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
  ...

1 files changed, 40 insertions, 7 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index e97af2e510c3..48ae509f2ac2 100644
--- a/fs/btrfs/block-group.c
+++ b/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);