From: Patrick McHardy <kaber@trash.net>
To: netdev@vger.kernel.org
Cc: Patrick McHardy <kaber@trash.net>
Subject: net_sched 05/07: reintroduce dev->qdisc for use by sch_api
Date: Fri, 4 Sep 2009 18:41:18 +0200 (MEST) [thread overview]
Message-ID: <20090904164117.27300.78712.sendpatchset@x2.localnet> (raw)
In-Reply-To: <20090904164111.27300.29929.sendpatchset@x2.localnet>
commit 57a016350a3d85dc351ab90ce91e4dc49ce2183a
Author: Patrick McHardy <kaber@trash.net>
Date: Fri Sep 4 16:12:45 2009 +0200
net_sched: reintroduce dev->qdisc for use by sch_api
Currently the multiqueue integration with the qdisc API suffers from
a few problems:
- with multiple queues, all root qdiscs use the same handle. This means
they can't be exposed to userspace in a backwards compatible fashion.
- all API operations always refer to queue number 0. Newly created
qdiscs are automatically shared between all queues, its not possible
to address individual queues or restore multiqueue behaviour once a
shared qdisc has been attached.
- Dumps only contain the root qdisc of queue 0, in case of non-shared
qdiscs this means the statistics are incomplete.
This patch reintroduces dev->qdisc, which points to the (single) root qdisc
from userspace's point of view. Currently it either points to the first
(non-shared) default qdisc, or a qdisc shared between all queues. The
following patches will introduce a classful dummy qdisc, which will be used
as root qdisc and contain the per-queue qdiscs as children.
Signed-off-by: Patrick McHardy <kaber@trash.net>
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 121cbad..a44118b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -832,6 +832,9 @@ struct net_device
/* Number of TX queues currently active in device */
unsigned int real_num_tx_queues;
+ /* root qdisc from userspace point of view */
+ struct Qdisc *qdisc;
+
unsigned long tx_queue_len; /* Max frames per queue allowed */
spinlock_t tx_global_lock;
/*
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index bbcba2a..eb42873 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -606,7 +606,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
int type, u32 pid, u32 seq, u32 change,
unsigned int flags)
{
- struct netdev_queue *txq;
struct ifinfomsg *ifm;
struct nlmsghdr *nlh;
const struct net_device_stats *stats;
@@ -637,9 +636,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
if (dev->master)
NLA_PUT_U32(skb, IFLA_MASTER, dev->master->ifindex);
- txq = netdev_get_tx_queue(dev, 0);
- if (txq->qdisc_sleeping)
- NLA_PUT_STRING(skb, IFLA_QDISC, txq->qdisc_sleeping->ops->id);
+ if (dev->qdisc)
+ NLA_PUT_STRING(skb, IFLA_QDISC, dev->qdisc->ops->id);
if (dev->ifalias)
NLA_PUT_STRING(skb, IFLA_IFALIAS, dev->ifalias);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index eaa8f43..8cbc66f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -168,8 +168,7 @@ replay:
/* Find qdisc */
if (!parent) {
- struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, 0);
- q = dev_queue->qdisc_sleeping;
+ q = dev->qdisc;
parent = q->handle;
} else {
q = qdisc_lookup(dev, TC_H_MAJ(t->tcm_parent));
@@ -408,7 +407,6 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n,
static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
- struct netdev_queue *dev_queue;
int t;
int s_t;
struct net_device *dev;
@@ -427,9 +425,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
if ((dev = dev_get_by_index(&init_net, tcm->tcm_ifindex)) == NULL)
return skb->len;
- dev_queue = netdev_get_tx_queue(dev, 0);
if (!tcm->tcm_parent)
- q = dev_queue->qdisc_sleeping;
+ q = dev->qdisc;
else
q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
if (!q)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 166fcca..8aa9a0c 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -207,7 +207,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
static void qdisc_list_add(struct Qdisc *q)
{
if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
- list_add_tail(&q->list, &qdisc_root_sleeping(q)->list);
+ list_add_tail(&q->list, &qdisc_dev(q)->qdisc->list);
}
void qdisc_list_del(struct Qdisc *q)
@@ -219,17 +219,11 @@ EXPORT_SYMBOL(qdisc_list_del);
struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle)
{
- unsigned int i;
struct Qdisc *q;
- for (i = 0; i < dev->num_tx_queues; i++) {
- struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
- struct Qdisc *txq_root = txq->qdisc_sleeping;
-
- q = qdisc_match_from_root(txq_root, handle);
- if (q)
- goto out;
- }
+ q = qdisc_match_from_root(dev->qdisc, handle);
+ if (q)
+ goto out;
q = qdisc_match_from_root(dev->rx_queue.qdisc_sleeping, handle);
out:
@@ -720,9 +714,14 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
if (new && i > 0)
atomic_inc(&new->refcnt);
- notify_and_destroy(skb, n, classid, old, new);
+ qdisc_destroy(old);
}
+ notify_and_destroy(skb, n, classid, dev->qdisc, new);
+ if (new)
+ atomic_inc(&new->refcnt);
+ dev->qdisc = new ? : &noop_qdisc;
+
if (dev->flags & IFF_UP)
dev_activate(dev);
} else {
@@ -974,9 +973,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
q = dev->rx_queue.qdisc_sleeping;
}
} else {
- struct netdev_queue *dev_queue;
- dev_queue = netdev_get_tx_queue(dev, 0);
- q = dev_queue->qdisc_sleeping;
+ q = dev->qdisc;
}
if (!q)
return -ENOENT;
@@ -1044,9 +1041,7 @@ replay:
q = dev->rx_queue.qdisc_sleeping;
}
} else {
- struct netdev_queue *dev_queue;
- dev_queue = netdev_get_tx_queue(dev, 0);
- q = dev_queue->qdisc_sleeping;
+ q = dev->qdisc;
}
/* It may be default qdisc, ignore it */
@@ -1291,8 +1286,7 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
s_q_idx = 0;
q_idx = 0;
- dev_queue = netdev_get_tx_queue(dev, 0);
- if (tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, &q_idx, s_q_idx) < 0)
+ if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx) < 0)
goto done;
dev_queue = &dev->rx_queue;
@@ -1323,7 +1317,6 @@ done:
static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
{
struct net *net = sock_net(skb->sk);
- struct netdev_queue *dev_queue;
struct tcmsg *tcm = NLMSG_DATA(n);
struct nlattr *tca[TCA_MAX + 1];
struct net_device *dev;
@@ -1361,7 +1354,6 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
/* Step 1. Determine qdisc handle X:0 */
- dev_queue = netdev_get_tx_queue(dev, 0);
if (pid != TC_H_ROOT) {
u32 qid1 = TC_H_MAJ(pid);
@@ -1372,7 +1364,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
} else if (qid1) {
qid = qid1;
} else if (qid == 0)
- qid = dev_queue->qdisc_sleeping->handle;
+ qid = dev->qdisc->handle;
/* Now qid is genuine qdisc handle consistent
both with parent and child.
@@ -1383,7 +1375,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
pid = TC_H_MAKE(qid, pid);
} else {
if (qid == 0)
- qid = dev_queue->qdisc_sleeping->handle;
+ qid = dev->qdisc->handle;
}
/* OK. Locate qdisc */
@@ -1588,8 +1580,7 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb)
s_t = cb->args[0];
t = 0;
- dev_queue = netdev_get_tx_queue(dev, 0);
- if (tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, &t, s_t) < 0)
+ if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t) < 0)
goto done;
dev_queue = &dev->rx_queue;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 6128e6f..a91f079 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -623,19 +623,6 @@ void qdisc_destroy(struct Qdisc *qdisc)
}
EXPORT_SYMBOL(qdisc_destroy);
-static bool dev_all_qdisc_sleeping_noop(struct net_device *dev)
-{
- unsigned int i;
-
- for (i = 0; i < dev->num_tx_queues; i++) {
- struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
-
- if (txq->qdisc_sleeping != &noop_qdisc)
- return false;
- }
- return true;
-}
-
static void attach_one_default_qdisc(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_unused)
@@ -677,6 +664,7 @@ static void transition_one_qdisc(struct net_device *dev,
void dev_activate(struct net_device *dev)
{
+ struct netdev_queue *txq;
int need_watchdog;
/* No queueing discipline is attached to device;
@@ -685,9 +673,14 @@ void dev_activate(struct net_device *dev)
virtual interfaces
*/
- if (dev_all_qdisc_sleeping_noop(dev))
+ if (dev->qdisc == &noop_qdisc) {
netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
+ txq = netdev_get_tx_queue(dev, 0);
+ dev->qdisc = txq->qdisc_sleeping;
+ atomic_inc(&dev->qdisc->refcnt);
+ }
+
if (!netif_carrier_ok(dev))
/* Delay activation until next carrier-on event */
return;
@@ -777,6 +770,7 @@ static void dev_init_scheduler_queue(struct net_device *dev,
void dev_init_scheduler(struct net_device *dev)
{
+ dev->qdisc = &noop_qdisc;
netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc);
dev_init_scheduler_queue(dev, &dev->rx_queue, &noop_qdisc);
@@ -802,5 +796,8 @@ void dev_shutdown(struct net_device *dev)
{
netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
shutdown_scheduler_queue(dev, &dev->rx_queue, &noop_qdisc);
+ qdisc_destroy(dev->qdisc);
+ dev->qdisc = &noop_qdisc;
+
WARN_ON(timer_pending(&dev->watchdog_timer));
}
next prev parent reply other threads:[~2009-09-04 16:41 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-09-04 16:41 net_sched 00/07: classful multiqueue dummy scheduler Patrick McHardy
2009-09-04 16:41 ` net_sched 01/07: fix class grafting errno codes Patrick McHardy
2009-09-04 16:41 ` net_sched 02/07: make cls_ops->tcf_chain() optional Patrick McHardy
2009-09-05 8:13 ` Jarek Poplawski
2009-09-05 11:57 ` Jarek Poplawski
2009-09-05 12:32 ` Jarek Poplawski
2009-09-05 17:03 ` Patrick McHardy
2009-09-06 9:06 ` David Miller
2009-09-04 16:41 ` net_sched 03/07: make cls_ops->change and cls_ops->delete optional Patrick McHardy
2009-09-04 16:41 ` net_sched 04/07: remove some unnecessary checks in classful schedulers Patrick McHardy
2009-09-04 16:41 ` Patrick McHardy [this message]
2009-09-06 18:57 ` net_sched 05/07: reintroduce dev->qdisc for use by sch_api Jarek Poplawski
2009-09-07 13:16 ` Patrick McHardy
2009-09-07 16:49 ` Jarek Poplawski
2009-09-04 16:41 ` net_sched 06/07: move dev_graft_qdisc() to sch_generic.c Patrick McHardy
2009-09-04 16:41 ` net_sched 07/07: add classful multiqueue dummy scheduler Patrick McHardy
2009-09-06 20:04 ` Jarek Poplawski
2009-09-07 13:27 ` Patrick McHardy
2009-09-07 18:22 ` Jarek Poplawski
2009-09-07 19:24 ` Jarek Poplawski
2009-09-07 19:49 ` Eric Dumazet
2009-09-09 16:02 ` Patrick McHardy
2009-09-09 19:52 ` Jarek Poplawski
2009-09-10 11:28 ` Patrick McHardy
2009-09-11 21:38 ` Jarek Poplawski
2009-09-11 22:10 ` David Miller
2009-09-11 22:21 ` Jarek Poplawski
2009-09-11 22:27 ` David Miller
2009-09-09 16:01 ` Patrick McHardy
2009-09-04 16:42 ` net_sched 00/07: " Patrick McHardy
2009-09-07 8:50 ` David Miller
2009-09-07 9:46 ` Jarek Poplawski
2009-09-07 13:00 ` Eric Dumazet
2009-09-07 13:29 ` Patrick McHardy
2009-09-07 14:23 ` Patrick McHardy
2009-09-07 17:21 ` Eric Dumazet
2009-09-07 17:28 ` Patrick McHardy
2009-09-07 17:30 ` Eric Dumazet
2009-09-07 17:33 ` Patrick McHardy
2009-09-07 17:38 ` Eric Dumazet
2009-09-07 17:46 ` Patrick McHardy
2009-09-08 9:31 ` David Miller
2009-09-08 15:53 ` Patrick McHardy
2009-09-05 7:27 ` David Miller
2009-09-05 17:02 ` Patrick McHardy
2009-09-06 9:01 ` David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20090904164117.27300.78712.sendpatchset@x2.localnet \
--to=kaber@trash.net \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).