[PATCH] bcachefs: Fix sysfs warning in fstests generic/730,731

[Kent Overstreet <kent.overstreet@linux.dev>]

sysfs warns if we're removing a symlink from a directory that's no
longer in sysfs; this is triggered by fstests generic/730, which
simulates hot removal of a block device.

This patch is however not a correct fix, since checking
kobj->state_in_sysfs on a kobj owned by another subsystem is racy.

A better fix would be to add the appropriate check to
sysfs_remove_link() - and sysfs_create_link() as well.

But kobject_add_internal()/kobject_del() do not as of today have locking
that would support that.

Note that the block/holder.c code appears to be subject to this race as
well.

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc:  Christoph Hellwig <hch@lst.de>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/super.c | 34 ++++++++++++++++++++++++----------
 1 file changed, 24 insertions(+), 10 deletions(-)

diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 843431e58cf5..f96355ecb296 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -184,6 +184,7 @@ static DEFINE_MUTEX(bch_fs_list_lock);
 
 DECLARE_WAIT_QUEUE_HEAD(bch2_read_only_wait);
 
+static void bch2_dev_unlink(struct bch_dev *);
 static void bch2_dev_free(struct bch_dev *);
 static int bch2_dev_alloc(struct bch_fs *, unsigned);
 static int bch2_dev_sysfs_online(struct bch_fs *, struct bch_dev *);
@@ -620,9 +621,7 @@ void __bch2_fs_stop(struct bch_fs *c)
 	up_write(&c->state_lock);
 
 	for_each_member_device(c, ca)
-		if (ca->kobj.state_in_sysfs &&
-		    ca->disk_sb.bdev)
-			sysfs_remove_link(bdev_kobj(ca->disk_sb.bdev), "bcachefs");
+		bch2_dev_unlink(ca);
 
 	if (c->kobj.state_in_sysfs)
 		kobject_del(&c->kobj);
@@ -1188,9 +1187,7 @@ static void bch2_dev_free(struct bch_dev *ca)
 {
 	cancel_work_sync(&ca->io_error_work);
 
-	if (ca->kobj.state_in_sysfs &&
-	    ca->disk_sb.bdev)
-		sysfs_remove_link(bdev_kobj(ca->disk_sb.bdev), "bcachefs");
+	bch2_dev_unlink(ca);
 
 	if (ca->kobj.state_in_sysfs)
 		kobject_del(&ca->kobj);
@@ -1227,10 +1224,7 @@ static void __bch2_dev_offline(struct bch_fs *c, struct bch_dev *ca)
 	percpu_ref_kill(&ca->io_ref);
 	wait_for_completion(&ca->io_ref_completion);
 
-	if (ca->kobj.state_in_sysfs) {
-		sysfs_remove_link(bdev_kobj(ca->disk_sb.bdev), "bcachefs");
-		sysfs_remove_link(&ca->kobj, "block");
-	}
+	bch2_dev_unlink(ca);
 
 	bch2_free_super(&ca->disk_sb);
 	bch2_dev_journal_exit(ca);
@@ -1252,6 +1246,26 @@ static void bch2_dev_io_ref_complete(struct percpu_ref *ref)
 	complete(&ca->io_ref_completion);
 }
 
+static void bch2_dev_unlink(struct bch_dev *ca)
+{
+	struct kobject *b;
+
+	/*
+	 * This is racy w.r.t. the underlying block device being hot-removed,
+	 * which removes it from sysfs.
+	 *
+	 * It'd be lovely if we had a way to handle this race, but the sysfs
+	 * code doesn't appear to provide a good method and block/holder.c is
+	 * susceptible as well:
+	 */
+	if (ca->kobj.state_in_sysfs &&
+	    ca->disk_sb.bdev &&
+	    (b = bdev_kobj(ca->disk_sb.bdev))->state_in_sysfs) {
+		sysfs_delete_link(b, &ca->kobj, "bcachefs");
+		sysfs_delete_link(&ca->kobj, b, "block");
+	}
+}
+
 static int bch2_dev_sysfs_online(struct bch_fs *c, struct bch_dev *ca)
 {
 	int ret;
-- 
2.45.2