From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756299Ab1IGQTF (ORCPT ); Wed, 7 Sep 2011 12:19:05 -0400 Received: from e3.ny.us.ibm.com ([32.97.182.143]:56940 "EHLO e3.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755727Ab1IGQTB (ORCPT ); Wed, 7 Sep 2011 12:19:01 -0400 Date: Wed, 7 Sep 2011 06:44:00 -0700 From: "Paul E. McKenney" To: Benjamin Herrenschmidt Cc: linux-kernel@vger.kernel.org, mingo@elte.hu, laijs@cn.fujitsu.com, dipankar@in.ibm.com, akpm@linux-foundation.org, mathieu.desnoyers@polymtl.ca, josh@joshtriplett.org, niv@us.ibm.com, tglx@linutronix.de, peterz@infradead.org, rostedt@goodmis.org, Valdis.Kletnieks@vt.edu, dhowells@redhat.com, eric.dumazet@gmail.com, darren@dvhart.com, patches@linaro.org, anton@samba.org, paulus@samba.org Subject: Re: [PATCH tip/core/rcu 55/55] powerpc: Work around tracing from dyntick-idle mode Message-ID: <20110907134400.GJ3610@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <20110906180015.GA2560@linux.vnet.ibm.com> <1315332049-2604-55-git-send-email-paulmck@linux.vnet.ibm.com> <1315389622.26118.17.camel@pasglop> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1315389622.26118.17.camel@pasglop> User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Sep 07, 2011 at 07:00:22AM -0300, Benjamin Herrenschmidt wrote: > On Tue, 2011-09-06 at 11:00 -0700, Paul E. McKenney wrote: > > PowerPC LPAR's __trace_hcall_exit() can invoke event tracing at a > > point where RCU has been told that the CPU is in dyntick-idle mode. > > Because event tracing uses RCU, this can result in failures. > > > > A correct fix would arrange for RCU to be told about dyntick-idle > > mode after tracing had completed, however, this will require some care > > because it appears that __trace_hcall_exit() can also be called from > > non-dyntick-idle mode. > > This obviously needs to be fixed properly. hcall tracing is very useful > and if I understand your patch properly, it just comments it out :-) That is exactly what it does, and I completely agree that this patch is nothing but a short-term work-around to allow my RCU tests to find other bugs. > I'm not sure what the best approach is, maybe have the hcall tracing > test for the dyntick-idle mode and skip tracing in that case ? Another approach would be to update Frederic Weisbecker's patch at: https://lkml.org/lkml/2011/8/20/83 so that powerpc does tick_nohz_enter_idle(false), and then uses rcu_enter_nohz() explicitly just after doing the hcall tracing. If pseries is the only powerpc architecture requiring this, then the argument to tick_nohz_enter_idle() could depend on the powerpc sub-architecture. The same thing would be needed for tick_nohz_exit_idle() and rcu_exit_nohz(): powerpc would need to invoke rcu_exit_nohz() after gaining control from the hypervisor but before doing its first tracing, and then it would need the idle loop to to tick_nohz_exit_idle(false). Again, if pseries is the only powerpc architecture requiring this, the argument to tick_nohz_exit_idle() could depend on the architecture. Would this approach work? Thanx, Paul > Cheers, > Ben. > > > Signed-off-by: Paul E. McKenney > > Cc: anton@samba.org > > Cc: benh@kernel.crashing.org > > Cc: paulus@samba.org > > --- > > arch/powerpc/platforms/pseries/lpar.c | 6 ++++++ > > 1 files changed, 6 insertions(+), 0 deletions(-) > > > > diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c > > index 39e6e0a..668f300 100644 > > --- a/arch/powerpc/platforms/pseries/lpar.c > > +++ b/arch/powerpc/platforms/pseries/lpar.c > > @@ -715,12 +715,14 @@ EXPORT_SYMBOL(arch_free_page); > > /* NB: reg/unreg are called while guarded with the tracepoints_mutex */ > > extern long hcall_tracepoint_refcount; > > > > +#if 0 /* work around buggy use of RCU from dyntick-idle mode */ > > /* > > * Since the tracing code might execute hcalls we need to guard against > > * recursion. One example of this are spinlocks calling H_YIELD on > > * shared processor partitions. > > */ > > static DEFINE_PER_CPU(unsigned int, hcall_trace_depth); > > +#endif /* #if 0 work around buggy use of RCU from dyntick-idle mode */ > > > > void hcall_tracepoint_regfunc(void) > > { > > @@ -734,6 +736,7 @@ void hcall_tracepoint_unregfunc(void) > > > > void __trace_hcall_entry(unsigned long opcode, unsigned long *args) > > { > > +#if 0 /* work around buggy use of RCU from dyntick-idle mode */ > > unsigned long flags; > > unsigned int *depth; > > > > @@ -750,11 +753,13 @@ void __trace_hcall_entry(unsigned long opcode, unsigned long *args) > > > > out: > > local_irq_restore(flags); > > +#endif /* #if 0 work around buggy use of RCU from dyntick-idle mode */ > > } > > > > void __trace_hcall_exit(long opcode, unsigned long retval, > > unsigned long *retbuf) > > { > > +#if 0 /* work around buggy use of RCU from dyntick-idle mode */ > > unsigned long flags; > > unsigned int *depth; > > > > @@ -771,6 +776,7 @@ void __trace_hcall_exit(long opcode, unsigned long retval, > > > > out: > > local_irq_restore(flags); > > +#endif /* #if 0 work around buggy use of RCU from dyntick-idle mode */ > > } > > #endif > > > >