Patchwork softirq: a single rcu_bh_qs() call is enough

login
register
mail settings
Submitter Eric Dumazet
Date April 16, 2014, 4:06 p.m.
Message ID <1397664384.4222.124.camel@edumazet-glaptop2.roam.corp.google.com>
Download mbox | patch
Permalink /patch/339627/
State Not Applicable
Delegated to: David Miller
Headers show

Comments

Eric Dumazet - April 16, 2014, 4:06 p.m.
From: Eric Dumazet <edumazet@google.com>

Calling rcu_bh_qs() after every softirq action is not really needed.

What RCU needs is at least one rcu_bh_qs() per softirq round to note a
quiescent state was passed for rcu_bh

Note for Paul and myself : this could be inlined as a single instruction
and avoid smp_processor_id()
(sone this_cpu_write(rcu_bh_data.passed_quiesce, 1))

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 kernel/softirq.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)



--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Paul E. McKenney - April 16, 2014, 10:51 p.m.
On Wed, Apr 16, 2014 at 09:06:24AM -0700, Eric Dumazet wrote:
> From: Eric Dumazet <edumazet@google.com>
> 
> Calling rcu_bh_qs() after every softirq action is not really needed.
> 
> What RCU needs is at least one rcu_bh_qs() per softirq round to note a
> quiescent state was passed for rcu_bh
> 
> Note for Paul and myself : this could be inlined as a single instruction
> and avoid smp_processor_id()
> (sone this_cpu_write(rcu_bh_data.passed_quiesce, 1))
> 
> Signed-off-by: Eric Dumazet <edumazet@google.com>

Looks plausible -- will give it a go!  If nothing breaks, queued for
3.16.

							Thanx, Paul

> ---
>  kernel/softirq.c |    4 +---
>  1 file changed, 1 insertion(+), 3 deletions(-)
> 
> diff --git a/kernel/softirq.c b/kernel/softirq.c
> index b50990a5bea0..b9b2d4906848 100644
> --- a/kernel/softirq.c
> +++ b/kernel/softirq.c
> @@ -232,7 +232,6 @@ asmlinkage void __do_softirq(void)
>  	bool in_hardirq;
>  	__u32 pending;
>  	int softirq_bit;
> -	int cpu;
> 
>  	/*
>  	 * Mask out PF_MEMALLOC s current task context is borrowed for the
> @@ -247,7 +246,6 @@ asmlinkage void __do_softirq(void)
>  	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
>  	in_hardirq = lockdep_softirq_start();
> 
> -	cpu = smp_processor_id();
>  restart:
>  	/* Reset the pending bitmask before enabling irqs */
>  	set_softirq_pending(0);
> @@ -276,11 +274,11 @@ restart:
>  			       prev_count, preempt_count());
>  			preempt_count_set(prev_count);
>  		}
> -		rcu_bh_qs(cpu);
>  		h++;
>  		pending >>= softirq_bit;
>  	}
> 
> +	rcu_bh_qs(smp_processor_id());
>  	local_irq_disable();
> 
>  	pending = local_softirq_pending();
> 
> 

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/kernel/softirq.c b/kernel/softirq.c
index b50990a5bea0..b9b2d4906848 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -232,7 +232,6 @@  asmlinkage void __do_softirq(void)
 	bool in_hardirq;
 	__u32 pending;
 	int softirq_bit;
-	int cpu;
 
 	/*
 	 * Mask out PF_MEMALLOC s current task context is borrowed for the
@@ -247,7 +246,6 @@  asmlinkage void __do_softirq(void)
 	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
 	in_hardirq = lockdep_softirq_start();
 
-	cpu = smp_processor_id();
 restart:
 	/* Reset the pending bitmask before enabling irqs */
 	set_softirq_pending(0);
@@ -276,11 +274,11 @@  restart:
 			       prev_count, preempt_count());
 			preempt_count_set(prev_count);
 		}
-		rcu_bh_qs(cpu);
 		h++;
 		pending >>= softirq_bit;
 	}
 
+	rcu_bh_qs(smp_processor_id());
 	local_irq_disable();
 
 	pending = local_softirq_pending();