1 files changed, 314 insertions, 0 deletions

diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
new file mode 100644
index 000000000..5a6b14557
--- /dev/null
+++ b/net/sched/sch_mq.c
@@ -0,0 +1,314 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * net/sched/sch_mq.c		Classful multiqueue dummy scheduler
+ *
+ * Copyright (c) 2009 Patrick McHardy <kaber@trash.net>
+ */
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/netlink.h>
+#include <net/pkt_cls.h>
+#include <net/pkt_sched.h>
+#include <net/sch_priv.h>
+
+static int mq_offload(struct Qdisc *sch, enum tc_mq_command cmd)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct tc_mq_qopt_offload opt = {
+		.command = cmd,
+		.handle = sch->handle,
+	};
+
+	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+		return -EOPNOTSUPP;
+
+	return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt);
+}
+
+static int mq_offload_stats(struct Qdisc *sch)
+{
+	struct tc_mq_qopt_offload opt = {
+		.command = TC_MQ_STATS,
+		.handle = sch->handle,
+		.stats = {
+			.bstats = &sch->bstats,
+			.qstats = &sch->qstats,
+		},
+	};
+
+	return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_MQ, &opt);
+}
+
+void mq_destroy_common(struct Qdisc *sch)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct 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);
+}
+EXPORT_SYMBOL_NS_GPL(mq_destroy_common, "NET_SCHED_INTERNAL");
+
+static void mq_destroy(struct Qdisc *sch)
+{
+	mq_offload(sch, TC_MQ_DESTROY);
+	mq_destroy_common(sch);
+}
+
+int mq_init_common(struct Qdisc *sch, struct nlattr *opt,
+		   struct netlink_ext_ack *extack,
+		   const struct Qdisc_ops *qdisc_ops)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct 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 = kzalloc_objs(priv->qdiscs[0], dev->num_tx_queues);
+	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,
+					  qdisc_ops ?: get_default_qdisc_ops(dev, ntx),
+					  TC_H_MAKE(TC_H_MAJ(sch->handle),
+						    TC_H_MIN(ntx + 1)),
+					  extack);
+		if (!qdisc)
+			return -ENOMEM;
+		priv->qdiscs[ntx] = qdisc;
+		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+	}
+
+	sch->flags |= TCQ_F_MQROOT;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(mq_init_common, "NET_SCHED_INTERNAL");
+
+static int mq_init(struct Qdisc *sch, struct nlattr *opt,
+		   struct netlink_ext_ack *extack)
+{
+	int ret;
+
+	ret = mq_init_common(sch, opt, extack, NULL);
+	if (ret)
+		return ret;
+
+	mq_offload(sch, TC_MQ_CREATE);
+	return 0;
+}
+
+void mq_attach(struct Qdisc *sch)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct 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;
+}
+EXPORT_SYMBOL_NS_GPL(mq_attach, "NET_SCHED_INTERNAL");
+
+void mq_dump_common(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct gnet_stats_queue qstats = { 0 };
+	struct gnet_stats_basic_sync bstats;
+	const struct Qdisc *qdisc;
+	unsigned int qlen = 0;
+	unsigned int ntx;
+
+	gnet_stats_basic_sync_init(&bstats);
+
+	/* 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.
+	 */
+	rcu_read_lock();
+	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
+		qdisc = rcu_dereference(netdev_get_tx_queue(dev, ntx)->qdisc_sleeping);
+
+		gnet_stats_add_basic(&bstats, qdisc->cpu_bstats,
+				     &qdisc->bstats, true);
+		gnet_stats_add_queue(&qstats, qdisc->cpu_qstats,
+				     &qdisc->qstats);
+		qlen += qdisc_qlen_lockless(qdisc);
+	}
+	rcu_read_unlock();
+
+	spin_lock_bh(qdisc_lock(sch));
+	_bstats_set(&sch->bstats, u64_stats_read(&bstats.bytes),
+		    u64_stats_read(&bstats.packets));
+	spin_unlock_bh(qdisc_lock(sch));
+
+	WRITE_ONCE(sch->qstats.qlen, qstats.qlen);
+	WRITE_ONCE(sch->qstats.backlog, qstats.backlog);
+	WRITE_ONCE(sch->qstats.drops, qstats.drops);
+	WRITE_ONCE(sch->qstats.requeues, qstats.requeues);
+	WRITE_ONCE(sch->qstats.overlimits, qstats.overlimits);
+
+	WRITE_ONCE(sch->q.qlen, qlen);
+}
+EXPORT_SYMBOL_NS_GPL(mq_dump_common, "NET_SCHED_INTERNAL");
+
+static int mq_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	mq_dump_common(sch, skb);
+	return mq_offload_stats(sch);
+}
+
+static struct netdev_queue *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);
+}
+
+struct netdev_queue *mq_select_queue(struct Qdisc *sch,
+				     struct tcmsg *tcm)
+{
+	return mq_queue_get(sch, TC_H_MIN(tcm->tcm_parent));
+}
+EXPORT_SYMBOL_NS_GPL(mq_select_queue, "NET_SCHED_INTERNAL");
+
+static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
+		    struct Qdisc **old, struct netlink_ext_ack *extack)
+{
+	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
+	struct tc_mq_qopt_offload graft_offload;
+	struct net_device *dev = qdisc_dev(sch);
+
+	if (dev->flags & IFF_UP)
+		dev_deactivate(dev, false);
+
+	*old = dev_graft_qdisc(dev_queue, new);
+	if (new)
+		new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+	if (dev->flags & IFF_UP)
+		dev_activate(dev);
+
+	graft_offload.handle = sch->handle;
+	graft_offload.graft_params.queue = cl - 1;
+	graft_offload.graft_params.child_handle = new ? new->handle : 0;
+	graft_offload.command = TC_MQ_GRAFT;
+
+	qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, *old,
+				   TC_SETUP_QDISC_MQ, &graft_offload, extack);
+	return 0;
+}
+
+struct Qdisc *mq_leaf(struct Qdisc *sch, unsigned long cl)
+{
+	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
+
+	return rtnl_dereference(dev_queue->qdisc_sleeping);
+}
+EXPORT_SYMBOL_NS_GPL(mq_leaf, "NET_SCHED_INTERNAL");
+
+unsigned long mq_find(struct Qdisc *sch, u32 classid)
+{
+	unsigned int ntx = TC_H_MIN(classid);
+
+	if (!mq_queue_get(sch, ntx))
+		return 0;
+	return ntx;
+}
+EXPORT_SYMBOL_NS_GPL(mq_find, "NET_SCHED_INTERNAL");
+
+int mq_dump_class(struct Qdisc *sch, unsigned long cl,
+		  struct sk_buff *skb, struct tcmsg *tcm)
+{
+	struct netdev_queue *dev_queue = 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;
+}
+EXPORT_SYMBOL_NS_GPL(mq_dump_class, "NET_SCHED_INTERNAL");
+
+int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
+			struct gnet_dump *d)
+{
+	struct netdev_queue *dev_queue = 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;
+}
+EXPORT_SYMBOL_NS_GPL(mq_dump_class_stats, "NET_SCHED_INTERNAL");
+
+void 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;
+	}
+}
+EXPORT_SYMBOL_NS_GPL(mq_walk, "NET_SCHED_INTERNAL");
+
+static const struct Qdisc_class_ops mq_class_ops = {
+	.select_queue	= mq_select_queue,
+	.graft		= mq_graft,
+	.leaf		= mq_leaf,
+	.find		= mq_find,
+	.walk		= mq_walk,
+	.dump		= mq_dump_class,
+	.dump_stats	= mq_dump_class_stats,
+};
+
+struct Qdisc_ops mq_qdisc_ops __read_mostly = {
+	.cl_ops		= &mq_class_ops,
+	.id		= "mq",
+	.priv_size	= sizeof(struct mq_sched),
+	.init		= mq_init,
+	.destroy	= mq_destroy,
+	.attach		= mq_attach,
+	.change_real_num_tx = mq_change_real_num_tx,
+	.dump		= mq_dump,
+	.owner		= THIS_MODULE,
+};