Merge tag 'for-6.3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "The usual mix of performance improvements and new features.

  The core change is reworking how checksums are processed, with
  followup cleanups and simplifications. There are two minor changes in
  block layer and iomap code.

  Features:

   - block group allocation class heuristics:
      - pack files by size (up to 128k, up to 8M, more) to avoid
        fragmentation in block groups, assuming that file size and life
        time is correlated, in particular this may help during balance
      - with tracepoints and extensible in the future

  Performance:

   - send: cache directory utimes and only emit the command when
     necessary
      - speedup up to 10x
      - smaller final stream produced (no redundant utimes commands
        issued)
      - compatibility not affected

   - fiemap: skip backref checks for shared leaves
      - speedup 3x on sample filesystem with all leaves shared (e.g. on
        snapshots)

   - micro optimized b-tree key lookup, speedup in metadata operations
     (sample benchmark: fs_mark +10% of files/sec)

  Core changes:

   - change where checksumming is done in the io path:
      - checksum and read repair does verification at lower layer
      - cascaded cleanups and simplifications

   - raid56 refactoring and cleanups

  Fixes:

   - sysfs: make sure that a run-time change of a feature is correctly
     tracked by the feature files

   - scrub: better reporting of tree block errors

  Other:

   - locally enable -Wmaybe-uninitialized after fixing all warnings

   - misc cleanups, spelling fixes

  Other code:

   - block: export bio_split_rw

   - iomap: remove IOMAP_F_ZONE_APPEND"

* tag 'for-6.3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (109 commits)
  btrfs: make kobj_type structures constant
  btrfs: remove the bdev argument to btrfs_rmap_block
  btrfs: don't rely on unchanging ->bi_bdev for zone append remaps
  btrfs: never return true for reads in btrfs_use_zone_append
  btrfs: pass a btrfs_bio to btrfs_use_append
  btrfs: set bbio->file_offset in alloc_new_bio
  btrfs: use file_offset to limit bios size in calc_bio_boundaries
  btrfs: do unsigned integer division in the extent buffer binary search loop
  btrfs: eliminate extra call when doing binary search on extent buffer
  btrfs: raid56: handle endio in scrub_rbio
  btrfs: raid56: handle endio in recover_rbio
  btrfs: raid56: handle endio in rmw_rbio
  btrfs: raid56: submit the read bios from scrub_assemble_read_bios
  btrfs: raid56: fold rmw_read_wait_recover into rmw_read_bios
  btrfs: raid56: fold recover_assemble_read_bios into recover_rbio
  btrfs: raid56: add a bio_list_put helper
  btrfs: raid56: wait for I/O completion in submit_read_bios
  btrfs: raid56: simplify code flow in rmw_rbio
  btrfs: raid56: simplify error handling and code flow in raid56_parity_write
  btrfs: replace btrfs_wait_tree_block_writeback by wait_on_extent_buffer_writeback
  ...

57 files changed, 2346 insertions, 2872 deletions

diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 555c962fdad6..90d53209755b 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -11,7 +11,8 @@ condflags := \
 	$(call cc-option, -Wunused-but-set-variable)		\
 	$(call cc-option, -Wunused-const-variable)		\
 	$(call cc-option, -Wpacked-not-aligned)			\
-	$(call cc-option, -Wstringop-truncation)
+	$(call cc-option, -Wstringop-truncation)		\
+	$(call cc-option, -Wmaybe-uninitialized)
 subdir-ccflags-y += $(condflags)
 # The following turn off the warnings enabled by -Wextra
 subdir-ccflags-y += -Wno-missing-field-initializers
@@ -31,7 +32,8 @@ 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 extent-io-tree.o fs.o messages.o bio.o
+	   subpage.o tree-mod-log.o extent-io-tree.o fs.o messages.o bio.o \
+	   lru_cache.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 46851511b661..90e40d5ceccd 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1252,8 +1252,12 @@ static bool lookup_backref_shared_cache(struct btrfs_backref_share_check_ctx *ct
 					struct btrfs_root *root,
 					u64 bytenr, int level, bool *is_shared)
 {
+	const struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_backref_shared_cache_entry *entry;
 
+	if (!current->journal_info)
+		lockdep_assert_held(&fs_info->commit_root_sem);
+
 	if (!ctx->use_path_cache)
 		return false;
 
@@ -1288,7 +1292,7 @@ static bool lookup_backref_shared_cache(struct btrfs_backref_share_check_ctx *ct
 	 * could be a snapshot sharing this extent buffer.
 	 */
 	if (entry->is_shared &&
-	    entry->gen != btrfs_get_last_root_drop_gen(root->fs_info))
+	    entry->gen != btrfs_get_last_root_drop_gen(fs_info))
 		return false;
 
 	*is_shared = entry->is_shared;
@@ -1318,9 +1322,13 @@ static void store_backref_shared_cache(struct btrfs_backref_share_check_ctx *ctx
 				       struct btrfs_root *root,
 				       u64 bytenr, int level, bool is_shared)
 {
+	const struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_backref_shared_cache_entry *entry;
 	u64 gen;
 
+	if (!current->journal_info)
+		lockdep_assert_held(&fs_info->commit_root_sem);
+
 	if (!ctx->use_path_cache)
 		return;
 
@@ -1336,7 +1344,7 @@ static void store_backref_shared_cache(struct btrfs_backref_share_check_ctx *ctx
 	ASSERT(level >= 0);
 
 	if (is_shared)
-		gen = btrfs_get_last_root_drop_gen(root->fs_info);
+		gen = btrfs_get_last_root_drop_gen(fs_info);
 	else
 		gen = btrfs_root_last_snapshot(&root->root_item);
 
@@ -1864,6 +1872,8 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr,
 		.have_delayed_delete_refs = false,
 	};
 	int level;
+	bool leaf_cached;
+	bool leaf_is_shared;
 
 	for (int i = 0; i < BTRFS_BACKREF_CTX_PREV_EXTENTS_SIZE; i++) {
 		if (ctx->prev_extents_cache[i].bytenr == bytenr)
@@ -1885,6 +1895,23 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr,
 		walk_ctx.time_seq = elem.seq;
 	}
 
+	ctx->use_path_cache = true;
+
+	/*
+	 * We may have previously determined that the current leaf is shared.
+	 * If it is, then we have a data extent that is shared due to a shared
+	 * subtree (caused by snapshotting) and we don't need to check for data
+	 * backrefs. If the leaf is not shared, then we must do backref walking
+	 * to determine if the data extent is shared through reflinks.
+	 */
+	leaf_cached = lookup_backref_shared_cache(ctx, root,
+						  ctx->curr_leaf_bytenr, 0,
+						  &leaf_is_shared);
+	if (leaf_cached && leaf_is_shared) {
+		ret = 1;
+		goto out_trans;
+	}
+
 	walk_ctx.ignore_extent_item_pos = true;
 	walk_ctx.trans = trans;
 	walk_ctx.fs_info = fs_info;
@@ -1893,7 +1920,6 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr,
 	/* -1 means we are in the bytenr of the data extent. */
 	level = -1;
 	ULIST_ITER_INIT(&uiter);
-	ctx->use_path_cache = true;
 	while (1) {
 		bool is_shared;
 		bool cached;
@@ -1964,6 +1990,7 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr,
 		ctx->prev_extents_cache_slot = slot;
 	}
 
+out_trans:
 	if (trans) {
 		btrfs_put_tree_mod_seq(fs_info, &elem);
 		btrfs_end_transaction(trans);
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 8affc88b0e0a..d8b90f95b157 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -14,19 +14,31 @@
 #include "dev-replace.h"
 #include "rcu-string.h"
 #include "zoned.h"
+#include "file-item.h"
 
 static struct bio_set btrfs_bioset;
+static struct bio_set btrfs_clone_bioset;
+static struct bio_set btrfs_repair_bioset;
+static mempool_t btrfs_failed_bio_pool;
+
+struct btrfs_failed_bio {
+	struct btrfs_bio *bbio;
+	int num_copies;
+	atomic_t repair_count;
+};
 
 /*
  * Initialize a btrfs_bio structure.  This skips the embedded bio itself as it
  * is already initialized by the block layer.
  */
-static inline void btrfs_bio_init(struct btrfs_bio *bbio,
-				  btrfs_bio_end_io_t end_io, void *private)
+void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_inode *inode,
+		    btrfs_bio_end_io_t end_io, void *private)
 {
 	memset(bbio, 0, offsetof(struct btrfs_bio, bio));
+	bbio->inode = inode;
 	bbio->end_io = end_io;
 	bbio->private = private;
+	atomic_set(&bbio->pending_ios, 1);
 }
 
 /*
@@ -37,32 +49,235 @@ static inline void btrfs_bio_init(struct btrfs_bio *bbio,
  * a mempool.
  */
 struct bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
+			    struct btrfs_inode *inode,
 			    btrfs_bio_end_io_t end_io, void *private)
 {
 	struct bio *bio;
 
 	bio = bio_alloc_bioset(NULL, nr_vecs, opf, GFP_NOFS, &btrfs_bioset);
-	btrfs_bio_init(btrfs_bio(bio), end_io, private);
+	btrfs_bio_init(btrfs_bio(bio), inode, end_io, private);
 	return bio;
 }
 
-struct bio *btrfs_bio_clone_partial(struct bio *orig, u64 offset, u64 size,
-				    btrfs_bio_end_io_t end_io, void *private)
+static struct bio *btrfs_split_bio(struct btrfs_fs_info *fs_info,
+				   struct bio *orig, u64 map_length,
+				   bool use_append)
 {
+	struct btrfs_bio *orig_bbio = btrfs_bio(orig);
 	struct bio *bio;
-	struct btrfs_bio *bbio;
 
-	ASSERT(offset <= UINT_MAX && size <= UINT_MAX);
+	if (use_append) {
+		unsigned int nr_segs;
+
+		bio = bio_split_rw(orig, &fs_info->limits, &nr_segs,
+				   &btrfs_clone_bioset, map_length);
+	} else {
+		bio = bio_split(orig, map_length >> SECTOR_SHIFT, GFP_NOFS,
+				&btrfs_clone_bioset);
+	}
+	btrfs_bio_init(btrfs_bio(bio), orig_bbio->inode, NULL, orig_bbio);
 
-	bio = bio_alloc_clone(orig->bi_bdev, orig, GFP_NOFS, &btrfs_bioset);
-	bbio = btrfs_bio(bio);
-	btrfs_bio_init(bbio, end_io, private);
+	btrfs_bio(bio)->file_offset = orig_bbio->file_offset;
+	if (!(orig->bi_opf & REQ_BTRFS_ONE_ORDERED))
+		orig_bbio->file_offset += map_length;
 
-	bio_trim(bio, offset >> 9, size >> 9);
-	bbio->iter = bio->bi_iter;
+	atomic_inc(&orig_bbio->pending_ios);
 	return bio;
 }
 
+static void btrfs_orig_write_end_io(struct bio *bio);
+
+static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio,
+				       struct btrfs_bio *orig_bbio)
+{
+	/*
+	 * For writes we tolerate nr_mirrors - 1 write failures, so we can't
+	 * just blindly propagate a write failure here.  Instead increment the
+	 * error count in the original I/O context so that it is guaranteed to
+	 * be larger than the error tolerance.
+	 */
+	if (bbio->bio.bi_end_io == &btrfs_orig_write_end_io) {
+		struct btrfs_io_stripe *orig_stripe = orig_bbio->bio.bi_private;
+		struct btrfs_io_context *orig_bioc = orig_stripe->bioc;
+
+		atomic_add(orig_bioc->max_errors, &orig_bioc->error);
+	} else {
+		orig_bbio->bio.bi_status = bbio->bio.bi_status;
+	}
+}
+
+static void btrfs_orig_bbio_end_io(struct btrfs_bio *bbio)
+{
+	if (bbio->bio.bi_pool == &btrfs_clone_bioset) {
+		struct btrfs_bio *orig_bbio = bbio->private;
+
+		if (bbio->bio.bi_status)
+			btrfs_bbio_propagate_error(bbio, orig_bbio);
+		bio_put(&bbio->bio);
+		bbio = orig_bbio;
+	}
+
+	if (atomic_dec_and_test(&bbio->pending_ios))
+		bbio->end_io(bbio);
+}
+
+static int next_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror)
+{
+	if (cur_mirror == fbio->num_copies)
+		return cur_mirror + 1 - fbio->num_copies;
+	return cur_mirror + 1;
+}
+
+static int prev_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror)
+{
+	if (cur_mirror == 1)
+		return fbio->num_copies;
+	return cur_mirror - 1;
+}
+
+static void btrfs_repair_done(struct btrfs_failed_bio *fbio)
+{
+	if (atomic_dec_and_test(&fbio->repair_count)) {
+		btrfs_orig_bbio_end_io(fbio->bbio);
+		mempool_free(fbio, &btrfs_failed_bio_pool);
+	}
+}
+
+static void btrfs_end_repair_bio(struct btrfs_bio *repair_bbio,
+				 struct btrfs_device *dev)
+{
+	struct btrfs_failed_bio *fbio = repair_bbio->private;
+	struct btrfs_inode *inode = repair_bbio->inode;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	struct bio_vec *bv = bio_first_bvec_all(&repair_bbio->bio);
+	int mirror = repair_bbio->mirror_num;
+
+	if (repair_bbio->bio.bi_status ||
+	    !btrfs_data_csum_ok(repair_bbio, dev, 0, bv)) {
+		bio_reset(&repair_bbio->bio, NULL, REQ_OP_READ);
+		repair_bbio->bio.bi_iter = repair_bbio->saved_iter;
+
+		mirror = next_repair_mirror(fbio, mirror);
+		if (mirror == fbio->bbio->mirror_num) {
+			btrfs_debug(fs_info, "no mirror left");
+			fbio->bbio->bio.bi_status = BLK_STS_IOERR;
+			goto done;
+		}
+
+		btrfs_submit_bio(&repair_bbio->bio, mirror);
+		return;
+	}
+
+	do {
+		mirror = prev_repair_mirror(fbio, mirror);
+		btrfs_repair_io_failure(fs_info, btrfs_ino(inode),
+				  repair_bbio->file_offset, fs_info->sectorsize,
+				  repair_bbio->saved_iter.bi_sector << SECTOR_SHIFT,
+				  bv->bv_page, bv->bv_offset, mirror);
+	} while (mirror != fbio->bbio->mirror_num);
+
+done:
+	btrfs_repair_done(fbio);
+	bio_put(&repair_bbio->bio);
+}
+
+/*
+ * Try to kick off a repair read to the next available mirror for a bad sector.
+ *
+ * This primarily tries to recover good data to serve the actual read request,
+ * but also tries to write the good data back to the bad mirror(s) when a
+ * read succeeded to restore the redundancy.
+ */
+static struct btrfs_failed_bio *repair_one_sector(struct btrfs_bio *failed_bbio,
+						  u32 bio_offset,
+						  struct bio_vec *bv,
+						  struct btrfs_failed_bio *fbio)
+{
+	struct btrfs_inode *inode = failed_bbio->inode;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	const u32 sectorsize = fs_info->sectorsize;
+	const u64 logical = (failed_bbio->saved_iter.bi_sector << SECTOR_SHIFT);
+	struct btrfs_bio *repair_bbio;
+	struct bio *repair_bio;
+	int num_copies;
+	int mirror;
+
+	btrfs_debug(fs_info, "repair read error: read error at %llu",
+		    failed_bbio->file_offset + bio_offset);
+
+	num_copies = btrfs_num_copies(fs_info, logical, sectorsize);
+	if (num_copies == 1) {
+		btrfs_debug(fs_info, "no copy to repair from");
+		failed_bbio->bio.bi_status = BLK_STS_IOERR;
+		return fbio;
+	}
+
+	if (!fbio) {
+		fbio = mempool_alloc(&btrfs_failed_bio_pool, GFP_NOFS);
+		fbio->bbio = failed_bbio;
+		fbio->num_copies = num_copies;
+		atomic_set(&fbio->repair_count, 1);
+	}
+
+	atomic_inc(&fbio->repair_count);
+
+	repair_bio = bio_alloc_bioset(NULL, 1, REQ_OP_READ, GFP_NOFS,
+				      &btrfs_repair_bioset);
+	repair_bio->bi_iter.bi_sector = failed_bbio->saved_iter.bi_sector;
+	bio_add_page(repair_bio, bv->bv_page, bv->bv_len, bv->bv_offset);
+
+	repair_bbio = btrfs_bio(repair_bio);
+	btrfs_bio_init(repair_bbio, failed_bbio->inode, NULL, fbio);
+	repair_bbio->file_offset = failed_bbio->file_offset + bio_offset;
+
+	mirror = next_repair_mirror(fbio, failed_bbio->mirror_num);
+	btrfs_debug(fs_info, "submitting repair read to mirror %d", mirror);
+	btrfs_submit_bio(repair_bio, mirror);
+	return fbio;
+}
+
+static void btrfs_check_read_bio(struct btrfs_bio *bbio, struct btrfs_device *dev)
+{
+	struct btrfs_inode *inode = bbio->inode;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	u32 sectorsize = fs_info->sectorsize;
+	struct bvec_iter *iter = &bbio->saved_iter;
+	blk_status_t status = bbio->bio.bi_status;
+	struct btrfs_failed_bio *fbio = NULL;
+	u32 offset = 0;
+
+	/*
+	 * Hand off repair bios to the repair code as there is no upper level
+	 * submitter for them.
+	 */
+	if (bbio->bio.bi_pool == &btrfs_repair_bioset) {
+		btrfs_end_repair_bio(bbio, dev);
+		return;
+	}
+
+	/* Clear the I/O error. A failed repair will reset it. */
+	bbio->bio.bi_status = BLK_STS_OK;
+
+	while (iter->bi_size) {
+		struct bio_vec bv = bio_iter_iovec(&bbio->bio, *iter);
+
+		bv.bv_len = min(bv.bv_len, sectorsize);
+		if (status || !btrfs_data_csum_ok(bbio, dev, offset, &bv))
+			fbio = repair_one_sector(bbio, offset, &bv, fbio);
+
+		bio_advance_iter_single(&bbio->bio, iter, sectorsize);
+		offset += sectorsize;
+	}
+
+	if (bbio->csum != bbio->csum_inline)
+		kfree(bbio->csum);
+
+	if (fbio)
+		btrfs_repair_done(fbio);
+	else
+		btrfs_orig_bbio_end_io(bbio);
+}
+
 static void btrfs_log_dev_io_error(struct bio *bio, struct btrfs_device *dev)
 {
 	if (!dev || !dev->bdev)
@@ -90,24 +305,31 @@ static void btrfs_end_bio_work(struct work_struct *work)
 {
 	struct btrfs_bio *bbio = container_of(work, struct btrfs_bio, end_io_work);
 
-	bbio->end_io(bbio);
+	/* Metadata reads are checked and repaired by the submitter. */
+	if (bbio->bio.bi_opf & REQ_META)
+		bbio->end_io(bbio);
+	else
+		btrfs_check_read_bio(bbio, bbio->bio.bi_private);
 }
 
 static void btrfs_simple_end_io(struct bio *bio)
 {
-	struct btrfs_fs_info *fs_info = bio->bi_private;
 	struct btrfs_bio *bbio = btrfs_bio(bio);
+	struct btrfs_device *dev = bio->bi_private;
+	struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info;
 
 	btrfs_bio_counter_dec(fs_info);
 
 	if (bio->bi_status)
-		btrfs_log_dev_io_error(bio, bbio->device);
+		btrfs_log_dev_io_error(bio, dev);
 
 	if (bio_op(bio) == REQ_OP_READ) {
 		INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work);
 		queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work);
 	} else {
-		bbio->end_io(bbio);
+		if (bio_op(bio) == REQ_OP_ZONE_APPEND)
+			btrfs_record_physical_zoned(bbio);
+		btrfs_orig_bbio_end_io(bbio);
 	}
 }
 
@@ -118,7 +340,10 @@ static void btrfs_raid56_end_io(struct bio *bio)
 
 	btrfs_bio_counter_dec(bioc->fs_info);
 	bbio->mirror_num = bioc->mirror_num;
-	bbio->end_io(bbio);
+	if (bio_op(bio) == REQ_OP_READ && !(bbio->bio.bi_opf & REQ_META))
+		btrfs_check_read_bio(bbio, NULL);
+	else
+		btrfs_orig_bbio_end_io(bbio);
 
 	btrfs_put_bioc(bioc);
 }
@@ -145,7 +370,7 @@ static void btrfs_orig_write_end_io(struct bio *bio)
 	else
 		bio->bi_status = BLK_STS_OK;
 
-	bbio->end_io(bbio);
+	btrfs_orig_bbio_end_io(bbio);
 	btrfs_put_bioc(bioc);
 }
 
@@ -181,16 +406,10 @@ static void btrfs_submit_dev_bio(struct btrfs_device *dev, struct bio *bio)
 	 */
 	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
 		u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
+		u64 zone_start = round_down(physical, dev->fs_info->zone_size);
 
-		if (btrfs_dev_is_sequential(dev, physical)) {
-			u64 zone_start = round_down(physical,
-						    dev->fs_info->zone_size);
-
-			bio->bi_iter.bi_sector = zone_start >> SECTOR_SHIFT;
-		} else {
-			bio->bi_opf &= ~REQ_OP_ZONE_APPEND;
-			bio->bi_opf |= REQ_OP_WRITE;
-		}
+		ASSERT(btrfs_dev_is_sequential(dev, physical));
+		bio->bi_iter.bi_sector = zone_start >> SECTOR_SHIFT;
 	}
 	btrfs_debug_in_rcu(dev->fs_info,
 	"%s: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
@@ -224,41 +443,21 @@ static void btrfs_submit_mirrored_bio(struct btrfs_io_context *bioc, int dev_nr)
 	btrfs_submit_dev_bio(bioc->stripes[dev_nr].dev, bio);
 }
 
-void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror_num)
+static void __btrfs_submit_bio(struct bio *bio, struct btrfs_io_context *bioc,
+			       struct btrfs_io_stripe *smap, int mirror_num)
 {
-	u64 logical = bio->bi_iter.bi_sector << 9;
-	u64 length = bio->bi_iter.bi_size;
-	u64 map_length = length;
-	struct btrfs_io_context *bioc = NULL;
-	struct btrfs_io_stripe smap;
-	int ret;
-
-	btrfs_bio_counter_inc_blocked(fs_info);
-	ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length,
-				&bioc, &smap, &mirror_num, 1);
-	if (ret) {
-		btrfs_bio_counter_dec(fs_info);
-		btrfs_bio_end_io(btrfs_bio(bio), errno_to_blk_status(ret));
-		return;
-	}
-
-	if (map_length < length) {
-		btrfs_crit(fs_info,
-			   "mapping failed logical %llu bio len %llu len %llu",
-			   logical, length, map_length);
-		BUG();
-	}
+	/* Do not leak our private flag into the block layer. */
+	bio->bi_opf &= ~REQ_BTRFS_ONE_ORDERED;
 
 	if (!bioc) {
-		/* Single mirror read/write fast path */
+		/* Single mirror read/write fast path. */
 		btrfs_bio(bio)->mirror_num = mirror_num;
-		btrfs_bio(bio)->device = smap.dev;
-		bio->bi_iter.bi_sector = smap.physical >> SECTOR_SHIFT;
-		bio->bi_private = fs_info;
+		bio->bi_iter.bi_sector = smap->physical >> SECTOR_SHIFT;
+		bio->bi_private = smap->dev;
 		bio->bi_end_io = btrfs_simple_end_io;
-		btrfs_submit_dev_bio(smap.dev, bio);
+		btrfs_submit_dev_bio(smap->dev, bio);
 	} else if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
-		/* Parity RAID write or read recovery */
+		/* Parity RAID write or read recovery. */
 		bio->bi_private = bioc;
 		bio->bi_end_io = btrfs_raid56_end_io;
 		if (bio_op(bio) == REQ_OP_READ)
@@ -266,16 +465,233 @@ void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror
 		else
 			raid56_parity_write(bio, bioc);
 	} else {
-		/* Write to multiple mirrors */
+		/* Write to multiple mirrors. */
 		int total_devs = bioc->num_stripes;
-		int dev_nr;
 
 		bioc->orig_bio = bio;
-		for (dev_nr = 0; dev_nr < total_devs; dev_nr++)
+		for (int dev_nr = 0; dev_nr < total_devs; dev_nr++)
 			btrfs_submit_mirrored_bio(bioc, dev_nr);
 	}
 }
 
+static blk_status_t btrfs_bio_csum(struct btrfs_bio *bbio)
+{
+	if (bbio->bio.bi_opf & REQ_META)
+		return btree_csum_one_bio(bbio);
+	return btrfs_csum_one_bio(bbio);
+}
+
+/*
+ * Async submit bios are used to offload expensive checksumming onto the worker
+ * threads.
+ */
+struct async_submit_bio {
+	struct btrfs_bio *bbio;
+	struct btrfs_io_context *bioc;
+	struct btrfs_io_stripe smap;
+	int mirror_num;
+	struct btrfs_work work;
+};
+
+/*
+ * In order to insert checksums into the metadata in large chunks, we wait
+ * until bio submission time.   All the pages in the bio are checksummed and
+ * sums are attached onto the ordered extent record.
+ *
+ * At IO completion time the csums attached on the ordered extent record are
+ * inserted into the btree.
+ */
+static void run_one_async_start(struct btrfs_work *work)
+{
+	struct async_submit_bio *async =
+		container_of(work, struct async_submit_bio, work);
+	blk_status_t ret;
+
+	ret = btrfs_bio_csum(async->bbio);
+	if (ret)
+		async->bbio->bio.bi_status = ret;
+}
+
+/*
+ * In order to insert checksums into the metadata in large chunks, we wait
+ * until bio submission time.   All the pages in the bio are checksummed and
+ * sums are attached onto the ordered extent record.
+ *
+ * At IO completion time the csums attached on the ordered extent record are
+ * inserted into the tree.
+ */
+static void run_one_async_done(struct btrfs_work *work)
+{
+	struct async_submit_bio *async =
+		container_of(work, struct async_submit_bio, work);
+	struct bio *bio = &async->bbio->bio;
+
+	/* If an error occurred we just want to clean up the bio and move on. */
+	if (bio->bi_status) {
+		btrfs_orig_bbio_end_io(async->bbio);
+		return;
+	}
+
+	/*
+	 * All of the bios that pass through here are from async helpers.
+	 * Use REQ_CGROUP_PUNT to issue them from the owning cgroup's context.
+	 * This changes nothing when cgroups aren't in use.
+	 */
+	bio->bi_opf |= REQ_CGROUP_PUNT;
+	__btrfs_submit_bio(bio, async->bioc, &async->smap, async->mirror_num);
+}
+
+static void run_one_async_free(struct btrfs_work *work)
+{
+	kfree(container_of(work, struct async_submit_bio, work));
+}
+
+static bool should_async_write(struct btrfs_bio *bbio)
+{
+	/*
+	 * If the I/O is not issued by fsync and friends, (->sync_writers != 0),
+	 * then try to defer the submission to a workqueue to parallelize the
+	 * checksum calculation.
+	 */
+	if (atomic_read(&bbio->inode->sync_writers))
+		return false;
+
+	/*
+	 * Submit metadata writes synchronously if the checksum implementation
+	 * is fast, or we are on a zoned device that wants I/O to be submitted
+	 * in order.
+	 */
+	if (bbio->bio.bi_opf & REQ_META) {
+		struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info;
+
+		if (btrfs_is_zoned(fs_info))
+			return false;
+		if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags))
+			return false;
+	}
+
+	return true;
+}
+
+/*
+ * Submit bio to an async queue.
+ *
+ * Return true if the work has been succesfuly submitted, else false.
+ */
+static bool btrfs_wq_submit_bio(struct btrfs_bio *bbio,
+				struct btrfs_io_context *bioc,
+				struct btrfs_io_stripe *smap, int mirror_num)
+{
+	struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info;
+	struct async_submit_bio *async;
+
+	async = kmalloc(sizeof(*async), GFP_NOFS);
+	if (!async)
+		return false;
+
+	async->bbio = bbio;
+	async->bioc = bioc;
+	async->smap = *smap;
+	async->mirror_num = mirror_num;
+
+	btrfs_init_work(&async->work, run_one_async_start, run_one_async_done,
+			run_one_async_free);
+	if (op_is_sync(bbio->bio.bi_opf))
+		btrfs_queue_work(fs_info->hipri_workers, &async->work);
+	else
+		btrfs_queue_work(fs_info->workers, &async->work);
+	return true;
+}
+
+static bool btrfs_submit_chunk(struct bio *bio, int mirror_num)
+{
+	struct btrfs_bio *bbio = btrfs_bio(bio);
+	struct btrfs_inode *inode = bbio->inode;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	struct btrfs_bio *orig_bbio = bbio;
+	u64 logical = bio->bi_iter.bi_sector << 9;
+	u64 length = bio->bi_iter.bi_size;
+	u64 map_length = length;
+	bool use_append = btrfs_use_zone_append(bbio);
+	struct btrfs_io_context *bioc = NULL;
+	struct btrfs_io_stripe smap;
+	blk_status_t ret;
+	int error;
+
+	btrfs_bio_counter_inc_blocked(fs_info);
+	error = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length,
+				  &bioc, &smap, &mirror_num, 1);
+	if (error) {
+		ret = errno_to_blk_status(error);
+		goto fail;
+	}
+
+	map_length = min(map_length, length);
+	if (use_append)
+		map_length = min(map_length, fs_info->max_zone_append_size);
+
+	if (map_length < length) {
+		bio = btrfs_split_bio(fs_info, bio, map_length, use_append);
+		bbio = btrfs_bio(bio);
+	}
+
+	/*
+	 * Save the iter for the end_io handler and preload the checksums for
+	 * data reads.
+	 */
+	if (bio_op(bio) == REQ_OP_READ && !(bio->bi_opf & REQ_META)) {
+		bbio->saved_iter = bio->bi_iter;
+		ret = btrfs_lookup_bio_sums(bbio);
+		if (ret)
+			goto fail_put_bio;
+	}
+
+	if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
+		if (use_append) {
+			bio->bi_opf &= ~REQ_OP_WRITE;
+			bio->bi_opf |= REQ_OP_ZONE_APPEND;
+			ret = btrfs_extract_ordered_extent(btrfs_bio(bio));
+			if (ret)
+				goto fail_put_bio;
+		}
+
+		/*
+		 * Csum items for reloc roots have already been cloned at this
+		 * point, so they are handled as part of the no-checksum case.
+		 */
+		if (!(inode->flags & BTRFS_INODE_NODATASUM) &&
+		    !test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state) &&
+		    !btrfs_is_data_reloc_root(inode->root)) {
+			if (should_async_write(bbio) &&
+			    btrfs_wq_submit_bio(bbio, bioc, &smap, mirror_num))
+				goto done;
+
+			ret = btrfs_bio_csum(bbio);
+			if (ret)
+				goto fail_put_bio;
+		}
+	}
+
+	__btrfs_submit_bio(bio, bioc, &smap, mirror_num);
+done:
+	return map_length == length;
+
+fail_put_bio:
+	if (map_length < length)
+		bio_put(bio);
+fail:
+	btrfs_bio_counter_dec(fs_info);
+	btrfs_bio_end_io(orig_bbio, ret);
+	/* Do not submit another chunk */
+	return true;
+}
+
+void btrfs_submit_bio(struct bio *bio, int mirror_num)
+{
+	while (!btrfs_submit_chunk(bio, mirror_num))
+		;
+}
+
 /*
  * Submit a repair write.
  *
@@ -283,7 +699,7 @@ void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror
  * RAID setup.  Here we only want to write the one bad copy, so we do the
  * mapping ourselves and submit the bio directly.
  *
- * The I/O is issued sychronously to block the repair read completion from
+ * The I/O is issued synchronously to block the repair read completion from
  * freeing the bio.
  */
 int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
@@ -381,10 +797,31 @@ int __init btrfs_bioset_init(void)
 			offsetof(struct btrfs_bio, bio),
 			BIOSET_NEED_BVECS))
 		return -ENOMEM;
+	if (bioset_init(&btrfs_clone_bioset, BIO_POOL_SIZE,
+			offsetof(struct btrfs_bio, bio), 0))
+		goto out_free_bioset;
+	if (bioset_init(&btrfs_repair_bioset, BIO_POOL_SIZE,
+			offsetof(struct btrfs_bio, bio),
+			BIOSET_NEED_BVECS))
+		goto out_free_clone_bioset;
+	if (mempool_init_kmalloc_pool(&btrfs_failed_bio_pool, BIO_POOL_SIZE,
+				      sizeof(struct btrfs_failed_bio)))
+		goto out_free_repair_bioset;
 	return 0;
+
+out_free_repair_bioset:
+	bioset_exit(&btrfs_repair_bioset);
+out_free_clone_bioset:
+	bioset_exit(&btrfs_clone_bioset);
+out_free_bioset:
+	bioset_exit(&btrfs_bioset);
+	return -ENOMEM;
 }
 
 void __cold btrfs_bioset_exit(void)
 {
+	mempool_exit(&btrfs_failed_bio_pool);
+	bioset_exit(&btrfs_repair_bioset);
+	bioset_exit(&btrfs_clone_bioset);
 	bioset_exit(&btrfs_bioset);
 }
diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h
index b12f84b3b341..873ff85817f0 100644
--- a/fs/btrfs/bio.h
+++ b/fs/btrfs/bio.h
@@ -26,32 +26,23 @@ struct btrfs_fs_info;
 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.
+ * Highlevel btrfs I/O structure.  It is allocated by btrfs_bio_alloc and
+ * passed to btrfs_submit_bio for mapping to the physical devices.
  */
 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 */
+	/* Inode and offset into it that this I/O operates on. */
+	struct btrfs_inode *inode;
 	u64 file_offset;
 
-	/* @device is for stripe IO submission. */
-	struct btrfs_device *device;
 	union {
-		/* For data checksum verification. */
+		/*
+		 * Data checksumming and original I/O information for internal
+		 * use in the btrfs_submit_bio machinery.
+		 */
 		struct {
 			u8 *csum;
 			u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
+			struct bvec_iter saved_iter;
 		};
 
 		/* For metadata parentness verification. */
@@ -62,7 +53,9 @@ struct btrfs_bio {
 	btrfs_bio_end_io_t end_io;
 	void *private;
 
-	/* For read end I/O handling */
+	/* For internal use in read end I/O handling */
+	unsigned int mirror_num;
+	atomic_t pending_ios;
 	struct work_struct end_io_work;
 
 	/*
@@ -80,11 +73,11 @@ static inline struct btrfs_bio *btrfs_bio(struct bio *bio)
 int __init btrfs_bioset_init(void);
 void __cold btrfs_bioset_exit(void);
 
+void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_inode *inode,
+		    btrfs_bio_end_io_t end_io, void *private);
 struct bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
+			    struct btrfs_inode *inode,
 			    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)
 {
@@ -92,34 +85,10 @@ static inline void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t 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;
-	}
-}
+/* Bio only refers to one ordered extent. */
+#define REQ_BTRFS_ONE_ORDERED			REQ_DRV
 
-/*
- * 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);
+void btrfs_submit_bio(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);
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 708d843daa72..5b10401d803b 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#include <linux/sizes.h>
 #include <linux/list_sort.h>
 #include "misc.h"
 #include "ctree.h"
@@ -539,6 +540,153 @@ u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end
 	return total_added;
 }
 
+/*
+ * Get an arbitrary extent item index / max_index through the block group
+ *
+ * @block_group   the block group to sample from
+ * @index:        the integral step through the block group to grab from
+ * @max_index:    the granularity of the sampling
+ * @key:          return value parameter for the item we find
+ *
+ * Pre-conditions on indices:
+ * 0 <= index <= max_index
+ * 0 < max_index
+ *
+ * Returns: 0 on success, 1 if the search didn't yield a useful item, negative
+ * error code on error.
+ */
+static int sample_block_group_extent_item(struct btrfs_caching_control *caching_ctl,
+					  struct btrfs_block_group *block_group,
+					  int index, int max_index,
+					  struct btrfs_key *key)
+{
+	struct btrfs_fs_info *fs_info = block_group->fs_info;
+	struct btrfs_root *extent_root;
+	int ret = 0;
+	u64 search_offset;
+	u64 search_end = block_group->start + block_group->length;
+	struct btrfs_path *path;
+
+	ASSERT(index >= 0);
+	ASSERT(index <= max_index);
+	ASSERT(max_index > 0);
+	lockdep_assert_held(&caching_ctl->mutex);
+	lockdep_assert_held_read(&fs_info->commit_root_sem);
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	extent_root = btrfs_extent_root(fs_info, max_t(u64, block_group->start,
+						       BTRFS_SUPER_INFO_OFFSET));
+
+	path->skip_locking = 1;
+	path->search_commit_root = 1;
+	path->reada = READA_FORWARD;
+
+	search_offset = index * div_u64(block_group->length, max_index);
+	key->objectid = block_group->start + search_offset;
+	key->type = BTRFS_EXTENT_ITEM_KEY;
+	key->offset = 0;
+
+	while (1) {
+		ret = btrfs_search_forward(extent_root, key, path, 0);
+		if (ret != 0)
+			goto out;
+		/* Success; sampled an extent item in the block group */
+		if (key->type == BTRFS_EXTENT_ITEM_KEY &&
+		    key->objectid >= block_group->start &&
+		    key->objectid + key->offset <= search_end)
+			goto out;
+
+		/* We can't possibly find a valid extent item anymore */
+		if (key->objectid >= search_end) {
+			ret = 1;
+			break;
+		}
+		if (key->type < BTRFS_EXTENT_ITEM_KEY)
+			key->type = BTRFS_EXTENT_ITEM_KEY;
+		else
+			key->objectid++;
+		btrfs_release_path(path);
+		up_read(&fs_info->commit_root_sem);
+		mutex_unlock(&caching_ctl->mutex);
+		cond_resched();
+		mutex_lock(&caching_ctl->mutex);
+		down_read(&fs_info->commit_root_sem);
+	}
+out:
+	lockdep_assert_held(&caching_ctl->mutex);
+	lockdep_assert_held_read(&fs_info->commit_root_sem);
+	btrfs_free_path(path);
+	return ret;
+}
+
+/*
+ * Best effort attempt to compute a block group's size class while caching it.
+ *
+ * @block_group: the block group we are caching
+ *
+ * We cannot infer the size class while adding free space extents, because that
+ * logic doesn't care about contiguous file extents (it doesn't differentiate
+ * between a 100M extent and 100 contiguous 1M extents). So we need to read the
+ * file extent items. Reading all of them is quite wasteful, because usually
+ * only a handful are enough to give a good answer. Therefore, we just grab 5 of
+ * them at even steps through the block group and pick the smallest size class
+ * we see. Since size class is best effort, and not guaranteed in general,
+ * inaccuracy is acceptable.
+ *
+ * To be more explicit about why this algorithm makes sense:
+ *
+ * If we are caching in a block group from disk, then there are three major cases
+ * to consider:
+ * 1. the block group is well behaved and all extents in it are the same size
+ *    class.
+ * 2. the block group is mostly one size class with rare exceptions for last
+ *    ditch allocations
+ * 3. the block group was populated before size classes and can have a totally
+ *    arbitrary mix of size classes.
+ *
+ * In case 1, looking at any extent in the block group will yield the correct
+ * result. For the mixed cases, taking the minimum size class seems like a good
+ * approximation, since gaps from frees will be usable to the size class. For
+ * 2., a small handful of file extents is likely to yield the right answer. For
+ * 3, we can either read every file extent, or admit that this is best effort
+ * anyway and try to stay fast.
+ *
+ * Returns: 0 on success, negative error code on error.
+ */
+static int load_block_group_size_class(struct btrfs_caching_control *caching_ctl,
+				       struct btrfs_block_group *block_group)
+{
+	struct btrfs_key key;
+	int i;
+	u64 min_size = block_group->length;
+	enum btrfs_block_group_size_class size_class = BTRFS_BG_SZ_NONE;
+	int ret;
+
+	if (!btrfs_block_group_should_use_size_class(block_group))
+		return 0;
+
+	for (i = 0; i < 5; ++i) {
+		ret = sample_block_group_extent_item(caching_ctl, block_group, i, 5, &key);
+		if (ret < 0)
+			goto out;
+		if (ret > 0)
+			continue;
+		min_size = min_t(u64, min_size, key.offset);
+		size_class = btrfs_calc_block_group_size_class(min_size);
+	}
+	if (size_class != BTRFS_BG_SZ_NONE) {
+		spin_lock(&block_group->lock);
+		block_group->size_class = size_class;
+		spin_unlock(&block_group->lock);
+	}
+
+out:
+	return ret;
+}
+
 static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
 {
 	struct btrfs_block_group *block_group = caching_ctl->block_group;
@@ -683,6 +831,7 @@ static noinline void caching_thread(struct btrfs_work *work)
 	mutex_lock(&caching_ctl->mutex);
 	down_read(&fs_info->commit_root_sem);
 
+	load_block_group_size_class(caching_ctl, block_group);
 	if (btrfs_test_opt(fs_info, SPACE_CACHE)) {
 		ret = load_free_space_cache(block_group);
 		if (ret == 1) {
@@ -1816,7 +1965,6 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
  *
  * @fs_info:       the filesystem
  * @chunk_start:   logical address of block group
- * @bdev:	   physical device to resolve, can be NULL to indicate any device
  * @physical:	   physical address to map to logical addresses
  * @logical:	   return array of logical addresses which map to @physical
  * @naddrs:	   length of @logical
@@ -1827,8 +1975,7 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
  * block copies.
  */
 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)
+		     u64 physical, u64 **logical, int *naddrs, int *stripe_len)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
@@ -1868,9 +2015,6 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 			      data_stripe_length))
 			continue;
 
-		if (bdev && map->stripes[i].dev->bdev != bdev)
-			continue;
-
 		stripe_nr = physical - map->stripes[i].physical;
 		stripe_nr = div64_u64_rem(stripe_nr, map->stripe_len, &offset);
 
@@ -1927,7 +2071,7 @@ static int exclude_super_stripes(struct btrfs_block_group *cache)
 
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
 		bytenr = btrfs_sb_offset(i);
-		ret = btrfs_rmap_block(fs_info, cache->start, NULL,
+		ret = btrfs_rmap_block(fs_info, cache->start,
 				       bytenr, &logical, &nr, &stripe_len);
 		if (ret)
 			return ret;
@@ -3330,7 +3474,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 	spin_unlock(&info->delalloc_root_lock);
 
 	while (total) {
-		bool reclaim;
+		bool reclaim = false;
 
 		cache = btrfs_lookup_block_group(info, bytenr);
 		if (!cache) {
@@ -3379,6 +3523,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 			cache->space_info->disk_used -= num_bytes * factor;
 
 			reclaim = should_reclaim_block_group(cache, num_bytes);
+
 			spin_unlock(&cache->lock);
 			spin_unlock(&cache->space_info->lock);
 
@@ -3433,32 +3578,42 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
  * reservation and return -EAGAIN, otherwise this function always succeeds.
  */
 int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
-			     u64 ram_bytes, u64 num_bytes, int delalloc)
+			     u64 ram_bytes, u64 num_bytes, int delalloc,
+			     bool force_wrong_size_class)
 {
 	struct btrfs_space_info *space_info = cache->space_info;
+	enum btrfs_block_group_size_class size_class;
 	int ret = 0;
 
 	spin_lock(&space_info->lock);
 	spin_lock(&cache->lock);
 	if (cache->ro) {
 		ret = -EAGAIN;
-	} else {
-		cache->reserved += num_bytes;
-		space_info->bytes_reserved += num_bytes;
-		trace_btrfs_space_reservation(cache->fs_info, "space_info",
-					      space_info->flags, num_bytes, 1);
-		btrfs_space_info_update_bytes_may_use(cache->fs_info,
-						      space_info, -ram_bytes);
-		if (delalloc)
-			cache->delalloc_bytes += num_bytes;
+		goto out;
+	}
 
-		/*
-		 * Compression can use less space than we reserved, so wake
-		 * tickets if that happens
-		 */
-		if (num_bytes < ram_bytes)
-			btrfs_try_granting_tickets(cache->fs_info, space_info);
+	if (btrfs_block_group_should_use_size_class(cache)) {
+		size_class = btrfs_calc_block_group_size_class(num_bytes);
+		ret = btrfs_use_block_group_size_class(cache, size_class, force_wrong_size_class);
+		if (ret)
+			goto out;
 	}
+	cache->reserved += num_bytes;
+	space_info->bytes_reserved += num_bytes;
+	trace_btrfs_space_reservation(cache->fs_info, "space_info",
+				      space_info->flags, num_bytes, 1);
+	btrfs_space_info_update_bytes_may_use(cache->fs_info,
+					      space_info, -ram_bytes);
+	if (delalloc)
+		cache->delalloc_bytes += num_bytes;
+
+	/*
+	 * Compression can use less space than we reserved, so wake tickets if
+	 * that happens.
+	 */
+	if (num_bytes < ram_bytes)
+		btrfs_try_granting_tickets(cache->fs_info, space_info);
+out:
 	spin_unlock(&cache->lock);
 	spin_unlock(&space_info->lock);
 	return ret;
@@ -4218,3 +4373,73 @@ void btrfs_dec_block_group_swap_extents(struct btrfs_block_group *bg, int amount
 	bg->swap_extents -= amount;
 	spin_unlock(&bg->lock);
 }
+
+enum btrfs_block_group_size_class btrfs_calc_block_group_size_class(u64 size)
+{
+	if (size <= SZ_128K)
+		return BTRFS_BG_SZ_SMALL;
+	if (size <= SZ_8M)
+		return BTRFS_BG_SZ_MEDIUM;
+	return BTRFS_BG_SZ_LARGE;
+}
+
+/*
+ * Handle a block group allocating an extent in a size class
+ *
+ * @bg:				The block group we allocated in.
+ * @size_class:			The size class of the allocation.
+ * @force_wrong_size_class:	Whether we are desperate enough to allow
+ *				mismatched size classes.
+ *
+ * Returns: 0 if the size class was valid for this block_group, -EAGAIN in the
+ * case of a race that leads to the wrong size class without
+ * force_wrong_size_class set.
+ *
+ * find_free_extent will skip block groups with a mismatched size class until
+ * it really needs to avoid ENOSPC. In that case it will set
+ * force_wrong_size_class. However, if a block group is newly allocated and
+ * doesn't yet have a size class, then it is possible for two allocations of
+ * different sizes to race and both try to use it. The loser is caught here and
+ * has to retry.
+ */
+int btrfs_use_block_group_size_class(struct btrfs_block_group *bg,
+				     enum btrfs_block_group_size_class size_class,
+				     bool force_wrong_size_class)
+{
+	ASSERT(size_class != BTRFS_BG_SZ_NONE);
+
+	/* The new allocation is in the right size class, do nothing */
+	if (bg->size_class == size_class)
+		return 0;
+	/*
+	 * The new allocation is in a mismatched size class.
+	 * This means one of two things:
+	 *
+	 * 1. Two tasks in find_free_extent for different size_classes raced
+	 *    and hit the same empty block_group. Make the loser try again.
+	 * 2. A call to find_free_extent got desperate enough to set
+	 *    'force_wrong_slab'. Don't change the size_class, but allow the
+	 *    allocation.
+	 */
+	if (bg->size_class != BTRFS_BG_SZ_NONE) {
+		if (force_wrong_size_class)
+			return 0;
+		return -EAGAIN;
+	}
+	/*
+	 * The happy new block group case: the new allocation is the first
+	 * one in the block_group so we set size_class.
+	 */
+	bg->size_class = size_class;
+
+	return 0;
+}
+
+bool btrfs_block_group_should_use_size_class(struct btrfs_block_group *bg)
+{
+	if (btrfs_is_zoned(bg->fs_info))
+		return false;
+	if (!btrfs_is_block_group_data_only(bg))
+		return false;
+	return true;
+}
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index a02ea76fd6cf..6e4a0b429ac3 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -12,6 +12,17 @@ enum btrfs_disk_cache_state {
 	BTRFS_DC_SETUP,
 };
 
+enum btrfs_block_group_size_class {
+	/* Unset */
+	BTRFS_BG_SZ_NONE,
+	/* 0 < size <= 128K */
+	BTRFS_BG_SZ_SMALL,
+	/* 128K < size <= 8M */
+	BTRFS_BG_SZ_MEDIUM,
+	/* 8M < size < BG_LENGTH */
+	BTRFS_BG_SZ_LARGE,
+};
+
 /*
  * This describes the state of the block_group for async discard.  This is due
  * to the two pass nature of it where extent discarding is prioritized over
@@ -233,6 +244,7 @@ struct btrfs_block_group {
 	struct list_head active_bg_list;
 	struct work_struct zone_finish_work;
 	struct extent_buffer *last_eb;
+	enum btrfs_block_group_size_class size_class;
 };
 
 static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group)
@@ -302,7 +314,8 @@ int btrfs_setup_space_cache(struct btrfs_trans_handle *trans);
 int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 			     u64 bytenr, u64 num_bytes, bool alloc);
 int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
-			     u64 ram_bytes, u64 num_bytes, int delalloc);
+			     u64 ram_bytes, u64 num_bytes, int delalloc,
+			     bool force_wrong_size_class);
 void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
 			       u64 num_bytes, int delalloc);
 int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
@@ -315,8 +328,7 @@ 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);
 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);
+		     u64 physical, u64 **logical, int *naddrs, int *stripe_len);
 
 static inline u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info)
 {
@@ -346,4 +358,10 @@ void btrfs_unfreeze_block_group(struct btrfs_block_group *cache);
 bool btrfs_inc_block_group_swap_extents(struct btrfs_block_group *bg);
 void btrfs_dec_block_group_swap_extents(struct btrfs_block_group *bg, int amount);
 
+enum btrfs_block_group_size_class btrfs_calc_block_group_size_class(u64 size);
+int btrfs_use_block_group_size_class(struct btrfs_block_group *bg,
+				     enum btrfs_block_group_size_class size_class,
+				     bool force_wrong_size_class);
+bool btrfs_block_group_should_use_size_class(struct btrfs_block_group *bg);
+
 #endif /* BTRFS_BLOCK_GROUP_H */
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 7c1527fcc7b3..9dc21622806e 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -93,12 +93,6 @@ struct btrfs_inode {
 	/* the io_tree does range state (DIRTY, LOCKED etc) */
 	struct extent_io_tree io_tree;
 
-	/* special utility tree used to record which mirrors have already been
-	 * tried when checksums fail for a given block
-	 */
-	struct rb_root io_failure_tree;
-	spinlock_t io_failure_lock;
-
 	/*
 	 * Keep track of where the inode has extent items mapped in order to
 	 * make sure the i_size adjustments are accurate
@@ -411,21 +405,11 @@ static inline void btrfs_inode_split_flags(u64 inode_item_flags,
 #define CSUM_FMT				"0x%*phN"
 #define CSUM_FMT_VALUE(size, bytes)		size, bytes
 
-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);
+blk_status_t btrfs_extract_ordered_extent(struct btrfs_bio *bbio);
+bool btrfs_data_csum_ok(struct btrfs_bio *bbio, struct btrfs_device *dev,
+			u32 bio_offset, struct bio_vec *bv);
 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);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 5122ca79f7ea..f42f31f22d13 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -141,12 +141,15 @@ static int compression_decompress(int type, struct list_head *ws,
 
 static int btrfs_decompress_bio(struct compressed_bio *cb);
 
-static void finish_compressed_bio_read(struct compressed_bio *cb)
+static void end_compressed_bio_read(struct btrfs_bio *bbio)
 {
+	struct compressed_bio *cb = bbio->private;
 	unsigned int index;
 	struct page *page;
 
-	if (cb->status == BLK_STS_OK)
+	if (bbio->bio.bi_status)
+		cb->status = bbio->bio.bi_status;
+	else
 		cb->status = errno_to_blk_status(btrfs_decompress_bio(cb));
 
 	/* Release the compressed pages */
@@ -162,54 +165,6 @@ static void finish_compressed_bio_read(struct compressed_bio *cb)
 	/* Finally free the cb struct */
 	kfree(cb->compressed_pages);
 	kfree(cb);
-}
-
-/*
- * Verify the checksums and kick off repair if needed on the uncompressed data
- * before decompressing it into the original bio and freeing the uncompressed
- * pages.
- */
-static void end_compressed_bio_read(struct btrfs_bio *bbio)
-{
-	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 = bbio->bio.bi_status;
-	struct bvec_iter iter;
-	struct bio_vec bv;
-	u32 offset;
-
-	btrfs_bio_for_each_sector(fs_info, bv, bbio, iter, offset) {
-		u64 start = bbio->file_offset + offset;
-
-		if (!status &&
-		    (!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);
-		} else {
-			int ret;
-
-			refcount_inc(&cb->pending_ios);
-			ret = btrfs_repair_one_sector(BTRFS_I(inode), bbio, offset,
-						      bv.bv_page, bv.bv_offset,
-						      true);
-			if (ret) {
-				refcount_dec(&cb->pending_ios);
-				status = errno_to_blk_status(ret);
-			}
-		}
-	}
-
-	if (status)
-		cb->status = status;
-
-	if (refcount_dec_and_test(&cb->pending_ios))
-		finish_compressed_bio_read(cb);
-	btrfs_bio_free_csum(bbio);
 	bio_put(&bbio->bio);
 }
 
@@ -303,68 +258,12 @@ static void btrfs_finish_compressed_write_work(struct work_struct *work)
 static void end_compressed_bio_write(struct btrfs_bio *bbio)
 {
 	struct compressed_bio *cb = bbio->private;
-
-	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, &bbio->bio);
-		queue_work(fs_info->compressed_write_workers, &cb->write_end_work);
-	}
-	bio_put(&bbio->bio);
-}
-
-/*
- * Allocate a compressed_bio, which will be used to read/write on-disk
- * (aka, compressed) * data.
- *
- * @cb:                 The compressed_bio structure, which records all the needed
- *                      information to bind the compressed data to the uncompressed
- *                      page cache.
- * @disk_byten:         The logical bytenr where the compressed data will be read
- *                      from or written to.
- * @endio_func:         The endio function to call after the IO for compressed data
- *                      is finished.
- * @next_stripe_start:  Return value of logical bytenr of where next stripe starts.
- *                      Let the caller know to only fill the bio up to the stripe
- *                      boundary.
- */
-
-
-static struct bio *alloc_compressed_bio(struct compressed_bio *cb, u64 disk_bytenr,
-					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);
-	struct btrfs_io_geometry geom;
-	struct extent_map *em;
-	struct bio *bio;
-	int ret;
 
-	bio = btrfs_bio_alloc(BIO_MAX_VECS, opf, endio_func, cb);
-	bio->bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT;
+	cb->status = bbio->bio.bi_status;
+	queue_work(fs_info->compressed_write_workers, &cb->write_end_work);
 
-	em = btrfs_get_chunk_map(fs_info, disk_bytenr, fs_info->sectorsize);
-	if (IS_ERR(em)) {
-		bio_put(bio);
-		return ERR_CAST(em);
-	}
-
-	if (bio_op(bio) == REQ_OP_ZONE_APPEND)
-		bio_set_dev(bio, em->map_lookup->stripes[0].dev->bdev);
-
-	ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(bio), disk_bytenr, &geom);
-	free_extent_map(em);
-	if (ret < 0) {
-		bio_put(bio);
-		return ERR_PTR(ret);
-	}
-	*next_stripe_start = disk_bytenr + geom.len;
-	refcount_inc(&cb->pending_ios);
-	return bio;
+	bio_put(&bbio->bio);
 }
 
 /*
@@ -389,18 +288,13 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 	struct bio *bio = NULL;
 	struct compressed_bio *cb;
 	u64 cur_disk_bytenr = disk_start;
-	u64 next_stripe_start;
 	blk_status_t ret = BLK_STS_OK;
-	int skip_sum = inode->flags & BTRFS_INODE_NODATASUM;
-	const bool use_append = btrfs_use_zone_append(inode, disk_start);
-	const enum req_op bio_op = use_append ? REQ_OP_ZONE_APPEND : REQ_OP_WRITE;
 
 	ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
 	       IS_ALIGNED(len, fs_info->sectorsize));
 	cb = kmalloc(sizeof(struct compressed_bio), GFP_NOFS);
 	if (!cb)
 		return BLK_STS_RESOURCE;
-	refcount_set(&cb->pending_ios, 1);
 	cb->status = BLK_STS_OK;
 	cb->inode = &inode->vfs_inode;
 	cb->start = start;
@@ -411,8 +305,16 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 	INIT_WORK(&cb->write_end_work, btrfs_finish_compressed_write_work);
 	cb->nr_pages = nr_pages;
 
-	if (blkcg_css)
+	if (blkcg_css) {
 		kthread_associate_blkcg(blkcg_css);
+		write_flags |= REQ_CGROUP_PUNT;
+	}
+
+	write_flags |= REQ_BTRFS_ONE_ORDERED;
+	bio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_WRITE | write_flags,
+			      BTRFS_I(cb->inode), end_compressed_bio_write, cb);
+	bio->bi_iter.bi_sector = cur_disk_bytenr >> SECTOR_SHIFT;
+	btrfs_bio(bio)->file_offset = start;
 
 	while (cur_disk_bytenr < disk_start + compressed_len) {
 		u64 offset = cur_disk_bytenr - disk_start;
@@ -420,77 +322,30 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 		unsigned int real_size;
 		unsigned int added;
 		struct page *page = compressed_pages[index];
-		bool submit = false;
-
-		/* Allocate new bio if submitted or not yet allocated */
-		if (!bio) {
-			bio = alloc_compressed_bio(cb, cur_disk_bytenr,
-				bio_op | write_flags, end_compressed_bio_write,
-				&next_stripe_start);
-			if (IS_ERR(bio)) {
-				ret = errno_to_blk_status(PTR_ERR(bio));
-				break;
-			}
-			if (blkcg_css)
-				bio->bi_opf |= REQ_CGROUP_PUNT;
-		}
-		/*
-		 * We should never reach next_stripe_start start as we will
-		 * submit comp_bio when reach the boundary immediately.
-		 */
-		ASSERT(cur_disk_bytenr != next_stripe_start);
 
 		/*
 		 * We have various limits on the real read size:
-		 * - stripe boundary
 		 * - page boundary
 		 * - compressed length boundary
 		 */
-		real_size = min_t(u64, U32_MAX, next_stripe_start - cur_disk_bytenr);
-		real_size = min_t(u64, real_size, PAGE_SIZE - offset_in_page(offset));
+		real_size = min_t(u64, U32_MAX, PAGE_SIZE - offset_in_page(offset));
 		real_size = min_t(u64, real_size, compressed_len - offset);
 		ASSERT(IS_ALIGNED(real_size, fs_info->sectorsize));
 
-		if (use_append)
-			added = bio_add_zone_append_page(bio, page, real_size,
-					offset_in_page(offset));
-		else
-			added = bio_add_page(bio, page, real_size,
-					offset_in_page(offset));
-		/* Reached zoned boundary */
-		if (added == 0)
-			submit = true;
-
+		added = bio_add_page(bio, page, real_size, offset_in_page(offset));
+		/*
+		 * Maximum compressed extent is smaller than bio size limit,
+		 * thus bio_add_page() should always success.
+		 */
+		ASSERT(added == real_size);
 		cur_disk_bytenr += added;
-		/* Reached stripe boundary */
-		if (cur_disk_bytenr == next_stripe_start)
-			submit = true;
-
-		/* Finished the range */
-		if (cur_disk_bytenr == disk_start + compressed_len)
-			submit = true;
-
-		if (submit) {
-			if (!skip_sum) {
-				ret = btrfs_csum_one_bio(inode, bio, start, true);
-				if (ret) {
-					btrfs_bio_end_io(btrfs_bio(bio), ret);
-					break;
-				}
-			}
-
-			ASSERT(bio->bi_iter.bi_size);
-			btrfs_submit_bio(fs_info, bio, 0);
-			bio = NULL;
-		}
-		cond_resched();
 	}
 
+	/* Finished the range. */
+	ASSERT(bio->bi_iter.bi_size);
+	btrfs_submit_bio(bio, 0);
 	if (blkcg_css)
 		kthread_associate_blkcg(NULL);
-
-	if (refcount_dec_and_test(&cb->pending_ios))
-		finish_compressed_bio_write(cb);
 	return ret;
 }
 
@@ -667,10 +522,9 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	struct extent_map_tree *em_tree;
 	struct compressed_bio *cb;
 	unsigned int compressed_len;
-	struct bio *comp_bio = NULL;
+	struct bio *comp_bio;
 	const u64 disk_bytenr = bio->bi_iter.bi_sector << SECTOR_SHIFT;
 	u64 cur_disk_byte = disk_bytenr;
-	u64 next_stripe_start;
 	u64 file_offset;
 	u64 em_len;
 	u64 em_start;
@@ -703,7 +557,6 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		goto out;
 	}
 
-	refcount_set(&cb->pending_ios, 1);
 	cb->status = BLK_STS_OK;
 	cb->inode = inode;
 
@@ -737,37 +590,23 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	/* include any pages we added in add_ra-bio_pages */
 	cb->len = bio->bi_iter.bi_size;
 
+	comp_bio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ, BTRFS_I(cb->inode),
+				   end_compressed_bio_read, cb);
+	comp_bio->bi_iter.bi_sector = (cur_disk_byte >> SECTOR_SHIFT);
+
 	while (cur_disk_byte < disk_bytenr + compressed_len) {
 		u64 offset = cur_disk_byte - disk_bytenr;
 		unsigned int index = offset >> PAGE_SHIFT;
 		unsigned int real_size;
 		unsigned int added;
 		struct page *page = cb->compressed_pages[index];
-		bool submit = false;
-
-		/* Allocate new bio if submitted or not yet allocated */
-		if (!comp_bio) {
-			comp_bio = alloc_compressed_bio(cb, cur_disk_byte,
-					REQ_OP_READ, end_compressed_bio_read,
-					&next_stripe_start);
-			if (IS_ERR(comp_bio)) {
-				cb->status = errno_to_blk_status(PTR_ERR(comp_bio));
-				break;
-			}
-		}
-		/*
-		 * We should never reach next_stripe_start start as we will
-		 * submit comp_bio when reach the boundary immediately.
-		 */
-		ASSERT(cur_disk_byte != next_stripe_start);
+
 		/*
 		 * We have various limit on the real read size:
-		 * - stripe boundary
 		 * - page boundary
 		 * - compressed length boundary
 		 */
-		real_size = min_t(u64, U32_MAX, next_stripe_start - cur_disk_byte);
-		real_size = min_t(u64, real_size, PAGE_SIZE - offset_in_page(offset));
+		real_size = min_t(u64, U32_MAX, PAGE_SIZE - offset_in_page(offset));
 		real_size = min_t(u64, real_size, compressed_len - offset);
 		ASSERT(IS_ALIGNED(real_size, fs_info->sectorsize));
 
@@ -778,45 +617,20 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		 */
 		ASSERT(added == real_size);
 		cur_disk_byte += added;
-
-		/* Reached stripe boundary, need to submit */
-		if (cur_disk_byte == next_stripe_start)
-			submit = true;
-
-		/* Has finished the range, need to submit */
-		if (cur_disk_byte == disk_bytenr + compressed_len)
-			submit = true;
-
-		if (submit) {
-			/* Save the original iter for read repair */
-			if (bio_op(comp_bio) == REQ_OP_READ)
-				btrfs_bio(comp_bio)->iter = comp_bio->bi_iter;
-
-			/*
-			 * Save the initial offset of this chunk, as there
-			 * is no direct correlation between compressed pages and
-			 * the original file offset.  The field is only used for
-			 * priting error messages.
-			 */
-			btrfs_bio(comp_bio)->file_offset = file_offset;
-
-			ret = btrfs_lookup_bio_sums(inode, comp_bio, NULL);
-			if (ret) {
-				btrfs_bio_end_io(btrfs_bio(comp_bio), ret);
-				break;
-			}
-
-			ASSERT(comp_bio->bi_iter.bi_size);
-			btrfs_submit_bio(fs_info, comp_bio, mirror_num);
-			comp_bio = NULL;
-		}
 	}
 
 	if (memstall)
 		psi_memstall_leave(&pflags);
 
-	if (refcount_dec_and_test(&cb->pending_ios))
-		finish_compressed_bio_read(cb);
+	/*
+	 * Stash the initial offset of this chunk, as there is no direct
+	 * correlation between compressed pages and the original file offset.
+	 * The field is only used for printing error messages anyway.
+	 */
+	btrfs_bio(comp_bio)->file_offset = file_offset;
+
+	ASSERT(comp_bio->bi_iter.bi_size);
+	btrfs_submit_bio(comp_bio, mirror_num);
 	return;
 
 fail:
@@ -1609,7 +1423,7 @@ static void heuristic_collect_sample(struct inode *inode, u64 start, u64 end,
 	index_end = end >> PAGE_SHIFT;
 
 	/* Don't miss unaligned end */
-	if (!IS_ALIGNED(end, PAGE_SIZE))
+	if (!PAGE_ALIGNED(end))
 		index_end++;
 
 	curr_sample_pos = 0;
@@ -1642,7 +1456,7 @@ static void heuristic_collect_sample(struct inode *inode, u64 start, u64 end,
  *
  * For now is's a naive and optimistic 'return true', we'll extend the logic to
  * quickly (compared to direct compression) detect data characteristics
- * (compressible/uncompressible) to avoid wasting CPU time on uncompressible
+ * (compressible/incompressible) to avoid wasting CPU time on incompressible
  * data.
  *
  * The following types of analysis can be performed:
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 6209d40a1e08..a5e3377db9ad 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -31,9 +31,6 @@ static_assert((BTRFS_MAX_COMPRESSED % PAGE_SIZE) == 0);
 #define	BTRFS_ZLIB_DEFAULT_LEVEL		3
 
 struct compressed_bio {
-	/* Number of outstanding bios */
-	refcount_t pending_ios;
-
 	/* Number of compressed pages in the array */
 	unsigned int nr_pages;
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 4754c9101a4c..a5b6bb54545f 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -484,7 +484,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 			if (ret)
 				return ret;
 		}
-		btrfs_clean_tree_block(buf);
+		btrfs_clear_buffer_dirty(trans, buf);
 		*last_ref = 1;
 	}
 	return 0;
@@ -853,8 +853,8 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 /*
  * Search for a key in the given extent_buffer.
  *
- * The lower boundary for the search is specified by the slot number @low. Use a
- * value of 0 to search over the whole extent buffer.
+ * The lower boundary for the search is specified by the slot number @first_slot.
+ * Use a value of 0 to search over the whole extent buffer.
  *
  * The slot in the extent buffer is returned via @slot. If the key exists in the
  * extent buffer, then @slot will point to the slot where the key is, otherwise
@@ -863,18 +863,23 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
  * Slot may point to the total number of items (i.e. one position beyond the last
  * key) if the key is bigger than the last key in the extent buffer.
  */
-static noinline int generic_bin_search(struct extent_buffer *eb, int low,
-				       const struct btrfs_key *key, int *slot)
+int btrfs_generic_bin_search(struct extent_buffer *eb, int first_slot,
+			     const struct btrfs_key *key, int *slot)
 {
 	unsigned long p;
 	int item_size;
-	int high = btrfs_header_nritems(eb);
+	/*
+	 * Use unsigned types for the low and high slots, so that we get a more
+	 * efficient division in the search loop below.
+	 */
+	u32 low = first_slot;
+	u32 high = btrfs_header_nritems(eb);
 	int ret;
 	const int key_size = sizeof(struct btrfs_disk_key);
 
-	if (low > high) {
+	if (unlikely(low > high)) {
 		btrfs_err(eb->fs_info,
-		 "%s: low (%d) > high (%d) eb %llu owner %llu level %d",
+		 "%s: low (%u) > high (%u) eb %llu owner %llu level %d",
 			  __func__, low, high, eb->start,
 			  btrfs_header_owner(eb), btrfs_header_level(eb));
 		return -EINVAL;
@@ -925,16 +930,6 @@ static noinline int generic_bin_search(struct extent_buffer *eb, int low,
 	return 1;
 }
 
-/*
- * Simple binary search on an extent buffer. Works for both leaves and nodes, and
- * always searches over the whole range of keys (slot 0 to slot 'nritems - 1').
- */
-int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
-		     int *slot)
-{
-	return generic_bin_search(eb, 0, key, slot);
-}
-
 static void root_add_used(struct btrfs_root *root, u32 size)
 {
 	spin_lock(&root->accounting_lock);
@@ -1054,7 +1049,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 
 		path->locks[level] = 0;
 		path->nodes[level] = NULL;
-		btrfs_clean_tree_block(mid);
+		btrfs_clear_buffer_dirty(trans, mid);
 		btrfs_tree_unlock(mid);
 		/* once for the path */
 		free_extent_buffer(mid);
@@ -1115,7 +1110,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		if (wret < 0 && wret != -ENOSPC)
 			ret = wret;
 		if (btrfs_header_nritems(right) == 0) {
-			btrfs_clean_tree_block(right);
+			btrfs_clear_buffer_dirty(trans, right);
 			btrfs_tree_unlock(right);
 			del_ptr(root, path, level + 1, pslot + 1);
 			root_sub_used(root, right->len);
@@ -1161,7 +1156,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		BUG_ON(wret == 1);
 	}
 	if (btrfs_header_nritems(mid) == 0) {
-		btrfs_clean_tree_block(mid);
+		btrfs_clear_buffer_dirty(trans, mid);
 		btrfs_tree_unlock(mid);
 		del_ptr(root, path, level + 1, pslot);
 		root_sub_used(root, mid->len);
@@ -1869,7 +1864,7 @@ static inline int search_for_key_slot(struct extent_buffer *eb,
 		return 0;
 	}
 
-	return generic_bin_search(eb, search_low_slot, key, slot);
+	return btrfs_generic_bin_search(eb, search_low_slot, key, slot);
 }
 
 static int search_leaf(struct btrfs_trans_handle *trans,
@@ -3041,7 +3036,8 @@ noinline int btrfs_leaf_free_space(struct extent_buffer *leaf)
  * min slot controls the lowest index we're willing to push to the
  * right.  We'll push up to and including min_slot, but no lower
  */
-static noinline int __push_leaf_right(struct btrfs_path *path,
+static noinline int __push_leaf_right(struct btrfs_trans_handle *trans,
+				      struct btrfs_path *path,
 				      int data_size, int empty,
 				      struct extent_buffer *right,
 				      int free_space, u32 left_nritems,
@@ -3139,7 +3135,7 @@ static noinline int __push_leaf_right(struct btrfs_path *path,
 	if (left_nritems)
 		btrfs_mark_buffer_dirty(left);
 	else
-		btrfs_clean_tree_block(left);
+		btrfs_clear_buffer_dirty(trans, left);
 
 	btrfs_mark_buffer_dirty(right);
 
@@ -3151,7 +3147,7 @@ static noinline int __push_leaf_right(struct btrfs_path *path,
 	if (path->slots[0] >= left_nritems) {
 		path->slots[0] -= left_nritems;
 		if (btrfs_header_nritems(path->nodes[0]) == 0)
-			btrfs_clean_tree_block(path->nodes[0]);
+			btrfs_clear_buffer_dirty(trans, path->nodes[0]);
 		btrfs_tree_unlock(path->nodes[0]);
 		free_extent_buffer(path->nodes[0]);
 		path->nodes[0] = right;
@@ -3243,8 +3239,8 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
 		return 0;
 	}
 
-	return __push_leaf_right(path, min_data_size, empty,
-				right, free_space, left_nritems, min_slot);
+	return __push_leaf_right(trans, path, min_data_size, empty, right,
+				 free_space, left_nritems, min_slot);
 out_unlock:
 	btrfs_tree_unlock(right);
 	free_extent_buffer(right);
@@ -3259,7 +3255,8 @@ out_unlock:
  * item at 'max_slot' won't be touched.  Use (u32)-1 to make us do all the
  * items
  */
-static noinline int __push_leaf_left(struct btrfs_path *path, int data_size,
+static noinline int __push_leaf_left(struct btrfs_trans_handle *trans,
+				     struct btrfs_path *path, int data_size,
 				     int empty, struct extent_buffer *left,
 				     int free_space, u32 right_nritems,
 				     u32 max_slot)
@@ -3363,7 +3360,7 @@ static noinline int __push_leaf_left(struct btrfs_path *path, int data_size,
 	if (right_nritems)
 		btrfs_mark_buffer_dirty(right);
 	else
-		btrfs_clean_tree_block(right);
+		btrfs_clear_buffer_dirty(trans, right);
 
 	btrfs_item_key(right, &disk_key, 0);
 	fixup_low_keys(path, &disk_key, 1);
@@ -3449,9 +3446,8 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root
 		ret = -EUCLEAN;
 		goto out;
 	}
-	return __push_leaf_left(path, min_data_size,
-			       empty, left, free_space, right_nritems,
-			       max_slot);
+	return __push_leaf_left(trans, path, min_data_size, empty, left,
+				free_space, right_nritems, max_slot);
 out:
 	btrfs_tree_unlock(left);
 	free_extent_buffer(left);
@@ -4400,7 +4396,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		if (leaf == root->node) {
 			btrfs_set_header_level(leaf, 0);
 		} else {
-			btrfs_clean_tree_block(leaf);
+			btrfs_clear_buffer_dirty(trans, leaf);
 			btrfs_del_leaf(trans, root, path, leaf);
 		}
 	} else {
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 6965703a81b6..97897107fab5 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -507,6 +507,21 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range);
 /* ctree.c */
 int __init btrfs_ctree_init(void);
 void __cold btrfs_ctree_exit(void);
+
+int btrfs_generic_bin_search(struct extent_buffer *eb, int first_slot,
+			     const struct btrfs_key *key, int *slot);
+
+/*
+ * Simple binary search on an extent buffer. Works for both leaves and nodes, and
+ * always searches over the whole range of keys (slot 0 to slot 'nritems - 1').
+ */
+static inline int btrfs_bin_search(struct extent_buffer *eb,
+				   const struct btrfs_key *key,
+				   int *slot)
+{
+	return btrfs_generic_bin_search(eb, 0, key, slot);
+}
+
 int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
 		     int *slot);
 int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c
index d81b764a7644..8065341d831a 100644
--- a/fs/btrfs/defrag.c
+++ b/fs/btrfs/defrag.c
@@ -765,7 +765,7 @@ again:
 			break;
 
 		unlock_page(page);
-		btrfs_start_ordered_extent(ordered, 1);
+		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
 		lock_page(page);
 		/*
@@ -999,7 +999,7 @@ next:
 }
 
 #define CLUSTER_SIZE	(SZ_256K)
-static_assert(IS_ALIGNED(CLUSTER_SIZE, PAGE_SIZE));
+static_assert(PAGE_ALIGNED(CLUSTER_SIZE));
 
 /*
  * Defrag one contiguous target range.
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 573ebab886e2..886ffb232eac 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -437,8 +437,7 @@ int btrfs_delayed_ref_lock(struct btrfs_delayed_ref_root *delayed_refs,
 	return 0;
 }
 
-static inline void drop_delayed_ref(struct btrfs_trans_handle *trans,
-				    struct btrfs_delayed_ref_root *delayed_refs,
+static inline void drop_delayed_ref(struct btrfs_delayed_ref_root *delayed_refs,
 				    struct btrfs_delayed_ref_head *head,
 				    struct btrfs_delayed_ref_node *ref)
 {
@@ -452,8 +451,7 @@ static inline void drop_delayed_ref(struct btrfs_trans_handle *trans,
 	atomic_dec(&delayed_refs->num_entries);
 }
 
-static bool merge_ref(struct btrfs_trans_handle *trans,
-		      struct btrfs_delayed_ref_root *delayed_refs,
+static bool merge_ref(struct btrfs_delayed_ref_root *delayed_refs,
 		      struct btrfs_delayed_ref_head *head,
 		      struct btrfs_delayed_ref_node *ref,
 		      u64 seq)
@@ -482,10 +480,10 @@ static bool merge_ref(struct btrfs_trans_handle *trans,
 			mod = -next->ref_mod;
 		}
 
-		drop_delayed_ref(trans, delayed_refs, head, next);
+		drop_delayed_ref(delayed_refs, head, next);
 		ref->ref_mod += mod;
 		if (ref->ref_mod == 0) {
-			drop_delayed_ref(trans, delayed_refs, head, ref);
+			drop_delayed_ref(delayed_refs, head, ref);
 			done = true;
 		} else {
 			/*
@@ -499,11 +497,10 @@ static bool merge_ref(struct btrfs_trans_handle *trans,
 	return done;
 }
 
-void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
+void btrfs_merge_delayed_refs(struct btrfs_fs_info *fs_info,
 			      struct btrfs_delayed_ref_root *delayed_refs,
 			      struct btrfs_delayed_ref_head *head)
 {
-	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_ref_node *ref;
 	struct rb_node *node;
 	u64 seq = 0;
@@ -524,7 +521,7 @@ again:
 		ref = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
 		if (seq && ref->seq >= seq)
 			continue;
-		if (merge_ref(trans, delayed_refs, head, ref, seq))
+		if (merge_ref(delayed_refs, head, ref, seq))
 			goto again;
 	}
 }
@@ -601,8 +598,7 @@ void btrfs_delete_ref_head(struct btrfs_delayed_ref_root *delayed_refs,
  * Return 0 for insert.
  * Return >0 for merge.
  */
-static int insert_delayed_ref(struct btrfs_trans_handle *trans,
-			      struct btrfs_delayed_ref_root *root,
+static int insert_delayed_ref(struct btrfs_delayed_ref_root *root,
 			      struct btrfs_delayed_ref_head *href,
 			      struct btrfs_delayed_ref_node *ref)
 {
@@ -641,7 +637,7 @@ static int insert_delayed_ref(struct btrfs_trans_handle *trans,
 
 	/* remove existing tail if its ref_mod is zero */
 	if (exist->ref_mod == 0)
-		drop_delayed_ref(trans, root, href, exist);
+		drop_delayed_ref(root, href, exist);
 	spin_unlock(&href->lock);
 	return ret;
 inserted:
@@ -978,7 +974,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	head_ref = add_delayed_ref_head(trans, head_ref, record,
 					action, &qrecord_inserted);
 
-	ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node);
+	ret = insert_delayed_ref(delayed_refs, head_ref, &ref->node);
 	spin_unlock(&delayed_refs->lock);
 
 	/*
@@ -1070,7 +1066,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 	head_ref = add_delayed_ref_head(trans, head_ref, record,
 					action, &qrecord_inserted);
 
-	ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node);
+	ret = insert_delayed_ref(delayed_refs, head_ref, &ref->node);
 	spin_unlock(&delayed_refs->lock);
 
 	/*
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index d6304b690ec4..2eb34abf700f 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -357,7 +357,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
 				u64 bytenr, u64 num_bytes,
 				struct btrfs_delayed_extent_op *extent_op);
-void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
+void btrfs_merge_delayed_refs(struct btrfs_fs_info *fs_info,
 			      struct btrfs_delayed_ref_root *delayed_refs,
 			      struct btrfs_delayed_ref_head *head);
 
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index ff2e524d9937..317aeff6c1da 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -78,6 +78,7 @@ static struct list_head *get_discard_list(struct btrfs_discard_ctl *discard_ctl,
 static void __add_to_discard_list(struct btrfs_discard_ctl *discard_ctl,
 				  struct btrfs_block_group *block_group)
 {
+	lockdep_assert_held(&discard_ctl->lock);
 	if (!btrfs_run_discard_work(discard_ctl))
 		return;
 
@@ -89,6 +90,8 @@ static void __add_to_discard_list(struct btrfs_discard_ctl *discard_ctl,
 						      BTRFS_DISCARD_DELAY);
 		block_group->discard_state = BTRFS_DISCARD_RESET_CURSOR;
 	}
+	if (list_empty(&block_group->discard_list))
+		btrfs_get_block_group(block_group);
 
 	list_move_tail(&block_group->discard_list,
 		       get_discard_list(discard_ctl, block_group));
@@ -108,8 +111,12 @@ static void add_to_discard_list(struct btrfs_discard_ctl *discard_ctl,
 static void add_to_discard_unused_list(struct btrfs_discard_ctl *discard_ctl,
 				       struct btrfs_block_group *block_group)
 {
+	bool queued;
+
 	spin_lock(&discard_ctl->lock);
 
+	queued = !list_empty(&block_group->discard_list);
+
 	if (!btrfs_run_discard_work(discard_ctl)) {
 		spin_unlock(&discard_ctl->lock);
 		return;
@@ -121,6 +128,8 @@ static void add_to_discard_unused_list(struct btrfs_discard_ctl *discard_ctl,
 	block_group->discard_eligible_time = (ktime_get_ns() +
 					      BTRFS_DISCARD_UNUSED_DELAY);
 	block_group->discard_state = BTRFS_DISCARD_RESET_CURSOR;
+	if (!queued)
+		btrfs_get_block_group(block_group);
 	list_add_tail(&block_group->discard_list,
 		      &discard_ctl->discard_list[BTRFS_DISCARD_INDEX_UNUSED]);
 
@@ -131,6 +140,7 @@ static bool remove_from_discard_list(struct btrfs_discard_ctl *discard_ctl,
 				     struct btrfs_block_group *block_group)
 {
 	bool running = false;
+	bool queued = false;
 
 	spin_lock(&discard_ctl->lock);
 
@@ -140,7 +150,16 @@ static bool remove_from_discard_list(struct btrfs_discard_ctl *discard_ctl,
 	}
 
 	block_group->discard_eligible_time = 0;
+	queued = !list_empty(&block_group->discard_list);
 	list_del_init(&block_group->discard_list);
+	/*
+	 * If the block group is currently running in the discard workfn, we
+	 * don't want to deref it, since it's still being used by the workfn.
+	 * The workfn will notice this case and deref the block group when it is
+	 * finished.
+	 */
+	if (queued && !running)
+		btrfs_put_block_group(block_group);
 
 	spin_unlock(&discard_ctl->lock);
 
@@ -214,10 +233,12 @@ again:
 	if (block_group && now >= block_group->discard_eligible_time) {
 		if (block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED &&
 		    block_group->used != 0) {
-			if (btrfs_is_block_group_data_only(block_group))
+			if (btrfs_is_block_group_data_only(block_group)) {
 				__add_to_discard_list(discard_ctl, block_group);
-			else
+			} else {
 				list_del_init(&block_group->discard_list);
+				btrfs_put_block_group(block_group);
+			}
 			goto again;
 		}
 		if (block_group->discard_state == BTRFS_DISCARD_RESET_CURSOR) {
@@ -511,6 +532,15 @@ static void btrfs_discard_workfn(struct work_struct *work)
 	spin_lock(&discard_ctl->lock);
 	discard_ctl->prev_discard = trimmed;
 	discard_ctl->prev_discard_time = now;
+	/*
+	 * If the block group was removed from the discard list while it was
+	 * running in this workfn, then we didn't deref it, since this function
+	 * still owned that reference. But we set the discard_ctl->block_group
+	 * back to NULL, so we can use that condition to know that now we need
+	 * to deref the block_group.
+	 */
+	if (discard_ctl->block_group == NULL)
+		btrfs_put_block_group(block_group);
 	discard_ctl->block_group = NULL;
 	__btrfs_discard_schedule_work(discard_ctl, now, false);
 	spin_unlock(&discard_ctl->lock);
@@ -651,8 +681,12 @@ void btrfs_discard_punt_unused_bgs_list(struct btrfs_fs_info *fs_info)
 	list_for_each_entry_safe(block_group, next, &fs_info->unused_bgs,
 				 bg_list) {
 		list_del_init(&block_group->bg_list);
-		btrfs_put_block_group(block_group);
 		btrfs_discard_queue_work(&fs_info->discard_ctl, block_group);
+		/*
+		 * This put is for the get done by btrfs_mark_bg_unused.
+		 * Queueing discard incremented it for discard's reference.
+		 */
+		btrfs_put_block_group(block_group);
 	}
 	spin_unlock(&fs_info->unused_bgs_lock);
 }
@@ -683,6 +717,7 @@ static void btrfs_discard_purge_list(struct btrfs_discard_ctl *discard_ctl)
 			if (block_group->used == 0)
 				btrfs_mark_bg_unused(block_group);
 			spin_lock(&discard_ctl->lock);
+			btrfs_put_block_group(block_group);
 		}
 	}
 	spin_unlock(&discard_ctl->lock);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3aa04224315e..b53f0e30ce2b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -79,23 +79,6 @@ static void btrfs_free_csum_hash(struct btrfs_fs_info *fs_info)
 }
 
 /*
- * async submit bios are used to offload expensive checksumming
- * onto the worker threads.  They checksum file and metadata bios
- * just before they are sent down the IO stack.
- */
-struct async_submit_bio {
-	struct btrfs_inode *inode;
-	struct bio *bio;
-	enum btrfs_wq_submit_cmd submit_cmd;
-	int mirror_num;
-
-	/* Optional parameter for used by direct io */
-	u64 dio_file_offset;
-	struct btrfs_work work;
-	blk_status_t status;
-};
-
-/*
  * Compute the csum of a btree block and store the result to provided buffer.
  */
 static void csum_tree_block(struct extent_buffer *buf, u8 *result)
@@ -455,6 +438,22 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec
 	return csum_one_extent_buffer(eb);
 }
 
+blk_status_t btree_csum_one_bio(struct btrfs_bio *bbio)
+{
+	struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info;
+	struct bvec_iter iter;
+	struct bio_vec bv;
+	int ret = 0;
+
+	bio_for_each_segment(bv, &bbio->bio, iter) {
+		ret = csum_dirty_buffer(fs_info, &bv);
+		if (ret)
+			break;
+	}
+
+	return errno_to_blk_status(ret);
+}
+
 static int check_tree_block_fsid(struct extent_buffer *eb)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
@@ -700,172 +699,6 @@ err:
 	return ret;
 }
 
-static void run_one_async_start(struct btrfs_work *work)
-{
-	struct async_submit_bio *async;
-	blk_status_t ret;
-
-	async = container_of(work, struct  async_submit_bio, work);
-	switch (async->submit_cmd) {
-	case WQ_SUBMIT_METADATA:
-		ret = btree_submit_bio_start(async->bio);
-		break;
-	case WQ_SUBMIT_DATA:
-		ret = btrfs_submit_bio_start(async->inode, async->bio);
-		break;
-	case WQ_SUBMIT_DATA_DIO:
-		ret = btrfs_submit_bio_start_direct_io(async->inode,
-				async->bio, async->dio_file_offset);
-		break;
-	}
-	if (ret)
-		async->status = ret;
-}
-
-/*
- * In order to insert checksums into the metadata in large chunks, we wait
- * until bio submission time.   All the pages in the bio are checksummed and
- * sums are attached onto the ordered extent record.
- *
- * At IO completion time the csums attached on the ordered extent record are
- * inserted into the tree.
- */
-static void run_one_async_done(struct btrfs_work *work)
-{
-	struct async_submit_bio *async =
-		container_of(work, struct  async_submit_bio, work);
-	struct btrfs_inode *inode = async->inode;
-	struct btrfs_bio *bbio = btrfs_bio(async->bio);
-
-	/* If an error occurred we just want to clean up the bio and move on */
-	if (async->status) {
-		btrfs_bio_end_io(bbio, async->status);
-		return;
-	}
-
-	/*
-	 * All of the bios that pass through here are from async helpers.
-	 * Use REQ_CGROUP_PUNT to issue them from the owning cgroup's context.
-	 * This changes nothing when cgroups aren't in use.
-	 */
-	async->bio->bi_opf |= REQ_CGROUP_PUNT;
-	btrfs_submit_bio(inode->root->fs_info, async->bio, async->mirror_num);
-}
-
-static void run_one_async_free(struct btrfs_work *work)
-{
-	struct async_submit_bio *async;
-
-	async = container_of(work, struct  async_submit_bio, work);
-	kfree(async);
-}
-
-/*
- * Submit bio to an async queue.
- *
- * Retrun:
- * - true if the work has been succesfuly submitted
- * - false in case of error
- */
-bool btrfs_wq_submit_bio(struct btrfs_inode *inode, struct bio *bio, int mirror_num,
-			 u64 dio_file_offset, enum btrfs_wq_submit_cmd cmd)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	struct async_submit_bio *async;
-
-	async = kmalloc(sizeof(*async), GFP_NOFS);
-	if (!async)
-		return false;
-
-	async->inode = inode;
-	async->bio = bio;
-	async->mirror_num = mirror_num;
-	async->submit_cmd = cmd;
-
-	btrfs_init_work(&async->work, run_one_async_start, run_one_async_done,
-			run_one_async_free);
-
-	async->dio_file_offset = dio_file_offset;
-
-	async->status = 0;
-
-	if (op_is_sync(bio->bi_opf))
-		btrfs_queue_work(fs_info->hipri_workers, &async->work);
-	else
-		btrfs_queue_work(fs_info->workers, &async->work);
-	return true;
-}
-
-static blk_status_t btree_csum_one_bio(struct bio *bio)
-{
-	struct bio_vec *bvec;
-	struct btrfs_root *root;
-	int ret = 0;
-	struct bvec_iter_all iter_all;
-
-	ASSERT(!bio_flagged(bio, BIO_CLONED));
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		root = BTRFS_I(bvec->bv_page->mapping->host)->root;
-		ret = csum_dirty_buffer(root->fs_info, bvec);
-		if (ret)
-			break;
-	}
-
-	return errno_to_blk_status(ret);
-}
-
-blk_status_t btree_submit_bio_start(struct bio *bio)
-{
-	/*
-	 * when we're called for a write, we're already in the async
-	 * submission context.  Just jump into btrfs_submit_bio.
-	 */
-	return btree_csum_one_bio(bio);
-}
-
-static bool should_async_write(struct btrfs_fs_info *fs_info,
-			     struct btrfs_inode *bi)
-{
-	if (btrfs_is_zoned(fs_info))
-		return false;
-	if (atomic_read(&bi->sync_writers))
-		return false;
-	if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags))
-		return false;
-	return true;
-}
-
-void btrfs_submit_metadata_bio(struct btrfs_inode *inode, struct bio *bio, int mirror_num)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	struct btrfs_bio *bbio = btrfs_bio(bio);
-	blk_status_t ret;
-
-	bio->bi_opf |= REQ_META;
-	bbio->is_metadata = 1;
-
-	if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
-		btrfs_submit_bio(fs_info, bio, mirror_num);
-		return;
-	}
-
-	/*
-	 * Kthread helpers are used to submit writes so that checksumming can
-	 * happen in parallel across all CPUs.
-	 */
-	if (should_async_write(fs_info, inode) &&
-	    btrfs_wq_submit_bio(inode, bio, mirror_num, 0, WQ_SUBMIT_METADATA))
-		return;
-
-	ret = btree_csum_one_bio(bio);
-	if (ret) {
-		btrfs_bio_end_io(bbio, ret);
-		return;
-	}
-
-	btrfs_submit_bio(fs_info, bio, mirror_num);
-}
-
 #ifdef CONFIG_MIGRATION
 static int btree_migrate_folio(struct address_space *mapping,
 		struct folio *dst, struct folio *src, enum migrate_mode mode)
@@ -1035,22 +868,6 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
 
 }
 
-void btrfs_clean_tree_block(struct extent_buffer *buf)
-{
-	struct btrfs_fs_info *fs_info = buf->fs_info;
-	if (btrfs_header_generation(buf) ==
-	    fs_info->running_transaction->transid) {
-		btrfs_assert_tree_write_locked(buf);
-
-		if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) {
-			percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
-						 -buf->len,
-						 fs_info->dirty_metadata_batch);
-			clear_extent_buffer_dirty(buf);
-		}
-	}
-}
-
 static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 			 u64 objectid)
 {
@@ -1910,6 +1727,9 @@ static int cleaner_kthread(void *arg)
 			goto sleep;
 		}
 
+		if (test_and_clear_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags))
+			btrfs_sysfs_feature_update(fs_info);
+
 		btrfs_run_delayed_iputs(fs_info);
 
 		again = btrfs_clean_one_deleted_snapshot(fs_info);
@@ -5159,11 +4979,12 @@ static int btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info,
 			start += fs_info->nodesize;
 			if (!eb)
 				continue;
+
+			btrfs_tree_lock(eb);
 			wait_on_extent_buffer_writeback(eb);
+			btrfs_clear_buffer_dirty(NULL, eb);
+			btrfs_tree_unlock(eb);
 
-			if (test_and_clear_bit(EXTENT_BUFFER_DIRTY,
-					       &eb->bflags))
-				clear_extent_buffer_dirty(eb);
 			free_extent_buffer_stale(eb);
 		}
 	}
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index f2f295eb6103..4d5772330110 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -39,7 +39,8 @@ struct extent_buffer *btrfs_find_create_tree_block(
 						struct btrfs_fs_info *fs_info,
 						u64 bytenr, u64 owner_root,
 						int level);
-void btrfs_clean_tree_block(struct extent_buffer *buf);
+void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
+			      struct extent_buffer *buf);
 void btrfs_clear_oneshot_options(struct btrfs_fs_info *fs_info);
 int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info);
 int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
@@ -86,7 +87,6 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 int btrfs_validate_metadata_buffer(struct btrfs_bio *bbio,
 				   struct page *page, u64 start, u64 end,
 				   int mirror);
-void btrfs_submit_metadata_bio(struct btrfs_inode *inode, struct bio *bio, int mirror_num);
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info);
 #endif
@@ -114,15 +114,7 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
 int btrfs_read_extent_buffer(struct extent_buffer *buf,
 			     struct btrfs_tree_parent_check *check);
 
-enum btrfs_wq_submit_cmd {
-	WQ_SUBMIT_METADATA,
-	WQ_SUBMIT_DATA,
-	WQ_SUBMIT_DATA_DIO,
-};
-
-bool btrfs_wq_submit_bio(struct btrfs_inode *inode, struct bio *bio, int mirror_num,
-			 u64 dio_file_offset, enum btrfs_wq_submit_cmd cmd);
-blk_status_t btree_submit_bio_start(struct bio *bio);
+blk_status_t btree_csum_one_bio(struct btrfs_bio *bbio);
 int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root);
 int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c
index 3c7766dfaa69..29a225836e28 100644
--- a/fs/btrfs/extent-io-tree.c
+++ b/fs/btrfs/extent-io-tree.c
@@ -972,8 +972,8 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 {
 	struct extent_state *state;
 	struct extent_state *prealloc = NULL;
-	struct rb_node **p;
-	struct rb_node *parent;
+	struct rb_node **p = NULL;
+	struct rb_node *parent = NULL;
 	int err = 0;
 	u64 last_start;
 	u64 last_end;
@@ -1218,8 +1218,8 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 {
 	struct extent_state *state;
 	struct extent_state *prealloc = NULL;
-	struct rb_node **p;
-	struct rb_node *parent;
+	struct rb_node **p = NULL;
+	struct rb_node *parent = NULL;
 	int err = 0;
 	u64 last_start;
 	u64 last_end;
@@ -1625,7 +1625,7 @@ search:
 }
 
 /*
- * Searche a range in the state tree for a given mask.  If 'filled' == 1, this
+ * Search a range in the state tree for a given mask.  If 'filled' == 1, this
  * returns 1 only if every extent in the tree has the bits set.  Otherwise, 1
  * is returned if any bit in the range is found set.
  */
diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h
index e3eeec380844..21766e49ec02 100644
--- a/fs/btrfs/extent-io-tree.h
+++ b/fs/btrfs/extent-io-tree.h
@@ -6,7 +6,6 @@
 #include "misc.h"
 
 struct extent_changeset;
-struct io_failure_record;
 
 /* Bits for the extent state */
 enum {
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 72ba13b027a9..824c657f59e8 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -16,7 +16,8 @@
 #include <linux/percpu_counter.h>
 #include <linux/lockdep.h>
 #include <linux/crc32c.h>
-#include "misc.h"
+#include "ctree.h"
+#include "extent-tree.h"
 #include "tree-log.h"
 #include "disk-io.h"
 #include "print-tree.h"
@@ -31,14 +32,12 @@
 #include "space-info.h"
 #include "block-rsv.h"
 #include "delalloc-space.h"
-#include "block-group.h"
 #include "discard.h"
 #include "rcu-string.h"
 #include "zoned.h"
 #include "dev-replace.h"
 #include "fs.h"
 #include "accessors.h"
-#include "extent-tree.h"
 #include "root-tree.h"
 #include "file-item.h"
 #include "orphan.h"
@@ -1966,7 +1965,7 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans,
 		cond_resched();
 
 		spin_lock(&locked_ref->lock);
-		btrfs_merge_delayed_refs(trans, delayed_refs, locked_ref);
+		btrfs_merge_delayed_refs(fs_info, delayed_refs, locked_ref);
 	}
 
 	return 0;
@@ -2013,7 +2012,7 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		 * insert_inline_extent_backref()).
 		 */
 		spin_lock(&locked_ref->lock);
-		btrfs_merge_delayed_refs(trans, delayed_refs, locked_ref);
+		btrfs_merge_delayed_refs(fs_info, delayed_refs, locked_ref);
 
 		ret = btrfs_run_delayed_refs_for_head(trans, locked_ref,
 						      &actual_count);
@@ -3385,7 +3384,9 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref)
 enum btrfs_loop_type {
 	LOOP_CACHING_NOWAIT,
 	LOOP_CACHING_WAIT,
+	LOOP_UNSET_SIZE_CLASS,
 	LOOP_ALLOC_CHUNK,
+	LOOP_WRONG_SIZE_CLASS,
 	LOOP_NO_EMPTY_SIZE,
 };
 
@@ -3453,81 +3454,6 @@ btrfs_release_block_group(struct btrfs_block_group *cache,
 	btrfs_put_block_group(cache);
 }
 
-enum btrfs_extent_allocation_policy {
-	BTRFS_EXTENT_ALLOC_CLUSTERED,
-	BTRFS_EXTENT_ALLOC_ZONED,
-};
-
-/*
- * Structure used internally for find_free_extent() function.  Wraps needed
- * parameters.
- */
-struct find_free_extent_ctl {
-	/* Basic allocation info */
-	u64 ram_bytes;
-	u64 num_bytes;
-	u64 min_alloc_size;
-	u64 empty_size;
-	u64 flags;
-	int delalloc;
-
-	/* Where to start the search inside the bg */
-	u64 search_start;
-
-	/* For clustered allocation */
-	u64 empty_cluster;
-	struct btrfs_free_cluster *last_ptr;
-	bool use_cluster;
-
-	bool have_caching_bg;
-	bool orig_have_caching_bg;
-
-	/* Allocation is called for tree-log */
-	bool for_treelog;
-
-	/* Allocation is called for data relocation */
-	bool for_data_reloc;
-
-	/* RAID index, converted from flags */
-	int index;
-
-	/*
-	 * Current loop number, check find_free_extent_update_loop() for details
-	 */
-	int loop;
-
-	/*
-	 * Whether we're refilling a cluster, if true we need to re-search
-	 * current block group but don't try to refill the cluster again.
-	 */
-	bool retry_clustered;
-
-	/*
-	 * Whether we're updating free space cache, if true we need to re-search
-	 * current block group but don't try updating free space cache again.
-	 */
-	bool retry_unclustered;
-
-	/* If current block group is cached */
-	int cached;
-
-	/* Max contiguous hole found */
-	u64 max_extent_size;
-
-	/* Total free space from free space cache, not always contiguous */
-	u64 total_free_space;
-
-	/* Found result */
-	u64 found_offset;
-
-	/* Hint where to start looking for an empty space */
-	u64 hint_byte;
-
-	/* Allocation policy */
-	enum btrfs_extent_allocation_policy policy;
-};
-
-
 /*
  * Helper function for find_free_extent().
  *
@@ -3559,8 +3485,7 @@ static int find_free_extent_clustered(struct btrfs_block_group *bg,
 	if (offset) {
 		/* We have a block, we're done */
 		spin_unlock(&last_ptr->refill_lock);
-		trace_btrfs_reserve_extent_cluster(cluster_bg,
-				ffe_ctl->search_start, ffe_ctl->num_bytes);
+		trace_btrfs_reserve_extent_cluster(cluster_bg, ffe_ctl);
 		*cluster_bg_ret = cluster_bg;
 		ffe_ctl->found_offset = offset;
 		return 0;
@@ -3610,10 +3535,8 @@ refill_cluster:
 		if (offset) {
 			/* We found one, proceed */
 			spin_unlock(&last_ptr->refill_lock);
-			trace_btrfs_reserve_extent_cluster(bg,
-					ffe_ctl->search_start,
-					ffe_ctl->num_bytes);
 			ffe_ctl->found_offset = offset;
+			trace_btrfs_reserve_extent_cluster(bg, ffe_ctl);
 			return 0;
 		}
 	} else if (!ffe_ctl->cached && ffe_ctl->loop > LOOP_CACHING_NOWAIT &&
@@ -4028,24 +3951,6 @@ static int can_allocate_chunk(struct btrfs_fs_info *fs_info,
 	}
 }
 
-static int chunk_allocation_failed(struct find_free_extent_ctl *ffe_ctl)
-{
-	switch (ffe_ctl->policy) {
-	case BTRFS_EXTENT_ALLOC_CLUSTERED:
-		/*
-		 * If we can't allocate a new chunk we've already looped through
-		 * at least once, move on to the NO_EMPTY_SIZE case.
-		 */
-		ffe_ctl->loop = LOOP_NO_EMPTY_SIZE;
-		return 0;
-	case BTRFS_EXTENT_ALLOC_ZONED:
-		/* Give up here */
-		return -ENOSPC;
-	default:
-		BUG();
-	}
-}
-
 /*
  * Return >0 means caller needs to re-search for free extent
  * Return 0 means we have the needed free extent.
@@ -4079,31 +3984,28 @@ static int find_free_extent_update_loop(struct btrfs_fs_info *fs_info,
 	 * LOOP_CACHING_NOWAIT, search partially cached block groups, kicking
 	 *			caching kthreads as we move along
 	 * LOOP_CACHING_WAIT, search everything, and wait if our bg is caching
+	 * LOOP_UNSET_SIZE_CLASS, allow unset size class
 	 * LOOP_ALLOC_CHUNK, force a chunk allocation and try again
 	 * LOOP_NO_EMPTY_SIZE, set empty_size and empty_cluster to 0 and try
 	 *		       again
 	 */
 	if (ffe_ctl->loop < LOOP_NO_EMPTY_SIZE) {
 		ffe_ctl->index = 0;
-		if (ffe_ctl->loop == LOOP_CACHING_NOWAIT) {
-			/*
-			 * We want to skip the LOOP_CACHING_WAIT step if we
-			 * don't have any uncached bgs and we've already done a
-			 * full search through.
-			 */
-			if (ffe_ctl->orig_have_caching_bg || !full_search)
-				ffe_ctl->loop = LOOP_CACHING_WAIT;
-			else
-				ffe_ctl->loop = LOOP_ALLOC_CHUNK;
-		} else {
+		/*
+		 * We want to skip the LOOP_CACHING_WAIT step if we don't have
+		 * any uncached bgs and we've already done a full search
+		 * through.
+		 */
+		if (ffe_ctl->loop == LOOP_CACHING_NOWAIT &&
+		    (!ffe_ctl->orig_have_caching_bg && full_search))
 			ffe_ctl->loop++;
-		}
+		ffe_ctl->loop++;
 
 		if (ffe_ctl->loop == LOOP_ALLOC_CHUNK) {
 			struct btrfs_trans_handle *trans;
 			int exist = 0;
 
-			/*Check if allocation policy allows to create a new chunk */
+			/* Check if allocation policy allows to create a new chunk */
 			ret = can_allocate_chunk(fs_info, ffe_ctl);
 			if (ret)
 				return ret;
@@ -4123,8 +4025,10 @@ static int find_free_extent_update_loop(struct btrfs_fs_info *fs_info,
 						CHUNK_ALLOC_FORCE_FOR_EXTENT);
 
 			/* Do not bail out on ENOSPC since we can do more. */
-			if (ret == -ENOSPC)
-				ret = chunk_allocation_failed(ffe_ctl);
+			if (ret == -ENOSPC) {
+				ret = 0;
+				ffe_ctl->loop++;
+			}
 			else if (ret < 0)
 				btrfs_abort_transaction(trans, ret);
 			else
@@ -4154,6 +4058,21 @@ static int find_free_extent_update_loop(struct btrfs_fs_info *fs_info,
 	return -ENOSPC;
 }
 
+static bool find_free_extent_check_size_class(struct find_free_extent_ctl *ffe_ctl,
+					      struct btrfs_block_group *bg)
+{
+	if (ffe_ctl->policy == BTRFS_EXTENT_ALLOC_ZONED)
+		return true;
+	if (!btrfs_block_group_should_use_size_class(bg))
+		return true;
+	if (ffe_ctl->loop >= LOOP_WRONG_SIZE_CLASS)
+		return true;
+	if (ffe_ctl->loop >= LOOP_UNSET_SIZE_CLASS &&
+	    bg->size_class == BTRFS_BG_SZ_NONE)
+		return true;
+	return ffe_ctl->size_class == bg->size_class;
+}
+
 static int prepare_allocation_clustered(struct btrfs_fs_info *fs_info,
 					struct find_free_extent_ctl *ffe_ctl,
 					struct btrfs_space_info *space_info,
@@ -4288,6 +4207,7 @@ static noinline int find_free_extent(struct btrfs_root *root,
 	ffe_ctl->total_free_space = 0;
 	ffe_ctl->found_offset = 0;
 	ffe_ctl->policy = BTRFS_EXTENT_ALLOC_CLUSTERED;
+	ffe_ctl->size_class = btrfs_calc_block_group_size_class(ffe_ctl->num_bytes);
 
 	if (btrfs_is_zoned(fs_info))
 		ffe_ctl->policy = BTRFS_EXTENT_ALLOC_ZONED;
@@ -4296,8 +4216,7 @@ static noinline int find_free_extent(struct btrfs_root *root,
 	ins->objectid = 0;
 	ins->offset = 0;
 
-	trace_find_free_extent(root, ffe_ctl->num_bytes, ffe_ctl->empty_size,
-			       ffe_ctl->flags);
+	trace_find_free_extent(root, ffe_ctl);
 
 	space_info = btrfs_find_space_info(fs_info, ffe_ctl->flags);
 	if (!space_info) {
@@ -4340,6 +4259,7 @@ static noinline int find_free_extent(struct btrfs_root *root,
 							block_group->flags);
 				btrfs_lock_block_group(block_group,
 						       ffe_ctl->delalloc);
+				ffe_ctl->hinted = true;
 				goto have_block_group;
 			}
 		} else if (block_group) {
@@ -4347,6 +4267,7 @@ static noinline int find_free_extent(struct btrfs_root *root,
 		}
 	}
 search:
+	trace_find_free_extent_search_loop(root, ffe_ctl);
 	ffe_ctl->have_caching_bg = false;
 	if (ffe_ctl->index == btrfs_bg_flags_to_raid_index(ffe_ctl->flags) ||
 	    ffe_ctl->index == 0)
@@ -4356,6 +4277,7 @@ search:
 			    &space_info->block_groups[ffe_ctl->index], list) {
 		struct btrfs_block_group *bg_ret;
 
+		ffe_ctl->hinted = false;
 		/* If the block group is read-only, we can skip it entirely. */
 		if (unlikely(block_group->ro)) {
 			if (ffe_ctl->for_treelog)
@@ -4397,6 +4319,7 @@ search:
 		}
 
 have_block_group:
+		trace_find_free_extent_have_block_group(root, ffe_ctl, block_group);
 		ffe_ctl->cached = btrfs_block_group_done(block_group);
 		if (unlikely(!ffe_ctl->cached)) {
 			ffe_ctl->have_caching_bg = true;
@@ -4421,6 +4344,9 @@ have_block_group:
 		if (unlikely(block_group->cached == BTRFS_CACHE_ERROR))
 			goto loop;
 
+		if (!find_free_extent_check_size_class(ffe_ctl, block_group))
+			goto loop;
+
 		bg_ret = NULL;
 		ret = do_allocation(block_group, ffe_ctl, &bg_ret);
 		if (ret == 0) {
@@ -4455,7 +4381,8 @@ have_block_group:
 
 		ret = btrfs_add_reserved_bytes(block_group, ffe_ctl->ram_bytes,
 					       ffe_ctl->num_bytes,
-					       ffe_ctl->delalloc);
+					       ffe_ctl->delalloc,
+					       ffe_ctl->loop >= LOOP_WRONG_SIZE_CLASS);
 		if (ret == -EAGAIN) {
 			btrfs_add_free_space_unused(block_group,
 					ffe_ctl->found_offset,
@@ -4468,8 +4395,7 @@ have_block_group:
 		ins->objectid = ffe_ctl->search_start;
 		ins->offset = ffe_ctl->num_bytes;
 
-		trace_btrfs_reserve_extent(block_group, ffe_ctl->search_start,
-					   ffe_ctl->num_bytes);
+		trace_btrfs_reserve_extent(block_group, ffe_ctl);
 		btrfs_release_block_group(block_group, ffe_ctl->delalloc);
 		break;
 loop:
@@ -4912,7 +4838,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	btrfs_set_buffer_lockdep_class(lockdep_owner, buf, level);
 
 	__btrfs_tree_lock(buf, nest);
-	btrfs_clean_tree_block(buf);
+	btrfs_clear_buffer_dirty(trans, buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
 	clear_bit(EXTENT_BUFFER_NO_CHECK, &buf->bflags);
 
@@ -5542,13 +5468,12 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 				}
 			}
 		}
-		/* make block locked assertion in btrfs_clean_tree_block happy */
-		if (!path->locks[level] &&
-		    btrfs_header_generation(eb) == trans->transid) {
+		/* Make block locked assertion in btrfs_clear_buffer_dirty happy. */
+		if (!path->locks[level]) {
 			btrfs_tree_lock(eb);
 			path->locks[level] = BTRFS_WRITE_LOCK;
 		}
-		btrfs_clean_tree_block(eb);
+		btrfs_clear_buffer_dirty(trans, eb);
 	}
 
 	if (eb == root->node) {
diff --git a/fs/btrfs/extent-tree.h b/fs/btrfs/extent-tree.h
index ae5425253603..0c958fc1b3b8 100644
--- a/fs/btrfs/extent-tree.h
+++ b/fs/btrfs/extent-tree.h
@@ -3,6 +3,87 @@
 #ifndef BTRFS_EXTENT_TREE_H
 #define BTRFS_EXTENT_TREE_H
 
+#include "misc.h"
+#include "block-group.h"
+
+struct btrfs_free_cluster;
+
+enum btrfs_extent_allocation_policy {
+	BTRFS_EXTENT_ALLOC_CLUSTERED,
+	BTRFS_EXTENT_ALLOC_ZONED,
+};
+
+struct find_free_extent_ctl {
+	/* Basic allocation info */
+	u64 ram_bytes;
+	u64 num_bytes;
+	u64 min_alloc_size;
+	u64 empty_size;
+	u64 flags;
+	int delalloc;
+
+	/* Where to start the search inside the bg */
+	u64 search_start;
+
+	/* For clustered allocation */
+	u64 empty_cluster;
+	struct btrfs_free_cluster *last_ptr;
+	bool use_cluster;
+
+	bool have_caching_bg;
+	bool orig_have_caching_bg;
+
+	/* Allocation is called for tree-log */
+	bool for_treelog;
+
+	/* Allocation is called for data relocation */
+	bool for_data_reloc;
+
+	/* RAID index, converted from flags */
+	int index;
+
+	/*
+	 * Current loop number, check find_free_extent_update_loop() for details
+	 */
+	int loop;
+
+	/*
+	 * Whether we're refilling a cluster, if true we need to re-search
+	 * current block group but don't try to refill the cluster again.
+	 */
+	bool retry_clustered;
+
+	/*
+	 * Whether we're updating free space cache, if true we need to re-search
+	 * current block group but don't try updating free space cache again.
+	 */
+	bool retry_unclustered;
+
+	/* If current block group is cached */
+	int cached;
+
+	/* Max contiguous hole found */
+	u64 max_extent_size;
+
+	/* Total free space from free space cache, not always contiguous */
+	u64 total_free_space;
+
+	/* Found result */
+	u64 found_offset;
+
+	/* Hint where to start looking for an empty space */
+	u64 hint_byte;
+
+	/* Allocation policy */
+	enum btrfs_extent_allocation_policy policy;
+
+	/* Whether or not the allocator is currently following a hint */
+	bool hinted;
+
+	/* Size class of block groups to prefer in early loops */
+	enum btrfs_block_group_size_class size_class;
+};
+
 enum btrfs_inline_ref_type {
 	BTRFS_REF_TYPE_INVALID,
 	BTRFS_REF_TYPE_BLOCK,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3bbf8703db2a..c25fa74d7615 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -36,6 +36,7 @@
 #include "file.h"
 #include "dev-replace.h"
 #include "super.h"
+#include "transaction.h"
 
 static struct kmem_cache *extent_buffer_cache;
 
@@ -99,7 +100,6 @@ struct btrfs_bio_ctrl {
 	struct bio *bio;
 	int mirror_num;
 	enum btrfs_compression_type compress_type;
-	u32 len_to_stripe_boundary;
 	u32 len_to_oe_boundary;
 	btrfs_bio_end_io_t end_io_func;
 
@@ -126,7 +126,7 @@ static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
 {
 	struct bio *bio;
 	struct bio_vec *bv;
-	struct btrfs_inode *inode;
+	struct inode *inode;
 	int mirror_num;
 
 	if (!bio_ctrl->bio)
@@ -134,15 +134,13 @@ static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
 
 	bio = bio_ctrl->bio;
 	bv = bio_first_bvec_all(bio);
-	inode = BTRFS_I(bv->bv_page->mapping->host);
+	inode = bv->bv_page->mapping->host;
 	mirror_num = bio_ctrl->mirror_num;
 
 	/* Caller should ensure the bio has at least some range added */
 	ASSERT(bio->bi_iter.bi_size);
 
-	btrfs_bio(bio)->file_offset = page_offset(bv->bv_page) + bv->bv_offset;
-
-	if (!is_data_inode(&inode->vfs_inode)) {
+	if (!is_data_inode(inode)) {
 		if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
 			/*
 			 * For metadata read, we should have the parent_check,
@@ -153,14 +151,15 @@ static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
 			       bio_ctrl->parent_check,
 			       sizeof(struct btrfs_tree_parent_check));
 		}
-		btrfs_submit_metadata_bio(inode, bio, mirror_num);
-	} else if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
-		btrfs_submit_data_write_bio(inode, bio, mirror_num);
-	} else {
-		btrfs_submit_data_read_bio(inode, bio, mirror_num,
-					   bio_ctrl->compress_type);
+		bio->bi_opf |= REQ_META;
 	}
 
+	if (btrfs_op(bio) == BTRFS_MAP_READ &&
+	    bio_ctrl->compress_type != BTRFS_COMPRESS_NONE)
+		btrfs_submit_compressed_read(inode, bio, mirror_num);
+	else
+		btrfs_submit_bio(bio, mirror_num);
+
 	/* The bio is owned by the end_io handler now */
 	bio_ctrl->bio = NULL;
 }
@@ -515,266 +514,6 @@ void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 			       start, end, page_ops, NULL);
 }
 
-static int insert_failrec(struct btrfs_inode *inode,
-			  struct io_failure_record *failrec)
-{
-	struct rb_node *exist;
-
-	spin_lock(&inode->io_failure_lock);
-	exist = rb_simple_insert(&inode->io_failure_tree, failrec->bytenr,
-				 &failrec->rb_node);
-	spin_unlock(&inode->io_failure_lock);
-
-	return (exist == NULL) ? 0 : -EEXIST;
-}
-
-static struct io_failure_record *get_failrec(struct btrfs_inode *inode, u64 start)
-{
-	struct rb_node *node;
-	struct io_failure_record *failrec = ERR_PTR(-ENOENT);
-
-	spin_lock(&inode->io_failure_lock);
-	node = rb_simple_search(&inode->io_failure_tree, start);
-	if (node)
-		failrec = rb_entry(node, struct io_failure_record, rb_node);
-	spin_unlock(&inode->io_failure_lock);
-	return failrec;
-}
-
-static void free_io_failure(struct btrfs_inode *inode,
-			    struct io_failure_record *rec)
-{
-	spin_lock(&inode->io_failure_lock);
-	rb_erase(&rec->rb_node, &inode->io_failure_tree);
-	spin_unlock(&inode->io_failure_lock);
-
-	kfree(rec);
-}
-
-static int next_mirror(const struct io_failure_record *failrec, int cur_mirror)
-{
-	if (cur_mirror == failrec->num_copies)
-		return cur_mirror + 1 - failrec->num_copies;
-	return cur_mirror + 1;
-}
-
-static int prev_mirror(const struct io_failure_record *failrec, int cur_mirror)
-{
-	if (cur_mirror == 1)
-		return failrec->num_copies;
-	return cur_mirror - 1;
-}
-
-/*
- * each time an IO finishes, we do a fast check in the IO failure tree
- * to see if we need to process or clean up an io_failure_record
- */
-int btrfs_clean_io_failure(struct btrfs_inode *inode, u64 start,
-			   struct page *page, unsigned int pg_offset)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	struct extent_io_tree *io_tree = &inode->io_tree;
-	u64 ino = btrfs_ino(inode);
-	u64 locked_start, locked_end;
-	struct io_failure_record *failrec;
-	int mirror;
-	int ret;
-
-	failrec = get_failrec(inode, start);
-	if (IS_ERR(failrec))
-		return 0;
-
-	BUG_ON(!failrec->this_mirror);
-
-	if (sb_rdonly(fs_info->sb))
-		goto out;
-
-	ret = find_first_extent_bit(io_tree, failrec->bytenr, &locked_start,
-				    &locked_end, EXTENT_LOCKED, NULL);
-	if (ret || locked_start > failrec->bytenr ||
-	    locked_end < failrec->bytenr + failrec->len - 1)
-		goto out;
-
-	mirror = failrec->this_mirror;
-	do {
-		mirror = prev_mirror(failrec, mirror);
-		btrfs_repair_io_failure(fs_info, ino, start, failrec->len,
-				  failrec->logical, page, pg_offset, mirror);
-	} while (mirror != failrec->failed_mirror);
-
-out:
-	free_io_failure(inode, failrec);
-	return 0;
-}
-
-/*
- * Can be called when
- * - hold extent lock
- * - under ordered extent
- * - the inode is freeing
- */
-void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, u64 end)
-{
-	struct io_failure_record *failrec;
-	struct rb_node *node, *next;
-
-	if (RB_EMPTY_ROOT(&inode->io_failure_tree))
-		return;
-
-	spin_lock(&inode->io_failure_lock);
-	node = rb_simple_search_first(&inode->io_failure_tree, start);
-	while (node) {
-		failrec = rb_entry(node, struct io_failure_record, rb_node);
-		if (failrec->bytenr > end)
-			break;
-
-		next = rb_next(node);
-		rb_erase(&failrec->rb_node, &inode->io_failure_tree);
-		kfree(failrec);
-
-		node = next;
-	}
-	spin_unlock(&inode->io_failure_lock);
-}
-
-static struct io_failure_record *btrfs_get_io_failure_record(struct inode *inode,
-							     struct btrfs_bio *bbio,
-							     unsigned int bio_offset)
-{
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	u64 start = bbio->file_offset + bio_offset;
-	struct io_failure_record *failrec;
-	const u32 sectorsize = fs_info->sectorsize;
-	int ret;
-
-	failrec = get_failrec(BTRFS_I(inode), start);
-	if (!IS_ERR(failrec)) {
-		btrfs_debug(fs_info,
-	"Get IO Failure Record: (found) logical=%llu, start=%llu, len=%llu",
-			failrec->logical, failrec->bytenr, failrec->len);
-		/*
-		 * when data can be on disk more than twice, add to failrec here
-		 * (e.g. with a list for failed_mirror) to make
-		 * clean_io_failure() clean all those errors at once.
-		 */
-		ASSERT(failrec->this_mirror == bbio->mirror_num);
-		ASSERT(failrec->len == fs_info->sectorsize);
-		return failrec;
-	}
-
-	failrec = kzalloc(sizeof(*failrec), GFP_NOFS);
-	if (!failrec)
-		return ERR_PTR(-ENOMEM);
-
-	RB_CLEAR_NODE(&failrec->rb_node);
-	failrec->bytenr = start;
-	failrec->len = sectorsize;
-	failrec->failed_mirror = bbio->mirror_num;
-	failrec->this_mirror = bbio->mirror_num;
-	failrec->logical = (bbio->iter.bi_sector << SECTOR_SHIFT) + bio_offset;
-
-	btrfs_debug(fs_info,
-		    "new io failure record logical %llu start %llu",
-		    failrec->logical, start);
-
-	failrec->num_copies = btrfs_num_copies(fs_info, failrec->logical, sectorsize);
-	if (failrec->num_copies == 1) {
-		/*
-		 * We only have a single copy of the data, so don't bother with
-		 * all the retry and error correction code that follows. No
-		 * matter what the error is, it is very likely to persist.
-		 */
-		btrfs_debug(fs_info,
-			"cannot repair logical %llu num_copies %d",
-			failrec->logical, failrec->num_copies);
-		kfree(failrec);
-		return ERR_PTR(-EIO);
-	}
-
-	/* Set the bits in the private failure tree */
-	ret = insert_failrec(BTRFS_I(inode), failrec);
-	if (ret) {
-		kfree(failrec);
-		return ERR_PTR(ret);
-	}
-
-	return failrec;
-}
-
-int btrfs_repair_one_sector(struct btrfs_inode *inode, struct btrfs_bio *failed_bbio,
-			    u32 bio_offset, struct page *page, unsigned int pgoff,
-			    bool submit_buffered)
-{
-	u64 start = failed_bbio->file_offset + bio_offset;
-	struct io_failure_record *failrec;
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	struct bio *failed_bio = &failed_bbio->bio;
-	const int icsum = bio_offset >> fs_info->sectorsize_bits;
-	struct bio *repair_bio;
-	struct btrfs_bio *repair_bbio;
-
-	btrfs_debug(fs_info,
-		   "repair read error: read error at %llu", start);
-
-	BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
-
-	failrec = btrfs_get_io_failure_record(&inode->vfs_inode, failed_bbio, bio_offset);
-	if (IS_ERR(failrec))
-		return PTR_ERR(failrec);
-
-	/*
-	 * There are two premises:
-	 * a) deliver good data to the caller
-	 * b) correct the bad sectors on disk
-	 *
-	 * Since we're only doing repair for one sector, we only need to get
-	 * a good copy of the failed sector and if we succeed, we have setup
-	 * everything for btrfs_repair_io_failure to do the rest for us.
-	 */
-	failrec->this_mirror = next_mirror(failrec, failrec->this_mirror);
-	if (failrec->this_mirror == failrec->failed_mirror) {
-		btrfs_debug(fs_info,
-			"failed to repair num_copies %d this_mirror %d failed_mirror %d",
-			failrec->num_copies, failrec->this_mirror, failrec->failed_mirror);
-		free_io_failure(inode, failrec);
-		return -EIO;
-	}
-
-	repair_bio = btrfs_bio_alloc(1, REQ_OP_READ, failed_bbio->end_io,
-				     failed_bbio->private);
-	repair_bbio = btrfs_bio(repair_bio);
-	repair_bbio->file_offset = start;
-	repair_bio->bi_iter.bi_sector = failrec->logical >> 9;
-
-	if (failed_bbio->csum) {
-		const u32 csum_size = fs_info->csum_size;
-
-		repair_bbio->csum = repair_bbio->csum_inline;
-		memcpy(repair_bbio->csum,
-		       failed_bbio->csum + csum_size * icsum, csum_size);
-	}
-
-	bio_add_page(repair_bio, page, failrec->len, pgoff);
-	repair_bbio->iter = repair_bio->bi_iter;
-
-	btrfs_debug(fs_info,
-		    "repair read error: submitting new read to mirror %d",
-		    failrec->this_mirror);
-
-	/*
-	 * At this point we have a bio, so any errors from bio submission will
-	 * be handled by the endio on the repair_bio, so we can't return an
-	 * error here.
-	 */
-	if (submit_buffered)
-		btrfs_submit_data_read_bio(inode, repair_bio,
-					   failrec->this_mirror, 0);
-	else
-		btrfs_submit_dio_repair_bio(inode, repair_bio, failrec->this_mirror);
-
-	return BLK_STS_OK;
-}
-
 static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
@@ -803,79 +542,6 @@ static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
 		btrfs_subpage_end_reader(fs_info, page, start, len);
 }
 
-static void end_sector_io(struct page *page, u64 offset, bool uptodate)
-{
-	struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
-	const u32 sectorsize = inode->root->fs_info->sectorsize;
-
-	end_page_read(page, uptodate, offset, sectorsize);
-	unlock_extent(&inode->io_tree, offset, offset + sectorsize - 1, NULL);
-}
-
-static void submit_data_read_repair(struct inode *inode,
-				    struct btrfs_bio *failed_bbio,
-				    u32 bio_offset, const struct bio_vec *bvec,
-				    unsigned int error_bitmap)
-{
-	const unsigned int pgoff = bvec->bv_offset;
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct page *page = bvec->bv_page;
-	const u64 start = page_offset(bvec->bv_page) + bvec->bv_offset;
-	const u64 end = start + bvec->bv_len - 1;
-	const u32 sectorsize = fs_info->sectorsize;
-	const int nr_bits = (end + 1 - start) >> fs_info->sectorsize_bits;
-	int i;
-
-	BUG_ON(bio_op(&failed_bbio->bio) == REQ_OP_WRITE);
-
-	/* This repair is only for data */
-	ASSERT(is_data_inode(inode));
-
-	/* We're here because we had some read errors or csum mismatch */
-	ASSERT(error_bitmap);
-
-	/*
-	 * We only get called on buffered IO, thus page must be mapped and bio
-	 * must not be cloned.
-	 */
-	ASSERT(page->mapping && !bio_flagged(&failed_bbio->bio, BIO_CLONED));
-
-	/* Iterate through all the sectors in the range */
-	for (i = 0; i < nr_bits; i++) {
-		const unsigned int offset = i * sectorsize;
-		bool uptodate = false;
-		int ret;
-
-		if (!(error_bitmap & (1U << i))) {
-			/*
-			 * This sector has no error, just end the page read
-			 * and unlock the range.
-			 */
-			uptodate = true;
-			goto next;
-		}
-
-		ret = btrfs_repair_one_sector(BTRFS_I(inode), failed_bbio,
-				bio_offset + offset, page, pgoff + offset,
-				true);
-		if (!ret) {
-			/*
-			 * We have submitted the read repair, the page release
-			 * will be handled by the endio function of the
-			 * submitted repair bio.
-			 * Thus we don't need to do any thing here.
-			 */
-			continue;
-		}
-		/*
-		 * Continue on failed repair, otherwise the remaining sectors
-		 * will not be properly unlocked.
-		 */
-next:
-		end_sector_io(page, start + offset, uptodate);
-	}
-}
-
 /* lots and lots of room for performance fixes in the end_bio funcs */
 
 void end_extent_writepage(struct page *page, int err, u64 start, u64 end)
@@ -919,7 +585,6 @@ static void end_bio_extent_writepage(struct btrfs_bio *bbio)
 	u64 start;
 	u64 end;
 	struct bvec_iter_all iter_all;
-	bool first_bvec = true;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, iter_all) {
@@ -941,11 +606,6 @@ static void end_bio_extent_writepage(struct btrfs_bio *bbio)
 		start = page_offset(page) + bvec->bv_offset;
 		end = start + bvec->bv_len - 1;
 
-		if (first_bvec) {
-			btrfs_record_physical_zoned(inode, start, bio);
-			first_bvec = false;
-		}
-
 		end_extent_writepage(page, error, start, end);
 
 		btrfs_page_clear_writeback(fs_info, page, start, bvec->bv_len);
@@ -1093,8 +753,6 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 		struct inode *inode = page->mapping->host;
 		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 		const u32 sectorsize = fs_info->sectorsize;
-		unsigned int error_bitmap = (unsigned int)-1;
-		bool repair = false;
 		u64 start;
 		u64 end;
 		u32 len;
@@ -1126,25 +784,14 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 		len = bvec->bv_len;
 
 		mirror = bbio->mirror_num;
-		if (likely(uptodate)) {
-			if (is_data_inode(inode)) {
-				error_bitmap = btrfs_verify_data_csum(bbio,
-						bio_offset, page, start, end);
-				if (error_bitmap)
-					uptodate = false;
-			} else {
-				if (btrfs_validate_metadata_buffer(bbio,
-						page, start, end, mirror))
-					uptodate = false;
-			}
-		}
+		if (uptodate && !is_data_inode(inode) &&
+		    btrfs_validate_metadata_buffer(bbio, page, start, end, mirror))
+			uptodate = false;
 
 		if (likely(uptodate)) {
 			loff_t i_size = i_size_read(inode);
 			pgoff_t end_index = i_size >> PAGE_SHIFT;
 
-			btrfs_clean_io_failure(BTRFS_I(inode), start, page, 0);
-
 			/*
 			 * Zero out the remaining part if this range straddles
 			 * i_size.
@@ -1161,19 +808,7 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 				zero_user_segment(page, zero_start,
 						  offset_in_page(end) + 1);
 			}
-		} else if (is_data_inode(inode)) {
-			/*
-			 * Only try to repair bios that actually made it to a
-			 * device.  If the bio failed to be submitted mirror
-			 * is 0 and we need to fail it without retrying.
-			 *
-			 * This also includes the high level bios for compressed
-			 * extents - these never make it to a device and repair
-			 * is already handled on the lower compressed bio.
-			 */
-			if (mirror > 0)
-				repair = true;
-		} else {
+		} else if (!is_data_inode(inode)) {
 			struct extent_buffer *eb;
 
 			eb = find_extent_buffer_readpage(fs_info, page, start);
@@ -1182,19 +817,10 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 			atomic_dec(&eb->io_pages);
 		}
 
-		if (repair) {
-			/*
-			 * submit_data_read_repair() will handle all the good
-			 * and bad sectors, we just continue to the next bvec.
-			 */
-			submit_data_read_repair(inode, bbio, bio_offset, bvec,
-						error_bitmap);
-		} else {
-			/* Update page status and unlock */
-			end_page_read(page, uptodate, start, len);
-			endio_readpage_release_extent(&processed, BTRFS_I(inode),
-					start, end, PageUptodate(page));
-		}
+		/* Update page status and unlock. */
+		end_page_read(page, uptodate, start, len);
+		endio_readpage_release_extent(&processed, BTRFS_I(inode),
+					      start, end, PageUptodate(page));
 
 		ASSERT(bio_offset + len > bio_offset);
 		bio_offset += len;
@@ -1202,7 +828,6 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 	}
 	/* Release the last extent */
 	endio_readpage_release_extent(&processed, NULL, 0, 0, false);
-	btrfs_bio_free_csum(bbio);
 	bio_put(bio);
 }
 
@@ -1270,11 +895,10 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl,
 	u32 real_size;
 	const sector_t sector = disk_bytenr >> SECTOR_SHIFT;
 	bool contig = false;
-	int ret;
 
 	ASSERT(bio);
 	/* The limit should be calculated when bio_ctrl->bio is allocated */
-	ASSERT(bio_ctrl->len_to_oe_boundary && bio_ctrl->len_to_stripe_boundary);
+	ASSERT(bio_ctrl->len_to_oe_boundary);
 	if (bio_ctrl->compress_type != compress_type)
 		return 0;
 
@@ -1310,9 +934,7 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl,
 	if (!contig)
 		return 0;
 
-	real_size = min(bio_ctrl->len_to_oe_boundary,
-			bio_ctrl->len_to_stripe_boundary) - bio_size;
-	real_size = min(real_size, size);
+	real_size = min(bio_ctrl->len_to_oe_boundary - bio_size, size);
 
 	/*
 	 * If real_size is 0, never call bio_add_*_page(), as even size is 0,
@@ -1321,82 +943,45 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl,
 	if (real_size == 0)
 		return 0;
 
-	if (bio_op(bio) == REQ_OP_ZONE_APPEND)
-		ret = bio_add_zone_append_page(bio, page, real_size, pg_offset);
-	else
-		ret = bio_add_page(bio, page, real_size, pg_offset);
-
-	return ret;
+	return bio_add_page(bio, page, real_size, pg_offset);
 }
 
-static int calc_bio_boundaries(struct btrfs_bio_ctrl *bio_ctrl,
-			       struct btrfs_inode *inode, u64 file_offset)
+static void calc_bio_boundaries(struct btrfs_bio_ctrl *bio_ctrl,
+				struct btrfs_inode *inode, u64 file_offset)
 {
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	struct btrfs_io_geometry geom;
 	struct btrfs_ordered_extent *ordered;
-	struct extent_map *em;
-	u64 logical = (bio_ctrl->bio->bi_iter.bi_sector << SECTOR_SHIFT);
-	int ret;
 
 	/*
-	 * Pages for compressed extent are never submitted to disk directly,
-	 * thus it has no real boundary, just set them to U32_MAX.
-	 *
-	 * The split happens for real compressed bio, which happens in
-	 * btrfs_submit_compressed_read/write().
+	 * Limit the extent to the ordered boundary for Zone Append.
+	 * Compressed bios aren't submitted directly, so it doesn't apply to
+	 * them.
 	 */
-	if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) {
-		bio_ctrl->len_to_oe_boundary = U32_MAX;
-		bio_ctrl->len_to_stripe_boundary = U32_MAX;
-		return 0;
-	}
-	em = btrfs_get_chunk_map(fs_info, logical, fs_info->sectorsize);
-	if (IS_ERR(em))
-		return PTR_ERR(em);
-	ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(bio_ctrl->bio),
-				    logical, &geom);
-	free_extent_map(em);
-	if (ret < 0) {
-		return ret;
-	}
-	if (geom.len > U32_MAX)
-		bio_ctrl->len_to_stripe_boundary = U32_MAX;
-	else
-		bio_ctrl->len_to_stripe_boundary = (u32)geom.len;
-
-	if (bio_op(bio_ctrl->bio) != REQ_OP_ZONE_APPEND) {
-		bio_ctrl->len_to_oe_boundary = U32_MAX;
-		return 0;
-	}
-
-	/* Ordered extent not yet created, so we're good */
-	ordered = btrfs_lookup_ordered_extent(inode, file_offset);
-	if (!ordered) {
-		bio_ctrl->len_to_oe_boundary = U32_MAX;
-		return 0;
+	if (bio_ctrl->compress_type == BTRFS_COMPRESS_NONE &&
+	    btrfs_use_zone_append(btrfs_bio(bio_ctrl->bio))) {
+		ordered = btrfs_lookup_ordered_extent(inode, file_offset);
+		if (ordered) {
+			bio_ctrl->len_to_oe_boundary = min_t(u32, U32_MAX,
+					ordered->file_offset +
+					ordered->disk_num_bytes - file_offset);
+			btrfs_put_ordered_extent(ordered);
+			return;
+		}
 	}
 
-	bio_ctrl->len_to_oe_boundary = min_t(u32, U32_MAX,
-		ordered->disk_bytenr + ordered->disk_num_bytes - logical);
-	btrfs_put_ordered_extent(ordered);
-	return 0;
+	bio_ctrl->len_to_oe_boundary = U32_MAX;
 }
 
-static int alloc_new_bio(struct btrfs_inode *inode,
-			 struct btrfs_bio_ctrl *bio_ctrl,
-			 struct writeback_control *wbc,
-			 blk_opf_t opf,
-			 u64 disk_bytenr, u32 offset, u64 file_offset,
-			 enum btrfs_compression_type compress_type)
+static void alloc_new_bio(struct btrfs_inode *inode,
+			  struct btrfs_bio_ctrl *bio_ctrl,
+			  struct writeback_control *wbc, blk_opf_t opf,
+			  u64 disk_bytenr, u32 offset, u64 file_offset,
+			  enum btrfs_compression_type compress_type)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct bio *bio;
-	int ret;
 
-	ASSERT(bio_ctrl->end_io_func);
-
-	bio = btrfs_bio_alloc(BIO_MAX_VECS, opf, bio_ctrl->end_io_func, NULL);
+	bio = btrfs_bio_alloc(BIO_MAX_VECS, opf, inode, bio_ctrl->end_io_func,
+			      NULL);
 	/*
 	 * For compressed page range, its disk_bytenr is always @disk_bytenr
 	 * passed in, no matter if we have added any range into previous bio.
@@ -1405,48 +990,21 @@ static int alloc_new_bio(struct btrfs_inode *inode,
 		bio->bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT;
 	else
 		bio->bi_iter.bi_sector = (disk_bytenr + offset) >> SECTOR_SHIFT;
+	btrfs_bio(bio)->file_offset = file_offset;
 	bio_ctrl->bio = bio;
 	bio_ctrl->compress_type = compress_type;
-	ret = calc_bio_boundaries(bio_ctrl, inode, file_offset);
-	if (ret < 0)
-		goto error;
+	calc_bio_boundaries(bio_ctrl, inode, file_offset);
 
 	if (wbc) {
 		/*
-		 * For Zone append we need the correct block_device that we are
-		 * going to write to set in the bio to be able to respect the
-		 * hardware limitation.  Look it up here:
+		 * Pick the last added device to support cgroup writeback.  For
+		 * multi-device file systems this means blk-cgroup policies have
+		 * to always be set on the last added/replaced device.
+		 * This is a bit odd but has been like that for a long time.
 		 */
-		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
-			struct btrfs_device *dev;
-
-			dev = btrfs_zoned_get_device(fs_info, disk_bytenr,
-						     fs_info->sectorsize);
-			if (IS_ERR(dev)) {
-				ret = PTR_ERR(dev);
-				goto error;
-			}
-
-			bio_set_dev(bio, dev->bdev);
-		} else {
-			/*
-			 * Otherwise pick the last added device to support
-			 * cgroup writeback.  For multi-device file systems this
-			 * means blk-cgroup policies have to always be set on the
-			 * last added/replaced device.  This is a bit odd but has
-			 * been like that for a long time.
-			 */
-			bio_set_dev(bio, fs_info->fs_devices->latest_dev->bdev);
-		}
+		bio_set_dev(bio, fs_info->fs_devices->latest_dev->bdev);
 		wbc_init_bio(wbc, bio);
-	} else {
-		ASSERT(bio_op(bio) != REQ_OP_ZONE_APPEND);
 	}
-	return 0;
-error:
-	bio_ctrl->bio = NULL;
-	btrfs_bio_end_io(btrfs_bio(bio), errno_to_blk_status(ret));
-	return ret;
 }
 
 /*
@@ -1472,7 +1030,6 @@ static int submit_extent_page(blk_opf_t opf,
 			      enum btrfs_compression_type compress_type,
 			      bool force_bio_submit)
 {
-	int ret = 0;
 	struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
 	unsigned int cur = pg_offset;
 
@@ -1492,12 +1049,9 @@ static int submit_extent_page(blk_opf_t opf,
 
 		/* Allocate new bio if needed */
 		if (!bio_ctrl->bio) {
-			ret = alloc_new_bio(inode, bio_ctrl, wbc, opf,
-					    disk_bytenr, offset,
-					    page_offset(page) + cur,
-					    compress_type);
-			if (ret < 0)
-				return ret;
+			alloc_new_bio(inode, bio_ctrl, wbc, opf, disk_bytenr,
+				      offset, page_offset(page) + cur,
+				      compress_type);
 		}
 		/*
 		 * We must go through btrfs_bio_add_page() to ensure each
@@ -2054,10 +1608,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 		 * find_next_dirty_byte() are all exclusive
 		 */
 		iosize = min(min(em_end, end + 1), dirty_range_end) - cur;
-
-		if (btrfs_use_zone_append(inode, em->block_start))
-			op = REQ_OP_ZONE_APPEND;
-
 		free_extent_map(em);
 		em = NULL;
 
@@ -2361,13 +1911,6 @@ static void set_btree_ioerr(struct page *page, struct extent_buffer *eb)
 	mapping_set_error(page->mapping, -EIO);
 
 	/*
-	 * If we error out, we should add back the dirty_metadata_bytes
-	 * to make it consistent.
-	 */
-	percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
-				 eb->len, fs_info->dirty_metadata_batch);
-
-	/*
 	 * If writeback for a btree extent that doesn't belong to a log tree
 	 * failed, increment the counter transaction->eb_write_errors.
 	 * We do this because while the transaction is running and before it's
@@ -4724,12 +4267,25 @@ static void clear_subpage_extent_buffer_dirty(const struct extent_buffer *eb)
 	WARN_ON(atomic_read(&eb->refs) == 0);
 }
 
-void clear_extent_buffer_dirty(const struct extent_buffer *eb)
+void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
+			      struct extent_buffer *eb)
 {
+	struct btrfs_fs_info *fs_info = eb->fs_info;
 	int i;
 	int num_pages;
 	struct page *page;
 
+	btrfs_assert_tree_write_locked(eb);
+
+	if (trans && btrfs_header_generation(eb) != trans->transid)
+		return;
+
+	if (!test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags))
+		return;
+
+	percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, -eb->len,
+				 fs_info->dirty_metadata_batch);
+
 	if (eb->fs_info->nodesize < PAGE_SIZE)
 		return clear_subpage_extent_buffer_dirty(eb);
 
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index a2c82448b2e0..4341ad978fb8 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -11,6 +11,8 @@
 #include "ulist.h"
 #include "misc.h"
 
+struct btrfs_trans_handle;
+
 enum {
 	EXTENT_BUFFER_UPTODATE,
 	EXTENT_BUFFER_DIRTY,
@@ -60,11 +62,9 @@ enum {
 #define BITMAP_LAST_BYTE_MASK(nbits) \
 	(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
 
-struct btrfs_bio;
 struct btrfs_root;
 struct btrfs_inode;
 struct btrfs_fs_info;
-struct io_failure_record;
 struct extent_io_tree;
 struct btrfs_tree_parent_check;
 
@@ -262,7 +262,6 @@ void extent_buffer_bitmap_set(const struct extent_buffer *eb, unsigned long star
 void extent_buffer_bitmap_clear(const struct extent_buffer *eb,
 				unsigned long start, unsigned long pos,
 				unsigned long len);
-void clear_extent_buffer_dirty(const struct extent_buffer *eb);
 bool set_extent_buffer_dirty(struct extent_buffer *eb);
 void set_extent_buffer_uptodate(struct extent_buffer *eb);
 void clear_extent_buffer_uptodate(struct extent_buffer *eb);
@@ -274,40 +273,13 @@ void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 				  u32 bits_to_clear, unsigned long page_ops);
 int extent_invalidate_folio(struct extent_io_tree *tree,
 			    struct folio *folio, size_t offset);
+void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
+			      struct extent_buffer *buf);
 
 int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array);
 
 void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
 
-/*
- * When IO fails, either with EIO or csum verification fails, we
- * try other mirrors that might have a good copy of the data.  This
- * io_failure_record is used to record state as we go through all the
- * mirrors.  If another mirror has good data, the sector is set up to date
- * and things continue.  If a good mirror can't be found, the original
- * 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 len;
-	u64 logical;
-	int this_mirror;
-	int failed_mirror;
-	int num_copies;
-};
-
-int btrfs_repair_one_sector(struct btrfs_inode *inode, struct btrfs_bio *failed_bbio,
-			    u32 bio_offset, struct page *page, unsigned int pgoff,
-			    bool submit_buffered);
-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,
 			     struct page *locked_page, u64 *start,
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 5de73466b2ca..41c77a100853 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -380,32 +380,25 @@ static int search_file_offset_in_bio(struct bio *bio, struct inode *inode,
 /*
  * Lookup the checksum for the read bio in csum tree.
  *
- * @inode:  inode that the bio is for.
- * @bio:    bio to look up.
- * @dst:    Buffer of size nblocks * btrfs_super_csum_size() used to return
- *          checksum (nblocks = bio->bi_iter.bi_size / fs_info->sectorsize). If
- *          NULL, the checksum buffer is allocated and returned in
- *          btrfs_bio(bio)->csum instead.
- *
  * Return: BLK_STS_RESOURCE if allocating memory fails, BLK_STS_OK otherwise.
  */
-blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst)
+blk_status_t btrfs_lookup_bio_sums(struct btrfs_bio *bbio)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
-	struct btrfs_bio *bbio = NULL;
+	struct btrfs_inode *inode = bbio->inode;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	struct extent_io_tree *io_tree = &inode->io_tree;
+	struct bio *bio = &bbio->bio;
 	struct btrfs_path *path;
 	const u32 sectorsize = fs_info->sectorsize;
 	const u32 csum_size = fs_info->csum_size;
 	u32 orig_len = bio->bi_iter.bi_size;
 	u64 orig_disk_bytenr = bio->bi_iter.bi_sector << SECTOR_SHIFT;
 	u64 cur_disk_bytenr;
-	u8 *csum;
 	const unsigned int nblocks = orig_len >> fs_info->sectorsize_bits;
 	int count = 0;
 	blk_status_t ret = BLK_STS_OK;
 
-	if ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) ||
+	if ((inode->flags & BTRFS_INODE_NODATASUM) ||
 	    test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state))
 		return BLK_STS_OK;
 
@@ -426,21 +419,14 @@ blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst
 	if (!path)
 		return BLK_STS_RESOURCE;
 
-	if (!dst) {
-		bbio = btrfs_bio(bio);
-
-		if (nblocks * csum_size > BTRFS_BIO_INLINE_CSUM_SIZE) {
-			bbio->csum = kmalloc_array(nblocks, csum_size, GFP_NOFS);
-			if (!bbio->csum) {
-				btrfs_free_path(path);
-				return BLK_STS_RESOURCE;
-			}
-		} else {
-			bbio->csum = bbio->csum_inline;
+	if (nblocks * csum_size > BTRFS_BIO_INLINE_CSUM_SIZE) {
+		bbio->csum = kmalloc_array(nblocks, csum_size, GFP_NOFS);
+		if (!bbio->csum) {
+			btrfs_free_path(path);
+			return BLK_STS_RESOURCE;
 		}
-		csum = bbio->csum;
 	} else {
-		csum = dst;
+		bbio->csum = bbio->csum_inline;
 	}
 
 	/*
@@ -456,7 +442,7 @@ blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst
 	 * read from the commit root and sidestep a nasty deadlock
 	 * between reading the free space cache and updating the csum tree.
 	 */
-	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+	if (btrfs_is_free_space_inode(inode)) {
 		path->search_commit_root = 1;
 		path->skip_locking = 1;
 	}
@@ -479,14 +465,15 @@ blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst
 		ASSERT(cur_disk_bytenr - orig_disk_bytenr < UINT_MAX);
 		sector_offset = (cur_disk_bytenr - orig_disk_bytenr) >>
 				fs_info->sectorsize_bits;
-		csum_dst = csum + sector_offset * csum_size;
+		csum_dst = bbio->csum + sector_offset * csum_size;
 
 		count = search_csum_tree(fs_info, path, cur_disk_bytenr,
 					 search_len, csum_dst);
 		if (count < 0) {
 			ret = errno_to_blk_status(count);
-			if (bbio)
-				btrfs_bio_free_csum(bbio);
+			if (bbio->csum != bbio->csum_inline)
+				kfree(bbio->csum);
+			bbio->csum = NULL;
 			break;
 		}
 
@@ -504,12 +491,13 @@ blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst
 			memset(csum_dst, 0, csum_size);
 			count = 1;
 
-			if (BTRFS_I(inode)->root->root_key.objectid ==
+			if (inode->root->root_key.objectid ==
 			    BTRFS_DATA_RELOC_TREE_OBJECTID) {
 				u64 file_offset;
 				int ret;
 
-				ret = search_file_offset_in_bio(bio, inode,
+				ret = search_file_offset_in_bio(bio,
+						&inode->vfs_inode,
 						cur_disk_bytenr, &file_offset);
 				if (ret)
 					set_extent_bits(io_tree, file_offset,
@@ -784,23 +772,16 @@ fail:
 
 /*
  * Calculate checksums of the data contained inside a bio.
- *
- * @inode:	 Owner of the data inside the bio
- * @bio:	 Contains the data to be checksummed
- * @offset:      If (u64)-1, @bio may contain discontiguous bio vecs, so the
- *               file offsets are determined from the page offsets in the bio.
- *               Otherwise, this is the starting file offset of the bio vecs in
- *               @bio, which must be contiguous.
- * @one_ordered: If true, @bio only refers to one ordered extent.
  */
-blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
-				u64 offset, bool one_ordered)
+blk_status_t btrfs_csum_one_bio(struct btrfs_bio *bbio)
 {
+	struct btrfs_inode *inode = bbio->inode;
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
+	struct bio *bio = &bbio->bio;
+	u64 offset = bbio->file_offset;
 	struct btrfs_ordered_sum *sums;
 	struct btrfs_ordered_extent *ordered = NULL;
-	const bool use_page_offsets = (offset == (u64)-1);
 	char *data;
 	struct bvec_iter iter;
 	struct bio_vec bvec;
@@ -828,9 +809,6 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
 	shash->tfm = fs_info->csum_shash;
 
 	bio_for_each_segment(bvec, bio, iter) {
-		if (use_page_offsets)
-			offset = page_offset(bvec.bv_page) + bvec.bv_offset;
-
 		if (!ordered) {
 			ordered = btrfs_lookup_ordered_extent(inode, offset);
 			/*
@@ -852,7 +830,7 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
 						 - 1);
 
 		for (i = 0; i < blockcount; i++) {
-			if (!one_ordered &&
+			if (!(bio->bi_opf & REQ_BTRFS_ONE_ORDERED) &&
 			    !in_range(offset, ordered->file_offset,
 				      ordered->num_bytes)) {
 				unsigned long bytes_left;
diff --git a/fs/btrfs/file-item.h b/fs/btrfs/file-item.h
index 031225668434..cd7f2ae515c0 100644
--- a/fs/btrfs/file-item.h
+++ b/fs/btrfs/file-item.h
@@ -38,7 +38,7 @@ static inline u32 btrfs_file_extent_calc_inline_size(u32 datasize)
 
 int btrfs_del_csums(struct btrfs_trans_handle *trans,
 		    struct btrfs_root *root, u64 bytenr, u64 len);
-blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst);
+blk_status_t btrfs_lookup_bio_sums(struct btrfs_bio *bbio);
 int btrfs_insert_hole_extent(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 objectid, u64 pos,
 			     u64 num_bytes);
@@ -49,8 +49,10 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans,
 int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct btrfs_ordered_sum *sums);
-blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
-				u64 offset, bool one_ordered);
+blk_status_t btrfs_csum_one_bio(struct btrfs_bio *bbio);
+int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
+			     struct list_head *list, int search_commit,
+			     bool nowait);
 int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
 			    struct list_head *list, int search_commit,
 			    bool nowait);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index af046d22300e..5cc5a1faaef5 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1017,7 +1017,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 				unlock_page(pages[i]);
 				put_page(pages[i]);
 			}
-			btrfs_start_ordered_extent(ordered, 1);
+			btrfs_start_ordered_extent(ordered);
 			btrfs_put_ordered_extent(ordered);
 			return -EAGAIN;
 		}
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index c667e878ef1a..4d155a48ec59 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1283,7 +1283,7 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info)
 	list_del(&free_space_root->dirty_list);
 
 	btrfs_tree_lock(free_space_root->node);
-	btrfs_clean_tree_block(free_space_root->node);
+	btrfs_clear_buffer_dirty(trans, free_space_root->node);
 	btrfs_tree_unlock(free_space_root->node);
 	btrfs_free_tree_block(trans, btrfs_root_id(free_space_root),
 			      free_space_root->node, 0, 1);
diff --git a/fs/btrfs/fs.c b/fs/btrfs/fs.c
index 5553e1f8afe8..31c1648bc0b4 100644
--- a/fs/btrfs/fs.c
+++ b/fs/btrfs/fs.c
@@ -24,6 +24,7 @@ void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag,
 				name, flag);
 		}
 		spin_unlock(&fs_info->super_lock);
+		set_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags);
 	}
 }
 
@@ -46,6 +47,7 @@ void __btrfs_clear_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag,
 				name, flag);
 		}
 		spin_unlock(&fs_info->super_lock);
+		set_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags);
 	}
 }
 
@@ -68,6 +70,7 @@ void __btrfs_set_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag,
 				name, flag);
 		}
 		spin_unlock(&fs_info->super_lock);
+		set_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags);
 	}
 }
 
@@ -90,5 +93,6 @@ void __btrfs_clear_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag,
 				name, flag);
 		}
 		spin_unlock(&fs_info->super_lock);
+		set_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags);
 	}
 }
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index 37b86acfcbcf..4c477eae6891 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -3,6 +3,7 @@
 #ifndef BTRFS_FS_H
 #define BTRFS_FS_H
 
+#include <linux/blkdev.h>
 #include <linux/fs.h>
 #include <linux/btrfs_tree.h>
 #include <linux/sizes.h>
@@ -125,6 +126,12 @@ enum {
 	 */
 	BTRFS_FS_NO_OVERCOMMIT,
 
+	/*
+	 * Indicate if we have some features changed, this is mostly for
+	 * cleaner thread to update the sysfs interface.
+	 */
+	BTRFS_FS_FEATURE_CHANGED,
+
 #if BITS_PER_LONG == 32
 	/* Indicate if we have error/warn message printed on 32bit systems */
 	BTRFS_FS_32BIT_ERROR,
@@ -742,8 +749,10 @@ struct btrfs_fs_info {
 	 */
 	u64 zone_size;
 
-	/* Max size to emit ZONE_APPEND write command */
+	/* Constraints for ZONE_APPEND commands: */
+	struct queue_limits limits;
 	u64 max_zone_append_size;
+
 	struct mutex zoned_meta_io_lock;
 	spinlock_t treelog_bg_lock;
 	u64 treelog_bg;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index efee6d35af52..6c18dc9a1831 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -84,27 +84,12 @@ struct btrfs_dio_data {
 };
 
 struct btrfs_dio_private {
-	struct btrfs_inode *inode;
-
-	/*
-	 * Since DIO can use anonymous page, we cannot use page_offset() to
-	 * grab the file offset, thus need a dedicated member for file offset.
-	 */
+	/* Range of I/O */
 	u64 file_offset;
-	/* Used for bio::bi_size */
 	u32 bytes;
 
-	/*
-	 * References to this structure. There is one reference per in-flight
-	 * bio plus one while we're still setting up.
-	 */
-	refcount_t refs;
-
-	/* Array of checksums */
-	u8 *csums;
-
 	/* This must be last */
-	struct bio bio;
+	struct btrfs_bio bbio;
 };
 
 static struct bio_set btrfs_dio_bioset;
@@ -228,7 +213,7 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
 {
 	unsigned long index = offset >> PAGE_SHIFT;
 	unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT;
-	u64 page_start, page_end;
+	u64 page_start = 0, page_end = 0;
 	struct page *page;
 
 	if (locked_page) {
@@ -2536,19 +2521,6 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
 }
 
 /*
- * in order to insert checksums into the metadata in large chunks,
- * we wait until bio submission time.   All the pages in the bio are
- * checksummed and sums are attached onto the ordered extent record.
- *
- * At IO completion time the cums attached on the ordered extent record
- * are inserted into the btree
- */
-blk_status_t btrfs_submit_bio_start(struct btrfs_inode *inode, struct bio *bio)
-{
-	return btrfs_csum_one_bio(inode, bio, (u64)-1, false);
-}
-
-/*
  * Split an extent_map at [start, start + len]
  *
  * This function is intended to be used only for extract_ordered_extent().
@@ -2663,19 +2635,19 @@ out:
 	return ret;
 }
 
-static blk_status_t extract_ordered_extent(struct btrfs_inode *inode,
-					   struct bio *bio, loff_t file_offset)
+blk_status_t btrfs_extract_ordered_extent(struct btrfs_bio *bbio)
 {
+	u64 start = (u64)bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT;
+	u64 len = bbio->bio.bi_iter.bi_size;
+	struct btrfs_inode *inode = bbio->inode;
 	struct btrfs_ordered_extent *ordered;
-	u64 start = (u64)bio->bi_iter.bi_sector << SECTOR_SHIFT;
 	u64 file_len;
-	u64 len = bio->bi_iter.bi_size;
 	u64 end = start + len;
 	u64 ordered_end;
 	u64 pre, post;
 	int ret = 0;
 
-	ordered = btrfs_lookup_ordered_extent(inode, file_offset);
+	ordered = btrfs_lookup_ordered_extent(inode, bbio->file_offset);
 	if (WARN_ON_ONCE(!ordered))
 		return BLK_STS_IOERR;
 
@@ -2715,7 +2687,7 @@ static blk_status_t extract_ordered_extent(struct btrfs_inode *inode,
 	ret = btrfs_split_ordered_extent(ordered, pre, post);
 	if (ret)
 		goto out;
-	ret = split_zoned_em(inode, file_offset, file_len, pre, post);
+	ret = split_zoned_em(inode, bbio->file_offset, file_len, pre, post);
 
 out:
 	btrfs_put_ordered_extent(ordered);
@@ -2723,75 +2695,6 @@ out:
 	return errno_to_blk_status(ret);
 }
 
-void btrfs_submit_data_write_bio(struct btrfs_inode *inode, struct bio *bio, int mirror_num)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	blk_status_t ret;
-
-	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
-		ret = extract_ordered_extent(inode, bio,
-				page_offset(bio_first_bvec_all(bio)->bv_page));
-		if (ret) {
-			btrfs_bio_end_io(btrfs_bio(bio), ret);
-			return;
-		}
-	}
-
-	/*
-	 * If we need to checksum, and the I/O is not issued by fsync and
-	 * friends, that is ->sync_writers != 0, defer the submission to a
-	 * workqueue to parallelize it.
-	 *
-	 * Csum items for reloc roots have already been cloned at this point,
-	 * so they are handled as part of the no-checksum case.
-	 */
-	if (!(inode->flags & BTRFS_INODE_NODATASUM) &&
-	    !test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state) &&
-	    !btrfs_is_data_reloc_root(inode->root)) {
-		if (!atomic_read(&inode->sync_writers) &&
-		    btrfs_wq_submit_bio(inode, bio, mirror_num, 0, WQ_SUBMIT_DATA))
-			return;
-
-		ret = btrfs_csum_one_bio(inode, bio, (u64)-1, false);
-		if (ret) {
-			btrfs_bio_end_io(btrfs_bio(bio), ret);
-			return;
-		}
-	}
-	btrfs_submit_bio(fs_info, bio, mirror_num);
-}
-
-void btrfs_submit_data_read_bio(struct btrfs_inode *inode, struct bio *bio,
-			int mirror_num, enum btrfs_compression_type compress_type)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	blk_status_t ret;
-
-	if (compress_type != BTRFS_COMPRESS_NONE) {
-		/*
-		 * btrfs_submit_compressed_read will handle completing the bio
-		 * if there were any errors, so just return here.
-		 */
-		btrfs_submit_compressed_read(&inode->vfs_inode, bio, mirror_num);
-		return;
-	}
-
-	/* Save the original iter for read repair */
-	btrfs_bio(bio)->iter = bio->bi_iter;
-
-	/*
-	 * Lookup bio sums does extra checks around whether we need to csum or
-	 * not, which is why we ignore skip_sum here.
-	 */
-	ret = btrfs_lookup_bio_sums(&inode->vfs_inode, bio, NULL);
-	if (ret) {
-		btrfs_bio_end_io(btrfs_bio(bio), ret);
-		return;
-	}
-
-	btrfs_submit_bio(fs_info, bio, mirror_num);
-}
-
 /*
  * given a list of ordered sums record them in the inode.  This happens
  * at IO completion time based on sums calculated at bio submission time.
@@ -2969,7 +2872,7 @@ again:
 		unlock_extent(&inode->io_tree, page_start, page_end,
 			      &cached_state);
 		unlock_page(page);
-		btrfs_start_ordered_extent(ordered, 1);
+		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
 		goto again;
 	}
@@ -3259,15 +3162,13 @@ int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		goto out;
 	}
 
-	/* A valid bdev implies a write on a sequential zone */
-	if (ordered_extent->bdev) {
+	/* A valid ->physical implies a write on a sequential zone. */
+	if (ordered_extent->physical != (u64)-1) {
 		btrfs_rewrite_logical_zoned(ordered_extent);
 		btrfs_zone_finish_endio(fs_info, ordered_extent->disk_bytenr,
 					ordered_extent->disk_num_bytes);
 	}
 
-	btrfs_free_io_failure_record(inode, start, end);
-
 	if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) {
 		truncated = true;
 		logical_len = ordered_extent->truncated_len;
@@ -3474,109 +3375,55 @@ static u8 *btrfs_csum_ptr(const struct btrfs_fs_info *fs_info, u8 *csums, u64 of
 }
 
 /*
- * check_data_csum - verify checksum of one sector of uncompressed data
- * @inode:	inode
- * @bbio:	btrfs_bio which contains the csum
+ * Verify the checksum of a single data sector.
+ *
+ * @bbio:	btrfs_io_bio which contains the csum
+ * @dev:	device the sector is on
  * @bio_offset:	offset to the beginning of the bio (in bytes)
- * @page:	page where is the data to be verified
- * @pgoff:	offset inside the page
+ * @bv:		bio_vec to check
  *
- * The length of such check is always one sector size.
+ * Check if the checksum on a data block is valid.  When a checksum mismatch is
+ * detected, report the error and fill the corrupted range with zero.
  *
- * When csum mismatch is detected, we will also report the error and fill the
- * corrupted range with zero. (Thus it needs the extra parameters)
+ * Return %true if the sector is ok or had no checksum to start with, else %false.
  */
-int btrfs_check_data_csum(struct btrfs_inode *inode, struct btrfs_bio *bbio,
-			  u32 bio_offset, struct page *page, u32 pgoff)
+bool btrfs_data_csum_ok(struct btrfs_bio *bbio, struct btrfs_device *dev,
+			u32 bio_offset, struct bio_vec *bv)
 {
+	struct btrfs_inode *inode = bbio->inode;
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	u32 len = fs_info->sectorsize;
+	u64 file_offset = bbio->file_offset + bio_offset;
+	u64 end = file_offset + bv->bv_len - 1;
 	u8 *csum_expected;
 	u8 csum[BTRFS_CSUM_SIZE];
 
-	ASSERT(pgoff + len <= PAGE_SIZE);
+	ASSERT(bv->bv_len == fs_info->sectorsize);
 
-	csum_expected = btrfs_csum_ptr(fs_info, bbio->csum, bio_offset);
+	if (!bbio->csum)
+		return true;
 
-	if (btrfs_check_sector_csum(fs_info, page, pgoff, csum, csum_expected))
+	if (btrfs_is_data_reloc_root(inode->root) &&
+	    test_range_bit(&inode->io_tree, file_offset, end, EXTENT_NODATASUM,
+			   1, NULL)) {
+		/* Skip the range without csum for data reloc inode */
+		clear_extent_bits(&inode->io_tree, file_offset, end,
+				  EXTENT_NODATASUM);
+		return true;
+	}
+
+	csum_expected = btrfs_csum_ptr(fs_info, bbio->csum, bio_offset);
+	if (btrfs_check_sector_csum(fs_info, bv->bv_page, bv->bv_offset, csum,
+				    csum_expected))
 		goto zeroit;
-	return 0;
+	return true;
 
 zeroit:
-	btrfs_print_data_csum_error(inode, bbio->file_offset + bio_offset,
-				    csum, csum_expected, bbio->mirror_num);
-	if (bbio->device)
-		btrfs_dev_stat_inc_and_print(bbio->device,
-					     BTRFS_DEV_STAT_CORRUPTION_ERRS);
-	memzero_page(page, pgoff, len);
-	return -EIO;
-}
-
-/*
- * When reads are done, we need to check csums to verify the data is correct.
- * if there's a match, we allow the bio to finish.  If not, the code in
- * extent_io.c will try to find good copies for us.
- *
- * @bio_offset:	offset to the beginning of the bio (in bytes)
- * @start:	file offset of the range start
- * @end:	file offset of the range end (inclusive)
- *
- * Return a bitmap where bit set means a csum mismatch, and bit not set means
- * csum match.
- */
-unsigned int btrfs_verify_data_csum(struct btrfs_bio *bbio,
-				    u32 bio_offset, struct page *page,
-				    u64 start, u64 end)
-{
-	struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
-	struct btrfs_root *root = inode->root;
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct extent_io_tree *io_tree = &inode->io_tree;
-	const u32 sectorsize = root->fs_info->sectorsize;
-	u32 pg_off;
-	unsigned int result = 0;
-
-	/*
-	 * This only happens for NODATASUM or compressed read.
-	 * Normally this should be covered by above check for compressed read
-	 * or the next check for NODATASUM.  Just do a quicker exit here.
-	 */
-	if (bbio->csum == NULL)
-		return 0;
-
-	if (inode->flags & BTRFS_INODE_NODATASUM)
-		return 0;
-
-	if (unlikely(test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state)))
-		return 0;
-
-	ASSERT(page_offset(page) <= start &&
-	       end <= page_offset(page) + PAGE_SIZE - 1);
-	for (pg_off = offset_in_page(start);
-	     pg_off < offset_in_page(end);
-	     pg_off += sectorsize, bio_offset += sectorsize) {
-		u64 file_offset = pg_off + page_offset(page);
-		int ret;
-
-		if (btrfs_is_data_reloc_root(root) &&
-		    test_range_bit(io_tree, file_offset,
-				   file_offset + sectorsize - 1,
-				   EXTENT_NODATASUM, 1, NULL)) {
-			/* Skip the range without csum for data reloc inode */
-			clear_extent_bits(io_tree, file_offset,
-					  file_offset + sectorsize - 1,
-					  EXTENT_NODATASUM);
-			continue;
-		}
-		ret = btrfs_check_data_csum(inode, bbio, bio_offset, page, pg_off);
-		if (ret < 0) {
-			const int nr_bit = (pg_off - offset_in_page(start)) >>
-				     root->fs_info->sectorsize_bits;
-
-			result |= (1U << nr_bit);
-		}
-	}
-	return result;
+	btrfs_print_data_csum_error(inode, file_offset, csum, csum_expected,
+				    bbio->mirror_num);
+	if (dev)
+		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_CORRUPTION_ERRS);
+	memzero_bvec(bv);
+	return false;
 }
 
 /*
@@ -4987,7 +4834,7 @@ again:
 		unlock_extent(io_tree, block_start, block_end, &cached_state);
 		unlock_page(page);
 		put_page(page);
-		btrfs_start_ordered_extent(ordered, 1);
+		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
 		goto again;
 	}
@@ -5466,8 +5313,6 @@ void btrfs_evict_inode(struct inode *inode)
 	if (is_bad_inode(inode))
 		goto no_delete;
 
-	btrfs_free_io_failure_record(BTRFS_I(inode), 0, (u64)-1);
-
 	if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags))
 		goto no_delete;
 
@@ -7392,7 +7237,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 			 */
 			if (writing ||
 			    test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags))
-				btrfs_start_ordered_extent(ordered, 1);
+				btrfs_start_ordered_extent(ordered);
 			else
 				ret = nowait ? -EAGAIN : -ENOTBLK;
 			btrfs_put_ordered_extent(ordered);
@@ -7833,10 +7678,6 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	iomap->offset = start;
 	iomap->bdev = fs_info->fs_devices->latest_dev->bdev;
 	iomap->length = len;
-
-	if (write && btrfs_use_zone_append(BTRFS_I(inode), em->block_start))
-		iomap->flags |= IOMAP_F_ZONE_APPEND;
-
 	free_extent_map(em);
 
 	return 0;
@@ -7888,267 +7729,47 @@ static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 	return ret;
 }
 
-static void btrfs_dio_private_put(struct btrfs_dio_private *dip)
-{
-	/*
-	 * This implies a barrier so that stores to dio_bio->bi_status before
-	 * this and loads of dio_bio->bi_status after this are fully ordered.
-	 */
-	if (!refcount_dec_and_test(&dip->refs))
-		return;
-
-	if (btrfs_op(&dip->bio) == BTRFS_MAP_WRITE) {
-		btrfs_mark_ordered_io_finished(dip->inode, NULL,
-					       dip->file_offset, dip->bytes,
-					       !dip->bio.bi_status);
-	} else {
-		unlock_extent(&dip->inode->io_tree,
-			      dip->file_offset,
-			      dip->file_offset + dip->bytes - 1, NULL);
-	}
-
-	kfree(dip->csums);
-	bio_endio(&dip->bio);
-}
-
-void btrfs_submit_dio_repair_bio(struct btrfs_inode *inode, struct bio *bio, int mirror_num)
-{
-	struct btrfs_dio_private *dip = btrfs_bio(bio)->private;
-
-	BUG_ON(bio_op(bio) == REQ_OP_WRITE);
-
-	refcount_inc(&dip->refs);
-	btrfs_submit_bio(inode->root->fs_info, bio, mirror_num);
-}
-
-static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip,
-					     struct btrfs_bio *bbio,
-					     const bool uptodate)
-{
-	struct inode *inode = &dip->inode->vfs_inode;
-	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
-	const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM);
-	blk_status_t err = BLK_STS_OK;
-	struct bvec_iter iter;
-	struct bio_vec bv;
-	u32 offset;
-
-	btrfs_bio_for_each_sector(fs_info, bv, bbio, iter, offset) {
-		u64 start = bbio->file_offset + offset;
-
-		if (uptodate &&
-		    (!csum || !btrfs_check_data_csum(BTRFS_I(inode), bbio, offset,
-						     bv.bv_page, bv.bv_offset))) {
-			btrfs_clean_io_failure(BTRFS_I(inode), start,
-					       bv.bv_page, bv.bv_offset);
-		} else {
-			int ret;
-
-			ret = btrfs_repair_one_sector(BTRFS_I(inode), bbio, offset,
-					bv.bv_page, bv.bv_offset, false);
-			if (ret)
-				err = errno_to_blk_status(ret);
-		}
-	}
-
-	return err;
-}
-
-blk_status_t btrfs_submit_bio_start_direct_io(struct btrfs_inode *inode,
-					      struct bio *bio,
-					      u64 dio_file_offset)
+static void btrfs_dio_end_io(struct btrfs_bio *bbio)
 {
-	return btrfs_csum_one_bio(inode, bio, dio_file_offset, false);
-}
-
-static void btrfs_end_dio_bio(struct btrfs_bio *bbio)
-{
-	struct btrfs_dio_private *dip = bbio->private;
+	struct btrfs_dio_private *dip =
+		container_of(bbio, struct btrfs_dio_private, bbio);
+	struct btrfs_inode *inode = bbio->inode;
 	struct bio *bio = &bbio->bio;
-	blk_status_t err = bio->bi_status;
-
-	if (err)
-		btrfs_warn(dip->inode->root->fs_info,
-			   "direct IO failed ino %llu rw %d,%u sector %#Lx len %u err no %d",
-			   btrfs_ino(dip->inode), bio_op(bio),
-			   bio->bi_opf, bio->bi_iter.bi_sector,
-			   bio->bi_iter.bi_size, err);
-
-	if (bio_op(bio) == REQ_OP_READ)
-		err = btrfs_check_read_dio_bio(dip, bbio, !err);
-
-	if (err)
-		dip->bio.bi_status = err;
-
-	btrfs_record_physical_zoned(&dip->inode->vfs_inode, bbio->file_offset, bio);
-
-	bio_put(bio);
-	btrfs_dio_private_put(dip);
-}
 
-static void btrfs_submit_dio_bio(struct bio *bio, struct btrfs_inode *inode,
-				 u64 file_offset, int async_submit)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	struct btrfs_dio_private *dip = btrfs_bio(bio)->private;
-	blk_status_t ret;
-
-	/* Save the original iter for read repair */
-	if (btrfs_op(bio) == BTRFS_MAP_READ)
-		btrfs_bio(bio)->iter = bio->bi_iter;
-
-	if (inode->flags & BTRFS_INODE_NODATASUM)
-		goto map;
+	if (bio->bi_status) {
+		btrfs_warn(inode->root->fs_info,
+		"direct IO failed ino %llu op 0x%0x offset %#llx len %u err no %d",
+			   btrfs_ino(inode), bio->bi_opf,
+			   dip->file_offset, dip->bytes, bio->bi_status);
+	}
 
-	if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
-		/* Check btrfs_submit_data_write_bio() for async submit rules */
-		if (async_submit && !atomic_read(&inode->sync_writers) &&
-		    btrfs_wq_submit_bio(inode, bio, 0, file_offset,
-					WQ_SUBMIT_DATA_DIO))
-			return;
+	if (btrfs_op(bio) == BTRFS_MAP_WRITE)
+		btrfs_mark_ordered_io_finished(inode, NULL, dip->file_offset,
+					       dip->bytes, !bio->bi_status);
+	else
+		unlock_extent(&inode->io_tree, dip->file_offset,
+			      dip->file_offset + dip->bytes - 1, NULL);
 
-		/*
-		 * If we aren't doing async submit, calculate the csum of the
-		 * bio now.
-		 */
-		ret = btrfs_csum_one_bio(inode, bio, file_offset, false);
-		if (ret) {
-			btrfs_bio_end_io(btrfs_bio(bio), ret);
-			return;
-		}
-	} else {
-		btrfs_bio(bio)->csum = btrfs_csum_ptr(fs_info, dip->csums,
-						      file_offset - dip->file_offset);
-	}
-map:
-	btrfs_submit_bio(fs_info, bio, 0);
+	bbio->bio.bi_private = bbio->private;
+	iomap_dio_bio_end_io(bio);
 }
 
-static void btrfs_submit_direct(const struct iomap_iter *iter,
-		struct bio *dio_bio, loff_t file_offset)
+static void btrfs_dio_submit_io(const struct iomap_iter *iter, struct bio *bio,
+				loff_t file_offset)
 {
+	struct btrfs_bio *bbio = btrfs_bio(bio);
 	struct btrfs_dio_private *dip =
-		container_of(dio_bio, struct btrfs_dio_private, bio);
-	struct inode *inode = iter->inode;
-	const bool write = (btrfs_op(dio_bio) == BTRFS_MAP_WRITE);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	const bool raid56 = (btrfs_data_alloc_profile(fs_info) &
-			     BTRFS_BLOCK_GROUP_RAID56_MASK);
-	struct bio *bio;
-	u64 start_sector;
-	int async_submit = 0;
-	u64 submit_len;
-	u64 clone_offset = 0;
-	u64 clone_len;
-	u64 logical;
-	int ret;
-	blk_status_t status;
-	struct btrfs_io_geometry geom;
+		container_of(bbio, struct btrfs_dio_private, bbio);
 	struct btrfs_dio_data *dio_data = iter->private;
-	struct extent_map *em = NULL;
-
-	dip->inode = BTRFS_I(inode);
-	dip->file_offset = file_offset;
-	dip->bytes = dio_bio->bi_iter.bi_size;
-	refcount_set(&dip->refs, 1);
-	dip->csums = NULL;
-
-	if (!write && !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
-		unsigned int nr_sectors =
-			(dio_bio->bi_iter.bi_size >> fs_info->sectorsize_bits);
-
-		/*
-		 * Load the csums up front to reduce csum tree searches and
-		 * contention when submitting bios.
-		 */
-		status = BLK_STS_RESOURCE;
-		dip->csums = kcalloc(nr_sectors, fs_info->csum_size, GFP_NOFS);
-		if (!dip->csums)
-			goto out_err;
-
-		status = btrfs_lookup_bio_sums(inode, dio_bio, dip->csums);
-		if (status != BLK_STS_OK)
-			goto out_err;
-	}
-
-	start_sector = dio_bio->bi_iter.bi_sector;
-	submit_len = dio_bio->bi_iter.bi_size;
-
-	do {
-		logical = start_sector << 9;
-		em = btrfs_get_chunk_map(fs_info, logical, submit_len);
-		if (IS_ERR(em)) {
-			status = errno_to_blk_status(PTR_ERR(em));
-			em = NULL;
-			goto out_err_em;
-		}
-		ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(dio_bio),
-					    logical, &geom);
-		if (ret) {
-			status = errno_to_blk_status(ret);
-			goto out_err_em;
-		}
 
-		clone_len = min(submit_len, geom.len);
-		ASSERT(clone_len <= UINT_MAX);
+	btrfs_bio_init(bbio, BTRFS_I(iter->inode), btrfs_dio_end_io, bio->bi_private);
+	bbio->file_offset = file_offset;
 
-		/*
-		 * This will never fail as it's passing GPF_NOFS and
-		 * the allocation is backed by btrfs_bioset.
-		 */
-		bio = btrfs_bio_clone_partial(dio_bio, clone_offset, clone_len,
-					      btrfs_end_dio_bio, dip);
-		btrfs_bio(bio)->file_offset = file_offset;
-
-		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
-			status = extract_ordered_extent(BTRFS_I(inode), bio,
-							file_offset);
-			if (status) {
-				bio_put(bio);
-				goto out_err;
-			}
-		}
-
-		ASSERT(submit_len >= clone_len);
-		submit_len -= clone_len;
-
-		/*
-		 * Increase the count before we submit the bio so we know
-		 * the end IO handler won't happen before we increase the
-		 * count. Otherwise, the dip might get freed before we're
-		 * done setting it up.
-		 *
-		 * We transfer the initial reference to the last bio, so we
-		 * don't need to increment the reference count for the last one.
-		 */
-		if (submit_len > 0) {
-			refcount_inc(&dip->refs);
-			/*
-			 * If we are submitting more than one bio, submit them
-			 * all asynchronously. The exception is RAID 5 or 6, as
-			 * asynchronous checksums make it difficult to collect
-			 * full stripe writes.
-			 */
-			if (!raid56)
-				async_submit = 1;
-		}
-
-		btrfs_submit_dio_bio(bio, BTRFS_I(inode), file_offset, async_submit);
-
-		dio_data->submitted += clone_len;
-		clone_offset += clone_len;
-		start_sector += clone_len >> 9;
-		file_offset += clone_len;
-
-		free_extent_map(em);
-	} while (submit_len > 0);
-	return;
+	dip->file_offset = file_offset;
+	dip->bytes = bio->bi_iter.bi_size;
 
-out_err_em:
-	free_extent_map(em);
-out_err:
-	dio_bio->bi_status = status;
-	btrfs_dio_private_put(dip);
+	dio_data->submitted += bio->bi_iter.bi_size;
+	btrfs_submit_bio(bio, 0);
 }
 
 static const struct iomap_ops btrfs_dio_iomap_ops = {
@@ -8157,7 +7778,7 @@ static const struct iomap_ops btrfs_dio_iomap_ops = {
 };
 
 static const struct iomap_dio_ops btrfs_dio_ops = {
-	.submit_io		= btrfs_submit_direct,
+	.submit_io		= btrfs_dio_submit_io,
 	.bio_set		= &btrfs_dio_bioset,
 };
 
@@ -8552,7 +8173,7 @@ again:
 		unlock_extent(io_tree, page_start, page_end, &cached_state);
 		unlock_page(page);
 		up_read(&BTRFS_I(inode)->i_mmap_lock);
-		btrfs_start_ordered_extent(ordered, 1);
+		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
 		goto again;
 	}
@@ -8850,7 +8471,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->last_log_commit = 0;
 
 	spin_lock_init(&ei->lock);
-	spin_lock_init(&ei->io_failure_lock);
 	ei->outstanding_extents = 0;
 	if (sb->s_magic != BTRFS_TEST_MAGIC)
 		btrfs_init_metadata_block_rsv(fs_info, &ei->block_rsv,
@@ -8870,7 +8490,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->io_tree.inode = ei;
 	extent_io_tree_init(fs_info, &ei->file_extent_tree,
 			    IO_TREE_INODE_FILE_EXTENT);
-	ei->io_failure_tree = RB_ROOT;
 	atomic_set(&ei->sync_writers, 0);
 	mutex_init(&ei->log_mutex);
 	btrfs_ordered_inode_tree_init(&ei->ordered_tree);
@@ -8994,7 +8613,7 @@ int __init btrfs_init_cachep(void)
 		goto fail;
 
 	if (bioset_init(&btrfs_dio_bioset, BIO_POOL_SIZE,
-			offsetof(struct btrfs_dio_private, bio),
+			offsetof(struct btrfs_dio_private, bbio.bio),
 			BIOSET_NEED_BVECS))
 		goto fail;
 
@@ -10289,65 +9908,13 @@ struct btrfs_encoded_read_private {
 	wait_queue_head_t wait;
 	atomic_t pending;
 	blk_status_t status;
-	bool skip_csum;
 };
 
-static blk_status_t submit_encoded_read_bio(struct btrfs_inode *inode,
-					    struct bio *bio, int mirror_num)
-{
-	struct btrfs_encoded_read_private *priv = btrfs_bio(bio)->private;
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	blk_status_t ret;
-
-	if (!priv->skip_csum) {
-		ret = btrfs_lookup_bio_sums(&inode->vfs_inode, bio, NULL);
-		if (ret)
-			return ret;
-	}
-
-	atomic_inc(&priv->pending);
-	btrfs_submit_bio(fs_info, bio, mirror_num);
-	return BLK_STS_OK;
-}
-
-static blk_status_t btrfs_encoded_read_verify_csum(struct btrfs_bio *bbio)
-{
-	const bool uptodate = (bbio->bio.bi_status == BLK_STS_OK);
-	struct btrfs_encoded_read_private *priv = bbio->private;
-	struct btrfs_inode *inode = priv->inode;
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	u32 sectorsize = fs_info->sectorsize;
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
-	u32 bio_offset = 0;
-
-	if (priv->skip_csum || !uptodate)
-		return bbio->bio.bi_status;
-
-	bio_for_each_segment_all(bvec, &bbio->bio, iter_all) {
-		unsigned int i, nr_sectors, pgoff;
-
-		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
-		pgoff = bvec->bv_offset;
-		for (i = 0; i < nr_sectors; i++) {
-			ASSERT(pgoff < PAGE_SIZE);
-			if (btrfs_check_data_csum(inode, bbio, bio_offset,
-					    bvec->bv_page, pgoff))
-				return BLK_STS_IOERR;
-			bio_offset += sectorsize;
-			pgoff += sectorsize;
-		}
-	}
-	return BLK_STS_OK;
-}
-
 static void btrfs_encoded_read_endio(struct btrfs_bio *bbio)
 {
 	struct btrfs_encoded_read_private *priv = bbio->private;
-	blk_status_t status;
 
-	status = btrfs_encoded_read_verify_csum(bbio);
-	if (status) {
+	if (bbio->bio.bi_status) {
 		/*
 		 * The memory barrier implied by the atomic_dec_return() here
 		 * pairs with the memory barrier implied by the
@@ -10356,11 +9923,10 @@ static void btrfs_encoded_read_endio(struct btrfs_bio *bbio)
 		 * write is observed before the load of status in
 		 * btrfs_encoded_read_regular_fill_pages().
 		 */
-		WRITE_ONCE(priv->status, status);
+		WRITE_ONCE(priv->status, bbio->bio.bi_status);
 	}
 	if (!atomic_dec_return(&priv->pending))
 		wake_up(&priv->wait);
-	btrfs_bio_free_csum(bbio);
 	bio_put(&bbio->bio);
 }
 
@@ -10368,47 +9934,26 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
 					  u64 file_offset, u64 disk_bytenr,
 					  u64 disk_io_size, struct page **pages)
 {
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_encoded_read_private priv = {
 		.inode = inode,
 		.file_offset = file_offset,
 		.pending = ATOMIC_INIT(1),
-		.skip_csum = (inode->flags & BTRFS_INODE_NODATASUM),
 	};
 	unsigned long i = 0;
 	u64 cur = 0;
-	int ret;
 
 	init_waitqueue_head(&priv.wait);
-	/*
-	 * Submit bios for the extent, splitting due to bio or stripe limits as
-	 * necessary.
-	 */
+	/* Submit bios for the extent, splitting due to bio limits as necessary. */
 	while (cur < disk_io_size) {
-		struct extent_map *em;
-		struct btrfs_io_geometry geom;
 		struct bio *bio = NULL;
-		u64 remaining;
+		u64 remaining = disk_io_size - cur;
 
-		em = btrfs_get_chunk_map(fs_info, disk_bytenr + cur,
-					 disk_io_size - cur);
-		if (IS_ERR(em)) {
-			ret = PTR_ERR(em);
-		} else {
-			ret = btrfs_get_io_geometry(fs_info, em, BTRFS_MAP_READ,
-						    disk_bytenr + cur, &geom);
-			free_extent_map(em);
-		}
-		if (ret) {
-			WRITE_ONCE(priv.status, errno_to_blk_status(ret));
-			break;
-		}
-		remaining = min(geom.len, disk_io_size - cur);
 		while (bio || remaining) {
 			size_t bytes = min_t(u64, remaining, PAGE_SIZE);
 
 			if (!bio) {
 				bio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ,
+						      inode,
 						      btrfs_encoded_read_endio,
 						      &priv);
 				bio->bi_iter.bi_sector =
@@ -10417,14 +9962,8 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
 
 			if (!bytes ||
 			    bio_add_page(bio, pages[i], bytes, 0) < bytes) {
-				blk_status_t status;
-
-				status = submit_encoded_read_bio(inode, bio, 0);
-				if (status) {
-					WRITE_ONCE(priv.status, status);
-					bio_put(bio);
-					goto out;
-				}
+				atomic_inc(&priv.pending);
+				btrfs_submit_bio(bio, 0);
 				bio = NULL;
 				continue;
 			}
@@ -10435,7 +9974,6 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
 		}
 	}
 
-out:
 	if (atomic_dec_return(&priv.pending))
 		io_wait_event(priv.wait, !atomic_read(&priv.pending));
 	/* See btrfs_encoded_read_endio() for ordering. */
@@ -10995,9 +10533,8 @@ static int btrfs_add_swap_extent(struct swap_info_struct *sis,
 		return 0;
 
 	max_pages = sis->max - bsi->nr_pages;
-	first_ppage = ALIGN(bsi->block_start, PAGE_SIZE) >> PAGE_SHIFT;
-	next_ppage = ALIGN_DOWN(bsi->block_start + bsi->block_len,
-				PAGE_SIZE) >> PAGE_SHIFT;
+	first_ppage = PAGE_ALIGN(bsi->block_start) >> PAGE_SHIFT;
+	next_ppage = PAGE_ALIGN_DOWN(bsi->block_start + bsi->block_len) >> PAGE_SHIFT;
 
 	if (first_ppage >= next_ppage)
 		return 0;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5ba1ff31713b..84626c8ad5bf 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -707,7 +707,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 		 * exists).
 		 */
 		btrfs_tree_lock(leaf);
-		btrfs_clean_tree_block(leaf);
+		btrfs_clear_buffer_dirty(trans, leaf);
 		btrfs_tree_unlock(leaf);
 		btrfs_free_tree_block(trans, objectid, leaf, 0, 1);
 		free_extent_buffer(leaf);
diff --git a/fs/btrfs/lru_cache.c b/fs/btrfs/lru_cache.c
new file mode 100644
index 000000000000..0fe0ae54ac67
--- /dev/null
+++ b/fs/btrfs/lru_cache.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/mm.h>
+#include "lru_cache.h"
+#include "messages.h"
+
+/*
+ * Initialize a cache object.
+ *
+ * @cache:      The cache.
+ * @max_size:   Maximum size (number of entries) for the cache.
+ *              Use 0 for unlimited size, it's the user's responsability to
+ *              trim the cache in that case.
+ */
+void btrfs_lru_cache_init(struct btrfs_lru_cache *cache, unsigned int max_size)
+{
+	INIT_LIST_HEAD(&cache->lru_list);
+	mt_init(&cache->entries);
+	cache->size = 0;
+	cache->max_size = max_size;
+}
+
+static struct btrfs_lru_cache_entry *match_entry(struct list_head *head, u64 key,
+						 u64 gen)
+{
+	struct btrfs_lru_cache_entry *entry;
+
+	list_for_each_entry(entry, head, list) {
+		if (entry->key == key && entry->gen == gen)
+			return entry;
+	}
+
+	return NULL;
+}
+
+/*
+ * Lookup for an entry in the cache.
+ *
+ * @cache:      The cache.
+ * @key:        The key of the entry we are looking for.
+ * @gen:        Generation associated to the key.
+ *
+ * Returns the entry associated with the key or NULL if none found.
+ */
+struct btrfs_lru_cache_entry *btrfs_lru_cache_lookup(struct btrfs_lru_cache *cache,
+						     u64 key, u64 gen)
+{
+	struct list_head *head;
+	struct btrfs_lru_cache_entry *entry;
+
+	head = mtree_load(&cache->entries, key);
+	if (!head)
+		return NULL;
+
+	entry = match_entry(head, key, gen);
+	if (entry)
+		list_move_tail(&entry->lru_list, &cache->lru_list);
+
+	return entry;
+}
+
+/*
+ * Remove an entry from the cache.
+ *
+ * @cache:     The cache to remove from.
+ * @entry:     The entry to remove from the cache.
+ *
+ * Note: this also frees the memory used by the entry.
+ */
+void btrfs_lru_cache_remove(struct btrfs_lru_cache *cache,
+			    struct btrfs_lru_cache_entry *entry)
+{
+	struct list_head *prev = entry->list.prev;
+
+	ASSERT(cache->size > 0);
+	ASSERT(!mtree_empty(&cache->entries));
+
+	list_del(&entry->list);
+	list_del(&entry->lru_list);
+
+	if (list_empty(prev)) {
+		struct list_head *head;
+
+		/*
+		 * If previous element in the list entry->list is now empty, it
+		 * means it's a head entry not pointing to any cached entries,
+		 * so remove it from the maple tree and free it.
+		 */
+		head = mtree_erase(&cache->entries, entry->key);
+		ASSERT(head == prev);
+		kfree(head);
+	}
+
+	kfree(entry);
+	cache->size--;
+}
+
+/*
+ * Store an entry in the cache.
+ *
+ * @cache:      The cache.
+ * @entry:      The entry to store.
+ *
+ * Returns 0 on success and < 0 on error.
+ */
+int btrfs_lru_cache_store(struct btrfs_lru_cache *cache,
+			  struct btrfs_lru_cache_entry *new_entry,
+			  gfp_t gfp)
+{
+	const u64 key = new_entry->key;
+	struct list_head *head;
+	int ret;
+
+	head = kmalloc(sizeof(*head), gfp);
+	if (!head)
+		return -ENOMEM;
+
+	ret = mtree_insert(&cache->entries, key, head, gfp);
+	if (ret == 0) {
+		INIT_LIST_HEAD(head);
+		list_add_tail(&new_entry->list, head);
+	} else if (ret == -EEXIST) {
+		kfree(head);
+		head = mtree_load(&cache->entries, key);
+		ASSERT(head != NULL);
+		if (match_entry(head, key, new_entry->gen) != NULL)
+			return -EEXIST;
+		list_add_tail(&new_entry->list, head);
+	} else if (ret < 0) {
+		kfree(head);
+		return ret;
+	}
+
+	if (cache->max_size > 0 && cache->size == cache->max_size) {
+		struct btrfs_lru_cache_entry *lru_entry;
+
+		lru_entry = list_first_entry(&cache->lru_list,
+					     struct btrfs_lru_cache_entry,
+					     lru_list);
+		btrfs_lru_cache_remove(cache, lru_entry);
+	}
+
+	list_add_tail(&new_entry->lru_list, &cache->lru_list);
+	cache->size++;
+
+	return 0;
+}
+
+/*
+ * Empty a cache.
+ *
+ * @cache:     The cache to empty.
+ *
+ * Removes all entries from the cache.
+ */
+void btrfs_lru_cache_clear(struct btrfs_lru_cache *cache)
+{
+	struct btrfs_lru_cache_entry *entry;
+	struct btrfs_lru_cache_entry *tmp;
+
+	list_for_each_entry_safe(entry, tmp, &cache->lru_list, lru_list)
+		btrfs_lru_cache_remove(cache, entry);
+
+	ASSERT(cache->size == 0);
+	ASSERT(mtree_empty(&cache->entries));
+}
diff --git a/fs/btrfs/lru_cache.h b/fs/btrfs/lru_cache.h
new file mode 100644
index 000000000000..de3e18bce24a
--- /dev/null
+++ b/fs/btrfs/lru_cache.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_LRU_CACHE_H
+#define BTRFS_LRU_CACHE_H
+
+#include <linux/maple_tree.h>
+#include <linux/list.h>
+
+/*
+ * A cache entry. This is meant to be embedded in a structure of a user of
+ * this module. Similar to how struct list_head and struct rb_node are used.
+ *
+ * Note: it should be embedded as the first element in a struct (offset 0), and
+ * this module assumes it was allocated with kmalloc(), so it calls kfree() when
+ * it needs to free an entry.
+ */
+struct btrfs_lru_cache_entry {
+	struct list_head lru_list;
+	u64 key;
+	/*
+	 * Optional generation associated to a key. Use 0 if not needed/used.
+	 * Entries with the same key and different generations are stored in a
+	 * linked list, so use this only for cases where there's a small number
+	 * of different generations.
+	 */
+	u64 gen;
+	/*
+	 * The maple tree uses unsigned long type for the keys, which is 32 bits
+	 * on 32 bits systems, and 64 bits on 64 bits systems. So if we want to
+	 * use something like inode numbers as keys, which are always a u64, we
+	 * have to deal with this in a special way - we store the key in the
+	 * entry itself, as a u64, and the values inserted into the maple tree
+	 * are linked lists of entries - so in case we are on a 64 bits system,
+	 * that list always has a single entry, while on 32 bits systems it
+	 * may have more than one, with each entry having the same value for
+	 * their lower 32 bits of the u64 key.
+	 */
+	struct list_head list;
+};
+
+struct btrfs_lru_cache {
+	struct list_head lru_list;
+	struct maple_tree entries;
+	/* Number of entries stored in the cache. */
+	unsigned int size;
+	/* Maximum number of entries the cache can have. */
+	unsigned int max_size;
+};
+
+#define btrfs_lru_cache_for_each_entry_safe(cache, entry, tmp)		\
+	list_for_each_entry_safe_reverse((entry), (tmp), &(cache)->lru_list, lru_list)
+
+static inline unsigned int btrfs_lru_cache_size(const struct btrfs_lru_cache *cache)
+{
+	return cache->size;
+}
+
+static inline bool btrfs_lru_cache_is_full(const struct btrfs_lru_cache *cache)
+{
+	return cache->size >= cache->max_size;
+}
+
+static inline struct btrfs_lru_cache_entry *btrfs_lru_cache_lru_entry(
+					      struct btrfs_lru_cache *cache)
+{
+	return list_first_entry_or_null(&cache->lru_list,
+					struct btrfs_lru_cache_entry, lru_list);
+}
+
+void btrfs_lru_cache_init(struct btrfs_lru_cache *cache, unsigned int max_size);
+struct btrfs_lru_cache_entry *btrfs_lru_cache_lookup(struct btrfs_lru_cache *cache,
+						     u64 key, u64 gen);
+int btrfs_lru_cache_store(struct btrfs_lru_cache *cache,
+			  struct btrfs_lru_cache_entry *new_entry,
+			  gfp_t gfp);
+void btrfs_lru_cache_remove(struct btrfs_lru_cache *cache,
+			    struct btrfs_lru_cache_entry *entry);
+void btrfs_lru_cache_clear(struct btrfs_lru_cache *cache);
+
+#endif
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index d5e78cbc8fbc..71f6d8302d50 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -280,7 +280,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 		}
 
 		/* Check if we have reached page boundary */
-		if (IS_ALIGNED(cur_in, PAGE_SIZE)) {
+		if (PAGE_ALIGNED(cur_in)) {
 			put_page(page_in);
 			page_in = NULL;
 		}
diff --git a/fs/btrfs/messages.c b/fs/btrfs/messages.c
index 625bbbbb2608..fde5aaa6e7c9 100644
--- a/fs/btrfs/messages.c
+++ b/fs/btrfs/messages.c
@@ -293,36 +293,6 @@ void __cold btrfs_err_32bit_limit(struct btrfs_fs_info *fs_info)
 #endif
 
 /*
- * We only mark the transaction aborted and then set the file system read-only.
- * This will prevent new transactions from starting or trying to join this
- * one.
- *
- * This means that error recovery at the call site is limited to freeing
- * any local memory allocations and passing the error code up without
- * further cleanup. The transaction should complete as it normally would
- * in the call path but will return -EIO.
- *
- * We'll complete the cleanup in btrfs_end_transaction and
- * btrfs_commit_transaction.
- */
-__cold
-void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
-			       const char *function,
-			       unsigned int line, int errno, bool first_hit)
-{
-	struct btrfs_fs_info *fs_info = trans->fs_info;
-
-	WRITE_ONCE(trans->aborted, errno);
-	WRITE_ONCE(trans->transaction->aborted, errno);
-	if (first_hit && errno == -ENOSPC)
-		btrfs_dump_space_info_for_trans_abort(fs_info);
-	/* Wake up anybody who may be waiting on this transaction */
-	wake_up(&fs_info->transaction_wait);
-	wake_up(&fs_info->transaction_blocked_wait);
-	__btrfs_handle_fs_error(fs_info, function, line, errno, NULL);
-}
-
-/*
  * __btrfs_panic decodes unexpected, fatal errors from the caller, issues an
  * alert, and either panics or BUGs, depending on mount options.
  */
diff --git a/fs/btrfs/messages.h b/fs/btrfs/messages.h
index 190af1f698d9..8c516ee58ff9 100644
--- a/fs/btrfs/messages.h
+++ b/fs/btrfs/messages.h
@@ -6,7 +6,6 @@
 #include <linux/types.h>
 
 struct btrfs_fs_info;
-struct btrfs_trans_handle;
 
 static inline __printf(2, 3) __cold
 void btrfs_no_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
@@ -178,39 +177,6 @@ void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function
 
 const char * __attribute_const__ btrfs_decode_error(int errno);
 
-__cold
-void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
-			       const char *function,
-			       unsigned int line, int errno, bool first_hit);
-
-bool __cold abort_should_print_stack(int errno);
-
-/*
- * Call btrfs_abort_transaction as early as possible when an error condition is
- * detected, that way the exact stack trace is reported for some errors.
- */
-#define btrfs_abort_transaction(trans, errno)			\
-do {								\
-	bool first = false;					\
-	/* Report first abort since mount */			\
-	if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED,	\
-			      &((trans)->fs_info->fs_state))) {	\
-		first = true;					\
-		if (WARN(abort_should_print_stack(errno),       \
-			KERN_ERR				\
-			"BTRFS: Transaction aborted (error %d)\n",	\
-			(errno))) {					\
-			/* Stack trace printed. */			\
-		} else {						\
-			btrfs_err((trans)->fs_info,			\
-				  "Transaction aborted (error %d)",     \
-				  (errno));			\
-		}						\
-	}							\
-	__btrfs_abort_transaction((trans), __func__,		\
-				  __LINE__, (errno), first);	\
-} while (0)
-
 #define btrfs_handle_fs_error(fs_info, errno, fmt, args...)		\
 	__btrfs_handle_fs_error((fs_info), __func__, __LINE__,		\
 				(errno), fmt, ##args)
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 57d8c72737e1..6c24b69e2d0a 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -616,7 +616,7 @@ static void btrfs_run_ordered_extent_work(struct btrfs_work *work)
 	struct btrfs_ordered_extent *ordered;
 
 	ordered = container_of(work, struct btrfs_ordered_extent, flush_work);
-	btrfs_start_ordered_extent(ordered, 1);
+	btrfs_start_ordered_extent(ordered);
 	complete(&ordered->completion);
 }
 
@@ -716,13 +716,12 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 }
 
 /*
- * Used to start IO or wait for a given ordered extent to finish.
+ * Start IO and wait for a given ordered extent to finish.
  *
- * If wait is one, this effectively waits on page writeback for all the pages
- * in the extent, and it waits on the io completion code to insert
- * metadata into the btree corresponding to the extent
+ * Wait on page writeback for all the pages in the extent and the IO completion
+ * code to insert metadata into the btree corresponding to the extent.
  */
-void btrfs_start_ordered_extent(struct btrfs_ordered_extent *entry, int wait)
+void btrfs_start_ordered_extent(struct btrfs_ordered_extent *entry)
 {
 	u64 start = entry->file_offset;
 	u64 end = start + entry->num_bytes - 1;
@@ -744,12 +743,10 @@ void btrfs_start_ordered_extent(struct btrfs_ordered_extent *entry, int wait)
 	 */
 	if (!test_bit(BTRFS_ORDERED_DIRECT, &entry->flags))
 		filemap_fdatawrite_range(inode->vfs_inode.i_mapping, start, end);
-	if (wait) {
-		if (!freespace_inode)
-			btrfs_might_wait_for_event(inode->root->fs_info, btrfs_ordered_extent);
-		wait_event(entry->wait, test_bit(BTRFS_ORDERED_COMPLETE,
-						 &entry->flags));
-	}
+
+	if (!freespace_inode)
+		btrfs_might_wait_for_event(inode->root->fs_info, btrfs_ordered_extent);
+	wait_event(entry->wait, test_bit(BTRFS_ORDERED_COMPLETE, &entry->flags));
 }
 
 /*
@@ -800,7 +797,7 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
 			btrfs_put_ordered_extent(ordered);
 			break;
 		}
-		btrfs_start_ordered_extent(ordered, 1);
+		btrfs_start_ordered_extent(ordered);
 		end = ordered->file_offset;
 		/*
 		 * If the ordered extent had an error save the error but don't
@@ -1061,7 +1058,7 @@ void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start,
 			break;
 		}
 		unlock_extent(&inode->io_tree, start, end, cachedp);
-		btrfs_start_ordered_extent(ordered, 1);
+		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
 	}
 }
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 89f82b78f590..eb40cb39f842 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -157,7 +157,6 @@ struct btrfs_ordered_extent {
 	 * command in a workqueue context
 	 */
 	u64 physical;
-	struct block_device *bdev;
 };
 
 static inline void
@@ -187,7 +186,7 @@ void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry,
 			   struct btrfs_ordered_sum *sum);
 struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode,
 							 u64 file_offset);
-void btrfs_start_ordered_extent(struct btrfs_ordered_extent *entry, int wait);
+void btrfs_start_ordered_extent(struct btrfs_ordered_extent *entry);
 int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len);
 struct btrfs_ordered_extent *
 btrfs_lookup_first_ordered_extent(struct btrfs_inode *inode, u64 file_offset);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index af97413abcf4..52a7d2fa2284 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1304,7 +1304,7 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 	list_del(&quota_root->dirty_list);
 
 	btrfs_tree_lock(quota_root->node);
-	btrfs_clean_tree_block(quota_root->node);
+	btrfs_clear_buffer_dirty(trans, quota_root->node);
 	btrfs_tree_unlock(quota_root->node);
 	btrfs_free_tree_block(trans, btrfs_root_id(quota_root),
 			      quota_root->node, 0, 1);
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index ff4b1d583788..642828c1b299 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -998,7 +998,7 @@ static int alloc_rbio_parity_pages(struct btrfs_raid_bio *rbio)
 }
 
 /*
- * Return the total numer of errors found in the vertical stripe of @sector_nr.
+ * Return the total number of errors found in the vertical stripe of @sector_nr.
  *
  * @faila and @failb will also be updated to the first and second stripe
  * number of the errors.
@@ -1183,7 +1183,15 @@ not_found:
 	trace_info->stripe_nr = -1;
 }
 
-/* Generate PQ for one veritical stripe. */
+static inline void bio_list_put(struct bio_list *bio_list)
+{
+	struct bio *bio;
+
+	while ((bio = bio_list_pop(bio_list)))
+		bio_put(bio);
+}
+
+/* Generate PQ for one vertical stripe. */
 static void generate_pq_vertical(struct btrfs_raid_bio *rbio, int sectornr)
 {
 	void **pointers = rbio->finish_pointers;
@@ -1228,7 +1236,6 @@ static void generate_pq_vertical(struct btrfs_raid_bio *rbio, int sectornr)
 static int rmw_assemble_write_bios(struct btrfs_raid_bio *rbio,
 				   struct bio_list *bio_list)
 {
-	struct bio *bio;
 	/* The total sector number inside the full stripe. */
 	int total_sector_nr;
 	int sectornr;
@@ -1317,8 +1324,7 @@ static int rmw_assemble_write_bios(struct btrfs_raid_bio *rbio,
 
 	return 0;
 error:
-	while ((bio = bio_list_pop(bio_list)))
-		bio_put(bio);
+	bio_list_put(bio_list);
 	return -EIO;
 }
 
@@ -1357,7 +1363,7 @@ static void set_rbio_range_error(struct btrfs_raid_bio *rbio, struct bio *bio)
 }
 
 /*
- * For subpage case, we can no longer set page Uptodate directly for
+ * For subpage case, we can no longer set page Up-to-date directly for
  * stripe_pages[], thus we need to locate the sector.
  */
 static struct sector_ptr *find_stripe_sector(struct btrfs_raid_bio *rbio,
@@ -1425,10 +1431,9 @@ static void rbio_update_error_bitmap(struct btrfs_raid_bio *rbio, struct bio *bi
 	int total_sector_nr = get_bio_sector_nr(rbio, bio);
 	u32 bio_size = 0;
 	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
 	int i;
 
-	bio_for_each_segment_all(bvec, bio, iter_all)
+	bio_for_each_bvec_all(bvec, bio, i)
 		bio_size += bvec->bv_len;
 
 	/*
@@ -1498,7 +1503,7 @@ static void raid_wait_read_end_io(struct bio *bio)
 		wake_up(&rbio->io_wait);
 }
 
-static void submit_read_bios(struct btrfs_raid_bio *rbio,
+static void submit_read_wait_bio_list(struct btrfs_raid_bio *rbio,
 			     struct bio_list *bio_list)
 {
 	struct bio *bio;
@@ -1515,41 +1520,8 @@ static void submit_read_bios(struct btrfs_raid_bio *rbio,
 		}
 		submit_bio(bio);
 	}
-}
-
-static int rmw_assemble_read_bios(struct btrfs_raid_bio *rbio,
-				  struct bio_list *bio_list)
-{
-	struct bio *bio;
-	int total_sector_nr;
-	int ret = 0;
-
-	ASSERT(bio_list_size(bio_list) == 0);
-
-	/*
-	 * Build a list of bios to read all sectors (including data and P/Q).
-	 *
-	 * This behaviro is to compensate the later csum verification and
-	 * recovery.
-	 */
-	for (total_sector_nr = 0; total_sector_nr < rbio->nr_sectors;
-	     total_sector_nr++) {
-		struct sector_ptr *sector;
-		int stripe = total_sector_nr / rbio->stripe_nsectors;
-		int sectornr = total_sector_nr % rbio->stripe_nsectors;
-
-		sector = rbio_stripe_sector(rbio, stripe, sectornr);
-		ret = rbio_add_io_sector(rbio, bio_list, sector,
-			       stripe, sectornr, REQ_OP_READ);
-		if (ret)
-			goto cleanup;
-	}
-	return 0;
 
-cleanup:
-	while ((bio = bio_list_pop(bio_list)))
-		bio_put(bio);
-	return ret;
+	wait_event(rbio->io_wait, atomic_read(&rbio->stripes_pending) == 0);
 }
 
 static int alloc_rbio_data_pages(struct btrfs_raid_bio *rbio)
@@ -1668,12 +1640,12 @@ void raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc)
 	struct btrfs_raid_bio *rbio;
 	struct btrfs_plug_cb *plug = NULL;
 	struct blk_plug_cb *cb;
-	int ret = 0;
 
 	rbio = alloc_rbio(fs_info, bioc);
 	if (IS_ERR(rbio)) {
-		ret = PTR_ERR(rbio);
-		goto fail;
+		bio->bi_status = errno_to_blk_status(PTR_ERR(rbio));
+		bio_endio(bio);
+		return;
 	}
 	rbio->operation = BTRFS_RBIO_WRITE;
 	rbio_add_bio(rbio, bio);
@@ -1682,31 +1654,24 @@ void raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc)
 	 * Don't plug on full rbios, just get them out the door
 	 * as quickly as we can
 	 */
-	if (rbio_is_full(rbio))
-		goto queue_rbio;
-
-	cb = blk_check_plugged(raid_unplug, fs_info, sizeof(*plug));
-	if (cb) {
-		plug = container_of(cb, struct btrfs_plug_cb, cb);
-		if (!plug->info) {
-			plug->info = fs_info;
-			INIT_LIST_HEAD(&plug->rbio_list);
+	if (!rbio_is_full(rbio)) {
+		cb = blk_check_plugged(raid_unplug, fs_info, sizeof(*plug));
+		if (cb) {
+			plug = container_of(cb, struct btrfs_plug_cb, cb);
+			if (!plug->info) {
+				plug->info = fs_info;
+				INIT_LIST_HEAD(&plug->rbio_list);
+			}
+			list_add_tail(&rbio->plug_list, &plug->rbio_list);
+			return;
 		}
-		list_add_tail(&rbio->plug_list, &plug->rbio_list);
-		return;
 	}
-queue_rbio:
+
 	/*
 	 * Either we don't have any existing plug, or we're doing a full stripe,
-	 * can queue the rmw work now.
+	 * queue the rmw work now.
 	 */
 	start_async_work(rbio, rmw_rbio_work);
-
-	return;
-
-fail:
-	bio->bi_status = errno_to_blk_status(ret);
-	bio_endio(bio);
 }
 
 static int verify_one_sector(struct btrfs_raid_bio *rbio,
@@ -1773,7 +1738,7 @@ static int recover_vertical(struct btrfs_raid_bio *rbio, int sector_nr,
 	found_errors = get_rbio_veritical_errors(rbio, sector_nr, &faila,
 						 &failb);
 	/*
-	 * No errors in the veritical stripe, skip it.  Can happen for recovery
+	 * No errors in the vertical stripe, skip it.  Can happen for recovery
 	 * which only part of a stripe failed csum check.
 	 */
 	if (!found_errors)
@@ -1949,14 +1914,25 @@ out:
 	return ret;
 }
 
-static int recover_assemble_read_bios(struct btrfs_raid_bio *rbio,
-				      struct bio_list *bio_list)
+static void recover_rbio(struct btrfs_raid_bio *rbio)
 {
-	struct bio *bio;
+	struct bio_list bio_list = BIO_EMPTY_LIST;
 	int total_sector_nr;
 	int ret = 0;
 
-	ASSERT(bio_list_size(bio_list) == 0);
+	/*
+	 * Either we're doing recover for a read failure or degraded write,
+	 * caller should have set error bitmap correctly.
+	 */
+	ASSERT(bitmap_weight(rbio->error_bitmap, rbio->nr_sectors));
+
+	/* For recovery, we need to read all sectors including P/Q. */
+	ret = alloc_rbio_pages(rbio);
+	if (ret < 0)
+		goto out;
+
+	index_rbio_pages(rbio);
+
 	/*
 	 * Read everything that hasn't failed. However this time we will
 	 * not trust any cached sector.
@@ -1987,78 +1963,32 @@ static int recover_assemble_read_bios(struct btrfs_raid_bio *rbio,
 		}
 
 		sector = rbio_stripe_sector(rbio, stripe, sectornr);
-		ret = rbio_add_io_sector(rbio, bio_list, sector, stripe,
+		ret = rbio_add_io_sector(rbio, &bio_list, sector, stripe,
 					 sectornr, REQ_OP_READ);
-		if (ret < 0)
-			goto error;
+		if (ret < 0) {
+			bio_list_put(&bio_list);
+			goto out;
+		}
 	}
-	return 0;
-error:
-	while ((bio = bio_list_pop(bio_list)))
-		bio_put(bio);
-
-	return -EIO;
-}
-
-static int recover_rbio(struct btrfs_raid_bio *rbio)
-{
-	struct bio_list bio_list;
-	struct bio *bio;
-	int ret;
-
-	/*
-	 * Either we're doing recover for a read failure or degraded write,
-	 * caller should have set error bitmap correctly.
-	 */
-	ASSERT(bitmap_weight(rbio->error_bitmap, rbio->nr_sectors));
-	bio_list_init(&bio_list);
-
-	/* For recovery, we need to read all sectors including P/Q. */
-	ret = alloc_rbio_pages(rbio);
-	if (ret < 0)
-		goto out;
-
-	index_rbio_pages(rbio);
-
-	ret = recover_assemble_read_bios(rbio, &bio_list);
-	if (ret < 0)
-		goto out;
-
-	submit_read_bios(rbio, &bio_list);
-	wait_event(rbio->io_wait, atomic_read(&rbio->stripes_pending) == 0);
 
+	submit_read_wait_bio_list(rbio, &bio_list);
 	ret = recover_sectors(rbio);
-
 out:
-	while ((bio = bio_list_pop(&bio_list)))
-		bio_put(bio);
-
-	return ret;
+	rbio_orig_end_io(rbio, errno_to_blk_status(ret));
 }
 
 static void recover_rbio_work(struct work_struct *work)
 {
 	struct btrfs_raid_bio *rbio;
-	int ret;
 
 	rbio = container_of(work, struct btrfs_raid_bio, work);
-
-	ret = lock_stripe_add(rbio);
-	if (ret == 0) {
-		ret = recover_rbio(rbio);
-		rbio_orig_end_io(rbio, errno_to_blk_status(ret));
-	}
+	if (!lock_stripe_add(rbio))
+		recover_rbio(rbio);
 }
 
 static void recover_rbio_work_locked(struct work_struct *work)
 {
-	struct btrfs_raid_bio *rbio;
-	int ret;
-
-	rbio = container_of(work, struct btrfs_raid_bio, work);
-
-	ret = recover_rbio(rbio);
-	rbio_orig_end_io(rbio, errno_to_blk_status(ret));
+	recover_rbio(container_of(work, struct btrfs_raid_bio, work));
 }
 
 static void set_rbio_raid6_extra_error(struct btrfs_raid_bio *rbio, int mirror_num)
@@ -2204,11 +2134,9 @@ no_csum:
 
 static int rmw_read_wait_recover(struct btrfs_raid_bio *rbio)
 {
-	struct bio_list bio_list;
-	struct bio *bio;
-	int ret;
-
-	bio_list_init(&bio_list);
+	struct bio_list bio_list = BIO_EMPTY_LIST;
+	int total_sector_nr;
+	int ret = 0;
 
 	/*
 	 * Fill the data csums we need for data verification.  We need to fill
@@ -2217,24 +2145,32 @@ static int rmw_read_wait_recover(struct btrfs_raid_bio *rbio)
 	 */
 	fill_data_csums(rbio);
 
-	ret = rmw_assemble_read_bios(rbio, &bio_list);
-	if (ret < 0)
-		goto out;
+	/*
+	 * Build a list of bios to read all sectors (including data and P/Q).
+	 *
+	 * This behavior is to compensate the later csum verification and recovery.
+	 */
+	for (total_sector_nr = 0; total_sector_nr < rbio->nr_sectors;
+	     total_sector_nr++) {
+		struct sector_ptr *sector;
+		int stripe = total_sector_nr / rbio->stripe_nsectors;
+		int sectornr = total_sector_nr % rbio->stripe_nsectors;
 
-	submit_read_bios(rbio, &bio_list);
-	wait_event(rbio->io_wait, atomic_read(&rbio->stripes_pending) == 0);
+		sector = rbio_stripe_sector(rbio, stripe, sectornr);
+		ret = rbio_add_io_sector(rbio, &bio_list, sector,
+			       stripe, sectornr, REQ_OP_READ);
+		if (ret) {
+			bio_list_put(&bio_list);
+			return ret;
+		}
+	}
 
 	/*
 	 * We may or may not have any corrupted sectors (including missing dev
 	 * and csum mismatch), just let recover_sectors() to handle them all.
 	 */
-	ret = recover_sectors(rbio);
-	return ret;
-out:
-	while ((bio = bio_list_pop(&bio_list)))
-		bio_put(bio);
-
-	return ret;
+	submit_read_wait_bio_list(rbio, &bio_list);
+	return recover_sectors(rbio);
 }
 
 static void raid_wait_write_end_io(struct bio *bio)
@@ -2290,7 +2226,7 @@ static bool need_read_stripe_sectors(struct btrfs_raid_bio *rbio)
 	return false;
 }
 
-static int rmw_rbio(struct btrfs_raid_bio *rbio)
+static void rmw_rbio(struct btrfs_raid_bio *rbio)
 {
 	struct bio_list bio_list;
 	int sectornr;
@@ -2302,30 +2238,28 @@ static int rmw_rbio(struct btrfs_raid_bio *rbio)
 	 */
 	ret = alloc_rbio_parity_pages(rbio);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	/*
 	 * Either full stripe write, or we have every data sector already
 	 * cached, can go to write path immediately.
 	 */
-	if (rbio_is_full(rbio) || !need_read_stripe_sectors(rbio))
-		goto write;
-
-	/*
-	 * Now we're doing sub-stripe write, also need all data stripes to do
-	 * the full RMW.
-	 */
-	ret = alloc_rbio_data_pages(rbio);
-	if (ret < 0)
-		return ret;
+	if (!rbio_is_full(rbio) && need_read_stripe_sectors(rbio)) {
+		/*
+		 * Now we're doing sub-stripe write, also need all data stripes
+		 * to do the full RMW.
+		 */
+		ret = alloc_rbio_data_pages(rbio);
+		if (ret < 0)
+			goto out;
 
-	index_rbio_pages(rbio);
+		index_rbio_pages(rbio);
 
-	ret = rmw_read_wait_recover(rbio);
-	if (ret < 0)
-		return ret;
+		ret = rmw_read_wait_recover(rbio);
+		if (ret < 0)
+			goto out;
+	}
 
-write:
 	/*
 	 * At this stage we're not allowed to add any new bios to the
 	 * bio list any more, anyone else that wants to change this stripe
@@ -2356,7 +2290,7 @@ write:
 	bio_list_init(&bio_list);
 	ret = rmw_assemble_write_bios(rbio, &bio_list);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	/* We should have at least one bio assembled. */
 	ASSERT(bio_list_size(&bio_list));
@@ -2373,32 +2307,22 @@ write:
 			break;
 		}
 	}
-	return ret;
+out:
+	rbio_orig_end_io(rbio, errno_to_blk_status(ret));
 }
 
 static void rmw_rbio_work(struct work_struct *work)
 {
 	struct btrfs_raid_bio *rbio;
-	int ret;
 
 	rbio = container_of(work, struct btrfs_raid_bio, work);
-
-	ret = lock_stripe_add(rbio);
-	if (ret == 0) {
-		ret = rmw_rbio(rbio);
-		rbio_orig_end_io(rbio, errno_to_blk_status(ret));
-	}
+	if (lock_stripe_add(rbio) == 0)
+		rmw_rbio(rbio);
 }
 
 static void rmw_rbio_work_locked(struct work_struct *work)
 {
-	struct btrfs_raid_bio *rbio;
-	int ret;
-
-	rbio = container_of(work, struct btrfs_raid_bio, work);
-
-	ret = rmw_rbio(rbio);
-	rbio_orig_end_io(rbio, errno_to_blk_status(ret));
+	rmw_rbio(container_of(work, struct btrfs_raid_bio, work));
 }
 
 /*
@@ -2506,7 +2430,6 @@ static int finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check)
 	struct sector_ptr p_sector = { 0 };
 	struct sector_ptr q_sector = { 0 };
 	struct bio_list bio_list;
-	struct bio *bio;
 	int is_replace = 0;
 	int ret;
 
@@ -2637,8 +2560,7 @@ submit_write:
 	return 0;
 
 cleanup:
-	while ((bio = bio_list_pop(&bio_list)))
-		bio_put(bio);
+	bio_list_put(&bio_list);
 	return ret;
 }
 
@@ -2733,15 +2655,12 @@ out:
 	return ret;
 }
 
-static int scrub_assemble_read_bios(struct btrfs_raid_bio *rbio,
-				    struct bio_list *bio_list)
+static int scrub_assemble_read_bios(struct btrfs_raid_bio *rbio)
 {
-	struct bio *bio;
+	struct bio_list bio_list = BIO_EMPTY_LIST;
 	int total_sector_nr;
 	int ret = 0;
 
-	ASSERT(bio_list_size(bio_list) == 0);
-
 	/* Build a list of bios to read all the missing parts. */
 	for (total_sector_nr = 0; total_sector_nr < rbio->nr_sectors;
 	     total_sector_nr++) {
@@ -2770,45 +2689,38 @@ static int scrub_assemble_read_bios(struct btrfs_raid_bio *rbio,
 		if (sector->uptodate)
 			continue;
 
-		ret = rbio_add_io_sector(rbio, bio_list, sector, stripe,
+		ret = rbio_add_io_sector(rbio, &bio_list, sector, stripe,
 					 sectornr, REQ_OP_READ);
-		if (ret)
-			goto error;
+		if (ret) {
+			bio_list_put(&bio_list);
+			return ret;
+		}
 	}
+
+	submit_read_wait_bio_list(rbio, &bio_list);
 	return 0;
-error:
-	while ((bio = bio_list_pop(bio_list)))
-		bio_put(bio);
-	return ret;
 }
 
-static int scrub_rbio(struct btrfs_raid_bio *rbio)
+static void scrub_rbio(struct btrfs_raid_bio *rbio)
 {
 	bool need_check = false;
-	struct bio_list bio_list;
 	int sector_nr;
 	int ret;
-	struct bio *bio;
-
-	bio_list_init(&bio_list);
 
 	ret = alloc_rbio_essential_pages(rbio);
 	if (ret)
-		goto cleanup;
+		goto out;
 
 	bitmap_clear(rbio->error_bitmap, 0, rbio->nr_sectors);
 
-	ret = scrub_assemble_read_bios(rbio, &bio_list);
+	ret = scrub_assemble_read_bios(rbio);
 	if (ret < 0)
-		goto cleanup;
-
-	submit_read_bios(rbio, &bio_list);
-	wait_event(rbio->io_wait, atomic_read(&rbio->stripes_pending) == 0);
+		goto out;
 
 	/* We may have some failures, recover the failed sectors first. */
 	ret = recover_scrub_rbio(rbio);
 	if (ret < 0)
-		goto cleanup;
+		goto out;
 
 	/*
 	 * We have every sector properly prepared. Can finish the scrub
@@ -2825,23 +2737,13 @@ static int scrub_rbio(struct btrfs_raid_bio *rbio)
 			break;
 		}
 	}
-	return ret;
-
-cleanup:
-	while ((bio = bio_list_pop(&bio_list)))
-		bio_put(bio);
-
-	return ret;
+out:
+	rbio_orig_end_io(rbio, errno_to_blk_status(ret));
 }
 
 static void scrub_rbio_work_locked(struct work_struct *work)
 {
-	struct btrfs_raid_bio *rbio;
-	int ret;
-
-	rbio = container_of(work, struct btrfs_raid_bio, work);
-	ret = scrub_rbio(rbio);
-	rbio_orig_end_io(rbio, errno_to_blk_status(ret));
+	scrub_rbio(container_of(work, struct btrfs_raid_bio, work));
 }
 
 void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio)
diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h
index 7c73a443939e..df0e0abdeb1f 100644
--- a/fs/btrfs/raid56.h
+++ b/fs/btrfs/raid56.h
@@ -65,7 +65,7 @@ struct btrfs_raid_bio {
 	/* Number of data stripes (no p/q) */
 	u8 nr_data;
 
-	/* Numer of all stripes (including P/Q) */
+	/* Number of all stripes (including P/Q) */
 	u8 real_stripes;
 
 	/* How many pages there are for each stripe */
@@ -132,7 +132,7 @@ struct btrfs_raid_bio {
 
 	/*
 	 * Checksum buffer if the rbio is for data.  The buffer should cover
-	 * all data sectors (exlcuding P/Q sectors).
+	 * all data sectors (excluding P/Q sectors).
 	 */
 	u8 *csum_buf;
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 31ec4a7658ce..ef13a9d4e370 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2825,7 +2825,7 @@ static noinline_for_stack int prealloc_file_extent_cluster(
 	 *
 	 * Here we have to manually invalidate the range (i_size, PAGE_END + 1).
 	 */
-	if (!IS_ALIGNED(i_size, PAGE_SIZE)) {
+	if (!PAGE_ALIGNED(i_size)) {
 		struct address_space *mapping = inode->vfs_inode.i_mapping;
 		struct btrfs_fs_info *fs_info = inode->root->fs_info;
 		const u32 sectorsize = fs_info->sectorsize;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 52b346795f66..69c93ae333f6 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -229,7 +229,7 @@ struct full_stripe_lock {
 };
 
 #ifndef CONFIG_64BIT
-/* This structure is for archtectures whose (void *) is smaller than u64 */
+/* This structure is for architectures whose (void *) is smaller than u64 */
 struct scrub_page_private {
 	u64 logical;
 };
@@ -2053,20 +2053,33 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock)
 	 * a) don't have an extent buffer and
 	 * b) the page is already kmapped
 	 */
-	if (sblock->logical != btrfs_stack_header_bytenr(h))
+	if (sblock->logical != btrfs_stack_header_bytenr(h)) {
 		sblock->header_error = 1;
-
-	if (sector->generation != btrfs_stack_header_generation(h)) {
-		sblock->header_error = 1;
-		sblock->generation_error = 1;
+		btrfs_warn_rl(fs_info,
+		"tree block %llu mirror %u has bad bytenr, has %llu want %llu",
+			      sblock->logical, sblock->mirror_num,
+			      btrfs_stack_header_bytenr(h),
+			      sblock->logical);
+		goto out;
 	}
 
-	if (!scrub_check_fsid(h->fsid, sector))
+	if (!scrub_check_fsid(h->fsid, sector)) {
 		sblock->header_error = 1;
+		btrfs_warn_rl(fs_info,
+		"tree block %llu mirror %u has bad fsid, has %pU want %pU",
+			      sblock->logical, sblock->mirror_num,
+			      h->fsid, sblock->dev->fs_devices->fsid);
+		goto out;
+	}
 
-	if (memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid,
-		   BTRFS_UUID_SIZE))
+	if (memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid, BTRFS_UUID_SIZE)) {
 		sblock->header_error = 1;
+		btrfs_warn_rl(fs_info,
+		"tree block %llu mirror %u has bad chunk tree uuid, has %pU want %pU",
+			      sblock->logical, sblock->mirror_num,
+			      h->chunk_tree_uuid, fs_info->chunk_tree_uuid);
+		goto out;
+	}
 
 	shash->tfm = fs_info->csum_shash;
 	crypto_shash_init(shash);
@@ -2079,9 +2092,27 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock)
 	}
 
 	crypto_shash_final(shash, calculated_csum);
-	if (memcmp(calculated_csum, on_disk_csum, sctx->fs_info->csum_size))
+	if (memcmp(calculated_csum, on_disk_csum, sctx->fs_info->csum_size)) {
 		sblock->checksum_error = 1;
+		btrfs_warn_rl(fs_info,
+		"tree block %llu mirror %u has bad csum, has " CSUM_FMT " want " CSUM_FMT,
+			      sblock->logical, sblock->mirror_num,
+			      CSUM_FMT_VALUE(fs_info->csum_size, on_disk_csum),
+			      CSUM_FMT_VALUE(fs_info->csum_size, calculated_csum));
+		goto out;
+	}
+
+	if (sector->generation != btrfs_stack_header_generation(h)) {
+		sblock->header_error = 1;
+		sblock->generation_error = 1;
+		btrfs_warn_rl(fs_info,
+		"tree block %llu mirror %u has bad generation, has %llu want %llu",
+			      sblock->logical, sblock->mirror_num,
+			      btrfs_stack_header_generation(h),
+			      sector->generation);
+	}
 
+out:
 	return sblock->header_error || sblock->checksum_error;
 }
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index d50182b6deec..e5c963bb873d 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -32,6 +32,7 @@
 #include "file-item.h"
 #include "ioctl.h"
 #include "verity.h"
+#include "lru_cache.h"
 
 /*
  * Maximum number of references an extent can have in order for us to attempt to
@@ -80,23 +81,23 @@ struct clone_root {
 	bool found_ref;
 };
 
-#define SEND_CTX_MAX_NAME_CACHE_SIZE 128
-#define SEND_CTX_NAME_CACHE_CLEAN_SIZE (SEND_CTX_MAX_NAME_CACHE_SIZE * 2)
+#define SEND_MAX_NAME_CACHE_SIZE			256
 
 /*
- * Limit the root_ids array of struct backref_cache_entry to 12 elements.
- * This makes the size of a cache entry to be exactly 128 bytes on x86_64.
+ * Limit the root_ids array of struct backref_cache_entry to 17 elements.
+ * This makes the size of a cache entry to be exactly 192 bytes on x86_64, which
+ * can be satisfied from the kmalloc-192 slab, without wasting any space.
  * The most common case is to have a single root for cloning, which corresponds
- * to the send root. Having the user specify more than 11 clone roots is not
+ * to the send root. Having the user specify more than 16 clone roots is not
  * common, and in such rare cases we simply don't use caching if the number of
- * cloning roots that lead down to a leaf is more than 12.
+ * cloning roots that lead down to a leaf is more than 17.
  */
-#define SEND_MAX_BACKREF_CACHE_ROOTS 12
+#define SEND_MAX_BACKREF_CACHE_ROOTS			17
 
 /*
  * Max number of entries in the cache.
- * With SEND_MAX_BACKREF_CACHE_ROOTS as 12, the size in bytes, excluding
- * maple tree's internal nodes, is 16K.
+ * With SEND_MAX_BACKREF_CACHE_ROOTS as 17, the size in bytes, excluding
+ * maple tree's internal nodes, is 24K.
  */
 #define SEND_MAX_BACKREF_CACHE_SIZE 128
 
@@ -107,15 +108,31 @@ struct clone_root {
  * x86_64).
  */
 struct backref_cache_entry {
-	/* List to link to the cache's lru list. */
-	struct list_head list;
-	/* The key for this entry in the cache. */
-	u64 key;
+	struct btrfs_lru_cache_entry entry;
 	u64 root_ids[SEND_MAX_BACKREF_CACHE_ROOTS];
 	/* Number of valid elements in the root_ids array. */
 	int num_roots;
 };
 
+/* See the comment at lru_cache.h about struct btrfs_lru_cache_entry. */
+static_assert(offsetof(struct backref_cache_entry, entry) == 0);
+
+/*
+ * Max number of entries in the cache that stores directories that were already
+ * created. The cache uses raw struct btrfs_lru_cache_entry entries, so it uses
+ * at most 4096 bytes - sizeof(struct btrfs_lru_cache_entry) is 48 bytes, but
+ * the kmalloc-64 slab is used, so we get 4096 bytes (64 bytes * 64).
+ */
+#define SEND_MAX_DIR_CREATED_CACHE_SIZE			64
+
+/*
+ * Max number of entries in the cache that stores directories that were already
+ * created. The cache uses raw struct btrfs_lru_cache_entry entries, so it uses
+ * at most 4096 bytes - sizeof(struct btrfs_lru_cache_entry) is 48 bytes, but
+ * the kmalloc-64 slab is used, so we get 4096 bytes (64 bytes * 64).
+ */
+#define SEND_MAX_DIR_UTIMES_CACHE_SIZE			64
+
 struct send_ctx {
 	struct file *send_filp;
 	loff_t send_off;
@@ -174,9 +191,7 @@ struct send_ctx {
 	struct list_head new_refs;
 	struct list_head deleted_refs;
 
-	struct radix_tree_root name_cache;
-	struct list_head name_cache_list;
-	int name_cache_size;
+	struct btrfs_lru_cache name_cache;
 
 	/*
 	 * The inode we are currently processing. It's not NULL only when we
@@ -285,13 +300,11 @@ struct send_ctx {
 	struct rb_root rbtree_new_refs;
 	struct rb_root rbtree_deleted_refs;
 
-	struct {
-		u64 last_reloc_trans;
-		struct list_head lru_list;
-		struct maple_tree entries;
-		/* Number of entries stored in the cache. */
-		int size;
-	} backref_cache;
+	struct btrfs_lru_cache backref_cache;
+	u64 backref_cache_last_reloc_trans;
+
+	struct btrfs_lru_cache dir_created_cache;
+	struct btrfs_lru_cache dir_utimes_cache;
 };
 
 struct pending_dir_move {
@@ -321,21 +334,15 @@ struct orphan_dir_info {
 	u64 ino;
 	u64 gen;
 	u64 last_dir_index_offset;
+	u64 dir_high_seq_ino;
 };
 
 struct name_cache_entry {
-	struct list_head list;
 	/*
-	 * radix_tree has only 32bit entries but we need to handle 64bit inums.
-	 * We use the lower 32bit of the 64bit inum to store it in the tree. If
-	 * more then one inum would fall into the same entry, we use radix_list
-	 * to store the additional entries. radix_list is also used to store
-	 * entries where two entries have the same inum but different
-	 * generations.
+	 * The key in the entry is an inode number, and the generation matches
+	 * the inode's generation.
 	 */
-	struct list_head radix_list;
-	u64 ino;
-	u64 gen;
+	struct btrfs_lru_cache_entry entry;
 	u64 parent_ino;
 	u64 parent_gen;
 	int ret;
@@ -344,6 +351,9 @@ struct name_cache_entry {
 	char name[];
 };
 
+/* See the comment at lru_cache.h about struct btrfs_lru_cache_entry. */
+static_assert(offsetof(struct name_cache_entry, entry) == 0);
+
 #define ADVANCE							1
 #define ADVANCE_ONLY_NEXT					-1
 
@@ -956,14 +966,12 @@ out:
 static int get_inode_gen(struct btrfs_root *root, u64 ino, u64 *gen)
 {
 	int ret;
-	struct btrfs_inode_info info;
+	struct btrfs_inode_info info = { 0 };
 
-	if (!gen)
-		return -EPERM;
+	ASSERT(gen);
 
 	ret = get_inode_info(root, ino, &info);
-	if (!ret)
-		*gen = info.gen;
+	*gen = info.gen;
 	return ret;
 }
 
@@ -1388,19 +1396,6 @@ static int iterate_backrefs(u64 ino, u64 offset, u64 num_bytes, u64 root_id,
 	return 0;
 }
 
-static void empty_backref_cache(struct send_ctx *sctx)
-{
-	struct backref_cache_entry *entry;
-	struct backref_cache_entry *tmp;
-
-	list_for_each_entry_safe(entry, tmp, &sctx->backref_cache.lru_list, list)
-		kfree(entry);
-
-	INIT_LIST_HEAD(&sctx->backref_cache.lru_list);
-	mtree_destroy(&sctx->backref_cache.entries);
-	sctx->backref_cache.size = 0;
-}
-
 static bool lookup_backref_cache(u64 leaf_bytenr, void *ctx,
 				 const u64 **root_ids_ret, int *root_count_ret)
 {
@@ -1408,9 +1403,10 @@ static bool lookup_backref_cache(u64 leaf_bytenr, void *ctx,
 	struct send_ctx *sctx = bctx->sctx;
 	struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
 	const u64 key = leaf_bytenr >> fs_info->sectorsize_bits;
+	struct btrfs_lru_cache_entry *raw_entry;
 	struct backref_cache_entry *entry;
 
-	if (sctx->backref_cache.size == 0)
+	if (btrfs_lru_cache_size(&sctx->backref_cache) == 0)
 		return false;
 
 	/*
@@ -1424,18 +1420,18 @@ static bool lookup_backref_cache(u64 leaf_bytenr, void *ctx,
 	 * transaction handle or holding fs_info->commit_root_sem, so no need
 	 * to take any lock here.
 	 */
-	if (fs_info->last_reloc_trans > sctx->backref_cache.last_reloc_trans) {
-		empty_backref_cache(sctx);
+	if (fs_info->last_reloc_trans > sctx->backref_cache_last_reloc_trans) {
+		btrfs_lru_cache_clear(&sctx->backref_cache);
 		return false;
 	}
 
-	entry = mtree_load(&sctx->backref_cache.entries, key);
-	if (!entry)
+	raw_entry = btrfs_lru_cache_lookup(&sctx->backref_cache, key, 0);
+	if (!raw_entry)
 		return false;
 
+	entry = container_of(raw_entry, struct backref_cache_entry, entry);
 	*root_ids_ret = entry->root_ids;
 	*root_count_ret = entry->num_roots;
-	list_move_tail(&entry->list, &sctx->backref_cache.lru_list);
 
 	return true;
 }
@@ -1461,7 +1457,8 @@ static void store_backref_cache(u64 leaf_bytenr, const struct ulist *root_ids,
 	if (!new_entry)
 		return;
 
-	new_entry->key = leaf_bytenr >> fs_info->sectorsize_bits;
+	new_entry->entry.key = leaf_bytenr >> fs_info->sectorsize_bits;
+	new_entry->entry.gen = 0;
 	new_entry->num_roots = 0;
 	ULIST_ITER_INIT(&uiter);
 	while ((node = ulist_next(root_ids, &uiter)) != NULL) {
@@ -1489,23 +1486,12 @@ static void store_backref_cache(u64 leaf_bytenr, const struct ulist *root_ids,
 	 * none of the roots is part of the list of roots from which we are
 	 * allowed to clone. Cache the new entry as it's still useful to avoid
 	 * backref walking to determine which roots have a path to the leaf.
+	 *
+	 * Also use GFP_NOFS because we're called while holding a transaction
+	 * handle or while holding fs_info->commit_root_sem.
 	 */
-
-	if (sctx->backref_cache.size >= SEND_MAX_BACKREF_CACHE_SIZE) {
-		struct backref_cache_entry *lru_entry;
-		struct backref_cache_entry *mt_entry;
-
-		lru_entry = list_first_entry(&sctx->backref_cache.lru_list,
-					     struct backref_cache_entry, list);
-		mt_entry = mtree_erase(&sctx->backref_cache.entries, lru_entry->key);
-		ASSERT(mt_entry == lru_entry);
-		list_del(&mt_entry->list);
-		kfree(mt_entry);
-		sctx->backref_cache.size--;
-	}
-
-	ret = mtree_insert(&sctx->backref_cache.entries, new_entry->key,
-			   new_entry, GFP_NOFS);
+	ret = btrfs_lru_cache_store(&sctx->backref_cache, &new_entry->entry,
+				    GFP_NOFS);
 	ASSERT(ret == 0 || ret == -ENOMEM);
 	if (ret) {
 		/* Caching is optional, no worries. */
@@ -1513,17 +1499,13 @@ static void store_backref_cache(u64 leaf_bytenr, const struct ulist *root_ids,
 		return;
 	}
 
-	list_add_tail(&new_entry->list, &sctx->backref_cache.lru_list);
-
 	/*
 	 * We are called from iterate_extent_inodes() while either holding a
 	 * transaction handle or holding fs_info->commit_root_sem, so no need
 	 * to take any lock here.
 	 */
-	if (sctx->backref_cache.size == 0)
-		sctx->backref_cache.last_reloc_trans = fs_info->last_reloc_trans;
-
-	sctx->backref_cache.size++;
+	if (btrfs_lru_cache_size(&sctx->backref_cache) == 1)
+		sctx->backref_cache_last_reloc_trans = fs_info->last_reloc_trans;
 }
 
 static int check_extent_item(u64 bytenr, const struct btrfs_extent_item *ei,
@@ -1886,7 +1868,8 @@ enum inode_state {
 	inode_state_did_delete,
 };
 
-static int get_cur_inode_state(struct send_ctx *sctx, u64 ino, u64 gen)
+static int get_cur_inode_state(struct send_ctx *sctx, u64 ino, u64 gen,
+			       u64 *send_gen, u64 *parent_gen)
 {
 	int ret;
 	int left_ret;
@@ -1900,6 +1883,8 @@ static int get_cur_inode_state(struct send_ctx *sctx, u64 ino, u64 gen)
 		goto out;
 	left_ret = (info.nlink == 0) ? -ENOENT : ret;
 	left_gen = info.gen;
+	if (send_gen)
+		*send_gen = ((left_ret == -ENOENT) ? 0 : info.gen);
 
 	if (!sctx->parent_root) {
 		right_ret = -ENOENT;
@@ -1909,6 +1894,8 @@ static int get_cur_inode_state(struct send_ctx *sctx, u64 ino, u64 gen)
 			goto out;
 		right_ret = (info.nlink == 0) ? -ENOENT : ret;
 		right_gen = info.gen;
+		if (parent_gen)
+			*parent_gen = ((right_ret == -ENOENT) ? 0 : info.gen);
 	}
 
 	if (!left_ret && !right_ret) {
@@ -1953,14 +1940,15 @@ out:
 	return ret;
 }
 
-static int is_inode_existent(struct send_ctx *sctx, u64 ino, u64 gen)
+static int is_inode_existent(struct send_ctx *sctx, u64 ino, u64 gen,
+			     u64 *send_gen, u64 *parent_gen)
 {
 	int ret;
 
 	if (ino == BTRFS_FIRST_FREE_OBJECTID)
 		return 1;
 
-	ret = get_cur_inode_state(sctx, ino, gen);
+	ret = get_cur_inode_state(sctx, ino, gen, send_gen, parent_gen);
 	if (ret < 0)
 		goto out;
 
@@ -2121,43 +2109,36 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 			      const char *name, int name_len,
 			      u64 *who_ino, u64 *who_gen, u64 *who_mode)
 {
-	int ret = 0;
-	u64 gen;
+	int ret;
+	u64 parent_root_dir_gen;
 	u64 other_inode = 0;
 	struct btrfs_inode_info info;
 
 	if (!sctx->parent_root)
-		goto out;
+		return 0;
 
-	ret = is_inode_existent(sctx, dir, dir_gen);
+	ret = is_inode_existent(sctx, dir, dir_gen, NULL, &parent_root_dir_gen);
 	if (ret <= 0)
-		goto out;
+		return 0;
 
 	/*
 	 * If we have a parent root we need to verify that the parent dir was
 	 * not deleted and then re-created, if it was then we have no overwrite
 	 * and we can just unlink this entry.
+	 *
+	 * @parent_root_dir_gen was set to 0 if the inode does not exist in the
+	 * parent root.
 	 */
-	if (sctx->parent_root && dir != BTRFS_FIRST_FREE_OBJECTID) {
-		ret = get_inode_gen(sctx->parent_root, dir, &gen);
-		if (ret < 0 && ret != -ENOENT)
-			goto out;
-		if (ret) {
-			ret = 0;
-			goto out;
-		}
-		if (gen != dir_gen)
-			goto out;
-	}
+	if (sctx->parent_root && dir != BTRFS_FIRST_FREE_OBJECTID &&
+	    parent_root_dir_gen != dir_gen)
+		return 0;
 
 	ret = lookup_dir_item_inode(sctx->parent_root, dir, name, name_len,
 				    &other_inode);
-	if (ret < 0 && ret != -ENOENT)
-		goto out;
-	if (ret) {
-		ret = 0;
-		goto out;
-	}
+	if (ret == -ENOENT)
+		return 0;
+	else if (ret < 0)
+		return ret;
 
 	/*
 	 * Check if the overwritten ref was already processed. If yes, the ref
@@ -2168,18 +2149,15 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 	    is_waiting_for_move(sctx, other_inode)) {
 		ret = get_inode_info(sctx->parent_root, other_inode, &info);
 		if (ret < 0)
-			goto out;
+			return ret;
 
-		ret = 1;
 		*who_ino = other_inode;
 		*who_gen = info.gen;
 		*who_mode = info.mode;
-	} else {
-		ret = 0;
+		return 1;
 	}
 
-out:
-	return ret;
+	return 0;
 }
 
 /*
@@ -2194,47 +2172,43 @@ static int did_overwrite_ref(struct send_ctx *sctx,
 			    u64 ino, u64 ino_gen,
 			    const char *name, int name_len)
 {
-	int ret = 0;
-	u64 gen;
+	int ret;
 	u64 ow_inode;
+	u64 ow_gen = 0;
+	u64 send_root_dir_gen;
 
 	if (!sctx->parent_root)
-		goto out;
+		return 0;
 
-	ret = is_inode_existent(sctx, dir, dir_gen);
+	ret = is_inode_existent(sctx, dir, dir_gen, &send_root_dir_gen, NULL);
 	if (ret <= 0)
-		goto out;
+		return ret;
 
-	if (dir != BTRFS_FIRST_FREE_OBJECTID) {
-		ret = get_inode_gen(sctx->send_root, dir, &gen);
-		if (ret < 0 && ret != -ENOENT)
-			goto out;
-		if (ret) {
-			ret = 0;
-			goto out;
-		}
-		if (gen != dir_gen)
-			goto out;
-	}
+	/*
+	 * @send_root_dir_gen was set to 0 if the inode does not exist in the
+	 * send root.
+	 */
+	if (dir != BTRFS_FIRST_FREE_OBJECTID && send_root_dir_gen != dir_gen)
+		return 0;
 
 	/* check if the ref was overwritten by another ref */
 	ret = lookup_dir_item_inode(sctx->send_root, dir, name, name_len,
 				    &ow_inode);
-	if (ret < 0 && ret != -ENOENT)
-		goto out;
-	if (ret) {
+	if (ret == -ENOENT) {
 		/* was never and will never be overwritten */
-		ret = 0;
-		goto out;
+		return 0;
+	} else if (ret < 0) {
+		return ret;
 	}
 
-	ret = get_inode_gen(sctx->send_root, ow_inode, &gen);
-	if (ret < 0)
-		goto out;
+	if (ow_inode == ino) {
+		ret = get_inode_gen(sctx->send_root, ow_inode, &ow_gen);
+		if (ret < 0)
+			return ret;
 
-	if (ow_inode == ino && gen == ino_gen) {
-		ret = 0;
-		goto out;
+		/* It's the same inode, so no overwrite happened. */
+		if (ow_gen == ino_gen)
+			return 0;
 	}
 
 	/*
@@ -2243,15 +2217,20 @@ static int did_overwrite_ref(struct send_ctx *sctx,
 	 * inode 'ino' to be orphanized, therefore check if ow_inode matches
 	 * the current inode being processed.
 	 */
-	if ((ow_inode < sctx->send_progress) ||
-	    (ino != sctx->cur_ino && ow_inode == sctx->cur_ino &&
-	     gen == sctx->cur_inode_gen))
-		ret = 1;
-	else
-		ret = 0;
+	if (ow_inode < sctx->send_progress)
+		return 1;
 
-out:
-	return ret;
+	if (ino != sctx->cur_ino && ow_inode == sctx->cur_ino) {
+		if (ow_gen == 0) {
+			ret = get_inode_gen(sctx->send_root, ow_inode, &ow_gen);
+			if (ret < 0)
+				return ret;
+		}
+		if (ow_gen == sctx->cur_inode_gen)
+			return 1;
+	}
+
+	return 0;
 }
 
 /*
@@ -2285,113 +2264,16 @@ out:
 	return ret;
 }
 
-/*
- * Insert a name cache entry. On 32bit kernels the radix tree index is 32bit,
- * so we need to do some special handling in case we have clashes. This function
- * takes care of this with the help of name_cache_entry::radix_list.
- * In case of error, nce is kfreed.
- */
-static int name_cache_insert(struct send_ctx *sctx,
-			     struct name_cache_entry *nce)
+static inline struct name_cache_entry *name_cache_search(struct send_ctx *sctx,
+							 u64 ino, u64 gen)
 {
-	int ret = 0;
-	struct list_head *nce_head;
-
-	nce_head = radix_tree_lookup(&sctx->name_cache,
-			(unsigned long)nce->ino);
-	if (!nce_head) {
-		nce_head = kmalloc(sizeof(*nce_head), GFP_KERNEL);
-		if (!nce_head) {
-			kfree(nce);
-			return -ENOMEM;
-		}
-		INIT_LIST_HEAD(nce_head);
-
-		ret = radix_tree_insert(&sctx->name_cache, nce->ino, nce_head);
-		if (ret < 0) {
-			kfree(nce_head);
-			kfree(nce);
-			return ret;
-		}
-	}
-	list_add_tail(&nce->radix_list, nce_head);
-	list_add_tail(&nce->list, &sctx->name_cache_list);
-	sctx->name_cache_size++;
-
-	return ret;
-}
+	struct btrfs_lru_cache_entry *entry;
 
-static void name_cache_delete(struct send_ctx *sctx,
-			      struct name_cache_entry *nce)
-{
-	struct list_head *nce_head;
-
-	nce_head = radix_tree_lookup(&sctx->name_cache,
-			(unsigned long)nce->ino);
-	if (!nce_head) {
-		btrfs_err(sctx->send_root->fs_info,
-	      "name_cache_delete lookup failed ino %llu cache size %d, leaking memory",
-			nce->ino, sctx->name_cache_size);
-	}
-
-	list_del(&nce->radix_list);
-	list_del(&nce->list);
-	sctx->name_cache_size--;
-
-	/*
-	 * We may not get to the final release of nce_head if the lookup fails
-	 */
-	if (nce_head && list_empty(nce_head)) {
-		radix_tree_delete(&sctx->name_cache, (unsigned long)nce->ino);
-		kfree(nce_head);
-	}
-}
-
-static struct name_cache_entry *name_cache_search(struct send_ctx *sctx,
-						    u64 ino, u64 gen)
-{
-	struct list_head *nce_head;
-	struct name_cache_entry *cur;
-
-	nce_head = radix_tree_lookup(&sctx->name_cache, (unsigned long)ino);
-	if (!nce_head)
+	entry = btrfs_lru_cache_lookup(&sctx->name_cache, ino, gen);
+	if (!entry)
 		return NULL;
 
-	list_for_each_entry(cur, nce_head, radix_list) {
-		if (cur->ino == ino && cur->gen == gen)
-			return cur;
-	}
-	return NULL;
-}
-
-/*
- * Remove some entries from the beginning of name_cache_list.
- */
-static void name_cache_clean_unused(struct send_ctx *sctx)
-{
-	struct name_cache_entry *nce;
-
-	if (sctx->name_cache_size < SEND_CTX_NAME_CACHE_CLEAN_SIZE)
-		return;
-
-	while (sctx->name_cache_size > SEND_CTX_MAX_NAME_CACHE_SIZE) {
-		nce = list_entry(sctx->name_cache_list.next,
-				struct name_cache_entry, list);
-		name_cache_delete(sctx, nce);
-		kfree(nce);
-	}
-}
-
-static void name_cache_free(struct send_ctx *sctx)
-{
-	struct name_cache_entry *nce;
-
-	while (!list_empty(&sctx->name_cache_list)) {
-		nce = list_entry(sctx->name_cache_list.next,
-				struct name_cache_entry, list);
-		name_cache_delete(sctx, nce);
-		kfree(nce);
-	}
+	return container_of(entry, struct name_cache_entry, entry);
 }
 
 /*
@@ -2410,7 +2292,7 @@ static int __get_cur_name_and_parent(struct send_ctx *sctx,
 {
 	int ret;
 	int nce_ret;
-	struct name_cache_entry *nce = NULL;
+	struct name_cache_entry *nce;
 
 	/*
 	 * First check if we already did a call to this function with the same
@@ -2420,17 +2302,9 @@ static int __get_cur_name_and_parent(struct send_ctx *sctx,
 	nce = name_cache_search(sctx, ino, gen);
 	if (nce) {
 		if (ino < sctx->send_progress && nce->need_later_update) {
-			name_cache_delete(sctx, nce);
-			kfree(nce);
+			btrfs_lru_cache_remove(&sctx->name_cache, &nce->entry);
 			nce = NULL;
 		} else {
-			/*
-			 * Removes the entry from the list and adds it back to
-			 * the end.  This marks the entry as recently used so
-			 * that name_cache_clean_unused does not remove it.
-			 */
-			list_move_tail(&nce->list, &sctx->name_cache_list);
-
 			*parent_ino = nce->parent_ino;
 			*parent_gen = nce->parent_gen;
 			ret = fs_path_add(dest, nce->name, nce->name_len);
@@ -2446,7 +2320,7 @@ static int __get_cur_name_and_parent(struct send_ctx *sctx,
 	 * This should only happen for the parent dir that we determine in
 	 * record_new_ref_if_needed().
 	 */
-	ret = is_inode_existent(sctx, ino, gen);
+	ret = is_inode_existent(sctx, ino, gen, NULL, NULL);
 	if (ret < 0)
 		goto out;
 
@@ -2497,8 +2371,8 @@ out_cache:
 		goto out;
 	}
 
-	nce->ino = ino;
-	nce->gen = gen;
+	nce->entry.key = ino;
+	nce->entry.gen = gen;
 	nce->parent_ino = *parent_ino;
 	nce->parent_gen = *parent_gen;
 	nce->name_len = fs_path_len(dest);
@@ -2510,10 +2384,11 @@ out_cache:
 	else
 		nce->need_later_update = 1;
 
-	nce_ret = name_cache_insert(sctx, nce);
-	if (nce_ret < 0)
+	nce_ret = btrfs_lru_cache_store(&sctx->name_cache, &nce->entry, GFP_KERNEL);
+	if (nce_ret < 0) {
+		kfree(nce);
 		ret = nce_ret;
-	name_cache_clean_unused(sctx);
+	}
 
 out:
 	return ret;
@@ -2884,6 +2759,63 @@ out:
 }
 
 /*
+ * If the cache is full, we can't remove entries from it and do a call to
+ * send_utimes() for each respective inode, because we might be finishing
+ * processing an inode that is a directory and it just got renamed, and existing
+ * entries in the cache may refer to inodes that have the directory in their
+ * full path - in which case we would generate outdated paths (pre-rename)
+ * for the inodes that the cache entries point to. Instead of prunning the
+ * cache when inserting, do it after we finish processing each inode at
+ * finish_inode_if_needed().
+ */
+static int cache_dir_utimes(struct send_ctx *sctx, u64 dir, u64 gen)
+{
+	struct btrfs_lru_cache_entry *entry;
+	int ret;
+
+	entry = btrfs_lru_cache_lookup(&sctx->dir_utimes_cache, dir, gen);
+	if (entry != NULL)
+		return 0;
+
+	/* Caching is optional, don't fail if we can't allocate memory. */
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return send_utimes(sctx, dir, gen);
+
+	entry->key = dir;
+	entry->gen = gen;
+
+	ret = btrfs_lru_cache_store(&sctx->dir_utimes_cache, entry, GFP_KERNEL);
+	ASSERT(ret != -EEXIST);
+	if (ret) {
+		kfree(entry);
+		return send_utimes(sctx, dir, gen);
+	}
+
+	return 0;
+}
+
+static int trim_dir_utimes_cache(struct send_ctx *sctx)
+{
+	while (btrfs_lru_cache_size(&sctx->dir_utimes_cache) >
+	       SEND_MAX_DIR_UTIMES_CACHE_SIZE) {
+		struct btrfs_lru_cache_entry *lru;
+		int ret;
+
+		lru = btrfs_lru_cache_lru_entry(&sctx->dir_utimes_cache);
+		ASSERT(lru != NULL);
+
+		ret = send_utimes(sctx, lru->key, lru->gen);
+		if (ret)
+			return ret;
+
+		btrfs_lru_cache_remove(&sctx->dir_utimes_cache, lru);
+	}
+
+	return 0;
+}
+
+/*
  * Sends a BTRFS_SEND_C_MKXXX or SYMLINK command to user space. We don't have
  * a valid path yet because we did not process the refs yet. So, the inode
  * is created as orphan.
@@ -2971,6 +2903,23 @@ out:
 	return ret;
 }
 
+static void cache_dir_created(struct send_ctx *sctx, u64 dir)
+{
+	struct btrfs_lru_cache_entry *entry;
+	int ret;
+
+	/* Caching is optional, ignore any failures. */
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return;
+
+	entry->key = dir;
+	entry->gen = 0;
+	ret = btrfs_lru_cache_store(&sctx->dir_created_cache, entry, GFP_KERNEL);
+	if (ret < 0)
+		kfree(entry);
+}
+
 /*
  * We need some special handling for inodes that get processed before the parent
  * directory got created. See process_recorded_refs for details.
@@ -2986,6 +2935,9 @@ static int did_create_dir(struct send_ctx *sctx, u64 dir)
 	struct btrfs_key di_key;
 	struct btrfs_dir_item *di;
 
+	if (btrfs_lru_cache_lookup(&sctx->dir_created_cache, dir, 0))
+		return 1;
+
 	path = alloc_path_for_send();
 	if (!path)
 		return -ENOMEM;
@@ -3009,6 +2961,7 @@ static int did_create_dir(struct send_ctx *sctx, u64 dir)
 		if (di_key.type != BTRFS_ROOT_ITEM_KEY &&
 		    di_key.objectid < sctx->send_progress) {
 			ret = 1;
+			cache_dir_created(sctx, dir);
 			break;
 		}
 	}
@@ -3038,7 +2991,12 @@ static int send_create_inode_if_needed(struct send_ctx *sctx)
 			return 0;
 	}
 
-	return send_create_inode(sctx, sctx->cur_ino);
+	ret = send_create_inode(sctx, sctx->cur_ino);
+
+	if (ret == 0 && S_ISDIR(sctx->cur_inode_mode))
+		cache_dir_created(sctx, sctx->cur_ino);
+
+	return ret;
 }
 
 struct recorded_ref {
@@ -3166,6 +3124,7 @@ static struct orphan_dir_info *add_orphan_dir_info(struct send_ctx *sctx,
 	odi->ino = dir_ino;
 	odi->gen = dir_gen;
 	odi->last_dir_index_offset = 0;
+	odi->dir_high_seq_ino = 0;
 
 	rb_link_node(&odi->node, parent, p);
 	rb_insert_color(&odi->node, &sctx->orphan_dirs);
@@ -3215,8 +3174,7 @@ static void free_orphan_dir_info(struct send_ctx *sctx,
  * We check this by iterating all dir items and checking if the inode behind
  * the dir item was already processed.
  */
-static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
-		     u64 send_progress)
+static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen)
 {
 	int ret = 0;
 	int iter_ret = 0;
@@ -3227,6 +3185,8 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 	struct btrfs_key loc;
 	struct btrfs_dir_item *di;
 	struct orphan_dir_info *odi = NULL;
+	u64 dir_high_seq_ino = 0;
+	u64 last_dir_index_offset = 0;
 
 	/*
 	 * Don't try to rmdir the top/root subvolume dir.
@@ -3234,17 +3194,62 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 	if (dir == BTRFS_FIRST_FREE_OBJECTID)
 		return 0;
 
+	odi = get_orphan_dir_info(sctx, dir, dir_gen);
+	if (odi && sctx->cur_ino < odi->dir_high_seq_ino)
+		return 0;
+
 	path = alloc_path_for_send();
 	if (!path)
 		return -ENOMEM;
 
+	if (!odi) {
+		/*
+		 * Find the inode number associated with the last dir index
+		 * entry. This is very likely the inode with the highest number
+		 * of all inodes that have an entry in the directory. We can
+		 * then use it to avoid future calls to can_rmdir(), when
+		 * processing inodes with a lower number, from having to search
+		 * the parent root b+tree for dir index keys.
+		 */
+		key.objectid = dir;
+		key.type = BTRFS_DIR_INDEX_KEY;
+		key.offset = (u64)-1;
+
+		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+		if (ret < 0) {
+			goto out;
+		} else if (ret > 0) {
+			/* Can't happen, the root is never empty. */
+			ASSERT(path->slots[0] > 0);
+			if (WARN_ON(path->slots[0] == 0)) {
+				ret = -EUCLEAN;
+				goto out;
+			}
+			path->slots[0]--;
+		}
+
+		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+		if (key.objectid != dir || key.type != BTRFS_DIR_INDEX_KEY) {
+			/* No index keys, dir can be removed. */
+			ret = 1;
+			goto out;
+		}
+
+		di = btrfs_item_ptr(path->nodes[0], path->slots[0],
+				    struct btrfs_dir_item);
+		btrfs_dir_item_key_to_cpu(path->nodes[0], di, &loc);
+		dir_high_seq_ino = loc.objectid;
+		if (sctx->cur_ino < dir_high_seq_ino) {
+			ret = 0;
+			goto out;
+		}
+
+		btrfs_release_path(path);
+	}
+
 	key.objectid = dir;
 	key.type = BTRFS_DIR_INDEX_KEY;
-	key.offset = 0;
-
-	odi = get_orphan_dir_info(sctx, dir, dir_gen);
-	if (odi)
-		key.offset = odi->last_dir_index_offset;
+	key.offset = (odi ? odi->last_dir_index_offset : 0);
 
 	btrfs_for_each_slot(root, &key, &found_key, path, iter_ret) {
 		struct waiting_dir_move *dm;
@@ -3257,29 +3262,18 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 				struct btrfs_dir_item);
 		btrfs_dir_item_key_to_cpu(path->nodes[0], di, &loc);
 
+		dir_high_seq_ino = max(dir_high_seq_ino, loc.objectid);
+		last_dir_index_offset = found_key.offset;
+
 		dm = get_waiting_dir_move(sctx, loc.objectid);
 		if (dm) {
-			odi = add_orphan_dir_info(sctx, dir, dir_gen);
-			if (IS_ERR(odi)) {
-				ret = PTR_ERR(odi);
-				goto out;
-			}
-			odi->gen = dir_gen;
-			odi->last_dir_index_offset = found_key.offset;
 			dm->rmdir_ino = dir;
 			dm->rmdir_gen = dir_gen;
 			ret = 0;
 			goto out;
 		}
 
-		if (loc.objectid > send_progress) {
-			odi = add_orphan_dir_info(sctx, dir, dir_gen);
-			if (IS_ERR(odi)) {
-				ret = PTR_ERR(odi);
-				goto out;
-			}
-			odi->gen = dir_gen;
-			odi->last_dir_index_offset = found_key.offset;
+		if (loc.objectid > sctx->cur_ino) {
 			ret = 0;
 			goto out;
 		}
@@ -3294,7 +3288,22 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 
 out:
 	btrfs_free_path(path);
-	return ret;
+
+	if (ret)
+		return ret;
+
+	if (!odi) {
+		odi = add_orphan_dir_info(sctx, dir, dir_gen);
+		if (IS_ERR(odi))
+			return PTR_ERR(odi);
+
+		odi->gen = dir_gen;
+	}
+
+	odi->last_dir_index_offset = last_dir_index_offset;
+	odi->dir_high_seq_ino = max(odi->dir_high_seq_ino, dir_high_seq_ino);
+
+	return 0;
 }
 
 static int is_waiting_for_move(struct send_ctx *sctx, u64 ino)
@@ -3579,7 +3588,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 		}
 		gen = odi->gen;
 
-		ret = can_rmdir(sctx, rmdir_ino, gen, sctx->cur_ino);
+		ret = can_rmdir(sctx, rmdir_ino, gen);
 		if (ret < 0)
 			goto out;
 		if (!ret)
@@ -3599,7 +3608,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 	}
 
 finish:
-	ret = send_utimes(sctx, pm->ino, pm->gen);
+	ret = cache_dir_utimes(sctx, pm->ino, pm->gen);
 	if (ret < 0)
 		goto out;
 
@@ -3619,7 +3628,7 @@ finish:
 		if (ret < 0)
 			goto out;
 
-		ret = send_utimes(sctx, cur->dir, cur->dir_gen);
+		ret = cache_dir_utimes(sctx, cur->dir, cur->dir_gen);
 		if (ret < 0)
 			goto out;
 	}
@@ -4242,7 +4251,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 	 * "testdir_2".
 	 */
 	list_for_each_entry(cur, &sctx->new_refs, list) {
-		ret = get_cur_inode_state(sctx, cur->dir, cur->dir_gen);
+		ret = get_cur_inode_state(sctx, cur->dir, cur->dir_gen, NULL, NULL);
 		if (ret < 0)
 			goto out;
 		if (ret == inode_state_will_create)
@@ -4288,12 +4297,9 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 				 * the source path when performing its rename
 				 * operation.
 				 */
-				if (is_waiting_for_move(sctx, ow_inode)) {
-					wdm = get_waiting_dir_move(sctx,
-								   ow_inode);
-					ASSERT(wdm);
+				wdm = get_waiting_dir_move(sctx, ow_inode);
+				if (wdm)
 					wdm->orphanized = true;
-				}
 
 				/*
 				 * Make sure we clear our orphanized inode's
@@ -4306,10 +4312,9 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 				 * and get instead the orphan name.
 				 */
 				nce = name_cache_search(sctx, ow_inode, ow_gen);
-				if (nce) {
-					name_cache_delete(sctx, nce);
-					kfree(nce);
-				}
+				if (nce)
+					btrfs_lru_cache_remove(&sctx->name_cache,
+							       &nce->entry);
 
 				/*
 				 * ow_inode might currently be an ancestor of
@@ -4358,7 +4363,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 		 * parent directory out of order. But we need to check if this
 		 * did already happen before due to other refs in the same dir.
 		 */
-		ret = get_cur_inode_state(sctx, cur->dir, cur->dir_gen);
+		ret = get_cur_inode_state(sctx, cur->dir, cur->dir_gen, NULL, NULL);
 		if (ret < 0)
 			goto out;
 		if (ret == inode_state_will_create) {
@@ -4388,6 +4393,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 				ret = send_create_inode(sctx, cur->dir);
 				if (ret < 0)
 					goto out;
+				cache_dir_created(sctx, cur->dir);
 			}
 		}
 
@@ -4470,8 +4476,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 		 * later, we do this check again and rmdir it then if possible.
 		 * See the use of check_dirs for more details.
 		 */
-		ret = can_rmdir(sctx, sctx->cur_ino, sctx->cur_inode_gen,
-				sctx->cur_ino);
+		ret = can_rmdir(sctx, sctx->cur_ino, sctx->cur_inode_gen);
 		if (ret < 0)
 			goto out;
 		if (ret) {
@@ -4564,20 +4569,18 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 		if (cur->dir > sctx->cur_ino)
 			continue;
 
-		ret = get_cur_inode_state(sctx, cur->dir, cur->dir_gen);
+		ret = get_cur_inode_state(sctx, cur->dir, cur->dir_gen, NULL, NULL);
 		if (ret < 0)
 			goto out;
 
 		if (ret == inode_state_did_create ||
 		    ret == inode_state_no_change) {
-			/* TODO delayed utimes */
-			ret = send_utimes(sctx, cur->dir, cur->dir_gen);
+			ret = cache_dir_utimes(sctx, cur->dir, cur->dir_gen);
 			if (ret < 0)
 				goto out;
 		} else if (ret == inode_state_did_delete &&
 			   cur->dir != last_dir_ino_rm) {
-			ret = can_rmdir(sctx, cur->dir, cur->dir_gen,
-					sctx->cur_ino);
+			ret = can_rmdir(sctx, cur->dir, cur->dir_gen);
 			if (ret < 0)
 				goto out;
 			if (ret) {
@@ -5635,7 +5638,7 @@ static int send_encoded_extent(struct send_ctx *sctx, struct btrfs_path *path,
 	 * boundary in the send buffer. This means that there may be a gap
 	 * between the beginning of the command and the file data.
 	 */
-	data_offset = ALIGN(sctx->send_size, PAGE_SIZE);
+	data_offset = PAGE_ALIGN(sctx->send_size);
 	if (data_offset > sctx->send_max_size ||
 	    sctx->send_max_size - data_offset < disk_num_bytes) {
 		ret = -EOVERFLOW;
@@ -5759,7 +5762,7 @@ static int send_extent_data(struct send_ctx *sctx, struct btrfs_path *path,
 		sent += size;
 	}
 
-	if (sctx->clean_page_cache && IS_ALIGNED(end, PAGE_SIZE)) {
+	if (sctx->clean_page_cache && PAGE_ALIGNED(end)) {
 		/*
 		 * Always operate only on ranges that are a multiple of the page
 		 * size. This is not only to prevent zeroing parts of a page in
@@ -6754,12 +6757,26 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 		 * it's moved/renamed, therefore we don't need to do it here.
 		 */
 		sctx->send_progress = sctx->cur_ino + 1;
-		ret = send_utimes(sctx, sctx->cur_ino, sctx->cur_inode_gen);
+
+		/*
+		 * If the current inode is a non-empty directory, delay issuing
+		 * the utimes command for it, as it's very likely we have inodes
+		 * with an higher number inside it. We want to issue the utimes
+		 * command only after adding all dentries to it.
+		 */
+		if (S_ISDIR(sctx->cur_inode_mode) && sctx->cur_inode_size > 0)
+			ret = cache_dir_utimes(sctx, sctx->cur_ino, sctx->cur_inode_gen);
+		else
+			ret = send_utimes(sctx, sctx->cur_ino, sctx->cur_inode_gen);
+
 		if (ret < 0)
 			goto out;
 	}
 
 out:
+	if (!ret)
+		ret = trim_dir_utimes_cache(sctx);
+
 	return ret;
 }
 
@@ -8044,6 +8061,8 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
 	int clone_sources_to_rollback = 0;
 	size_t alloc_size;
 	int sort_clone_roots = 0;
+	struct btrfs_lru_cache_entry *entry;
+	struct btrfs_lru_cache_entry *tmp;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -8094,11 +8113,22 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
 
 	INIT_LIST_HEAD(&sctx->new_refs);
 	INIT_LIST_HEAD(&sctx->deleted_refs);
-	INIT_RADIX_TREE(&sctx->name_cache, GFP_KERNEL);
-	INIT_LIST_HEAD(&sctx->name_cache_list);
 
-	INIT_LIST_HEAD(&sctx->backref_cache.lru_list);
-	mt_init(&sctx->backref_cache.entries);
+	btrfs_lru_cache_init(&sctx->name_cache, SEND_MAX_NAME_CACHE_SIZE);
+	btrfs_lru_cache_init(&sctx->backref_cache, SEND_MAX_BACKREF_CACHE_SIZE);
+	btrfs_lru_cache_init(&sctx->dir_created_cache,
+			     SEND_MAX_DIR_CREATED_CACHE_SIZE);
+	/*
+	 * This cache is periodically trimmed to a fixed size elsewhere, see
+	 * cache_dir_utimes() and trim_dir_utimes_cache().
+	 */
+	btrfs_lru_cache_init(&sctx->dir_utimes_cache, 0);
+
+	sctx->pending_dir_moves = RB_ROOT;
+	sctx->waiting_dir_moves = RB_ROOT;
+	sctx->orphan_dirs = RB_ROOT;
+	sctx->rbtree_new_refs = RB_ROOT;
+	sctx->rbtree_deleted_refs = RB_ROOT;
 
 	sctx->flags = arg->flags;
 
@@ -8165,12 +8195,6 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
 		goto out;
 	}
 
-	sctx->pending_dir_moves = RB_ROOT;
-	sctx->waiting_dir_moves = RB_ROOT;
-	sctx->orphan_dirs = RB_ROOT;
-	sctx->rbtree_new_refs = RB_ROOT;
-	sctx->rbtree_deleted_refs = RB_ROOT;
-
 	sctx->clone_roots = kvcalloc(sizeof(*sctx->clone_roots),
 				     arg->clone_sources_count + 1,
 				     GFP_KERNEL);
@@ -8279,6 +8303,13 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
 	if (ret < 0)
 		goto out;
 
+	btrfs_lru_cache_for_each_entry_safe(&sctx->dir_utimes_cache, entry, tmp) {
+		ret = send_utimes(sctx, entry->key, entry->gen);
+		if (ret < 0)
+			goto out;
+		btrfs_lru_cache_remove(&sctx->dir_utimes_cache, entry);
+	}
+
 	if (!(sctx->flags & BTRFS_SEND_FLAG_OMIT_END_CMD)) {
 		ret = begin_cmd(sctx, BTRFS_SEND_C_END);
 		if (ret < 0)
@@ -8358,11 +8389,12 @@ out:
 		kvfree(sctx->send_buf);
 		kvfree(sctx->verity_descriptor);
 
-		name_cache_free(sctx);
-
 		close_current_inode(sctx);
 
-		empty_backref_cache(sctx);
+		btrfs_lru_cache_clear(&sctx->name_cache);
+		btrfs_lru_cache_clear(&sctx->backref_cache);
+		btrfs_lru_cache_clear(&sctx->dir_created_cache);
+		btrfs_lru_cache_clear(&sctx->dir_utimes_cache);
 
 		kfree(sctx);
 	}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 433ce221dc5c..581845bc206a 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -58,6 +58,7 @@
 #include "scrub.h"
 #include "verity.h"
 #include "super.h"
+#include "extent-tree.h"
 #define CREATE_TRACE_POINTS
 #include <trace/events/btrfs.h>
 
@@ -2049,7 +2050,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 		}
 
 		/*
-		 * Metadata in mixed block goup profiles are accounted in data
+		 * Metadata in mixed block group profiles are accounted in data
 		 */
 		if (!mixed && found->flags & BTRFS_BLOCK_GROUP_METADATA) {
 			if (found->flags & BTRFS_BLOCK_GROUP_DATA)
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 45615ce36498..8c5efa5813b3 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -702,7 +702,7 @@ static void release_raid_kobj(struct kobject *kobj)
 	kfree(to_raid_kobj(kobj));
 }
 
-static struct kobj_type btrfs_raid_ktype = {
+static const struct kobj_type btrfs_raid_ktype = {
 	.sysfs_ops = &kobj_sysfs_ops,
 	.release = release_raid_kobj,
 	.default_groups = raid_groups,
@@ -900,7 +900,7 @@ static void space_info_release(struct kobject *kobj)
 	kfree(sinfo);
 }
 
-static struct kobj_type space_info_ktype = {
+static const struct kobj_type space_info_ktype = {
 	.sysfs_ops = &kobj_sysfs_ops,
 	.release = space_info_release,
 	.default_groups = space_info_groups,
@@ -1259,7 +1259,7 @@ static void btrfs_release_fsid_kobj(struct kobject *kobj)
 	complete(&fs_devs->kobj_unregister);
 }
 
-static struct kobj_type btrfs_ktype = {
+static const struct kobj_type btrfs_ktype = {
 	.sysfs_ops	= &kobj_sysfs_ops,
 	.release	= btrfs_release_fsid_kobj,
 };
@@ -1789,7 +1789,7 @@ static void btrfs_release_devid_kobj(struct kobject *kobj)
 	complete(&device->kobj_unregister);
 }
 
-static struct kobj_type devid_ktype = {
+static const struct kobj_type devid_ktype = {
 	.sysfs_ops	= &kobj_sysfs_ops,
 	.default_groups = devid_groups,
 	.release	= btrfs_release_devid_kobj,
@@ -2103,7 +2103,7 @@ static void qgroups_release(struct kobject *kobj)
 	kfree(kobj);
 }
 
-static struct kobj_type qgroups_ktype = {
+static const struct kobj_type qgroups_ktype = {
 	.sysfs_ops = &kobj_sysfs_ops,
 	.default_groups = qgroups_groups,
 	.release = qgroups_release,
@@ -2173,7 +2173,7 @@ static void qgroup_release(struct kobject *kobj)
 	memset(&qgroup->kobj, 0, sizeof(*kobj));
 }
 
-static struct kobj_type qgroup_ktype = {
+static const struct kobj_type qgroup_ktype = {
 	.sysfs_ops = &kobj_sysfs_ops,
 	.release = qgroup_release,
 	.default_groups = qgroup_groups,
@@ -2272,36 +2272,23 @@ void btrfs_sysfs_del_one_qgroup(struct btrfs_fs_info *fs_info,
  * Change per-fs features in /sys/fs/btrfs/UUID/features to match current
  * values in superblock. Call after any changes to incompat/compat_ro flags
  */
-void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info,
-		u64 bit, enum btrfs_feature_set set)
+void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_fs_devices *fs_devs;
 	struct kobject *fsid_kobj;
-	u64 __maybe_unused features;
-	int __maybe_unused ret;
+	int ret;
 
 	if (!fs_info)
 		return;
 
-	/*
-	 * See 14e46e04958df74 and e410e34fad913dd, feature bit updates are not
-	 * safe when called from some contexts (eg. balance)
-	 */
-	features = get_features(fs_info, set);
-	ASSERT(bit & supported_feature_masks[set]);
-
-	fs_devs = fs_info->fs_devices;
-	fsid_kobj = &fs_devs->fsid_kobj;
-
+	fsid_kobj = &fs_info->fs_devices->fsid_kobj;
 	if (!fsid_kobj->state_initialized)
 		return;
 
-	/*
-	 * FIXME: this is too heavy to update just one value, ideally we'd like
-	 * to use sysfs_update_group but some refactoring is needed first.
-	 */
-	sysfs_remove_group(fsid_kobj, &btrfs_feature_attr_group);
-	ret = sysfs_create_group(fsid_kobj, &btrfs_feature_attr_group);
+	ret = sysfs_update_group(fsid_kobj, &btrfs_feature_attr_group);
+	if (ret < 0)
+		btrfs_warn(fs_info,
+			   "failed to update /sys/fs/btrfs/%pU/features: %d",
+			   fs_info->fs_devices->fsid, ret);
 }
 
 int __init btrfs_init_sysfs(void)
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index bacef43f7267..86c7eef12873 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -19,8 +19,7 @@ void btrfs_sysfs_remove_device(struct btrfs_device *device);
 int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs);
 void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs);
 void btrfs_sysfs_update_sprout_fsid(struct btrfs_fs_devices *fs_devices);
-void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info,
-		u64 bit, enum btrfs_feature_set set);
+void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info);
 void btrfs_kobject_uevent(struct block_device *bdev, enum kobject_action action);
 
 int __init btrfs_init_sysfs(void);
diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c
index c5b3a631bf4f..f2f2e11dac4c 100644
--- a/fs/btrfs/tests/extent-map-tests.c
+++ b/fs/btrfs/tests/extent-map-tests.c
@@ -509,7 +509,7 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info,
 		goto out_free;
 	}
 
-	ret = btrfs_rmap_block(fs_info, em->start, NULL, btrfs_sb_offset(1),
+	ret = btrfs_rmap_block(fs_info, em->start, btrfs_sb_offset(1),
 			       &logical, &out_ndaddrs, &out_stripe_len);
 	if (ret || (out_ndaddrs == 0 && test->expected_mapped_addr)) {
 		test_err("didn't rmap anything but expected %d",
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index b8c52e89688c..18329ebcb1cb 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -2464,6 +2464,11 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	wake_up(&fs_info->transaction_wait);
 	btrfs_trans_state_lockdep_release(fs_info, BTRFS_LOCKDEP_TRANS_UNBLOCKED);
 
+	/* If we have features changed, wake up the cleaner to update sysfs. */
+	if (test_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags) &&
+	    fs_info->cleaner_kthread)
+		wake_up_process(fs_info->cleaner_kthread);
+
 	ret = btrfs_write_and_wait_transaction(trans);
 	if (ret) {
 		btrfs_handle_fs_error(fs_info, ret,
@@ -2604,6 +2609,35 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_fs_info *fs_info)
 	return (ret < 0) ? 0 : 1;
 }
 
+/*
+ * We only mark the transaction aborted and then set the file system read-only.
+ * This will prevent new transactions from starting or trying to join this
+ * one.
+ *
+ * This means that error recovery at the call site is limited to freeing
+ * any local memory allocations and passing the error code up without
+ * further cleanup. The transaction should complete as it normally would
+ * in the call path but will return -EIO.
+ *
+ * We'll complete the cleanup in btrfs_end_transaction and
+ * btrfs_commit_transaction.
+ */
+void __cold __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
+				      const char *function,
+				      unsigned int line, int errno, bool first_hit)
+{
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+
+	WRITE_ONCE(trans->aborted, errno);
+	WRITE_ONCE(trans->transaction->aborted, errno);
+	if (first_hit && errno == -ENOSPC)
+		btrfs_dump_space_info_for_trans_abort(fs_info);
+	/* Wake up anybody who may be waiting on this transaction */
+	wake_up(&fs_info->transaction_wait);
+	wake_up(&fs_info->transaction_blocked_wait);
+	__btrfs_handle_fs_error(fs_info, function, line, errno, NULL);
+}
+
 int __init btrfs_transaction_init(void)
 {
 	btrfs_trans_handle_cachep = kmem_cache_create("btrfs_trans_handle",
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 97f6c39f59c8..fa728ab80826 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -202,6 +202,34 @@ static inline void btrfs_clear_skip_qgroup(struct btrfs_trans_handle *trans)
 	delayed_refs->qgroup_to_skip = 0;
 }
 
+bool __cold abort_should_print_stack(int errno);
+
+/*
+ * Call btrfs_abort_transaction as early as possible when an error condition is
+ * detected, that way the exact stack trace is reported for some errors.
+ */
+#define btrfs_abort_transaction(trans, errno)		\
+do {								\
+	bool first = false;					\
+	/* Report first abort since mount */			\
+	if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED,	\
+			&((trans)->fs_info->fs_state))) {	\
+		first = true;					\
+		if (WARN(abort_should_print_stack(errno),	\
+			KERN_ERR				\
+			"BTRFS: Transaction aborted (error %d)\n",	\
+			(errno))) {					\
+			/* Stack trace printed. */			\
+		} else {						\
+			btrfs_debug((trans)->fs_info,			\
+				    "Transaction aborted (error %d)", \
+				  (errno));			\
+		}						\
+	}							\
+	__btrfs_abort_transaction((trans), __func__,		\
+				  __LINE__, (errno), first);	\
+} while (0)
+
 int btrfs_end_transaction(struct btrfs_trans_handle *trans);
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
 						   unsigned int num_items);
@@ -236,6 +264,9 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction);
 void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root);
 void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
+void __cold __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
+				      const char *function,
+				      unsigned int line, int errno, bool first_hit);
 
 int __init btrfs_transaction_init(void);
 void __cold btrfs_transaction_exit(void);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 58599189bd18..200cea6e49e5 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -279,12 +279,6 @@ void btrfs_end_log_trans(struct btrfs_root *root)
 	}
 }
 
-static void btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
-{
-	filemap_fdatawait_range(buf->pages[0]->mapping,
-			        buf->start, buf->start + buf->len - 1);
-}
-
 /*
  * the walk control struct is used to pass state down the chain when
  * processing the log tree.  The stage field tells us which part
@@ -2623,11 +2617,12 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 					return ret;
 				}
 
+				btrfs_tree_lock(next);
+				btrfs_clear_buffer_dirty(trans, next);
+				wait_on_extent_buffer_writeback(next);
+				btrfs_tree_unlock(next);
+
 				if (trans) {
-					btrfs_tree_lock(next);
-					btrfs_clean_tree_block(next);
-					btrfs_wait_tree_block_writeback(next);
-					btrfs_tree_unlock(next);
 					ret = btrfs_pin_reserved_extent(trans,
 							bytenr, blocksize);
 					if (ret) {
@@ -2637,8 +2632,6 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 					btrfs_redirty_list_add(
 						trans->transaction, next);
 				} else {
-					if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
-						clear_extent_buffer_dirty(next);
 					unaccount_log_buffer(fs_info, bytenr);
 				}
 			}
@@ -2693,11 +2686,12 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
 
 				next = path->nodes[*level];
 
+				btrfs_tree_lock(next);
+				btrfs_clear_buffer_dirty(trans, next);
+				wait_on_extent_buffer_writeback(next);
+				btrfs_tree_unlock(next);
+
 				if (trans) {
-					btrfs_tree_lock(next);
-					btrfs_clean_tree_block(next);
-					btrfs_wait_tree_block_writeback(next);
-					btrfs_tree_unlock(next);
 					ret = btrfs_pin_reserved_extent(trans,
 						     path->nodes[*level]->start,
 						     path->nodes[*level]->len);
@@ -2706,9 +2700,6 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
 					btrfs_redirty_list_add(trans->transaction,
 							       next);
 				} else {
-					if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
-						clear_extent_buffer_dirty(next);
-
 					unaccount_log_buffer(fs_info,
 						path->nodes[*level]->start);
 				}
@@ -2776,19 +2767,18 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 
 			next = path->nodes[orig_level];
 
+			btrfs_tree_lock(next);
+			btrfs_clear_buffer_dirty(trans, next);
+			wait_on_extent_buffer_writeback(next);
+			btrfs_tree_unlock(next);
+
 			if (trans) {
-				btrfs_tree_lock(next);
-				btrfs_clean_tree_block(next);
-				btrfs_wait_tree_block_writeback(next);
-				btrfs_tree_unlock(next);
 				ret = btrfs_pin_reserved_extent(trans,
 						next->start, next->len);
 				if (ret)
 					goto out;
 				btrfs_redirty_list_add(trans->transaction, next);
 			} else {
-				if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
-					clear_extent_buffer_dirty(next);
 				unaccount_log_buffer(fs_info, next->start);
 			}
 		}
@@ -3652,11 +3642,10 @@ static int flush_dir_items_batch(struct btrfs_trans_handle *trans,
 
 	/*
 	 * If for some unexpected reason the last item's index is not greater
-	 * than the last index we logged, warn and return an error to fallback
-	 * to a transaction commit.
+	 * than the last index we logged, warn and force a transaction commit.
 	 */
 	if (WARN_ON(last_index <= inode->last_dir_index_offset))
-		ret = -EUCLEAN;
+		ret = BTRFS_LOG_FORCE_COMMIT;
 	else
 		inode->last_dir_index_offset = last_index;
 out:
@@ -3794,7 +3783,6 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 	struct btrfs_key min_key;
 	struct btrfs_root *root = inode->root;
 	struct btrfs_root *log = root->log_root;
-	int err = 0;
 	int ret;
 	u64 last_old_dentry_offset = min_offset - 1;
 	u64 last_offset = (u64)-1;
@@ -3835,8 +3823,8 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 					      path->slots[0]);
 			if (tmp.type == BTRFS_DIR_INDEX_KEY)
 				last_old_dentry_offset = tmp.offset;
-		} else if (ret < 0) {
-			err = ret;
+		} else if (ret > 0) {
+			ret = 0;
 		}
 
 		goto done;
@@ -3859,7 +3847,6 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 		if (tmp.type == BTRFS_DIR_INDEX_KEY)
 			last_old_dentry_offset = tmp.offset;
 	} else if (ret < 0) {
-		err = ret;
 		goto done;
 	}
 
@@ -3881,12 +3868,15 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 	 */
 search:
 	ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
-	if (ret > 0)
+	if (ret > 0) {
 		ret = btrfs_next_item(root, path);
+		if (ret > 0) {
+			/* There are no more keys in the inode's root. */
+			ret = 0;
+			goto done;
+		}
+	}
 	if (ret < 0)
-		err = ret;
-	/* If ret is 1, there are no more keys in the inode's root. */
-	if (ret != 0)
 		goto done;
 
 	/*
@@ -3897,8 +3887,8 @@ search:
 		ret = process_dir_items_leaf(trans, inode, path, dst_path, ctx,
 					     &last_old_dentry_offset);
 		if (ret != 0) {
-			if (ret < 0)
-				err = ret;
+			if (ret > 0)
+				ret = 0;
 			goto done;
 		}
 		path->slots[0] = btrfs_header_nritems(path->nodes[0]);
@@ -3909,10 +3899,10 @@ search:
 		 */
 		ret = btrfs_next_leaf(root, path);
 		if (ret) {
-			if (ret == 1)
+			if (ret == 1) {
 				last_offset = (u64)-1;
-			else
-				err = ret;
+				ret = 0;
+			}
 			goto done;
 		}
 		btrfs_item_key_to_cpu(path->nodes[0], &min_key, path->slots[0]);
@@ -3943,7 +3933,7 @@ done:
 	btrfs_release_path(path);
 	btrfs_release_path(dst_path);
 
-	if (err == 0) {
+	if (ret == 0) {
 		*last_offset_ret = last_offset;
 		/*
 		 * In case the leaf was changed in the current transaction but
@@ -3954,15 +3944,13 @@ done:
 		 * a range, last_old_dentry_offset is == to last_offset.
 		 */
 		ASSERT(last_old_dentry_offset <= last_offset);
-		if (last_old_dentry_offset < last_offset) {
+		if (last_old_dentry_offset < last_offset)
 			ret = insert_dir_log_key(trans, log, path, ino,
 						 last_old_dentry_offset + 1,
 						 last_offset);
-			if (ret)
-				err = ret;
-		}
 	}
-	return err;
+
+	return ret;
 }
 
 /*
@@ -5604,10 +5592,8 @@ static int add_conflicting_inode(struct btrfs_trans_handle *trans,
 	 * LOG_INODE_EXISTS mode) and slow down other fsyncs or transaction
 	 * commits.
 	 */
-	if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES) {
-		btrfs_set_log_full_commit(trans);
+	if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES)
 		return BTRFS_LOG_FORCE_COMMIT;
-	}
 
 	inode = btrfs_iget(root->fs_info->sb, ino, root);
 	/*
@@ -6466,7 +6452,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	 * result in losing the file after a log replay.
 	 */
 	if (full_dir_logging && inode->last_unlink_trans >= trans->transid) {
-		btrfs_set_log_full_commit(trans);
 		ret = BTRFS_LOG_FORCE_COMMIT;
 		goto out_unlock;
 	}
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index 85cd24cb0540..bdeb5216718f 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -13,8 +13,13 @@
 /* return value for btrfs_log_dentry_safe that means we don't need to log it at all */
 #define BTRFS_NO_LOG_SYNC 256
 
-/* We can't use the tree log for whatever reason, force a transaction commit */
-#define BTRFS_LOG_FORCE_COMMIT				(1)
+/*
+ * We can't use the tree log for whatever reason, force a transaction commit.
+ * We use a negative value because there are functions through the logging code
+ * that need to return an error (< 0 value), false (0) or true (1). Any negative
+ * value will do, as it will cause the log to be marked for a full sync.
+ */
+#define BTRFS_LOG_FORCE_COMMIT				(-(MAX_ERRNO + 1))
 
 struct btrfs_log_ctx {
 	int log_ret;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index df43093b7a46..7823168c08a6 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -728,7 +728,7 @@ static struct btrfs_fs_devices *find_fsid_reverted_metadata(
 	/*
 	 * Handle the case where the scanned device is part of an fs whose last
 	 * metadata UUID change reverted it to the original FSID. At the same
-	 * time * fs_devices was first created by another constitutent device
+	 * time fs_devices was first created by another constituent device
 	 * which didn't fully observe the operation. This results in an
 	 * btrfs_fs_devices created with metadata/fsid different AND
 	 * btrfs_fs_devices::fsid_change set AND the metadata_uuid of the
@@ -6284,91 +6284,42 @@ static bool need_full_stripe(enum btrfs_map_op op)
 	return (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS);
 }
 
-/*
- * Calculate the geometry of a particular (address, len) tuple. This
- * information is used to calculate how big a particular bio can get before it
- * straddles a stripe.
- *
- * @fs_info: the filesystem
- * @em:      mapping containing the logical extent
- * @op:      type of operation - write or read
- * @logical: address that we want to figure out the geometry of
- * @io_geom: pointer used to return values
- *
- * Returns < 0 in case a chunk for the given logical address cannot be found,
- * usually shouldn't happen unless @logical is corrupted, 0 otherwise.
- */
-int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *em,
-			  enum btrfs_map_op op, u64 logical,
-			  struct btrfs_io_geometry *io_geom)
+static u64 btrfs_max_io_len(struct map_lookup *map, enum btrfs_map_op op,
+			    u64 offset, u64 *stripe_nr, u64 *stripe_offset,
+			    u64 *full_stripe_start)
 {
-	struct map_lookup *map;
-	u64 len;
-	u64 offset;
-	u64 stripe_offset;
-	u64 stripe_nr;
-	u32 stripe_len;
-	u64 raid56_full_stripe_start = (u64)-1;
-	int data_stripes;
+	u32 stripe_len = map->stripe_len;
 
 	ASSERT(op != BTRFS_MAP_DISCARD);
 
-	map = em->map_lookup;
-	/* Offset of this logical address in the chunk */
-	offset = logical - em->start;
-	/* Len of a stripe in a chunk */
-	stripe_len = map->stripe_len;
 	/*
-	 * Stripe_nr is where this block falls in
-	 * stripe_offset is the offset of this block in its stripe.
+	 * Stripe_nr is the stripe where this block falls.  stripe_offset is
+	 * the offset of this block in its stripe.
 	 */
-	stripe_nr = div64_u64_rem(offset, stripe_len, &stripe_offset);
-	ASSERT(stripe_offset < U32_MAX);
+	*stripe_nr = div64_u64_rem(offset, stripe_len, stripe_offset);
+	ASSERT(*stripe_offset < U32_MAX);
 
-	data_stripes = nr_data_stripes(map);
+	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+		unsigned long full_stripe_len = stripe_len * nr_data_stripes(map);
 
-	/* Only stripe based profiles needs to check against stripe length. */
-	if (map->type & BTRFS_BLOCK_GROUP_STRIPE_MASK) {
-		u64 max_len = stripe_len - stripe_offset;
+		*full_stripe_start =
+			div64_u64(offset, full_stripe_len) * full_stripe_len;
 
 		/*
-		 * In case of raid56, we need to know the stripe aligned start
+		 * For writes to RAID56, allow to write a full stripe set, but
+		 * no straddling of stripe sets.
 		 */
-		if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
-			unsigned long full_stripe_len = stripe_len * data_stripes;
-			raid56_full_stripe_start = offset;
-
-			/*
-			 * Allow a write of a full stripe, but make sure we
-			 * don't allow straddling of stripes
-			 */
-			raid56_full_stripe_start = div64_u64(raid56_full_stripe_start,
-					full_stripe_len);
-			raid56_full_stripe_start *= full_stripe_len;
-
-			/*
-			 * For writes to RAID[56], allow a full stripeset across
-			 * all disks. For other RAID types and for RAID[56]
-			 * reads, just allow a single stripe (on a single disk).
-			 */
-			if (op == BTRFS_MAP_WRITE) {
-				max_len = stripe_len * data_stripes -
-					  (offset - raid56_full_stripe_start);
-			}
-		}
-		len = min_t(u64, em->len - offset, max_len);
-	} else {
-		len = em->len - offset;
+		if (op == BTRFS_MAP_WRITE)
+			return full_stripe_len - (offset - *full_stripe_start);
 	}
 
-	io_geom->len = len;
-	io_geom->offset = offset;
-	io_geom->stripe_len = stripe_len;
-	io_geom->stripe_nr = stripe_nr;
-	io_geom->stripe_offset = stripe_offset;
-	io_geom->raid56_stripe_offset = raid56_full_stripe_start;
-
-	return 0;
+	/*
+	 * For other RAID types and for RAID56 reads, allow a single stripe (on
+	 * a single disk).
+	 */
+	if (map->type & BTRFS_BLOCK_GROUP_STRIPE_MASK)
+		return stripe_len - *stripe_offset;
+	return U64_MAX;
 }
 
 static void set_io_stripe(struct btrfs_io_stripe *dst, const struct map_lookup *map,
@@ -6387,6 +6338,7 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 {
 	struct extent_map *em;
 	struct map_lookup *map;
+	u64 map_offset;
 	u64 stripe_offset;
 	u64 stripe_nr;
 	u64 stripe_len;
@@ -6405,7 +6357,7 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	int patch_the_first_stripe_for_dev_replace = 0;
 	u64 physical_to_patch_in_first_stripe = 0;
 	u64 raid56_full_stripe_start = (u64)-1;
-	struct btrfs_io_geometry geom;
+	u64 max_len;
 
 	ASSERT(bioc_ret);
 	ASSERT(op != BTRFS_MAP_DISCARD);
@@ -6413,18 +6365,14 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	em = btrfs_get_chunk_map(fs_info, logical, *length);
 	ASSERT(!IS_ERR(em));
 
-	ret = btrfs_get_io_geometry(fs_info, em, op, logical, &geom);
-	if (ret < 0)
-		return ret;
-
 	map = em->map_lookup;
-
-	*length = geom.len;
-	stripe_len = geom.stripe_len;
-	stripe_nr = geom.stripe_nr;
-	stripe_offset = geom.stripe_offset;
-	raid56_full_stripe_start = geom.raid56_stripe_offset;
 	data_stripes = nr_data_stripes(map);
+	stripe_len = map->stripe_len;
+
+	map_offset = logical - em->start;
+	max_len = btrfs_max_io_len(map, op, map_offset, &stripe_nr,
+				   &stripe_offset, &raid56_full_stripe_start);
+	*length = min_t(u64, em->len - map_offset, max_len);
 
 	down_read(&dev_replace->rwsem);
 	dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 6b7a05f6cf82..7e51f2238f72 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -53,21 +53,6 @@ enum btrfs_raid_types {
 	BTRFS_NR_RAID_TYPES
 };
 
-struct btrfs_io_geometry {
-	/* remaining bytes before crossing a stripe */
-	u64 len;
-	/* offset of logical address in chunk */
-	u64 offset;
-	/* length of single IO stripe */
-	u32 stripe_len;
-	/* offset of address in stripe */
-	u32 stripe_offset;
-	/* number of stripe where address falls */
-	u64 stripe_nr;
-	/* offset of raid56 stripe into the chunk */
-	u64 raid56_stripe_offset;
-};
-
 /*
  * Use sequence counter to get consistent device stat data on
  * 32-bit processors.
@@ -545,9 +530,6 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 					       u64 logical, u64 *length_ret,
 					       u32 *num_stripes);
-int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *map,
-			  enum btrfs_map_op op, u64 logical,
-			  struct btrfs_io_geometry *io_geom);
 int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
 int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
 struct btrfs_block_group *btrfs_create_chunk(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 1f503e8e42d4..f95b2c94d619 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -17,6 +17,7 @@
 #include "space-info.h"
 #include "fs.h"
 #include "accessors.h"
+#include "bio.h"
 
 /* Maximum number of zones to report per blkdev_report_zones() call */
 #define BTRFS_REPORT_NR_ZONES   4096
@@ -160,7 +161,7 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones,
  */
 static inline u32 sb_zone_number(int shift, int mirror)
 {
-	u64 zone;
+	u64 zone = U64_MAX;
 
 	ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
 	switch (mirror) {
@@ -220,7 +221,6 @@ static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos,
 			       struct blk_zone *zones, unsigned int *nr_zones)
 {
 	struct btrfs_zoned_device_info *zinfo = device->zone_info;
-	u32 zno;
 	int ret;
 
 	if (!*nr_zones)
@@ -235,6 +235,7 @@ static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos,
 	/* Check cache */
 	if (zinfo->zone_cache) {
 		unsigned int i;
+		u32 zno;
 
 		ASSERT(IS_ALIGNED(pos, zinfo->zone_size));
 		zno = pos >> zinfo->zone_size_shift;
@@ -274,9 +275,12 @@ static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos,
 		return -EIO;
 
 	/* Populate cache */
-	if (zinfo->zone_cache)
+	if (zinfo->zone_cache) {
+		u32 zno = pos >> zinfo->zone_size_shift;
+
 		memcpy(zinfo->zone_cache + zno, zones,
 		       sizeof(*zinfo->zone_cache) * *nr_zones);
+	}
 
 	return 0;
 }
@@ -417,25 +421,6 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
 	nr_sectors = bdev_nr_sectors(bdev);
 	zone_info->zone_size_shift = ilog2(zone_info->zone_size);
 	zone_info->nr_zones = nr_sectors >> ilog2(zone_sectors);
-	/*
-	 * We limit max_zone_append_size also by max_segments *
-	 * PAGE_SIZE. Technically, we can have multiple pages per segment. But,
-	 * since btrfs adds the pages one by one to a bio, and btrfs cannot
-	 * increase the metadata reservation even if it increases the number of
-	 * extents, it is safe to stick with the limit.
-	 *
-	 * With the zoned emulation, we can have non-zoned device on the zoned
-	 * mode. In this case, we don't have a valid max zone append size. So,
-	 * use max_segments * PAGE_SIZE as the pseudo max_zone_append_size.
-	 */
-	if (bdev_is_zoned(bdev)) {
-		zone_info->max_zone_append_size = min_t(u64,
-			(u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT,
-			(u64)bdev_max_segments(bdev) << PAGE_SHIFT);
-	} else {
-		zone_info->max_zone_append_size =
-			(u64)bdev_max_segments(bdev) << PAGE_SHIFT;
-	}
 	if (!IS_ALIGNED(nr_sectors, zone_sectors))
 		zone_info->nr_zones++;
 
@@ -715,9 +700,9 @@ static int btrfs_check_for_zoned_device(struct btrfs_fs_info *fs_info)
 
 int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 {
+	struct queue_limits *lim = &fs_info->limits;
 	struct btrfs_device *device;
 	u64 zone_size = 0;
-	u64 max_zone_append_size = 0;
 	int ret;
 
 	/*
@@ -727,6 +712,8 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 	if (!btrfs_fs_incompat(fs_info, ZONED))
 		return btrfs_check_for_zoned_device(fs_info);
 
+	blk_set_stacking_limits(lim);
+
 	list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
 		struct btrfs_zoned_device_info *zone_info = device->zone_info;
 
@@ -741,10 +728,17 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 				  zone_info->zone_size, zone_size);
 			return -EINVAL;
 		}
-		if (!max_zone_append_size ||
-		    (zone_info->max_zone_append_size &&
-		     zone_info->max_zone_append_size < max_zone_append_size))
-			max_zone_append_size = zone_info->max_zone_append_size;
+
+		/*
+		 * With the zoned emulation, we can have non-zoned device on the
+		 * zoned mode. In this case, we don't have a valid max zone
+		 * append size.
+		 */
+		if (bdev_is_zoned(device->bdev)) {
+			blk_stack_limits(lim,
+					 &bdev_get_queue(device->bdev)->limits,
+					 0);
+		}
 	}
 
 	/*
@@ -765,8 +759,18 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 	}
 
 	fs_info->zone_size = zone_size;
-	fs_info->max_zone_append_size = ALIGN_DOWN(max_zone_append_size,
-						   fs_info->sectorsize);
+	/*
+	 * Also limit max_zone_append_size by max_segments * PAGE_SIZE.
+	 * Technically, we can have multiple pages per segment. But, since
+	 * we add the pages one by one to a bio, and cannot increase the
+	 * metadata reservation even if it increases the number of extents, it
+	 * is safe to stick with the limit.
+	 */
+	fs_info->max_zone_append_size = ALIGN_DOWN(
+		min3((u64)lim->max_zone_append_sectors << SECTOR_SHIFT,
+		     (u64)lim->max_sectors << SECTOR_SHIFT,
+		     (u64)lim->max_segments << PAGE_SHIFT),
+		fs_info->sectorsize);
 	fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED;
 	if (fs_info->max_zone_append_size < fs_info->max_extent_size)
 		fs_info->max_extent_size = fs_info->max_zone_append_size;
@@ -1623,8 +1627,10 @@ void btrfs_free_redirty_list(struct btrfs_transaction *trans)
 	spin_unlock(&trans->releasing_ebs_lock);
 }
 
-bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start)
+bool btrfs_use_zone_append(struct btrfs_bio *bbio)
 {
+	u64 start = (bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT);
+	struct btrfs_inode *inode = bbio->inode;
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_block_group *cache;
 	bool ret = false;
@@ -1635,6 +1641,9 @@ bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start)
 	if (!is_data_inode(&inode->vfs_inode))
 		return false;
 
+	if (btrfs_op(&bbio->bio) != BTRFS_MAP_WRITE)
+		return false;
+
 	/*
 	 * Using REQ_OP_ZONE_APPNED for relocation can break assumptions on the
 	 * extent layout the relocation code has.
@@ -1657,22 +1666,16 @@ bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start)
 	return ret;
 }
 
-void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset,
-				 struct bio *bio)
+void btrfs_record_physical_zoned(struct btrfs_bio *bbio)
 {
+	const u64 physical = bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT;
 	struct btrfs_ordered_extent *ordered;
-	const u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
 
-	if (bio_op(bio) != REQ_OP_ZONE_APPEND)
-		return;
-
-	ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode), file_offset);
+	ordered = btrfs_lookup_ordered_extent(bbio->inode, bbio->file_offset);
 	if (WARN_ON(!ordered))
 		return;
 
 	ordered->physical = physical;
-	ordered->bdev = bio->bi_bdev;
-
 	btrfs_put_ordered_extent(ordered);
 }
 
@@ -1684,43 +1687,46 @@ void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered)
 	struct extent_map *em;
 	struct btrfs_ordered_sum *sum;
 	u64 orig_logical = ordered->disk_bytenr;
-	u64 *logical = NULL;
-	int nr, stripe_len;
+	struct map_lookup *map;
+	u64 physical = ordered->physical;
+	u64 chunk_start_phys;
+	u64 logical;
 
-	/* Zoned devices should not have partitions. So, we can assume it is 0 */
-	ASSERT(!bdev_is_partition(ordered->bdev));
-	if (WARN_ON(!ordered->bdev))
+	em = btrfs_get_chunk_map(fs_info, orig_logical, 1);
+	if (IS_ERR(em))
 		return;
+	map = em->map_lookup;
+	chunk_start_phys = map->stripes[0].physical;
 
-	if (WARN_ON(btrfs_rmap_block(fs_info, orig_logical, ordered->bdev,
-				     ordered->physical, &logical, &nr,
-				     &stripe_len)))
-		goto out;
-
-	WARN_ON(nr != 1);
+	if (WARN_ON_ONCE(map->num_stripes > 1) ||
+	    WARN_ON_ONCE((map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0) ||
+	    WARN_ON_ONCE(physical < chunk_start_phys) ||
+	    WARN_ON_ONCE(physical > chunk_start_phys + em->orig_block_len)) {
+		free_extent_map(em);
+		return;
+	}
+	logical = em->start + (physical - map->stripes[0].physical);
+	free_extent_map(em);
 
-	if (orig_logical == *logical)
-		goto out;
+	if (orig_logical == logical)
+		return;
 
-	ordered->disk_bytenr = *logical;
+	ordered->disk_bytenr = logical;
 
 	em_tree = &inode->extent_tree;
 	write_lock(&em_tree->lock);
 	em = search_extent_mapping(em_tree, ordered->file_offset,
 				   ordered->num_bytes);
-	em->block_start = *logical;
+	em->block_start = logical;
 	free_extent_map(em);
 	write_unlock(&em_tree->lock);
 
 	list_for_each_entry(sum, &ordered->list, list) {
-		if (*logical < orig_logical)
-			sum->bytenr -= orig_logical - *logical;
+		if (logical < orig_logical)
+			sum->bytenr -= orig_logical - logical;
 		else
-			sum->bytenr += *logical - orig_logical;
+			sum->bytenr += logical - orig_logical;
 	}
-
-out:
-	kfree(logical);
 }
 
 bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
@@ -1845,26 +1851,6 @@ int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical,
 	return btrfs_zoned_issue_zeroout(tgt_dev, physical_pos, length);
 }
 
-struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info,
-					    u64 logical, u64 length)
-{
-	struct btrfs_device *device;
-	struct extent_map *em;
-	struct map_lookup *map;
-
-	em = btrfs_get_chunk_map(fs_info, logical, length);
-	if (IS_ERR(em))
-		return ERR_CAST(em);
-
-	map = em->map_lookup;
-	/* We only support single profile for now */
-	device = map->stripes[0].dev;
-
-	free_extent_map(em);
-
-	return device;
-}
-
 /*
  * Activate block group and underlying device zones
  *
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index f43990985d80..c0570d35fea2 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -20,7 +20,6 @@ struct btrfs_zoned_device_info {
 	 */
 	u64 zone_size;
 	u8  zone_size_shift;
-	u64 max_zone_append_size;
 	u32 nr_zones;
 	unsigned int max_active_zones;
 	atomic_t active_zones_left;
@@ -56,9 +55,8 @@ void btrfs_calc_zone_unusable(struct btrfs_block_group *cache);
 void btrfs_redirty_list_add(struct btrfs_transaction *trans,
 			    struct extent_buffer *eb);
 void btrfs_free_redirty_list(struct btrfs_transaction *trans);
-bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start);
-void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset,
-				 struct bio *bio);
+bool btrfs_use_zone_append(struct btrfs_bio *bbio);
+void btrfs_record_physical_zoned(struct btrfs_bio *bbio);
 void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered);
 bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
 				    struct extent_buffer *eb,
@@ -68,8 +66,6 @@ void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache,
 int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length);
 int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical,
 				  u64 physical_start, u64 physical_pos);
-struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info,
-					    u64 logical, u64 length);
 bool btrfs_zone_activate(struct btrfs_block_group *block_group);
 int btrfs_zone_finish(struct btrfs_block_group *block_group);
 bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags);
@@ -185,13 +181,12 @@ static inline void btrfs_redirty_list_add(struct btrfs_transaction *trans,
 					  struct extent_buffer *eb) { }
 static inline void btrfs_free_redirty_list(struct btrfs_transaction *trans) { }
 
-static inline bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start)
+static inline bool btrfs_use_zone_append(struct btrfs_bio *bbio)
 {
 	return false;
 }
 
-static inline void btrfs_record_physical_zoned(struct inode *inode,
-					       u64 file_offset, struct bio *bio)
+static inline void btrfs_record_physical_zoned(struct btrfs_bio *bbio)
 {
 }
 
@@ -224,13 +219,6 @@ static inline int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev,
 	return -EOPNOTSUPP;
 }
 
-static inline struct btrfs_device *btrfs_zoned_get_device(
-						  struct btrfs_fs_info *fs_info,
-						  u64 logical, u64 length)
-{
-	return ERR_PTR(-EOPNOTSUPP);
-}
-
 static inline bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 {
 	return true;
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 9804714b1751..f771001574d0 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -217,16 +217,10 @@ static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio,
 {
 	blk_opf_t opflags = REQ_SYNC | REQ_IDLE;
 
-	if (!(dio->flags & IOMAP_DIO_WRITE)) {
-		WARN_ON_ONCE(iomap->flags & IOMAP_F_ZONE_APPEND);
+	if (!(dio->flags & IOMAP_DIO_WRITE))
 		return REQ_OP_READ;
-	}
-
-	if (iomap->flags & IOMAP_F_ZONE_APPEND)
-		opflags |= REQ_OP_ZONE_APPEND;
-	else
-		opflags |= REQ_OP_WRITE;
 
+	opflags |= REQ_OP_WRITE;
 	if (use_fua)
 		opflags |= REQ_FUA;
 	else