gfs2: Fix asynchronous thread destruction

The kernel threads are currently stopped and destroyed synchronously by
gfs2_make_fs_ro() and gfs2_put_super(), and asynchronously by
signal_our_withdraw(), with no synchronization, so the synchronous and
asynchronous contexts can race with each other.

First, when creating the kernel threads, take an extra task struct
reference so that the task struct won't go away immediately when they
terminate.  This allows those kthreads to terminate immediately when
they're done rather than hanging around as zombies until they are reaped
by kthread_stop().  When kthread_stop() is called on a terminated
kthread, it will return immediately.

Second, in signal_our_withdraw(), once the SDF_JOURNAL_LIVE flag has
been cleared, wake up the logd and quotad wait queues instead of
stopping the logd and quotad kthreads.  The kthreads are then expected
to terminate automatically within short time, but if they cannot, they
will not block the withdraw.

For example, if a user process and one of the kthread decide to withdraw
at the same time, only one of them will perform the actual withdraw and
the other will wait for it to be done.  If the kthread ends up being the
one to wait, the withdrawing user process won't be able to stop it.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>

1 files changed, 25 insertions, 10 deletions

diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 6ea295cee4630..a1a8be56ead58 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1103,29 +1103,49 @@ static int init_threads(struct gfs2_sbd *sdp)
 	struct task_struct *p;
 	int error = 0;
 
-	p = kthread_run(gfs2_logd, sdp, "gfs2_logd");
+	p = kthread_create(gfs2_logd, sdp, "gfs2_logd");
 	if (IS_ERR(p)) {
 		error = PTR_ERR(p);
-		fs_err(sdp, "can't start logd thread: %d\n", error);
+		fs_err(sdp, "can't create logd thread: %d\n", error);
 		return error;
 	}
+	get_task_struct(p);
 	sdp->sd_logd_process = p;
 
-	p = kthread_run(gfs2_quotad, sdp, "gfs2_quotad");
+	p = kthread_create(gfs2_quotad, sdp, "gfs2_quotad");
 	if (IS_ERR(p)) {
 		error = PTR_ERR(p);
-		fs_err(sdp, "can't start quotad thread: %d\n", error);
+		fs_err(sdp, "can't create quotad thread: %d\n", error);
 		goto fail;
 	}
+	get_task_struct(p);
 	sdp->sd_quotad_process = p;
+
+	wake_up_process(sdp->sd_logd_process);
+	wake_up_process(sdp->sd_quotad_process);
 	return 0;
 
 fail:
 	kthread_stop(sdp->sd_logd_process);
+	put_task_struct(sdp->sd_logd_process);
 	sdp->sd_logd_process = NULL;
 	return error;
 }
 
+void gfs2_destroy_threads(struct gfs2_sbd *sdp)
+{
+	if (sdp->sd_logd_process) {
+		kthread_stop(sdp->sd_logd_process);
+		put_task_struct(sdp->sd_logd_process);
+		sdp->sd_logd_process = NULL;
+	}
+	if (sdp->sd_quotad_process) {
+		kthread_stop(sdp->sd_quotad_process);
+		put_task_struct(sdp->sd_quotad_process);
+		sdp->sd_quotad_process = NULL;
+	}
+}
+
 /**
  * gfs2_fill_super - Read in superblock
  * @sb: The VFS superblock
@@ -1276,12 +1296,7 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	if (error) {
 		gfs2_freeze_unlock(&sdp->sd_freeze_gh);
-		if (sdp->sd_quotad_process)
-			kthread_stop(sdp->sd_quotad_process);
-		sdp->sd_quotad_process = NULL;
-		if (sdp->sd_logd_process)
-			kthread_stop(sdp->sd_logd_process);
-		sdp->sd_logd_process = NULL;
+		gfs2_destroy_threads(sdp);
 		fs_err(sdp, "can't make FS RW: %d\n", error);
 		goto fail_per_node;
 	}