Merge tag 'for-6.2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "This round there are a lot of cleanups and moved code so the diffstat
  looks huge, otherwise there are some nice performance improvements and
  an update to raid56 reliability.

  User visible features:

   - raid56 reliability vs performance trade off:
      - fix destructive RMW for raid5 data (raid6 still needs work): do
        full checksum verification for all data during RMW cycle, this
        should prevent rewriting potentially corrupted data without
        notice
      - stripes are cached in memory which should reduce the performance
        impact but still can hurt some workloads
      - checksums are verified after repair again
      - this is the last option without introducing additional features
        (write intent bitmap, journal, another tree), the extra checksum
        read/verification was supposed to be avoided by the original
        implementation exactly for performance reasons but that caused
        all the reliability problems

   - discard=async by default for devices that support it

   - implement emergency flush reserve to avoid almost all unnecessary
     transaction aborts due to ENOSPC in cases where there are too many
     delayed refs or delayed allocation

   - skip block group synchronization if there's no change in used
     bytes, can reduce transaction commit count for some workloads

  Performance improvements:

   - fiemap and lseek:
      - overall speedup due to skipping unnecessary or duplicate
        searches (-40% run time)
      - cache some data structures and sharedness of extents (-30% run
        time)

   - send:
      - faster backref resolution when finding clones
      - cached leaf to root mapping for faster backref walking
      - improved clone/sharing detection
      - overall run time improvements (-70%)

  Core:

   - module initialization converted to a table of function pointers run
     in a sequence

   - preparation for fscrypt, extend passing file names across calls,
     dir item can store encryption status

   - raid56 updates:
      - more accurate error tracking of sectors within stripe
      - simplify recovery path and remove dedicated endio worker kthread
      - simplify scrub call paths
      - refactoring to support the extra data checksum verification
        during RMW cycle

   - tree block parentness checks consolidated and done at metadata read
     time

   - improved error handling

   - cleanups:
      - move a lot of code for better synchronization between kernel and
        user space sources, split big files
      - enum cleanups
      - GFP flag cleanups
      - header file cleanups, prototypes, dependencies
      - redundant parameter cleanups
      - inline extent handling simplifications
      - inode parameter conversion
      - data structure cleanups, reductions, renames, merges"

* tag 'for-6.2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (249 commits)
  btrfs: print transaction aborted messages with an error level
  btrfs: sync some cleanups from progs into uapi/btrfs.h
  btrfs: do not BUG_ON() on ENOMEM when dropping extent items for a range
  btrfs: fix extent map use-after-free when handling missing device in read_one_chunk
  btrfs: remove outdated logic from overwrite_item() and add assertion
  btrfs: unify overwrite_item() and do_overwrite_item()
  btrfs: replace strncpy() with strscpy()
  btrfs: fix uninitialized variable in find_first_clear_extent_bit
  btrfs: fix uninitialized parent in insert_state
  btrfs: add might_sleep() annotations
  btrfs: add stack helpers for a few btrfs items
  btrfs: add nr_global_roots to the super block definition
  btrfs: remove BTRFS_LEAF_DATA_OFFSET
  btrfs: add helpers for manipulating leaf items and data
  btrfs: add eb to btrfs_node_key_ptr_offset
  btrfs: pass the extent buffer for the btrfs_item_nr helpers
  btrfs: move the csum helpers into ctree.h
  btrfs: move eb offset helpers into extent_io.h
  btrfs: move file_extent_item helpers into file-item.h
  btrfs: move leaf_data_end into ctree.c
  ...

fs/btrfs/Makefile

@@ -23,15 +23,15 @@ obj-$(CONFIG_BTRFS_FS) := btrfs.o
 
 btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   file-item.o inode-item.o disk-io.o \
-	   transaction.o inode.o file.o tree-defrag.o \
-	   extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
+	   transaction.o inode.o file.o defrag.o \
+	   extent_map.o sysfs.o accessors.o xattr.o ordered-data.o \
 	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
 	   export.o tree-log.o free-space-cache.o zlib.o lzo.o zstd.o \
 	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
 	   backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
 	   uuid-tree.o props.o free-space-tree.o tree-checker.o space-info.o \
 	   block-rsv.o delalloc-space.o block-group.o discard.o reflink.o \
-	   subpage.o tree-mod-log.o extent-io-tree.o
+	   subpage.o tree-mod-log.o extent-io-tree.o fs.o messages.o bio.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o

fs/btrfs/struct-funcs.c → fs/btrfs/accessors.c

@@ -4,8 +4,9 @@
  */
 
 #include <asm/unaligned.h>
-
+#include "messages.h"
 #include "ctree.h"
+#include "accessors.h"
 
 static bool check_setget_bounds(const struct extent_buffer *eb,
 				const void *ptr, unsigned off, int size)
@@ -23,6 +24,13 @@ static bool check_setget_bounds(const struct extent_buffer *eb,
 	return true;
 }
 
+void btrfs_init_map_token(struct btrfs_map_token *token, struct extent_buffer *eb)
+{
+	token->eb = eb;
+	token->kaddr = page_address(eb->pages[0]);
+	token->offset = 0;
+}
+
 /*
  * Macro templates that define helpers to read/write extent buffer data of a
  * given size, that are also used via ctree.h for access to item members by
@@ -160,7 +168,7 @@ DEFINE_BTRFS_SETGET_BITS(64)
 void btrfs_node_key(const struct extent_buffer *eb,
 		    struct btrfs_disk_key *disk_key, int nr)
 {
-	unsigned long ptr = btrfs_node_key_ptr_offset(nr);
+	unsigned long ptr = btrfs_node_key_ptr_offset(eb, nr);
 	read_eb_member(eb, (struct btrfs_key_ptr *)ptr,
 		       struct btrfs_key_ptr, key, disk_key);
 }

fs/btrfs/acl.c

@@ -11,10 +11,10 @@
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
 #include <linux/slab.h>
-
 #include "ctree.h"
 #include "btrfs_inode.h"
 #include "xattr.h"
+#include "acl.h"
 
 struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu)
 {

fs/btrfs/acl.h

+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_ACL_H
+#define BTRFS_ACL_H
+
+#ifdef CONFIG_BTRFS_FS_POSIX_ACL
+
+struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu);
+int btrfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
+		  struct posix_acl *acl, int type);
+int __btrfs_set_acl(struct btrfs_trans_handle *trans, struct inode *inode,
+		    struct posix_acl *acl, int type);
+
+#else
+
+#define btrfs_get_acl NULL
+#define btrfs_set_acl NULL
+static inline int __btrfs_set_acl(struct btrfs_trans_handle *trans,
+				  struct inode *inode, struct posix_acl *acl,
+				  int type)
+{
+	return -EOPNOTSUPP;
+}
+
+#endif
+
+#endif

fs/btrfs/backref.h

@@ -7,10 +7,128 @@
 #define BTRFS_BACKREF_H
 
 #include <linux/btrfs.h>
+#include "messages.h"
 #include "ulist.h"
 #include "disk-io.h"
 #include "extent_io.h"
 
+/*
+ * Used by implementations of iterate_extent_inodes_t (see definition below) to
+ * signal that backref iteration can stop immediately and no error happened.
+ * The value must be non-negative and must not be 0, 1 (which is a common return
+ * value from things like btrfs_search_slot() and used internally in the backref
+ * walking code) and different from BACKREF_FOUND_SHARED and
+ * BACKREF_FOUND_NOT_SHARED
+ */
+#define BTRFS_ITERATE_EXTENT_INODES_STOP 5
+
+/*
+ * Should return 0 if no errors happened and iteration of backrefs should
+ * continue. Can return BTRFS_ITERATE_EXTENT_INODES_STOP or any other non-zero
+ * value to immediately stop iteration and possibly signal an error back to
+ * the caller.
+ */
+typedef int (iterate_extent_inodes_t)(u64 inum, u64 offset, u64 num_bytes,
+				      u64 root, void *ctx);
+
+/*
+ * Context and arguments for backref walking functions. Some of the fields are
+ * to be filled by the caller of such functions while other are filled by the
+ * functions themselves, as described below.
+ */
+struct btrfs_backref_walk_ctx {
+	/*
+	 * The address of the extent for which we are doing backref walking.
+	 * Can be either a data extent or a metadata extent.
+	 *
+	 * Must always be set by the top level caller.
+	 */
+	u64 bytenr;
+	/*
+	 * Offset relative to the target extent. This is only used for data
+	 * extents, and it's meaningful because we can have file extent items
+	 * that point only to a section of a data extent ("bookend" extents),
+	 * and we want to filter out any that don't point to a section of the
+	 * data extent containing the given offset.
+	 *
+	 * Must always be set by the top level caller.
+	 */
+	u64 extent_item_pos;
+	/*
+	 * If true and bytenr corresponds to a data extent, then references from
+	 * all file extent items that point to the data extent are considered,
+	 * @extent_item_pos is ignored.
+	 */
+	bool ignore_extent_item_pos;
+	/* A valid transaction handle or NULL. */
+	struct btrfs_trans_handle *trans;
+	/*
+	 * The file system's info object, can not be NULL.
+	 *
+	 * Must always be set by the top level caller.
+	 */
+	struct btrfs_fs_info *fs_info;
+	/*
+	 * Time sequence acquired from btrfs_get_tree_mod_seq(), in case the
+	 * caller joined the tree mod log to get a consistent view of b+trees
+	 * while we do backref walking, or BTRFS_SEQ_LAST.
+	 * When using BTRFS_SEQ_LAST, delayed refs are not checked and it uses
+	 * commit roots when searching b+trees - this is a special case for
+	 * qgroups used during a transaction commit.
+	 */
+	u64 time_seq;
+	/*
+	 * Used to collect the bytenr of metadata extents that point to the
+	 * target extent.
+	 */
+	struct ulist *refs;
+	/*
+	 * List used to collect the IDs of the roots from which the target
+	 * extent is accessible. Can be NULL in case the caller does not care
+	 * about collecting root IDs.
+	 */
+	struct ulist *roots;
+	/*
+	 * Used by iterate_extent_inodes() and the main backref walk code
+	 * (find_parent_nodes()). Lookup and store functions for an optional
+	 * cache which maps the logical address (bytenr) of leaves to an array
+	 * of root IDs.
+	 */
+	bool (*cache_lookup)(u64 leaf_bytenr, void *user_ctx,
+			     const u64 **root_ids_ret, int *root_count_ret);
+	void (*cache_store)(u64 leaf_bytenr, const struct ulist *root_ids,
+			    void *user_ctx);
+	/*
+	 * If this is not NULL, then the backref walking code will call this
+	 * for each indirect data extent reference as soon as it finds one,
+	 * before collecting all the remaining backrefs and before resolving
+	 * indirect backrefs. This allows for the caller to terminate backref
+	 * walking as soon as it finds one backref that matches some specific
+	 * criteria. The @cache_lookup and @cache_store callbacks should not
+	 * be NULL in order to use this callback.
+	 */
+	iterate_extent_inodes_t *indirect_ref_iterator;
+	/*
+	 * If this is not NULL, then the backref walking code will call this for
+	 * each extent item it's meant to process before it actually starts
+	 * processing it. If this returns anything other than 0, then it stops
+	 * the backref walking code immediately.
+	 */
+	int (*check_extent_item)(u64 bytenr, const struct btrfs_extent_item *ei,
+				 const struct extent_buffer *leaf, void *user_ctx);
+	/*
+	 * If this is not NULL, then the backref walking code will call this for
+	 * each extent data ref it finds (BTRFS_EXTENT_DATA_REF_KEY keys) before
+	 * processing that data ref. If this callback return false, then it will
+	 * ignore this data ref and it will never resolve the indirect data ref,
+	 * saving time searching for leaves in a fs tree with file extent items
+	 * matching the data ref.
+	 */
+	bool (*skip_data_ref)(u64 root, u64 ino, u64 offset, void *user_ctx);
+	/* Context object to pass to the callbacks defined above. */
+	void *user_ctx;
+};
+
 struct inode_fs_paths {
 	struct btrfs_path		*btrfs_path;
 	struct btrfs_root		*fs_root;
@@ -23,17 +141,59 @@ struct btrfs_backref_shared_cache_entry {
 	bool is_shared;
 };
 
-struct btrfs_backref_shared_cache {
+#define BTRFS_BACKREF_CTX_PREV_EXTENTS_SIZE 8
+
+struct btrfs_backref_share_check_ctx {
+	/* Ulists used during backref walking. */
+	struct ulist refs;
+	/*
+	 * The current leaf the caller of btrfs_is_data_extent_shared() is at.
+	 * Typically the caller (at the moment only fiemap) tries to determine
+	 * the sharedness of data extents point by file extent items from entire
+	 * leaves.
+	 */
+	u64 curr_leaf_bytenr;
+	/*
+	 * The previous leaf the caller was at in the previous call to
+	 * btrfs_is_data_extent_shared(). This may be the same as the current
+	 * leaf. On the first call it must be 0.
+	 */
+	u64 prev_leaf_bytenr;
 	/*
 	 * A path from a root to a leaf that has a file extent item pointing to
 	 * a given data extent should never exceed the maximum b+tree height.
 	 */
-	struct btrfs_backref_shared_cache_entry entries[BTRFS_MAX_LEVEL];
-	bool use_cache;
+	struct btrfs_backref_shared_cache_entry path_cache_entries[BTRFS_MAX_LEVEL];
+	bool use_path_cache;
+	/*
+	 * Cache the sharedness result for the last few extents we have found,
+	 * but only for extents for which we have multiple file extent items
+	 * that point to them.
+	 * It's very common to have several file extent items that point to the
+	 * same extent (bytenr) but with different offsets and lengths. This
+	 * typically happens for COW writes, partial writes into prealloc
+	 * extents, NOCOW writes after snapshoting a root, hole punching or
+	 * reflinking within the same file (less common perhaps).
+	 * So keep a small cache with the lookup results for the extent pointed
+	 * by the last few file extent items. This cache is checked, with a
+	 * linear scan, whenever btrfs_is_data_extent_shared() is called, so
+	 * it must be small so that it does not negatively affect performance in
+	 * case we don't have multiple file extent items that point to the same
+	 * data extent.
+	 */
+	struct {
+		u64 bytenr;
+		bool is_shared;
+	} prev_extents_cache[BTRFS_BACKREF_CTX_PREV_EXTENTS_SIZE];
+	/*
+	 * The slot in the prev_extents_cache array that will be used for
+	 * storing the sharedness result of a new data extent.
+	 */
+	int prev_extents_cache_slot;
 };
 
-typedef int (iterate_extent_inodes_t)(u64 inum, u64 offset, u64 root,
-		void *ctx);
+struct btrfs_backref_share_check_ctx *btrfs_alloc_backref_share_check_ctx(void);
+void btrfs_free_backref_share_ctx(struct btrfs_backref_share_check_ctx *ctx);
 
 int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 			struct btrfs_path *path, struct btrfs_key *found_key,
@@ -43,11 +203,9 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 			    struct btrfs_key *key, struct btrfs_extent_item *ei,
 			    u32 item_size, u64 *out_root, u8 *out_level);
 
-int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
-				u64 extent_item_objectid,
-				u64 extent_offset, int search_commit_root,
-				iterate_extent_inodes_t *iterate, void *ctx,
-				bool ignore_offset);
+int iterate_extent_inodes(struct btrfs_backref_walk_ctx *ctx,
+			  bool search_commit_root,
+			  iterate_extent_inodes_t *iterate, void *user_ctx);
 
 int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
 				struct btrfs_path *path, void *ctx,
@@ -55,13 +213,8 @@ int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
 
 int paths_from_inode(u64 inum, struct inode_fs_paths *ipath);
 
-int btrfs_find_all_leafs(struct btrfs_trans_handle *trans,
-			 struct btrfs_fs_info *fs_info, u64 bytenr,
-			 u64 time_seq, struct ulist **leafs,
-			 const u64 *extent_item_pos, bool ignore_offset);
-int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
-			 struct btrfs_fs_info *fs_info, u64 bytenr,
-			 u64 time_seq, struct ulist **roots,
+int btrfs_find_all_leafs(struct btrfs_backref_walk_ctx *ctx);
+int btrfs_find_all_roots(struct btrfs_backref_walk_ctx *ctx,
 			 bool skip_commit_root_sem);
 char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 			u32 name_len, unsigned long name_off,
@@ -77,10 +230,9 @@ int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid,
 			  u64 start_off, struct btrfs_path *path,
 			  struct btrfs_inode_extref **ret_extref,
 			  u64 *found_off);
-int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr,
+int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr,
 				u64 extent_gen,
-				struct ulist *roots, struct ulist *tmp,
-				struct btrfs_backref_shared_cache *cache);
+				struct btrfs_backref_share_check_ctx *ctx);
 
 int __init btrfs_prelim_ref_init(void);
 void __cold btrfs_prelim_ref_exit(void);
@@ -111,8 +263,7 @@ struct btrfs_backref_iter {
 	u32 end_ptr;
 };
 
-struct btrfs_backref_iter *btrfs_backref_iter_alloc(
-		struct btrfs_fs_info *fs_info, gfp_t gfp_flag);
+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)
 {

fs/btrfs/bio.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2007 Oracle.  All rights reserved.
+ * Copyright (C) 2022 Christoph Hellwig.
+ */
+
+#ifndef BTRFS_BIO_H
+#define BTRFS_BIO_H
+
+#include <linux/bio.h>
+#include <linux/workqueue.h>
+#include "tree-checker.h"
+
+struct btrfs_bio;
+struct btrfs_fs_info;
+
+#define BTRFS_BIO_INLINE_CSUM_SIZE	64
+
+/*
+ * Maximum number of sectors for a single bio to limit the size of the
+ * checksum array.  This matches the number of bio_vecs per bio and thus the
+ * I/O size for buffered I/O.
+ */
+#define BTRFS_MAX_BIO_SECTORS		(256)
+
+typedef void (*btrfs_bio_end_io_t)(struct btrfs_bio *bbio);
+
+/*
+ * Additional info to pass along bio.
+ *
+ * Mostly for btrfs specific features like csum and mirror_num.
+ */
+struct btrfs_bio {
+	unsigned int mirror_num:7;
+
+	/*
+	 * Extra indicator for metadata bios.
+	 * For some btrfs bios they use pages without a mapping, thus
+	 * we can not rely on page->mapping->host to determine if
+	 * it's a metadata bio.
+	 */
+	unsigned int is_metadata:1;
+	struct bvec_iter iter;
+
+	/* for direct I/O */
+	u64 file_offset;
+
+	/* @device is for stripe IO submission. */
+	struct btrfs_device *device;
+	union {
+		/* For data checksum verification. */
+		struct {
+			u8 *csum;
+			u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
+		};
+
+		/* For metadata parentness verification. */
+		struct btrfs_tree_parent_check parent_check;
+	};
+
+	/* End I/O information supplied to btrfs_bio_alloc */
+	btrfs_bio_end_io_t end_io;
+	void *private;
+
+	/* For read end I/O handling */
+	struct work_struct end_io_work;
+
+	/*
+	 * This member must come last, bio_alloc_bioset will allocate enough
+	 * bytes for entire btrfs_bio but relies on bio being last.
+	 */
+	struct bio bio;
+};
+
+static inline struct btrfs_bio *btrfs_bio(struct bio *bio)
+{
+	return container_of(bio, struct btrfs_bio, bio);
+}
+
+int __init btrfs_bioset_init(void);
+void __cold btrfs_bioset_exit(void);
+
+struct bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
+			    btrfs_bio_end_io_t end_io, void *private);
+struct bio *btrfs_bio_clone_partial(struct bio *orig, u64 offset, u64 size,
+				    btrfs_bio_end_io_t end_io, void *private);
+
+
+static inline void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
+{
+	bbio->bio.bi_status = status;
+	bbio->end_io(bbio);
+}
+
+static inline void btrfs_bio_free_csum(struct btrfs_bio *bbio)
+{
+	if (bbio->is_metadata)
+		return;
+	if (bbio->csum != bbio->csum_inline) {
+		kfree(bbio->csum);
+		bbio->csum = NULL;
+	}
+}
+
+/*
+ * Iterate through a btrfs_bio (@bbio) on a per-sector basis.
+ *
+ * bvl        - struct bio_vec
+ * bbio       - struct btrfs_bio
+ * iters      - struct bvec_iter
+ * bio_offset - unsigned int
+ */
+#define btrfs_bio_for_each_sector(fs_info, bvl, bbio, iter, bio_offset)	\
+	for ((iter) = (bbio)->iter, (bio_offset) = 0;			\
+	     (iter).bi_size &&					\
+	     (((bvl) = bio_iter_iovec((&(bbio)->bio), (iter))), 1);	\
+	     (bio_offset) += fs_info->sectorsize,			\
+	     bio_advance_iter_single(&(bbio)->bio, &(iter),		\
+	     (fs_info)->sectorsize))
+
+void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
+		      int mirror_num);
+int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
+			    u64 length, u64 logical, struct page *page,
+			    unsigned int pg_offset, int mirror_num);
+
+#endif

fs/btrfs/block-group.c

@@ -17,6 +17,21 @@
 #include "discard.h"
 #include "raid56.h"
 #include "zoned.h"
+#include "fs.h"
+#include "accessors.h"
+#include "extent-tree.h"
+
+#ifdef CONFIG_BTRFS_DEBUG
+int btrfs_should_fragment_free_space(struct btrfs_block_group *block_group)
+{
+	struct btrfs_fs_info *fs_info = block_group->fs_info;
+
+	return (btrfs_test_opt(fs_info, FRAGMENT_METADATA) &&
+		block_group->flags & BTRFS_BLOCK_GROUP_METADATA) ||
+	       (btrfs_test_opt(fs_info, FRAGMENT_DATA) &&
+		block_group->flags &  BTRFS_BLOCK_GROUP_DATA);
+}
+#endif
 
 /*
  * Return target flags in extended format or 0 if restripe for this chunk_type
@@ -284,7 +299,7 @@ struct btrfs_block_group *btrfs_next_block_group(
 	return cache;
 }
 
-/**
+/*
  * Check if we can do a NOCOW write for a given extent.
  *
  * @fs_info:       The filesystem information object.
@@ -325,11 +340,9 @@ struct btrfs_block_group *btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info,
 	return bg;
 }
 
-/**
+/*
  * Decrement the number of NOCOW writers in a block group.
  *
- * @bg:       The block group.
- *
  * This is meant to be called after a previous call to btrfs_inc_nocow_writers(),
  * and on the block group returned by that call. Typically this is called after
  * creating an ordered extent for a NOCOW write, to prevent races with scrub and
@@ -1527,6 +1540,30 @@ static inline bool btrfs_should_reclaim(struct btrfs_fs_info *fs_info)
 	return true;
 }
 
+static bool should_reclaim_block_group(struct btrfs_block_group *bg, u64 bytes_freed)
+{
+	const struct btrfs_space_info *space_info = bg->space_info;
+	const int reclaim_thresh = READ_ONCE(space_info->bg_reclaim_threshold);
+	const u64 new_val = bg->used;
+	const u64 old_val = new_val + bytes_freed;
+	u64 thresh;
+
+	if (reclaim_thresh == 0)
+		return false;
+
+	thresh = mult_perc(bg->length, reclaim_thresh);
+
+	/*
+	 * If we were below the threshold before don't reclaim, we are likely a
+	 * brand new block group and we don't want to relocate new block groups.
+	 */
+	if (old_val < thresh)
+		return false;
+	if (new_val >= thresh)
+		return false;
+	return true;
+}
+
 void btrfs_reclaim_bgs_work(struct work_struct *work)
 {
 	struct btrfs_fs_info *fs_info =
@@ -1594,6 +1631,40 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 			up_write(&space_info->groups_sem);
 			goto next;
 		}
+		if (bg->used == 0) {
+			/*
+			 * It is possible that we trigger relocation on a block
+			 * group as its extents are deleted and it first goes
+			 * below the threshold, then shortly after goes empty.
+			 *
+			 * In this case, relocating it does delete it, but has
+			 * some overhead in relocation specific metadata, looking
+			 * for the non-existent extents and running some extra
+			 * transactions, which we can avoid by using one of the
+			 * other mechanisms for dealing with empty block groups.
+			 */
+			if (!btrfs_test_opt(fs_info, DISCARD_ASYNC))
+				btrfs_mark_bg_unused(bg);
+			spin_unlock(&bg->lock);
+			up_write(&space_info->groups_sem);
+			goto next;
+
+		}
+		/*
+		 * The block group might no longer meet the reclaim condition by
+		 * the time we get around to reclaiming it, so to avoid
+		 * reclaiming overly full block_groups, skip reclaiming them.
+		 *
+		 * Since the decision making process also depends on the amount
+		 * being freed, pass in a fake giant value to skip that extra
+		 * check, which is more meaningful when adding to the list in
+		 * the first place.
+		 */
+		if (!should_reclaim_block_group(bg, bg->length)) {
+			spin_unlock(&bg->lock);
+			up_write(&space_info->groups_sem);
+			goto next;
+		}
 		spin_unlock(&bg->lock);
 
 		/* Get out fast, in case we're unmounting the filesystem */
@@ -1740,8 +1811,8 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 	write_sequnlock(&fs_info->profiles_lock);
 }
 
-/**
- * Map a physical disk address to a list of logical addresses
+/*
+ * Map a physical disk address to a list of logical addresses.
  *
  * @fs_info:       the filesystem
  * @chunk_start:   logical address of block group
@@ -2001,6 +2072,7 @@ static int read_one_block_group(struct btrfs_fs_info *info,
 
 	cache->length = key->offset;
 	cache->used = btrfs_stack_block_group_used(bgi);
+	cache->commit_used = cache->used;
 	cache->flags = btrfs_stack_block_group_flags(bgi);
 	cache->global_root_id = btrfs_stack_block_group_chunk_objectid(bgi);
 
@@ -2481,7 +2553,7 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran
 	cache->global_root_id = calculate_global_root_id(fs_info, cache->start);
 
 	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
-		cache->needs_free_space = 1;
+		set_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &cache->runtime_flags);
 
 	ret = btrfs_load_block_group_zone_info(cache, true);
 	if (ret) {
@@ -2692,6 +2764,25 @@ static int update_block_group_item(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 	struct btrfs_block_group_item bgi;
 	struct btrfs_key key;
+	u64 old_commit_used;
+	u64 used;
+
+	/*
+	 * Block group items update can be triggered out of commit transaction
+	 * critical section, thus we need a consistent view of used bytes.
+	 * We cannot use cache->used directly outside of the spin lock, as it
+	 * may be changed.
+	 */
+	spin_lock(&cache->lock);
+	old_commit_used = cache->commit_used;
+	used = cache->used;
+	/* No change in used bytes, can safely skip it. */
+	if (cache->commit_used == used) {
+		spin_unlock(&cache->lock);
+		return 0;
+	}
+	cache->commit_used = used;
+	spin_unlock(&cache->lock);
 
 	key.objectid = cache->start;
 	key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
@@ -2706,7 +2797,7 @@ static int update_block_group_item(struct btrfs_trans_handle *trans,
 
 	leaf = path->nodes[0];
 	bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
-	btrfs_set_stack_block_group_used(&bgi, cache->used);
+	btrfs_set_stack_block_group_used(&bgi, used);
 	btrfs_set_stack_block_group_chunk_objectid(&bgi,
 						   cache->global_root_id);
 	btrfs_set_stack_block_group_flags(&bgi, cache->flags);
@@ -2714,6 +2805,12 @@ static int update_block_group_item(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 fail:
 	btrfs_release_path(path);
+	/* We didn't update the block group item, need to revert @commit_used. */
+	if (ret < 0) {
+		spin_lock(&cache->lock);
+		cache->commit_used = old_commit_used;
+		spin_unlock(&cache->lock);
+	}
 	return ret;
 
 }
@@ -3211,31 +3308,6 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
 	return ret;
 }
 
-static inline bool should_reclaim_block_group(struct btrfs_block_group *bg,
-					      u64 bytes_freed)
-{
-	const struct btrfs_space_info *space_info = bg->space_info;
-	const int reclaim_thresh = READ_ONCE(space_info->bg_reclaim_threshold);
-	const u64 new_val = bg->used;
-	const u64 old_val = new_val + bytes_freed;
-	u64 thresh;
-
-	if (reclaim_thresh == 0)
-		return false;
-
-	thresh = div_factor_fine(bg->length, reclaim_thresh);
-
-	/*
-	 * If we were below the threshold before don't reclaim, we are likely a
-	 * brand new block group and we don't want to relocate new block groups.
-	 */
-	if (old_val < thresh)
-		return false;
-	if (new_val >= thresh)
-		return false;
-	return true;
-}
-
 int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 			     u64 bytenr, u64 num_bytes, bool alloc)
 {
@@ -3347,8 +3419,9 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-/**
- * btrfs_add_reserved_bytes - update the block_group and space info counters
+/*
+ * Update the block_group and space info counters.
+ *
  * @cache:	The cache we are manipulating
  * @ram_bytes:  The number of bytes of file content, and will be same to
  *              @num_bytes except for the compress path.
@@ -3391,8 +3464,9 @@ int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
 	return ret;
 }
 
-/**
- * btrfs_free_reserved_bytes - update the block_group and space info counters
+/*
+ * Update the block_group and space info counters.
+ *
  * @cache:      The cache we are manipulating
  * @num_bytes:  The number of bytes in question
  * @delalloc:   The blocks are allocated for the delalloc write
@@ -3449,13 +3523,13 @@ static int should_alloc_chunk(struct btrfs_fs_info *fs_info,
 	 */
 	if (force == CHUNK_ALLOC_LIMITED) {
 		thresh = btrfs_super_total_bytes(fs_info->super_copy);
-		thresh = max_t(u64, SZ_64M, div_factor_fine(thresh, 1));
+		thresh = max_t(u64, SZ_64M, mult_perc(thresh, 1));
 
 		if (sinfo->total_bytes - bytes_used < thresh)
 			return 1;
 	}
 
-	if (bytes_used + SZ_2M < div_factor(sinfo->total_bytes, 8))
+	if (bytes_used + SZ_2M < mult_perc(sinfo->total_bytes, 80))
 		return 0;
 	return 1;
 }

fs/btrfs/block-group.h

@@ -55,6 +55,10 @@ enum btrfs_block_group_flags {
 	BLOCK_GROUP_FLAG_CHUNK_ITEM_INSERTED,
 	BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE,
 	BLOCK_GROUP_FLAG_ZONED_DATA_RELOC,
+	/* Does the block group need to be added to the free space tree? */
+	BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE,
+	/* Indicate that the block group is placed on a sequential zone */
+	BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE,
 };
 
 enum btrfs_caching_type {
@@ -99,6 +103,12 @@ struct btrfs_block_group {
 	u64 cache_generation;
 	u64 global_root_id;
 
+	/*
+	 * The last committed used bytes of this block group, if the above @used
+	 * is still the same as @commit_used, we don't need to update block
+	 * group item of this block group.
+	 */
+	u64 commit_used;
 	/*
 	 * If the free space extent count exceeds this number, convert the block
 	 * group to bitmaps.
@@ -202,15 +212,6 @@ struct btrfs_block_group {
 	/* Lock for free space tree operations. */
 	struct mutex free_space_lock;
 
-	/*
-	 * Does the block group need to be added to the free space tree?
-	 * Protected by free_space_lock.
-	 */
-	int needs_free_space;
-
-	/* Flag indicating this block group is placed on a sequential zone */
-	bool seq_zone;
-
 	/*
 	 * Number of extents in this block group used for swap files.
 	 * All accesses protected by the spinlock 'lock'.
@@ -251,16 +252,7 @@ static inline bool btrfs_is_block_group_data_only(
 }
 
 #ifdef CONFIG_BTRFS_DEBUG
-static inline int btrfs_should_fragment_free_space(
-		struct btrfs_block_group *block_group)
-{
-	struct btrfs_fs_info *fs_info = block_group->fs_info;
-
-	return (btrfs_test_opt(fs_info, FRAGMENT_METADATA) &&
-		block_group->flags & BTRFS_BLOCK_GROUP_METADATA) ||
-	       (btrfs_test_opt(fs_info, FRAGMENT_DATA) &&
-		block_group->flags &  BTRFS_BLOCK_GROUP_DATA);
-}
+int btrfs_should_fragment_free_space(struct btrfs_block_group *block_group);
 #endif
 
 struct btrfs_block_group *btrfs_lookup_first_block_group(

fs/btrfs/block-rsv.c

@@ -7,6 +7,8 @@
 #include "transaction.h"
 #include "block-group.h"
 #include "disk-io.h"
+#include "fs.h"
+#include "accessors.h"
 
 /*
  * HOW DO BLOCK RESERVES WORK
@@ -225,7 +227,7 @@ int btrfs_block_rsv_add(struct btrfs_fs_info *fs_info,
 	return ret;
 }
 
-int btrfs_block_rsv_check(struct btrfs_block_rsv *block_rsv, int min_factor)
+int btrfs_block_rsv_check(struct btrfs_block_rsv *block_rsv, int min_percent)
 {
 	u64 num_bytes = 0;
 	int ret = -ENOSPC;
@@ -234,7 +236,7 @@ int btrfs_block_rsv_check(struct btrfs_block_rsv *block_rsv, int min_factor)
 		return 0;
 
 	spin_lock(&block_rsv->lock);
-	num_bytes = div_factor(block_rsv->size, min_factor);
+	num_bytes = mult_perc(block_rsv->size, min_percent);
 	if (block_rsv->reserved >= num_bytes)
 		ret = 0;
 	spin_unlock(&block_rsv->lock);
@@ -323,31 +325,6 @@ void btrfs_block_rsv_add_bytes(struct btrfs_block_rsv *block_rsv,
 	spin_unlock(&block_rsv->lock);
 }
 
-int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
-			     struct btrfs_block_rsv *dest, u64 num_bytes,
-			     int min_factor)
-{
-	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
-	u64 min_bytes;
-
-	if (global_rsv->space_info != dest->space_info)
-		return -ENOSPC;
-
-	spin_lock(&global_rsv->lock);
-	min_bytes = div_factor(global_rsv->size, min_factor);
-	if (global_rsv->reserved < min_bytes + num_bytes) {
-		spin_unlock(&global_rsv->lock);
-		return -ENOSPC;
-	}
-	global_rsv->reserved -= num_bytes;
-	if (global_rsv->reserved < global_rsv->size)
-		global_rsv->full = false;
-	spin_unlock(&global_rsv->lock);
-
-	btrfs_block_rsv_add_bytes(dest, num_bytes, true);
-	return 0;
-}
-
 void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
@@ -552,5 +529,17 @@ struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans,
 		if (!ret)
 			return global_rsv;
 	}
+
+	/*
+	 * All hope is lost, but of course our reservations are overly
+	 * pessimistic, so instead of possibly having an ENOSPC abort here, try
+	 * one last time to force a reservation if there's enough actual space
+	 * on disk to make the reservation.
+	 */
+	ret = btrfs_reserve_metadata_bytes(fs_info, block_rsv, blocksize,
+					   BTRFS_RESERVE_FLUSH_EMERGENCY);
+	if (!ret)
+		return block_rsv;
+
 	return ERR_PTR(ret);
 }

fs/btrfs/block-rsv.h

@@ -4,6 +4,7 @@
 #define BTRFS_BLOCK_RSV_H
 
 struct btrfs_trans_handle;
+struct btrfs_root;
 enum btrfs_reserve_flush_enum;
 
 /*
@@ -62,7 +63,7 @@ void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info,
 int btrfs_block_rsv_add(struct btrfs_fs_info *fs_info,
 			struct btrfs_block_rsv *block_rsv, u64 num_bytes,
 			enum btrfs_reserve_flush_enum flush);
-int btrfs_block_rsv_check(struct btrfs_block_rsv *block_rsv, int min_factor);
+int btrfs_block_rsv_check(struct btrfs_block_rsv *block_rsv, int min_percent);
 int btrfs_block_rsv_refill(struct btrfs_fs_info *fs_info,
 			   struct btrfs_block_rsv *block_rsv, u64 min_reserved,
 			   enum btrfs_reserve_flush_enum flush);
@@ -70,9 +71,6 @@ int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
 			    struct btrfs_block_rsv *dst_rsv, u64 num_bytes,
 			    bool update_size);
 int btrfs_block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv, u64 num_bytes);
-int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
-			     struct btrfs_block_rsv *dest, u64 num_bytes,
-			     int min_factor);
 void btrfs_block_rsv_add_bytes(struct btrfs_block_rsv *block_rsv,
 			       u64 num_bytes, bool update_size);
 u64 btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,

fs/btrfs/btrfs_inode.h

@@ -411,29 +411,142 @@ static inline void btrfs_inode_split_flags(u64 inode_item_flags,
 #define CSUM_FMT				"0x%*phN"
 #define CSUM_FMT_VALUE(size, bytes)		size, bytes
 
-static inline void btrfs_print_data_csum_error(struct btrfs_inode *inode,
-		u64 logical_start, u8 *csum, u8 *csum_expected, int mirror_num)
-{
-	struct btrfs_root *root = inode->root;
-	const u32 csum_size = root->fs_info->csum_size;
-
-	/* Output minus objectid, which is more meaningful */
-	if (root->root_key.objectid >= BTRFS_LAST_FREE_OBJECTID)
-		btrfs_warn_rl(root->fs_info,
-"csum failed root %lld ino %lld off %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d",
-			root->root_key.objectid, btrfs_ino(inode),
-			logical_start,
-			CSUM_FMT_VALUE(csum_size, csum),
-			CSUM_FMT_VALUE(csum_size, csum_expected),
-			mirror_num);
-	else
-		btrfs_warn_rl(root->fs_info,
-"csum failed root %llu ino %llu off %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d",
-			root->root_key.objectid, btrfs_ino(inode),
-			logical_start,
-			CSUM_FMT_VALUE(csum_size, csum),
-			CSUM_FMT_VALUE(csum_size, csum_expected),
-			mirror_num);
-}
+void btrfs_submit_data_write_bio(struct btrfs_inode *inode, struct bio *bio, int mirror_num);
+void btrfs_submit_data_read_bio(struct btrfs_inode *inode, struct bio *bio,
+			int mirror_num, enum btrfs_compression_type compress_type);
+void btrfs_submit_dio_repair_bio(struct btrfs_inode *inode, struct bio *bio, int mirror_num);
+blk_status_t btrfs_submit_bio_start(struct btrfs_inode *inode, struct bio *bio);
+blk_status_t btrfs_submit_bio_start_direct_io(struct btrfs_inode *inode,
+					      struct bio *bio,
+					      u64 dio_file_offset);
+int btrfs_check_sector_csum(struct btrfs_fs_info *fs_info, struct page *page,
+			    u32 pgoff, u8 *csum, const u8 * const csum_expected);
+int btrfs_check_data_csum(struct btrfs_inode *inode, struct btrfs_bio *bbio,
+			  u32 bio_offset, struct page *page, u32 pgoff);
+unsigned int btrfs_verify_data_csum(struct btrfs_bio *bbio,
+				    u32 bio_offset, struct page *page,
+				    u64 start, u64 end);
+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);
+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,
+		       struct btrfs_inode *dir, struct btrfs_inode *inode,
+		       const struct fscrypt_str *name);
+int btrfs_add_link(struct btrfs_trans_handle *trans,
+		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
+		   const struct fscrypt_str *name, int add_backref, u64 index);
+int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry);
+int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
+			 int front);
+
+int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context);
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr,
+			       bool in_reclaim_context);
+int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
+			      unsigned int extra_bits,
+			      struct extent_state **cached_state);
+
+struct btrfs_new_inode_args {
+	/* Input */
+	struct inode *dir;
+	struct dentry *dentry;
+	struct inode *inode;
+	bool orphan;
+	bool subvol;
+
+	/* Output from btrfs_new_inode_prepare(), input to btrfs_create_new_inode(). */
+	struct posix_acl *default_acl;
+	struct posix_acl *acl;
+	struct fscrypt_name fname;
+};
+
+int btrfs_new_inode_prepare(struct btrfs_new_inode_args *args,
+			    unsigned int *trans_num_items);
+int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
+			   struct btrfs_new_inode_args *args);
+void btrfs_new_inode_args_destroy(struct btrfs_new_inode_args *args);
+struct inode *btrfs_new_subvol_inode(struct user_namespace *mnt_userns,
+				     struct inode *dir);
+ void btrfs_set_delalloc_extent(struct btrfs_inode *inode, struct extent_state *state,
+			        u32 bits);
+void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
+				 struct extent_state *state, u32 bits);
+void btrfs_merge_delalloc_extent(struct btrfs_inode *inode, struct extent_state *new,
+				 struct extent_state *other);
+void btrfs_split_delalloc_extent(struct btrfs_inode *inode,
+				 struct extent_state *orig, u64 split);
+void btrfs_set_range_writeback(struct btrfs_inode *inode, u64 start, u64 end);
+vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf);
+void btrfs_evict_inode(struct inode *inode);
+struct inode *btrfs_alloc_inode(struct super_block *sb);
+void btrfs_destroy_inode(struct inode *inode);
+void btrfs_free_inode(struct inode *inode);
+int btrfs_drop_inode(struct inode *inode);
+int __init btrfs_init_cachep(void);
+void __cold btrfs_destroy_cachep(void);
+struct inode *btrfs_iget_path(struct super_block *s, 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 end);
+int btrfs_update_inode(struct btrfs_trans_handle *trans,
+		       struct btrfs_root *root, struct btrfs_inode *inode);
+int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root, struct btrfs_inode *inode);
+int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct btrfs_inode *inode);
+int btrfs_orphan_cleanup(struct btrfs_root *root);
+int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size);
+void btrfs_add_delayed_iput(struct btrfs_inode *inode);
+void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info);
+int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info);
+int btrfs_prealloc_file_range(struct inode *inode, int mode,
+			      u64 start, u64 num_bytes, u64 min_size,
+			      loff_t actual_len, u64 *alloc_hint);
+int btrfs_prealloc_file_range_trans(struct inode *inode,
+				    struct btrfs_trans_handle *trans, int mode,
+				    u64 start, u64 num_bytes, u64 min_size,
+				    loff_t actual_len, u64 *alloc_hint);
+int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page,
+			     u64 start, u64 end, int *page_started,
+			     unsigned long *nr_written, struct writeback_control *wbc);
+int btrfs_writepage_cow_fixup(struct page *page);
+void btrfs_writepage_endio_finish_ordered(struct btrfs_inode *inode,
+					  struct page *page, u64 start,
+					  u64 end, bool uptodate);
+int btrfs_encoded_io_compression_from_extent(struct btrfs_fs_info *fs_info,
+					     int compress_type);
+int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
+					  u64 file_offset, u64 disk_bytenr,
+					  u64 disk_io_size,
+					  struct page **pages);
+ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
+			   struct btrfs_ioctl_encoded_io_args *encoded);
+ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
+			       const struct btrfs_ioctl_encoded_io_args *encoded);
+
+ssize_t btrfs_dio_read(struct kiocb *iocb, struct iov_iter *iter,
+		       size_t done_before);
+struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter,
+				  size_t done_before);
+
+extern const struct dentry_operations btrfs_dentry_operations;
+
+/* Inode locking type flags, by default the exclusive lock is taken. */
+enum btrfs_ilock_type {
+	ENUM_BIT(BTRFS_ILOCK_SHARED),
+	ENUM_BIT(BTRFS_ILOCK_TRY),
+	ENUM_BIT(BTRFS_ILOCK_MMAP),
+};
+
+int btrfs_inode_lock(struct btrfs_inode *inode, unsigned int ilock_flags);
+void btrfs_inode_unlock(struct btrfs_inode *inode, unsigned int ilock_flags);
+void btrfs_update_inode_bytes(struct btrfs_inode *inode, const u64 add_bytes,
+			      const u64 del_bytes);
+void btrfs_assert_inode_range_clean(struct btrfs_inode *inode, u64 start, u64 end);
 
 #endif

fs/btrfs/check-integrity.c

@@ -82,6 +82,7 @@
 #include <linux/mm.h>
 #include <linux/string.h>
 #include <crypto/hash.h>
+#include "messages.h"
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -92,6 +93,7 @@
 #include "check-integrity.h"
 #include "rcu-string.h"
 #include "compression.h"
+#include "accessors.h"
 
 #define BTRFSIC_BLOCK_HASHTABLE_SIZE 0x10000
 #define BTRFSIC_BLOCK_LINK_HASHTABLE_SIZE 0x10000
@@ -755,7 +757,7 @@ static int btrfsic_process_superblock_dev_mirror(
 			btrfs_info_in_rcu(fs_info,
 			"new initial S-block (bdev %p, %s) @%llu (%pg/%llu/%d)",
 				     superblock_bdev,
-				     rcu_str_deref(device->name), dev_bytenr,
+				     btrfs_dev_name(device), dev_bytenr,
 				     dev_state->bdev, dev_bytenr,
 				     superblock_mirror_num);
 		list_add(&superblock_tmp->all_blocks_node,

fs/btrfs/compression.c

@@ -23,16 +23,19 @@
 #include <crypto/hash.h>
 #include "misc.h"
 #include "ctree.h"
+#include "fs.h"
 #include "disk-io.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
-#include "volumes.h"
+#include "bio.h"
 #include "ordered-data.h"
 #include "compression.h"
 #include "extent_io.h"
 #include "extent_map.h"
 #include "subpage.h"
 #include "zoned.h"
+#include "file-item.h"
+#include "super.h"
 
 static const char* const btrfs_compress_types[] = { "", "zlib", "lzo", "zstd" };
 
@@ -116,7 +119,7 @@ static int compression_decompress_bio(struct list_head *ws,
 }
 
 static int compression_decompress(int type, struct list_head *ws,
-               unsigned char *data_in, struct page *dest_page,
+               const u8 *data_in, struct page *dest_page,
                unsigned long start_byte, size_t srclen, size_t destlen)
 {
 	switch (type) {
@@ -183,7 +186,7 @@ static void end_compressed_bio_read(struct btrfs_bio *bbio)
 		u64 start = bbio->file_offset + offset;
 
 		if (!status &&
-		    (!csum || !btrfs_check_data_csum(inode, bbio, offset,
+		    (!csum || !btrfs_check_data_csum(bi, bbio, offset,
 						     bv.bv_page, bv.bv_offset))) {
 			btrfs_clean_io_failure(bi, start, bv.bv_page,
 					       bv.bv_offset);
@@ -191,9 +194,9 @@ static void end_compressed_bio_read(struct btrfs_bio *bbio)
 			int ret;
 
 			refcount_inc(&cb->pending_ios);
-			ret = btrfs_repair_one_sector(inode, bbio, offset,
+			ret = btrfs_repair_one_sector(BTRFS_I(inode), bbio, offset,
 						      bv.bv_page, bv.bv_offset,
-						      btrfs_submit_data_read_bio);
+						      true);
 			if (ret) {
 				refcount_dec(&cb->pending_ios);
 				status = errno_to_blk_status(ret);
@@ -1229,7 +1232,7 @@ static int btrfs_decompress_bio(struct compressed_bio *cb)
  * single page, and we want to read a single page out of it.
  * start_byte tells us the offset into the compressed data we're interested in
  */
-int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
+int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page,
 		     unsigned long start_byte, size_t srclen, size_t destlen)
 {
 	struct list_head *workspace;
@@ -1243,12 +1246,13 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 	return ret;
 }
 
-void __init btrfs_init_compress(void)
+int __init btrfs_init_compress(void)
 {
 	btrfs_init_workspace_manager(BTRFS_COMPRESS_NONE);
 	btrfs_init_workspace_manager(BTRFS_COMPRESS_ZLIB);
 	btrfs_init_workspace_manager(BTRFS_COMPRESS_LZO);
 	zstd_init_workspace_manager();
+	return 0;
 }
 
 void __cold btrfs_exit_compress(void)

fs/btrfs/compression.h

@@ -6,6 +6,7 @@
 #ifndef BTRFS_COMPRESSION_H
 #define BTRFS_COMPRESSION_H
 
+#include <linux/blk_types.h>
 #include <linux/sizes.h>
 
 struct btrfs_inode;
@@ -77,7 +78,7 @@ static inline unsigned int btrfs_compress_level(unsigned int type_level)
 	return ((type_level & 0xF0) >> 4);
 }
 
-void __init btrfs_init_compress(void);
+int __init btrfs_init_compress(void);
 void __cold btrfs_exit_compress(void);
 
 int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
@@ -85,7 +86,7 @@ int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
 			 unsigned long *out_pages,
 			 unsigned long *total_in,
 			 unsigned long *total_out);
-int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
+int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page,
 		     unsigned long start_byte, size_t srclen, size_t destlen);
 int btrfs_decompress_buf2page(const char *buf, u32 buf_len,
 			      struct compressed_bio *cb, u32 decompressed);
@@ -149,7 +150,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 		u64 start, struct page **pages, unsigned long *out_pages,
 		unsigned long *total_in, unsigned long *total_out);
 int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
-int zlib_decompress(struct list_head *ws, unsigned char *data_in,
+int zlib_decompress(struct list_head *ws, const u8 *data_in,
 		struct page *dest_page, unsigned long start_byte, size_t srclen,
 		size_t destlen);
 struct list_head *zlib_alloc_workspace(unsigned int level);
@@ -160,7 +161,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 		u64 start, struct page **pages, unsigned long *out_pages,
 		unsigned long *total_in, unsigned long *total_out);
 int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
-int lzo_decompress(struct list_head *ws, unsigned char *data_in,
+int lzo_decompress(struct list_head *ws, const u8 *data_in,
 		struct page *dest_page, unsigned long start_byte, size_t srclen,
 		size_t destlen);
 struct list_head *lzo_alloc_workspace(unsigned int level);
@@ -170,7 +171,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 		u64 start, struct page **pages, unsigned long *out_pages,
 		unsigned long *total_in, unsigned long *total_out);
 int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
-int zstd_decompress(struct list_head *ws, unsigned char *data_in,
+int zstd_decompress(struct list_head *ws, const u8 *data_in,
 		struct page *dest_page, unsigned long start_byte, size_t srclen,
 		size_t destlen);
 void zstd_init_workspace_manager(void);

fs/btrfs/defrag.h

+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_DEFRAG_H
+#define BTRFS_DEFRAG_H
+
+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);
+int __init btrfs_auto_defrag_init(void);
+void __cold btrfs_auto_defrag_exit(void);
+int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
+			   struct btrfs_inode *inode, u32 extent_thresh);
+int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info);
+void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info);
+int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, struct btrfs_root *root);
+
+static inline int btrfs_defrag_cancelled(struct btrfs_fs_info *fs_info)
+{
+	return signal_pending(current);
+}
+
+#endif

fs/btrfs/delalloc-space.c

 // SPDX-License-Identifier: GPL-2.0
 
+#include "messages.h"
 #include "ctree.h"
 #include "delalloc-space.h"
 #include "block-rsv.h"
@@ -8,6 +9,7 @@
 #include "transaction.h"
 #include "qgroup.h"
 #include "block-group.h"
+#include "fs.h"
 
 /*
  * HOW DOES THIS WORK
@@ -200,8 +202,8 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode,
 	btrfs_qgroup_free_data(inode, reserved, start, len);
 }
 
-/**
- * Release any excessive reservation
+/*
+ * Release any excessive reservations for an inode.
  *
  * @inode:       the inode we need to release from
  * @qgroup_free: free or convert qgroup meta. Unlike normal operation, qgroup
@@ -375,12 +377,12 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
 	return 0;
 }
 
-/**
- * Release a metadata reservation for an inode
+/*
+ * Release a metadata reservation for an inode.
  *
- * @inode: the inode to release the reservation for.
- * @num_bytes: the number of bytes we are releasing.
- * @qgroup_free: free qgroup reservation or convert it to per-trans reservation
+ * @inode:        the inode to release the reservation for.
+ * @num_bytes:    the number of bytes we are releasing.
+ * @qgroup_free:  free qgroup reservation or convert it to per-trans reservation
  *
  * This will release the metadata reservation for an inode.  This can be called
  * once we complete IO for a given set of bytes to release their metadata
@@ -403,10 +405,11 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 	btrfs_inode_rsv_release(inode, qgroup_free);
 }
 
-/**
- * btrfs_delalloc_release_extents - release our outstanding_extents
- * @inode: the inode to balance the reservation for.
- * @num_bytes: the number of bytes we originally reserved with
+/*
+ * Release our outstanding_extents for an inode.
+ *
+ * @inode:      the inode to balance the reservation for.
+ * @num_bytes:  the number of bytes we originally reserved with
  *
  * When we reserve space we increase outstanding_extents for the extents we may
  * add.  Once we've set the range as delalloc or created our ordered extents we
@@ -431,30 +434,30 @@ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes)
 	btrfs_inode_rsv_release(inode, true);
 }
 
-/**
- * btrfs_delalloc_reserve_space - reserve data and metadata space for
- * delalloc
- * @inode: inode we're writing to
- * @start: start range we are writing to
- * @len: how long the range we are writing to
- * @reserved: mandatory parameter, record actually reserved qgroup ranges of
- * 	      current reservation.
+/*
+ * Reserve data and metadata space for delalloc
+ *
+ * @inode:     inode we're writing to
+ * @start:     start range we are writing to
+ * @len:       how long the range we are writing to
+ * @reserved:  mandatory parameter, record actually reserved qgroup ranges of
+ * 	       current reservation.
  *
  * This will do the following things
  *
- * - reserve space in data space info for num bytes
- *   and reserve precious corresponding qgroup space
+ * - reserve space in data space info for num bytes and reserve precious
+ *   corresponding qgroup space
  *   (Done in check_data_free_space)
  *
  * - reserve space for metadata space, based on the number of outstanding
- *   extents and how much csums will be needed
- *   also reserve metadata space in a per root over-reserve method.
+ *   extents and how much csums will be needed also reserve metadata space in a
+ *   per root over-reserve method.
  * - add to the inodes->delalloc_bytes
  * - add it to the fs_info's delalloc inodes list.
  *   (Above 3 all done in delalloc_reserve_metadata)
  *
  * Return 0 for success
- * Return <0 for error(-ENOSPC or -EQUOT)
+ * Return <0 for error(-ENOSPC or -EDQUOT)
  */
 int btrfs_delalloc_reserve_space(struct btrfs_inode *inode,
 			struct extent_changeset **reserved, u64 start, u64 len)
@@ -473,7 +476,7 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode,
 	return ret;
 }
 
-/**
+/*
  * Release data and metadata space for delalloc
  *
  * @inode:       inode we're releasing space for
@@ -482,10 +485,10 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode,
  * @len:         length of the space already reserved
  * @qgroup_free: should qgroup reserved-space also be freed
  *
- * This function will release the metadata space that was not used and will
- * decrement ->delalloc_bytes and remove it from the fs_info delalloc_inodes
- * list if there are no delalloc bytes left.
- * Also it will handle the qgroup reserved space.
+ * Release the metadata space that was not used and will decrement
+ * ->delalloc_bytes and remove it from the fs_info->delalloc_inodes list if
+ * there are no delalloc bytes left.  Also it will handle the qgroup reserved
+ * space.
  */
 void btrfs_delalloc_release_space(struct btrfs_inode *inode,
 				  struct extent_changeset *reserved,

fs/btrfs/delalloc-space.h

@@ -20,5 +20,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 				     bool qgroup_free);
 int btrfs_delalloc_reserve_space(struct btrfs_inode *inode,
 			struct extent_changeset **reserved, u64 start, u64 len);
+int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
+				    u64 disk_num_bytes, bool noflush);
+void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);
 
 #endif /* BTRFS_DELALLOC_SPACE_H */

fs/btrfs/delayed-inode.h

@@ -113,7 +113,7 @@ static inline void btrfs_init_delayed_root(
 int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 				   const char *name, int name_len,
 				   struct btrfs_inode *dir,
-				   struct btrfs_disk_key *disk_key, u8 type,
+				   struct btrfs_disk_key *disk_key, u8 flags,
 				   u64 index);
 
 int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,

fs/btrfs/dev-replace.h

@@ -25,5 +25,13 @@ int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
 bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev,
 				      struct btrfs_block_group *cache,
 				      u64 physical);
+void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info);
+void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount);
+
+static inline void btrfs_bio_counter_dec(struct btrfs_fs_info *fs_info)
+{
+	btrfs_bio_counter_sub(fs_info, 1);
+}
+
 
 #endif

fs/btrfs/export.h

@@ -19,8 +19,7 @@ struct btrfs_fid {
 } __attribute__ ((packed));
 
 struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
-				u64 root_objectid, u64 generation,
-				int check_generation);
+				u64 root_objectid, u64 generation);
 struct dentry *btrfs_get_parent(struct dentry *child);
 
 #endif

fs/btrfs/locking.c

@@ -12,6 +12,7 @@
 #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