Merge tag 'for-6.1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "There's a bunch of performance improvements, most notably the FIEMAP
  speedup, the new block group tree to speed up mount on large
  filesystems, more io_uring integration, some sysfs exports and the
  usual fixes and core updates.

  Summary:

  Performance:

   - outstanding FIEMAP speed improvement
      - algorithmic change how extents are enumerated leads to orders of
        magnitude speed boost (uncached and cached)
      - extent sharing check speedup (2.2x uncached, 3x cached)
      - add more cancellation points, allowing to interrupt seeking in
        files with large number of extents
      - more efficient hole and data seeking (4x uncached, 1.3x cached)
      - sample results:
	    256M, 32K extents:   4s ->  29ms  (~150x)
	    512M, 64K extents:  30s ->  59ms  (~550x)
	    1G,  128K extents: 225s -> 120ms (~1800x)

   - improved inode logging, especially for directories (on dbench
     workload throughput +25%, max latency -21%)

   - improved buffered IO, remove redundant extent state tracking,
     lowering memory consumption and avoiding rb tree traversal

   - add sysfs tunable to let qgroup temporarily skip exact accounting
     when deleting snapshot, leading to a speedup but requiring a rescan
     after that, will be used by snapper

   - support io_uring and buffered writes, until now it was just for
     direct IO, with the no-wait semantics implemented in the buffered
     write path it now works and leads to speed improvement in IOPS
     (2x), throughput (2.2x), latency (depends, 2x to 150x)

   - small performance improvements when dropping and searching for
     extent maps as well as when flushing delalloc in COW mode
     (throughput +5MB/s)

  User visible changes:

   - new incompatible feature block-group-tree adding a dedicated tree
     for tracking block groups, this allows a much faster load during
     mount and avoids seeking unlike when it's scattered in the extent
     tree items
      - this reduces mount time for many-terabyte sized filesystems
      - conversion tool will be provided so existing filesystem can also
        be updated in place
      - to reduce test matrix and feature combinations requires no-holes
        and free-space-tree (mkfs defaults since 5.15)

   - improved reporting of super block corruption detected by scrub

   - scrub also tries to repair super block and does not wait until next
     commit

   - discard stats and tunables are exported in sysfs
     (/sys/fs/btrfs/FSID/discard)

   - qgroup status is exported in sysfs
     (/sys/sys/fs/btrfs/FSID/qgroups/)

   - verify that super block was not modified when thawing filesystem

  Fixes:

   - FIEMAP fixes
      - fix extent sharing status, does not depend on the cached status
        where merged
      - flush delalloc so compressed extents are reported correctly

   - fix alignment of VMA for memory mapped files on THP

   - send: fix failures when processing inodes with no links (orphan
     files and directories)

   - fix race between quota enable and quota rescan ioctl

   - handle more corner cases for read-only compat feature verification

   - fix missed extent on fsync after dropping extent maps

  Core:

   - lockdep annotations to validate various transactions states and
     state transitions

   - preliminary support for fs-verity in send

   - more effective memory use in scrub for subpage where sector is
     smaller than page

   - block group caching progress logic has been removed, load is now
     synchronous

   - simplify end IO callbacks and bio handling, use chained bios
     instead of own tracking

   - add no-wait semantics to several functions (tree search, nocow,
     flushing, buffered write

   - cleanups and refactoring

  MM changes:

   - export balance_dirty_pages_ratelimited_flags"

* tag 'for-6.1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (177 commits)
  btrfs: set generation before calling btrfs_clean_tree_block in btrfs_init_new_buffer
  btrfs: drop extent map range more efficiently
  btrfs: avoid pointless extent map tree search when flushing delalloc
  btrfs: remove unnecessary next extent map search
  btrfs: remove unnecessary NULL pointer checks when searching extent maps
  btrfs: assert tree is locked when clearing extent map from logging
  btrfs: remove unnecessary extent map initializations
  btrfs: remove the refcount warning/check at free_extent_map()
  btrfs: add helper to replace extent map range with a new extent map
  btrfs: move open coded extent map tree deletion out of inode eviction
  btrfs: use cond_resched_rwlock_write() during inode eviction
  btrfs: use extent_map_end() at btrfs_drop_extent_map_range()
  btrfs: move btrfs_drop_extent_cache() to extent_map.c
  btrfs: fix missed extent on fsync after dropping extent maps
  btrfs: remove stale prototype of btrfs_write_inode
  btrfs: enable nowait async buffered writes
  btrfs: assert nowait mode is not used for some btree search functions
  btrfs: make btrfs_buffered_write nowait compatible
  btrfs: plumb NOWAIT through the write path
  btrfs: make lock_and_cleanup_extent_if_need nowait compatible
  ...

fs/btrfs/Makefile

@@ -31,7 +31,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.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
+	   subpage.o tree-mod-log.o extent-io-tree.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o

fs/btrfs/backref.c

@@ -1511,16 +1511,118 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-/**
- * Check if an extent is shared or not
+/*
+ * The caller has joined a transaction or is holding a read lock on the
+ * fs_info->commit_root_sem semaphore, so no need to worry about the root's last
+ * snapshot field changing while updating or checking the cache.
+ */
+static bool lookup_backref_shared_cache(struct btrfs_backref_shared_cache *cache,
+					struct btrfs_root *root,
+					u64 bytenr, int level, bool *is_shared)
+{
+	struct btrfs_backref_shared_cache_entry *entry;
+
+	if (WARN_ON_ONCE(level >= BTRFS_MAX_LEVEL))
+		return false;
+
+	/*
+	 * Level -1 is used for the data extent, which is not reliable to cache
+	 * because its reference count can increase or decrease without us
+	 * realizing. We cache results only for extent buffers that lead from
+	 * the root node down to the leaf with the file extent item.
+	 */
+	ASSERT(level >= 0);
+
+	entry = &cache->entries[level];
+
+	/* Unused cache entry or being used for some other extent buffer. */
+	if (entry->bytenr != bytenr)
+		return false;
+
+	/*
+	 * We cached a false result, but the last snapshot generation of the
+	 * root changed, so we now have a snapshot. Don't trust the result.
+	 */
+	if (!entry->is_shared &&
+	    entry->gen != btrfs_root_last_snapshot(&root->root_item))
+		return false;
+
+	/*
+	 * If we cached a true result and the last generation used for dropping
+	 * a root changed, we can not trust the result, because the dropped root
+	 * could be a snapshot sharing this extent buffer.
+	 */
+	if (entry->is_shared &&
+	    entry->gen != btrfs_get_last_root_drop_gen(root->fs_info))
+		return false;
+
+	*is_shared = entry->is_shared;
+
+	return true;
+}
+
+/*
+ * The caller has joined a transaction or is holding a read lock on the
+ * fs_info->commit_root_sem semaphore, so no need to worry about the root's last
+ * snapshot field changing while updating or checking the cache.
+ */
+static void store_backref_shared_cache(struct btrfs_backref_shared_cache *cache,
+				       struct btrfs_root *root,
+				       u64 bytenr, int level, bool is_shared)
+{
+	struct btrfs_backref_shared_cache_entry *entry;
+	u64 gen;
+
+	if (WARN_ON_ONCE(level >= BTRFS_MAX_LEVEL))
+		return;
+
+	/*
+	 * Level -1 is used for the data extent, which is not reliable to cache
+	 * because its reference count can increase or decrease without us
+	 * realizing. We cache results only for extent buffers that lead from
+	 * the root node down to the leaf with the file extent item.
+	 */
+	ASSERT(level >= 0);
+
+	if (is_shared)
+		gen = btrfs_get_last_root_drop_gen(root->fs_info);
+	else
+		gen = btrfs_root_last_snapshot(&root->root_item);
+
+	entry = &cache->entries[level];
+	entry->bytenr = bytenr;
+	entry->is_shared = is_shared;
+	entry->gen = gen;
+
+	/*
+	 * If we found an extent buffer is shared, set the cache result for all
+	 * extent buffers below it to true. As nodes in the path are COWed,
+	 * their sharedness is moved to their children, and if a leaf is COWed,
+	 * then the sharedness of a data extent becomes direct, the refcount of
+	 * data extent is increased in the extent item at the extent tree.
+	 */
+	if (is_shared) {
+		for (int i = 0; i < level; i++) {
+			entry = &cache->entries[i];
+			entry->is_shared = is_shared;
+			entry->gen = gen;
+		}
+	}
+}
+
+/*
+ * Check if a data extent is shared or not.
  *
- * @root:   root inode belongs to
- * @inum:   inode number of the inode whose extent we are checking
- * @bytenr: logical bytenr of the extent we are checking
- * @roots:  list of roots this extent is shared among
- * @tmp:    temporary list used for iteration
+ * @root:        The root the inode belongs to.
+ * @inum:        Number of the inode whose extent we are checking.
+ * @bytenr:      Logical bytenr of the extent we are checking.
+ * @extent_gen:  Generation of the extent (file extent item) or 0 if it is
+ *               not known.
+ * @roots:       List of roots this extent is shared among.
+ * @tmp:         Temporary list used for iteration.
+ * @cache:       A backref lookup result cache.
  *
- * btrfs_check_shared uses the backref walking code but will short
+ * btrfs_is_data_extent_shared uses the backref walking code but will short
  * circuit as soon as it finds a root or inode that doesn't match the
  * one passed in. This provides a significant performance benefit for
  * callers (such as fiemap) which want to know whether the extent is
@@ -1531,8 +1633,10 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
  *
  * Return: 0 if extent is not shared, 1 if it is shared, < 0 on error.
  */
-int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr,
-		struct ulist *roots, struct ulist *tmp)
+int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr,
+				u64 extent_gen,
+				struct ulist *roots, struct ulist *tmp,
+				struct btrfs_backref_shared_cache *cache)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_trans_handle *trans;
@@ -1545,6 +1649,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr,
 		.inum = inum,
 		.share_count = 0,
 	};
+	int level;
 
 	ulist_init(roots);
 	ulist_init(tmp);
@@ -1561,22 +1666,52 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr,
 		btrfs_get_tree_mod_seq(fs_info, &elem);
 	}
 
+	/* -1 means we are in the bytenr of the data extent. */
+	level = -1;
 	ULIST_ITER_INIT(&uiter);
 	while (1) {
+		bool is_shared;
+		bool cached;
+
 		ret = find_parent_nodes(trans, fs_info, bytenr, elem.seq, tmp,
 					roots, NULL, &shared, false);
 		if (ret == BACKREF_FOUND_SHARED) {
 			/* this is the only condition under which we return 1 */
 			ret = 1;
+			if (level >= 0)
+				store_backref_shared_cache(cache, root, bytenr,
+							   level, true);
 			break;
 		}
 		if (ret < 0 && ret != -ENOENT)
 			break;
 		ret = 0;
+		/*
+		 * If our data extent is not shared through reflinks and it was
+		 * created in a generation after the last one used to create a
+		 * snapshot of the inode's root, then it can not be shared
+		 * indirectly through subtrees, as that can only happen with
+		 * snapshots. In this case bail out, no need to check for the
+		 * sharedness of extent buffers.
+		 */
+		if (level == -1 &&
+		    extent_gen > btrfs_root_last_snapshot(&root->root_item))
+			break;
+
+		if (level >= 0)
+			store_backref_shared_cache(cache, root, bytenr,
+						   level, false);
 		node = ulist_next(tmp, &uiter);
 		if (!node)
 			break;
 		bytenr = node->val;
+		level++;
+		cached = lookup_backref_shared_cache(cache, root, bytenr, level,
+						     &is_shared);
+		if (cached) {
+			ret = (is_shared ? 1 : 0);
+			break;
+		}
 		shared.share_count = 0;
 		cond_resched();
 	}

fs/btrfs/backref.h

@@ -17,6 +17,20 @@ struct inode_fs_paths {
 	struct btrfs_data_container	*fspath;
 };
 
+struct btrfs_backref_shared_cache_entry {
+	u64 bytenr;
+	u64 gen;
+	bool is_shared;
+};
+
+struct btrfs_backref_shared_cache {
+	/*
+	 * 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];
+};
+
 typedef int (iterate_extent_inodes_t)(u64 inum, u64 offset, u64 root,
 		void *ctx);
 
@@ -62,8 +76,10 @@ 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_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr,
-		struct ulist *roots, struct ulist *tmp_ulist);
+int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr,
+				u64 extent_gen,
+				struct ulist *roots, struct ulist *tmp,
+				struct btrfs_backref_shared_cache *cache);
 
 int __init btrfs_prelim_ref_init(void);
 void __cold btrfs_prelim_ref_exit(void);

fs/btrfs/block-group.h

@@ -46,19 +46,44 @@ enum btrfs_chunk_alloc_enum {
 	CHUNK_ALLOC_FORCE_FOR_EXTENT,
 };
 
+/* Block group flags set at runtime */
+enum btrfs_block_group_flags {
+	BLOCK_GROUP_FLAG_IREF,
+	BLOCK_GROUP_FLAG_REMOVED,
+	BLOCK_GROUP_FLAG_TO_COPY,
+	BLOCK_GROUP_FLAG_RELOCATING_REPAIR,
+	BLOCK_GROUP_FLAG_CHUNK_ITEM_INSERTED,
+	BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE,
+	BLOCK_GROUP_FLAG_ZONED_DATA_RELOC,
+};
+
+enum btrfs_caching_type {
+	BTRFS_CACHE_NO,
+	BTRFS_CACHE_STARTED,
+	BTRFS_CACHE_FINISHED,
+	BTRFS_CACHE_ERROR,
+};
+
 struct btrfs_caching_control {
 	struct list_head list;
 	struct mutex mutex;
 	wait_queue_head_t wait;
 	struct btrfs_work work;
 	struct btrfs_block_group *block_group;
-	u64 progress;
 	refcount_t count;
 };
 
 /* Once caching_thread() finds this much free space, it will wake up waiters. */
 #define CACHING_CTL_WAKE_UP SZ_2M
 
+/*
+ * Tree to record all locked full stripes of a RAID5/6 block group
+ */
+struct btrfs_full_stripe_locks_tree {
+	struct rb_root root;
+	struct mutex lock;
+};
+
 struct btrfs_block_group {
 	struct btrfs_fs_info *fs_info;
 	struct inode *inode;
@@ -95,23 +120,15 @@ struct btrfs_block_group {
 
 	/* For raid56, this is a full stripe, without parity */
 	unsigned long full_stripe_len;
+	unsigned long runtime_flags;
 
 	unsigned int ro;
-	unsigned int iref:1;
-	unsigned int has_caching_ctl:1;
-	unsigned int removed:1;
-	unsigned int to_copy:1;
-	unsigned int relocating_repair:1;
-	unsigned int chunk_item_inserted:1;
-	unsigned int zone_is_active:1;
-	unsigned int zoned_data_reloc_ongoing:1;
 
 	int disk_cache_state;
 
 	/* Cache tracking stuff */
 	int cached;
 	struct btrfs_caching_control *caching_ctl;
-	u64 last_byte_to_unpin;
 
 	struct btrfs_space_info *space_info;
 
@@ -305,8 +322,6 @@ void btrfs_reserve_chunk_metadata(struct btrfs_trans_handle *trans,
 u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
 int btrfs_free_block_groups(struct btrfs_fs_info *info);
-void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache,
-				struct btrfs_caching_control *caching_ctl);
 int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 		       struct block_device *bdev, u64 physical, u64 **logical,
 		       int *naddrs, int *stripe_len);

fs/btrfs/block-rsv.c

@@ -286,7 +286,7 @@ u64 btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
 	 */
 	if (block_rsv == delayed_rsv)
 		target = global_rsv;
-	else if (block_rsv != global_rsv && !delayed_rsv->full)
+	else if (block_rsv != global_rsv && !btrfs_block_rsv_full(delayed_rsv))
 		target = delayed_rsv;
 
 	if (target && block_rsv->space_info != target->space_info)
@@ -424,6 +424,7 @@ void btrfs_init_root_block_rsv(struct btrfs_root *root)
 	case BTRFS_CSUM_TREE_OBJECTID:
 	case BTRFS_EXTENT_TREE_OBJECTID:
 	case BTRFS_FREE_SPACE_TREE_OBJECTID:
+	case BTRFS_BLOCK_GROUP_TREE_OBJECTID:
 		root->block_rsv = &fs_info->delayed_refs_rsv;
 		break;
 	case BTRFS_ROOT_TREE_OBJECTID:

fs/btrfs/block-rsv.h

@@ -92,4 +92,13 @@ static inline void btrfs_unuse_block_rsv(struct btrfs_fs_info *fs_info,
 	btrfs_block_rsv_release(fs_info, block_rsv, 0, NULL);
 }
 
+/*
+ * Fast path to check if the reserve is full, may be carefully used outside of
+ * locks.
+ */
+static inline bool btrfs_block_rsv_full(const struct btrfs_block_rsv *rsv)
+{
+	return data_race(rsv->full);
+}
+
 #endif /* BTRFS_BLOCK_RSV_H */

fs/btrfs/btrfs_inode.h

@@ -65,6 +65,8 @@ enum {
 	 * on the same file.
 	 */
 	BTRFS_INODE_VERITY_IN_PROGRESS,
+	/* Set when this inode is a free space inode. */
+	BTRFS_INODE_FREE_SPACE_INODE,
 };
 
 /* in memory btrfs inode */
@@ -94,7 +96,8 @@ struct btrfs_inode {
 	/* special utility tree used to record which mirrors have already been
 	 * tried when checksums fail for a given block
 	 */
-	struct extent_io_tree io_failure_tree;
+	struct rb_root io_failure_tree;
+	spinlock_t io_failure_lock;
 
 	/*
 	 * Keep track of where the inode has extent items mapped in order to
@@ -250,11 +253,6 @@ struct btrfs_inode {
 	struct inode vfs_inode;
 };
 
-static inline u32 btrfs_inode_sectorsize(const struct btrfs_inode *inode)
-{
-	return inode->root->fs_info->sectorsize;
-}
-
 static inline struct btrfs_inode *BTRFS_I(const struct inode *inode)
 {
 	return container_of(inode, struct btrfs_inode, vfs_inode);
@@ -272,13 +270,6 @@ static inline unsigned long btrfs_inode_hash(u64 objectid,
 	return (unsigned long)h;
 }
 
-static inline void btrfs_insert_inode_hash(struct inode *inode)
-{
-	unsigned long h = btrfs_inode_hash(inode->i_ino, BTRFS_I(inode)->root);
-
-	__insert_inode_hash(inode, h);
-}
-
 #if BITS_PER_LONG == 32
 
 /*
@@ -312,13 +303,7 @@ static inline void btrfs_i_size_write(struct btrfs_inode *inode, u64 size)
 
 static inline bool btrfs_is_free_space_inode(struct btrfs_inode *inode)
 {
-	struct btrfs_root *root = inode->root;
-
-	if (root == root->fs_info->tree_root &&
-	    btrfs_ino(inode) != BTRFS_BTREE_INODE_OBJECTID)
-		return true;
-
-	return false;
+	return test_bit(BTRFS_INODE_FREE_SPACE_INODE, &inode->runtime_flags);
 }
 
 static inline bool is_data_inode(struct inode *inode)

fs/btrfs/compression.c

@@ -152,9 +152,7 @@ static void finish_compressed_bio_read(struct compressed_bio *cb)
 	}
 
 	/* Do io completion on the original bio */
-	if (cb->status != BLK_STS_OK)
-		cb->orig_bio->bi_status = cb->status;
-	bio_endio(cb->orig_bio);
+	btrfs_bio_end_io(btrfs_bio(cb->orig_bio), cb->status);
 
 	/* Finally free the cb struct */
 	kfree(cb->compressed_pages);
@@ -166,16 +164,15 @@ static void finish_compressed_bio_read(struct compressed_bio *cb)
  * before decompressing it into the original bio and freeing the uncompressed
  * pages.
  */
-static void end_compressed_bio_read(struct bio *bio)
+static void end_compressed_bio_read(struct btrfs_bio *bbio)
 {
-	struct compressed_bio *cb = bio->bi_private;
+	struct compressed_bio *cb = bbio->private;
 	struct inode *inode = cb->inode;
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_inode *bi = BTRFS_I(inode);
 	bool csum = !(bi->flags & BTRFS_INODE_NODATASUM) &&
 		    !test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state);
-	blk_status_t status = bio->bi_status;
-	struct btrfs_bio *bbio = btrfs_bio(bio);
+	blk_status_t status = bbio->bio.bi_status;
 	struct bvec_iter iter;
 	struct bio_vec bv;
 	u32 offset;
@@ -186,9 +183,8 @@ static void end_compressed_bio_read(struct bio *bio)
 		if (!status &&
 		    (!csum || !btrfs_check_data_csum(inode, bbio, offset,
 						     bv.bv_page, bv.bv_offset))) {
-			clean_io_failure(fs_info, &bi->io_failure_tree,
-					 &bi->io_tree, start, bv.bv_page,
-					 btrfs_ino(bi), bv.bv_offset);
+			btrfs_clean_io_failure(bi, start, bv.bv_page,
+					       bv.bv_offset);
 		} else {
 			int ret;
 
@@ -209,7 +205,7 @@ static void end_compressed_bio_read(struct bio *bio)
 	if (refcount_dec_and_test(&cb->pending_ios))
 		finish_compressed_bio_read(cb);
 	btrfs_bio_free_csum(bbio);
-	bio_put(bio);
+	bio_put(&bbio->bio);
 }
 
 /*
@@ -301,20 +297,20 @@ static void btrfs_finish_compressed_write_work(struct work_struct *work)
  * This also calls the writeback end hooks for the file pages so that metadata
  * and checksums can be updated in the file.
  */
-static void end_compressed_bio_write(struct bio *bio)
+static void end_compressed_bio_write(struct btrfs_bio *bbio)
 {
-	struct compressed_bio *cb = bio->bi_private;
+	struct compressed_bio *cb = bbio->private;
 
-	if (bio->bi_status)
-		cb->status = bio->bi_status;
+	if (bbio->bio.bi_status)
+		cb->status = bbio->bio.bi_status;
 
 	if (refcount_dec_and_test(&cb->pending_ios)) {
 		struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb);
 
-		btrfs_record_physical_zoned(cb->inode, cb->start, bio);
+		btrfs_record_physical_zoned(cb->inode, cb->start, &bbio->bio);
 		queue_work(fs_info->compressed_write_workers, &cb->write_end_work);
 	}
-	bio_put(bio);
+	bio_put(&bbio->bio);
 }
 
 /*
@@ -335,7 +331,8 @@ static void end_compressed_bio_write(struct bio *bio)
 
 
 static struct bio *alloc_compressed_bio(struct compressed_bio *cb, u64 disk_bytenr,
-					blk_opf_t opf, bio_end_io_t endio_func,
+					blk_opf_t opf,
+					btrfs_bio_end_io_t endio_func,
 					u64 *next_stripe_start)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb);
@@ -344,12 +341,8 @@ static struct bio *alloc_compressed_bio(struct compressed_bio *cb, u64 disk_byte
 	struct bio *bio;
 	int ret;
 
-	bio = btrfs_bio_alloc(BIO_MAX_VECS);
-
+	bio = btrfs_bio_alloc(BIO_MAX_VECS, opf, endio_func, cb);
 	bio->bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT;
-	bio->bi_opf = opf;
-	bio->bi_private = cb;
-	bio->bi_end_io = endio_func;
 
 	em = btrfs_get_chunk_map(fs_info, disk_bytenr, fs_info->sectorsize);
 	if (IS_ERR(em)) {
@@ -478,8 +471,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 			if (!skip_sum) {
 				ret = btrfs_csum_one_bio(inode, bio, start, true);
 				if (ret) {
-					bio->bi_status = ret;
-					bio_endio(bio);
+					btrfs_bio_end_io(btrfs_bio(bio), ret);
 					break;
 				}
 			}
@@ -596,7 +588,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		}
 
 		page_end = (pg_index << PAGE_SHIFT) + PAGE_SIZE - 1;
-		lock_extent(tree, cur, page_end);
+		lock_extent(tree, cur, page_end, NULL);
 		read_lock(&em_tree->lock);
 		em = lookup_extent_mapping(em_tree, cur, page_end + 1 - cur);
 		read_unlock(&em_tree->lock);
@@ -610,7 +602,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		    (cur + fs_info->sectorsize > extent_map_end(em)) ||
 		    (em->block_start >> 9) != cb->orig_bio->bi_iter.bi_sector) {
 			free_extent_map(em);
-			unlock_extent(tree, cur, page_end);
+			unlock_extent(tree, cur, page_end, NULL);
 			unlock_page(page);
 			put_page(page);
 			break;
@@ -630,7 +622,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		add_size = min(em->start + em->len, page_end + 1) - cur;
 		ret = bio_add_page(cb->orig_bio, page, add_size, offset_in_page(cur));
 		if (ret != add_size) {
-			unlock_extent(tree, cur, page_end);
+			unlock_extent(tree, cur, page_end, NULL);
 			unlock_page(page);
 			put_page(page);
 			break;
@@ -799,8 +791,7 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 
 			ret = btrfs_lookup_bio_sums(inode, comp_bio, NULL);
 			if (ret) {
-				comp_bio->bi_status = ret;
-				bio_endio(comp_bio);
+				btrfs_bio_end_io(btrfs_bio(comp_bio), ret);
 				break;
 			}
 
@@ -826,8 +817,7 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	kfree(cb);
 out:
 	free_extent_map(em);
-	bio->bi_status = ret;
-	bio_endio(bio);
+	btrfs_bio_end_io(btrfs_bio(bio), ret);
 	return;
 }
 

fs/btrfs/ctree.c

@@ -1447,6 +1447,11 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 			return 0;
 		}
 
+		if (p->nowait) {
+			free_extent_buffer(tmp);
+			return -EAGAIN;
+		}
+
 		if (unlock_up)
 			btrfs_unlock_up_safe(p, level + 1);
 
@@ -1467,6 +1472,8 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 			ret = -EAGAIN;
 
 		goto out;
+	} else if (p->nowait) {
+		return -EAGAIN;
 	}
 
 	if (unlock_up) {
@@ -1634,7 +1641,13 @@ static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root,
 		 * We don't know the level of the root node until we actually
 		 * have it read locked
 		 */
+		if (p->nowait) {
+			b = btrfs_try_read_lock_root_node(root);
+			if (IS_ERR(b))
+				return b;
+		} else {
 			b = btrfs_read_lock_root_node(root);
+		}
 		level = btrfs_header_level(b);
 		if (level > write_lock_level)
 			goto out;
@@ -1910,6 +1923,13 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	WARN_ON(p->nodes[0] != NULL);
 	BUG_ON(!cow && ins_len);
 
+	/*
+	 * For now only allow nowait for read only operations.  There's no
+	 * strict reason why we can't, we just only need it for reads so it's
+	 * only implemented for reads.
+	 */
+	ASSERT(!p->nowait || !cow);
+
 	if (ins_len < 0) {
 		lowest_unlock = 2;
 
@@ -1936,8 +1956,13 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 
 	if (p->need_commit_sem) {
 		ASSERT(p->search_commit_root);
+		if (p->nowait) {
+			if (!down_read_trylock(&fs_info->commit_root_sem))
+				return -EAGAIN;
+		} else {
 			down_read(&fs_info->commit_root_sem);
 		}
+	}
 
 again:
 	prev_cmp = -1;
@@ -2081,8 +2106,16 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			if (level <= write_lock_level) {
 				btrfs_tree_lock(b);
 				p->locks[level] = BTRFS_WRITE_LOCK;
+			} else {
+				if (p->nowait) {
+					if (!btrfs_try_tree_read_lock(b)) {
+						free_extent_buffer(b);
+						ret = -EAGAIN;
+						goto done;
+					}
 				} else {
 					btrfs_tree_read_lock(b);
+				}
 				p->locks[level] = BTRFS_READ_LOCK;
 			}
 			p->nodes[level] = b;
@@ -2131,6 +2164,7 @@ int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key,
 
 	lowest_level = p->lowest_level;
 	WARN_ON(p->nodes[0] != NULL);
+	ASSERT(!p->nowait);
 
 	if (p->search_commit_root) {
 		BUG_ON(time_seq);
@@ -4432,6 +4466,7 @@ int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key,
 	int ret = 1;
 	int keep_locks = path->keep_locks;
 
+	ASSERT(!path->nowait);
 	path->keep_locks = 1;
 again:
 	cur = btrfs_read_lock_root_node(root);
@@ -4612,6 +4647,8 @@ int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path,
 	int ret;
 	int i;
 
+	ASSERT(!path->nowait);
+
 	nritems = btrfs_header_nritems(path->nodes[0]);
 	if (nritems == 0)
 		return 1;

fs/btrfs/delalloc-space.c

@@ -127,9 +127,11 @@ int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes)
 }
 
 int btrfs_check_data_free_space(struct btrfs_inode *inode,
-			struct extent_changeset **reserved, u64 start, u64 len)
+				struct extent_changeset **reserved, u64 start,
+				u64 len, bool noflush)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_DATA;
 	int ret;
 
 	/* align the range */
@@ -137,7 +139,12 @@ int btrfs_check_data_free_space(struct btrfs_inode *inode,
 	      round_down(start, fs_info->sectorsize);
 	start = round_down(start, fs_info->sectorsize);
 
-	ret = btrfs_alloc_data_chunk_ondemand(inode, len);
+	if (noflush)
+		flush = BTRFS_RESERVE_NO_FLUSH;
+	else if (btrfs_is_free_space_inode(inode))
+		flush = BTRFS_RESERVE_FLUSH_FREE_SPACE_INODE;
+
+	ret = btrfs_reserve_data_bytes(fs_info, len, flush);
 	if (ret < 0)
 		return ret;
 
@@ -454,7 +461,7 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode,
 {
 	int ret;
 
-	ret = btrfs_check_data_free_space(inode, reserved, start, len);
+	ret = btrfs_check_data_free_space(inode, reserved, start, len, false);
 	if (ret < 0)
 		return ret;
 	ret = btrfs_delalloc_reserve_metadata(inode, len, len, false);

fs/btrfs/delalloc-space.h

@@ -7,7 +7,8 @@ struct extent_changeset;
 
 int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes);
 int btrfs_check_data_free_space(struct btrfs_inode *inode,
-			struct extent_changeset **reserved, u64 start, u64 len);
+			struct extent_changeset **reserved, u64 start, u64 len,
+			bool noflush);
 void btrfs_free_reserved_data_space(struct btrfs_inode *inode,
 			struct extent_changeset *reserved, u64 start, u64 len);
 void btrfs_delalloc_release_space(struct btrfs_inode *inode,

fs/btrfs/delayed-inode.h

@@ -16,9 +16,10 @@
 #include <linux/refcount.h>
 #include "ctree.h"
 
-/* types of the delayed item */
-#define BTRFS_DELAYED_INSERTION_ITEM	1
-#define BTRFS_DELAYED_DELETION_ITEM	2
+enum btrfs_delayed_item_type {
+	BTRFS_DELAYED_INSERTION_ITEM,
+	BTRFS_DELAYED_DELETION_ITEM
+};
 
 struct btrfs_delayed_root {
 	spinlock_t lock;
@@ -73,14 +74,27 @@ struct btrfs_delayed_node {
 
 struct btrfs_delayed_item {
 	struct rb_node rb_node;
-	struct btrfs_key key;
+	/* Offset value of the corresponding dir index key. */
+	u64 index;
 	struct list_head tree_list;	/* used for batch insert/delete items */
 	struct list_head readdir_list;	/* used for readdir items */
+	/*
+	 * Used when logging a directory.
+	 * Insertions and deletions to this list are protected by the parent
+	 * delayed node's mutex.
+	 */
+	struct list_head log_list;
 	u64 bytes_reserved;
 	struct btrfs_delayed_node *delayed_node;
 	refcount_t refs;
-	int ins_or_del;
-	u32 data_len;
+	enum btrfs_delayed_item_type type:8;
+	/*
+	 * Track if this delayed item was already logged.
+	 * Protected by the mutex of the parent delayed inode.
+	 */
+	bool logged;
+	/* The maximum leaf size is 64K, so u16 is more than enough. */
+	u16 data_len;
 	char data[];
 };
 
@@ -144,6 +158,14 @@ int btrfs_should_delete_dir_index(struct list_head *del_list,
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
 				    struct list_head *ins_list);
 
+/* Used during directory logging. */
+void btrfs_log_get_delayed_items(struct btrfs_inode *inode,
+				 struct list_head *ins_list,
+				 struct list_head *del_list);
+void btrfs_log_put_delayed_items(struct btrfs_inode *inode,
+				 struct list_head *ins_list,
+				 struct list_head *del_list);
+
 /* for init */
 int __init btrfs_delayed_inode_init(void);
 void __cold btrfs_delayed_inode_exit(void);

fs/btrfs/dev-replace.c

@@ -545,10 +545,7 @@ static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info,
 		if (!cache)
 			continue;
 
-		spin_lock(&cache->lock);
-		cache->to_copy = 1;
-		spin_unlock(&cache->lock);
-
+		set_bit(BLOCK_GROUP_FLAG_TO_COPY, &cache->runtime_flags);
 		btrfs_put_block_group(cache);
 	}
 	if (iter_ret < 0)
@@ -577,7 +574,7 @@ bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev,
 		return true;
 
 	spin_lock(&cache->lock);
-	if (cache->removed) {
+	if (test_bit(BLOCK_GROUP_FLAG_REMOVED, &cache->runtime_flags)) {
 		spin_unlock(&cache->lock);
 		return true;
 	}
@@ -610,9 +607,7 @@ bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev,
 	}
 
 	/* Last stripe on this device */
-	spin_lock(&cache->lock);
-	cache->to_copy = 0;
-	spin_unlock(&cache->lock);
+	clear_bit(BLOCK_GROUP_FLAG_TO_COPY, &cache->runtime_flags);
 
 	return true;
 }
@@ -1288,11 +1283,6 @@ int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
 	return 1;
 }
 
-void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info)
-{
-	percpu_counter_inc(&fs_info->dev_replace.bio_counter);
-}
-
 void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount)
 {
 	percpu_counter_sub(&fs_info->dev_replace.bio_counter, amount);

fs/btrfs/dev-replace.h

@@ -7,6 +7,10 @@
 #define BTRFS_DEV_REPLACE_H
 
 struct btrfs_ioctl_dev_replace_args;
+struct btrfs_fs_info;
+struct btrfs_trans_handle;
+struct btrfs_dev_replace;
+struct btrfs_block_group;
 
 int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info);
 int btrfs_run_dev_replace(struct btrfs_trans_handle *trans);

fs/btrfs/disk-io.h

@@ -46,10 +46,13 @@ int __cold open_ctree(struct super_block *sb,
 	       struct btrfs_fs_devices *fs_devices,
 	       char *options);
 void __cold close_ctree(struct btrfs_fs_info *fs_info);
+int btrfs_validate_super(struct btrfs_fs_info *fs_info,
+			 struct btrfs_super_block *sb, int mirror_num);
+int btrfs_check_features(struct btrfs_fs_info *fs_info, struct super_block *sb);
 int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors);
 struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev);
 struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev,
-						   int copy_num);
+						   int copy_num, bool drop_cache);
 int btrfs_commit_super(struct btrfs_fs_info *fs_info);
 struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
 					struct btrfs_key *key);
@@ -103,7 +106,7 @@ static inline struct btrfs_root *btrfs_grab_root(struct btrfs_root *root)
 
 static inline struct btrfs_root *btrfs_block_group_root(struct btrfs_fs_info *fs_info)
 {
-	if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2))
+	if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE))
 		return fs_info->block_group_root;
 	return btrfs_extent_root(fs_info, 0);
 }

fs/btrfs/extent-io-tree.h

@@ -17,7 +17,6 @@ struct io_failure_record;
 #define EXTENT_NODATASUM	(1U << 7)
 #define EXTENT_CLEAR_META_RESV	(1U << 8)
 #define EXTENT_NEED_WAIT	(1U << 9)
-#define EXTENT_DAMAGED		(1U << 10)
 #define EXTENT_NORESERVE	(1U << 11)
 #define EXTENT_QGROUP_RESERVED	(1U << 12)
 #define EXTENT_CLEAR_DATA_RESV	(1U << 13)
@@ -35,10 +34,18 @@ struct io_failure_record;
  * delalloc bytes decremented, in an atomic way to prevent races with stat(2).
  */
 #define EXTENT_ADD_INODE_BYTES  (1U << 15)
+
+/*
+ * Set during truncate when we're clearing an entire range and we just want the
+ * extent states to go away.
+ */
+#define EXTENT_CLEAR_ALL_BITS	(1U << 16)
+
 #define EXTENT_DO_ACCOUNTING    (EXTENT_CLEAR_META_RESV | \
 				 EXTENT_CLEAR_DATA_RESV)
 #define EXTENT_CTLBITS		(EXTENT_DO_ACCOUNTING | \
-				 EXTENT_ADD_INODE_BYTES)
+				 EXTENT_ADD_INODE_BYTES | \
+				 EXTENT_CLEAR_ALL_BITS)
 
 /*
  * Redefined bits above which are used only in the device allocation tree,
@@ -56,7 +63,6 @@ enum {
 	IO_TREE_FS_EXCLUDED_EXTENTS,
 	IO_TREE_BTREE_INODE_IO,
 	IO_TREE_INODE_IO,
-	IO_TREE_INODE_IO_FAILURE,
 	IO_TREE_RELOC_BLOCKS,
 	IO_TREE_TRANS_DIRTY_PAGES,
 	IO_TREE_ROOT_DIRTY_LOG_PAGES,
@@ -70,8 +76,6 @@ struct extent_io_tree {
 	struct rb_root state;
 	struct btrfs_fs_info *fs_info;
 	void *private_data;
-	u64 dirty_bytes;
-	bool track_uptodate;
 
 	/* Who owns this io tree, should be one of IO_TREE_* */
 	u8 owner;
@@ -89,33 +93,23 @@ struct extent_state {
 	refcount_t refs;
 	u32 state;
 
-	struct io_failure_record *failrec;
-
 #ifdef CONFIG_BTRFS_DEBUG
 	struct list_head leak_list;
 #endif
 };
 
-int __init extent_state_cache_init(void);
-void __cold extent_state_cache_exit(void);
-
 void extent_io_tree_init(struct btrfs_fs_info *fs_info,
 			 struct extent_io_tree *tree, unsigned int owner,
 			 void *private_data);
 void extent_io_tree_release(struct extent_io_tree *tree);
 
-int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+int lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
 		struct extent_state **cached);
 
-static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	return lock_extent_bits(tree, start, end, NULL);
-}
-
 int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 
-int __init extent_io_init(void);
-void __cold extent_io_exit(void);
+int __init extent_state_init_cachep(void);
+void __cold extent_state_free_cachep(void);
 
 u64 count_range_bits(struct extent_io_tree *tree,
 		     u64 *start, u64 search_end,
@@ -126,72 +120,66 @@ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		   u32 bits, int filled, struct extent_state *cached_state);
 int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 			     u32 bits, struct extent_changeset *changeset);
-int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		     u32 bits, int wake, int delete,
-		     struct extent_state **cached);
 int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		     u32 bits, int wake, int delete,
-		     struct extent_state **cached, gfp_t mask,
+		       u32 bits, struct extent_state **cached, gfp_t mask,
 		       struct extent_changeset *changeset);
 
-static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
+static inline int clear_extent_bit(struct extent_io_tree *tree, u64 start,
+				   u64 end, u32 bits,
+				   struct extent_state **cached)
 {
-	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL);
+	return __clear_extent_bit(tree, start, end, bits, cached,
+				  GFP_NOFS, NULL);
 }
 
-static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
-		u64 end, struct extent_state **cached)
+static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end,
+				struct extent_state **cached)
 {
-	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
+	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, cached,
 				  GFP_NOFS, NULL);
 }
 
-static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree,
-		u64 start, u64 end, struct extent_state **cached)
+static inline int unlock_extent_atomic(struct extent_io_tree *tree, u64 start,
+				       u64 end, struct extent_state **cached)
 {
-	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
+	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, cached,
 				  GFP_ATOMIC, NULL);
 }
 
 static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
 				    u64 end, u32 bits)
 {
-	int wake = 0;
-
-	if (bits & EXTENT_LOCKED)
-		wake = 1;
-
-	return clear_extent_bit(tree, start, end, bits, wake, 0, NULL);
+	return clear_extent_bit(tree, start, end, bits, NULL);
 }
 
 int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 			   u32 bits, struct extent_changeset *changeset);
 int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   u32 bits, unsigned exclusive_bits, u64 *failed_start,
-		   struct extent_state **cached_state, gfp_t mask,
-		   struct extent_changeset *changeset);
-int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end,
-			   u32 bits);
+		   u32 bits, struct extent_state **cached_state, gfp_t mask);
+
+static inline int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start,
+					 u64 end, u32 bits)
+{
+	return set_extent_bit(tree, start, end, bits, NULL, GFP_NOWAIT);
+}
 
 static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
 		u64 end, u32 bits)
 {
-	return set_extent_bit(tree, start, end, bits, 0, NULL, NULL, GFP_NOFS,
-			      NULL);
+	return set_extent_bit(tree, start, end, bits, NULL, GFP_NOFS);
 }
 
 static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
 		u64 end, struct extent_state **cached_state)
 {
-	return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
+	return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE,
 				  cached_state, GFP_NOFS, NULL);
 }
 
 static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
 		u64 end, gfp_t mask)
 {
-	return set_extent_bit(tree, start, end, EXTENT_DIRTY, 0, NULL, NULL,
-			      mask, NULL);
+	return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL, mask);
 }
 
 static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
@@ -199,7 +187,7 @@ static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
 {
 	return clear_extent_bit(tree, start, end,
 				EXTENT_DIRTY | EXTENT_DELALLOC |
-				EXTENT_DO_ACCOUNTING, 0, 0, cached);
+				EXTENT_DO_ACCOUNTING, cached);
 }
 
 int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
@@ -211,30 +199,29 @@ static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
 				      struct extent_state **cached_state)
 {
 	return set_extent_bit(tree, start, end,
-			      EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
-			      0, NULL, cached_state, GFP_NOFS, NULL);
+			      EXTENT_DELALLOC | extra_bits,
+			      cached_state, GFP_NOFS);
 }
 
 static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
 		u64 end, struct extent_state **cached_state)
 {
 	return set_extent_bit(tree, start, end,
-			      EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
-			      0, NULL, cached_state, GFP_NOFS, NULL);
+			      EXTENT_DELALLOC | EXTENT_DEFRAG,
+			      cached_state, GFP_NOFS);
 }
 
 static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
 		u64 end)
 {
-	return set_extent_bit(tree, start, end, EXTENT_NEW, 0, NULL, NULL,
-			      GFP_NOFS, NULL);
+	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, GFP_NOFS);
 }
 
 static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
 		u64 end, struct extent_state **cached_state, gfp_t mask)
 {
-	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, NULL,
-			      cached_state, mask, NULL);
+	return set_extent_bit(tree, start, end, EXTENT_UPTODATE,
+			      cached_state, mask);
 }
 
 int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
@@ -244,24 +231,9 @@ void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
 				 u64 *start_ret, u64 *end_ret, u32 bits);
 int find_contiguous_extent_bit(struct extent_io_tree *tree, u64 start,
 			       u64 *start_ret, u64 *end_ret, u32 bits);
-int extent_invalidate_folio(struct extent_io_tree *tree,
-			  struct folio *folio, size_t offset);
 bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
 			       u64 *end, u64 max_bytes,
 			       struct extent_state **cached_state);
-
-/* This should be reworked in the future and put elsewhere. */
-struct io_failure_record *get_state_failrec(struct extent_io_tree *tree, u64 start);
-int set_state_failrec(struct extent_io_tree *tree, u64 start,
-		      struct io_failure_record *failrec);
-void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
-		u64 end);
-int free_io_failure(struct extent_io_tree *failure_tree,
-		    struct extent_io_tree *io_tree,
-		    struct io_failure_record *rec);
-int clean_io_failure(struct btrfs_fs_info *fs_info,
-		     struct extent_io_tree *failure_tree,
-		     struct extent_io_tree *io_tree, u64 start,
-		     struct page *page, u64 ino, unsigned int pg_offset);
+void wait_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, u32 bits);
 
 #endif /* BTRFS_EXTENT_IO_TREE_H */

fs/btrfs/extent-tree.c

@@ -2220,6 +2220,12 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
 	}
 
 	if (!mutex_trylock(&head->mutex)) {
+		if (path->nowait) {
+			spin_unlock(&delayed_refs->lock);
+			btrfs_put_transaction(cur_trans);
+			return -EAGAIN;
+		}
+
 		refcount_inc(&head->refs);
 		spin_unlock(&delayed_refs->lock);
 
@@ -2686,13 +2692,8 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 		len = cache->start + cache->length - start;
 		len = min(len, end + 1 - start);
 
-		down_read(&fs_info->commit_root_sem);
-		if (start < cache->last_byte_to_unpin && return_free_space) {
-			u64 add_len = min(len, cache->last_byte_to_unpin - start);
-
-			btrfs_add_free_space(cache, start, add_len);
-		}
-		up_read(&fs_info->commit_root_sem);
+		if (return_free_space)
+			btrfs_add_free_space(cache, start, len);
 
 		start += len;
 		total_unpinned += len;
@@ -3804,7 +3805,8 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
 	       block_group->start == fs_info->data_reloc_bg ||
 	       fs_info->data_reloc_bg == 0);
 
-	if (block_group->ro || block_group->zoned_data_reloc_ongoing) {
+	if (block_group->ro ||
+	    test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) {
 		ret = 1;
 		goto out;
 	}
@@ -3881,7 +3883,7 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
 		 * regular extents) at the same time to the same zone, which
 		 * easily break the write pointer.
 		 */
-		block_group->zoned_data_reloc_ongoing = 1;
+		set_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags);
 		fs_info->data_reloc_bg = 0;
 	}
 	spin_unlock(&fs_info->relocation_bg_lock);
@@ -4888,6 +4890,9 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	    !test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state))
 		lockdep_owner = BTRFS_FS_TREE_OBJECTID;
 
+	/* btrfs_clean_tree_block() accesses generation field. */
+	btrfs_set_header_generation(buf, trans->transid);
+
 	/*
 	 * This needs to stay, because we could allocate a freed block from an
 	 * old tree into a new tree, so we need to make sure this new block is
@@ -5639,6 +5644,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
  */
 int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 {
+	const bool is_reloc_root = (root->root_key.objectid ==
+				    BTRFS_TREE_RELOC_OBJECTID);
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_path *path;
 	struct btrfs_trans_handle *trans;
@@ -5798,6 +5805,9 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 				goto out_end_trans;
 			}
 
+			if (!is_reloc_root)
+				btrfs_set_last_root_drop_gen(fs_info, trans->transid);
+
 			btrfs_end_transaction_throttle(trans);
 			if (!for_reloc && btrfs_need_cleaner_sleep(fs_info)) {
 				btrfs_debug(fs_info,
@@ -5832,7 +5842,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 		goto out_end_trans;
 	}
 
-	if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID) {
+	if (!is_reloc_root) {
 		ret = btrfs_find_root(tree_root, &root->root_key, path,
 				      NULL, NULL);
 		if (ret < 0) {
@@ -5864,6 +5874,9 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 		btrfs_put_root(root);
 	root_dropped = true;
 out_end_trans:
+	if (!is_reloc_root)
+		btrfs_set_last_root_drop_gen(fs_info, trans->transid);
+
 	btrfs_end_transaction_throttle(trans);
 out_free:
 	kfree(wc);

fs/btrfs/extent_io.h

@@ -60,11 +60,13 @@ enum {
 struct btrfs_bio;
 struct btrfs_root;
 struct btrfs_inode;
-struct btrfs_io_bio;
 struct btrfs_fs_info;
 struct io_failure_record;
 struct extent_io_tree;
 
+int __init extent_buffer_init_cachep(void);
+void __cold extent_buffer_free_cachep(void);
+
 typedef void (submit_bio_hook_t)(struct inode *inode, struct bio *bio,
 					 int mirror_num,
 					 enum btrfs_compression_type compress_type);
@@ -240,10 +242,10 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
 void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 				  struct page *locked_page,
 				  u32 bits_to_clear, unsigned long page_ops);
+int extent_invalidate_folio(struct extent_io_tree *tree,
+			    struct folio *folio, size_t offset);
 
 int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array);
-struct bio *btrfs_bio_alloc(unsigned int nr_iovecs);
-struct bio *btrfs_bio_clone_partial(struct bio *orig, u64 offset, u64 size);
 
 void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
 int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, int mirror_num);
@@ -257,8 +259,12 @@ int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, int mirror_num);
  * bio end_io callback is called to indicate things have failed.
  */
 struct io_failure_record {
+	/* Use rb_simple_node for search/insert */
+	struct {
+		struct rb_node rb_node;
+		u64 bytenr;
+	};
 	struct page *page;
-	u64 start;
 	u64 len;
 	u64 logical;
 	int this_mirror;
@@ -269,6 +275,9 @@ struct io_failure_record {
 int btrfs_repair_one_sector(struct inode *inode, struct btrfs_bio *failed_bbio,
 			    u32 bio_offset, struct page *page, unsigned int pgoff,
 			    submit_bio_hook_t *submit_bio_hook);
+void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, u64 end);
+int btrfs_clean_io_failure(struct btrfs_inode *inode, u64 start,
+			   struct page *page, unsigned int pg_offset);
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 bool find_lock_delalloc_range(struct inode *inode,

fs/btrfs/extent_map.h

@@ -63,6 +63,8 @@ struct extent_map_tree {
 	rwlock_t lock;
 };
 
+struct btrfs_inode;
+
 static inline int extent_map_in_tree(const struct extent_map *em)
 {
 	return !RB_EMPTY_NODE(&em->rb_node);
@@ -104,5 +106,11 @@ struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
 int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
 			     struct extent_map_tree *em_tree,
 			     struct extent_map **em_in, u64 start, u64 len);
+void btrfs_drop_extent_map_range(struct btrfs_inode *inode,
+				 u64 start, u64 end,
+				 bool skip_pinned);
+int btrfs_replace_extent_map_range(struct btrfs_inode *inode,
+				   struct extent_map *new_em,
+				   bool modified);
 
 #endif

fs/btrfs/file-item.c

@@ -118,7 +118,7 @@ int btrfs_inode_clear_file_extent_range(struct btrfs_inode *inode, u64 start,
 	if (btrfs_fs_incompat(inode->root->fs_info, NO_HOLES))
 		return 0;
 	return clear_extent_bit(&inode->file_extent_tree, start,
-				start + len - 1, EXTENT_DIRTY, 0, 0, NULL);
+				start + len - 1, EXTENT_DIRTY, NULL);
 }
 
 static inline u32 max_ordered_sum_bytes(struct btrfs_fs_info *fs_info,
@@ -129,12 +129,20 @@ static inline u32 max_ordered_sum_bytes(struct btrfs_fs_info *fs_info,
 	return ncsums * fs_info->sectorsize;
 }
 
-int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
+/*
+ * Calculate the total size needed to allocate for an ordered sum structure
+ * spanning @bytes in the file.
+ */
+static int btrfs_ordered_sum_size(struct btrfs_fs_info *fs_info, unsigned long bytes)
+{
+	int num_sectors = (int)DIV_ROUND_UP(bytes, fs_info->sectorsize);
+
+	return sizeof(struct btrfs_ordered_sum) + num_sectors * fs_info->csum_size;
+}
+
+int btrfs_insert_hole_extent(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root,
-			     u64 objectid, u64 pos,
-			     u64 disk_offset, u64 disk_num_bytes,
-			     u64 num_bytes, u64 offset, u64 ram_bytes,
-			     u8 compression, u8 encryption, u16 other_encoding)
+			     u64 objectid, u64 pos, u64 num_bytes)
 {
 	int ret = 0;
 	struct btrfs_file_extent_item *item;
@@ -157,16 +165,16 @@ int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
 	leaf = path->nodes[0];
 	item = btrfs_item_ptr(leaf, path->slots[0],
 			      struct btrfs_file_extent_item);
-	btrfs_set_file_extent_disk_bytenr(leaf, item, disk_offset);
-	btrfs_set_file_extent_disk_num_bytes(leaf, item, disk_num_bytes);
-	btrfs_set_file_extent_offset(leaf, item, offset);
+	btrfs_set_file_extent_disk_bytenr(leaf, item, 0);
+	btrfs_set_file_extent_disk_num_bytes(leaf, item, 0);
+	btrfs_set_file_extent_offset(leaf, item, 0);
 	btrfs_set_file_extent_num_bytes(leaf, item, num_bytes);
-	btrfs_set_file_extent_ram_bytes(leaf, item, ram_bytes);
+	btrfs_set_file_extent_ram_bytes(leaf, item, num_bytes);
 	btrfs_set_file_extent_generation(leaf, item, trans->transid);
 	btrfs_set_file_extent_type(leaf, item, BTRFS_FILE_EXTENT_REG);
-	btrfs_set_file_extent_compression(leaf, item, compression);
-	btrfs_set_file_extent_encryption(leaf, item, encryption);
-	btrfs_set_file_extent_other_encoding(leaf, item, other_encoding);
+	btrfs_set_file_extent_compression(leaf, item, 0);
+	btrfs_set_file_extent_encryption(leaf, item, 0);
+	btrfs_set_file_extent_other_encoding(leaf, item, 0);
 
 	btrfs_mark_buffer_dirty(leaf);
 out:
@@ -503,7 +511,8 @@ blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst
 }
 
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
-			     struct list_head *list, int search_commit)
+			     struct list_head *list, int search_commit,
+			     bool nowait)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_key key;
@@ -525,6 +534,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 	if (!path)
 		return -ENOMEM;
 
+	path->nowait = nowait;
 	if (search_commit) {
 		path->skip_locking = 1;
 		path->reada = READA_FORWARD;

fs/btrfs/free-space-cache.h

@@ -113,7 +113,6 @@ int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group,
 				       u64 bytenr, u64 size);
 int btrfs_remove_free_space(struct btrfs_block_group *block_group,
 			    u64 bytenr, u64 size);
-void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl);
 void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group);
 bool btrfs_is_free_space_trimmed(struct btrfs_block_group *block_group);
 u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,

fs/btrfs/free-space-tree.c

@@ -1453,8 +1453,6 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
 		ASSERT(key.type == BTRFS_FREE_SPACE_BITMAP_KEY);
 		ASSERT(key.objectid < end && key.objectid + key.offset <= end);
 
-		caching_ctl->progress = key.objectid;
-
 		offset = key.objectid;
 		while (offset < key.objectid + key.offset) {
 			bit = free_space_test_bit(block_group, path, offset);
@@ -1490,8 +1488,6 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
 		goto out;
 	}
 
-	caching_ctl->progress = (u64)-1;
-
 	ret = 0;
 out:
 	return ret;
@@ -1531,8 +1527,6 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
 		ASSERT(key.type == BTRFS_FREE_SPACE_EXTENT_KEY);
 		ASSERT(key.objectid < end && key.objectid + key.offset <= end);
 
-		caching_ctl->progress = key.objectid;
-
 		total_found += add_new_free_space(block_group, key.objectid,
 						  key.objectid + key.offset);
 		if (total_found > CACHING_CTL_WAKE_UP) {
@@ -1552,8 +1546,6 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
 		goto out;
 	}
 
-	caching_ctl->progress = (u64)-1;
-
 	ret = 0;
 out:
 	return ret;

fs/btrfs/ioctl.c

@@ -1218,10 +1218,10 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start,
 
 		/* get the big lock and read metadata off disk */
 		if (!locked)
-			lock_extent_bits(io_tree, start, end, &cached);
+			lock_extent(io_tree, start, end, &cached);
 		em = defrag_get_extent(BTRFS_I(inode), start, newer_than);
 		if (!locked)
-			unlock_extent_cached(io_tree, start, end, &cached);
+			unlock_extent(io_tree, start, end, &cached);
 
 		if (IS_ERR(em))
 			return NULL;
@@ -1333,9 +1333,9 @@ static struct page *defrag_prepare_one_page(struct btrfs_inode *inode,
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
 
-		lock_extent_bits(&inode->io_tree, page_start, page_end, &cached_state);
+		lock_extent(&inode->io_tree, page_start, page_end, &cached_state);
 		ordered = btrfs_lookup_ordered_range(inode, page_start, PAGE_SIZE);
-		unlock_extent_cached(&inode->io_tree, page_start, page_end,
+		unlock_extent(&inode->io_tree, page_start, page_end,
 			      &cached_state);
 		if (!ordered)
 			break;
@@ -1616,7 +1616,7 @@ static int defrag_one_locked_target(struct btrfs_inode *inode,
 		return ret;
 	clear_extent_bit(&inode->io_tree, start, start + len - 1,
 			 EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
-			 EXTENT_DEFRAG, 0, 0, cached_state);
+			 EXTENT_DEFRAG, cached_state);
 	set_extent_defrag(&inode->io_tree, start, start + len - 1, cached_state);
 
 	/* Update the page status */
@@ -1666,7 +1666,7 @@ static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len,
 		wait_on_page_writeback(pages[i]);
 
 	/* Lock the pages range */
-	lock_extent_bits(&inode->io_tree, start_index << PAGE_SHIFT,
+	lock_extent(&inode->io_tree, start_index << PAGE_SHIFT,
 		    (last_index << PAGE_SHIFT) + PAGE_SIZE - 1,
 		    &cached_state);
 	/*
@@ -1694,7 +1694,7 @@ static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len,
 		kfree(entry);
 	}
 unlock_extent:
-	unlock_extent_cached(&inode->io_tree, start_index << PAGE_SHIFT,
+	unlock_extent(&inode->io_tree, start_index << PAGE_SHIFT,
 		      (last_index << PAGE_SHIFT) + PAGE_SIZE - 1,
 		      &cached_state);
 free_pages:

fs/btrfs/locking.c

@@ -285,6 +285,31 @@ struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
 	return eb;
 }
 
+/*
+ * Loop around taking references on and locking the root node of the tree in
+ * nowait mode until we end up with a lock on the root node or returning to
+ * avoid blocking.
+ *
+ * Return: root extent buffer with read lock held or -EAGAIN.
+ */
+struct extent_buffer *btrfs_try_read_lock_root_node(struct btrfs_root *root)
+{
+	struct extent_buffer *eb;
+
+	while (1) {
+		eb = btrfs_root_node(root);
+		if (!btrfs_try_tree_read_lock(eb)) {
+			free_extent_buffer(eb);
+			return ERR_PTR(-EAGAIN);
+		}
+		if (eb == root->node)
+			break;
+		btrfs_tree_read_unlock(eb);
+		free_extent_buffer(eb);
+	}
+	return eb;
+}
+
 /*
  * DREW locks
  * ==========

fs/btrfs/locking.h

@@ -94,6 +94,7 @@ int btrfs_try_tree_read_lock(struct extent_buffer *eb);
 int btrfs_try_tree_write_lock(struct extent_buffer *eb);
 struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
 struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root);
+struct extent_buffer *btrfs_try_read_lock_root_node(struct btrfs_root *root);
 
 #ifdef CONFIG_BTRFS_DEBUG
 static inline void btrfs_assert_tree_write_locked(struct extent_buffer *eb)

fs/btrfs/props.c

@@ -270,11 +270,8 @@ int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	u64 ino = btrfs_ino(BTRFS_I(inode));
-	int ret;
-
-	ret = iterate_object_props(root, path, ino, inode_prop_iterator, inode);
 
-	return ret;
+	return iterate_object_props(root, path, ino, inode_prop_iterator, inode);
 }
 
 static int prop_compression_validate(const struct btrfs_inode *inode,

fs/btrfs/qgroup.h

@@ -100,6 +100,9 @@
  *     subtree rescan for them.
  */
 
+#define BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN		(1UL << 3)
+#define BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING		(1UL << 4)
+
 /*
  * Record a dirty extent, and info qgroup to update quota on it
  * TODO: Use kmem cache to alloc it.