Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1276751

Re: [PATCH v3 09/22] kthread: Allow to cancel kthread work

From Linus Torvalds <torvalds@linux-foundation.org>
Newsgroups linux.kernel
Subject Re: [PATCH v3 09/22] kthread: Allow to cancel kthread work
Date 2015-11-24 21:30 +0100
Message-ID <qysnT-4vl-9@gated-at.bofh.it> (permalink)
References <qwaYa-3sP-5@gated-at.bofh.it> <qwb7R-3wi-15@gated-at.bofh.it> <qy8fw-89o-19@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On Mon, Nov 23, 2015 at 2:58 PM, Tejun Heo <tj@kernel.org> wrote:
>
> And the timer can do (ignoring the multiple worker support, do we even
> need that?)
>
>         while (!trylock(worker)) {
>                 if (work->canceling)
>                         return;
>                 cpu_relax();
>         }

No no no!

People, you need to learn that code like the above is *not*
acceptable. It's busy-looping on a spinlock, and constantly trying to
*write* to the spinlock.

It will literally crater performance on a multi-socket SMP system if
it ever triggers. We're talking 10x slowdowns, and absolutely
unacceptable cache coherency traffic.

These kinds of loops absolutely *have* to have the read-only part. The
"cpu_relax()" above needs to be a loop that just tests the lock state
by *reading* it, so the cpu_relax() needs to be replaced with
something like

        while (spin_is_locked(lock)) cpu_relax();

instead (possibly just "spin_unlock_wait()" - but the explicit loop
might be worth it if you then want to check the "canceling" flag
independently of the lock state too).

In general, it's very dangerous to try to cook up your own locking
rules. People *always* get it wrong.

                      Linus
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Back to linux.kernel | Previous | NextPrevious in thread | Next in thread | Find similar | Unroll thread


Thread

[PATCH v3 00/22] kthread: Use kthread worker API more widely Petr Mladek <pmladek@suse.com> - 2015-11-18 14:30 +0100
  [PATCH v3 22/22] thermal/intel_powerclamp: Convert the kthread to kthread worker API Petr Mladek <pmladek@suse.com> - 2015-11-18 14:30 +0100
  [PATCH v3 06/22] kthread: Add destroy_kthread_worker() Petr Mladek <pmladek@suse.com> - 2015-11-18 14:30 +0100
  [PATCH v3 20/22] memstick/r592: convert r592_io kthread into kthread worker API Petr Mladek <pmladek@suse.com> - 2015-11-18 14:30 +0100
  [PATCH v3 18/22] IB/fmr_pool: Convert the cleanup thread into kthread worker API Petr Mladek <pmladek@suse.com> - 2015-11-18 14:30 +0100
    Re: [PATCH v3 18/22] IB/fmr_pool: Convert the cleanup thread into  kthread worker API Yuval Shaia <yuval.shaia@oracle.com> - 2015-11-19 13:50 +0100
  [PATCH v3 10/22] kthread: Allow to modify delayed kthread work Petr Mladek <pmladek@suse.com> - 2015-11-18 14:30 +0100
  [PATCH v3 11/22] kthread: Better support freezable kthread workers Petr Mladek <pmladek@suse.com> - 2015-11-18 14:30 +0100
  [PATCH v3 08/22] kthread: Initial support for delayed kthread work Petr Mladek <pmladek@suse.com> - 2015-11-18 14:40 +0100
  [PATCH v3 12/22] kthread: Use try_lock_kthread_work() in flush_kthread_work() Petr Mladek <pmladek@suse.com> - 2015-11-18 14:40 +0100
  [PATCH v3 05/22] kthread: Add drain_kthread_worker() Petr Mladek <pmladek@suse.com> - 2015-11-18 14:40 +0100
  [PATCH v3 13/22] mm/huge_page: Convert khugepaged() into kthread worker API Petr Mladek <pmladek@suse.com> - 2015-11-18 14:40 +0100
  [PATCH v3 09/22] kthread: Allow to cancel kthread work Petr Mladek <pmladek@suse.com> - 2015-11-18 14:40 +0100
    Re: [PATCH v3 09/22] kthread: Allow to cancel kthread work Tejun Heo <tj@kernel.org> - 2015-11-24 00:00 +0100
      Re: [PATCH v3 09/22] kthread: Allow to cancel kthread work Petr Mladek <pmladek@suse.com> - 2015-11-24 11:30 +0100
      Re: [PATCH v3 09/22] kthread: Allow to cancel kthread work Tejun Heo <tj@kernel.org> - 2015-11-24 21:30 +0100
        Re: [PATCH v3 09/22] kthread: Allow to cancel kthread work Linus Torvalds <torvalds@linux-foundation.org> - 2015-11-24 21:50 +0100
      Re: [PATCH v3 09/22] kthread: Allow to cancel kthread work Linus Torvalds <torvalds@linux-foundation.org> - 2015-11-24 21:30 +0100
  [PATCH v3 04/22] kthread: Add create_kthread_worker*() Petr Mladek <pmladek@suse.com> - 2015-11-18 14:40 +0100
  Re: [PATCH v3 00/22] kthread: Use kthread worker API more widely "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2015-11-18 15:30 +0100

csiph-web