[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20210604113159.26177-1-frederic@kernel.org>
Date: Fri, 4 Jun 2021 13:31:53 +0200
From: Frederic Weisbecker <frederic@...nel.org>
To: Thomas Gleixner <tglx@...utronix.de>
Cc: LKML <linux-kernel@...r.kernel.org>,
Frederic Weisbecker <frederic@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
"Eric W . Biederman" <ebiederm@...ssion.com>,
Oleg Nesterov <oleg@...hat.com>, Ingo Molnar <mingo@...nel.org>
Subject: [PATCH 0/6] posix-cpu-timers: Bunch of fixes
The first is a race due to locklessly starting process wide cputime
counting.
The others stop the process wide cputime counting and tick dependency
when they are not necessary anymore.
Note I don't really like patch 5/6 and in fact I hope we could manage to
remove this early inline cpu_timer_fire() call from timer_settime(). All
we get from it is headaches. Besides, the handler isn't invoked from the
actual target and that doesn't sound ideal.
git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
timers/urgent
HEAD: f8f908c9d2b2f1e100cd549206c95a4e65e5f023
Thanks,
Frederic
---
Frederic Weisbecker (6):
posix-cpu-timers: Fix rearm racing against process tick
posix-cpu-timers: Don't start process wide cputime counter if timer is disabled
posix-cpu-timers: Force next_expiration recalc after timer deletion
posix-cpu-timers: Force next_expiration recalc after timer reset
posix-cpu-timers: Force next expiration recalc after early timer firing
posix-cpu-timers: Force next expiration recalc after itimer reset
include/linux/posix-timers.h | 11 ++++-
kernel/time/posix-cpu-timers.c | 97 +++++++++++++++++++++++++++++++++---------
2 files changed, 87 insertions(+), 21 deletions(-)
Powered by blists - more mailing lists