From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756051Ab2IYL7d (ORCPT ); Tue, 25 Sep 2012 07:59:33 -0400 Received: from mail-qa0-f46.google.com ([209.85.216.46]:42535 "EHLO mail-qa0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755957Ab2IYL7b (ORCPT ); Tue, 25 Sep 2012 07:59:31 -0400 Date: Tue, 25 Sep 2012 13:59:26 +0200 From: Frederic Weisbecker To: "Paul E. McKenney" Cc: Sasha Levin , Michael Wang , Dave Jones , "linux-kernel@vger.kernel.org" Subject: Re: RCU idle CPU detection is broken in linux-next Message-ID: <20120925115917.GB2310@somewhere.redhat.com> References: <20120923002105.GA1112@linux.vnet.ibm.com> <505EA09B.6040105@gmail.com> <5060E31B.3070203@gmail.com> <5060E498.7030003@gmail.com> <5060E863.6020006@gmail.com> <20120925040420.GB2436@linux.vnet.ibm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20120925040420.GB2436@linux.vnet.ibm.com> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Sep 24, 2012 at 09:04:20PM -0700, Paul E. McKenney wrote: > On Tue, Sep 25, 2012 at 01:41:18AM +0200, Frederic Weisbecker wrote: > > > > > > [ 168.703017] ------------[ cut here ]------------ > > > [ 168.708117] WARNING: at kernel/rcutree.c:502 rcu_eqs_exit_common+0x4a/0x3a0() > > > [ 168.710034] Pid: 7871, comm: trinity-child65 Tainted: G W > > > 3.6.0-rc6-next-20120924-sasha-00030-g71f256c #5 > > > [ 168.710034] Call Trace: > > > [ 168.710034] [] ? rcu_eqs_exit_common+0x4a/0x3a0 > > > [ 168.710034] [] warn_slowpath_common+0x86/0xb0 > > > [ 168.710034] [] warn_slowpath_null+0x15/0x20 > > > [ 168.710034] [] rcu_eqs_exit_common+0x4a/0x3a0 > > > [ 168.710034] [] rcu_eqs_exit+0x9c/0xb0 > > > [ 168.710034] [] rcu_user_exit+0x6c/0xd0 > > > [ 168.710034] [] do_general_protection+0x1f/0x170 > > > [ 168.710034] [] ? restore_args+0x30/0x30 > > > [ 168.710034] [] general_protection+0x25/0x30 > > > [ 168.710034] [] ? native_read_msr_safe+0x6/0x20 > > > [ 168.710034] [] __rdmsr_safe_on_cpu+0x2b/0x50 > > > [ 168.710034] [] ? list_del+0x11/0x40 > > > [ 168.710034] [] > > > generic_smp_call_function_single_interrupt+0xec/0x120 > > > [ 168.710034] [] ? account_system_vtime+0xd7/0x140 > > > [ 168.710034] [] > > > smp_call_function_single_interrupt+0x22/0x40 > > > [ 168.710034] [] call_function_single_interrupt+0x6f/0x80 > > > [ 168.710034] [] ? retint_restore_args+0x13/0x13 > > > [ 168.710034] [] ? rcu_user_enter+0x105/0x110 > > > [ 168.710034] [] syscall_trace_leave+0xfd/0x150 > > > [ 168.710034] [] int_check_syscall_exit_work+0x34/0x3d > > > [ 168.710034] ---[ end trace fd408dd21b70b87c ]--- > > > > > > This is an exception inside an interrupt, and the interrupt > > > interrupted RCU user mode. > > > And we have that nesting: > > > > > > rcu_irq_enter(); <--- irq entry > > > rcu_user_exit(); <--- exception entry > > > > > > And rcu_eqs_exit() doesn't handle that very well... > > > > So either I should return immediately from rcu_user_exit() if > > we are in an interrupt, or we make rcu_user_exit() able to nest > > on rcu_irq_enter() :) > > Both of the two are eminently doable, with varying degrees of hackery. > > What makes the most sense from an adaptive-idle viewpoint? Given that we have: rcu_irq_enter() rcu_user_exit() rcu_user_enter() rcu_irq_exit() And we already have rcu_user_exit_after_irq(), this starts to be confusing if we allow that nesting. Although if we find a solution that, in the end, merge rcu_user_exit() with rcu_user_exit_after_irq() and same for the enter version, this would probably be a good thing. Provided this doesn't involve some more complicated rdtp->dyntick_nesting trickies nor more overhead. Otherwise we could avoid to call rcu_user_* when we are in an irq. When we'll have the user_hooks layer, we can perhaps manage that from that place. For now may be we can return after in_interrupt() in the rcu user apis. Let's first ensure I diagnosed it well and we don't have other problems detected by Sasha. I'm cooking a testing patch.