[PATCH RFC tip/core/rcu] Avoid resched_cpu() when rescheduling the current CPU

["Paul E. McKenney" <paulmck@linux.vnet.ibm.com>]

Hello, Peter,

It occurred to me that it is wasteful to let resched_cpu() acquire
->pi_lock when doing something like resched_cpu(smp_processor_id()),
and that it would be better to instead use set_tsk_need_resched(current)
and set_preempt_need_resched().

But is doing so really worthwhile?  For that matter, are there some
constraints on the use of those two functions that I am failing to
allow for in the patch below?

							Thanx, Paul

------------------------------------------------------------------------

commit e95e2d26fff60af9bb4111a9c17461ecd5e17a7d
Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Date:   Thu Jul 26 13:44:00 2018 -0700

    rcu: Avoid resched_cpu() when rescheduling the current CPU
    
    The resched_cpu() interface is quite handy, but it does acquire the
    specified CPU's runqueue lock, which does not come for free.  This
    commit therefore substitutes the following when directing resched_cpu()
    at the current CPU:
    
            set_tsk_need_resched(current);
            set_preempt_need_resched();
    
    Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
    Cc: Peter Zijlstra <peterz@infradead.org>

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 595059141c40..061ceb171d8e 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1353,7 +1353,8 @@ static void print_cpu_stall(void)
 	 * progress and it could be we're stuck in kernel space without context
 	 * switches for an entirely unreasonable amount of time.
 	 */
-	resched_cpu(smp_processor_id());
+	set_tsk_need_resched(current);
+	set_preempt_need_resched();
 }
 
 static void check_cpu_stall(struct rcu_data *rdp)
@@ -2674,10 +2675,12 @@ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused
 	WARN_ON_ONCE(!rdp->beenonline);
 
 	/* Report any deferred quiescent states if preemption enabled. */
-	if (!(preempt_count() & PREEMPT_MASK))
+	if (!(preempt_count() & PREEMPT_MASK)) {
 		rcu_preempt_deferred_qs(current);
-	else if (rcu_preempt_need_deferred_qs(current))
-		resched_cpu(rdp->cpu); /* Provoke future context switch. */
+	} else if (rcu_preempt_need_deferred_qs(current)) {
+		set_tsk_need_resched(current);
+		set_preempt_need_resched();
+	}
 
 	/* Update RCU state based on any recent quiescent states. */
 	rcu_check_quiescent_state(rdp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index b3e2c873b8e4..62d363d7fab2 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -672,7 +672,8 @@ static void sync_rcu_exp_handler(void *unused)
 			rcu_report_exp_rdp(rdp);
 		} else {
 			rdp->deferred_qs = true;
-			resched_cpu(rdp->cpu);
+			set_tsk_need_resched(t);
+			set_preempt_need_resched();
 		}
 		return;
 	}
@@ -710,15 +711,16 @@ static void sync_rcu_exp_handler(void *unused)
 	 * because we are in an interrupt handler, which will cause that
 	 * function to take an early exit without doing anything.
 	 *
-	 * Otherwise, use resched_cpu() to force a context switch after
-	 * the CPU enables everything.
+	 * Otherwise, force a context switch after the CPU enables everything.
 	 */
 	rdp->deferred_qs = true;
 	if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
-	    WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs()))
+	    WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs())) {
 		rcu_preempt_deferred_qs(t);
-	else
-		resched_cpu(rdp->cpu);
+	} else {
+		set_tsk_need_resched(t);
+		set_preempt_need_resched();
+	}
 }
 
 /* PREEMPT=y, so no PREEMPT=n expedited grace period to clean up after. */
@@ -779,7 +781,8 @@ static void sync_sched_exp_handler(void *unused)
 	__this_cpu_write(rcu_data.cpu_no_qs.b.exp, true);
 	/* Store .exp before .rcu_urgent_qs. */
 	smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
-	resched_cpu(smp_processor_id());
+	set_tsk_need_resched(current);
+	set_preempt_need_resched();
 }
 
 /* Send IPI for expedited cleanup if needed at end of CPU-hotplug operation. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 5f4c8bab7c72..d3ccf4389a67 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -791,8 +791,10 @@ static void rcu_flavor_check_callbacks(int user)
 	if (t->rcu_read_lock_nesting > 0 ||
 	    (preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK))) {
 		/* No QS, force context switch if deferred. */
-		if (rcu_preempt_need_deferred_qs(t))
-			resched_cpu(smp_processor_id());
+		if (rcu_preempt_need_deferred_qs(t)) {
+			set_tsk_need_resched(t);
+			set_preempt_need_resched();
+		}
 	} else if (rcu_preempt_need_deferred_qs(t)) {
 		rcu_preempt_deferred_qs(t); /* Report deferred QS. */
 		return;