[NET_SCHED]: Fix endless loops caused by inaccurate qlen counters (part 1)

There are multiple problems related to qlen adjustment that can lead
to an upper qdisc getting out of sync with the real number of packets
queued, leading to endless dequeueing attempts by the upper layer code.

All qdiscs must maintain an accurate q.qlen counter. There are basically
two groups of operations affecting the qlen: operations that propagate
down the tree (enqueue, dequeue, requeue, drop, reset) beginning at the
root qdisc and operations only affecting a subtree or single qdisc
(change, graft, delete class). Since qlen changes during operations from
the second group don't propagate to ancestor qdiscs, their qlen values
become desynchronized.

This patch adds a function to propagate qlen changes up the qdisc tree,
optionally calling a callback function to perform qdisc-internal
maintenance when the child qdisc becomes empty. The follow-up patches
will convert all qdiscs to use this function where necessary.

Noticed by Timo Steinbach <tsteinbach@astaro.com>.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 32 insertions, 6 deletions

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index d99802f3023..05a93da6f05 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -191,21 +191,27 @@ int unregister_qdisc(struct Qdisc_ops *qops)
    (root qdisc, all its children, children of children etc.)
  */
 
-struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle)
+static struct Qdisc *__qdisc_lookup(struct net_device *dev, u32 handle)
 {
 	struct Qdisc *q;
 
-	read_lock(&qdisc_tree_lock);
 	list_for_each_entry(q, &dev->qdisc_list, list) {
-		if (q->handle == handle) {
-			read_unlock(&qdisc_tree_lock);
+		if (q->handle == handle)
 			return q;
-		}
 	}
-	read_unlock(&qdisc_tree_lock);
 	return NULL;
 }
 
+struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle)
+{
+	struct Qdisc *q;
+
+	read_lock(&qdisc_tree_lock);
+	q = __qdisc_lookup(dev, handle);
+	read_unlock(&qdisc_tree_lock);
+	return q;
+}
+
 static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid)
 {
 	unsigned long cl;
@@ -348,6 +354,26 @@ dev_graft_qdisc(struct net_device *dev, struct Qdisc *qdisc)
 	return oqdisc;
 }
 
+void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
+{
+	struct Qdisc_class_ops *cops;
+	unsigned long cl;
+	u32 parentid;
+
+	if (n == 0)
+		return;
+	while ((parentid = sch->parent)) {
+		sch = __qdisc_lookup(sch->dev, TC_H_MAJ(parentid));
+		cops = sch->ops->cl_ops;
+		if (cops->qlen_notify) {
+			cl = cops->get(sch, parentid);
+			cops->qlen_notify(sch, cl);
+			cops->put(sch, cl);
+		}
+		sch->q.qlen -= n;
+	}
+}
+EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
 
 /* Graft qdisc "new" to class "classid" of qdisc "parent" or
    to device "dev".