Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <20210812203137.2880834-1-joshdon@google.com>
In-Reply-To: <20210812203137.2880834-1-joshdon@google.com>
From:   Eric Dumazet <edumazet@google.com>
Date:   Thu, 12 Aug 2021 22:42:23 +0200
Message-ID: <CANn89iJK-PzFrN2S_jojN2rvZBfBJY4cLTg6q+uzF-vcrfrAeQ@mail.gmail.com>
Subject: Re: [PATCH] fs/proc/uptime.c: fix idle time reporting in /proc/uptime
To:     Josh Don <joshdon@google.com>
Cc:     Ingo Molnar <mingo@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        LKML <linux-kernel@vger.kernel.org>,
        linux-fsdevel <linux-fsdevel@vger.kernel.org>,
        Luigi Rizzo <lrizzo@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Thu, Aug 12, 2021 at 10:31 PM Josh Don <joshdon@google.com> wrote:
>
> /proc/uptime reports idle time by reading the CPUTIME_IDLE field from
> the per-cpu kcpustats. However, on NO_HZ systems, idle time is not
> continually updated on idle cpus, leading this value to appear
> incorrectly small.
>
> /proc/stat performs an accounting update when reading idle time; we can
> use the same approach for uptime.
>
> With this patch, /proc/stat and /proc/uptime now agree on idle time.
> Additionally, the following shows idle time tick up consistently on an
> idle machine:
> (while true; do cat /proc/uptime; sleep 1; done) | awk '{print $2-prev; prev=$2}'
>
> Reported-by: Luigi Rizzo <lrizzo@google.com>
> Signed-off-by: Josh Don <joshdon@google.com>
> ---
>  fs/proc/stat.c              | 26 --------------------------
>  fs/proc/uptime.c            | 13 ++++++++-----
>  include/linux/kernel_stat.h |  1 +
>  kernel/sched/cputime.c      | 28 ++++++++++++++++++++++++++++
>  4 files changed, 37 insertions(+), 31 deletions(-)
>
> diff --git a/fs/proc/stat.c b/fs/proc/stat.c
> index 6561a06ef905..99796a8a5223 100644
> --- a/fs/proc/stat.c
> +++ b/fs/proc/stat.c
> @@ -24,16 +24,6 @@
>
>  #ifdef arch_idle_time
>
> -static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
> -{
> -       u64 idle;
> -
> -       idle = kcs->cpustat[CPUTIME_IDLE];
> -       if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
> -               idle += arch_idle_time(cpu);
> -       return idle;
> -}
> -
>  static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu)
>  {
>         u64 iowait;
> @@ -46,22 +36,6 @@ static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu)
>
>  #else
>
> -static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
> -{
> -       u64 idle, idle_usecs = -1ULL;
> -
> -       if (cpu_online(cpu))
> -               idle_usecs = get_cpu_idle_time_us(cpu, NULL);
> -
> -       if (idle_usecs == -1ULL)
> -               /* !NO_HZ or cpu offline so we can rely on cpustat.idle */
> -               idle = kcs->cpustat[CPUTIME_IDLE];
> -       else
> -               idle = idle_usecs * NSEC_PER_USEC;
> -
> -       return idle;
> -}
> -
>  static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu)
>  {
>         u64 iowait, iowait_usecs = -1ULL;

...

> diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
> index 872e481d5098..9d7629e21164 100644
> --- a/kernel/sched/cputime.c
> +++ b/kernel/sched/cputime.c
> @@ -227,6 +227,34 @@ void account_idle_time(u64 cputime)
>                 cpustat[CPUTIME_IDLE] += cputime;
>  }
>
> +/*
> + * Returns the total idle time for the given cpu.
> + * @kcs: The kernel_cpustat for the desired cpu.
> + * @cpu: The desired cpu.
> + */
> +u64 get_idle_time(const struct kernel_cpustat *kcs, int cpu)
> +{
> +       u64 idle;
> +       u64 __maybe_unused idle_usecs = -1ULL;
> +
> +#ifdef arch_idle_time
> +       idle = kcs->cpustat[CPUTIME_IDLE];
> +       if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
> +               idle += arch_idle_time(cpu);
> +#else
> +       if (cpu_online(cpu))
> +               idle_usecs = get_cpu_idle_time_us(cpu, NULL);
> +
> +       if (idle_usecs == -1ULL)
> +               /* !NO_HZ or cpu offline so we can rely on cpustat.idle */
> +               idle = kcs->cpustat[CPUTIME_IDLE];
> +       else
> +               idle = idle_usecs * NSEC_PER_USEC;
> +#endif
> +
> +       return idle;
> +}
> +
>

Not sure why you moved get_idle_time() in kernel/sched/cputime.c

For builds where CONFIG_PROC_FS is not set, this function is not used/needed.