blkio: Take care of cgroup deletion and cfq group reference counting

o One can choose to change elevator or delete a cgroup. Implement group
  reference counting so that both elevator exit and cgroup deletion can
  take place gracefully.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Nauman Rafique <nauman@google.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

1 files changed, 95 insertions, 0 deletions

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index a877eee..8bc31a5 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -192,6 +192,7 @@ struct cfq_group {
 	struct blkio_group blkg;
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 	struct hlist_node cfqd_node;
+	atomic_t ref;
 #endif
 };
 
@@ -924,6 +925,14 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 		*st = CFQ_RB_ROOT;
 	RB_CLEAR_NODE(&cfqg->rb_node);
 
+	/*
+	 * Take the initial reference that will be released on destroy
+	 * This can be thought of a joint reference by cgroup and
+	 * elevator which will be dropped by either elevator exit
+	 * or cgroup deletion path depending on who is exiting first.
+	 */
+	atomic_set(&cfqg->ref, 1);
+
 	/* Add group onto cgroup list */
 	blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd);
 
@@ -960,7 +969,77 @@ static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg)
 		cfqg = &cfqq->cfqd->root_group;
 
 	cfqq->cfqg = cfqg;
+	/* cfqq reference on cfqg */
+	atomic_inc(&cfqq->cfqg->ref);
+}
+
+static void cfq_put_cfqg(struct cfq_group *cfqg)
+{
+	struct cfq_rb_root *st;
+	int i, j;
+
+	BUG_ON(atomic_read(&cfqg->ref) <= 0);
+	if (!atomic_dec_and_test(&cfqg->ref))
+		return;
+	for_each_cfqg_st(cfqg, i, j, st)
+		BUG_ON(!RB_EMPTY_ROOT(&st->rb) || st->active != NULL);
+	kfree(cfqg);
+}
+
+static void cfq_destroy_cfqg(struct cfq_data *cfqd, struct cfq_group *cfqg)
+{
+	/* Something wrong if we are trying to remove same group twice */
+	BUG_ON(hlist_unhashed(&cfqg->cfqd_node));
+
+	hlist_del_init(&cfqg->cfqd_node);
+
+	/*
+	 * Put the reference taken at the time of creation so that when all
+	 * queues are gone, group can be destroyed.
+	 */
+	cfq_put_cfqg(cfqg);
+}
+
+static void cfq_release_cfq_groups(struct cfq_data *cfqd)
+{
+	struct hlist_node *pos, *n;
+	struct cfq_group *cfqg;
+
+	hlist_for_each_entry_safe(cfqg, pos, n, &cfqd->cfqg_list, cfqd_node) {
+		/*
+		 * If cgroup removal path got to blk_group first and removed
+		 * it from cgroup list, then it will take care of destroying
+		 * cfqg also.
+		 */
+		if (!blkiocg_del_blkio_group(&cfqg->blkg))
+			cfq_destroy_cfqg(cfqd, cfqg);
+	}
 }
+
+/*
+ * Blk cgroup controller notification saying that blkio_group object is being
+ * delinked as associated cgroup object is going away. That also means that
+ * no new IO will come in this group. So get rid of this group as soon as
+ * any pending IO in the group is finished.
+ *
+ * This function is called under rcu_read_lock(). key is the rcu protected
+ * pointer. That means "key" is a valid cfq_data pointer as long as we are rcu
+ * read lock.
+ *
+ * "key" was fetched from blkio_group under blkio_cgroup->lock. That means
+ * it should not be NULL as even if elevator was exiting, cgroup deltion
+ * path got to it first.
+ */
+void cfq_unlink_blkio_group(void *key, struct blkio_group *blkg)
+{
+	unsigned long  flags;
+	struct cfq_data *cfqd = key;
+
+	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
+	cfq_destroy_cfqg(cfqd, cfqg_of_blkg(blkg));
+	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
+}
+
 #else /* GROUP_IOSCHED */
 static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
 {
@@ -971,6 +1050,9 @@ cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) {
 	cfqq->cfqg = cfqg;
 }
 
+static void cfq_release_cfq_groups(struct cfq_data *cfqd) {}
+static inline void cfq_put_cfqg(struct cfq_group *cfqg) {}
+
 #endif /* GROUP_IOSCHED */
 
 /*
@@ -2172,11 +2254,13 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
  * task holds one reference to the queue, dropped when task exits. each rq
  * in-flight on this queue also holds a reference, dropped when rq is freed.
  *
+ * Each cfq queue took a reference on the parent group. Drop it now.
  * queue lock must be held here.
  */
 static void cfq_put_queue(struct cfq_queue *cfqq)
 {
 	struct cfq_data *cfqd = cfqq->cfqd;
+	struct cfq_group *cfqg;
 
 	BUG_ON(atomic_read(&cfqq->ref) <= 0);
 
@@ -2186,6 +2270,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 	cfq_log_cfqq(cfqd, cfqq, "put_queue");
 	BUG_ON(rb_first(&cfqq->sort_list));
 	BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
+	cfqg = cfqq->cfqg;
 
 	if (unlikely(cfqd->active_queue == cfqq)) {
 		__cfq_slice_expired(cfqd, cfqq, 0);
@@ -2194,6 +2279,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	kmem_cache_free(cfq_pool, cfqq);
+	cfq_put_cfqg(cfqg);
 }
 
 /*
@@ -3369,11 +3455,15 @@ static void cfq_exit_queue(struct elevator_queue *e)
 	}
 
 	cfq_put_async_queues(cfqd);
+	cfq_release_cfq_groups(cfqd);
+	blkiocg_del_blkio_group(&cfqd->root_group.blkg);
 
 	spin_unlock_irq(q->queue_lock);
 
 	cfq_shutdown_timer_wq(cfqd);
 
+	/* Wait for cfqg->blkg->key accessors to exit their grace periods. */
+	synchronize_rcu();
 	kfree(cfqd);
 }
 
@@ -3401,6 +3491,11 @@ static void *cfq_init_queue(struct request_queue *q)
 	cfqg->weight = 2*BLKIO_WEIGHT_DEFAULT;
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
+	/*
+	 * Take a reference to root group which we never drop. This is just
+	 * to make sure that cfq_put_cfqg() does not try to kfree root group
+	 */
+	atomic_set(&cfqg->ref, 1);
 	blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, (void *)cfqd);
 #endif
 	/*