From b2a02fc43a1f40ef4eb2fb2b06357382608d4d84 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 26 May 2020 18:11:01 +0200
Subject: [PATCH] smp: Optimize send_call_function_single_ipi()

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

[ mingo: Fix UP build bug. ]

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200526161907.953304789@infradead.org
---
 kernel/sched/core.c  | 10 ++++++++++
 kernel/sched/idle.c  |  5 +++++
 kernel/sched/sched.h |  7 ++++---
 kernel/smp.c         | 16 +++++++++++++++-
 4 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2cacc1e44a84..fa0d4990618e 100644
--- 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
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index b743bf38f08f..387fd75ee6f7 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -289,6 +289,11 @@ static void do_idle(void)
 	 */
 	smp_mb__after_atomic();
 
+	/*
+	 * RCU relies on this call to be done outside of an RCU read-side
+	 * critical section.
+	 */
+	flush_smp_call_function_from_idle();
 	sched_ttwu_pending();
 	schedule_idle();
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3c163cb5493f..75b062999c43 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1506,11 +1506,12 @@ static inline void unregister_sched_domain_sysctl(void)
 }
 #endif
 
-#else
+extern void flush_smp_call_function_from_idle(void);
 
+#else /* !CONFIG_SMP: */
+static inline void flush_smp_call_function_from_idle(void) { }
 static inline void sched_ttwu_pending(void) { }
-
-#endif /* CONFIG_SMP */
+#endif
 
 #include "stats.h"
 #include "autogroup.h"
diff --git a/kernel/smp.c b/kernel/smp.c
index f720e38e880d..9f1181375141 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -135,6 +135,8 @@ static __always_inline void csd_unlock(call_single_data_t *csd)
 
 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, call_single_data_t *csd,
 	 * 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_queue(bool warn_cpu_offline)
 	}
 }
 
+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.