sched: update correct entity's runtime in check_preempt_wakeup()
authorPaul Turner <pjt@google.com>
Wed, 6 Jul 2011 02:07:21 +0000 (19:07 -0700)
committerIngo Molnar <mingo@elte.hu>
Thu, 21 Jul 2011 16:01:43 +0000 (18:01 +0200)
commit9bbd7374361d9bfc75108c3ad1c1b6db28b1be59
treed787a387a2a2e3d8c0476b79ae57dd217098763f
parent994bf1c92270e3d7731ea08f1d1bd7a668314e60
sched: update correct entity's runtime in check_preempt_wakeup()

While looking at check_preempt_wakeup() I realized that we are
potentially updating the wrong entity in the fair-group scheduling
case. In this case the current task's cfs_rq may not be the same as
the one used for the comparison between the waking task and the
existing task's vruntime.

This potentially results in us using a stale vruntime in the
pre-emption decision, providing a small false preference for the
previous task. The effects of this are bounded since we always
perform a hierarchal update on the tick.

Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/CAPM31R+2Ke2urUZKao5W92_LupdR4AYEv-EZWiJ3tG=tEes2cw@mail.gmail.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
kernel/sched_fair.c