[PATCH v3 tip/core/rcu 22/34] rcu-tasks: Provide boot parameter to delay IPIs until late in grace period

[paulmck]

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

This commit provides a rcupdate.rcu_task_ipi_delay kernel boot parameter
that specifies how old the RCU tasks trace grace period must be before
the grace-period kthread starts sending IPIs.  This delay allows more
tasks to pass through rcu_tasks_qs() quiescent states, thus reducing
(or even eliminating) the number of IPIs that must be sent.

On a short rcutorture test setting this kernel boot parameter to HZ/2
resulted in zero IPIs for all 877 RCU-tasks trace grace periods that
elapsed during that test.

Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
---
 Documentation/admin-guide/kernel-parameters.txt |  7 +++++++
 kernel/rcu/tasks.h                              | 15 ++++++++++-----
 2 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index df2baf9..6f3b3be 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4246,6 +4246,13 @@
 			only normal grace-period primitives.  No effect
 			on CONFIG_TINY_RCU kernels.
 
+	rcupdate.rcu_task_ipi_delay= [KNL]
+			Set time in jiffies during which RCU tasks will
+			avoid sending IPIs, starting with the beginning
+			of a given grace period.  Setting a large
+			number avoids disturbing real-time workloads,
+			but lengthens grace periods.
+
 	rcupdate.rcu_task_stall_timeout= [KNL]
 			Set timeout in jiffies for RCU task stall warning
 			messages.  Disable with a value less than or equal
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index fa9c069..a034f48 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -74,6 +74,11 @@ static struct rcu_tasks rt_name =					\
 /* Track exiting tasks in order to allow them to be waited for. */
 DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
 
+/* Avoid IPIing CPUs early in the grace period. */
+#define RCU_TASK_IPI_DELAY (HZ / 2)
+static int rcu_task_ipi_delay __read_mostly = RCU_TASK_IPI_DELAY;
+module_param(rcu_task_ipi_delay, int, 0644);
+
 /* Control stall timeouts.  Disable with <= 0, otherwise jiffies till stall. */
 #define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
 static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
@@ -713,6 +718,10 @@ DECLARE_WAIT_QUEUE_HEAD(trc_wait);	// List of holdout tasks.
 // Record outstanding IPIs to each CPU.  No point in sending two...
 static DEFINE_PER_CPU(bool, trc_ipi_to_cpu);
 
+void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
+DEFINE_RCU_TASKS(rcu_tasks_trace, rcu_tasks_wait_gp, call_rcu_tasks_trace,
+		 "RCU Tasks Trace");
+
 /* If we are the last reader, wake up the grace-period kthread. */
 void rcu_read_unlock_trace_special(struct task_struct *t)
 {
@@ -825,7 +834,7 @@ static void trc_wait_for_one_reader(struct task_struct *t,
 
 	// If currently running, send an IPI, either way, add to list.
 	trc_add_holdout(t, bhp);
-	if (task_curr(t)) {
+	if (task_curr(t) && time_after(jiffies, rcu_tasks_trace.gp_start + rcu_task_ipi_delay)) {
 		// The task is currently running, so try IPIing it.
 		cpu = task_cpu(t);
 
@@ -994,10 +1003,6 @@ void exit_tasks_rcu_finish_trace(struct task_struct *t)
 		rcu_read_unlock_trace_special(t);
 }
 
-void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
-DEFINE_RCU_TASKS(rcu_tasks_trace, rcu_tasks_wait_gp, call_rcu_tasks_trace,
-		 "RCU Tasks Trace");
-
 /**
  * call_rcu_tasks_trace() - Queue a callback trace task-based grace period
  * @rhp: structure to be used for queueing the RCU updates.
-- 
2.9.5