* spin_is_locked() broken for uniprocessor?
@ 2009-08-18 22:09 Kumar Gala
2009-08-18 22:24 ` Thomas Gleixner
2009-08-19 9:38 ` David Howells
0 siblings, 2 replies; 8+ messages in thread
From: Kumar Gala @ 2009-08-18 22:09 UTC (permalink / raw)
To: Linux-Kernel List; +Cc: Thomas Gleixner, linuxppc-dev list
I just want to validate that what I'm seeing (for UP, non-debug
features):
spin_is_locked() is defined as:
include/linux/spinlock.h:#define spin_is_locked(lock)
__raw_spin_is_locked(&(lock)->raw_lock)
for UP that should get us:
include/linux/spinlock_up.h:#define __raw_spin_is_locked(lock) ((void)
(lock), 0)
which implies to me that spin_is_locked() will always return false.
Is this expected behavior.
- k
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: spin_is_locked() broken for uniprocessor?
2009-08-18 22:09 spin_is_locked() broken for uniprocessor? Kumar Gala
@ 2009-08-18 22:24 ` Thomas Gleixner
2009-08-19 9:38 ` David Howells
1 sibling, 0 replies; 8+ messages in thread
From: Thomas Gleixner @ 2009-08-18 22:24 UTC (permalink / raw)
To: Kumar Gala
Cc: Peter Zijlstra, Linux-Kernel List, Steven Rostedt,
linuxppc-dev list, Ingo Molnar
On Tue, 18 Aug 2009, Kumar Gala wrote:
> I just want to validate that what I'm seeing (for UP, non-debug features):
>
> spin_is_locked() is defined as:
>
> include/linux/spinlock.h:#define spin_is_locked(lock)
> __raw_spin_is_locked(&(lock)->raw_lock)
>
> for UP that should get us:
>
> include/linux/spinlock_up.h:#define __raw_spin_is_locked(lock) ((void)(lock),
> 0)
>
> which implies to me that spin_is_locked() will always return false. Is this
> expected behavior.
That's wrong. spin_is_locked should always return true on UP.
Thanks,
tglx
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: spin_is_locked() broken for uniprocessor?
2009-08-18 22:09 spin_is_locked() broken for uniprocessor? Kumar Gala
2009-08-18 22:24 ` Thomas Gleixner
@ 2009-08-19 9:38 ` David Howells
2009-08-19 9:41 ` Peter Zijlstra
2009-08-19 10:53 ` Alan Cox
1 sibling, 2 replies; 8+ messages in thread
From: David Howells @ 2009-08-19 9:38 UTC (permalink / raw)
To: Thomas Gleixner
Cc: Peter Zijlstra, Steven Rostedt, Linux-Kernel List,
linuxppc-dev list, Ingo Molnar
Thomas Gleixner <tglx@linutronix.de> wrote:
> > which implies to me that spin_is_locked() will always return false. Is this
> > expected behavior.
>
> That's wrong. spin_is_locked should always return true on UP.
Surely it's not that simple? Maybe spin_is_lock() should be undefined on UP.
David
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: spin_is_locked() broken for uniprocessor?
2009-08-19 9:38 ` David Howells
@ 2009-08-19 9:41 ` Peter Zijlstra
2009-08-27 9:32 ` Benjamin Herrenschmidt
2009-08-19 10:53 ` Alan Cox
1 sibling, 1 reply; 8+ messages in thread
From: Peter Zijlstra @ 2009-08-19 9:41 UTC (permalink / raw)
To: David Howells
Cc: Steven Rostedt, Linux-Kernel List, linuxppc-dev list,
Thomas Gleixner, Ingo Molnar
On Wed, 2009-08-19 at 10:38 +0100, David Howells wrote:
> Thomas Gleixner <tglx@linutronix.de> wrote:
>
> > > which implies to me that spin_is_locked() will always return false. Is this
> > > expected behavior.
> >
> > That's wrong. spin_is_locked should always return true on UP.
>
> Surely it's not that simple? Maybe spin_is_lock() should be undefined on UP.
#define spin_is_locked(l) panic()
should sort things out quickly ;-)
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: spin_is_locked() broken for uniprocessor?
2009-08-19 9:38 ` David Howells
2009-08-19 9:41 ` Peter Zijlstra
@ 2009-08-19 10:53 ` Alan Cox
2009-08-19 11:16 ` Leon Woestenberg
1 sibling, 1 reply; 8+ messages in thread
From: Alan Cox @ 2009-08-19 10:53 UTC (permalink / raw)
To: David Howells
Cc: Peter Zijlstra, Steven Rostedt, Linux-Kernel List,
linuxppc-dev list, Thomas Gleixner, Ingo Molnar
On Wed, 19 Aug 2009 10:38:06 +0100
David Howells <dhowells@redhat.com> wrote:
> Thomas Gleixner <tglx@linutronix.de> wrote:
>
> > > which implies to me that spin_is_locked() will always return false. Is this
> > > expected behavior.
> >
> > That's wrong. spin_is_locked should always return true on UP.
>
> Surely it's not that simple? Maybe spin_is_lock() should be undefined on UP.
That would lead to a lot of
#ifdef CONFIG_SMP
#endif
in drivers because there is driver code that uses spin_is_locked() in
fairly sensible fashion when dealing with locking.
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: spin_is_locked() broken for uniprocessor?
2009-08-19 10:53 ` Alan Cox
@ 2009-08-19 11:16 ` Leon Woestenberg
2009-08-19 11:23 ` Peter Zijlstra
0 siblings, 1 reply; 8+ messages in thread
From: Leon Woestenberg @ 2009-08-19 11:16 UTC (permalink / raw)
To: Alan Cox
Cc: Peter Zijlstra, Steven Rostedt, Linux-Kernel List,
linuxppc-dev list, Thomas Gleixner, Ingo Molnar
Hello,
On Wed, Aug 19, 2009 at 12:53 PM, Alan Cox<alan@lxorguk.ukuu.org.uk> wrote:
> On Wed, 19 Aug 2009 10:38:06 +0100
>
> in drivers because there is driver code that uses spin_is_locked() in
> fairly sensible fashion when dealing with locking.
>
One use is to measure lock contention hits on a particular spin lock.
However I wonder if there are tracing capabilities to measure lock
contention on a particular lock?
Currently I have inserted code much like this to get a feeling on the
contention:
this_cpu = get_cpu();
put_cpu();
contention = spin_is_locked(&lock);
spin_lock*(&lock);
if (contention) {
/* spin lock was contended, prev_cpu, this_cpu */
/* no hard guarantee, as we had a possible race inbetween
is_locked() and lock(), but works for driver/irq spin lock */
}
/* critical section */
prev_cpu = this_cpu;
spin_unlock*(&lock);
Regards,
--
Leon
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: spin_is_locked() broken for uniprocessor?
2009-08-19 11:16 ` Leon Woestenberg
@ 2009-08-19 11:23 ` Peter Zijlstra
0 siblings, 0 replies; 8+ messages in thread
From: Peter Zijlstra @ 2009-08-19 11:23 UTC (permalink / raw)
To: Leon Woestenberg
Cc: Steven Rostedt, Linux-Kernel List, linuxppc-dev list,
Thomas Gleixner, Ingo Molnar, Alan Cox
On Wed, 2009-08-19 at 13:16 +0200, Leon Woestenberg wrote:
> Hello,
>
> On Wed, Aug 19, 2009 at 12:53 PM, Alan Cox<alan@lxorguk.ukuu.org.uk> wrote:
> > On Wed, 19 Aug 2009 10:38:06 +0100
> >
> > in drivers because there is driver code that uses spin_is_locked() in
> > fairly sensible fashion when dealing with locking.
> >
> One use is to measure lock contention hits on a particular spin lock.
>
>
> However I wonder if there are tracing capabilities to measure lock
> contention on a particular lock?
lock_stat no good for you?
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: spin_is_locked() broken for uniprocessor?
2009-08-19 9:41 ` Peter Zijlstra
@ 2009-08-27 9:32 ` Benjamin Herrenschmidt
0 siblings, 0 replies; 8+ messages in thread
From: Benjamin Herrenschmidt @ 2009-08-27 9:32 UTC (permalink / raw)
To: Peter Zijlstra
Cc: Linux-Kernel List, Steven Rostedt, linuxppc-dev list,
Thomas Gleixner, Ingo Molnar
On Wed, 2009-08-19 at 11:41 +0200, Peter Zijlstra wrote:
> > > > which implies to me that spin_is_locked() will always return
> false. Is this
> > > > expected behavior.
> > >
> > > That's wrong. spin_is_locked should always return true on UP.
> >
> > Surely it's not that simple? Maybe spin_is_lock() should be
> undefined on UP.
>
> #define spin_is_locked(l) panic()
>
> should sort things out quickly ;-)
Not defining it would sort things out even faster and avoid nasty case
of system panic'ing when a module is loaded :-)
Cheers,
Ben.
^ permalink raw reply [flat|nested] 8+ messages in thread
end of thread, other threads:[~2009-08-27 9:33 UTC | newest]
Thread overview: 8+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2009-08-18 22:09 spin_is_locked() broken for uniprocessor? Kumar Gala
2009-08-18 22:24 ` Thomas Gleixner
2009-08-19 9:38 ` David Howells
2009-08-19 9:41 ` Peter Zijlstra
2009-08-27 9:32 ` Benjamin Herrenschmidt
2009-08-19 10:53 ` Alan Cox
2009-08-19 11:16 ` Leon Woestenberg
2009-08-19 11:23 ` Peter Zijlstra
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).