Re: [PATCH 37/41] rcu: New rcu_user_enter() and rcu_user_exit() APIs

["Paul E. McKenney" <paulmck@linux.vnet.ibm.com>]

On Tue, May 01, 2012 at 01:55:11AM +0200, Frederic Weisbecker wrote:
> These two APIs are provided to help the implementation
> of an adaptive tickless kernel (cf: nohz cpusets). We need
> to run into RCU extended quiescent state when we are in
> userland so that a tickless CPU is not involved in the
> global RCU state machine and can shutdown its tick safely.
> 
> These APIs are called from syscall and exception entry/exit
> points and can't be called from interrupt.
> 
> They are essentially the same than rcu_idle_enter() and
> rcu_idle_exit() minus the checks that ensure the CPU is
> running the idle task.

This looks reasonably sane.  There are a few nits like missing comment
headers for functions and the need for tracing, but I can handle that
when I pull it in.  I am happy to do that pretty much any time, but not
before the API stabilizes.  ;-)

So let me know when it is ready for -rcu.

							Thanx, Paul

> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
> Cc: Alessio Igor Bogani <abogani@kernel.org>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Avi Kivity <avi@redhat.com>
> Cc: Chris Metcalf <cmetcalf@tilera.com>
> Cc: Christoph Lameter <cl@linux.com>
> Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
> Cc: Geoff Levand <geoff@infradead.org>
> Cc: Gilad Ben Yossef <gilad@benyossef.com>
> Cc: Hakan Akkan <hakanakkan@gmail.com>
> Cc: Ingo Molnar <mingo@kernel.org>
> Cc: Kevin Hilman <khilman@ti.com>
> Cc: Max Krasnyansky <maxk@qualcomm.com>
> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Stephen Hemminger <shemminger@vyatta.com>
> Cc: Steven Rostedt <rostedt@goodmis.org>
> Cc: Sven-Thorsten Dietrich <thebigcorporation@gmail.com>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> ---
>  include/linux/rcupdate.h |    5 ++
>  kernel/rcutree.c         |  107 ++++++++++++++++++++++++++++++++-------------
>  2 files changed, 81 insertions(+), 31 deletions(-)
> 
> diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
> index e06639e..6539290 100644
> --- a/include/linux/rcupdate.h
> +++ b/include/linux/rcupdate.h
> @@ -191,6 +191,11 @@ extern void rcu_idle_exit(void);
>  extern void rcu_irq_enter(void);
>  extern void rcu_irq_exit(void);
> 
> +#ifdef CONFIG_CPUSETS_NO_HZ
> +void rcu_user_enter(void);
> +void rcu_user_exit(void);
> +#endif
> +
>  /*
>   * Infrastructure to implement the synchronize_() primitives in
>   * TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
> diff --git a/kernel/rcutree.c b/kernel/rcutree.c
> index b8d300c..cba1332 100644
> --- a/kernel/rcutree.c
> +++ b/kernel/rcutree.c
> @@ -357,16 +357,8 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp)
> 
>  #endif /* #ifdef CONFIG_SMP */
> 
> -/*
> - * rcu_idle_enter_common - inform RCU that current CPU is moving towards idle
> - *
> - * If the new value of the ->dynticks_nesting counter now is zero,
> - * we really have entered idle, and must do the appropriate accounting.
> - * The caller must have disabled interrupts.
> - */
> -static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval)
> +static void rcu_check_idle_enter(long long oldval)
>  {
> -	trace_rcu_dyntick("Start", oldval, 0);
>  	if (!is_idle_task(current)) {
>  		struct task_struct *idle = idle_task(smp_processor_id());
> 
> @@ -376,6 +368,18 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval)
>  			  current->pid, current->comm,
>  			  idle->pid, idle->comm); /* must be idle task! */
>  	}
> +}
> +
> +/*
> + * rcu_idle_enter_common - inform RCU that current CPU is moving towards idle
> + *
> + * If the new value of the ->dynticks_nesting counter now is zero,
> + * we really have entered idle, and must do the appropriate accounting.
> + * The caller must have disabled interrupts.
> + */
> +static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval)
> +{
> +	trace_rcu_dyntick("Start", oldval, 0);
>  	rcu_prepare_for_idle(smp_processor_id());
>  	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
>  	smp_mb__before_atomic_inc();  /* See above. */
> @@ -384,6 +388,22 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval)
>  	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
>  }
> 
> +static long long __rcu_idle_enter(void)
> +{
> +	unsigned long flags;
> +	long long oldval;
> +	struct rcu_dynticks *rdtp;
> +
> +	local_irq_save(flags);
> +	rdtp = &__get_cpu_var(rcu_dynticks);
> +	oldval = rdtp->dynticks_nesting;
> +	rdtp->dynticks_nesting = 0;
> +	rcu_idle_enter_common(rdtp, oldval);
> +	local_irq_restore(flags);
> +
> +	return oldval;
> +}
> +
>  /**
>   * rcu_idle_enter - inform RCU that current CPU is entering idle
>   *
> @@ -398,16 +418,15 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval)
>   */
>  void rcu_idle_enter(void)
>  {
> -	unsigned long flags;
>  	long long oldval;
> -	struct rcu_dynticks *rdtp;
> 
> -	local_irq_save(flags);
> -	rdtp = &__get_cpu_var(rcu_dynticks);
> -	oldval = rdtp->dynticks_nesting;
> -	rdtp->dynticks_nesting = 0;
> -	rcu_idle_enter_common(rdtp, oldval);
> -	local_irq_restore(flags);
> +	oldval = __rcu_idle_enter();
> +	rcu_check_idle_enter(oldval);
> +}
> +
> +void rcu_user_enter(void)
> +{
> +	__rcu_idle_enter();
>  }
> 
>  /**
> @@ -437,6 +456,7 @@ void rcu_irq_exit(void)
>  	oldval = rdtp->dynticks_nesting;
>  	rdtp->dynticks_nesting--;
>  	WARN_ON_ONCE(rdtp->dynticks_nesting < 0);
> +
>  	if (rdtp->dynticks_nesting)
>  		trace_rcu_dyntick("--=", oldval, rdtp->dynticks_nesting);
>  	else
> @@ -444,6 +464,20 @@ void rcu_irq_exit(void)
>  	local_irq_restore(flags);
>  }
> 
> +static void rcu_check_idle_exit(struct rcu_dynticks *rdtp, long long oldval)
> +{
> +	if (!is_idle_task(current)) {
> +		struct task_struct *idle = idle_task(smp_processor_id());
> +
> +		trace_rcu_dyntick("Error on exit: not idle task",
> +				  oldval, rdtp->dynticks_nesting);
> +		ftrace_dump(DUMP_ALL);
> +		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
> +			  current->pid, current->comm,
> +			  idle->pid, idle->comm); /* must be idle task! */
> +	}
> +}
> +
>  /*
>   * rcu_idle_exit_common - inform RCU that current CPU is moving away from idle
>   *
> @@ -460,16 +494,18 @@ static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval)
>  	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
>  	rcu_cleanup_after_idle(smp_processor_id());
>  	trace_rcu_dyntick("End", oldval, rdtp->dynticks_nesting);
> -	if (!is_idle_task(current)) {
> -		struct task_struct *idle = idle_task(smp_processor_id());
> +}
> 
> -		trace_rcu_dyntick("Error on exit: not idle task",
> -				  oldval, rdtp->dynticks_nesting);
> -		ftrace_dump(DUMP_ALL);
> -		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
> -			  current->pid, current->comm,
> -			  idle->pid, idle->comm); /* must be idle task! */
> -	}
> +static long long __rcu_idle_exit(struct rcu_dynticks *rdtp)
> +{
> +	long long oldval;
> +
> +	oldval = rdtp->dynticks_nesting;
> +	WARN_ON_ONCE(oldval != 0);
> +	rdtp->dynticks_nesting = LLONG_MAX / 2;
> +	rcu_idle_exit_common(rdtp, oldval);
> +
> +	return oldval;
>  }
> 
>  /**
> @@ -485,16 +521,25 @@ static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval)
>   */
>  void rcu_idle_exit(void)
>  {
> +	long long oldval;
> +	struct rcu_dynticks *rdtp;
>  	unsigned long flags;
> +
> +	local_irq_save(flags);
> +	rdtp = &__get_cpu_var(rcu_dynticks);
> +	oldval = __rcu_idle_exit(rdtp);
> +	rcu_check_idle_exit(rdtp, oldval);
> +	local_irq_restore(flags);
> +}
> +
> +void rcu_user_exit(void)
> +{
>  	struct rcu_dynticks *rdtp;
> -	long long oldval;
> +	unsigned long flags;
> 
>  	local_irq_save(flags);
>  	rdtp = &__get_cpu_var(rcu_dynticks);
> -	oldval = rdtp->dynticks_nesting;
> -	WARN_ON_ONCE(oldval != 0);
> -	rdtp->dynticks_nesting = DYNTICK_TASK_NESTING;
> -	rcu_idle_exit_common(rdtp, oldval);
> +	 __rcu_idle_exit(rdtp);
>  	local_irq_restore(flags);
>  }
> 
> -- 
> 1.7.5.4
>