Re: [PATCH v3] rcu: Allow to eliminate softirq processing from rcutree

[Joel Fernandes]

On Fri, Mar 22, 2019 at 05:25:19PM -0700, Paul E. McKenney wrote:
> On Fri, Mar 22, 2019 at 07:48:19PM -0400, Joel Fernandes wrote:
> > On Wed, Mar 20, 2019 at 10:13:33PM +0100, Sebastian Andrzej Siewior wrote:
> > > Running RCU out of softirq is a problem for some workloads that would
> > > like to manage RCU core processing independently of other softirq
> > > work, for example, setting kthread priority.  This commit therefore
> > > introduces the `rcunosoftirq' option which moves the RCU core work
> > > from softirq to a per-CPU/per-flavor SCHED_OTHER kthread named rcuc.
> > > The SCHED_OTHER approach avoids the scalability problems that appeared
> > > with the earlier attempt to move RCU core processing to from softirq
> > > to kthreads.  That said, kernels built with RCU_BOOST=y will run the
> > > rcuc kthreads at the RCU-boosting priority.
> > [snip]
> > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > > index 0f31b79eb6761..05a1e42fdaf10 100644
> > > --- a/kernel/rcu/tree.c
> > > +++ b/kernel/rcu/tree.c
> > > @@ -51,6 +51,12 @@
> > >  #include <linux/tick.h>
> > >  #include <linux/sysrq.h>
> > >  #include <linux/kprobes.h>
> > > +#include <linux/gfp.h>
> > > +#include <linux/oom.h>
> > > +#include <linux/smpboot.h>
> > > +#include <linux/jiffies.h>
> > > +#include <linux/sched/isolation.h>
> > > +#include "../time/tick-internal.h"
> > >  
> > >  #include "tree.h"
> > >  #include "rcu.h"
> > > @@ -92,6 +98,9 @@ struct rcu_state rcu_state = {
> > >  /* Dump rcu_node combining tree at boot to verify correct setup. */
> > >  static bool dump_tree;
> > >  module_param(dump_tree, bool, 0444);
> > > +/* Move RCU_SOFTIRQ to rcuc kthreads. */
> > > +static bool use_softirq = 1;
> > > +module_param(use_softirq, bool, 0444);
> > >  /* Control rcu_node-tree auto-balancing at boot time. */
> > >  static bool rcu_fanout_exact;
> > >  module_param(rcu_fanout_exact, bool, 0444);
> > > @@ -2253,7 +2262,7 @@ void rcu_force_quiescent_state(void)
> > >  EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
> > >  
> > >  /* Perform RCU core processing work for the current CPU.  */
> > > -static __latent_entropy void rcu_core(struct softirq_action *unused)
> > > +static __latent_entropy void rcu_core(void)
> > >  {
> > >  	unsigned long flags;
> > >  	struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
> > > @@ -2295,6 +2304,34 @@ static __latent_entropy void rcu_core(struct softirq_action *unused)
> > >  	trace_rcu_utilization(TPS("End RCU core"));
> > >  }
> > >  
> > > +static void rcu_core_si(struct softirq_action *h)
> > > +{
> > > +	rcu_core();
> > > +}
> > > +
> > > +static void rcu_wake_cond(struct task_struct *t, int status)
> > > +{
> > > +	/*
> > > +	 * If the thread is yielding, only wake it when this
> > > +	 * is invoked from idle
> > > +	 */
> > > +	if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current)))
> > > +		wake_up_process(t);
> > > +}
> > > +
> > > +static void invoke_rcu_core_kthread(void)
> > > +{
> > > +	struct task_struct *t;
> > > +	unsigned long flags;
> > > +
> > > +	local_irq_save(flags);
> > > +	__this_cpu_write(rcu_data.rcu_cpu_has_work, 1);
> > > +	t = __this_cpu_read(rcu_data.rcu_cpu_kthread_task);
> > > +	if (t != NULL && t != current)
> > > +		rcu_wake_cond(t, __this_cpu_read(rcu_data.rcu_cpu_kthread_status));
> > > +	local_irq_restore(flags);
> > > +}
> > > +
> > >  /*
> > >   * Schedule RCU callback invocation.  If the running implementation of RCU
> > >   * does not support RCU priority boosting, just do a direct call, otherwise
> > > @@ -2306,19 +2343,95 @@ static void invoke_rcu_callbacks(struct rcu_data *rdp)
> > >  {
> > >  	if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
> > >  		return;
> > > -	if (likely(!rcu_state.boost)) {
> > > -		rcu_do_batch(rdp);
> > > -		return;
> > > -	}
> > > -	invoke_rcu_callbacks_kthread();
> > > +	if (rcu_state.boost || !use_softirq)
> > > +		invoke_rcu_core_kthread();
> > > +	rcu_do_batch(rdp);
> > 
> > Shouldn't there be an else before the rcu_do_batch? If we are waking up the
> > rcuc thread, then that will do the rcu_do_batch when it runs right?
> > 
> > Something like:
> > 	if (rcu_state.boost || !use_softirq)
> > 		invoke_rcu_core_kthread();
> > 	else
> > 		rcu_do_batch(rdp);
> > 
> > Previous code similarly had a return; also.
> 
> I believe that you are correct, so I will give it a shot.  Good eyes!

Thanks! Also I am sending some the lockdep dyntick checking patches shortly :)

> > >  }
> > >  
> > > +/*
> > > + * Wake up this CPU's rcuc kthread to do RCU core processing.
> > > + */
> > >  static void invoke_rcu_core(void)
> > >  {
> > > -	if (cpu_online(smp_processor_id()))
> > > +	if (!cpu_online(smp_processor_id()))
> > > +		return;
> > > +	if (use_softirq)
> > >  		raise_softirq(RCU_SOFTIRQ);
> > > +	else
> > > +		invoke_rcu_core_kthread();
> > >  }
> > >  
> > > +static void rcu_cpu_kthread_park(unsigned int cpu)
> > > +{
> > > +	per_cpu(rcu_data.rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
> > > +}
> > > +
> > > +static int rcu_cpu_kthread_should_run(unsigned int cpu)
> > > +{
> > > +	return __this_cpu_read(rcu_data.rcu_cpu_has_work);
> > > +}
> > > +
> > > +/*
> > > + * Per-CPU kernel thread that invokes RCU callbacks.  This replaces
> > > + * the RCU softirq used in configurations of RCU that do not support RCU
> > > + * priority boosting.
> > > + */
> > > +static void rcu_cpu_kthread(unsigned int cpu)
> > > +{
> > > +	unsigned int *statusp = this_cpu_ptr(&rcu_data.rcu_cpu_kthread_status);
> > > +	char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work);
> > > +	int spincnt;
> > > +
> > > +	for (spincnt = 0; spincnt < 10; spincnt++) {
> > > +		trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait"));
> > > +		local_bh_disable();
> > > +		*statusp = RCU_KTHREAD_RUNNING;
> > > +		local_irq_disable();
> > > +		work = *workp;
> > > +		*workp = 0;
> > > +		local_irq_enable();
> > > +		if (work)
> > > +			rcu_core();
> > > +		local_bh_enable();
> > > +		if (*workp == 0) {
> > > +			trace_rcu_utilization(TPS("End CPU kthread@rcu_wait"));
> > > +			*statusp = RCU_KTHREAD_WAITING;
> > > +			return;
> > > +		}
> > > +	}
> > > +	*statusp = RCU_KTHREAD_YIELDING;
> > > +	trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield"));
> > > +	schedule_timeout_interruptible(2);
> > > +	trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
> > > +	*statusp = RCU_KTHREAD_WAITING;
> > > +}
> > > +
> > [snip]
> > > diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
> > > index e253d11af3c49..a1a72a1ecb026 100644
> > > --- a/kernel/rcu/tree.h
> > > +++ b/kernel/rcu/tree.h
> > > @@ -407,8 +407,8 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func);
> > >  static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
> > >  static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
> > >  static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
> > > -static void invoke_rcu_callbacks_kthread(void);
> > >  static bool rcu_is_callbacks_kthread(void);
> > > +static void rcu_cpu_kthread_setup(unsigned int cpu);
> > >  static void __init rcu_spawn_boost_kthreads(void);
> > >  static void rcu_prepare_kthreads(int cpu);
> > >  static void rcu_cleanup_after_idle(void);
> > > diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
> > > index f46b4af96ab95..b807204ffd83f 100644
> > > --- a/kernel/rcu/tree_plugin.h
> > > +++ b/kernel/rcu/tree_plugin.h
> > > @@ -11,29 +11,7 @@
> > >   *	   Paul E. McKenney <paulmck@xxxxxxxxxxxxx>
> > >   */
> > >  
> > > -#include <linux/delay.h>
> > > -#include <linux/gfp.h>
> > > -#include <linux/oom.h>
> > > -#include <linux/sched/debug.h>
> > > -#include <linux/smpboot.h>
> > > -#include <linux/sched/isolation.h>
> > > -#include <uapi/linux/sched/types.h>
> > > -#include "../time/tick-internal.h"
> > > -
> > > -#ifdef CONFIG_RCU_BOOST
> > >  #include "../locking/rtmutex_common.h"
> > > -#else /* #ifdef CONFIG_RCU_BOOST */
> > > -
> > > -/*
> > > - * Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST,
> > > - * all uses are in dead code.  Provide a definition to keep the compiler
> > > - * happy, but add WARN_ON_ONCE() to complain if used in the wrong place.
> > > - * This probably needs to be excluded from -rt builds.
> > > - */
> > > -#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; })
> > > -#define rt_mutex_futex_unlock(x) WARN_ON_ONCE(1)
> > > -
> > > -#endif /* #else #ifdef CONFIG_RCU_BOOST */
> > >  
> > >  #ifdef CONFIG_RCU_NOCB_CPU
> > >  static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
> > > @@ -94,6 +72,8 @@ static void __init rcu_bootup_announce_oddness(void)
> > >  		pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_init_delay);
> > >  	if (gp_cleanup_delay)
> > >  		pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_cleanup_delay);
> > > +	if (!use_softirq)
> > > +		pr_info("\tRCU_SOFTIRQ processing moved to rcuc kthreads.\n");
> > >  	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG))
> > >  		pr_info("\tRCU debug extended QS entry/exit.\n");
> > >  	rcupdate_announce_bootup_oddness();
> > > @@ -629,7 +609,10 @@ static void rcu_read_unlock_special(struct task_struct *t)
> > >  		/* Need to defer quiescent state until everything is enabled. */
> > >  		if (irqs_were_disabled) {
> > >  			/* Enabling irqs does not reschedule, so... */
> > > -			raise_softirq_irqoff(RCU_SOFTIRQ);
> > > +			if (!use_softirq)
> > > +				raise_softirq_irqoff(RCU_SOFTIRQ);
> > 
> > I believe this exclamation has been corrected in Paul's tree so that's Ok.
> > 
> > > +			else
> > > +				invoke_rcu_core();
> > 
> > But why not just directly call invoke_rcu_core() here? That will do the
> > appropriate use_softirq check right?
> 
> It is -so- close!  But it invokes raise_softirq() instead of the needed
> raise_softirq_irqoff().
> 
> Plus I bet that this has a few more changes to go before it is all the
> way there.  ;-)

Ah yes, you are right :-)

thanks,

 - Joel