Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

115 files changed, 1929 insertions, 1066 deletions

diff --git a/fs/btrfs/accessors.c b/fs/btrfs/accessors.c
index 1925a0919c..79026917db 100644
--- a/fs/btrfs/accessors.c
+++ b/fs/btrfs/accessors.c
@@ -5,7 +5,8 @@
 
 #include <asm/unaligned.h>
 #include "messages.h"
-#include "ctree.h"
+#include "extent_io.h"
+#include "fs.h"
 #include "accessors.h"
 
 static bool check_setget_bounds(const struct extent_buffer *eb,
@@ -63,8 +64,8 @@ u##bits btrfs_get_token_##bits(struct btrfs_map_token *token,		\
 	const unsigned long idx = get_eb_folio_index(token->eb, member_offset); \
 	const unsigned long oil = get_eb_offset_in_folio(token->eb,	\
 							 member_offset);\
-	const int unit_size = folio_size(token->eb->folios[0]);		\
-	const int unit_shift = folio_shift(token->eb->folios[0]);	\
+	const int unit_size = token->eb->folio_size;			\
+	const int unit_shift = token->eb->folio_shift;			\
 	const int size = sizeof(u##bits);				\
 	u8 lebytes[sizeof(u##bits)];					\
 	const int part = unit_size - oil;				\
@@ -94,7 +95,7 @@ u##bits btrfs_get_##bits(const struct extent_buffer *eb,		\
 	const unsigned long idx = get_eb_folio_index(eb, member_offset);\
 	const unsigned long oil = get_eb_offset_in_folio(eb,		\
 							 member_offset);\
-	const int unit_size = folio_size(eb->folios[0]);		\
+	const int unit_size = eb->folio_size;				\
 	char *kaddr = folio_address(eb->folios[idx]);			\
 	const int size = sizeof(u##bits);				\
 	const int part = unit_size - oil;				\
@@ -117,8 +118,8 @@ void btrfs_set_token_##bits(struct btrfs_map_token *token,		\
 	const unsigned long idx = get_eb_folio_index(token->eb, member_offset); \
 	const unsigned long oil = get_eb_offset_in_folio(token->eb,	\
 							 member_offset);\
-	const int unit_size = folio_size(token->eb->folios[0]);		\
-	const int unit_shift = folio_shift(token->eb->folios[0]);	\
+	const int unit_size = token->eb->folio_size;			\
+	const int unit_shift = token->eb->folio_shift;			\
 	const int size = sizeof(u##bits);				\
 	u8 lebytes[sizeof(u##bits)];					\
 	const int part = unit_size - oil;				\
@@ -151,7 +152,7 @@ void btrfs_set_##bits(const struct extent_buffer *eb, void *ptr,	\
 	const unsigned long idx = get_eb_folio_index(eb, member_offset);\
 	const unsigned long oil = get_eb_offset_in_folio(eb,		\
 							 member_offset);\
-	const int unit_size = folio_size(eb->folios[0]);		\
+	const int unit_size = eb->folio_size;				\
 	char *kaddr = folio_address(eb->folios[idx]);			\
 	const int size = sizeof(u##bits);				\
 	const int part = unit_size - oil;				\
diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h
index ed7aa32972..6fce3e8d3d 100644
--- a/fs/btrfs/accessors.h
+++ b/fs/btrfs/accessors.h
@@ -3,8 +3,17 @@
 #ifndef BTRFS_ACCESSORS_H
 #define BTRFS_ACCESSORS_H
 
-#include <linux/stddef.h>
 #include <asm/unaligned.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/align.h>
+#include <linux/build_bug.h>
+#include <linux/compiler.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <uapi/linux/btrfs_tree.h>
+
+struct extent_buffer;
 
 struct btrfs_map_token {
 	struct extent_buffer *eb;
@@ -844,45 +853,6 @@ static inline void btrfs_set_balance_sys(struct extent_buffer *eb,
 	write_eb_member(eb, bi, struct btrfs_balance_item, sys, ba);
 }
 
-static inline void btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
-			       const struct btrfs_disk_balance_args *disk)
-{
-	memset(cpu, 0, sizeof(*cpu));
-
-	cpu->profiles = le64_to_cpu(disk->profiles);
-	cpu->usage = le64_to_cpu(disk->usage);
-	cpu->devid = le64_to_cpu(disk->devid);
-	cpu->pstart = le64_to_cpu(disk->pstart);
-	cpu->pend = le64_to_cpu(disk->pend);
-	cpu->vstart = le64_to_cpu(disk->vstart);
-	cpu->vend = le64_to_cpu(disk->vend);
-	cpu->target = le64_to_cpu(disk->target);
-	cpu->flags = le64_to_cpu(disk->flags);
-	cpu->limit = le64_to_cpu(disk->limit);
-	cpu->stripes_min = le32_to_cpu(disk->stripes_min);
-	cpu->stripes_max = le32_to_cpu(disk->stripes_max);
-}
-
-static inline void btrfs_cpu_balance_args_to_disk(
-				struct btrfs_disk_balance_args *disk,
-				const struct btrfs_balance_args *cpu)
-{
-	memset(disk, 0, sizeof(*disk));
-
-	disk->profiles = cpu_to_le64(cpu->profiles);
-	disk->usage = cpu_to_le64(cpu->usage);
-	disk->devid = cpu_to_le64(cpu->devid);
-	disk->pstart = cpu_to_le64(cpu->pstart);
-	disk->pend = cpu_to_le64(cpu->pend);
-	disk->vstart = cpu_to_le64(cpu->vstart);
-	disk->vend = cpu_to_le64(cpu->vend);
-	disk->target = cpu_to_le64(cpu->target);
-	disk->flags = cpu_to_le64(cpu->flags);
-	disk->limit = cpu_to_le64(cpu->limit);
-	disk->stripes_min = cpu_to_le32(cpu->stripes_min);
-	disk->stripes_max = cpu_to_le32(cpu->stripes_max);
-}
-
 /* struct btrfs_super_block */
 BTRFS_SETGET_STACK_FUNCS(super_bytenr, struct btrfs_super_block, bytenr, 64);
 BTRFS_SETGET_STACK_FUNCS(super_flags, struct btrfs_super_block, flags, 64);
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 7427449a04..e0ba00d64e 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -12,7 +12,6 @@
 #include <linux/sched/mm.h>
 #include <linux/slab.h>
 #include "ctree.h"
-#include "btrfs_inode.h"
 #include "xattr.h"
 #include "acl.h"
 
diff --git a/fs/btrfs/acl.h b/fs/btrfs/acl.h
index a270e71ec0..48b9ddae4a 100644
--- a/fs/btrfs/acl.h
+++ b/fs/btrfs/acl.h
@@ -3,8 +3,15 @@
 #ifndef BTRFS_ACL_H
 #define BTRFS_ACL_H
 
+struct posix_acl;
+struct inode;
+struct btrfs_trans_handle;
+
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
 
+struct mnt_idmap;
+struct dentry;
+
 struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu);
 int btrfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		  struct posix_acl *acl, int type);
@@ -13,6 +20,10 @@ int __btrfs_set_acl(struct btrfs_trans_handle *trans, struct inode *inode,
 
 #else
 
+#include <linux/errno.h>
+
+struct btrfs_trans_handle;
+
 #define btrfs_get_acl NULL
 #define btrfs_set_acl NULL
 static inline int __btrfs_set_acl(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 9e261aac67..361a866c19 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -11,7 +11,6 @@
 #include <linux/freezer.h>
 #include <trace/events/btrfs.h>
 #include "async-thread.h"
-#include "ctree.h"
 
 enum {
 	WORK_DONE_BIT,
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 62b8a0d578..04c2f31758 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -7,11 +7,14 @@
 #ifndef BTRFS_ASYNC_THREAD_H
 #define BTRFS_ASYNC_THREAD_H
 
+#include <linux/compiler_types.h>
 #include <linux/workqueue.h>
+#include <linux/list.h>
 
 struct btrfs_fs_info;
 struct btrfs_workqueue;
 struct btrfs_work;
+
 typedef void (*btrfs_func_t)(struct btrfs_work *arg);
 typedef void (*btrfs_ordered_func_t)(struct btrfs_work *arg, bool);
 
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index fc0930dd92..58110c9686 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -198,10 +198,7 @@ static struct kmem_cache *btrfs_prelim_ref_cache;
 int __init btrfs_prelim_ref_init(void)
 {
 	btrfs_prelim_ref_cache = kmem_cache_create("btrfs_prelim_ref",
-					sizeof(struct prelim_ref),
-					0,
-					SLAB_MEM_SPREAD,
-					NULL);
+					sizeof(struct prelim_ref), 0, 0, NULL);
 	if (!btrfs_prelim_ref_cache)
 		return -ENOMEM;
 	return 0;
@@ -1036,8 +1033,6 @@ static int add_inline_refs(struct btrfs_backref_walk_ctx *ctx,
 	slot = path->slots[0];
 
 	item_size = btrfs_item_size(leaf, slot);
-	BUG_ON(item_size < sizeof(*ei));
-
 	ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
 
 	if (ctx->check_extent_item) {
@@ -1435,8 +1430,10 @@ again:
 	if (ret < 0)
 		goto out;
 	if (ret == 0) {
-		/* This shouldn't happen, indicates a bug or fs corruption. */
-		ASSERT(ret != 0);
+		/*
+		 * Key with offset -1 found, there would have to exist an extent
+		 * item with such offset, but this is out of the valid range.
+		 */
 		ret = -EUCLEAN;
 		goto out;
 	}
@@ -2225,6 +2222,13 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
 	if (ret < 0)
 		return ret;
+	if (ret == 0) {
+		/*
+		 * Key with offset -1 found, there would have to exist an extent
+		 * item with such offset, but this is out of the valid range.
+		 */
+		return -EUCLEAN;
+	}
 
 	ret = btrfs_previous_extent_item(extent_root, path, 0);
 	if (ret) {
@@ -2247,7 +2251,6 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 
 	eb = path->nodes[0];
 	item_size = btrfs_item_size(eb, path->slots[0]);
-	BUG_ON(item_size < sizeof(*ei));
 
 	ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
 	flags = btrfs_extent_flags(eb, ei);
@@ -2844,6 +2847,16 @@ struct btrfs_backref_iter *btrfs_backref_iter_alloc(struct btrfs_fs_info *fs_inf
 	return ret;
 }
 
+static void btrfs_backref_iter_release(struct btrfs_backref_iter *iter)
+{
+	iter->bytenr = 0;
+	iter->item_ptr = 0;
+	iter->cur_ptr = 0;
+	iter->end_ptr = 0;
+	btrfs_release_path(iter->path);
+	memset(&iter->cur_key, 0, sizeof(iter->cur_key));
+}
+
 int btrfs_backref_iter_start(struct btrfs_backref_iter *iter, u64 bytenr)
 {
 	struct btrfs_fs_info *fs_info = iter->fs_info;
@@ -2862,6 +2875,10 @@ int btrfs_backref_iter_start(struct btrfs_backref_iter *iter, u64 bytenr)
 	if (ret < 0)
 		return ret;
 	if (ret == 0) {
+		/*
+		 * Key with offset -1 found, there would have to exist an extent
+		 * item with such offset, but this is out of the valid range.
+		 */
 		ret = -EUCLEAN;
 		goto release;
 	}
@@ -2932,6 +2949,14 @@ release:
 	return ret;
 }
 
+static bool btrfs_backref_iter_is_inline_ref(struct btrfs_backref_iter *iter)
+{
+	if (iter->cur_key.type == BTRFS_EXTENT_ITEM_KEY ||
+	    iter->cur_key.type == BTRFS_METADATA_ITEM_KEY)
+		return true;
+	return false;
+}
+
 /*
  * Go to the next backref item of current bytenr, can be either inlined or
  * keyed.
@@ -2944,7 +2969,7 @@ release:
  */
 int btrfs_backref_iter_next(struct btrfs_backref_iter *iter)
 {
-	struct extent_buffer *eb = btrfs_backref_get_eb(iter);
+	struct extent_buffer *eb = iter->path->nodes[0];
 	struct btrfs_root *extent_root;
 	struct btrfs_path *path = iter->path;
 	struct btrfs_extent_inline_ref *iref;
@@ -3032,6 +3057,19 @@ struct btrfs_backref_node *btrfs_backref_alloc_node(
 	return node;
 }
 
+void btrfs_backref_free_node(struct btrfs_backref_cache *cache,
+			     struct btrfs_backref_node *node)
+{
+	if (node) {
+		ASSERT(list_empty(&node->list));
+		ASSERT(list_empty(&node->lower));
+		ASSERT(node->eb == NULL);
+		cache->nr_nodes--;
+		btrfs_put_root(node->root);
+		kfree(node);
+	}
+}
+
 struct btrfs_backref_edge *btrfs_backref_alloc_edge(
 		struct btrfs_backref_cache *cache)
 {
@@ -3043,6 +3081,52 @@ struct btrfs_backref_edge *btrfs_backref_alloc_edge(
 	return edge;
 }
 
+void btrfs_backref_free_edge(struct btrfs_backref_cache *cache,
+			     struct btrfs_backref_edge *edge)
+{
+	if (edge) {
+		cache->nr_edges--;
+		kfree(edge);
+	}
+}
+
+void btrfs_backref_unlock_node_buffer(struct btrfs_backref_node *node)
+{
+	if (node->locked) {
+		btrfs_tree_unlock(node->eb);
+		node->locked = 0;
+	}
+}
+
+void btrfs_backref_drop_node_buffer(struct btrfs_backref_node *node)
+{
+	if (node->eb) {
+		btrfs_backref_unlock_node_buffer(node);
+		free_extent_buffer(node->eb);
+		node->eb = NULL;
+	}
+}
+
+/*
+ * Drop the backref node from cache without cleaning up its children
+ * edges.
+ *
+ * This can only be called on node without parent edges.
+ * The children edges are still kept as is.
+ */
+void btrfs_backref_drop_node(struct btrfs_backref_cache *tree,
+			     struct btrfs_backref_node *node)
+{
+	ASSERT(list_empty(&node->upper));
+
+	btrfs_backref_drop_node_buffer(node);
+	list_del_init(&node->list);
+	list_del_init(&node->lower);
+	if (!RB_EMPTY_NODE(&node->rb_node))
+		rb_erase(&node->rb_node, &tree->rb_root);
+	btrfs_backref_free_node(tree, node);
+}
+
 /*
  * Drop the backref node from cache, also cleaning up all its
  * upper edges and any uncached nodes in the path.
@@ -3114,6 +3198,19 @@ void btrfs_backref_release_cache(struct btrfs_backref_cache *cache)
 	ASSERT(!cache->nr_edges);
 }
 
+void btrfs_backref_link_edge(struct btrfs_backref_edge *edge,
+			     struct btrfs_backref_node *lower,
+			     struct btrfs_backref_node *upper,
+			     int link_which)
+{
+	ASSERT(upper && lower && upper->level == lower->level + 1);
+	edge->node[LOWER] = lower;
+	edge->node[UPPER] = upper;
+	if (link_which & LINK_LOWER)
+		list_add_tail(&edge->list[LOWER], &lower->upper);
+	if (link_which & LINK_UPPER)
+		list_add_tail(&edge->list[UPPER], &upper->lower);
+}
 /*
  * Handle direct tree backref
  *
@@ -3422,7 +3519,7 @@ int btrfs_backref_add_tree_node(struct btrfs_trans_handle *trans,
 		int type;
 
 		cond_resched();
-		eb = btrfs_backref_get_eb(iter);
+		eb = iter->path->nodes[0];
 
 		key.objectid = iter->bytenr;
 		if (btrfs_backref_iter_is_inline_ref(iter)) {
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index ab4ca0eda6..e8c22cccb5 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -6,11 +6,23 @@
 #ifndef BTRFS_BACKREF_H
 #define BTRFS_BACKREF_H
 
-#include <linux/btrfs.h>
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <uapi/linux/btrfs.h>
+#include <uapi/linux/btrfs_tree.h>
 #include "messages.h"
-#include "ulist.h"
+#include "locking.h"
 #include "disk-io.h"
 #include "extent_io.h"
+#include "ctree.h"
+
+struct extent_inode_elem;
+struct ulist;
+struct btrfs_extent_item;
+struct btrfs_trans_handle;
+struct btrfs_fs_info;
 
 /*
  * Used by implementations of iterate_extent_inodes_t (see definition below) to
@@ -271,22 +283,6 @@ struct btrfs_backref_iter {
 
 struct btrfs_backref_iter *btrfs_backref_iter_alloc(struct btrfs_fs_info *fs_info);
 
-static inline void btrfs_backref_iter_free(struct btrfs_backref_iter *iter)
-{
-	if (!iter)
-		return;
-	btrfs_free_path(iter->path);
-	kfree(iter);
-}
-
-static inline struct extent_buffer *btrfs_backref_get_eb(
-		struct btrfs_backref_iter *iter)
-{
-	if (!iter)
-		return NULL;
-	return iter->path->nodes[0];
-}
-
 /*
  * For metadata with EXTENT_ITEM key (non-skinny) case, the first inline data
  * is btrfs_tree_block_info, without a btrfs_extent_inline_ref header.
@@ -306,25 +302,6 @@ int btrfs_backref_iter_start(struct btrfs_backref_iter *iter, u64 bytenr);
 
 int btrfs_backref_iter_next(struct btrfs_backref_iter *iter);
 
-static inline bool btrfs_backref_iter_is_inline_ref(
-		struct btrfs_backref_iter *iter)
-{
-	if (iter->cur_key.type == BTRFS_EXTENT_ITEM_KEY ||
-	    iter->cur_key.type == BTRFS_METADATA_ITEM_KEY)
-		return true;
-	return false;
-}
-
-static inline void btrfs_backref_iter_release(struct btrfs_backref_iter *iter)
-{
-	iter->bytenr = 0;
-	iter->item_ptr = 0;
-	iter->cur_ptr = 0;
-	iter->end_ptr = 0;
-	btrfs_release_path(iter->path);
-	memset(&iter->cur_key, 0, sizeof(iter->cur_key));
-}
-
 /*
  * Backref cache related structures
  *
@@ -452,83 +429,22 @@ struct btrfs_backref_edge *btrfs_backref_alloc_edge(
 
 #define		LINK_LOWER	(1 << 0)
 #define		LINK_UPPER	(1 << 1)
-static inline void btrfs_backref_link_edge(struct btrfs_backref_edge *edge,
-					   struct btrfs_backref_node *lower,
-					   struct btrfs_backref_node *upper,
-					   int link_which)
-{
-	ASSERT(upper && lower && upper->level == lower->level + 1);
-	edge->node[LOWER] = lower;
-	edge->node[UPPER] = upper;
-	if (link_which & LINK_LOWER)
-		list_add_tail(&edge->list[LOWER], &lower->upper);
-	if (link_which & LINK_UPPER)
-		list_add_tail(&edge->list[UPPER], &upper->lower);
-}
-
-static inline void btrfs_backref_free_node(struct btrfs_backref_cache *cache,
-					   struct btrfs_backref_node *node)
-{
-	if (node) {
-		ASSERT(list_empty(&node->list));
-		ASSERT(list_empty(&node->lower));
-		ASSERT(node->eb == NULL);
-		cache->nr_nodes--;
-		btrfs_put_root(node->root);
-		kfree(node);
-	}
-}
-
-static inline void btrfs_backref_free_edge(struct btrfs_backref_cache *cache,
-					   struct btrfs_backref_edge *edge)
-{
-	if (edge) {
-		cache->nr_edges--;
-		kfree(edge);
-	}
-}
-
-static inline void btrfs_backref_unlock_node_buffer(
-		struct btrfs_backref_node *node)
-{
-	if (node->locked) {
-		btrfs_tree_unlock(node->eb);
-		node->locked = 0;
-	}
-}
 
-static inline void btrfs_backref_drop_node_buffer(
-		struct btrfs_backref_node *node)
-{
-	if (node->eb) {
-		btrfs_backref_unlock_node_buffer(node);
-		free_extent_buffer(node->eb);
-		node->eb = NULL;
-	}
-}
-
-/*
- * Drop the backref node from cache without cleaning up its children
- * edges.
- *
- * This can only be called on node without parent edges.
- * The children edges are still kept as is.
- */
-static inline void btrfs_backref_drop_node(struct btrfs_backref_cache *tree,
-					   struct btrfs_backref_node *node)
-{
-	ASSERT(list_empty(&node->upper));
-
-	btrfs_backref_drop_node_buffer(node);
-	list_del_init(&node->list);
-	list_del_init(&node->lower);
-	if (!RB_EMPTY_NODE(&node->rb_node))
-		rb_erase(&node->rb_node, &tree->rb_root);
-	btrfs_backref_free_node(tree, node);
-}
+void btrfs_backref_link_edge(struct btrfs_backref_edge *edge,
+			     struct btrfs_backref_node *lower,
+			     struct btrfs_backref_node *upper,
+			     int link_which);
+void btrfs_backref_free_node(struct btrfs_backref_cache *cache,
+			     struct btrfs_backref_node *node);
+void btrfs_backref_free_edge(struct btrfs_backref_cache *cache,
+			     struct btrfs_backref_edge *edge);
+void btrfs_backref_unlock_node_buffer(struct btrfs_backref_node *node);
+void btrfs_backref_drop_node_buffer(struct btrfs_backref_node *node);
 
 void btrfs_backref_cleanup_node(struct btrfs_backref_cache *cache,
 				struct btrfs_backref_node *node);
+void btrfs_backref_drop_node(struct btrfs_backref_cache *tree,
+			     struct btrfs_backref_node *node);
 
 void btrfs_backref_release_cache(struct btrfs_backref_cache *cache);
 
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 928f512cdb..e3a57196b0 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -11,7 +11,6 @@
 #include "raid56.h"
 #include "async-thread.h"
 #include "dev-replace.h"
-#include "rcu-string.h"
 #include "zoned.h"
 #include "file-item.h"
 #include "raid-stripe-tree.h"
@@ -509,8 +508,6 @@ static void __btrfs_submit_bio(struct bio *bio, struct btrfs_io_context *bioc,
 	if (!bioc) {
 		/* Single mirror read/write fast path. */
 		btrfs_bio(bio)->mirror_num = mirror_num;
-		if (bio_op(bio) != REQ_OP_READ)
-			btrfs_bio(bio)->orig_physical = smap->physical;
 		bio->bi_iter.bi_sector = smap->physical >> SECTOR_SHIFT;
 		if (bio_op(bio) != REQ_OP_READ)
 			btrfs_bio(bio)->orig_physical = smap->physical;
@@ -611,8 +608,20 @@ static void run_one_async_done(struct btrfs_work *work, bool do_free)
 
 static bool should_async_write(struct btrfs_bio *bbio)
 {
+	bool auto_csum_mode = true;
+
+#ifdef CONFIG_BTRFS_DEBUG
+	struct btrfs_fs_devices *fs_devices = bbio->fs_info->fs_devices;
+	enum btrfs_offload_csum_mode csum_mode = READ_ONCE(fs_devices->offload_csum_mode);
+
+	if (csum_mode == BTRFS_OFFLOAD_CSUM_FORCE_OFF)
+		return false;
+
+	auto_csum_mode = (csum_mode == BTRFS_OFFLOAD_CSUM_AUTO);
+#endif
+
 	/* Submit synchronously if the checksum implementation is fast. */
-	if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &bbio->fs_info->flags))
+	if (auto_csum_mode && test_bit(BTRFS_FS_CSUM_IMPL_FAST, &bbio->fs_info->flags))
 		return false;
 
 	/*
@@ -732,7 +741,9 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 			ret = btrfs_bio_csum(bbio);
 			if (ret)
 				goto fail_put_bio;
-		} else if (use_append) {
+		} else if (use_append ||
+			   (btrfs_is_zoned(fs_info) && inode &&
+			    inode->flags & BTRFS_INODE_NODATASUM)) {
 			ret = btrfs_alloc_dummy_sum(bbio);
 			if (ret)
 				goto fail_put_bio;
diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h
index bbaed31716..d9dd527609 100644
--- a/fs/btrfs/bio.h
+++ b/fs/btrfs/bio.h
@@ -7,12 +7,14 @@
 #ifndef BTRFS_BIO_H
 #define BTRFS_BIO_H
 
+#include <linux/types.h>
 #include <linux/bio.h>
 #include <linux/workqueue.h>
 #include "tree-checker.h"
 
 struct btrfs_bio;
 struct btrfs_fs_info;
+struct btrfs_inode;
 
 #define BTRFS_BIO_INLINE_CSUM_SIZE	64
 
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index be70acea87..1a66be33bb 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -418,7 +418,7 @@ struct btrfs_caching_control *btrfs_get_caching_control(
 	return ctl;
 }
 
-void btrfs_put_caching_control(struct btrfs_caching_control *ctl)
+static void btrfs_put_caching_control(struct btrfs_caching_control *ctl)
 {
 	if (refcount_dec_and_test(&ctl->count))
 		kfree(ctl);
@@ -1063,7 +1063,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	bool remove_rsv = false;
 
 	block_group = btrfs_lookup_block_group(fs_info, map->start);
-	BUG_ON(!block_group);
+	if (!block_group)
+		return -ENOENT;
+
 	BUG_ON(!block_group->ro);
 
 	trace_btrfs_remove_block_group(block_group);
@@ -1429,7 +1431,7 @@ static bool clean_pinned_extents(struct btrfs_trans_handle *trans,
 	 * group in pinned_extents before we were able to clear the whole block
 	 * group range from pinned_extents. This means that task can lookup for
 	 * the block group after we unpinned it from pinned_extents and removed
-	 * it, leading to a BUG_ON() at unpin_extent_range().
+	 * it, leading to an error at unpin_extent_range().
 	 */
 	mutex_lock(&fs_info->unused_bg_unpin_mutex);
 	if (prev_trans) {
@@ -1522,6 +1524,13 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 			 * outstanding allocations in this block group.  We do
 			 * the ro check in case balance is currently acting on
 			 * this block group.
+			 *
+			 * Also bail out if this is the only block group for its
+			 * type, because otherwise we would lose profile
+			 * information from fs_info->avail_*_alloc_bits and the
+			 * next block group of this type would be created with a
+			 * "single" profile (even if we're in a raid fs) because
+			 * fs_info->avail_*_alloc_bits would be 0.
 			 */
 			trace_btrfs_skip_unused_block_group(block_group);
 			spin_unlock(&block_group->lock);
@@ -1776,6 +1785,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 		container_of(work, struct btrfs_fs_info, reclaim_bgs_work);
 	struct btrfs_block_group *bg;
 	struct btrfs_space_info *space_info;
+	LIST_HEAD(retry_list);
 
 	if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
 		return;
@@ -1912,8 +1922,11 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 		}
 
 next:
-		if (ret)
-			btrfs_mark_bg_to_reclaim(bg);
+		if (ret) {
+			/* Refcount held by the reclaim_bgs list after splice. */
+			btrfs_get_block_group(bg);
+			list_add_tail(&bg->bg_list, &retry_list);
+		}
 		btrfs_put_block_group(bg);
 
 		mutex_unlock(&fs_info->reclaim_bgs_lock);
@@ -1933,6 +1946,9 @@ next:
 	spin_unlock(&fs_info->unused_bgs_lock);
 	mutex_unlock(&fs_info->reclaim_bgs_lock);
 end:
+	spin_lock(&fs_info->unused_bgs_lock);
+	list_splice_tail(&retry_list, &fs_info->reclaim_bgs);
+	spin_unlock(&fs_info->unused_bgs_lock);
 	btrfs_exclop_finish(fs_info);
 	sb_end_write(fs_info->sb);
 }
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index 962b119839..85e2d4cd12 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -3,9 +3,22 @@
 #ifndef BTRFS_BLOCK_GROUP_H
 #define BTRFS_BLOCK_GROUP_H
 
+#include <linux/atomic.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/refcount.h>
+#include <linux/wait.h>
+#include <linux/sizes.h>
+#include <linux/rwsem.h>
+#include <linux/rbtree.h>
+#include <uapi/linux/btrfs_tree.h>
 #include "free-space-cache.h"
 
 struct btrfs_chunk_map;
+struct btrfs_fs_info;
+struct btrfs_inode;
+struct btrfs_trans_handle;
 
 enum btrfs_disk_cache_state {
 	BTRFS_DC_WRITTEN,
@@ -297,7 +310,6 @@ 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_cache_block_group(struct btrfs_block_group *cache, bool wait);
-void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
 struct btrfs_caching_control *btrfs_get_caching_control(
 		struct btrfs_block_group *cache);
 int btrfs_add_new_free_space(struct btrfs_block_group *block_group,
diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c
index 1043a81423..95c174f9fd 100644
--- a/fs/btrfs/block-rsv.c
+++ b/fs/btrfs/block-rsv.c
@@ -6,7 +6,6 @@
 #include "space-info.h"
 #include "transaction.h"
 #include "block-group.h"
-#include "disk-io.h"
 #include "fs.h"
 #include "accessors.h"
 
diff --git a/fs/btrfs/block-rsv.h b/fs/btrfs/block-rsv.h
index 43a9a6b5a7..1f53b967d0 100644
--- a/fs/btrfs/block-rsv.h
+++ b/fs/btrfs/block-rsv.h
@@ -3,8 +3,15 @@
 #ifndef BTRFS_BLOCK_RSV_H
 #define BTRFS_BLOCK_RSV_H
 
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/spinlock.h>
+
 struct btrfs_trans_handle;
 struct btrfs_root;
+struct btrfs_space_info;
+struct btrfs_block_rsv;
+struct btrfs_fs_info;
 enum btrfs_reserve_flush_enum;
 
 /*
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 7f7c5a92d2..100020ca46 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -8,13 +8,32 @@
 
 #include <linux/hash.h>
 #include <linux/refcount.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/rwsem.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/compiler.h>
 #include <linux/fscrypt.h>
+#include <linux/lockdep.h>
+#include <uapi/linux/btrfs_tree.h>
 #include <trace/events/btrfs.h>
+#include "block-rsv.h"
+#include "btrfs_inode.h"
 #include "extent_map.h"
 #include "extent_io.h"
+#include "extent-io-tree.h"
 #include "ordered-data.h"
 #include "delayed-inode.h"
 
+struct extent_state;
+struct posix_acl;
+struct iov_iter;
+struct writeback_control;
+struct btrfs_root;
+struct btrfs_fs_info;
+struct btrfs_trans_handle;
+
 /*
  * Since we search a directory based on f_pos (struct dir_context::pos) we have
  * to start at 2 since '.' and '..' have f_pos of 0 and 1 respectively, so
@@ -41,7 +60,6 @@ enum {
 	  */
 	BTRFS_INODE_NEEDS_FULL_SYNC,
 	BTRFS_INODE_COPY_EVERYTHING,
-	BTRFS_INODE_IN_DELALLOC_LIST,
 	BTRFS_INODE_HAS_PROPS,
 	BTRFS_INODE_SNAPSHOT_FLUSH,
 	/*
@@ -428,7 +446,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
 			      u64 *ram_bytes, bool nowait, bool strict);
 
-void __btrfs_del_delalloc_inode(struct btrfs_root *root, struct btrfs_inode *inode);
+void btrfs_del_delalloc_inode(struct btrfs_inode *inode);
 struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry);
 int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
 int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
@@ -490,8 +508,7 @@ struct inode *btrfs_iget_path(struct super_block *s, u64 ino,
 			      struct btrfs_root *root, struct btrfs_path *path);
 struct inode *btrfs_iget(struct super_block *s, u64 ino, struct btrfs_root *root);
 struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
-				    struct page *page, size_t pg_offset,
-				    u64 start, u64 len);
+				    struct page *page, u64 start, u64 len);
 int btrfs_update_inode(struct btrfs_trans_handle *trans,
 		       struct btrfs_inode *inode);
 int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 0041613a36..b2b9400995 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -25,8 +25,6 @@
 #include "misc.h"
 #include "ctree.h"
 #include "fs.h"
-#include "disk-io.h"
-#include "transaction.h"
 #include "btrfs_inode.h"
 #include "bio.h"
 #include "ordered-data.h"
@@ -34,8 +32,7 @@
 #include "extent_io.h"
 #include "extent_map.h"
 #include "subpage.h"
-#include "zoned.h"
-#include "file-item.h"
+#include "messages.h"
 #include "super.h"
 
 static struct bio_set btrfs_compressed_bioset;
@@ -1479,11 +1476,6 @@ static void heuristic_collect_sample(struct inode *inode, u64 start, u64 end,
 /*
  * Compression heuristic.
  *
- * For now is's a naive and optimistic 'return true', we'll extend the logic to
- * quickly (compared to direct compression) detect data characteristics
- * (compressible/incompressible) to avoid wasting CPU time on incompressible
- * data.
- *
  * The following types of analysis can be performed:
  * - detect mostly zero data
  * - detect data with low "byte set" size (text, etc)
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index afd7e50d07..4691a84ca8 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -7,10 +7,18 @@
 #define BTRFS_COMPRESSION_H
 
 #include <linux/sizes.h>
+#include <linux/mm.h>
+#include <linux/list.h>
+#include <linux/workqueue.h>
+#include <linux/wait.h>
 #include "bio.h"
 
+struct address_space;
+struct page;
+struct inode;
 struct btrfs_inode;
 struct btrfs_ordered_extent;
+struct btrfs_bio;
 
 /*
  * We want to make sure that amount of RAM required to uncompress an extent is
@@ -32,8 +40,6 @@ static_assert((BTRFS_MAX_COMPRESSED % PAGE_SIZE) == 0);
 
 #define	BTRFS_ZLIB_DEFAULT_LEVEL		3
 
-struct page;
-
 struct compressed_bio {
 	/* Number of compressed pages in the array */
 	unsigned int nr_pages;
@@ -169,7 +175,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 		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, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen);
 void zstd_init_workspace_manager(void);
 void zstd_cleanup_workspace_manager(void);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index e65e012bac..aaf53fd843 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -820,7 +820,7 @@ int btrfs_bin_search(struct extent_buffer *eb, int first_slot,
 	}
 
 	while (low < high) {
-		const int unit_size = folio_size(eb->folios[0]);
+		const int unit_size = eb->folio_size;
 		unsigned long oil;
 		unsigned long offset;
 		struct btrfs_disk_key *tmp;
@@ -4280,6 +4280,10 @@ void btrfs_setup_item_for_insert(struct btrfs_trans_handle *trans,
 /*
  * Given a key and some data, insert items into the tree.
  * This does all the path init required, making room in the tree if needed.
+ *
+ * Returns: 0        on success
+ *          -EEXIST  if the first key already exists
+ *          < 0      on other errors
  */
 int btrfs_insert_empty_items(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root,
@@ -5082,9 +5086,7 @@ int btrfs_previous_extent_item(struct btrfs_root *root,
 
 int __init btrfs_ctree_init(void)
 {
-	btrfs_path_cachep = kmem_cache_create("btrfs_path",
-			sizeof(struct btrfs_path), 0,
-			SLAB_MEM_SPREAD, NULL);
+	btrfs_path_cachep = KMEM_CACHE(btrfs_path, 0);
 	if (!btrfs_path_cachep)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 70e828d331..c03c582460 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -7,25 +7,24 @@
 #define BTRFS_CTREE_H
 
 #include <linux/pagemap.h>
+#include <linux/spinlock.h>
+#include <linux/rbtree.h>
+#include <linux/mutex.h>
+#include <linux/wait.h>
+#include <linux/list.h>
+#include <linux/atomic.h>
+#include <linux/xarray.h>
+#include <linux/refcount.h>
+#include <uapi/linux/btrfs_tree.h>
 #include "locking.h"
 #include "fs.h"
 #include "accessors.h"
+#include "extent-io-tree.h"
 
+struct extent_buffer;
+struct btrfs_block_rsv;
 struct btrfs_trans_handle;
-struct btrfs_transaction;
-struct btrfs_pending_snapshot;
-struct btrfs_delayed_ref_root;
-struct btrfs_space_info;
 struct btrfs_block_group;
-struct btrfs_ordered_sum;
-struct btrfs_ref;
-struct btrfs_bio;
-struct btrfs_ioctl_encoded_io_args;
-struct btrfs_device;
-struct btrfs_fs_devices;
-struct btrfs_balance_control;
-struct btrfs_delayed_root;
-struct reloc_control;
 
 /* Read ahead values for struct btrfs_path.reada */
 enum {
@@ -478,8 +477,7 @@ static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
 	return mapping_gfp_constraint(mapping, ~__GFP_FS);
 }
 
-int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
-				   u64 start, u64 end);
+void btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, u64 start, u64 end);
 int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 			 u64 num_bytes, u64 *actual_bytes);
 int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range);
diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c
index a77be9896d..f015fa1b63 100644
--- a/fs/btrfs/defrag.c
+++ b/fs/btrfs/defrag.c
@@ -6,7 +6,6 @@
 #include <linux/sched.h>
 #include "ctree.h"
 #include "disk-io.h"
-#include "print-tree.h"
 #include "transaction.h"
 #include "locking.h"
 #include "accessors.h"
@@ -521,7 +520,7 @@ static int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 	 * keep_locks set and lowest_level is 1, regardless of the value of
 	 * path->slots[1].
 	 */
-	BUG_ON(path->locks[1] == 0);
+	ASSERT(path->locks[1] != 0);
 	ret = btrfs_realloc_node(trans, root,
 				 path->nodes[1], 0,
 				 &last_ret,
@@ -861,20 +860,21 @@ out:
  * NOTE: Caller should also wait for page writeback after the cluster is
  * prepared, here we don't do writeback wait for each page.
  */
-static struct page *defrag_prepare_one_page(struct btrfs_inode *inode, pgoff_t index)
+static struct folio *defrag_prepare_one_folio(struct btrfs_inode *inode, pgoff_t index)
 {
 	struct address_space *mapping = inode->vfs_inode.i_mapping;
 	gfp_t mask = btrfs_alloc_write_mask(mapping);
 	u64 page_start = (u64)index << PAGE_SHIFT;
 	u64 page_end = page_start + PAGE_SIZE - 1;
 	struct extent_state *cached_state = NULL;
-	struct page *page;
+	struct folio *folio;
 	int ret;
 
 again:
-	page = find_or_create_page(mapping, index, mask);
-	if (!page)
-		return ERR_PTR(-ENOMEM);
+	folio = __filemap_get_folio(mapping, index,
+				    FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mask);
+	if (IS_ERR(folio))
+		return folio;
 
 	/*
 	 * Since we can defragment files opened read-only, we can encounter
@@ -884,16 +884,16 @@ again:
 	 * executables that explicitly enable them, so this isn't very
 	 * restrictive.
 	 */
-	if (PageCompound(page)) {
-		unlock_page(page);
-		put_page(page);
+	if (folio_test_large(folio)) {
+		folio_unlock(folio);
+		folio_put(folio);
 		return ERR_PTR(-ETXTBSY);
 	}
 
-	ret = set_page_extent_mapped(page);
+	ret = set_folio_extent_mapped(folio);
 	if (ret < 0) {
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 		return ERR_PTR(ret);
 	}
 
@@ -908,17 +908,17 @@ again:
 		if (!ordered)
 			break;
 
-		unlock_page(page);
+		folio_unlock(folio);
 		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
-		lock_page(page);
+		folio_lock(folio);
 		/*
-		 * We unlocked the page above, so we need check if it was
+		 * We unlocked the folio above, so we need check if it was
 		 * released or not.
 		 */
-		if (page->mapping != mapping || !PagePrivate(page)) {
-			unlock_page(page);
-			put_page(page);
+		if (folio->mapping != mapping || !folio->private) {
+			folio_unlock(folio);
+			folio_put(folio);
 			goto again;
 		}
 	}
@@ -927,21 +927,21 @@ again:
 	 * Now the page range has no ordered extent any more.  Read the page to
 	 * make it uptodate.
 	 */
-	if (!PageUptodate(page)) {
-		btrfs_read_folio(NULL, page_folio(page));
-		lock_page(page);
-		if (page->mapping != mapping || !PagePrivate(page)) {
-			unlock_page(page);
-			put_page(page);
+	if (!folio_test_uptodate(folio)) {
+		btrfs_read_folio(NULL, folio);
+		folio_lock(folio);
+		if (folio->mapping != mapping || !folio->private) {
+			folio_unlock(folio);
+			folio_put(folio);
 			goto again;
 		}
-		if (!PageUptodate(page)) {
-			unlock_page(page);
-			put_page(page);
+		if (!folio_test_uptodate(folio)) {
+			folio_unlock(folio);
+			folio_put(folio);
 			return ERR_PTR(-EIO);
 		}
 	}
-	return page;
+	return folio;
 }
 
 struct defrag_target_range {
@@ -1162,7 +1162,7 @@ static_assert(PAGE_ALIGNED(CLUSTER_SIZE));
  */
 static int defrag_one_locked_target(struct btrfs_inode *inode,
 				    struct defrag_target_range *target,
-				    struct page **pages, int nr_pages,
+				    struct folio **folios, int nr_pages,
 				    struct extent_state **cached_state)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
@@ -1171,7 +1171,7 @@ static int defrag_one_locked_target(struct btrfs_inode *inode,
 	const u64 len = target->len;
 	unsigned long last_index = (start + len - 1) >> PAGE_SHIFT;
 	unsigned long start_index = start >> PAGE_SHIFT;
-	unsigned long first_index = page_index(pages[0]);
+	unsigned long first_index = folios[0]->index;
 	int ret = 0;
 	int i;
 
@@ -1188,8 +1188,8 @@ static int defrag_one_locked_target(struct btrfs_inode *inode,
 
 	/* Update the page status */
 	for (i = start_index - first_index; i <= last_index - first_index; i++) {
-		ClearPageChecked(pages[i]);
-		btrfs_folio_clamp_set_dirty(fs_info, page_folio(pages[i]), start, len);
+		folio_clear_checked(folios[i]);
+		btrfs_folio_clamp_set_dirty(fs_info, folios[i], start, len);
 	}
 	btrfs_delalloc_release_extents(inode, len);
 	extent_changeset_free(data_reserved);
@@ -1205,7 +1205,7 @@ static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len,
 	struct defrag_target_range *entry;
 	struct defrag_target_range *tmp;
 	LIST_HEAD(target_list);
-	struct page **pages;
+	struct folio **folios;
 	const u32 sectorsize = inode->root->fs_info->sectorsize;
 	u64 last_index = (start + len - 1) >> PAGE_SHIFT;
 	u64 start_index = start >> PAGE_SHIFT;
@@ -1216,21 +1216,21 @@ static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len,
 	ASSERT(nr_pages <= CLUSTER_SIZE / PAGE_SIZE);
 	ASSERT(IS_ALIGNED(start, sectorsize) && IS_ALIGNED(len, sectorsize));
 
-	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
-	if (!pages)
+	folios = kcalloc(nr_pages, sizeof(struct folio *), GFP_NOFS);
+	if (!folios)
 		return -ENOMEM;
 
 	/* Prepare all pages */
 	for (i = 0; i < nr_pages; i++) {
-		pages[i] = defrag_prepare_one_page(inode, start_index + i);
-		if (IS_ERR(pages[i])) {
-			ret = PTR_ERR(pages[i]);
-			pages[i] = NULL;
-			goto free_pages;
+		folios[i] = defrag_prepare_one_folio(inode, start_index + i);
+		if (IS_ERR(folios[i])) {
+			ret = PTR_ERR(folios[i]);
+			nr_pages = i;
+			goto free_folios;
 		}
 	}
 	for (i = 0; i < nr_pages; i++)
-		wait_on_page_writeback(pages[i]);
+		folio_wait_writeback(folios[i]);
 
 	/* Lock the pages range */
 	lock_extent(&inode->io_tree, start_index << PAGE_SHIFT,
@@ -1250,7 +1250,7 @@ static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len,
 		goto unlock_extent;
 
 	list_for_each_entry(entry, &target_list, list) {
-		ret = defrag_one_locked_target(inode, entry, pages, nr_pages,
+		ret = defrag_one_locked_target(inode, entry, folios, nr_pages,
 					       &cached_state);
 		if (ret < 0)
 			break;
@@ -1264,14 +1264,12 @@ unlock_extent:
 	unlock_extent(&inode->io_tree, start_index << PAGE_SHIFT,
 		      (last_index << PAGE_SHIFT) + PAGE_SIZE - 1,
 		      &cached_state);
-free_pages:
+free_folios:
 	for (i = 0; i < nr_pages; i++) {
-		if (pages[i]) {
-			unlock_page(pages[i]);
-			put_page(pages[i]);
-		}
+		folio_unlock(folios[i]);
+		folio_put(folios[i]);
 	}
-	kfree(pages);
+	kfree(folios);
 	return ret;
 }
 
@@ -1512,9 +1510,7 @@ void __cold btrfs_auto_defrag_exit(void)
 int __init btrfs_auto_defrag_init(void)
 {
 	btrfs_inode_defrag_cachep = kmem_cache_create("btrfs_inode_defrag",
-					sizeof(struct inode_defrag), 0,
-					SLAB_MEM_SPREAD,
-					NULL);
+					sizeof(struct inode_defrag), 0, 0, NULL);
 	if (!btrfs_inode_defrag_cachep)
 		return -ENOMEM;
 
diff --git a/fs/btrfs/defrag.h b/fs/btrfs/defrag.h
index 5a62763528..878528e086 100644
--- a/fs/btrfs/defrag.h
+++ b/fs/btrfs/defrag.h
@@ -3,6 +3,16 @@
 #ifndef BTRFS_DEFRAG_H
 #define BTRFS_DEFRAG_H
 
+#include <linux/types.h>
+#include <linux/compiler_types.h>
+
+struct inode;
+struct file_ra_state;
+struct btrfs_fs_info;
+struct btrfs_root;
+struct btrfs_trans_handle;
+struct btrfs_ioctl_defrag_range_args;
+
 int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
 		      struct btrfs_ioctl_defrag_range_args *range,
 		      u64 newer_than, unsigned long max_to_defrag);
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index acf9f4b6c0..b3527efd0b 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -6,9 +6,7 @@
 #include "block-rsv.h"
 #include "btrfs_inode.h"
 #include "space-info.h"
-#include "transaction.h"
 #include "qgroup.h"
-#include "block-group.h"
 #include "fs.h"
 
 /*
diff --git a/fs/btrfs/delalloc-space.h b/fs/btrfs/delalloc-space.h
index c5d573f236..ce4f889e4f 100644
--- a/fs/btrfs/delalloc-space.h
+++ b/fs/btrfs/delalloc-space.h
@@ -3,7 +3,11 @@
 #ifndef BTRFS_DELALLOC_SPACE_H
 #define BTRFS_DELALLOC_SPACE_H
 
+#include <linux/types.h>
+
 struct extent_changeset;
+struct btrfs_inode;
+struct btrfs_fs_info;
 
 int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes);
 int btrfs_check_data_free_space(struct btrfs_inode *inode,
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index ab5a833e7d..121ab890bd 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -28,11 +28,7 @@ static struct kmem_cache *delayed_node_cache;
 
 int __init btrfs_delayed_inode_init(void)
 {
-	delayed_node_cache = kmem_cache_create("btrfs_delayed_node",
-					sizeof(struct btrfs_delayed_node),
-					0,
-					SLAB_MEM_SPREAD,
-					NULL);
+	delayed_node_cache = KMEM_CACHE(btrfs_delayed_node, 0);
 	if (!delayed_node_cache)
 		return -ENOMEM;
 	return 0;
@@ -43,6 +39,17 @@ void __cold btrfs_delayed_inode_exit(void)
 	kmem_cache_destroy(delayed_node_cache);
 }
 
+void btrfs_init_delayed_root(struct btrfs_delayed_root *delayed_root)
+{
+	atomic_set(&delayed_root->items, 0);
+	atomic_set(&delayed_root->items_seq, 0);
+	delayed_root->nodes = 0;
+	spin_lock_init(&delayed_root->lock);
+	init_waitqueue_head(&delayed_root->wait);
+	INIT_LIST_HEAD(&delayed_root->node_list);
+	INIT_LIST_HEAD(&delayed_root->prepare_list);
+}
+
 static inline void btrfs_init_delayed_node(
 				struct btrfs_delayed_node *delayed_node,
 				struct btrfs_root *root, u64 inode_id)
@@ -430,8 +437,6 @@ static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
 
 	delayed_root = delayed_node->root->fs_info->delayed_root;
 
-	BUG_ON(!delayed_root);
-
 	if (delayed_item->type == BTRFS_DELAYED_INSERTION_ITEM)
 		root = &delayed_node->ins_root;
 	else
@@ -980,7 +985,7 @@ static void btrfs_release_delayed_inode(struct btrfs_delayed_node *delayed_node)
 
 	if (delayed_node &&
 	    test_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags)) {
-		BUG_ON(!delayed_node->root);
+		ASSERT(delayed_node->root);
 		clear_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags);
 		delayed_node->count--;
 
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 5cceb31bbd..64e115d974 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -7,15 +7,23 @@
 #ifndef BTRFS_DELAYED_INODE_H
 #define BTRFS_DELAYED_INODE_H
 
+#include <linux/types.h>
 #include <linux/rbtree.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/wait.h>
+#include <linux/fs.h>
 #include <linux/atomic.h>
 #include <linux/refcount.h>
 #include "ctree.h"
 
+struct btrfs_disk_key;
+struct btrfs_fs_info;
+struct btrfs_inode;
+struct btrfs_root;
+struct btrfs_trans_handle;
+
 enum btrfs_delayed_item_type {
 	BTRFS_DELAYED_INSERTION_ITEM,
 	BTRFS_DELAYED_DELETION_ITEM
@@ -98,18 +106,7 @@ struct btrfs_delayed_item {
 	char data[] __counted_by(data_len);
 };
 
-static inline void btrfs_init_delayed_root(
-				struct btrfs_delayed_root *delayed_root)
-{
-	atomic_set(&delayed_root->items, 0);
-	atomic_set(&delayed_root->items_seq, 0);
-	delayed_root->nodes = 0;
-	spin_lock_init(&delayed_root->lock);
-	init_waitqueue_head(&delayed_root->wait);
-	INIT_LIST_HEAD(&delayed_root->node_list);
-	INIT_LIST_HEAD(&delayed_root->prepare_list);
-}
-
+void btrfs_init_delayed_root(struct btrfs_delayed_root *delayed_root);
 int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 				   const char *name, int name_len,
 				   struct btrfs_inode *dir,
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 891ea2fa26..e44e62cf76 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -1004,6 +1004,52 @@ static void init_delayed_ref_common(struct btrfs_fs_info *fs_info,
 	INIT_LIST_HEAD(&ref->add_list);
 }
 
+void btrfs_init_generic_ref(struct btrfs_ref *generic_ref, int action, u64 bytenr,
+			    u64 len, u64 parent, u64 owning_root)
+{
+	generic_ref->action = action;
+	generic_ref->bytenr = bytenr;
+	generic_ref->len = len;
+	generic_ref->parent = parent;
+	generic_ref->owning_root = owning_root;
+}
+
+void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level, u64 root,
+			 u64 mod_root, bool skip_qgroup)
+{
+#ifdef CONFIG_BTRFS_FS_REF_VERIFY
+	/* If @real_root not set, use @root as fallback */
+	generic_ref->real_root = mod_root ?: root;
+#endif
+	generic_ref->tree_ref.level = level;
+	generic_ref->tree_ref.ref_root = root;
+	generic_ref->type = BTRFS_REF_METADATA;
+	if (skip_qgroup || !(is_fstree(root) &&
+			     (!mod_root || is_fstree(mod_root))))
+		generic_ref->skip_qgroup = true;
+	else
+		generic_ref->skip_qgroup = false;
+
+}
+
+void btrfs_init_data_ref(struct btrfs_ref *generic_ref, u64 ref_root, u64 ino,
+			 u64 offset, u64 mod_root, bool skip_qgroup)
+{
+#ifdef CONFIG_BTRFS_FS_REF_VERIFY
+	/* If @real_root not set, use @root as fallback */
+	generic_ref->real_root = mod_root ?: ref_root;
+#endif
+	generic_ref->data_ref.ref_root = ref_root;
+	generic_ref->data_ref.ino = ino;
+	generic_ref->data_ref.offset = offset;
+	generic_ref->type = BTRFS_REF_DATA;
+	if (skip_qgroup || !(is_fstree(ref_root) &&
+			     (!mod_root || is_fstree(mod_root))))
+		generic_ref->skip_qgroup = true;
+	else
+		generic_ref->skip_qgroup = false;
+}
+
 /*
  * add a delayed tree ref.  This does all of the accounting required
  * to make sure the delayed ref is eventually processed before this
@@ -1220,6 +1266,25 @@ int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
+{
+	if (refcount_dec_and_test(&ref->refs)) {
+		WARN_ON(!RB_EMPTY_NODE(&ref->ref_node));
+		switch (ref->type) {
+		case BTRFS_TREE_BLOCK_REF_KEY:
+		case BTRFS_SHARED_BLOCK_REF_KEY:
+			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+			break;
+		case BTRFS_EXTENT_DATA_REF_KEY:
+		case BTRFS_SHARED_DATA_REF_KEY:
+			kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
+			break;
+		default:
+			BUG();
+		}
+	}
+}
+
 /*
  * This does a simple search for the head node for a given extent.  Returns the
  * head node if found, or NULL if not.
@@ -1242,31 +1307,19 @@ void __cold btrfs_delayed_ref_exit(void)
 
 int __init btrfs_delayed_ref_init(void)
 {
-	btrfs_delayed_ref_head_cachep = kmem_cache_create(
-				"btrfs_delayed_ref_head",
-				sizeof(struct btrfs_delayed_ref_head), 0,
-				SLAB_MEM_SPREAD, NULL);
+	btrfs_delayed_ref_head_cachep = KMEM_CACHE(btrfs_delayed_ref_head, 0);
 	if (!btrfs_delayed_ref_head_cachep)
 		goto fail;
 
-	btrfs_delayed_tree_ref_cachep = kmem_cache_create(
-				"btrfs_delayed_tree_ref",
-				sizeof(struct btrfs_delayed_tree_ref), 0,
-				SLAB_MEM_SPREAD, NULL);
+	btrfs_delayed_tree_ref_cachep = KMEM_CACHE(btrfs_delayed_tree_ref, 0);
 	if (!btrfs_delayed_tree_ref_cachep)
 		goto fail;
 
-	btrfs_delayed_data_ref_cachep = kmem_cache_create(
-				"btrfs_delayed_data_ref",
-				sizeof(struct btrfs_delayed_data_ref), 0,
-				SLAB_MEM_SPREAD, NULL);
+	btrfs_delayed_data_ref_cachep = KMEM_CACHE(btrfs_delayed_data_ref, 0);
 	if (!btrfs_delayed_data_ref_cachep)
 		goto fail;
 
-	btrfs_delayed_extent_op_cachep = kmem_cache_create(
-				"btrfs_delayed_extent_op",
-				sizeof(struct btrfs_delayed_extent_op), 0,
-				SLAB_MEM_SPREAD, NULL);
+	btrfs_delayed_extent_op_cachep = KMEM_CACHE(btrfs_delayed_extent_op, 0);
 	if (!btrfs_delayed_extent_op_cachep)
 		goto fail;
 
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 62d679d40f..b291147cb8 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -6,7 +6,17 @@
 #ifndef BTRFS_DELAYED_REF_H
 #define BTRFS_DELAYED_REF_H
 
+#include <linux/types.h>
 #include <linux/refcount.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <uapi/linux/btrfs_tree.h>
+
+struct btrfs_trans_handle;
+struct btrfs_fs_info;
 
 /* these are the possible values of struct btrfs_delayed_ref_node->action */
 enum btrfs_delayed_ref_action {
@@ -308,53 +318,12 @@ static inline u64 btrfs_calc_delayed_ref_csum_bytes(const struct btrfs_fs_info *
 	return btrfs_calc_metadata_size(fs_info, num_csum_items);
 }
 
-static inline void btrfs_init_generic_ref(struct btrfs_ref *generic_ref,
-					  int action, u64 bytenr, u64 len,
-					  u64 parent, u64 owning_root)
-{
-	generic_ref->action = action;
-	generic_ref->bytenr = bytenr;
-	generic_ref->len = len;
-	generic_ref->parent = parent;
-	generic_ref->owning_root = owning_root;
-}
-
-static inline void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level,
-				       u64 root, u64 mod_root, bool skip_qgroup)
-{
-#ifdef CONFIG_BTRFS_FS_REF_VERIFY
-	/* If @real_root not set, use @root as fallback */
-	generic_ref->real_root = mod_root ?: root;
-#endif
-	generic_ref->tree_ref.level = level;
-	generic_ref->tree_ref.ref_root = root;
-	generic_ref->type = BTRFS_REF_METADATA;
-	if (skip_qgroup || !(is_fstree(root) &&
-			     (!mod_root || is_fstree(mod_root))))
-		generic_ref->skip_qgroup = true;
-	else
-		generic_ref->skip_qgroup = false;
-
-}
-
-static inline void btrfs_init_data_ref(struct btrfs_ref *generic_ref,
-				u64 ref_root, u64 ino, u64 offset, u64 mod_root,
-				bool skip_qgroup)
-{
-#ifdef CONFIG_BTRFS_FS_REF_VERIFY
-	/* If @real_root not set, use @root as fallback */
-	generic_ref->real_root = mod_root ?: ref_root;
-#endif
-	generic_ref->data_ref.ref_root = ref_root;
-	generic_ref->data_ref.ino = ino;
-	generic_ref->data_ref.offset = offset;
-	generic_ref->type = BTRFS_REF_DATA;
-	if (skip_qgroup || !(is_fstree(ref_root) &&
-			     (!mod_root || is_fstree(mod_root))))
-		generic_ref->skip_qgroup = true;
-	else
-		generic_ref->skip_qgroup = false;
-}
+void btrfs_init_generic_ref(struct btrfs_ref *generic_ref, int action, u64 bytenr,
+			    u64 len, u64 parent, u64 owning_root);
+void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level, u64 root,
+			 u64 mod_root, bool skip_qgroup);
+void btrfs_init_data_ref(struct btrfs_ref *generic_ref, u64 ref_root, u64 ino,
+			 u64 offset, u64 mod_root, bool skip_qgroup);
 
 static inline struct btrfs_delayed_extent_op *
 btrfs_alloc_delayed_extent_op(void)
@@ -369,24 +338,7 @@ btrfs_free_delayed_extent_op(struct btrfs_delayed_extent_op *op)
 		kmem_cache_free(btrfs_delayed_extent_op_cachep, op);
 }
 
-static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
-{
-	if (refcount_dec_and_test(&ref->refs)) {
-		WARN_ON(!RB_EMPTY_NODE(&ref->ref_node));
-		switch (ref->type) {
-		case BTRFS_TREE_BLOCK_REF_KEY:
-		case BTRFS_SHARED_BLOCK_REF_KEY:
-			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
-			break;
-		case BTRFS_EXTENT_DATA_REF_KEY:
-		case BTRFS_SHARED_DATA_REF_KEY:
-			kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
-			break;
-		default:
-			BUG();
-		}
-	}
-}
+void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref);
 
 static inline u64 btrfs_ref_head_to_space_flags(
 				struct btrfs_delayed_ref_head *head_ref)
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 79c4293ddf..7696beec4c 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -11,10 +11,8 @@
 #include <linux/math64.h>
 #include "misc.h"
 #include "ctree.h"
-#include "extent_map.h"
 #include "disk-io.h"
 #include "transaction.h"
-#include "print-tree.h"
 #include "volumes.h"
 #include "async-thread.h"
 #include "dev-replace.h"
@@ -246,7 +244,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *device;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bdev;
 	u64 devid = BTRFS_DEV_REPLACE_DEVID;
 	int ret = 0;
@@ -257,13 +255,13 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 		return -EINVAL;
 	}
 
-	bdev_handle = bdev_open_by_path(device_path, BLK_OPEN_WRITE,
+	bdev_file = bdev_file_open_by_path(device_path, BLK_OPEN_WRITE,
 					fs_info->bdev_holder, NULL);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		btrfs_err(fs_info, "target device %s is invalid!", device_path);
-		return PTR_ERR(bdev_handle);
+		return PTR_ERR(bdev_file);
 	}
-	bdev = bdev_handle->bdev;
+	bdev = file_bdev(bdev_file);
 
 	if (!btrfs_check_device_zone_type(fs_info, bdev)) {
 		btrfs_err(fs_info,
@@ -314,7 +312,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	device->commit_bytes_used = device->bytes_used;
 	device->fs_info = fs_info;
 	device->bdev = bdev;
-	device->bdev_handle = bdev_handle;
+	device->bdev_file = bdev_file;
 	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
 	device->dev_stats_valid = 1;
@@ -335,7 +333,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	return 0;
 
 error:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	return ret;
 }
 
@@ -1000,8 +998,7 @@ error:
 	btrfs_sysfs_remove_device(src_device);
 	btrfs_sysfs_update_devid(tgt_device);
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &src_device->dev_state))
-		btrfs_scratch_superblocks(fs_info, src_device->bdev,
-					  src_device->name->str);
+		btrfs_scratch_superblocks(fs_info, src_device);
 
 	/* write back the superblocks */
 	trans = btrfs_start_transaction(root, 0);
diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h
index 675082ccec..23e480efe5 100644
--- a/fs/btrfs/dev-replace.h
+++ b/fs/btrfs/dev-replace.h
@@ -6,11 +6,15 @@
 #ifndef BTRFS_DEV_REPLACE_H
 #define BTRFS_DEV_REPLACE_H
 
+#include <linux/types.h>
+#include <linux/compiler_types.h>
+
 struct btrfs_ioctl_dev_replace_args;
 struct btrfs_fs_info;
 struct btrfs_trans_handle;
 struct btrfs_dev_replace;
 struct btrfs_block_group;
+struct btrfs_device;
 
 int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info);
 int btrfs_run_dev_replace(struct btrfs_trans_handle *trans);
diff --git a/fs/btrfs/dir-item.h b/fs/btrfs/dir-item.h
index e40a226373..00b3d83d75 100644
--- a/fs/btrfs/dir-item.h
+++ b/fs/btrfs/dir-item.h
@@ -3,9 +3,15 @@
 #ifndef BTRFS_DIR_ITEM_H
 #define BTRFS_DIR_ITEM_H
 
+#include <linux/types.h>
 #include <linux/crc32c.h>
 
 struct fscrypt_str;
+struct btrfs_fs_info;
+struct btrfs_key;
+struct btrfs_path;
+struct btrfs_root;
+struct btrfs_trans_handle;
 
 int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
 			  const struct fscrypt_str *name);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 2567821224..3a47eec87b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -29,7 +29,6 @@
 #include "tree-log.h"
 #include "free-space-cache.h"
 #include "free-space-tree.h"
-#include "rcu-string.h"
 #include "dev-replace.h"
 #include "raid56.h"
 #include "sysfs.h"
@@ -193,7 +192,7 @@ static int btrfs_repair_eb_io_failure(const struct extent_buffer *eb,
 		struct folio *folio = eb->folios[i];
 		u64 start = max_t(u64, eb->start, folio_pos(folio));
 		u64 end = min_t(u64, eb->start + eb->len,
-				folio_pos(folio) + folio_size(folio));
+				folio_pos(folio) + eb->folio_size);
 		u32 len = end - start;
 
 		ret = btrfs_repair_io_failure(fs_info, 0, start, len,
@@ -1245,6 +1244,7 @@ void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info)
 		btrfs_err(fs_info, "leaked root %s refcount %d",
 			  btrfs_root_name(&root->root_key, buf),
 			  refcount_read(&root->refs));
+		WARN_ON_ONCE(1);
 		while (refcount_read(&root->refs) > 1)
 			btrfs_put_root(root);
 		btrfs_put_root(root);
@@ -2240,7 +2240,7 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 	struct btrfs_key location;
 	int ret;
 
-	BUG_ON(!fs_info->tree_root);
+	ASSERT(fs_info->tree_root);
 
 	ret = load_global_roots(tree_root);
 	if (ret)
@@ -4544,18 +4544,10 @@ static void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				       struct btrfs_fs_info *fs_info)
 {
 	struct rb_node *node;
-	struct btrfs_delayed_ref_root *delayed_refs;
+	struct btrfs_delayed_ref_root *delayed_refs = &trans->delayed_refs;
 	struct btrfs_delayed_ref_node *ref;
 
-	delayed_refs = &trans->delayed_refs;
-
 	spin_lock(&delayed_refs->lock);
-	if (atomic_read(&delayed_refs->num_entries) == 0) {
-		spin_unlock(&delayed_refs->lock);
-		btrfs_debug(fs_info, "delayed_refs has NO entry");
-		return;
-	}
-
 	while ((node = rb_first_cached(&delayed_refs->href_root)) != NULL) {
 		struct btrfs_delayed_ref_head *head;
 		struct rb_node *n;
@@ -4629,7 +4621,7 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
 		struct inode *inode = NULL;
 		btrfs_inode = list_first_entry(&splice, struct btrfs_inode,
 					       delalloc_inodes);
-		__btrfs_del_delalloc_inode(root, btrfs_inode);
+		btrfs_del_delalloc_inode(btrfs_inode);
 		spin_unlock(&root->delalloc_lock);
 
 		/*
@@ -4928,7 +4920,14 @@ int btrfs_init_root_free_objectid(struct btrfs_root *root)
 	ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
 	if (ret < 0)
 		goto error;
-	BUG_ON(ret == 0); /* Corruption */
+	if (ret == 0) {
+		/*
+		 * Key with offset -1 found, there would have to exist a root
+		 * with such id, but this is out of valid range.
+		 */
+		ret = -EUCLEAN;
+		goto error;
+	}
 	if (path->slots[0] > 0) {
 		slot = path->slots[0] - 1;
 		l = path->nodes[0];
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index eb3473d1c1..76eb53fe7a 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -6,6 +6,22 @@
 #ifndef BTRFS_DISK_IO_H
 #define BTRFS_DISK_IO_H
 
+#include <linux/sizes.h>
+#include <linux/compiler_types.h>
+#include "ctree.h"
+#include "fs.h"
+
+struct block_device;
+struct super_block;
+struct extent_buffer;
+struct btrfs_device;
+struct btrfs_fs_devices;
+struct btrfs_fs_info;
+struct btrfs_super_block;
+struct btrfs_trans_handle;
+struct btrfs_tree_parent_check;
+struct btrfs_transaction;
+
 #define BTRFS_SUPER_MIRROR_MAX	 3
 #define BTRFS_SUPER_MIRROR_SHIFT 12
 
@@ -25,10 +41,6 @@ static inline u64 btrfs_sb_offset(int mirror)
 	return BTRFS_SUPER_INFO_OFFSET;
 }
 
-struct btrfs_device;
-struct btrfs_fs_devices;
-struct btrfs_tree_parent_check;
-
 void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info);
 void btrfs_init_fs_info(struct btrfs_fs_info *fs_info);
 struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 1ac00ee795..8398d345ec 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -5,7 +5,6 @@
 #include "ctree.h"
 #include "disk-io.h"
 #include "btrfs_inode.h"
-#include "print-tree.h"
 #include "export.h"
 #include "accessors.h"
 #include "super.h"
diff --git a/fs/btrfs/export.h b/fs/btrfs/export.h
index eba6bc4f5a..464582273a 100644
--- a/fs/btrfs/export.h
+++ b/fs/btrfs/export.h
@@ -4,6 +4,10 @@
 #define BTRFS_EXPORT_H
 
 #include <linux/exportfs.h>
+#include <linux/types.h>
+
+struct dentry;
+struct super_block;
 
 extern const struct export_operations btrfs_export_ops;
 
diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c
index e3ee5449cc..c09b428823 100644
--- a/fs/btrfs/extent-io-tree.c
+++ b/fs/btrfs/extent-io-tree.c
@@ -6,7 +6,6 @@
 #include "ctree.h"
 #include "extent-io-tree.h"
 #include "btrfs_inode.h"
-#include "misc.h"
 
 static struct kmem_cache *extent_state_cache;
 
@@ -48,6 +47,7 @@ static inline void btrfs_extent_state_leak_debug_check(void)
 		       extent_state_in_tree(state),
 		       refcount_read(&state->refs));
 		list_del(&state->leak_list);
+		WARN_ON_ONCE(1);
 		kmem_cache_free(extent_state_cache, state);
 	}
 }
@@ -1883,8 +1883,8 @@ void __cold extent_state_free_cachep(void)
 int __init extent_state_init_cachep(void)
 {
 	extent_state_cache = kmem_cache_create("btrfs_extent_state",
-			sizeof(struct extent_state), 0,
-			SLAB_MEM_SPREAD, NULL);
+					       sizeof(struct extent_state), 0, 0,
+					       NULL);
 	if (!extent_state_cache)
 		return -ENOMEM;
 
diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h
index ebe6390d65..9d3a52d8f5 100644
--- a/fs/btrfs/extent-io-tree.h
+++ b/fs/btrfs/extent-io-tree.h
@@ -3,9 +3,16 @@
 #ifndef BTRFS_EXTENT_IO_TREE_H
 #define BTRFS_EXTENT_IO_TREE_H
 
+#include <linux/rbtree.h>
+#include <linux/spinlock.h>
+#include <linux/refcount.h>
+#include <linux/list.h>
+#include <linux/wait.h>
 #include "misc.h"
 
 struct extent_changeset;
+struct btrfs_fs_info;
+struct btrfs_inode;
 
 /* Bits for the extent state */
 enum {
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 8e8cc11112..257d044bca 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -18,7 +18,7 @@
 #include <linux/crc32c.h>
 #include "ctree.h"
 #include "extent-tree.h"
-#include "tree-log.h"
+#include "transaction.h"
 #include "disk-io.h"
 #include "print-tree.h"
 #include "volumes.h"
@@ -26,14 +26,11 @@
 #include "locking.h"
 #include "free-space-cache.h"
 #include "free-space-tree.h"
-#include "sysfs.h"
 #include "qgroup.h"
 #include "ref-verify.h"
 #include "space-info.h"
 #include "block-rsv.h"
-#include "delalloc-space.h"
 #include "discard.h"
-#include "rcu-string.h"
 #include "zoned.h"
 #include "dev-replace.h"
 #include "fs.h"
@@ -2399,7 +2396,14 @@ static noinline int check_committed_ref(struct btrfs_root *root,
 	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
 	if (ret < 0)
 		goto out;
-	BUG_ON(ret == 0); /* Corruption */
+	if (ret == 0) {
+		/*
+		 * Key with offset -1 found, there would have to exist an extent
+		 * item with such offset, but this is out of the valid range.
+		 */
+		ret = -EUCLEAN;
+		goto out;
+	}
 
 	ret = -ENOENT;
 	if (path->slots[0] == 0)
@@ -2780,6 +2784,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 	u64 total_unpinned = 0;
 	u64 empty_cluster = 0;
 	bool readonly;
+	int ret = 0;
 
 	while (start <= end) {
 		readonly = false;
@@ -2789,7 +2794,11 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 				btrfs_put_block_group(cache);
 			total_unpinned = 0;
 			cache = btrfs_lookup_block_group(fs_info, start);
-			BUG_ON(!cache); /* Logic error */
+			if (cache == NULL) {
+				/* Logic error, something removed the block group. */
+				ret = -EUCLEAN;
+				goto out;
+			}
 
 			cluster = fetch_cluster_info(fs_info,
 						     cache->space_info,
@@ -2858,7 +2867,8 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 
 	if (cache)
 		btrfs_put_block_group(cache);
-	return 0;
+out:
+	return ret;
 }
 
 int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
@@ -2888,7 +2898,8 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 						   end + 1 - start, NULL);
 
 		clear_extent_dirty(unpin, start, end, &cached_state);
-		unpin_extent_range(fs_info, start, end, true);
+		ret = unpin_extent_range(fs_info, start, end, true);
+		BUG_ON(ret);
 		mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 		free_extent_state(cached_state);
 		cond_resched();
@@ -3447,16 +3458,25 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			   u64 parent, int last_ref)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_ref generic_ref = { 0 };
 	struct btrfs_block_group *bg;
 	int ret;
 
-	btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF,
-			       buf->start, buf->len, parent, btrfs_header_owner(buf));
-	btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf),
-			    root_id, 0, false);
-
 	if (root_id != BTRFS_TREE_LOG_OBJECTID) {
+		struct btrfs_ref generic_ref = { 0 };
+
+		/*
+		 * Assert that the extent buffer is not cleared due to
+		 * EXTENT_BUFFER_ZONED_ZEROOUT. Please refer
+		 * btrfs_clear_buffer_dirty() and btree_csum_one_bio() for
+		 * detail.
+		 */
+		ASSERT(btrfs_header_bytenr(buf) != 0);
+
+		btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF,
+				       buf->start, buf->len, parent,
+				       btrfs_header_owner(buf));
+		btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf),
+				    root_id, 0, false);
 		btrfs_ref_tree_mod(fs_info, &generic_ref);
 		ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL);
 		BUG_ON(ret); /* -ENOMEM */
@@ -4950,7 +4970,7 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 	u64 root_objectid = root->root_key.objectid;
 	u64 owning_root = root_objectid;
 
-	BUG_ON(root_objectid == BTRFS_TREE_LOG_OBJECTID);
+	ASSERT(root_objectid != BTRFS_TREE_LOG_OBJECTID);
 
 	if (btrfs_is_data_reloc_root(root) && is_fstree(root->relocation_src_root))
 		owning_root = root->relocation_src_root;
@@ -6167,10 +6187,13 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
-				   u64 start, u64 end)
+/*
+ * Unpin the extent range in an error context and don't add the space back.
+ * Errors are not propagated further.
+ */
+void btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, u64 start, u64 end)
 {
-	return unpin_extent_range(fs_info, start, end, false);
+	unpin_extent_range(fs_info, start, end, false);
 }
 
 /*
diff --git a/fs/btrfs/extent-tree.h b/fs/btrfs/extent-tree.h
index 2e066035cc..af9f8800d5 100644
--- a/fs/btrfs/extent-tree.h
+++ b/fs/btrfs/extent-tree.h
@@ -3,11 +3,21 @@
 #ifndef BTRFS_EXTENT_TREE_H
 #define BTRFS_EXTENT_TREE_H
 
+#include <linux/types.h>
 #include "misc.h"
 #include "block-group.h"
+#include "locking.h"
 
+struct extent_buffer;
 struct btrfs_free_cluster;
+struct btrfs_fs_info;
+struct btrfs_root;
+struct btrfs_path;
+struct btrfs_ref;
+struct btrfs_disk_key;
 struct btrfs_delayed_ref_head;
+struct btrfs_delayed_ref_root;
+struct btrfs_extent_inline_ref;
 
 enum btrfs_extent_allocation_policy {
 	BTRFS_EXTENT_ALLOC_CLUSTERED,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index b5175b9929..41173701f1 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -14,7 +14,6 @@
 #include <linux/pagevec.h>
 #include <linux/prefetch.h>
 #include <linux/fsverity.h>
-#include "misc.h"
 #include "extent_io.h"
 #include "extent-io-tree.h"
 #include "extent_map.h"
@@ -22,7 +21,6 @@
 #include "btrfs_inode.h"
 #include "bio.h"
 #include "locking.h"
-#include "rcu-string.h"
 #include "backref.h"
 #include "disk-io.h"
 #include "subpage.h"
@@ -78,10 +76,11 @@ void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info)
 		eb = list_first_entry(&fs_info->allocated_ebs,
 				      struct extent_buffer, leak_list);
 		pr_err(
-	"BTRFS: buffer leak start %llu len %lu refs %d bflags %lu owner %llu\n",
+	"BTRFS: buffer leak start %llu len %u refs %d bflags %lu owner %llu\n",
 		       eb->start, eb->len, atomic_read(&eb->refs), eb->bflags,
 		       btrfs_header_owner(eb));
 		list_del(&eb->leak_list);
+		WARN_ON_ONCE(1);
 		kmem_cache_free(extent_buffer_cache, eb);
 	}
 	spin_unlock_irqrestore(&fs_info->eb_leak_lock, flags);
@@ -147,8 +146,8 @@ static void submit_write_bio(struct btrfs_bio_ctrl *bio_ctrl, int ret)
 int __init extent_buffer_init_cachep(void)
 {
 	extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer",
-			sizeof(struct extent_buffer), 0,
-			SLAB_MEM_SPREAD, NULL);
+						sizeof(struct extent_buffer), 0, 0,
+						NULL);
 	if (!extent_buffer_cache)
 		return -ENOMEM;
 
@@ -462,16 +461,15 @@ static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
  */
 static void end_bbio_data_write(struct btrfs_bio *bbio)
 {
+	struct btrfs_fs_info *fs_info = bbio->fs_info;
 	struct bio *bio = &bbio->bio;
 	int error = blk_status_to_errno(bio->bi_status);
 	struct folio_iter fi;
+	const u32 sectorsize = fs_info->sectorsize;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_folio_all(fi, bio) {
 		struct folio *folio = fi.folio;
-		struct inode *inode = folio->mapping->host;
-		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-		const u32 sectorsize = fs_info->sectorsize;
 		u64 start = folio_pos(folio) + fi.offset;
 		u32 len = fi.length;
 
@@ -593,22 +591,17 @@ static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page)
  */
 static void end_bbio_data_read(struct btrfs_bio *bbio)
 {
+	struct btrfs_fs_info *fs_info = bbio->fs_info;
 	struct bio *bio = &bbio->bio;
 	struct processed_extent processed = { 0 };
 	struct folio_iter fi;
-	/*
-	 * The offset to the beginning of a bio, since one bio can never be
-	 * larger than UINT_MAX, u32 here is enough.
-	 */
-	u32 bio_offset = 0;
+	const u32 sectorsize = fs_info->sectorsize;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_folio_all(fi, &bbio->bio) {
 		bool uptodate = !bio->bi_status;
 		struct folio *folio = fi.folio;
 		struct inode *inode = folio->mapping->host;
-		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-		const u32 sectorsize = fs_info->sectorsize;
 		u64 start;
 		u64 end;
 		u32 len;
@@ -667,10 +660,6 @@ static void end_bbio_data_read(struct btrfs_bio *bbio)
 		end_page_read(folio_page(folio, 0), uptodate, start, len);
 		endio_readpage_release_extent(&processed, BTRFS_I(inode),
 					      start, end, uptodate);
-
-		ASSERT(bio_offset + len > bio_offset);
-		bio_offset += len;
-
 	}
 	/* Release the last extent */
 	endio_readpage_release_extent(&processed, NULL, 0, 0, false);
@@ -728,6 +717,8 @@ static int alloc_eb_folio_array(struct extent_buffer *eb, gfp_t extra_gfp)
 
 	for (int i = 0; i < num_pages; i++)
 		eb->folios[i] = page_folio(page_array[i]);
+	eb->folio_size = PAGE_SIZE;
+	eb->folio_shift = PAGE_SHIFT;
 	return 0;
 }
 
@@ -964,13 +955,14 @@ void clear_page_extent_mapped(struct page *page)
 	folio_detach_private(folio);
 }
 
-static struct extent_map *
-__get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
+static struct extent_map *__get_extent_map(struct inode *inode, struct page *page,
 		 u64 start, u64 len, struct extent_map **em_cached)
 {
 	struct extent_map *em;
 
-	if (em_cached && *em_cached) {
+	ASSERT(em_cached);
+
+	if (*em_cached) {
 		em = *em_cached;
 		if (extent_map_in_tree(em) && start >= em->start &&
 		    start < extent_map_end(em)) {
@@ -982,8 +974,8 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
 		*em_cached = NULL;
 	}
 
-	em = btrfs_get_extent(BTRFS_I(inode), page, pg_offset, start, len);
-	if (em_cached && !IS_ERR(em)) {
+	em = btrfs_get_extent(BTRFS_I(inode), page, start, len);
+	if (!IS_ERR(em)) {
 		BUG_ON(*em_cached);
 		refcount_inc(&em->refs);
 		*em_cached = em;
@@ -1045,8 +1037,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 			end_page_read(page, true, cur, iosize);
 			break;
 		}
-		em = __get_extent_map(inode, page, pg_offset, cur,
-				      end - cur + 1, em_cached);
+		em = __get_extent_map(inode, page, cur, end - cur + 1, em_cached);
 		if (IS_ERR(em)) {
 			unlock_extent(tree, cur, end, NULL);
 			end_page_read(page, false, cur, end + 1 - cur);
@@ -1155,11 +1146,14 @@ int btrfs_read_folio(struct file *file, struct folio *folio)
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_SIZE - 1;
 	struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ };
+	struct extent_map *em_cached = NULL;
 	int ret;
 
 	btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);
 
-	ret = btrfs_do_readpage(page, NULL, &bio_ctrl, NULL);
+	ret = btrfs_do_readpage(page, &em_cached, &bio_ctrl, NULL);
+	free_extent_map(em_cached);
+
 	/*
 	 * If btrfs_do_readpage() failed we will want to submit the assembled
 	 * bio to do the cleanup.
@@ -1177,6 +1171,8 @@ static inline void contiguous_readpages(struct page *pages[], int nr_pages,
 	struct btrfs_inode *inode = page_to_inode(pages[0]);
 	int index;
 
+	ASSERT(em_cached);
+
 	btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);
 
 	for (index = 0; index < nr_pages; index++) {
@@ -1365,7 +1361,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 			continue;
 		}
 
-		em = btrfs_get_extent(inode, NULL, 0, cur, len);
+		em = btrfs_get_extent(inode, NULL, cur, len);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR_OR_ZERO(em);
 			goto out_error;
@@ -1733,10 +1729,10 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
 			folio_lock(folio);
 			folio_clear_dirty_for_io(folio);
 			folio_start_writeback(folio);
-			ret = bio_add_folio(&bbio->bio, folio, folio_size(folio), 0);
+			ret = bio_add_folio(&bbio->bio, folio, eb->folio_size, 0);
 			ASSERT(ret);
 			wbc_account_cgroup_owner(wbc, folio_page(folio, 0),
-						 folio_size(folio));
+						 eb->folio_size);
 			wbc->nr_to_write -= folio_nr_pages(folio);
 			folio_unlock(folio);
 		}
@@ -2746,7 +2742,7 @@ static int emit_last_fiemap_cache(struct fiemap_extent_info *fieinfo,
 
 static int fiemap_next_leaf_item(struct btrfs_inode *inode, struct btrfs_path *path)
 {
-	struct extent_buffer *clone;
+	struct extent_buffer *clone = path->nodes[0];
 	struct btrfs_key key;
 	int slot;
 	int ret;
@@ -2755,29 +2751,51 @@ static int fiemap_next_leaf_item(struct btrfs_inode *inode, struct btrfs_path *p
 	if (path->slots[0] < btrfs_header_nritems(path->nodes[0]))
 		return 0;
 
+	/*
+	 * Add a temporary extra ref to an already cloned extent buffer to
+	 * prevent btrfs_next_leaf() freeing it, we want to reuse it to avoid
+	 * the cost of allocating a new one.
+	 */
+	ASSERT(test_bit(EXTENT_BUFFER_UNMAPPED, &clone->bflags));
+	atomic_inc(&clone->refs);
+
 	ret = btrfs_next_leaf(inode->root, path);
 	if (ret != 0)
-		return ret;
+		goto out;
 
 	/*
 	 * Don't bother with cloning if there are no more file extent items for
 	 * our inode.
 	 */
 	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
-	if (key.objectid != btrfs_ino(inode) || key.type != BTRFS_EXTENT_DATA_KEY)
-		return 1;
+	if (key.objectid != btrfs_ino(inode) || key.type != BTRFS_EXTENT_DATA_KEY) {
+		ret = 1;
+		goto out;
+	}
 
+	/*
+	 * Important to preserve the start field, for the optimizations when
+	 * checking if extents are shared (see extent_fiemap()).
+	 *
+	 * We must set ->start before calling copy_extent_buffer_full().  If we
+	 * are on sub-pagesize blocksize, we use ->start to determine the offset
+	 * into the folio where our eb exists, and if we update ->start after
+	 * the fact then any subsequent reads of the eb may read from a
+	 * different offset in the folio than where we originally copied into.
+	 */
+	clone->start = path->nodes[0]->start;
 	/* See the comment at fiemap_search_slot() about why we clone. */
-	clone = btrfs_clone_extent_buffer(path->nodes[0]);
-	if (!clone)
-		return -ENOMEM;
+	copy_extent_buffer_full(clone, path->nodes[0]);
 
 	slot = path->slots[0];
 	btrfs_release_path(path);
 	path->nodes[0] = clone;
 	path->slots[0] = slot;
+out:
+	if (ret)
+		free_extent_buffer(clone);
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -3644,6 +3662,8 @@ static struct extent_buffer *grab_extent_buffer(
 	struct folio *folio = page_folio(page);
 	struct extent_buffer *exists;
 
+	lockdep_assert_held(&page->mapping->i_private_lock);
+
 	/*
 	 * For subpage case, we completely rely on radix tree to ensure we
 	 * don't try to insert two ebs for the same bytenr.  So here we always
@@ -3711,13 +3731,14 @@ static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start)
  * The caller needs to free the existing folios and retry using the same order.
  */
 static int attach_eb_folio_to_filemap(struct extent_buffer *eb, int i,
+				      struct btrfs_subpage *prealloc,
 				      struct extent_buffer **found_eb_ret)
 {
 
 	struct btrfs_fs_info *fs_info = eb->fs_info;
 	struct address_space *mapping = fs_info->btree_inode->i_mapping;
 	const unsigned long index = eb->start >> PAGE_SHIFT;
-	struct folio *existing_folio;
+	struct folio *existing_folio = NULL;
 	int ret;
 
 	ASSERT(found_eb_ret);
@@ -3729,30 +3750,31 @@ retry:
 	ret = filemap_add_folio(mapping, eb->folios[i], index + i,
 				GFP_NOFS | __GFP_NOFAIL);
 	if (!ret)
-		return 0;
+		goto finish;
 
 	existing_folio = filemap_lock_folio(mapping, index + i);
 	/* The page cache only exists for a very short time, just retry. */
-	if (IS_ERR(existing_folio))
+	if (IS_ERR(existing_folio)) {
+		existing_folio = NULL;
 		goto retry;
+	}
 
 	/* For now, we should only have single-page folios for btree inode. */
 	ASSERT(folio_nr_pages(existing_folio) == 1);
 
-	if (folio_size(existing_folio) != folio_size(eb->folios[0])) {
+	if (folio_size(existing_folio) != eb->folio_size) {
 		folio_unlock(existing_folio);
 		folio_put(existing_folio);
 		return -EAGAIN;
 	}
 
-	if (fs_info->nodesize < PAGE_SIZE) {
-		/*
-		 * We're going to reuse the existing page, can drop our page
-		 * and subpage structure now.
-		 */
+finish:
+	spin_lock(&mapping->i_private_lock);
+	if (existing_folio && fs_info->nodesize < PAGE_SIZE) {
+		/* We're going to reuse the existing page, can drop our folio now. */
 		__free_page(folio_page(eb->folios[i], 0));
 		eb->folios[i] = existing_folio;
-	} else {
+	} else if (existing_folio) {
 		struct extent_buffer *existing_eb;
 
 		existing_eb = grab_extent_buffer(fs_info,
@@ -3760,6 +3782,7 @@ retry:
 		if (existing_eb) {
 			/* The extent buffer still exists, we can use it directly. */
 			*found_eb_ret = existing_eb;
+			spin_unlock(&mapping->i_private_lock);
 			folio_unlock(existing_folio);
 			folio_put(existing_folio);
 			return 1;
@@ -3768,6 +3791,22 @@ retry:
 		__free_page(folio_page(eb->folios[i], 0));
 		eb->folios[i] = existing_folio;
 	}
+	eb->folio_size = folio_size(eb->folios[i]);
+	eb->folio_shift = folio_shift(eb->folios[i]);
+	/* Should not fail, as we have preallocated the memory. */
+	ret = attach_extent_buffer_folio(eb, eb->folios[i], prealloc);
+	ASSERT(!ret);
+	/*
+	 * To inform we have an extra eb under allocation, so that
+	 * detach_extent_buffer_page() won't release the folio private when the
+	 * eb hasn't been inserted into radix tree yet.
+	 *
+	 * The ref will be decreased when the eb releases the page, in
+	 * detach_extent_buffer_page().  Thus needs no special handling in the
+	 * error path.
+	 */
+	btrfs_folio_inc_eb_refs(fs_info, eb->folios[i]);
+	spin_unlock(&mapping->i_private_lock);
 	return 0;
 }
 
@@ -3779,7 +3818,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	int attached = 0;
 	struct extent_buffer *eb;
 	struct extent_buffer *existing_eb = NULL;
-	struct address_space *mapping = fs_info->btree_inode->i_mapping;
 	struct btrfs_subpage *prealloc = NULL;
 	u64 lockdep_owner = owner_root;
 	bool page_contig = true;
@@ -3845,7 +3883,7 @@ reallocate:
 	for (int i = 0; i < num_folios; i++) {
 		struct folio *folio;
 
-		ret = attach_eb_folio_to_filemap(eb, i, &existing_eb);
+		ret = attach_eb_folio_to_filemap(eb, i, prealloc, &existing_eb);
 		if (ret > 0) {
 			ASSERT(existing_eb);
 			goto out;
@@ -3882,22 +3920,6 @@ reallocate:
 		 * and free the allocated page.
 		 */
 		folio = eb->folios[i];
-		spin_lock(&mapping->i_private_lock);
-		/* Should not fail, as we have preallocated the memory */
-		ret = attach_extent_buffer_folio(eb, folio, prealloc);
-		ASSERT(!ret);
-		/*
-		 * To inform we have extra eb under allocation, so that
-		 * detach_extent_buffer_page() won't release the folio private
-		 * when the eb hasn't yet been inserted into radix tree.
-		 *
-		 * The ref will be decreased when the eb released the page, in
-		 * detach_extent_buffer_page().
-		 * Thus needs no special handling in error path.
-		 */
-		btrfs_folio_inc_eb_refs(fs_info, folio);
-		spin_unlock(&mapping->i_private_lock);
-
 		WARN_ON(btrfs_folio_test_dirty(fs_info, folio, eb->start, eb->len));
 
 		/*
@@ -4169,6 +4191,7 @@ void set_extent_buffer_dirty(struct extent_buffer *eb)
 	num_folios = num_extent_folios(eb);
 	WARN_ON(atomic_read(&eb->refs) == 0);
 	WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
+	WARN_ON(test_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags));
 
 	if (!was_dirty) {
 		bool subpage = eb->fs_info->nodesize < PAGE_SIZE;
@@ -4344,7 +4367,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
 		for (int i = 0; i < num_folios; i++) {
 			struct folio *folio = eb->folios[i];
 
-			ret = bio_add_folio(&bbio->bio, folio, folio_size(folio), 0);
+			ret = bio_add_folio(&bbio->bio, folio, eb->folio_size, 0);
 			ASSERT(ret);
 		}
 	}
@@ -4364,7 +4387,7 @@ static bool report_eb_range(const struct extent_buffer *eb, unsigned long start,
 			    unsigned long len)
 {
 	btrfs_warn(eb->fs_info,
-		"access to eb bytenr %llu len %lu out of range start %lu len %lu",
+		"access to eb bytenr %llu len %u out of range start %lu len %lu",
 		eb->start, eb->len, start, len);
 	WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
 
@@ -4393,7 +4416,7 @@ static inline int check_eb_range(const struct extent_buffer *eb,
 void read_extent_buffer(const struct extent_buffer *eb, void *dstv,
 			unsigned long start, unsigned long len)
 {
-	const int unit_size = folio_size(eb->folios[0]);
+	const int unit_size = eb->folio_size;
 	size_t cur;
 	size_t offset;
 	char *dst = (char *)dstv;
@@ -4433,7 +4456,7 @@ int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
 				       void __user *dstv,
 				       unsigned long start, unsigned long len)
 {
-	const int unit_size = folio_size(eb->folios[0]);
+	const int unit_size = eb->folio_size;
 	size_t cur;
 	size_t offset;
 	char __user *dst = (char __user *)dstv;
@@ -4473,7 +4496,7 @@ int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
 int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
 			 unsigned long start, unsigned long len)
 {
-	const int unit_size = folio_size(eb->folios[0]);
+	const int unit_size = eb->folio_size;
 	size_t cur;
 	size_t offset;
 	char *kaddr;
@@ -4544,7 +4567,7 @@ static void __write_extent_buffer(const struct extent_buffer *eb,
 				  const void *srcv, unsigned long start,
 				  unsigned long len, bool use_memmove)
 {
-	const int unit_size = folio_size(eb->folios[0]);
+	const int unit_size = eb->folio_size;
 	size_t cur;
 	size_t offset;
 	char *kaddr;
@@ -4593,7 +4616,7 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
 static void memset_extent_buffer(const struct extent_buffer *eb, int c,
 				 unsigned long start, unsigned long len)
 {
-	const int unit_size = folio_size(eb->folios[0]);
+	const int unit_size = eb->folio_size;
 	unsigned long cur = start;
 
 	if (eb->addr) {
@@ -4624,7 +4647,7 @@ void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start,
 void copy_extent_buffer_full(const struct extent_buffer *dst,
 			     const struct extent_buffer *src)
 {
-	const int unit_size = folio_size(src->folios[0]);
+	const int unit_size = src->folio_size;
 	unsigned long cur = 0;
 
 	ASSERT(dst->len == src->len);
@@ -4646,7 +4669,7 @@ void copy_extent_buffer(const struct extent_buffer *dst,
 			unsigned long dst_offset, unsigned long src_offset,
 			unsigned long len)
 {
-	const int unit_size = folio_size(dst->folios[0]);
+	const int unit_size = dst->folio_size;
 	u64 dst_len = dst->len;
 	size_t cur;
 	size_t offset;
@@ -4702,10 +4725,10 @@ static inline void eb_bitmap_offset(const struct extent_buffer *eb,
 	 * the bitmap item in the extent buffer + the offset of the byte in the
 	 * bitmap item.
 	 */
-	offset = start + offset_in_folio(eb->folios[0], eb->start) + byte_offset;
+	offset = start + offset_in_eb_folio(eb, eb->start) + byte_offset;
 
-	*folio_index = offset >> folio_shift(eb->folios[0]);
-	*folio_offset = offset_in_folio(eb->folios[0], offset);
+	*folio_index = offset >> eb->folio_shift;
+	*folio_offset = offset_in_eb_folio(eb, offset);
 }
 
 /*
@@ -4819,7 +4842,7 @@ void memcpy_extent_buffer(const struct extent_buffer *dst,
 			  unsigned long dst_offset, unsigned long src_offset,
 			  unsigned long len)
 {
-	const int unit_size = folio_size(dst->folios[0]);
+	const int unit_size = dst->folio_size;
 	unsigned long cur_off = 0;
 
 	if (check_eb_range(dst, dst_offset, len) ||
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 2c9d6570b0..e3530d427e 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -7,11 +7,32 @@
 #include <linux/refcount.h>
 #include <linux/fiemap.h>
 #include <linux/btrfs_tree.h>
+#include <linux/spinlock.h>
+#include <linux/atomic.h>
+#include <linux/rwsem.h>
+#include <linux/list.h>
+#include <linux/slab.h>
 #include "compression.h"
+#include "messages.h"
 #include "ulist.h"
 #include "misc.h"
 
+struct page;
+struct file;
+struct folio;
+struct inode;
+struct fiemap_extent_info;
+struct readahead_control;
+struct address_space;
+struct writeback_control;
+struct extent_io_tree;
+struct extent_map_tree;
+struct btrfs_block_group;
+struct btrfs_fs_info;
+struct btrfs_inode;
+struct btrfs_root;
 struct btrfs_trans_handle;
+struct btrfs_tree_parent_check;
 
 enum {
 	EXTENT_BUFFER_UPTODATE,
@@ -63,11 +84,6 @@ enum {
 #define BITMAP_LAST_BYTE_MASK(nbits) \
 	(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
 
-struct btrfs_root;
-struct btrfs_inode;
-struct btrfs_fs_info;
-struct extent_io_tree;
-struct btrfs_tree_parent_check;
 
 int __init extent_buffer_init_cachep(void);
 void __cold extent_buffer_free_cachep(void);
@@ -75,7 +91,8 @@ void __cold extent_buffer_free_cachep(void);
 #define INLINE_EXTENT_BUFFER_PAGES     (BTRFS_MAX_METADATA_BLOCKSIZE / PAGE_SIZE)
 struct extent_buffer {
 	u64 start;
-	unsigned long len;
+	u32 len;
+	u32 folio_size;
 	unsigned long bflags;
 	struct btrfs_fs_info *fs_info;
 
@@ -90,6 +107,7 @@ struct extent_buffer {
 	int read_mirror;
 	/* >= 0 if eb belongs to a log tree, -1 otherwise */
 	s8 log_index;
+	u8 folio_shift;
 	struct rcu_head rcu_head;
 
 	struct rw_semaphore lock;
@@ -113,6 +131,13 @@ struct btrfs_eb_write_context {
 	struct btrfs_block_group *zoned_bg;
 };
 
+static inline unsigned long offset_in_eb_folio(const struct extent_buffer *eb,
+					       u64 start)
+{
+	ASSERT(eb->folio_size);
+	return start & (eb->folio_size - 1);
+}
+
 /*
  * Get the correct offset inside the page of extent buffer.
  *
@@ -151,13 +176,13 @@ static inline unsigned long get_eb_folio_index(const struct extent_buffer *eb,
 	 *	   the folio_shift would be large enough to always make us
 	 *	   return 0 as index.
 	 *    1.2) Several page sized folios
-	 *         The folio_shift() would be PAGE_SHIFT, giving us the correct
+	 *         The folio_shift would be PAGE_SHIFT, giving us the correct
 	 *         index.
 	 *
 	 * 2) sectorsize < PAGE_SIZE and nodesize < PAGE_SIZE case
 	 *    The folio would only be page sized, and always give us 0 as index.
 	 */
-	return offset >> folio_shift(eb->folios[0]);
+	return offset >> eb->folio_shift;
 }
 
 /*
@@ -205,8 +230,6 @@ static inline void extent_changeset_free(struct extent_changeset *changeset)
 	kfree(changeset);
 }
 
-struct extent_map_tree;
-
 int try_release_extent_mapping(struct page *page, gfp_t mask);
 int try_release_extent_buffer(struct page *page);
 
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 54e111b5fa..24a048210b 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -5,7 +5,6 @@
 #include <linux/spinlock.h>
 #include "messages.h"
 #include "ctree.h"
-#include "volumes.h"
 #include "extent_map.h"
 #include "compression.h"
 #include "btrfs_inode.h"
@@ -16,8 +15,7 @@ static struct kmem_cache *extent_map_cache;
 int __init extent_map_init(void)
 {
 	extent_map_cache = kmem_cache_create("btrfs_extent_map",
-			sizeof(struct extent_map), 0,
-			SLAB_MEM_SPREAD, NULL);
+					     sizeof(struct extent_map), 0, 0, NULL);
 	if (!extent_map_cache)
 		return -ENOMEM;
 	return 0;
@@ -539,7 +537,8 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree,
 	u64 end;
 	u64 start_diff;
 
-	BUG_ON(map_start < em->start || map_start >= extent_map_end(em));
+	if (map_start < em->start || map_start >= extent_map_end(em))
+		return -EINVAL;
 
 	if (existing->start > map_start) {
 		next = existing;
@@ -630,13 +629,13 @@ int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
 			 */
 			ret = merge_extent_mapping(em_tree, existing,
 						   em, start);
-			if (ret) {
+			if (WARN_ON(ret)) {
 				free_extent_map(em);
 				*em_in = NULL;
-				WARN_ONCE(ret,
-"unexpected error %d: merge existing(start %llu len %llu) with em(start %llu len %llu)\n",
-					  ret, existing->start, existing->len,
-					  orig_start, orig_len);
+				btrfs_warn(fs_info,
+"extent map merge error existing [%llu, %llu) with em [%llu, %llu) start %llu",
+					   existing->start, extent_map_end(existing),
+					   orig_start, orig_start + orig_len, start);
 			}
 			free_extent_map(existing);
 		}
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index e380fc08bb..c5a098c99c 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -3,10 +3,18 @@
 #ifndef BTRFS_EXTENT_MAP_H
 #define BTRFS_EXTENT_MAP_H
 
+#include <linux/compiler_types.h>
+#include <linux/rwlock_types.h>
 #include <linux/rbtree.h>
+#include <linux/list.h>
 #include <linux/refcount.h>
+#include "misc.h"
+#include "extent_map.h"
 #include "compression.h"
 
+struct btrfs_inode;
+struct btrfs_fs_info;
+
 #define EXTENT_MAP_LAST_BYTE ((u64)-4)
 #define EXTENT_MAP_HOLE ((u64)-3)
 #define EXTENT_MAP_INLINE ((u64)-2)
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 81ac1d474b..e58fb5347e 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -10,17 +10,14 @@
 #include <linux/sched/mm.h>
 #include <crypto/hash.h>
 #include "messages.h"
-#include "misc.h"
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
 #include "bio.h"
-#include "print-tree.h"
 #include "compression.h"
 #include "fs.h"
 #include "accessors.h"
 #include "file-item.h"
-#include "super.h"
 
 #define __MAX_CSUM_ITEMS(r, size) ((unsigned long)(((BTRFS_LEAF_DATA_SIZE(r) - \
 				   sizeof(struct btrfs_item) * 2) / \
@@ -179,7 +176,6 @@ int btrfs_insert_hole_extent(struct btrfs_trans_handle *trans,
 				      sizeof(*item));
 	if (ret < 0)
 		goto out;
-	BUG_ON(ret); /* Can't happen */
 	leaf = path->nodes[0];
 	item = btrfs_item_ptr(leaf, path->slots[0],
 			      struct btrfs_file_extent_item);
@@ -1229,8 +1225,6 @@ insert:
 				      ins_size);
 	if (ret < 0)
 		goto out;
-	if (WARN_ON(ret != 0))
-		goto out;
 	leaf = path->nodes[0];
 csum:
 	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_csum_item);
diff --git a/fs/btrfs/file-item.h b/fs/btrfs/file-item.h
index 04bd2d34ef..15c05cc0fc 100644
--- a/fs/btrfs/file-item.h
+++ b/fs/btrfs/file-item.h
@@ -3,8 +3,21 @@
 #ifndef BTRFS_FILE_ITEM_H
 #define BTRFS_FILE_ITEM_H
 
+#include <linux/list.h>
+#include <uapi/linux/btrfs_tree.h>
 #include "accessors.h"
 
+struct extent_map;
+struct btrfs_file_extent_item;
+struct btrfs_fs_info;
+struct btrfs_path;
+struct btrfs_bio;
+struct btrfs_trans_handle;
+struct btrfs_root;
+struct btrfs_ordered_sum;
+struct btrfs_path;
+struct btrfs_inode;
+
 #define BTRFS_FILE_EXTENT_INLINE_DATA_START		\
 		(offsetof(struct btrfs_file_extent_item, disk_bytenr))
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 616790d6e5..f9d7607239 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -22,10 +22,8 @@
 #include "disk-io.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
-#include "print-tree.h"
 #include "tree-log.h"
 #include "locking.h"
-#include "volumes.h"
 #include "qgroup.h"
 #include "compression.h"
 #include "delalloc-space.h"
@@ -1912,6 +1910,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		goto out_release_extents;
 	}
 
+	btrfs_init_log_ctx_scratch_eb(&ctx);
+
 	/*
 	 * We use start here because we will need to wait on the IO to complete
 	 * in btrfs_sync_log, which could require joining a transaction (for
@@ -1931,6 +1931,15 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	trans->in_fsync = true;
 
 	ret = btrfs_log_dentry_safe(trans, dentry, &ctx);
+	/*
+	 * Scratch eb no longer needed, release before syncing log or commit
+	 * transaction, to avoid holding unnecessary memory during such long
+	 * operations.
+	 */
+	if (ctx.scratch_eb) {
+		free_extent_buffer(ctx.scratch_eb);
+		ctx.scratch_eb = NULL;
+	}
 	btrfs_release_log_ctx_extents(&ctx);
 	if (ret < 0) {
 		/* Fallthrough and commit/free transaction. */
@@ -2006,6 +2015,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	ret = btrfs_commit_transaction(trans);
 out:
+	free_extent_buffer(ctx.scratch_eb);
 	ASSERT(list_empty(&ctx.list));
 	ASSERT(list_empty(&ctx.conflict_inodes));
 	err = file_check_and_advance_wb_err(file);
@@ -2176,7 +2186,7 @@ static int find_first_non_hole(struct btrfs_inode *inode, u64 *start, u64 *len)
 	struct extent_map *em;
 	int ret = 0;
 
-	em = btrfs_get_extent(inode, NULL, 0,
+	em = btrfs_get_extent(inode, NULL,
 			      round_down(*start, fs_info->sectorsize),
 			      round_up(*len, fs_info->sectorsize));
 	if (IS_ERR(em))
@@ -2835,7 +2845,7 @@ static int btrfs_zero_range_check_range_boundary(struct btrfs_inode *inode,
 	int ret;
 
 	offset = round_down(offset, sectorsize);
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(inode, NULL, offset, sectorsize);
 	if (IS_ERR(em))
 		return PTR_ERR(em);
 
@@ -2866,7 +2876,7 @@ static int btrfs_zero_range(struct inode *inode,
 	u64 bytes_to_reserve = 0;
 	bool space_reserved = false;
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, alloc_start,
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, alloc_start,
 			      alloc_end - alloc_start);
 	if (IS_ERR(em)) {
 		ret = PTR_ERR(em);
@@ -2909,8 +2919,7 @@ static int btrfs_zero_range(struct inode *inode,
 
 	if (BTRFS_BYTES_TO_BLKS(fs_info, offset) ==
 	    BTRFS_BYTES_TO_BLKS(fs_info, offset + len - 1)) {
-		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, alloc_start,
-				      sectorsize);
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, alloc_start, sectorsize);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
 			goto out;
@@ -3005,7 +3014,7 @@ reserve_space:
 		}
 		ret = btrfs_prealloc_file_range(inode, mode, alloc_start,
 						alloc_end - alloc_start,
-						i_blocksize(inode),
+						fs_info->sectorsize,
 						offset + len, &alloc_hint);
 		unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			      &cached_state);
@@ -3126,7 +3135,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 
 	/* First, check if we exceed the qgroup limit */
 	while (cur_offset < alloc_end) {
-		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset,
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, cur_offset,
 				      alloc_end - cur_offset);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
@@ -3177,7 +3186,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 		if (!ret) {
 			ret = btrfs_prealloc_file_range(inode, mode,
 					range->start,
-					range->len, i_blocksize(inode),
+					range->len, blocksize,
 					offset + len, &alloc_hint);
 			/*
 			 * btrfs_prealloc_file_range() releases space even
diff --git a/fs/btrfs/file.h b/fs/btrfs/file.h
index 82b34fbb29..77aaca208c 100644
--- a/fs/btrfs/file.h
+++ b/fs/btrfs/file.h
@@ -3,6 +3,21 @@
 #ifndef BTRFS_FILE_H
 #define BTRFS_FILE_H
 
+#include <linux/types.h>
+
+struct file;
+struct extent_state;
+struct kiocb;
+struct iov_iter;
+struct page;
+struct btrfs_ioctl_encoded_io_args;
+struct btrfs_drop_extents_args;
+struct btrfs_inode;
+struct btrfs_root;
+struct btrfs_path;
+struct btrfs_replace_extent_info;
+struct btrfs_trans_handle;
+
 extern const struct file_operations btrfs_file_operations;
 
 int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 815bb146b1..c8a05d5eb9 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -19,9 +19,7 @@
 #include "transaction.h"
 #include "disk-io.h"
 #include "extent_io.h"
-#include "volumes.h"
 #include "space-info.h"
-#include "delalloc-space.h"
 #include "block-group.h"
 #include "discard.h"
 #include "subpage.h"
@@ -2621,7 +2619,7 @@ static void steal_from_bitmap(struct btrfs_free_space_ctl *ctl,
 	}
 }
 
-int __btrfs_add_free_space(struct btrfs_block_group *block_group,
+static int __btrfs_add_free_space(struct btrfs_block_group *block_group,
 			   u64 offset, u64 bytes,
 			   enum btrfs_trim_state trim_state)
 {
@@ -4156,15 +4154,13 @@ out:
 
 int __init btrfs_free_space_init(void)
 {
-	btrfs_free_space_cachep = kmem_cache_create("btrfs_free_space",
-			sizeof(struct btrfs_free_space), 0,
-			SLAB_MEM_SPREAD, NULL);
+	btrfs_free_space_cachep = KMEM_CACHE(btrfs_free_space, 0);
 	if (!btrfs_free_space_cachep)
 		return -ENOMEM;
 
 	btrfs_free_space_bitmap_cachep = kmem_cache_create("btrfs_free_space_bitmap",
 							PAGE_SIZE, PAGE_SIZE,
-							SLAB_MEM_SPREAD, NULL);
+							0, NULL);
 	if (!btrfs_free_space_bitmap_cachep) {
 		kmem_cache_destroy(btrfs_free_space_cachep);
 		return -ENOMEM;
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 33b4da3271..83774bfd7b 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -6,6 +6,19 @@
 #ifndef BTRFS_FREE_SPACE_CACHE_H
 #define BTRFS_FREE_SPACE_CACHE_H
 
+#include <linux/rbtree.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include "fs.h"
+
+struct inode;
+struct page;
+struct btrfs_fs_info;
+struct btrfs_path;
+struct btrfs_trans_handle;
+struct btrfs_trim_block_group;
+
 /*
  * This is the trim state of an extent or bitmap.
  *
@@ -114,8 +127,6 @@ int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
 
 void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group,
 			       struct btrfs_free_space_ctl *ctl);
-int __btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr,
-			   u64 size, enum btrfs_trim_state trim_state);
 int btrfs_add_free_space(struct btrfs_block_group *block_group,
 			 u64 bytenr, u64 size);
 int btrfs_add_free_space_unused(struct btrfs_block_group *block_group,
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 7b598b0707..90f2938bd7 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1176,12 +1176,16 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
 					    BTRFS_FREE_SPACE_TREE_OBJECTID);
 	if (IS_ERR(free_space_root)) {
 		ret = PTR_ERR(free_space_root);
-		goto abort;
+		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
+		goto out_clear;
 	}
 	ret = btrfs_global_root_insert(free_space_root);
 	if (ret) {
 		btrfs_put_root(free_space_root);
-		goto abort;
+		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
+		goto out_clear;
 	}
 
 	node = rb_first_cached(&fs_info->block_group_cache_tree);
@@ -1189,8 +1193,11 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
 		block_group = rb_entry(node, struct btrfs_block_group,
 				       cache_node);
 		ret = populate_free_space_tree(trans, block_group);
-		if (ret)
-			goto abort;
+		if (ret) {
+			btrfs_abort_transaction(trans, ret);
+			btrfs_end_transaction(trans);
+			goto out_clear;
+		}
 		node = rb_next(node);
 	}
 
@@ -1206,11 +1213,9 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
 	clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
 	return ret;
 
-abort:
+out_clear:
 	clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
 	clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
-	btrfs_abort_transaction(trans, ret);
-	btrfs_end_transaction(trans);
 	return ret;
 }
 
@@ -1273,12 +1278,18 @@ int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info)
 	btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID);
 
 	ret = clear_free_space_tree(trans, free_space_root);
-	if (ret)
-		goto abort;
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
+		return ret;
+	}
 
 	ret = btrfs_del_root(trans, &free_space_root->root_key);
-	if (ret)
-		goto abort;
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
+		return ret;
+	}
 
 	btrfs_global_root_delete(free_space_root);
 
@@ -1295,11 +1306,6 @@ int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info)
 	btrfs_put_root(free_space_root);
 
 	return btrfs_commit_transaction(trans);
-
-abort:
-	btrfs_abort_transaction(trans, ret);
-	btrfs_end_transaction(trans);
-	return ret;
 }
 
 int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info)
@@ -1322,8 +1328,11 @@ int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info)
 	set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
 
 	ret = clear_free_space_tree(trans, free_space_root);
-	if (ret)
-		goto abort;
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
+		return ret;
+	}
 
 	node = rb_first_cached(&fs_info->block_group_cache_tree);
 	while (node) {
@@ -1332,8 +1341,11 @@ int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info)
 		block_group = rb_entry(node, struct btrfs_block_group,
 				       cache_node);
 		ret = populate_free_space_tree(trans, block_group);
-		if (ret)
-			goto abort;
+		if (ret) {
+			btrfs_abort_transaction(trans, ret);
+			btrfs_end_transaction(trans);
+			return ret;
+		}
 		node = rb_next(node);
 	}
 
@@ -1344,10 +1356,6 @@ int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info)
 	ret = btrfs_commit_transaction(trans);
 	clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
 	return ret;
-abort:
-	btrfs_abort_transaction(trans, ret);
-	btrfs_end_transaction(trans);
-	return ret;
 }
 
 static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h
index 6d5551d0ce..e6c6d6f4f2 100644
--- a/fs/btrfs/free-space-tree.h
+++ b/fs/btrfs/free-space-tree.h
@@ -6,7 +6,13 @@
 #ifndef BTRFS_FREE_SPACE_TREE_H
 #define BTRFS_FREE_SPACE_TREE_H
 
+#include <linux/bits.h>
+
 struct btrfs_caching_control;
+struct btrfs_fs_info;
+struct btrfs_path;
+struct btrfs_block_group;
+struct btrfs_trans_handle;
 
 /*
  * The default size for new free space bitmap items. The last bitmap in a block
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index bd59cf0aae..93f5c57ea4 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -4,13 +4,50 @@
 #define BTRFS_FS_H
 
 #include <linux/blkdev.h>
-#include <linux/fs.h>
-#include <linux/btrfs_tree.h>
 #include <linux/sizes.h>
+#include <linux/time64.h>
+#include <linux/compiler.h>
+#include <linux/math.h>
+#include <linux/atomic.h>
+#include <linux/blkdev.h>
+#include <linux/percpu_counter.h>
+#include <linux/completion.h>
+#include <linux/lockdep.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/rwlock_types.h>
+#include <linux/rwsem.h>
+#include <linux/semaphore.h>
+#include <linux/list.h>
+#include <linux/radix-tree.h>
+#include <linux/workqueue.h>
+#include <linux/wait.h>
+#include <linux/wait_bit.h>
+#include <linux/sched.h>
+#include <linux/rbtree.h>
+#include <uapi/linux/btrfs.h>
+#include <uapi/linux/btrfs_tree.h>
 #include "extent-io-tree.h"
-#include "extent_map.h"
 #include "async-thread.h"
 #include "block-rsv.h"
+#include "fs.h"
+
+struct inode;
+struct super_block;
+struct kobject;
+struct reloc_control;
+struct crypto_shash;
+struct ulist;
+struct btrfs_device;
+struct btrfs_block_group;
+struct btrfs_root;
+struct btrfs_fs_devices;
+struct btrfs_transaction;
+struct btrfs_delayed_root;
+struct btrfs_balance_control;
+struct btrfs_subpage_info;
+struct btrfs_stripe_hash_table;
+struct btrfs_space_info;
 
 #define BTRFS_MAX_EXTENT_SIZE SZ_128M
 
@@ -732,10 +769,13 @@ struct btrfs_fs_info {
 
 	/* Reclaim partially filled block groups in the background */
 	struct work_struct reclaim_bgs_work;
+	/* Protected by unused_bgs_lock. */
 	struct list_head reclaim_bgs;
 	int bg_reclaim_threshold;
 
+	/* Protects the lists unused_bgs and reclaim_bgs. */
 	spinlock_t unused_bgs_lock;
+	/* Protected by unused_bgs_lock. */
 	struct list_head unused_bgs;
 	struct mutex unused_bg_unpin_mutex;
 	/* Protect block groups that are going to be deleted */
@@ -933,6 +973,8 @@ void btrfs_exclop_finish(struct btrfs_fs_info *fs_info);
 void btrfs_exclop_balance(struct btrfs_fs_info *fs_info,
 			  enum btrfs_exclusive_operation op);
 
+int btrfs_check_ioctl_vol_args_path(const struct btrfs_ioctl_vol_args *vol_args);
+
 /* Compatibility and incompatibility defines */
 void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag,
 			     const char *name);
diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c
index 7d734830e5..9c1394c0a6 100644
--- a/fs/btrfs/inode-item.c
+++ b/fs/btrfs/inode-item.c
@@ -9,7 +9,6 @@
 #include "inode-item.h"
 #include "disk-io.h"
 #include "transaction.h"
-#include "print-tree.h"
 #include "space-info.h"
 #include "accessors.h"
 #include "extent-tree.h"
diff --git a/fs/btrfs/inode-item.h b/fs/btrfs/inode-item.h
index 4337bb26f4..c4aded8270 100644
--- a/fs/btrfs/inode-item.h
+++ b/fs/btrfs/inode-item.h
@@ -6,14 +6,15 @@
 #include <linux/types.h>
 #include <linux/crc32c.h>
 
+struct fscrypt_str;
+struct extent_buffer;
 struct btrfs_trans_handle;
 struct btrfs_root;
 struct btrfs_path;
 struct btrfs_key;
 struct btrfs_inode_extref;
 struct btrfs_inode;
-struct extent_buffer;
-struct fscrypt_str;
+struct btrfs_truncate_control;
 
 /*
  * Return this if we need to call truncate_block for the last bit of the
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d3c534c1bf..7fed887e70 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -39,14 +39,12 @@
 #include "disk-io.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
-#include "print-tree.h"
 #include "ordered-data.h"
 #include "xattr.h"
 #include "tree-log.h"
 #include "bio.h"
 #include "compression.h"
 #include "locking.h"
-#include "free-space-cache.h"
 #include "props.h"
 #include "qgroup.h"
 #include "delalloc-space.h"
@@ -740,7 +738,8 @@ static noinline int add_async_extent(struct async_chunk *cow,
 	struct async_extent *async_extent;
 
 	async_extent = kmalloc(sizeof(*async_extent), GFP_NOFS);
-	BUG_ON(!async_extent); /* -ENOMEM */
+	if (!async_extent)
+		return -ENOMEM;
 	async_extent->start = start;
 	async_extent->ram_size = ram_size;
 	async_extent->compressed_size = compressed_size;
@@ -1027,8 +1026,9 @@ again:
 	 * The async work queues will take care of doing actual allocation on
 	 * disk for these compressed pages, and will submit the bios.
 	 */
-	add_async_extent(async_chunk, start, total_in, total_compressed, pages,
-			 nr_pages, compress_type);
+	ret = add_async_extent(async_chunk, start, total_in, total_compressed, pages,
+			       nr_pages, compress_type);
+	BUG_ON(ret);
 	if (start + total_in < end) {
 		start += total_in;
 		cond_resched();
@@ -1040,8 +1040,9 @@ mark_incompressible:
 	if (!btrfs_test_opt(fs_info, FORCE_COMPRESS) && !inode->prop_compress)
 		inode->flags |= BTRFS_INODE_NOCOMPRESS;
 cleanup_and_bail_uncompressed:
-	add_async_extent(async_chunk, start, end - start + 1, 0, NULL, 0,
-			 BTRFS_COMPRESS_NONE);
+	ret = add_async_extent(async_chunk, start, end - start + 1, 0, NULL, 0,
+			       BTRFS_COMPRESS_NONE);
+	BUG_ON(ret);
 free_pages:
 	if (pages) {
 		for (i = 0; i < nr_pages; i++) {
@@ -2301,6 +2302,8 @@ void btrfs_split_delalloc_extent(struct btrfs_inode *inode,
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	u64 size;
 
+	lockdep_assert_held(&inode->io_tree.lock);
+
 	/* not delalloc, ignore it */
 	if (!(orig->state & EXTENT_DELALLOC))
 		return;
@@ -2339,6 +2342,8 @@ void btrfs_merge_delalloc_extent(struct btrfs_inode *inode, struct extent_state
 	u64 new_size, old_size;
 	u32 num_extents;
 
+	lockdep_assert_held(&inode->io_tree.lock);
+
 	/* not delalloc, ignore it */
 	if (!(other->state & EXTENT_DELALLOC))
 		return;
@@ -2386,55 +2391,50 @@ void btrfs_merge_delalloc_extent(struct btrfs_inode *inode, struct extent_state
 	spin_unlock(&inode->lock);
 }
 
-static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
-				      struct btrfs_inode *inode)
+static void btrfs_add_delalloc_inode(struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	struct btrfs_root *root = inode->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	spin_lock(&root->delalloc_lock);
-	if (list_empty(&inode->delalloc_inodes)) {
-		list_add_tail(&inode->delalloc_inodes, &root->delalloc_inodes);
-		set_bit(BTRFS_INODE_IN_DELALLOC_LIST, &inode->runtime_flags);
-		root->nr_delalloc_inodes++;
-		if (root->nr_delalloc_inodes == 1) {
-			spin_lock(&fs_info->delalloc_root_lock);
-			BUG_ON(!list_empty(&root->delalloc_root));
-			list_add_tail(&root->delalloc_root,
-				      &fs_info->delalloc_roots);
-			spin_unlock(&fs_info->delalloc_root_lock);
-		}
+	ASSERT(list_empty(&inode->delalloc_inodes));
+	list_add_tail(&inode->delalloc_inodes, &root->delalloc_inodes);
+	root->nr_delalloc_inodes++;
+	if (root->nr_delalloc_inodes == 1) {
+		spin_lock(&fs_info->delalloc_root_lock);
+		ASSERT(list_empty(&root->delalloc_root));
+		list_add_tail(&root->delalloc_root, &fs_info->delalloc_roots);
+		spin_unlock(&fs_info->delalloc_root_lock);
 	}
 	spin_unlock(&root->delalloc_lock);
 }
 
-void __btrfs_del_delalloc_inode(struct btrfs_root *root,
-				struct btrfs_inode *inode)
+void btrfs_del_delalloc_inode(struct btrfs_inode *inode)
 {
+	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
+	lockdep_assert_held(&root->delalloc_lock);
+
+	/*
+	 * We may be called after the inode was already deleted from the list,
+	 * namely in the transaction abort path btrfs_destroy_delalloc_inodes(),
+	 * and then later through btrfs_clear_delalloc_extent() while the inode
+	 * still has ->delalloc_bytes > 0.
+	 */
 	if (!list_empty(&inode->delalloc_inodes)) {
 		list_del_init(&inode->delalloc_inodes);
-		clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
-			  &inode->runtime_flags);
 		root->nr_delalloc_inodes--;
 		if (!root->nr_delalloc_inodes) {
 			ASSERT(list_empty(&root->delalloc_inodes));
 			spin_lock(&fs_info->delalloc_root_lock);
-			BUG_ON(list_empty(&root->delalloc_root));
+			ASSERT(!list_empty(&root->delalloc_root));
 			list_del_init(&root->delalloc_root);
 			spin_unlock(&fs_info->delalloc_root_lock);
 		}
 	}
 }
 
-static void btrfs_del_delalloc_inode(struct btrfs_root *root,
-				     struct btrfs_inode *inode)
-{
-	spin_lock(&root->delalloc_lock);
-	__btrfs_del_delalloc_inode(root, inode);
-	spin_unlock(&root->delalloc_lock);
-}
-
 /*
  * Properly track delayed allocation bytes in the inode and to maintain the
  * list of inodes that have pending delalloc work to be done.
@@ -2444,6 +2444,8 @@ void btrfs_set_delalloc_extent(struct btrfs_inode *inode, struct extent_state *s
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 
+	lockdep_assert_held(&inode->io_tree.lock);
+
 	if ((bits & EXTENT_DEFRAG) && !(bits & EXTENT_DELALLOC))
 		WARN_ON(1);
 	/*
@@ -2452,10 +2454,9 @@ void btrfs_set_delalloc_extent(struct btrfs_inode *inode, struct extent_state *s
 	 * bit, which is only set or cleared with irqs on
 	 */
 	if (!(state->state & EXTENT_DELALLOC) && (bits & EXTENT_DELALLOC)) {
-		struct btrfs_root *root = inode->root;
 		u64 len = state->end + 1 - state->start;
+		u64 prev_delalloc_bytes;
 		u32 num_extents = count_max_extents(fs_info, len);
-		bool do_list = !btrfs_is_free_space_inode(inode);
 
 		spin_lock(&inode->lock);
 		btrfs_mod_outstanding_extents(inode, num_extents);
@@ -2468,13 +2469,20 @@ void btrfs_set_delalloc_extent(struct btrfs_inode *inode, struct extent_state *s
 		percpu_counter_add_batch(&fs_info->delalloc_bytes, len,
 					 fs_info->delalloc_batch);
 		spin_lock(&inode->lock);
+		prev_delalloc_bytes = inode->delalloc_bytes;
 		inode->delalloc_bytes += len;
 		if (bits & EXTENT_DEFRAG)
 			inode->defrag_bytes += len;
-		if (do_list && !test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
-					 &inode->runtime_flags))
-			btrfs_add_delalloc_inodes(root, inode);
 		spin_unlock(&inode->lock);
+
+		/*
+		 * We don't need to be under the protection of the inode's lock,
+		 * because we are called while holding the inode's io_tree lock
+		 * and are therefore protected against concurrent calls of this
+		 * function and btrfs_clear_delalloc_extent().
+		 */
+		if (!btrfs_is_free_space_inode(inode) && prev_delalloc_bytes == 0)
+			btrfs_add_delalloc_inode(inode);
 	}
 
 	if (!(state->state & EXTENT_DELALLOC_NEW) &&
@@ -2496,6 +2504,8 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
 	u64 len = state->end + 1 - state->start;
 	u32 num_extents = count_max_extents(fs_info, len);
 
+	lockdep_assert_held(&inode->io_tree.lock);
+
 	if ((state->state & EXTENT_DEFRAG) && (bits & EXTENT_DEFRAG)) {
 		spin_lock(&inode->lock);
 		inode->defrag_bytes -= len;
@@ -2509,7 +2519,7 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
 	 */
 	if ((state->state & EXTENT_DELALLOC) && (bits & EXTENT_DELALLOC)) {
 		struct btrfs_root *root = inode->root;
-		bool do_list = !btrfs_is_free_space_inode(inode);
+		u64 new_delalloc_bytes;
 
 		spin_lock(&inode->lock);
 		btrfs_mod_outstanding_extents(inode, -num_extents);
@@ -2529,7 +2539,8 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
 			return;
 
 		if (!btrfs_is_data_reloc_root(root) &&
-		    do_list && !(state->state & EXTENT_NORESERVE) &&
+		    !btrfs_is_free_space_inode(inode) &&
+		    !(state->state & EXTENT_NORESERVE) &&
 		    (bits & EXTENT_CLEAR_DATA_RESV))
 			btrfs_free_reserved_data_space_noquota(fs_info, len);
 
@@ -2537,11 +2548,20 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
 					 fs_info->delalloc_batch);
 		spin_lock(&inode->lock);
 		inode->delalloc_bytes -= len;
-		if (do_list && inode->delalloc_bytes == 0 &&
-		    test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
-					&inode->runtime_flags))
-			btrfs_del_delalloc_inode(root, inode);
+		new_delalloc_bytes = inode->delalloc_bytes;
 		spin_unlock(&inode->lock);
+
+		/*
+		 * We don't need to be under the protection of the inode's lock,
+		 * because we are called while holding the inode's io_tree lock
+		 * and are therefore protected against concurrent calls of this
+		 * function and btrfs_set_delalloc_extent().
+		 */
+		if (!btrfs_is_free_space_inode(inode) && new_delalloc_bytes == 0) {
+			spin_lock(&root->delalloc_lock);
+			btrfs_del_delalloc_inode(inode);
+			spin_unlock(&root->delalloc_lock);
+		}
 	}
 
 	if ((state->state & EXTENT_DELALLOC_NEW) &&
@@ -2631,7 +2651,7 @@ static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
 		u64 em_len;
 		int ret = 0;
 
-		em = btrfs_get_extent(inode, NULL, 0, search_start, search_len);
+		em = btrfs_get_extent(inode, NULL, search_start, search_len);
 		if (IS_ERR(em))
 			return PTR_ERR(em);
 
@@ -4387,7 +4407,14 @@ static noinline int may_destroy_subvol(struct btrfs_root *root)
 	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
 	if (ret < 0)
 		goto out;
-	BUG_ON(ret == 0);
+	if (ret == 0) {
+		/*
+		 * Key with offset -1 found, there would have to exist a root
+		 * with such id, but this is out of valid range.
+		 */
+		ret = -EUCLEAN;
+		goto out;
+	}
 
 	ret = 0;
 	if (path->slots[0] > 0) {
@@ -4710,7 +4737,7 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
 	u32 blocksize = fs_info->sectorsize;
 	pgoff_t index = from >> PAGE_SHIFT;
 	unsigned offset = from & (blocksize - 1);
-	struct page *page;
+	struct folio *folio;
 	gfp_t mask = btrfs_alloc_write_mask(mapping);
 	size_t write_bytes = blocksize;
 	int ret = 0;
@@ -4742,8 +4769,9 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
 		goto out;
 	}
 again:
-	page = find_or_create_page(mapping, index, mask);
-	if (!page) {
+	folio = __filemap_get_folio(mapping, index,
+				    FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mask);
+	if (IS_ERR(folio)) {
 		btrfs_delalloc_release_space(inode, data_reserved, block_start,
 					     blocksize, true);
 		btrfs_delalloc_release_extents(inode, blocksize);
@@ -4751,15 +4779,15 @@ again:
 		goto out;
 	}
 
-	if (!PageUptodate(page)) {
-		ret = btrfs_read_folio(NULL, page_folio(page));
-		lock_page(page);
-		if (page->mapping != mapping) {
-			unlock_page(page);
-			put_page(page);
+	if (!folio_test_uptodate(folio)) {
+		ret = btrfs_read_folio(NULL, folio);
+		folio_lock(folio);
+		if (folio->mapping != mapping) {
+			folio_unlock(folio);
+			folio_put(folio);
 			goto again;
 		}
-		if (!PageUptodate(page)) {
+		if (!folio_test_uptodate(folio)) {
 			ret = -EIO;
 			goto out_unlock;
 		}
@@ -4771,19 +4799,19 @@ again:
 	 * folio private, but left the page in the mapping.  Set the page mapped
 	 * here to make sure it's properly set for the subpage stuff.
 	 */
-	ret = set_page_extent_mapped(page);
+	ret = set_folio_extent_mapped(folio);
 	if (ret < 0)
 		goto out_unlock;
 
-	wait_on_page_writeback(page);
+	folio_wait_writeback(folio);
 
 	lock_extent(io_tree, block_start, block_end, &cached_state);
 
 	ordered = btrfs_lookup_ordered_extent(inode, block_start);
 	if (ordered) {
 		unlock_extent(io_tree, block_start, block_end, &cached_state);
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
 		goto again;
@@ -4804,15 +4832,16 @@ again:
 		if (!len)
 			len = blocksize - offset;
 		if (front)
-			memzero_page(page, (block_start - page_offset(page)),
-				     offset);
+			folio_zero_range(folio, block_start - folio_pos(folio),
+					 offset);
 		else
-			memzero_page(page, (block_start - page_offset(page)) + offset,
-				     len);
+			folio_zero_range(folio,
+					 (block_start - folio_pos(folio)) + offset,
+					 len);
 	}
-	btrfs_folio_clear_checked(fs_info, page_folio(page), block_start,
+	btrfs_folio_clear_checked(fs_info, folio, block_start,
 				  block_end + 1 - block_start);
-	btrfs_folio_set_dirty(fs_info, page_folio(page), block_start,
+	btrfs_folio_set_dirty(fs_info, folio, block_start,
 			      block_end + 1 - block_start);
 	unlock_extent(io_tree, block_start, block_end, &cached_state);
 
@@ -4829,8 +4858,8 @@ out_unlock:
 					block_start, blocksize, true);
 	}
 	btrfs_delalloc_release_extents(inode, blocksize);
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 out:
 	if (only_release_metadata)
 		btrfs_check_nocow_unlock(inode);
@@ -4922,8 +4951,7 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 					   &cached_state);
 	cur_offset = hole_start;
 	while (1) {
-		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
-				      block_end - cur_offset);
+		em = btrfs_get_extent(inode, NULL, cur_offset, block_end - cur_offset);
 		if (IS_ERR(em)) {
 			err = PTR_ERR(em);
 			em = NULL;
@@ -5549,7 +5577,6 @@ static int btrfs_init_locked_inode(struct inode *inode, void *p)
 	BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
 	BTRFS_I(inode)->location.offset = 0;
 	BTRFS_I(inode)->root = btrfs_grab_root(args->root);
-	BUG_ON(args->root && !BTRFS_I(inode)->root);
 
 	if (args->root && args->root == args->root->fs_info->tree_root &&
 	    args->ino != BTRFS_BTREE_INODE_OBJECTID)
@@ -6772,7 +6799,6 @@ static int read_inline_extent(struct btrfs_inode *inode, struct btrfs_path *path
  *
  * @inode:	file to search in
  * @page:	page to read extent data into if the extent is inline
- * @pg_offset:	offset into @page to copy to
  * @start:	file offset
  * @len:	length of range starting at @start
  *
@@ -6786,8 +6812,7 @@ static int read_inline_extent(struct btrfs_inode *inode, struct btrfs_path *path
  * Return: ERR_PTR on error, non-NULL extent_map on success.
  */
 struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
-				    struct page *page, size_t pg_offset,
-				    u64 start, u64 len)
+				    struct page *page, u64 start, u64 len)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	int ret = 0;
@@ -6930,7 +6955,6 @@ next:
 		 * ensured by tree-checker and inline extent creation path.
 		 * Thus all members representing file offsets should be zero.
 		 */
-		ASSERT(pg_offset == 0);
 		ASSERT(extent_start == 0);
 		ASSERT(em->start == 0);
 
@@ -7571,7 +7595,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	if (ret < 0)
 		goto err;
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len);
 	if (IS_ERR(em)) {
 		ret = PTR_ERR(em);
 		goto unlock_err;
@@ -8716,7 +8740,7 @@ int __init btrfs_init_cachep(void)
 {
 	btrfs_inode_cachep = kmem_cache_create("btrfs_inode",
 			sizeof(struct btrfs_inode), 0,
-			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT,
+			SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT,
 			init_once);
 	if (!btrfs_inode_cachep)
 		goto fail;
@@ -10180,7 +10204,7 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 		cond_resched();
 	}
 
-	em = btrfs_get_extent(inode, NULL, 0, start, lockend - start + 1);
+	em = btrfs_get_extent(inode, NULL, start, lockend - start + 1);
 	if (IS_ERR(em)) {
 		ret = PTR_ERR(em);
 		goto out_unlock_extent;
@@ -10760,7 +10784,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 		struct btrfs_block_group *bg;
 		u64 len = isize - start;
 
-		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len);
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
 			goto out;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 8851ba7a1e..0493272a76 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -34,11 +34,9 @@
 #include "export.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
-#include "print-tree.h"
 #include "volumes.h"
 #include "locking.h"
 #include "backref.h"
-#include "rcu-string.h"
 #include "send.h"
 #include "dev-replace.h"
 #include "props.h"
@@ -47,9 +45,7 @@
 #include "tree-log.h"
 #include "compression.h"
 #include "space-info.h"
-#include "delalloc-space.h"
 #include "block-group.h"
-#include "subpage.h"
 #include "fs.h"
 #include "accessors.h"
 #include "extent-tree.h"
@@ -231,6 +227,20 @@ static int check_fsflags_compatible(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+int btrfs_check_ioctl_vol_args_path(const struct btrfs_ioctl_vol_args *vol_args)
+{
+	if (memchr(vol_args->name, 0, sizeof(vol_args->name)) == NULL)
+		return -ENAMETOOLONG;
+	return 0;
+}
+
+static int btrfs_check_ioctl_vol_args2_subvol_name(const struct btrfs_ioctl_vol_args_v2 *vol_args2)
+{
+	if (memchr(vol_args2->name, 0, sizeof(vol_args2->name)) == NULL)
+		return -ENAMETOOLONG;
+	return 0;
+}
+
 /*
  * Set flags/xflags from the internal inode flags. The remaining items of
  * fsxattr are zeroed.
@@ -929,7 +939,9 @@ static int btrfs_may_delete(struct mnt_idmap *idmap,
 	if (d_really_is_negative(victim))
 		return -ENOENT;
 
-	BUG_ON(d_inode(victim->d_parent) != dir);
+	/* The @victim is not inside @dir. */
+	if (d_inode(victim->d_parent) != dir)
+		return -EINVAL;
 	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
 
 	error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC);
@@ -1147,7 +1159,10 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 		ret = PTR_ERR(vol_args);
 		goto out_drop;
 	}
-	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args_path(vol_args);
+	if (ret < 0)
+		goto out_free;
+
 	sizestr = vol_args->name;
 	cancel = (strcmp("cancel", sizestr) == 0);
 	ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_RESIZE, cancel);
@@ -1347,12 +1362,15 @@ static noinline int btrfs_ioctl_snap_create(struct file *file,
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
-	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args_path(vol_args);
+	if (ret < 0)
+		goto out;
 
 	ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file),
 					vol_args->name, vol_args->fd, subvol,
 					false, NULL);
 
+out:
 	kfree(vol_args);
 	return ret;
 }
@@ -1371,7 +1389,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
-	vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args2_subvol_name(vol_args);
+	if (ret < 0)
+		goto free_args;
 
 	if (vol_args->flags & ~BTRFS_SUBVOL_CREATE_ARGS_MASK) {
 		ret = -EOPNOTSUPP;
@@ -2391,7 +2411,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		 * name, same as v1 currently does.
 		 */
 		if (!(vol_args2->flags & BTRFS_SUBVOL_SPEC_BY_ID)) {
-			vol_args2->name[BTRFS_SUBVOL_NAME_MAX] = 0;
+			err = btrfs_check_ioctl_vol_args2_subvol_name(vol_args2);
+			if (err < 0)
+				goto out;
 			subvol_name = vol_args2->name;
 
 			err = mnt_want_write_file(file);
@@ -2475,7 +2497,10 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		if (IS_ERR(vol_args))
 			return PTR_ERR(vol_args);
 
-		vol_args->name[BTRFS_PATH_NAME_MAX] = 0;
+		err = btrfs_check_ioctl_vol_args_path(vol_args);
+		if (err < 0)
+			goto out;
+
 		subvol_name = vol_args->name;
 
 		err = mnt_want_write_file(file);
@@ -2686,12 +2711,16 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg)
 		goto out;
 	}
 
-	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args_path(vol_args);
+	if (ret < 0)
+		goto out_free;
+
 	ret = btrfs_init_new_device(fs_info, vol_args->name);
 
 	if (!ret)
 		btrfs_info(fs_info, "disk added %s", vol_args->name);
 
+out_free:
 	kfree(vol_args);
 out:
 	if (restore_op)
@@ -2707,7 +2736,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_ioctl_vol_args_v2 *vol_args;
-	struct bdev_handle *bdev_handle = NULL;
+	struct file *bdev_file = NULL;
 	int ret;
 	bool cancel = false;
 
@@ -2723,7 +2752,10 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 		goto out;
 	}
 
-	vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args2_subvol_name(vol_args);
+	if (ret < 0)
+		goto out;
+
 	if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) {
 		args.devid = vol_args->devid;
 	} else if (!strcmp("cancel", vol_args->name)) {
@@ -2744,7 +2776,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 		goto err_drop;
 
 	/* Exclusive operation is now claimed */
-	ret = btrfs_rm_device(fs_info, &args, &bdev_handle);
+	ret = btrfs_rm_device(fs_info, &args, &bdev_file);
 
 	btrfs_exclop_finish(fs_info);
 
@@ -2758,8 +2790,8 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 	}
 err_drop:
 	mnt_drop_write_file(file);
-	if (bdev_handle)
-		bdev_release(bdev_handle);
+	if (bdev_file)
+		fput(bdev_file);
 out:
 	btrfs_put_dev_args_from_path(&args);
 	kfree(vol_args);
@@ -2772,7 +2804,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_ioctl_vol_args *vol_args;
-	struct bdev_handle *bdev_handle = NULL;
+	struct file *bdev_file = NULL;
 	int ret;
 	bool cancel = false;
 
@@ -2783,7 +2815,10 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
 
-	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args_path(vol_args);
+	if (ret < 0)
+		goto out_free;
+
 	if (!strcmp("cancel", vol_args->name)) {
 		cancel = true;
 	} else {
@@ -2799,17 +2834,18 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE,
 					   cancel);
 	if (ret == 0) {
-		ret = btrfs_rm_device(fs_info, &args, &bdev_handle);
+		ret = btrfs_rm_device(fs_info, &args, &bdev_file);
 		if (!ret)
 			btrfs_info(fs_info, "disk deleted %s", vol_args->name);
 		btrfs_exclop_finish(fs_info);
 	}
 
 	mnt_drop_write_file(file);
-	if (bdev_handle)
-		bdev_release(bdev_handle);
+	if (bdev_file)
+		fput(bdev_file);
 out:
 	btrfs_put_dev_args_from_path(&args);
+out_free:
 	kfree(vol_args);
 	return ret;
 }
diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h
index d51b9a2f2f..2c5dc25ec6 100644
--- a/fs/btrfs/ioctl.h
+++ b/fs/btrfs/ioctl.h
@@ -3,6 +3,15 @@
 #ifndef BTRFS_IOCTL_H
 #define BTRFS_IOCTL_H
 
+#include <linux/types.h>
+
+struct file;
+struct dentry;
+struct mnt_idmap;
+struct fileattr;
+struct btrfs_fs_info;
+struct btrfs_ioctl_balance_args;
+
 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_fileattr_get(struct dentry *dentry, struct fileattr *fa);
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 74d8e2003f..99ccab86bb 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -13,7 +13,6 @@
 #include "ctree.h"
 #include "extent_io.h"
 #include "locking.h"
-#include "accessors.h"
 
 /*
  * Lockdep class keys for extent_buffer->lock's in this root.  For a given
@@ -85,7 +84,7 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int
 {
 	struct btrfs_lockdep_keyset *ks;
 
-	BUG_ON(level >= ARRAY_SIZE(ks->keys));
+	ASSERT(level < ARRAY_SIZE(ks->keys));
 
 	/* Find the matching keyset, id 0 is the default entry */
 	for (ks = btrfs_lockdep_keysets; ks->id; ks++)
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index 7d6ee1e609..9576f485a3 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -8,8 +8,14 @@
 
 #include <linux/atomic.h>
 #include <linux/wait.h>
+#include <linux/lockdep.h>
 #include <linux/percpu_counter.h>
 #include "extent_io.h"
+#include "locking.h"
+
+struct extent_buffer;
+struct btrfs_path;
+struct btrfs_root;
 
 #define BTRFS_WRITE_LOCK 1
 #define BTRFS_READ_LOCK 2
@@ -157,8 +163,6 @@ enum btrfs_lockdep_trans_states {
 static_assert(BTRFS_NESTING_MAX <= MAX_LOCKDEP_SUBCLASSES,
 	      "too many lock subclasses defined");
 
-struct btrfs_path;
-
 void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
 void btrfs_tree_lock(struct extent_buffer *eb);
 void btrfs_tree_unlock(struct extent_buffer *eb);
diff --git a/fs/btrfs/lru_cache.h b/fs/btrfs/lru_cache.h
index 00328c856b..e32906ab6f 100644
--- a/fs/btrfs/lru_cache.h
+++ b/fs/btrfs/lru_cache.h
@@ -3,8 +3,10 @@
 #ifndef BTRFS_LRU_CACHE_H
 #define BTRFS_LRU_CACHE_H
 
+#include <linux/types.h>
 #include <linux/maple_tree.h>
 #include <linux/list.h>
+#include "lru_cache.h"
 
 /*
  * A cache entry. This is meant to be embedded in a structure of a user of
@@ -50,11 +52,6 @@ struct btrfs_lru_cache {
 #define btrfs_lru_cache_for_each_entry_safe(cache, entry, tmp)		\
 	list_for_each_entry_safe_reverse((entry), (tmp), &(cache)->lru_list, lru_list)
 
-static inline unsigned int btrfs_lru_cache_size(const struct btrfs_lru_cache *cache)
-{
-	return cache->size;
-}
-
 static inline struct btrfs_lru_cache_entry *btrfs_lru_cache_lru_entry(
 					      struct btrfs_lru_cache *cache)
 {
diff --git a/fs/btrfs/messages.c b/fs/btrfs/messages.c
index cdada48658..210d9c82e2 100644
--- a/fs/btrfs/messages.c
+++ b/fs/btrfs/messages.c
@@ -3,13 +3,11 @@
 #include "fs.h"
 #include "messages.h"
 #include "discard.h"
-#include "transaction.h"
-#include "space-info.h"
 #include "super.h"
 
 #ifdef CONFIG_PRINTK
 
-#define STATE_STRING_PREFACE	": state "
+#define STATE_STRING_PREFACE	" state "
 #define STATE_STRING_BUF_LEN	(sizeof(STATE_STRING_PREFACE) + BTRFS_FS_STATE_COUNT + 1)
 
 /*
diff --git a/fs/btrfs/misc.h b/fs/btrfs/misc.h
index 40f2d9f1a1..dde4904aea 100644
--- a/fs/btrfs/misc.h
+++ b/fs/btrfs/misc.h
@@ -3,6 +3,8 @@
 #ifndef BTRFS_MISC_H
 #define BTRFS_MISC_H
 
+#include <linux/types.h>
+#include <linux/bitmap.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
 #include <linux/math64.h>
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 81f67ebf74..c2a42bcde9 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -19,7 +19,6 @@
 #include "qgroup.h"
 #include "subpage.h"
 #include "file.h"
-#include "super.h"
 
 static struct kmem_cache *btrfs_ordered_extent_cache;
 
@@ -1237,10 +1236,7 @@ struct btrfs_ordered_extent *btrfs_split_ordered_extent(
 
 int __init ordered_data_init(void)
 {
-	btrfs_ordered_extent_cache = kmem_cache_create("btrfs_ordered_extent",
-				     sizeof(struct btrfs_ordered_extent), 0,
-				     SLAB_MEM_SPREAD,
-				     NULL);
+	btrfs_ordered_extent_cache = KMEM_CACHE(btrfs_ordered_extent, 0);
 	if (!btrfs_ordered_extent_cache)
 		return -ENOMEM;
 
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 127ef8bf0f..34413fc5b4 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -6,6 +6,21 @@
 #ifndef BTRFS_ORDERED_DATA_H
 #define BTRFS_ORDERED_DATA_H
 
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/refcount.h>
+#include <linux/completion.h>
+#include <linux/rbtree.h>
+#include <linux/wait.h>
+#include "async-thread.h"
+
+struct inode;
+struct page;
+struct extent_state;
+struct btrfs_inode;
+struct btrfs_root;
+struct btrfs_fs_info;
+
 struct btrfs_ordered_sum {
 	/*
 	 * Logical start address and length for of the blocks covered by
diff --git a/fs/btrfs/orphan.c b/fs/btrfs/orphan.c
index 7a1b021b56..6195a2215b 100644
--- a/fs/btrfs/orphan.c
+++ b/fs/btrfs/orphan.c
@@ -4,7 +4,6 @@
  */
 
 #include "ctree.h"
-#include "disk-io.h"
 #include "orphan.h"
 
 int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/orphan.h b/fs/btrfs/orphan.h
index 3faab5cbb5..aa54a88a60 100644
--- a/fs/btrfs/orphan.h
+++ b/fs/btrfs/orphan.h
@@ -3,6 +3,11 @@
 #ifndef BTRFS_ORPHAN_H
 #define BTRFS_ORPHAN_H
 
+#include <linux/types.h>
+
+struct btrfs_trans_handle;
+struct btrfs_root;
+
 int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 offset);
 int btrfs_del_orphan_item(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/print-tree.h b/fs/btrfs/print-tree.h
index c42bc666d5..8504bf1702 100644
--- a/fs/btrfs/print-tree.h
+++ b/fs/btrfs/print-tree.h
@@ -9,6 +9,9 @@
 /* Buffer size to contain tree name and possibly additional data (offset) */
 #define BTRFS_ROOT_NAME_BUF_LEN				48
 
+struct extent_buffer;
+struct btrfs_key;
+
 void btrfs_print_leaf(const struct extent_buffer *l);
 void btrfs_print_tree(const struct extent_buffer *c, bool follow);
 const char *btrfs_root_name(const struct btrfs_key *key, char *buf);
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index ac4a0af2b5..2a9b7b029e 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/hashtable.h>
+#include <linux/xattr.h>
 #include "messages.h"
 #include "props.h"
 #include "btrfs_inode.h"
diff --git a/fs/btrfs/props.h b/fs/btrfs/props.h
index 6e283196e3..f60cd89feb 100644
--- a/fs/btrfs/props.h
+++ b/fs/btrfs/props.h
@@ -6,7 +6,12 @@
 #ifndef BTRFS_PROPS_H
 #define BTRFS_PROPS_H
 
-#include "ctree.h"
+#include <linux/compiler_types.h>
+
+struct inode;
+struct btrfs_inode;
+struct btrfs_path;
+struct btrfs_trans_handle;
 
 int __init btrfs_props_init(void);
 
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index cacc12d0ff..1167899a16 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -468,6 +468,7 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
 		}
 		if (!qgroup) {
 			struct btrfs_qgroup *prealloc;
+			struct btrfs_root *tree_root = fs_info->tree_root;
 
 			prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL);
 			if (!prealloc) {
@@ -475,6 +476,25 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
 				goto out;
 			}
 			qgroup = add_qgroup_rb(fs_info, prealloc, found_key.offset);
+			/*
+			 * If a qgroup exists for a subvolume ID, it is possible
+			 * that subvolume has been deleted, in which case
+			 * re-using that ID would lead to incorrect accounting.
+			 *
+			 * Ensure that we skip any such subvol ids.
+			 *
+			 * We don't need to lock because this is only called
+			 * during mount before we start doing things like creating
+			 * subvolumes.
+			 */
+			if (is_fstree(qgroup->qgroupid) &&
+			    qgroup->qgroupid > tree_root->free_objectid)
+				/*
+				 * Don't need to check against BTRFS_LAST_FREE_OBJECTID,
+				 * as it will get checked on the next call to
+				 * btrfs_get_free_objectid.
+				 */
+				tree_root->free_objectid = qgroup->qgroupid + 1;
 		}
 		ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup);
 		if (ret < 0)
@@ -1324,7 +1344,7 @@ static int flush_reservations(struct btrfs_fs_info *fs_info)
 	trans = btrfs_join_transaction(fs_info->tree_root);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
-	btrfs_commit_transaction(trans);
+	ret = btrfs_commit_transaction(trans);
 
 	return ret;
 }
@@ -2500,8 +2520,8 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
 	struct extent_buffer *eb = root_eb;
 	struct btrfs_path *path = NULL;
 
-	BUG_ON(root_level < 0 || root_level >= BTRFS_MAX_LEVEL);
-	BUG_ON(root_eb == NULL);
+	ASSERT(0 <= root_level && root_level < BTRFS_MAX_LEVEL);
+	ASSERT(root_eb != NULL);
 
 	if (!btrfs_qgroup_full_accounting(fs_info))
 		return 0;
@@ -2856,8 +2876,6 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 	if (nr_old_roots == 0 && nr_new_roots == 0)
 		goto out_free;
 
-	BUG_ON(!fs_info->quota_root);
-
 	trace_btrfs_qgroup_account_extent(fs_info, trans->transid, bytenr,
 					num_bytes, nr_old_roots, nr_new_roots);
 
@@ -3131,13 +3149,69 @@ static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info,
 	qgids = res->qgroups;
 
 	list_for_each_entry(qg_list, &inode_qg->groups, next_group)
-		qgids[i] = qg_list->group->qgroupid;
+		qgids[i++] = qg_list->group->qgroupid;
 
 	*inherit = res;
 	return 0;
 }
 
 /*
+ * Check if we can skip rescan when inheriting qgroups.  If @src has a single
+ * @parent, and that @parent is owning all its bytes exclusively, we can skip
+ * the full rescan, by just adding nodesize to the @parent's excl/rfer.
+ *
+ * Return <0 for fatal errors (like srcid/parentid has no qgroup).
+ * Return 0 if a quick inherit is done.
+ * Return >0 if a quick inherit is not possible, and a full rescan is needed.
+ */
+static int qgroup_snapshot_quick_inherit(struct btrfs_fs_info *fs_info,
+					 u64 srcid, u64 parentid)
+{
+	struct btrfs_qgroup *src;
+	struct btrfs_qgroup *parent;
+	struct btrfs_qgroup_list *list;
+	int nr_parents = 0;
+
+	src = find_qgroup_rb(fs_info, srcid);
+	if (!src)
+		return -ENOENT;
+	parent = find_qgroup_rb(fs_info, parentid);
+	if (!parent)
+		return -ENOENT;
+
+	/*
+	 * Source has no parent qgroup, but our new qgroup would have one.
+	 * Qgroup numbers would become inconsistent.
+	 */
+	if (list_empty(&src->groups))
+		return 1;
+
+	list_for_each_entry(list, &src->groups, next_group) {
+		/* The parent is not the same, quick update is not possible. */
+		if (list->group->qgroupid != parentid)
+			return 1;
+		nr_parents++;
+		/*
+		 * More than one parent qgroup, we can't be sure about accounting
+		 * consistency.
+		 */
+		if (nr_parents > 1)
+			return 1;
+	}
+
+	/*
+	 * The parent is not exclusively owning all its bytes.  We're not sure
+	 * if the source has any bytes not fully owned by the parent.
+	 */
+	if (parent->excl != parent->rfer)
+		return 1;
+
+	parent->excl += fs_info->nodesize;
+	parent->rfer += fs_info->nodesize;
+	return 0;
+}
+
+/*
  * Copy the accounting information between qgroups. This is necessary
  * when a snapshot or a subvolume is created. Throwing an error will
  * cause a transaction abort so we take extra care here to only error
@@ -3305,6 +3379,13 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 
 		qgroup_dirty(fs_info, dstgroup);
 		qgroup_dirty(fs_info, srcgroup);
+
+		/*
+		 * If the source qgroup has parent but the new one doesn't,
+		 * we need a full rescan.
+		 */
+		if (!inherit && !list_empty(&srcgroup->groups))
+			need_rescan = true;
 	}
 
 	if (!inherit)
@@ -3319,14 +3400,16 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 			if (ret)
 				goto unlock;
 		}
+		if (srcid) {
+			/* Check if we can do a quick inherit. */
+			ret = qgroup_snapshot_quick_inherit(fs_info, srcid, *i_qgroups);
+			if (ret < 0)
+				goto unlock;
+			if (ret > 0)
+				need_rescan = true;
+			ret = 0;
+		}
 		++i_qgroups;
-
-		/*
-		 * If we're doing a snapshot, and adding the snapshot to a new
-		 * qgroup, the numbers are guaranteed to be incorrect.
-		 */
-		if (srcid)
-			need_rescan = true;
 	}
 
 	for (i = 0; i <  inherit->num_ref_copies; ++i, i_qgroups += 2) {
@@ -3763,14 +3846,14 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 		/* we're resuming qgroup rescan at mount time */
 		if (!(fs_info->qgroup_flags &
 		      BTRFS_QGROUP_STATUS_FLAG_RESCAN)) {
-			btrfs_warn(fs_info,
+			btrfs_debug(fs_info,
 			"qgroup rescan init failed, qgroup rescan is not queued");
 			ret = -EINVAL;
 		} else if (!(fs_info->qgroup_flags &
 			     BTRFS_QGROUP_STATUS_FLAG_ON)) {
-			btrfs_warn(fs_info,
+			btrfs_debug(fs_info,
 			"qgroup rescan init failed, qgroup is not enabled");
-			ret = -EINVAL;
+			ret = -ENOTCONN;
 		}
 
 		if (ret)
@@ -3781,14 +3864,12 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 
 	if (init_flags) {
 		if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) {
-			btrfs_warn(fs_info,
-				   "qgroup rescan is already in progress");
 			ret = -EINPROGRESS;
 		} else if (!(fs_info->qgroup_flags &
 			     BTRFS_QGROUP_STATUS_FLAG_ON)) {
-			btrfs_warn(fs_info,
+			btrfs_debug(fs_info,
 			"qgroup rescan init failed, qgroup is not enabled");
-			ret = -EINVAL;
+			ret = -ENOTCONN;
 		} else if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) {
 			/* Quota disable is in progress */
 			ret = -EBUSY;
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 45a7d8920d..706640be0e 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -6,12 +6,22 @@
 #ifndef BTRFS_QGROUP_H
 #define BTRFS_QGROUP_H
 
+#include <linux/types.h>
 #include <linux/spinlock.h>
 #include <linux/rbtree.h>
 #include <linux/kobject.h>
-#include "ulist.h"
-#include "delayed-ref.h"
-#include "misc.h"
+#include <linux/list.h>
+#include <uapi/linux/btrfs_tree.h>
+
+struct extent_buffer;
+struct extent_changeset;
+struct btrfs_delayed_extent_op;
+struct btrfs_fs_info;
+struct btrfs_root;
+struct btrfs_ioctl_quota_ctl_args;
+struct btrfs_trans_handle;
+struct btrfs_delayed_ref_root;
+struct btrfs_inode;
 
 /*
  * Btrfs qgroup overview
@@ -321,7 +331,6 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid,
 		       struct btrfs_qgroup_limit *limit);
 int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info);
 void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info);
-struct btrfs_delayed_extent_op;
 
 int btrfs_qgroup_trace_extent_nolock(
 		struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c
index 9589362acf..6af6b4b9a3 100644
--- a/fs/btrfs/raid-stripe-tree.c
+++ b/fs/btrfs/raid-stripe-tree.c
@@ -11,7 +11,6 @@
 #include "disk-io.h"
 #include "raid-stripe-tree.h"
 #include "volumes.h"
-#include "misc.h"
 #include "print-tree.h"
 
 int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 length)
diff --git a/fs/btrfs/raid-stripe-tree.h b/fs/btrfs/raid-stripe-tree.h
index cdb58b38fc..c9c258f849 100644
--- a/fs/btrfs/raid-stripe-tree.h
+++ b/fs/btrfs/raid-stripe-tree.h
@@ -6,6 +6,10 @@
 #ifndef BTRFS_RAID_STRIPE_TREE_H
 #define BTRFS_RAID_STRIPE_TREE_H
 
+#include <linux/types.h>
+#include <uapi/linux/btrfs_tree.h>
+#include "fs.h"
+
 #define BTRFS_RST_SUPP_BLOCK_GROUP_MASK    (BTRFS_BLOCK_GROUP_DUP |		\
 					    BTRFS_BLOCK_GROUP_RAID1_MASK |	\
 					    BTRFS_BLOCK_GROUP_RAID0 |		\
@@ -13,6 +17,7 @@
 
 struct btrfs_io_context;
 struct btrfs_io_stripe;
+struct btrfs_fs_info;
 struct btrfs_ordered_extent;
 struct btrfs_trans_handle;
 
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 792c8e17c3..6f4a9cfeea 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -14,7 +14,6 @@
 #include <linux/raid/xor.h>
 #include <linux/mm.h>
 #include "messages.h"
-#include "misc.h"
 #include "ctree.h"
 #include "disk-io.h"
 #include "volumes.h"
@@ -918,6 +917,13 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
 	 */
 	ASSERT(stripe_nsectors <= BITS_PER_LONG);
 
+	/*
+	 * Real stripes must be between 2 (2 disks RAID5, aka RAID1) and 256
+	 * (limited by u8).
+	 */
+	ASSERT(real_stripes >= 2);
+	ASSERT(real_stripes <= U8_MAX);
+
 	rbio = kzalloc(sizeof(*rbio), GFP_NOFS);
 	if (!rbio)
 		return ERR_PTR(-ENOMEM);
@@ -955,6 +961,7 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
 
 	ASSERT(btrfs_nr_parity_stripes(bioc->map_type));
 	rbio->nr_data = real_stripes - btrfs_nr_parity_stripes(bioc->map_type);
+	ASSERT(rbio->nr_data > 0);
 
 	return rbio;
 }
@@ -1181,6 +1188,26 @@ static inline void bio_list_put(struct bio_list *bio_list)
 		bio_put(bio);
 }
 
+static void assert_rbio(struct btrfs_raid_bio *rbio)
+{
+	if (!IS_ENABLED(CONFIG_BTRFS_DEBUG) ||
+	    !IS_ENABLED(CONFIG_BTRFS_ASSERT))
+		return;
+
+	/*
+	 * At least two stripes (2 disks RAID5), and since real_stripes is U8,
+	 * we won't go beyond 256 disks anyway.
+	 */
+	ASSERT(rbio->real_stripes >= 2);
+	ASSERT(rbio->nr_data > 0);
+
+	/*
+	 * This is another check to make sure nr data stripes is smaller
+	 * than total stripes.
+	 */
+	ASSERT(rbio->nr_data < rbio->real_stripes);
+}
+
 /* Generate PQ for one vertical stripe. */
 static void generate_pq_vertical(struct btrfs_raid_bio *rbio, int sectornr)
 {
@@ -1212,6 +1239,7 @@ static void generate_pq_vertical(struct btrfs_raid_bio *rbio, int sectornr)
 		pointers[stripe++] = kmap_local_page(sector->page) +
 				     sector->pgoff;
 
+		assert_rbio(rbio);
 		raid6_call.gen_syndrome(rbio->real_stripes, sectorsize,
 					pointers);
 	} else {
@@ -2473,6 +2501,7 @@ static int finish_parity_scrub(struct btrfs_raid_bio *rbio)
 		}
 
 		if (has_qstripe) {
+			assert_rbio(rbio);
 			/* RAID6, call the library function to fill in our P/Q */
 			raid6_call.gen_syndrome(rbio->real_stripes, sectorsize,
 						pointers);
diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h
index 4702136888..0d7b4c2fb6 100644
--- a/fs/btrfs/raid56.h
+++ b/fs/btrfs/raid56.h
@@ -7,9 +7,18 @@
 #ifndef BTRFS_RAID56_H
 #define BTRFS_RAID56_H
 
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/bio.h>
+#include <linux/refcount.h>
 #include <linux/workqueue.h>
 #include "volumes.h"
 
+struct page;
+struct sector_ptr;
+struct btrfs_fs_info;
+
 enum btrfs_rbio_ops {
 	BTRFS_RBIO_WRITE,
 	BTRFS_RBIO_READ_REBUILD,
diff --git a/fs/btrfs/rcu-string.h b/fs/btrfs/rcu-string.h
index 5c2b66d155..1c2d7cb1fe 100644
--- a/fs/btrfs/rcu-string.h
+++ b/fs/btrfs/rcu-string.h
@@ -6,6 +6,12 @@
 #ifndef BTRFS_RCU_STRING_H
 #define BTRFS_RCU_STRING_H
 
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/rcupdate.h>
+#include <linux/printk.h>
+
 struct rcu_string {
 	struct rcu_head rcu;
 	char str[];
diff --git a/fs/btrfs/ref-verify.h b/fs/btrfs/ref-verify.h
index 855de37719..3511e1a5c9 100644
--- a/fs/btrfs/ref-verify.h
+++ b/fs/btrfs/ref-verify.h
@@ -6,7 +6,16 @@
 #ifndef BTRFS_REF_VERIFY_H
 #define BTRFS_REF_VERIFY_H
 
+#include <linux/types.h>
+#include <linux/rbtree_types.h>
+
+struct btrfs_fs_info;
+struct btrfs_ref;
+
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
+
+#include <linux/spinlock.h>
+
 int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info);
 void btrfs_free_ref_cache(struct btrfs_fs_info *fs_info);
 int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/reflink.h b/fs/btrfs/reflink.h
index ecb309b4da..1e291f7d85 100644
--- a/fs/btrfs/reflink.h
+++ b/fs/btrfs/reflink.h
@@ -3,7 +3,9 @@
 #ifndef BTRFS_REFLINK_H
 #define BTRFS_REFLINK_H
 
-#include <linux/fs.h>
+#include <linux/types.h>
+
+struct file;
 
 loff_t btrfs_remap_file_range(struct file *file_in, loff_t pos_in,
 			      struct file *file_out, loff_t pos_out,
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 2fca67f2b3..f96f267fb4 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -523,7 +523,8 @@ static noinline_for_stack struct btrfs_backref_node *build_backref_tree(
 	if (handle_useless_nodes(rc, node))
 		node = NULL;
 out:
-	btrfs_backref_iter_free(iter);
+	btrfs_free_path(iter->path);
+	kfree(iter);
 	btrfs_free_path(path);
 	if (err) {
 		btrfs_backref_error_cleanup(cache, node);
diff --git a/fs/btrfs/relocation.h b/fs/btrfs/relocation.h
index 5fb60f2deb..788c86d863 100644
--- a/fs/btrfs/relocation.h
+++ b/fs/btrfs/relocation.h
@@ -3,6 +3,15 @@
 #ifndef BTRFS_RELOCATION_H
 #define BTRFS_RELOCATION_H
 
+#include <linux/types.h>
+
+struct extent_buffer;
+struct btrfs_fs_info;
+struct btrfs_root;
+struct btrfs_trans_handle;
+struct btrfs_ordered_extent;
+struct btrfs_pending_snapshot;
+
 int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start);
 int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, struct btrfs_root *root);
 int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 5260677ad5..7007f9e0c9 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -10,7 +10,6 @@
 #include "messages.h"
 #include "transaction.h"
 #include "disk-io.h"
-#include "print-tree.h"
 #include "qgroup.h"
 #include "space-info.h"
 #include "accessors.h"
@@ -82,7 +81,14 @@ int btrfs_find_root(struct btrfs_root *root, const struct btrfs_key *search_key,
 		if (ret > 0)
 			goto out;
 	} else {
-		BUG_ON(ret == 0);		/* Logical error */
+		/*
+		 * Key with offset -1 found, there would have to exist a root
+		 * with such id, but this is out of the valid range.
+		 */
+		if (ret == 0) {
+			ret = -EUCLEAN;
+			goto out;
+		}
 		if (path->slots[0] == 0)
 			goto out;
 		path->slots[0]--;
@@ -323,8 +329,11 @@ int btrfs_del_root(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot(trans, root, key, path, -1, 1);
 	if (ret < 0)
 		goto out;
-
-	BUG_ON(ret != 0);
+	if (ret != 0) {
+		/* The root must exist but we did not find it by the key. */
+		ret = -EUCLEAN;
+		goto out;
+	}
 
 	ret = btrfs_del_item(trans, root, path);
 out:
diff --git a/fs/btrfs/root-tree.h b/fs/btrfs/root-tree.h
index de0175cbdb..8f5739e732 100644
--- a/fs/btrfs/root-tree.h
+++ b/fs/btrfs/root-tree.h
@@ -3,7 +3,17 @@
 #ifndef BTRFS_ROOT_TREE_H
 #define BTRFS_ROOT_TREE_H
 
+#include <linux/types.h>
+
 struct fscrypt_str;
+struct extent_buffer;
+struct btrfs_key;
+struct btrfs_root;
+struct btrfs_root_item;
+struct btrfs_path;
+struct btrfs_fs_info;
+struct btrfs_block_rsv;
+struct btrfs_trans_handle;
 
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     struct btrfs_block_rsv *rsv,
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index d89d5c0a8c..4b22cfe9a9 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1390,8 +1390,15 @@ static int find_first_extent_item(struct btrfs_root *extent_root,
 	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
 	if (ret < 0)
 		return ret;
+	if (ret == 0) {
+		/*
+		 * Key with offset -1 found, there would have to exist an extent
+		 * item with such offset, but this is out of the valid range.
+		 */
+		btrfs_release_path(path);
+		return -EUCLEAN;
+	}
 
-	ASSERT(ret > 0);
 	/*
 	 * Here we intentionally pass 0 as @min_objectid, as there could be
 	 * an extent item starting before @search_start.
diff --git a/fs/btrfs/scrub.h b/fs/btrfs/scrub.h
index 7639103ebf..f0df597b75 100644
--- a/fs/btrfs/scrub.h
+++ b/fs/btrfs/scrub.h
@@ -3,6 +3,12 @@
 #ifndef BTRFS_SCRUB_H
 #define BTRFS_SCRUB_H
 
+#include <linux/types.h>
+
+struct btrfs_fs_info;
+struct btrfs_device;
+struct btrfs_scrub_progress;
+
 int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		    u64 end, struct btrfs_scrub_progress *progress,
 		    int readonly, int is_dev_replace);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index e818766915..50b4a76ac8 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -25,7 +25,6 @@
 #include "btrfs_inode.h"
 #include "transaction.h"
 #include "compression.h"
-#include "xattr.h"
 #include "print-tree.h"
 #include "accessors.h"
 #include "dir-item.h"
@@ -777,7 +776,12 @@ static int begin_cmd(struct send_ctx *sctx, int cmd)
 	if (WARN_ON(!sctx->send_buf))
 		return -EINVAL;
 
-	BUG_ON(sctx->send_size);
+	if (unlikely(sctx->send_size != 0)) {
+		btrfs_err(sctx->send_root->fs_info,
+			  "send: command header buffer not empty cmd %d offset %llu",
+			  cmd, sctx->send_off);
+		return -EINVAL;
+	}
 
 	sctx->send_size += sizeof(*hdr);
 	hdr = (struct btrfs_cmd_header *)sctx->send_buf;
@@ -1414,7 +1418,7 @@ static bool lookup_backref_cache(u64 leaf_bytenr, void *ctx,
 	struct btrfs_lru_cache_entry *raw_entry;
 	struct backref_cache_entry *entry;
 
-	if (btrfs_lru_cache_size(&sctx->backref_cache) == 0)
+	if (sctx->backref_cache.size == 0)
 		return false;
 
 	/*
@@ -1512,7 +1516,7 @@ static void store_backref_cache(u64 leaf_bytenr, const struct ulist *root_ids,
 	 * transaction handle or holding fs_info->commit_root_sem, so no need
 	 * to take any lock here.
 	 */
-	if (btrfs_lru_cache_size(&sctx->backref_cache) == 1)
+	if (sctx->backref_cache.size == 1)
 		sctx->backref_cache_last_reloc_trans = fs_info->last_reloc_trans;
 }
 
@@ -2817,8 +2821,7 @@ static int cache_dir_utimes(struct send_ctx *sctx, u64 dir, u64 gen)
 
 static int trim_dir_utimes_cache(struct send_ctx *sctx)
 {
-	while (btrfs_lru_cache_size(&sctx->dir_utimes_cache) >
-	       SEND_MAX_DIR_UTIMES_CACHE_SIZE) {
+	while (sctx->dir_utimes_cache.size > SEND_MAX_DIR_UTIMES_CACHE_SIZE) {
 		struct btrfs_lru_cache_entry *lru;
 		int ret;
 
@@ -4190,7 +4193,13 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 	 * This should never happen as the root dir always has the same ref
 	 * which is always '..'
 	 */
-	BUG_ON(sctx->cur_ino <= BTRFS_FIRST_FREE_OBJECTID);
+	if (unlikely(sctx->cur_ino <= BTRFS_FIRST_FREE_OBJECTID)) {
+		btrfs_err(fs_info,
+			  "send: unexpected inode %llu in process_recorded_refs()",
+			  sctx->cur_ino);
+		ret = -EINVAL;
+		goto out;
+	}
 
 	valid_path = fs_path_alloc();
 	if (!valid_path) {
@@ -6466,21 +6475,18 @@ static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
 	if (sctx->cur_ino != key->objectid || !need_send_hole(sctx))
 		return 0;
 
-	if (sctx->cur_inode_last_extent == (u64)-1) {
-		ret = get_last_extent(sctx, key->offset - 1);
-		if (ret)
-			return ret;
-	}
-
-	if (path->slots[0] == 0 &&
-	    sctx->cur_inode_last_extent < key->offset) {
-		/*
-		 * We might have skipped entire leafs that contained only
-		 * file extent items for our current inode. These leafs have
-		 * a generation number smaller (older) than the one in the
-		 * current leaf and the leaf our last extent came from, and
-		 * are located between these 2 leafs.
-		 */
+	/*
+	 * Get last extent's end offset (exclusive) if we haven't determined it
+	 * yet (we're processing the first file extent item that is new), or if
+	 * we're at the first slot of a leaf and the last extent's end is less
+	 * than the current extent's offset, because we might have skipped
+	 * entire leaves that contained only file extent items for our current
+	 * inode. These leaves have a generation number smaller (older) than the
+	 * one in the current leaf and the leaf our last extent came from, and
+	 * are located between these 2 leaves.
+	 */
+	if ((sctx->cur_inode_last_extent == (u64)-1) ||
+	    (path->slots[0] == 0 && sctx->cur_inode_last_extent < key->offset)) {
 		ret = get_last_extent(sctx, key->offset - 1);
 		if (ret)
 			return ret;
@@ -7437,8 +7443,8 @@ static int tree_move_down(struct btrfs_path *path, int *level, u64 reada_min_gen
 	u64 reada_done = 0;
 
 	lockdep_assert_held_read(&parent->fs_info->commit_root_sem);
+	ASSERT(*level != 0);
 
-	BUG_ON(*level == 0);
 	eb = btrfs_read_node_slot(parent, slot);
 	if (IS_ERR(eb))
 		return PTR_ERR(eb);
diff --git a/fs/btrfs/send.h b/fs/btrfs/send.h
index 4f5509cb18..dd1c9f02b0 100644
--- a/fs/btrfs/send.h
+++ b/fs/btrfs/send.h
@@ -8,6 +8,11 @@
 #define BTRFS_SEND_H
 
 #include <linux/types.h>
+#include <linux/sizes.h>
+#include <linux/align.h>
+
+struct inode;
+struct btrfs_ioctl_send_args;
 
 #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream"
 /* Conditional support for the upcoming protocol version. */
@@ -25,9 +30,6 @@
 #define BTRFS_SEND_BUF_SIZE_V1				SZ_64K
 #define BTRFS_SEND_BUF_SIZE_V2	ALIGN(SZ_16K + BTRFS_MAX_COMPRESSED, PAGE_SIZE)
 
-struct inode;
-struct btrfs_ioctl_send_args;
-
 enum btrfs_tlv_type {
 	BTRFS_TLV_U8,
 	BTRFS_TLV_U16,
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 3b54eb5834..d620323d08 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -9,7 +9,6 @@
 #include "ordered-data.h"
 #include "transaction.h"
 #include "block-group.h"
-#include "zoned.h"
 #include "fs.h"
 #include "accessors.h"
 #include "extent-tree.h"
diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h
index 92c595fed1..a733458fd1 100644
--- a/fs/btrfs/space-info.h
+++ b/fs/btrfs/space-info.h
@@ -4,8 +4,17 @@
 #define BTRFS_SPACE_INFO_H
 
 #include <trace/events/btrfs.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/kobject.h>
+#include <linux/lockdep.h>
+#include <linux/wait.h>
+#include <linux/rwsem.h>
 #include "volumes.h"
 
+struct btrfs_fs_info;
+struct btrfs_block_group;
+
 /*
  * Different levels for to flush space when doing space reservations.
  *
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index 0e49dab8da..54736f6238 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -111,6 +111,9 @@ void btrfs_init_subpage_info(struct btrfs_subpage_info *subpage_info, u32 sector
 	subpage_info->checked_offset = cur;
 	cur += nr_bits;
 
+	subpage_info->locked_offset = cur;
+	cur += nr_bits;
+
 	subpage_info->total_nr_bits = cur;
 }
 
@@ -237,28 +240,58 @@ static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info,
 		       start + len <= folio_pos(folio) + PAGE_SIZE);
 }
 
+#define subpage_calc_start_bit(fs_info, folio, name, start, len)	\
+({									\
+	unsigned int start_bit;						\
+									\
+	btrfs_subpage_assert(fs_info, folio, start, len);		\
+	start_bit = offset_in_page(start) >> fs_info->sectorsize_bits;	\
+	start_bit += fs_info->subpage_info->name##_offset;		\
+	start_bit;							\
+})
+
 void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info,
 				struct folio *folio, u64 start, u32 len)
 {
 	struct btrfs_subpage *subpage = folio_get_private(folio);
+	const int start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len);
 	const int nbits = len >> fs_info->sectorsize_bits;
+	unsigned long flags;
+
 
 	btrfs_subpage_assert(fs_info, folio, start, len);
 
+	spin_lock_irqsave(&subpage->lock, flags);
+	/*
+	 * Even though it's just for reading the page, no one should have
+	 * locked the subpage range.
+	 */
+	ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits));
+	bitmap_set(subpage->bitmaps, start_bit, nbits);
 	atomic_add(nbits, &subpage->readers);
+	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
 void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
 			      struct folio *folio, u64 start, u32 len)
 {
 	struct btrfs_subpage *subpage = folio_get_private(folio);
+	const int start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len);
 	const int nbits = len >> fs_info->sectorsize_bits;
+	unsigned long flags;
 	bool is_data;
 	bool last;
 
 	btrfs_subpage_assert(fs_info, folio, start, len);
 	is_data = is_data_inode(folio->mapping->host);
+
+	spin_lock_irqsave(&subpage->lock, flags);
+
+	/* The range should have already been locked. */
+	ASSERT(bitmap_test_range_all_set(subpage->bitmaps, start_bit, nbits));
 	ASSERT(atomic_read(&subpage->readers) >= nbits);
+
+	bitmap_clear(subpage->bitmaps, start_bit, nbits);
 	last = atomic_sub_and_test(nbits, &subpage->readers);
 
 	/*
@@ -270,6 +303,7 @@ void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
 	 */
 	if (is_data && last)
 		folio_unlock(folio);
+	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
 static void btrfs_subpage_clamp_range(struct folio *folio, u64 *start, u32 *len)
@@ -290,28 +324,38 @@ static void btrfs_subpage_clamp_range(struct folio *folio, u64 *start, u32 *len)
 			     orig_start + orig_len) - *start;
 }
 
-void btrfs_subpage_start_writer(const struct btrfs_fs_info *fs_info,
-				struct folio *folio, u64 start, u32 len)
+static void btrfs_subpage_start_writer(const struct btrfs_fs_info *fs_info,
+				       struct folio *folio, u64 start, u32 len)
 {
 	struct btrfs_subpage *subpage = folio_get_private(folio);
+	const int start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len);
 	const int nbits = (len >> fs_info->sectorsize_bits);
+	unsigned long flags;
 	int ret;
 
 	btrfs_subpage_assert(fs_info, folio, start, len);
 
+	spin_lock_irqsave(&subpage->lock, flags);
 	ASSERT(atomic_read(&subpage->readers) == 0);
+	ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits));
+	bitmap_set(subpage->bitmaps, start_bit, nbits);
 	ret = atomic_add_return(nbits, &subpage->writers);
 	ASSERT(ret == nbits);
+	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
-bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
-				       struct folio *folio, u64 start, u32 len)
+static bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
+					      struct folio *folio, u64 start, u32 len)
 {
 	struct btrfs_subpage *subpage = folio_get_private(folio);
+	const int start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len);
 	const int nbits = (len >> fs_info->sectorsize_bits);
+	unsigned long flags;
+	bool last;
 
 	btrfs_subpage_assert(fs_info, folio, start, len);
 
+	spin_lock_irqsave(&subpage->lock, flags);
 	/*
 	 * We have call sites passing @lock_page into
 	 * extent_clear_unlock_delalloc() for compression path.
@@ -319,11 +363,18 @@ bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
 	 * This @locked_page is locked by plain lock_page(), thus its
 	 * subpage::writers is 0.  Handle them in a special way.
 	 */
-	if (atomic_read(&subpage->writers) == 0)
+	if (atomic_read(&subpage->writers) == 0) {
+		spin_unlock_irqrestore(&subpage->lock, flags);
 		return true;
+	}
 
 	ASSERT(atomic_read(&subpage->writers) >= nbits);
-	return atomic_sub_and_test(nbits, &subpage->writers);
+	/* The target range should have been locked. */
+	ASSERT(bitmap_test_range_all_set(subpage->bitmaps, start_bit, nbits));
+	bitmap_clear(subpage->bitmaps, start_bit, nbits);
+	last = atomic_sub_and_test(nbits, &subpage->writers);
+	spin_unlock_irqrestore(&subpage->lock, flags);
+	return last;
 }
 
 /*
@@ -365,16 +416,6 @@ void btrfs_folio_end_writer_lock(const struct btrfs_fs_info *fs_info,
 		folio_unlock(folio);
 }
 
-#define subpage_calc_start_bit(fs_info, folio, name, start, len)	\
-({									\
-	unsigned int start_bit;						\
-									\
-	btrfs_subpage_assert(fs_info, folio, start, len);		\
-	start_bit = offset_in_page(start) >> fs_info->sectorsize_bits;	\
-	start_bit += fs_info->subpage_info->name##_offset;		\
-	start_bit;							\
-})
-
 #define subpage_test_bitmap_all_set(fs_info, subpage, name)		\
 	bitmap_test_range_all_set(subpage->bitmaps,			\
 			fs_info->subpage_info->name##_offset,		\
@@ -751,6 +792,7 @@ void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info,
 	GET_SUBPAGE_BITMAP(subpage, subpage_info, writeback, &writeback_bitmap);
 	GET_SUBPAGE_BITMAP(subpage, subpage_info, ordered, &ordered_bitmap);
 	GET_SUBPAGE_BITMAP(subpage, subpage_info, checked, &checked_bitmap);
+	GET_SUBPAGE_BITMAP(subpage, subpage_info, locked, &checked_bitmap);
 	spin_unlock_irqrestore(&subpage->lock, flags);
 
 	dump_page(folio_page(folio, 0), "btrfs subpage dump");
diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h
index 793c2b314a..b6dc013b0f 100644
--- a/fs/btrfs/subpage.h
+++ b/fs/btrfs/subpage.h
@@ -4,6 +4,11 @@
 #define BTRFS_SUBPAGE_H
 
 #include <linux/spinlock.h>
+#include <linux/atomic.h>
+
+struct address_space;
+struct folio;
+struct btrfs_fs_info;
 
 /*
  * Extra info for subpapge bitmap.
@@ -28,7 +33,7 @@ struct btrfs_subpage_info {
 	unsigned int total_nr_bits;
 
 	/*
-	 * *_start indicates where the bitmap starts, the length is always
+	 * *_offset indicates where the bitmap starts, the length is always
 	 * @bitmap_size, which is calculated from PAGE_SIZE / sectorsize.
 	 */
 	unsigned int uptodate_offset;
@@ -36,6 +41,16 @@ struct btrfs_subpage_info {
 	unsigned int writeback_offset;
 	unsigned int ordered_offset;
 	unsigned int checked_offset;
+
+	/*
+	 * For locked bitmaps, normally it's subpage representation for folio
+	 * Locked flag, but metadata is different:
+	 *
+	 * - Metadata doesn't really lock the folio
+	 *   It's just to prevent page::private get cleared before the last
+	 *   end_page_read().
+	 */
+	unsigned int locked_offset;
 };
 
 /*
@@ -93,10 +108,6 @@ void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info,
 void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
 			      struct folio *folio, u64 start, u32 len);
 
-void btrfs_subpage_start_writer(const struct btrfs_fs_info *fs_info,
-				struct folio *folio, u64 start, u32 len);
-bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
-				       struct folio *folio, u64 start, u32 len);
 int btrfs_folio_start_writer_lock(const struct btrfs_fs_info *fs_info,
 				  struct folio *folio, u64 start, u32 len);
 void btrfs_folio_end_writer_lock(const struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index c45fdaf24c..fa6964de34 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -34,13 +34,11 @@
 #include "disk-io.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
-#include "print-tree.h"
 #include "props.h"
 #include "xattr.h"
 #include "bio.h"
 #include "export.h"
 #include "compression.h"
-#include "rcu-string.h"
 #include "dev-replace.h"
 #include "free-space-cache.h"
 #include "backref.h"
@@ -121,6 +119,7 @@ enum {
 	Opt_thread_pool,
 	Opt_treelog,
 	Opt_user_subvol_rm_allowed,
+	Opt_norecovery,
 
 	/* Rescue options */
 	Opt_rescue,
@@ -247,6 +246,8 @@ static const struct fs_parameter_spec btrfs_fs_parameters[] = {
 	__fsparam(NULL, "nologreplay", Opt_nologreplay, fs_param_deprecated, NULL),
 	/* Deprecated, with alias rescue=usebackuproot */
 	__fsparam(NULL, "usebackuproot", Opt_usebackuproot, fs_param_deprecated, NULL),
+	/* For compatibility only, alias for "rescue=nologreplay". */
+	fsparam_flag("norecovery", Opt_norecovery),
 
 	/* Debugging options. */
 	fsparam_flag_no("enospc_debug", Opt_enospc_debug),
@@ -440,6 +441,11 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		"'nologreplay' is deprecated, use 'rescue=nologreplay' instead");
 		btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY);
 		break;
+	case Opt_norecovery:
+		btrfs_info(NULL,
+"'norecovery' is for compatibility only, recommended to use 'rescue=nologreplay'");
+		btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY);
+		break;
 	case Opt_flushoncommit:
 		if (result.negated)
 			btrfs_clear_opt(ctx->mount_opt, FLUSHONCOMMIT);
@@ -2203,7 +2209,9 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 	vol = memdup_user((void __user *)arg, sizeof(*vol));
 	if (IS_ERR(vol))
 		return PTR_ERR(vol);
-	vol->name[BTRFS_PATH_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args_path(vol);
+	if (ret < 0)
+		goto out;
 
 	switch (cmd) {
 	case BTRFS_IOC_SCAN_DEV:
@@ -2245,6 +2253,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 		break;
 	}
 
+out:
 	kfree(vol);
 	return ret;
 }
diff --git a/fs/btrfs/super.h b/fs/btrfs/super.h
index f18253ca28..cbcab434b5 100644
--- a/fs/btrfs/super.h
+++ b/fs/btrfs/super.h
@@ -3,6 +3,13 @@
 #ifndef BTRFS_SUPER_H
 #define BTRFS_SUPER_H
 
+#include <linux/types.h>
+#include <linux/fs.h>
+#include "fs.h"
+
+struct super_block;
+struct btrfs_fs_info;
+
 bool btrfs_check_options(struct btrfs_fs_info *info, unsigned long *mount_opt,
 			 unsigned long flags);
 int btrfs_sync_fs(struct super_block *sb, int wait);
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 84c05246ff..c6387a8ddb 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -421,7 +421,7 @@ BTRFS_ATTR(static_feature, supported_sectorsizes,
 
 static ssize_t acl_show(struct kobject *kobj, struct kobj_attribute *a, char *buf)
 {
-	return sysfs_emit(buf, "%d\n", !!IS_ENABLED(CONFIG_BTRFS_FS_POSIX_ACL));
+	return sysfs_emit(buf, "%d\n", IS_ENABLED(CONFIG_BTRFS_FS_POSIX_ACL));
 }
 BTRFS_ATTR(static_feature, acl, acl_show);
 
@@ -1228,11 +1228,12 @@ static ssize_t btrfs_read_policy_show(struct kobject *kobj,
 				      struct kobj_attribute *a, char *buf)
 {
 	struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj);
+	const enum btrfs_read_policy policy = READ_ONCE(fs_devices->read_policy);
 	ssize_t ret = 0;
 	int i;
 
 	for (i = 0; i < BTRFS_NR_READ_POLICY; i++) {
-		if (fs_devices->read_policy == i)
+		if (policy == i)
 			ret += sysfs_emit_at(buf, ret, "%s[%s]",
 					 (ret == 0 ? "" : " "),
 					 btrfs_read_policy_name[i]);
@@ -1256,8 +1257,8 @@ static ssize_t btrfs_read_policy_store(struct kobject *kobj,
 
 	for (i = 0; i < BTRFS_NR_READ_POLICY; i++) {
 		if (sysfs_streq(buf, btrfs_read_policy_name[i])) {
-			if (i != fs_devices->read_policy) {
-				fs_devices->read_policy = i;
+			if (i != READ_ONCE(fs_devices->read_policy)) {
+				WRITE_ONCE(fs_devices->read_policy, i);
 				btrfs_info(fs_devices->fs_info,
 					   "read policy set to '%s'",
 					   btrfs_read_policy_name[i]);
@@ -1306,6 +1307,47 @@ static ssize_t btrfs_bg_reclaim_threshold_store(struct kobject *kobj,
 BTRFS_ATTR_RW(, bg_reclaim_threshold, btrfs_bg_reclaim_threshold_show,
 	      btrfs_bg_reclaim_threshold_store);
 
+#ifdef CONFIG_BTRFS_DEBUG
+static ssize_t btrfs_offload_csum_show(struct kobject *kobj,
+				       struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj);
+
+	switch (READ_ONCE(fs_devices->offload_csum_mode)) {
+	case BTRFS_OFFLOAD_CSUM_AUTO:
+		return sysfs_emit(buf, "auto\n");
+	case BTRFS_OFFLOAD_CSUM_FORCE_ON:
+		return sysfs_emit(buf, "1\n");
+	case BTRFS_OFFLOAD_CSUM_FORCE_OFF:
+		return sysfs_emit(buf, "0\n");
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+}
+
+static ssize_t btrfs_offload_csum_store(struct kobject *kobj,
+					struct kobj_attribute *a, const char *buf,
+					size_t len)
+{
+	struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj);
+	int ret;
+	bool val;
+
+	ret = kstrtobool(buf, &val);
+	if (ret == 0)
+		WRITE_ONCE(fs_devices->offload_csum_mode,
+			   val ? BTRFS_OFFLOAD_CSUM_FORCE_ON : BTRFS_OFFLOAD_CSUM_FORCE_OFF);
+	else if (ret == -EINVAL && sysfs_streq(buf, "auto"))
+		WRITE_ONCE(fs_devices->offload_csum_mode, BTRFS_OFFLOAD_CSUM_AUTO);
+	else
+		return -EINVAL;
+
+	return len;
+}
+BTRFS_ATTR_RW(, offload_csum, btrfs_offload_csum_show, btrfs_offload_csum_store);
+#endif
+
 /*
  * Per-filesystem information and stats.
  *
@@ -1325,6 +1367,9 @@ static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(, bg_reclaim_threshold),
 	BTRFS_ATTR_PTR(, commit_stats),
 	BTRFS_ATTR_PTR(, temp_fsid),
+#ifdef CONFIG_BTRFS_DEBUG
+	BTRFS_ATTR_PTR(, offload_csum),
+#endif
 	NULL,
 };
 
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index 86c7eef128..e6a284c598 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -3,8 +3,17 @@
 #ifndef BTRFS_SYSFS_H
 #define BTRFS_SYSFS_H
 
+#include <linux/types.h>
+#include <linux/compiler_types.h>
 #include <linux/kobject.h>
 
+struct btrfs_fs_info;
+struct btrfs_device;
+struct btrfs_fs_devices;
+struct btrfs_block_group;
+struct btrfs_space_info;
+struct btrfs_qgroup;
+
 enum btrfs_feature_set {
 	FEAT_COMPAT,
 	FEAT_COMPAT_RO,
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 9957de9f78..99da9d34b7 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -258,7 +258,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	/* First with no extents */
 	BTRFS_I(inode)->root = root;
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, sectorsize);
 	if (IS_ERR(em)) {
 		em = NULL;
 		test_err("got an error when we shouldn't have");
@@ -278,7 +278,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	 */
 	setup_file_extents(root, sectorsize);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, (u64)-1);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, (u64)-1);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -316,7 +316,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -339,7 +339,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Regular extent */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -367,7 +367,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* The next 3 are split extents */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -396,7 +396,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -418,7 +418,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -452,7 +452,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Prealloc extent */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -481,7 +481,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* The next 3 are a half written prealloc extent */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -511,7 +511,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -544,7 +544,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -579,7 +579,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Now for the compressed extent */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -613,7 +613,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Split compressed extent */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -648,7 +648,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -675,7 +675,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -710,7 +710,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* A hole between regular extents but no hole extent */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset + 6, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset + 6, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -737,7 +737,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, SZ_4M);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, SZ_4M);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -770,7 +770,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -850,7 +850,7 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 	insert_inode_item_key(root);
 	insert_extent(root, sectorsize, sectorsize, sectorsize, 0, sectorsize,
 		      sectorsize, BTRFS_FILE_EXTENT_REG, 0, 1);
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, 2 * sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 2 * sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -872,7 +872,7 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 	}
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, sectorsize, 2 * sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, sectorsize, 2 * sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index b93cdf5f17..85f359e0e0 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -23,12 +23,10 @@
 #include "qgroup.h"
 #include "block-group.h"
 #include "space-info.h"
-#include "zoned.h"
 #include "fs.h"
 #include "accessors.h"
 #include "extent-tree.h"
 #include "root-tree.h"
-#include "defrag.h"
 #include "dir-item.h"
 #include "uuid-tree.h"
 #include "ioctl.h"
@@ -1958,19 +1956,6 @@ static void update_super_roots(struct btrfs_fs_info *fs_info)
 		super->uuid_tree_generation = root_item->generation;
 }
 
-int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
-{
-	struct btrfs_transaction *trans;
-	int ret = 0;
-
-	spin_lock(&info->trans_lock);
-	trans = info->running_transaction;
-	if (trans)
-		ret = (trans->state >= TRANS_STATE_COMMIT_START);
-	spin_unlock(&info->trans_lock);
-	return ret;
-}
-
 int btrfs_transaction_blocked(struct btrfs_fs_info *info)
 {
 	struct btrfs_transaction *trans;
@@ -2685,9 +2670,7 @@ void __cold __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
 
 int __init btrfs_transaction_init(void)
 {
-	btrfs_trans_handle_cachep = kmem_cache_create("btrfs_trans_handle",
-			sizeof(struct btrfs_trans_handle), 0,
-			SLAB_TEMPORARY | SLAB_MEM_SPREAD, NULL);
+	btrfs_trans_handle_cachep = KMEM_CACHE(btrfs_trans_handle, SLAB_TEMPORARY);
 	if (!btrfs_trans_handle_cachep)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 2bf8bbdfd0..4e451ab173 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -6,12 +6,27 @@
 #ifndef BTRFS_TRANSACTION_H
 #define BTRFS_TRANSACTION_H
 
+#include <linux/atomic.h>
 #include <linux/refcount.h>
+#include <linux/list.h>
+#include <linux/time64.h>
+#include <linux/mutex.h>
+#include <linux/wait.h>
 #include "btrfs_inode.h"
 #include "delayed-ref.h"
-#include "ctree.h"
+#include "extent-io-tree.h"
+#include "block-rsv.h"
+#include "messages.h"
 #include "misc.h"
 
+struct dentry;
+struct inode;
+struct btrfs_pending_snapshot;
+struct btrfs_fs_info;
+struct btrfs_root_item;
+struct btrfs_root;
+struct btrfs_path;
+
 /* Radix-tree tag for roots that are part of the trasaction. */
 #define BTRFS_ROOT_TRANS_TAG			0
 
@@ -262,7 +277,6 @@ int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
 				struct extent_io_tree *dirty_pages, int mark);
 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);
 void btrfs_put_transaction(struct btrfs_transaction *transaction);
 void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root);
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 75c78a5556..32604e9b31 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -21,7 +21,6 @@
 #include "messages.h"
 #include "ctree.h"
 #include "tree-checker.h"
-#include "disk-io.h"
 #include "compression.h"
 #include "volumes.h"
 #include "misc.h"
@@ -30,7 +29,6 @@
 #include "file-item.h"
 #include "inode-item.h"
 #include "dir-item.h"
-#include "raid-stripe-tree.h"
 #include "extent-tree.h"
 
 /*
@@ -67,6 +65,7 @@ static void generic_err(const struct extent_buffer *eb, int slot,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	dump_page(folio_page(eb->folios[0], 0), "eb page dump");
 	btrfs_crit(fs_info,
 		"corrupt %s: root=%llu block=%llu slot=%d, %pV",
 		btrfs_header_level(eb) == 0 ? "leaf" : "node",
@@ -94,6 +93,7 @@ static void file_extent_err(const struct extent_buffer *eb, int slot,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	dump_page(folio_page(eb->folios[0], 0), "eb page dump");
 	btrfs_crit(fs_info,
 	"corrupt %s: root=%llu block=%llu slot=%d ino=%llu file_offset=%llu, %pV",
 		btrfs_header_level(eb) == 0 ? "leaf" : "node",
@@ -154,6 +154,7 @@ static void dir_item_err(const struct extent_buffer *eb, int slot,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	dump_page(folio_page(eb->folios[0], 0), "eb page dump");
 	btrfs_crit(fs_info,
 		"corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV",
 		btrfs_header_level(eb) == 0 ? "leaf" : "node",
@@ -649,6 +650,7 @@ static void block_group_err(const struct extent_buffer *eb, int slot,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	dump_page(folio_page(eb->folios[0], 0), "eb page dump");
 	btrfs_crit(fs_info,
 	"corrupt %s: root=%llu block=%llu slot=%d bg_start=%llu bg_len=%llu, %pV",
 		btrfs_header_level(eb) == 0 ? "leaf" : "node",
@@ -1005,6 +1007,7 @@ static void dev_item_err(const struct extent_buffer *eb, int slot,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	dump_page(folio_page(eb->folios[0], 0), "eb page dump");
 	btrfs_crit(eb->fs_info,
 	"corrupt %s: root=%llu block=%llu slot=%d devid=%llu %pV",
 		btrfs_header_level(eb) == 0 ? "leaf" : "node",
@@ -1260,6 +1263,7 @@ static void extent_err(const struct extent_buffer *eb, int slot,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	dump_page(folio_page(eb->folios[0], 0), "eb page dump");
 	btrfs_crit(eb->fs_info,
 	"corrupt %s: block=%llu slot=%d extent bytenr=%llu len=%llu %pV",
 		btrfs_header_level(eb) == 0 ? "leaf" : "node",
diff --git a/fs/btrfs/tree-checker.h b/fs/btrfs/tree-checker.h
index 580ec4fde0..01669cfa65 100644
--- a/fs/btrfs/tree-checker.h
+++ b/fs/btrfs/tree-checker.h
@@ -6,10 +6,12 @@
 #ifndef BTRFS_TREE_CHECKER_H
 #define BTRFS_TREE_CHECKER_H
 
+#include <linux/types.h>
 #include <uapi/linux/btrfs_tree.h>
 
 struct extent_buffer;
 struct btrfs_chunk;
+struct btrfs_key;
 
 /* All the extra info needed to verify the parentness of a tree block. */
 struct btrfs_tree_parent_check {
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 331fc74299..d4fc5fedd8 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -13,13 +13,11 @@
 #include "tree-log.h"
 #include "disk-io.h"
 #include "locking.h"
-#include "print-tree.h"
 #include "backref.h"
 #include "compression.h"
 #include "qgroup.h"
 #include "block-group.h"
 #include "space-info.h"
-#include "zoned.h"
 #include "inode-item.h"
 #include "fs.h"
 #include "accessors.h"
@@ -2820,6 +2818,52 @@ static void wait_for_writer(struct btrfs_root *root)
 	finish_wait(&root->log_writer_wait, &wait);
 }
 
+void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, struct inode *inode)
+{
+	ctx->log_ret = 0;
+	ctx->log_transid = 0;
+	ctx->log_new_dentries = false;
+	ctx->logging_new_name = false;
+	ctx->logging_new_delayed_dentries = false;
+	ctx->logged_before = false;
+	ctx->inode = inode;
+	INIT_LIST_HEAD(&ctx->list);
+	INIT_LIST_HEAD(&ctx->ordered_extents);
+	INIT_LIST_HEAD(&ctx->conflict_inodes);
+	ctx->num_conflict_inodes = 0;
+	ctx->logging_conflict_inodes = false;
+	ctx->scratch_eb = NULL;
+}
+
+void btrfs_init_log_ctx_scratch_eb(struct btrfs_log_ctx *ctx)
+{
+	struct btrfs_inode *inode = BTRFS_I(ctx->inode);
+
+	if (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) &&
+	    !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags))
+		return;
+
+	/*
+	 * Don't care about allocation failure. This is just for optimization,
+	 * if we fail to allocate here, we will try again later if needed.
+	 */
+	ctx->scratch_eb = alloc_dummy_extent_buffer(inode->root->fs_info, 0);
+}
+
+void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx)
+{
+	struct btrfs_ordered_extent *ordered;
+	struct btrfs_ordered_extent *tmp;
+
+	ASSERT(inode_is_locked(ctx->inode));
+
+	list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) {
+		list_del_init(&ordered->log_list);
+		btrfs_put_ordered_extent(ordered);
+	}
+}
+
+
 static inline void btrfs_remove_log_ctx(struct btrfs_root *root,
 					struct btrfs_log_ctx *ctx)
 {
@@ -3619,6 +3663,30 @@ out:
 	return ret;
 }
 
+static int clone_leaf(struct btrfs_path *path, struct btrfs_log_ctx *ctx)
+{
+	const int slot = path->slots[0];
+
+	if (ctx->scratch_eb) {
+		copy_extent_buffer_full(ctx->scratch_eb, path->nodes[0]);
+	} else {
+		ctx->scratch_eb = btrfs_clone_extent_buffer(path->nodes[0]);
+		if (!ctx->scratch_eb)
+			return -ENOMEM;
+	}
+
+	btrfs_release_path(path);
+	path->nodes[0] = ctx->scratch_eb;
+	path->slots[0] = slot;
+	/*
+	 * Add extra ref to scratch eb so that it is not freed when callers
+	 * release the path, so we can reuse it later if needed.
+	 */
+	atomic_inc(&ctx->scratch_eb->refs);
+
+	return 0;
+}
+
 static int process_dir_items_leaf(struct btrfs_trans_handle *trans,
 				  struct btrfs_inode *inode,
 				  struct btrfs_path *path,
@@ -3633,23 +3701,20 @@ static int process_dir_items_leaf(struct btrfs_trans_handle *trans,
 	bool last_found = false;
 	int batch_start = 0;
 	int batch_size = 0;
-	int i;
+	int ret;
 
 	/*
 	 * We need to clone the leaf, release the read lock on it, and use the
 	 * clone before modifying the log tree. See the comment at copy_items()
 	 * about why we need to do this.
 	 */
-	src = btrfs_clone_extent_buffer(path->nodes[0]);
-	if (!src)
-		return -ENOMEM;
+	ret = clone_leaf(path, ctx);
+	if (ret < 0)
+		return ret;
 
-	i = path->slots[0];
-	btrfs_release_path(path);
-	path->nodes[0] = src;
-	path->slots[0] = i;
+	src = path->nodes[0];
 
-	for (; i < nritems; i++) {
+	for (int i = path->slots[0]; i < nritems; i++) {
 		struct btrfs_dir_item *di;
 		struct btrfs_key key;
 		int ret;
@@ -4259,17 +4324,16 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 			       struct btrfs_path *dst_path,
 			       struct btrfs_path *src_path,
 			       int start_slot, int nr, int inode_only,
-			       u64 logged_isize)
+			       u64 logged_isize, struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_root *log = inode->root->log_root;
 	struct btrfs_file_extent_item *extent;
 	struct extent_buffer *src;
-	int ret = 0;
+	int ret;
 	struct btrfs_key *ins_keys;
 	u32 *ins_sizes;
 	struct btrfs_item_batch batch;
 	char *ins_data;
-	int i;
 	int dst_index;
 	const bool skip_csum = (inode->flags & BTRFS_INODE_NODATASUM);
 	const u64 i_size = i_size_read(&inode->vfs_inode);
@@ -4302,14 +4366,11 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	 * while the other is holding the delayed node's mutex and wants to
 	 * write lock the same subvolume leaf for flushing delayed items.
 	 */
-	src = btrfs_clone_extent_buffer(src_path->nodes[0]);
-	if (!src)
-		return -ENOMEM;
+	ret = clone_leaf(src_path, ctx);
+	if (ret < 0)
+		return ret;
 
-	i = src_path->slots[0];
-	btrfs_release_path(src_path);
-	src_path->nodes[0] = src;
-	src_path->slots[0] = i;
+	src = src_path->nodes[0];
 
 	ins_data = kmalloc(nr * sizeof(struct btrfs_key) +
 			   nr * sizeof(u32), GFP_NOFS);
@@ -4324,7 +4385,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	batch.nr = 0;
 
 	dst_index = 0;
-	for (i = 0; i < nr; i++) {
+	for (int i = 0; i < nr; i++) {
 		const int src_slot = start_slot + i;
 		struct btrfs_root *csum_root;
 		struct btrfs_ordered_sum *sums;
@@ -4431,7 +4492,7 @@ add_to_batch:
 		goto out;
 
 	dst_index = 0;
-	for (i = 0; i < nr; i++) {
+	for (int i = 0; i < nr; i++) {
 		const int src_slot = start_slot + i;
 		const int dst_slot = dst_path->slots[0] + dst_index;
 		struct btrfs_key key;
@@ -4704,7 +4765,8 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
  */
 static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 				      struct btrfs_inode *inode,
-				      struct btrfs_path *path)
+				      struct btrfs_path *path,
+				      struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_root *root = inode->root;
 	struct btrfs_key key;
@@ -4770,7 +4832,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 		if (slot >= btrfs_header_nritems(leaf)) {
 			if (ins_nr > 0) {
 				ret = copy_items(trans, inode, dst_path, path,
-						 start_slot, ins_nr, 1, 0);
+						 start_slot, ins_nr, 1, 0, ctx);
 				if (ret < 0)
 					goto out;
 				ins_nr = 0;
@@ -4794,18 +4856,23 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 			path->slots[0]++;
 			continue;
 		}
-		if (!dropped_extents) {
-			/*
-			 * Avoid logging extent items logged in past fsync calls
-			 * and leading to duplicate keys in the log tree.
-			 */
+		/*
+		 * Avoid overlapping items in the log tree. The first time we
+		 * get here, get rid of everything from a past fsync. After
+		 * that, if the current extent starts before the end of the last
+		 * extent we copied, truncate the last one. This can happen if
+		 * an ordered extent completion modifies the subvolume tree
+		 * while btrfs_next_leaf() has the tree unlocked.
+		 */
+		if (!dropped_extents || key.offset < truncate_offset) {
 			ret = truncate_inode_items(trans, root->log_root, inode,
-						   truncate_offset,
+						   min(key.offset, truncate_offset),
 						   BTRFS_EXTENT_DATA_KEY);
 			if (ret)
 				goto out;
 			dropped_extents = true;
 		}
+		truncate_offset = btrfs_file_extent_end(path);
 		if (ins_nr == 0)
 			start_slot = slot;
 		ins_nr++;
@@ -4820,7 +4887,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 	}
 	if (ins_nr > 0)
 		ret = copy_items(trans, inode, dst_path, path,
-				 start_slot, ins_nr, 1, 0);
+				 start_slot, ins_nr, 1, 0, ctx);
 out:
 	btrfs_release_path(path);
 	btrfs_free_path(dst_path);
@@ -4899,7 +4966,7 @@ process:
 	write_unlock(&tree->lock);
 
 	if (!ret)
-		ret = btrfs_log_prealloc_extents(trans, inode, path);
+		ret = btrfs_log_prealloc_extents(trans, inode, path, ctx);
 	if (ret)
 		return ret;
 
@@ -4980,7 +5047,8 @@ static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode,
 static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 				struct btrfs_inode *inode,
 				struct btrfs_path *path,
-				struct btrfs_path *dst_path)
+				struct btrfs_path *dst_path,
+				struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_root *root = inode->root;
 	int ret;
@@ -5009,7 +5077,7 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 		if (slot >= nritems) {
 			if (ins_nr > 0) {
 				ret = copy_items(trans, inode, dst_path, path,
-						 start_slot, ins_nr, 1, 0);
+						 start_slot, ins_nr, 1, 0, ctx);
 				if (ret < 0)
 					return ret;
 				ins_nr = 0;
@@ -5035,7 +5103,7 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 	}
 	if (ins_nr > 0) {
 		ret = copy_items(trans, inode, dst_path, path,
-				 start_slot, ins_nr, 1, 0);
+				 start_slot, ins_nr, 1, 0, ctx);
 		if (ret < 0)
 			return ret;
 	}
@@ -5847,7 +5915,7 @@ again:
 				}
 				ret = copy_items(trans, inode, dst_path, path,
 						 ins_start_slot, ins_nr,
-						 inode_only, logged_isize);
+						 inode_only, logged_isize, ctx);
 				if (ret < 0)
 					return ret;
 				ins_nr = 0;
@@ -5866,7 +5934,7 @@ again:
 				goto next_slot;
 			ret = copy_items(trans, inode, dst_path, path,
 					 ins_start_slot,
-					 ins_nr, inode_only, logged_isize);
+					 ins_nr, inode_only, logged_isize, ctx);
 			if (ret < 0)
 				return ret;
 			ins_nr = 0;
@@ -5883,7 +5951,7 @@ again:
 		}
 
 		ret = copy_items(trans, inode, dst_path, path, ins_start_slot,
-				 ins_nr, inode_only, logged_isize);
+				 ins_nr, inode_only, logged_isize, ctx);
 		if (ret < 0)
 			return ret;
 		ins_nr = 1;
@@ -5898,7 +5966,7 @@ next_slot:
 		if (ins_nr) {
 			ret = copy_items(trans, inode, dst_path, path,
 					 ins_start_slot, ins_nr, inode_only,
-					 logged_isize);
+					 logged_isize, ctx);
 			if (ret < 0)
 				return ret;
 			ins_nr = 0;
@@ -5923,7 +5991,7 @@ next_key:
 	}
 	if (ins_nr) {
 		ret = copy_items(trans, inode, dst_path, path, ins_start_slot,
-				 ins_nr, inode_only, logged_isize);
+				 ins_nr, inode_only, logged_isize, ctx);
 		if (ret)
 			return ret;
 	}
@@ -5934,7 +6002,7 @@ next_key:
 		 * lock the same leaf with btrfs_log_prealloc_extents() below.
 		 */
 		btrfs_release_path(path);
-		ret = btrfs_log_prealloc_extents(trans, inode, dst_path);
+		ret = btrfs_log_prealloc_extents(trans, inode, dst_path, ctx);
 	}
 
 	return ret;
@@ -6526,7 +6594,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 
 	btrfs_release_path(path);
 	btrfs_release_path(dst_path);
-	ret = btrfs_log_all_xattrs(trans, inode, path, dst_path);
+	ret = btrfs_log_all_xattrs(trans, inode, path, dst_path, ctx);
 	if (ret)
 		goto out_unlock;
 	xattrs_logged = true;
@@ -6553,7 +6621,7 @@ log_extents:
 		 * BTRFS_INODE_COPY_EVERYTHING set.
 		 */
 		if (!xattrs_logged && inode->logged_trans < trans->transid) {
-			ret = btrfs_log_all_xattrs(trans, inode, path, dst_path);
+			ret = btrfs_log_all_xattrs(trans, inode, path, dst_path, ctx);
 			if (ret)
 				goto out_unlock;
 			btrfs_release_path(path);
@@ -7502,6 +7570,7 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans,
 
 	btrfs_init_log_ctx(&ctx, &inode->vfs_inode);
 	ctx.logging_new_name = true;
+	btrfs_init_log_ctx_scratch_eb(&ctx);
 	/*
 	 * We don't care about the return value. If we fail to log the new name
 	 * then we know the next attempt to sync the log will fallback to a full
@@ -7510,6 +7579,7 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans,
 	 * inconsistent state after a rename operation.
 	 */
 	btrfs_log_inode_parent(trans, inode, parent, LOG_INODE_EXISTS, &ctx);
+	free_extent_buffer(ctx.scratch_eb);
 	ASSERT(list_empty(&ctx.conflict_inodes));
 out:
 	/*
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index a550a8a375..22e9cbc815 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -6,10 +6,18 @@
 #ifndef BTRFS_TREE_LOG_H
 #define BTRFS_TREE_LOG_H
 
+#include <linux/list.h>
+#include <linux/fs.h>
 #include "messages.h"
 #include "ctree.h"
 #include "transaction.h"
 
+struct inode;
+struct dentry;
+struct btrfs_ordered_extent;
+struct btrfs_root;
+struct btrfs_trans_handle;
+
 /* return value for btrfs_log_dentry_safe that means we don't need to log it at all */
 #define BTRFS_NO_LOG_SYNC 256
 
@@ -36,37 +44,20 @@ struct btrfs_log_ctx {
 	struct list_head conflict_inodes;
 	int num_conflict_inodes;
 	bool logging_conflict_inodes;
+	/*
+	 * Used for fsyncs that need to copy items from the subvolume tree to
+	 * the log tree (full sync flag set or copy everything flag set) to
+	 * avoid allocating a temporary extent buffer while holding a lock on
+	 * an extent buffer of the subvolume tree and under the log transaction.
+	 * Also helps to avoid allocating and freeing a temporary extent buffer
+	 * in case we need to process multiple leaves from the subvolume tree.
+	 */
+	struct extent_buffer *scratch_eb;
 };
 
-static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx,
-				      struct inode *inode)
-{
-	ctx->log_ret = 0;
-	ctx->log_transid = 0;
-	ctx->log_new_dentries = false;
-	ctx->logging_new_name = false;
-	ctx->logging_new_delayed_dentries = false;
-	ctx->logged_before = false;
-	ctx->inode = inode;
-	INIT_LIST_HEAD(&ctx->list);
-	INIT_LIST_HEAD(&ctx->ordered_extents);
-	INIT_LIST_HEAD(&ctx->conflict_inodes);
-	ctx->num_conflict_inodes = 0;
-	ctx->logging_conflict_inodes = false;
-}
-
-static inline void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx)
-{
-	struct btrfs_ordered_extent *ordered;
-	struct btrfs_ordered_extent *tmp;
-
-	ASSERT(inode_is_locked(ctx->inode));
-
-	list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) {
-		list_del_init(&ordered->log_list);
-		btrfs_put_ordered_extent(ordered);
-	}
-}
+void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, struct inode *inode);
+void btrfs_init_log_ctx_scratch_eb(struct btrfs_log_ctx *ctx);
+void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx);
 
 static inline void btrfs_set_log_full_commit(struct btrfs_trans_handle *trans)
 {
diff --git a/fs/btrfs/tree-mod-log.c b/fs/btrfs/tree-mod-log.c
index 3df6153d5d..43b3accbed 100644
--- a/fs/btrfs/tree-mod-log.c
+++ b/fs/btrfs/tree-mod-log.c
@@ -44,7 +44,7 @@ struct tree_mod_elem {
 /*
  * Pull a new tree mod seq number for our operation.
  */
-static inline u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info)
+static u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info)
 {
 	return atomic64_inc_return(&fs_info->tree_mod_seq);
 }
@@ -170,8 +170,7 @@ static noinline int tree_mod_log_insert(struct btrfs_fs_info *fs_info,
  * this until all tree mod log insertions are recorded in the rb tree and then
  * write unlock fs_info::tree_mod_log_lock.
  */
-static inline bool tree_mod_dont_log(struct btrfs_fs_info *fs_info,
-				    struct extent_buffer *eb)
+static bool tree_mod_dont_log(struct btrfs_fs_info *fs_info, struct extent_buffer *eb)
 {
 	if (!test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags))
 		return true;
@@ -188,7 +187,7 @@ static inline bool tree_mod_dont_log(struct btrfs_fs_info *fs_info,
 }
 
 /* Similar to tree_mod_dont_log, but doesn't acquire any locks. */
-static inline bool tree_mod_need_log(const struct btrfs_fs_info *fs_info,
+static bool tree_mod_need_log(const struct btrfs_fs_info *fs_info,
 				    struct extent_buffer *eb)
 {
 	if (!test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags))
@@ -367,9 +366,9 @@ free_tms:
 	return ret;
 }
 
-static inline int tree_mod_log_free_eb(struct btrfs_fs_info *fs_info,
-				       struct tree_mod_elem **tm_list,
-				       int nritems)
+static int tree_mod_log_free_eb(struct btrfs_fs_info *fs_info,
+				struct tree_mod_elem **tm_list,
+				int nritems)
 {
 	int i, j;
 	int ret;
diff --git a/fs/btrfs/tree-mod-log.h b/fs/btrfs/tree-mod-log.h
index 94f10afeee..ff00c8e8a3 100644
--- a/fs/btrfs/tree-mod-log.h
+++ b/fs/btrfs/tree-mod-log.h
@@ -3,7 +3,13 @@
 #ifndef BTRFS_TREE_MOD_LOG_H
 #define BTRFS_TREE_MOD_LOG_H
 
-#include "ctree.h"
+#include <linux/list.h>
+
+struct extent_buffer;
+struct btrfs_fs_info;
+struct btrfs_path;
+struct btrfs_root;
+struct btrfs_seq_list;
 
 /* Represents a tree mod log user. */
 struct btrfs_seq_list {
diff --git a/fs/btrfs/ulist.c b/fs/btrfs/ulist.c
index b4ac2b0cd2..183863f4bf 100644
--- a/fs/btrfs/ulist.c
+++ b/fs/btrfs/ulist.c
@@ -7,7 +7,6 @@
 #include <linux/slab.h>
 #include "messages.h"
 #include "ulist.h"
-#include "ctree.h"
 
 /*
  * ulist is a generic data structure to hold a collection of unique u64
diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h
index b2cef187ea..8e200fe1a2 100644
--- a/fs/btrfs/ulist.h
+++ b/fs/btrfs/ulist.h
@@ -7,6 +7,7 @@
 #ifndef BTRFS_ULIST_H
 #define BTRFS_ULIST_H
 
+#include <linux/types.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
 
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
index 5be74f9e47..b0aff297d6 100644
--- a/fs/btrfs/uuid-tree.c
+++ b/fs/btrfs/uuid-tree.c
@@ -9,7 +9,6 @@
 #include "ctree.h"
 #include "transaction.h"
 #include "disk-io.h"
-#include "print-tree.h"
 #include "fs.h"
 #include "accessors.h"
 #include "uuid-tree.h"
@@ -114,7 +113,7 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
 
 	ret = btrfs_insert_empty_item(trans, uuid_root, path, &key,
 				      sizeof(subid_le));
-	if (ret >= 0) {
+	if (ret == 0) {
 		/* Add an item for the type for the first time */
 		eb = path->nodes[0];
 		slot = path->slots[0];
diff --git a/fs/btrfs/uuid-tree.h b/fs/btrfs/uuid-tree.h
index 5350c87fe2..080ede0227 100644
--- a/fs/btrfs/uuid-tree.h
+++ b/fs/btrfs/uuid-tree.h
@@ -3,6 +3,11 @@
 #ifndef BTRFS_UUID_TREE_H
 #define BTRFS_UUID_TREE_H
 
+#include <linux/types.h>
+
+struct btrfs_trans_handle;
+struct btrfs_fs_info;
+
 int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
 			u64 subid);
 int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
diff --git a/fs/btrfs/verity.c b/fs/btrfs/verity.c
index 66e2270b0d..4042dd6437 100644
--- a/fs/btrfs/verity.c
+++ b/fs/btrfs/verity.c
@@ -14,7 +14,6 @@
 #include "ctree.h"
 #include "btrfs_inode.h"
 #include "transaction.h"
-#include "disk-io.h"
 #include "locking.h"
 #include "fs.h"
 #include "accessors.h"
diff --git a/fs/btrfs/verity.h b/fs/btrfs/verity.h
index 91c10f7d0a..d696659e43 100644
--- a/fs/btrfs/verity.h
+++ b/fs/btrfs/verity.h
@@ -3,8 +3,13 @@
 #ifndef BTRFS_VERITY_H
 #define BTRFS_VERITY_H
 
+struct inode;
+struct btrfs_inode;
+
 #ifdef CONFIG_FS_VERITY
 
+#include <linux/fsverity.h>
+
 extern const struct fsverity_operations btrfs_verityops;
 
 int btrfs_drop_verity_items(struct btrfs_inode *inode);
@@ -12,6 +17,8 @@ int btrfs_get_verity_descriptor(struct inode *inode, void *buf, size_t buf_size)
 
 #else
 
+#include <linux/errno.h>
+
 static inline int btrfs_drop_verity_items(struct btrfs_inode *inode)
 {
 	return 0;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 3ebadc5ec8..ef6bd2f425 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -14,10 +14,8 @@
 #include <linux/namei.h>
 #include "misc.h"
 #include "ctree.h"
-#include "extent_map.h"
 #include "disk-io.h"
 #include "transaction.h"
-#include "print-tree.h"
 #include "volumes.h"
 #include "raid56.h"
 #include "rcu-string.h"
@@ -468,39 +466,39 @@ static noinline struct btrfs_fs_devices *find_fsid(
 
 static int
 btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder,
-		      int flush, struct bdev_handle **bdev_handle,
+		      int flush, struct file **bdev_file,
 		      struct btrfs_super_block **disk_super)
 {
 	struct block_device *bdev;
 	int ret;
 
-	*bdev_handle = bdev_open_by_path(device_path, flags, holder, NULL);
+	*bdev_file = bdev_file_open_by_path(device_path, flags, holder, NULL);
 
-	if (IS_ERR(*bdev_handle)) {
-		ret = PTR_ERR(*bdev_handle);
+	if (IS_ERR(*bdev_file)) {
+		ret = PTR_ERR(*bdev_file);
 		goto error;
 	}
-	bdev = (*bdev_handle)->bdev;
+	bdev = file_bdev(*bdev_file);
 
 	if (flush)
 		sync_blockdev(bdev);
 	ret = set_blocksize(bdev, BTRFS_BDEV_BLOCKSIZE);
 	if (ret) {
-		bdev_release(*bdev_handle);
+		fput(*bdev_file);
 		goto error;
 	}
 	invalidate_bdev(bdev);
 	*disk_super = btrfs_read_dev_super(bdev);
 	if (IS_ERR(*disk_super)) {
 		ret = PTR_ERR(*disk_super);
-		bdev_release(*bdev_handle);
+		fput(*bdev_file);
 		goto error;
 	}
 
 	return 0;
 
 error:
-	*bdev_handle = NULL;
+	*bdev_file = NULL;
 	return ret;
 }
 
@@ -643,7 +641,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 			struct btrfs_device *device, blk_mode_t flags,
 			void *holder)
 {
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct btrfs_super_block *disk_super;
 	u64 devid;
 	int ret;
@@ -654,7 +652,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 		return -EINVAL;
 
 	ret = btrfs_get_bdev_and_sb(device->name->str, flags, holder, 1,
-				    &bdev_handle, &disk_super);
+				    &bdev_file, &disk_super);
 	if (ret)
 		return ret;
 
@@ -678,20 +676,20 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 		clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 		fs_devices->seeding = true;
 	} else {
-		if (bdev_read_only(bdev_handle->bdev))
+		if (bdev_read_only(file_bdev(bdev_file)))
 			clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 		else
 			set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 	}
 
-	if (!bdev_nonrot(bdev_handle->bdev))
+	if (!bdev_nonrot(file_bdev(bdev_file)))
 		fs_devices->rotating = true;
 
-	if (bdev_max_discard_sectors(bdev_handle->bdev))
+	if (bdev_max_discard_sectors(file_bdev(bdev_file)))
 		fs_devices->discardable = true;
 
-	device->bdev_handle = bdev_handle;
-	device->bdev = bdev_handle->bdev;
+	device->bdev_file = bdev_file;
+	device->bdev = file_bdev(bdev_file);
 	clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 
 	if (device->devt != device->bdev->bd_dev) {
@@ -716,7 +714,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 
 error_free_page:
 	btrfs_release_disk_super(disk_super);
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 
 	return -EINVAL;
 }
@@ -779,8 +777,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		if (same_fsid_diff_dev) {
 			generate_random_uuid(fs_devices->fsid);
 			fs_devices->temp_fsid = true;
-			pr_info("BTRFS: device %s using temp-fsid %pU\n",
-				path, fs_devices->fsid);
+		pr_info("BTRFS: device %s (%d:%d) using temp-fsid %pU\n",
+				path, MAJOR(path_devt), MINOR(path_devt),
+				fs_devices->fsid);
 		}
 
 		mutex_lock(&fs_devices->device_list_mutex);
@@ -809,8 +808,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 		if (fs_devices->opened) {
 			btrfs_err(NULL,
-"device %s belongs to fsid %pU, and the fs is already mounted, scanned by %s (%d)",
-				  path, fs_devices->fsid, current->comm,
+"device %s (%d:%d) belongs to fsid %pU, and the fs is already mounted, scanned by %s (%d)",
+				  path, MAJOR(path_devt), MINOR(path_devt),
+				  fs_devices->fsid, current->comm,
 				  task_pid_nr(current));
 			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-EBUSY);
@@ -836,13 +836,15 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 		if (disk_super->label[0])
 			pr_info(
-	"BTRFS: device label %s devid %llu transid %llu %s scanned by %s (%d)\n",
+"BTRFS: device label %s devid %llu transid %llu %s (%d:%d) scanned by %s (%d)\n",
 				disk_super->label, devid, found_transid, path,
+				MAJOR(path_devt), MINOR(path_devt),
 				current->comm, task_pid_nr(current));
 		else
 			pr_info(
-	"BTRFS: device fsid %pU devid %llu transid %llu %s scanned by %s (%d)\n",
+"BTRFS: device fsid %pU devid %llu transid %llu %s (%d:%d) scanned by %s (%d)\n",
 				disk_super->fsid, devid, found_transid, path,
+				MAJOR(path_devt), MINOR(path_devt),
 				current->comm, task_pid_nr(current));
 
 	} else if (!device->name || strcmp(device->name->str, path)) {
@@ -1025,10 +1027,10 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
 		if (device->devid == BTRFS_DEV_REPLACE_DEVID)
 			continue;
 
-		if (device->bdev_handle) {
-			bdev_release(device->bdev_handle);
+		if (device->bdev_file) {
+			fput(device->bdev_file);
 			device->bdev = NULL;
-			device->bdev_handle = NULL;
+			device->bdev_file = NULL;
 			fs_devices->open_devices--;
 		}
 		if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
@@ -1073,7 +1075,7 @@ static void btrfs_close_bdev(struct btrfs_device *device)
 		invalidate_bdev(device->bdev);
 	}
 
-	bdev_release(device->bdev_handle);
+	fput(device->bdev_file);
 }
 
 static void btrfs_close_one_device(struct btrfs_device *device)
@@ -1374,8 +1376,9 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
 	struct btrfs_super_block *disk_super;
 	bool new_device_added = false;
 	struct btrfs_device *device = NULL;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	u64 bytenr, bytenr_orig;
+	dev_t devt;
 	int ret;
 
 	lockdep_assert_held(&uuid_mutex);
@@ -1397,31 +1400,30 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
 	 * values temporarily, as the device paths of the fsid are the only
 	 * required information for assembling the volume.
 	 */
-	bdev_handle = bdev_open_by_path(path, flags, NULL, NULL);
-	if (IS_ERR(bdev_handle))
-		return ERR_CAST(bdev_handle);
+	bdev_file = bdev_file_open_by_path(path, flags, NULL, NULL);
+	if (IS_ERR(bdev_file))
+		return ERR_CAST(bdev_file);
 
 	bytenr_orig = btrfs_sb_offset(0);
-	ret = btrfs_sb_log_location_bdev(bdev_handle->bdev, 0, READ, &bytenr);
+	ret = btrfs_sb_log_location_bdev(file_bdev(bdev_file), 0, READ, &bytenr);
 	if (ret) {
 		device = ERR_PTR(ret);
 		goto error_bdev_put;
 	}
 
-	disk_super = btrfs_read_disk_super(bdev_handle->bdev, bytenr,
+	disk_super = btrfs_read_disk_super(file_bdev(bdev_file), bytenr,
 					   bytenr_orig);
 	if (IS_ERR(disk_super)) {
 		device = ERR_CAST(disk_super);
 		goto error_bdev_put;
 	}
 
-	if (btrfs_skip_registration(disk_super, path, bdev_handle->bdev->bd_dev,
-				    mount_arg_dev)) {
+	devt = file_bdev(bdev_file)->bd_dev;
+	if (btrfs_skip_registration(disk_super, path, devt, mount_arg_dev)) {
 		pr_debug("BTRFS: skip registering single non-seed device %s (%d:%d)\n",
-			  path, MAJOR(bdev_handle->bdev->bd_dev),
-			  MINOR(bdev_handle->bdev->bd_dev));
+			  path, MAJOR(devt), MINOR(devt));
 
-		btrfs_free_stale_devices(bdev_handle->bdev->bd_dev, NULL);
+		btrfs_free_stale_devices(devt, NULL);
 
 		device = NULL;
 		goto free_disk_super;
@@ -1435,7 +1437,7 @@ free_disk_super:
 	btrfs_release_disk_super(disk_super);
 
 error_bdev_put:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 
 	return device;
 }
@@ -2086,11 +2088,10 @@ static void btrfs_scratch_superblock(struct btrfs_fs_info *fs_info,
 			copy_num, ret);
 }
 
-void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
-			       struct block_device *bdev,
-			       const char *device_path)
+void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, struct btrfs_device *device)
 {
 	int copy_num;
+	struct block_device *bdev = device->bdev;
 
 	if (!bdev)
 		return;
@@ -2106,12 +2107,12 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
 	btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
 
 	/* Update ctime/mtime for device path for libblkid */
-	update_dev_time(device_path);
+	update_dev_time(device->name->str);
 }
 
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		    struct btrfs_dev_lookup_args *args,
-		    struct bdev_handle **bdev_handle)
+		    struct file **bdev_file)
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
@@ -2220,7 +2221,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 
 	btrfs_assign_next_active_device(device, NULL);
 
-	if (device->bdev_handle) {
+	if (device->bdev_file) {
 		cur_devices->open_devices--;
 		/* remove sysfs entry */
 		btrfs_sysfs_remove_device(device);
@@ -2236,20 +2237,19 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 	 * free the device.
 	 *
 	 * We cannot call btrfs_close_bdev() here because we're holding the sb
-	 * write lock, and bdev_release() will pull in the ->open_mutex on
-	 * the block device and it's dependencies.  Instead just flush the
-	 * device and let the caller do the final bdev_release.
+	 * write lock, and fput() on the block device will pull in the
+	 * ->open_mutex on the block device and it's dependencies.  Instead
+	 *  just flush the device and let the caller do the final bdev_release.
 	 */
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
-		btrfs_scratch_superblocks(fs_info, device->bdev,
-					  device->name->str);
+		btrfs_scratch_superblocks(fs_info, device);
 		if (device->bdev) {
 			sync_blockdev(device->bdev);
 			invalidate_bdev(device->bdev);
 		}
 	}
 
-	*bdev_handle = device->bdev_handle;
+	*bdev_file = device->bdev_file;
 	synchronize_rcu();
 	btrfs_free_device(device);
 
@@ -2355,8 +2355,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev)
 
 	mutex_unlock(&fs_devices->device_list_mutex);
 
-	btrfs_scratch_superblocks(tgtdev->fs_info, tgtdev->bdev,
-				  tgtdev->name->str);
+	btrfs_scratch_superblocks(tgtdev->fs_info, tgtdev);
 
 	btrfs_close_bdev(tgtdev);
 	synchronize_rcu();
@@ -2386,7 +2385,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 				 const char *path)
 {
 	struct btrfs_super_block *disk_super;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int ret;
 
 	if (!path || !path[0])
@@ -2404,7 +2403,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 	}
 
 	ret = btrfs_get_bdev_and_sb(path, BLK_OPEN_READ, NULL, 0,
-				    &bdev_handle, &disk_super);
+				    &bdev_file, &disk_super);
 	if (ret) {
 		btrfs_put_dev_args_from_path(args);
 		return ret;
@@ -2417,7 +2416,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 	else
 		memcpy(args->fsid, disk_super->fsid, BTRFS_FSID_SIZE);
 	btrfs_release_disk_super(disk_super);
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	return 0;
 }
 
@@ -2637,7 +2636,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	struct btrfs_root *root = fs_info->dev_root;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct super_block *sb = fs_info->sb;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_fs_devices *seed_devices = NULL;
@@ -2650,12 +2649,12 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	if (sb_rdonly(sb) && !fs_devices->seeding)
 		return -EROFS;
 
-	bdev_handle = bdev_open_by_path(device_path, BLK_OPEN_WRITE,
+	bdev_file = bdev_file_open_by_path(device_path, BLK_OPEN_WRITE,
 					fs_info->bdev_holder, NULL);
-	if (IS_ERR(bdev_handle))
-		return PTR_ERR(bdev_handle);
+	if (IS_ERR(bdev_file))
+		return PTR_ERR(bdev_file);
 
-	if (!btrfs_check_device_zone_type(fs_info, bdev_handle->bdev)) {
+	if (!btrfs_check_device_zone_type(fs_info, file_bdev(bdev_file))) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -2667,11 +2666,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		locked = true;
 	}
 
-	sync_blockdev(bdev_handle->bdev);
+	sync_blockdev(file_bdev(bdev_file));
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) {
-		if (device->bdev == bdev_handle->bdev) {
+		if (device->bdev == file_bdev(bdev_file)) {
 			ret = -EEXIST;
 			rcu_read_unlock();
 			goto error;
@@ -2687,8 +2686,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	}
 
 	device->fs_info = fs_info;
-	device->bdev_handle = bdev_handle;
-	device->bdev = bdev_handle->bdev;
+	device->bdev_file = bdev_file;
+	device->bdev = file_bdev(bdev_file);
 	ret = lookup_bdev(device_path, &device->devt);
 	if (ret)
 		goto error_free_device;
@@ -2871,7 +2870,7 @@ error_free_zone:
 error_free_device:
 	btrfs_free_device(device);
 error:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	if (locked) {
 		mutex_unlock(&uuid_mutex);
 		up_write(&sb->s_umount);
@@ -3545,6 +3544,44 @@ static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+static void btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
+					   const struct btrfs_disk_balance_args *disk)
+{
+	memset(cpu, 0, sizeof(*cpu));
+
+	cpu->profiles = le64_to_cpu(disk->profiles);
+	cpu->usage = le64_to_cpu(disk->usage);
+	cpu->devid = le64_to_cpu(disk->devid);
+	cpu->pstart = le64_to_cpu(disk->pstart);
+	cpu->pend = le64_to_cpu(disk->pend);
+	cpu->vstart = le64_to_cpu(disk->vstart);
+	cpu->vend = le64_to_cpu(disk->vend);
+	cpu->target = le64_to_cpu(disk->target);
+	cpu->flags = le64_to_cpu(disk->flags);
+	cpu->limit = le64_to_cpu(disk->limit);
+	cpu->stripes_min = le32_to_cpu(disk->stripes_min);
+	cpu->stripes_max = le32_to_cpu(disk->stripes_max);
+}
+
+static void btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk,
+					   const struct btrfs_balance_args *cpu)
+{
+	memset(disk, 0, sizeof(*disk));
+
+	disk->profiles = cpu_to_le64(cpu->profiles);
+	disk->usage = cpu_to_le64(cpu->usage);
+	disk->devid = cpu_to_le64(cpu->devid);
+	disk->pstart = cpu_to_le64(cpu->pstart);
+	disk->pend = cpu_to_le64(cpu->pend);
+	disk->vstart = cpu_to_le64(cpu->vstart);
+	disk->vend = cpu_to_le64(cpu->vend);
+	disk->target = cpu_to_le64(cpu->target);
+	disk->flags = cpu_to_le64(cpu->flags);
+	disk->limit = cpu_to_le64(cpu->limit);
+	disk->stripes_min = cpu_to_le32(cpu->stripes_min);
+	disk->stripes_max = cpu_to_le32(cpu->stripes_max);
+}
+
 static int insert_balance_item(struct btrfs_fs_info *fs_info,
 			       struct btrfs_balance_control *bctl)
 {
@@ -3689,7 +3726,7 @@ static void reset_balance_state(struct btrfs_fs_info *fs_info)
 	struct btrfs_balance_control *bctl = fs_info->balance_ctl;
 	int ret;
 
-	BUG_ON(!fs_info->balance_ctl);
+	ASSERT(fs_info->balance_ctl);
 
 	spin_lock(&fs_info->balance_lock);
 	fs_info->balance_ctl = NULL;
@@ -6009,6 +6046,7 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
 			    struct btrfs_chunk_map *map, int first,
 			    int dev_replace_is_ongoing)
 {
+	const enum btrfs_read_policy policy = READ_ONCE(fs_info->fs_devices->read_policy);
 	int i;
 	int num_stripes;
 	int preferred_mirror;
@@ -6023,13 +6061,12 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
 	else
 		num_stripes = map->num_stripes;
 
-	switch (fs_info->fs_devices->read_policy) {
+	switch (policy) {
 	default:
 		/* Shouldn't happen, just warn and use pid instead of failing */
-		btrfs_warn_rl(fs_info,
-			      "unknown read_policy type %u, reset to pid",
-			      fs_info->fs_devices->read_policy);
-		fs_info->fs_devices->read_policy = BTRFS_READ_POLICY_PID;
+		btrfs_warn_rl(fs_info, "unknown read_policy type %u, reset to pid",
+			      policy);
+		WRITE_ONCE(fs_info->fs_devices->read_policy, BTRFS_READ_POLICY_PID);
 		fallthrough;
 	case BTRFS_READ_POLICY_PID:
 		preferred_mirror = first + (current->pid % num_stripes);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 53f87f398d..93854609a4 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -6,13 +6,28 @@
 #ifndef BTRFS_VOLUMES_H
 #define BTRFS_VOLUMES_H
 
+#include <linux/blk_types.h>
+#include <linux/sizes.h>
+#include <linux/atomic.h>
 #include <linux/sort.h>
-#include <linux/btrfs.h>
-#include "async-thread.h"
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/log2.h>
+#include <linux/kobject.h>
+#include <linux/refcount.h>
+#include <linux/completion.h>
+#include <linux/rbtree.h>
+#include <uapi/linux/btrfs.h>
 #include "messages.h"
-#include "tree-checker.h"
 #include "rcu-string.h"
 
+struct block_device;
+struct bdev_handle;
+struct btrfs_fs_info;
+struct btrfs_block_group;
+struct btrfs_trans_handle;
+struct btrfs_zoned_device_info;
+
 #define BTRFS_MAX_DATA_CHUNK_SIZE	(10ULL * SZ_1G)
 
 extern struct mutex uuid_mutex;
@@ -77,7 +92,7 @@ enum btrfs_raid_types {
 #define BTRFS_DEV_STATE_FLUSH_SENT	(4)
 #define BTRFS_DEV_STATE_NO_READA	(5)
 
-struct btrfs_zoned_device_info;
+struct btrfs_fs_devices;
 
 struct btrfs_device {
 	struct list_head dev_list; /* device_list_mutex */
@@ -90,7 +105,7 @@ struct btrfs_device {
 
 	u64 generation;
 
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bdev;
 
 	struct btrfs_zoned_device_info *zone_info;
@@ -276,6 +291,25 @@ enum btrfs_read_policy {
 	BTRFS_NR_READ_POLICY,
 };
 
+#ifdef CONFIG_BTRFS_DEBUG
+/*
+ * Checksum mode - offload it to workqueues or do it synchronously in
+ * btrfs_submit_chunk().
+ */
+enum btrfs_offload_csum_mode {
+	/*
+	 * Choose offloading checksum or do it synchronously automatically.
+	 * Do it synchronously if the checksum is fast, or offload to workqueues
+	 * otherwise.
+	 */
+	BTRFS_OFFLOAD_CSUM_AUTO,
+	/* Always offload checksum to workqueues. */
+	BTRFS_OFFLOAD_CSUM_FORCE_ON,
+	/* Never offload checksum to workqueues. */
+	BTRFS_OFFLOAD_CSUM_FORCE_OFF,
+};
+#endif
+
 struct btrfs_fs_devices {
 	u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
 
@@ -380,6 +414,11 @@ struct btrfs_fs_devices {
 
 	/* Policy used to read the mirrored stripes. */
 	enum btrfs_read_policy read_policy;
+
+#ifdef CONFIG_BTRFS_DEBUG
+	/* Checksum mode - offload it or do it synchronously. */
+	enum btrfs_offload_csum_mode offload_csum_mode;
+#endif
 };
 
 #define BTRFS_MAX_DEVS(info) ((BTRFS_MAX_ITEM_SIZE(info)	\
@@ -557,8 +596,6 @@ static inline void btrfs_free_chunk_map(struct btrfs_chunk_map *map)
 	}
 }
 
-struct btrfs_balance_args;
-struct btrfs_balance_progress;
 struct btrfs_balance_control {
 	struct btrfs_balance_args data;
 	struct btrfs_balance_args meta;
@@ -661,7 +698,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 void btrfs_put_dev_args_from_path(struct btrfs_dev_lookup_args *args);
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		    struct btrfs_dev_lookup_args *args,
-		    struct bdev_handle **bdev_handle);
+		    struct file **bdev_file);
 void __exit btrfs_cleanup_fs_uuids(void);
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,
@@ -780,9 +817,7 @@ void btrfs_commit_device_sizes(struct btrfs_transaction *trans);
 struct list_head * __attribute_const__ btrfs_get_fs_uuids(void);
 bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
 					struct btrfs_device *failing_dev);
-void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
-			       struct block_device *bdev,
-			       const char *device_path);
+void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, struct btrfs_device *device);
 
 enum btrfs_raid_types __attribute_const__ btrfs_bg_flags_to_raid_index(u64 flags);
 int btrfs_bg_type_to_factor(u64 flags);
diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h
index 118118ca3e..b9376ea258 100644
--- a/fs/btrfs/xattr.h
+++ b/fs/btrfs/xattr.h
@@ -6,7 +6,11 @@
 #ifndef BTRFS_XATTR_H
 #define BTRFS_XATTR_H
 
-#include <linux/xattr.h>
+struct dentry;
+struct inode;
+struct qstr;
+struct xattr_handler;
+struct btrfs_trans_handle;
 
 extern const struct xattr_handler * const btrfs_xattr_handlers[];
 
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 8da66ea699..e5b3f20038 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -398,7 +398,7 @@ int zlib_decompress(struct list_head *ws, const u8 *data_in,
 
 out:
 	if (unlikely(to_copy != destlen)) {
-		pr_warn_ratelimited("BTRFS: infalte failed, decompressed=%lu expected=%zu\n",
+		pr_warn_ratelimited("BTRFS: inflate failed, decompressed=%lu expected=%zu\n",
 					to_copy, destlen);
 		ret = -EIO;
 	} else {
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 9729fa29c7..459514da16 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -12,10 +12,8 @@
 #include "rcu-string.h"
 #include "disk-io.h"
 #include "block-group.h"
-#include "transaction.h"
 #include "dev-replace.h"
 #include "space-info.h"
-#include "super.h"
 #include "fs.h"
 #include "accessors.h"
 #include "bio.h"
@@ -824,11 +822,14 @@ static int sb_log_location(struct block_device *bdev, struct blk_zone *zones,
 			reset = &zones[1];
 
 		if (reset && reset->cond != BLK_ZONE_COND_EMPTY) {
+			unsigned int nofs_flags;
+
 			ASSERT(sb_zone_is_full(reset));
 
+			nofs_flags = memalloc_nofs_save();
 			ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
-					       reset->start, reset->len,
-					       GFP_NOFS);
+					       reset->start, reset->len);
+			memalloc_nofs_restore(nofs_flags);
 			if (ret)
 				return ret;
 
@@ -974,11 +975,14 @@ int btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
 			 * explicit ZONE_FINISH is not necessary.
 			 */
 			if (zone->wp != zone->start + zone->capacity) {
+				unsigned int nofs_flags;
 				int ret;
 
+				nofs_flags = memalloc_nofs_save();
 				ret = blkdev_zone_mgmt(device->bdev,
 						REQ_OP_ZONE_FINISH, zone->start,
-						zone->len, GFP_NOFS);
+						zone->len);
+				memalloc_nofs_restore(nofs_flags);
 				if (ret)
 					return ret;
 			}
@@ -996,11 +1000,13 @@ int btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
 
 int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
 {
+	unsigned int nofs_flags;
 	sector_t zone_sectors;
 	sector_t nr_sectors;
 	u8 zone_sectors_shift;
 	u32 sb_zone;
 	u32 nr_zones;
+	int ret;
 
 	zone_sectors = bdev_zone_sectors(bdev);
 	zone_sectors_shift = ilog2(zone_sectors);
@@ -1011,9 +1017,12 @@ int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
 	if (sb_zone + 1 >= nr_zones)
 		return -ENOENT;
 
-	return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
-				zone_start_sector(sb_zone, bdev),
-				zone_sectors * BTRFS_NR_SB_LOG_ZONES, GFP_NOFS);
+	nofs_flags = memalloc_nofs_save();
+	ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+			       zone_start_sector(sb_zone, bdev),
+			       zone_sectors * BTRFS_NR_SB_LOG_ZONES);
+	memalloc_nofs_restore(nofs_flags);
+	return ret;
 }
 
 /*
@@ -1124,12 +1133,14 @@ static void btrfs_dev_clear_active_zone(struct btrfs_device *device, u64 pos)
 int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
 			    u64 length, u64 *bytes)
 {
+	unsigned int nofs_flags;
 	int ret;
 
 	*bytes = 0;
+	nofs_flags = memalloc_nofs_save();
 	ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_RESET,
-			       physical >> SECTOR_SHIFT, length >> SECTOR_SHIFT,
-			       GFP_NOFS);
+			       physical >> SECTOR_SHIFT, length >> SECTOR_SHIFT);
+	memalloc_nofs_restore(nofs_flags);
 	if (ret)
 		return ret;
 
@@ -1279,7 +1290,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 				struct btrfs_chunk_map *map)
 {
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
-	struct btrfs_device *device = map->stripes[zone_idx].dev;
+	struct btrfs_device *device;
 	int dev_replace_is_ongoing = 0;
 	unsigned int nofs_flag;
 	struct blk_zone zone;
@@ -1287,7 +1298,11 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 
 	info->physical = map->stripes[zone_idx].physical;
 
+	down_read(&dev_replace->rwsem);
+	device = map->stripes[zone_idx].dev;
+
 	if (!device->bdev) {
+		up_read(&dev_replace->rwsem);
 		info->alloc_offset = WP_MISSING_DEV;
 		return 0;
 	}
@@ -1297,6 +1312,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 		__set_bit(zone_idx, active);
 
 	if (!btrfs_dev_is_sequential(device, info->physical)) {
+		up_read(&dev_replace->rwsem);
 		info->alloc_offset = WP_CONVENTIONAL;
 		return 0;
 	}
@@ -1304,11 +1320,9 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 	/* This zone will be used for allocation, so mark this zone non-empty. */
 	btrfs_dev_clear_zone_empty(device, info->physical);
 
-	down_read(&dev_replace->rwsem);
 	dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
 	if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL)
 		btrfs_dev_clear_zone_empty(dev_replace->tgtdev, info->physical);
-	up_read(&dev_replace->rwsem);
 
 	/*
 	 * The group is mapped to a sequential zone. Get the zone write pointer
@@ -1319,6 +1333,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 	ret = btrfs_get_dev_zone(device, info->physical, &zone);
 	memalloc_nofs_restore(nofs_flag);
 	if (ret) {
+		up_read(&dev_replace->rwsem);
 		if (ret != -EIO && ret != -EOPNOTSUPP)
 			return ret;
 		info->alloc_offset = WP_MISSING_DEV;
@@ -1330,6 +1345,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 		"zoned: unexpected conventional zone %llu on device %s (devid %llu)",
 			zone.start << SECTOR_SHIFT, rcu_str_deref(device->name),
 			device->devid);
+		up_read(&dev_replace->rwsem);
 		return -EIO;
 	}
 
@@ -1357,6 +1373,8 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 		break;
 	}
 
+	up_read(&dev_replace->rwsem);
+
 	return 0;
 }
 
@@ -2241,14 +2259,16 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 		struct btrfs_device *device = map->stripes[i].dev;
 		const u64 physical = map->stripes[i].physical;
 		struct btrfs_zoned_device_info *zinfo = device->zone_info;
+		unsigned int nofs_flags;
 
 		if (zinfo->max_active_zones == 0)
 			continue;
 
+		nofs_flags = memalloc_nofs_save();
 		ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH,
 				       physical >> SECTOR_SHIFT,
-				       zinfo->zone_size >> SECTOR_SHIFT,
-				       GFP_NOFS);
+				       zinfo->zone_size >> SECTOR_SHIFT);
+		memalloc_nofs_restore(nofs_flags);
 
 		if (ret) {
 			up_read(&dev_replace->rwsem);
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index f573bda496..77c4321e33 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -4,12 +4,27 @@
 #define BTRFS_ZONED_H
 
 #include <linux/types.h>
+#include <linux/atomic.h>
 #include <linux/blkdev.h>
+#include <linux/blkzoned.h>
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include "messages.h"
 #include "volumes.h"
 #include "disk-io.h"
 #include "block-group.h"
 #include "btrfs_inode.h"
+#include "fs.h"
+
+struct block_device;
+struct extent_buffer;
+struct btrfs_bio;
+struct btrfs_ordered_extent;
+struct btrfs_fs_info;
+struct btrfs_space_info;
+struct btrfs_eb_write_context;
+struct btrfs_fs_devices;
 
 #define BTRFS_DEFAULT_RECLAIM_THRESH           			(75)
 
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 0d66db8bc1..92b3744b81 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -18,8 +18,9 @@
 #include <linux/slab.h>
 #include <linux/zstd.h>
 #include "misc.h"
+#include "fs.h"
 #include "compression.h"
-#include "ctree.h"
+#include "super.h"
 
 #define ZSTD_BTRFS_MAX_WINDOWLOG 17
 #define ZSTD_BTRFS_MAX_INPUT (1 << ZSTD_BTRFS_MAX_WINDOWLOG)
@@ -618,80 +619,48 @@ done:
 }
 
 int zstd_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
+	const u32 sectorsize = fs_info->sectorsize;
 	zstd_dstream *stream;
 	int ret = 0;
-	size_t ret2;
-	unsigned long total_out = 0;
-	unsigned long pg_offset = 0;
+	unsigned long to_copy = 0;
 
 	stream = zstd_init_dstream(
 			ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
 	if (!stream) {
 		pr_warn("BTRFS: zstd_init_dstream failed\n");
-		ret = -EIO;
 		goto finish;
 	}
 
-	destlen = min_t(size_t, destlen, PAGE_SIZE);
-
 	workspace->in_buf.src = data_in;
 	workspace->in_buf.pos = 0;
 	workspace->in_buf.size = srclen;
 
 	workspace->out_buf.dst = workspace->buf;
 	workspace->out_buf.pos = 0;
-	workspace->out_buf.size = PAGE_SIZE;
-
-	ret2 = 1;
-	while (pg_offset < destlen
-	       && workspace->in_buf.pos < workspace->in_buf.size) {
-		unsigned long buf_start;
-		unsigned long buf_offset;
-		unsigned long bytes;
-
-		/* Check if the frame is over and we still need more input */
-		if (ret2 == 0) {
-			pr_debug("BTRFS: zstd_decompress_stream ended early\n");
-			ret = -EIO;
-			goto finish;
-		}
-		ret2 = zstd_decompress_stream(stream, &workspace->out_buf,
-				&workspace->in_buf);
-		if (zstd_is_error(ret2)) {
-			pr_debug("BTRFS: zstd_decompress_stream returned %d\n",
-					zstd_get_error_code(ret2));
-			ret = -EIO;
-			goto finish;
-		}
-
-		buf_start = total_out;
-		total_out += workspace->out_buf.pos;
-		workspace->out_buf.pos = 0;
-
-		if (total_out <= start_byte)
-			continue;
-
-		if (total_out > start_byte && buf_start < start_byte)
-			buf_offset = start_byte - buf_start;
-		else
-			buf_offset = 0;
-
-		bytes = min_t(unsigned long, destlen - pg_offset,
-				workspace->out_buf.size - buf_offset);
-
-		memcpy_to_page(dest_page, pg_offset,
-			       workspace->out_buf.dst + buf_offset, bytes);
-
-		pg_offset += bytes;
+	workspace->out_buf.size = sectorsize;
+
+	/*
+	 * Since both input and output buffers should not exceed one sector,
+	 * one call should end the decompression.
+	 */
+	ret = zstd_decompress_stream(stream, &workspace->out_buf, &workspace->in_buf);
+	if (zstd_is_error(ret)) {
+		pr_warn_ratelimited("BTRFS: zstd_decompress_stream return %d\n",
+				    zstd_get_error_code(ret));
+		goto finish;
 	}
-	ret = 0;
+	to_copy = workspace->out_buf.pos;
+	memcpy_to_page(dest_page, dest_pgoff, workspace->out_buf.dst, to_copy);
 finish:
-	if (pg_offset < destlen) {
-		memzero_page(dest_page, pg_offset, destlen - pg_offset);
+	/* Error or early end. */
+	if (unlikely(to_copy < destlen)) {
+		ret = -EIO;
+		memzero_page(dest_page, dest_pgoff + to_copy, destlen - to_copy);
 	}
 	return ret;
 }