[Devel] [PATCH RHEL8 COMMIT] sched/stat: account ctxsw per task group

[Konstantin Khorenko]

The commit is pushed to "branch-rh8-4.18.0-193.6.3.vz8.4.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh8-4.18.0-193.6.3.vz8.4.15
------>
commit b8f0da164311bd1acf6b78e3cbaa73ab8c2875f3
Author: Vladimir Davydov <vdavydov.dev at gmail.com>
Date:   Thu Mar 14 21:00:44 2013 +0400

    sched/stat: account ctxsw per task group
    
    This is a backport of diff-sched-account-ctxsw-per-task-group:
    
     Subject: sched: account ctxsw per task group
     Date: Fri, 28 Dec 2012 15:09:45 +0400
    
    * [sched] the number of context switches should be reported correctly
            inside a CT in /proc/stat (PSBM-18113)
    
    For /proc/stat:ctxt to be correct inside containers.
    
    https://jira.sw.ru/browse/PSBM-18113
    
    Signed-off-by: Vladimir Davydov <vdavydov at parallels.com>
    
    (cherry picked from vz7 commit d388f0bf64adb74cd62c4deff58e181bd63d62ac)
    Signed-off-by: Konstantin Khorenko <khorenko at virtuozzo.com>
    Reviewed-by: Andrey Ryabinin <aryabinin at virtuozzo.com>
---
 kernel/sched/cpuacct.c |  4 +++-
 kernel/sched/fair.c    | 14 ++++++++++++--
 kernel/sched/sched.h   |  3 +++
 3 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index aafaee1f0722..8756560d0b4f 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -647,6 +647,7 @@ int cpu_cgroup_proc_stat(struct cgroup_subsys_state *cpu_css,
 	struct kernel_cpustat *kcpustat;
 	unsigned long tg_nr_running = 0;
 	unsigned long tg_nr_iowait = 0;
+	unsigned long long tg_nr_switches = 0;
 
 	getboottime64(&boottime);
 
@@ -665,6 +666,7 @@ int cpu_cgroup_proc_stat(struct cgroup_subsys_state *cpu_css,
 #ifdef CONFIG_FAIR_GROUP_SCHED
 		tg_nr_running += tg->cfs_rq[i]->h_nr_running;
 		tg_nr_iowait  += tg->cfs_rq[i]->nr_iowait;
+		tg_nr_switches += tg->cfs_rq[i]->nr_switches;
 #endif
 #ifdef CONFIG_RT_GROUP_SCHED
 		tg_nr_running += tg->rt_rq[i]->rt_nr_running;
@@ -738,7 +740,7 @@ int cpu_cgroup_proc_stat(struct cgroup_subsys_state *cpu_css,
 		   "processes %lu\n"
 		   "procs_running %lu\n"
 		   "procs_blocked %lu\n",
-		   nr_context_switches(),
+		   tg_nr_switches,
 		   (unsigned long long)boot_sec,
 		   total_forks,
 		   tg_nr_running,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6546d8511417..0b9bb108625a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4153,6 +4153,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	clear_buddies(cfs_rq, se);
 
+	if (cfs_rq->prev == se)
+		cfs_rq->prev = NULL;
+
 	if (se != cfs_rq->curr)
 		__dequeue_entity(cfs_rq, se);
 	se->on_rq = 0;
@@ -4167,8 +4170,12 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	if (!(flags & DEQUEUE_SLEEP))
 		se->vruntime -= cfs_rq->min_vruntime;
 
-	/* return excess runtime on last dequeue */
-	return_cfs_rq_runtime(cfs_rq);
+	if (!cfs_rq->nr_running) {
+		/* return excess runtime on last dequeue */
+		return_cfs_rq_runtime(cfs_rq);
+		/* account switch to idle task */
+		cfs_rq->nr_switches++;
+	}
 
 	update_cfs_group(se);
 
@@ -4242,6 +4249,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 	update_stats_curr_start(cfs_rq, se);
 	cfs_rq->curr = se;
+	if (cfs_rq->prev != se)
+		cfs_rq->nr_switches++;
 
 	/*
 	 * Track our maximum slice length, if the CPU's load is at
@@ -4341,6 +4350,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 		__enqueue_entity(cfs_rq, prev);
 		/* in !on_rq case, update occurred at dequeue */
 		update_load_avg(cfs_rq, prev, 0);
+		cfs_rq->prev = prev;
 	}
 	cfs_rq->curr = NULL;
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d8331e5b4c4f..3d55b45f1ea6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -542,6 +542,9 @@ struct cfs_rq {
 	struct sched_entity	*next;
 	struct sched_entity	*last;
 	struct sched_entity	*skip;
+	struct sched_entity	*prev;
+
+	u64 nr_switches;
 
 #ifdef	CONFIG_SCHED_DEBUG
 	unsigned int		nr_spread_over;