rcu: Refactor rcu_{nmi,irq}_{enter,exit}()

When entering or exiting irq or NMI handlers, the current code uses
->dynticks_nmi_nesting to detect if it is in the outermost handler,
that is, the one interrupting or returning to an RCU-idle context (the
idle loop or nohz_full usermode execution).  When entering the outermost
handler via an interrupt (as opposed to NMI), it is necessary to invoke
rcu_dynticks_task_exit() just before the CPU is marked non-idle from an
RCU perspective and to invoke rcu_cleanup_after_idle() just after the
CPU is marked non-idle.  Similarly, when exiting the outermost handler
via an interrupt, it is necessary to invoke rcu_prepare_for_idle() just
before marking the CPU idle and to invoke rcu_dynticks_task_enter()
just after marking the CPU idle.

The decision to execute these four functions is currently taken in
rcu_irq_enter() and rcu_irq_exit() as follows:

   rcu_irq_enter()
      /* A conditional branch with ->dynticks_nmi_nesting */
      rcu_nmi_enter()
         /* A conditional branch with ->dynticks */
      /* A conditional branch with ->dynticks_nmi_nesting */

   rcu_irq_exit()
      /* A conditional branch with ->dynticks_nmi_nesting */
      rcu_nmi_exit()
         /* A conditional branch with ->dynticks_nmi_nesting */
      /* A conditional branch with ->dynticks_nmi_nesting */

   rcu_nmi_enter()
      /* A conditional branch with ->dynticks */

   rcu_nmi_exit()
      /* A conditional branch with ->dynticks_nmi_nesting */

This works, but the conditional branches in rcu_irq_enter() and
rcu_irq_exit() are redundant with those in rcu_nmi_enter() and
rcu_nmi_exit(), respectively.  Redundant branches are not something
we want in the to/from-idle fastpaths, so this commit refactors
rcu_{nmi,irq}_{enter,exit}() so they use a common inlined function passed
a constant argument as follows:

   rcu_irq_enter() inlining rcu_nmi_enter_common(irq=true)
      /* A conditional branch with ->dynticks */

   rcu_irq_exit() inlining rcu_nmi_exit_common(irq=true)
      /* A conditional branch with ->dynticks_nmi_nesting */

   rcu_nmi_enter() inlining rcu_nmi_enter_common(irq=false)
      /* A conditional branch with ->dynticks */

   rcu_nmi_exit() inlining rcu_nmi_exit_common(irq=false)
      /* A conditional branch with ->dynticks_nmi_nesting */

The combination of the constant function argument and the inlining allows
the compiler to discard the conditionals that previously controlled
execution of rcu_dynticks_task_exit(), rcu_cleanup_after_idle(),
rcu_prepare_for_idle(), and rcu_dynticks_task_enter().  This reduces both
the to-idle and from-idle path lengths by two conditional branches each,
and improves readability as well.

This commit also changes order of execution from this:

	rcu_dynticks_task_exit();
	rcu_dynticks_eqs_exit();
	trace_rcu_dyntick();
	rcu_cleanup_after_idle();

To this:

	rcu_dynticks_task_exit();
	rcu_dynticks_eqs_exit();
	rcu_cleanup_after_idle();
	trace_rcu_dyntick();

In other words, the calls to rcu_cleanup_after_idle() and
trace_rcu_dyntick() are reversed.  This has no functional effect because
the real concern is whether a given call is before or after the call to
rcu_dynticks_eqs_exit(), and this patch does not change that.  Before the
call to rcu_dynticks_eqs_exit(), RCU is not yet watching the current
CPU and after that call RCU is watching.

A similar switch in calling order happens on the idle-entry path, with
similar lack of effect for the same reasons.
Suggested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Byungchul Park <byungchul.park@lge.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Applied Steven Rostedt feedback. ]
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

kernel/rcu/tree.c

@@ -770,18 +770,16 @@ void rcu_user_enter(void)
 }
 #endif /* CONFIG_NO_HZ_FULL */
 
-/**
- * rcu_nmi_exit - inform RCU of exit from NMI context
- *
+/*
  * If we are returning from the outermost NMI handler that interrupted an
  * RCU-idle period, update rdtp->dynticks and rdtp->dynticks_nmi_nesting
  * to let the RCU grace-period handling know that the CPU is back to
  * being RCU-idle.
  *
- * If you add or remove a call to rcu_nmi_exit(), be sure to test
+ * If you add or remove a call to rcu_nmi_exit_common(), be sure to test
  * with CONFIG_RCU_EQS_DEBUG=y.
  */
-void rcu_nmi_exit(void)
+static __always_inline void rcu_nmi_exit_common(bool irq)
 {
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
@@ -807,7 +805,26 @@ void rcu_nmi_exit(void)
 	/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
 	trace_rcu_dyntick(TPS("Startirq"), rdtp->dynticks_nmi_nesting, 0, rdtp->dynticks);
 	WRITE_ONCE(rdtp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
+
+	if (irq)
+		rcu_prepare_for_idle();
+
 	rcu_dynticks_eqs_enter();
+
+	if (irq)
+		rcu_dynticks_task_enter();
+}
+
+/**
+ * rcu_nmi_exit - inform RCU of exit from NMI context
+ * @irq: Is this call from rcu_irq_exit?
+ *
+ * If you add or remove a call to rcu_nmi_exit(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
+ */
+void rcu_nmi_exit(void)
+{
+	rcu_nmi_exit_common(false);
 }
 
 /**
@@ -831,14 +848,8 @@ void rcu_nmi_exit(void)
  */
 void rcu_irq_exit(void)
 {
-	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
-
 	lockdep_assert_irqs_disabled();
-	if (rdtp->dynticks_nmi_nesting == 1)
-		rcu_prepare_for_idle();
-	rcu_nmi_exit();
-	if (rdtp->dynticks_nmi_nesting == 0)
-		rcu_dynticks_task_enter();
+	rcu_nmi_exit_common(true);
 }
 
 /*
@@ -921,7 +932,8 @@ void rcu_user_exit(void)
 #endif /* CONFIG_NO_HZ_FULL */
 
 /**
- * rcu_nmi_enter - inform RCU of entry to NMI context
+ * rcu_nmi_enter_common - inform RCU of entry to NMI context
+ * @irq: Is this call from rcu_irq_enter?
  *
  * If the CPU was idle from RCU's viewpoint, update rdtp->dynticks and
  * rdtp->dynticks_nmi_nesting to let the RCU grace-period handling know
@@ -929,10 +941,10 @@ void rcu_user_exit(void)
  * long as the nesting level does not overflow an int.  (You will probably
  * run out of stack space first.)
  *
- * If you add or remove a call to rcu_nmi_enter(), be sure to test
+ * If you add or remove a call to rcu_nmi_enter_common(), be sure to test
  * with CONFIG_RCU_EQS_DEBUG=y.
  */
-void rcu_nmi_enter(void)
+static __always_inline void rcu_nmi_enter_common(bool irq)
 {
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 	long incby = 2;
@@ -949,7 +961,15 @@ void rcu_nmi_enter(void)
 	 * period (observation due to Andy Lutomirski).
 	 */
 	if (rcu_dynticks_curr_cpu_in_eqs()) {
+
+		if (irq)
+			rcu_dynticks_task_exit();
+
 		rcu_dynticks_eqs_exit();
+
+		if (irq)
+			rcu_cleanup_after_idle();
+
 		incby = 1;
 	}
 	trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
@@ -960,6 +980,14 @@ void rcu_nmi_enter(void)
 	barrier();
 }
 
+/**
+ * rcu_nmi_enter - inform RCU of entry to NMI context
+ */
+void rcu_nmi_enter(void)
+{
+	rcu_nmi_enter_common(false);
+}
+
 /**
  * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
  *
@@ -984,14 +1012,8 @@ void rcu_nmi_enter(void)
  */
 void rcu_irq_enter(void)
 {
-	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
-
 	lockdep_assert_irqs_disabled();
-	if (rdtp->dynticks_nmi_nesting == 0)
-		rcu_dynticks_task_exit();
-	rcu_nmi_enter();
-	if (rdtp->dynticks_nmi_nesting == 1)
-		rcu_cleanup_after_idle();
+	rcu_nmi_enter_common(true);
 }
 
 /*