xref: /kernel/linux/linux-5.10/net/sched/sch_mq.c (revision 8c2ecf20) 
1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * net/sched/sch_mq.c		Classful multiqueue dummy scheduler
4 *
5 * Copyright (c) 2009 Patrick McHardy <kaber@trash.net>
6 */
7
8#include <linux/types.h>
9#include <linux/slab.h>
10#include <linux/kernel.h>
11#include <linux/export.h>
12#include <linux/string.h>
13#include <linux/errno.h>
14#include <linux/skbuff.h>
15#include <net/netlink.h>
16#include <net/pkt_cls.h>
17#include <net/pkt_sched.h>
18#include <net/sch_generic.h>
19
20struct mq_sched {
21	struct Qdisc		**qdiscs;
22};
23
24static int mq_offload(struct Qdisc *sch, enum tc_mq_command cmd)
25{
26	struct net_device *dev = qdisc_dev(sch);
27	struct tc_mq_qopt_offload opt = {
28		.command = cmd,
29		.handle = sch->handle,
30	};
31
32	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
33		return -EOPNOTSUPP;
34
35	return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt);
36}
37
38static int mq_offload_stats(struct Qdisc *sch)
39{
40	struct tc_mq_qopt_offload opt = {
41		.command = TC_MQ_STATS,
42		.handle = sch->handle,
43		.stats = {
44			.bstats = &sch->bstats,
45			.qstats = &sch->qstats,
46		},
47	};
48
49	return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_MQ, &opt);
50}
51
52static void mq_destroy(struct Qdisc *sch)
53{
54	struct net_device *dev = qdisc_dev(sch);
55	struct mq_sched *priv = qdisc_priv(sch);
56	unsigned int ntx;
57
58	mq_offload(sch, TC_MQ_DESTROY);
59
60	if (!priv->qdiscs)
61		return;
62	for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++)
63		qdisc_put(priv->qdiscs[ntx]);
64	kfree(priv->qdiscs);
65}
66
67static int mq_init(struct Qdisc *sch, struct nlattr *opt,
68		   struct netlink_ext_ack *extack)
69{
70	struct net_device *dev = qdisc_dev(sch);
71	struct mq_sched *priv = qdisc_priv(sch);
72	struct netdev_queue *dev_queue;
73	struct Qdisc *qdisc;
74	unsigned int ntx;
75
76	if (sch->parent != TC_H_ROOT)
77		return -EOPNOTSUPP;
78
79	if (!netif_is_multiqueue(dev))
80		return -EOPNOTSUPP;
81
82	/* pre-allocate qdiscs, attachment can't fail */
83	priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]),
84			       GFP_KERNEL);
85	if (!priv->qdiscs)
86		return -ENOMEM;
87
88	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
89		dev_queue = netdev_get_tx_queue(dev, ntx);
90		qdisc = qdisc_create_dflt(dev_queue, get_default_qdisc_ops(dev, ntx),
91					  TC_H_MAKE(TC_H_MAJ(sch->handle),
92						    TC_H_MIN(ntx + 1)),
93					  extack);
94		if (!qdisc)
95			return -ENOMEM;
96		priv->qdiscs[ntx] = qdisc;
97		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
98	}
99
100	sch->flags |= TCQ_F_MQROOT;
101
102	mq_offload(sch, TC_MQ_CREATE);
103	return 0;
104}
105
106static void mq_attach(struct Qdisc *sch)
107{
108	struct net_device *dev = qdisc_dev(sch);
109	struct mq_sched *priv = qdisc_priv(sch);
110	struct Qdisc *qdisc, *old;
111	unsigned int ntx;
112
113	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
114		qdisc = priv->qdiscs[ntx];
115		old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
116		if (old)
117			qdisc_put(old);
118#ifdef CONFIG_NET_SCHED
119		if (ntx < dev->real_num_tx_queues)
120			qdisc_hash_add(qdisc, false);
121#endif
122
123	}
124	kfree(priv->qdiscs);
125	priv->qdiscs = NULL;
126}
127
128static void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx)
129{
130#ifdef CONFIG_NET_SCHED
131	struct net_device *dev = qdisc_dev(sch);
132	struct Qdisc *qdisc;
133	unsigned int i;
134
135	for (i = new_real_tx; i < dev->real_num_tx_queues; i++) {
136		qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping;
137		/* Only update the default qdiscs we created,
138		 * qdiscs with handles are always hashed.
139		 */
140		if (qdisc != &noop_qdisc && !qdisc->handle)
141			qdisc_hash_del(qdisc);
142	}
143	for (i = dev->real_num_tx_queues; i < new_real_tx; i++) {
144		qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping;
145		if (qdisc != &noop_qdisc && !qdisc->handle)
146			qdisc_hash_add(qdisc, false);
147	}
148#endif
149}
150
151static int mq_dump(struct Qdisc *sch, struct sk_buff *skb)
152{
153	struct net_device *dev = qdisc_dev(sch);
154	struct Qdisc *qdisc;
155	unsigned int ntx;
156	__u32 qlen = 0;
157
158	sch->q.qlen = 0;
159	memset(&sch->bstats, 0, sizeof(sch->bstats));
160	memset(&sch->qstats, 0, sizeof(sch->qstats));
161
162	/* MQ supports lockless qdiscs. However, statistics accounting needs
163	 * to account for all, none, or a mix of locked and unlocked child
164	 * qdiscs. Percpu stats are added to counters in-band and locking
165	 * qdisc totals are added at end.
166	 */
167	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
168		qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping;
169		spin_lock_bh(qdisc_lock(qdisc));
170
171		if (qdisc_is_percpu_stats(qdisc)) {
172			qlen = qdisc_qlen_sum(qdisc);
173			__gnet_stats_copy_basic(NULL, &sch->bstats,
174						qdisc->cpu_bstats,
175						&qdisc->bstats);
176			__gnet_stats_copy_queue(&sch->qstats,
177						qdisc->cpu_qstats,
178						&qdisc->qstats, qlen);
179			sch->q.qlen		+= qlen;
180		} else {
181			sch->q.qlen		+= qdisc->q.qlen;
182			sch->bstats.bytes	+= qdisc->bstats.bytes;
183			sch->bstats.packets	+= qdisc->bstats.packets;
184			sch->qstats.qlen	+= qdisc->qstats.qlen;
185			sch->qstats.backlog	+= qdisc->qstats.backlog;
186			sch->qstats.drops	+= qdisc->qstats.drops;
187			sch->qstats.requeues	+= qdisc->qstats.requeues;
188			sch->qstats.overlimits	+= qdisc->qstats.overlimits;
189		}
190
191		spin_unlock_bh(qdisc_lock(qdisc));
192	}
193
194	return mq_offload_stats(sch);
195}
196
197static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl)
198{
199	struct net_device *dev = qdisc_dev(sch);
200	unsigned long ntx = cl - 1;
201
202	if (ntx >= dev->num_tx_queues)
203		return NULL;
204	return netdev_get_tx_queue(dev, ntx);
205}
206
207static struct netdev_queue *mq_select_queue(struct Qdisc *sch,
208					    struct tcmsg *tcm)
209{
210	return mq_queue_get(sch, TC_H_MIN(tcm->tcm_parent));
211}
212
213static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
214		    struct Qdisc **old, struct netlink_ext_ack *extack)
215{
216	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
217	struct tc_mq_qopt_offload graft_offload;
218	struct net_device *dev = qdisc_dev(sch);
219
220	if (dev->flags & IFF_UP)
221		dev_deactivate(dev);
222
223	*old = dev_graft_qdisc(dev_queue, new);
224	if (new)
225		new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
226	if (dev->flags & IFF_UP)
227		dev_activate(dev);
228
229	graft_offload.handle = sch->handle;
230	graft_offload.graft_params.queue = cl - 1;
231	graft_offload.graft_params.child_handle = new ? new->handle : 0;
232	graft_offload.command = TC_MQ_GRAFT;
233
234	qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, *old,
235				   TC_SETUP_QDISC_MQ, &graft_offload, extack);
236	return 0;
237}
238
239static struct Qdisc *mq_leaf(struct Qdisc *sch, unsigned long cl)
240{
241	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
242
243	return dev_queue->qdisc_sleeping;
244}
245
246static unsigned long mq_find(struct Qdisc *sch, u32 classid)
247{
248	unsigned int ntx = TC_H_MIN(classid);
249
250	if (!mq_queue_get(sch, ntx))
251		return 0;
252	return ntx;
253}
254
255static int mq_dump_class(struct Qdisc *sch, unsigned long cl,
256			 struct sk_buff *skb, struct tcmsg *tcm)
257{
258	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
259
260	tcm->tcm_parent = TC_H_ROOT;
261	tcm->tcm_handle |= TC_H_MIN(cl);
262	tcm->tcm_info = dev_queue->qdisc_sleeping->handle;
263	return 0;
264}
265
266static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
267			       struct gnet_dump *d)
268{
269	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
270
271	sch = dev_queue->qdisc_sleeping;
272	if (gnet_stats_copy_basic(&sch->running, d, sch->cpu_bstats,
273				  &sch->bstats) < 0 ||
274	    qdisc_qstats_copy(d, sch) < 0)
275		return -1;
276	return 0;
277}
278
279static void mq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
280{
281	struct net_device *dev = qdisc_dev(sch);
282	unsigned int ntx;
283
284	if (arg->stop)
285		return;
286
287	arg->count = arg->skip;
288	for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) {
289		if (arg->fn(sch, ntx + 1, arg) < 0) {
290			arg->stop = 1;
291			break;
292		}
293		arg->count++;
294	}
295}
296
297static const struct Qdisc_class_ops mq_class_ops = {
298	.select_queue	= mq_select_queue,
299	.graft		= mq_graft,
300	.leaf		= mq_leaf,
301	.find		= mq_find,
302	.walk		= mq_walk,
303	.dump		= mq_dump_class,
304	.dump_stats	= mq_dump_class_stats,
305};
306
307struct Qdisc_ops mq_qdisc_ops __read_mostly = {
308	.cl_ops		= &mq_class_ops,
309	.id		= "mq",
310	.priv_size	= sizeof(struct mq_sched),
311	.init		= mq_init,
312	.destroy	= mq_destroy,
313	.attach		= mq_attach,
314	.change_real_num_tx = mq_change_real_num_tx,
315	.dump		= mq_dump,
316	.owner		= THIS_MODULE,
317};
318