@@ -308,6 +308,8 @@ struct Qdisc_ops {
struct netlink_ext_ack *extack);
void (*attach)(struct Qdisc *sch);
int (*change_tx_queue_len)(struct Qdisc *, unsigned int);
+ void (*change_real_num_tx)(struct Qdisc *sch,
+ unsigned int new_real_tx);
int (*dump)(struct Qdisc *, struct sk_buff *);
int (*dump_stats)(struct Qdisc *, struct gnet_dump *);
@@ -684,6 +686,8 @@ void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *);
void qdisc_class_hash_destroy(struct Qdisc_class_hash *);
int dev_qdisc_change_tx_queue_len(struct net_device *dev);
+void dev_qdisc_change_real_num_tx(struct net_device *dev,
+ unsigned int new_real_tx);
void dev_init_scheduler(struct net_device *dev);
void dev_shutdown(struct net_device *dev);
void dev_activate(struct net_device *dev);
@@ -2921,6 +2921,8 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
if (dev->num_tc)
netif_setup_tc(dev, txq);
+ dev_qdisc_change_real_num_tx(dev, txq);
+
dev->real_num_tx_queues = txq;
if (disabling) {
@@ -1330,6 +1330,15 @@ static int qdisc_change_tx_queue_len(struct net_device *dev,
return 0;
}
+void dev_qdisc_change_real_num_tx(struct net_device *dev,
+ unsigned int new_real_tx)
+{
+ struct Qdisc *qdisc = dev->qdisc;
+
+ if (qdisc->ops->change_real_num_tx)
+ qdisc->ops->change_real_num_tx(qdisc, new_real_tx);
+}
+
int dev_qdisc_change_tx_queue_len(struct net_device *dev)
{
bool up = dev->flags & IFF_UP;
@@ -125,6 +125,29 @@ static void mq_attach(struct Qdisc *sch)
priv->qdiscs = NULL;
}
+static void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx)
+{
+#ifdef CONFIG_NET_SCHED
+ struct net_device *dev = qdisc_dev(sch);
+ struct Qdisc *qdisc;
+ unsigned int i;
+
+ for (i = new_real_tx; i < dev->real_num_tx_queues; i++) {
+ qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping;
+ /* Only update the default qdiscs we created,
+ * qdiscs with handles are always hashed.
+ */
+ if (qdisc != &noop_qdisc && !qdisc->handle)
+ qdisc_hash_del(qdisc);
+ }
+ for (i = dev->real_num_tx_queues; i < new_real_tx; i++) {
+ qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping;
+ if (qdisc != &noop_qdisc && !qdisc->handle)
+ qdisc_hash_add(qdisc, false);
+ }
+#endif
+}
+
static int mq_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct net_device *dev = qdisc_dev(sch);
@@ -288,6 +311,7 @@ struct Qdisc_ops mq_qdisc_ops __read_mostly = {
.init = mq_init,
.destroy = mq_destroy,
.attach = mq_attach,
+ .change_real_num_tx = mq_change_real_num_tx,
.dump = mq_dump,
.owner = THIS_MODULE,
};
@@ -306,6 +306,28 @@ static void mqprio_attach(struct Qdisc *sch)
priv->qdiscs = NULL;
}
+static void mqprio_change_real_num_tx(struct Qdisc *sch,
+ unsigned int new_real_tx)
+{
+ struct net_device *dev = qdisc_dev(sch);
+ struct Qdisc *qdisc;
+ unsigned int i;
+
+ for (i = new_real_tx; i < dev->real_num_tx_queues; i++) {
+ qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping;
+ /* Only update the default qdiscs we created,
+ * qdiscs with handles are always hashed.
+ */
+ if (qdisc != &noop_qdisc && !qdisc->handle)
+ qdisc_hash_del(qdisc);
+ }
+ for (i = dev->real_num_tx_queues; i < new_real_tx; i++) {
+ qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping;
+ if (qdisc != &noop_qdisc && !qdisc->handle)
+ qdisc_hash_add(qdisc, false);
+ }
+}
+
static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch,
unsigned long cl)
{
@@ -623,6 +645,7 @@ static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = {
.init = mqprio_init,
.destroy = mqprio_destroy,
.attach = mqprio_attach,
+ .change_real_num_tx = mqprio_change_real_num_tx,
.dump = mqprio_dump,
.owner = THIS_MODULE,
};
mq / mqprio make the default child qdiscs visible. They only do so for the qdiscs which are within real_num_tx_queues when the device is registered. Depending on order of calls in the driver, or if user space changes config via ethtool -L the number of qdiscs visible under tc qdisc show will differ from the number of queues. This is confusing to users and potentially to system configuration scripts which try to make sure qdiscs have the right parameters. Add a new Qdisc_ops callback and make relevant qdiscs TTRT. Note that this uncovers the "shortcut" created by commit 1f27cde313d7 ("net: sched: use pfifo_fast for non real queues") The default child qdiscs beyond initial real_num_tx are always pfifo_fast, no matter what the sysfs setting is. Fixing this gets a little tricky because we'd need to keep a reference on whatever the default qdisc was at the time of creation. In practice this is likely an non-issue the qdiscs likely have to be configured to non-default settings, so whatever user space is doing such configuration can replace the pfifos... now that it will see them. Reported-by: Matthew Massey <matthewmassey@fb.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org> --- include/net/sch_generic.h | 4 ++++ net/core/dev.c | 2 ++ net/sched/sch_generic.c | 9 +++++++++ net/sched/sch_mq.c | 24 ++++++++++++++++++++++++ net/sched/sch_mqprio.c | 23 +++++++++++++++++++++++ 5 files changed, 62 insertions(+)