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, 103 insertions, 0 deletions

diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 3f93fc3b5648..fad781ca7791 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -4,6 +4,109 @@
  */
 #include "sched.h"
 
+void __update_stats_wait_start(struct rq *rq, struct task_struct *p,
+			       struct sched_statistics *stats)
+{
+	u64 wait_start, prev_wait_start;
+
+	wait_start = rq_clock(rq);
+	prev_wait_start = schedstat_val(stats->wait_start);
+
+	if (p && likely(wait_start > prev_wait_start))
+		wait_start -= prev_wait_start;
+
+	__schedstat_set(stats->wait_start, wait_start);
+}
+
+void __update_stats_wait_end(struct rq *rq, struct task_struct *p,
+			     struct sched_statistics *stats)
+{
+	u64 delta = rq_clock(rq) - schedstat_val(stats->wait_start);
+
+	if (p) {
+		if (task_on_rq_migrating(p)) {
+			/*
+			 * Preserve migrating task's wait time so wait_start
+			 * time stamp can be adjusted to accumulate wait time
+			 * prior to migration.
+			 */
+			__schedstat_set(stats->wait_start, delta);
+
+			return;
+		}
+
+		trace_sched_stat_wait(p, delta);
+	}
+
+	__schedstat_set(stats->wait_max,
+			max(schedstat_val(stats->wait_max), delta));
+	__schedstat_inc(stats->wait_count);
+	__schedstat_add(stats->wait_sum, delta);
+	__schedstat_set(stats->wait_start, 0);
+}
+
+void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
+				    struct sched_statistics *stats)
+{
+	u64 sleep_start, block_start;
+
+	sleep_start = schedstat_val(stats->sleep_start);
+	block_start = schedstat_val(stats->block_start);
+
+	if (sleep_start) {
+		u64 delta = rq_clock(rq) - sleep_start;
+
+		if ((s64)delta < 0)
+			delta = 0;
+
+		if (unlikely(delta > schedstat_val(stats->sleep_max)))
+			__schedstat_set(stats->sleep_max, delta);
+
+		__schedstat_set(stats->sleep_start, 0);
+		__schedstat_add(stats->sum_sleep_runtime, delta);
+
+		if (p) {
+			account_scheduler_latency(p, delta >> 10, 1);
+			trace_sched_stat_sleep(p, delta);
+		}
+	}
+
+	if (block_start) {
+		u64 delta = rq_clock(rq) - block_start;
+
+		if ((s64)delta < 0)
+			delta = 0;
+
+		if (unlikely(delta > schedstat_val(stats->block_max)))
+			__schedstat_set(stats->block_max, delta);
+
+		__schedstat_set(stats->block_start, 0);
+		__schedstat_add(stats->sum_sleep_runtime, delta);
+
+		if (p) {
+			if (p->in_iowait) {
+				__schedstat_add(stats->iowait_sum, delta);
+				__schedstat_inc(stats->iowait_count);
+				trace_sched_stat_iowait(p, delta);
+			}
+
+			trace_sched_stat_blocked(p, delta);
+
+			/*
+			 * Blocking time is in units of nanosecs, so shift by
+			 * 20 to get a milliseconds-range estimation of the
+			 * amount of time that the task spent sleeping:
+			 */
+			if (unlikely(prof_on == SLEEP_PROFILING)) {
+				profile_hits(SLEEP_PROFILING,
+					     (void *)get_wchan(p),
+					     delta >> 20);
+			}
+			account_scheduler_latency(p, delta >> 10, 0);
+		}
+	}
+}
+
 /*
  * Current schedstat API version.
  *