md: initialise ->writes_pending in personality modules.

The new per-cpu counter for writes_pending is initialised in
md_alloc(), which is not called by dm-raid.
So dm-raid fails when md_write_start() is called.

Move the initialization to the personality modules
that need it.  This way it is always initialised when needed,
but isn't unnecessarily initialized (requiring memory allocation)
when the personality doesn't use writes_pending.

Reported-by: Heinz Mauelshagen <heinzm@redhat.com>
Fixes: 4ad23a976413 ("MD: use per-cpu counter for writes_pending")
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>

5 files changed, 21 insertions, 4 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 212a6777ff31..87edc342ccb3 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5174,6 +5174,18 @@ static void mddev_delayed_delete(struct work_struct *ws)
 
 static void no_op(struct percpu_ref *r) {}
 
+int mddev_init_writes_pending(struct mddev *mddev)
+{
+	if (mddev->writes_pending.percpu_count_ptr)
+		return 0;
+	if (percpu_ref_init(&mddev->writes_pending, no_op, 0, GFP_KERNEL) < 0)
+		return -ENOMEM;
+	/* We want to start with the refcount at zero */
+	percpu_ref_put(&mddev->writes_pending);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mddev_init_writes_pending);
+
 static int md_alloc(dev_t dev, char *name)
 {
 	/*
@@ -5239,10 +5251,6 @@ static int md_alloc(dev_t dev, char *name)
 	blk_queue_make_request(mddev->queue, md_make_request);
 	blk_set_stacking_limits(&mddev->queue->limits);
 
-	if (percpu_ref_init(&mddev->writes_pending, no_op, 0, GFP_KERNEL) < 0)
-		goto abort;
-	/* We want to start with the refcount at zero */
-	percpu_ref_put(&mddev->writes_pending);
 	disk = alloc_disk(1 << shift);
 	if (!disk) {
 		blk_cleanup_queue(mddev->queue);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 11f15146ce51..0fa1de42c42b 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -648,6 +648,7 @@ extern void md_unregister_thread(struct md_thread **threadp);
 extern void md_wakeup_thread(struct md_thread *thread);
 extern void md_check_recovery(struct mddev *mddev);
 extern void md_reap_sync_thread(struct mddev *mddev);
+extern int mddev_init_writes_pending(struct mddev *mddev);
 extern void md_write_start(struct mddev *mddev, struct bio *bi);
 extern void md_write_inc(struct mddev *mddev, struct bio *bi);
 extern void md_write_end(struct mddev *mddev);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index af5056d56878..e1a7e3d4c5e4 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3063,6 +3063,8 @@ static int raid1_run(struct mddev *mddev)
 			mdname(mddev));
 		return -EIO;
 	}
+	if (mddev_init_writes_pending(mddev) < 0)
+		return -ENOMEM;
 	/*
 	 * copy the already verified devices into our private RAID1
 	 * bookkeeping area. [whatever we allocate in run(),
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 4343d7ff9916..797ed60abd5e 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3611,6 +3611,9 @@ static int raid10_run(struct mddev *mddev)
 	int first = 1;
 	bool discard_supported = false;
 
+	if (mddev_init_writes_pending(mddev) < 0)
+		return -ENOMEM;
+
 	if (mddev->private == NULL) {
 		conf = setup_conf(mddev);
 		if (IS_ERR(conf))
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 722064689e82..ec0f951ae19f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7118,6 +7118,9 @@ static int raid5_run(struct mddev *mddev)
 	long long min_offset_diff = 0;
 	int first = 1;
 
+	if (mddev_init_writes_pending(mddev) < 0)
+		return -ENOMEM;
+
 	if (mddev->recovery_cp != MaxSector)
 		pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
 			  mdname(mddev));