rcu-tasks: Add Kconfig option to mediate smp_mb() vs. IPI

This commit provides a new TASKS_TRACE_RCU_READ_MB Kconfig option that
enables use of read-side memory barriers by both rcu_read_lock_trace()
and rcu_read_unlock_trace() when the are executed with the
current->trc_reader_special.b.need_mb flag set.  This flag is currently
never set.  Doing that is the subject of a later commit.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

include/linux/rcupdate_trace.h

@@ -50,7 +50,8 @@ static inline void rcu_read_lock_trace(void)
 	struct task_struct *t = current;
 
 	WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1);
-	if (t->trc_reader_special.b.need_mb)
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
+	    t->trc_reader_special.b.need_mb)
 		smp_mb(); // Pairs with update-side barriers
 	rcu_lock_acquire(&rcu_trace_lock_map);
 }

kernel/rcu/Kconfig

@@ -234,4 +234,22 @@ config RCU_NOCB_CPU
 	  Say Y here if you want to help to debug reduced OS jitter.
 	  Say N here if you are unsure.
 
+config TASKS_TRACE_RCU_READ_MB
+	bool "Tasks Trace RCU readers use memory barriers in user and idle"
+	depends on RCU_EXPERT
+	default PREEMPT_RT || NR_CPUS < 8
+	help
+	  Use this option to further reduce the number of IPIs sent
+	  to CPUs executing in userspace or idle during tasks trace
+	  RCU grace periods.  Given that a reasonable setting of
+	  the rcupdate.rcu_task_ipi_delay kernel boot parameter
+	  eliminates such IPIs for many workloads, proper setting
+	  of this Kconfig option is important mostly for aggressive
+	  real-time installations and for battery-powered devices,
+	  hence the default chosen above.
+
+	  Say Y here if you hate IPIs.
+	  Say N here if you hate read-side memory barriers.
+	  Take the default if you are unsure.
+
 endmenu # "RCU Subsystem"

kernel/rcu/tasks.h

@@ -734,7 +734,8 @@ void rcu_read_unlock_trace_special(struct task_struct *t, int nesting)
 {
 	int nq = t->trc_reader_special.b.need_qs;
 
-	if (t->trc_reader_special.b.need_mb)
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
+	    t->trc_reader_special.b.need_mb)
 		smp_mb(); // Pairs with update-side barriers.
 	// Update .need_qs before ->trc_reader_nesting for irq/NMI handlers.
 	if (nq)