Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper

From: Paul E. McKenney
Date: Fri May 03 2013 - 12:31:15 EST


On Fri, May 03, 2013 at 10:52:36AM +0300, Julian Anastasov wrote:
>
> Hello,
>
> On Thu, 2 May 2013, Paul E. McKenney wrote:
>
> > mainline, and missed the one that you added. Revisiting that, a
> > question:
> >
> > > +#ifdef CONFIG_PREEMPT_RCU
> > > +#define PREEMPT_RCU_OFFSET 1
> >
> > Does this really want to be "1" instead of PREEMPT_OFFSET?
>
> In this case when CONFIG_PREEMPT_RCU is enabled
> we (RCU) do not touch the preempt counters. Instead, the units
> are accounted in current->rcu_read_lock_nesting:
>
> #define rcu_preempt_depth() (current->rcu_read_lock_nesting)
>
> __rcu_read_lock:
> current->rcu_read_lock_nesting++;
>
> and the path is __might_sleep -> preempt_count_equals ->
> rcu_preempt_depth
>
> For now both places do not use PREEMPT_OFFSET:
>
> - #define inc_preempt_count() add_preempt_count(1)
> - __rcu_read_lock: current->rcu_read_lock_nesting++;
>
> so, ... it does not matter much for me. In short,
> the trick is in preempt_count_equals() where preempt_offset
> is a combination of preempt count and RCU preempt depth:
>
> #ifdef CONFIG_PREEMPT_RCU
> #define PREEMPT_RCU_OFFSET (0 /* preempt */ + 1 /* RCU */)
> #else
> #define PREEMPT_RCU_OFFSET (PREEMPT_CHECK_OFFSET + 0 /* RCU */)
> #endif
>
> Let me know for your preference about this definition...

OK, after getting some sleep, I might have located the root cause of
my confusion yesterday.

The key point is that I don't understand why we cannot get the effect
we are looking for with the following in sched.h (or wherever):

static inline int cond_resched_rcu(void)
{
#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
rcu_read_unlock();
cond_resched();
rcu_read_lock();
#endif
}

This adds absolutely no overhead in non-debug builds of CONFIG_PREEMPT_RCU,
does the checking in debug builds, and allows voluntary preemption in
!CONFIG_PREEMPT_RCU builds. CONFIG_PROVE_RCU builds will check for an
(illegal) outer rcu_read_lock() in CONFIG_PREEMPT_RCU builds, and you
will get "scheduling while atomic" in response to an outer rcu_read_lock()
in !CONFIG_PREEMPT_RCU builds.

It also seems to me a lot simpler.

Does this work, or am I still missing something?

Thanx, Paul

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