[PATCH 2/3] Provide and use an always inline version of finish_task_switch

[Xie Yuanbin <qq570070308@gmail.com>]

finish_task_switch is called during context switching,
inlining it can bring some performance benefits.

Add an always inline version `finish_task_switch_ainline` to be called
during context switching, and keep the original version for being called
elsewhere, so as to take into account the size impact.

Signed-off-by: Xie Yuanbin <qq570070308@gmail.com>
---
 kernel/sched/core.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1842285eac1e..6cb3f57c4d35 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5069,21 +5069,21 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
  * Note that we may have delayed dropping an mm in context_switch(). If
  * so, we finish that here outside of the runqueue lock. (Doing it
  * with the lock held can cause deadlocks; see schedule() for
  * details.)
  *
  * The context switch have flipped the stack from under us and restored the
  * local variables which were saved when this task called schedule() in the
  * past. 'prev == current' is still correct but we need to recalculate this_rq
  * because prev may have moved to another CPU.
  */
-static struct rq *finish_task_switch(struct task_struct *prev)
+static __always_inline struct rq *finish_task_switch_ainline(struct task_struct *prev)
 	__releases(rq->lock)
 {
 	struct rq *rq = this_rq();
 	struct mm_struct *mm = rq->prev_mm;
 	unsigned int prev_state;
 
 	/*
 	 * The previous task will have left us with a preempt_count of 2
 	 * because it left us after:
 	 *
@@ -5153,20 +5153,25 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 
 		/* Task is done with its stack. */
 		put_task_stack(prev);
 
 		put_task_struct_rcu_user(prev);
 	}
 
 	return rq;
 }
 
+static struct rq *finish_task_switch(struct task_struct *prev)
+{
+	return finish_task_switch_ainline(prev);
+}
+
 /**
  * schedule_tail - first thing a freshly forked thread must call.
  * @prev: the thread we just switched away from.
  */
 asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	__releases(rq->lock)
 {
 	/*
 	 * New tasks start with FORK_PREEMPT_COUNT, see there and
 	 * finish_task_switch() for details.
@@ -5247,21 +5252,21 @@ context_switch(struct rq *rq, struct task_struct *prev,
 
 	/* switch_mm_cid() requires the memory barriers above. */
 	switch_mm_cid(rq, prev, next);
 
 	prepare_lock_switch(rq, next, rf);
 
 	/* Here we just switch the register state and the stack. */
 	switch_to(prev, next, prev);
 	barrier();
 
-	return finish_task_switch(prev);
+	return finish_task_switch_ainline(prev);
 }
 
 /*
  * nr_running and nr_context_switches:
  *
  * externally visible scheduler statistics: current number of runnable
  * threads, total number of context switches performed since bootup.
  */
 unsigned int nr_running(void)
 {
-- 
2.51.0