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>

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

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

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

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,