From mboxrd@z Thu Jan 1 00:00:00 1970 From: Marc.Zyngier@arm.com (Marc Zyngier) Date: Wed, 25 May 2011 13:23:19 +0100 Subject: [BUG] "sched: Remove rq->lock from the first half of ttwu()" locks up on ARM In-Reply-To: <20110524213924.GO27634@elte.hu> References: <1306260792.27474.133.camel@e102391-lin.cambridge.arm.com> <1306272750.2497.79.camel@laptop> <20110524213924.GO27634@elte.hu> Message-ID: <1306326199.27474.153.camel@e102391-lin.cambridge.arm.com> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Tue, 2011-05-24 at 23:39 +0200, Ingo Molnar wrote: > * Peter Zijlstra wrote: > > > On Tue, 2011-05-24 at 19:13 +0100, Marc Zyngier wrote: > > > Peter, > > > > > > I've experienced all kind of lock-ups on ARM SMP platforms recently, and > > > finally tracked it down to the following patch: > > > > > > e4a52bcb9a18142d79e231b6733cabdbf2e67c1f [sched: Remove rq->lock from the first half of ttwu()]. > > > > > > Even on moderate load, the machine locks up, often silently, and > > > sometimes with a few messages like: > > > INFO: rcu_preempt_state detected stalls on CPUs/tasks: { 0} (detected by 1, t=12002 jiffies) > > > > > > Another side effect of this patch is that the load average is always 0, > > > whatever load I throw at the system. > > > > > > Reverting the sched changes up to that patch (included) gives me a > > > working system again, which happily survives parallel kernel > > > compilations without complaining. > > > > > > My knowledge of the scheduler being rather limited, I haven't been able > > > to pinpoint the exact problem (though it probably have something to do > > > with __ARCH_WANT_INTERRUPTS_ON_CTXSW being defined on ARM). The enclosed > > > patch somehow papers over the load average problem, but the system ends > > > up locking up anyway: > > > > Hurm.. I'll try and make x86 use __ARCH_WANT_INTERRUPTS_ON_CTXSW, IIRC > > Ingo once said that that is possible and try to see if I can reproduce. > > No clear ideas atm. > > Yes, should be possible to just disable it on x86 - no further tricks needed. > It's been a long time since i tested that though. I can confirm this is SMP only. UP is fine. SMP+nosmp locks up as well. M. -- Reality is an implementation detail.