Merge tag 'for-6.5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Mainly core changes, refactoring and optimizations.

  Performance is improved in some areas, overall there may be a
  cumulative improvement due to refactoring that removed lookups in the
  IO path or simplified IO submission tracking.

  Core:

   - submit IO synchronously for fast checksums (crc32c and xxhash),
     remove high priority worker kthread

   - read extent buffer in one go, simplify IO tracking, bio submission
     and locking

   - remove additional tracking of redirtied extent buffers, originally
     added for zoned mode but actually not needed

   - track ordered extent pointer in bio to avoid rbtree lookups during
     IO

   - scrub, use recovered data stripes as cache to avoid unnecessary
     read

   - in zoned mode, optimize logical to physical mappings of extents

   - remove PageError handling, not set by VFS nor writeback

   - cleanups, refactoring, better structure packing

   - lots of error handling improvements

   - more assertions, lockdep annotations

   - print assertion failure with the exact line where it happens

   - tracepoint updates

   - more debugging prints

  Performance:

   - speedup in fsync(), better tracking of inode logged status can
     avoid transaction commit

   - IO path structures track logical offsets in data structures and
     does not need to look it up

  User visible changes:

   - don't commit transaction for every created subvolume, this can
     reduce time when many subvolumes are created in a batch

   - print affected files when relocation fails

   - trigger orphan file cleanup during START_SYNC ioctl

  Notable fixes:

   - fix crash when disabling quota and relocation

   - fix crashes when removing roots from drity list

   - fix transacion abort during relocation when converting from newer
     profiles not covered by fallback

   - in zoned mode, stop reclaiming block groups if filesystem becomes
     read-only

   - fix rare race condition in tree mod log rewind that can miss some
     btree node slots

   - with enabled fsverity, drop up-to-date page bit in case the
     verification fails"

* tag 'for-6.5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (194 commits)
  btrfs: fix race between quota disable and relocation
  btrfs: add comment to struct btrfs_fs_info::dirty_cowonly_roots
  btrfs: fix race when deleting free space root from the dirty cow roots list
  btrfs: fix race when deleting quota root from the dirty cow roots list
  btrfs: tracepoints: also show actual number of the outstanding extents
  btrfs: update i_version in update_dev_time
  btrfs: make btrfs_compressed_bioset static
  btrfs: add handling for RAID1C23/DUP to btrfs_reduce_alloc_profile
  btrfs: scrub: remove btrfs_fs_info::scrub_wr_completion_workers
  btrfs: scrub: remove scrub_ctx::csum_list member
  btrfs: do not BUG_ON after failure to migrate space during truncation
  btrfs: do not BUG_ON on failure to get dir index for new snapshot
  btrfs: send: do not BUG_ON() on unexpected symlink data extent
  btrfs: do not BUG_ON() when dropping inode items from log root
  btrfs: replace BUG_ON() at split_item() with proper error handling
  btrfs: do not BUG_ON() on tree mod log failures at btrfs_del_ptr()
  btrfs: do not BUG_ON() on tree mod log failures at insert_ptr()
  btrfs: do not BUG_ON() on tree mod log failure at insert_new_root()
  btrfs: do not BUG_ON() on tree mod log failures at push_nodes_for_insert()
  btrfs: abort transaction at update_ref_for_cow() when ref count is zero
  ...

fs/btrfs/async-thread.c

@@ -71,6 +71,16 @@ bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq)
 	return atomic_read(&wq->pending) > wq->thresh * 2;
 }
 
+static void btrfs_init_workqueue(struct btrfs_workqueue *wq,
+				 struct btrfs_fs_info *fs_info)
+{
+	wq->fs_info = fs_info;
+	atomic_set(&wq->pending, 0);
+	INIT_LIST_HEAD(&wq->ordered_list);
+	spin_lock_init(&wq->list_lock);
+	spin_lock_init(&wq->thres_lock);
+}
+
 struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
 					      const char *name, unsigned int flags,
 					      int limit_active, int thresh)
@@ -80,9 +90,9 @@ struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
 	if (!ret)
 		return NULL;
 
-	ret->fs_info = fs_info;
+	btrfs_init_workqueue(ret, fs_info);
+
 	ret->limit_active = limit_active;
-	atomic_set(&ret->pending, 0);
 	if (thresh == 0)
 		thresh = DFT_THRESHOLD;
 	/* For low threshold, disabling threshold is a better choice */
@@ -106,9 +116,33 @@ struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
 		return NULL;
 	}
 
-	INIT_LIST_HEAD(&ret->ordered_list);
-	spin_lock_init(&ret->list_lock);
-	spin_lock_init(&ret->thres_lock);
+	trace_btrfs_workqueue_alloc(ret, name);
+	return ret;
+}
+
+struct btrfs_workqueue *btrfs_alloc_ordered_workqueue(
+				struct btrfs_fs_info *fs_info, const char *name,
+				unsigned int flags)
+{
+	struct btrfs_workqueue *ret;
+
+	ret = kzalloc(sizeof(*ret), GFP_KERNEL);
+	if (!ret)
+		return NULL;
+
+	btrfs_init_workqueue(ret, fs_info);
+
+	/* Ordered workqueues don't allow @max_active adjustments. */
+	ret->limit_active = 1;
+	ret->current_active = 1;
+	ret->thresh = NO_THRESHOLD;
+
+	ret->normal_wq = alloc_ordered_workqueue("btrfs-%s", flags, name);
+	if (!ret->normal_wq) {
+		kfree(ret);
+		return NULL;
+	}
+
 	trace_btrfs_workqueue_alloc(ret, name);
 	return ret;
 }

fs/btrfs/async-thread.h

@@ -31,6 +31,9 @@ struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
 					      unsigned int flags,
 					      int limit_active,
 					      int thresh);
+struct btrfs_workqueue *btrfs_alloc_ordered_workqueue(
+				struct btrfs_fs_info *fs_info, const char *name,
+				unsigned int flags);
 void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
 		     btrfs_func_t ordered_func, btrfs_func_t ordered_free);
 void btrfs_queue_work(struct btrfs_workqueue *wq,

fs/btrfs/bio.c

@@ -27,6 +27,17 @@ struct btrfs_failed_bio {
 	atomic_t repair_count;
 };
 
+/* Is this a data path I/O that needs storage layer checksum and repair? */
+static inline bool is_data_bbio(struct btrfs_bio *bbio)
+{
+	return bbio->inode && is_data_inode(&bbio->inode->vfs_inode);
+}
+
+static bool bbio_has_ordered_extent(struct btrfs_bio *bbio)
+{
+	return is_data_bbio(bbio) && btrfs_op(&bbio->bio) == BTRFS_MAP_WRITE;
+}
+
 /*
  * Initialize a btrfs_bio structure.  This skips the embedded bio itself as it
  * is already initialized by the block layer.
@@ -61,20 +72,6 @@ struct btrfs_bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
 	return bbio;
 }
 
-static blk_status_t btrfs_bio_extract_ordered_extent(struct btrfs_bio *bbio)
-{
-	struct btrfs_ordered_extent *ordered;
-	int ret;
-
-	ordered = btrfs_lookup_ordered_extent(bbio->inode, bbio->file_offset);
-	if (WARN_ON_ONCE(!ordered))
-		return BLK_STS_IOERR;
-	ret = btrfs_extract_ordered_extent(bbio, ordered);
-	btrfs_put_ordered_extent(ordered);
-
-	return errno_to_blk_status(ret);
-}
-
 static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info,
 					 struct btrfs_bio *orig_bbio,
 					 u64 map_length, bool use_append)
@@ -95,13 +92,41 @@ static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info,
 	btrfs_bio_init(bbio, fs_info, NULL, orig_bbio);
 	bbio->inode = orig_bbio->inode;
 	bbio->file_offset = orig_bbio->file_offset;
-	if (!(orig_bbio->bio.bi_opf & REQ_BTRFS_ONE_ORDERED))
-		orig_bbio->file_offset += map_length;
-
+	orig_bbio->file_offset += map_length;
+	if (bbio_has_ordered_extent(bbio)) {
+		refcount_inc(&orig_bbio->ordered->refs);
+		bbio->ordered = orig_bbio->ordered;
+	}
 	atomic_inc(&orig_bbio->pending_ios);
 	return bbio;
 }
 
+/* Free a bio that was never submitted to the underlying device. */
+static void btrfs_cleanup_bio(struct btrfs_bio *bbio)
+{
+	if (bbio_has_ordered_extent(bbio))
+		btrfs_put_ordered_extent(bbio->ordered);
+	bio_put(&bbio->bio);
+}
+
+static void __btrfs_bio_end_io(struct btrfs_bio *bbio)
+{
+	if (bbio_has_ordered_extent(bbio)) {
+		struct btrfs_ordered_extent *ordered = bbio->ordered;
+
+		bbio->end_io(bbio);
+		btrfs_put_ordered_extent(ordered);
+	} else {
+		bbio->end_io(bbio);
+	}
+}
+
+void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
+{
+	bbio->bio.bi_status = status;
+	__btrfs_bio_end_io(bbio);
+}
+
 static void btrfs_orig_write_end_io(struct bio *bio);
 
 static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio,
@@ -130,12 +155,12 @@ static void btrfs_orig_bbio_end_io(struct btrfs_bio *bbio)
 
 		if (bbio->bio.bi_status)
 			btrfs_bbio_propagate_error(bbio, orig_bbio);
-		bio_put(&bbio->bio);
+		btrfs_cleanup_bio(bbio);
 		bbio = orig_bbio;
 	}
 
 	if (atomic_dec_and_test(&bbio->pending_ios))
-		bbio->end_io(bbio);
+		__btrfs_bio_end_io(bbio);
 }
 
 static int next_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror)
@@ -327,7 +352,7 @@ static void btrfs_end_bio_work(struct work_struct *work)
 	struct btrfs_bio *bbio = container_of(work, struct btrfs_bio, end_io_work);
 
 	/* Metadata reads are checked and repaired by the submitter. */
-	if (bbio->inode && !(bbio->bio.bi_opf & REQ_META))
+	if (is_data_bbio(bbio))
 		btrfs_check_read_bio(bbio, bbio->bio.bi_private);
 	else
 		btrfs_orig_bbio_end_io(bbio);
@@ -348,7 +373,7 @@ static void btrfs_simple_end_io(struct bio *bio)
 		INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work);
 		queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work);
 	} else {
-		if (bio_op(bio) == REQ_OP_ZONE_APPEND)
+		if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status)
 			btrfs_record_physical_zoned(bbio);
 		btrfs_orig_bbio_end_io(bbio);
 	}
@@ -361,8 +386,7 @@ static void btrfs_raid56_end_io(struct bio *bio)
 
 	btrfs_bio_counter_dec(bioc->fs_info);
 	bbio->mirror_num = bioc->mirror_num;
-	if (bio_op(bio) == REQ_OP_READ && bbio->inode &&
-	    !(bbio->bio.bi_opf & REQ_META))
+	if (bio_op(bio) == REQ_OP_READ && is_data_bbio(bbio))
 		btrfs_check_read_bio(bbio, NULL);
 	else
 		btrfs_orig_bbio_end_io(bbio);
@@ -472,13 +496,12 @@ static void btrfs_submit_mirrored_bio(struct btrfs_io_context *bioc, int dev_nr)
 static void __btrfs_submit_bio(struct bio *bio, struct btrfs_io_context *bioc,
 			       struct btrfs_io_stripe *smap, int mirror_num)
 {
-	/* 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. */
 		btrfs_bio(bio)->mirror_num = mirror_num;
 		bio->bi_iter.bi_sector = smap->physical >> SECTOR_SHIFT;
+		if (bio_op(bio) != REQ_OP_READ)
+			btrfs_bio(bio)->orig_physical = smap->physical;
 		bio->bi_private = smap->dev;
 		bio->bi_end_io = btrfs_simple_end_io;
 		btrfs_submit_dev_bio(smap->dev, bio);
@@ -574,27 +597,20 @@ static void run_one_async_free(struct btrfs_work *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))
+	/* Submit synchronously if the checksum implementation is fast. */
+	if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &bbio->fs_info->flags))
 		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.
+	 * Try to defer the submission to a workqueue to parallelize the
+	 * checksum calculation unless the I/O is issued synchronously.
 	 */
-	if (bbio->bio.bi_opf & REQ_META) {
-		struct btrfs_fs_info *fs_info = bbio->fs_info;
+	if (op_is_sync(bbio->bio.bi_opf))
+		return false;
 
-		if (btrfs_is_zoned(fs_info))
-			return false;
-		if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags))
-			return false;
-	}
+	/* Zoned devices require I/O to be submitted in order. */
+	if ((bbio->bio.bi_opf & REQ_META) && btrfs_is_zoned(bbio->fs_info))
+		return false;
 
 	return true;
 }
@@ -622,10 +638,7 @@ static bool btrfs_wq_submit_bio(struct btrfs_bio *bbio,
 
 	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);
+	btrfs_queue_work(fs_info->workers, &async->work);
 	return true;
 }
 
@@ -635,7 +648,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 	struct btrfs_fs_info *fs_info = bbio->fs_info;
 	struct btrfs_bio *orig_bbio = bbio;
 	struct bio *bio = &bbio->bio;
-	u64 logical = bio->bi_iter.bi_sector << 9;
+	u64 logical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
 	u64 length = bio->bi_iter.bi_size;
 	u64 map_length = length;
 	bool use_append = btrfs_use_zone_append(bbio);
@@ -645,8 +658,8 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 	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);
+	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;
@@ -665,7 +678,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 	 * Save the iter for the end_io handler and preload the checksums for
 	 * data reads.
 	 */
-	if (bio_op(bio) == REQ_OP_READ && inode && !(bio->bi_opf & REQ_META)) {
+	if (bio_op(bio) == REQ_OP_READ && is_data_bbio(bbio)) {
 		bbio->saved_iter = bio->bi_iter;
 		ret = btrfs_lookup_bio_sums(bbio);
 		if (ret)
@@ -676,9 +689,6 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 		if (use_append) {
 			bio->bi_opf &= ~REQ_OP_WRITE;
 			bio->bi_opf |= REQ_OP_ZONE_APPEND;
-			ret = btrfs_bio_extract_ordered_extent(bbio);
-			if (ret)
-				goto fail_put_bio;
 		}
 
 		/*
@@ -695,6 +705,10 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 			ret = btrfs_bio_csum(bbio);
 			if (ret)
 				goto fail_put_bio;
+		} else if (use_append) {
+			ret = btrfs_alloc_dummy_sum(bbio);
+			if (ret)
+				goto fail_put_bio;
 		}
 	}
 
@@ -704,7 +718,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 
 fail_put_bio:
 	if (map_length < length)
-		bio_put(bio);
+		btrfs_cleanup_bio(bbio);
 fail:
 	btrfs_bio_counter_dec(fs_info);
 	btrfs_bio_end_io(orig_bbio, ret);

fs/btrfs/bio.h

@@ -39,8 +39,8 @@ struct btrfs_bio {
 
 	union {
 		/*
-		 * Data checksumming and original I/O information for internal
-		 * use in the btrfs_submit_bio machinery.
+		 * For data reads: checksumming and original I/O information.
+		 * (for internal use in the btrfs_submit_bio machinery only)
 		 */
 		struct {
 			u8 *csum;
@@ -48,7 +48,20 @@ struct btrfs_bio {
 			struct bvec_iter saved_iter;
 		};
 
-		/* For metadata parentness verification. */
+		/*
+		 * For data writes:
+		 * - ordered extent covering the bio
+		 * - pointer to the checksums for this bio
+		 * - original physical address from the allocator
+		 *   (for zone append only)
+		 */
+		struct {
+			struct btrfs_ordered_extent *ordered;
+			struct btrfs_ordered_sum *sums;
+			u64 orig_physical;
+		};
+
+		/* For metadata reads: parentness verification. */
 		struct btrfs_tree_parent_check parent_check;
 	};
 
@@ -84,15 +97,7 @@ void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_fs_info *fs_info,
 struct btrfs_bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
 				  struct btrfs_fs_info *fs_info,
 				  btrfs_bio_end_io_t end_io, void *private);
-
-static inline void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
-{
-	bbio->bio.bi_status = status;
-	bbio->end_io(bbio);
-}
-
-/* Bio only refers to one ordered extent. */
-#define REQ_BTRFS_ONE_ORDERED			REQ_DRV
+void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status);
 
 /* Submit using blkcg_punt_bio_submit. */
 #define REQ_BTRFS_CGROUP_PUNT			REQ_FS_PRIVATE

fs/btrfs/block-group.c

@@ -95,14 +95,21 @@ static u64 btrfs_reduce_alloc_profile(struct btrfs_fs_info *fs_info, u64 flags)
 	}
 	allowed &= flags;
 
-	if (allowed & BTRFS_BLOCK_GROUP_RAID6)
+	/* Select the highest-redundancy RAID level. */
+	if (allowed & BTRFS_BLOCK_GROUP_RAID1C4)
+		allowed = BTRFS_BLOCK_GROUP_RAID1C4;
+	else if (allowed & BTRFS_BLOCK_GROUP_RAID6)
 		allowed = BTRFS_BLOCK_GROUP_RAID6;
+	else if (allowed & BTRFS_BLOCK_GROUP_RAID1C3)
+		allowed = BTRFS_BLOCK_GROUP_RAID1C3;
 	else if (allowed & BTRFS_BLOCK_GROUP_RAID5)
 		allowed = BTRFS_BLOCK_GROUP_RAID5;
 	else if (allowed & BTRFS_BLOCK_GROUP_RAID10)
 		allowed = BTRFS_BLOCK_GROUP_RAID10;
 	else if (allowed & BTRFS_BLOCK_GROUP_RAID1)
 		allowed = BTRFS_BLOCK_GROUP_RAID1;
+	else if (allowed & BTRFS_BLOCK_GROUP_DUP)
+		allowed = BTRFS_BLOCK_GROUP_DUP;
 	else if (allowed & BTRFS_BLOCK_GROUP_RAID0)
 		allowed = BTRFS_BLOCK_GROUP_RAID0;
 
@@ -1633,11 +1640,14 @@ void btrfs_mark_bg_unused(struct btrfs_block_group *bg)
 {
 	struct btrfs_fs_info *fs_info = bg->fs_info;
 
+	trace_btrfs_add_unused_block_group(bg);
 	spin_lock(&fs_info->unused_bgs_lock);
 	if (list_empty(&bg->bg_list)) {
 		btrfs_get_block_group(bg);
-		trace_btrfs_add_unused_block_group(bg);
 		list_add_tail(&bg->bg_list, &fs_info->unused_bgs);
+	} else {
+		/* Pull out the block group from the reclaim_bgs list. */
+		list_move_tail(&bg->bg_list, &fs_info->unused_bgs);
 	}
 	spin_unlock(&fs_info->unused_bgs_lock);
 }
@@ -1791,8 +1801,15 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 		}
 		spin_unlock(&bg->lock);
 
-		/* Get out fast, in case we're unmounting the filesystem */
-		if (btrfs_fs_closing(fs_info)) {
+		/*
+		 * Get out fast, in case we're read-only or unmounting the
+		 * filesystem. It is OK to drop block groups from the list even
+		 * for the read-only case. As we did sb_start_write(),
+		 * "mount -o remount,ro" won't happen and read-only filesystem
+		 * means it is forced read-only due to a fatal error. So, it
+		 * never gets back to read-write to let us reclaim again.
+		 */
+		if (btrfs_need_cleaner_sleep(fs_info)) {
 			up_write(&space_info->groups_sem);
 			goto next;
 		}
@@ -1823,11 +1840,27 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 		}
 
 next:
+		if (ret)
+			btrfs_mark_bg_to_reclaim(bg);
 		btrfs_put_block_group(bg);
+
+		mutex_unlock(&fs_info->reclaim_bgs_lock);
+		/*
+		 * Reclaiming all the block groups in the list can take really
+		 * long.  Prioritize cleaning up unused block groups.
+		 */
+		btrfs_delete_unused_bgs(fs_info);
+		/*
+		 * If we are interrupted by a balance, we can just bail out. The
+		 * cleaner thread restart again if necessary.
+		 */
+		if (!mutex_trylock(&fs_info->reclaim_bgs_lock))
+			goto end;
 		spin_lock(&fs_info->unused_bgs_lock);
 	}
 	spin_unlock(&fs_info->unused_bgs_lock);
 	mutex_unlock(&fs_info->reclaim_bgs_lock);
+end:
 	btrfs_exclop_finish(fs_info);
 	sb_end_write(fs_info->sb);
 }
@@ -3521,9 +3554,9 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 			spin_unlock(&cache->lock);
 			spin_unlock(&space_info->lock);
 
-			set_extent_dirty(&trans->transaction->pinned_extents,
-					 bytenr, bytenr + num_bytes - 1,
-					 GFP_NOFS | __GFP_NOFAIL);
+			set_extent_bit(&trans->transaction->pinned_extents,
+				       bytenr, bytenr + num_bytes - 1,
+				       EXTENT_DIRTY, NULL);
 		}
 
 		spin_lock(&trans->transaction->dirty_bgs_lock);

fs/btrfs/block-group.h

@@ -162,7 +162,14 @@ struct btrfs_block_group {
 	 */
 	struct list_head cluster_list;
 
-	/* For delayed block group creation or deletion of empty block groups */
+	/*
+	 * Used for several lists:
+	 *
+	 * 1) struct btrfs_fs_info::unused_bgs
+	 * 2) struct btrfs_fs_info::reclaim_bgs
+	 * 3) struct btrfs_transaction::deleted_bgs
+	 * 4) struct btrfs_trans_handle::new_bgs
+	 */
 	struct list_head bg_list;
 
 	/* For read-only block groups */

fs/btrfs/block-rsv.c

@@ -541,3 +541,22 @@ struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans,
 
 	return ERR_PTR(ret);
 }
+
+int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
+				       struct btrfs_block_rsv *rsv)
+{
+	u64 needed_bytes;
+	int ret;
+
+	/* 1 for slack space, 1 for updating the inode */
+	needed_bytes = btrfs_calc_insert_metadata_size(fs_info, 1) +
+		btrfs_calc_metadata_size(fs_info, 1);
+
+	spin_lock(&rsv->lock);
+	if (rsv->reserved < needed_bytes)
+		ret = -ENOSPC;
+	else
+		ret = 0;
+	spin_unlock(&rsv->lock);
+	return ret;
+}

fs/btrfs/block-rsv.h

@@ -82,6 +82,8 @@ void btrfs_release_global_block_rsv(struct btrfs_fs_info *fs_info);
 struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans,
 					    struct btrfs_root *root,
 					    u32 blocksize);
+int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
+				       struct btrfs_block_rsv *rsv);
 static inline void btrfs_unuse_block_rsv(struct btrfs_fs_info *fs_info,
 					 struct btrfs_block_rsv *block_rsv,
 					 u32 blocksize)

fs/btrfs/btrfs_inode.h

@@ -116,9 +116,6 @@ struct btrfs_inode {
 
 	unsigned long runtime_flags;
 
-	/* Keep track of who's O_SYNC/fsyncing currently */
-	atomic_t sync_writers;
-
 	/* full 64 bit generation number, struct vfs_inode doesn't have a big
 	 * enough field for this.
 	 */
@@ -335,7 +332,7 @@ static inline void btrfs_mod_outstanding_extents(struct btrfs_inode *inode,
 	if (btrfs_is_free_space_inode(inode))
 		return;
 	trace_btrfs_inode_mod_outstanding_extents(inode->root, btrfs_ino(inode),
-						  mod);
+						  mod, inode->outstanding_extents);
 }
 
 /*
@@ -407,30 +404,12 @@ static inline bool btrfs_inode_can_compress(const struct btrfs_inode *inode)
 	return true;
 }
 
-/*
- * btrfs_inode_item stores flags in a u64, btrfs_inode stores them in two
- * separate u32s. These two functions convert between the two representations.
- */
-static inline u64 btrfs_inode_combine_flags(u32 flags, u32 ro_flags)
-{
-	return (flags | ((u64)ro_flags << 32));
-}
-
-static inline void btrfs_inode_split_flags(u64 inode_item_flags,
-					   u32 *flags, u32 *ro_flags)
-{
-	*flags = (u32)inode_item_flags;
-	*ro_flags = (u32)(inode_item_flags >> 32);
-}
-
 /* Array of bytes with variable length, hexadecimal format 0x1234 */
 #define CSUM_FMT				"0x%*phN"
 #define CSUM_FMT_VALUE(size, bytes)		size, bytes
 
 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_extract_ordered_extent(struct btrfs_bio *bbio,
-				 struct btrfs_ordered_extent *ordered);
 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,

fs/btrfs/check-integrity.c

@@ -1459,13 +1459,13 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len,
 	struct btrfs_fs_info *fs_info = state->fs_info;
 	int ret;
 	u64 length;
-	struct btrfs_io_context *multi = NULL;
+	struct btrfs_io_context *bioc = NULL;
+	struct btrfs_io_stripe smap, *map;
 	struct btrfs_device *device;
 
 	length = len;
-	ret = btrfs_map_block(fs_info, BTRFS_MAP_READ,
-			      bytenr, &length, &multi, mirror_num);
-
+	ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, bytenr, &length, &bioc,
+			      NULL, &mirror_num, 0);
 	if (ret) {
 		block_ctx_out->start = 0;
 		block_ctx_out->dev_bytenr = 0;
@@ -1478,21 +1478,26 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len,
 		return ret;
 	}
 
-	device = multi->stripes[0].dev;
+	if (bioc)
+		map = &bioc->stripes[0];
+	else
+		map = &smap;
+
+	device = map->dev;
 	if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state) ||
 	    !device->bdev || !device->name)
 		block_ctx_out->dev = NULL;
 	else
 		block_ctx_out->dev = btrfsic_dev_state_lookup(
 							device->bdev->bd_dev);
-	block_ctx_out->dev_bytenr = multi->stripes[0].physical;
+	block_ctx_out->dev_bytenr = map->physical;
 	block_ctx_out->start = bytenr;
 	block_ctx_out->len = len;
 	block_ctx_out->datav = NULL;
 	block_ctx_out->pagev = NULL;
 	block_ctx_out->mem_to_free = NULL;
 
-	kfree(multi);
+	kfree(bioc);
 	if (NULL == block_ctx_out->dev) {
 		ret = -ENXIO;
 		pr_info("btrfsic: error, cannot lookup dev (#1)!\n");
@@ -1565,7 +1570,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 
 		bio = bio_alloc(block_ctx->dev->bdev, num_pages - i,
 				REQ_OP_READ, GFP_NOFS);
-		bio->bi_iter.bi_sector = dev_bytenr >> 9;
+		bio->bi_iter.bi_sector = dev_bytenr >> SECTOR_SHIFT;
 
 		for (j = i; j < num_pages; j++) {
 			ret = bio_add_page(bio, block_ctx->pagev[j],

fs/btrfs/compression.c

@@ -37,7 +37,7 @@
 #include "file-item.h"
 #include "super.h"
 
-struct bio_set btrfs_compressed_bioset;
+static struct bio_set btrfs_compressed_bioset;
 
 static const char* const btrfs_compress_types[] = { "", "zlib", "lzo", "zstd" };
 
@@ -211,8 +211,6 @@ static noinline void end_compressed_writeback(const struct compressed_bio *cb)
 		for (i = 0; i < ret; i++) {
 			struct folio *folio = fbatch.folios[i];
 
-			if (errno)
-				folio_set_error(folio);
 			btrfs_page_clamp_clear_writeback(fs_info, &folio->page,
 							 cb->start, cb->len);
 		}
@@ -226,13 +224,8 @@ static void btrfs_finish_compressed_write_work(struct work_struct *work)
 	struct compressed_bio *cb =
 		container_of(work, struct compressed_bio, write_end_work);
 
-	/*
-	 * Ok, we're the last bio for this extent, step one is to call back
-	 * into the FS and do all the end_io operations.
-	 */
-	btrfs_writepage_endio_finish_ordered(cb->bbio.inode, NULL,
-			cb->start, cb->start + cb->len - 1,
-			cb->bbio.bio.bi_status == BLK_STS_OK);
+	btrfs_finish_ordered_extent(cb->bbio.ordered, NULL, cb->start, cb->len,
+				    cb->bbio.bio.bi_status == BLK_STS_OK);
 
 	if (cb->writeback)
 		end_compressed_writeback(cb);
@@ -281,32 +274,31 @@ static void btrfs_add_compressed_bio_pages(struct compressed_bio *cb)
  * This also checksums the file bytes and gets things ready for
  * the end io hooks.
  */
-void btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
-				 unsigned int len, u64 disk_start,
-				 unsigned int compressed_len,
-				 struct page **compressed_pages,
-				 unsigned int nr_pages,
-				 blk_opf_t write_flags,
-				 bool writeback)
+void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered,
+				   struct page **compressed_pages,
+				   unsigned int nr_pages,
+				   blk_opf_t write_flags,
+				   bool writeback)
 {
+	struct btrfs_inode *inode = BTRFS_I(ordered->inode);
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct compressed_bio *cb;
 
-	ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
-	       IS_ALIGNED(len, fs_info->sectorsize));
-
-	write_flags |= REQ_BTRFS_ONE_ORDERED;
+	ASSERT(IS_ALIGNED(ordered->file_offset, fs_info->sectorsize));
+	ASSERT(IS_ALIGNED(ordered->num_bytes, fs_info->sectorsize));
 
-	cb = alloc_compressed_bio(inode, start, REQ_OP_WRITE | write_flags,
+	cb = alloc_compressed_bio(inode, ordered->file_offset,
+				  REQ_OP_WRITE | write_flags,
 				  end_compressed_bio_write);
-	cb->start = start;
-	cb->len = len;
+	cb->start = ordered->file_offset;
+	cb->len = ordered->num_bytes;
 	cb->compressed_pages = compressed_pages;
-	cb->compressed_len = compressed_len;
+	cb->compressed_len = ordered->disk_num_bytes;
 	cb->writeback = writeback;
 	INIT_WORK(&cb->write_end_work, btrfs_finish_compressed_write_work);
 	cb->nr_pages = nr_pages;
-	cb->bbio.bio.bi_iter.bi_sector = disk_start >> SECTOR_SHIFT;
+	cb->bbio.bio.bi_iter.bi_sector = ordered->disk_bytenr >> SECTOR_SHIFT;
+	cb->bbio.ordered = ordered;
 	btrfs_add_compressed_bio_pages(cb);
 
 	btrfs_submit_bio(&cb->bbio, 0);
@@ -421,7 +413,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		 */
 		if (!em || cur < em->start ||
 		    (cur + fs_info->sectorsize > extent_map_end(em)) ||
-		    (em->block_start >> 9) != orig_bio->bi_iter.bi_sector) {
+		    (em->block_start >> SECTOR_SHIFT) != orig_bio->bi_iter.bi_sector) {
 			free_extent_map(em);
 			unlock_extent(tree, cur, page_end, NULL);
 			unlock_page(page);
@@ -472,7 +464,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
  * After the compressed pages are read, we copy the bytes into the
  * bio we were passed and then call the bio end_io calls
  */
-void btrfs_submit_compressed_read(struct btrfs_bio *bbio, int mirror_num)
+void btrfs_submit_compressed_read(struct btrfs_bio *bbio)
 {
 	struct btrfs_inode *inode = bbio->inode;
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
@@ -538,7 +530,7 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio, int mirror_num)
 	if (memstall)
 		psi_memstall_leave(&pflags);
 
-	btrfs_submit_bio(&cb->bbio, mirror_num);
+	btrfs_submit_bio(&cb->bbio, 0);
 	return;
 
 out_free_compressed_pages:

fs/btrfs/compression.h

@@ -10,6 +10,7 @@
 #include "bio.h"
 
 struct btrfs_inode;
+struct btrfs_ordered_extent;
 
 /*
  * We want to make sure that amount of RAM required to uncompress an extent is
@@ -86,14 +87,12 @@ int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page,
 int btrfs_decompress_buf2page(const char *buf, u32 buf_len,
 			      struct compressed_bio *cb, u32 decompressed);
 
-void btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
-				  unsigned int len, u64 disk_start,
-				  unsigned int compressed_len,
+void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered,
 				  struct page **compressed_pages,
 				  unsigned int nr_pages,
 				  blk_opf_t write_flags,
 				  bool writeback);
-void btrfs_submit_compressed_read(struct btrfs_bio *bbio, int mirror_num);
+void btrfs_submit_compressed_read(struct btrfs_bio *bbio);
 
 unsigned int btrfs_compress_str2level(unsigned int type, const char *str);
 

fs/btrfs/ctree.h

@@ -541,6 +541,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 		      struct extent_buffer **cow_ret, u64 new_root_objectid);
 int btrfs_block_can_be_shared(struct btrfs_root *root,
 			      struct extent_buffer *buf);
+int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		  struct btrfs_path *path, int level, int slot);
 void btrfs_extend_item(struct btrfs_path *path, u32 data_size);
 void btrfs_truncate_item(struct btrfs_path *path, u32 new_size, int from_end);
 int btrfs_split_item(struct btrfs_trans_handle *trans,
@@ -633,7 +635,6 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans,
 	return btrfs_insert_empty_items(trans, root, path, &batch);
 }
 
-int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path);
 int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path,
 			u64 time_seq);
 
@@ -686,7 +687,7 @@ static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p)
 {
 	return btrfs_next_old_item(root, p, 0);
 }
-int btrfs_leaf_free_space(struct extent_buffer *leaf);
+int btrfs_leaf_free_space(const struct extent_buffer *leaf);
 
 static inline int is_fstree(u64 rootid)
 {
@@ -702,6 +703,7 @@ static inline bool btrfs_is_data_reloc_root(const struct btrfs_root *root)
 	return root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID;
 }
 
+u16 btrfs_csum_type_size(u16 type);
 int btrfs_super_csum_size(const struct btrfs_super_block *s);
 const char *btrfs_super_csum_name(u16 csum_type);
 const char *btrfs_super_csum_driver(u16 csum_type);

fs/btrfs/defrag.c

@@ -1040,7 +1040,8 @@ static int defrag_one_locked_target(struct btrfs_inode *inode,
 	clear_extent_bit(&inode->io_tree, start, start + len - 1,
 			 EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
 			 EXTENT_DEFRAG, cached_state);
-	set_extent_defrag(&inode->io_tree, start, start + len - 1, cached_state);
+	set_extent_bit(&inode->io_tree, start, start + len - 1,
+		       EXTENT_DELALLOC | EXTENT_DEFRAG, cached_state);
 
 	/* Update the page status */
 	for (i = start_index - first_index; i <= last_index - first_index; i++) {

fs/btrfs/delayed-ref.c

@@ -407,7 +407,6 @@ static inline void drop_delayed_ref(struct btrfs_delayed_ref_root *delayed_refs,
 	RB_CLEAR_NODE(&ref->ref_node);
 	if (!list_empty(&ref->add_list))
 		list_del(&ref->add_list);
-	ref->in_tree = 0;
 	btrfs_put_delayed_ref(ref);
 	atomic_dec(&delayed_refs->num_entries);
 }
@@ -507,6 +506,7 @@ struct btrfs_delayed_ref_head *btrfs_select_ref_head(
 {
 	struct btrfs_delayed_ref_head *head;
 
+	lockdep_assert_held(&delayed_refs->lock);
 again:
 	head = find_ref_head(delayed_refs, delayed_refs->run_delayed_start,
 			     true);
@@ -531,7 +531,7 @@ struct btrfs_delayed_ref_head *btrfs_select_ref_head(
 				href_node);
 	}
 
-	head->processing = 1;
+	head->processing = true;
 	WARN_ON(delayed_refs->num_heads_ready == 0);
 	delayed_refs->num_heads_ready--;
 	delayed_refs->run_delayed_start = head->bytenr +
@@ -549,31 +549,35 @@ void btrfs_delete_ref_head(struct btrfs_delayed_ref_root *delayed_refs,
 	RB_CLEAR_NODE(&head->href_node);
 	atomic_dec(&delayed_refs->num_entries);
 	delayed_refs->num_heads--;
-	if (head->processing == 0)
+	if (!head->processing)
 		delayed_refs->num_heads_ready--;
 }
 
 /*
  * Helper to insert the ref_node to the tail or merge with tail.
  *
- * Return 0 for insert.
- * Return >0 for merge.
+ * Return false if the ref was inserted.
+ * Return true if the ref was merged into an existing one (and therefore can be
+ * freed by the caller).
  */
-static int insert_delayed_ref(struct btrfs_delayed_ref_root *root,
-			      struct btrfs_delayed_ref_head *href,
-			      struct btrfs_delayed_ref_node *ref)
+static bool insert_delayed_ref(struct btrfs_delayed_ref_root *root,
+			       struct btrfs_delayed_ref_head *href,
+			       struct btrfs_delayed_ref_node *ref)
 {
 	struct btrfs_delayed_ref_node *exist;
 	int mod;
-	int ret = 0;
 
 	spin_lock(&href->lock);
 	exist = tree_insert(&href->ref_tree, ref);
-	if (!exist)
-		goto inserted;
+	if (!exist) {
+		if (ref->action == BTRFS_ADD_DELAYED_REF)
+			list_add_tail(&ref->add_list, &href->ref_add_list);
+		atomic_inc(&root->num_entries);
+		spin_unlock(&href->lock);
+		return false;
+	}
 
 	/* Now we are sure we can merge */
-	ret = 1;
 	if (exist->action == ref->action) {
 		mod = ref->ref_mod;
 	} else {
@@ -600,13 +604,7 @@ static int insert_delayed_ref(struct btrfs_delayed_ref_root *root,
 	if (exist->ref_mod == 0)
 		drop_delayed_ref(root, href, exist);
 	spin_unlock(&href->lock);
-	return ret;
-inserted:
-	if (ref->action == BTRFS_ADD_DELAYED_REF)
-		list_add_tail(&ref->add_list, &href->ref_add_list);
-	atomic_inc(&root->num_entries);
-	spin_unlock(&href->lock);
-	return ret;
+	return true;
 }
 
 /*
@@ -699,34 +697,38 @@ static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
 				  bool is_system)
 {
 	int count_mod = 1;
-	int must_insert_reserved = 0;
+	bool must_insert_reserved = false;
 
 	/* If reserved is provided, it must be a data extent. */
 	BUG_ON(!is_data && reserved);
 
-	/*
-	 * The head node stores the sum of all the mods, so dropping a ref
-	 * should drop the sum in the head node by one.
-	 */
-	if (action == BTRFS_UPDATE_DELAYED_HEAD)
+	switch (action) {
+	case BTRFS_UPDATE_DELAYED_HEAD:
 		count_mod = 0;
-	else if (action == BTRFS_DROP_DELAYED_REF)
+		break;
+	case BTRFS_DROP_DELAYED_REF:
+		/*
+		 * The head node stores the sum of all the mods, so dropping a ref
+		 * should drop the sum in the head node by one.
+		 */
 		count_mod = -1;
-
-	/*
-	 * BTRFS_ADD_DELAYED_EXTENT means that we need to update the reserved
-	 * accounting when the extent is finally added, or if a later
-	 * modification deletes the delayed ref without ever inserting the
-	 * extent into the extent allocation tree.  ref->must_insert_reserved
-	 * is the flag used to record that accounting mods are required.
-	 *
-	 * Once we record must_insert_reserved, switch the action to
-	 * BTRFS_ADD_DELAYED_REF because other special casing is not required.
-	 */
-	if (action == BTRFS_ADD_DELAYED_EXTENT)
-		must_insert_reserved = 1;
-	else
-		must_insert_reserved = 0;
+		break;
+	case BTRFS_ADD_DELAYED_EXTENT:
+		/*
+		 * BTRFS_ADD_DELAYED_EXTENT means that we need to update the
+		 * reserved accounting when the extent is finally added, or if a
+		 * later modification deletes the delayed ref without ever
+		 * inserting the extent into the extent allocation tree.
+		 * ref->must_insert_reserved is the flag used to record that
+		 * accounting mods are required.
+		 *
+		 * Once we record must_insert_reserved, switch the action to
+		 * BTRFS_ADD_DELAYED_REF because other special casing is not
+		 * required.
+		 */
+		must_insert_reserved = true;
+		break;
+	}
 
 	refcount_set(&head_ref->refs, 1);
 	head_ref->bytenr = bytenr;
@@ -738,7 +740,7 @@ static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
 	head_ref->ref_tree = RB_ROOT_CACHED;
 	INIT_LIST_HEAD(&head_ref->ref_add_list);
 	RB_CLEAR_NODE(&head_ref->href_node);
-	head_ref->processing = 0;
+	head_ref->processing = false;
 	head_ref->total_ref_mod = count_mod;
 	spin_lock_init(&head_ref->lock);
 	mutex_init(&head_ref->mutex);
@@ -763,11 +765,11 @@ static noinline struct btrfs_delayed_ref_head *
 add_delayed_ref_head(struct btrfs_trans_handle *trans,
 		     struct btrfs_delayed_ref_head *head_ref,
 		     struct btrfs_qgroup_extent_record *qrecord,
-		     int action, int *qrecord_inserted_ret)
+		     int action, bool *qrecord_inserted_ret)
 {
 	struct btrfs_delayed_ref_head *existing;
 	struct btrfs_delayed_ref_root *delayed_refs;
-	int qrecord_inserted = 0;
+	bool qrecord_inserted = false;
 
 	delayed_refs = &trans->transaction->delayed_refs;
 
@@ -777,7 +779,7 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans,
 					delayed_refs, qrecord))
 			kfree(qrecord);
 		else
-			qrecord_inserted = 1;
+			qrecord_inserted = true;
 	}
 
 	trace_add_delayed_ref_head(trans->fs_info, head_ref, action);
@@ -853,8 +855,6 @@ static void init_delayed_ref_common(struct btrfs_fs_info *fs_info,
 	ref->num_bytes = num_bytes;
 	ref->ref_mod = 1;
 	ref->action = action;
-	ref->is_head = 0;
-	ref->in_tree = 1;
 	ref->seq = seq;
 	ref->type = ref_type;
 	RB_CLEAR_NODE(&ref->ref_node);
@@ -875,11 +875,11 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct btrfs_qgroup_extent_record *record = NULL;
-	int qrecord_inserted;
+	bool qrecord_inserted;
 	bool is_system;
+	bool merged;
 	int action = generic_ref->action;
 	int level = generic_ref->tree_ref.level;
-	int ret;
 	u64 bytenr = generic_ref->bytenr;
 	u64 num_bytes = generic_ref->len;
 	u64 parent = generic_ref->parent;
@@ -935,7 +935,7 @@ 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(delayed_refs, head_ref, &ref->node);
+	merged = insert_delayed_ref(delayed_refs, head_ref, &ref->node);
 	spin_unlock(&delayed_refs->lock);
 
 	/*
@@ -947,7 +947,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	trace_add_delayed_tree_ref(fs_info, &ref->node, ref,
 				   action == BTRFS_ADD_DELAYED_EXTENT ?
 				   BTRFS_ADD_DELAYED_REF : action);
-	if (ret > 0)
+	if (merged)
 		kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
 
 	if (qrecord_inserted)
@@ -968,9 +968,9 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct btrfs_qgroup_extent_record *record = NULL;
-	int qrecord_inserted;
+	bool qrecord_inserted;
 	int action = generic_ref->action;
-	int ret;
+	bool merged;
 	u64 bytenr = generic_ref->bytenr;
 	u64 num_bytes = generic_ref->len;
 	u64 parent = generic_ref->parent;
@@ -1027,7 +1027,7 @@ 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(delayed_refs, head_ref, &ref->node);
+	merged = insert_delayed_ref(delayed_refs, head_ref, &ref->node);
 	spin_unlock(&delayed_refs->lock);
 
 	/*
@@ -1039,7 +1039,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 	trace_add_delayed_data_ref(trans->fs_info, &ref->node, ref,
 				   action == BTRFS_ADD_DELAYED_EXTENT ?
 				   BTRFS_ADD_DELAYED_REF : action);
-	if (ret > 0)
+	if (merged)
 		kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
 
 

fs/btrfs/delayed-ref.h

@@ -48,9 +48,6 @@ struct btrfs_delayed_ref_node {
 
 	unsigned int action:8;
 	unsigned int type:8;
-	/* is this node still in the rbtree? */
-	unsigned int is_head:1;
-	unsigned int in_tree:1;
 };
 
 struct btrfs_delayed_extent_op {
@@ -70,20 +67,26 @@ struct btrfs_delayed_extent_op {
 struct btrfs_delayed_ref_head {
 	u64 bytenr;
 	u64 num_bytes;
-	refcount_t refs;
+	/*
+	 * For insertion into struct btrfs_delayed_ref_root::href_root.
+	 * Keep it in the same cache line as 'bytenr' for more efficient
+	 * searches in the rbtree.
+	 */
+	struct rb_node href_node;
 	/*
 	 * the mutex is held while running the refs, and it is also
 	 * held when checking the sum of reference modifications.
 	 */
 	struct mutex mutex;
 
+	refcount_t refs;
+
+	/* Protects 'ref_tree' and 'ref_add_list'. */
 	spinlock_t lock;
 	struct rb_root_cached ref_tree;
 	/* accumulate add BTRFS_ADD_DELAYED_REF nodes to this ref_add_list. */
 	struct list_head ref_add_list;
 
-	struct rb_node href_node;
-
 	struct btrfs_delayed_extent_op *extent_op;
 
 	/*
@@ -113,10 +116,10 @@ struct btrfs_delayed_ref_head {
 	 * we need to update the in ram accounting to properly reflect
 	 * the free has happened.
 	 */
-	unsigned int must_insert_reserved:1;
-	unsigned int is_data:1;
-	unsigned int is_system:1;
-	unsigned int processing:1;
+	bool must_insert_reserved;
+	bool is_data;
+	bool is_system;
+	bool processing;
 };
 
 struct btrfs_delayed_tree_ref {
@@ -337,7 +340,7 @@ static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
 {
 	WARN_ON(refcount_read(&ref->refs) == 0);
 	if (refcount_dec_and_test(&ref->refs)) {
-		WARN_ON(ref->in_tree);
+		WARN_ON(!RB_EMPTY_NODE(&ref->ref_node));
 		switch (ref->type) {
 		case BTRFS_TREE_BLOCK_REF_KEY:
 		case BTRFS_SHARED_BLOCK_REF_KEY:

fs/btrfs/dev-replace.c

@@ -41,7 +41,7 @@
  *   All new writes will be written to both target and source devices, so even
  *   if replace gets canceled, sources device still contains up-to-date data.
  *
- *   Location:		handle_ops_on_dev_replace() from __btrfs_map_block()
+ *   Location:		handle_ops_on_dev_replace() from btrfs_map_block()
  *   Start:		btrfs_dev_replace_start()
  *   End:		btrfs_dev_replace_finishing()
  *   Content:		Latest data/metadata
@@ -795,8 +795,8 @@ static int btrfs_set_target_alloc_state(struct btrfs_device *srcdev,
 	while (!find_first_extent_bit(&srcdev->alloc_state, start,
 				      &found_start, &found_end,
 				      CHUNK_ALLOCATED, &cached_state)) {
-		ret = set_extent_bits(&tgtdev->alloc_state, found_start,
-				      found_end, CHUNK_ALLOCATED);
+		ret = set_extent_bit(&tgtdev->alloc_state, found_start,
+				     found_end, CHUNK_ALLOCATED, NULL);
 		if (ret)
 			break;
 		start = found_end + 1;

fs/btrfs/discard.c

@@ -73,6 +73,23 @@ static struct list_head *get_discard_list(struct btrfs_discard_ctl *discard_ctl,
 	return &discard_ctl->discard_list[block_group->discard_index];
 }
 
+/*
+ * Determine if async discard should be running.
+ *
+ * @discard_ctl: discard control
+ *
+ * Check if the file system is writeable and BTRFS_FS_DISCARD_RUNNING is set.
+ */
+static bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl)
+{
+	struct btrfs_fs_info *fs_info = container_of(discard_ctl,
+						     struct btrfs_fs_info,
+						     discard_ctl);
+
+	return (!(fs_info->sb->s_flags & SB_RDONLY) &&
+		test_bit(BTRFS_FS_DISCARD_RUNNING, &fs_info->flags));
+}
+
 static void __add_to_discard_list(struct btrfs_discard_ctl *discard_ctl,
 				  struct btrfs_block_group *block_group)
 {
@@ -544,23 +561,6 @@ static void btrfs_discard_workfn(struct work_struct *work)
 	spin_unlock(&discard_ctl->lock);
 }
 
-/*
- * Determine if async discard should be running.
- *
- * @discard_ctl: discard control
- *
- * Check if the file system is writeable and BTRFS_FS_DISCARD_RUNNING is set.
- */
-bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl)
-{
-	struct btrfs_fs_info *fs_info = container_of(discard_ctl,
-						     struct btrfs_fs_info,
-						     discard_ctl);
-
-	return (!(fs_info->sb->s_flags & SB_RDONLY) &&
-		test_bit(BTRFS_FS_DISCARD_RUNNING, &fs_info->flags));
-}
-
 /*
  * Recalculate the base delay.
  *

fs/btrfs/discard.h

@@ -24,7 +24,6 @@ void btrfs_discard_queue_work(struct btrfs_discard_ctl *discard_ctl,
 			      struct btrfs_block_group *block_group);
 void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
 				 bool override);
-bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl);
 
 /* Update operations */
 void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl);

fs/btrfs/disk-io.h

@@ -31,8 +31,6 @@ struct btrfs_tree_parent_check;
 
 void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info);
 void btrfs_init_fs_info(struct btrfs_fs_info *fs_info);
-int btrfs_verify_level_key(struct extent_buffer *eb, int level,
-			   struct btrfs_key *first_key, u64 parent_transid);
 struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
 				      struct btrfs_tree_parent_check *check);
 struct extent_buffer *btrfs_find_create_tree_block(
@@ -84,9 +82,8 @@ void btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info);
 void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info);
 void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 				 struct btrfs_root *root);
-int btrfs_validate_metadata_buffer(struct btrfs_bio *bbio,
-				   struct page *page, u64 start, u64 end,
-				   int mirror);
+int btrfs_validate_extent_buffer(struct extent_buffer *eb,
+				 struct btrfs_tree_parent_check *check);
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info);
 #endif

fs/btrfs/extent-io-tree.c

@@ -532,6 +532,16 @@ static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
 	return next;
 }
 
+/*
+ * Detect if extent bits request NOWAIT semantics and set the gfp mask accordingly,
+ * unset the EXTENT_NOWAIT bit.
+ */
+static void set_gfp_mask_from_bits(u32 *bits, gfp_t *mask)
+{
+	*mask = (*bits & EXTENT_NOWAIT ? GFP_NOWAIT : GFP_NOFS);
+	*bits &= EXTENT_NOWAIT - 1;
+}
+
 /*
  * Clear some bits on a range in the tree.  This may require splitting or
  * inserting elements in the tree, so the gfp mask is used to indicate which
@@ -546,7 +556,7 @@ static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
  */
 int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		       u32 bits, struct extent_state **cached_state,
-		       gfp_t mask, struct extent_changeset *changeset)
+		       struct extent_changeset *changeset)
 {
 	struct extent_state *state;
 	struct extent_state *cached;
@@ -556,7 +566,9 @@ int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	int clear = 0;
 	int wake;
 	int delete = (bits & EXTENT_CLEAR_ALL_BITS);
+	gfp_t mask;
 
+	set_gfp_mask_from_bits(&bits, &mask);
 	btrfs_debug_check_extent_io_range(tree, start, end);
 	trace_btrfs_clear_extent_bit(tree, start, end - start + 1, bits);
 
@@ -953,7 +965,8 @@ bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
 
 /*
  * Set some bits on a range in the tree.  This may require allocations or
- * sleeping, so the gfp mask is used to indicate what is allowed.
+ * sleeping. By default all allocations use GFP_NOFS, use EXTENT_NOWAIT for
+ * GFP_NOWAIT.
  *
  * If any of the exclusive bits are set, this will fail with -EEXIST if some
  * part of the range already has the desired bits set.  The extent_state of the
@@ -968,7 +981,7 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 			    u32 bits, u64 *failed_start,
 			    struct extent_state **failed_state,
 			    struct extent_state **cached_state,
-			    struct extent_changeset *changeset, gfp_t mask)
+			    struct extent_changeset *changeset)
 {
 	struct extent_state *state;
 	struct extent_state *prealloc = NULL;
@@ -978,7 +991,9 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	u64 last_start;
 	u64 last_end;
 	u32 exclusive_bits = (bits & EXTENT_LOCKED);
+	gfp_t mask;
 
+	set_gfp_mask_from_bits(&bits, &mask);
 	btrfs_debug_check_extent_io_range(tree, start, end);
 	trace_btrfs_set_extent_bit(tree, start, end - start + 1, bits);
 
@@ -1188,10 +1203,10 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 }
 
 int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   u32 bits, struct extent_state **cached_state, gfp_t mask)
+		   u32 bits, struct extent_state **cached_state)
 {
 	return __set_extent_bit(tree, start, end, bits, NULL, NULL,
-				cached_state, NULL, mask);
+				cached_state, NULL);
 }
 
 /*
@@ -1687,8 +1702,7 @@ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 	 */
 	ASSERT(!(bits & EXTENT_LOCKED));
 
-	return __set_extent_bit(tree, start, end, bits, NULL, NULL, NULL,
-				changeset, GFP_NOFS);
+	return __set_extent_bit(tree, start, end, bits, NULL, NULL, NULL, changeset);
 }
 
 int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
@@ -1700,8 +1714,7 @@ int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 	 */
 	ASSERT(!(bits & EXTENT_LOCKED));
 
-	return __clear_extent_bit(tree, start, end, bits, NULL, GFP_NOFS,
-				  changeset);
+	return __clear_extent_bit(tree, start, end, bits, NULL, changeset);
 }
 
 int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
@@ -1711,7 +1724,7 @@ int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
 	u64 failed_start;
 
 	err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start,
-			       NULL, cached, NULL, GFP_NOFS);
+			       NULL, cached, NULL);
 	if (err == -EEXIST) {
 		if (failed_start > start)
 			clear_extent_bit(tree, start, failed_start - 1,
@@ -1733,7 +1746,7 @@ int lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
 	u64 failed_start;
 
 	err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start,
-			       &failed_state, cached_state, NULL, GFP_NOFS);
+			       &failed_state, cached_state, NULL);
 	while (err == -EEXIST) {
 		if (failed_start != start)
 			clear_extent_bit(tree, start, failed_start - 1,
@@ -1743,7 +1756,7 @@ int lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
 				&failed_state);
 		err = __set_extent_bit(tree, start, end, EXTENT_LOCKED,
 				       &failed_start, &failed_state,
-				       cached_state, NULL, GFP_NOFS);
+				       cached_state, NULL);
 	}
 	return err;
 }

fs/btrfs/extent-io-tree.h

@@ -43,6 +43,15 @@ enum {
 	 * want the extent states to go away.
 	 */
 	ENUM_BIT(EXTENT_CLEAR_ALL_BITS),
+
+	/*
+	 * This must be last.
+	 *
+	 * Bit not representing a state but a request for NOWAIT semantics,
+	 * e.g. when allocating memory, and must be masked out from the other
+	 * bits.
+	 */
+	ENUM_BIT(EXTENT_NOWAIT)
 };
 
 #define EXTENT_DO_ACCOUNTING    (EXTENT_CLEAR_META_RESV | \
@@ -127,22 +136,20 @@ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
 int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 			     u32 bits, struct extent_changeset *changeset);
 int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		       u32 bits, struct extent_state **cached, gfp_t mask,
+		       u32 bits, struct extent_state **cached,
 		       struct extent_changeset *changeset);
 
 static inline int clear_extent_bit(struct extent_io_tree *tree, u64 start,
 				   u64 end, u32 bits,
 				   struct extent_state **cached)
 {
-	return __clear_extent_bit(tree, start, end, bits, cached,
-				  GFP_NOFS, NULL);
+	return __clear_extent_bit(tree, start, end, bits, cached, NULL);
 }
 
 static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end,
 				struct extent_state **cached)
 {
-	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, cached,
-				  GFP_NOFS, NULL);
+	return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, cached, NULL);
 }
 
 static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
@@ -154,31 +161,13 @@ static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
 int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 			   u32 bits, struct extent_changeset *changeset);
 int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   u32 bits, struct extent_state **cached_state, gfp_t mask);
-
-static inline int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start,
-					 u64 end, u32 bits)
-{
-	return set_extent_bit(tree, start, end, bits, NULL, GFP_NOWAIT);
-}
-
-static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
-		u64 end, u32 bits)
-{
-	return set_extent_bit(tree, start, end, bits, NULL, GFP_NOFS);
-}
+		   u32 bits, struct extent_state **cached_state);
 
 static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
 		u64 end, struct extent_state **cached_state)
 {
 	return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE,
-				  cached_state, GFP_NOFS, NULL);
-}
-
-static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
-		u64 end, gfp_t mask)
-{
-	return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL, mask);
+				  cached_state, NULL);
 }
 
 static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
@@ -193,29 +182,6 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		       u32 bits, u32 clear_bits,
 		       struct extent_state **cached_state);
 
-static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
-				      u64 end, u32 extra_bits,
-				      struct extent_state **cached_state)
-{
-	return set_extent_bit(tree, start, end,
-			      EXTENT_DELALLOC | extra_bits,
-			      cached_state, GFP_NOFS);
-}
-
-static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
-		u64 end, struct extent_state **cached_state)
-{
-	return set_extent_bit(tree, start, end,
-			      EXTENT_DELALLOC | EXTENT_DEFRAG,
-			      cached_state, GFP_NOFS);
-}
-
-static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
-		u64 end)
-{
-	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, GFP_NOFS);
-}
-
 int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
 			  u64 *start_ret, u64 *end_ret, u32 bits,
 			  struct extent_state **cached_state);

fs/btrfs/extent-tree.h

@@ -141,7 +141,7 @@ int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		  struct extent_buffer *buf, int full_backref);
 int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
-				struct extent_buffer *eb, u64 flags, int level);
+				struct extent_buffer *eb, u64 flags);
 int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref);
 
 int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,

fs/btrfs/extent_io.h

@@ -29,6 +29,8 @@ enum {
 	/* write IO error */
 	EXTENT_BUFFER_WRITE_ERR,
 	EXTENT_BUFFER_NO_CHECK,
+	/* Indicate that extent buffer pages a being read */
+	EXTENT_BUFFER_READING,
 };
 
 /* these are flags for __process_pages_contig */
@@ -38,7 +40,6 @@ enum {
 	ENUM_BIT(PAGE_START_WRITEBACK),
 	ENUM_BIT(PAGE_END_WRITEBACK),
 	ENUM_BIT(PAGE_SET_ORDERED),
-	ENUM_BIT(PAGE_SET_ERROR),
 	ENUM_BIT(PAGE_LOCK),
 };
 
@@ -79,7 +80,6 @@ struct extent_buffer {
 	struct btrfs_fs_info *fs_info;
 	spinlock_t refs_lock;
 	atomic_t refs;
-	atomic_t io_pages;
 	int read_mirror;
 	struct rcu_head rcu_head;
 	pid_t lock_owner;
@@ -89,7 +89,6 @@ struct extent_buffer {
 	struct rw_semaphore lock;
 
 	struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
-	struct list_head release_list;
 #ifdef CONFIG_BTRFS_DEBUG
 	struct list_head leak_list;
 #endif
@@ -179,7 +178,8 @@ int try_release_extent_mapping(struct page *page, gfp_t mask);
 int try_release_extent_buffer(struct page *page);
 
 int btrfs_read_folio(struct file *file, struct folio *folio);
-int extent_write_locked_range(struct inode *inode, u64 start, u64 end);
+int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
+			      struct writeback_control *wbc);
 int extent_writepages(struct address_space *mapping,
 		      struct writeback_control *wbc);
 int btree_write_cache_pages(struct address_space *mapping,
@@ -262,10 +262,9 @@ 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);
-bool set_extent_buffer_dirty(struct extent_buffer *eb);
+void 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);
-int extent_buffer_under_io(const struct extent_buffer *eb);
 void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
 void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
 void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,

fs/btrfs/extent_map.c

@@ -364,8 +364,9 @@ static void extent_map_device_set_bits(struct extent_map *em, unsigned bits)
 		struct btrfs_io_stripe *stripe = &map->stripes[i];
 		struct btrfs_device *device = stripe->dev;
 
-		set_extent_bits_nowait(&device->alloc_state, stripe->physical,
-				 stripe->physical + stripe_size - 1, bits);
+		set_extent_bit(&device->alloc_state, stripe->physical,
+			       stripe->physical + stripe_size - 1,
+			       bits | EXTENT_NOWAIT, NULL);
 	}
 }
 
@@ -380,8 +381,9 @@ static void extent_map_device_clear_bits(struct extent_map *em, unsigned bits)
 		struct btrfs_device *device = stripe->dev;
 
 		__clear_extent_bit(&device->alloc_state, stripe->physical,
-				   stripe->physical + stripe_size - 1, bits,
-				   NULL, GFP_NOWAIT, NULL);
+				   stripe->physical + stripe_size - 1,
+				   bits | EXTENT_NOWAIT,
+				   NULL, NULL);
 	}
 }
 
@@ -502,10 +504,10 @@ void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em)
 	RB_CLEAR_NODE(&em->rb_node);
 }
 
-void replace_extent_mapping(struct extent_map_tree *tree,
-			    struct extent_map *cur,
-			    struct extent_map *new,
-			    int modified)
+static void replace_extent_mapping(struct extent_map_tree *tree,
+				   struct extent_map *cur,
+				   struct extent_map *new,
+				   int modified)
 {
 	lockdep_assert_held_write(&tree->lock);
 
@@ -959,3 +961,95 @@ int btrfs_replace_extent_map_range(struct btrfs_inode *inode,
 
 	return ret;
 }
+
+/*
+ * Split off the first pre bytes from the extent_map at [start, start + len],
+ * and set the block_start for it to new_logical.
+ *
+ * This function is used when an ordered_extent needs to be split.
+ */
+int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre,
+		     u64 new_logical)
+{
+	struct extent_map_tree *em_tree = &inode->extent_tree;
+	struct extent_map *em;
+	struct extent_map *split_pre = NULL;
+	struct extent_map *split_mid = NULL;
+	int ret = 0;
+	unsigned long flags;
+
+	ASSERT(pre != 0);
+	ASSERT(pre < len);
+
+	split_pre = alloc_extent_map();
+	if (!split_pre)
+		return -ENOMEM;
+	split_mid = alloc_extent_map();
+	if (!split_mid) {
+		ret = -ENOMEM;
+		goto out_free_pre;
+	}
+
+	lock_extent(&inode->io_tree, start, start + len - 1, NULL);
+	write_lock(&em_tree->lock);
+	em = lookup_extent_mapping(em_tree, start, len);
+	if (!em) {
+		ret = -EIO;
+		goto out_unlock;
+	}
+
+	ASSERT(em->len == len);
+	ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags));
+	ASSERT(em->block_start < EXTENT_MAP_LAST_BYTE);
+	ASSERT(test_bit(EXTENT_FLAG_PINNED, &em->flags));
+	ASSERT(!test_bit(EXTENT_FLAG_LOGGING, &em->flags));
+	ASSERT(!list_empty(&em->list));
+
+	flags = em->flags;
+	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+
+	/* First, replace the em with a new extent_map starting from * em->start */
+	split_pre->start = em->start;
+	split_pre->len = pre;
+	split_pre->orig_start = split_pre->start;
+	split_pre->block_start = new_logical;
+	split_pre->block_len = split_pre->len;
+	split_pre->orig_block_len = split_pre->block_len;
+	split_pre->ram_bytes = split_pre->len;
+	split_pre->flags = flags;
+	split_pre->compress_type = em->compress_type;
+	split_pre->generation = em->generation;
+
+	replace_extent_mapping(em_tree, em, split_pre, 1);
+
+	/*
+	 * Now we only have an extent_map at:
+	 *     [em->start, em->start + pre]
+	 */
+
+	/* Insert the middle extent_map. */
+	split_mid->start = em->start + pre;
+	split_mid->len = em->len - pre;
+	split_mid->orig_start = split_mid->start;
+	split_mid->block_start = em->block_start + pre;
+	split_mid->block_len = split_mid->len;
+	split_mid->orig_block_len = split_mid->block_len;
+	split_mid->ram_bytes = split_mid->len;
+	split_mid->flags = flags;
+	split_mid->compress_type = em->compress_type;
+	split_mid->generation = em->generation;
+	add_extent_mapping(em_tree, split_mid, 1);
+
+	/* Once for us */
+	free_extent_map(em);
+	/* Once for the tree */
+	free_extent_map(em);
+
+out_unlock:
+	write_unlock(&em_tree->lock);
+	unlock_extent(&inode->io_tree, start, start + len - 1, NULL);
+	free_extent_map(split_mid);
+out_free_pre:
+	free_extent_map(split_pre);
+	return ret;
+}

fs/btrfs/extent_map.h

@@ -90,10 +90,8 @@ struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree,
 int add_extent_mapping(struct extent_map_tree *tree,
 		       struct extent_map *em, int modified);
 void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em);
-void replace_extent_mapping(struct extent_map_tree *tree,
-			    struct extent_map *cur,
-			    struct extent_map *new,
-			    int modified);
+int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre,
+		     u64 new_logical);
 
 struct extent_map *alloc_extent_map(void);
 void free_extent_map(struct extent_map *em);

fs/btrfs/file-item.c

@@ -94,8 +94,8 @@ int btrfs_inode_set_file_extent_range(struct btrfs_inode *inode, u64 start,
 
 	if (btrfs_fs_incompat(inode->root->fs_info, NO_HOLES))
 		return 0;
-	return set_extent_bits(&inode->file_extent_tree, start, start + len - 1,
-			       EXTENT_DIRTY);
+	return set_extent_bit(&inode->file_extent_tree, start, start + len - 1,
+			      EXTENT_DIRTY, NULL);
 }
 
 /*
@@ -438,9 +438,9 @@ blk_status_t btrfs_lookup_bio_sums(struct btrfs_bio *bbio)
 			    BTRFS_DATA_RELOC_TREE_OBJECTID) {
 				u64 file_offset = bbio->file_offset + bio_offset;
 
-				set_extent_bits(&inode->io_tree, file_offset,
-						file_offset + sectorsize - 1,
-						EXTENT_NODATASUM);
+				set_extent_bit(&inode->io_tree, file_offset,
+					       file_offset + sectorsize - 1,
+					       EXTENT_NODATASUM, NULL);
 			} else {
 				btrfs_warn_rl(fs_info,
 			"csum hole found for disk bytenr range [%llu, %llu)",
@@ -560,8 +560,8 @@ int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
 				goto fail;
 			}
 
-			sums->bytenr = start;
-			sums->len = (int)size;
+			sums->logical = start;
+			sums->len = size;
 
 			offset = bytes_to_csum_size(fs_info, start - key.offset);
 
@@ -721,20 +721,17 @@ int btrfs_lookup_csums_bitmap(struct btrfs_root *root, u64 start, u64 end,
  */
 blk_status_t btrfs_csum_one_bio(struct btrfs_bio *bbio)
 {
+	struct btrfs_ordered_extent *ordered = bbio->ordered;
 	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;
 	char *data;
 	struct bvec_iter iter;
 	struct bio_vec bvec;
 	int index;
 	unsigned int blockcount;
-	unsigned long total_bytes = 0;
-	unsigned long this_sum_bytes = 0;
 	int i;
 	unsigned nofs_flag;
 
@@ -749,61 +746,17 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_bio *bbio)
 	sums->len = bio->bi_iter.bi_size;
 	INIT_LIST_HEAD(&sums->list);
 
-	sums->bytenr = bio->bi_iter.bi_sector << 9;
+	sums->logical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
 	index = 0;
 
 	shash->tfm = fs_info->csum_shash;
 
 	bio_for_each_segment(bvec, bio, iter) {
-		if (!ordered) {
-			ordered = btrfs_lookup_ordered_extent(inode, offset);
-			/*
-			 * The bio range is not covered by any ordered extent,
-			 * must be a code logic error.
-			 */
-			if (unlikely(!ordered)) {
-				WARN(1, KERN_WARNING
-			"no ordered extent for root %llu ino %llu offset %llu\n",
-				     inode->root->root_key.objectid,
-				     btrfs_ino(inode), offset);
-				kvfree(sums);
-				return BLK_STS_IOERR;
-			}
-		}
-
 		blockcount = BTRFS_BYTES_TO_BLKS(fs_info,
 						 bvec.bv_len + fs_info->sectorsize
 						 - 1);
 
 		for (i = 0; i < blockcount; i++) {
-			if (!(bio->bi_opf & REQ_BTRFS_ONE_ORDERED) &&
-			    !in_range(offset, ordered->file_offset,
-				      ordered->num_bytes)) {
-				unsigned long bytes_left;
-
-				sums->len = this_sum_bytes;
-				this_sum_bytes = 0;
-				btrfs_add_ordered_sum(ordered, sums);
-				btrfs_put_ordered_extent(ordered);
-
-				bytes_left = bio->bi_iter.bi_size - total_bytes;
-
-				nofs_flag = memalloc_nofs_save();
-				sums = kvzalloc(btrfs_ordered_sum_size(fs_info,
-						      bytes_left), GFP_KERNEL);
-				memalloc_nofs_restore(nofs_flag);
-				if (!sums)
-					return BLK_STS_RESOURCE;
-
-				sums->len = bytes_left;
-				ordered = btrfs_lookup_ordered_extent(inode,
-								offset);
-				ASSERT(ordered); /* Logic error */
-				sums->bytenr = (bio->bi_iter.bi_sector << 9)
-					+ total_bytes;
-				index = 0;
-			}
-
 			data = bvec_kmap_local(&bvec);
 			crypto_shash_digest(shash,
 					    data + (i * fs_info->sectorsize),
@@ -811,15 +764,28 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_bio *bbio)
 					    sums->sums + index);
 			kunmap_local(data);
 			index += fs_info->csum_size;
-			offset += fs_info->sectorsize;
-			this_sum_bytes += fs_info->sectorsize;
-			total_bytes += fs_info->sectorsize;
 		}
 
 	}
-	this_sum_bytes = 0;
+
+	bbio->sums = sums;
 	btrfs_add_ordered_sum(ordered, sums);
-	btrfs_put_ordered_extent(ordered);
+	return 0;
+}
+
+/*
+ * Nodatasum I/O on zoned file systems still requires an btrfs_ordered_sum to
+ * record the updated logical address on Zone Append completion.
+ * Allocate just the structure with an empty sums array here for that case.
+ */
+blk_status_t btrfs_alloc_dummy_sum(struct btrfs_bio *bbio)
+{
+	bbio->sums = kmalloc(sizeof(*bbio->sums), GFP_NOFS);
+	if (!bbio->sums)
+		return BLK_STS_RESOURCE;
+	bbio->sums->len = bbio->bio.bi_iter.bi_size;
+	bbio->sums->logical = bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT;
+	btrfs_add_ordered_sum(bbio->ordered, bbio->sums);
 	return 0;
 }
 
@@ -1086,7 +1052,7 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 again:
 	next_offset = (u64)-1;
 	found_next = 0;
-	bytenr = sums->bytenr + total_bytes;
+	bytenr = sums->logical + total_bytes;
 	file_key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
 	file_key.offset = bytenr;
 	file_key.type = BTRFS_EXTENT_CSUM_KEY;

fs/btrfs/file-item.h

@@ -50,6 +50,7 @@ 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_bio *bbio);
+blk_status_t btrfs_alloc_dummy_sum(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);

fs/btrfs/file.c

@@ -1651,7 +1651,6 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from,
 	struct file *file = iocb->ki_filp;
 	struct btrfs_inode *inode = BTRFS_I(file_inode(file));
 	ssize_t num_written, num_sync;
-	const bool sync = iocb_is_dsync(iocb);
 
 	/*
 	 * If the fs flips readonly due to some impossible error, although we
@@ -1664,9 +1663,6 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from,
 	if (encoded && (iocb->ki_flags & IOCB_NOWAIT))
 		return -EOPNOTSUPP;
 
-	if (sync)
-		atomic_inc(&inode->sync_writers);
-
 	if (encoded) {
 		num_written = btrfs_encoded_write(iocb, from, encoded);
 		num_sync = encoded->len;
@@ -1686,9 +1682,6 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from,
 			num_written = num_sync;
 	}
 
-	if (sync)
-		atomic_dec(&inode->sync_writers);
-
 	current->backing_dev_info = NULL;
 	return num_written;
 }
@@ -1733,9 +1726,7 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
 	 * several segments of stripe length (currently 64K).
 	 */
 	blk_start_plug(&plug);
-	atomic_inc(&BTRFS_I(inode)->sync_writers);
 	ret = btrfs_fdatawrite_range(inode, start, end);
-	atomic_dec(&BTRFS_I(inode)->sync_writers);
 	blk_finish_plug(&plug);
 
 	return ret;
@@ -3709,7 +3700,8 @@ static int btrfs_file_open(struct inode *inode, struct file *filp)
 {
 	int ret;
 
-	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC;
+	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC |
+		        FMODE_CAN_ODIRECT;
 
 	ret = fsverity_file_open(inode, filp);
 	if (ret)

fs/btrfs/free-space-cache.h

@@ -101,8 +101,6 @@ int btrfs_remove_free_space_inode(struct btrfs_trans_handle *trans,
 				  struct inode *inode,
 				  struct btrfs_block_group *block_group);
 
-int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
-				       struct btrfs_block_rsv *rsv);
 int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
 				    struct btrfs_block_group *block_group,
 				    struct inode *inode);

fs/btrfs/free-space-tree.c

@@ -1280,7 +1280,10 @@ int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info)
 		goto abort;
 
 	btrfs_global_root_delete(free_space_root);
+
+	spin_lock(&fs_info->trans_lock);
 	list_del(&free_space_root->dirty_list);
+	spin_unlock(&fs_info->trans_lock);
 
 	btrfs_tree_lock(free_space_root->node);
 	btrfs_clear_buffer_dirty(trans, free_space_root->node);

fs/btrfs/fs.h

@@ -543,7 +543,6 @@ struct btrfs_fs_info {
 	 * A third pool does submit_bio to avoid deadlocking with the other two.
 	 */
 	struct btrfs_workqueue *workers;
-	struct btrfs_workqueue *hipri_workers;
 	struct btrfs_workqueue *delalloc_workers;
 	struct btrfs_workqueue *flush_workers;
 	struct workqueue_struct *endio_workers;
@@ -577,6 +576,7 @@ struct btrfs_fs_info {
 	s32 dirty_metadata_batch;
 	s32 delalloc_batch;
 
+	/* Protected by 'trans_lock'. */
 	struct list_head dirty_cowonly_roots;
 
 	struct btrfs_fs_devices *fs_devices;
@@ -643,7 +643,6 @@ struct btrfs_fs_info {
 	 */
 	refcount_t scrub_workers_refcnt;
 	struct workqueue_struct *scrub_workers;
-	struct workqueue_struct *scrub_wr_completion_workers;
 	struct btrfs_subpage_info *subpage_info;
 
 	struct btrfs_discard_ctl discard_ctl;
@@ -854,7 +853,7 @@ static inline u64 btrfs_calc_metadata_size(const struct btrfs_fs_info *fs_info,
 
 static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info)
 {
-	return fs_info->zone_size > 0;
+	return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && fs_info->zone_size > 0;
 }
 
 /*

fs/btrfs/inode-item.h

@@ -60,6 +60,22 @@ struct btrfs_truncate_control {
 	bool clear_extent_range;
 };
 
+/*
+ * btrfs_inode_item stores flags in a u64, btrfs_inode stores them in two
+ * separate u32s. These two functions convert between the two representations.
+ */
+static inline u64 btrfs_inode_combine_flags(u32 flags, u32 ro_flags)
+{
+	return (flags | ((u64)ro_flags << 32));
+}
+
+static inline void btrfs_inode_split_flags(u64 inode_item_flags,
+					   u32 *flags, u32 *ro_flags)
+{
+	*flags = (u32)inode_item_flags;
+	*ro_flags = (u32)(inode_item_flags >> 32);
+}
+
 int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root,
 			       struct btrfs_truncate_control *control);

fs/btrfs/locking.c

@@ -57,8 +57,8 @@
 
 static struct btrfs_lockdep_keyset {
 	u64			id;		/* root objectid */
-	/* Longest entry: btrfs-free-space-00 */
-	char			names[BTRFS_MAX_LEVEL][20];
+	/* Longest entry: btrfs-block-group-00 */
+	char			names[BTRFS_MAX_LEVEL][24];
 	struct lock_class_key	keys[BTRFS_MAX_LEVEL];
 } btrfs_lockdep_keysets[] = {
 	{ .id = BTRFS_ROOT_TREE_OBJECTID,	DEFINE_NAME("root")	},
@@ -72,6 +72,7 @@ static struct btrfs_lockdep_keyset {
 	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	DEFINE_NAME("dreloc")	},
 	{ .id = BTRFS_UUID_TREE_OBJECTID,	DEFINE_NAME("uuid")	},
 	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	DEFINE_NAME("free-space") },
+	{ .id = BTRFS_BLOCK_GROUP_TREE_OBJECTID, DEFINE_NAME("block-group") },
 	{ .id = 0,				DEFINE_NAME("tree")	},
 };