rcu: Pull rcu_sched_qs_mask into rcu_dynticks structure

The rcu_sched_qs_mask variable is yet another isolated per-CPU variable,
so this commit pulls it into the pre-existing rcu_dynticks per-CPU
structure.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

Documentation/RCU/Design/Data-Structures/Data-Structures.html

@@ -1104,6 +1104,7 @@ Its fields are as follows:
   1   int dynticks_nesting;
   2   int dynticks_nmi_nesting;
   3   atomic_t dynticks;
+  4   int rcu_sched_qs_mask;
 </pre>
 
 <p>The <tt>-&gt;dynticks_nesting</tt> field counts the
@@ -1117,11 +1118,17 @@ NMIs are counted by the <tt>-&gt;dynticks_nmi_nesting</tt>
 field, except that NMIs that interrupt non-dyntick-idle execution
 are not counted.
 
-</p><p>Finally, the <tt>-&gt;dynticks</tt> field counts the corresponding
+</p><p>The <tt>-&gt;dynticks</tt> field counts the corresponding
 CPU's transitions to and from dyntick-idle mode, so that this counter
 has an even value when the CPU is in dyntick-idle mode and an odd
 value otherwise.
 
+</p><p>Finally, the  <tt>-&gt;rcu_sched_qs_mask</tt> field is used
+to record the fact that the RCU core code would really like to
+see a quiescent state from the corresponding CPU.
+This flag is checked by RCU's context-switch and <tt>cond_resched()</tt>
+code, which provide a momentary idle sojourn in response.
+
 <table>
 <tr><th>&nbsp;</th></tr>
 <tr><th align="left">Quick Quiz:</th></tr>

kernel/rcu/tree.c

@@ -272,8 +272,6 @@ void rcu_bh_qs(void)
 	}
 }
 
-static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
-
 /*
  * Steal a bit from the bottom of ->dynticks for idle entry/exit
  * control.  Initially this is for TLB flushing.
@@ -464,8 +462,8 @@ static void rcu_momentary_dyntick_idle(void)
 	 * Yes, we can lose flag-setting operations.  This is OK, because
 	 * the flag will be set again after some delay.
 	 */
-	resched_mask = raw_cpu_read(rcu_sched_qs_mask);
-	raw_cpu_write(rcu_sched_qs_mask, 0);
+	resched_mask = raw_cpu_read(rcu_dynticks.rcu_sched_qs_mask);
+	raw_cpu_write(rcu_dynticks.rcu_sched_qs_mask, 0);
 
 	/* Find the flavor that needs a quiescent state. */
 	for_each_rcu_flavor(rsp) {
@@ -499,7 +497,7 @@ void rcu_note_context_switch(void)
 	trace_rcu_utilization(TPS("Start context switch"));
 	rcu_sched_qs();
 	rcu_preempt_note_context_switch();
-	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
+	if (unlikely(raw_cpu_read(rcu_dynticks.rcu_sched_qs_mask)))
 		rcu_momentary_dyntick_idle();
 	trace_rcu_utilization(TPS("End context switch"));
 	barrier(); /* Avoid RCU read-side critical sections leaking up. */
@@ -524,7 +522,7 @@ void rcu_all_qs(void)
 	unsigned long flags;
 
 	barrier(); /* Avoid RCU read-side critical sections leaking down. */
-	if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) {
+	if (unlikely(raw_cpu_read(rcu_dynticks.rcu_sched_qs_mask))) {
 		local_irq_save(flags);
 		rcu_momentary_dyntick_idle();
 		local_irq_restore(flags);
@@ -1351,7 +1349,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	 * is set too high, we override with half of the RCU CPU stall
 	 * warning delay.
 	 */
-	rcrmp = &per_cpu(rcu_sched_qs_mask, rdp->cpu);
+	rcrmp = &per_cpu(rcu_dynticks.rcu_sched_qs_mask, rdp->cpu);
 	if (time_after(jiffies, rdp->rsp->gp_start + jtsq) ||
 	    time_after(jiffies, rdp->rsp->jiffies_resched)) {
 		if (!(READ_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {

kernel/rcu/tree.h

@@ -113,6 +113,7 @@ struct rcu_dynticks {
 				    /* Process level is worth LLONG_MAX/2. */
 	int dynticks_nmi_nesting;   /* Track NMI nesting level. */
 	atomic_t dynticks;	    /* Even value for idle, else odd. */
+	int rcu_sched_qs_mask;      /* GP old, need quiescent state. */
 #ifdef CONFIG_NO_HZ_FULL_SYSIDLE
 	long long dynticks_idle_nesting;
 				    /* irq/process nesting level from idle. */