[RFC][PATCH 4/7] smp: Optimize send_call_function_single_ipi()

[Peter Zijlstra]

Just like the ttwu_queue_remote() IPI, make use of _TIF_POLLING_NRFLAG
to avoid sending IPIs to idle CPUs.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 kernel/sched/core.c  |   10 ++++++++++
 kernel/sched/idle.c  |    1 +
 kernel/sched/sched.h |    2 ++
 kernel/smp.c         |   16 +++++++++++++++-
 4 files changed, 28 insertions(+), 1 deletion(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2296,6 +2296,16 @@ static void wake_csd_func(void *info)
 	sched_ttwu_pending();
 }
 
+void send_call_function_single_ipi(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+
+	if (!set_nr_if_polling(rq->idle))
+		arch_send_call_function_single_ipi(cpu);
+	else
+		trace_sched_wake_idle_without_ipi(cpu);
+}
+
 /*
  * Queue a task on the target CPUs wake_list and wake the CPU via IPI if
  * necessary. The wakee CPU on receipt of the IPI will queue the task
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -289,6 +289,7 @@ static void do_idle(void)
 	 */
 	smp_mb__after_atomic();
 
+	flush_smp_call_function_from_idle();
 	sched_ttwu_pending();
 	schedule_idle();
 
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1506,6 +1506,8 @@ static inline void unregister_sched_doma
 }
 #endif
 
+extern void flush_smp_call_function_from_idle(void);
+
 #else
 
 static inline void sched_ttwu_pending(void) { }
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -135,6 +135,8 @@ static __always_inline void csd_unlock(c
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data);
 
+extern void send_call_function_single_ipi(int cpu);
+
 /*
  * Insert a previously allocated call_single_data_t element
  * for execution on the given CPU. data must already have
@@ -178,7 +180,7 @@ static int generic_exec_single(int cpu,
 	 * equipped to do the right thing...
 	 */
 	if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
-		arch_send_call_function_single_ipi(cpu);
+		send_call_function_single_ipi(cpu);
 
 	return 0;
 }
@@ -278,6 +280,18 @@ static void flush_smp_call_function_queu
 	}
 }
 
+void flush_smp_call_function_from_idle(void)
+{
+	unsigned long flags;
+
+	if (llist_empty(this_cpu_ptr(&call_single_queue)))
+		return;
+
+	local_irq_save(flags);
+	flush_smp_call_function_queue(true);
+	local_irq_restore(flags);
+}
+
 /*
  * smp_call_function_single - Run a function on a specific CPU
  * @func: The function to run. This must be fast and non-blocking.