[PATCH 2/5] btrfs: zoned: drop stale dirty btree buffers at close_ctree()

On a zoned filesystem btrfs_clear_buffer_dirty() keeps a freed-but-dirty
tree block dirty (EXTENT_BUFFER_ZONED_ZEROOUT) so its zero-out keeps the
zone write pointer moving. A block left ahead of the block group's
meta_write_pointer (e.g. a tree-log block freed before being written) can
never be written by btree_writepages() and survives to unmount.

close_ctree() stops the endio workqueues before the final iput() of the
btree inode but frees the block groups only afterwards. Once the block
group is gone btrfs_check_meta_write_pointer() no longer defers the buffer,
so the iput() submits it for writeback; its completion can no longer be
queued on the destroyed endio_meta_workers and umount hangs on writeback
that never finishes.

btrfs_free_block_groups() has to stay after btrfs_stop_all_workers()
(see also commit 5cdd7db6c5c9), so instead drop the dirty state of such
stale buffers in invalidate_and_check_btree_folios(), which still runs
while the workqueues are alive.

Assisted-by: LLM (debugging, commit message)
Signed-off-by: Johannes Thumshirn <[email protected]>
---
 fs/btrfs/disk-io.c   |  4 ++++
 fs/btrfs/extent_io.c | 12 ++++++++++++
 fs/btrfs/extent_io.h |  1 +
 3 files changed, 17 insertions(+)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index acff40469589..b66525701b33 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3317,6 +3317,10 @@ static void invalidate_and_check_btree_folios(struct btrfs_fs_info *fs_info)
 		if (test_bit(EXTENT_BUFFER_READING, &eb->bflags))
 			wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_READING,
 				       TASK_UNINTERRUPTIBLE);
+
+		if (btrfs_is_zoned(fs_info) &&
+		    test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags))
+			btrfs_clear_stale_buffer_dirty(eb);
 		/*
 		 * The refs threshold is 2, one held by us at the beginning
 		 * of the loop, one for the ownership in the buffer tree.
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4dd8fc5ad247..480d4ec8ca7f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3841,6 +3841,18 @@ void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
 	__btrfs_clear_buffer_dirty(eb);
 }
 
+/*
+ * Drop the dirty state of a stale, already-freed metadata buffer, bypassing
+ * the zoned EXTENT_BUFFER_ZONED_ZEROOUT deferral of btrfs_clear_buffer_dirty().
+ */
+void btrfs_clear_stale_buffer_dirty(struct extent_buffer *eb)
+{
+	btrfs_tree_lock(eb);
+	clear_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags);
+	__btrfs_clear_buffer_dirty(eb);
+	btrfs_tree_unlock(eb);
+}
+
 void set_extent_buffer_dirty(struct extent_buffer *eb)
 {
 	bool was_dirty;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 869925337699..290d6cff6ddb 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -393,6 +393,7 @@ void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 				  u32 bits_to_clear, unsigned long page_ops);
 void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
 			      struct extent_buffer *buf);
+void btrfs_clear_stale_buffer_dirty(struct extent_buffer *eb);
 
 static inline void btrfs_clear_folio_dirty_tag(struct folio *folio)
 {
-- 
2.54.0