[PATCH 1/1] sched/cputime: Improve getrusage(RUSAGE_THREAD) with nohz_full

From: Hasegawa Hitomi
Date: Tue Sep 28 2021 - 01:15:37 EST


The getrusage(RUSAGE_THREAD) with nohz_full returns shorter utime/stime
than the actual time.

In the current implementation, task_cputime_adjusted() calls task_cputime()
to get the "current" utime and stime, then calls cputime_adjust () to
adjust the sum of utime and stime to be equal to cputime.sum_exec_runtime.
In nohz_full, sum_exec_runtime is not updated regularly, which is the cause
of this discrepancy.

This patch add a process to update sum_exec_runtime.
This addition applies only when run with nohz_full.

Signed-off-by: Hasegawa Hitomi <hasegawa-hitomi@xxxxxxxxxxx>
---
include/linux/sched/cputime.h | 5 +++--
kernel/sched/cputime.c | 12 +++++++++---
2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h
index 6c9f19a33865..ce3c58286062 100644
--- a/include/linux/sched/cputime.h
+++ b/include/linux/sched/cputime.h
@@ -18,15 +18,16 @@
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */

#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-extern void task_cputime(struct task_struct *t,
+extern bool task_cputime(struct task_struct *t,
u64 *utime, u64 *stime);
extern u64 task_gtime(struct task_struct *t);
#else
-static inline void task_cputime(struct task_struct *t,
+static inline bool task_cputime(struct task_struct *t,
u64 *utime, u64 *stime)
{
*utime = t->utime;
*stime = t->stime;
+ return false;
}

static inline u64 task_gtime(struct task_struct *t)
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 872e481d5098..9392aea1804e 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -615,7 +615,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
.sum_exec_runtime = p->se.sum_exec_runtime,
};

- task_cputime(p, &cputime.utime, &cputime.stime);
+ if (task_cputime(p, &cputime.utime, &cputime.stime))
+ cputime.sum_exec_runtime = task_sched_runtime(p);
cputime_adjust(&cputime, &p->prev_cputime, ut, st);
}
EXPORT_SYMBOL_GPL(task_cputime_adjusted);
@@ -828,19 +829,21 @@ u64 task_gtime(struct task_struct *t)
* add up the pending nohz execution time since the last
* cputime snapshot.
*/
-void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
+bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
{
struct vtime *vtime = &t->vtime;
unsigned int seq;
u64 delta;
+ int ret;

if (!vtime_accounting_enabled()) {
*utime = t->utime;
*stime = t->stime;
- return;
+ return false;
}

do {
+ ret = false;
seq = read_seqcount_begin(&vtime->seqcount);

*utime = t->utime;
@@ -850,6 +853,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
if (vtime->state < VTIME_SYS)
continue;

+ ret = true;
delta = vtime_delta(vtime);

/*
@@ -861,6 +865,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
else
*utime += vtime->utime + delta;
} while (read_seqcount_retry(&vtime->seqcount, seq));
+
+ return ret;
}

static int vtime_state_fetch(struct vtime *vtime, int cpu)
--
2.25.1