sched: Make schedstats helpers independent of fair sched class

The original prototype of the schedstats helpers are

  update_stats_wait_*(struct cfs_rq *cfs_rq, struct sched_entity *se)

The cfs_rq in these helpers is used to get the rq_clock, and the se is
used to get the struct sched_statistics and the struct task_struct. In
order to make these helpers available by all sched classes, we can pass
the rq, sched_statistics and task_struct directly.

Then the new helpers are

  update_stats_wait_*(struct rq *rq, struct task_struct *p,
                      struct sched_statistics *stats)

which are independent of fair sched class.

To avoid vmlinux growing too large or introducing ovehead when
!schedstat_enabled(), some new helpers after schedstat_enabled() are also
introduced, Suggested by Mel. These helpers are in sched/stats.c,

  __update_stats_wait_*(struct rq *rq, struct task_struct *p,
                        struct sched_statistics *stats)

The size of vmlinux as follows,
                      Before          After
  Size of vmlinux     826308552       826304640
The size is a litte smaller as some functions are not inlined again after
the change.

I also compared the sched performance with 'perf bench sched pipe',
suggested by Mel. The result as followsi (in usecs/op),
                             Before                After
  kernel.sched_schedstats=0  5.2~5.4               5.2~5.4
  kernel.sched_schedstats=1  5.3~5.5               5.3~5.5

[These data is a little difference with the prev version, that is
because my old test machine is destroyed so I have to use a new
different test machine.]
Almost no difference.

No functional change.

[lkp@intel.com: reported build failure in prev version]

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Link: https://lore.kernel.org/r/20210905143547.4668-4-laoar.shao@gmail.com

1 files changed, 30 insertions, 0 deletions

diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index fb6022e860af..cfb0893a83d4 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -2,6 +2,8 @@
 
 #ifdef CONFIG_SCHEDSTATS
 
+extern struct static_key_false sched_schedstats;
+
 /*
  * Expects runqueue lock to be held for atomicity of update
  */
@@ -40,6 +42,29 @@ rq_sched_info_dequeue(struct rq *rq, unsigned long long delta)
 #define   schedstat_val(var)		(var)
 #define   schedstat_val_or_zero(var)	((schedstat_enabled()) ? (var) : 0)
 
+void __update_stats_wait_start(struct rq *rq, struct task_struct *p,
+			       struct sched_statistics *stats);
+
+void __update_stats_wait_end(struct rq *rq, struct task_struct *p,
+			     struct sched_statistics *stats);
+void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
+				    struct sched_statistics *stats);
+
+static inline void
+check_schedstat_required(void)
+{
+	if (schedstat_enabled())
+		return;
+
+	/* Force schedstat enabled if a dependent tracepoint is active */
+	if (trace_sched_stat_wait_enabled()    ||
+	    trace_sched_stat_sleep_enabled()   ||
+	    trace_sched_stat_iowait_enabled()  ||
+	    trace_sched_stat_blocked_enabled() ||
+	    trace_sched_stat_runtime_enabled())
+		printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, stat_blocked and stat_runtime require the kernel parameter schedstats=enable or kernel.sched_schedstats=1\n");
+}
+
 #else /* !CONFIG_SCHEDSTATS: */
 
 static inline void rq_sched_info_arrive  (struct rq *rq, unsigned long long delta) { }
@@ -55,6 +80,11 @@ static inline void rq_sched_info_depart  (struct rq *rq, unsigned long long delt
 # define   schedstat_val(var)		0
 # define   schedstat_val_or_zero(var)	0
 
+# define __update_stats_wait_start(rq, p, stats)       do { } while (0)
+# define __update_stats_wait_end(rq, p, stats)         do { } while (0)
+# define __update_stats_enqueue_sleeper(rq, p, stats)  do { } while (0)
+# define check_schedstat_required()                    do { } while (0)
+
 #endif /* CONFIG_SCHEDSTATS */
 
 #ifdef CONFIG_FAIR_GROUP_SCHED