Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Ma Xing <maxing.lan@bytedance.com>
To:     maxing.lan@bytedance.com
Cc:     mingo@redhat.com, peterz@infradead.org, juri.lelli@redhat.com,
        vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
        rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
        bristot@redhat.com, vschneid@redhat.com,
        linux-kernel@vger.kernel.org
Subject: [PATCH] sched/cputime: Make cputime_adjust() more accurate
Date:   Mon, 26 Dec 2022 11:10:10 +0800
Message-Id: <20221226031010.4079885-1-maxing.lan@bytedance.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

In the current algorithm of cputime_adjust(), the accumulated stime and
utime are used to divide the accumulated rtime. When the value is very
large, it is easy for the stime or utime not to be updated.

A better and intuitive way is to save the last stime and utime, and
divide the rtime increment proportionally according to the tick
increment.

Signed-off-by: Ma Xing <maxing.lan@bytedance.com>
---
 include/linux/sched.h         |  2 ++
 include/linux/sched/cputime.h |  1 +
 kernel/sched/cputime.c        | 38 +++++++++++++++++++++++++----------
 3 files changed, 30 insertions(+), 11 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 853d08f7562b..41b69ea8b717 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -325,6 +325,8 @@ struct prev_cputime {
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	u64				utime;
 	u64				stime;
+	u64				utick;
+	u64				stick;
 	raw_spinlock_t			lock;
 #endif
 };
diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h
index ce3c58286062..db5c32d4a467 100644
--- a/include/linux/sched/cputime.h
+++ b/include/linux/sched/cputime.h
@@ -182,6 +182,7 @@ static inline void prev_cputime_init(struct prev_cputime *prev)
 {
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	prev->utime = prev->stime = 0;
+	prev->utick = prev->stick = 0;
 	raw_spin_lock_init(&prev->lock);
 #endif
 }
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 95fc77853743..d94e9a306478 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -555,6 +555,7 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
 		    u64 *ut, u64 *st)
 {
 	u64 rtime, stime, utime;
+	s64 delta_rtime, delta_stime, delta_utime;
 	unsigned long flags;
 
 	/* Serialize concurrent callers such that we can honour our guarantees */
@@ -575,22 +576,36 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
 	stime = curr->stime;
 	utime = curr->utime;
 
+
+	delta_rtime = rtime - prev->stime - prev->utime;
+	delta_stime = stime - prev->stick;
+	delta_utime = utime - prev->utick;
+
+	prev->stick = stime;
+	prev->utick = utime;
+
 	/*
 	 * If either stime or utime are 0, assume all runtime is userspace.
 	 * Once a task gets some ticks, the monotonicity code at 'update:'
 	 * will ensure things converge to the observed ratio.
 	 */
 	if (stime == 0) {
-		utime = rtime;
+		delta_utime = delta_rtime;
 		goto update;
 	}
 
 	if (utime == 0) {
-		stime = rtime;
+		delta_stime = delta_rtime;
 		goto update;
 	}
 
-	stime = mul_u64_u64_div_u64(stime, rtime, stime + utime);
+	if (delta_stime <= 0)
+		goto update;
+
+	if (delta_utime <= 0)
+		goto update;
+
+	delta_stime = mul_u64_u64_div_u64(delta_stime, delta_rtime, delta_stime + delta_utime);
 
 update:
 	/*
@@ -602,21 +617,22 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
 	 *            = (rtime_i+1 - rtime_i) + utime_i
 	 *            >= utime_i
 	 */
-	if (stime < prev->stime)
-		stime = prev->stime;
-	utime = rtime - stime;
+	if (delta_stime <= 0)
+		delta_stime = 0;
+	delta_utime = delta_rtime - delta_stime;
+
 
 	/*
 	 * Make sure utime doesn't go backwards; this still preserves
 	 * monotonicity for stime, analogous argument to above.
 	 */
-	if (utime < prev->utime) {
-		utime = prev->utime;
-		stime = rtime - utime;
+	if (delta_utime <= 0) {
+		delta_utime = 0;
+		delta_stime = delta_rtime - delta_utime;
 	}
 
-	prev->stime = stime;
-	prev->utime = utime;
+	prev->stime += delta_stime;
+	prev->utime += delta_utime;
 out:
 	*ut = prev->utime;
 	*st = prev->stime;
-- 
2.20.1