rcu: Make ksoftirqd do RCU quiescent states

rcu: Make ksoftirqd do RCU quiescent states

[Paul E. McKenney]

> Implementing RCU-bh in terms of RCU-preempt makes the system vulnerable
> to network-based denial-of-service attacks.  This patch therefore
> makes __do_softirq() invoke rcu_bh_qs(), but only when __do_softirq()
> is running in ksoftirqd context.  A wrapper layer in interposed so that
> other calls to __do_softirq() avoid invoking rcu_bh_qs().  The underlying
> function __do_softirq_common() does the actual work.
> 
> The reason that rcu_bh_qs() is bad in these non-ksoftirqd contexts is
> that there might be a local_bh_enable() inside an RCU-preempt read-side
> critical section.  This local_bh_enable() can invoke __do_softirq()
> directly, so if __do_softirq() were to invoke rcu_bh_qs() (which just
> calls rcu_preempt_qs() in the PREEMPT_RT_FULL case), there would be
> an illegal RCU-preempt quiescent state in the middle of an RCU-preempt
> read-side critical section.  Therefore, quiescent states can only happen
> in cases where __do_softirq() is invoked directly from ksoftirqd.

I -think- that the need for this goes away in the current merge window
because RCU-bh is going away.  There might still be an rt-specific need
to disable irqs, though.

							Thanx, Paul

> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> Link: http://lkml.kernel.org/r/20111005184518.GA21601@linux.vnet.ibm.com
> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
> 
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 197088cdb56e..968579b86401 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -244,7 +244,19 @@ void rcu_sched_qs(void)
>  			   this_cpu_ptr(&rcu_sched_data), true);
>  }
>  
> -#ifndef CONFIG_PREEMPT_RT_FULL
> +#ifdef CONFIG_PREEMPT_RT_FULL
> +static void rcu_preempt_qs(void);
> +
> +void rcu_bh_qs(void)
> +{
> +	unsigned long flags;
> +
> +	/* Callers to this function, rcu_preempt_qs(), must disable irqs. */
> +	local_irq_save(flags);
> +	rcu_preempt_qs();
> +	local_irq_restore(flags);
> +}
> +#else
>  void rcu_bh_qs(void)
>  {
>  	RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!");
> diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
> index 429a2f144e19..bee9bffeb0ce 100644
> --- a/kernel/rcu/tree_plugin.h
> +++ b/kernel/rcu/tree_plugin.h
> @@ -29,6 +29,7 @@
>  #include <linux/oom.h>
>  #include <linux/sched/debug.h>
>  #include <linux/smpboot.h>
> +#include <linux/jiffies.h>
>  #include <linux/sched/isolation.h>
>  #include <uapi/linux/sched/types.h>
>  #include "../time/tick-internal.h"
> @@ -1407,7 +1408,7 @@ static void rcu_prepare_kthreads(int cpu)
>  
>  #endif /* #else #ifdef CONFIG_RCU_BOOST */
>  
> -#if !defined(CONFIG_RCU_FAST_NO_HZ)
> +#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL)
>  
>  /*
>   * Check to see if any future RCU-related work will need to be done
> @@ -1423,7 +1424,9 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
>  	*nextevt = KTIME_MAX;
>  	return rcu_cpu_has_callbacks(NULL);
>  }
> +#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */
>  
> +#if !defined(CONFIG_RCU_FAST_NO_HZ)
>  /*
>   * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
>   * after it.
> @@ -1520,6 +1523,8 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
>  	return cbs_ready;
>  }
>  
> +#ifndef CONFIG_PREEMPT_RT_FULL
> +
>  /*
>   * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready
>   * to invoke.  If the CPU has callbacks, try to advance them.  Tell the
> @@ -1562,6 +1567,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
>  	*nextevt = basemono + dj * TICK_NSEC;
>  	return 0;
>  }
> +#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */
>  
>  /*
>   * Prepare a CPU for idle from an RCU perspective.  The first major task