From: Eric Dumazet <eric.dumazet@gmail.com>
To: "David S. Miller" <davem@davemloft.net>,
Herbert Xu <herbert@gondor.apana.org.au>,
Stephen Hemminger <shemminger@vyatta.com>
Cc: Linux Netdev List <netdev@vger.kernel.org>
Subject: PATCH net-next-2.6] linkwatch: linkwatch_forget_dev() to speedup device dismantle
Date: Mon, 16 Nov 2009 22:50:48 +0100 [thread overview]
Message-ID: <4B01C938.8000705@gmail.com> (raw)
In-Reply-To: <4B019381.2010509@gmail.com>
time ip link del eth3.103 ; time ip link del eth3.104 ; time ip link del eth3.105
real 0m0.266s
user 0m0.000s
sys 0m0.001s
real 0m0.770s
user 0m0.000s
sys 0m0.000s
real 0m1.022s
user 0m0.000s
sys 0m0.000s
One problem of current schem in vlan dismantle phase is the
holding of device done by following chain :
vlan_dev_stop() ->
netif_carrier_off(dev) ->
linkwatch_fire_event(dev) ->
dev_hold() ...
And __linkwatch_run_queue() runs up to one second later...
A generic fix to this problem is to add a linkwatch_forget_dev() method
to unlink the device from the list of watched devices.
dev->link_watch_next becomes dev->link_watch_list (and use a bit more memory),
to be able to unlink device in O(1).
After patch :
time ip link del eth3.103 ; time ip link del eth3.104 ; time ip link del eth3.105
real 0m0.024s
user 0m0.000s
sys 0m0.000s
real 0m0.032s
user 0m0.000s
sys 0m0.001s
real 0m0.033s
user 0m0.000s
sys 0m0.000s
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
include/linux/netdevice.h | 3 +-
net/core/dev.c | 3 ++
net/core/link_watch.c | 42 ++++++++++++++++++++++++------------
3 files changed, 33 insertions(+), 15 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7043f85..4e25730 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -896,7 +896,7 @@ struct net_device {
/* device index hash chain */
struct hlist_node index_hlist;
- struct net_device *link_watch_next;
+ struct list_head link_watch_list;
/* register/unregister state machine */
enum { NETREG_UNINITIALIZED=0,
@@ -1600,6 +1600,7 @@ static inline void dev_hold(struct net_device *dev)
*/
extern void linkwatch_fire_event(struct net_device *dev);
+extern void linkwatch_forget_dev(struct net_device *dev);
/**
* netif_carrier_ok - test if carrier present
diff --git a/net/core/dev.c b/net/core/dev.c
index 4b24d79..649de02 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5066,6 +5066,8 @@ static void netdev_wait_allrefs(struct net_device *dev)
{
unsigned long rebroadcast_time, warning_time;
+ linkwatch_forget_dev(dev);
+
rebroadcast_time = warning_time = jiffies;
while (atomic_read(&dev->refcnt) != 0) {
if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
@@ -5280,6 +5282,7 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
+ INIT_LIST_HEAD(&dev->link_watch_list);
dev->priv_flags = IFF_XMIT_DST_RELEASE;
setup(dev);
strcpy(dev->name, name);
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index bf8f7af..05fe273 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -35,7 +35,7 @@ static unsigned long linkwatch_nextevent;
static void linkwatch_event(struct work_struct *dummy);
static DECLARE_DELAYED_WORK(linkwatch_work, linkwatch_event);
-static struct net_device *lweventlist;
+static LIST_HEAD(lweventlist);
static DEFINE_SPINLOCK(lweventlist_lock);
static unsigned char default_operstate(const struct net_device *dev)
@@ -89,8 +89,10 @@ static void linkwatch_add_event(struct net_device *dev)
unsigned long flags;
spin_lock_irqsave(&lweventlist_lock, flags);
- dev->link_watch_next = lweventlist;
- lweventlist = dev;
+ if (list_empty(&dev->link_watch_list)) {
+ list_add_tail(&dev->link_watch_list, &lweventlist);
+ dev_hold(dev);
+ }
spin_unlock_irqrestore(&lweventlist_lock, flags);
}
@@ -135,7 +137,8 @@ static void linkwatch_schedule_work(int urgent)
static void __linkwatch_run_queue(int urgent_only)
{
- struct net_device *next;
+ struct net_device *dev;
+ LIST_HEAD(wrk);
/*
* Limit the number of linkwatch events to one
@@ -153,19 +156,18 @@ static void __linkwatch_run_queue(int urgent_only)
clear_bit(LW_URGENT, &linkwatch_flags);
spin_lock_irq(&lweventlist_lock);
- next = lweventlist;
- lweventlist = NULL;
- spin_unlock_irq(&lweventlist_lock);
+ list_splice_init(&lweventlist, &wrk);
- while (next) {
- struct net_device *dev = next;
+ while (!list_empty(&wrk)) {
- next = dev->link_watch_next;
+ dev = list_first_entry(&wrk, struct net_device, link_watch_list);
+ list_del_init(&dev->link_watch_list);
if (urgent_only && !linkwatch_urgent_event(dev)) {
- linkwatch_add_event(dev);
+ list_add_tail(&dev->link_watch_list, &lweventlist);
continue;
}
+ spin_unlock_irq(&lweventlist_lock);
/*
* Make sure the above read is complete since it can be
@@ -189,10 +191,24 @@ static void __linkwatch_run_queue(int urgent_only)
}
dev_put(dev);
+ spin_lock_irq(&lweventlist_lock);
}
- if (lweventlist)
+ if (!list_empty(&lweventlist))
linkwatch_schedule_work(0);
+ spin_unlock_irq(&lweventlist_lock);
+}
+
+void linkwatch_forget_dev(struct net_device *dev)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&lweventlist_lock, flags);
+ if (!list_empty(&dev->link_watch_list)) {
+ list_del_init(&dev->link_watch_list);
+ dev_put(dev);
+ }
+ spin_unlock_irqrestore(&lweventlist_lock, flags);
}
@@ -216,8 +232,6 @@ void linkwatch_fire_event(struct net_device *dev)
bool urgent = linkwatch_urgent_event(dev);
if (!test_and_set_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) {
- dev_hold(dev);
-
linkwatch_add_event(dev);
} else if (!urgent)
return;
next prev parent reply other threads:[~2009-11-16 21:50 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-11-16 18:01 [RFC] dev->refcnt long term holder Eric Dumazet
2009-11-16 19:02 ` Stephen Hemminger
2009-11-16 19:54 ` Eric Dumazet
2009-11-17 8:30 ` David Miller
2009-11-17 8:37 ` Herbert Xu
2009-11-17 17:58 ` Stephen Hemminger
2009-11-17 19:18 ` David Miller
2009-11-16 21:50 ` Eric Dumazet [this message]
2009-11-16 22:39 ` PATCH net-next-2.6] linkwatch: linkwatch_forget_dev() to speedup device dismantle Stephen Hemminger
2009-11-17 12:26 ` David Miller
2009-11-17 12:31 ` Herbert Xu
2009-11-17 15:59 ` Eric Dumazet
2009-11-18 13:05 ` 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=4B01C938.8000705@gmail.com \
--to=eric.dumazet@gmail.com \
--cc=davem@davemloft.net \
--cc=herbert@gondor.apana.org.au \
--cc=netdev@vger.kernel.org \
--cc=shemminger@vyatta.com \
/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).