Re: [PATCH] tracing/perf: Move rcu_irq_enter/exit_irqson() to perf trace point hook

From: Steven Rostedt <rostedt@goodmis.org>
To: Peter Zijlstra <peterz@infradead.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Ingo Molnar <mingo@kernel.org>,
	"Joel Fernandes (Google)" <joel@joelfernandes.org>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	"Gustavo A. R. Silva" <gustavo@embeddedor.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	"Paul E. McKenney" <paulmck@kernel.org>,
	Josh Triplett <josh@joshtriplett.org>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Lai Jiangshan <jiangshanlai@gmail.com>
Subject: Re: [PATCH] tracing/perf: Move rcu_irq_enter/exit_irqson() to perf trace point hook
Date: Tue, 11 Feb 2020 09:10:40 -0500	[thread overview]
Message-ID: <20200211091040.25d92244@gandalf.local.home> (raw)
In-Reply-To: <20200211122120.GM14914@hirez.programming.kicks-ass.net>

On Tue, 11 Feb 2020 13:21:20 +0100
Peter Zijlstra <peterz@infradead.org> wrote:

> > @@ -68,6 +78,9 @@ perf_trace_##call(void *__data, proto)					\
> >  	perf_trace_run_bpf_submit(entry, __entry_size, rctx,		\
> >  				  event_call, __count, __regs,		\
> >  				  head, __task);			\
> > +out:									\
> > +	if (!rcu_watching)						\
> > +		rcu_irq_exit_irqson();					\
> >  }  
> 
> It is probably okay to move that into perf_tp_event(), then this:
> 
> >  /*
> > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > index 1694a6b57ad8..3e6f07b62515 100644
> > --- a/kernel/rcu/tree.c
> > +++ b/kernel/rcu/tree.c
> > @@ -719,6 +719,7 @@ void rcu_irq_exit_irqson(void)
> >  	rcu_irq_exit();
> >  	local_irq_restore(flags);
> >  }
> > +EXPORT_SYMBOL_GPL(rcu_irq_exit_irqson);
> >  
> >  /*
> >   * Exit an RCU extended quiescent state, which can be either the
> > @@ -890,6 +891,7 @@ void rcu_irq_enter_irqson(void)
> >  	rcu_irq_enter();
> >  	local_irq_restore(flags);
> >  }
> > +EXPORT_SYMBOL_GPL(rcu_irq_enter_irqson);
> >  
> >  /*
> >   * If any sort of urgency was applied to the current CPU (for example,  
> 
> can go too. Those things really should not be exported.

Thanks, I'll send an updated patch.

-- Steve