* Thoughts on this RCU idle entry/exit patch?
@ 2013-10-07 15:39 Paul E. McKenney
2013-10-08 20:34 ` Frederic Weisbecker
0 siblings, 1 reply; 5+ messages in thread
From: Paul E. McKenney @ 2013-10-07 15:39 UTC (permalink / raw)
To: fweisbec; +Cc: linux-kernel
Hello, Frederic!
The following patch seems to me to be a good idea to better handle
task nesting. Any reason why it would be a bad thing?
Thanx, Paul
------------------------------------------------------------------------
rcu: Allow task-level idle entry/exit nesting
The current task-level idle entry/exit code forces an entry/exit on
each call, regardless of the nesting level. This commit therefore
properly accounts for nesting.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 106f7f5cdd1d..f0be20886617 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -411,11 +411,12 @@ static void rcu_eqs_enter(bool user)
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
- if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
+ if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
rdtp->dynticks_nesting = 0;
- else
+ rcu_eqs_enter_common(rdtp, oldval, user);
+ } else {
rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
- rcu_eqs_enter_common(rdtp, oldval, user);
+ }
}
/**
@@ -533,11 +534,12 @@ static void rcu_eqs_exit(bool user)
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE(oldval < 0);
- if (oldval & DYNTICK_TASK_NEST_MASK)
+ if (oldval & DYNTICK_TASK_NEST_MASK) {
rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
- else
+ } else {
rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
- rcu_eqs_exit_common(rdtp, oldval, user);
+ rcu_eqs_exit_common(rdtp, oldval, user);
+ }
}
/**
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: Thoughts on this RCU idle entry/exit patch?
2013-10-07 15:39 Thoughts on this RCU idle entry/exit patch? Paul E. McKenney
@ 2013-10-08 20:34 ` Frederic Weisbecker
2013-10-08 21:12 ` Paul E. McKenney
0 siblings, 1 reply; 5+ messages in thread
From: Frederic Weisbecker @ 2013-10-08 20:34 UTC (permalink / raw)
To: Paul E. McKenney; +Cc: linux-kernel
On Mon, Oct 07, 2013 at 08:39:55AM -0700, Paul E. McKenney wrote:
> Hello, Frederic!
>
> The following patch seems to me to be a good idea to better handle
> task nesting. Any reason why it would be a bad thing?
>
> Thanx, Paul
>
> ------------------------------------------------------------------------
>
> rcu: Allow task-level idle entry/exit nesting
>
> The current task-level idle entry/exit code forces an entry/exit on
> each call, regardless of the nesting level. This commit therefore
> properly accounts for nesting.
>
> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Looks good. In fact, the current code is even buggy because two nesting rcu_user_eqs()
as in:
rcu_eqs_enter()
rcu_eqs_enter()
rcu_eqs_exit()
rcu_eqs_exit()
would result in rdtp->dynticks wrong increment, right?
So that's even a bug fix. I wonder if it's a regression. That said rcu_eqs_enter_common()
should warn on such miscount, so may be these functions actually don't nest in practice
or you would have received such warnings.
So I wonder, do we want to continue to allow this nesting? I remember that DYNTICK_TASK_NEST_*
stuff is there to protects against non finishing interrupts on some archs (I also remember that
this, or at least a practical scenario for this, was hard to really define though :o)
But then wouldn't it involve other kind of scenario like this?
rcu_irq_enter()
rcu_eqs_enter()
rcu_eqs_exit()
...
Anyway, that's just random thougths on further simplifications, in any case, this
patch looks good.
Thanks.
>
> diff --git a/kernel/rcutree.c b/kernel/rcutree.c
> index 106f7f5cdd1d..f0be20886617 100644
> --- a/kernel/rcutree.c
> +++ b/kernel/rcutree.c
> @@ -411,11 +411,12 @@ static void rcu_eqs_enter(bool user)
> rdtp = this_cpu_ptr(&rcu_dynticks);
> oldval = rdtp->dynticks_nesting;
> WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
> - if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
> + if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
> rdtp->dynticks_nesting = 0;
> - else
> + rcu_eqs_enter_common(rdtp, oldval, user);
> + } else {
> rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
> - rcu_eqs_enter_common(rdtp, oldval, user);
> + }
> }
>
> /**
> @@ -533,11 +534,12 @@ static void rcu_eqs_exit(bool user)
> rdtp = this_cpu_ptr(&rcu_dynticks);
> oldval = rdtp->dynticks_nesting;
> WARN_ON_ONCE(oldval < 0);
> - if (oldval & DYNTICK_TASK_NEST_MASK)
> + if (oldval & DYNTICK_TASK_NEST_MASK) {
> rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
> - else
> + } else {
> rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
> - rcu_eqs_exit_common(rdtp, oldval, user);
> + rcu_eqs_exit_common(rdtp, oldval, user);
> + }
> }
>
> /**
>
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: Thoughts on this RCU idle entry/exit patch?
2013-10-08 20:34 ` Frederic Weisbecker
@ 2013-10-08 21:12 ` Paul E. McKenney
2013-10-09 14:56 ` Frederic Weisbecker
0 siblings, 1 reply; 5+ messages in thread
From: Paul E. McKenney @ 2013-10-08 21:12 UTC (permalink / raw)
To: Frederic Weisbecker; +Cc: linux-kernel
On Tue, Oct 08, 2013 at 10:34:28PM +0200, Frederic Weisbecker wrote:
> On Mon, Oct 07, 2013 at 08:39:55AM -0700, Paul E. McKenney wrote:
> > Hello, Frederic!
> >
> > The following patch seems to me to be a good idea to better handle
> > task nesting. Any reason why it would be a bad thing?
> >
> > Thanx, Paul
> >
> > ------------------------------------------------------------------------
> >
> > rcu: Allow task-level idle entry/exit nesting
> >
> > The current task-level idle entry/exit code forces an entry/exit on
> > each call, regardless of the nesting level. This commit therefore
> > properly accounts for nesting.
> >
> > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
>
> Looks good. In fact, the current code is even buggy because two nesting rcu_user_eqs()
> as in:
>
> rcu_eqs_enter()
> rcu_eqs_enter()
> rcu_eqs_exit()
> rcu_eqs_exit()
>
> would result in rdtp->dynticks wrong increment, right?
That was my thought, but I figured I should run it past you in case
there was some subtle tie-in to NO_HZ_FULL.
> So that's even a bug fix. I wonder if it's a regression. That said rcu_eqs_enter_common()
> should warn on such miscount, so may be these functions actually don't nest in practice
> or you would have received such warnings.
And the lack of such warnings was another reason I felt the need to check
with you.
> So I wonder, do we want to continue to allow this nesting? I remember that DYNTICK_TASK_NEST_*
> stuff is there to protects against non finishing interrupts on some archs (I also remember that
> this, or at least a practical scenario for this, was hard to really define though :o)
> But then wouldn't it involve other kind of scenario like this?
>
> rcu_irq_enter()
> rcu_eqs_enter()
> rcu_eqs_exit()
> ...
>
> Anyway, that's just random thougths on further simplifications, in any case, this
> patch looks good.
Yep, if no task-level nesting is ever required, things could be a bit
simpler. I would be a bit slow about making such a change, though.
After all, the need to deal with Hotel California interrupts means that
handling nesting isn't that big of a deal comparatively. ;-)
May I add your Reviewed-by?
Thanx, Paul
> Thanks.
>
> >
> > diff --git a/kernel/rcutree.c b/kernel/rcutree.c
> > index 106f7f5cdd1d..f0be20886617 100644
> > --- a/kernel/rcutree.c
> > +++ b/kernel/rcutree.c
> > @@ -411,11 +411,12 @@ static void rcu_eqs_enter(bool user)
> > rdtp = this_cpu_ptr(&rcu_dynticks);
> > oldval = rdtp->dynticks_nesting;
> > WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
> > - if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
> > + if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
> > rdtp->dynticks_nesting = 0;
> > - else
> > + rcu_eqs_enter_common(rdtp, oldval, user);
> > + } else {
> > rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
> > - rcu_eqs_enter_common(rdtp, oldval, user);
> > + }
> > }
> >
> > /**
> > @@ -533,11 +534,12 @@ static void rcu_eqs_exit(bool user)
> > rdtp = this_cpu_ptr(&rcu_dynticks);
> > oldval = rdtp->dynticks_nesting;
> > WARN_ON_ONCE(oldval < 0);
> > - if (oldval & DYNTICK_TASK_NEST_MASK)
> > + if (oldval & DYNTICK_TASK_NEST_MASK) {
> > rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
> > - else
> > + } else {
> > rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
> > - rcu_eqs_exit_common(rdtp, oldval, user);
> > + rcu_eqs_exit_common(rdtp, oldval, user);
> > + }
> > }
> >
> > /**
> >
>
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: Thoughts on this RCU idle entry/exit patch?
2013-10-08 21:12 ` Paul E. McKenney
@ 2013-10-09 14:56 ` Frederic Weisbecker
2013-10-09 15:08 ` Paul E. McKenney
0 siblings, 1 reply; 5+ messages in thread
From: Frederic Weisbecker @ 2013-10-09 14:56 UTC (permalink / raw)
To: Paul E. McKenney; +Cc: linux-kernel
On Tue, Oct 08, 2013 at 02:12:18PM -0700, Paul E. McKenney wrote:
> On Tue, Oct 08, 2013 at 10:34:28PM +0200, Frederic Weisbecker wrote:
> > So I wonder, do we want to continue to allow this nesting? I remember that DYNTICK_TASK_NEST_*
> > stuff is there to protects against non finishing interrupts on some archs (I also remember that
> > this, or at least a practical scenario for this, was hard to really define though :o)
> > But then wouldn't it involve other kind of scenario like this?
> >
> > rcu_irq_enter()
> > rcu_eqs_enter()
> > rcu_eqs_exit()
> > ...
> >
> > Anyway, that's just random thougths on further simplifications, in any case, this
> > patch looks good.
>
> Yep, if no task-level nesting is ever required, things could be a bit
> simpler. I would be a bit slow about making such a change, though.
> After all, the need to deal with Hotel California interrupts means that
> handling nesting isn't that big of a deal comparatively. ;-)
Right, well ideally it would be even best to fix the corner case(s) if there aren't
that many of them. I mean calling rcu_irq_exit() from the end of those half interrupts
I guess. It would make it much simpler than this complicated nesting handled on the core code.
But I agree there is a bit of unknown out there, so yeah lets be prudent :)
> May I add your Reviewed-by?
Sure, thanks!
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: Thoughts on this RCU idle entry/exit patch?
2013-10-09 14:56 ` Frederic Weisbecker
@ 2013-10-09 15:08 ` Paul E. McKenney
0 siblings, 0 replies; 5+ messages in thread
From: Paul E. McKenney @ 2013-10-09 15:08 UTC (permalink / raw)
To: Frederic Weisbecker; +Cc: linux-kernel
On Wed, Oct 09, 2013 at 04:56:19PM +0200, Frederic Weisbecker wrote:
> On Tue, Oct 08, 2013 at 02:12:18PM -0700, Paul E. McKenney wrote:
> > On Tue, Oct 08, 2013 at 10:34:28PM +0200, Frederic Weisbecker wrote:
> > > So I wonder, do we want to continue to allow this nesting? I remember that DYNTICK_TASK_NEST_*
> > > stuff is there to protects against non finishing interrupts on some archs (I also remember that
> > > this, or at least a practical scenario for this, was hard to really define though :o)
> > > But then wouldn't it involve other kind of scenario like this?
> > >
> > > rcu_irq_enter()
> > > rcu_eqs_enter()
> > > rcu_eqs_exit()
> > > ...
> > >
> > > Anyway, that's just random thougths on further simplifications, in any case, this
> > > patch looks good.
> >
> > Yep, if no task-level nesting is ever required, things could be a bit
> > simpler. I would be a bit slow about making such a change, though.
> > After all, the need to deal with Hotel California interrupts means that
> > handling nesting isn't that big of a deal comparatively. ;-)
>
> Right, well ideally it would be even best to fix the corner case(s) if there aren't
> that many of them. I mean calling rcu_irq_exit() from the end of those half interrupts
> I guess. It would make it much simpler than this complicated nesting handled on the core code.
> But I agree there is a bit of unknown out there, so yeah lets be prudent :)
>
> > May I add your Reviewed-by?
>
> Sure, thanks!
Done!
Thanx, Paul
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2013-10-09 15:08 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2013-10-07 15:39 Thoughts on this RCU idle entry/exit patch? Paul E. McKenney
2013-10-08 20:34 ` Frederic Weisbecker
2013-10-08 21:12 ` Paul E. McKenney
2013-10-09 14:56 ` Frederic Weisbecker
2013-10-09 15:08 ` Paul E. McKenney
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).