rcu/nocb: Avoid polling when my_rdp->nocb_head_rdp list is empty

Currently, if the 'rcu_nocb_poll' kernel boot parameter is enabled, all
rcuog kthreads enter polling mode.  However, if all of a given group
of rcuo kthreads correspond to CPUs that have been de-offloaded, the
corresponding rcuog kthread will nonetheless still wake up periodically,
unnecessarily consuming power and perturbing workloads.  Fortunately,
this situation is easily detected by the fact that the rcuog kthread's
CPU's rcu_data structure's ->nocb_head_rdp list is empty.

This commit saves power and avoids unnecessarily perturbing workloads
by putting an rcuog kthread to sleep during any time period when all of
its rcuo kthreads' CPUs are de-offloaded.

Co-developed-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>

diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index fa8e4f8..a8f574d 100644 (file)
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -584,6 +584,14 @@ static int nocb_gp_toggle_rdp(struct rcu_data *rdp,
        return ret;
 }
 
+static void nocb_gp_sleep(struct rcu_data *my_rdp, int cpu)
+{
+       trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Sleep"));
+       swait_event_interruptible_exclusive(my_rdp->nocb_gp_wq,
+                                       !READ_ONCE(my_rdp->nocb_gp_sleep));
+       trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("EndSleep"));
+}
+
 /*
  * No-CBs GP kthreads come here to wait for additional callbacks to show up
  * or for grace periods to end.
@@ -701,13 +709,19 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
                /* Polling, so trace if first poll in the series. */
                if (gotcbs)
                        trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Poll"));
-               schedule_timeout_idle(1);
+               if (list_empty(&my_rdp->nocb_head_rdp)) {
+                       raw_spin_lock_irqsave(&my_rdp->nocb_gp_lock, flags);
+                       if (!my_rdp->nocb_toggling_rdp)
+                               WRITE_ONCE(my_rdp->nocb_gp_sleep, true);
+                       raw_spin_unlock_irqrestore(&my_rdp->nocb_gp_lock, flags);
+                       /* Wait for any offloading rdp */
+                       nocb_gp_sleep(my_rdp, cpu);
+               } else {
+                       schedule_timeout_idle(1);
+               }
        } else if (!needwait_gp) {
                /* Wait for callbacks to appear. */
-               trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Sleep"));
-               swait_event_interruptible_exclusive(my_rdp->nocb_gp_wq,
-                               !READ_ONCE(my_rdp->nocb_gp_sleep));
-               trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("EndSleep"));
+               nocb_gp_sleep(my_rdp, cpu);
        } else {
                rnp = my_rdp->mynode;
                trace_rcu_this_gp(rnp, my_rdp, wait_gp_seq, TPS("StartWait"));