Message-Id: <20250924-mq-cake-sub-qdisc-v1-2-43a060d1112a@redhat.com>
Date: Wed, 24 Sep 2025 14:16:04 +0200
From: Toke Høiland-Jørgensen <toke@...hat.com>
To: Toke Høiland-Jørgensen <toke@...e.dk>, 
 Jamal Hadi Salim <jhs@...atatu.com>, Cong Wang <xiyou.wangcong@...il.com>, 
 Jiri Pirko <jiri@...nulli.us>, "David S. Miller" <davem@...emloft.net>, 
 Eric Dumazet <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>, 
 Paolo Abeni <pabeni@...hat.com>, Simon Horman <horms@...nel.org>
Cc: Jonas Köppeler <j.koeppeler@...berlin.de>, 
 cake@...ts.bufferbloat.net, netdev@...r.kernel.org, 
 Toke Høiland-Jørgensen <toke@...hat.com>
Subject: [PATCH RFC net-next 2/4] net/sched: sch_cake: Add cake_mq qdisc
 for using cake on mq devices

Add a cake_mq qdisc which installs cake instances on each hardware
queue on a multi-queue device.

This is just a copy of sch_mq that installs cake instead of the default
qdisc on each queue. Subsequent commits will add sharing of the ckae
cake config between cake instances, as well as a multi-queue aware
shaper algorithm.

Signed-off-by: Toke Høiland-Jørgensen <toke@...hat.com>
---
 net/sched/sch_cake.c | 214 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 213 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index a02f3cfcb09b50bda6ee66dfc8a8df584ae6a365..d17d7669de389bb21ca6ce3b209e0272cfaa5112 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -3154,14 +3154,226 @@ static struct Qdisc_ops cake_qdisc_ops __read_mostly = {
 };
 MODULE_ALIAS_NET_SCH("cake");
 
+struct cake_mq_sched {
+	struct Qdisc		**qdiscs;
+};
+
+static void cake_mq_destroy(struct Qdisc *sch)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct cake_mq_sched *priv = qdisc_priv(sch);
+	unsigned int ntx;
+
+	if (!priv->qdiscs)
+		return;
+	for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++)
+		qdisc_put(priv->qdiscs[ntx]);
+	kfree(priv->qdiscs);
+}
+
+static int cake_mq_init(struct Qdisc *sch, struct nlattr *opt,
+			struct netlink_ext_ack *extack)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct cake_mq_sched *priv = qdisc_priv(sch);
+	struct netdev_queue *dev_queue;
+	struct Qdisc *qdisc;
+	unsigned int ntx;
+
+	if (sch->parent != TC_H_ROOT)
+		return -EOPNOTSUPP;
+
+	if (!netif_is_multiqueue(dev))
+		return -EOPNOTSUPP;
+
+	/* pre-allocate qdiscs, attachment can't fail */
+	priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]),
+			       GFP_KERNEL);
+	if (!priv->qdiscs)
+		return -ENOMEM;
+
+	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
+		dev_queue = netdev_get_tx_queue(dev, ntx);
+		qdisc = qdisc_create_dflt(dev_queue, &cake_qdisc_ops,
+					  TC_H_MAKE(TC_H_MAJ(sch->handle),
+						    TC_H_MIN(ntx + 1)),
+					  extack);
+		if (!qdisc) {
+			kfree(priv->qdiscs);
+			return -ENOMEM;
+		}
+		priv->qdiscs[ntx] = qdisc;
+		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+	}
+
+	sch->flags |= TCQ_F_MQROOT;
+
+	return 0;
+}
+
+static void cake_mq_attach(struct Qdisc *sch)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct cake_mq_sched *priv = qdisc_priv(sch);
+	struct Qdisc *qdisc, *old;
+	unsigned int ntx;
+
+	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
+		qdisc = priv->qdiscs[ntx];
+		old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
+		if (old)
+			qdisc_put(old);
+#ifdef CONFIG_NET_SCHED
+		if (ntx < dev->real_num_tx_queues)
+			qdisc_hash_add(qdisc, false);
+#endif
+	}
+	kfree(priv->qdiscs);
+	priv->qdiscs = NULL;
+}
+
+static int cake_mq_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct Qdisc *qdisc;
+	unsigned int ntx;
+
+	sch->q.qlen = 0;
+	gnet_stats_basic_sync_init(&sch->bstats);
+	memset(&sch->qstats, 0, sizeof(sch->qstats));
+
+	/* MQ supports lockless qdiscs. However, statistics accounting needs
+	 * to account for all, none, or a mix of locked and unlocked child
+	 * qdiscs. Percpu stats are added to counters in-band and locking
+	 * qdisc totals are added at end.
+	 */
+	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
+		qdisc = rtnl_dereference(netdev_get_tx_queue(dev, ntx)->qdisc_sleeping);
+		spin_lock_bh(qdisc_lock(qdisc));
+
+		gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats,
+				     &qdisc->bstats, false);
+		gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats,
+				     &qdisc->qstats);
+		sch->q.qlen += qdisc_qlen(qdisc);
+
+		spin_unlock_bh(qdisc_lock(qdisc));
+	}
+
+	return 0;
+}
+
+static struct netdev_queue *cake_mq_queue_get(struct Qdisc *sch, unsigned long cl)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned long ntx = cl - 1;
+
+	if (ntx >= dev->num_tx_queues)
+		return NULL;
+	return netdev_get_tx_queue(dev, ntx);
+}
+
+static struct netdev_queue *cake_mq_select_queue(struct Qdisc *sch,
+						 struct tcmsg *tcm)
+{
+	return cake_mq_queue_get(sch, TC_H_MIN(tcm->tcm_parent));
+}
+
+static int cake_mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
+			 struct Qdisc **old, struct netlink_ext_ack *extack)
+{
+	NL_SET_ERR_MSG(extack, "can't replace cake_mq sub-qdiscs");
+	return -EOPNOTSUPP;
+}
+
+static struct Qdisc *cake_mq_leaf(struct Qdisc *sch, unsigned long cl)
+{
+	struct netdev_queue *dev_queue = cake_mq_queue_get(sch, cl);
+
+	return rtnl_dereference(dev_queue->qdisc_sleeping);
+}
+
+static unsigned long cake_mq_find(struct Qdisc *sch, u32 classid)
+{
+	unsigned int ntx = TC_H_MIN(classid);
+
+	if (!cake_mq_queue_get(sch, ntx))
+		return 0;
+	return ntx;
+}
+
+static int cake_mq_dump_class(struct Qdisc *sch, unsigned long cl,
+			      struct sk_buff *skb, struct tcmsg *tcm)
+{
+	struct netdev_queue *dev_queue = cake_mq_queue_get(sch, cl);
+
+	tcm->tcm_parent = TC_H_ROOT;
+	tcm->tcm_handle |= TC_H_MIN(cl);
+	tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle;
+	return 0;
+}
+
+static int cake_mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
+				    struct gnet_dump *d)
+{
+	struct netdev_queue *dev_queue = cake_mq_queue_get(sch, cl);
+
+	sch = rtnl_dereference(dev_queue->qdisc_sleeping);
+	if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 ||
+	    qdisc_qstats_copy(d, sch) < 0)
+		return -1;
+	return 0;
+}
+
+static void cake_mq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned int ntx;
+
+	if (arg->stop)
+		return;
+
+	arg->count = arg->skip;
+	for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) {
+		if (!tc_qdisc_stats_dump(sch, ntx + 1, arg))
+			break;
+	}
+}
+
+static const struct Qdisc_class_ops cake_mq_class_ops = {
+	.select_queue	= cake_mq_select_queue,
+	.graft		= cake_mq_graft,
+	.leaf		= cake_mq_leaf,
+	.find		= cake_mq_find,
+	.walk		= cake_mq_walk,
+	.dump		= cake_mq_dump_class,
+	.dump_stats	= cake_mq_dump_class_stats,
+};
+
+static struct Qdisc_ops cake_mq_qdisc_ops __read_mostly = {
+	.cl_ops		=	&cake_mq_class_ops,
+	.id		=	"cake_mq",
+	.priv_size	=	sizeof(struct cake_mq_sched),
+	.init		=	cake_mq_init,
+	.destroy	=	cake_mq_destroy,
+	.attach		= cake_mq_attach,
+	//	.change		=	cake_mq_change,
+	.change_real_num_tx = mq_change_real_num_tx,
+	.dump		=	cake_mq_dump,
+	.owner		=	THIS_MODULE,
+};
+MODULE_ALIAS_NET_SCH("cake_mq");
+
 static int __init cake_module_init(void)
 {
-	return register_qdisc(&cake_qdisc_ops);
+	return register_qdisc(&cake_qdisc_ops) ?:
+		register_qdisc(&cake_mq_qdisc_ops);
 }
 
 static void __exit cake_module_exit(void)
 {
 	unregister_qdisc(&cake_qdisc_ops);
+	unregister_qdisc(&cake_mq_qdisc_ops);
 }
 
 module_init(cake_module_init)

-- 
2.51.0

Powered by blists - more mailing lists