net_sched: implement a root container qdisc sch_mqprio

This implements a mqprio queueing discipline that by default creates
a pfifo_fast qdisc per tx queue and provides the needed configuration
interface.

Using the mqprio qdisc the number of tcs currently in use along
with the range of queues alloted to each class can be configured. By
default skbs are mapped to traffic classes using the skb priority.
This mapping is configurable.

Configurable parameters,

struct tc_mqprio_qopt {
	__u8    num_tc;
	__u8    prio_tc_map[TC_BITMASK + 1];
	__u8    hw;
	__u16   count[TC_MAX_QUEUE];
	__u16   offset[TC_MAX_QUEUE];
};

Here the count/offset pairing give the queue alignment and the
prio_tc_map gives the mapping from skb->priority to tc.

The hw bit determines if the hardware should configure the count
and offset values. If the hardware bit is set then the operation
will fail if the hardware does not implement the ndo_setup_tc
operation. This is to avoid undetermined states where the hardware
may or may not control the queue mapping. Also minimal bounds
checking is done on the count/offset to verify a queue does not
exceed num_tx_queues and that queue ranges do not overlap. Otherwise
it is left to user policy or hardware configuration to create
useful mappings.

It is expected that hardware QOS schemes can be implemented by
creating appropriate mappings of queues in ndo_tc_setup().

One expected use case is drivers will use the ndo_setup_tc to map
queue ranges onto 802.1Q traffic classes. This provides a generic
mechanism to map network traffic onto these traffic classes and
removes the need for lower layer drivers to know specifics about
traffic types.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 446 insertions, 0 deletions

diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h
index 2cfa4bc8dea..776cd93d5f7 100644
--- a/include/linux/pkt_sched.h
+++ b/include/linux/pkt_sched.h
@@ -481,4 +481,16 @@ struct tc_drr_stats {
 	__u32	deficit;
 };
 
+/* MQPRIO */
+#define TC_QOPT_BITMASK 15
+#define TC_QOPT_MAX_QUEUE 16
+
+struct tc_mqprio_qopt {
+	__u8	num_tc;
+	__u8	prio_tc_map[TC_QOPT_BITMASK + 1];
+	__u8	hw;
+	__u16	count[TC_QOPT_MAX_QUEUE];
+	__u16	offset[TC_QOPT_MAX_QUEUE];
+};
+
 #endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index f04d4a484d5..73431d4aa6e 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -205,6 +205,18 @@ config NET_SCH_DRR
 
 	  If unsure, say N.
 
+config NET_SCH_MQPRIO
+	tristate "Multi-queue priority scheduler (MQPRIO)"
+	help
+	  Say Y here if you want to use the Multi-queue Priority scheduler.
+	  This scheduler allows QOS to be offloaded on NICs that have support
+	  for offloading QOS schedulers.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called sch_mqprio.
+
+	  If unsure, say N.
+
 config NET_SCH_INGRESS
 	tristate "Ingress Qdisc"
 	depends on NET_CLS_ACT
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 960f5dba630..26ce681a2c6 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_NET_SCH_MULTIQ)	+= sch_multiq.o
 obj-$(CONFIG_NET_SCH_ATM)	+= sch_atm.o
 obj-$(CONFIG_NET_SCH_NETEM)	+= sch_netem.o
 obj-$(CONFIG_NET_SCH_DRR)	+= sch_drr.o
+obj-$(CONFIG_NET_SCH_MQPRIO)	+= sch_mqprio.o
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
 obj-$(CONFIG_NET_CLS_FW)	+= cls_fw.o
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 34dc598440a..723b27849a5 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -540,6 +540,7 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = {
 	.dump		=	pfifo_fast_dump,
 	.owner		=	THIS_MODULE,
 };
+EXPORT_SYMBOL(pfifo_fast_ops);
 
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  struct Qdisc_ops *ops)
@@ -674,6 +675,7 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 
 	return oqdisc;
 }
+EXPORT_SYMBOL(dev_graft_qdisc);
 
 static void attach_one_default_qdisc(struct net_device *dev,
 				     struct netdev_queue *dev_queue,
@@ -761,6 +763,7 @@ void dev_activate(struct net_device *dev)
 		dev_watchdog_up(dev);
 	}
 }
+EXPORT_SYMBOL(dev_activate);
 
 static void dev_deactivate_queue(struct net_device *dev,
 				 struct netdev_queue *dev_queue,
@@ -840,6 +843,7 @@ void dev_deactivate(struct net_device *dev)
 	list_add(&dev->unreg_list, &single);
 	dev_deactivate_many(&single);
 }
+EXPORT_SYMBOL(dev_deactivate);
 
 static void dev_init_scheduler_queue(struct net_device *dev,
 				     struct netdev_queue *dev_queue,
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
new file mode 100644
index 00000000000..8620c65f480
--- /dev/null
+++ b/net/sched/sch_mqprio.c
@@ -0,0 +1,417 @@
+/*
+ * net/sched/sch_mqprio.c
+ *
+ * Copyright (c) 2010 John Fastabend <john.r.fastabend@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <net/sch_generic.h>
+
+struct mqprio_sched {
+	struct Qdisc		**qdiscs;
+	int hw_owned;
+};
+
+static void mqprio_destroy(struct Qdisc *sch)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct mqprio_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_destroy(priv->qdiscs[ntx]);
+
+	if (priv->hw_owned && dev->netdev_ops->ndo_setup_tc)
+		dev->netdev_ops->ndo_setup_tc(dev, 0);
+	else
+		netdev_set_num_tc(dev, 0);
+
+	kfree(priv->qdiscs);
+}
+
+static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt)
+{
+	int i, j;
+
+	/* Verify num_tc is not out of max range */
+	if (qopt->num_tc > TC_MAX_QUEUE)
+		return -EINVAL;
+
+	/* Verify priority mapping uses valid tcs */
+	for (i = 0; i < TC_BITMASK + 1; i++) {
+		if (qopt->prio_tc_map[i] >= qopt->num_tc)
+			return -EINVAL;
+	}
+
+	/* net_device does not support requested operation */
+	if (qopt->hw && !dev->netdev_ops->ndo_setup_tc)
+		return -EINVAL;
+
+	/* if hw owned qcount and qoffset are taken from LLD so
+	 * no reason to verify them here
+	 */
+	if (qopt->hw)
+		return 0;
+
+	for (i = 0; i < qopt->num_tc; i++) {
+		unsigned int last = qopt->offset[i] + qopt->count[i];
+
+		/* Verify the queue count is in tx range being equal to the
+		 * real_num_tx_queues indicates the last queue is in use.
+		 */
+		if (qopt->offset[i] >= dev->real_num_tx_queues ||
+		    !qopt->count[i] ||
+		    last > dev->real_num_tx_queues)
+			return -EINVAL;
+
+		/* Verify that the offset and counts do not overlap */
+		for (j = i + 1; j < qopt->num_tc; j++) {
+			if (last > qopt->offset[j])
+				return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	struct netdev_queue *dev_queue;
+	struct Qdisc *qdisc;
+	int i, err = -EOPNOTSUPP;
+	struct tc_mqprio_qopt *qopt = NULL;
+
+	BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE);
+	BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK);
+
+	if (sch->parent != TC_H_ROOT)
+		return -EOPNOTSUPP;
+
+	if (!netif_is_multiqueue(dev))
+		return -EOPNOTSUPP;
+
+	if (nla_len(opt) < sizeof(*qopt))
+		return -EINVAL;
+
+	qopt = nla_data(opt);
+	if (mqprio_parse_opt(dev, qopt))
+		return -EINVAL;
+
+	/* pre-allocate qdisc, attachment can't fail */
+	priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]),
+			       GFP_KERNEL);
+	if (priv->qdiscs == NULL) {
+		err = -ENOMEM;
+		goto err;
+	}
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		dev_queue = netdev_get_tx_queue(dev, i);
+		qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops,
+					  TC_H_MAKE(TC_H_MAJ(sch->handle),
+						    TC_H_MIN(i + 1)));
+		if (qdisc == NULL) {
+			err = -ENOMEM;
+			goto err;
+		}
+		qdisc->flags |= TCQ_F_CAN_BYPASS;
+		priv->qdiscs[i] = qdisc;
+	}
+
+	/* If the mqprio options indicate that hardware should own
+	 * the queue mapping then run ndo_setup_tc otherwise use the
+	 * supplied and verified mapping
+	 */
+	if (qopt->hw) {
+		priv->hw_owned = 1;
+		err = dev->netdev_ops->ndo_setup_tc(dev, qopt->num_tc);
+		if (err)
+			goto err;
+	} else {
+		netdev_set_num_tc(dev, qopt->num_tc);
+		for (i = 0; i < qopt->num_tc; i++)
+			netdev_set_tc_queue(dev, i,
+					    qopt->count[i], qopt->offset[i]);
+	}
+
+	/* Always use supplied priority mappings */
+	for (i = 0; i < TC_BITMASK + 1; i++)
+		netdev_set_prio_tc_map(dev, i, qopt->prio_tc_map[i]);
+
+	sch->flags |= TCQ_F_MQROOT;
+	return 0;
+
+err:
+	mqprio_destroy(sch);
+	return err;
+}
+
+static void mqprio_attach(struct Qdisc *sch)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	struct Qdisc *qdisc;
+	unsigned int ntx;
+
+	/* Attach underlying qdisc */
+	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
+		qdisc = priv->qdiscs[ntx];
+		qdisc = dev_graft_qdisc(qdisc->dev_queue, qdisc);
+		if (qdisc)
+			qdisc_destroy(qdisc);
+	}
+	kfree(priv->qdiscs);
+	priv->qdiscs = NULL;
+}
+
+static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch,
+					     unsigned long cl)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned long ntx = cl - 1 - netdev_get_num_tc(dev);
+
+	if (ntx >= dev->num_tx_queues)
+		return NULL;
+	return netdev_get_tx_queue(dev, ntx);
+}
+
+static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
+		    struct Qdisc **old)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
+
+	if (!dev_queue)
+		return -EINVAL;
+
+	if (dev->flags & IFF_UP)
+		dev_deactivate(dev);
+
+	*old = dev_graft_qdisc(dev_queue, new);
+
+	if (dev->flags & IFF_UP)
+		dev_activate(dev);
+
+	return 0;
+}
+
+static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tc_mqprio_qopt opt;
+	struct Qdisc *qdisc;
+	unsigned int i;
+
+	sch->q.qlen = 0;
+	memset(&sch->bstats, 0, sizeof(sch->bstats));
+	memset(&sch->qstats, 0, sizeof(sch->qstats));
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		qdisc = netdev_get_tx_queue(dev, i)->qdisc;
+		spin_lock_bh(qdisc_lock(qdisc));
+		sch->q.qlen		+= qdisc->q.qlen;
+		sch->bstats.bytes	+= qdisc->bstats.bytes;
+		sch->bstats.packets	+= qdisc->bstats.packets;
+		sch->qstats.qlen	+= qdisc->qstats.qlen;
+		sch->qstats.backlog	+= qdisc->qstats.backlog;
+		sch->qstats.drops	+= qdisc->qstats.drops;
+		sch->qstats.requeues	+= qdisc->qstats.requeues;
+		sch->qstats.overlimits	+= qdisc->qstats.overlimits;
+		spin_unlock_bh(qdisc_lock(qdisc));
+	}
+
+	opt.num_tc = netdev_get_num_tc(dev);
+	memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map));
+	opt.hw = priv->hw_owned;
+
+	for (i = 0; i < netdev_get_num_tc(dev); i++) {
+		opt.count[i] = dev->tc_to_txq[i].count;
+		opt.offset[i] = dev->tc_to_txq[i].offset;
+	}
+
+	NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
+
+	return skb->len;
+nla_put_failure:
+	nlmsg_trim(skb, b);
+	return -1;
+}
+
+static struct Qdisc *mqprio_leaf(struct Qdisc *sch, unsigned long cl)
+{
+	struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
+
+	if (!dev_queue)
+		return NULL;
+
+	return dev_queue->qdisc_sleeping;
+}
+
+static unsigned long mqprio_get(struct Qdisc *sch, u32 classid)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned int ntx = TC_H_MIN(classid);
+
+	if (ntx > dev->num_tx_queues + netdev_get_num_tc(dev))
+		return 0;
+	return ntx;
+}
+
+static void mqprio_put(struct Qdisc *sch, unsigned long cl)
+{
+}
+
+static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl,
+			 struct sk_buff *skb, struct tcmsg *tcm)
+{
+	struct net_device *dev = qdisc_dev(sch);
+
+	if (cl <= netdev_get_num_tc(dev)) {
+		tcm->tcm_parent = TC_H_ROOT;
+		tcm->tcm_info = 0;
+	} else {
+		int i;
+		struct netdev_queue *dev_queue;
+
+		dev_queue = mqprio_queue_get(sch, cl);
+		tcm->tcm_parent = 0;
+		for (i = 0; i < netdev_get_num_tc(dev); i++) {
+			struct netdev_tc_txq tc = dev->tc_to_txq[i];
+			int q_idx = cl - netdev_get_num_tc(dev);
+
+			if (q_idx > tc.offset &&
+			    q_idx <= tc.offset + tc.count) {
+				tcm->tcm_parent =
+					TC_H_MAKE(TC_H_MAJ(sch->handle),
+						  TC_H_MIN(i + 1));
+				break;
+			}
+		}
+		tcm->tcm_info = dev_queue->qdisc_sleeping->handle;
+	}
+	tcm->tcm_handle |= TC_H_MIN(cl);
+	return 0;
+}
+
+static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
+			       struct gnet_dump *d)
+{
+	struct net_device *dev = qdisc_dev(sch);
+
+	if (cl <= netdev_get_num_tc(dev)) {
+		int i;
+		struct Qdisc *qdisc;
+		struct gnet_stats_queue qstats = {0};
+		struct gnet_stats_basic_packed bstats = {0};
+		struct netdev_tc_txq tc = dev->tc_to_txq[cl - 1];
+
+		/* Drop lock here it will be reclaimed before touching
+		 * statistics this is required because the d->lock we
+		 * hold here is the look on dev_queue->qdisc_sleeping
+		 * also acquired below.
+		 */
+		spin_unlock_bh(d->lock);
+
+		for (i = tc.offset; i < tc.offset + tc.count; i++) {
+			qdisc = netdev_get_tx_queue(dev, i)->qdisc;
+			spin_lock_bh(qdisc_lock(qdisc));
+			bstats.bytes      += qdisc->bstats.bytes;
+			bstats.packets    += qdisc->bstats.packets;
+			qstats.qlen       += qdisc->qstats.qlen;
+			qstats.backlog    += qdisc->qstats.backlog;
+			qstats.drops      += qdisc->qstats.drops;
+			qstats.requeues   += qdisc->qstats.requeues;
+			qstats.overlimits += qdisc->qstats.overlimits;
+			spin_unlock_bh(qdisc_lock(qdisc));
+		}
+		/* Reclaim root sleeping lock before completing stats */
+		spin_lock_bh(d->lock);
+		if (gnet_stats_copy_basic(d, &bstats) < 0 ||
+		    gnet_stats_copy_queue(d, &qstats) < 0)
+			return -1;
+	} else {
+		struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
+
+		sch = dev_queue->qdisc_sleeping;
+		sch->qstats.qlen = sch->q.qlen;
+		if (gnet_stats_copy_basic(d, &sch->bstats) < 0 ||
+		    gnet_stats_copy_queue(d, &sch->qstats) < 0)
+			return -1;
+	}
+	return 0;
+}
+
+static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned long ntx;
+
+	if (arg->stop)
+		return;
+
+	/* Walk hierarchy with a virtual class per tc */
+	arg->count = arg->skip;
+	for (ntx = arg->skip;
+	     ntx < dev->num_tx_queues + netdev_get_num_tc(dev);
+	     ntx++) {
+		if (arg->fn(sch, ntx + 1, arg) < 0) {
+			arg->stop = 1;
+			break;
+		}
+		arg->count++;
+	}
+}
+
+static const struct Qdisc_class_ops mqprio_class_ops = {
+	.graft		= mqprio_graft,
+	.leaf		= mqprio_leaf,
+	.get		= mqprio_get,
+	.put		= mqprio_put,
+	.walk		= mqprio_walk,
+	.dump		= mqprio_dump_class,
+	.dump_stats	= mqprio_dump_class_stats,
+};
+
+struct Qdisc_ops mqprio_qdisc_ops __read_mostly = {
+	.cl_ops		= &mqprio_class_ops,
+	.id		= "mqprio",
+	.priv_size	= sizeof(struct mqprio_sched),
+	.init		= mqprio_init,
+	.destroy	= mqprio_destroy,
+	.attach		= mqprio_attach,
+	.dump		= mqprio_dump,
+	.owner		= THIS_MODULE,
+};
+
+static int __init mqprio_module_init(void)
+{
+	return register_qdisc(&mqprio_qdisc_ops);
+}
+
+static void __exit mqprio_module_exit(void)
+{
+	unregister_qdisc(&mqprio_qdisc_ops);
+}
+
+module_init(mqprio_module_init);
+module_exit(mqprio_module_exit);
+
+MODULE_LICENSE("GPL");