UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/net/sched/sch_mqprio.c

427 lines
10 KiB
C
Raw Normal View History

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>
2011-01-17 16:06:09 +08:00
/*
* 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>
net: Fix files explicitly needing to include module.h With calls to modular infrastructure, these files really needs the full module.h header. Call it out so some of the cleanups of implicit and unrequired includes elsewhere can be cleaned up. Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2011-05-27 21:12:25 +08:00
#include <linux/module.h>
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>
2011-01-17 16:06:09 +08:00
#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;
sch_mqprio: Always set num_tc to 0 in mqprio_destroy() All the cleanup code in mqprio_destroy() is currently conditional on priv->qdiscs being non-null, but that condition should only apply to the per-queue qdisc cleanup. We should always set the number of traffic classes back to 0 here. Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
2011-02-15 03:02:23 +08:00
if (priv->qdiscs) {
for (ntx = 0;
ntx < dev->num_tx_queues && priv->qdiscs[ntx];
ntx++)
qdisc_destroy(priv->qdiscs[ntx]);
kfree(priv->qdiscs);
}
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>
2011-01-17 16:06:09 +08:00
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);
}
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;
mqprio: Avoid panic if no options are provided Userspace may not provide TCA_OPTIONS, in fact tc currently does so not do so if no arguments are specified on the command line. Return EINVAL instead of panicing. Signed-off-by: Thomas Graf <tgraf@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-12-22 10:05:07 +08:00
if (!opt || nla_len(opt) < sizeof(*qopt))
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>
2011-01-17 16:06:09 +08:00
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: allow setting default queuing discipline By default, the pfifo_fast queue discipline has been used by default for all devices. But we have better choices now. This patch allow setting the default queueing discipline with sysctl. This allows easy use of better queueing disciplines on all devices without having to use tc qdisc scripts. It is intended to allow an easy path for distributions to make fq_codel or sfq the default qdisc. This patch also makes pfifo_fast more of a first class qdisc, since it is now possible to manually override the default and explicitly use pfifo_fast. The behavior for systems who do not use the sysctl is unchanged, they still get pfifo_fast Also removes leftover random # in sysctl net core. Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-28 07:19:08 +08:00
qdisc = qdisc_create_dflt(dev_queue, default_qdisc_ops,
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>
2011-01-17 16:06:09 +08:00
TC_H_MAKE(TC_H_MAJ(sch->handle),
TC_H_MIN(i + 1)));
if (qdisc == NULL) {
err = -ENOMEM;
goto err;
}
priv->qdiscs[i] = qdisc;
pkt_sched: avoid requeues if possible With BQL being deployed, we can more likely have following behavior : We dequeue a packet from qdisc in dequeue_skb(), then we realize target tx queue is in XOFF state in sch_direct_xmit(), and we have to hold the skb into gso_skb for later. This shows in stats (tc -s qdisc dev eth0) as requeues. Problem of these requeues is that high priority packets can not be dequeued as long as this (possibly low prio and big TSO packet) is not removed from gso_skb. At 1Gbps speed, a full size TSO packet is 500 us of extra latency. In some cases, we know that all packets dequeued from a qdisc are for a particular and known txq : - If device is non multi queue - For all MQ/MQPRIO slave qdiscs This patch introduces a new qdisc flag, TCQ_F_ONETXQUEUE to mark this capability, so that dequeue_skb() is allowed to dequeue a packet only if the associated txq is not stopped. This indeed reduce latencies for high prio packets (or improve fairness with sfq/fq_codel), and almost remove qdisc 'requeues'. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-12-11 23:54:33 +08:00
qdisc->flags |= TCQ_F_ONETXQUEUE;
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>
2011-01-17 16:06:09 +08:00
}
/* 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);
pkt_sched: give visibility to mq slave qdiscs Commit 6da7c8fcbcbd ("qdisc: allow setting default queuing discipline") added the ability to change default qdisc from pfifo_fast to say fq But as most modern ethernet devices are multiqueue, we cant really see all the statistics from "tc -s qdisc show", as the default root qdisc is mq. This patch adds the calls to qdisc_list_add() to mq and mqprio Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-06 03:12:02 +08:00
struct Qdisc *qdisc, *old;
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>
2011-01-17 16:06:09 +08:00
unsigned int ntx;
/* Attach underlying qdisc */
for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
qdisc = priv->qdiscs[ntx];
pkt_sched: give visibility to mq slave qdiscs Commit 6da7c8fcbcbd ("qdisc: allow setting default queuing discipline") added the ability to change default qdisc from pfifo_fast to say fq But as most modern ethernet devices are multiqueue, we cant really see all the statistics from "tc -s qdisc show", as the default root qdisc is mq. This patch adds the calls to qdisc_list_add() to mq and mqprio Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-06 03:12:02 +08:00
old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
if (old)
qdisc_destroy(old);
if (ntx < dev->real_num_tx_queues)
qdisc_list_add(qdisc);
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>
2011-01-17 16:06:09 +08:00
}
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);
pkt_sched: avoid requeues if possible With BQL being deployed, we can more likely have following behavior : We dequeue a packet from qdisc in dequeue_skb(), then we realize target tx queue is in XOFF state in sch_direct_xmit(), and we have to hold the skb into gso_skb for later. This shows in stats (tc -s qdisc dev eth0) as requeues. Problem of these requeues is that high priority packets can not be dequeued as long as this (possibly low prio and big TSO packet) is not removed from gso_skb. At 1Gbps speed, a full size TSO packet is 500 us of extra latency. In some cases, we know that all packets dequeued from a qdisc are for a particular and known txq : - If device is non multi queue - For all MQ/MQPRIO slave qdiscs This patch introduces a new qdisc flag, TCQ_F_ONETXQUEUE to mark this capability, so that dequeue_skb() is allowed to dequeue a packet only if the associated txq is not stopped. This indeed reduce latencies for high prio packets (or improve fairness with sfq/fq_codel), and almost remove qdisc 'requeues'. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-12-11 23:54:33 +08:00
if (new)
new->flags |= TCQ_F_ONETXQUEUE;
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>
2011-01-17 16:06:09 +08:00
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);
net_sched: sch_mqprio: dont leak kernel memory mqprio_dump() should make sure all fields of struct tc_mqprio_qopt are initialized. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-26 15:21:57 +08:00
struct tc_mqprio_qopt opt = { 0 };
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>
2011-01-17 16:06:09 +08:00
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;
}
pkt_sched: Stop using NLA_PUT*(). These macros contain a hidden goto, and are thus extremely error prone and make code hard to audit. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-29 17:11:39 +08:00
if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
goto nla_put_failure;
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>
2011-01-17 16:06:09 +08:00
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,
mqprio: cleanups * make qdisc_ops local * add sparse annotation about expected unlock/unlock in dump_class_stats * fix indentation Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-23 17:06:51 +08:00
struct gnet_dump *d)
__releases(d->lock)
__acquires(d->lock)
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>
2011-01-17 16:06:09 +08:00
{
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,
};
mqprio: cleanups * make qdisc_ops local * add sparse annotation about expected unlock/unlock in dump_class_stats * fix indentation Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-23 17:06:51 +08:00
static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = {
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>
2011-01-17 16:06:09 +08:00
.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");