From nobody Sun Feb 8 05:27:44 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id EBA6438A2AE; Fri, 16 Jan 2026 14:53:55 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768575236; cv=none; b=YKCI9iAYy/1FxVEi5ZWiNZYd+TggcFmohKVv6ZuysmWmJux0te0AA3NoQlul79EE2cSxYtXaLzPG6j8maeYQQzs/IkmUZDv50I623X7YjZp4fktuyt7vAgY2MA64IaWDj8QklKKnxGTFFUKCCMd3mE7EK/3msLbNeTrKavNhzT4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768575236; c=relaxed/simple; bh=8v3ULYDqt0dF0OoyYvjCFXVF3r/R8dp2K5PMXJFm6yY=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=jl3B62ObX2V5KqqnZ5NY9iTQGpGNP8WPAImGcr66qVOX0GWqzKsBbBPIZlWEIp2YQqmKpofoKp04jenXYh/fkZKfOiMkpixiCObwSspmUGF363k3HUtRB6NpD2zO+is9sKhOzzofpnKoO2XHuMYB5vJToRCHPyW/2otrRx6f7iE= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=QTuE+pev; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="QTuE+pev" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 8BFCFC116C6; Fri, 16 Jan 2026 14:53:48 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1768575235; bh=8v3ULYDqt0dF0OoyYvjCFXVF3r/R8dp2K5PMXJFm6yY=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=QTuE+pevi7Ewtc5J4XzS2UyPIDX6nKym9hfu473HaWWIdWlledSc2OUe2hDm9GjOu aIpXiBUIscS+O2fSFPLXX3Tag46bUkGLCfL75SiNLjoAITlPVWYZuanFHF6VjbaKdw daTCh/g4e/qMOdWH3BpJWKAuEzWjK/sDbXfsXBnjZ5mVW6FI5Z33aH80Afp37MySD8 Jxi8QkRD+ZeXuYuXyAgdatTG1bSK6XRmNw9+ZaYjhhSMzGB8vaMxhspoZJfxHBSPo3 CkHOTOCFZB2yfJWRjUQfoFmcssxDFrE+v0AAlOiNVBOdxgzmUMTuR4lKnN+oaWQQoG mNnXatX/ElVkg== From: Frederic Weisbecker To: LKML Cc: Frederic Weisbecker , "Christophe Leroy (CS GROUP)" , "Rafael J. Wysocki" , Alexander Gordeev , Anna-Maria Behnsen , Ben Segall , Boqun Feng , Christian Borntraeger , Dietmar Eggemann , Heiko Carstens , Ingo Molnar , Jan Kiszka , Joel Fernandes , Juri Lelli , Kieran Bingham , Madhavan Srinivasan , Mel Gorman , Michael Ellerman , Neeraj Upadhyay , Nicholas Piggin , "Paul E . McKenney" , Peter Zijlstra , Steven Rostedt , Sven Schnelle , Thomas Gleixner , Uladzislau Rezki , Valentin Schneider , Vasily Gorbik , Vincent Guittot , Viresh Kumar , Xin Zhao , linux-pm@vger.kernel.org, linux-s390@vger.kernel.org, linuxppc-dev@lists.ozlabs.org Subject: [PATCH 13/15] sched/cputime: Consolidate get_cpu_[idle|iowait]_time_us() Date: Fri, 16 Jan 2026 15:52:06 +0100 Message-ID: <20260116145208.87445-14-frederic@kernel.org> X-Mailer: git-send-email 2.51.1 In-Reply-To: <20260116145208.87445-1-frederic@kernel.org> References: <20260116145208.87445-1-frederic@kernel.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" get_cpu_idle/iowait_time_us() may ultimately fail if generic vtime accounting is enabled. The ad-hoc replacement solution by cpufreq is to compute jiffies minus the whole busy cputime. Although the intention should provide a coherent low resolution estimation of the idle and iowait time, the implementation is buggy because jiffies don't start at 0. Enhance instead get_cpu_[idle|iowait]_time_us() to provide support for vtime generic accounting. Signed-off-by: Frederic Weisbecker --- drivers/cpufreq/cpufreq.c | 29 +---------------------------- include/linux/kernel_stat.h | 3 +++ include/linux/tick.h | 4 ---- kernel/sched/cputime.c | 14 ++++++++++---- 4 files changed, 14 insertions(+), 36 deletions(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 4472bb1ec83c..ecb9634cd06b 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -130,38 +130,11 @@ struct kobject *get_governor_parent_kobj(struct cpufr= eq_policy *policy) } EXPORT_SYMBOL_GPL(get_governor_parent_kobj); =20 -static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall) -{ - struct kernel_cpustat kcpustat; - u64 cur_wall_time; - u64 idle_time; - u64 busy_time; - - cur_wall_time =3D jiffies64_to_nsecs(get_jiffies_64()); - - kcpustat_cpu_fetch(&kcpustat, cpu); - - busy_time =3D kcpustat.cpustat[CPUTIME_USER]; - busy_time +=3D kcpustat.cpustat[CPUTIME_SYSTEM]; - busy_time +=3D kcpustat.cpustat[CPUTIME_IRQ]; - busy_time +=3D kcpustat.cpustat[CPUTIME_SOFTIRQ]; - busy_time +=3D kcpustat.cpustat[CPUTIME_STEAL]; - busy_time +=3D kcpustat.cpustat[CPUTIME_NICE]; - - idle_time =3D cur_wall_time - busy_time; - if (wall) - *wall =3D div_u64(cur_wall_time, NSEC_PER_USEC); - - return div_u64(idle_time, NSEC_PER_USEC); -} - u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy) { u64 idle_time =3D get_cpu_idle_time_us(cpu, io_busy ? wall : NULL); =20 - if (idle_time =3D=3D -1ULL) - return get_cpu_idle_time_jiffy(cpu, wall); - else if (!io_busy) + if (!io_busy) idle_time +=3D get_cpu_iowait_time_us(cpu, wall); =20 return idle_time; diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index e1efd26e56f0..e59916477075 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -133,6 +133,9 @@ static inline bool kcpustat_idle_dyntick(void) } #endif /* CONFIG_NO_HZ_COMMON */ =20 +extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); +extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); + /* Fetch cputime values when vtime is disabled on a CPU */ static inline u64 kcpustat_field_default(enum cpu_usage_stat usage, int cp= u) { diff --git a/include/linux/tick.h b/include/linux/tick.h index ac76ae9fa36d..1296cba67bee 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -138,8 +138,6 @@ extern bool tick_nohz_idle_got_tick(void); extern ktime_t tick_nohz_get_next_hrtimer(void); extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next); extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu); -extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); -extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); #else /* !CONFIG_NO_HZ_COMMON */ #define tick_nohz_enabled (0) static inline int tick_nohz_tick_stopped(void) { return 0; } @@ -160,8 +158,6 @@ static inline ktime_t tick_nohz_get_sleep_length(ktime_= t *delta_next) *delta_next =3D TICK_NSEC; return *delta_next; } -static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } -static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1= ; } #endif /* !CONFIG_NO_HZ_COMMON */ =20 /* diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 9906abe5d7bc..f0620b429698 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -511,6 +511,13 @@ u64 kcpustat_field_iowait(int cpu) nr_iowait_cpu(cpu), ktime_get()); } EXPORT_SYMBOL_GPL(kcpustat_field_iowait); +#else +static u64 kcpustat_field_dyntick(int cpu, enum cpu_usage_stat idx, + bool compute_delta, ktime_t now) +{ + return kcpustat_cpu(cpu).cpustat[idx]; +} +#endif /* CONFIG_NO_HZ_COMMON */ =20 static u64 get_cpu_sleep_time_us(int cpu, enum cpu_usage_stat idx, bool compute_delta, u64 *last_update_time) @@ -519,7 +526,7 @@ static u64 get_cpu_sleep_time_us(int cpu, enum cpu_usag= e_stat idx, u64 res; =20 if (vtime_generic_enabled_cpu(cpu)) - return -1; + res =3D kcpustat_field(idx, cpu); else res =3D kcpustat_field_dyntick(cpu, idx, compute_delta, now); =20 @@ -544,7 +551,7 @@ static u64 get_cpu_sleep_time_us(int cpu, enum cpu_usag= e_stat idx, * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * - * Return: -1 if generic vtime is enabled, else total idle time of the @cpu + * Return: total idle time of the @cpu */ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) { @@ -568,7 +575,7 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * - * Return: -1 if generic vtime is enabled, else total iowait time of @cpu + * Return: total iowait time of @cpu */ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) { @@ -576,7 +583,6 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_ti= me) nr_iowait_cpu(cpu), last_update_time); } EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); -#endif /* CONFIG_NO_HZ_COMMON */ =20 /* * Use precise platform statistics if available: --=20 2.51.1