[PATCH 0/4] btrfs: move random block rsv code around

[PATCH 0/4] btrfs: move random block rsv code around

[Josef Bacik]

We have some specialized block rsvs, like the inode rsv and the delayed refs
rsv, that have their own special oddities.  These don't fit in extent-tree.c, so
migrate them to different places.  Most of them go to existing files, but the
delalloc stuff gets its own file because it's a lot of code, and inode.c and
file.c are relatively large already.

This depends on the previous two chunks of migrations.  These are relatively
small and straightforward since all of the functions were exported already as
they are used throughout the entire codebase.  The diffstat is as follows

 fs/btrfs/Makefile           |   2 +-
 fs/btrfs/ctree.h            |  24 --
 fs/btrfs/delalloc-space.c   | 497 ++++++++++++++++++++++++++++++
 fs/btrfs/delalloc-space.h   |  25 ++
 fs/btrfs/delayed-ref.c      | 177 +++++++++++
 fs/btrfs/delayed-ref.h      |  10 +
 fs/btrfs/extent-tree.c      | 733 +-------------------------------------------
 fs/btrfs/file.c             |   1 +
 fs/btrfs/free-space-cache.c |   1 +
 fs/btrfs/inode-map.c        |   1 +
 fs/btrfs/inode.c            |   1 +
 fs/btrfs/ioctl.c            |   1 +
 fs/btrfs/ordered-data.c     |   1 +
 fs/btrfs/relocation.c       |   1 +
 fs/btrfs/root-tree.c        |  56 ++++
 fs/btrfs/transaction.c      |  18 ++
 fs/btrfs/transaction.h      |   1 +
 17 files changed, 793 insertions(+), 757 deletions(-)

Thanks,

Josef

[PATCH 1/4] btrfs: migrate the delayed refs rsv code

[Josef Bacik]

These belong with the delayed refs related code, not in extent-tree.c.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
---
 fs/btrfs/ctree.h       |   9 ---
 fs/btrfs/delayed-ref.c | 177 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/btrfs/delayed-ref.h |  10 +++
 fs/btrfs/extent-tree.c | 175 ------------------------------------------------
 4 files changed, 187 insertions(+), 184 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9b8b8d07e66f..f6ba024cd273 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2606,8 +2606,6 @@ static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_fs_info *fs_info,
 	return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
 }
 
-int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans);
-bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info);
 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);
@@ -2768,13 +2766,6 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 				     bool qgroup_free);
 int btrfs_delalloc_reserve_space(struct inode *inode,
 			struct extent_changeset **reserved, u64 start, u64 len);
-void btrfs_delayed_refs_rsv_release(struct btrfs_fs_info *fs_info, int nr);
-void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans);
-int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
-				  enum btrfs_reserve_flush_enum flush);
-void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info,
-				       struct btrfs_block_rsv *src,
-				       u64 num_bytes);
 int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache);
 void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index a94fae897b3f..e24b3a7f9932 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -10,6 +10,7 @@
 #include "delayed-ref.h"
 #include "transaction.h"
 #include "qgroup.h"
+#include "space-info.h"
 
 struct kmem_cache *btrfs_delayed_ref_head_cachep;
 struct kmem_cache *btrfs_delayed_tree_ref_cachep;
@@ -24,6 +25,182 @@ struct kmem_cache *btrfs_delayed_extent_op_cachep;
  * of hammering updates on the extent allocation tree.
  */
 
+
+bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
+	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
+	bool ret = false;
+	u64 reserved;
+
+	spin_lock(&global_rsv->lock);
+	reserved = global_rsv->reserved;
+	spin_unlock(&global_rsv->lock);
+
+	/*
+	 * Since the global reserve is just kind of magic we don't really want
+	 * to rely on it to save our bacon, so if our size is more than the
+	 * delayed_refs_rsv and the global rsv then it's time to think about
+	 * bailing.
+	 */
+	spin_lock(&delayed_refs_rsv->lock);
+	reserved += delayed_refs_rsv->reserved;
+	if (delayed_refs_rsv->size >= reserved)
+		ret = true;
+	spin_unlock(&delayed_refs_rsv->lock);
+	return ret;
+}
+
+int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans)
+{
+	u64 num_entries =
+		atomic_read(&trans->transaction->delayed_refs.num_entries);
+	u64 avg_runtime;
+	u64 val;
+
+	smp_mb();
+	avg_runtime = trans->fs_info->avg_delayed_ref_runtime;
+	val = num_entries * avg_runtime;
+	if (val >= NSEC_PER_SEC)
+		return 1;
+	if (val >= NSEC_PER_SEC / 2)
+		return 2;
+
+	return btrfs_check_space_for_delayed_refs(trans->fs_info);
+}
+
+/**
+ * btrfs_delayed_refs_rsv_release - release a ref head's reservation.
+ * @fs_info - the fs_info for our fs.
+ * @nr - the number of items to drop.
+ *
+ * This drops the delayed ref head's count from the delayed refs rsv and frees
+ * any excess reservation we had.
+ */
+void btrfs_delayed_refs_rsv_release(struct btrfs_fs_info *fs_info, int nr)
+{
+	struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv;
+	u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, nr);
+	u64 released = 0;
+
+	released = __btrfs_block_rsv_release(fs_info, block_rsv, num_bytes,
+					     NULL);
+	if (released)
+		trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
+					      0, released, 0);
+}
+
+
+/*
+ * btrfs_update_delayed_refs_rsv - adjust the size of the delayed refs rsv
+ * @trans - the trans that may have generated delayed refs
+ *
+ * This is to be called anytime we may have adjusted trans->delayed_ref_updates,
+ * it'll calculate the additional size and add it to the delayed_refs_rsv.
+ */
+void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans)
+{
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+	struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv;
+	u64 num_bytes;
+
+	if (!trans->delayed_ref_updates)
+		return;
+
+	num_bytes = btrfs_calc_trans_metadata_size(fs_info,
+						   trans->delayed_ref_updates);
+	spin_lock(&delayed_rsv->lock);
+	delayed_rsv->size += num_bytes;
+	delayed_rsv->full = 0;
+	spin_unlock(&delayed_rsv->lock);
+	trans->delayed_ref_updates = 0;
+}
+
+/**
+ * btrfs_migrate_to_delayed_refs_rsv - transfer bytes to our delayed refs rsv.
+ * @fs_info - the fs info for our fs.
+ * @src - the source block rsv to transfer from.
+ * @num_bytes - the number of bytes to transfer.
+ *
+ * This transfers up to the num_bytes amount from the src rsv to the
+ * delayed_refs_rsv.  Any extra bytes are returned to the space info.
+ */
+void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info,
+				       struct btrfs_block_rsv *src,
+				       u64 num_bytes)
+{
+	struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
+	u64 to_free = 0;
+
+	spin_lock(&src->lock);
+	src->reserved -= num_bytes;
+	src->size -= num_bytes;
+	spin_unlock(&src->lock);
+
+	spin_lock(&delayed_refs_rsv->lock);
+	if (delayed_refs_rsv->size > delayed_refs_rsv->reserved) {
+		u64 delta = delayed_refs_rsv->size -
+			delayed_refs_rsv->reserved;
+		if (num_bytes > delta) {
+			to_free = num_bytes - delta;
+			num_bytes = delta;
+		}
+	} else {
+		to_free = num_bytes;
+		num_bytes = 0;
+	}
+
+	if (num_bytes)
+		delayed_refs_rsv->reserved += num_bytes;
+	if (delayed_refs_rsv->reserved >= delayed_refs_rsv->size)
+		delayed_refs_rsv->full = 1;
+	spin_unlock(&delayed_refs_rsv->lock);
+
+	if (num_bytes)
+		trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
+					      0, num_bytes, 1);
+	if (to_free)
+		btrfs_space_info_add_old_bytes(fs_info,
+					       delayed_refs_rsv->space_info,
+					       to_free);
+}
+
+/**
+ * btrfs_delayed_refs_rsv_refill - refill based on our delayed refs usage.
+ * @fs_info - the fs_info for our fs.
+ * @flush - control how we can flush for this reservation.
+ *
+ * This will refill the delayed block_rsv up to 1 items size worth of space and
+ * will return -ENOSPC if we can't make the reservation.
+ */
+int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
+				  enum btrfs_reserve_flush_enum flush)
+{
+	struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv;
+	u64 limit = btrfs_calc_trans_metadata_size(fs_info, 1);
+	u64 num_bytes = 0;
+	int ret = -ENOSPC;
+
+	spin_lock(&block_rsv->lock);
+	if (block_rsv->reserved < block_rsv->size) {
+		num_bytes = block_rsv->size - block_rsv->reserved;
+		num_bytes = min(num_bytes, limit);
+	}
+	spin_unlock(&block_rsv->lock);
+
+	if (!num_bytes)
+		return 0;
+
+	ret = btrfs_reserve_metadata_bytes(fs_info->extent_root, block_rsv,
+					   num_bytes, flush);
+	if (ret)
+		return ret;
+	btrfs_block_rsv_add_bytes(block_rsv, num_bytes, 0);
+	trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
+				      0, num_bytes, 1);
+	return 0;
+}
+
 /*
  * compare two delayed tree backrefs with same bytenr and type
  */
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index c18f93ea88ed..1c977e6d45dc 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -364,6 +364,16 @@ struct btrfs_delayed_ref_head *btrfs_select_ref_head(
 
 int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq);
 
+void btrfs_delayed_refs_rsv_release(struct btrfs_fs_info *fs_info, int nr);
+void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans);
+int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
+				  enum btrfs_reserve_flush_enum flush);
+void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info,
+				       struct btrfs_block_rsv *src,
+				       u64 num_bytes);
+int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans);
+bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info);
+
 /*
  * helper functions to cast a node into its container
  */
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index dffd338b01fc..0b94f17fa751 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2753,49 +2753,6 @@ u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes)
 	return num_csums;
 }
 
-bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info)
-{
-	struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
-	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
-	bool ret = false;
-	u64 reserved;
-
-	spin_lock(&global_rsv->lock);
-	reserved = global_rsv->reserved;
-	spin_unlock(&global_rsv->lock);
-
-	/*
-	 * Since the global reserve is just kind of magic we don't really want
-	 * to rely on it to save our bacon, so if our size is more than the
-	 * delayed_refs_rsv and the global rsv then it's time to think about
-	 * bailing.
-	 */
-	spin_lock(&delayed_refs_rsv->lock);
-	reserved += delayed_refs_rsv->reserved;
-	if (delayed_refs_rsv->size >= reserved)
-		ret = true;
-	spin_unlock(&delayed_refs_rsv->lock);
-	return ret;
-}
-
-int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans)
-{
-	u64 num_entries =
-		atomic_read(&trans->transaction->delayed_refs.num_entries);
-	u64 avg_runtime;
-	u64 val;
-
-	smp_mb();
-	avg_runtime = trans->fs_info->avg_delayed_ref_runtime;
-	val = num_entries * avg_runtime;
-	if (val >= NSEC_PER_SEC)
-		return 1;
-	if (val >= NSEC_PER_SEC / 2)
-		return 2;
-
-	return btrfs_check_space_for_delayed_refs(trans->fs_info);
-}
-
 /*
  * this starts processing the delayed reference count updates and
  * extent insertions we have queued up so far.  count can be
@@ -4349,91 +4306,6 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 	return ret;
 }
 
-/**
- * btrfs_migrate_to_delayed_refs_rsv - transfer bytes to our delayed refs rsv.
- * @fs_info - the fs info for our fs.
- * @src - the source block rsv to transfer from.
- * @num_bytes - the number of bytes to transfer.
- *
- * This transfers up to the num_bytes amount from the src rsv to the
- * delayed_refs_rsv.  Any extra bytes are returned to the space info.
- */
-void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info,
-				       struct btrfs_block_rsv *src,
-				       u64 num_bytes)
-{
-	struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
-	u64 to_free = 0;
-
-	spin_lock(&src->lock);
-	src->reserved -= num_bytes;
-	src->size -= num_bytes;
-	spin_unlock(&src->lock);
-
-	spin_lock(&delayed_refs_rsv->lock);
-	if (delayed_refs_rsv->size > delayed_refs_rsv->reserved) {
-		u64 delta = delayed_refs_rsv->size -
-			delayed_refs_rsv->reserved;
-		if (num_bytes > delta) {
-			to_free = num_bytes - delta;
-			num_bytes = delta;
-		}
-	} else {
-		to_free = num_bytes;
-		num_bytes = 0;
-	}
-
-	if (num_bytes)
-		delayed_refs_rsv->reserved += num_bytes;
-	if (delayed_refs_rsv->reserved >= delayed_refs_rsv->size)
-		delayed_refs_rsv->full = 1;
-	spin_unlock(&delayed_refs_rsv->lock);
-
-	if (num_bytes)
-		trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
-					      0, num_bytes, 1);
-	if (to_free)
-		btrfs_space_info_add_old_bytes(fs_info,
-					       delayed_refs_rsv->space_info,
-					       to_free);
-}
-
-/**
- * btrfs_delayed_refs_rsv_refill - refill based on our delayed refs usage.
- * @fs_info - the fs_info for our fs.
- * @flush - control how we can flush for this reservation.
- *
- * This will refill the delayed block_rsv up to 1 items size worth of space and
- * will return -ENOSPC if we can't make the reservation.
- */
-int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
-				  enum btrfs_reserve_flush_enum flush)
-{
-	struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv;
-	u64 limit = btrfs_calc_trans_metadata_size(fs_info, 1);
-	u64 num_bytes = 0;
-	int ret = -ENOSPC;
-
-	spin_lock(&block_rsv->lock);
-	if (block_rsv->reserved < block_rsv->size) {
-		num_bytes = block_rsv->size - block_rsv->reserved;
-		num_bytes = min(num_bytes, limit);
-	}
-	spin_unlock(&block_rsv->lock);
-
-	if (!num_bytes)
-		return 0;
-
-	ret = btrfs_reserve_metadata_bytes(fs_info->extent_root, block_rsv,
-					   num_bytes, flush);
-	if (ret)
-		return ret;
-	btrfs_block_rsv_add_bytes(block_rsv, num_bytes, 0);
-	trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
-				      0, num_bytes, 1);
-	return 0;
-}
-
 /**
  * btrfs_inode_rsv_release - release any excessive reservation.
  * @inode - the inode we need to release from.
@@ -4469,53 +4341,6 @@ static void btrfs_inode_rsv_release(struct btrfs_inode *inode, bool qgroup_free)
 						   qgroup_to_release);
 }
 
-/**
- * btrfs_delayed_refs_rsv_release - release a ref head's reservation.
- * @fs_info - the fs_info for our fs.
- * @nr - the number of items to drop.
- *
- * This drops the delayed ref head's count from the delayed refs rsv and frees
- * any excess reservation we had.
- */
-void btrfs_delayed_refs_rsv_release(struct btrfs_fs_info *fs_info, int nr)
-{
-	struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv;
-	u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, nr);
-	u64 released = 0;
-
-	released = __btrfs_block_rsv_release(fs_info, block_rsv, num_bytes,
-					     NULL);
-	if (released)
-		trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
-					      0, released, 0);
-}
-
-
-/*
- * btrfs_update_delayed_refs_rsv - adjust the size of the delayed refs rsv
- * @trans - the trans that may have generated delayed refs
- *
- * This is to be called anytime we may have adjusted trans->delayed_ref_updates,
- * it'll calculate the additional size and add it to the delayed_refs_rsv.
- */
-void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans)
-{
-	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv;
-	u64 num_bytes;
-
-	if (!trans->delayed_ref_updates)
-		return;
-
-	num_bytes = btrfs_calc_trans_metadata_size(fs_info,
-						   trans->delayed_ref_updates);
-	spin_lock(&delayed_rsv->lock);
-	delayed_rsv->size += num_bytes;
-	delayed_rsv->full = 0;
-	spin_unlock(&delayed_rsv->lock);
-	trans->delayed_ref_updates = 0;
-}
-
 /*
  * To be called after all the new block groups attached to the transaction
  * handle have been created (btrfs_create_pending_block_groups()).
-- 
2.14.3

[PATCH 2/4] btrfs: migrate btrfs_trans_release_chunk_metadata

[Josef Bacik]

Move this into transaction.c with the rest of the transaction related
code.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
---
 fs/btrfs/ctree.h       |  1 -
 fs/btrfs/extent-tree.c | 18 ------------------
 fs/btrfs/transaction.c | 18 ++++++++++++++++++
 fs/btrfs/transaction.h |  1 +
 4 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index f6ba024cd273..afd329184e36 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2752,7 +2752,6 @@ void btrfs_delalloc_release_space(struct inode *inode,
 				  u64 start, u64 len, bool qgroup_free);
 void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
 					    u64 len);
-void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     struct btrfs_block_rsv *rsv,
 				     int nitems, bool use_global_rsv);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 0b94f17fa751..20b9b3284af2 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4341,24 +4341,6 @@ static void btrfs_inode_rsv_release(struct btrfs_inode *inode, bool qgroup_free)
 						   qgroup_to_release);
 }
 
-/*
- * To be called after all the new block groups attached to the transaction
- * handle have been created (btrfs_create_pending_block_groups()).
- */
-void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
-{
-	struct btrfs_fs_info *fs_info = trans->fs_info;
-
-	if (!trans->chunk_bytes_reserved)
-		return;
-
-	WARN_ON_ONCE(!list_empty(&trans->new_bgs));
-
-	btrfs_block_rsv_release(fs_info, &fs_info->chunk_block_rsv,
-				trans->chunk_bytes_reserved);
-	trans->chunk_bytes_reserved = 0;
-}
-
 /*
  * btrfs_subvolume_reserve_metadata() - reserve space for subvolume operation
  * root: the root of the parent directory
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 3f6811cdf803..3b8ae1a8f02d 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -128,6 +128,24 @@ static inline int extwriter_counter_read(struct btrfs_transaction *trans)
 	return atomic_read(&trans->num_extwriters);
 }
 
+/*
+ * To be called after all the new block groups attached to the transaction
+ * handle have been created (btrfs_create_pending_block_groups()).
+ */
+void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
+{
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+
+	if (!trans->chunk_bytes_reserved)
+		return;
+
+	WARN_ON_ONCE(!list_empty(&trans->new_bgs));
+
+	btrfs_block_rsv_release(fs_info, &fs_info->chunk_block_rsv,
+				trans->chunk_bytes_reserved);
+	trans->chunk_bytes_reserved = 0;
+}
+
 /*
  * either allocate a new transaction or hop into the existing one
  */
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 78c446c222b7..527ea94b57d9 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -224,5 +224,6 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction);
 void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info);
 void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root);
+void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
 
 #endif
-- 
2.14.3

[PATCH 3/4] btrfs: migrate the delalloc space stuff to it's own home

[Josef Bacik]

We have code for data and metadata reservations for delalloc.  There's
quite a bit of code here, and it's used in a lot of places so I've
separated it out to it's own file.  inode.c and file.c are already
pretty large, and this code is complicated enough to live in its own
space.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
---
 fs/btrfs/Makefile           |   2 +-
 fs/btrfs/ctree.h            |  14 --
 fs/btrfs/delalloc-space.c   | 497 ++++++++++++++++++++++++++++++++++++++++++++
 fs/btrfs/delalloc-space.h   |  25 +++
 fs/btrfs/extent-tree.c      | 486 +------------------------------------------
 fs/btrfs/file.c             |   1 +
 fs/btrfs/free-space-cache.c |   1 +
 fs/btrfs/inode-map.c        |   1 +
 fs/btrfs/inode.c            |   1 +
 fs/btrfs/ioctl.c            |   1 +
 fs/btrfs/ordered-data.c     |   1 +
 fs/btrfs/relocation.c       |   1 +
 12 files changed, 531 insertions(+), 500 deletions(-)
 create mode 100644 fs/btrfs/delalloc-space.c
 create mode 100644 fs/btrfs/delalloc-space.h

diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 032700ae7704..76a843198bcb 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -11,7 +11,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
 	   reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
 	   uuid-tree.o props.o free-space-tree.o tree-checker.o space-info.o \
-	   block-rsv.o
+	   block-rsv.o delalloc-space.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index afd329184e36..73e28d9c14bd 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2742,16 +2742,6 @@ enum btrfs_chunk_alloc_enum {
 
 int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 		      enum btrfs_chunk_alloc_enum force);
-int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes);
-int btrfs_check_data_free_space(struct inode *inode,
-			struct extent_changeset **reserved, u64 start, u64 len);
-void btrfs_free_reserved_data_space(struct inode *inode,
-			struct extent_changeset *reserved, u64 start, u64 len);
-void btrfs_delalloc_release_space(struct inode *inode,
-				  struct extent_changeset *reserved,
-				  u64 start, u64 len, bool qgroup_free);
-void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
-					    u64 len);
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     struct btrfs_block_rsv *rsv,
 				     int nitems, bool use_global_rsv);
@@ -2761,10 +2751,6 @@ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
 				    bool qgroup_free);
 
 int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
-void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
-				     bool qgroup_free);
-int btrfs_delalloc_reserve_space(struct inode *inode,
-			struct extent_changeset **reserved, u64 start, u64 len);
 int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache);
 void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
new file mode 100644
index 000000000000..260c152d0d84
--- /dev/null
+++ b/fs/btrfs/delalloc-space.c
@@ -0,0 +1,497 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Facebook.  All rights reserved.
+ */
+
+#include "ctree.h"
+#include "delalloc-space.h"
+#include "block-rsv.h"
+#include "btrfs_inode.h"
+#include "space-info.h"
+#include "transaction.h"
+#include "qgroup.h"
+
+int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes)
+{
+	struct btrfs_root *root = inode->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_space_info *data_sinfo = fs_info->data_sinfo;
+	u64 used;
+	int ret = 0;
+	int need_commit = 2;
+	int have_pinned_space;
+
+	/* make sure bytes are sectorsize aligned */
+	bytes = ALIGN(bytes, fs_info->sectorsize);
+
+	if (btrfs_is_free_space_inode(inode)) {
+		need_commit = 0;
+		ASSERT(current->journal_info);
+	}
+
+again:
+	/* make sure we have enough space to handle the data first */
+	spin_lock(&data_sinfo->lock);
+	used = btrfs_space_info_used(data_sinfo, true);
+
+	if (used + bytes > data_sinfo->total_bytes) {
+		struct btrfs_trans_handle *trans;
+
+		/*
+		 * if we don't have enough free bytes in this space then we need
+		 * to alloc a new chunk.
+		 */
+		if (!data_sinfo->full) {
+			u64 alloc_target;
+
+			data_sinfo->force_alloc = CHUNK_ALLOC_FORCE;
+			spin_unlock(&data_sinfo->lock);
+
+			alloc_target = btrfs_data_alloc_profile(fs_info);
+			/*
+			 * It is ugly that we don't call nolock join
+			 * transaction for the free space inode case here.
+			 * But it is safe because we only do the data space
+			 * reservation for the free space cache in the
+			 * transaction context, the common join transaction
+			 * just increase the counter of the current transaction
+			 * handler, doesn't try to acquire the trans_lock of
+			 * the fs.
+			 */
+			trans = btrfs_join_transaction(root);
+			if (IS_ERR(trans))
+				return PTR_ERR(trans);
+
+			ret = btrfs_chunk_alloc(trans, alloc_target,
+						CHUNK_ALLOC_NO_FORCE);
+			btrfs_end_transaction(trans);
+			if (ret < 0) {
+				if (ret != -ENOSPC)
+					return ret;
+				else {
+					have_pinned_space = 1;
+					goto commit_trans;
+				}
+			}
+
+			goto again;
+		}
+
+		/*
+		 * If we don't have enough pinned space to deal with this
+		 * allocation, and no removed chunk in current transaction,
+		 * don't bother committing the transaction.
+		 */
+		have_pinned_space = __percpu_counter_compare(
+			&data_sinfo->total_bytes_pinned,
+			used + bytes - data_sinfo->total_bytes,
+			BTRFS_TOTAL_BYTES_PINNED_BATCH);
+		spin_unlock(&data_sinfo->lock);
+
+		/* commit the current transaction and try again */
+commit_trans:
+		if (need_commit) {
+			need_commit--;
+
+			if (need_commit > 0) {
+				btrfs_start_delalloc_roots(fs_info, -1);
+				btrfs_wait_ordered_roots(fs_info, U64_MAX, 0,
+							 (u64)-1);
+			}
+
+			trans = btrfs_join_transaction(root);
+			if (IS_ERR(trans))
+				return PTR_ERR(trans);
+			if (have_pinned_space >= 0 ||
+			    test_bit(BTRFS_TRANS_HAVE_FREE_BGS,
+				     &trans->transaction->flags) ||
+			    need_commit > 0) {
+				ret = btrfs_commit_transaction(trans);
+				if (ret)
+					return ret;
+				/*
+				 * The cleaner kthread might still be doing iput
+				 * operations. Wait for it to finish so that
+				 * more space is released.  We don't need to
+				 * explicitly run the delayed iputs here because
+				 * the commit_transaction would have woken up
+				 * the cleaner.
+				 */
+				ret = btrfs_wait_on_delayed_iputs(fs_info);
+				if (ret)
+					return ret;
+				goto again;
+			} else {
+				btrfs_end_transaction(trans);
+			}
+		}
+
+		trace_btrfs_space_reservation(fs_info,
+					      "space_info:enospc",
+					      data_sinfo->flags, bytes, 1);
+		return -ENOSPC;
+	}
+	btrfs_space_info_update_bytes_may_use(fs_info, data_sinfo, bytes);
+	trace_btrfs_space_reservation(fs_info, "space_info",
+				      data_sinfo->flags, bytes, 1);
+	spin_unlock(&data_sinfo->lock);
+
+	return 0;
+}
+
+int btrfs_check_data_free_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	int ret;
+
+	/* align the range */
+	len = round_up(start + len, fs_info->sectorsize) -
+	      round_down(start, fs_info->sectorsize);
+	start = round_down(start, fs_info->sectorsize);
+
+	ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), len);
+	if (ret < 0)
+		return ret;
+
+	/* Use new btrfs_qgroup_reserve_data to reserve precious data space. */
+	ret = btrfs_qgroup_reserve_data(inode, reserved, start, len);
+	if (ret < 0)
+		btrfs_free_reserved_data_space_noquota(inode, start, len);
+	else
+		ret = 0;
+	return ret;
+}
+
+/*
+ * Called if we need to clear a data reservation for this inode
+ * Normally in a error case.
+ *
+ * This one will *NOT* use accurate qgroup reserved space API, just for case
+ * which we can't sleep and is sure it won't affect qgroup reserved space.
+ * Like clear_bit_hook().
+ */
+void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
+					    u64 len)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_space_info *data_sinfo;
+
+	/* Make sure the range is aligned to sectorsize */
+	len = round_up(start + len, fs_info->sectorsize) -
+	      round_down(start, fs_info->sectorsize);
+	start = round_down(start, fs_info->sectorsize);
+
+	data_sinfo = fs_info->data_sinfo;
+	spin_lock(&data_sinfo->lock);
+	btrfs_space_info_update_bytes_may_use(fs_info, data_sinfo, -len);
+	trace_btrfs_space_reservation(fs_info, "space_info",
+				      data_sinfo->flags, len, 0);
+	spin_unlock(&data_sinfo->lock);
+}
+
+/*
+ * Called if we need to clear a data reservation for this inode
+ * Normally in a error case.
+ *
+ * This one will handle the per-inode data rsv map for accurate reserved
+ * space framework.
+ */
+void btrfs_free_reserved_data_space(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len)
+{
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+
+	/* Make sure the range is aligned to sectorsize */
+	len = round_up(start + len, root->fs_info->sectorsize) -
+	      round_down(start, root->fs_info->sectorsize);
+	start = round_down(start, root->fs_info->sectorsize);
+
+	btrfs_free_reserved_data_space_noquota(inode, start, len);
+	btrfs_qgroup_free_data(inode, reserved, start, len);
+}
+
+/**
+ * btrfs_inode_rsv_release - release any excessive reservation.
+ * @inode - the inode we need to release from.
+ * @qgroup_free - free or convert qgroup meta.
+ *   Unlike normal operation, qgroup meta reservation needs to know if we are
+ *   freeing qgroup reservation or just converting it into per-trans.  Normally
+ *   @qgroup_free is true for error handling, and false for normal release.
+ *
+ * This is the same as btrfs_block_rsv_release, except that it handles the
+ * tracepoint for the reservation.
+ */
+static void btrfs_inode_rsv_release(struct btrfs_inode *inode, bool qgroup_free)
+{
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
+	u64 released = 0;
+	u64 qgroup_to_release = 0;
+
+	/*
+	 * Since we statically set the block_rsv->size we just want to say we
+	 * are releasing 0 bytes, and then we'll just get the reservation over
+	 * the size free'd.
+	 */
+	released = __btrfs_block_rsv_release(fs_info, block_rsv, 0,
+					     &qgroup_to_release);
+	if (released > 0)
+		trace_btrfs_space_reservation(fs_info, "delalloc",
+					      btrfs_ino(inode), released, 0);
+	if (qgroup_free)
+		btrfs_qgroup_free_meta_prealloc(inode->root, qgroup_to_release);
+	else
+		btrfs_qgroup_convert_reserved_meta(inode->root,
+						   qgroup_to_release);
+}
+
+static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
+						 struct btrfs_inode *inode)
+{
+	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
+	u64 reserve_size = 0;
+	u64 qgroup_rsv_size = 0;
+	u64 csum_leaves;
+	unsigned outstanding_extents;
+
+	lockdep_assert_held(&inode->lock);
+	outstanding_extents = inode->outstanding_extents;
+	if (outstanding_extents)
+		reserve_size = btrfs_calc_trans_metadata_size(fs_info,
+						outstanding_extents + 1);
+	csum_leaves = btrfs_csum_bytes_to_leaves(fs_info,
+						 inode->csum_bytes);
+	reserve_size += btrfs_calc_trans_metadata_size(fs_info,
+						       csum_leaves);
+	/*
+	 * For qgroup rsv, the calculation is very simple:
+	 * account one nodesize for each outstanding extent
+	 *
+	 * This is overestimating in most cases.
+	 */
+	qgroup_rsv_size = (u64)outstanding_extents * fs_info->nodesize;
+
+	spin_lock(&block_rsv->lock);
+	block_rsv->size = reserve_size;
+	block_rsv->qgroup_rsv_size = qgroup_rsv_size;
+	spin_unlock(&block_rsv->lock);
+}
+
+static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
+				    u64 num_bytes, u64 *meta_reserve,
+				    u64 *qgroup_reserve)
+{
+	u64 nr_extents = count_max_extents(num_bytes);
+	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, num_bytes);
+
+	/* We add one for the inode update at finish ordered time */
+	*meta_reserve = btrfs_calc_trans_metadata_size(fs_info,
+						nr_extents + csum_leaves + 1);
+	*qgroup_reserve = nr_extents * fs_info->nodesize;
+}
+
+int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
+{
+	struct btrfs_root *root = inode->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
+	u64 meta_reserve, qgroup_reserve;
+	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
+	 * the middle of a transaction commit.  We also don't need the delalloc
+	 * mutex since we won't race with anybody.  We need this mostly to make
+	 * lockdep shut its filthy mouth.
+	 *
+	 * If we have a transaction open (can happen if we call truncate_block
+	 * from truncate), then we need FLUSH_LIMIT so we don't deadlock.
+	 */
+	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;
+
+		if (btrfs_transaction_in_commit(fs_info))
+			schedule_timeout(1);
+	}
+
+	if (delalloc_lock)
+		mutex_lock(&inode->delalloc_mutex);
+
+	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
+
+	/*
+	 * We always want to do it this way, every other way is wrong and ends
+	 * in tears.  Pre-reserving the amount we are going to add will always
+	 * be the right way, because otherwise if we have enough parallelism we
+	 * could end up with thousands of inodes all holding little bits of
+	 * reservations they were able to make previously and the only way to
+	 * reclaim that space is to ENOSPC out the operations and clear
+	 * everything out and try again, which is bad.  This way we just
+	 * over-reserve slightly, and clean up the mess when we are done.
+	 */
+	calc_inode_reservations(fs_info, num_bytes, &meta_reserve,
+				&qgroup_reserve);
+	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true);
+	if (ret)
+		goto out_fail;
+	ret = btrfs_reserve_metadata_bytes(root, block_rsv, meta_reserve,
+					   flush);
+	if (ret)
+		goto out_qgroup;
+
+	/*
+	 * Now we need to update our outstanding extents and csum bytes _first_
+	 * and then add the reservation to the block_rsv.  This keeps us from
+	 * racing with an ordered completion or some such that would think it
+	 * needs to free the reservation we just made.
+	 */
+	spin_lock(&inode->lock);
+	nr_extents = count_max_extents(num_bytes);
+	btrfs_mod_outstanding_extents(inode, nr_extents);
+	inode->csum_bytes += num_bytes;
+	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
+	spin_unlock(&inode->lock);
+
+	/* Now we can safely add our space to our block rsv */
+	btrfs_block_rsv_add_bytes(block_rsv, meta_reserve, false);
+	trace_btrfs_space_reservation(root->fs_info, "delalloc",
+				      btrfs_ino(inode), meta_reserve, 1);
+
+	spin_lock(&block_rsv->lock);
+	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:
+	btrfs_inode_rsv_release(inode, true);
+	if (delalloc_lock)
+		mutex_unlock(&inode->delalloc_mutex);
+	return ret;
+}
+
+/**
+ * btrfs_delalloc_release_metadata - release a metadata reservation for an inode
+ * @inode: the inode to release the reservation for.
+ * @num_bytes: the number of bytes we are releasing.
+ * @qgroup_free: free qgroup reservation or convert it to per-trans reservation
+ *
+ * This will release the metadata reservation for an inode.  This can be called
+ * once we complete IO for a given set of bytes to release their metadata
+ * reservations, or on error for the same reason.
+ */
+void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
+				     bool qgroup_free)
+{
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+
+	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
+	spin_lock(&inode->lock);
+	inode->csum_bytes -= num_bytes;
+	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
+	spin_unlock(&inode->lock);
+
+	if (btrfs_is_testing(fs_info))
+		return;
+
+	btrfs_inode_rsv_release(inode, qgroup_free);
+}
+
+/**
+ * btrfs_delalloc_release_extents - release our outstanding_extents
+ * @inode: the inode to balance the reservation for.
+ * @num_bytes: the number of bytes we originally reserved with
+ * @qgroup_free: do we need to free qgroup meta reservation or convert them.
+ *
+ * When we reserve space we increase outstanding_extents for the extents we may
+ * add.  Once we've set the range as delalloc or created our ordered extents we
+ * have outstanding_extents to track the real usage, so we use this to free our
+ * temporarily tracked outstanding_extents.  This _must_ be used in conjunction
+ * with btrfs_delalloc_reserve_metadata.
+ */
+void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
+				    bool qgroup_free)
+{
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	unsigned num_extents;
+
+	spin_lock(&inode->lock);
+	num_extents = count_max_extents(num_bytes);
+	btrfs_mod_outstanding_extents(inode, -num_extents);
+	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
+	spin_unlock(&inode->lock);
+
+	if (btrfs_is_testing(fs_info))
+		return;
+
+	btrfs_inode_rsv_release(inode, qgroup_free);
+}
+
+/**
+ * btrfs_delalloc_reserve_space - reserve data and metadata space for
+ * delalloc
+ * @inode: inode we're writing to
+ * @start: start range we are writing to
+ * @len: how long the range we are writing to
+ * @reserved: mandatory parameter, record actually reserved qgroup ranges of
+ * 	      current reservation.
+ *
+ * This will do the following things
+ *
+ * o reserve space in data space info for num bytes
+ *   and reserve precious corresponding qgroup space
+ *   (Done in check_data_free_space)
+ *
+ * o reserve space for metadata space, based on the number of outstanding
+ *   extents and how much csums will be needed
+ *   also reserve metadata space in a per root over-reserve method.
+ * o add to the inodes->delalloc_bytes
+ * o add it to the fs_info's delalloc inodes list.
+ *   (Above 3 all done in delalloc_reserve_metadata)
+ *
+ * Return 0 for success
+ * Return <0 for error(-ENOSPC or -EQUOT)
+ */
+int btrfs_delalloc_reserve_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len)
+{
+	int ret;
+
+	ret = btrfs_check_data_free_space(inode, reserved, start, len);
+	if (ret < 0)
+		return ret;
+	ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len);
+	if (ret < 0)
+		btrfs_free_reserved_data_space(inode, *reserved, start, len);
+	return ret;
+}
+
+/**
+ * btrfs_delalloc_release_space - release data and metadata space for delalloc
+ * @inode: inode we're releasing space for
+ * @start: start position of the space already reserved
+ * @len: the len of the space already reserved
+ * @release_bytes: the len of the space we consumed or didn't use
+ *
+ * This function will release the metadata space that was not used and will
+ * decrement ->delalloc_bytes and remove it from the fs_info delalloc_inodes
+ * list if there are no delalloc bytes left.
+ * Also it will handle the qgroup reserved space.
+ */
+void btrfs_delalloc_release_space(struct inode *inode,
+				  struct extent_changeset *reserved,
+				  u64 start, u64 len, bool qgroup_free)
+{
+	btrfs_delalloc_release_metadata(BTRFS_I(inode), len, qgroup_free);
+	btrfs_free_reserved_data_space(inode, reserved, start, len);
+}
diff --git a/fs/btrfs/delalloc-space.h b/fs/btrfs/delalloc-space.h
new file mode 100644
index 000000000000..8f7ceb264a30
--- /dev/null
+++ b/fs/btrfs/delalloc-space.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Facebook.  All rights reserved.
+ */
+
+#ifndef BTRFS_DELALLOC_SPACE_H
+#define BTRFS_DELALLOC_SPACE_H
+
+struct extent_changeset;
+
+int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes);
+int btrfs_check_data_free_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len);
+void btrfs_free_reserved_data_space(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len);
+void btrfs_delalloc_release_space(struct inode *inode,
+				  struct extent_changeset *reserved,
+				  u64 start, u64 len, bool qgroup_free);
+void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
+					    u64 len);
+void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
+				     bool qgroup_free);
+int btrfs_delalloc_reserve_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len);
+#endif /* BTRFS_DELALLOC_SPACE_H */
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 20b9b3284af2..c407e3188845 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -30,6 +30,7 @@
 #include "ref-verify.h"
 #include "space-info.h"
 #include "block-rsv.h"
+#include "delalloc-space.h"
 
 #undef SCRAMBLE_DELAYED_REFS
 
@@ -3867,206 +3868,6 @@ u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
 	return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
 }
 
-int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes)
-{
-	struct btrfs_root *root = inode->root;
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_space_info *data_sinfo = fs_info->data_sinfo;
-	u64 used;
-	int ret = 0;
-	int need_commit = 2;
-	int have_pinned_space;
-
-	/* make sure bytes are sectorsize aligned */
-	bytes = ALIGN(bytes, fs_info->sectorsize);
-
-	if (btrfs_is_free_space_inode(inode)) {
-		need_commit = 0;
-		ASSERT(current->journal_info);
-	}
-
-again:
-	/* make sure we have enough space to handle the data first */
-	spin_lock(&data_sinfo->lock);
-	used = btrfs_space_info_used(data_sinfo, true);
-
-	if (used + bytes > data_sinfo->total_bytes) {
-		struct btrfs_trans_handle *trans;
-
-		/*
-		 * if we don't have enough free bytes in this space then we need
-		 * to alloc a new chunk.
-		 */
-		if (!data_sinfo->full) {
-			u64 alloc_target;
-
-			data_sinfo->force_alloc = CHUNK_ALLOC_FORCE;
-			spin_unlock(&data_sinfo->lock);
-
-			alloc_target = btrfs_data_alloc_profile(fs_info);
-			/*
-			 * It is ugly that we don't call nolock join
-			 * transaction for the free space inode case here.
-			 * But it is safe because we only do the data space
-			 * reservation for the free space cache in the
-			 * transaction context, the common join transaction
-			 * just increase the counter of the current transaction
-			 * handler, doesn't try to acquire the trans_lock of
-			 * the fs.
-			 */
-			trans = btrfs_join_transaction(root);
-			if (IS_ERR(trans))
-				return PTR_ERR(trans);
-
-			ret = btrfs_chunk_alloc(trans, alloc_target,
-						CHUNK_ALLOC_NO_FORCE);
-			btrfs_end_transaction(trans);
-			if (ret < 0) {
-				if (ret != -ENOSPC)
-					return ret;
-				else {
-					have_pinned_space = 1;
-					goto commit_trans;
-				}
-			}
-
-			goto again;
-		}
-
-		/*
-		 * If we don't have enough pinned space to deal with this
-		 * allocation, and no removed chunk in current transaction,
-		 * don't bother committing the transaction.
-		 */
-		have_pinned_space = __percpu_counter_compare(
-			&data_sinfo->total_bytes_pinned,
-			used + bytes - data_sinfo->total_bytes,
-			BTRFS_TOTAL_BYTES_PINNED_BATCH);
-		spin_unlock(&data_sinfo->lock);
-
-		/* commit the current transaction and try again */
-commit_trans:
-		if (need_commit) {
-			need_commit--;
-
-			if (need_commit > 0) {
-				btrfs_start_delalloc_roots(fs_info, -1);
-				btrfs_wait_ordered_roots(fs_info, U64_MAX, 0,
-							 (u64)-1);
-			}
-
-			trans = btrfs_join_transaction(root);
-			if (IS_ERR(trans))
-				return PTR_ERR(trans);
-			if (have_pinned_space >= 0 ||
-			    test_bit(BTRFS_TRANS_HAVE_FREE_BGS,
-				     &trans->transaction->flags) ||
-			    need_commit > 0) {
-				ret = btrfs_commit_transaction(trans);
-				if (ret)
-					return ret;
-				/*
-				 * The cleaner kthread might still be doing iput
-				 * operations. Wait for it to finish so that
-				 * more space is released.  We don't need to
-				 * explicitly run the delayed iputs here because
-				 * the commit_transaction would have woken up
-				 * the cleaner.
-				 */
-				ret = btrfs_wait_on_delayed_iputs(fs_info);
-				if (ret)
-					return ret;
-				goto again;
-			} else {
-				btrfs_end_transaction(trans);
-			}
-		}
-
-		trace_btrfs_space_reservation(fs_info,
-					      "space_info:enospc",
-					      data_sinfo->flags, bytes, 1);
-		return -ENOSPC;
-	}
-	btrfs_space_info_update_bytes_may_use(fs_info, data_sinfo, bytes);
-	trace_btrfs_space_reservation(fs_info, "space_info",
-				      data_sinfo->flags, bytes, 1);
-	spin_unlock(&data_sinfo->lock);
-
-	return 0;
-}
-
-int btrfs_check_data_free_space(struct inode *inode,
-			struct extent_changeset **reserved, u64 start, u64 len)
-{
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	int ret;
-
-	/* align the range */
-	len = round_up(start + len, fs_info->sectorsize) -
-	      round_down(start, fs_info->sectorsize);
-	start = round_down(start, fs_info->sectorsize);
-
-	ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), len);
-	if (ret < 0)
-		return ret;
-
-	/* Use new btrfs_qgroup_reserve_data to reserve precious data space. */
-	ret = btrfs_qgroup_reserve_data(inode, reserved, start, len);
-	if (ret < 0)
-		btrfs_free_reserved_data_space_noquota(inode, start, len);
-	else
-		ret = 0;
-	return ret;
-}
-
-/*
- * Called if we need to clear a data reservation for this inode
- * Normally in a error case.
- *
- * This one will *NOT* use accurate qgroup reserved space API, just for case
- * which we can't sleep and is sure it won't affect qgroup reserved space.
- * Like clear_bit_hook().
- */
-void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
-					    u64 len)
-{
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_space_info *data_sinfo;
-
-	/* Make sure the range is aligned to sectorsize */
-	len = round_up(start + len, fs_info->sectorsize) -
-	      round_down(start, fs_info->sectorsize);
-	start = round_down(start, fs_info->sectorsize);
-
-	data_sinfo = fs_info->data_sinfo;
-	spin_lock(&data_sinfo->lock);
-	btrfs_space_info_update_bytes_may_use(fs_info, data_sinfo, -len);
-	trace_btrfs_space_reservation(fs_info, "space_info",
-				      data_sinfo->flags, len, 0);
-	spin_unlock(&data_sinfo->lock);
-}
-
-/*
- * Called if we need to clear a data reservation for this inode
- * Normally in a error case.
- *
- * This one will handle the per-inode data rsv map for accurate reserved
- * space framework.
- */
-void btrfs_free_reserved_data_space(struct inode *inode,
-			struct extent_changeset *reserved, u64 start, u64 len)
-{
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-
-	/* Make sure the range is aligned to sectorsize */
-	len = round_up(start + len, root->fs_info->sectorsize) -
-	      round_down(start, root->fs_info->sectorsize);
-	start = round_down(start, root->fs_info->sectorsize);
-
-	btrfs_free_reserved_data_space_noquota(inode, start, len);
-	btrfs_qgroup_free_data(inode, reserved, start, len);
-}
-
 static void force_metadata_allocation(struct btrfs_fs_info *info)
 {
 	struct list_head *head = &info->space_info;
@@ -4306,41 +4107,6 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 	return ret;
 }
 
-/**
- * btrfs_inode_rsv_release - release any excessive reservation.
- * @inode - the inode we need to release from.
- * @qgroup_free - free or convert qgroup meta.
- *   Unlike normal operation, qgroup meta reservation needs to know if we are
- *   freeing qgroup reservation or just converting it into per-trans.  Normally
- *   @qgroup_free is true for error handling, and false for normal release.
- *
- * This is the same as btrfs_block_rsv_release, except that it handles the
- * tracepoint for the reservation.
- */
-static void btrfs_inode_rsv_release(struct btrfs_inode *inode, bool qgroup_free)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
-	u64 released = 0;
-	u64 qgroup_to_release = 0;
-
-	/*
-	 * Since we statically set the block_rsv->size we just want to say we
-	 * are releasing 0 bytes, and then we'll just get the reservation over
-	 * the size free'd.
-	 */
-	released = __btrfs_block_rsv_release(fs_info, block_rsv, 0,
-					     &qgroup_to_release);
-	if (released > 0)
-		trace_btrfs_space_reservation(fs_info, "delalloc",
-					      btrfs_ino(inode), released, 0);
-	if (qgroup_free)
-		btrfs_qgroup_free_meta_prealloc(inode->root, qgroup_to_release);
-	else
-		btrfs_qgroup_convert_reserved_meta(inode->root,
-						   qgroup_to_release);
-}
-
 /*
  * btrfs_subvolume_reserve_metadata() - reserve space for subvolume operation
  * root: the root of the parent directory
@@ -4395,256 +4161,6 @@ void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
 	btrfs_block_rsv_release(fs_info, rsv, (u64)-1);
 }
 
-static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
-						 struct btrfs_inode *inode)
-{
-	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
-	u64 reserve_size = 0;
-	u64 qgroup_rsv_size = 0;
-	u64 csum_leaves;
-	unsigned outstanding_extents;
-
-	lockdep_assert_held(&inode->lock);
-	outstanding_extents = inode->outstanding_extents;
-	if (outstanding_extents)
-		reserve_size = btrfs_calc_trans_metadata_size(fs_info,
-						outstanding_extents + 1);
-	csum_leaves = btrfs_csum_bytes_to_leaves(fs_info,
-						 inode->csum_bytes);
-	reserve_size += btrfs_calc_trans_metadata_size(fs_info,
-						       csum_leaves);
-	/*
-	 * For qgroup rsv, the calculation is very simple:
-	 * account one nodesize for each outstanding extent
-	 *
-	 * This is overestimating in most cases.
-	 */
-	qgroup_rsv_size = (u64)outstanding_extents * fs_info->nodesize;
-
-	spin_lock(&block_rsv->lock);
-	block_rsv->size = reserve_size;
-	block_rsv->qgroup_rsv_size = qgroup_rsv_size;
-	spin_unlock(&block_rsv->lock);
-}
-
-static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
-				    u64 num_bytes, u64 *meta_reserve,
-				    u64 *qgroup_reserve)
-{
-	u64 nr_extents = count_max_extents(num_bytes);
-	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, num_bytes);
-
-	/* We add one for the inode update at finish ordered time */
-	*meta_reserve = btrfs_calc_trans_metadata_size(fs_info,
-						nr_extents + csum_leaves + 1);
-	*qgroup_reserve = nr_extents * fs_info->nodesize;
-}
-
-int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
-{
-	struct btrfs_root *root = inode->root;
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
-	u64 meta_reserve, qgroup_reserve;
-	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
-	 * the middle of a transaction commit.  We also don't need the delalloc
-	 * mutex since we won't race with anybody.  We need this mostly to make
-	 * lockdep shut its filthy mouth.
-	 *
-	 * If we have a transaction open (can happen if we call truncate_block
-	 * from truncate), then we need FLUSH_LIMIT so we don't deadlock.
-	 */
-	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;
-
-		if (btrfs_transaction_in_commit(fs_info))
-			schedule_timeout(1);
-	}
-
-	if (delalloc_lock)
-		mutex_lock(&inode->delalloc_mutex);
-
-	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
-
-	/*
-	 * We always want to do it this way, every other way is wrong and ends
-	 * in tears.  Pre-reserving the amount we are going to add will always
-	 * be the right way, because otherwise if we have enough parallelism we
-	 * could end up with thousands of inodes all holding little bits of
-	 * reservations they were able to make previously and the only way to
-	 * reclaim that space is to ENOSPC out the operations and clear
-	 * everything out and try again, which is bad.  This way we just
-	 * over-reserve slightly, and clean up the mess when we are done.
-	 */
-	calc_inode_reservations(fs_info, num_bytes, &meta_reserve,
-				&qgroup_reserve);
-	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true);
-	if (ret)
-		goto out_fail;
-	ret = btrfs_reserve_metadata_bytes(root, block_rsv, meta_reserve,
-					   flush);
-	if (ret)
-		goto out_qgroup;
-
-	/*
-	 * Now we need to update our outstanding extents and csum bytes _first_
-	 * and then add the reservation to the block_rsv.  This keeps us from
-	 * racing with an ordered completion or some such that would think it
-	 * needs to free the reservation we just made.
-	 */
-	spin_lock(&inode->lock);
-	nr_extents = count_max_extents(num_bytes);
-	btrfs_mod_outstanding_extents(inode, nr_extents);
-	inode->csum_bytes += num_bytes;
-	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
-	spin_unlock(&inode->lock);
-
-	/* Now we can safely add our space to our block rsv */
-	btrfs_block_rsv_add_bytes(block_rsv, meta_reserve, false);
-	trace_btrfs_space_reservation(root->fs_info, "delalloc",
-				      btrfs_ino(inode), meta_reserve, 1);
-
-	spin_lock(&block_rsv->lock);
-	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:
-	btrfs_inode_rsv_release(inode, true);
-	if (delalloc_lock)
-		mutex_unlock(&inode->delalloc_mutex);
-	return ret;
-}
-
-/**
- * btrfs_delalloc_release_metadata - release a metadata reservation for an inode
- * @inode: the inode to release the reservation for.
- * @num_bytes: the number of bytes we are releasing.
- * @qgroup_free: free qgroup reservation or convert it to per-trans reservation
- *
- * This will release the metadata reservation for an inode.  This can be called
- * once we complete IO for a given set of bytes to release their metadata
- * reservations, or on error for the same reason.
- */
-void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
-				     bool qgroup_free)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-
-	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
-	spin_lock(&inode->lock);
-	inode->csum_bytes -= num_bytes;
-	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
-	spin_unlock(&inode->lock);
-
-	if (btrfs_is_testing(fs_info))
-		return;
-
-	btrfs_inode_rsv_release(inode, qgroup_free);
-}
-
-/**
- * btrfs_delalloc_release_extents - release our outstanding_extents
- * @inode: the inode to balance the reservation for.
- * @num_bytes: the number of bytes we originally reserved with
- * @qgroup_free: do we need to free qgroup meta reservation or convert them.
- *
- * When we reserve space we increase outstanding_extents for the extents we may
- * add.  Once we've set the range as delalloc or created our ordered extents we
- * have outstanding_extents to track the real usage, so we use this to free our
- * temporarily tracked outstanding_extents.  This _must_ be used in conjunction
- * with btrfs_delalloc_reserve_metadata.
- */
-void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
-				    bool qgroup_free)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	unsigned num_extents;
-
-	spin_lock(&inode->lock);
-	num_extents = count_max_extents(num_bytes);
-	btrfs_mod_outstanding_extents(inode, -num_extents);
-	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
-	spin_unlock(&inode->lock);
-
-	if (btrfs_is_testing(fs_info))
-		return;
-
-	btrfs_inode_rsv_release(inode, qgroup_free);
-}
-
-/**
- * btrfs_delalloc_reserve_space - reserve data and metadata space for
- * delalloc
- * @inode: inode we're writing to
- * @start: start range we are writing to
- * @len: how long the range we are writing to
- * @reserved: mandatory parameter, record actually reserved qgroup ranges of
- * 	      current reservation.
- *
- * This will do the following things
- *
- * o reserve space in data space info for num bytes
- *   and reserve precious corresponding qgroup space
- *   (Done in check_data_free_space)
- *
- * o reserve space for metadata space, based on the number of outstanding
- *   extents and how much csums will be needed
- *   also reserve metadata space in a per root over-reserve method.
- * o add to the inodes->delalloc_bytes
- * o add it to the fs_info's delalloc inodes list.
- *   (Above 3 all done in delalloc_reserve_metadata)
- *
- * Return 0 for success
- * Return <0 for error(-ENOSPC or -EQUOT)
- */
-int btrfs_delalloc_reserve_space(struct inode *inode,
-			struct extent_changeset **reserved, u64 start, u64 len)
-{
-	int ret;
-
-	ret = btrfs_check_data_free_space(inode, reserved, start, len);
-	if (ret < 0)
-		return ret;
-	ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len);
-	if (ret < 0)
-		btrfs_free_reserved_data_space(inode, *reserved, start, len);
-	return ret;
-}
-
-/**
- * btrfs_delalloc_release_space - release data and metadata space for delalloc
- * @inode: inode we're releasing space for
- * @start: start position of the space already reserved
- * @len: the len of the space already reserved
- * @release_bytes: the len of the space we consumed or didn't use
- *
- * This function will release the metadata space that was not used and will
- * decrement ->delalloc_bytes and remove it from the fs_info delalloc_inodes
- * list if there are no delalloc bytes left.
- * Also it will handle the qgroup reserved space.
- */
-void btrfs_delalloc_release_space(struct inode *inode,
-				  struct extent_changeset *reserved,
-				  u64 start, u64 len, bool qgroup_free)
-{
-	btrfs_delalloc_release_metadata(BTRFS_I(inode), len, qgroup_free);
-	btrfs_free_reserved_data_space(inode, reserved, start, len);
-}
-
 static int update_block_group(struct btrfs_trans_handle *trans,
 			      u64 bytenr, u64 num_bytes, int alloc)
 {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 7c1e2984bb72..c41188df562d 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -26,6 +26,7 @@
 #include "volumes.h"
 #include "qgroup.h"
 #include "compression.h"
+#include "delalloc-space.h"
 
 static struct kmem_cache *btrfs_inode_defrag_cachep;
 /*
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 390cd3d7d5ea..062be9dde4c6 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -19,6 +19,7 @@
 #include "inode-map.h"
 #include "volumes.h"
 #include "space-info.h"
+#include "delalloc-space.h"
 
 #define BITS_PER_BITMAP		(PAGE_SIZE * 8UL)
 #define MAX_CACHE_BYTES_PER_GIG	SZ_32K
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index ffca2abf13d0..2e8bb402050b 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -11,6 +11,7 @@
 #include "free-space-cache.h"
 #include "inode-map.h"
 #include "transaction.h"
+#include "delalloc-space.h"
 
 static int caching_kthread(void *data)
 {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c311bf6d52f4..8e389c51f4e9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -47,6 +47,7 @@
 #include "props.h"
 #include "qgroup.h"
 #include "dedupe.h"
+#include "delalloc-space.h"
 
 struct btrfs_iget_args {
 	struct btrfs_key *location;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 1af3af3d708c..bae04a4f09d2 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -44,6 +44,7 @@
 #include "tree-log.h"
 #include "compression.h"
 #include "space-info.h"
+#include "delalloc-space.h"
 
 #ifdef CONFIG_64BIT
 /* If we have a 32-bit userspace and 64-bit kernel, then the UAPI
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 3f67b7827393..1744ba8b2754 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -13,6 +13,7 @@
 #include "extent_io.h"
 #include "disk-io.h"
 #include "compression.h"
+#include "delalloc-space.h"
 
 static struct kmem_cache *btrfs_ordered_extent_cache;
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 22a3c69864fa..7f219851fa23 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -20,6 +20,7 @@
 #include "inode-map.h"
 #include "qgroup.h"
 #include "print-tree.h"
+#include "delalloc-space.h"
 
 /*
  * backref_node, mapping_node and tree_block start with this
-- 
2.14.3

[PATCH 4/4] btrfs: move the subvolume reservation stuff out of extent-tree.c

[Josef Bacik]

This is just two functions, put it in root-tree.c since it involves root
items.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
---
 fs/btrfs/extent-tree.c | 54 ------------------------------------------------
 fs/btrfs/root-tree.c   | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 56 insertions(+), 54 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c407e3188845..a0115e019ee8 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4107,60 +4107,6 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 	return ret;
 }
 
-/*
- * btrfs_subvolume_reserve_metadata() - reserve space for subvolume operation
- * root: the root of the parent directory
- * rsv: block reservation
- * items: the number of items that we need do reservation
- * use_global_rsv: allow fallback to the global block reservation
- *
- * This function is used to reserve the space for snapshot/subvolume
- * creation and deletion. Those operations are different with the
- * common file/directory operations, they change two fs/file trees
- * and root tree, the number of items that the qgroup reserves is
- * different with the free space reservation. So we can not use
- * the space reservation mechanism in start_transaction().
- */
-int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
-				     struct btrfs_block_rsv *rsv, int items,
-				     bool use_global_rsv)
-{
-	u64 qgroup_num_bytes = 0;
-	u64 num_bytes;
-	int ret;
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
-
-	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
-		/* One for parent inode, two for dir entries */
-		qgroup_num_bytes = 3 * fs_info->nodesize;
-		ret = btrfs_qgroup_reserve_meta_prealloc(root,
-				qgroup_num_bytes, true);
-		if (ret)
-			return ret;
-	}
-
-	num_bytes = btrfs_calc_trans_metadata_size(fs_info, items);
-	rsv->space_info = btrfs_find_space_info(fs_info,
-					    BTRFS_BLOCK_GROUP_METADATA);
-	ret = btrfs_block_rsv_add(root, rsv, num_bytes,
-				  BTRFS_RESERVE_FLUSH_ALL);
-
-	if (ret == -ENOSPC && use_global_rsv)
-		ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes, true);
-
-	if (ret && qgroup_num_bytes)
-		btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes);
-
-	return ret;
-}
-
-void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
-				      struct btrfs_block_rsv *rsv)
-{
-	btrfs_block_rsv_release(fs_info, rsv, (u64)-1);
-}
-
 static int update_block_group(struct btrfs_trans_handle *trans,
 			      u64 bytenr, u64 num_bytes, int alloc)
 {
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 22124122728c..47733fb55df7 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -9,6 +9,8 @@
 #include "transaction.h"
 #include "disk-io.h"
 #include "print-tree.h"
+#include "qgroup.h"
+#include "space-info.h"
 
 /*
  * Read a root item from the tree. In case we detect a root item smaller then
@@ -497,3 +499,57 @@ void btrfs_update_root_times(struct btrfs_trans_handle *trans,
 	btrfs_set_stack_timespec_nsec(&item->ctime, ct.tv_nsec);
 	spin_unlock(&root->root_item_lock);
 }
+
+/*
+ * btrfs_subvolume_reserve_metadata() - reserve space for subvolume operation
+ * root: the root of the parent directory
+ * rsv: block reservation
+ * items: the number of items that we need do reservation
+ * use_global_rsv: allow fallback to the global block reservation
+ *
+ * This function is used to reserve the space for snapshot/subvolume
+ * creation and deletion. Those operations are different with the
+ * common file/directory operations, they change two fs/file trees
+ * and root tree, the number of items that the qgroup reserves is
+ * different with the free space reservation. So we can not use
+ * the space reservation mechanism in start_transaction().
+ */
+int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
+				     struct btrfs_block_rsv *rsv, int items,
+				     bool use_global_rsv)
+{
+	u64 qgroup_num_bytes = 0;
+	u64 num_bytes;
+	int ret;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
+
+	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
+		/* One for parent inode, two for dir entries */
+		qgroup_num_bytes = 3 * fs_info->nodesize;
+		ret = btrfs_qgroup_reserve_meta_prealloc(root,
+				qgroup_num_bytes, true);
+		if (ret)
+			return ret;
+	}
+
+	num_bytes = btrfs_calc_trans_metadata_size(fs_info, items);
+	rsv->space_info = btrfs_find_space_info(fs_info,
+					    BTRFS_BLOCK_GROUP_METADATA);
+	ret = btrfs_block_rsv_add(root, rsv, num_bytes,
+				  BTRFS_RESERVE_FLUSH_ALL);
+
+	if (ret == -ENOSPC && use_global_rsv)
+		ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes, true);
+
+	if (ret && qgroup_num_bytes)
+		btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes);
+
+	return ret;
+}
+
+void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
+				      struct btrfs_block_rsv *rsv)
+{
+	btrfs_block_rsv_release(fs_info, rsv, (u64)-1);
+}
-- 
2.14.3