[PATCH RFC nohz_full 8/8] nohz_full: Force RCU's grace-period kthreads onto timekeeping CPU

[Paul E. McKenney]

From: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>

Because RCU's quiescent-state-forcing mechanism is used to drive the
full-system-idle state machine, and because this mechanism is executed
by RCU's grace-period kthreads, this commit forces these kthreads to
run on the timekeeping CPU (tick_do_timer_cpu).  To do otherwise would
mean that the RCU grace-period kthreads would force the system into
non-idle state every time they drove the state machine, which would
be just a bit on the futile side.

Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
---
 kernel/rcutree.c        |  1 +
 kernel/rcutree.h        |  1 +
 kernel/rcutree_plugin.h | 20 +++++++++++++++++++-
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 10e74d6..0fe28ed 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1289,6 +1289,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
+	rcu_bind_gp_kthread();
 	raw_spin_lock_irq(&rnp->lock);
 	rsp->gp_flags = 0; /* Clear all flags: New grace period. */
 
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 8e869fc..7a8cdb4 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -561,6 +561,7 @@ static void rcu_sysidle_nmi_jiffies(struct rcu_dynticks *rdtp);
 static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
 				  unsigned long *maxj);
 static bool is_sysidle_rcu_state(struct rcu_state *rsp);
+static void rcu_bind_gp_kthread(void);
 static void rcu_sysidle_report(struct rcu_state *rsp, int isidle,
 			       unsigned long maxj);
 static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index c3ce268..39a3091 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -2553,7 +2553,7 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
 	if (!*isidle || rdp->rsp != rcu_sysidle_state ||
 	    cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu)
 		return;
-	/* WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu); */
+	WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu);
 
 	/*
 	 * Pick up current idle and NMI-nesting counters, check.  We check
@@ -2593,6 +2593,20 @@ static bool is_sysidle_rcu_state(struct rcu_state *rsp)
 }
 
 /*
+ * Bind the grace-period kthread for the sysidle flavor of RCU to the
+ * timekeeping CPU.
+ */
+static void rcu_bind_gp_kthread(void)
+{
+	int cpu = ACCESS_ONCE(tick_do_timer_cpu);
+
+	if (cpu < 0 || cpu >= nr_cpu_ids)
+		return;
+	if (raw_smp_processor_id() != cpu)
+		set_cpus_allowed_ptr(current, cpumask_of(cpu));
+}
+
+/*
  * Return a delay in jiffies based on the number of CPUs, rcu_node
  * leaf fanout, and jiffies tick rate.  The idea is to allow larger
  * systems more time to transition to full-idle state in order to
@@ -2764,6 +2778,10 @@ static bool is_sysidle_rcu_state(struct rcu_state *rsp)
 	return false;
 }
 
+static void rcu_bind_gp_kthread(void)
+{
+}
+
 static void rcu_sysidle_report(struct rcu_state *rsp, int isidle,
 			       unsigned long maxj)
 {
-- 
1.8.1.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/