Re: [PATCH v3 05/22] rcu: Make RCU IRQ enter/exit functions rely on in_nmi()

[Paul E. McKenney]

On Wed, Feb 19, 2020 at 03:47:29PM +0100, Peter Zijlstra wrote:
> From: Paul E. McKenney <paulmck@xxxxxxxxxx>
> 
> The rcu_nmi_enter_common() and rcu_nmi_exit_common() functions take an
> "irq" parameter that indicates whether these functions are invoked from
> an irq handler (irq==true) or an NMI handler (irq==false).  However,
> recent changes have applied notrace to a few critical functions such
> that rcu_nmi_enter_common() and rcu_nmi_exit_common() many now rely
> on in_nmi().  Note that in_nmi() works no differently than before,
> but rather that tracing is now prohibited in code regions where in_nmi()
> would incorrectly report NMI state.
> 
> This commit therefore removes the "irq" parameter and inlines
> rcu_nmi_enter_common() and rcu_nmi_exit_common() into rcu_nmi_enter()
> and rcu_nmi_exit(), respectively.
> 
> Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
> Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>

Again, thank you.

Would you like to also take the added comment for NOKPROBE_SYMBOL(),
or would you prefer that I carry that separately?  (I dropped it for
now to avoid the conflict with the patch below.)

Here is the latest version of that comment, posted by Steve Rostedt.

							Thanx, Paul

/*
 * All functions called in the breakpoint trap handler (e.g. do_int3()
 * on x86), must not allow kprobes until the kprobe breakpoint handler
 * is called, otherwise it can cause an infinite recursion.
 * On some archs, rcu_nmi_enter() is called in the breakpoint handler
 * before the kprobe breakpoint handler is called, thus it must be
 * marked as NOKPROBE.
 */

> ---
>  kernel/rcu/tree.c |   45 ++++++++++++++-------------------------------
>  1 file changed, 14 insertions(+), 31 deletions(-)
> 
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -614,16 +614,18 @@ void rcu_user_enter(void)
>  }
>  #endif /* CONFIG_NO_HZ_FULL */
>  
> -/*
> +/**
> + * rcu_nmi_exit - inform RCU of exit from NMI context
> + *
>   * If we are returning from the outermost NMI handler that interrupted an
>   * RCU-idle period, update rdp->dynticks and rdp->dynticks_nmi_nesting
>   * to let the RCU grace-period handling know that the CPU is back to
>   * being RCU-idle.
>   *
> - * If you add or remove a call to rcu_nmi_exit_common(), be sure to test
> + * If you add or remove a call to rcu_nmi_exit(), be sure to test
>   * with CONFIG_RCU_EQS_DEBUG=y.
>   */
> -static __always_inline void rcu_nmi_exit_common(bool irq)
> +void rcu_nmi_exit(void)
>  {
>  	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
>  
> @@ -651,27 +653,16 @@ static __always_inline void rcu_nmi_exit
>  	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
>  	WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
>  
> -	if (irq)
> +	if (!in_nmi())
>  		rcu_prepare_for_idle();
>  
>  	rcu_dynticks_eqs_enter();
>  
> -	if (irq)
> +	if (!in_nmi())
>  		rcu_dynticks_task_enter();
>  }
>  
>  /**
> - * rcu_nmi_exit - inform RCU of exit from NMI context
> - *
> - * If you add or remove a call to rcu_nmi_exit(), be sure to test
> - * with CONFIG_RCU_EQS_DEBUG=y.
> - */
> -void rcu_nmi_exit(void)
> -{
> -	rcu_nmi_exit_common(false);
> -}
> -
> -/**
>   * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
>   *
>   * Exit from an interrupt handler, which might possibly result in entering
> @@ -693,7 +684,7 @@ void rcu_nmi_exit(void)
>  void rcu_irq_exit(void)
>  {
>  	lockdep_assert_irqs_disabled();
> -	rcu_nmi_exit_common(true);
> +	rcu_nmi_exit();
>  }
>  
>  /*
> @@ -777,7 +768,7 @@ void rcu_user_exit(void)
>  #endif /* CONFIG_NO_HZ_FULL */
>  
>  /**
> - * rcu_nmi_enter_common - inform RCU of entry to NMI context
> + * rcu_nmi_enter - inform RCU of entry to NMI context
>   * @irq: Is this call from rcu_irq_enter?
>   *
>   * If the CPU was idle from RCU's viewpoint, update rdp->dynticks and
> @@ -786,10 +777,10 @@ void rcu_user_exit(void)
>   * long as the nesting level does not overflow an int.  (You will probably
>   * run out of stack space first.)
>   *
> - * If you add or remove a call to rcu_nmi_enter_common(), be sure to test
> + * If you add or remove a call to rcu_nmi_enter(), be sure to test
>   * with CONFIG_RCU_EQS_DEBUG=y.
>   */
> -static __always_inline void rcu_nmi_enter_common(bool irq)
> +void rcu_nmi_enter(void)
>  {
>  	long incby = 2;
>  	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
> @@ -807,12 +798,12 @@ static __always_inline void rcu_nmi_ente
>  	 */
>  	if (rcu_dynticks_curr_cpu_in_eqs()) {
>  
> -		if (irq)
> +		if (!in_nmi())
>  			rcu_dynticks_task_exit();
>  
>  		rcu_dynticks_eqs_exit();
>  
> -		if (irq)
> +		if (!in_nmi())
>  			rcu_cleanup_after_idle();
>  
>  		incby = 1;
> @@ -834,14 +825,6 @@ static __always_inline void rcu_nmi_ente
>  		   rdp->dynticks_nmi_nesting + incby);
>  	barrier();
>  }
> -
> -/**
> - * rcu_nmi_enter - inform RCU of entry to NMI context
> - */
> -void rcu_nmi_enter(void)
> -{
> -	rcu_nmi_enter_common(false);
> -}
>  NOKPROBE_SYMBOL(rcu_nmi_enter);
>  
>  /**
> @@ -869,7 +852,7 @@ NOKPROBE_SYMBOL(rcu_nmi_enter);
>  void rcu_irq_enter(void)
>  {
>  	lockdep_assert_irqs_disabled();
> -	rcu_nmi_enter_common(true);
> +	rcu_nmi_enter();
>  }
>  
>  /*
> 
>