Messages in this thread | | | From | "Liu, Chuansheng" <> | Subject | RE: [PATCH] Fix the race between smp_call_function and CPU booting | Date | Mon, 19 Mar 2012 00:58:21 +0000 |
| |
> -----Original Message----- > From: Peter Zijlstra [mailto:peterz@infradead.org] > Sent: Friday, March 16, 2012 5:49 PM > To: Liu, Chuansheng > Cc: linux-kernel@vger.kernel.org; Yanmin Zhang; tglx@linutronix.de > Subject: RE: [PATCH] Fix the race between smp_call_function and CPU booting > > On Fri, 2012-03-16 at 06:24 +0000, Liu, Chuansheng wrote: > > > Based on your patch, I did a little modification, how do you think of that? > > > --- a/kernel/cpu.c > > +++ b/kernel/cpu.c > > @@ -640,8 +640,10 @@ void set_cpu_present(unsigned int cpu, bool > > present) > > > > void set_cpu_online(unsigned int cpu, bool online) { > > - if (online) > > + if (online) { > > cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits)); > > + cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits)); > > + } > > else > > cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits)); > > } > > I'm thinking this lacks rationale. What was wrong, Why does this fix it. > If you can't answer that stop tinkering and start thinking. Your patch advance the setting active bit before online setting, that will cause an warning error, I just move the setting active bit after setting online setting, it can fix the warning error, and it can fix the race issue between smp_call_function and CPU booting.
I have tested it by some stress tests.
| |