On Fri, Sep 11, 2015 at 02:59:37PM -0700, Paul E. McKenney wrote:
> 
> Queued for v4.4, thank you!  Please see below for updated commit log,
> and please let me know if there are any problems with it.
> 

Looks great to me! Thank you ;-)

Regards,
Boqun

> ------------------------------------------------------------------------
> 
>     rcu: Don't disable preemption for Tiny and Tree RCU readers
>     
>     Because preempt_disable() maps to barrier() for non-debug builds,
>     it forces the compiler to spill and reload registers.  Because Tree
>     RCU and Tiny RCU now only appear in CONFIG_PREEMPT=n builds, these
>     barrier() instances generate needless extra code for each instance of
>     rcu_read_lock() and rcu_read_unlock().  This extra code slows down Tree
>     RCU and bloats Tiny RCU.
>     
>     This commit therefore removes the preempt_disable() and preempt_enable()
>     from the non-preemptible implementations of __rcu_read_lock() and
>     __rcu_read_unlock(), respectively.  However, for debug purposes,
>     preempt_disable() and preempt_enable() are still invoked if
>     CONFIG_PREEMPT_COUNT=y, because this allows detection of sleeping inside
>     atomic sections in non-preemptible kernels.
>     
>     This is based on an earlier patch by Paul E. McKenney, fixing
>     a bug encountered in kernels built with CONFIG_PREEMPT=n and
>     CONFIG_PREEMPT_COUNT=y.
>     
>     Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
>     Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> 
> diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
> index d63bb77dab35..6c3ceceb6148 100644
> --- a/include/linux/rcupdate.h
> +++ b/include/linux/rcupdate.h
> @@ -297,12 +297,14 @@ void synchronize_rcu(void);
>  
>  static inline void __rcu_read_lock(void)
>  {
> -	preempt_disable();
> +	if (IS_ENABLED(CONFIG_PREEMPT_COUNT))
> +		preempt_disable();
>  }
>  
>  static inline void __rcu_read_unlock(void)
>  {
> -	preempt_enable();
> +	if (IS_ENABLED(CONFIG_PREEMPT_COUNT))
> +		preempt_enable();
>  }
>  
>  static inline void synchronize_rcu(void)
> diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
> index c8a0722f77ea..4c1aaf9cce7b 100644
> --- a/include/linux/rcutiny.h
> +++ b/include/linux/rcutiny.h
> @@ -216,6 +216,7 @@ static inline bool rcu_is_watching(void)
>  
>  static inline void rcu_all_qs(void)
>  {
> +	barrier(); /* Avoid RCU read-side critical sections leaking across. */
>  }
>  
>  #endif /* __LINUX_RCUTINY_H */
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index ce43fac5ff91..b4882f8b8a9e 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -337,12 +337,14 @@ static void rcu_momentary_dyntick_idle(void)
>   */
>  void rcu_note_context_switch(void)
>  {
> +	barrier(); /* Avoid RCU read-side critical sections leaking down. */
>  	trace_rcu_utilization(TPS("Start context switch"));
>  	rcu_sched_qs();
>  	rcu_preempt_note_context_switch();
>  	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
>  		rcu_momentary_dyntick_idle();
>  	trace_rcu_utilization(TPS("End context switch"));
> +	barrier(); /* Avoid RCU read-side critical sections leaking up. */
>  }
>  EXPORT_SYMBOL_GPL(rcu_note_context_switch);
>  
> @@ -353,12 +355,19 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
>   * RCU flavors in desperate need of a quiescent state, which will normally
>   * be none of them).  Either way, do a lightweight quiescent state for
>   * all RCU flavors.
> + *
> + * The barrier() calls are redundant in the common case when this is
> + * called externally, but just in case this is called from within this
> + * file.
> + *
>   */
>  void rcu_all_qs(void)
>  {
> +	barrier(); /* Avoid RCU read-side critical sections leaking down. */
>  	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
>  		rcu_momentary_dyntick_idle();
>  	this_cpu_inc(rcu_qs_ctr);
> +	barrier(); /* Avoid RCU read-side critical sections leaking up. */
>  }
>  EXPORT_SYMBOL_GPL(rcu_all_qs);
>  
>