[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <a3671d96-5003-6a50-ad2d-64833ca216a1@arm.com>
Date: Wed, 23 Jan 2019 09:25:56 +0100
From: Dietmar Eggemann <dietmar.eggemann@....com>
To: Vincent Guittot <vincent.guittot@...aro.org>, peterz@...radead.org,
mingo@...nel.org, linux-kernel@...r.kernel.org
Cc: rjw@...ysocki.net, Morten.Rasmussen@....com,
patrick.bellasi@....com, pjt@...gle.com, bsegall@...gle.com,
thara.gopinath@...aro.org, pkondeti@...eaurora.org,
quentin.perret@....com, srinivas.pandruvada@...ux.intel.com
Subject: Re: [PATCH v8 2/3] sched/fair: update scale invariance of PELT
On 1/16/19 10:43 AM, Vincent Guittot wrote:
[...]
> +static inline u64 rq_clock_pelt(struct rq *rq)
> +{
Doesn't this function need
lockdep_assert_held(&rq->lock);
assert_clock_updated(rq);
like rq_clock() and rq_clock_task()? Later to support commit
cb42c9a3ebbb "sched/core: Add debugging code to catch missing
update_rq_clock() calls".
> + return rq->clock_pelt - rq->lost_idle_time;
> +}
[...]
Powered by blists - more mailing lists