[Devel] [PATCH RHEL8 COMMIT] sched: Account task_group::avenrun

[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.vz8.4.14
------>
commit 028c54e613a351bd48d8dc69cb8c833e69c089f1
Author: Konstantin Khorenko <khorenko at virtuozzo.com>
Date:   Mon Dec 11 23:40:07 2017 +0300

    sched: Account task_group::avenrun
    
    This patch is a part of vz7 commit (only avenrun part)
    34a1dc1e4e3d ("sched: Account task_group::cpustat,taskstats,avenrun")
    
      Extracted from "Initial patch".
    
      Signed-off-by: Kirill Tkhai <ktkhai at virtuozzo.com>
    
      +++
      ve/sched: Do not use kstat_glb_lock to update kstat_glob::nr_unint_avg
    
      kstat_glob::nr_unint_avg can't be updated in parallel on two or
      more cpus, so on modifications we have to protect against readers
      only.
    
      So, avoid using global kstat_glb_lock here, to minimize its
      sharing with another counters it protects.
    
      Signed-off-by: Kirill Tkhai <ktkhai at virtuozzo.com>
    
    (cherry picked from commit 715f311fdb4ab0b7922f9e53617c5821ae36bfaf)
    Signed-off-by: Konstantin Khorenko <khorenko at virtuozzo.com>
    
    v2: added a related hunk from another commit in do_sysinfo()
---
 include/linux/sched/loadavg.h |  2 ++
 kernel/sched/loadavg.c        | 38 ++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h          |  1 +
 kernel/sys.c                  |  4 ----
 4 files changed, 41 insertions(+), 4 deletions(-)

diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h
index 4859bea47a7b..3c0a0db53559 100644
--- a/include/linux/sched/loadavg.h
+++ b/include/linux/sched/loadavg.h
@@ -14,6 +14,8 @@
  */
 extern unsigned long avenrun[];		/* Load averages */
 extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
+extern void get_avenrun_ve(unsigned long *loads,
+			   unsigned long offset, int shift);
 
 #define FSHIFT		11		/* nr of bits of precision */
 #define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index de22da666ac7..dafa428dc1ba 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -76,6 +76,14 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
 	loads[2] = (avenrun[2] + offset) << shift;
 }
 
+void get_avenrun_ve(unsigned long *loads, unsigned long offset, int shift)
+{
+	struct task_group *tg = task_group(current);
+	loads[0] = (tg->avenrun[0] + offset) << shift;
+	loads[1] = (tg->avenrun[1] + offset) << shift;
+	loads[2] = (tg->avenrun[2] + offset) << shift;
+}
+
 long calc_load_fold_active(struct rq *this_rq, long adjust)
 {
 	long nr_active, delta = 0;
@@ -91,6 +99,34 @@ long calc_load_fold_active(struct rq *this_rq, long adjust)
 	return delta;
 }
 
+#ifdef CONFIG_VE
+static void calc_load_ve(void)
+{
+	unsigned long nr_active;
+	struct task_group *tg;
+	int i;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		nr_active = 0;
+		for_each_possible_cpu(i) {
+#ifdef CONFIG_FAIR_GROUP_SCHED
+			nr_active += tg->cfs_rq[i]->nr_running;
+			nr_active += tg->cfs_rq[i]->nr_unint;
+#endif
+		}
+		nr_active *= FIXED_1;
+
+		tg->avenrun[0] = calc_load(tg->avenrun[0], EXP_1, nr_active);
+		tg->avenrun[1] = calc_load(tg->avenrun[1], EXP_5, nr_active);
+		tg->avenrun[2] = calc_load(tg->avenrun[2], EXP_15, nr_active);
+	}
+	rcu_read_unlock();
+}
+#else
+#define calc_load_ve()	do { } while (0)
+#endif
+
 /**
  * fixed_power_int - compute: x^n, in O(log n) time
  *
@@ -372,6 +408,8 @@ void calc_global_load(unsigned long ticks)
 
 	WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ);
 
+	calc_load_ve();
+
 	/*
 	 * In case we went to NO_HZ for multiple LOAD_FREQ intervals
 	 * catch up in bulk.
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b2f0c26b2c50..485eee54f378 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -404,6 +404,7 @@ struct task_group {
 	struct autogroup	*autogroup;
 #endif
 
+	unsigned long avenrun[3];	/* loadavg data */
 	/* Monotonic time in nsecs: */
 	u64			start_time;
 
diff --git a/kernel/sys.c b/kernel/sys.c
index df02329b0e5c..0b8f9b050114 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2575,11 +2575,7 @@ static int do_sysinfo(struct sysinfo *info)
 
 		info->procs = nr_threads_ve(ve);
 
-#if 0
-FIXME after
-715f311fdb4a ("sched: Account task_group::cpustat,taskstats,avenrun") is ported
 		get_avenrun_ve(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
-#endif
 	}
 
 	/*