[RFC PATCH 07/17] net: sched: drop qdisc_reset from dev_graft_qdisc

[John Fastabend <john.fastabend@gmail.com>]

In qdisc_graft_qdisc a "new" qdisc is attached and the 'qdisc_destroy'
operation is called on the old qdisc. The destroy operation will wait
a rcu grace period and call qdisc_rcu_free(). At which point
gso_cpu_skb is free'd along with all stats so no need to zero stats
and gso_cpu_skb from the graft operation itself.

Further after dropping the qdisc locks we can not continue to call
qdisc_reset before waiting an rcu grace period so that the qdisc is
detached from all cpus. By removing the qdisc_reset() here we get
the correct property of waiting an rcu grace period and letting the
qdisc_destroy operation clean up the qdisc correctly.

Note, a refcnt greater than 1 would cause the destroy operation to
be aborted however if this ever happened the reference to the qdisc
would be lost and we would have a memory leak.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
---
 0 files changed

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 1055bec..ea017ce 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -818,10 +818,6 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 	root_lock = qdisc_lock(oqdisc);
 	spin_lock_bh(root_lock);
 
-	/* Prune old scheduler */
-	if (oqdisc && refcount_read(&oqdisc->refcnt) <= 1)
-		qdisc_reset(oqdisc);
-
 	/* ... and graft new one */
 	if (qdisc == NULL)
 		qdisc = &noop_qdisc;
@@ -976,6 +972,16 @@ static bool some_qdisc_is_busy(struct net_device *dev)
 	return false;
 }
 
+static void dev_qdisc_reset(struct net_device *dev,
+			    struct netdev_queue *dev_queue,
+			    void *none)
+{
+	struct Qdisc *qdisc = dev_queue->qdisc_sleeping;
+
+	if (qdisc)
+		qdisc_reset(qdisc);
+}
+
 /**
  * 	dev_deactivate_many - deactivate transmissions on several devices
  * 	@head: list of devices to deactivate
@@ -986,7 +992,6 @@ static bool some_qdisc_is_busy(struct net_device *dev)
 void dev_deactivate_many(struct list_head *head)
 {
 	struct net_device *dev;
-	bool sync_needed = false;
 
 	list_for_each_entry(dev, head, close_list) {
 		netdev_for_each_tx_queue(dev, dev_deactivate_queue,
@@ -996,20 +1001,25 @@ void dev_deactivate_many(struct list_head *head)
 					     &noop_qdisc);
 
 		dev_watchdog_down(dev);
-		sync_needed |= !dev->dismantle;
 	}
 
 	/* Wait for outstanding qdisc-less dev_queue_xmit calls.
 	 * This is avoided if all devices are in dismantle phase :
 	 * Caller will call synchronize_net() for us
 	 */
-	if (sync_needed)
-		synchronize_net();
+	synchronize_net();
 
 	/* Wait for outstanding qdisc_run calls. */
-	list_for_each_entry(dev, head, close_list)
+	list_for_each_entry(dev, head, close_list) {
 		while (some_qdisc_is_busy(dev))
 			yield();
+		/* The new qdisc is assigned at this point so we can safely
+		 * unwind stale skb lists and qdisc statistics
+		 */
+		netdev_for_each_tx_queue(dev, dev_qdisc_reset, NULL);
+		if (dev_ingress_queue(dev))
+			dev_qdisc_reset(dev, dev_ingress_queue(dev), NULL);
+	}
 }
 
 void dev_deactivate(struct net_device *dev)