md linear: fix a race between linear_add() and linear_congested()

am: 5a1f03f1ee

Change-Id: I3fd7c0c0cbf911b61d8aca203a75e13e698d7840

drivers/md/linear.c

@@ -52,18 +52,26 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
 	return conf->disks + lo;
 }
 
+/*
+ * In linear_congested() conf->raid_disks is used as a copy of
+ * mddev->raid_disks to iterate conf->disks[], because conf->raid_disks
+ * and conf->disks[] are created in linear_conf(), they are always
+ * consitent with each other, but mddev->raid_disks does not.
+ */
 static int linear_congested(struct mddev *mddev, int bits)
 {
 	struct linear_conf *conf;
 	int i, ret = 0;
 
-	conf = mddev->private;
+	rcu_read_lock();
+	conf = rcu_dereference(mddev->private);
 
-	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
+	for (i = 0; i < conf->raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
 		ret |= bdi_congested(&q->backing_dev_info, bits);
 	}
 
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -143,6 +151,19 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 			conf->disks[i-1].end_sector +
 			conf->disks[i].rdev->sectors;
 
+	/*
+	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
+	 * keep a copy of mddev->raid_disks in struct linear_conf is,
+	 * mddev->raid_disks may not be consistent with pointers number of
+	 * conf->disks[] when it is updated in linear_add() and used to
+	 * iterate old conf->disks[] earray in linear_congested().
+	 * Here conf->raid_disks is always consitent with number of
+	 * pointers in conf->disks[] array, and mddev->private is updated
+	 * with rcu_assign_pointer() in linear_addr(), such race can be
+	 * avoided.
+	 */
+	conf->raid_disks = raid_disks;
+
 	return conf;
 
 out:
@@ -195,15 +216,23 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	if (!newconf)
 		return -ENOMEM;
 
+	/* newconf->raid_disks already keeps a copy of * the increased
+	 * value of mddev->raid_disks, WARN_ONCE() is just used to make
+	 * sure of this. It is possible that oldconf is still referenced
+	 * in linear_congested(), therefore kfree_rcu() is used to free
+	 * oldconf until no one uses it anymore.
+	 */
 	mddev_suspend(mddev);
-	oldconf = mddev->private;
+	oldconf = rcu_dereference(mddev->private);
 	mddev->raid_disks++;
-	mddev->private = newconf;
+	WARN_ONCE(mddev->raid_disks != newconf->raid_disks,
+		"copied raid_disks doesn't match mddev->raid_disks");
+	rcu_assign_pointer(mddev->private, newconf);
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev_resume(mddev);
 	revalidate_disk(mddev->gendisk);
-	kfree(oldconf);
+	kfree_rcu(oldconf, rcu);
 	return 0;
 }
 

drivers/md/linear.h

@@ -10,6 +10,7 @@ struct linear_conf
 {
 	struct rcu_head		rcu;
 	sector_t		array_sectors;
+	int			raid_disks; /* a copy of mddev->raid_disks */
 	struct dev_info		disks[0];
 };
 #endif