	ret = btrfs_reserve_metadata_bytes(root, block_rsv, meta_reserve, flush);
-	if (ret)
-		goto out_qgroup;
+	if (ret) {
+		btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve);
+		return ret;
+	}
 
 	/*
 	 * Now we need to update our outstanding extents and csum bytes _first_
@@ -375,15 +372,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	block_rsv->qgroup_rsv_reserved += qgroup_reserve;
 	spin_unlock(&block_rsv->lock);
 
-	if (delalloc_lock)
-		mutex_unlock(&inode->delalloc_mutex);
 	return 0;
-out_qgroup:
-	btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve);
-out_fail:
-	if (delalloc_lock)
-		mutex_unlock(&inode->delalloc_mutex);
-	return ret;
 }
 
 /**
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 1f7f39b10bd0..d3e15e1d4a91 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -12,6 +12,7 @@
 #include "transaction.h"
 #include "ctree.h"
 #include "qgroup.h"
+#include "locking.h"
 
 #define BTRFS_DELAYED_WRITEBACK		512
 #define BTRFS_DELAYED_BACKGROUND	128
@@ -1367,8 +1368,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
 		return -ENOMEM;
 
 	async_work->delayed_root = delayed_root;
-	btrfs_init_work(&async_work->work, btrfs_delayed_meta_helper,
-			btrfs_async_run_delayed_root, NULL, NULL);
+	btrfs_init_work(&async_work->work, btrfs_async_run_delayed_root, NULL,
+			NULL);
 	async_work->nr = nr;
 
 	btrfs_queue_work(fs_info->delayed_workers, &async_work->work);
@@ -1949,12 +1950,19 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root)
 		}
 
 		inode_id = delayed_nodes[n - 1]->inode_id + 1;
-
-		for (i = 0; i < n; i++)
-			refcount_inc(&delayed_nodes[i]->refs);
+		for (i = 0; i < n; i++) {
+			/*
+			 * Don't increase refs in case the node is dead and
+			 * about to be removed from the tree in the loop below
+			 */
+			if (!refcount_inc_not_zero(&delayed_nodes[i]->refs))
+				delayed_nodes[i] = NULL;
+		}
 		spin_unlock(&root->inode_lock);
 
 		for (i = 0; i < n; i++) {
+			if (!delayed_nodes[i])
+				continue;
 			__btrfs_kill_delayed_node(delayed_nodes[i]);
 			btrfs_release_delayed_node(delayed_nodes[i]);
 		}
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 48890826b5e6..f639dde2a679 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -986,7 +986,7 @@ static int btrfs_dev_replace_kthread(void *data)
 	return 0;
 }
 
-int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
+int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
 {
 	if (!dev_replace->is_valid)
 		return 0;
diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h
index 78c5d8f1adda..60b70dacc299 100644
--- a/fs/btrfs/dev-replace.h
+++ b/fs/btrfs/dev-replace.h
@@ -17,6 +17,6 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info);
 void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info);
 int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info);
-int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
+int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
 
 #endif
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 402b61bf345c..e0edfdc9c82b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -205,7 +205,6 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode,
 		struct page *page, size_t pg_offset, u64 start, u64 len,
 		int create)
 {
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	int ret;
@@ -213,7 +212,6 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode,
 	read_lock(&em_tree->lock);
 	em = lookup_extent_mapping(em_tree, start, len);
 	if (em) {
-		em->bdev = fs_info->fs_devices->latest_bdev;
 		read_unlock(&em_tree->lock);
 		goto out;
 	}
@@ -228,7 +226,6 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode,
 	em->len = (u64)-1;
 	em->block_len = (u64)-1;
 	em->block_start = 0;
-	em->bdev = fs_info->fs_devices->latest_bdev;
 
 	write_lock(&em_tree->lock);
 	ret = add_extent_mapping(em_tree, em, 0);
@@ -352,6 +349,9 @@ static bool btrfs_supported_super_csum(u16 csum_type)
 {
 	switch (csum_type) {
 	case BTRFS_CSUM_TYPE_CRC32:
+	case BTRFS_CSUM_TYPE_XXHASH:
+	case BTRFS_CSUM_TYPE_SHA256:
+	case BTRFS_CSUM_TYPE_BLAKE2:
 		return true;
 	default:
 		return false;
@@ -545,9 +545,11 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
 		ret = btrfs_check_leaf_full(eb);
 
 	if (ret < 0) {
+		btrfs_print_tree(eb, 0);
 		btrfs_err(fs_info,
 		"block=%llu write time tree block corruption detected",
 			  eb->start);
+		WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
 		return ret;
 	}
 	write_extent_buffer(eb, result, 0, csum_size);
@@ -608,7 +610,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	/* the pending IO might have been the only thing that kept this buffer
 	 * in memory.  Make sure we have a ref for all this other checks
 	 */
-	extent_buffer_get(eb);
+	atomic_inc(&eb->refs);
 
 	reads_done = atomic_dec_and_test(&eb->io_pages);
 	if (!reads_done)
@@ -706,43 +708,31 @@ static void end_workqueue_bio(struct bio *bio)
 	struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_workqueue *wq;
-	btrfs_work_func_t func;
 
 	fs_info = end_io_wq->info;
 	end_io_wq->status = bio->bi_status;
 
 	if (bio_op(bio) == REQ_OP_WRITE) {
-		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
+		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
 			wq = fs_info->endio_meta_write_workers;
-			func = btrfs_endio_meta_write_helper;
-		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) {
+		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
 			wq = fs_info->endio_freespace_worker;
-			func = btrfs_freespace_write_helper;
-		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
 			wq = fs_info->endio_raid56_workers;
-			func = btrfs_endio_raid56_helper;
-		} else {
+		else
 			wq = fs_info->endio_write_workers;
-			func = btrfs_endio_write_helper;
-		}
 	} else {
-		if (unlikely(end_io_wq->metadata ==
-			     BTRFS_WQ_ENDIO_DIO_REPAIR)) {
+		if (unlikely(end_io_wq->metadata == BTRFS_WQ_ENDIO_DIO_REPAIR))
 			wq = fs_info->endio_repair_workers;
-			func = btrfs_endio_repair_helper;
-		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
 			wq = fs_info->endio_raid56_workers;
-			func = btrfs_endio_raid56_helper;
-		} else if (end_io_wq->metadata) {
+		else if (end_io_wq->metadata)
 			wq = fs_info->endio_meta_workers;
-			func = btrfs_endio_meta_helper;
-		} else {
+		else
 			wq = fs_info->endio_workers;
-			func = btrfs_endio_helper;
-		}
 	}
 
-	btrfs_init_work(&end_io_wq->work, func, end_workqueue_fn, NULL, NULL);
+	btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
 	btrfs_queue_work(wq, &end_io_wq->work);
 }
 
@@ -803,8 +793,13 @@ static void run_one_async_done(struct btrfs_work *work)
 		return;
 	}
 
-	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio,
-			async->mirror_num, 1);
+	/*
+	 * All of the bios that pass through here are from async helpers.
+	 * Use REQ_CGROUP_PUNT to issue them from the owning cgroup's context.
+	 * This changes nothing when cgroups aren't in use.
+	 */
+	async->bio->bi_opf |= REQ_CGROUP_PUNT;
+	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio, async->mirror_num);
 	if (ret) {
 		async->bio->bi_status = ret;
 		bio_endio(async->bio);
@@ -835,8 +830,8 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	async->mirror_num = mirror_num;
 	async->submit_bio_start = submit_bio_start;
 
-	btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
-			run_one_async_done, run_one_async_free);
+	btrfs_init_work(&async->work, run_one_async_start, run_one_async_done,
+			run_one_async_free);
 
 	async->bio_offset = bio_offset;
 
@@ -904,12 +899,12 @@ static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio,
 					  BTRFS_WQ_ENDIO_METADATA);
 		if (ret)
 			goto out_w_error;
-		ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+		ret = btrfs_map_bio(fs_info, bio, mirror_num);
 	} else if (!async) {
 		ret = btree_csum_one_bio(bio);
 		if (ret)
 			goto out_w_error;
-		ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+		ret = btrfs_map_bio(fs_info, bio, mirror_num);
 	} else {
 		/*
 		 * kthread helpers are used to submit writes so that
@@ -1657,8 +1652,8 @@ static void end_workqueue_fn(struct btrfs_work *work)
 	bio->bi_status = end_io_wq->status;
 	bio->bi_private = end_io_wq->private;
 	bio->bi_end_io = end_io_wq->end_io;
-	kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
 	bio_endio(bio);
+	kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
 }
 
 static int cleaner_kthread(void *arg)
@@ -1753,7 +1748,7 @@ static int transaction_kthread(void *arg)
 		}
 
 		now = ktime_get_seconds();
-		if (cur->state < TRANS_STATE_BLOCKED &&
+		if (cur->state < TRANS_STATE_COMMIT_START &&
 		    !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) &&
 		    (now < cur->start_time ||
 		     now - cur->start_time < fs_info->commit_interval)) {
@@ -1792,18 +1787,18 @@ sleep:
 }
 
 /*
- * this will find the highest generation in the array of
- * root backups.  The index of the highest array is returned,
- * or -1 if we can't find anything.
+ * This will find the highest generation in the array of root backups.  The
+ * index of the highest array is returned, or -EINVAL if we can't find
+ * anything.
  *
  * We check to make sure the array is valid by comparing the
  * generation of the latest  root in the array with the generation
  * in the super block.  If they don't match we pitch it.
  */
-static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen)
+static int find_newest_super_backup(struct btrfs_fs_info *info)
 {
+	const u64 newest_gen = btrfs_super_generation(info->super_copy);
 	u64 cur;
-	int newest_index = -1;
 	struct btrfs_root_backup *root_backup;
 	int i;
 
@@ -1811,37 +1806,10 @@ static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen)
 		root_backup = info->super_copy->super_roots + i;
 		cur = btrfs_backup_tree_root_gen(root_backup);
 		if (cur == newest_gen)
-			newest_index = i;
+			return i;
 	}
 
-	/* check to see if we actually wrapped around */
-	if (newest_index == BTRFS_NUM_BACKUP_ROOTS - 1) {
-		root_backup = info->super_copy->super_roots;
-		cur = btrfs_backup_tree_root_gen(root_backup);
-		if (cur == newest_gen)
-			newest_index = 0;
-	}
-	return newest_index;
-}
-
-
-/*
- * find the oldest backup so we know where to store new entries
- * in the backup array.  This will set the backup_root_index
- * field in the fs_info struct
- */
-static void find_oldest_super_backup(struct btrfs_fs_info *info,
-				     u64 newest_gen)
-{
-	int newest_index = -1;
-
-	newest_index = find_newest_super_backup(info, newest_gen);
-	/* if there was garbage in there, just move along */
-	if (newest_index == -1) {
-		info->backup_root_index = 0;
-	} else {
-		info->backup_root_index = (newest_index + 1) % BTRFS_NUM_BACKUP_ROOTS;
-	}
+	return -EINVAL;
 }
 
 /*
@@ -1851,22 +1819,8 @@ static void find_oldest_super_backup(struct btrfs_fs_info *info,
  */
 static void backup_super_roots(struct btrfs_fs_info *info)
 {
-	int next_backup;
+	const int next_backup = info->backup_root_index;
 	struct btrfs_root_backup *root_backup;
-	int last_backup;
-
-	next_backup = info->backup_root_index;
-	last_backup = (next_backup + BTRFS_NUM_BACKUP_ROOTS - 1) %
-		BTRFS_NUM_BACKUP_ROOTS;
-
-	/*
-	 * just overwrite the last backup if we're at the same generation
-	 * this happens only at umount
-	 */
-	root_backup = info->super_for_commit->super_roots + last_backup;
-	if (btrfs_backup_tree_root_gen(root_backup) ==
-	    btrfs_header_generation(info->tree_root->node))
-		next_backup = last_backup;
 
 	root_backup = info->super_for_commit->super_roots + next_backup;
 
@@ -1939,40 +1893,31 @@ static void backup_super_roots(struct btrfs_fs_info *info)
 }
 
 /*
- * this copies info out of the root backup array and back into
- * the in-memory super block.  It is meant to help iterate through
- * the array, so you send it the number of backups you've already
- * tried and the last backup index you used.
+ * read_backup_root - Reads a backup root based on the passed priority. Prio 0
+ * is the newest, prio 1/2/3 are 2nd newest/3rd newest/4th (oldest) backup roots
  *
- * this returns -1 when it has tried all the backups
+ * fs_info - filesystem whose backup roots need to be read
+ * priority - priority of backup root required
+ *
+ * Returns backup root index on success and -EINVAL otherwise.
  */
-static noinline int next_root_backup(struct btrfs_fs_info *info,
-				     struct btrfs_super_block *super,
-				     int *num_backups_tried, int *backup_index)
+static int read_backup_root(struct btrfs_fs_info *fs_info, u8 priority)
 {
+	int backup_index = find_newest_super_backup(fs_info);
+	struct btrfs_super_block *super = fs_info->super_copy;
 	struct btrfs_root_backup *root_backup;
-	int newest = *backup_index;
-
-	if (*num_backups_tried == 0) {
-		u64 gen = btrfs_super_generation(super);
 
-		newest = find_newest_super_backup(info, gen);
-		if (newest == -1)
-			return -1;
+	if (priority < BTRFS_NUM_BACKUP_ROOTS && backup_index >= 0) {
+		if (priority == 0)
+			return backup_index;
 
-		*backup_index = newest;
-		*num_backups_tried = 1;
-	} else if (*num_backups_tried == BTRFS_NUM_BACKUP_ROOTS) {
-		/* we've tried all the backups, all done */
-		return -1;
+		backup_index = backup_index + BTRFS_NUM_BACKUP_ROOTS - priority;
+		backup_index %= BTRFS_NUM_BACKUP_ROOTS;
 	} else {
-		/* jump to the next oldest backup */
-		newest = (*backup_index + BTRFS_NUM_BACKUP_ROOTS - 1) %
-			BTRFS_NUM_BACKUP_ROOTS;
-		*backup_index = newest;
-		*num_backups_tried += 1;
+		return -EINVAL;
 	}
-	root_backup = super->super_roots + newest;
+
+	root_backup = super->super_roots + backup_index;
 
 	btrfs_set_super_generation(super,
 				   btrfs_backup_tree_root_gen(root_backup));
@@ -1982,12 +1927,13 @@ static noinline int next_root_backup(struct btrfs_fs_info *info,
 	btrfs_set_super_bytes_used(super, btrfs_backup_bytes_used(root_backup));
 
 	/*
-	 * fixme: the total bytes and num_devices need to match or we should
+	 * Fixme: the total bytes and num_devices need to match or we should
 	 * need a fsck
 	 */
 	btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup));
 	btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup));
-	return 0;
+
+	return backup_index;
 }
 
 /* helper to cleanup workers */
@@ -2002,7 +1948,6 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_workqueue(fs_info->rmw_workers);
 	btrfs_destroy_workqueue(fs_info->endio_write_workers);
 	btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
-	btrfs_destroy_workqueue(fs_info->submit_workers);
 	btrfs_destroy_workqueue(fs_info->delayed_workers);
 	btrfs_destroy_workqueue(fs_info->caching_workers);
 	btrfs_destroy_workqueue(fs_info->readahead_workers);
@@ -2028,7 +1973,7 @@ static void free_root_extent_buffers(struct btrfs_root *root)
 }
 
 /* helper to cleanup tree roots */
-static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
+static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root)
 {
 	free_root_extent_buffers(info->tree_root);
 
@@ -2037,7 +1982,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
 	free_root_extent_buffers(info->csum_root);
 	free_root_extent_buffers(info->quota_root);
 	free_root_extent_buffers(info->uuid_root);
-	if (chunk_root)
+	if (free_chunk_root)
 		free_root_extent_buffers(info->chunk_root);
 	free_root_extent_buffers(info->free_space_root);
 }
@@ -2167,16 +2112,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 	fs_info->caching_workers =
 		btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0);
 
-	/*
-	 * a higher idle thresh on the submit workers makes it much more
-	 * likely that bios will be send down in a sane order to the
-	 * devices
-	 */
-	fs_info->submit_workers =
-		btrfs_alloc_workqueue(fs_info, "submit", flags,
-				      min_t(u64, fs_devices->num_devices,
-					    max_active), 64);
-
 	fs_info->fixup_workers =
 		btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0);
 
@@ -2215,7 +2150,7 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 		btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0);
 
 	if (!(fs_info->workers && fs_info->delalloc_workers &&
-	      fs_info->submit_workers && fs_info->flush_workers &&
+	      fs_info->flush_workers &&
 	      fs_info->endio_workers && fs_info->endio_meta_workers &&
 	      fs_info->endio_meta_write_workers &&
 	      fs_info->endio_repair_workers &&
@@ -2233,13 +2168,13 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type)
 {
 	struct crypto_shash *csum_shash;
-	const char *csum_name = btrfs_super_csum_name(csum_type);
+	const char *csum_driver = btrfs_super_csum_driver(csum_type);
 
-	csum_shash = crypto_alloc_shash(csum_name, 0, 0);
+	csum_shash = crypto_alloc_shash(csum_driver, 0, 0);
 
 	if (IS_ERR(csum_shash)) {
 		btrfs_err(fs_info, "error allocating %s hash for checksum",
-			  csum_name);
+			  csum_driver);
 		return PTR_ERR(csum_shash);
 	}
 
@@ -2589,7 +2524,101 @@ out:
 	return ret;
 }
 
-int open_ctree(struct super_block *sb,
+static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
+{
+	int backup_index = find_newest_super_backup(fs_info);
+	struct btrfs_super_block *sb = fs_info->super_copy;
+	struct btrfs_root *tree_root = fs_info->tree_root;
+	bool handle_error = false;
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
+		u64 generation;
+		int level;
+
+		if (handle_error) {
+			if (!IS_ERR(tree_root->node))
+				free_extent_buffer(tree_root->node);
+			tree_root->node = NULL;
+
+			if (!btrfs_test_opt(fs_info, USEBACKUPROOT))
+				break;
+
+			free_root_pointers(fs_info, 0);
+
+			/*
+			 * Don't use the log in recovery mode, it won't be
+			 * valid
+			 */
+			btrfs_set_super_log_root(sb, 0);
+
+			/* We can't trust the free space cache either */
+			btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE);
+
+			ret = read_backup_root(fs_info, i);
+			backup_index = ret;
+			if (ret < 0)
+				return ret;
+		}
+		generation = btrfs_super_generation(sb);
+		level = btrfs_super_root_level(sb);
+		tree_root->node = read_tree_block(fs_info, btrfs_super_root(sb),
+						  generation, level, NULL);
+		if (IS_ERR(tree_root->node) ||
+		    !extent_buffer_uptodate(tree_root->node)) {
+			handle_error = true;
+
+			if (IS_ERR(tree_root->node))
+				ret = PTR_ERR(tree_root->node);
+			else if (!extent_buffer_uptodate(tree_root->node))
+				ret = -EUCLEAN;
+
+			btrfs_warn(fs_info, "failed to read tree root");
+			continue;
+		}
+
+		btrfs_set_root_node(&tree_root->root_item, tree_root->node);
+		tree_root->commit_root = btrfs_root_node(tree_root);
+		btrfs_set_root_refs(&tree_root->root_item, 1);
+
+		/*
+		 * No need to hold btrfs_root::objectid_mutex since the fs
+		 * hasn't been fully initialised and we are the only user
+		 */
+		ret = btrfs_find_highest_objectid(tree_root,
+						&tree_root->highest_objectid);
+		if (ret < 0) {
+			handle_error = true;
+			continue;
+		}
+
+		ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+		ret = btrfs_read_roots(fs_info);
+		if (ret < 0) {
+			handle_error = true;
+			continue;
+		}
+
+		/* All successful */
+		fs_info->generation = generation;
+		fs_info->last_trans_committed = generation;
+
+		/* Always begin writing backup roots after the one being used */
+		if (backup_index < 0) {
+			fs_info->backup_root_index = 0;
+		} else {
+			fs_info->backup_root_index = backup_index + 1;
+			fs_info->backup_root_index %= BTRFS_NUM_BACKUP_ROOTS;
+		}
+		break;
+	}
+
+	return ret;
+}
+
+int __cold open_ctree(struct super_block *sb,
 	       struct btrfs_fs_devices *fs_devices,
 	       char *options)
 {
@@ -2607,8 +2636,6 @@ int open_ctree(struct super_block *sb,
 	struct btrfs_root *chunk_root;
 	int ret;
 	int err = -EINVAL;
-	int num_backups_tried = 0;
-	int backup_index = 0;
 	int clear_free_space_tree = 0;
 	int level;
 
@@ -2879,13 +2906,6 @@ int open_ctree(struct super_block *sb,
 		set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
 
 	/*
-	 * run through our array of backup supers and setup
-	 * our ring pointer to the oldest one
-	 */
-	generation = btrfs_super_generation(disk_super);
-	find_oldest_super_backup(fs_info, generation);
-
-	/*
 	 * In the long term, we'll store the compression type in the super
 	 * block, and it'll be used for per file compression control.
 	 */
@@ -3031,44 +3051,9 @@ int open_ctree(struct super_block *sb,
 		goto fail_tree_roots;
 	}
 
-retry_root_backup:
-	generation = btrfs_super_generation(disk_super);
-	level = btrfs_super_root_level(disk_super);
-
-	tree_root->node = read_tree_block(fs_info,
-					  btrfs_super_root(disk_super),
-					  generation, level, NULL);
-	if (IS_ERR(tree_root->node) ||
-	    !extent_buffer_uptodate(tree_root->node)) {
-		btrfs_warn(fs_info, "failed to read tree root");
-		if (!IS_ERR(tree_root->node))
-			free_extent_buffer(tree_root->node);
-		tree_root->node = NULL;
-		goto recovery_tree_root;
-	}
-
-	btrfs_set_root_node(&tree_root->root_item, tree_root->node);
-	tree_root->commit_root = btrfs_root_node(tree_root);
-	btrfs_set_root_refs(&tree_root->root_item, 1);
-
-	mutex_lock(&tree_root->objectid_mutex);
-	ret = btrfs_find_highest_objectid(tree_root,
-					&tree_root->highest_objectid);
-	if (ret) {
-		mutex_unlock(&tree_root->objectid_mutex);
-		goto recovery_tree_root;
-	}
-
-	ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
-
-	mutex_unlock(&tree_root->objectid_mutex);
-
-	ret = btrfs_read_roots(fs_info);
+	ret = init_tree_roots(fs_info);
 	if (ret)
-		goto recovery_tree_root;
-
-	fs_info->generation = generation;
-	fs_info->last_trans_committed = generation;
+		goto fail_tree_roots;
 
 	ret = btrfs_verify_dev_extents(fs_info);
 	if (ret) {
@@ -3336,7 +3321,7 @@ fail_block_groups:
 	btrfs_put_block_group_cache(fs_info);
 
 fail_tree_roots:
-	free_root_pointers(fs_info, 1);
+	free_root_pointers(fs_info, true);
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 
 fail_sb_buffer:
@@ -3363,24 +3348,6 @@ fail:
 	btrfs_free_stripe_hash_table(fs_info);
 	btrfs_close_devices(fs_info->fs_devices);
 	return err;
-
-recovery_tree_root:
-	if (!btrfs_test_opt(fs_info, USEBACKUPROOT))
-		goto fail_tree_roots;
-
-	free_root_pointers(fs_info, 0);
-
-	/* don't use the log in recovery mode, it won't be valid */
-	btrfs_set_super_log_root(disk_super, 0);
-
-	/* we can't trust the free space cache either */
-	btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE);
-
-	ret = next_root_backup(fs_info, fs_info->super_copy,
-			       &num_backups_tried, &backup_index);
-	if (ret == -1)
-		goto fail_block_groups;
-	goto retry_root_backup;
 }
 ALLOW_ERROR_INJECTION(open_ctree, ERRNO);
 
@@ -3974,7 +3941,7 @@ int btrfs_commit_super(struct btrfs_fs_info *fs_info)
 	return btrfs_commit_transaction(trans);
 }
 
-void close_ctree(struct btrfs_fs_info *fs_info)
+void __cold close_ctree(struct btrfs_fs_info *fs_info)
 {
 	int ret;
 
@@ -4062,7 +4029,7 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	btrfs_free_block_groups(fs_info);
 
 	clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
-	free_root_pointers(fs_info, 1);
+	free_root_pointers(fs_info, true);
 
 	iput(fs_info->btree_inode);
 
@@ -4439,7 +4406,7 @@ again:
 	return 0;
 }
 
-static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache)
+static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache)
 {
 	struct inode *inode;
 
@@ -4456,12 +4423,12 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache)
 void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
 			     struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 
 	spin_lock(&cur_trans->dirty_bgs_lock);
 	while (!list_empty(&cur_trans->dirty_bgs)) {
 		cache = list_first_entry(&cur_trans->dirty_bgs,
-					 struct btrfs_block_group_cache,
+					 struct btrfs_block_group,
 					 dirty_list);
 
 		if (!list_empty(&cache->io_list)) {
@@ -4489,7 +4456,7 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
 	 */
 	while (!list_empty(&cur_trans->io_bgs)) {
 		cache = list_first_entry(&cur_trans->io_bgs,
-					 struct btrfs_block_group_cache,
+					 struct btrfs_block_group,
 					 io_list);
 
 		list_del_init(&cache->io_list);
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index a6958103d87e..76f123ebb292 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -49,10 +49,10 @@ struct extent_buffer *btrfs_find_create_tree_block(
 						struct btrfs_fs_info *fs_info,
 						u64 bytenr);
 void btrfs_clean_tree_block(struct extent_buffer *buf);
-int open_ctree(struct super_block *sb,
+int __cold open_ctree(struct super_block *sb,
 	       struct btrfs_fs_devices *fs_devices,
 	       char *options);
-void close_ctree(struct btrfs_fs_info *fs_info);
+void __cold close_ctree(struct btrfs_fs_info *fs_info);
 int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors);
 struct buffer_head *btrfs_read_dev_super(struct block_device *bdev);
 int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num,
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index ddf28ecf17f9..72e312cae69d 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -87,7 +87,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	inode = btrfs_iget(sb, &key, root, NULL);
+	inode = btrfs_iget(sb, &key, root);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto fail;
@@ -214,7 +214,7 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
 
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
-	return d_obtain_alias(btrfs_iget(fs_info->sb, &key, root, NULL));
+	return d_obtain_alias(btrfs_iget(fs_info->sb, &key, root));
 fail:
 	btrfs_free_path(path);
 	return ERR_PTR(ret);
diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h
new file mode 100644
index 000000000000..a3febe746c79
--- /dev/null
+++ b/fs/btrfs/extent-io-tree.h
@@ -0,0 +1,248 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_EXTENT_IO_TREE_H
+#define BTRFS_EXTENT_IO_TREE_H
+
+struct extent_changeset;
+struct io_failure_record;
+
+/* Bits for the extent state */
+#define EXTENT_DIRTY		(1U << 0)
+#define EXTENT_UPTODATE		(1U << 1)
+#define EXTENT_LOCKED		(1U << 2)
+#define EXTENT_NEW		(1U << 3)
+#define EXTENT_DELALLOC		(1U << 4)
+#define EXTENT_DEFRAG		(1U << 5)
+#define EXTENT_BOUNDARY		(1U << 6)
+#define EXTENT_NODATASUM	(1U << 7)
+#define EXTENT_CLEAR_META_RESV	(1U << 8)
+#define EXTENT_NEED_WAIT	(1U << 9)
+#define EXTENT_DAMAGED		(1U << 10)
+#define EXTENT_NORESERVE	(1U << 11)
+#define EXTENT_QGROUP_RESERVED	(1U << 12)
+#define EXTENT_CLEAR_DATA_RESV	(1U << 13)
+#define EXTENT_DELALLOC_NEW	(1U << 14)
+#define EXTENT_DO_ACCOUNTING    (EXTENT_CLEAR_META_RESV | \
+				 EXTENT_CLEAR_DATA_RESV)
+#define EXTENT_CTLBITS		(EXTENT_DO_ACCOUNTING)
+
+/*
+ * Redefined bits above which are used only in the device allocation tree,
+ * shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV
+ * / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit
+ * manipulation functions
+ */
+#define CHUNK_ALLOCATED				EXTENT_DIRTY
+#define CHUNK_TRIMMED				EXTENT_DEFRAG
+
+enum {
+	IO_TREE_FS_INFO_FREED_EXTENTS0,
+	IO_TREE_FS_INFO_FREED_EXTENTS1,
+	IO_TREE_INODE_IO,
+	IO_TREE_INODE_IO_FAILURE,
+	IO_TREE_RELOC_BLOCKS,
+	IO_TREE_TRANS_DIRTY_PAGES,
+	IO_TREE_ROOT_DIRTY_LOG_PAGES,
+	IO_TREE_SELFTEST,
+};
+
+struct extent_io_tree {
+	struct rb_root state;
+	struct btrfs_fs_info *fs_info;
+	void *private_data;
+	u64 dirty_bytes;
+	bool track_uptodate;
+
+	/* Who owns this io tree, should be one of IO_TREE_* */
+	u8 owner;
+
+	spinlock_t lock;
+	const struct extent_io_ops *ops;
+};
+
+struct extent_state {
+	u64 start;
+	u64 end; /* inclusive */
+	struct rb_node rb_node;
+
+	/* ADD NEW ELEMENTS AFTER THIS */
+	wait_queue_head_t wq;
+	refcount_t refs;
+	unsigned state;
+
+	struct io_failure_record *failrec;
+
+#ifdef CONFIG_BTRFS_DEBUG
+	struct list_head leak_list;
+#endif
+};
+
+int __init extent_state_cache_init(void);
+void __cold extent_state_cache_exit(void);
+
+void extent_io_tree_init(struct btrfs_fs_info *fs_info,
+			 struct extent_io_tree *tree, unsigned int owner,
+			 void *private_data);
+void extent_io_tree_release(struct extent_io_tree *tree);
+
+int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+		     struct extent_state **cached);
+
+static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
+{
+	return lock_extent_bits(tree, start, end, NULL);
+}
+
+int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
+
+int __init extent_io_init(void);
+void __cold extent_io_exit(void);
+
+u64 count_range_bits(struct extent_io_tree *tree,
+		     u64 *start, u64 search_end,
+		     u64 max_bytes, unsigned bits, int contig);
+
+void free_extent_state(struct extent_state *state);
+int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		   unsigned bits, int filled,
+		   struct extent_state *cached_state);
+int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+		unsigned bits, struct extent_changeset *changeset);
+int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		     unsigned bits, int wake, int delete,
+		     struct extent_state **cached);
+int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		     unsigned bits, int wake, int delete,
+		     struct extent_state **cached, gfp_t mask,
+		     struct extent_changeset *changeset);
+
+static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
+{
+	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL);
+}
+
+static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached)
+{
+	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
+				GFP_NOFS, NULL);
+}
+
+static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree,
+		u64 start, u64 end, struct extent_state **cached)
+{
+	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
+				GFP_ATOMIC, NULL);
+}
+
+static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
+		u64 end, unsigned bits)
+{
+	int wake = 0;
+
+	if (bits & EXTENT_LOCKED)
+		wake = 1;
+
+	return clear_extent_bit(tree, start, end, bits, wake, 0, NULL);
+}
+
+int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+			   unsigned bits, struct extent_changeset *changeset);
+int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		   unsigned bits, u64 *failed_start,
+		   struct extent_state **cached_state, gfp_t mask);
+int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end,
+			   unsigned bits);
+
+static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
+		u64 end, unsigned bits)
+{
+	return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS);
+}
+
+static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached_state)
+{
+	return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
+				cached_state, GFP_NOFS, NULL);
+}
+
+static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
+		u64 end, gfp_t mask)
+{
+	return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
+			      NULL, mask);
+}
+
+static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
+				     u64 end, struct extent_state **cached)
+{
+	return clear_extent_bit(tree, start, end,
+				EXTENT_DIRTY | EXTENT_DELALLOC |
+				EXTENT_DO_ACCOUNTING, 0, 0, cached);
+}
+
+int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		       unsigned bits, unsigned clear_bits,
+		       struct extent_state **cached_state);
+
+static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
+				      u64 end, unsigned int extra_bits,
+				      struct extent_state **cached_state)
+{
+	return set_extent_bit(tree, start, end,
+			      EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
+			      NULL, cached_state, GFP_NOFS);
+}
+
+static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached_state)
+{
+	return set_extent_bit(tree, start, end,
+			      EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
+			      NULL, cached_state, GFP_NOFS);
+}
+
+static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
+		u64 end)
+{
+	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL,
+			GFP_NOFS);
+}
+
+static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached_state, gfp_t mask)
+{
+	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL,
+			      cached_state, mask);
+}
+
+int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
+			  u64 *start_ret, u64 *end_ret, unsigned bits,
+			  struct extent_state **cached_state);
+void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
+				 u64 *start_ret, u64 *end_ret, unsigned bits);
+int extent_invalidatepage(struct extent_io_tree *tree,
+			  struct page *page, unsigned long offset);
+bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
+			       u64 *end, u64 max_bytes,
+			       struct extent_state **cached_state);
+
+/* This should be reworked in the future and put elsewhere. */
+int get_state_failrec(struct extent_io_tree *tree, u64 start,
+		      struct io_failure_record **failrec);
+int set_state_failrec(struct extent_io_tree *tree, u64 start,
+		      struct io_failure_record *failrec);
+void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
+		u64 end);
+int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
+				struct io_failure_record **failrec_ret);
+int free_io_failure(struct extent_io_tree *failure_tree,
+		    struct extent_io_tree *io_tree,
+		    struct io_failure_record *rec);
+int clean_io_failure(struct btrfs_fs_info *fs_info,
+		     struct extent_io_tree *failure_tree,
+		     struct extent_io_tree *io_tree, u64 start,
+		     struct page *page, u64 ino, unsigned int pg_offset);
+
+#endif /* BTRFS_EXTENT_IO_TREE_H */
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 49cb26fa7c63..153f71a5bba9 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -54,7 +54,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 static int find_next_key(struct btrfs_path *path, int level,
 			 struct btrfs_key *key);
 
-static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits)
+static int block_group_bits(struct btrfs_block_group *cache, u64 bits)
 {
 	return (cache->flags & bits) == bits;
 }
@@ -70,13 +70,13 @@ int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-void btrfs_free_excluded_extents(struct btrfs_block_group_cache *cache)
+void btrfs_free_excluded_extents(struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	u64 start, end;
 
-	start = cache->key.objectid;
-	end = start + cache->key.offset - 1;
+	start = cache->start;
+	end = start + cache->length - 1;
 
 	clear_extent_bits(&fs_info->freed_extents[0],
 			  start, end, EXTENT_UPTODATE);
@@ -1306,8 +1306,10 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
 int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 			 u64 num_bytes, u64 *actual_bytes)
 {
-	int ret;
+	int ret = 0;
 	u64 discarded_bytes = 0;
+	u64 end = bytenr + num_bytes;
+	u64 cur = bytenr;
 	struct btrfs_bio *bbio = NULL;
 
 
@@ -1316,15 +1318,23 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 	 * associated to its stripes that don't go away while we are discarding.
 	 */
 	btrfs_bio_counter_inc_blocked(fs_info);
-	/* Tell the block device(s) that the sectors can be discarded */
-	ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, bytenr, &num_bytes,
-			      &bbio, 0);
-	/* Error condition is -ENOMEM */
-	if (!ret) {
-		struct btrfs_bio_stripe *stripe = bbio->stripes;
+	while (cur < end) {
+		struct btrfs_bio_stripe *stripe;
 		int i;
 
+		num_bytes = end - cur;
+		/* Tell the block device(s) that the sectors can be discarded */
+		ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, cur,
+				      &num_bytes, &bbio, 0);
+		/*
+		 * Error can be -ENOMEM, -ENOENT (no such chunk mapping) or
+		 * -EOPNOTSUPP. For any such error, @num_bytes is not updated,
+		 * thus we can't continue anyway.
+		 */
+		if (ret < 0)
+			goto out;
 
+		stripe = bbio->stripes;
 		for (i = 0; i < bbio->num_stripes; i++, stripe++) {
 			u64 bytes;
 			struct request_queue *req_q;
@@ -1341,10 +1351,19 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 						  stripe->physical,
 						  stripe->length,
 						  &bytes);
-			if (!ret)
+			if (!ret) {
 				discarded_bytes += bytes;
-			else if (ret != -EOPNOTSUPP)
-				break; /* Logic errors or -ENOMEM, or -EIO but I don't know how that could happen JDM */
+			} else if (ret != -EOPNOTSUPP) {
+				/*
+				 * Logic errors or -ENOMEM, or -EIO, but
+				 * unlikely to happen.
+				 *
+				 * And since there are two loops, explicitly
+				 * go to out to avoid confusion.
+				 */
+				btrfs_put_bbio(bbio);
+				goto out;
+			}
 
 			/*
 			 * Just in case we get back EOPNOTSUPP for some reason,
@@ -1354,7 +1373,9 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 			ret = 0;
 		}
 		btrfs_put_bbio(bbio);
+		cur += num_bytes;
 	}
+out:
 	btrfs_bio_counter_dec(fs_info);
 
 	if (actual_bytes)
@@ -2516,7 +2537,7 @@ int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 
 int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	int readonly = 0;
 
 	block_group = btrfs_lookup_block_group(fs_info, bytenr);
@@ -2546,7 +2567,7 @@ static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data)
 
 static u64 first_logical_byte(struct btrfs_fs_info *fs_info, u64 search_start)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	u64 bytenr;
 
 	spin_lock(&fs_info->block_group_cache_lock);
@@ -2560,13 +2581,13 @@ static u64 first_logical_byte(struct btrfs_fs_info *fs_info, u64 search_start)
 	if (!cache)
 		return 0;
 
-	bytenr = cache->key.objectid;
+	bytenr = cache->start;
 	btrfs_put_block_group(cache);
 
 	return bytenr;
 }
 
-static int pin_down_extent(struct btrfs_block_group_cache *cache,
+static int pin_down_extent(struct btrfs_block_group *cache,
 			   u64 bytenr, u64 num_bytes, int reserved)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
@@ -2590,13 +2611,12 @@ static int pin_down_extent(struct btrfs_block_group_cache *cache,
 	return 0;
 }
 
-/*
- * this function must be called within transaction
- */
 int btrfs_pin_extent(struct btrfs_fs_info *fs_info,
 		     u64 bytenr, u64 num_bytes, int reserved)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
+
+	ASSERT(fs_info->running_transaction);
 
 	cache = btrfs_lookup_block_group(fs_info, bytenr);
 	BUG_ON(!cache); /* Logic error */
@@ -2613,7 +2633,7 @@ int btrfs_pin_extent(struct btrfs_fs_info *fs_info,
 int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info,
 				    u64 bytenr, u64 num_bytes)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	int ret;
 
 	cache = btrfs_lookup_block_group(fs_info, bytenr);
@@ -2640,7 +2660,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
 				   u64 start, u64 num_bytes)
 {
 	int ret;
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_caching_control *caching_ctl;
 
 	block_group = btrfs_lookup_block_group(fs_info, start);
@@ -2652,7 +2672,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
 
 	if (!caching_ctl) {
 		/* Logic error */
-		BUG_ON(!btrfs_block_group_cache_done(block_group));
+		BUG_ON(!btrfs_block_group_done(block_group));
 		ret = btrfs_remove_free_space(block_group, start, num_bytes);
 	} else {
 		mutex_lock(&caching_ctl->mutex);
@@ -2717,7 +2737,7 @@ int btrfs_exclude_logged_extents(struct extent_buffer *eb)
 }
 
 static void
-btrfs_inc_block_group_reservations(struct btrfs_block_group_cache *bg)
+btrfs_inc_block_group_reservations(struct btrfs_block_group *bg)
 {
 	atomic_inc(&bg->reservations);
 }
@@ -2726,14 +2746,14 @@ void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_caching_control *next;
 	struct btrfs_caching_control *caching_ctl;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 
 	down_write(&fs_info->commit_root_sem);
 
 	list_for_each_entry_safe(caching_ctl, next,
 				 &fs_info->caching_block_groups, list) {
 		cache = caching_ctl->block_group;
-		if (btrfs_block_group_cache_done(cache)) {
+		if (btrfs_block_group_done(cache)) {
 			cache->last_byte_to_unpin = (u64)-1;
 			list_del_init(&caching_ctl->list);
 			btrfs_put_caching_control(caching_ctl);
@@ -2785,7 +2805,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 			      u64 start, u64 end,
 			      const bool return_free_space)
 {
-	struct btrfs_block_group_cache *cache = NULL;
+	struct btrfs_block_group *cache = NULL;
 	struct btrfs_space_info *space_info;
 	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
 	struct btrfs_free_cluster *cluster = NULL;
@@ -2797,7 +2817,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 	while (start <= end) {
 		readonly = false;
 		if (!cache ||
-		    start >= cache->key.objectid + cache->key.offset) {
+		    start >= cache->start + cache->length) {
 			if (cache)
 				btrfs_put_block_group(cache);
 			total_unpinned = 0;
@@ -2810,7 +2830,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 			empty_cluster <<= 1;
 		}
 
-		len = cache->key.objectid + cache->key.offset - start;
+		len = cache->start + cache->length - start;
 		len = min(len, end + 1 - start);
 
 		if (start < cache->last_byte_to_unpin) {
@@ -2880,7 +2900,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_group_cache *block_group, *tmp;
+	struct btrfs_block_group *block_group, *tmp;
 	struct list_head *deleted_bgs;
 	struct extent_io_tree *unpin;
 	u64 start;
@@ -2926,8 +2946,8 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 		ret = -EROFS;
 		if (!trans->aborted)
 			ret = btrfs_discard_extent(fs_info,
-						   block_group->key.objectid,
-						   block_group->key.offset,
+						   block_group->start,
+						   block_group->length,
 						   &trimmed);
 
 		list_del_init(&block_group->bg_list);
@@ -3262,7 +3282,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 	}
 
 	if (last_ref && btrfs_header_generation(buf) == trans->transid) {
-		struct btrfs_block_group_cache *cache;
+		struct btrfs_block_group *cache;
 
 		if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
 			ret = check_ref_cleanup(trans, buf->start);
@@ -3349,15 +3369,14 @@ enum btrfs_loop_type {
 };
 
 static inline void
-btrfs_lock_block_group(struct btrfs_block_group_cache *cache,
+btrfs_lock_block_group(struct btrfs_block_group *cache,
 		       int delalloc)
 {
 	if (delalloc)
 		down_read(&cache->data_rwsem);
 }
 
-static inline void
-btrfs_grab_block_group(struct btrfs_block_group_cache *cache,
+static inline void btrfs_grab_block_group(struct btrfs_block_group *cache,
 		       int delalloc)
 {
 	btrfs_get_block_group(cache);
@@ -3365,12 +3384,12 @@ btrfs_grab_block_group(struct btrfs_block_group_cache *cache,
 		down_read(&cache->data_rwsem);
 }
 
-static struct btrfs_block_group_cache *
-btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
+static struct btrfs_block_group *btrfs_lock_cluster(
+		   struct btrfs_block_group *block_group,
 		   struct btrfs_free_cluster *cluster,
 		   int delalloc)
 {
-	struct btrfs_block_group_cache *used_bg = NULL;
+	struct btrfs_block_group *used_bg = NULL;
 
 	spin_lock(&cluster->refill_lock);
 	while (1) {
@@ -3404,7 +3423,7 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
 }
 
 static inline void
-btrfs_release_block_group(struct btrfs_block_group_cache *cache,
+btrfs_release_block_group(struct btrfs_block_group *cache,
 			 int delalloc)
 {
 	if (delalloc)
@@ -3475,12 +3494,12 @@ struct find_free_extent_ctl {
  * Return >0 to inform caller that we find nothing
  * Return 0 means we have found a location and set ffe_ctl->found_offset.
  */
-static int find_free_extent_clustered(struct btrfs_block_group_cache *bg,
+static int find_free_extent_clustered(struct btrfs_block_group *bg,
 		struct btrfs_free_cluster *last_ptr,
 		struct find_free_extent_ctl *ffe_ctl,
-		struct btrfs_block_group_cache **cluster_bg_ret)
+		struct btrfs_block_group **cluster_bg_ret)
 {
-	struct btrfs_block_group_cache *cluster_bg;
+	struct btrfs_block_group *cluster_bg;
 	u64 aligned_cluster;
 	u64 offset;
 	int ret;
@@ -3493,7 +3512,7 @@ static int find_free_extent_clustered(struct btrfs_block_group_cache *bg,
 		goto release_cluster;
 
 	offset = btrfs_alloc_from_cluster(cluster_bg, last_ptr,
-			ffe_ctl->num_bytes, cluster_bg->key.objectid,
+			ffe_ctl->num_bytes, cluster_bg->start,
 			&ffe_ctl->max_extent_size);
 	if (offset) {
 		/* We have a block, we're done */
@@ -3579,7 +3598,7 @@ refill_cluster:
  * Return 0 when we found an free extent and set ffe_ctrl->found_offset
  * Return -EAGAIN to inform caller that we need to re-search this block group
  */
-static int find_free_extent_unclustered(struct btrfs_block_group_cache *bg,
+static int find_free_extent_unclustered(struct btrfs_block_group *bg,
 		struct btrfs_free_cluster *last_ptr,
 		struct find_free_extent_ctl *ffe_ctl)
 {
@@ -3781,7 +3800,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
 {
 	int ret = 0;
 	struct btrfs_free_cluster *last_ptr = NULL;
-	struct btrfs_block_group_cache *block_group = NULL;
+	struct btrfs_block_group *block_group = NULL;
 	struct find_free_extent_ctl ffe_ctl = {0};
 	struct btrfs_space_info *space_info;
 	bool use_cluster = true;
@@ -3904,7 +3923,7 @@ search:
 			continue;
 
 		btrfs_grab_block_group(block_group, delalloc);
-		ffe_ctl.search_start = block_group->key.objectid;
+		ffe_ctl.search_start = block_group->start;
 
 		/*
 		 * this can happen if we end up cycling through all the
@@ -3935,7 +3954,7 @@ search:
 		}
 
 have_block_group:
-		ffe_ctl.cached = btrfs_block_group_cache_done(block_group);
+		ffe_ctl.cached = btrfs_block_group_done(block_group);
 		if (unlikely(!ffe_ctl.cached)) {
 			ffe_ctl.have_caching_bg = true;
 			ret = btrfs_cache_block_group(block_group, 0);
@@ -3951,7 +3970,7 @@ have_block_group:
 		 * lets look there
 		 */
 		if (last_ptr && use_cluster) {
-			struct btrfs_block_group_cache *cluster_bg = NULL;
+			struct btrfs_block_group *cluster_bg = NULL;
 
 			ret = find_free_extent_clustered(block_group, last_ptr,
 							 &ffe_ctl, &cluster_bg);
@@ -3984,7 +4003,7 @@ checks:
 
 		/* move on to the next group */
 		if (ffe_ctl.search_start + num_bytes >
-		    block_group->key.objectid + block_group->key.offset) {
+		    block_group->start + block_group->length) {
 			btrfs_add_free_space(block_group, ffe_ctl.found_offset,
 					     num_bytes);
 			goto loop;
@@ -4133,7 +4152,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
 					u64 start, u64 len,
 					int pin, int delalloc)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	int ret = 0;
 
 	cache = btrfs_lookup_block_group(fs_info, start);
@@ -4366,7 +4385,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_space_info *space_info;
 
 	/*
@@ -5436,7 +5455,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 
 	btrfs_assert_tree_locked(parent);
 	parent_level = btrfs_header_level(parent);
-	extent_buffer_get(parent);
+	atomic_inc(&parent->refs);
 	path->nodes[parent_level] = parent;
 	path->slots[parent_level] = btrfs_header_nritems(parent);
 
@@ -5480,7 +5499,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
  */
 u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	u64 free_bytes = 0;
 	int factor;
 
@@ -5498,9 +5517,8 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
 		}
 
 		factor = btrfs_bg_type_to_factor(block_group->flags);
-		free_bytes += (block_group->key.offset -
-			       btrfs_block_group_used(&block_group->item)) *
-			       factor;
+		free_bytes += (block_group->length -
+			       block_group->used) * factor;
 
 		spin_unlock(&block_group->lock);
 	}
@@ -5623,7 +5641,7 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed)
  */
 int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 {
-	struct btrfs_block_group_cache *cache = NULL;
+	struct btrfs_block_group *cache = NULL;
 	struct btrfs_device *device;
 	struct list_head *devices;
 	u64 group_trimmed;
@@ -5647,16 +5665,16 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 
 	cache = btrfs_lookup_first_block_group(fs_info, range->start);
 	for (; cache; cache = btrfs_next_block_group(cache)) {
-		if (cache->key.objectid >= range_end) {
+		if (cache->start >= range_end) {
 			btrfs_put_block_group(cache);
 			break;
 		}
 
-		start = max(range->start, cache->key.objectid);
-		end = min(range_end, cache->key.objectid + cache->key.offset);
+		start = max(range->start, cache->start);
+		end = min(range_end, cache->start + cache->length);
 
 		if (end - start >= range->minlen) {
-			if (!btrfs_block_group_cache_done(cache)) {
+			if (!btrfs_block_group_done(cache)) {
 				ret = btrfs_cache_block_group(cache, 0);
 				if (ret) {
 					bg_failed++;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index cceaf05aada2..eb8bd0258360 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -14,6 +14,7 @@
 #include <linux/prefetch.h>
 #include <linux/cleancache.h>
 #include "extent_io.h"
+#include "extent-io-tree.h"
 #include "extent_map.h"
 #include "ctree.h"
 #include "btrfs_inode.h"
@@ -59,12 +60,23 @@ void btrfs_leak_debug_del(struct list_head *entry)
 	spin_unlock_irqrestore(&leak_lock, flags);
 }
 
-static inline
-void btrfs_leak_debug_check(void)
+static inline void btrfs_extent_buffer_leak_debug_check(void)
 {
-	struct extent_state *state;
 	struct extent_buffer *eb;
 
+	while (!list_empty(&buffers)) {
+		eb = list_entry(buffers.next, struct extent_buffer, leak_list);
+		pr_err("BTRFS: buffer leak start %llu len %lu refs %d bflags %lu\n",
+		       eb->start, eb->len, atomic_read(&eb->refs), eb->bflags);
+		list_del(&eb->leak_list);
+		kmem_cache_free(extent_buffer_cache, eb);
+	}
+}
+
+static inline void btrfs_extent_state_leak_debug_check(void)
+{
+	struct extent_state *state;
+
 	while (!list_empty(&states)) {
 		state = list_entry(states.next, struct extent_state, leak_list);
 		pr_err("BTRFS: state leak: start %llu end %llu state %u in tree %d refs %d\n",
@@ -74,14 +86,6 @@ void btrfs_leak_debug_check(void)
 		list_del(&state->leak_list);
 		kmem_cache_free(extent_state_cache, state);
 	}
-
-	while (!list_empty(&buffers)) {
-		eb = list_entry(buffers.next, struct extent_buffer, leak_list);
-		pr_err("BTRFS: buffer leak start %llu len %lu refs %d bflags %lu\n",
-		       eb->start, eb->len, atomic_read(&eb->refs), eb->bflags);
-		list_del(&eb->leak_list);
-		kmem_cache_free(extent_buffer_cache, eb);
-	}
 }
 
 #define btrfs_debug_check_extent_io_range(tree, start, end)		\
@@ -105,7 +109,8 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller,
 #else
 #define btrfs_leak_debug_add(new, head)	do {} while (0)
 #define btrfs_leak_debug_del(entry)	do {} while (0)
-#define btrfs_leak_debug_check()	do {} while (0)
+#define btrfs_extent_buffer_leak_debug_check()	do {} while (0)
+#define btrfs_extent_state_leak_debug_check()	do {} while (0)
 #define btrfs_debug_check_extent_io_range(c, s, e)	do {} while (0)
 #endif
 
@@ -196,19 +201,23 @@ static int __must_check flush_write_bio(struct extent_page_data *epd)
 	return ret;
 }
 
-int __init extent_io_init(void)
+int __init extent_state_cache_init(void)
 {
 	extent_state_cache = kmem_cache_create("btrfs_extent_state",
 			sizeof(struct extent_state), 0,
 			SLAB_MEM_SPREAD, NULL);
 	if (!extent_state_cache)
 		return -ENOMEM;
+	return 0;
+}
 
+int __init extent_io_init(void)
+{
 	extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer",
 			sizeof(struct extent_buffer), 0,
 			SLAB_MEM_SPREAD, NULL);
 	if (!extent_buffer_cache)
-		goto free_state_cache;
+		return -ENOMEM;
 
 	if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE,
 			offsetof(struct btrfs_io_bio, bio),
@@ -226,23 +235,24 @@ free_bioset:
 free_buffer_cache:
 	kmem_cache_destroy(extent_buffer_cache);
 	extent_buffer_cache = NULL;
+	return -ENOMEM;
+}
 
-free_state_cache:
+void __cold extent_state_cache_exit(void)
+{
+	btrfs_extent_state_leak_debug_check();
 	kmem_cache_destroy(extent_state_cache);
-	extent_state_cache = NULL;
-	return -ENOMEM;
 }
 
 void __cold extent_io_exit(void)
 {
-	btrfs_leak_debug_check();
+	btrfs_extent_buffer_leak_debug_check();
 
 	/*
 	 * Make sure all delayed rcu free are flushed before we
 	 * destroy caches.
 	 */
 	rcu_barrier();
-	kmem_cache_destroy(extent_state_cache);
 	kmem_cache_destroy(extent_buffer_cache);
 	bioset_exit(&btrfs_bioset);
 }
@@ -1676,9 +1686,9 @@ out:
  *
  * true is returned if we find something, false if nothing was in the tree
  */
-static noinline bool find_delalloc_range(struct extent_io_tree *tree,
-					u64 *start, u64 *end, u64 max_bytes,
-					struct extent_state **cached_state)
+bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
+			       u64 *end, u64 max_bytes,
+			       struct extent_state **cached_state)
 {
 	struct rb_node *node;
 	struct extent_state *state;
@@ -1796,8 +1806,8 @@ again:
 	/* step one, find a bunch of delalloc bytes starting at start */
 	delalloc_start = *start;
 	delalloc_end = 0;
-	found = find_delalloc_range(tree, &delalloc_start, &delalloc_end,
-				    max_bytes, &cached_state);
+	found = btrfs_find_delalloc_range(tree, &delalloc_start, &delalloc_end,
+					  max_bytes, &cached_state);
 	if (!found || delalloc_end <= *start) {
 		*start = delalloc_start;
 		*end = delalloc_end;
@@ -1899,7 +1909,7 @@ static int __process_pages_contig(struct address_space *mapping,
 			if (page_ops & PAGE_SET_PRIVATE2)
 				SetPagePrivate2(pages[i]);
 
-			if (pages[i] == locked_page) {
+			if (locked_page && pages[i] == locked_page) {
 				put_page(pages[i]);
 				pages_locked++;
 				continue;
@@ -2014,8 +2024,8 @@ out:
  * set the private field for a given byte offset in the tree.  If there isn't
  * an extent_state there already, this does nothing.
  */
-static noinline int set_state_failrec(struct extent_io_tree *tree, u64 start,
-		struct io_failure_record *failrec)
+int set_state_failrec(struct extent_io_tree *tree, u64 start,
+		      struct io_failure_record *failrec)
 {
 	struct rb_node *node;
 	struct extent_state *state;
@@ -2042,8 +2052,8 @@ out:
 	return ret;
 }
 
-static noinline int get_state_failrec(struct extent_io_tree *tree, u64 start,
-		struct io_failure_record **failrec)
+int get_state_failrec(struct extent_io_tree *tree, u64 start,
+		      struct io_failure_record **failrec)
 {
 	struct rb_node *node;
 	struct extent_state *state;
@@ -2534,7 +2544,6 @@ struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
 	bio = btrfs_io_bio_alloc(1);
 	bio->bi_end_io = endio_func;
 	bio->bi_iter.bi_sector = failrec->logical >> 9;
-	bio_set_dev(bio, fs_info->fs_devices->latest_bdev);
 	bio->bi_iter.bi_size = 0;
 	bio->bi_private = data;
 
@@ -2920,7 +2929,6 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size)
  *              a contiguous page to the previous one
  * @size:	portion of page that we want to write
  * @offset:	starting offset in the page
- * @bdev:	attach newly created bios to this bdev
  * @bio_ret:	must be valid pointer, newly allocated bio will be stored there
  * @end_io_func:     end_io callback for new bio
  * @mirror_num:	     desired mirror to read/write
@@ -2931,7 +2939,6 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 			      struct writeback_control *wbc,
 			      struct page *page, u64 offset,
 			      size_t size, unsigned long pg_offset,
-			      struct block_device *bdev,
 			      struct bio **bio_ret,
 			      bio_end_io_t end_io_func,
 			      int mirror_num,
@@ -2977,13 +2984,16 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 	}
 
 	bio = btrfs_bio_alloc(offset);
-	bio_set_dev(bio, bdev);
 	bio_add_page(bio, page, page_size, pg_offset);
 	bio->bi_end_io = end_io_func;
 	bio->bi_private = tree;
 	bio->bi_write_hint = page->mapping->host->i_write_hint;
 	bio->bi_opf = opf;
 	if (wbc) {
+		struct block_device *bdev;
+
+		bdev = BTRFS_I(page->mapping->host)->root->fs_info->fs_devices->latest_bdev;
+		bio_set_dev(bio, bdev);
 		wbc_init_bio(wbc, bio);
 		wbc_account_cgroup_owner(wbc, page, page_size);
 	}
@@ -3065,7 +3075,6 @@ static int __do_readpage(struct extent_io_tree *tree,
 	u64 block_start;
 	u64 cur_end;
 	struct extent_map *em;
-	struct block_device *bdev;
 	int ret = 0;
 	int nr = 0;
 	size_t pg_offset = 0;
@@ -3142,7 +3151,6 @@ static int __do_readpage(struct extent_io_tree *tree,
 			offset = em->block_start + extent_offset;
 			disk_io_size = iosize;
 		}
-		bdev = em->bdev;
 		block_start = em->block_start;
 		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 			block_start = EXTENT_MAP_HOLE;
@@ -3232,7 +3240,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 
 		ret = submit_extent_page(REQ_OP_READ | read_flags, tree, NULL,
 					 page, offset, disk_io_size,
-					 pg_offset, bdev, bio,
+					 pg_offset, bio,
 					 end_bio_extent_readpage, mirror_num,
 					 *bio_flags,
 					 this_bio_flag,
@@ -3409,7 +3417,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 				 struct extent_page_data *epd,
 				 loff_t i_size,
 				 unsigned long nr_written,
-				 unsigned int write_flags, int *nr_ret)
+				 int *nr_ret)
 {
 	struct extent_io_tree *tree = epd->tree;
 	u64 start = page_offset(page);
@@ -3420,11 +3428,11 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 	u64 block_start;
 	u64 iosize;
 	struct extent_map *em;
-	struct block_device *bdev;
 	size_t pg_offset = 0;
 	size_t blocksize;
 	int ret = 0;
 	int nr = 0;
+	const unsigned int write_flags = wbc_to_write_flags(wbc);
 	bool compressed;
 
 	ret = btrfs_writepage_cow_fixup(page, start, page_end);
@@ -3478,7 +3486,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 		iosize = min(em_end - cur, end - cur + 1);
 		iosize = ALIGN(iosize, blocksize);
 		offset = em->block_start + extent_offset;
-		bdev = em->bdev;
 		block_start = em->block_start;
 		compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
 		free_extent_map(em);
@@ -3520,7 +3527,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 
 		ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc,
 					 page, offset, iosize, pg_offset,
-					 bdev, &epd->bio,
+					 &epd->bio,
 					 end_bio_extent_writepage,
 					 0, 0, 0, false);
 		if (ret) {
@@ -3558,11 +3565,8 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	size_t pg_offset = 0;
 	loff_t i_size = i_size_read(inode);
 	unsigned long end_index = i_size >> PAGE_SHIFT;
-	unsigned int write_flags = 0;
 	unsigned long nr_written = 0;
 
-	write_flags = wbc_to_write_flags(wbc);
-
 	trace___extent_writepage(page, inode, wbc);
 
 	WARN_ON(!PageLocked(page));
@@ -3600,7 +3604,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	}
 
 	ret = __extent_writepage_io(inode, page, wbc, epd,
-				    i_size, nr_written, write_flags, &nr);
+				    i_size, nr_written, &nr);
 	if (ret == 1)
 		goto done_unlocked;
 
@@ -3849,7 +3853,6 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 			struct extent_page_data *epd)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
-	struct block_device *bdev = fs_info->fs_devices->latest_bdev;
 	struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
 	u64 offset = eb->start;
 	u32 nritems;
@@ -3884,7 +3887,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 		clear_page_dirty_for_io(p);
 		set_page_writeback(p);
 		ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc,
-					 p, offset, PAGE_SIZE, 0, bdev,
+					 p, offset, PAGE_SIZE, 0,
 					 &epd->bio,
 					 end_bio_extent_buffer_writepage,
 					 0, 0, 0, false);
@@ -4121,7 +4124,7 @@ retry:
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
-			done_index = page->index;
+			done_index = page->index + 1;
 			/*
 			 * At this point we hold neither the i_pages lock nor
 			 * the page lock: the page may be truncated or
@@ -4156,16 +4159,6 @@ retry:
 
 			ret = __extent_writepage(page, wbc, epd);
 			if (ret < 0) {
-				/*
-				 * done_index is set past this page,
-				 * so media errors will not choke
-				 * background writeout for the entire
-				 * file. This has consequences for
-				 * range_cyclic semantics (ie. it may
-				 * not be suitable for data integrity
-				 * writeout).
-				 */
-				done_index = page->index + 1;
 				done = 1;
 				break;
 			}
@@ -4240,8 +4233,12 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
 		.nr_to_write	= nr_pages * 2,
 		.range_start	= start,
 		.range_end	= end + 1,
+		/* We're called from an async helper function */
+		.punt_to_cgroup	= 1,
+		.no_cgroup_owner = 1,
 	};
 
+	wbc_attach_fdatawrite_inode(&wbc_writepages, inode);
 	while (start <= end) {
 		page = find_get_page(mapping, start >> PAGE_SHIFT);
 		if (clear_page_dirty_for_io(page))
@@ -4256,11 +4253,12 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
 	}
 
 	ASSERT(ret <= 0);
-	if (ret < 0) {
+	if (ret == 0)
+		ret = flush_write_bio(&epd);
+	else
 		end_write_bio(&epd, ret);
-		return ret;
-	}
-	ret = flush_write_bio(&epd);
+
+	wbc_detach_inode(&wbc_writepages);
 	return ret;
 }
 
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index cf3424d58fec..a8551a1f56e2 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -7,35 +7,6 @@
 #include <linux/refcount.h>
 #include "ulist.h"
 
-/* bits for the extent state */
-#define EXTENT_DIRTY		(1U << 0)
-#define EXTENT_UPTODATE		(1U << 1)
-#define EXTENT_LOCKED		(1U << 2)
-#define EXTENT_NEW		(1U << 3)
-#define EXTENT_DELALLOC		(1U << 4)
-#define EXTENT_DEFRAG		(1U << 5)
-#define EXTENT_BOUNDARY		(1U << 6)
-#define EXTENT_NODATASUM	(1U << 7)
-#define EXTENT_CLEAR_META_RESV	(1U << 8)
-#define EXTENT_NEED_WAIT	(1U << 9)
-#define EXTENT_DAMAGED		(1U << 10)
-#define EXTENT_NORESERVE	(1U << 11)
-#define EXTENT_QGROUP_RESERVED	(1U << 12)
-#define EXTENT_CLEAR_DATA_RESV	(1U << 13)
-#define EXTENT_DELALLOC_NEW	(1U << 14)
-#define EXTENT_DO_ACCOUNTING    (EXTENT_CLEAR_META_RESV | \
-				 EXTENT_CLEAR_DATA_RESV)
-#define EXTENT_CTLBITS		(EXTENT_DO_ACCOUNTING)
-
-/*
- * Redefined bits above which are used only in the device allocation tree,
- * shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV
- * / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit
- * manipulation functions
- */
-#define CHUNK_ALLOCATED EXTENT_DIRTY
-#define CHUNK_TRIMMED   EXTENT_DEFRAG
-
 /*
  * flags for bio submission. The high bits indicate the compression
  * type for this bio
@@ -89,12 +60,11 @@ enum {
 #define BITMAP_LAST_BYTE_MASK(nbits) \
 	(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
 
-struct extent_state;
 struct btrfs_root;
 struct btrfs_inode;
 struct btrfs_io_bio;
 struct io_failure_record;
-
+struct extent_io_tree;
 
 typedef blk_status_t (extent_submit_bio_start_t)(void *private_data,
 		struct bio *bio, u64 bio_offset);
@@ -111,47 +81,6 @@ struct extent_io_ops {
 				    int mirror);
 };
 
-enum {
-	IO_TREE_FS_INFO_FREED_EXTENTS0,
-	IO_TREE_FS_INFO_FREED_EXTENTS1,
-	IO_TREE_INODE_IO,
-	IO_TREE_INODE_IO_FAILURE,
-	IO_TREE_RELOC_BLOCKS,
-	IO_TREE_TRANS_DIRTY_PAGES,
-	IO_TREE_ROOT_DIRTY_LOG_PAGES,
-	IO_TREE_SELFTEST,
-};
-
-struct extent_io_tree {
-	struct rb_root state;
-	struct btrfs_fs_info *fs_info;
-	void *private_data;
-	u64 dirty_bytes;
-	bool track_uptodate;
-
-	/* Who owns this io tree, should be one of IO_TREE_* */
-	u8 owner;
-
-	spinlock_t lock;
-	const struct extent_io_ops *ops;
-};
-
-struct extent_state {
-	u64 start;
-	u64 end; /* inclusive */
-	struct rb_node rb_node;
-
-	/* ADD NEW ELEMENTS AFTER THIS */
-	wait_queue_head_t wq;
-	refcount_t refs;
-	unsigned state;
-
-	struct io_failure_record *failrec;
-
-#ifdef CONFIG_BTRFS_DEBUG
-	struct list_head leak_list;
-#endif
-};
 
 #define INLINE_EXTENT_BUFFER_PAGES 16
 #define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_SIZE)
@@ -259,152 +188,11 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode,
 					  u64 start, u64 len,
 					  int create);
 
-void extent_io_tree_init(struct btrfs_fs_info *fs_info,
-			 struct extent_io_tree *tree, unsigned int owner,
-			 void *private_data);
-void extent_io_tree_release(struct extent_io_tree *tree);
 int try_release_extent_mapping(struct page *page, gfp_t mask);
 int try_release_extent_buffer(struct page *page);
-int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		     struct extent_state **cached);
 
-static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	return lock_extent_bits(tree, start, end, NULL);
-}
-
-int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 			  get_extent_t *get_extent, int mirror_num);
-int __init extent_io_init(void);
-void __cold extent_io_exit(void);
-
-u64 count_range_bits(struct extent_io_tree *tree,
-		     u64 *start, u64 search_end,
-		     u64 max_bytes, unsigned bits, int contig);
-
-void free_extent_state(struct extent_state *state);
-int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   unsigned bits, int filled,
-		   struct extent_state *cached_state);
-int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		unsigned bits, struct extent_changeset *changeset);
-int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		     unsigned bits, int wake, int delete,
-		     struct extent_state **cached);
-int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		     unsigned bits, int wake, int delete,
-		     struct extent_state **cached, gfp_t mask,
-		     struct extent_changeset *changeset);
-
-static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL);
-}
-
-static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
-		u64 end, struct extent_state **cached)
-{
-	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
-				GFP_NOFS, NULL);
-}
-
-static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree,
-		u64 start, u64 end, struct extent_state **cached)
-{
-	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
-				GFP_ATOMIC, NULL);
-}
-
-static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
-		u64 end, unsigned bits)
-{
-	int wake = 0;
-
-	if (bits & EXTENT_LOCKED)
-		wake = 1;
-
-	return clear_extent_bit(tree, start, end, bits, wake, 0, NULL);
-}
-
-int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-			   unsigned bits, struct extent_changeset *changeset);
-int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   unsigned bits, u64 *failed_start,
-		   struct extent_state **cached_state, gfp_t mask);
-int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end,
-			   unsigned bits);
-
-static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
-		u64 end, unsigned bits)
-{
-	return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS);
-}
-
-static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
-		u64 end, struct extent_state **cached_state)
-{
-	return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
-				cached_state, GFP_NOFS, NULL);
-}
-
-static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
-		u64 end, gfp_t mask)
-{
-	return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
-			      NULL, mask);
-}
-
-static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
-				     u64 end, struct extent_state **cached)
-{
-	return clear_extent_bit(tree, start, end,
-				EXTENT_DIRTY | EXTENT_DELALLOC |
-				EXTENT_DO_ACCOUNTING, 0, 0, cached);
-}
-
-int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		       unsigned bits, unsigned clear_bits,
-		       struct extent_state **cached_state);
-
-static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
-				      u64 end, unsigned int extra_bits,
-				      struct extent_state **cached_state)
-{
-	return set_extent_bit(tree, start, end,
-			      EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
-			      NULL, cached_state, GFP_NOFS);
-}
-
-static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
-		u64 end, struct extent_state **cached_state)
-{
-	return set_extent_bit(tree, start, end,
-			      EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
-			      NULL, cached_state, GFP_NOFS);
-}
-
-static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
-		u64 end)
-{
-	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL,
-			GFP_NOFS);
-}
-
-static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
-		u64 end, struct extent_state **cached_state, gfp_t mask)
-{
-	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL,
-			      cached_state, mask);
-}
-
-int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
-			  u64 *start_ret, u64 *end_ret, unsigned bits,
-			  struct extent_state **cached_state);
-void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
-				 u64 *start_ret, u64 *end_ret, unsigned bits);
-int extent_invalidatepage(struct extent_io_tree *tree,
-			  struct page *page, unsigned long offset);
 int extent_write_full_page(struct page *page, struct writeback_control *wbc);
 int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
 			      int mode);
@@ -442,11 +230,6 @@ static inline int num_extent_pages(const struct extent_buffer *eb)
 	       (eb->start >> PAGE_SHIFT);
 }
 
-static inline void extent_buffer_get(struct extent_buffer *eb)
-{
-	atomic_inc(&eb->refs);
-}
-
 static inline int extent_buffer_uptodate(struct extent_buffer *eb)
 {
 	return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
@@ -508,10 +291,6 @@ struct btrfs_inode;
 int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 		      u64 length, u64 logical, struct page *page,
 		      unsigned int pg_offset, int mirror_num);
-int clean_io_failure(struct btrfs_fs_info *fs_info,
-		     struct extent_io_tree *failure_tree,
-		     struct extent_io_tree *io_tree, u64 start,
-		     struct page *page, u64 ino, unsigned int pg_offset);
 void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
 int btrfs_repair_eb_io_failure(struct extent_buffer *eb, int mirror_num);
 
@@ -535,19 +314,12 @@ struct io_failure_record {
 };
 
 
-void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
-		u64 end);
-int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
-				struct io_failure_record **failrec_ret);
 bool btrfs_check_repairable(struct inode *inode, unsigned failed_bio_pages,
 			    struct io_failure_record *failrec, int fail_mirror);
 struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
 				    struct io_failure_record *failrec,
 				    struct page *page, int pg_offset, int icsum,
 				    bio_end_io_t *endio_func, void *data);
-int free_io_failure(struct extent_io_tree *failure_tree,
-		    struct extent_io_tree *io_tree,
-		    struct io_failure_record *rec);
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 bool find_lock_delalloc_range(struct inode *inode,
 			     struct page *locked_page, u64 *start,
@@ -555,5 +327,4 @@ bool find_lock_delalloc_range(struct inode *inode,
 #endif
 struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
 					       u64 start);
-
 #endif
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 9d30acca55e1..6f417ff68980 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -214,9 +214,13 @@ static int mergable_maps(struct extent_map *prev, struct extent_map *next)
 	ASSERT(next->block_start != EXTENT_MAP_DELALLOC &&
 	       prev->block_start != EXTENT_MAP_DELALLOC);
 
+	if (prev->map_lookup || next->map_lookup)
+		ASSERT(test_bit(EXTENT_FLAG_FS_MAPPING, &prev->flags) &&
+		       test_bit(EXTENT_FLAG_FS_MAPPING, &next->flags));
+
 	if (extent_map_end(prev) == next->start &&
 	    prev->flags == next->flags &&
-	    prev->bdev == next->bdev &&
+	    prev->map_lookup == next->map_lookup &&
 	    ((next->block_start == EXTENT_MAP_HOLE &&
 	      prev->block_start == EXTENT_MAP_HOLE) ||
 	     (next->block_start == EXTENT_MAP_INLINE &&
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 473f039fcd7c..8e217337dff9 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -42,15 +42,8 @@ struct extent_map {
 	u64 block_len;
 	u64 generation;
 	unsigned long flags;
-	union {
-		struct block_device *bdev;
-
-		/*
-		 * used for chunk mappings
-		 * flags & EXTENT_FLAG_FS_MAPPING must be set
-		 */
-		struct map_lookup *map_lookup;
-	};
+	/* Used for chunk mappings, flag EXTENT_FLAG_FS_MAPPING must be set */
+	struct map_lookup *map_lookup;
 	refcount_t refs;
 	unsigned int compress_type;
 	struct list_head list;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 1a599f50837b..3270a40b0777 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -945,7 +945,6 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 	u8 type = btrfs_file_extent_type(leaf, fi);
 	int compress_type = btrfs_file_extent_compression(leaf, fi);
 
-	em->bdev = fs_info->fs_devices->latest_bdev;
 	btrfs_item_key_to_cpu(leaf, &key, slot);
 	extent_start = key.offset;
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 435a502a3226..0cb43b682789 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -296,7 +296,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 	key.objectid = defrag->ino;
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
-	inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, inode_root);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);
 		goto cleanup;
@@ -667,7 +667,6 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
 			}
 
 			split->generation = gen;
-			split->bdev = em->bdev;
 			split->flags = flags;
 			split->compress_type = em->compress_type;
 			replace_extent_mapping(em_tree, em, split, modified);
@@ -680,7 +679,6 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
 
 			split->start = start + len;
 			split->len = em->start + em->len - (start + len);
-			split->bdev = em->bdev;
 			split->flags = flags;
 			split->compress_type = em->compress_type;
 			split->generation = gen;
@@ -1636,6 +1634,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
 			break;
 		}
 
+		only_release_metadata = false;
 		sector_offset = pos & (fs_info->sectorsize - 1);
 		reserve_bytes = round_up(write_bytes + sector_offset,
 				fs_info->sectorsize);
@@ -1791,7 +1790,6 @@ again:
 			set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
 				       lockend, EXTENT_NORESERVE, NULL,
 				       NULL, GFP_NOFS);
-			only_release_metadata = false;
 		}
 
 		btrfs_drop_pages(pages, num_pages);
@@ -1903,9 +1901,10 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	    (iocb->ki_flags & IOCB_NOWAIT))
 		return -EOPNOTSUPP;
 
-	if (!inode_trylock(inode)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock(inode))
 			return -EAGAIN;
+	} else {
 		inode_lock(inode);
 	}
 
@@ -2359,7 +2358,6 @@ out:
 		hole_em->block_start = EXTENT_MAP_HOLE;
 		hole_em->block_len = 0;
 		hole_em->orig_block_len = 0;
-		hole_em->bdev = fs_info->fs_devices->latest_bdev;
 		hole_em->compress_type = BTRFS_COMPRESS_NONE;
 		hole_em->generation = trans->transid;
 
@@ -3350,29 +3348,30 @@ out:
 	return ret;
 }
 
-static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
+static loff_t find_desired_extent(struct inode *inode, loff_t offset,
+				  int whence)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct extent_map *em = NULL;
 	struct extent_state *cached_state = NULL;
+	loff_t i_size = inode->i_size;
 	u64 lockstart;
 	u64 lockend;
 	u64 start;
 	u64 len;
 	int ret = 0;
 
-	if (inode->i_size == 0)
+	if (i_size == 0 || offset >= i_size)
 		return -ENXIO;
 
 	/*
-	 * *offset can be negative, in this case we start finding DATA/HOLE from
+	 * offset can be negative, in this case we start finding DATA/HOLE from
 	 * the very start of the file.
 	 */
-	start = max_t(loff_t, 0, *offset);
+	start = max_t(loff_t, 0, offset);
 
 	lockstart = round_down(start, fs_info->sectorsize);
-	lockend = round_up(i_size_read(inode),
-			   fs_info->sectorsize);
+	lockend = round_up(i_size, fs_info->sectorsize);
 	if (lockend <= lockstart)
 		lockend = lockstart + fs_info->sectorsize;
 	lockend--;
@@ -3381,7 +3380,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			 &cached_state);
 
-	while (start < inode->i_size) {
+	while (start < i_size) {
 		em = btrfs_get_extent_fiemap(BTRFS_I(inode), start, len);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
@@ -3404,46 +3403,39 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 		cond_resched();
 	}
 	free_extent_map(em);
-	if (!ret) {
-		if (whence == SEEK_DATA && start >= inode->i_size)
-			ret = -ENXIO;
-		else
-			*offset = min_t(loff_t, start, inode->i_size);
-	}
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			     &cached_state);
-	return ret;
+	if (ret) {
+		offset = ret;
+	} else {
+		if (whence == SEEK_DATA && start >= i_size)
+			offset = -ENXIO;
+		else
+			offset = min_t(loff_t, start, i_size);
+	}
+
+	return offset;
 }
 
 static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
-	int ret;
 
-	inode_lock(inode);
 	switch (whence) {
-	case SEEK_END:
-	case SEEK_CUR:
-		offset = generic_file_llseek(file, offset, whence);
-		goto out;
+	default:
+		return generic_file_llseek(file, offset, whence);
 	case SEEK_DATA:
 	case SEEK_HOLE:
-		if (offset >= i_size_read(inode)) {
-			inode_unlock(inode);
-			return -ENXIO;
-		}
-
-		ret = find_desired_extent(inode, &offset, whence);
-		if (ret) {
-			inode_unlock(inode);
-			return ret;
-		}
+		inode_lock_shared(inode);
+		offset = find_desired_extent(inode, offset, whence);
+		inode_unlock_shared(inode);
+		break;
 	}
 
-	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
-out:
-	inode_unlock(inode);
-	return offset;
+	if (offset < 0)
+		return offset;
+
+	return vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 }
 
 static int btrfs_file_open(struct inode *inode, struct file *filp)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index d54dcd0ab230..3283da419200 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -78,7 +78,7 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	 * sure NOFS is set to keep us from deadlocking.
 	 */
 	nofs_flag = memalloc_nofs_save();
-	inode = btrfs_iget_path(fs_info->sb, &location, root, NULL, path);
+	inode = btrfs_iget_path(fs_info->sb, &location, root, path);
 	btrfs_release_path(path);
 	memalloc_nofs_restore(nofs_flag);
 	if (IS_ERR(inode))
@@ -91,8 +91,7 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	return inode;
 }
 
-struct inode *lookup_free_space_inode(
-		struct btrfs_block_group_cache *block_group,
+struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group,
 		struct btrfs_path *path)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
@@ -107,7 +106,7 @@ struct inode *lookup_free_space_inode(
 		return inode;
 
 	inode = __lookup_free_space_inode(fs_info->tree_root, path,
-					  block_group->key.objectid);
+					  block_group->start);
 	if (IS_ERR(inode))
 		return inode;
 
@@ -190,7 +189,7 @@ static int __create_free_space_inode(struct btrfs_root *root,
 }
 
 int create_free_space_inode(struct btrfs_trans_handle *trans,
-			    struct btrfs_block_group_cache *block_group,
+			    struct btrfs_block_group *block_group,
 			    struct btrfs_path *path)
 {
 	int ret;
@@ -201,7 +200,7 @@ int create_free_space_inode(struct btrfs_trans_handle *trans,
 		return ret;
 
 	return __create_free_space_inode(trans->fs_info->tree_root, trans, path,
-					 ino, block_group->key.objectid);
+					 ino, block_group->start);
 }
 
 int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
@@ -224,7 +223,7 @@ int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
 }
 
 int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
-				    struct btrfs_block_group_cache *block_group,
+				    struct btrfs_block_group *block_group,
 				    struct inode *inode)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -385,6 +384,12 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, struct inode *inode
 		if (uptodate && !PageUptodate(page)) {
 			btrfs_readpage(NULL, page);
 			lock_page(page);
+			if (page->mapping != inode->i_mapping) {
+				btrfs_err(BTRFS_I(inode)->root->fs_info,
+					  "free space cache page truncated");
+				io_ctl_drop_pages(io_ctl);
+				return -EIO;
+			}
 			if (!PageUptodate(page)) {
 				btrfs_err(BTRFS_I(inode)->root->fs_info,
 					   "error reading free space cache");
@@ -814,7 +819,7 @@ free_cache:
 	goto out;
 }
 
-int load_free_space_cache(struct btrfs_block_group_cache *block_group)
+int load_free_space_cache(struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -822,7 +827,7 @@ int load_free_space_cache(struct btrfs_block_group_cache *block_group)
 	struct btrfs_path *path;
 	int ret = 0;
 	bool matched;
-	u64 used = btrfs_block_group_used(&block_group->item);
+	u64 used = block_group->used;
 
 	/*
 	 * If this block group has been marked to be cleared for one reason or
@@ -876,13 +881,13 @@ int load_free_space_cache(struct btrfs_block_group_cache *block_group)
 	spin_unlock(&block_group->lock);
 
 	ret = __load_free_space_cache(fs_info->tree_root, inode, ctl,
-				      path, block_group->key.objectid);
+				      path, block_group->start);
 	btrfs_free_path(path);
 	if (ret <= 0)
 		goto out;
 
 	spin_lock(&ctl->tree_lock);
-	matched = (ctl->free_space == (block_group->key.offset - used -
+	matched = (ctl->free_space == (block_group->length - used -
 				       block_group->bytes_super));
 	spin_unlock(&ctl->tree_lock);
 
@@ -890,7 +895,7 @@ int load_free_space_cache(struct btrfs_block_group_cache *block_group)
 		__btrfs_remove_free_space_cache(ctl);
 		btrfs_warn(fs_info,
 			   "block group %llu has wrong amount of free space",
-			   block_group->key.objectid);
+			   block_group->start);
 		ret = -1;
 	}
 out:
@@ -903,7 +908,7 @@ out:
 
 		btrfs_warn(fs_info,
 			   "failed to load free space cache for block group %llu, rebuilding it now",
-			   block_group->key.objectid);
+			   block_group->start);
 	}
 
 	iput(inode);
@@ -913,7 +918,7 @@ out:
 static noinline_for_stack
 int write_cache_extent_entries(struct btrfs_io_ctl *io_ctl,
 			      struct btrfs_free_space_ctl *ctl,
-			      struct btrfs_block_group_cache *block_group,
+			      struct btrfs_block_group *block_group,
 			      int *entries, int *bitmaps,
 			      struct list_head *bitmap_list)
 {
@@ -1041,7 +1046,7 @@ fail:
 }
 
 static noinline_for_stack int write_pinned_extent_entries(
-			    struct btrfs_block_group_cache *block_group,
+			    struct btrfs_block_group *block_group,
 			    struct btrfs_io_ctl *io_ctl,
 			    int *entries)
 {
@@ -1061,9 +1066,9 @@ static noinline_for_stack int write_pinned_extent_entries(
 	 */
 	unpin = block_group->fs_info->pinned_extents;
 
-	start = block_group->key.objectid;
+	start = block_group->start;
 
-	while (start < block_group->key.objectid + block_group->key.offset) {
+	while (start < block_group->start + block_group->length) {
 		ret = find_first_extent_bit(unpin, start,
 					    &extent_start, &extent_end,
 					    EXTENT_DIRTY, NULL);
@@ -1071,13 +1076,12 @@ static noinline_for_stack int write_pinned_extent_entries(
 			return 0;
 
 		/* This pinned extent is out of our range */
-		if (extent_start >= block_group->key.objectid +
-		    block_group->key.offset)
+		if (extent_start >= block_group->start + block_group->length)
 			return 0;
 
 		extent_start = max(extent_start, start);
-		extent_end = min(block_group->key.objectid +
-				 block_group->key.offset, extent_end + 1);
+		extent_end = min(block_group->start + block_group->length,
+				 extent_end + 1);
 		len = extent_end - extent_start;
 
 		*entries += 1;
@@ -1141,7 +1145,7 @@ cleanup_write_cache_enospc(struct inode *inode,
 
 static int __btrfs_wait_cache_io(struct btrfs_root *root,
 				 struct btrfs_trans_handle *trans,
-				 struct btrfs_block_group_cache *block_group,
+				 struct btrfs_block_group *block_group,
 				 struct btrfs_io_ctl *io_ctl,
 				 struct btrfs_path *path, u64 offset)
 {
@@ -1168,7 +1172,7 @@ out:
 #ifdef DEBUG
 			btrfs_err(root->fs_info,
 				  "failed to write free space cache for block group %llu",
-				  block_group->key.objectid);
+				  block_group->start);
 #endif
 		}
 	}
@@ -1210,12 +1214,12 @@ static int btrfs_wait_cache_io_root(struct btrfs_root *root,
 }
 
 int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
-			struct btrfs_block_group_cache *block_group,
+			struct btrfs_block_group *block_group,
 			struct btrfs_path *path)
 {
 	return __btrfs_wait_cache_io(block_group->fs_info->tree_root, trans,
 				     block_group, &block_group->io_ctl,
-				     path, block_group->key.objectid);
+				     path, block_group->start);
 }
 
 /**
@@ -1231,7 +1235,7 @@ int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
  */
 static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 				   struct btrfs_free_space_ctl *ctl,
-				   struct btrfs_block_group_cache *block_group,
+				   struct btrfs_block_group *block_group,
 				   struct btrfs_io_ctl *io_ctl,
 				   struct btrfs_trans_handle *trans)
 {
@@ -1369,7 +1373,7 @@ out_unlock:
 }
 
 int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
-			  struct btrfs_block_group_cache *block_group,
+			  struct btrfs_block_group *block_group,
 			  struct btrfs_path *path)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -1394,7 +1398,7 @@ int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
 #ifdef DEBUG
 		btrfs_err(fs_info,
 			  "failed to write free space cache for block group %llu",
-			  block_group->key.objectid);
+			  block_group->start);
 #endif
 		spin_lock(&block_group->lock);
 		block_group->disk_cache_state = BTRFS_DC_ERROR;
@@ -1647,11 +1651,11 @@ static int link_free_space(struct btrfs_free_space_ctl *ctl,
 
 static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
 {
-	struct btrfs_block_group_cache *block_group = ctl->private;
+	struct btrfs_block_group *block_group = ctl->private;
 	u64 max_bytes;
 	u64 bitmap_bytes;
 	u64 extent_bytes;
-	u64 size = block_group->key.offset;
+	u64 size = block_group->length;
 	u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit;
 	u64 max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg);
 
@@ -1991,7 +1995,7 @@ static u64 add_bytes_to_bitmap(struct btrfs_free_space_ctl *ctl,
 static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
 		      struct btrfs_free_space *info)
 {
-	struct btrfs_block_group_cache *block_group = ctl->private;
+	struct btrfs_block_group *block_group = ctl->private;
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	bool forced = false;
 
@@ -2028,7 +2032,7 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
 	 * so allow those block groups to still be allowed to have a bitmap
 	 * entry.
 	 */
-	if (((BITS_PER_BITMAP * ctl->unit) >> 1) > block_group->key.offset)
+	if (((BITS_PER_BITMAP * ctl->unit) >> 1) > block_group->length)
 		return false;
 
 	return true;
@@ -2043,7 +2047,7 @@ static int insert_into_bitmap(struct btrfs_free_space_ctl *ctl,
 			      struct btrfs_free_space *info)
 {
 	struct btrfs_free_space *bitmap_info;
-	struct btrfs_block_group_cache *block_group = NULL;
+	struct btrfs_block_group *block_group = NULL;
 	int added = 0;
 	u64 bytes, offset, bytes_added;
 	int ret;
@@ -2380,7 +2384,7 @@ out:
 	return ret;
 }
 
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
+int btrfs_add_free_space(struct btrfs_block_group *block_group,
 			 u64 bytenr, u64 size)
 {
 	return __btrfs_add_free_space(block_group->fs_info,
@@ -2388,7 +2392,7 @@ int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
 				      bytenr, size);
 }
 
-int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
+int btrfs_remove_free_space(struct btrfs_block_group *block_group,
 			    u64 offset, u64 bytes)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -2478,7 +2482,7 @@ out:
 	return ret;
 }
 
-void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
+void btrfs_dump_free_space(struct btrfs_block_group *block_group,
 			   u64 bytes)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
@@ -2503,14 +2507,14 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
 		   "%d blocks of free space at or bigger than bytes is", count);
 }
 
-void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group)
+void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 
 	spin_lock_init(&ctl->tree_lock);
 	ctl->unit = fs_info->sectorsize;
-	ctl->start = block_group->key.objectid;
+	ctl->start = block_group->start;
 	ctl->private = block_group;
 	ctl->op = &free_space_op;
 	INIT_LIST_HEAD(&ctl->trimming_ranges);
@@ -2532,7 +2536,7 @@ void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group)
  */
 static int
 __btrfs_return_cluster_to_free_space(
-			     struct btrfs_block_group_cache *block_group,
+			     struct btrfs_block_group *block_group,
 			     struct btrfs_free_cluster *cluster)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -2598,7 +2602,7 @@ void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl)
 	spin_unlock(&ctl->tree_lock);
 }
 
-void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
+void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_cluster *cluster;
@@ -2620,7 +2624,7 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
 
 }
 
-u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
+u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
 			       u64 offset, u64 bytes, u64 empty_size,
 			       u64 *max_extent_size)
 {
@@ -2674,7 +2678,7 @@ out:
  * cluster and remove the cluster from it.
  */
 int btrfs_return_cluster_to_free_space(
-			       struct btrfs_block_group_cache *block_group,
+			       struct btrfs_block_group *block_group,
 			       struct btrfs_free_cluster *cluster)
 {
 	struct btrfs_free_space_ctl *ctl;
@@ -2708,7 +2712,7 @@ int btrfs_return_cluster_to_free_space(
 	return ret;
 }
 
-static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
+static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group *block_group,
 				   struct btrfs_free_cluster *cluster,
 				   struct btrfs_free_space *entry,
 				   u64 bytes, u64 min_start,
@@ -2741,7 +2745,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
  * if it couldn't find anything suitably large, or a logical disk offset
  * if things worked out
  */
-u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
+u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group,
 			     struct btrfs_free_cluster *cluster, u64 bytes,
 			     u64 min_start, u64 *max_extent_size)
 {
@@ -2827,7 +2831,7 @@ out:
 	return ret;
 }
 
-static int btrfs_bitmap_cluster(struct btrfs_block_group_cache *block_group,
+static int btrfs_bitmap_cluster(struct btrfs_block_group *block_group,
 				struct btrfs_free_space *entry,
 				struct btrfs_free_cluster *cluster,
 				u64 offset, u64 bytes,
@@ -2909,7 +2913,7 @@ again:
  * extent of cont1_bytes, and other clusters of at least min_bytes.
  */
 static noinline int
-setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
+setup_cluster_no_bitmap(struct btrfs_block_group *block_group,
 			struct btrfs_free_cluster *cluster,
 			struct list_head *bitmaps, u64 offset, u64 bytes,
 			u64 cont1_bytes, u64 min_bytes)
@@ -3000,7 +3004,7 @@ setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
  * that we have already failed to find extents that will work.
  */
 static noinline int
-setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
+setup_cluster_bitmap(struct btrfs_block_group *block_group,
 		     struct btrfs_free_cluster *cluster,
 		     struct list_head *bitmaps, u64 offset, u64 bytes,
 		     u64 cont1_bytes, u64 min_bytes)
@@ -3050,7 +3054,7 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
  * returns zero and sets up cluster if things worked out, otherwise
  * it returns -enospc
  */
-int btrfs_find_space_cluster(struct btrfs_block_group_cache *block_group,
+int btrfs_find_space_cluster(struct btrfs_block_group *block_group,
 			     struct btrfs_free_cluster *cluster,
 			     u64 offset, u64 bytes, u64 empty_size)
 {
@@ -3141,7 +3145,7 @@ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster)
 	cluster->block_group = NULL;
 }
 
-static int do_trimming(struct btrfs_block_group_cache *block_group,
+static int do_trimming(struct btrfs_block_group *block_group,
 		       u64 *total_trimmed, u64 start, u64 bytes,
 		       u64 reserved_start, u64 reserved_bytes,
 		       struct btrfs_trim_range *trim_entry)
@@ -3186,7 +3190,7 @@ static int do_trimming(struct btrfs_block_group_cache *block_group,
 	return ret;
 }
 
-static int trim_no_bitmap(struct btrfs_block_group_cache *block_group,
+static int trim_no_bitmap(struct btrfs_block_group *block_group,
 			  u64 *total_trimmed, u64 start, u64 end, u64 minlen)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -3271,7 +3275,7 @@ out:
 	return ret;
 }
 
-static int trim_bitmaps(struct btrfs_block_group_cache *block_group,
+static int trim_bitmaps(struct btrfs_block_group *block_group,
 			u64 *total_trimmed, u64 start, u64 end, u64 minlen)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
@@ -3352,12 +3356,12 @@ next:
 	return ret;
 }
 
-void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache)
+void btrfs_get_block_group_trimming(struct btrfs_block_group *cache)
 {
 	atomic_inc(&cache->trimming);
 }
 
-void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *block_group)
+void btrfs_put_block_group_trimming(struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct extent_map_tree *em_tree;
@@ -3373,7 +3377,7 @@ void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *block_group)
 		mutex_lock(&fs_info->chunk_mutex);
 		em_tree = &fs_info->mapping_tree;
 		write_lock(&em_tree->lock);
-		em = lookup_extent_mapping(em_tree, block_group->key.objectid,
+		em = lookup_extent_mapping(em_tree, block_group->start,
 					   1);
 		BUG_ON(!em); /* logic error, can't happen */
 		remove_extent_mapping(em_tree, em);
@@ -3392,7 +3396,7 @@ void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *block_group)
 	}
 }
 
-int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
+int btrfs_trim_block_group(struct btrfs_block_group *block_group,
 			   u64 *trimmed, u64 start, u64 end, u64 minlen)
 {
 	int ret;
@@ -3590,7 +3594,7 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root,
  * how the free space cache loading stuff works, so you can get really weird
  * configurations.
  */
-int test_add_free_space_entry(struct btrfs_block_group_cache *cache,
+int test_add_free_space_entry(struct btrfs_block_group *cache,
 			      u64 offset, u64 bytes, bool bitmap)
 {
 	struct btrfs_free_space_ctl *ctl = cache->free_space_ctl;
@@ -3658,7 +3662,7 @@ again:
  * just used to check the absence of space, so if there is free space in the
  * range at all we will return 1.
  */
-int test_check_exists(struct btrfs_block_group_cache *cache,
+int test_check_exists(struct btrfs_block_group *cache,
 		      u64 offset, u64 bytes)
 {
 	struct btrfs_free_space_ctl *ctl = cache->free_space_ctl;
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 39c32c8fc24f..ba9a23241101 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -50,24 +50,23 @@ struct btrfs_io_ctl {
 	unsigned check_crcs:1;
 };
 
-struct inode *lookup_free_space_inode(
-		struct btrfs_block_group_cache *block_group,
+struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group,
 		struct btrfs_path *path);
 int create_free_space_inode(struct btrfs_trans_handle *trans,
-			    struct btrfs_block_group_cache *block_group,
+			    struct btrfs_block_group *block_group,
 			    struct btrfs_path *path);
 
 int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
 				       struct btrfs_block_rsv *rsv);
 int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
-				    struct btrfs_block_group_cache *block_group,
+				    struct btrfs_block_group *block_group,
 				    struct inode *inode);
-int load_free_space_cache(struct btrfs_block_group_cache *block_group);
+int load_free_space_cache(struct btrfs_block_group *block_group);
 int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
-			struct btrfs_block_group_cache *block_group,
+			struct btrfs_block_group *block_group,
 			struct btrfs_path *path);
 int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
-			  struct btrfs_block_group_cache *block_group,
+			  struct btrfs_block_group *block_group,
 			  struct btrfs_path *path);
 struct inode *lookup_free_ino_inode(struct btrfs_root *root,
 				    struct btrfs_path *path);
@@ -81,42 +80,40 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root,
 			      struct btrfs_path *path,
 			      struct inode *inode);
 
-void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group);
+void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group);
 int __btrfs_add_free_space(struct btrfs_fs_info *fs_info,
 			   struct btrfs_free_space_ctl *ctl,
 			   u64 bytenr, u64 size);
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
+int btrfs_add_free_space(struct btrfs_block_group *block_group,
 			 u64 bytenr, u64 size);
-int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
+int btrfs_remove_free_space(struct btrfs_block_group *block_group,
 			    u64 bytenr, u64 size);
 void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl);
-void btrfs_remove_free_space_cache(struct btrfs_block_group_cache
-				     *block_group);
-u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
+void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group);
+u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
 			       u64 offset, u64 bytes, u64 empty_size,
 			       u64 *max_extent_size);
 u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root);
-void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
+void btrfs_dump_free_space(struct btrfs_block_group *block_group,
 			   u64 bytes);
-int btrfs_find_space_cluster(struct btrfs_block_group_cache *block_group,
+int btrfs_find_space_cluster(struct btrfs_block_group *block_group,
 			     struct btrfs_free_cluster *cluster,
 			     u64 offset, u64 bytes, u64 empty_size);
 void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster);
-u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
+u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group,
 			     struct btrfs_free_cluster *cluster, u64 bytes,
 			     u64 min_start, u64 *max_extent_size);
 int btrfs_return_cluster_to_free_space(
-			       struct btrfs_block_group_cache *block_group,
+			       struct btrfs_block_group *block_group,
 			       struct btrfs_free_cluster *cluster);
-int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
+int btrfs_trim_block_group(struct btrfs_block_group *block_group,
 			   u64 *trimmed, u64 start, u64 end, u64 minlen);
 
 /* Support functions for running our sanity tests */
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-int test_add_free_space_entry(struct btrfs_block_group_cache *cache,
+int test_add_free_space_entry(struct btrfs_block_group *cache,
 			      u64 offset, u64 bytes, bool bitmap);
-int test_check_exists(struct btrfs_block_group_cache *cache,
-		      u64 offset, u64 bytes);
+int test_check_exists(struct btrfs_block_group *cache, u64 offset, u64 bytes);
 #endif
 
 #endif
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 48a03f5240f5..258cb3fae17a 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -13,10 +13,10 @@
 #include "block-group.h"
 
 static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
-					struct btrfs_block_group_cache *block_group,
+					struct btrfs_block_group *block_group,
 					struct btrfs_path *path);
 
-void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache)
+void set_free_space_tree_thresholds(struct btrfs_block_group *cache)
 {
 	u32 bitmap_range;
 	size_t bitmap_size;
@@ -27,8 +27,7 @@ void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache)
 	 * exceeds that required for using bitmaps.
 	 */
 	bitmap_range = cache->fs_info->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS;
-	num_bitmaps = div_u64(cache->key.offset + bitmap_range - 1,
-			      bitmap_range);
+	num_bitmaps = div_u64(cache->length + bitmap_range - 1, bitmap_range);
 	bitmap_size = sizeof(struct btrfs_item) + BTRFS_FREE_SPACE_BITMAP_SIZE;
 	total_bitmap_size = num_bitmaps * bitmap_size;
 	cache->bitmap_high_thresh = div_u64(total_bitmap_size,
@@ -45,7 +44,7 @@ void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache)
 }
 
 static int add_new_free_space_info(struct btrfs_trans_handle *trans,
-				   struct btrfs_block_group_cache *block_group,
+				   struct btrfs_block_group *block_group,
 				   struct btrfs_path *path)
 {
 	struct btrfs_root *root = trans->fs_info->free_space_root;
@@ -54,9 +53,9 @@ static int add_new_free_space_info(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 	int ret;
 
-	key.objectid = block_group->key.objectid;
+	key.objectid = block_group->start;
 	key.type = BTRFS_FREE_SPACE_INFO_KEY;
-	key.offset = block_group->key.offset;
+	key.offset = block_group->length;
 
 	ret = btrfs_insert_empty_item(trans, root, path, &key, sizeof(*info));
 	if (ret)
@@ -78,7 +77,7 @@ out:
 EXPORT_FOR_TESTS
 struct btrfs_free_space_info *search_free_space_info(
 		struct btrfs_trans_handle *trans,
-		struct btrfs_block_group_cache *block_group,
+		struct btrfs_block_group *block_group,
 		struct btrfs_path *path, int cow)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
@@ -86,16 +85,16 @@ struct btrfs_free_space_info *search_free_space_info(
 	struct btrfs_key key;
 	int ret;
 
-	key.objectid = block_group->key.objectid;
+	key.objectid = block_group->start;
 	key.type = BTRFS_FREE_SPACE_INFO_KEY;
-	key.offset = block_group->key.offset;
+	key.offset = block_group->length;
 
 	ret = btrfs_search_slot(trans, root, &key, path, 0, cow);
 	if (ret < 0)
 		return ERR_PTR(ret);
 	if (ret != 0) {
 		btrfs_warn(fs_info, "missing free space info for %llu",
-			   block_group->key.objectid);
+			   block_group->start);
 		ASSERT(0);
 		return ERR_PTR(-ENOENT);
 	}
@@ -180,7 +179,7 @@ static void le_bitmap_set(unsigned long *map, unsigned int start, int len)
 
 EXPORT_FOR_TESTS
 int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -197,7 +196,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
 	int done = 0, nr;
 	int ret;
 
-	bitmap_size = free_space_bitmap_size(block_group->key.offset,
+	bitmap_size = free_space_bitmap_size(block_group->length,
 					     fs_info->sectorsize);
 	bitmap = alloc_bitmap(bitmap_size);
 	if (!bitmap) {
@@ -205,8 +204,8 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	start = block_group->key.objectid;
-	end = block_group->key.objectid + block_group->key.offset;
+	start = block_group->start;
+	end = block_group->start + block_group->length;
 
 	key.objectid = end - 1;
 	key.type = (u8)-1;
@@ -224,8 +223,8 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
 			btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);
 
 			if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
-				ASSERT(found_key.objectid == block_group->key.objectid);
-				ASSERT(found_key.offset == block_group->key.offset);
+				ASSERT(found_key.objectid == block_group->start);
+				ASSERT(found_key.offset == block_group->length);
 				done = 1;
 				break;
 			} else if (found_key.type == BTRFS_FREE_SPACE_EXTENT_KEY) {
@@ -271,7 +270,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
 	if (extent_count != expected_extent_count) {
 		btrfs_err(fs_info,
 			  "incorrect extent count for %llu; counted %u, expected %u",
-			  block_group->key.objectid, extent_count,
+			  block_group->start, extent_count,
 			  expected_extent_count);
 		ASSERT(0);
 		ret = -EIO;
@@ -320,7 +319,7 @@ out:
 
 EXPORT_FOR_TESTS
 int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -336,7 +335,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 	int done = 0, nr;
 	int ret;
 
-	bitmap_size = free_space_bitmap_size(block_group->key.offset,
+	bitmap_size = free_space_bitmap_size(block_group->length,
 					     fs_info->sectorsize);
 	bitmap = alloc_bitmap(bitmap_size);
 	if (!bitmap) {
@@ -344,8 +343,8 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	start = block_group->key.objectid;
-	end = block_group->key.objectid + block_group->key.offset;
+	start = block_group->start;
+	end = block_group->start + block_group->length;
 
 	key.objectid = end - 1;
 	key.type = (u8)-1;
@@ -363,8 +362,8 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 			btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);
 
 			if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
-				ASSERT(found_key.objectid == block_group->key.objectid);
-				ASSERT(found_key.offset == block_group->key.offset);
+				ASSERT(found_key.objectid == block_group->start);
+				ASSERT(found_key.offset == block_group->length);
 				done = 1;
 				break;
 			} else if (found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) {
@@ -413,7 +412,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
 
-	nrbits = div_u64(block_group->key.offset, block_group->fs_info->sectorsize);
+	nrbits = div_u64(block_group->length, block_group->fs_info->sectorsize);
 	start_bit = find_next_bit_le(bitmap, nrbits, 0);
 
 	while (start_bit < nrbits) {
@@ -437,7 +436,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 	if (extent_count != expected_extent_count) {
 		btrfs_err(fs_info,
 			  "incorrect extent count for %llu; counted %u, expected %u",
-			  block_group->key.objectid, extent_count,
+			  block_group->start, extent_count,
 			  expected_extent_count);
 		ASSERT(0);
 		ret = -EIO;
@@ -453,7 +452,7 @@ out:
 }
 
 static int update_free_space_extent_count(struct btrfs_trans_handle *trans,
-					  struct btrfs_block_group_cache *block_group,
+					  struct btrfs_block_group *block_group,
 					  struct btrfs_path *path,
 					  int new_extents)
 {
@@ -491,7 +490,7 @@ out:
 }
 
 EXPORT_FOR_TESTS
-int free_space_test_bit(struct btrfs_block_group_cache *block_group,
+int free_space_test_bit(struct btrfs_block_group *block_group,
 			struct btrfs_path *path, u64 offset)
 {
 	struct extent_buffer *leaf;
@@ -513,7 +512,7 @@ int free_space_test_bit(struct btrfs_block_group_cache *block_group,
 	return !!extent_buffer_test_bit(leaf, ptr, i);
 }
 
-static void free_space_set_bits(struct btrfs_block_group_cache *block_group,
+static void free_space_set_bits(struct btrfs_block_group *block_group,
 				struct btrfs_path *path, u64 *start, u64 *size,
 				int bit)
 {
@@ -581,7 +580,7 @@ static int free_space_next_bitmap(struct btrfs_trans_handle *trans,
  * the bitmap.
  */
 static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
-				    struct btrfs_block_group_cache *block_group,
+				    struct btrfs_block_group *block_group,
 				    struct btrfs_path *path,
 				    u64 start, u64 size, int remove)
 {
@@ -597,7 +596,7 @@ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
 	 * Read the bit for the block immediately before the extent of space if
 	 * that block is within the block group.
 	 */
-	if (start > block_group->key.objectid) {
+	if (start > block_group->start) {
 		u64 prev_block = start - block_group->fs_info->sectorsize;
 
 		key.objectid = prev_block;
@@ -649,7 +648,7 @@ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
 	 * Read the bit for the block immediately after the extent of space if
 	 * that block is within the block group.
 	 */
-	if (end < block_group->key.objectid + block_group->key.offset) {
+	if (end < block_group->start + block_group->length) {
 		/* The next block may be in the next bitmap. */
 		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
 		if (end >= key.objectid + key.offset) {
@@ -694,7 +693,7 @@ out:
 }
 
 static int remove_free_space_extent(struct btrfs_trans_handle *trans,
-				    struct btrfs_block_group_cache *block_group,
+				    struct btrfs_block_group *block_group,
 				    struct btrfs_path *path,
 				    u64 start, u64 size)
 {
@@ -781,7 +780,7 @@ out:
 
 EXPORT_FOR_TESTS
 int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path, u64 start, u64 size)
 {
 	struct btrfs_free_space_info *info;
@@ -812,7 +811,7 @@ int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
 int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
 				u64 start, u64 size)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_path *path;
 	int ret;
 
@@ -846,7 +845,7 @@ out:
 }
 
 static int add_free_space_extent(struct btrfs_trans_handle *trans,
-				 struct btrfs_block_group_cache *block_group,
+				 struct btrfs_block_group *block_group,
 				 struct btrfs_path *path,
 				 u64 start, u64 size)
 {
@@ -880,7 +879,7 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans,
 	new_key.offset = size;
 
 	/* Search for a neighbor on the left. */
-	if (start == block_group->key.objectid)
+	if (start == block_group->start)
 		goto right;
 	key.objectid = start - 1;
 	key.type = (u8)-1;
@@ -900,8 +899,8 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans,
 
 	found_start = key.objectid;
 	found_end = key.objectid + key.offset;
-	ASSERT(found_start >= block_group->key.objectid &&
-	       found_end > block_group->key.objectid);
+	ASSERT(found_start >= block_group->start &&
+	       found_end > block_group->start);
 	ASSERT(found_start < start && found_end <= start);
 
 	/*
@@ -920,7 +919,7 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans,
 
 right:
 	/* Search for a neighbor on the right. */
-	if (end == block_group->key.objectid + block_group->key.offset)
+	if (end == block_group->start + block_group->length)
 		goto insert;
 	key.objectid = end;
 	key.type = (u8)-1;
@@ -940,8 +939,8 @@ right:
 
 	found_start = key.objectid;
 	found_end = key.objectid + key.offset;
-	ASSERT(found_start >= block_group->key.objectid &&
-	       found_end > block_group->key.objectid);
+	ASSERT(found_start >= block_group->start &&
+	       found_end > block_group->start);
 	ASSERT((found_start < start && found_end <= start) ||
 	       (found_start >= end && found_end > end));
 
@@ -974,7 +973,7 @@ out:
 
 EXPORT_FOR_TESTS
 int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
-			     struct btrfs_block_group_cache *block_group,
+			     struct btrfs_block_group *block_group,
 			     struct btrfs_path *path, u64 start, u64 size)
 {
 	struct btrfs_free_space_info *info;
@@ -1005,7 +1004,7 @@ int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
 int add_to_free_space_tree(struct btrfs_trans_handle *trans,
 			   u64 start, u64 size)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_path *path;
 	int ret;
 
@@ -1043,7 +1042,7 @@ out:
  * through the normal add/remove hooks.
  */
 static int populate_free_space_tree(struct btrfs_trans_handle *trans,
-				    struct btrfs_block_group_cache *block_group)
+				    struct btrfs_block_group *block_group)
 {
 	struct btrfs_root *extent_root = trans->fs_info->extent_root;
 	struct btrfs_path *path, *path2;
@@ -1075,7 +1074,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 	 * BLOCK_GROUP_ITEM, so an extent may precede the block group that it's
 	 * contained in.
 	 */
-	key.objectid = block_group->key.objectid;
+	key.objectid = block_group->start;
 	key.type = BTRFS_EXTENT_ITEM_KEY;
 	key.offset = 0;
 
@@ -1084,8 +1083,8 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 		goto out_locked;
 	ASSERT(ret == 0);
 
-	start = block_group->key.objectid;
-	end = block_group->key.objectid + block_group->key.offset;
+	start = block_group->start;
+	end = block_group->start + block_group->length;
 	while (1) {
 		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
 
@@ -1109,7 +1108,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 			else
 				start += key.offset;
 		} else if (key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) {
-			if (key.objectid != block_group->key.objectid)
+			if (key.objectid != block_group->start)
 				break;
 		}
 
@@ -1140,7 +1139,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *tree_root = fs_info->tree_root;
 	struct btrfs_root *free_space_root;
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct rb_node *node;
 	int ret;
 
@@ -1159,7 +1158,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
 
 	node = rb_first(&fs_info->block_group_cache_tree);
 	while (node) {
-		block_group = rb_entry(node, struct btrfs_block_group_cache,
+		block_group = rb_entry(node, struct btrfs_block_group,
 				       cache_node);
 		ret = populate_free_space_tree(trans, block_group);
 		if (ret)
@@ -1265,7 +1264,7 @@ abort:
 }
 
 static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
-					struct btrfs_block_group_cache *block_group,
+					struct btrfs_block_group *block_group,
 					struct btrfs_path *path)
 {
 	int ret;
@@ -1277,12 +1276,12 @@ static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
 		return ret;
 
 	return __add_to_free_space_tree(trans, block_group, path,
-					block_group->key.objectid,
-					block_group->key.offset);
+					block_group->start,
+					block_group->length);
 }
 
 int add_block_group_free_space(struct btrfs_trans_handle *trans,
-			       struct btrfs_block_group_cache *block_group)
+			       struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_path *path = NULL;
@@ -1312,7 +1311,7 @@ out:
 }
 
 int remove_block_group_free_space(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group)
+				  struct btrfs_block_group *block_group)
 {
 	struct btrfs_root *root = trans->fs_info->free_space_root;
 	struct btrfs_path *path;
@@ -1336,8 +1335,8 @@ int remove_block_group_free_space(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	start = block_group->key.objectid;
-	end = block_group->key.objectid + block_group->key.offset;
+	start = block_group->start;
+	end = block_group->start + block_group->length;
 
 	key.objectid = end - 1;
 	key.type = (u8)-1;
@@ -1355,8 +1354,8 @@ int remove_block_group_free_space(struct btrfs_trans_handle *trans,
 			btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);
 
 			if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
-				ASSERT(found_key.objectid == block_group->key.objectid);
-				ASSERT(found_key.offset == block_group->key.offset);
+				ASSERT(found_key.objectid == block_group->start);
+				ASSERT(found_key.offset == block_group->length);
 				done = 1;
 				nr++;
 				path->slots[0]--;
@@ -1391,7 +1390,7 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
 				   struct btrfs_path *path,
 				   u32 expected_extent_count)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_root *root;
 	struct btrfs_key key;
@@ -1407,7 +1406,7 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
 	fs_info = block_group->fs_info;
 	root = fs_info->free_space_root;
 
-	end = block_group->key.objectid + block_group->key.offset;
+	end = block_group->start + block_group->length;
 
 	while (1) {
 		ret = btrfs_next_item(root, path);
@@ -1454,7 +1453,7 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
 	if (extent_count != expected_extent_count) {
 		btrfs_err(fs_info,
 			  "incorrect extent count for %llu; counted %u, expected %u",
-			  block_group->key.objectid, extent_count,
+			  block_group->start, extent_count,
 			  expected_extent_count);
 		ASSERT(0);
 		ret = -EIO;
@@ -1472,7 +1471,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
 				   struct btrfs_path *path,
 				   u32 expected_extent_count)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_root *root;
 	struct btrfs_key key;
@@ -1485,7 +1484,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
 	fs_info = block_group->fs_info;
 	root = fs_info->free_space_root;
 
-	end = block_group->key.objectid + block_group->key.offset;
+	end = block_group->start + block_group->length;
 
 	while (1) {
 		ret = btrfs_next_item(root, path);
@@ -1516,7 +1515,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
 	if (extent_count != expected_extent_count) {
 		btrfs_err(fs_info,
 			  "incorrect extent count for %llu; counted %u, expected %u",
-			  block_group->key.objectid, extent_count,
+			  block_group->start, extent_count,
 			  expected_extent_count);
 		ASSERT(0);
 		ret = -EIO;
@@ -1532,7 +1531,7 @@ out:
 
 int load_free_space_tree(struct btrfs_caching_control *caching_ctl)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	struct btrfs_free_space_info *info;
 	struct btrfs_path *path;
 	u32 extent_count, flags;
diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h
index 360d50e1cdea..dc2463e4cfe3 100644
--- a/fs/btrfs/free-space-tree.h
+++ b/fs/btrfs/free-space-tree.h
@@ -16,14 +16,14 @@ struct btrfs_caching_control;
 #define BTRFS_FREE_SPACE_BITMAP_SIZE 256
 #define BTRFS_FREE_SPACE_BITMAP_BITS (BTRFS_FREE_SPACE_BITMAP_SIZE * BITS_PER_BYTE)
 
-void set_free_space_tree_thresholds(struct btrfs_block_group_cache *block_group);
+void set_free_space_tree_thresholds(struct btrfs_block_group *block_group);
 int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info);
 int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info);
 int load_free_space_tree(struct btrfs_caching_control *caching_ctl);
 int add_block_group_free_space(struct btrfs_trans_handle *trans,
-			       struct btrfs_block_group_cache *block_group);
+			       struct btrfs_block_group *block_group);
 int remove_block_group_free_space(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group);
+				  struct btrfs_block_group *block_group);
 int add_to_free_space_tree(struct btrfs_trans_handle *trans,
 			   u64 start, u64 size);
 int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
@@ -32,21 +32,21 @@ int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 struct btrfs_free_space_info *
 search_free_space_info(struct btrfs_trans_handle *trans,
-		       struct btrfs_block_group_cache *block_group,
+		       struct btrfs_block_group *block_group,
 		       struct btrfs_path *path, int cow);
 int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
-			     struct btrfs_block_group_cache *block_group,
+			     struct btrfs_block_group *block_group,
 			     struct btrfs_path *path, u64 start, u64 size);
 int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path, u64 start, u64 size);
 int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path);
 int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
-				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_block_group *block_group,
 				  struct btrfs_path *path);
-int free_space_test_bit(struct btrfs_block_group_cache *block_group,
+int free_space_test_bit(struct btrfs_block_group *block_group,
 			struct btrfs_path *path, u64 offset);
 #endif
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 015910079e73..56032c518b26 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -368,6 +368,7 @@ struct async_chunk {
 	u64 end;
 	unsigned int write_flags;
 	struct list_head extents;
+	struct cgroup_subsys_state *blkcg_css;
 	struct btrfs_work work;
 	atomic_t *pending;
 };
@@ -712,10 +713,12 @@ cleanup_and_bail_uncompressed:
 	 * to our extent and set things up for the async work queue to run
 	 * cow_file_range to do the normal delalloc dance.
 	 */
-	if (page_offset(async_chunk->locked_page) >= start &&
-	    page_offset(async_chunk->locked_page) <= end)
+	if (async_chunk->locked_page &&
+	    (page_offset(async_chunk->locked_page) >= start &&
+	     page_offset(async_chunk->locked_page)) <= end) {
 		__set_page_dirty_nobuffers(async_chunk->locked_page);
 		/* unlocked later on in the async handlers */
+	}
 
 	if (redirty)
 		extent_range_redirty_for_io(inode, start, end);
@@ -795,7 +798,7 @@ retry:
 						  async_extent->start +
 						  async_extent->ram_size - 1,
 						  WB_SYNC_ALL);
-			else if (ret)
+			else if (ret && async_chunk->locked_page)
 				unlock_page(async_chunk->locked_page);
 			kfree(async_extent);
 			cond_resched();
@@ -878,7 +881,8 @@ retry:
 				    ins.objectid,
 				    ins.offset, async_extent->pages,
 				    async_extent->nr_pages,
-				    async_chunk->write_flags)) {
+				    async_chunk->write_flags,
+				    async_chunk->blkcg_css)) {
 			struct page *p = async_extent->pages[0];
 			const u64 start = async_extent->start;
 			const u64 end = start + async_extent->ram_size - 1;
@@ -1196,6 +1200,8 @@ static noinline void async_cow_free(struct btrfs_work *work)
 	async_chunk = container_of(work, struct async_chunk, work);
 	if (async_chunk->inode)
 		btrfs_add_delayed_iput(async_chunk->inode);
+	if (async_chunk->blkcg_css)
+		css_put(async_chunk->blkcg_css);
 	/*
 	 * Since the pointer to 'pending' is at the beginning of the array of
 	 * async_chunk's, freeing it ensures the whole array has been freed.
@@ -1204,12 +1210,14 @@ static noinline void async_cow_free(struct btrfs_work *work)
 		kvfree(async_chunk->pending);
 }
 
-static int cow_file_range_async(struct inode *inode, struct page *locked_page,
+static int cow_file_range_async(struct inode *inode,
+				struct writeback_control *wbc,
+				struct page *locked_page,
 				u64 start, u64 end, int *page_started,
-				unsigned long *nr_written,
-				unsigned int write_flags)
+				unsigned long *nr_written)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct cgroup_subsys_state *blkcg_css = wbc_blkcg_css(wbc);
 	struct async_cow *ctx;
 	struct async_chunk *async_chunk;
 	unsigned long nr_pages;
@@ -1218,6 +1226,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 	int i;
 	bool should_compress;
 	unsigned nofs_flag;
+	const unsigned int write_flags = wbc_to_write_flags(wbc);
 
 	unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
 
@@ -1264,14 +1273,45 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 		async_chunk[i].inode = inode;
 		async_chunk[i].start = start;
 		async_chunk[i].end = cur_end;
-		async_chunk[i].locked_page = locked_page;
 		async_chunk[i].write_flags = write_flags;
 		INIT_LIST_HEAD(&async_chunk[i].extents);
 
-		btrfs_init_work(&async_chunk[i].work,
-				btrfs_delalloc_helper,
-				async_cow_start, async_cow_submit,
-				async_cow_free);
+		/*
+		 * The locked_page comes all the way from writepage and its
+		 * the original page we were actually given.  As we spread
+		 * this large delalloc region across multiple async_chunk
+		 * structs, only the first struct needs a pointer to locked_page
+		 *
+		 * This way we don't need racey decisions about who is supposed
+		 * to unlock it.
+		 */
+		if (locked_page) {
+			/*
+			 * Depending on the compressibility, the pages might or
+			 * might not go through async.  We want all of them to
+			 * be accounted against wbc once.  Let's do it here
+			 * before the paths diverge.  wbc accounting is used
+			 * only for foreign writeback detection and doesn't
+			 * need full accuracy.  Just account the whole thing
+			 * against the first page.
+			 */
+			wbc_account_cgroup_owner(wbc, locked_page,
+						 cur_end - start);
+			async_chunk[i].locked_page = locked_page;
+			locked_page = NULL;
+		} else {
+			async_chunk[i].locked_page = NULL;
+		}
+
+		if (blkcg_css != blkcg_root_css) {
+			css_get(blkcg_css);
+			async_chunk[i].blkcg_css = blkcg_css;
+		} else {
+			async_chunk[i].blkcg_css = NULL;
+		}
+
+		btrfs_init_work(&async_chunk[i].work, async_cow_start,
+				async_cow_submit, async_cow_free);
 
 		nr_pages = DIV_ROUND_UP(cur_end - start, PAGE_SIZE);
 		atomic_add(nr_pages, &fs_info->async_delalloc_pages);
@@ -1697,7 +1737,6 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page,
 {
 	int ret;
 	int force_cow = need_force_cow(inode, start, end);
-	unsigned int write_flags = wbc_to_write_flags(wbc);
 
 	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW && !force_cow) {
 		ret = run_delalloc_nocow(inode, locked_page, start, end,
@@ -1712,9 +1751,8 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page,
 	} else {
 		set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
 			&BTRFS_I(inode)->runtime_flags);
-		ret = cow_file_range_async(inode, locked_page, start, end,
-					   page_started, nr_written,
-					   write_flags);
+		ret = cow_file_range_async(inode, wbc, locked_page, start, end,
+					   page_started, nr_written);
 	}
 	if (ret)
 		btrfs_cleanup_ordered_extents(inode, locked_page, start,
@@ -2110,7 +2148,7 @@ static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
 	}
 
 mapit:
-	ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+	ret = btrfs_map_bio(fs_info, bio, mirror_num);
 
 out:
 	if (ret) {
@@ -2214,12 +2252,16 @@ again:
 		mapping_set_error(page->mapping, ret);
 		end_extent_writepage(page, ret, page_start, page_end);
 		ClearPageChecked(page);
-		goto out;
+		goto out_reserved;
 	}
 
 	ClearPageChecked(page);
 	set_page_dirty(page);
+out_reserved:
 	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
+	if (ret)
+		btrfs_delalloc_release_space(inode, data_reserved, page_start,
+					     PAGE_SIZE, true);
 out:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end,
 			     &cached_state);
@@ -2260,8 +2302,7 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end)
 
 	SetPageChecked(page);
 	get_page(page);
-	btrfs_init_work(&fixup->work, btrfs_fixup_helper,
-			btrfs_writepage_fixup_worker, NULL, NULL);
+	btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
 	fixup->page = page;
 	btrfs_queue_work(fs_info->fixup_workers, &fixup->work);
 	return -EBUSY;
@@ -2675,7 +2716,7 @@ static noinline int relink_extent_backref(struct btrfs_path *path,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, root);
 	if (IS_ERR(inode)) {
 		srcu_read_unlock(&fs_info->subvol_srcu, index);
 		return 0;
@@ -2999,7 +3040,7 @@ out_kfree:
 static void btrfs_release_delalloc_bytes(struct btrfs_fs_info *fs_info,
 					 u64 start, u64 len)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 
 	cache = btrfs_lookup_block_group(fs_info, start);
 	ASSERT(cache);
@@ -3027,7 +3068,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 	int compress_type = 0;
 	int ret = 0;
 	u64 logical_len = ordered_extent->len;
-	bool nolock;
+	bool freespace_inode;
 	bool truncated = false;
 	bool range_locked = false;
 	bool clear_new_delalloc_bytes = false;
@@ -3038,7 +3079,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 	    !test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags))
 		clear_new_delalloc_bytes = true;
 
-	nolock = btrfs_is_free_space_inode(BTRFS_I(inode));
+	freespace_inode = btrfs_is_free_space_inode(BTRFS_I(inode));
 
 	if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) {
 		ret = -EIO;
@@ -3069,8 +3110,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset,
 				       ordered_extent->len);
 		btrfs_ordered_update_i_size(inode, 0, ordered_extent);
-		if (nolock)
-			trans = btrfs_join_transaction_nolock(root);
+		if (freespace_inode)
+			trans = btrfs_join_transaction_spacecache(root);
 		else
 			trans = btrfs_join_transaction(root);
 		if (IS_ERR(trans)) {
@@ -3104,8 +3145,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 			EXTENT_DEFRAG, 0, 0, &cached_state);
 	}
 
-	if (nolock)
-		trans = btrfs_join_transaction_nolock(root);
+	if (freespace_inode)
+		trans = btrfs_join_transaction_spacecache(root);
 	else
 		trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans)) {
@@ -3254,7 +3295,6 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ordered_extent *ordered_extent = NULL;
 	struct btrfs_workqueue *wq;
-	btrfs_work_func_t func;
 
 	trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
 
@@ -3263,16 +3303,12 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
 					    end - start + 1, uptodate))
 		return;
 
-	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode)))
 		wq = fs_info->endio_freespace_worker;
-		func = btrfs_freespace_write_helper;
-	} else {
+	else
 		wq = fs_info->endio_write_workers;
-		func = btrfs_endio_write_helper;
-	}
 
-	btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
-			NULL);
+	btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
 	btrfs_queue_work(wq, &ordered_extent->work);
 }
 
@@ -3531,7 +3567,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 		found_key.objectid = found_key.offset;
 		found_key.type = BTRFS_INODE_ITEM_KEY;
 		found_key.offset = 0;
-		inode = btrfs_iget(fs_info->sb, &found_key, root, NULL);
+		inode = btrfs_iget(fs_info->sb, &found_key, root);
 		ret = PTR_ERR_OR_ZERO(inode);
 		if (ret && ret != -ENOENT)
 			goto out;
@@ -5153,7 +5189,6 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 			hole_em->block_len = 0;
 			hole_em->orig_block_len = 0;
 			hole_em->ram_bytes = hole_size;
-			hole_em->bdev = fs_info->fs_devices->latest_bdev;
 			hole_em->compress_type = BTRFS_COMPRESS_NONE;
 			hole_em->generation = fs_info->generation;
 
@@ -5750,12 +5785,14 @@ static struct inode *btrfs_iget_locked(struct super_block *s,
 	return inode;
 }
 
-/* Get an inode object given its location and corresponding root.
- * Returns in *is_new if the inode was read from disk
+/*
+ * Get an inode object given its location and corresponding root.
+ * Path can be preallocated to prevent recursing back to iget through
+ * allocator. NULL is also valid but may require an additional allocation
+ * later.
  */
 struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
-			      struct btrfs_root *root, int *new,
-			      struct btrfs_path *path)
+			      struct btrfs_root *root, struct btrfs_path *path)
 {
 	struct inode *inode;
 
@@ -5770,8 +5807,6 @@ struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
 		if (!ret) {
 			inode_tree_add(inode);
 			unlock_new_inode(inode);
-			if (new)
-				*new = 1;
 		} else {
 			iget_failed(inode);
 			/*
@@ -5789,9 +5824,9 @@ struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
 }
 
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
-			 struct btrfs_root *root, int *new)
+			 struct btrfs_root *root)
 {
-	return btrfs_iget_path(s, location, root, new, NULL);
+	return btrfs_iget_path(s, location, root, NULL);
 }
 
 static struct inode *new_simple_dir(struct super_block *s,
@@ -5857,7 +5892,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 		return ERR_PTR(ret);
 
 	if (location.type == BTRFS_INODE_ITEM_KEY) {
-		inode = btrfs_iget(dir->i_sb, &location, root, NULL);
+		inode = btrfs_iget(dir->i_sb, &location, root);
 		if (IS_ERR(inode))
 			return inode;
 
@@ -5882,7 +5917,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 		else
 			inode = new_simple_dir(dir->i_sb, &location, sub_root);
 	} else {
-		inode = btrfs_iget(dir->i_sb, &location, sub_root, NULL);
+		inode = btrfs_iget(dir->i_sb, &location, sub_root);
 	}
 	srcu_read_unlock(&fs_info->subvol_srcu, index);
 
@@ -6931,8 +6966,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 
 	read_lock(&em_tree->lock);
 	em = lookup_extent_mapping(em_tree, start, len);
-	if (em)
-		em->bdev = fs_info->fs_devices->latest_bdev;
 	read_unlock(&em_tree->lock);
 
 	if (em) {
@@ -6948,7 +6981,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 		err = -ENOMEM;
 		goto out;
 	}
-	em->bdev = fs_info->fs_devices->latest_bdev;
 	em->start = EXTENT_MAP_HOLE;
 	em->orig_start = EXTENT_MAP_HOLE;
 	em->len = (u64)-1;
@@ -7207,7 +7239,6 @@ struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
 			err = -ENOMEM;
 			goto out;
 		}
-		em->bdev = NULL;
 
 		ASSERT(hole_em);
 		/*
@@ -7567,7 +7598,6 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
 {
 	struct extent_map_tree *em_tree;
 	struct extent_map *em;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
 
 	ASSERT(type == BTRFS_ORDERED_PREALLOC ||
@@ -7585,7 +7615,6 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
 	em->len = len;
 	em->block_len = block_len;
 	em->block_start = block_start;
-	em->bdev = root->fs_info->fs_devices->latest_bdev;
 	em->orig_block_len = orig_block_len;
 	em->ram_bytes = ram_bytes;
 	em->generation = -1;
@@ -7624,6 +7653,8 @@ static int btrfs_get_blocks_direct_read(struct extent_map *em,
 					struct inode *inode,
 					u64 start, u64 len)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+
 	if (em->block_start == EXTENT_MAP_HOLE ||
 			test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 		return -ENOENT;
@@ -7633,7 +7664,7 @@ static int btrfs_get_blocks_direct_read(struct extent_map *em,
 	bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
 		inode->i_blkbits;
 	bh_result->b_size = len;
-	bh_result->b_bdev = em->bdev;
+	bh_result->b_bdev = fs_info->fs_devices->latest_bdev;
 	set_buffer_mapped(bh_result);
 
 	return 0;
@@ -7716,7 +7747,7 @@ skip_cow:
 	bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
 		inode->i_blkbits;
 	bh_result->b_size = len;
-	bh_result->b_bdev = em->bdev;
+	bh_result->b_bdev = fs_info->fs_devices->latest_bdev;
 	set_buffer_mapped(bh_result);
 
 	if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
@@ -7858,7 +7889,7 @@ static inline blk_status_t submit_dio_repair_bio(struct inode *inode,
 	if (ret)
 		return ret;
 
-	ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+	ret = btrfs_map_bio(fs_info, bio, mirror_num);
 
 	return ret;
 }
@@ -8211,18 +8242,14 @@ static void __endio_write_update_ordered(struct inode *inode,
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ordered_extent *ordered = NULL;
 	struct btrfs_workqueue *wq;
-	btrfs_work_func_t func;
 	u64 ordered_offset = offset;
 	u64 ordered_bytes = bytes;
 	u64 last_offset;
 
-	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode)))
 		wq = fs_info->endio_freespace_worker;
-		func = btrfs_freespace_write_helper;
-	} else {
+	else
 		wq = fs_info->endio_write_workers;
-		func = btrfs_endio_write_helper;
-	}
 
 	while (ordered_offset < offset + bytes) {
 		last_offset = ordered_offset;
@@ -8230,9 +8257,8 @@ static void __endio_write_update_ordered(struct inode *inode,
 							   &ordered_offset,
 							   ordered_bytes,
 							   uptodate)) {
-			btrfs_init_work(&ordered->work, func,
-					finish_ordered_fn,
-					NULL, NULL);
+			btrfs_init_work(&ordered->work, finish_ordered_fn, NULL,
+					NULL);
 			btrfs_queue_work(wq, &ordered->work);
 		}
 		/*
@@ -8389,7 +8415,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio,
 			goto err;
 	}
 map:
-	ret = btrfs_map_bio(fs_info, bio, 0, 0);
+	ret = btrfs_map_bio(fs_info, bio, 0);
 err:
 	return ret;
 }
@@ -9321,7 +9347,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->io_failure_tree.track_uptodate = true;
 	atomic_set(&ei->sync_writers, 0);
 	mutex_init(&ei->log_mutex);
-	mutex_init(&ei->delalloc_mutex);
 	btrfs_ordered_inode_tree_init(&ei->ordered_tree);
 	INIT_LIST_HEAD(&ei->delalloc_inodes);
 	INIT_LIST_HEAD(&ei->delayed_iput);
@@ -9550,6 +9575,9 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 		goto out_notrans;
 	}
 
+	if (dest != root)
+		btrfs_record_root_in_trans(trans, dest);
+
 	/*
 	 * We need to find a free sequence number both in the source and
 	 * in the destination directory for the exchange.
@@ -10116,8 +10144,7 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode
 	init_completion(&work->completion);
 	INIT_LIST_HEAD(&work->list);
 	work->inode = inode;
-	btrfs_init_work(&work->work, btrfs_flush_delalloc_helper,
-			btrfs_run_delalloc_work, NULL, NULL);
+	btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
 
 	return work;
 }
@@ -10450,7 +10477,6 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 		em->block_len = ins.offset;
 		em->orig_block_len = ins.offset;
 		em->ram_bytes = ins.offset;
-		em->bdev = fs_info->fs_devices->latest_bdev;
 		set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
 		em->generation = trans->transid;
 
@@ -10806,7 +10832,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	start = 0;
 	while (start < isize) {
 		u64 logical_block_start, physical_block_start;
-		struct btrfs_block_group_cache *bg;
+		struct btrfs_block_group *bg;
 		u64 len = isize - start;
 
 		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len, 0);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 23272d9154f3..a1ee0b775e65 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -479,10 +479,9 @@ static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
 	return put_user(inode->i_generation, arg);
 }
 
-static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
+static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info,
+					void __user *arg)
 {
-	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_device *device;
 	struct request_queue *q;
 	struct fstrim_range range;
@@ -541,7 +540,7 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
 	return 0;
 }
 
-int btrfs_is_empty_uuid(u8 *uuid)
+int __pure btrfs_is_empty_uuid(u8 *uuid)
 {
 	int i;
 
@@ -1409,7 +1408,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 		return -EINVAL;
 
 	if (do_compress) {
-		if (range->compress_type > BTRFS_COMPRESS_TYPES)
+		if (range->compress_type >= BTRFS_NR_COMPRESS_TYPES)
 			return -EINVAL;
 		if (range->compress_type)
 			compress_type = range->compress_type;
@@ -2462,7 +2461,7 @@ static int btrfs_search_path_in_tree_user(struct inode *inode,
 				goto out;
 			}
 
-			temp_inode = btrfs_iget(sb, &key2, root, NULL);
+			temp_inode = btrfs_iget(sb, &key2, root);
 			if (IS_ERR(temp_inode)) {
 				ret = PTR_ERR(temp_inode);
 				goto out;
@@ -4032,16 +4031,15 @@ out:
 static void get_block_group_info(struct list_head *groups_list,
 				 struct btrfs_ioctl_space_info *space)
 {
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 
 	space->total_bytes = 0;
 	space->used_bytes = 0;
 	space->flags = 0;
 	list_for_each_entry(block_group, groups_list, list) {
 		space->flags = block_group->flags;
-		space->total_bytes += block_group->key.offset;
-		space->used_bytes +=
-			btrfs_block_group_used(&block_group->item);
+		space->total_bytes += block_group->length;
+		space->used_bytes += block_group->used;
 	}
 }
 
@@ -4952,10 +4950,9 @@ drop_write:
 	return ret;
 }
 
-static long btrfs_ioctl_quota_rescan_status(struct file *file, void __user *arg)
+static long btrfs_ioctl_quota_rescan_status(struct btrfs_fs_info *fs_info,
+						void __user *arg)
 {
-	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_quota_rescan_args *qsa;
 	int ret = 0;
 
@@ -4978,11 +4975,9 @@ static long btrfs_ioctl_quota_rescan_status(struct file *file, void __user *arg)
 	return ret;
 }
 
-static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg)
+static long btrfs_ioctl_quota_rescan_wait(struct btrfs_fs_info *fs_info,
+						void __user *arg)
 {
-	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
@@ -5154,10 +5149,9 @@ out:
 	return ret;
 }
 
-static int btrfs_ioctl_get_fslabel(struct file *file, void __user *arg)
+static int btrfs_ioctl_get_fslabel(struct btrfs_fs_info *fs_info,
+					void __user *arg)
 {
-	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	size_t len;
 	int ret;
 	char label[BTRFS_LABEL_SIZE];
@@ -5241,10 +5235,9 @@ int btrfs_ioctl_get_supported_features(void __user *arg)
 	return 0;
 }
 
-static int btrfs_ioctl_get_features(struct file *file, void __user *arg)
+static int btrfs_ioctl_get_features(struct btrfs_fs_info *fs_info,
+					void __user *arg)
 {
-	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_super_block *super_block = fs_info->super_copy;
 	struct btrfs_ioctl_feature_flags features;
 
@@ -5445,11 +5438,11 @@ long btrfs_ioctl(struct file *file, unsigned int
 	case FS_IOC_GETVERSION:
 		return btrfs_ioctl_getversion(file, argp);
 	case FS_IOC_GETFSLABEL:
-		return btrfs_ioctl_get_fslabel(file, argp);
+		return btrfs_ioctl_get_fslabel(fs_info, argp);
 	case FS_IOC_SETFSLABEL:
 		return btrfs_ioctl_set_fslabel(file, argp);
 	case FITRIM:
-		return btrfs_ioctl_fitrim(file, argp);
+		return btrfs_ioctl_fitrim(fs_info, argp);
 	case BTRFS_IOC_SNAP_CREATE:
 		return btrfs_ioctl_snap_create(file, argp, 0);
 	case BTRFS_IOC_SNAP_CREATE_V2:
@@ -5554,15 +5547,15 @@ long btrfs_ioctl(struct file *file, unsigned int
 	case BTRFS_IOC_QUOTA_RESCAN:
 		return btrfs_ioctl_quota_rescan(file, argp);
 	case BTRFS_IOC_QUOTA_RESCAN_STATUS:
-		return btrfs_ioctl_quota_rescan_status(file, argp);
+		return btrfs_ioctl_quota_rescan_status(fs_info, argp);
 	case BTRFS_IOC_QUOTA_RESCAN_WAIT:
-		return btrfs_ioctl_quota_rescan_wait(file, argp);
+		return btrfs_ioctl_quota_rescan_wait(fs_info, argp);
 	case BTRFS_IOC_DEV_REPLACE:
 		return btrfs_ioctl_dev_replace(fs_info, argp);
 	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
 		return btrfs_ioctl_get_supported_features(argp);
 	case BTRFS_IOC_GET_FEATURES:
-		return btrfs_ioctl_get_features(file, argp);
+		return btrfs_ioctl_get_features(fs_info, argp);
 	case BTRFS_IOC_SET_FEATURES:
 		return btrfs_ioctl_set_features(file, argp);
 	case FS_IOC_FSGETXATTR:
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 7f9a578a1a20..571c4826c428 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -13,65 +13,164 @@
 #include "extent_io.h"
 #include "locking.h"
 
+/*
+ * Extent buffer locking
+ * =====================
+ *
+ * The locks use a custom scheme that allows to do more operations than are
+ * available fromt current locking primitives. The building blocks are still
+ * rwlock and wait queues.
+ *
+ * Required semantics:
+ *
+ * - reader/writer exclusion
+ * - writer/writer exclusion
+ * - reader/reader sharing
+ * - spinning lock semantics
+ * - blocking lock semantics
+ * - try-lock semantics for readers and writers
+ * - one level nesting, allowing read lock to be taken by the same thread that
+ *   already has write lock
+ *
+ * The extent buffer locks (also called tree locks) manage access to eb data
+ * related to the storage in the b-tree (keys, items, but not the individual
+ * members of eb).
+ * We want concurrency of many readers and safe updates. The underlying locking
+ * is done by read-write spinlock and the blocking part is implemented using
+ * counters and wait queues.
+ *
+ * spinning semantics - the low-level rwlock is held so all other threads that
+ *                      want to take it are spinning on it.
+ *
+ * blocking semantics - the low-level rwlock is not held but the counter
+ *                      denotes how many times the blocking lock was held;
+ *                      sleeping is possible
+ *
+ * Write lock always allows only one thread to access the data.
+ *
+ *
+ * Debugging
+ * ---------
+ *
+ * There are additional state counters that are asserted in various contexts,
+ * removed from non-debug build to reduce extent_buffer size and for
+ * performance reasons.
+ *
+ *
+ * Lock nesting
+ * ------------
+ *
+ * A write operation on a tree might indirectly start a look up on the same
+ * tree.  This can happen when btrfs_cow_block locks the tree and needs to
+ * lookup free extents.
+ *
+ * btrfs_cow_block
+ *   ..
+ *   alloc_tree_block_no_bg_flush
+ *     btrfs_alloc_tree_block
+ *       btrfs_reserve_extent
+ *         ..
+ *         load_free_space_cache
+ *           ..
+ *           btrfs_lookup_file_extent
+ *             btrfs_search_slot
+ *
+ *
+ * Locking pattern - spinning
+ * --------------------------
+ *
+ * The simple locking scenario, the +--+ denotes the spinning section.
+ *
+ * +- btrfs_tree_lock
+ * | - extent_buffer::rwlock is held
+ * | - no heavy operations should happen, eg. IO, memory allocations, large
+ * |   structure traversals
+ * +- btrfs_tree_unock
+*
+*
+ * Locking pattern - blocking
+ * --------------------------
+ *
+ * The blocking write uses the following scheme.  The +--+ denotes the spinning
+ * section.
+ *
+ * +- btrfs_tree_lock
+ * |
+ * +- btrfs_set_lock_blocking_write
+ *
+ *   - allowed: IO, memory allocations, etc.
+ *
+ * -- btrfs_tree_unlock - note, no explicit unblocking necessary
+ *
+ *
+ * Blocking read is similar.
+ *
+ * +- btrfs_tree_read_lock
+ * |
+ * +- btrfs_set_lock_blocking_read
+ *
+ *  - heavy operations allowed
+ *
+ * +- btrfs_tree_read_unlock_blocking
+ * |
+ * +- btrfs_tree_read_unlock
+ *
+ */
+
 #ifdef CONFIG_BTRFS_DEBUG
-static void btrfs_assert_spinning_writers_get(struct extent_buffer *eb)
+static inline void btrfs_assert_spinning_writers_get(struct extent_buffer *eb)
 {
 	WARN_ON(eb->spinning_writers);
 	eb->spinning_writers++;
 }
 
-static void btrfs_assert_spinning_writers_put(struct extent_buffer *eb)
+static inline void btrfs_assert_spinning_writers_put(struct extent_buffer *eb)
 {
 	WARN_ON(eb->spinning_writers != 1);
 	eb->spinning_writers--;
 }
 
-static void btrfs_assert_no_spinning_writers(struct extent_buffer *eb)
+static inline void btrfs_assert_no_spinning_writers(struct extent_buffer *eb)
 {
 	WARN_ON(eb->spinning_writers);
 }
 
-static void btrfs_assert_spinning_readers_get(struct extent_buffer *eb)
+static inline void btrfs_assert_spinning_readers_get(struct extent_buffer *eb)
 {
 	atomic_inc(&eb->spinning_readers);
 }
 
-static void btrfs_assert_spinning_readers_put(struct extent_buffer *eb)
+static inline void btrfs_assert_spinning_readers_put(struct extent_buffer *eb)
 {
 	WARN_ON(atomic_read(&eb->spinning_readers) == 0);
 	atomic_dec(&eb->spinning_readers);
 }
 
-static void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb)
 {
 	atomic_inc(&eb->read_locks);
 }
 
-static void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb)
 {
 	atomic_dec(&eb->read_locks);
 }
 
-static void btrfs_assert_tree_read_locked(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_read_locked(struct extent_buffer *eb)
 {
 	BUG_ON(!atomic_read(&eb->read_locks));
 }
 
-static void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb)
 {
 	eb->write_locks++;
 }
 
-static void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb)
+static inline void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb)
 {
 	eb->write_locks--;
 }
 
-void btrfs_assert_tree_locked(struct extent_buffer *eb)
-{
-	BUG_ON(!eb->write_locks);
-}
-
 #else
 static void btrfs_assert_spinning_writers_get(struct extent_buffer *eb) { }
 static void btrfs_assert_spinning_writers_put(struct extent_buffer *eb) { }
@@ -81,11 +180,19 @@ static void btrfs_assert_spinning_readers_get(struct extent_buffer *eb) { }
 static void btrfs_assert_tree_read_locked(struct extent_buffer *eb) { }
 static void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb) { }
 static void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb) { }
-void btrfs_assert_tree_locked(struct extent_buffer *eb) { }
 static void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb) { }
 static void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb) { }
 #endif
 
+/*
+ * Mark already held read lock as blocking. Can be nested in write lock by the
+ * same thread.
+ *
+ * Use when there are potentially long operations ahead so other thread waiting
+ * on the lock will not actively spin but sleep instead.
+ *
+ * The rwlock is released and blocking reader counter is increased.
+ */
 void btrfs_set_lock_blocking_read(struct extent_buffer *eb)
 {
 	trace_btrfs_set_lock_blocking_read(eb);
@@ -102,6 +209,14 @@ void btrfs_set_lock_blocking_read(struct extent_buffer *eb)
 	read_unlock(&eb->lock);
 }
 
+/*
+ * Mark already held write lock as blocking.
+ *
+ * Use when there are potentially long operations ahead so other threads
+ * waiting on the lock will not actively spin but sleep instead.
+ *
+ * The rwlock is released and blocking writers is set.
+ */
 void btrfs_set_lock_blocking_write(struct extent_buffer *eb)
 {
 	trace_btrfs_set_lock_blocking_write(eb);
@@ -115,14 +230,19 @@ void btrfs_set_lock_blocking_write(struct extent_buffer *eb)
 	if (eb->blocking_writers == 0) {
 		btrfs_assert_spinning_writers_put(eb);
 		btrfs_assert_tree_locked(eb);
-		eb->blocking_writers++;
+		WRITE_ONCE(eb->blocking_writers, 1);
 		write_unlock(&eb->lock);
 	}
 }
 
 /*
- * take a spinning read lock.  This will wait for any blocking
- * writers
+ * Lock the extent buffer for read. Wait for any writers (spinning or blocking).
+ * Can be nested in write lock by the same thread.
+ *
+ * Use when the locked section does only lightweight actions and busy waiting
+ * would be cheaper than making other threads do the wait/wake loop.
+ *
+ * The rwlock is held upon exit.
  */
 void btrfs_tree_read_lock(struct extent_buffer *eb)
 {
@@ -134,23 +254,24 @@ again:
 	read_lock(&eb->lock);
 	BUG_ON(eb->blocking_writers == 0 &&
 	       current->pid == eb->lock_owner);
-	if (eb->blocking_writers && current->pid == eb->lock_owner) {
-		/*
-		 * This extent is already write-locked by our thread. We allow
-		 * an additional read lock to be added because it's for the same
-		 * thread. btrfs_find_all_roots() depends on this as it may be
-		 * called on a partly (write-)locked tree.
-		 */
-		BUG_ON(eb->lock_nested);
-		eb->lock_nested = true;
-		read_unlock(&eb->lock);
-		trace_btrfs_tree_read_lock(eb, start_ns);
-		return;
-	}
 	if (eb->blocking_writers) {
+		if (current->pid == eb->lock_owner) {
+			/*
+			 * This extent is already write-locked by our thread.
+			 * We allow an additional read lock to be added because
+			 * it's for the same thread. btrfs_find_all_roots()
+			 * depends on this as it may be called on a partly
+			 * (write-)locked tree.
+			 */
+			BUG_ON(eb->lock_nested);
+			eb->lock_nested = true;
+			read_unlock(&eb->lock);
+			trace_btrfs_tree_read_lock(eb, start_ns);
+			return;
+		}
 		read_unlock(&eb->lock);
 		wait_event(eb->write_lock_wq,
-			   eb->blocking_writers == 0);
+			   READ_ONCE(eb->blocking_writers) == 0);
 		goto again;
 	}
 	btrfs_assert_tree_read_locks_get(eb);
@@ -159,17 +280,19 @@ again:
 }
 
 /*
- * take a spinning read lock.
- * returns 1 if we get the read lock and 0 if we don't
- * this won't wait for blocking writers
+ * Lock extent buffer for read, optimistically expecting that there are no
+ * contending blocking writers. If there are, don't wait.
+ *
+ * Return 1 if the rwlock has been taken, 0 otherwise
  */
 int btrfs_tree_read_lock_atomic(struct extent_buffer *eb)
 {
-	if (eb->blocking_writers)
+	if (READ_ONCE(eb->blocking_writers))
 		return 0;
 
 	read_lock(&eb->lock);
-	if (eb->blocking_writers) {
+	/* Refetch value after lock */
+	if (READ_ONCE(eb->blocking_writers)) {
 		read_unlock(&eb->lock);
 		return 0;
 	}
@@ -180,18 +303,20 @@ int btrfs_tree_read_lock_atomic(struct extent_buffer *eb)
 }
 
 /*
- * returns 1 if we get the read lock and 0 if we don't
- * this won't wait for blocking writers
+ * Try-lock for read. Don't block or wait for contending writers.
+ *
+ * Retrun 1 if the rwlock has been taken, 0 otherwise
  */
 int btrfs_try_tree_read_lock(struct extent_buffer *eb)
 {
-	if (eb->blocking_writers)
+	if (READ_ONCE(eb->blocking_writers))
 		return 0;
 
 	if (!read_trylock(&eb->lock))
 		return 0;
 
-	if (eb->blocking_writers) {
+	/* Refetch value after lock */
+	if (READ_ONCE(eb->blocking_writers)) {
 		read_unlock(&eb->lock);
 		return 0;
 	}
@@ -202,16 +327,19 @@ int btrfs_try_tree_read_lock(struct extent_buffer *eb)
 }
 
 /*
- * returns 1 if we get the read lock and 0 if we don't
- * this won't wait for blocking writers or readers
+ * Try-lock for write. May block until the lock is uncontended, but does not
+ * wait until it is free.
+ *
+ * Retrun 1 if the rwlock has been taken, 0 otherwise
  */
 int btrfs_try_tree_write_lock(struct extent_buffer *eb)
 {
-	if (eb->blocking_writers || atomic_read(&eb->blocking_readers))
+	if (READ_ONCE(eb->blocking_writers) || atomic_read(&eb->blocking_readers))
 		return 0;
 
 	write_lock(&eb->lock);
-	if (eb->blocking_writers || atomic_read(&eb->blocking_readers)) {
+	/* Refetch value after lock */
+	if (READ_ONCE(eb->blocking_writers) || atomic_read(&eb->blocking_readers)) {
 		write_unlock(&eb->lock);
 		return 0;
 	}
@@ -223,7 +351,10 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
 }
 
 /*
- * drop a spinning read lock
+ * Release read lock. Must be used only if the lock is in spinning mode.  If
+ * the read lock is nested, must pair with read lock before the write unlock.
+ *
+ * The rwlock is not held upon exit.
  */
 void btrfs_tree_read_unlock(struct extent_buffer *eb)
 {
@@ -245,7 +376,11 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb)
 }
 
 /*
- * drop a blocking read lock
+ * Release read lock, previously set to blocking by a pairing call to
+ * btrfs_set_lock_blocking_read(). Can be nested in write lock by the same
+ * thread.
+ *
+ * State of rwlock is unchanged, last reader wakes waiting threads.
  */
 void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
 {
@@ -269,8 +404,10 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
 }
 
 /*
- * take a spinning write lock.  This will wait for both
- * blocking readers or writers
+ * Lock for write. Wait for all blocking and spinning readers and writers. This
+ * starts context where reader lock could be nested by the same thread.
+ *
+ * The rwlock is held for write upon exit.
  */
 void btrfs_tree_lock(struct extent_buffer *eb)
 {
@@ -282,9 +419,11 @@ void btrfs_tree_lock(struct extent_buffer *eb)
 	WARN_ON(eb->lock_owner == current->pid);
 again:
 	wait_event(eb->read_lock_wq, atomic_read(&eb->blocking_readers) == 0);
-	wait_event(eb->write_lock_wq, eb->blocking_writers == 0);
+	wait_event(eb->write_lock_wq, READ_ONCE(eb->blocking_writers) == 0);
 	write_lock(&eb->lock);
-	if (atomic_read(&eb->blocking_readers) || eb->blocking_writers) {
+	/* Refetch value after lock */
+	if (atomic_read(&eb->blocking_readers) ||
+	    READ_ONCE(eb->blocking_writers)) {
 		write_unlock(&eb->lock);
 		goto again;
 	}
@@ -295,10 +434,19 @@ again:
 }
 
 /*
- * drop a spinning or a blocking write lock.
+ * Release the write lock, either blocking or spinning (ie. there's no need
+ * for an explicit blocking unlock, like btrfs_tree_read_unlock_blocking).
+ * This also ends the context for nesting, the read lock must have been
+ * released already.
+ *
+ * Tasks blocked and waiting are woken, rwlock is not held upon exit.
  */
 void btrfs_tree_unlock(struct extent_buffer *eb)
 {
+	/*
+	 * This is read both locked and unlocked but always by the same thread
+	 * that already owns the lock so we don't need to use READ_ONCE
+	 */
 	int blockers = eb->blocking_writers;
 
 	BUG_ON(blockers > 1);
@@ -310,7 +458,8 @@ void btrfs_tree_unlock(struct extent_buffer *eb)
 
 	if (blockers) {
 		btrfs_assert_no_spinning_writers(eb);
-		eb->blocking_writers--;
+		/* Unlocked write */
+		WRITE_ONCE(eb->blocking_writers, 0);
 		/*
 		 * We need to order modifying blocking_writers above with
 		 * actually waking up the sleepers to ensure they see the
@@ -322,3 +471,55 @@ void btrfs_tree_unlock(struct extent_buffer *eb)
 		write_unlock(&eb->lock);
 	}
 }
+
+/*
+ * Set all locked nodes in the path to blocking locks.  This should be done
+ * before scheduling
+ */
+void btrfs_set_path_blocking(struct btrfs_path *p)
+{
+	int i;
+
+	for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
+		if (!p->nodes[i] || !p->locks[i])
+			continue;
+		/*
+		 * If we currently have a spinning reader or writer lock this
+		 * will bump the count of blocking holders and drop the
+		 * spinlock.
+		 */
+		if (p->locks[i] == BTRFS_READ_LOCK) {
+			btrfs_set_lock_blocking_read(p->nodes[i]);
+			p->locks[i] = BTRFS_READ_LOCK_BLOCKING;
+		} else if (p->locks[i] == BTRFS_WRITE_LOCK) {
+			btrfs_set_lock_blocking_write(p->nodes[i]);
+			p->locks[i] = BTRFS_WRITE_LOCK_BLOCKING;
+		}
+	}
+}
+
+/*
+ * This releases any locks held in the path starting at level and going all the
+ * way up to the root.
+ *
+ * btrfs_search_slot will keep the lock held on higher nodes in a few corner
+ * cases, such as COW of the block at slot zero in the node.  This ignores
+ * those rules, and it should only be called when there are no more updates to
+ * be done higher up in the tree.
+ */
+void btrfs_unlock_up_safe(struct btrfs_path *path, int level)
+{
+	int i;
+
+	if (path->keep_locks)
+		return;
+
+	for (i = level; i < BTRFS_MAX_LEVEL; i++) {
+		if (!path->nodes[i])
+			continue;
+		if (!path->locks[i])
+			continue;
+		btrfs_tree_unlock_rw(path->nodes[i], path->locks[i]);
+		path->locks[i] = 0;
+	}
+}
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index b775a4207ed9..21a285883e89 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -6,6 +6,8 @@
 #ifndef BTRFS_LOCKING_H
 #define BTRFS_LOCKING_H
 
+#include "extent_io.h"
+
 #define BTRFS_WRITE_LOCK 1
 #define BTRFS_READ_LOCK 2
 #define BTRFS_WRITE_LOCK_BLOCKING 3
@@ -19,11 +21,20 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb);
 void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb);
 void btrfs_set_lock_blocking_read(struct extent_buffer *eb);
 void btrfs_set_lock_blocking_write(struct extent_buffer *eb);
-void btrfs_assert_tree_locked(struct extent_buffer *eb);
 int btrfs_try_tree_read_lock(struct extent_buffer *eb);
 int btrfs_try_tree_write_lock(struct extent_buffer *eb);
 int btrfs_tree_read_lock_atomic(struct extent_buffer *eb);
 
+#ifdef CONFIG_BTRFS_DEBUG
+static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) {
+	BUG_ON(!eb->write_locks);
+}
+#else
+static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) { }
+#endif
+
+void btrfs_set_path_blocking(struct btrfs_path *p);
+void btrfs_unlock_up_safe(struct btrfs_path *path, int level);
 
 static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw)
 {
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index acad4174f68d..aa9cd11f4b78 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -63,27 +63,7 @@ struct workspace {
 
 static struct workspace_manager wsm;
 
-static void lzo_init_workspace_manager(void)
-{
-	btrfs_init_workspace_manager(&wsm, &btrfs_lzo_compress);
-}
-
-static void lzo_cleanup_workspace_manager(void)
-{
-	btrfs_cleanup_workspace_manager(&wsm);
-}
-
-static struct list_head *lzo_get_workspace(unsigned int level)
-{
-	return btrfs_get_workspace(&wsm, level);
-}
-
-static void lzo_put_workspace(struct list_head *ws)
-{
-	btrfs_put_workspace(&wsm, ws);
-}
-
-static void lzo_free_workspace(struct list_head *ws)
+void lzo_free_workspace(struct list_head *ws)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 
@@ -93,7 +73,7 @@ static void lzo_free_workspace(struct list_head *ws)
 	kfree(workspace);
 }
 
-static struct list_head *lzo_alloc_workspace(unsigned int level)
+struct list_head *lzo_alloc_workspace(unsigned int level)
 {
 	struct workspace *workspace;
 
@@ -131,13 +111,9 @@ static inline size_t read_compress_length(const char *buf)
 	return le32_to_cpu(dlen);
 }
 
-static int lzo_compress_pages(struct list_head *ws,
-			      struct address_space *mapping,
-			      u64 start,
-			      struct page **pages,
-			      unsigned long *out_pages,
-			      unsigned long *total_in,
-			      unsigned long *total_out)
+int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
+		u64 start, struct page **pages, unsigned long *out_pages,
+		unsigned long *total_in, unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0;
@@ -303,7 +279,7 @@ out:
 	return ret;
 }
 
-static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
+int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0, ret2;
@@ -444,10 +420,9 @@ done:
 	return ret;
 }
 
-static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
-			  struct page *dest_page,
-			  unsigned long start_byte,
-			  size_t srclen, size_t destlen)
+int lzo_decompress(struct list_head *ws, unsigned char *data_in,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	size_t in_len;
@@ -508,15 +483,7 @@ out:
 }
 
 const struct btrfs_compress_op btrfs_lzo_compress = {
-	.init_workspace_manager	= lzo_init_workspace_manager,
-	.cleanup_workspace_manager = lzo_cleanup_workspace_manager,
-	.get_workspace		= lzo_get_workspace,
-	.put_workspace		= lzo_put_workspace,
-	.alloc_workspace	= lzo_alloc_workspace,
-	.free_workspace		= lzo_free_workspace,
-	.compress_pages		= lzo_compress_pages,
-	.decompress_bio		= lzo_decompress_bio,
-	.decompress		= lzo_decompress,
+	.workspace_manager	= &wsm,
 	.max_level		= 1,
 	.default_level		= 1,
 };
diff --git a/fs/btrfs/misc.h b/fs/btrfs/misc.h
index 7d564924dfeb..72bab64ecf60 100644
--- a/fs/btrfs/misc.h
+++ b/fs/btrfs/misc.h
@@ -47,4 +47,15 @@ static inline u64 div_factor_fine(u64 num, int factor)
 	return div_u64(num, 100);
 }
 
+/* Copy of is_power_of_two that is 64bit safe */
+static inline bool is_power_of_two_u64(u64 n)
+{
+	return n != 0 && (n & (n - 1)) == 0;
+}
+
+static inline bool has_single_bit_set(u64 n)
+{
+	return is_power_of_two_u64(n);
+}
+
 #endif
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 24b6c72b9a59..fb09bc2f8e4d 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -547,7 +547,6 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 		spin_unlock(&root->ordered_extent_lock);
 
 		btrfs_init_work(&ordered->flush_work,
-				btrfs_flush_delalloc_helper,
 				btrfs_run_ordered_extent_work, NULL, NULL);
 		list_add_tail(&ordered->work_list, &works);
 		btrfs_queue_work(fs_info->flush_workers, &ordered->flush_work);
@@ -573,12 +572,11 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 	return count;
 }
 
-u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
+void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 			     const u64 range_start, const u64 range_len)
 {
 	struct btrfs_root *root;
 	struct list_head splice;
-	u64 total_done = 0;
 	u64 done;
 
 	INIT_LIST_HEAD(&splice);
@@ -598,7 +596,6 @@ u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 		done = btrfs_wait_ordered_extents(root, nr,
 						  range_start, range_len);
 		btrfs_put_fs_root(root);
-		total_done += done;
 
 		spin_lock(&fs_info->ordered_root_lock);
 		if (nr != U64_MAX) {
@@ -608,8 +605,6 @@ u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 	list_splice_tail(&splice, &fs_info->ordered_roots);
 	spin_unlock(&fs_info->ordered_root_lock);
 	mutex_unlock(&fs_info->ordered_operations_mutex);
-
-	return total_done;
 }
 
 /*
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 5204171ea962..4eb0319a86d7 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -186,7 +186,7 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
 			   u8 *sum, int len);
 u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 			       const u64 range_start, const u64 range_len);
-u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
+void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 			      const u64 range_start, const u64 range_len);
 void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree,
 					struct btrfs_inode *inode, u64 start,
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 9cb50577d982..873b6b694107 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -266,9 +266,9 @@ void btrfs_print_leaf(struct extent_buffer *l)
 					    struct btrfs_block_group_item);
 			pr_info(
 		   "\t\tblock group used %llu chunk_objectid %llu flags %llu\n",
-				btrfs_disk_block_group_used(l, bi),
-				btrfs_disk_block_group_chunk_objectid(l, bi),
-				btrfs_disk_block_group_flags(l, bi));
+				btrfs_block_group_used(l, bi),
+				btrfs_block_group_chunk_objectid(l, bi),
+				btrfs_block_group_flags(l, bi));
 			break;
 		case BTRFS_CHUNK_ITEM_KEY:
 			print_chunk(l, btrfs_item_ptr(l, i,
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index 1e664e0b59b8..deb59e7cfcac 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -416,11 +416,11 @@ int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	parent_inode = btrfs_iget(sb, &key, parent_root, NULL);
+	parent_inode = btrfs_iget(sb, &key, parent_root);
 	if (IS_ERR(parent_inode))
 		return PTR_ERR(parent_inode);
 
-	child_inode = btrfs_iget(sb, &key, root, NULL);
+	child_inode = btrfs_iget(sb, &key, root);
 	if (IS_ERR(child_inode)) {
 		iput(parent_inode);
 		return PTR_ERR(child_inode);
@@ -437,8 +437,6 @@ void __init btrfs_props_init(void)
 {
 	int i;
 
-	hash_init(prop_handlers_ht);
-
 	for (i = 0; i < ARRAY_SIZE(prop_handlers); i++) {
 		struct prop_handler *p = &prop_handlers[i];
 		u64 h = btrfs_name_hash(p->xattr_name, strlen(p->xattr_name));
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 3ad151655eb8..93aeb2e539a4 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1811,7 +1811,7 @@ static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans,
 		btrfs_item_key_to_cpu(dst_path->nodes[dst_level], &key, 0);
 
 	/* For src_path */
-	extent_buffer_get(src_eb);
+	atomic_inc(&src_eb->refs);
 	src_path->nodes[root_level] = src_eb;
 	src_path->slots[root_level] = dst_path->slots[root_level];
 	src_path->locks[root_level] = 0;
@@ -2067,7 +2067,7 @@ static int qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 	/* For dst_path */
-	extent_buffer_get(dst_eb);
+	atomic_inc(&dst_eb->refs);
 	dst_path->nodes[level] = dst_eb;
 	dst_path->slots[level] = 0;
 	dst_path->locks[level] = 0;
@@ -2126,7 +2126,7 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
 	 * walk back up the tree (adjusting slot pointers as we go)
 	 * and restart the search process.
 	 */
-	extent_buffer_get(root_eb); /* For path */
+	atomic_inc(&root_eb->refs);	/* For path */
 	path->nodes[root_level] = root_eb;
 	path->slots[root_level] = 0;
 	path->locks[root_level] = 0; /* so release_path doesn't try to unlock */
@@ -3277,10 +3277,7 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 	spin_unlock(&fs_info->qgroup_lock);
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
-	memset(&fs_info->qgroup_rescan_work, 0,
-	       sizeof(fs_info->qgroup_rescan_work));
 	btrfs_init_work(&fs_info->qgroup_rescan_work,
-			btrfs_qgroup_rescan_helper,
 			btrfs_qgroup_rescan_worker, NULL, NULL);
 	return 0;
 }
@@ -3826,7 +3823,7 @@ out:
  */
 int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans,
 		struct btrfs_root *subvol_root,
-		struct btrfs_block_group_cache *bg,
+		struct btrfs_block_group *bg,
 		struct extent_buffer *subvol_parent, int subvol_slot,
 		struct extent_buffer *reloc_parent, int reloc_slot,
 		u64 last_snapshot)
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 46ba7bd2961c..236f12224d52 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -408,7 +408,7 @@ void btrfs_qgroup_init_swapped_blocks(
 void btrfs_qgroup_clean_swapped_blocks(struct btrfs_root *root);
 int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans,
 		struct btrfs_root *subvol_root,
-		struct btrfs_block_group_cache *bg,
+		struct btrfs_block_group *bg,
 		struct extent_buffer *subvol_parent, int subvol_slot,
 		struct extent_buffer *reloc_parent, int reloc_slot,
 		u64 last_snapshot);
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 57a2ac721985..a8e53c8e7b01 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -190,7 +190,7 @@ static void scrub_parity_work(struct btrfs_work *work);
 
 static void start_async_work(struct btrfs_raid_bio *rbio, btrfs_func_t work_func)
 {
-	btrfs_init_work(&rbio->work, btrfs_rmw_helper, work_func, NULL, NULL);
+	btrfs_init_work(&rbio->work, work_func, NULL, NULL);
 	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
 }
 
@@ -671,8 +671,7 @@ static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index)
  */
 static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio)
 {
-	int bucket = rbio_bucket(rbio);
-	struct btrfs_stripe_hash *h = rbio->fs_info->stripe_hash_table->table + bucket;
+	struct btrfs_stripe_hash *h;
 	struct btrfs_raid_bio *cur;
 	struct btrfs_raid_bio *pending;
 	unsigned long flags;
@@ -680,64 +679,63 @@ static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio)
 	struct btrfs_raid_bio *cache_drop = NULL;
 	int ret = 0;
 
+	h = rbio->fs_info->stripe_hash_table->table + rbio_bucket(rbio);
+
 	spin_lock_irqsave(&h->lock, flags);
 	list_for_each_entry(cur, &h->hash_list, hash_list) {
-		if (cur->bbio->raid_map[0] == rbio->bbio->raid_map[0]) {
-			spin_lock(&cur->bio_list_lock);
-
-			/* can we steal this cached rbio's pages? */
-			if (bio_list_empty(&cur->bio_list) &&
-			    list_empty(&cur->plug_list) &&
-			    test_bit(RBIO_CACHE_BIT, &cur->flags) &&
-			    !test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags)) {
-				list_del_init(&cur->hash_list);
-				refcount_dec(&cur->refs);
-
-				steal_rbio(cur, rbio);
-				cache_drop = cur;
-				spin_unlock(&cur->bio_list_lock);
+		if (cur->bbio->raid_map[0] != rbio->bbio->raid_map[0])
+			continue;
 
-				goto lockit;
-			}
+		spin_lock(&cur->bio_list_lock);
 
-			/* can we merge into the lock owner? */
-			if (rbio_can_merge(cur, rbio)) {
-				merge_rbio(cur, rbio);
-				spin_unlock(&cur->bio_list_lock);
-				freeit = rbio;
-				ret = 1;
-				goto out;
-			}
+		/* Can we steal this cached rbio's pages? */
+		if (bio_list_empty(&cur->bio_list) &&
+		    list_empty(&cur->plug_list) &&
+		    test_bit(RBIO_CACHE_BIT, &cur->flags) &&
+		    !test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags)) {
+			list_del_init(&cur->hash_list);
+			refcount_dec(&cur->refs);
 
+			steal_rbio(cur, rbio);
+			cache_drop = cur;
+			spin_unlock(&cur->bio_list_lock);
 
-			/*
-			 * we couldn't merge with the running
-			 * rbio, see if we can merge with the
-			 * pending ones.  We don't have to
-			 * check for rmw_locked because there
-			 * is no way they are inside finish_rmw
-			 * right now
-			 */
-			list_for_each_entry(pending, &cur->plug_list,
-					    plug_list) {
-				if (rbio_can_merge(pending, rbio)) {
-					merge_rbio(pending, rbio);
-					spin_unlock(&cur->bio_list_lock);
-					freeit = rbio;
-					ret = 1;
-					goto out;
-				}
-			}
+			goto lockit;
+		}
 
-			/* no merging, put us on the tail of the plug list,
-			 * our rbio will be started with the currently
-			 * running rbio unlocks
-			 */
-			list_add_tail(&rbio->plug_list, &cur->plug_list);
+		/* Can we merge into the lock owner? */
+		if (rbio_can_merge(cur, rbio)) {
+			merge_rbio(cur, rbio);
 			spin_unlock(&cur->bio_list_lock);
+			freeit = rbio;
 			ret = 1;
 			goto out;
 		}
+
+
+		/*
+		 * We couldn't merge with the running rbio, see if we can merge
+		 * with the pending ones.  We don't have to check for rmw_locked
+		 * because there is no way they are inside finish_rmw right now
+		 */
+		list_for_each_entry(pending, &cur->plug_list, plug_list) {
+			if (rbio_can_merge(pending, rbio)) {
+				merge_rbio(pending, rbio);
+				spin_unlock(&cur->bio_list_lock);
+				freeit = rbio;
+				ret = 1;
+				goto out;
+			}
+		}
+
+		/*
+		 * No merging, put us on the tail of the plug list, our rbio
+		 * will be started with the currently running rbio unlocks
+		 */
+		list_add_tail(&rbio->plug_list, &cur->plug_list);
+		spin_unlock(&cur->bio_list_lock);
+		ret = 1;
+		goto out;
 	}
 lockit:
 	refcount_inc(&rbio->refs);
@@ -1743,8 +1741,7 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	plug = container_of(cb, struct btrfs_plug_cb, cb);
 
 	if (from_schedule) {
-		btrfs_init_work(&plug->work, btrfs_rmw_helper,
-				unplug_work, NULL, NULL);
+		btrfs_init_work(&plug->work, unplug_work, NULL, NULL);
 		btrfs_queue_work(plug->info->rmw_workers,
 				 &plug->work);
 		return;
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index ee6f60547a8d..243a2e44526e 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -227,7 +227,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
 	struct btrfs_fs_info *fs_info = dev->fs_info;
 	int ret;
 	struct reada_zone *zone;
-	struct btrfs_block_group_cache *cache = NULL;
+	struct btrfs_block_group *cache = NULL;
 	u64 start;
 	u64 end;
 	int i;
@@ -248,8 +248,8 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
 	if (!cache)
 		return NULL;
 
-	start = cache->key.objectid;
-	end = start + cache->key.offset - 1;
+	start = cache->start;
+	end = start + cache->length - 1;
 	btrfs_put_block_group(cache);
 
 	zone = kzalloc(sizeof(*zone), GFP_KERNEL);
@@ -752,21 +752,19 @@ static int reada_start_machine_dev(struct btrfs_device *dev)
 static void reada_start_machine_worker(struct btrfs_work *work)
 {
 	struct reada_machine_work *rmw;
-	struct btrfs_fs_info *fs_info;
 	int old_ioprio;
 
 	rmw = container_of(work, struct reada_machine_work, work);
-	fs_info = rmw->fs_info;
-
-	kfree(rmw);
 
 	old_ioprio = IOPRIO_PRIO_VALUE(task_nice_ioclass(current),
 				       task_nice_ioprio(current));
 	set_task_ioprio(current, BTRFS_IOPRIO_READA);
-	__reada_start_machine(fs_info);
+	__reada_start_machine(rmw->fs_info);
 	set_task_ioprio(current, old_ioprio);
 
-	atomic_dec(&fs_info->reada_works_cnt);
+	atomic_dec(&rmw->fs_info->reada_works_cnt);
+
+	kfree(rmw);
 }
 
 static void __reada_start_machine(struct btrfs_fs_info *fs_info)
@@ -821,8 +819,7 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info)
 		/* FIXME we cannot handle this properly right now */
 		BUG();
 	}
-	btrfs_init_work(&rmw->work, btrfs_readahead_helper,
-			reada_start_machine_worker, NULL, NULL);
+	btrfs_init_work(&rmw->work, reada_start_machine_worker, NULL, NULL);
 	rmw->fs_info = fs_info;
 
 	btrfs_queue_work(fs_info->readahead_workers, &rmw->work);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 5cd42b66818c..d897a8e5e430 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -147,7 +147,7 @@ struct file_extent_cluster {
 
 struct reloc_control {
 	/* block group to relocate */
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	/* extent tree */
 	struct btrfs_root *extent_root;
 	/* inode for moving data */
@@ -1560,11 +1560,10 @@ again:
 	return NULL;
 }
 
-static int in_block_group(u64 bytenr,
-			  struct btrfs_block_group_cache *block_group)
+static int in_block_group(u64 bytenr, struct btrfs_block_group *block_group)
 {
-	if (bytenr >= block_group->key.objectid &&
-	    bytenr < block_group->key.objectid + block_group->key.offset)
+	if (bytenr >= block_group->start &&
+	    bytenr < block_group->start + block_group->length)
 		return 1;
 	return 0;
 }
@@ -2246,7 +2245,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 
 	if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) {
 		level = btrfs_root_level(root_item);
-		extent_buffer_get(reloc_root->node);
+		atomic_inc(&reloc_root->node->refs);
 		path->nodes[level] = reloc_root->node;
 		path->slots[level] = 0;
 	} else {
@@ -3195,7 +3194,6 @@ static noinline_for_stack
 int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
 			 u64 block_start)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	struct extent_map *em;
 	int ret = 0;
@@ -3208,7 +3206,6 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
 	em->len = end + 1 - start;
 	em->block_len = em->len;
 	em->block_start = block_start;
-	em->bdev = fs_info->fs_devices->latest_bdev;
 	set_bit(EXTENT_FLAG_PINNED, &em->flags);
 
 	lock_extent(&BTRFS_I(inode)->io_tree, start, end);
@@ -3544,7 +3541,7 @@ static int block_use_full_backref(struct reloc_control *rc,
 }
 
 static int delete_block_group_cache(struct btrfs_fs_info *fs_info,
-				    struct btrfs_block_group_cache *block_group,
+				    struct btrfs_block_group *block_group,
 				    struct inode *inode,
 				    u64 ino)
 {
@@ -3560,7 +3557,7 @@ static int delete_block_group_cache(struct btrfs_fs_info *fs_info,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, root);
 	if (IS_ERR(inode))
 		return -ENOENT;
 
@@ -3863,7 +3860,7 @@ int find_next_extent(struct reloc_control *rc, struct btrfs_path *path,
 	u64 start, end, last;
 	int ret;
 
-	last = rc->block_group->key.objectid + rc->block_group->key.offset;
+	last = rc->block_group->start + rc->block_group->length;
 	while (1) {
 		cond_resched();
 		if (rc->search_start >= last) {
@@ -3980,7 +3977,7 @@ int prepare_to_relocate(struct reloc_control *rc)
 		return -ENOMEM;
 
 	memset(&rc->cluster, 0, sizeof(rc->cluster));
-	rc->search_start = rc->block_group->key.objectid;
+	rc->search_start = rc->block_group->start;
 	rc->extents_found = 0;
 	rc->nodes_relocated = 0;
 	rc->merging_rsv_size = 0;
@@ -4219,7 +4216,7 @@ out:
  */
 static noinline_for_stack
 struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
-				 struct btrfs_block_group_cache *group)
+				 struct btrfs_block_group *group)
 {
 	struct inode *inode = NULL;
 	struct btrfs_trans_handle *trans;
@@ -4246,9 +4243,9 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
 	key.objectid = objectid;
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
-	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, root);
 	BUG_ON(IS_ERR(inode));
-	BTRFS_I(inode)->index_cnt = group->key.objectid;
+	BTRFS_I(inode)->index_cnt = group->start;
 
 	err = btrfs_orphan_add(trans, BTRFS_I(inode));
 out:
@@ -4283,7 +4280,7 @@ static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info)
  * Print the block group being relocated
  */
 static void describe_relocation(struct btrfs_fs_info *fs_info,
-				struct btrfs_block_group_cache *block_group)
+				struct btrfs_block_group *block_group)
 {
 	char buf[128] = {'\0'};
 
@@ -4291,7 +4288,7 @@ static void describe_relocation(struct btrfs_fs_info *fs_info,
 
 	btrfs_info(fs_info,
 		   "relocating block group %llu flags %s",
-		   block_group->key.objectid, buf);
+		   block_group->start, buf);
 }
 
 /*
@@ -4299,7 +4296,7 @@ static void describe_relocation(struct btrfs_fs_info *fs_info,
  */
 int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 {
-	struct btrfs_block_group_cache *bg;
+	struct btrfs_block_group *bg;
 	struct btrfs_root *extent_root = fs_info->extent_root;
 	struct reloc_control *rc;
 	struct inode *inode;
@@ -4326,7 +4323,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 	rc->extent_root = extent_root;
 	rc->block_group = bg;
 
-	ret = btrfs_inc_block_group_ro(rc->block_group);
+	ret = btrfs_inc_block_group_ro(rc->block_group, true);
 	if (ret) {
 		err = ret;
 		goto out;
@@ -4364,8 +4361,8 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 	btrfs_wait_block_group_reservations(rc->block_group);
 	btrfs_wait_nocow_writers(rc->block_group);
 	btrfs_wait_ordered_roots(fs_info, U64_MAX,
-				 rc->block_group->key.objectid,
-				 rc->block_group->key.offset);
+				 rc->block_group->start,
+				 rc->block_group->length);
 
 	while (1) {
 		mutex_lock(&fs_info->cleaner_mutex);
@@ -4405,7 +4402,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 
 	WARN_ON(rc->block_group->pinned > 0);
 	WARN_ON(rc->block_group->reserved > 0);
-	WARN_ON(btrfs_block_group_used(&rc->block_group->item) > 0);
+	WARN_ON(rc->block_group->used > 0);
 out:
 	if (err && rw)
 		btrfs_dec_block_group_ro(rc->block_group);
@@ -4688,7 +4685,7 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
 		       node->new_bytenr != buf->start);
 
 		drop_node_buffer(node);
-		extent_buffer_get(cow);
+		atomic_inc(&cow->refs);
 		node->eb = cow;
 		node->new_bytenr = cow->start;
 
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index f7d4e03f4c5d..21de630b0730 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -389,8 +389,7 @@ static struct full_stripe_lock *search_full_stripe_lock(
  *
  * Caller must ensure @cache is a RAID56 block group.
  */
-static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache,
-				   u64 bytenr)
+static u64 get_full_stripe_logical(struct btrfs_block_group *cache, u64 bytenr)
 {
 	u64 ret;
 
@@ -404,8 +403,8 @@ static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache,
 	 * round_down() can only handle power of 2, while RAID56 full
 	 * stripe length can be 64KiB * n, so we need to manually round down.
 	 */
-	ret = div64_u64(bytenr - cache->key.objectid, cache->full_stripe_len) *
-		cache->full_stripe_len + cache->key.objectid;
+	ret = div64_u64(bytenr - cache->start, cache->full_stripe_len) *
+			cache->full_stripe_len + cache->start;
 	return ret;
 }
 
@@ -423,7 +422,7 @@ static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache,
 static int lock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr,
 			    bool *locked_ret)
 {
-	struct btrfs_block_group_cache *bg_cache;
+	struct btrfs_block_group *bg_cache;
 	struct btrfs_full_stripe_locks_tree *locks_root;
 	struct full_stripe_lock *existing;
 	u64 fstripe_start;
@@ -470,7 +469,7 @@ out:
 static int unlock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr,
 			      bool locked)
 {
-	struct btrfs_block_group_cache *bg_cache;
+	struct btrfs_block_group *bg_cache;
 	struct btrfs_full_stripe_locks_tree *locks_root;
 	struct full_stripe_lock *fstripe_lock;
 	u64 fstripe_start;
@@ -598,8 +597,8 @@ static noinline_for_stack struct scrub_ctx *scrub_setup_ctx(
 		sbio->index = i;
 		sbio->sctx = sctx;
 		sbio->page_count = 0;
-		btrfs_init_work(&sbio->work, btrfs_scrub_helper,
-				scrub_bio_end_io_worker, NULL, NULL);
+		btrfs_init_work(&sbio->work, scrub_bio_end_io_worker, NULL,
+				NULL);
 
 		if (i != SCRUB_BIOS_PER_SCTX - 1)
 			sctx->bios[i]->next_free = i + 1;
@@ -1720,8 +1719,7 @@ static void scrub_wr_bio_end_io(struct bio *bio)
 	sbio->status = bio->bi_status;
 	sbio->bio = bio;
 
-	btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper,
-			 scrub_wr_bio_end_io_worker, NULL, NULL);
+	btrfs_init_work(&sbio->work, scrub_wr_bio_end_io_worker, NULL, NULL);
 	btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work);
 }
 
@@ -2149,14 +2147,13 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work)
 		scrub_write_block_to_dev_replace(sblock);
 	}
 
-	scrub_block_put(sblock);
-
 	if (sctx->is_dev_replace && sctx->flush_all_writes) {
 		mutex_lock(&sctx->wr_lock);
 		scrub_wr_submit(sctx);
 		mutex_unlock(&sctx->wr_lock);
 	}
 
+	scrub_block_put(sblock);
 	scrub_pending_bio_dec(sctx);
 }
 
@@ -2204,8 +2201,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 		raid56_add_scrub_pages(rbio, spage->page, spage->logical);
 	}
 
-	btrfs_init_work(&sblock->work, btrfs_scrub_helper,
-			scrub_missing_raid56_worker, NULL, NULL);
+	btrfs_init_work(&sblock->work, scrub_missing_raid56_worker, NULL, NULL);
 	scrub_block_get(sblock);
 	scrub_pending_bio_inc(sctx);
 	raid56_submit_missing_rbio(rbio);
@@ -2743,8 +2739,8 @@ static void scrub_parity_bio_endio(struct bio *bio)
 
 	bio_put(bio);
 
-	btrfs_init_work(&sparity->work, btrfs_scrubparity_helper,
-			scrub_parity_bio_endio_worker, NULL, NULL);
+	btrfs_init_work(&sparity->work, scrub_parity_bio_endio_worker, NULL,
+			NULL);
 	btrfs_queue_work(fs_info->scrub_parity_workers, &sparity->work);
 }
 
@@ -3420,7 +3416,7 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
 					  struct btrfs_device *scrub_dev,
 					  u64 chunk_offset, u64 length,
 					  u64 dev_offset,
-					  struct btrfs_block_group_cache *cache)
+					  struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
@@ -3484,7 +3480,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 	struct extent_buffer *l;
 	struct btrfs_key key;
 	struct btrfs_key found_key;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 
 	path = btrfs_alloc_path();
@@ -3563,46 +3559,26 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 * -> btrfs_scrub_pause()
 		 */
 		scrub_pause_on(fs_info);
-		ret = btrfs_inc_block_group_ro(cache);
-		if (!ret && sctx->is_dev_replace) {
-			/*
-			 * If we are doing a device replace wait for any tasks
-			 * that started delalloc right before we set the block
-			 * group to RO mode, as they might have just allocated
-			 * an extent from it or decided they could do a nocow
-			 * write. And if any such tasks did that, wait for their
-			 * ordered extents to complete and then commit the
-			 * current transaction, so that we can later see the new
-			 * extent items in the extent tree - the ordered extents
-			 * create delayed data references (for cow writes) when
-			 * they complete, which will be run and insert the
-			 * corresponding extent items into the extent tree when
-			 * we commit the transaction they used when running
-			 * inode.c:btrfs_finish_ordered_io(). We later use
-			 * the commit root of the extent tree to find extents
-			 * to copy from the srcdev into the tgtdev, and we don't
-			 * want to miss any new extents.
-			 */
-			btrfs_wait_block_group_reservations(cache);
-			btrfs_wait_nocow_writers(cache);
-			ret = btrfs_wait_ordered_roots(fs_info, U64_MAX,
-						       cache->key.objectid,
-						       cache->key.offset);
-			if (ret > 0) {
-				struct btrfs_trans_handle *trans;
-
-				trans = btrfs_join_transaction(root);
-				if (IS_ERR(trans))
-					ret = PTR_ERR(trans);
-				else
-					ret = btrfs_commit_transaction(trans);
-				if (ret) {
-					scrub_pause_off(fs_info);
-					btrfs_put_block_group(cache);
-					break;
-				}
-			}
-		}
+
+		/*
+		 * Don't do chunk preallocation for scrub.
+		 *
+		 * This is especially important for SYSTEM bgs, or we can hit
+		 * -EFBIG from btrfs_finish_chunk_alloc() like:
+		 * 1. The only SYSTEM bg is marked RO.
+		 *    Since SYSTEM bg is small, that's pretty common.
+		 * 2. New SYSTEM bg will be allocated
+		 *    Due to regular version will allocate new chunk.
+		 * 3. New SYSTEM bg is empty and will get cleaned up
+		 *    Before cleanup really happens, it's marked RO again.
+		 * 4. Empty SYSTEM bg get scrubbed
+		 *    We go back to 2.
+		 *
+		 * This can easily boost the amount of SYSTEM chunks if cleaner
+		 * thread can't be triggered fast enough, and use up all space
+		 * of btrfs_super_block::sys_chunk_array
+		 */
+		ret = btrfs_inc_block_group_ro(cache, false);
 		scrub_pause_off(fs_info);
 
 		if (ret == 0) {
@@ -3623,7 +3599,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 			break;
 		}
 
-		down_write(&fs_info->dev_replace.rwsem);
+		down_write(&dev_replace->rwsem);
 		dev_replace->cursor_right = found_key.offset + length;
 		dev_replace->cursor_left = found_key.offset;
 		dev_replace->item_needs_writeback = 1;
@@ -3664,10 +3640,10 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 
 		scrub_pause_off(fs_info);
 
-		down_write(&fs_info->dev_replace.rwsem);
+		down_write(&dev_replace->rwsem);
 		dev_replace->cursor_left = dev_replace->cursor_right;
 		dev_replace->item_needs_writeback = 1;
-		up_write(&fs_info->dev_replace.rwsem);
+		up_write(&dev_replace->rwsem);
 
 		if (ro_set)
 			btrfs_dec_block_group_ro(cache);
@@ -3681,7 +3657,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 */
 		spin_lock(&cache->lock);
 		if (!cache->removed && !cache->ro && cache->reserved == 0 &&
-		    btrfs_block_group_used(&cache->item) == 0) {
+		    cache->used == 0) {
 			spin_unlock(&cache->lock);
 			btrfs_mark_bg_unused(cache);
 		} else {
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 123ac54af071..ae2db5eb1549 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -25,6 +25,14 @@
 #include "compression.h"
 
 /*
+ * Maximum number of references an extent can have in order for us to attempt to
+ * issue clone operations instead of write operations. This currently exists to
+ * avoid hitting limitations of the backreference walking code (taking a lot of
+ * time and using too much memory for extents with large number of references).
+ */
+#define SEND_MAX_EXTENT_REFS	64
+
+/*
  * A fs_path is a helper to dynamically build path names with unknown size.
  * It reallocates the internal buffer on demand.
  * It allows fast adding of path elements on the right side (normal path) and
@@ -1248,12 +1256,20 @@ static int __iterate_backrefs(u64 ino, u64 offset, u64 root, void *ctx_)
 	 */
 	if (found->root == bctx->sctx->send_root) {
 		/*
-		 * TODO for the moment we don't accept clones from the inode
-		 * that is currently send. We may change this when
-		 * BTRFS_IOC_CLONE_RANGE supports cloning from and to the same
-		 * file.
+		 * If the source inode was not yet processed we can't issue a
+		 * clone operation, as the source extent does not exist yet at
+		 * the destination of the stream.
 		 */
-		if (ino >= bctx->cur_objectid)
+		if (ino > bctx->cur_objectid)
+			return 0;
+		/*
+		 * We clone from the inode currently being sent as long as the
+		 * source extent is already processed, otherwise we could try
+		 * to clone from an extent that does not exist yet at the
+		 * destination of the stream.
+		 */
+		if (ino == bctx->cur_objectid &&
+		    offset >= bctx->sctx->cur_inode_next_write_offset)
 			return 0;
 	}
 
@@ -1302,6 +1318,7 @@ static int find_extent_clone(struct send_ctx *sctx,
 	struct clone_root *cur_clone_root;
 	struct btrfs_key found_key;
 	struct btrfs_path *tmp_path;
+	struct btrfs_extent_item *ei;
 	int compressed;
 	u32 i;
 
@@ -1349,7 +1366,6 @@ static int find_extent_clone(struct send_ctx *sctx,
 	ret = extent_from_logical(fs_info, disk_byte, tmp_path,
 				  &found_key, &flags);
 	up_read(&fs_info->commit_root_sem);
-	btrfs_release_path(tmp_path);
 
 	if (ret < 0)
 		goto out;
@@ -1358,6 +1374,21 @@ static int find_extent_clone(struct send_ctx *sctx,
 		goto out;
 	}
 
+	ei = btrfs_item_ptr(tmp_path->nodes[0], tmp_path->slots[0],
+			    struct btrfs_extent_item);
+	/*
+	 * Backreference walking (iterate_extent_inodes() below) is currently
+	 * too expensive when an extent has a large number of references, both
+	 * in time spent and used memory. So for now just fallback to write
+	 * operations instead of clone operations when an extent has more than
+	 * a certain amount of references.
+	 */
+	if (btrfs_extent_refs(tmp_path->nodes[0], ei) > SEND_MAX_EXTENT_REFS) {
+		ret = -ENOENT;
+		goto out;
+	}
+	btrfs_release_path(tmp_path);
+
 	/*
 	 * Setup the clone roots.
 	 */
@@ -4779,7 +4810,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, root);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index e8a4b0ebe97f..f09aa6ee9113 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -10,7 +10,7 @@
 #include "transaction.h"
 #include "block-group.h"
 
-u64 btrfs_space_info_used(struct btrfs_space_info *s_info,
+u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info,
 			  bool may_use_included)
 {
 	ASSERT(s_info);
@@ -58,7 +58,6 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags)
 	spin_lock_init(&space_info->lock);
 	space_info->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
 	space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
-	init_waitqueue_head(&space_info->wait);
 	INIT_LIST_HEAD(&space_info->ro_bgs);
 	INIT_LIST_HEAD(&space_info->tickets);
 	INIT_LIST_HEAD(&space_info->priority_tickets);
@@ -285,7 +284,7 @@ void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
 			   struct btrfs_space_info *info, u64 bytes,
 			   int dump_block_groups)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	int index = 0;
 
 	spin_lock(&info->lock);
@@ -301,8 +300,7 @@ again:
 		spin_lock(&cache->lock);
 		btrfs_info(fs_info,
 			"block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s",
-			cache->key.objectid, cache->key.offset,
-			btrfs_block_group_used(&cache->item), cache->pinned,
+			cache->start, cache->length, cache->used, cache->pinned,
 			cache->reserved, cache->ro ? "[readonly]" : "");
 		btrfs_dump_free_space(cache, bytes);
 		spin_unlock(&cache->lock);
diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h
index 8867e84aa33d..1a349e3f9cc1 100644
--- a/fs/btrfs/space-info.h
+++ b/fs/btrfs/space-info.h
@@ -63,7 +63,6 @@ struct btrfs_space_info {
 	struct rw_semaphore groups_sem;
 	/* for block groups in our same type */
 	struct list_head block_groups[BTRFS_NR_RAID_TYPES];
-	wait_queue_head_t wait;
 
 	struct kobject kobj;
 	struct kobject *block_group_kobjs[BTRFS_NR_RAID_TYPES];
@@ -116,7 +115,7 @@ void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags,
 			     struct btrfs_space_info **space_info);
 struct btrfs_space_info *btrfs_find_space_info(struct btrfs_fs_info *info,
 					       u64 flags);
-u64 btrfs_space_info_used(struct btrfs_space_info *s_info,
+u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info,
 			  bool may_use_included);
 void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
 void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 1b151af25772..a98c3c71fc54 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -66,7 +66,7 @@ static struct file_system_type btrfs_root_fs_type;
 
 static int btrfs_remount(struct super_block *sb, int *flags, char *data);
 
-const char *btrfs_decode_error(int errno)
+const char * __attribute_const__ btrfs_decode_error(int errno)
 {
 	char *errstr = "unknown";
 
@@ -187,7 +187,7 @@ static struct ratelimit_state printk_limits[] = {
 	RATELIMIT_STATE_INIT(printk_limits[7], DEFAULT_RATELIMIT_INTERVAL, 100),
 };
 
-void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
+void __cold btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
 {
 	char lvl[PRINTK_MAX_SINGLE_HEADER_LEN + 1] = "\0";
 	struct va_format vaf;
@@ -1219,7 +1219,7 @@ static int btrfs_fill_super(struct super_block *sb,
 	key.objectid = BTRFS_FIRST_FREE_OBJECTID;
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
-	inode = btrfs_iget(sb, &key, fs_info->fs_root, NULL);
+	inode = btrfs_iget(sb, &key, fs_info->fs_root);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto fail_close;
@@ -1669,7 +1669,6 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
 
 	btrfs_workqueue_set_max(fs_info->workers, new_pool_size);
 	btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size);
-	btrfs_workqueue_set_max(fs_info->submit_workers, new_pool_size);
 	btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size);
 	btrfs_workqueue_set_max(fs_info->endio_workers, new_pool_size);
 	btrfs_workqueue_set_max(fs_info->endio_meta_workers, new_pool_size);
@@ -1936,6 +1935,10 @@ static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
 		num_stripes = nr_devices;
 	else if (type & BTRFS_BLOCK_GROUP_RAID1)
 		num_stripes = 2;
+	else if (type & BTRFS_BLOCK_GROUP_RAID1C3)
+		num_stripes = 3;
+	else if (type & BTRFS_BLOCK_GROUP_RAID1C4)
+		num_stripes = 4;
 	else if (type & BTRFS_BLOCK_GROUP_RAID10)
 		num_stripes = 4;
 
@@ -2022,7 +2025,6 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb);
 	struct btrfs_super_block *disk_super = fs_info->super_copy;
-	struct list_head *head = &fs_info->space_info;
 	struct btrfs_space_info *found;
 	u64 total_used = 0;
 	u64 total_free_data = 0;
@@ -2036,7 +2038,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	int mixed = 0;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(found, head, list) {
+	list_for_each_entry_rcu(found, &fs_info->space_info, list) {
 		if (found->flags & BTRFS_BLOCK_GROUP_DATA) {
 			int i;
 
@@ -2360,10 +2362,14 @@ static int __init init_btrfs_fs(void)
 	if (err)
 		goto free_cachep;
 
-	err = extent_map_init();
+	err = extent_state_cache_init();
 	if (err)
 		goto free_extent_io;
 
+	err = extent_map_init();
+	if (err)
+		goto free_extent_state_cache;
+
 	err = ordered_data_init();
 	if (err)
 		goto free_extent_map;
@@ -2422,6 +2428,8 @@ free_ordered_data:
 	ordered_data_exit();
 free_extent_map:
 	extent_map_exit();
+free_extent_state_cache:
+	extent_state_cache_exit();
 free_extent_io:
 	extent_io_exit();
 free_cachep:
@@ -2442,6 +2450,7 @@ static void __exit exit_btrfs_fs(void)
 	btrfs_prelim_ref_exit();
 	ordered_data_exit();
 	extent_map_exit();
+	extent_state_cache_exit();
 	extent_io_exit();
 	btrfs_interface_exit();
 	btrfs_end_io_wq_exit();
@@ -2456,3 +2465,6 @@ module_exit(exit_btrfs_fs)
 
 MODULE_LICENSE("GPL");
 MODULE_SOFTDEP("pre: crc32c");
+MODULE_SOFTDEP("pre: xxhash64");
+MODULE_SOFTDEP("pre: sha256");
+MODULE_SOFTDEP("pre: blake2b-256");
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index f6d3c80f2e28..5ebbe8a5ee76 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -9,6 +9,7 @@
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/bug.h>
+#include <crypto/hash.h>
 
 #include "ctree.h"
 #include "disk-io.h"
@@ -258,6 +259,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA);
 BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES);
 BTRFS_FEAT_ATTR_INCOMPAT(metadata_uuid, METADATA_UUID);
 BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE);
+BTRFS_FEAT_ATTR_INCOMPAT(raid1c34, RAID1C34);
 
 static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(mixed_backref),
@@ -272,6 +274,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(no_holes),
 	BTRFS_FEAT_ATTR_PTR(metadata_uuid),
 	BTRFS_FEAT_ATTR_PTR(free_space_tree),
+	BTRFS_FEAT_ATTR_PTR(raid1c34),
 	NULL
 };
 
@@ -295,8 +298,30 @@ static ssize_t rmdir_subvol_show(struct kobject *kobj,
 }
 BTRFS_ATTR(static_feature, rmdir_subvol, rmdir_subvol_show);
 
+static ssize_t supported_checksums_show(struct kobject *kobj,
+					struct kobj_attribute *a, char *buf)
+{
+	ssize_t ret = 0;
+	int i;
+
+	for (i = 0; i < btrfs_get_num_csums(); i++) {
+		/*
+		 * This "trick" only works as long as 'enum btrfs_csum_type' has
+		 * no holes in it
+		 */
+		ret += snprintf(buf + ret, PAGE_SIZE - ret, "%s%s",
+				(i == 0 ? "" : " "), btrfs_super_csum_name(i));
+
+	}
+
+	ret += snprintf(buf + ret, PAGE_SIZE - ret, "\n");
+	return ret;
+}
+BTRFS_ATTR(static_feature, supported_checksums, supported_checksums_show);
+
 static struct attribute *btrfs_supported_static_feature_attrs[] = {
 	BTRFS_ATTR_PTR(static_feature, rmdir_subvol),
+	BTRFS_ATTR_PTR(static_feature, supported_checksums),
 	NULL
 };
 
@@ -372,16 +397,16 @@ static ssize_t raid_bytes_show(struct kobject *kobj,
 
 {
 	struct btrfs_space_info *sinfo = to_space_info(kobj->parent);
-	struct btrfs_block_group_cache *block_group;
+	struct btrfs_block_group *block_group;
 	int index = btrfs_bg_flags_to_raid_index(to_raid_kobj(kobj)->flags);
 	u64 val = 0;
 
 	down_read(&sinfo->groups_sem);
 	list_for_each_entry(block_group, &sinfo->block_groups[index], list) {
 		if (&attr->attr == BTRFS_ATTR_PTR(raid, total_bytes))
-			val += block_group->key.offset;
+			val += block_group->length;
 		else
-			val += btrfs_block_group_used(&block_group->item);
+			val += block_group->used;
 	}
 	up_read(&sinfo->groups_sem);
 	return snprintf(buf, PAGE_SIZE, "%llu\n", val);
@@ -604,6 +629,19 @@ static ssize_t btrfs_metadata_uuid_show(struct kobject *kobj,
 
 BTRFS_ATTR(, metadata_uuid, btrfs_metadata_uuid_show);
 
+static ssize_t btrfs_checksum_show(struct kobject *kobj,
+				   struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+	u16 csum_type = btrfs_super_csum_type(fs_info->super_copy);
+
+	return snprintf(buf, PAGE_SIZE, "%s (%s)\n",
+			btrfs_super_csum_name(csum_type),
+			crypto_shash_driver_name(fs_info->csum_shash));
+}
+
+BTRFS_ATTR(, checksum, btrfs_checksum_show);
+
 static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(, label),
 	BTRFS_ATTR_PTR(, nodesize),
@@ -611,6 +649,7 @@ static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(, clone_alignment),
 	BTRFS_ATTR_PTR(, quota_override),
 	BTRFS_ATTR_PTR(, metadata_uuid),
+	BTRFS_ATTR_PTR(, checksum),
 	NULL,
 };
 
@@ -822,7 +861,7 @@ static void init_feature_attrs(void)
  * Create a sysfs entry for a given block group type at path
  * /sys/fs/btrfs/UUID/allocation/data/TYPE
  */
-void btrfs_sysfs_add_block_group_type(struct btrfs_block_group_cache *cache)
+void btrfs_sysfs_add_block_group_type(struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_space_info *space_info = cache->space_info;
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index 610e9c36a94c..e10c3adfc30f 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -32,7 +32,7 @@ int __init btrfs_init_sysfs(void);
 void __cold btrfs_exit_sysfs(void);
 int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info);
 void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info);
-void btrfs_sysfs_add_block_group_type(struct btrfs_block_group_cache *cache);
+void btrfs_sysfs_add_block_group_type(struct btrfs_block_group *cache);
 int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info,
 				    struct btrfs_space_info *space_info);
 void btrfs_sysfs_remove_space_info(struct btrfs_space_info *space_info);
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 99fe9bf3fdac..a7aca4141788 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -202,11 +202,11 @@ void btrfs_free_dummy_root(struct btrfs_root *root)
 	kfree(root);
 }
 
-struct btrfs_block_group_cache *
+struct btrfs_block_group *
 btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info,
 			      unsigned long length)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 
 	cache = kzalloc(sizeof(*cache), GFP_KERNEL);
 	if (!cache)
@@ -218,9 +218,8 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info,
 		return NULL;
 	}
 
-	cache->key.objectid = 0;
-	cache->key.offset = length;
-	cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+	cache->start = 0;
+	cache->length = length;
 	cache->full_stripe_len = fs_info->sectorsize;
 	cache->fs_info = fs_info;
 
@@ -233,7 +232,7 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info,
 	return cache;
 }
 
-void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_free_dummy_block_group(struct btrfs_block_group *cache)
 {
 	if (!cache)
 		return;
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index ee277bbd939b..9e52527357d8 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -41,9 +41,9 @@ struct inode *btrfs_new_test_inode(void);
 struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize);
 void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info);
 void btrfs_free_dummy_root(struct btrfs_root *root);
-struct btrfs_block_group_cache *
+struct btrfs_block_group *
 btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, unsigned long length);
-void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache);
+void btrfs_free_dummy_block_group(struct btrfs_block_group *cache);
 void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans,
 			    struct btrfs_fs_info *fs_info);
 #else
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
index 43ec7060fcd2..aebdf23f0cdd 100644
--- a/fs/btrfs/tests/free-space-tests.c
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -17,7 +17,7 @@
  * entry and remove space from either end and the middle, and make sure we can
  * remove space that covers adjacent extent entries.
  */
-static int test_extents(struct btrfs_block_group_cache *cache)
+static int test_extents(struct btrfs_block_group *cache)
 {
 	int ret = 0;
 
@@ -87,8 +87,7 @@ static int test_extents(struct btrfs_block_group_cache *cache)
 	return 0;
 }
 
-static int test_bitmaps(struct btrfs_block_group_cache *cache,
-			u32 sectorsize)
+static int test_bitmaps(struct btrfs_block_group *cache, u32 sectorsize)
 {
 	u64 next_bitmap_offset;
 	int ret;
@@ -156,7 +155,7 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache,
 }
 
 /* This is the high grade jackassery */
-static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
+static int test_bitmaps_and_extents(struct btrfs_block_group *cache,
 				    u32 sectorsize)
 {
 	u64 bitmap_offset = (u64)(BITS_PER_BITMAP * sectorsize);
@@ -331,7 +330,7 @@ static bool test_use_bitmap(struct btrfs_free_space_ctl *ctl,
 
 /* Used by test_steal_space_from_bitmap_to_extent(). */
 static int
-check_num_extents_and_bitmaps(const struct btrfs_block_group_cache *cache,
+check_num_extents_and_bitmaps(const struct btrfs_block_group *cache,
 			      const int num_extents,
 			      const int num_bitmaps)
 {
@@ -351,7 +350,7 @@ check_num_extents_and_bitmaps(const struct btrfs_block_group_cache *cache,
 }
 
 /* Used by test_steal_space_from_bitmap_to_extent(). */
-static int check_cache_empty(struct btrfs_block_group_cache *cache)
+static int check_cache_empty(struct btrfs_block_group *cache)
 {
 	u64 offset;
 	u64 max_extent_size;
@@ -393,7 +392,7 @@ static int check_cache_empty(struct btrfs_block_group_cache *cache)
  * requests.
  */
 static int
-test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
+test_steal_space_from_bitmap_to_extent(struct btrfs_block_group *cache,
 				       u32 sectorsize)
 {
 	int ret;
@@ -829,7 +828,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
 int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_fs_info *fs_info;
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	struct btrfs_root *root = NULL;
 	int ret = -ENOMEM;
 
diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c
index bc92df977630..1a846bf6e197 100644
--- a/fs/btrfs/tests/free-space-tree-tests.c
+++ b/fs/btrfs/tests/free-space-tree-tests.c
@@ -18,7 +18,7 @@ struct free_space_extent {
 
 static int __check_free_space_extents(struct btrfs_trans_handle *trans,
 				      struct btrfs_fs_info *fs_info,
-				      struct btrfs_block_group_cache *cache,
+				      struct btrfs_block_group *cache,
 				      struct btrfs_path *path,
 				      const struct free_space_extent * const extents,
 				      unsigned int num_extents)
@@ -48,7 +48,7 @@ static int __check_free_space_extents(struct btrfs_trans_handle *trans,
 	if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
 		if (path->slots[0] != 0)
 			goto invalid;
-		end = cache->key.objectid + cache->key.offset;
+		end = cache->start + cache->length;
 		i = 0;
 		while (++path->slots[0] < btrfs_header_nritems(path->nodes[0])) {
 			btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
@@ -107,7 +107,7 @@ invalid:
 
 static int check_free_space_extents(struct btrfs_trans_handle *trans,
 				    struct btrfs_fs_info *fs_info,
-				    struct btrfs_block_group_cache *cache,
+				    struct btrfs_block_group *cache,
 				    struct btrfs_path *path,
 				    const struct free_space_extent * const extents,
 				    unsigned int num_extents)
@@ -150,12 +150,12 @@ static int check_free_space_extents(struct btrfs_trans_handle *trans,
 
 static int test_empty_block_group(struct btrfs_trans_handle *trans,
 				  struct btrfs_fs_info *fs_info,
-				  struct btrfs_block_group_cache *cache,
+				  struct btrfs_block_group *cache,
 				  struct btrfs_path *path,
 				  u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid, cache->key.offset},
+		{cache->start, cache->length},
 	};
 
 	return check_free_space_extents(trans, fs_info, cache, path,
@@ -164,7 +164,7 @@ static int test_empty_block_group(struct btrfs_trans_handle *trans,
 
 static int test_remove_all(struct btrfs_trans_handle *trans,
 			   struct btrfs_fs_info *fs_info,
-			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_block_group *cache,
 			   struct btrfs_path *path,
 			   u32 alignment)
 {
@@ -172,8 +172,8 @@ static int test_remove_all(struct btrfs_trans_handle *trans,
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid,
-					    cache->key.offset);
+					    cache->start,
+					    cache->length);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
@@ -185,18 +185,17 @@ static int test_remove_all(struct btrfs_trans_handle *trans,
 
 static int test_remove_beginning(struct btrfs_trans_handle *trans,
 				 struct btrfs_fs_info *fs_info,
-				 struct btrfs_block_group_cache *cache,
+				 struct btrfs_block_group *cache,
 				 struct btrfs_path *path,
 				 u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid + alignment,
-			cache->key.offset - alignment},
+		{cache->start + alignment, cache->length - alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid, alignment);
+					    cache->start, alignment);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
@@ -209,19 +208,18 @@ static int test_remove_beginning(struct btrfs_trans_handle *trans,
 
 static int test_remove_end(struct btrfs_trans_handle *trans,
 			   struct btrfs_fs_info *fs_info,
-			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_block_group *cache,
 			   struct btrfs_path *path,
 			   u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid, cache->key.offset - alignment},
+		{cache->start, cache->length - alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid +
-					    cache->key.offset - alignment,
-					    alignment);
+				    cache->start + cache->length - alignment,
+				    alignment);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
@@ -233,19 +231,18 @@ static int test_remove_end(struct btrfs_trans_handle *trans,
 
 static int test_remove_middle(struct btrfs_trans_handle *trans,
 			      struct btrfs_fs_info *fs_info,
-			      struct btrfs_block_group_cache *cache,
+			      struct btrfs_block_group *cache,
 			      struct btrfs_path *path,
 			      u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid, alignment},
-		{cache->key.objectid + 2 * alignment,
-			cache->key.offset - 2 * alignment},
+		{cache->start, alignment},
+		{cache->start + 2 * alignment, cache->length - 2 * alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid + alignment,
+					    cache->start + alignment,
 					    alignment);
 	if (ret) {
 		test_err("could not remove free space");
@@ -258,24 +255,23 @@ static int test_remove_middle(struct btrfs_trans_handle *trans,
 
 static int test_merge_left(struct btrfs_trans_handle *trans,
 			   struct btrfs_fs_info *fs_info,
-			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_block_group *cache,
 			   struct btrfs_path *path,
 			   u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid, 2 * alignment},
+		{cache->start, 2 * alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid,
-					    cache->key.offset);
+					    cache->start, cache->length);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+	ret = __add_to_free_space_tree(trans, cache, path, cache->start,
 				       alignment);
 	if (ret) {
 		test_err("could not add free space");
@@ -283,7 +279,7 @@ static int test_merge_left(struct btrfs_trans_handle *trans,
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + alignment,
+				       cache->start + alignment,
 				       alignment);
 	if (ret) {
 		test_err("could not add free space");
@@ -296,25 +292,24 @@ static int test_merge_left(struct btrfs_trans_handle *trans,
 
 static int test_merge_right(struct btrfs_trans_handle *trans,
 			   struct btrfs_fs_info *fs_info,
-			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_block_group *cache,
 			   struct btrfs_path *path,
 			   u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid + alignment, 2 * alignment},
+		{cache->start + alignment, 2 * alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid,
-					    cache->key.offset);
+					    cache->start, cache->length);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + 2 * alignment,
+				       cache->start + 2 * alignment,
 				       alignment);
 	if (ret) {
 		test_err("could not add free space");
@@ -322,7 +317,7 @@ static int test_merge_right(struct btrfs_trans_handle *trans,
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + alignment,
+				       cache->start + alignment,
 				       alignment);
 	if (ret) {
 		test_err("could not add free space");
@@ -335,24 +330,23 @@ static int test_merge_right(struct btrfs_trans_handle *trans,
 
 static int test_merge_both(struct btrfs_trans_handle *trans,
 			   struct btrfs_fs_info *fs_info,
-			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_block_group *cache,
 			   struct btrfs_path *path,
 			   u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid, 3 * alignment},
+		{cache->start, 3 * alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid,
-					    cache->key.offset);
+					    cache->start, cache->length);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+	ret = __add_to_free_space_tree(trans, cache, path, cache->start,
 				       alignment);
 	if (ret) {
 		test_err("could not add free space");
@@ -360,16 +354,14 @@ static int test_merge_both(struct btrfs_trans_handle *trans,
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + 2 * alignment,
-				       alignment);
+				       cache->start + 2 * alignment, alignment);
 	if (ret) {
 		test_err("could not add free space");
 		return ret;
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + alignment,
-				       alignment);
+				       cache->start + alignment, alignment);
 	if (ret) {
 		test_err("could not add free space");
 		return ret;
@@ -381,26 +373,25 @@ static int test_merge_both(struct btrfs_trans_handle *trans,
 
 static int test_merge_none(struct btrfs_trans_handle *trans,
 			   struct btrfs_fs_info *fs_info,
-			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_block_group *cache,
 			   struct btrfs_path *path,
 			   u32 alignment)
 {
 	const struct free_space_extent extents[] = {
-		{cache->key.objectid, alignment},
-		{cache->key.objectid + 2 * alignment, alignment},
-		{cache->key.objectid + 4 * alignment, alignment},
+		{cache->start, alignment},
+		{cache->start + 2 * alignment, alignment},
+		{cache->start + 4 * alignment, alignment},
 	};
 	int ret;
 
 	ret = __remove_from_free_space_tree(trans, cache, path,
-					    cache->key.objectid,
-					    cache->key.offset);
+					    cache->start, cache->length);
 	if (ret) {
 		test_err("could not remove free space");
 		return ret;
 	}
 
-	ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+	ret = __add_to_free_space_tree(trans, cache, path, cache->start,
 				       alignment);
 	if (ret) {
 		test_err("could not add free space");
@@ -408,16 +399,14 @@ static int test_merge_none(struct btrfs_trans_handle *trans,
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + 4 * alignment,
-				       alignment);
+				       cache->start + 4 * alignment, alignment);
 	if (ret) {
 		test_err("could not add free space");
 		return ret;
 	}
 
 	ret = __add_to_free_space_tree(trans, cache, path,
-				       cache->key.objectid + 2 * alignment,
-				       alignment);
+				       cache->start + 2 * alignment, alignment);
 	if (ret) {
 		test_err("could not add free space");
 		return ret;
@@ -429,7 +418,7 @@ static int test_merge_none(struct btrfs_trans_handle *trans,
 
 typedef int (*test_func_t)(struct btrfs_trans_handle *,
 			   struct btrfs_fs_info *,
-			   struct btrfs_block_group_cache *,
+			   struct btrfs_block_group *,
 			   struct btrfs_path *,
 			   u32 alignment);
 
@@ -438,7 +427,7 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
 {
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_root *root = NULL;
-	struct btrfs_block_group_cache *cache = NULL;
+	struct btrfs_block_group *cache = NULL;
 	struct btrfs_trans_handle trans;
 	struct btrfs_path *path = NULL;
 	int ret;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 8624bdee8c5b..cfc08ef9b876 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -24,9 +24,79 @@
 
 #define BTRFS_ROOT_TRANS_TAG 0
 
+/*
+ * Transaction states and transitions
+ *
+ * No running transaction (fs tree blocks are not modified)
+ * |
+ * | To next stage:
+ * |  Call start_transaction() variants. Except btrfs_join_transaction_nostart().
+ * V
+ * Transaction N [[TRANS_STATE_RUNNING]]
+ * |
+ * | New trans handles can be attached to transaction N by calling all
+ * | start_transaction() variants.
+ * |
+ * | To next stage:
+ * |  Call btrfs_commit_transaction() on any trans handle attached to
+ * |  transaction N
+ * V
+ * Transaction N [[TRANS_STATE_COMMIT_START]]
+ * |
+ * | Will wait for previous running transaction to completely finish if there
+ * | is one
+ * |
+ * | Then one of the following happes:
+ * | - Wait for all other trans handle holders to release.
+ * |   The btrfs_commit_transaction() caller will do the commit work.
+ * | - Wait for current transaction to be committed by others.
+ * |   Other btrfs_commit_transaction() caller will do the commit work.
+ * |
+ * | At this stage, only btrfs_join_transaction*() variants can attach
+ * | to this running transaction.
+ * | All other variants will wait for current one to finish and attach to
+ * | transaction N+1.
+ * |
+ * | To next stage:
+ * |  Caller is chosen to commit transaction N, and all other trans handle
+ * |  haven been released.
+ * V
+ * Transaction N [[TRANS_STATE_COMMIT_DOING]]
+ * |
+ * | The heavy lifting transaction work is started.
+ * | From running delayed refs (modifying extent tree) to creating pending
+ * | snapshots, running qgroups.
+ * | In short, modify supporting trees to reflect modifications of subvolume
+ * | trees.
+ * |
+ * | At this stage, all start_transaction() calls will wait for this
+ * | transaction to finish and attach to transaction N+1.
+ * |
+ * | To next stage:
+ * |  Until all supporting trees are updated.
+ * V
+ * Transaction N [[TRANS_STATE_UNBLOCKED]]
+ * |						    Transaction N+1
+ * | All needed trees are modified, thus we only    [[TRANS_STATE_RUNNING]]
+ * | need to write them back to disk and update	    |
+ * | super blocks.				    |
+ * |						    |
+ * | At this stage, new transaction is allowed to   |
+ * | start.					    |
+ * | All new start_transaction() calls will be	    |
+ * | attached to transid N+1.			    |
+ * |						    |
+ * | To next stage:				    |
+ * |  Until all tree blocks are super blocks are    |
+ * |  written to block devices			    |
+ * V						    |
+ * Transaction N [[TRANS_STATE_COMPLETED]]	    V
+ *   All tree blocks and super blocks are written.  Transaction N+1
+ *   This transaction is finished and all its	    [[TRANS_STATE_COMMIT_START]]
+ *   data structures will be cleaned up.	    | Life goes on
+ */
 static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = {
 	[TRANS_STATE_RUNNING]		= 0U,
-	[TRANS_STATE_BLOCKED]		=  __TRANS_START,
 	[TRANS_STATE_COMMIT_START]	= (__TRANS_START | __TRANS_ATTACH),
 	[TRANS_STATE_COMMIT_DOING]	= (__TRANS_START |
 					   __TRANS_ATTACH |
@@ -63,10 +133,10 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction)
 		 * discard the physical locations of the block groups.
 		 */
 		while (!list_empty(&transaction->deleted_bgs)) {
-			struct btrfs_block_group_cache *cache;
+			struct btrfs_block_group *cache;
 
 			cache = list_first_entry(&transaction->deleted_bgs,
-						 struct btrfs_block_group_cache,
+						 struct btrfs_block_group,
 						 bg_list);
 			list_del_init(&cache->bg_list);
 			btrfs_put_block_group_trimming(cache);
@@ -383,7 +453,7 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 
 static inline int is_transaction_blocked(struct btrfs_transaction *trans)
 {
-	return (trans->state >= TRANS_STATE_BLOCKED &&
+	return (trans->state >= TRANS_STATE_COMMIT_START &&
 		trans->state < TRANS_STATE_UNBLOCKED &&
 		!trans->aborted);
 }
@@ -570,7 +640,7 @@ again:
 	INIT_LIST_HEAD(&h->new_bgs);
 
 	smp_mb();
-	if (cur_trans->state >= TRANS_STATE_BLOCKED &&
+	if (cur_trans->state >= TRANS_STATE_COMMIT_START &&
 	    may_wait_transaction(fs_info, type)) {
 		current->journal_info = h;
 		btrfs_commit_transaction(h);
@@ -659,7 +729,7 @@ struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root)
 				 true);
 }
 
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root)
+struct btrfs_trans_handle *btrfs_join_transaction_spacecache(struct btrfs_root *root)
 {
 	return start_transaction(root, 0, TRANS_JOIN_NOLOCK,
 				 BTRFS_RESERVE_NO_FLUSH, true);
@@ -798,7 +868,7 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans)
 	struct btrfs_transaction *cur_trans = trans->transaction;
 
 	smp_mb();
-	if (cur_trans->state >= TRANS_STATE_BLOCKED ||
+	if (cur_trans->state >= TRANS_STATE_COMMIT_START ||
 	    cur_trans->delayed_refs.flushing)
 		return 1;
 
@@ -831,7 +901,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_fs_info *info = trans->fs_info;
 	struct btrfs_transaction *cur_trans = trans->transaction;
-	int lock = (trans->type != TRANS_JOIN_NOLOCK);
 	int err = 0;
 
 	if (refcount_read(&trans->use_count) > 1) {
@@ -847,13 +916,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 
 	btrfs_trans_release_chunk_metadata(trans);
 
-	if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) {
-		if (throttle)
-			return btrfs_commit_transaction(trans);
-		else
-			wake_up_process(info->transaction_kthread);
-	}
-
 	if (trans->type & __TRANS_FREEZABLE)
 		sb_end_intwrite(info->sb);
 
@@ -990,7 +1052,7 @@ static int __btrfs_wait_marked_extents(struct btrfs_fs_info *fs_info,
 	return werr;
 }
 
-int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
+static int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
 		       struct extent_io_tree *dirty_pages)
 {
 	bool errors = false;
@@ -1875,7 +1937,7 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
 static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
 {
        struct btrfs_fs_info *fs_info = trans->fs_info;
-       struct btrfs_block_group_cache *block_group, *tmp;
+       struct btrfs_block_group *block_group, *tmp;
 
        list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
                btrfs_delayed_refs_rsv_release(fs_info, 1);
@@ -1949,6 +2011,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	struct btrfs_transaction *prev_trans = NULL;
 	int ret;
 
+	ASSERT(refcount_read(&trans->use_count) == 1);
+
 	/* Stop the commit early if ->aborted is set */
 	if (unlikely(READ_ONCE(cur_trans->aborted))) {
 		ret = cur_trans->aborted;
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 2c5a6f6e5bb0..49f7196368f5 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -13,7 +13,6 @@
 
 enum btrfs_trans_state {
 	TRANS_STATE_RUNNING,
-	TRANS_STATE_BLOCKED,
 	TRANS_STATE_COMMIT_START,
 	TRANS_STATE_COMMIT_DOING,
 	TRANS_STATE_UNBLOCKED,
@@ -184,7 +183,7 @@ struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
 					unsigned int num_items,
 					int min_factor);
 struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root);
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_join_transaction_spacecache(struct btrfs_root *root);
 struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root);
 struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root);
 struct btrfs_trans_handle *btrfs_attach_transaction_barrier(
@@ -218,8 +217,6 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root);
 int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
 				struct extent_io_tree *dirty_pages, int mark);
-int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
-		       struct extent_io_tree *dirty_pages);
 int btrfs_wait_tree_log_extents(struct btrfs_root *root, int mark);
 int btrfs_transaction_blocked(struct btrfs_fs_info *info);
 int btrfs_transaction_in_commit(struct btrfs_fs_info *info);
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 076d5b8014fb..493d4d9e0f79 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -23,6 +23,7 @@
 #include "disk-io.h"
 #include "compression.h"
 #include "volumes.h"
+#include "misc.h"
 
 /*
  * Error message should follow the following format:
@@ -124,6 +125,74 @@ static u64 file_extent_end(struct extent_buffer *leaf,
 	return end;
 }
 
+/*
+ * Customized report for dir_item, the only new important information is
+ * key->objectid, which represents inode number
+ */
+__printf(3, 4)
+__cold
+static void dir_item_err(const struct extent_buffer *eb, int slot,
+			 const char *fmt, ...)
+{
+	const struct btrfs_fs_info *fs_info = eb->fs_info;
+	struct btrfs_key key;
+	struct va_format vaf;
+	va_list args;
+
+	btrfs_item_key_to_cpu(eb, &key, slot);
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	btrfs_crit(fs_info,
+		"corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV",
+		btrfs_header_level(eb) == 0 ? "leaf" : "node",
+		btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
+		key.objectid, &vaf);
+	va_end(args);
+}
+
+/*
+ * This functions checks prev_key->objectid, to ensure current key and prev_key
+ * share the same objectid as inode number.
+ *
+ * This is to detect missing INODE_ITEM in subvolume trees.
+ *
+ * Return true if everything is OK or we don't need to check.
+ * Return false if anything is wrong.
+ */
+static bool check_prev_ino(struct extent_buffer *leaf,
+			   struct btrfs_key *key, int slot,
+			   struct btrfs_key *prev_key)
+{
+	/* No prev key, skip check */
+	if (slot == 0)
+		return true;
+
+	/* Only these key->types needs to be checked */
+	ASSERT(key->type == BTRFS_XATTR_ITEM_KEY ||
+	       key->type == BTRFS_INODE_REF_KEY ||
+	       key->type == BTRFS_DIR_INDEX_KEY ||
+	       key->type == BTRFS_DIR_ITEM_KEY ||
+	       key->type == BTRFS_EXTENT_DATA_KEY);
+
+	/*
+	 * Only subvolume trees along with their reloc trees need this check.
+	 * Things like log tree doesn't follow this ino requirement.
+	 */
+	if (!is_fstree(btrfs_header_owner(leaf)))
+		return true;
+
+	if (key->objectid == prev_key->objectid)
+		return true;
+
+	/* Error found */
+	dir_item_err(leaf, slot,
+		"invalid previous key objectid, have %llu expect %llu",
+		prev_key->objectid, key->objectid);
+	return false;
+}
 static int check_extent_data_item(struct extent_buffer *leaf,
 				  struct btrfs_key *key, int slot,
 				  struct btrfs_key *prev_key)
@@ -141,13 +210,33 @@ static int check_extent_data_item(struct extent_buffer *leaf,
 		return -EUCLEAN;
 	}
 
+	/*
+	 * Previous key must have the same key->objectid (ino).
+	 * It can be XATTR_ITEM, INODE_ITEM or just another EXTENT_DATA.
+	 * But if objectids mismatch, it means we have a missing
+	 * INODE_ITEM.
+	 */
+	if (!check_prev_ino(leaf, key, slot, prev_key))
+		return -EUCLEAN;
+
 	fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
 
-	if (btrfs_file_extent_type(leaf, fi) > BTRFS_FILE_EXTENT_TYPES) {
+	/*
+	 * Make sure the item contains at least inline header, so the file
+	 * extent type is not some garbage.
+	 */
+	if (item_size < BTRFS_FILE_EXTENT_INLINE_DATA_START) {
+		file_extent_err(leaf, slot,
+				"invalid item size, have %u expect [%lu, %u)",
+				item_size, BTRFS_FILE_EXTENT_INLINE_DATA_START,
+				SZ_4K);
+		return -EUCLEAN;
+	}
+	if (btrfs_file_extent_type(leaf, fi) >= BTRFS_NR_FILE_EXTENT_TYPES) {
 		file_extent_err(leaf, slot,
 		"invalid type for file extent, have %u expect range [0, %u]",
 			btrfs_file_extent_type(leaf, fi),
-			BTRFS_FILE_EXTENT_TYPES);
+			BTRFS_NR_FILE_EXTENT_TYPES - 1);
 		return -EUCLEAN;
 	}
 
@@ -155,11 +244,11 @@ static int check_extent_data_item(struct extent_buffer *leaf,
 	 * Support for new compression/encryption must introduce incompat flag,
 	 * and must be caught in open_ctree().
 	 */
-	if (btrfs_file_extent_compression(leaf, fi) > BTRFS_COMPRESS_TYPES) {
+	if (btrfs_file_extent_compression(leaf, fi) >= BTRFS_NR_COMPRESS_TYPES) {
 		file_extent_err(leaf, slot,
 	"invalid compression for file extent, have %u expect range [0, %u]",
 			btrfs_file_extent_compression(leaf, fi),
-			BTRFS_COMPRESS_TYPES);
+			BTRFS_NR_COMPRESS_TYPES - 1);
 		return -EUCLEAN;
 	}
 	if (btrfs_file_extent_encryption(leaf, fi)) {
@@ -270,42 +359,17 @@ static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key,
 	return 0;
 }
 
-/*
- * Customized reported for dir_item, only important new info is key->objectid,
- * which represents inode number
- */
-__printf(3, 4)
-__cold
-static void dir_item_err(const struct extent_buffer *eb, int slot,
-			 const char *fmt, ...)
-{
-	const struct btrfs_fs_info *fs_info = eb->fs_info;
-	struct btrfs_key key;
-	struct va_format vaf;
-	va_list args;
-
-	btrfs_item_key_to_cpu(eb, &key, slot);
-	va_start(args, fmt);
-
-	vaf.fmt = fmt;
-	vaf.va = &args;
-
-	btrfs_crit(fs_info,
-	"corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV",
-		btrfs_header_level(eb) == 0 ? "leaf" : "node",
-		btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
-		key.objectid, &vaf);
-	va_end(args);
-}
-
 static int check_dir_item(struct extent_buffer *leaf,
-			  struct btrfs_key *key, int slot)
+			  struct btrfs_key *key, struct btrfs_key *prev_key,
+			  int slot)
 {
 	struct btrfs_fs_info *fs_info = leaf->fs_info;
 	struct btrfs_dir_item *di;
 	u32 item_size = btrfs_item_size_nr(leaf, slot);
 	u32 cur = 0;
 
+	if (!check_prev_ino(leaf, key, slot, prev_key))
+		return -EUCLEAN;
 	di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
 	while (cur < item_size) {
 		u32 name_len;
@@ -459,23 +523,23 @@ static int check_block_group_item(struct extent_buffer *leaf,
 
 	read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
 			   sizeof(bgi));
-	if (btrfs_block_group_chunk_objectid(&bgi) !=
+	if (btrfs_stack_block_group_chunk_objectid(&bgi) !=
 	    BTRFS_FIRST_CHUNK_TREE_OBJECTID) {
 		block_group_err(leaf, slot,
 		"invalid block group chunk objectid, have %llu expect %llu",
-				btrfs_block_group_chunk_objectid(&bgi),
+				btrfs_stack_block_group_chunk_objectid(&bgi),
 				BTRFS_FIRST_CHUNK_TREE_OBJECTID);
 		return -EUCLEAN;
 	}
 
-	if (btrfs_block_group_used(&bgi) > key->offset) {
+	if (btrfs_stack_block_group_used(&bgi) > key->offset) {
 		block_group_err(leaf, slot,
 			"invalid block group used, have %llu expect [0, %llu)",
-				btrfs_block_group_used(&bgi), key->offset);
+				btrfs_stack_block_group_used(&bgi), key->offset);
 		return -EUCLEAN;
 	}
 
-	flags = btrfs_block_group_flags(&bgi);
+	flags = btrfs_stack_block_group_flags(&bgi);
 	if (hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1) {
 		block_group_err(leaf, slot,
 "invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set",
@@ -609,7 +673,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf,
 		return -EUCLEAN;
 	}
 
-	if (!is_power_of_2(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) &&
+	if (!has_single_bit_set(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) &&
 	    (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0) {
 		chunk_err(leaf, chunk, logical,
 		"invalid chunk profile flag: 0x%llx, expect 0 or 1 bit set",
@@ -785,11 +849,11 @@ static int check_inode_item(struct extent_buffer *leaf,
 	}
 
 	/*
-	 * S_IFMT is not bit mapped so we can't completely rely on is_power_of_2,
-	 * but is_power_of_2() can save us from checking FIFO/CHR/DIR/REG.
-	 * Only needs to check BLK, LNK and SOCKS
+	 * S_IFMT is not bit mapped so we can't completely rely on
+	 * is_power_of_2/has_single_bit_set, but it can save us from checking
+	 * FIFO/CHR/DIR/REG.  Only needs to check BLK, LNK and SOCKS
 	 */
-	if (!is_power_of_2(mode & S_IFMT)) {
+	if (!has_single_bit_set(mode & S_IFMT)) {
 		if (!S_ISLNK(mode) && !S_ISBLK(mode) && !S_ISSOCK(mode)) {
 			inode_item_err(fs_info, leaf, slot,
 			"invalid mode: has 0%o expect valid S_IF* bit(s)",
@@ -1010,8 +1074,8 @@ static int check_extent_item(struct extent_buffer *leaf,
 			   btrfs_super_generation(fs_info->super_copy) + 1);
 		return -EUCLEAN;
 	}
-	if (!is_power_of_2(flags & (BTRFS_EXTENT_FLAG_DATA |
-				    BTRFS_EXTENT_FLAG_TREE_BLOCK))) {
+	if (!has_single_bit_set(flags & (BTRFS_EXTENT_FLAG_DATA |
+					 BTRFS_EXTENT_FLAG_TREE_BLOCK))) {
 		extent_err(leaf, slot,
 		"invalid extent flag, have 0x%llx expect 1 bit set in 0x%llx",
 			flags, BTRFS_EXTENT_FLAG_DATA |
@@ -1224,6 +1288,58 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
 	return 0;
 }
 
+#define inode_ref_err(fs_info, eb, slot, fmt, args...)			\
+	inode_item_err(fs_info, eb, slot, fmt, ##args)
+static int check_inode_ref(struct extent_buffer *leaf,
+			   struct btrfs_key *key, struct btrfs_key *prev_key,
+			   int slot)
+{
+	struct btrfs_inode_ref *iref;
+	unsigned long ptr;
+	unsigned long end;
+
+	if (!check_prev_ino(leaf, key, slot, prev_key))
+		return -EUCLEAN;
+	/* namelen can't be 0, so item_size == sizeof() is also invalid */
+	if (btrfs_item_size_nr(leaf, slot) <= sizeof(*iref)) {
+		inode_ref_err(fs_info, leaf, slot,
+			"invalid item size, have %u expect (%zu, %u)",
+			btrfs_item_size_nr(leaf, slot),
+			sizeof(*iref), BTRFS_LEAF_DATA_SIZE(leaf->fs_info));
+		return -EUCLEAN;
+	}
+
+	ptr = btrfs_item_ptr_offset(leaf, slot);
+	end = ptr + btrfs_item_size_nr(leaf, slot);
+	while (ptr < end) {
+		u16 namelen;
+
+		if (ptr + sizeof(iref) > end) {
+			inode_ref_err(fs_info, leaf, slot,
+			"inode ref overflow, ptr %lu end %lu inode_ref_size %zu",
+				ptr, end, sizeof(iref));
+			return -EUCLEAN;
+		}
+
+		iref = (struct btrfs_inode_ref *)ptr;
+		namelen = btrfs_inode_ref_name_len(leaf, iref);
+		if (ptr + sizeof(*iref) + namelen > end) {
+			inode_ref_err(fs_info, leaf, slot,
+				"inode ref overflow, ptr %lu end %lu namelen %u",
+				ptr, end, namelen);
+			return -EUCLEAN;
+		}
+
+		/*
+		 * NOTE: In theory we should record all found index numbers
+		 * to find any duplicated indexes, but that will be too time
+		 * consuming for inodes with too many hard links.
+		 */
+		ptr += sizeof(*iref) + namelen;
+	}
+	return 0;
+}
+
 /*
  * Common point to switch the item-specific validation.
  */
@@ -1244,7 +1360,10 @@ static int check_leaf_item(struct extent_buffer *leaf,
 	case BTRFS_DIR_ITEM_KEY:
 	case BTRFS_DIR_INDEX_KEY:
 	case BTRFS_XATTR_ITEM_KEY:
-		ret = check_dir_item(leaf, key, slot);
+		ret = check_dir_item(leaf, key, prev_key, slot);
+		break;
+	case BTRFS_INODE_REF_KEY:
+		ret = check_inode_ref(leaf, key, prev_key, slot);
 		break;
 	case BTRFS_BLOCK_GROUP_ITEM_KEY:
 		ret = check_block_group_item(leaf, key, slot);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 8a6cc600bf18..6f757361db53 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -559,7 +559,7 @@ static noinline struct inode *read_one_inode(struct btrfs_root *root,
 	key.objectid = objectid;
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
-	inode = btrfs_iget(root->fs_info->sb, &key, root, NULL);
+	inode = btrfs_iget(root->fs_info->sb, &key, root);
 	if (IS_ERR(inode))
 		inode = NULL;
 	return inode;
@@ -945,54 +945,32 @@ static noinline int backref_in_log(struct btrfs_root *log,
 				   const char *name, int namelen)
 {
 	struct btrfs_path *path;
-	struct btrfs_inode_ref *ref;
-	unsigned long ptr;
-	unsigned long ptr_end;
-	unsigned long name_ptr;
-	int found_name_len;
-	int item_size;
 	int ret;
-	int match = 0;
 
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
 	ret = btrfs_search_slot(NULL, log, key, path, 0, 0);
-	if (ret != 0)
+	if (ret < 0) {
 		goto out;
-
-	ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
-
-	if (key->type == BTRFS_INODE_EXTREF_KEY) {
-		if (btrfs_find_name_in_ext_backref(path->nodes[0],
-						   path->slots[0],
-						   ref_objectid,
-						   name, namelen))
-			match = 1;
-
+	} else if (ret == 1) {
+		ret = 0;
 		goto out;
 	}
 
-	item_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
-	ptr_end = ptr + item_size;
-	while (ptr < ptr_end) {
-		ref = (struct btrfs_inode_ref *)ptr;
-		found_name_len = btrfs_inode_ref_name_len(path->nodes[0], ref);
-		if (found_name_len == namelen) {
-			name_ptr = (unsigned long)(ref + 1);
-			ret = memcmp_extent_buffer(path->nodes[0], name,
-						   name_ptr, namelen);
-			if (ret == 0) {
-				match = 1;
-				goto out;
-			}
-		}
-		ptr = (unsigned long)(ref + 1) + found_name_len;
-	}
+	if (key->type == BTRFS_INODE_EXTREF_KEY)
+		ret = !!btrfs_find_name_in_ext_backref(path->nodes[0],
+						       path->slots[0],
+						       ref_objectid,
+						       name, namelen);
+	else
+		ret = !!btrfs_find_name_in_backref(path->nodes[0],
+						   path->slots[0],
+						   name, namelen);
 out:
 	btrfs_free_path(path);
-	return match;
+	return ret;
 }
 
 static inline int __add_inode_ref(struct btrfs_trans_handle *trans,
@@ -1050,10 +1028,13 @@ again:
 					   (unsigned long)(victim_ref + 1),
 					   victim_name_len);
 
-			if (!backref_in_log(log_root, &search_key,
-					    parent_objectid,
-					    victim_name,
-					    victim_name_len)) {
+			ret = backref_in_log(log_root, &search_key,
+					     parent_objectid, victim_name,
+					     victim_name_len);
+			if (ret < 0) {
+				kfree(victim_name);
+				return ret;
+			} else if (!ret) {
 				inc_nlink(&inode->vfs_inode);
 				btrfs_release_path(path);
 
@@ -1115,10 +1096,12 @@ again:
 			search_key.offset = btrfs_extref_hash(parent_objectid,
 							      victim_name,
 							      victim_name_len);
-			ret = 0;
-			if (!backref_in_log(log_root, &search_key,
-					    parent_objectid, victim_name,
-					    victim_name_len)) {
+			ret = backref_in_log(log_root, &search_key,
+					     parent_objectid, victim_name,
+					     victim_name_len);
+			if (ret < 0) {
+				return ret;
+			} else if (!ret) {
 				ret = -ENOENT;
 				victim_parent = read_one_inode(root,
 						parent_objectid);
@@ -1885,30 +1868,6 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans,
 }
 
 /*
- * Return true if an inode reference exists in the log for the given name,
- * inode and parent inode.
- */
-static bool name_in_log_ref(struct btrfs_root *log_root,
-			    const char *name, const int name_len,
-			    const u64 dirid, const u64 ino)
-{
-	struct btrfs_key search_key;
-
-	search_key.objectid = ino;
-	search_key.type = BTRFS_INODE_REF_KEY;
-	search_key.offset = dirid;
-	if (backref_in_log(log_root, &search_key, dirid, name, name_len))
-		return true;
-
-	search_key.type = BTRFS_INODE_EXTREF_KEY;
-	search_key.offset = btrfs_extref_hash(dirid, name, name_len);
-	if (backref_in_log(log_root, &search_key, dirid, name, name_len))
-		return true;
-
-	return false;
-}
-
-/*
  * take a single entry in a log directory item and replay it into
  * the subvolume.
  *
@@ -2024,8 +1983,31 @@ out:
 	return ret;
 
 insert:
-	if (name_in_log_ref(root->log_root, name, name_len,
-			    key->objectid, log_key.objectid)) {
+	/*
+	 * Check if the inode reference exists in the log for the given name,
+	 * inode and parent inode
+	 */
+	found_key.objectid = log_key.objectid;
+	found_key.type = BTRFS_INODE_REF_KEY;
+	found_key.offset = key->objectid;
+	ret = backref_in_log(root->log_root, &found_key, 0, name, name_len);
+	if (ret < 0) {
+	        goto out;
+	} else if (ret) {
+	        /* The dentry will be added later. */
+	        ret = 0;
+	        update_size = false;
+	        goto out;
+	}
+
+	found_key.objectid = log_key.objectid;
+	found_key.type = BTRFS_INODE_EXTREF_KEY;
+	found_key.offset = key->objectid;
+	ret = backref_in_log(root->log_root, &found_key, key->objectid, name,
+			     name_len);
+	if (ret < 0) {
+		goto out;
+	} else if (ret) {
 		/* The dentry will be added later. */
 		ret = 0;
 		update_size = false;
@@ -2869,7 +2851,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 	level = btrfs_header_level(log->node);
 	orig_level = level;
 	path->nodes[level] = log->node;
-	extent_buffer_get(log->node);
+	atomic_inc(&log->node->refs);
 	path->slots[level] = 0;
 
 	while (1) {
@@ -4983,7 +4965,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
 		key.objectid = ino;
 		key.type = BTRFS_INODE_ITEM_KEY;
 		key.offset = 0;
-		inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+		inode = btrfs_iget(fs_info->sb, &key, root);
 		/*
 		 * If the other inode that had a conflicting dir entry was
 		 * deleted in the current transaction, we need to log its parent
@@ -4993,8 +4975,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
 			ret = PTR_ERR(inode);
 			if (ret == -ENOENT) {
 				key.objectid = parent;
-				inode = btrfs_iget(fs_info->sb, &key, root,
-						   NULL);
+				inode = btrfs_iget(fs_info->sb, &key, root);
 				if (IS_ERR(inode)) {
 					ret = PTR_ERR(inode);
 				} else {
@@ -5699,7 +5680,7 @@ process_leaf:
 				continue;
 
 			btrfs_release_path(path);
-			di_inode = btrfs_iget(fs_info->sb, &di_key, root, NULL);
+			di_inode = btrfs_iget(fs_info->sb, &di_key, root);
 			if (IS_ERR(di_inode)) {
 				ret = PTR_ERR(di_inode);
 				goto next_dir_inode;
@@ -5825,8 +5806,7 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
 				cur_offset = item_size;
 			}
 
-			dir_inode = btrfs_iget(fs_info->sb, &inode_key,
-					       root, NULL);
+			dir_inode = btrfs_iget(fs_info->sb, &inode_key, root);
 			/*
 			 * If the parent inode was deleted, return an error to
 			 * fallback to a transaction commit. This is to prevent
@@ -5900,7 +5880,7 @@ static int log_new_ancestors(struct btrfs_trans_handle *trans,
 		search_key.objectid = found_key.offset;
 		search_key.type = BTRFS_INODE_ITEM_KEY;
 		search_key.offset = 0;
-		inode = btrfs_iget(fs_info->sb, &search_key, root, NULL);
+		inode = btrfs_iget(fs_info->sb, &search_key, root);
 		if (IS_ERR(inode))
 			return PTR_ERR(inode);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index e04409f85063..d8e5560db285 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -58,6 +58,30 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 		.bg_flag	= BTRFS_BLOCK_GROUP_RAID1,
 		.mindev_error	= BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET,
 	},
+	[BTRFS_RAID_RAID1C3] = {
+		.sub_stripes	= 1,
+		.dev_stripes	= 1,
+		.devs_max	= 0,
+		.devs_min	= 3,
+		.tolerated_failures = 2,
+		.devs_increment	= 3,
+		.ncopies	= 3,
+		.raid_name	= "raid1c3",
+		.bg_flag	= BTRFS_BLOCK_GROUP_RAID1C3,
+		.mindev_error	= BTRFS_ERROR_DEV_RAID1C3_MIN_NOT_MET,
+	},
+	[BTRFS_RAID_RAID1C4] = {
+		.sub_stripes	= 1,
+		.dev_stripes	= 1,
+		.devs_max	= 0,
+		.devs_min	= 4,
+		.tolerated_failures = 3,
+		.devs_increment	= 4,
+		.ncopies	= 4,
+		.raid_name	= "raid1c4",
+		.bg_flag	= BTRFS_BLOCK_GROUP_RAID1C4,
+		.mindev_error	= BTRFS_ERROR_DEV_RAID1C4_MIN_NOT_MET,
+	},
 	[BTRFS_RAID_DUP] = {
 		.sub_stripes	= 1,
 		.dev_stripes	= 2,
@@ -297,7 +321,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 
 DEFINE_MUTEX(uuid_mutex);
 static LIST_HEAD(fs_uuids);
-struct list_head *btrfs_get_fs_uuids(void)
+struct list_head * __attribute_const__ btrfs_get_fs_uuids(void)
 {
 	return &fs_uuids;
 }
@@ -397,8 +421,6 @@ static struct btrfs_device *__alloc_device(void)
 	INIT_LIST_HEAD(&dev->dev_alloc_list);
 	INIT_LIST_HEAD(&dev->post_commit_list);
 
-	spin_lock_init(&dev->io_lock);
-
 	atomic_set(&dev->reada_in_flight, 0);
 	atomic_set(&dev->dev_stats_ccnt, 0);
 	btrfs_device_data_ordered_init(dev);
@@ -501,212 +523,6 @@ error:
 	return ret;
 }
 
-static void requeue_list(struct btrfs_pending_bios *pending_bios,
-			struct bio *head, struct bio *tail)
-{
-
-	struct bio *old_head;
-
-	old_head = pending_bios->head;
-	pending_bios->head = head;
-	if (pending_bios->tail)
-		tail->bi_next = old_head;
-	else
-		pending_bios->tail = tail;
-}
-
-/*
- * we try to collect pending bios for a device so we don't get a large
- * number of procs sending bios down to the same device.  This greatly
- * improves the schedulers ability to collect and merge the bios.
- *
- * But, it also turns into a long list of bios to process and that is sure
- * to eventually make the worker thread block.  The solution here is to
- * make some progress and then put this work struct back at the end of
- * the list if the block device is congested.  This way, multiple devices
- * can make progress from a single worker thread.
- */
-static noinline void run_scheduled_bios(struct btrfs_device *device)
-{
-	struct btrfs_fs_info *fs_info = device->fs_info;
-	struct bio *pending;
-	struct backing_dev_info *bdi;
-	struct btrfs_pending_bios *pending_bios;
-	struct bio *tail;
-	struct bio *cur;
-	int again = 0;
-	unsigned long num_run;
-	unsigned long batch_run = 0;
-	unsigned long last_waited = 0;
-	int force_reg = 0;
-	int sync_pending = 0;
-	struct blk_plug plug;
-
-	/*
-	 * this function runs all the bios we've collected for
-	 * a particular device.  We don't want to wander off to
-	 * another device without first sending all of these down.
-	 * So, setup a plug here and finish it off before we return
-	 */
-	blk_start_plug(&plug);
-
-	bdi = device->bdev->bd_bdi;
-
-loop:
-	spin_lock(&device->io_lock);
-
-loop_lock:
-	num_run = 0;
-
-	/* take all the bios off the list at once and process them
-	 * later on (without the lock held).  But, remember the
-	 * tail and other pointers so the bios can be properly reinserted
-	 * into the list if we hit congestion
-	 */
-	if (!force_reg && device->pending_sync_bios.head) {
-		pending_bios = &device->pending_sync_bios;
-		force_reg = 1;
-	} else {
-		pending_bios = &device->pending_bios;
-		force_reg = 0;
-	}
-
-	pending = pending_bios->head;
-	tail = pending_bios->tail;
-	WARN_ON(pending && !tail);
-
-	/*
-	 * if pending was null this time around, no bios need processing
-	 * at all and we can stop.  Otherwise it'll loop back up again
-	 * and do an additional check so no bios are missed.
-	 *
-	 * device->running_pending is used to synchronize with the
-	 * schedule_bio code.
-	 */
-	if (device->pending_sync_bios.head == NULL &&
-	    device->pending_bios.head == NULL) {
-		again = 0;
-		device->running_pending = 0;
-	} else {
-		again = 1;
-		device->running_pending = 1;
-	}
-
-	pending_bios->head = NULL;
-	pending_bios->tail = NULL;
-
-	spin_unlock(&device->io_lock);
-
-	while (pending) {
-
-		rmb();
-		/* we want to work on both lists, but do more bios on the
-		 * sync list than the regular list
-		 */
-		if ((num_run > 32 &&
-		    pending_bios != &device->pending_sync_bios &&
-		    device->pending_sync_bios.head) ||
-		   (num_run > 64 && pending_bios == &device->pending_sync_bios &&
-		    device->pending_bios.head)) {
-			spin_lock(&device->io_lock);
-			requeue_list(pending_bios, pending, tail);
-			goto loop_lock;
-		}
-
-		cur = pending;
-		pending = pending->bi_next;
-		cur->bi_next = NULL;
-
-		BUG_ON(atomic_read(&cur->__bi_cnt) == 0);
-
-		/*
-		 * if we're doing the sync list, record that our
-		 * plug has some sync requests on it
-		 *
-		 * If we're doing the regular list and there are
-		 * sync requests sitting around, unplug before
-		 * we add more
-		 */
-		if (pending_bios == &device->pending_sync_bios) {
-			sync_pending = 1;
-		} else if (sync_pending) {
-			blk_finish_plug(&plug);
-			blk_start_plug(&plug);
-			sync_pending = 0;
-		}
-
-		btrfsic_submit_bio(cur);
-		num_run++;
-		batch_run++;
-
-		cond_resched();
-
-		/*
-		 * we made progress, there is more work to do and the bdi
-		 * is now congested.  Back off and let other work structs
-		 * run instead
-		 */
-		if (pending && bdi_write_congested(bdi) && batch_run > 8 &&
-		    fs_info->fs_devices->open_devices > 1) {
-			struct io_context *ioc;
-
-			ioc = current->io_context;
-
-			/*
-			 * the main goal here is that we don't want to
-			 * block if we're going to be able to submit
-			 * more requests without blocking.
-			 *
-			 * This code does two great things, it pokes into
-			 * the elevator code from a filesystem _and_
-			 * it makes assumptions about how batching works.
-			 */
-			if (ioc && ioc->nr_batch_requests > 0 &&
-			    time_before(jiffies, ioc->last_waited + HZ/50UL) &&
-			    (last_waited == 0 ||
-			     ioc->last_waited == last_waited)) {
-				/*
-				 * we want to go through our batch of
-				 * requests and stop.  So, we copy out
-				 * the ioc->last_waited time and test
-				 * against it before looping
-				 */
-				last_waited = ioc->last_waited;
-				cond_resched();
-				continue;
-			}
-			spin_lock(&device->io_lock);
-			requeue_list(pending_bios, pending, tail);
-			device->running_pending = 1;
-
-			spin_unlock(&device->io_lock);
-			btrfs_queue_work(fs_info->submit_workers,
-					 &device->work);
-			goto done;
-		}
-	}
-
-	cond_resched();
-	if (again)
-		goto loop;
-
-	spin_lock(&device->io_lock);
-	if (device->pending_bios.head || device->pending_sync_bios.head)
-		goto loop_lock;
-	spin_unlock(&device->io_lock);
-
-done:
-	blk_finish_plug(&plug);
-}
-
-static void pending_bios_fn(struct btrfs_work *work)
-{
-	struct btrfs_device *device;
-
-	device = container_of(work, struct btrfs_device, work);
-	run_scheduled_bios(device);
-}
-
 static bool device_path_matched(const char *path, struct btrfs_device *device)
 {
 	int found;
@@ -818,7 +634,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 		}
 
 		clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
-		fs_devices->seeding = 1;
+		fs_devices->seeding = true;
 	} else {
 		if (bdev_read_only(bdev))
 			clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
@@ -828,7 +644,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 
 	q = bdev_get_queue(bdev);
 	if (!blk_queue_nonrot(q))
-		fs_devices->rotating = 1;
+		fs_devices->rotating = true;
 
 	device->bdev = bdev;
 	clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
@@ -1005,11 +821,15 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		*new_device_added = true;
 
 		if (disk_super->label[0])
-			pr_info("BTRFS: device label %s devid %llu transid %llu %s\n",
-				disk_super->label, devid, found_transid, path);
+			pr_info(
+	"BTRFS: device label %s devid %llu transid %llu %s scanned by %s (%d)\n",
+				disk_super->label, devid, found_transid, path,
+				current->comm, task_pid_nr(current));
 		else
-			pr_info("BTRFS: device fsid %pU devid %llu transid %llu %s\n",
-				disk_super->fsid, devid, found_transid, path);
+			pr_info(
+	"BTRFS: device fsid %pU devid %llu transid %llu %s scanned by %s (%d)\n",
+				disk_super->fsid, devid, found_transid, path,
+				current->comm, task_pid_nr(current));
 
 	} else if (!device->name || strcmp(device->name->str, path)) {
 		/*
@@ -1295,7 +1115,7 @@ static int close_fs_devices(struct btrfs_fs_devices *fs_devices)
 	WARN_ON(fs_devices->open_devices);
 	WARN_ON(fs_devices->rw_devices);
 	fs_devices->opened = 0;
-	fs_devices->seeding = 0;
+	fs_devices->seeding = false;
 
 	return 0;
 }
@@ -2048,7 +1868,7 @@ static struct btrfs_device * btrfs_find_next_active_device(
  * where this function called, there should be always be another device (or
  * this_dev) which is active.
  */
-void btrfs_assign_next_active_device(struct btrfs_device *device,
+void __cold btrfs_assign_next_active_device(struct btrfs_device *device,
 				     struct btrfs_device *this_dev)
 {
 	struct btrfs_fs_info *fs_info = device->fs_info;
@@ -2450,11 +2270,11 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 	list_splice_init(&fs_devices->alloc_list, &seed_devices->alloc_list);
 	mutex_unlock(&fs_info->chunk_mutex);
 
-	fs_devices->seeding = 0;
+	fs_devices->seeding = false;
 	fs_devices->num_devices = 0;
 	fs_devices->open_devices = 0;
 	fs_devices->missing_devices = 0;
-	fs_devices->rotating = 0;
+	fs_devices->rotating = false;
 	fs_devices->seed = seed_devices;
 
 	generate_random_uuid(fs_devices->fsid);
@@ -2649,7 +2469,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	atomic64_add(device->total_bytes, &fs_info->free_chunk_space);
 
 	if (!blk_queue_nonrot(q))
-		fs_devices->rotating = 1;
+		fs_devices->rotating = true;
 
 	orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
 	btrfs_set_super_total_bytes(fs_info->super_copy,
@@ -3177,7 +2997,7 @@ error:
 static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
 				      u64 chunk_offset)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	u64 bytes_used;
 	u64 chunk_type;
 
@@ -3186,27 +3006,28 @@ static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
 	chunk_type = cache->flags;
 	btrfs_put_block_group(cache);
 
-	if (chunk_type & BTRFS_BLOCK_GROUP_DATA) {
-		spin_lock(&fs_info->data_sinfo->lock);
-		bytes_used = fs_info->data_sinfo->bytes_used;
-		spin_unlock(&fs_info->data_sinfo->lock);
+	if (!(chunk_type & BTRFS_BLOCK_GROUP_DATA))
+		return 0;
+
+	spin_lock(&fs_info->data_sinfo->lock);
+	bytes_used = fs_info->data_sinfo->bytes_used;
+	spin_unlock(&fs_info->data_sinfo->lock);
 
-		if (!bytes_used) {
-			struct btrfs_trans_handle *trans;
-			int ret;
+	if (!bytes_used) {
+		struct btrfs_trans_handle *trans;
+		int ret;
 
-			trans =	btrfs_join_transaction(fs_info->tree_root);
-			if (IS_ERR(trans))
-				return PTR_ERR(trans);
+		trans =	btrfs_join_transaction(fs_info->tree_root);
+		if (IS_ERR(trans))
+			return PTR_ERR(trans);
 
-			ret = btrfs_force_chunk_alloc(trans,
-						      BTRFS_BLOCK_GROUP_DATA);
-			btrfs_end_transaction(trans);
-			if (ret < 0)
-				return ret;
-			return 1;
-		}
+		ret = btrfs_force_chunk_alloc(trans, BTRFS_BLOCK_GROUP_DATA);
+		btrfs_end_transaction(trans);
+		if (ret < 0)
+			return ret;
+		return 1;
 	}
+
 	return 0;
 }
 
@@ -3385,28 +3206,28 @@ static int chunk_profiles_filter(u64 chunk_type,
 static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
 			      struct btrfs_balance_args *bargs)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	u64 chunk_used;
 	u64 user_thresh_min;
 	u64 user_thresh_max;
 	int ret = 1;
 
 	cache = btrfs_lookup_block_group(fs_info, chunk_offset);
-	chunk_used = btrfs_block_group_used(&cache->item);
+	chunk_used = cache->used;
 
 	if (bargs->usage_min == 0)
 		user_thresh_min = 0;
 	else
-		user_thresh_min = div_factor_fine(cache->key.offset,
-					bargs->usage_min);
+		user_thresh_min = div_factor_fine(cache->length,
+						  bargs->usage_min);
 
 	if (bargs->usage_max == 0)
 		user_thresh_max = 1;
 	else if (bargs->usage_max > 100)
-		user_thresh_max = cache->key.offset;
+		user_thresh_max = cache->length;
 	else
-		user_thresh_max = div_factor_fine(cache->key.offset,
-					bargs->usage_max);
+		user_thresh_max = div_factor_fine(cache->length,
+						  bargs->usage_max);
 
 	if (user_thresh_min <= chunk_used && chunk_used < user_thresh_max)
 		ret = 0;
@@ -3418,20 +3239,19 @@ static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_off
 static int chunk_usage_filter(struct btrfs_fs_info *fs_info,
 		u64 chunk_offset, struct btrfs_balance_args *bargs)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 	u64 chunk_used, user_thresh;
 	int ret = 1;
 
 	cache = btrfs_lookup_block_group(fs_info, chunk_offset);
-	chunk_used = btrfs_block_group_used(&cache->item);
+	chunk_used = cache->used;
 
 	if (bargs->usage_min == 0)
 		user_thresh = 1;
 	else if (bargs->usage > 100)
-		user_thresh = cache->key.offset;
+		user_thresh = cache->length;
 	else
-		user_thresh = div_factor_fine(cache->key.offset,
-					      bargs->usage);
+		user_thresh = div_factor_fine(cache->length, bargs->usage);
 
 	if (chunk_used < user_thresh)
 		ret = 0;
@@ -3844,12 +3664,7 @@ static int alloc_profile_is_valid(u64 flags, int extended)
 	if (flags == 0)
 		return !extended; /* "0" is valid for usual profiles */
 
-	/* true if exactly one bit set */
-	/*
-	 * Don't use is_power_of_2(unsigned long) because it won't work
-	 * for the single profile (1ULL << 48) on 32-bit CPUs.
-	 */
-	return flags != 0 && (flags & (flags - 1)) == 0;
+	return has_single_bit_set(flags);
 }
 
 static inline int balance_need_close(struct btrfs_fs_info *fs_info)
@@ -4036,7 +3851,7 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
 	int ret;
 	u64 num_devices;
 	unsigned seq;
-	bool reducing_integrity;
+	bool reducing_redundancy;
 	int i;
 
 	if (btrfs_fs_closing(fs_info) ||
@@ -4119,9 +3934,9 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
 		    ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
 		     (fs_info->avail_metadata_alloc_bits & allowed) &&
 		     !(bctl->meta.target & allowed)))
-			reducing_integrity = true;
+			reducing_redundancy = true;
 		else
-			reducing_integrity = false;
+			reducing_redundancy = false;
 
 		/* if we're not converting, the target field is uninitialized */
 		meta_target = (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) ?
@@ -4130,13 +3945,13 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
 			bctl->data.target : fs_info->avail_data_alloc_bits;
 	} while (read_seqretry(&fs_info->profiles_lock, seq));
 
-	if (reducing_integrity) {
+	if (reducing_redundancy) {
 		if (bctl->flags & BTRFS_BALANCE_FORCE) {
 			btrfs_info(fs_info,
-				   "balance: force reducing metadata integrity");
+			   "balance: force reducing metadata redundancy");
 		} else {
 			btrfs_err(fs_info,
-	  "balance: reduces metadata integrity, use --force if you want this");
+	"balance: reduces metadata redundancy, use --force if you want this");
 			ret = -EINVAL;
 			goto out;
 		}
@@ -4902,6 +4717,14 @@ static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type)
 	btrfs_set_fs_incompat(info, RAID56);
 }
 
+static void check_raid1c34_incompat_flag(struct btrfs_fs_info *info, u64 type)
+{
+	if (!(type & (BTRFS_BLOCK_GROUP_RAID1C3 | BTRFS_BLOCK_GROUP_RAID1C4)))
+		return;
+
+	btrfs_set_fs_incompat(info, RAID1C34);
+}
+
 static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 			       u64 start, u64 type)
 {
@@ -5048,8 +4871,11 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	sort(devices_info, ndevs, sizeof(struct btrfs_device_info),
 	     btrfs_cmp_device_info, NULL);
 
-	/* round down to number of usable stripes */
-	ndevs = round_down(ndevs, devs_increment);
+	/*
+	 * Round down to number of usable stripes, devs_increment can be any
+	 * number so we can't use round_down()
+	 */
+	ndevs -= ndevs % devs_increment;
 
 	if (ndevs < devs_min) {
 		ret = -ENOSPC;
@@ -5165,6 +4991,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
 	free_extent_map(em);
 	check_raid56_incompat_flag(info, type);
+	check_raid1c34_incompat_flag(info, type);
 
 	kfree(devices_info);
 	return 0;
@@ -5583,12 +5410,13 @@ void btrfs_put_bbio(struct btrfs_bio *bbio)
  * replace.
  */
 static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
-					 u64 logical, u64 length,
+					 u64 logical, u64 *length_ret,
 					 struct btrfs_bio **bbio_ret)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
 	struct btrfs_bio *bbio;
+	u64 length = *length_ret;
 	u64 offset;
 	u64 stripe_nr;
 	u64 stripe_nr_end;
@@ -5621,7 +5449,8 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
 	}
 
 	offset = logical - em->start;
-	length = min_t(u64, em->len - offset, length);
+	length = min_t(u64, em->start + em->len - logical, length);
+	*length_ret = length;
 
 	stripe_len = map->stripe_len;
 	/*
@@ -6036,7 +5865,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 
 	if (op == BTRFS_MAP_DISCARD)
 		return __btrfs_map_block_for_discard(fs_info, logical,
-						     *length, bbio_ret);
+						     length, bbio_ret);
 
 	ret = btrfs_get_io_geometry(fs_info, op, logical, *length, &geom);
 	if (ret < 0)
@@ -6416,52 +6245,8 @@ static void btrfs_end_bio(struct bio *bio)
 	}
 }
 
-/*
- * see run_scheduled_bios for a description of why bios are collected for
- * async submit.
- *
- * This will add one bio to the pending list for a device and make sure
- * the work struct is scheduled.
- */
-static noinline void btrfs_schedule_bio(struct btrfs_device *device,
-					struct bio *bio)
-{
-	struct btrfs_fs_info *fs_info = device->fs_info;
-	int should_queue = 1;
-	struct btrfs_pending_bios *pending_bios;
-
-	/* don't bother with additional async steps for reads, right now */
-	if (bio_op(bio) == REQ_OP_READ) {
-		btrfsic_submit_bio(bio);
-		return;
-	}
-
-	WARN_ON(bio->bi_next);
-	bio->bi_next = NULL;
-
-	spin_lock(&device->io_lock);
-	if (op_is_sync(bio->bi_opf))
-		pending_bios = &device->pending_sync_bios;
-	else
-		pending_bios = &device->pending_bios;
-
-	if (pending_bios->tail)
-		pending_bios->tail->bi_next = bio;
-
-	pending_bios->tail = bio;
-	if (!pending_bios->head)
-		pending_bios->head = bio;
-	if (device->running_pending)
-		should_queue = 0;
-
-	spin_unlock(&device->io_lock);
-
-	if (should_queue)
-		btrfs_queue_work(fs_info->submit_workers, &device->work);
-}
-
 static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
-			      u64 physical, int dev_nr, int async)
+			      u64 physical, int dev_nr)
 {
 	struct btrfs_device *dev = bbio->stripes[dev_nr].dev;
 	struct btrfs_fs_info *fs_info = bbio->fs_info;
@@ -6479,10 +6264,7 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
 
 	btrfs_bio_counter_inc_noblocked(fs_info);
 
-	if (async)
-		btrfs_schedule_bio(dev, bio);
-	else
-		btrfsic_submit_bio(bio);
+	btrfsic_submit_bio(bio);
 }
 
 static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
@@ -6503,7 +6285,7 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
 }
 
 blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
-			   int mirror_num, int async_submit)
+			   int mirror_num)
 {
 	struct btrfs_device *dev;
 	struct bio *first_bio = bio;
@@ -6572,7 +6354,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 			bio = first_bio;
 
 		submit_stripe_bio(bbio, bio, bbio->stripes[dev_nr].physical,
-				  dev_nr, async_submit);
+				  dev_nr);
 	}
 	btrfs_bio_counter_dec(fs_info);
 	return BLK_STS_OK;
@@ -6676,9 +6458,6 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 	else
 		generate_random_uuid(dev->uuid);
 
-	btrfs_init_work(&dev->work, btrfs_submit_helper,
-			pending_bios_fn, NULL, NULL);
-
 	return dev;
 }
 
@@ -6875,7 +6654,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
 		if (IS_ERR(fs_devices))
 			return fs_devices;
 
-		fs_devices->seeding = 1;
+		fs_devices->seeding = true;
 		fs_devices->opened = 1;
 		return fs_devices;
 	}
@@ -7064,48 +6843,49 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info)
 		sb_array_offset += len;
 		cur_offset += len;
 
-		if (key.type == BTRFS_CHUNK_ITEM_KEY) {
-			chunk = (struct btrfs_chunk *)sb_array_offset;
-			/*
-			 * At least one btrfs_chunk with one stripe must be
-			 * present, exact stripe count check comes afterwards
-			 */
-			len = btrfs_chunk_item_size(1);
-			if (cur_offset + len > array_size)
-				goto out_short_read;
-
-			num_stripes = btrfs_chunk_num_stripes(sb, chunk);
-			if (!num_stripes) {
-				btrfs_err(fs_info,
-					"invalid number of stripes %u in sys_array at offset %u",
-					num_stripes, cur_offset);
-				ret = -EIO;
-				break;
-			}
+		if (key.type != BTRFS_CHUNK_ITEM_KEY) {
+			btrfs_err(fs_info,
+			    "unexpected item type %u in sys_array at offset %u",
+				  (u32)key.type, cur_offset);
+			ret = -EIO;
+			break;
+		}
 
-			type = btrfs_chunk_type(sb, chunk);
-			if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) {
-				btrfs_err(fs_info,
-			    "invalid chunk type %llu in sys_array at offset %u",
-					type, cur_offset);
-				ret = -EIO;
-				break;
-			}
+		chunk = (struct btrfs_chunk *)sb_array_offset;
+		/*
+		 * At least one btrfs_chunk with one stripe must be present,
+		 * exact stripe count check comes afterwards
+		 */
+		len = btrfs_chunk_item_size(1);
+		if (cur_offset + len > array_size)
+			goto out_short_read;
 
-			len = btrfs_chunk_item_size(num_stripes);
-			if (cur_offset + len > array_size)
-				goto out_short_read;
+		num_stripes = btrfs_chunk_num_stripes(sb, chunk);
+		if (!num_stripes) {
+			btrfs_err(fs_info,
+			"invalid number of stripes %u in sys_array at offset %u",
+				  num_stripes, cur_offset);
+			ret = -EIO;
+			break;
+		}
 
-			ret = read_one_chunk(&key, sb, chunk);
-			if (ret)
-				break;
-		} else {
+		type = btrfs_chunk_type(sb, chunk);
+		if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) {
 			btrfs_err(fs_info,
-			    "unexpected item type %u in sys_array at offset %u",
-				  (u32)key.type, cur_offset);
+			"invalid chunk type %llu in sys_array at offset %u",
+				  type, cur_offset);
 			ret = -EIO;
 			break;
 		}
+
+		len = btrfs_chunk_item_size(num_stripes);
+		if (cur_offset + len > array_size)
+			goto out_short_read;
+
+		ret = read_one_chunk(&key, sb, chunk);
+		if (ret)
+			break;
+
 		array_ptr += len;
 		sb_array_offset += len;
 		cur_offset += len;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index a7da1f3e3627..fc1b564b9cfe 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -18,10 +18,6 @@ extern struct mutex uuid_mutex;
 #define BTRFS_STRIPE_LEN	SZ_64K
 
 struct buffer_head;
-struct btrfs_pending_bios {
-	struct bio *head;
-	struct bio *tail;
-};
 
 struct btrfs_io_geometry {
 	/* remaining bytes before crossing a stripe */
@@ -68,13 +64,6 @@ struct btrfs_device {
 
 	u64 generation;
 
-	spinlock_t io_lock ____cacheline_aligned;
-	int running_pending;
-	/* regular prio bios */
-	struct btrfs_pending_bios pending_bios;
-	/* sync bios */
-	struct btrfs_pending_bios pending_sync_bios;
-
 	struct block_device *bdev;
 
 	/* the mode sent to blkdev_get */
@@ -254,14 +243,14 @@ struct btrfs_fs_devices {
 	struct list_head alloc_list;
 
 	struct btrfs_fs_devices *seed;
-	int seeding;
+	bool seeding;
 
 	int opened;
 
 	/* set when we find or add a device that doesn't have the
 	 * nonrot flag set
 	 */
-	int rotating;
+	bool rotating;
 
 	struct btrfs_fs_info *fs_info;
 	/* sysfs kobjects */
@@ -330,7 +319,6 @@ struct btrfs_bio {
 	u64 map_type; /* get from map_lookup->type */
 	bio_end_io_t *end_io;
 	struct bio *orig_bio;
-	unsigned long flags;
 	void *private;
 	atomic_t error;
 	int max_errors;
@@ -436,7 +424,7 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
 int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type);
 void btrfs_mapping_tree_free(struct extent_map_tree *tree);
 blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
-			   int mirror_num, int async_submit);
+			   int mirror_num);
 int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		       fmode_t flags, void *holder);
 struct btrfs_device *btrfs_scan_one_device(const char *path,
@@ -557,6 +545,10 @@ static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags)
 		return BTRFS_RAID_RAID10;
 	else if (flags & BTRFS_BLOCK_GROUP_RAID1)
 		return BTRFS_RAID_RAID1;
+	else if (flags & BTRFS_BLOCK_GROUP_RAID1C3)
+		return BTRFS_RAID_RAID1C3;
+	else if (flags & BTRFS_BLOCK_GROUP_RAID1C4)
+		return BTRFS_RAID_RAID1C4;
 	else if (flags & BTRFS_BLOCK_GROUP_DUP)
 		return BTRFS_RAID_DUP;
 	else if (flags & BTRFS_BLOCK_GROUP_RAID0)
@@ -571,7 +563,7 @@ static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags)
 
 void btrfs_commit_device_sizes(struct btrfs_transaction *trans);
 
-struct list_head *btrfs_get_fs_uuids(void);
+struct list_head * __attribute_const__ btrfs_get_fs_uuids(void);
 void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info);
 void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info);
 bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index df1aace5df50..a6c90a003c12 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -29,19 +29,9 @@ struct workspace {
 
 static struct workspace_manager wsm;
 
-static void zlib_init_workspace_manager(void)
+struct list_head *zlib_get_workspace(unsigned int level)
 {
-	btrfs_init_workspace_manager(&wsm, &btrfs_zlib_compress);
-}
-
-static void zlib_cleanup_workspace_manager(void)
-{
-	btrfs_cleanup_workspace_manager(&wsm);
-}
-
-static struct list_head *zlib_get_workspace(unsigned int level)
-{
-	struct list_head *ws = btrfs_get_workspace(&wsm, level);
+	struct list_head *ws = btrfs_get_workspace(BTRFS_COMPRESS_ZLIB, level);
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 
 	workspace->level = level;
@@ -49,12 +39,7 @@ static struct list_head *zlib_get_workspace(unsigned int level)
 	return ws;
 }
 
-static void zlib_put_workspace(struct list_head *ws)
-{
-	btrfs_put_workspace(&wsm, ws);
-}
-
-static void zlib_free_workspace(struct list_head *ws)
+void zlib_free_workspace(struct list_head *ws)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 
@@ -63,7 +48,7 @@ static void zlib_free_workspace(struct list_head *ws)
 	kfree(workspace);
 }
 
-static struct list_head *zlib_alloc_workspace(unsigned int level)
+struct list_head *zlib_alloc_workspace(unsigned int level)
 {
 	struct workspace *workspace;
 	int workspacesize;
@@ -88,13 +73,9 @@ fail:
 	return ERR_PTR(-ENOMEM);
 }
 
-static int zlib_compress_pages(struct list_head *ws,
-			       struct address_space *mapping,
-			       u64 start,
-			       struct page **pages,
-			       unsigned long *out_pages,
-			       unsigned long *total_in,
-			       unsigned long *total_out)
+int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
+		u64 start, struct page **pages, unsigned long *out_pages,
+		unsigned long *total_in, unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret;
@@ -228,7 +209,7 @@ out:
 	return ret;
 }
 
-static int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
+int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0, ret2;
@@ -319,10 +300,9 @@ done:
 	return ret;
 }
 
-static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
-			   struct page *dest_page,
-			   unsigned long start_byte,
-			   size_t srclen, size_t destlen)
+int zlib_decompress(struct list_head *ws, unsigned char *data_in,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0;
@@ -419,15 +399,7 @@ next:
 }
 
 const struct btrfs_compress_op btrfs_zlib_compress = {
-	.init_workspace_manager	= zlib_init_workspace_manager,
-	.cleanup_workspace_manager = zlib_cleanup_workspace_manager,
-	.get_workspace		= zlib_get_workspace,
-	.put_workspace		= zlib_put_workspace,
-	.alloc_workspace	= zlib_alloc_workspace,
-	.free_workspace		= zlib_free_workspace,
-	.compress_pages		= zlib_compress_pages,
-	.decompress_bio		= zlib_decompress_bio,
-	.decompress		= zlib_decompress,
+	.workspace_manager	= &wsm,
 	.max_level		= 9,
 	.default_level		= BTRFS_ZLIB_DEFAULT_LEVEL,
 };
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 764d47b107e5..9a4871636c6c 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -91,9 +91,8 @@ static inline struct workspace *list_to_workspace(struct list_head *list)
 	return container_of(list, struct workspace, list);
 }
 
-static void zstd_free_workspace(struct list_head *ws);
-static struct list_head *zstd_alloc_workspace(unsigned int level);
-
+void zstd_free_workspace(struct list_head *ws);
+struct list_head *zstd_alloc_workspace(unsigned int level);
 /*
  * zstd_reclaim_timer_fn - reclaim timer
  * @t: timer
@@ -168,7 +167,7 @@ static void zstd_calc_ws_mem_sizes(void)
 	}
 }
 
-static void zstd_init_workspace_manager(void)
+void zstd_init_workspace_manager(void)
 {
 	struct list_head *ws;
 	int i;
@@ -194,7 +193,7 @@ static void zstd_init_workspace_manager(void)
 	}
 }
 
-static void zstd_cleanup_workspace_manager(void)
+void zstd_cleanup_workspace_manager(void)
 {
 	struct workspace *workspace;
 	int i;
@@ -261,7 +260,7 @@ static struct list_head *zstd_find_workspace(unsigned int level)
  * attempt to allocate a new workspace.  If we fail to allocate one due to
  * memory pressure, go to sleep waiting for the max level workspace to free up.
  */
-static struct list_head *zstd_get_workspace(unsigned int level)
+struct list_head *zstd_get_workspace(unsigned int level)
 {
 	struct list_head *ws;
 	unsigned int nofs_flag;
@@ -302,7 +301,7 @@ again:
  * isn't set, it is also set here.  Only the max level workspace tries and wakes
  * up waiting workspaces.
  */
-static void zstd_put_workspace(struct list_head *ws)
+void zstd_put_workspace(struct list_head *ws)
 {
 	struct workspace *workspace = list_to_workspace(ws);
 
@@ -332,7 +331,7 @@ static void zstd_put_workspace(struct list_head *ws)
 		cond_wake_up(&wsm.wait);
 }
 
-static void zstd_free_workspace(struct list_head *ws)
+void zstd_free_workspace(struct list_head *ws)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 
@@ -341,7 +340,7 @@ static void zstd_free_workspace(struct list_head *ws)
 	kfree(workspace);
 }
 
-static struct list_head *zstd_alloc_workspace(unsigned int level)
+struct list_head *zstd_alloc_workspace(unsigned int level)
 {
 	struct workspace *workspace;
 
@@ -367,13 +366,9 @@ fail:
 	return ERR_PTR(-ENOMEM);
 }
 
-static int zstd_compress_pages(struct list_head *ws,
-		struct address_space *mapping,
-		u64 start,
-		struct page **pages,
-		unsigned long *out_pages,
-		unsigned long *total_in,
-		unsigned long *total_out)
+int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
+		u64 start, struct page **pages, unsigned long *out_pages,
+		unsigned long *total_in, unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	ZSTD_CStream *stream;
@@ -548,7 +543,7 @@ out:
 	return ret;
 }
 
-static int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
+int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	struct page **pages_in = cb->compressed_pages;
@@ -626,10 +621,9 @@ done:
 	return ret;
 }
 
-static int zstd_decompress(struct list_head *ws, unsigned char *data_in,
-		struct page *dest_page,
-		unsigned long start_byte,
-		size_t srclen, size_t destlen)
+int zstd_decompress(struct list_head *ws, unsigned char *data_in,
+		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	ZSTD_DStream *stream;
@@ -712,15 +706,8 @@ finish:
 }
 
 const struct btrfs_compress_op btrfs_zstd_compress = {
-	.init_workspace_manager = zstd_init_workspace_manager,
-	.cleanup_workspace_manager = zstd_cleanup_workspace_manager,
-	.get_workspace = zstd_get_workspace,
-	.put_workspace = zstd_put_workspace,
-	.alloc_workspace = zstd_alloc_workspace,
-	.free_workspace = zstd_free_workspace,
-	.compress_pages = zstd_compress_pages,
-	.decompress_bio = zstd_decompress_bio,
-	.decompress = zstd_decompress,
+	/* ZSTD uses own workspace manager */
+	.workspace_manager = NULL,
 	.max_level	= ZSTD_BTRFS_MAX_LEVEL,
 	.default_level	= ZSTD_BTRFS_DEFAULT_LEVEL,
 };