From: Oleg Nesterov <oleg@tv-sign.ru>
To: Gautham R Shenoy <ego@in.ibm.com>
Cc: akpm@osdl.org, paulmck@us.ibm.com, mingo@elte.hu,
vatsa@in.ibm.com, dipankar@in.ibm.com,
venkatesh.pallipadi@intel.com, linux-kernel@vger.kernel.org,
rjw@sisk.pl
Subject: Re: [RFC PATCH(Experimental) 2/4] Revert changes to workqueue.c
Date: Wed, 14 Feb 2007 23:09:04 +0300 [thread overview]
Message-ID: <20070214200904.GB301@tv-sign.ru> (raw)
In-Reply-To: <20070214144305.GB19789@in.ibm.com>
On 02/14, Gautham R Shenoy wrote:
>
> This patch reverts all the recent workqueue hacks added to make it
> hotplug safe.
In my opinion these hacks are cleanups :)
Ok. If we use freezer then yes, we can remove cpu_populated_map and just
use for_each_online_cpu(). This is easy and good.
What else you don't like? Why do you want to remove cwq_should_stop() and
restore an ugly (ugly for workqueue.c) kthread_stop/kthread_should_stop() ?
We can restore take_over_works(), although I don't see why this is needed.
But cwq_should_stop() will just work regardless, why do you want to add
this "wait_to_die" ... well, hack :)
> -static DEFINE_MUTEX(workqueue_mutex);
> +static DEFINE_SPINLOCK(workqueue_lock);
No. We can't do this. see below.
> struct workqueue_struct *__create_workqueue(const char *name,
> int singlethread, int freezeable)
> {
> @@ -798,17 +756,20 @@ struct workqueue_struct *__create_workqu
> INIT_LIST_HEAD(&wq->list);
> cwq = init_cpu_workqueue(wq, singlethread_cpu);
> err = create_workqueue_thread(cwq, singlethread_cpu);
> + if (!err)
> + wake_up_process(cwq->thread);
> } else {
> - mutex_lock(&workqueue_mutex);
> + spin_lock(&workqueue_lock);
> list_add(&wq->list, &workqueues);
> -
> - for_each_possible_cpu(cpu) {
> + spin_unlock(&workqueue_lock);
> + for_each_online_cpu(cpu) {
> cwq = init_cpu_workqueue(wq, cpu);
> - if (err || !(cpu_online(cpu) || cpu == embryonic_cpu))
> - continue;
> err = create_workqueue_thread(cwq, cpu);
> + if (err)
> + break;
No, we can't break. We are going to execute destroy_workqueue(), it will
iterate over all cwqs.
> +static void take_over_work(struct workqueue_struct *wq, unsigned int cpu)
> +{
> + struct cpu_workqueue_struct *cwq = per_cpu_ptr(wq->cpu_wq, cpu);
> + struct list_head list;
> + struct work_struct *work;
> +
> + spin_lock_irq(&cwq->lock);
> + list_replace_init(&cwq->worklist, &list);
> +
> + while (!list_empty(&list)) {
> + work = list_entry(list.next,struct work_struct,entry);
> + list_del(&work->entry);
> + __queue_work(per_cpu_ptr(wq->cpu_wq, smp_processor_id()), work);
> + }
> +
> + spin_unlock_irq(&cwq->lock);
> +}
I think this is unneeded complication, but ok, should work.
> static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
> unsigned long action,
> void *hcpu)
> + case CPU_UP_CANCELED:
> + list_for_each_entry(wq, &workqueues, list) {
> + if (!per_cpu_ptr(wq->cpu_wq, hotcpu)->thread)
> + continue;
> + /* Unbind so it can run. */
> + kthread_bind(per_cpu_ptr(wq->cpu_wq, hotcpu)->thread,
> + any_online_cpu(cpu_online_map));
> + cleanup_workqueue_thread(wq, hotcpu);
> }
> + break;
> +
> + case CPU_DEAD:
> + list_for_each_entry(wq, &workqueues, list)
> + take_over_work(wq, hotcpu);
> + break;
> +
> + case CPU_DEAD_KILL_THREADS:
> + list_for_each_entry(wq, &workqueues, list)
> + cleanup_workqueue_thread(wq, hotcpu);
> }
Both CPU_UP_CANCELED and CPU_DEAD_KILL_THREADS runs after thaw_processes(),
this means that workqueue_cpu_callback() is racy wrt create/destroy workqueue,
we should take the mutex, and it can't be spinlock_t.
Oleg.
next prev parent reply other threads:[~2007-02-14 20:09 UTC|newest]
Thread overview: 92+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-02-14 14:40 [RFC PATCH(Experimental) 0/4] Freezer based Cpu-hotplug Gautham R Shenoy
2007-02-14 14:42 ` [RFC PATCH(Experimental) 1/4] freezer-cpu-hotplug core Gautham R Shenoy
2007-02-14 14:43 ` [RFC PATCH(Experimental) 2/4] Revert changes to workqueue.c Gautham R Shenoy
2007-02-14 14:43 ` [RFC PATCH(Experimental) 3/4] Revert changes to sched.c and slab.c Gautham R Shenoy
2007-02-14 14:44 ` [RFC PATCH(Experimental) 4/4] Rip out lock_cpu_hotplug from linux Gautham R Shenoy
2007-02-14 14:59 ` [RFC PATCH(Experimental) 2/4] Revert changes to workqueue.c Srivatsa Vaddagiri
2007-02-14 15:24 ` Srivatsa Vaddagiri
2007-02-14 20:23 ` Oleg Nesterov
2007-02-14 20:09 ` Oleg Nesterov [this message]
2007-02-16 5:26 ` Srivatsa Vaddagiri
2007-02-16 15:33 ` Oleg Nesterov
2007-02-16 16:47 ` Srivatsa Vaddagiri
2007-02-16 18:45 ` Oleg Nesterov
2007-02-16 23:59 ` Oleg Nesterov
2007-02-17 2:29 ` Srivatsa Vaddagiri
2007-02-17 21:59 ` Oleg Nesterov
2007-02-20 15:12 ` Srivatsa Vaddagiri
2007-02-20 20:09 ` Oleg Nesterov
2007-02-21 6:29 ` Srivatsa Vaddagiri
2007-02-21 14:30 ` Oleg Nesterov
2007-02-21 14:37 ` Gautham R Shenoy
2007-02-21 15:53 ` Srivatsa Vaddagiri
2007-02-14 15:31 ` [RFC PATCH(Experimental) 1/4] freezer-cpu-hotplug core Srivatsa Vaddagiri
2007-02-14 19:47 ` Oleg Nesterov
2007-02-16 6:48 ` Srivatsa Vaddagiri
2007-02-16 15:47 ` Oleg Nesterov
2007-02-14 20:22 ` Oleg Nesterov
2007-02-16 7:16 ` Srivatsa Vaddagiri
2007-02-16 8:12 ` Srivatsa Vaddagiri
2007-02-16 9:29 ` Rafael J. Wysocki
2007-02-16 9:59 ` Srivatsa Vaddagiri
2007-02-16 11:06 ` Rafael J. Wysocki
2007-02-16 19:46 ` Oleg Nesterov
2007-02-17 2:31 ` Srivatsa Vaddagiri
2007-02-17 5:32 ` Gautham R Shenoy
2007-02-17 11:19 ` Gautham R Shenoy
2007-02-16 16:06 ` Oleg Nesterov
2007-02-14 21:43 ` [RFC PATCH(Experimental) 0/4] Freezer based Cpu-hotplug Rafael J. Wysocki
2007-02-15 6:34 ` Gautham R Shenoy
2007-02-15 8:09 ` Rafael J. Wysocki
2007-02-15 12:20 ` Gautham R Shenoy
2007-02-15 13:31 ` Rafael J. Wysocki
2007-02-15 14:25 ` Gautham R Shenoy
2007-02-17 11:24 ` Rafael J. Wysocki
2007-02-17 21:34 ` Oleg Nesterov
2007-02-17 22:24 ` Rafael J. Wysocki
2007-02-17 23:42 ` Oleg Nesterov
2007-02-17 23:47 ` Oleg Nesterov
2007-02-18 10:43 ` Rafael J. Wysocki
2007-02-18 11:31 ` Oleg Nesterov
2007-02-18 12:14 ` Rafael J. Wysocki
2007-02-18 14:52 ` freezer problems Oleg Nesterov
2007-02-18 15:14 ` Rafael J. Wysocki
2007-02-18 16:19 ` Oleg Nesterov
2007-02-18 18:14 ` Rafael J. Wysocki
2007-02-18 18:56 ` Rafael J. Wysocki
2007-02-18 22:01 ` Oleg Nesterov
2007-02-18 23:19 ` Rafael J. Wysocki
2007-02-19 20:23 ` Oleg Nesterov
2007-02-19 21:21 ` Rafael J. Wysocki
2007-02-19 22:41 ` Oleg Nesterov
2007-02-19 23:35 ` Rafael J. Wysocki
2007-02-20 0:12 ` Oleg Nesterov
2007-02-20 0:32 ` Rafael J. Wysocki
2007-02-20 0:50 ` Oleg Nesterov
2007-02-20 18:28 ` Rafael J. Wysocki
2007-02-20 18:29 ` Rafael J. Wysocki
2007-02-21 18:14 ` Paul E. McKenney
2007-02-21 18:13 ` Rafael J. Wysocki
2007-02-21 18:27 ` Paul E. McKenney
2007-02-21 20:03 ` Oleg Nesterov
2007-02-21 20:47 ` Rafael J. Wysocki
2007-02-21 21:06 ` Paul E. McKenney
2007-02-21 23:10 ` Rafael J. Wysocki
2007-02-22 10:47 ` Oleg Nesterov
2007-02-22 11:33 ` Oleg Nesterov
2007-02-22 17:03 ` Rafael J. Wysocki
2007-02-22 17:44 ` Oleg Nesterov
2007-02-22 21:56 ` Rafael J. Wysocki
2007-02-23 18:15 ` Oleg Nesterov
2007-02-23 3:02 ` Gautham R Shenoy
2007-02-18 15:09 ` [RFC PATCH(Experimental) 0/4] Freezer based Cpu-hotplug Rafael J. Wysocki
2007-02-18 16:11 ` Oleg Nesterov
2007-02-18 18:51 ` Rafael J. Wysocki
2007-02-18 10:32 ` Rafael J. Wysocki
2007-02-18 11:32 ` Oleg Nesterov
2007-02-18 12:12 ` Rafael J. Wysocki
2007-02-18 15:06 ` Oleg Nesterov
2007-02-18 12:56 ` Pavel Machek
2007-02-21 14:52 ` Gautham R Shenoy
2007-02-21 19:42 ` Pavel Machek
[not found] ` <200702231041.17136.rjw@sisk.pl>
[not found] ` <20070223100817.GA10973@in.ibm.com>
[not found] ` <200702231115.00718.rjw@sisk.pl>
[not found] ` <20070223104723.GB10973@in.ibm.com>
[not found] ` <20070223110201.GC10973@in.ibm.com>
2007-02-23 19:03 ` freezer problems Gautham R Shenoy
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=20070214200904.GB301@tv-sign.ru \
--to=oleg@tv-sign.ru \
--cc=akpm@osdl.org \
--cc=dipankar@in.ibm.com \
--cc=ego@in.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=paulmck@us.ibm.com \
--cc=rjw@sisk.pl \
--cc=vatsa@in.ibm.com \
--cc=venkatesh.pallipadi@intel.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).