Merge tag 'for-5.19-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Features:

   - subpage:
      - support for PAGE_SIZE > 4K (previously only 64K)
      - make it work with raid56

   - repair super block num_devices automatically if it does not match
     the number of device items

   - defrag can convert inline extents to regular extents, up to now
     inline files were skipped but the setting of mount option
     max_inline could affect the decision logic

   - zoned:
      - minimal accepted zone size is explicitly set to 4MiB
      - make zone reclaim less aggressive and don't reclaim if there are
        enough free zones
      - add per-profile sysfs tunable of the reclaim threshold

   - allow automatic block group reclaim for non-zoned filesystems, with
     sysfs tunables

   - tree-checker: new check, compare extent buffer owner against owner
     rootid

  Performance:

   - avoid blocking on space reservation when doing nowait direct io
     writes (+7% throughput for reads and writes)

   - NOCOW write throughput improvement due to refined locking (+3%)

   - send: reduce pressure to page cache by dropping extent pages right
     after they're processed

  Core:

   - convert all radix trees to xarray

   - add iterators for b-tree node items

   - support printk message index

   - user bulk page allocation for extent buffers

   - switch to bio_alloc API, use on-stack bios where convenient, other
     bio cleanups

   - use rw lock for block groups to favor concurrent reads

   - simplify workques, don't allocate high priority threads for all
     normal queues as we need only one

   - refactor scrub, process chunks based on their constraints and
     similarity

   - allocate direct io structures on stack and pass around only
     pointers, avoids allocation and reduces potential error handling

  Fixes:

   - fix count of reserved transaction items for various inode
     operations

   - fix deadlock between concurrent dio writes when low on free data
     space

   - fix a few cases when zones need to be finished

  VFS, iomap:

   - add helper to check if sb write has started (usable for assertions)

   - new helper iomap_dio_alloc_bio, export iomap_dio_bio_end_io"

* tag 'for-5.19-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (173 commits)
  btrfs: zoned: introduce a minimal zone size 4M and reject mount
  btrfs: allow defrag to convert inline extents to regular extents
  btrfs: add "0x" prefix for unsupported optional features
  btrfs: do not account twice for inode ref when reserving metadata units
  btrfs: zoned: fix comparison of alloc_offset vs meta_write_pointer
  btrfs: send: avoid trashing the page cache
  btrfs: send: keep the current inode open while processing it
  btrfs: allocate the btrfs_dio_private as part of the iomap dio bio
  btrfs: move struct btrfs_dio_private to inode.c
  btrfs: remove the disk_bytenr in struct btrfs_dio_private
  btrfs: allocate dio_data on stack
  iomap: add per-iomap_iter private data
  iomap: allow the file system to provide a bio_set for direct I/O
  btrfs: add a btrfs_dio_rw wrapper
  btrfs: zoned: zone finish unused block group
  btrfs: zoned: properly finish block group on metadata write
  btrfs: zoned: finish block group when there are no more allocatable bytes left
  btrfs: zoned: consolidate zone finish functions
  btrfs: zoned: introduce btrfs_zoned_bg_is_full
  btrfs: improve error reporting in lookup_inline_extent_backref
  ...

1 files changed, 13 insertions, 39 deletions

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index f26202621989..a7dd6ba25e99 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -474,6 +474,7 @@ static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info,
 	struct btrfs_dev_extent *dev_extent = NULL;
 	struct btrfs_block_group *cache;
 	struct btrfs_trans_handle *trans;
+	int iter_ret = 0;
 	int ret = 0;
 	u64 chunk_offset;
 
@@ -524,29 +525,8 @@ static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info,
 	key.type = BTRFS_DEV_EXTENT_KEY;
 	key.offset = 0;
 
-	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-	if (ret < 0)
-		goto free_path;
-	if (ret > 0) {
-		if (path->slots[0] >=
-		    btrfs_header_nritems(path->nodes[0])) {
-			ret = btrfs_next_leaf(root, path);
-			if (ret < 0)
-				goto free_path;
-			if (ret > 0) {
-				ret = 0;
-				goto free_path;
-			}
-		} else {
-			ret = 0;
-		}
-	}
-
-	while (1) {
+	btrfs_for_each_slot(root, &key, &found_key, path, iter_ret) {
 		struct extent_buffer *leaf = path->nodes[0];
-		int slot = path->slots[0];
-
-		btrfs_item_key_to_cpu(leaf, &found_key, slot);
 
 		if (found_key.objectid != src_dev->devid)
 			break;
@@ -557,30 +537,23 @@ static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info,
 		if (found_key.offset < key.offset)
 			break;
 
-		dev_extent = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent);
+		dev_extent = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent);
 
 		chunk_offset = btrfs_dev_extent_chunk_offset(leaf, dev_extent);
 
 		cache = btrfs_lookup_block_group(fs_info, chunk_offset);
 		if (!cache)
-			goto skip;
+			continue;
 
 		spin_lock(&cache->lock);
 		cache->to_copy = 1;
 		spin_unlock(&cache->lock);
 
 		btrfs_put_block_group(cache);
-
-skip:
-		ret = btrfs_next_item(root, path);
-		if (ret != 0) {
-			if (ret > 0)
-				ret = 0;
-			break;
-		}
 	}
+	if (iter_ret < 0)
+		ret = iter_ret;
 
-free_path:
 	btrfs_free_path(path);
 unlock:
 	mutex_unlock(&fs_info->chunk_mutex);
@@ -881,6 +854,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 				       int scrub_ret)
 {
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *tgt_device;
 	struct btrfs_device *src_device;
 	struct btrfs_root *root = fs_info->tree_root;
@@ -930,12 +904,12 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 		WARN_ON(ret);
 
 		/* Prevent write_all_supers() during the finishing procedure */
-		mutex_lock(&fs_info->fs_devices->device_list_mutex);
+		mutex_lock(&fs_devices->device_list_mutex);
 		/* Prevent new chunks being allocated on the source device */
 		mutex_lock(&fs_info->chunk_mutex);
 
 		if (!list_empty(&src_device->post_commit_list)) {
-			mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+			mutex_unlock(&fs_devices->device_list_mutex);
 			mutex_unlock(&fs_info->chunk_mutex);
 		} else {
 			break;
@@ -972,7 +946,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 error:
 		up_write(&dev_replace->rwsem);
 		mutex_unlock(&fs_info->chunk_mutex);
-		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+		mutex_unlock(&fs_devices->device_list_mutex);
 		btrfs_rm_dev_replace_blocked(fs_info);
 		if (tgt_device)
 			btrfs_destroy_dev_replace_tgtdev(tgt_device);
@@ -1001,8 +975,8 @@ error:
 
 	btrfs_assign_next_active_device(src_device, tgt_device);
 
-	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
-	fs_info->fs_devices->rw_devices++;
+	list_add(&tgt_device->dev_alloc_list, &fs_devices->alloc_list);
+	fs_devices->rw_devices++;
 
 	up_write(&dev_replace->rwsem);
 	btrfs_rm_dev_replace_blocked(fs_info);
@@ -1025,7 +999,7 @@ error:
 	 * belong to this filesystem.
 	 */
 	mutex_unlock(&fs_info->chunk_mutex);
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&fs_devices->device_list_mutex);
 
 	/* replace the sysfs entry */
 	btrfs_sysfs_remove_device(src_device);