rcu: Round FAST_NO_HZ lazy timeout to nearest second

Currently, if several CPUs in the same package have all lazy RCU
callbacks, their wakeups will be uncorrelated.  If all the CPUs are in the
same power domain (as is often the case), this will result in unnecessary
power-ups of the package.  This commit therefore uses round_jiffies()
to round the timeouts to a second boundary, increasing the odds that
they can be coalesced with each other or with other timeouts.

Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 3e48994..c28d255 100644 (file)
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1968,7 +1968,7 @@ static void rcu_idle_count_callbacks_posted(void)
  */
 #define RCU_IDLE_FLUSHES 5             /* Number of dyntick-idle tries. */
 #define RCU_IDLE_OPT_FLUSHES 3         /* Optional dyntick-idle tries. */
-#define RCU_IDLE_GP_DELAY 6            /* Roughly one grace period. */
+#define RCU_IDLE_GP_DELAY 4            /* Roughly one grace period. */
 #define RCU_IDLE_LAZY_GP_DELAY (6 * HZ)        /* Roughly six seconds. */
 
 /*
@@ -2047,10 +2047,13 @@ int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
                return 1;
        }
        /* Set up for the possibility that RCU will post a timer. */
-       if (rcu_cpu_has_nonlazy_callbacks(cpu))
-               *delta_jiffies = RCU_IDLE_GP_DELAY;
-       else
-               *delta_jiffies = RCU_IDLE_LAZY_GP_DELAY;
+       if (rcu_cpu_has_nonlazy_callbacks(cpu)) {
+               *delta_jiffies = round_up(RCU_IDLE_GP_DELAY + jiffies,
+                                         RCU_IDLE_GP_DELAY) - jiffies;
+       } else {
+               *delta_jiffies = jiffies + RCU_IDLE_LAZY_GP_DELAY;
+               *delta_jiffies = round_jiffies(*delta_jiffies) - jiffies;
+       }
        return 0;
 }
 
@@ -2187,10 +2190,11 @@ static void rcu_prepare_for_idle(int cpu)
                if (rcu_cpu_has_nonlazy_callbacks(cpu)) {
                        trace_rcu_prep_idle("Dyntick with callbacks");
                        rdtp->idle_gp_timer_expires =
-                                          jiffies + RCU_IDLE_GP_DELAY;
+                               round_up(jiffies + RCU_IDLE_GP_DELAY,
+                                        RCU_IDLE_GP_DELAY);
                } else {
                        rdtp->idle_gp_timer_expires =
-                                          jiffies + RCU_IDLE_LAZY_GP_DELAY;
+                               round_jiffies(jiffies + RCU_IDLE_LAZY_GP_DELAY);
                        trace_rcu_prep_idle("Dyntick with lazy callbacks");
                }
                tp = &rdtp->idle_gp_timer;