net: qdisc: use rcu prefix and silence sparse warnings

Add __rcu notation to qdisc handling by doing this we can make
smatch output more legible. And anyways some of the cases should
be using rcu_dereference() see qdisc_all_tx_empty(),
qdisc_tx_chainging(), and so on.

Also *wake_queue() API is commonly called from driver timer routines
without rcu lock or rtnl lock. So I added rcu_read_lock() blocks
around netif_wake_subqueue and netif_tx_wake_queue.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 63 insertions, 11 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 3c6a967..b3d6dbc 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2177,6 +2177,53 @@ static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb)
 	return (struct dev_kfree_skb_cb *)skb->cb;
 }
 
+void netif_schedule_queue(struct netdev_queue *txq)
+{
+	rcu_read_lock();
+	if (!(txq->state & QUEUE_STATE_ANY_XOFF)) {
+		struct Qdisc *q = rcu_dereference(txq->qdisc);
+
+		__netif_schedule(q);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(netif_schedule_queue);
+
+/**
+ *	netif_wake_subqueue - allow sending packets on subqueue
+ *	@dev: network device
+ *	@queue_index: sub queue index
+ *
+ * Resume individual transmit queue of a device with multiple transmit queues.
+ */
+void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
+{
+	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
+
+	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)) {
+		struct Qdisc *q;
+
+		rcu_read_lock();
+		q = rcu_dereference(txq->qdisc);
+		__netif_schedule(q);
+		rcu_read_unlock();
+	}
+}
+EXPORT_SYMBOL(netif_wake_subqueue);
+
+void netif_tx_wake_queue(struct netdev_queue *dev_queue)
+{
+	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) {
+		struct Qdisc *q;
+
+		rcu_read_lock();
+		q = rcu_dereference(dev_queue->qdisc);
+		__netif_schedule(q);
+		rcu_read_unlock();
+	}
+}
+EXPORT_SYMBOL(netif_tx_wake_queue);
+
 void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
 {
 	unsigned long flags;
@@ -3432,7 +3479,7 @@ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq)
 	skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl);
 	skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
 
-	q = rxq->qdisc;
+	q = rcu_dereference(rxq->qdisc);
 	if (q != &noop_qdisc) {
 		spin_lock(qdisc_lock(q));
 		if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
@@ -3449,7 +3496,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb,
 {
 	struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue);
 
-	if (!rxq || rxq->qdisc == &noop_qdisc)
+	if (!rxq || rcu_access_pointer(rxq->qdisc) == &noop_qdisc)
 		goto out;
 
 	if (*pt_prev) {
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 19696eb..346ef85 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -783,7 +783,7 @@ static void dev_deactivate_queue(struct net_device *dev,
 	struct Qdisc *qdisc_default = _qdisc_default;
 	struct Qdisc *qdisc;
 
-	qdisc = dev_queue->qdisc;
+	qdisc = rtnl_dereference(dev_queue->qdisc);
 	if (qdisc) {
 		spin_lock_bh(qdisc_lock(qdisc));
 
@@ -876,7 +876,7 @@ static void dev_init_scheduler_queue(struct net_device *dev,
 {
 	struct Qdisc *qdisc = _qdisc;
 
-	dev_queue->qdisc = qdisc;
+	rcu_assign_pointer(dev_queue->qdisc, qdisc);
 	dev_queue->qdisc_sleeping = qdisc;
 }
 
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 6749e2f..37e7d25 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -231,7 +231,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 	memset(&sch->qstats, 0, sizeof(sch->qstats));
 
 	for (i = 0; i < dev->num_tx_queues; i++) {
-		qdisc = netdev_get_tx_queue(dev, i)->qdisc;
+		qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc);
 		spin_lock_bh(qdisc_lock(qdisc));
 		sch->q.qlen		+= qdisc->q.qlen;
 		sch->bstats.bytes	+= qdisc->bstats.bytes;
@@ -340,7 +340,9 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		spin_unlock_bh(d->lock);
 
 		for (i = tc.offset; i < tc.offset + tc.count; i++) {
-			qdisc = netdev_get_tx_queue(dev, i)->qdisc;
+			struct netdev_queue *q = netdev_get_tx_queue(dev, i);
+
+			qdisc = rtnl_dereference(q->qdisc);
 			spin_lock_bh(qdisc_lock(qdisc));
 			bstats.bytes      += qdisc->bstats.bytes;
 			bstats.packets    += qdisc->bstats.packets;
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index aaa8d03..5cd291b 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -96,11 +96,14 @@ teql_dequeue(struct Qdisc *sch)
 	struct teql_sched_data *dat = qdisc_priv(sch);
 	struct netdev_queue *dat_queue;
 	struct sk_buff *skb;
+	struct Qdisc *q;
 
 	skb = __skb_dequeue(&dat->q);
 	dat_queue = netdev_get_tx_queue(dat->m->dev, 0);
+	q = rcu_dereference_bh(dat_queue->qdisc);
+
 	if (skb == NULL) {
-		struct net_device *m = qdisc_dev(dat_queue->qdisc);
+		struct net_device *m = qdisc_dev(q);
 		if (m) {
 			dat->m->slaves = sch;
 			netif_wake_queue(m);
@@ -108,7 +111,7 @@ teql_dequeue(struct Qdisc *sch)
 	} else {
 		qdisc_bstats_update(sch, skb);
 	}
-	sch->q.qlen = dat->q.qlen + dat_queue->qdisc->q.qlen;
+	sch->q.qlen = dat->q.qlen + q->q.qlen;
 	return skb;
 }
 
@@ -157,9 +160,9 @@ teql_destroy(struct Qdisc *sch)
 						txq = netdev_get_tx_queue(master->dev, 0);
 						master->slaves = NULL;
 
-						root_lock = qdisc_root_sleeping_lock(txq->qdisc);
+						root_lock = qdisc_root_sleeping_lock(rtnl_dereference(txq->qdisc));
 						spin_lock_bh(root_lock);
-						qdisc_reset(txq->qdisc);
+						qdisc_reset(rtnl_dereference(txq->qdisc));
 						spin_unlock_bh(root_lock);
 					}
 				}
@@ -266,7 +269,7 @@ static inline int teql_resolve(struct sk_buff *skb,
 	struct dst_entry *dst = skb_dst(skb);
 	int res;
 
-	if (txq->qdisc == &noop_qdisc)
+	if (rcu_access_pointer(txq->qdisc) == &noop_qdisc)
 		return -ENODEV;
 
 	if (!dev->header_ops || !dst)