3 files changed, 57 insertions, 8 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f28cef8217dea..ffeb1d7d8ad9d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3272,6 +3272,55 @@ static bool fs_is_full_ro(const struct btrfs_fs_info *fs_info)
 	return false;
 }
 
+/*
+ * Try to wait for any metadata readahead, and invalidate all btree folios.
+ *
+ * If the invalidation failed, report any dirty/held extent buffers.
+ */
+static void invalidate_and_check_btree_folios(struct btrfs_fs_info *fs_info)
+{
+	unsigned long index = 0;
+	struct extent_buffer *eb;
+	int ret;
+
+	ret = invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
+	if (likely(ret == 0))
+		return;
+
+	/*
+	 * Some btree pages can not be invalidated, this happens when some tree
+	 * blocks are still held (either by readahead or some task is holding a ref).
+	 */
+	rcu_read_lock();
+	xa_for_each(&fs_info->buffer_tree, index, eb) {
+		/* Increase the ref so that the eb won't disappear. */
+		if (!refcount_inc_not_zero(&eb->refs))
+			continue;
+		rcu_read_unlock();
+
+		/* Wait for any readahead first. */
+		if (test_bit(EXTENT_BUFFER_READING, &eb->bflags))
+			wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_READING,
+				       TASK_UNINTERRUPTIBLE);
+		/*
+		 * The refs threshold is 2, one held by us at the beginning
+		 * of the loop, one for the ownership in the buffer tree.
+		 */
+		if (unlikely(refcount_read(&eb->refs) > 2 || extent_buffer_under_io(eb))) {
+			WARN_ON_ONCE(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+			btrfs_warn(fs_info,
+			"unable to release extent buffer %llu owner %llu gen %llu refs %u flags 0x%lx",
+				   eb->start, btrfs_header_owner(eb),
+				   btrfs_header_generation(eb),
+				   refcount_read(&eb->refs), eb->bflags);
+		}
+		free_extent_buffer(eb);
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
+}
+
 int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices)
 {
 	u32 sectorsize;
@@ -3709,7 +3758,7 @@ fail_tree_roots:
 	if (fs_info->data_reloc_root)
 		btrfs_drop_and_free_fs_root(fs_info, fs_info->data_reloc_root);
 	free_root_pointers(fs_info, true);
-	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
+	invalidate_and_check_btree_folios(fs_info);
 
 fail_sb_buffer:
 	btrfs_stop_all_workers(fs_info);
@@ -4438,7 +4487,7 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	 * We must make sure there is not any read request to
 	 * submit after we stop all workers.
 	 */
-	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
+	invalidate_and_check_btree_folios(fs_info);
 	btrfs_stop_all_workers(fs_info);
 
 	/*
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e9ca4f6f47d1e..1b7550b344ca5 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2882,12 +2882,6 @@ next:
 	return try_release_extent_state(io_tree, folio);
 }
 
-static int extent_buffer_under_io(const struct extent_buffer *eb)
-{
-	return (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) ||
-		test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
-}
-
 static bool folio_range_has_eb(struct folio *folio)
 {
 	struct btrfs_folio_state *bfs;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index b310a5145cf69..7b4152387d886 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -327,6 +327,12 @@ static inline bool extent_buffer_uptodate(const struct extent_buffer *eb)
 	return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 }
 
+static inline bool extent_buffer_under_io(const struct extent_buffer *eb)
+{
+	return (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) ||
+		test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
+}
+
 int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
 			 unsigned long start, unsigned long len);
 void read_extent_buffer(const struct extent_buffer *eb, void *dst,