1 files changed, 139 insertions, 108 deletions

diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 79359b69ad8d..9e2b9a490db2 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -1,11 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * net/sched/sch_prio.c	Simple 3-band priority "scheduler".
  *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		as published by the Free Software Foundation; either version
- *		2 of the License, or (at your option) any later version.
- *
  * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
  * Fixes:       19990609: J Hadi Salim <hadi@nortelnetworks.com>:
  *              Init --  EINVAL when opt undefined
@@ -20,11 +16,12 @@
 #include <linux/skbuff.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
-
+#include <net/pkt_cls.h>
 
 struct prio_sched_data {
 	int bands;
-	struct tcf_proto *filter_list;
+	struct tcf_proto __rcu *filter_list;
+	struct tcf_block *block;
 	u8  prio2band[TC_PRIO_MAX+1];
 	struct Qdisc *queues[TCQ_PRIO_BANDS];
 };
@@ -36,21 +33,25 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 	struct prio_sched_data *q = qdisc_priv(sch);
 	u32 band = skb->priority;
 	struct tcf_result res;
+	struct tcf_proto *fl;
 	int err;
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	if (TC_H_MAJ(skb->priority) != sch->handle) {
-		err = tc_classify(skb, q->filter_list, &res);
+		fl = rcu_dereference_bh(q->filter_list);
+		err = tcf_classify(skb, NULL, fl, &res, false);
 #ifdef CONFIG_NET_CLS_ACT
 		switch (err) {
 		case TC_ACT_STOLEN:
 		case TC_ACT_QUEUED:
+		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			fallthrough;
 		case TC_ACT_SHOT:
 			return NULL;
 		}
 #endif
-		if (!q->filter_list || err < 0) {
+		if (!fl || err < 0) {
 			if (TC_H_MAJ(band))
 				band = 0;
 			return q->queues[q->prio2band[band & TC_PRIO_MAX]];
@@ -65,8 +66,9 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 }
 
 static int
-prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 {
+	unsigned int len = qdisc_pkt_len(skb);
 	struct Qdisc *qdisc;
 	int ret;
 
@@ -75,19 +77,20 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (qdisc == NULL) {
 
 		if (ret & __NET_XMIT_BYPASS)
-			sch->qstats.drops++;
-		kfree_skb(skb);
+			qdisc_qstats_drop(sch);
+		__qdisc_drop(skb, to_free);
 		return ret;
 	}
 #endif
 
-	ret = qdisc_enqueue(skb, qdisc);
+	ret = qdisc_enqueue(skb, qdisc, to_free);
 	if (ret == NET_XMIT_SUCCESS) {
+		sch->qstats.backlog += len;
 		sch->q.qlen++;
 		return NET_XMIT_SUCCESS;
 	}
 	if (net_xmit_drop_count(ret))
-		sch->qstats.drops++;
+		qdisc_qstats_drop(sch);
 	return ret;
 }
 
@@ -115,6 +118,7 @@ static struct sk_buff *prio_dequeue(struct Qdisc *sch)
 		struct sk_buff *skb = qdisc_dequeue_peeked(qdisc);
 		if (skb) {
 			qdisc_bstats_update(sch, skb);
+			qdisc_qstats_backlog_dec(sch, skb);
 			sch->q.qlen--;
 			return skb;
 		}
@@ -123,24 +127,6 @@ static struct sk_buff *prio_dequeue(struct Qdisc *sch)
 
 }
 
-static unsigned int prio_drop(struct Qdisc *sch)
-{
-	struct prio_sched_data *q = qdisc_priv(sch);
-	int prio;
-	unsigned int len;
-	struct Qdisc *qdisc;
-
-	for (prio = q->bands-1; prio >= 0; prio--) {
-		qdisc = q->queues[prio];
-		if (qdisc->ops->drop && (len = qdisc->ops->drop(qdisc)) != 0) {
-			sch->q.qlen--;
-			return len;
-		}
-	}
-	return 0;
-}
-
-
 static void
 prio_reset(struct Qdisc *sch)
 {
@@ -149,7 +135,30 @@ prio_reset(struct Qdisc *sch)
 
 	for (prio = 0; prio < q->bands; prio++)
 		qdisc_reset(q->queues[prio]);
-	sch->q.qlen = 0;
+}
+
+static int prio_offload(struct Qdisc *sch, struct tc_prio_qopt *qopt)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct tc_prio_qopt_offload opt = {
+		.handle = sch->handle,
+		.parent = sch->parent,
+	};
+
+	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+		return -EOPNOTSUPP;
+
+	if (qopt) {
+		opt.command = TC_PRIO_REPLACE;
+		opt.replace_params.bands = qopt->bands;
+		memcpy(&opt.replace_params.priomap, qopt->priomap,
+		       TC_PRIO_MAX + 1);
+		opt.replace_params.qstats = &sch->qstats;
+	} else {
+		opt.command = TC_PRIO_DESTROY;
+	}
+
+	return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_PRIO, &opt);
 }
 
 static void
@@ -158,22 +167,25 @@ prio_destroy(struct Qdisc *sch)
 	int prio;
 	struct prio_sched_data *q = qdisc_priv(sch);
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_block_put(q->block);
+	prio_offload(sch, NULL);
 	for (prio = 0; prio < q->bands; prio++)
-		qdisc_destroy(q->queues[prio]);
+		qdisc_put(q->queues[prio]);
 }
 
-static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
+static int prio_tune(struct Qdisc *sch, struct nlattr *opt,
+		     struct netlink_ext_ack *extack)
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *queues[TCQ_PRIO_BANDS];
+	int oldbands = q->bands, i;
 	struct tc_prio_qopt *qopt;
-	int i;
 
 	if (nla_len(opt) < sizeof(*qopt))
 		return -EINVAL;
 	qopt = nla_data(opt);
 
-	if (qopt->bands > TCQ_PRIO_BANDS || qopt->bands < 2)
+	if (qopt->bands > TCQ_PRIO_BANDS || qopt->bands < TCQ_MIN_PRIO_BANDS)
 		return -EINVAL;
 
 	for (i = 0; i <= TC_PRIO_MAX; i++) {
@@ -181,61 +193,70 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 			return -EINVAL;
 	}
 
+	/* Before commit, make sure we can allocate all new qdiscs */
+	for (i = oldbands; i < qopt->bands; i++) {
+		queues[i] = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+					      TC_H_MAKE(sch->handle, i + 1),
+					      extack);
+		if (!queues[i]) {
+			while (i > oldbands)
+				qdisc_put(queues[--i]);
+			return -ENOMEM;
+		}
+	}
+
+	prio_offload(sch, qopt);
 	sch_tree_lock(sch);
 	q->bands = qopt->bands;
 	memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1);
 
-	for (i = q->bands; i < TCQ_PRIO_BANDS; i++) {
-		struct Qdisc *child = q->queues[i];
-		q->queues[i] = &noop_qdisc;
-		if (child != &noop_qdisc) {
-			qdisc_tree_decrease_qlen(child, child->q.qlen);
-			qdisc_destroy(child);
-		}
+	for (i = q->bands; i < oldbands; i++)
+		qdisc_purge_queue(q->queues[i]);
+
+	for (i = oldbands; i < q->bands; i++) {
+		q->queues[i] = queues[i];
+		if (q->queues[i] != &noop_qdisc)
+			qdisc_hash_add(q->queues[i], true);
 	}
+
 	sch_tree_unlock(sch);
 
-	for (i = 0; i < q->bands; i++) {
-		if (q->queues[i] == &noop_qdisc) {
-			struct Qdisc *child, *old;
-
-			child = qdisc_create_dflt(sch->dev_queue,
-						  &pfifo_qdisc_ops,
-						  TC_H_MAKE(sch->handle, i + 1));
-			if (child) {
-				sch_tree_lock(sch);
-				old = q->queues[i];
-				q->queues[i] = child;
-
-				if (old != &noop_qdisc) {
-					qdisc_tree_decrease_qlen(old,
-								 old->q.qlen);
-					qdisc_destroy(old);
-				}
-				sch_tree_unlock(sch);
-			}
-		}
-	}
+	for (i = q->bands; i < oldbands; i++)
+		qdisc_put(q->queues[i]);
 	return 0;
 }
 
-static int prio_init(struct Qdisc *sch, struct nlattr *opt)
+static int prio_init(struct Qdisc *sch, struct nlattr *opt,
+		     struct netlink_ext_ack *extack)
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
-	int i;
-
-	for (i = 0; i < TCQ_PRIO_BANDS; i++)
-		q->queues[i] = &noop_qdisc;
+	int err;
 
-	if (opt == NULL) {
+	if (!opt)
 		return -EINVAL;
-	} else {
-		int err;
 
-		if ((err = prio_tune(sch, opt)) != 0)
-			return err;
-	}
-	return 0;
+	err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
+	if (err)
+		return err;
+
+	return prio_tune(sch, opt, extack);
+}
+
+static int prio_dump_offload(struct Qdisc *sch)
+{
+	struct tc_prio_qopt_offload hw_stats = {
+		.command = TC_PRIO_STATS,
+		.handle = sch->handle,
+		.parent = sch->parent,
+		{
+			.stats = {
+				.bstats = &sch->bstats,
+				.qstats = &sch->qstats,
+			},
+		},
+	};
+
+	return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_PRIO, &hw_stats);
 }
 
 static int prio_dump(struct Qdisc *sch, struct sk_buff *skb)
@@ -243,10 +264,15 @@ static int prio_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct prio_sched_data *q = qdisc_priv(sch);
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tc_prio_qopt opt;
+	int err;
 
 	opt.bands = q->bands;
 	memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX + 1);
 
+	err = prio_dump_offload(sch);
+	if (err)
+		goto nla_put_failure;
+
 	if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
@@ -258,21 +284,32 @@ nla_put_failure:
 }
 
 static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
-		      struct Qdisc **old)
+		      struct Qdisc **old, struct netlink_ext_ack *extack)
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
+	struct tc_prio_qopt_offload graft_offload;
 	unsigned long band = arg - 1;
 
-	if (new == NULL)
-		new = &noop_qdisc;
+	if (!new) {
+		new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+					TC_H_MAKE(sch->handle, arg), extack);
+		if (!new)
+			new = &noop_qdisc;
+		else
+			qdisc_hash_add(new, true);
+	}
 
-	sch_tree_lock(sch);
-	*old = q->queues[band];
-	q->queues[band] = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &q->queues[band]);
+
+	graft_offload.handle = sch->handle;
+	graft_offload.parent = sch->parent;
+	graft_offload.graft_params.band = band;
+	graft_offload.graft_params.child_handle = new->handle;
+	graft_offload.command = TC_PRIO_GRAFT;
 
+	qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, *old,
+				   TC_SETUP_QDISC_PRIO, &graft_offload,
+				   extack);
 	return 0;
 }
 
@@ -285,7 +322,7 @@ prio_leaf(struct Qdisc *sch, unsigned long arg)
 	return q->queues[band];
 }
 
-static unsigned long prio_get(struct Qdisc *sch, u32 classid)
+static unsigned long prio_find(struct Qdisc *sch, u32 classid)
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
 	unsigned long band = TC_H_MIN(classid);
@@ -297,11 +334,11 @@ static unsigned long prio_get(struct Qdisc *sch, u32 classid)
 
 static unsigned long prio_bind(struct Qdisc *sch, unsigned long parent, u32 classid)
 {
-	return prio_get(sch, classid);
+	return prio_find(sch, classid);
 }
 
 
-static void prio_put(struct Qdisc *q, unsigned long cl)
+static void prio_unbind(struct Qdisc *q, unsigned long cl)
 {
 }
 
@@ -322,9 +359,9 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	struct Qdisc *cl_q;
 
 	cl_q = q->queues[cl - 1];
-	cl_q->qstats.qlen = cl_q->q.qlen;
-	if (gnet_stats_copy_basic(d, &cl_q->bstats) < 0 ||
-	    gnet_stats_copy_queue(d, &cl_q->qstats) < 0)
+	if (gnet_stats_copy_basic(d, cl_q->cpu_bstats,
+				  &cl_q->bstats, true) < 0 ||
+	    qdisc_qstats_copy(d, cl_q) < 0)
 		return -1;
 
 	return 0;
@@ -339,36 +376,29 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
 		return;
 
 	for (prio = 0; prio < q->bands; prio++) {
-		if (arg->count < arg->skip) {
-			arg->count++;
-			continue;
-		}
-		if (arg->fn(sch, prio + 1, arg) < 0) {
-			arg->stop = 1;
+		if (!tc_qdisc_stats_dump(sch, prio + 1, arg))
 			break;
-		}
-		arg->count++;
 	}
 }
 
-static struct tcf_proto **prio_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_block *prio_tcf_block(struct Qdisc *sch, unsigned long cl,
+					struct netlink_ext_ack *extack)
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
 
 	if (cl)
 		return NULL;
-	return &q->filter_list;
+	return q->block;
 }
 
 static const struct Qdisc_class_ops prio_class_ops = {
 	.graft		=	prio_graft,
 	.leaf		=	prio_leaf,
-	.get		=	prio_get,
-	.put		=	prio_put,
+	.find		=	prio_find,
 	.walk		=	prio_walk,
-	.tcf_chain	=	prio_find_tcf,
+	.tcf_block	=	prio_tcf_block,
 	.bind_tcf	=	prio_bind,
-	.unbind_tcf	=	prio_put,
+	.unbind_tcf	=	prio_unbind,
 	.dump		=	prio_dump_class,
 	.dump_stats	=	prio_dump_class_stats,
 };
@@ -381,7 +411,6 @@ static struct Qdisc_ops prio_qdisc_ops __read_mostly = {
 	.enqueue	=	prio_enqueue,
 	.dequeue	=	prio_dequeue,
 	.peek		=	prio_peek,
-	.drop		=	prio_drop,
 	.init		=	prio_init,
 	.reset		=	prio_reset,
 	.destroy	=	prio_destroy,
@@ -389,6 +418,7 @@ static struct Qdisc_ops prio_qdisc_ops __read_mostly = {
 	.dump		=	prio_dump,
 	.owner		=	THIS_MODULE,
 };
+MODULE_ALIAS_NET_SCH("prio");
 
 static int __init prio_module_init(void)
 {
@@ -404,3 +434,4 @@ module_init(prio_module_init)
 module_exit(prio_module_exit)
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Simple 3-band priority qdisc");