rcu: Simplify rcu_read_unlock_special() quiescent-state accounting

The earlier approach required two scheduling-clock ticks to note an
preemptable-RCU quiescent state in the situation in which the
scheduling-clock interrupt is unlucky enough to always interrupt an
RCU read-side critical section.

With this change, the quiescent state is instead noted by the
outermost rcu_read_unlock() immediately following the first
scheduling-clock tick, or, alternatively, by the first subsequent
context switch.  Therefore, this change also speeds up grace
periods.

Suggested-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: akpm@linux-foundation.org
Cc: mathieu.desnoyers@polymtl.ca
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
LKML-Reference: <12528585111945-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index e9a4ae9..6c99553 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -107,27 +107,23 @@
  */
 void rcu_sched_qs(int cpu)
 {
-	unsigned long flags;
 	struct rcu_data *rdp;
 
-	local_irq_save(flags);
 	rdp = &per_cpu(rcu_sched_data, cpu);
-	rdp->passed_quiesc = 1;
 	rdp->passed_quiesc_completed = rdp->completed;
-	rcu_preempt_qs(cpu);
-	local_irq_restore(flags);
+	barrier();
+	rdp->passed_quiesc = 1;
+	rcu_preempt_note_context_switch(cpu);
 }
 
 void rcu_bh_qs(int cpu)
 {
-	unsigned long flags;
 	struct rcu_data *rdp;
 
-	local_irq_save(flags);
 	rdp = &per_cpu(rcu_bh_data, cpu);
-	rdp->passed_quiesc = 1;
 	rdp->passed_quiesc_completed = rdp->completed;
-	local_irq_restore(flags);
+	barrier();
+	rdp->passed_quiesc = 1;
 }
 
 #ifdef CONFIG_NO_HZ
@@ -615,6 +611,7 @@
 
 	/* Advance to a new grace period and initialize state. */
 	rsp->gpnum++;
+	WARN_ON_ONCE(rsp->signaled == RCU_GP_INIT);
 	rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */
 	rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
 	record_gp_stall_check_time(rsp);