sched: Make struct sched_statistics independent of fair sched class

If we want to use the schedstats facility to trace other sched classes, we
should make it independent of fair sched class. The struct sched_statistics
is the schedular statistics of a task_struct or a task_group. So we can
move it into struct task_struct and struct task_group to achieve the goal.

After the patch, schestats are orgnized as follows,

    struct task_struct {
       ...
       struct sched_entity se;
       struct sched_rt_entity rt;
       struct sched_dl_entity dl;
       ...
       struct sched_statistics stats;
       ...
   };

Regarding the task group, schedstats is only supported for fair group
sched, and a new struct sched_entity_stats is introduced, suggested by
Peter -

    struct sched_entity_stats {
        struct sched_entity     se;
        struct sched_statistics stats;
    } __no_randomize_layout;

Then with the se in a task_group, we can easily get the stats.

The sched_statistics members may be frequently modified when schedstats is
enabled, in order to avoid impacting on random data which may in the same
cacheline with them, the struct sched_statistics is defined as cacheline
aligned.

As this patch changes the core struct of scheduler, so I verified the
performance it may impact on the scheduler with 'perf bench sched
pipe', suggested by Mel. Below is the result, in which all the values
are 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 earlier version, that is
 because my old test machine is destroyed so I have to use a new
 different test machine.]

Almost no impact on the sched performance.

No functional change.

[lkp@intel.com: reported build failure in earlier 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/20210905143547.4668-3-laoar.shao@gmail.com

1 files changed, 48 insertions, 44 deletions

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 34913a7f775a..76fd38ea844c 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -449,9 +449,11 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	struct sched_entity *se = tg->se[cpu];
 
 #define P(F)		SEQ_printf(m, "  .%-30s: %lld\n",	#F, (long long)F)
-#define P_SCHEDSTAT(F)	SEQ_printf(m, "  .%-30s: %lld\n",	#F, (long long)schedstat_val(F))
+#define P_SCHEDSTAT(F)	SEQ_printf(m, "  .%-30s: %lld\n",	\
+		#F, (long long)schedstat_val(stats->F))
 #define PN(F)		SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))
-#define PN_SCHEDSTAT(F)	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(F)))
+#define PN_SCHEDSTAT(F)	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", \
+		#F, SPLIT_NS((long long)schedstat_val(stats->F)))
 
 	if (!se)
 		return;
@@ -461,16 +463,18 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	PN(se->sum_exec_runtime);
 
 	if (schedstat_enabled()) {
-		PN_SCHEDSTAT(se->statistics.wait_start);
-		PN_SCHEDSTAT(se->statistics.sleep_start);
-		PN_SCHEDSTAT(se->statistics.block_start);
-		PN_SCHEDSTAT(se->statistics.sleep_max);
-		PN_SCHEDSTAT(se->statistics.block_max);
-		PN_SCHEDSTAT(se->statistics.exec_max);
-		PN_SCHEDSTAT(se->statistics.slice_max);
-		PN_SCHEDSTAT(se->statistics.wait_max);
-		PN_SCHEDSTAT(se->statistics.wait_sum);
-		P_SCHEDSTAT(se->statistics.wait_count);
+               struct sched_statistics *stats =  __schedstats_from_se(se);
+
+		PN_SCHEDSTAT(wait_start);
+		PN_SCHEDSTAT(sleep_start);
+		PN_SCHEDSTAT(block_start);
+		PN_SCHEDSTAT(sleep_max);
+		PN_SCHEDSTAT(block_max);
+		PN_SCHEDSTAT(exec_max);
+		PN_SCHEDSTAT(slice_max);
+		PN_SCHEDSTAT(wait_max);
+		PN_SCHEDSTAT(wait_sum);
+		P_SCHEDSTAT(wait_count);
 	}
 
 	P(se->load.weight);
@@ -537,9 +541,9 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		p->prio);
 
 	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
-		SPLIT_NS(schedstat_val_or_zero(p->se.statistics.wait_sum)),
+		SPLIT_NS(schedstat_val_or_zero(p->stats.wait_sum)),
 		SPLIT_NS(p->se.sum_exec_runtime),
-		SPLIT_NS(schedstat_val_or_zero(p->se.statistics.sum_sleep_runtime)));
+		SPLIT_NS(schedstat_val_or_zero(p->stats.sum_sleep_runtime)));
 
 #ifdef CONFIG_NUMA_BALANCING
 	SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
@@ -958,8 +962,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		"---------------------------------------------------------"
 		"----------\n");
 
-#define P_SCHEDSTAT(F)  __PS(#F, schedstat_val(p->F))
-#define PN_SCHEDSTAT(F) __PSN(#F, schedstat_val(p->F))
+#define P_SCHEDSTAT(F)  __PS(#F, schedstat_val(p->stats.F))
+#define PN_SCHEDSTAT(F) __PSN(#F, schedstat_val(p->stats.F))
 
 	PN(se.exec_start);
 	PN(se.vruntime);
@@ -972,33 +976,33 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	if (schedstat_enabled()) {
 		u64 avg_atom, avg_per_cpu;
 
-		PN_SCHEDSTAT(se.statistics.sum_sleep_runtime);
-		PN_SCHEDSTAT(se.statistics.wait_start);
-		PN_SCHEDSTAT(se.statistics.sleep_start);
-		PN_SCHEDSTAT(se.statistics.block_start);
-		PN_SCHEDSTAT(se.statistics.sleep_max);
-		PN_SCHEDSTAT(se.statistics.block_max);
-		PN_SCHEDSTAT(se.statistics.exec_max);
-		PN_SCHEDSTAT(se.statistics.slice_max);
-		PN_SCHEDSTAT(se.statistics.wait_max);
-		PN_SCHEDSTAT(se.statistics.wait_sum);
-		P_SCHEDSTAT(se.statistics.wait_count);
-		PN_SCHEDSTAT(se.statistics.iowait_sum);
-		P_SCHEDSTAT(se.statistics.iowait_count);
-		P_SCHEDSTAT(se.statistics.nr_migrations_cold);
-		P_SCHEDSTAT(se.statistics.nr_failed_migrations_affine);
-		P_SCHEDSTAT(se.statistics.nr_failed_migrations_running);
-		P_SCHEDSTAT(se.statistics.nr_failed_migrations_hot);
-		P_SCHEDSTAT(se.statistics.nr_forced_migrations);
-		P_SCHEDSTAT(se.statistics.nr_wakeups);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_sync);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_migrate);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_local);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_remote);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_affine);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_affine_attempts);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_passive);
-		P_SCHEDSTAT(se.statistics.nr_wakeups_idle);
+		PN_SCHEDSTAT(sum_sleep_runtime);
+		PN_SCHEDSTAT(wait_start);
+		PN_SCHEDSTAT(sleep_start);
+		PN_SCHEDSTAT(block_start);
+		PN_SCHEDSTAT(sleep_max);
+		PN_SCHEDSTAT(block_max);
+		PN_SCHEDSTAT(exec_max);
+		PN_SCHEDSTAT(slice_max);
+		PN_SCHEDSTAT(wait_max);
+		PN_SCHEDSTAT(wait_sum);
+		P_SCHEDSTAT(wait_count);
+		PN_SCHEDSTAT(iowait_sum);
+		P_SCHEDSTAT(iowait_count);
+		P_SCHEDSTAT(nr_migrations_cold);
+		P_SCHEDSTAT(nr_failed_migrations_affine);
+		P_SCHEDSTAT(nr_failed_migrations_running);
+		P_SCHEDSTAT(nr_failed_migrations_hot);
+		P_SCHEDSTAT(nr_forced_migrations);
+		P_SCHEDSTAT(nr_wakeups);
+		P_SCHEDSTAT(nr_wakeups_sync);
+		P_SCHEDSTAT(nr_wakeups_migrate);
+		P_SCHEDSTAT(nr_wakeups_local);
+		P_SCHEDSTAT(nr_wakeups_remote);
+		P_SCHEDSTAT(nr_wakeups_affine);
+		P_SCHEDSTAT(nr_wakeups_affine_attempts);
+		P_SCHEDSTAT(nr_wakeups_passive);
+		P_SCHEDSTAT(nr_wakeups_idle);
 
 		avg_atom = p->se.sum_exec_runtime;
 		if (nr_switches)
@@ -1064,7 +1068,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 void proc_sched_set_task(struct task_struct *p)
 {
 #ifdef CONFIG_SCHEDSTATS
-	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
+	memset(&p->stats, 0, sizeof(p->stats));
 #endif
 }