From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752039AbaJST2M (ORCPT ); Sun, 19 Oct 2014 15:28:12 -0400 Received: from mx1.redhat.com ([209.132.183.28]:28770 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751495AbaJST2L (ORCPT ); Sun, 19 Oct 2014 15:28:11 -0400 Date: Sun, 19 Oct 2014 21:24:37 +0200 From: Oleg Nesterov To: Kirill Tkhai Cc: Kirill Tkhai , Peter Zijlstra , "linux-kernel@vger.kernel.org" , Ingo Molnar , Vladimir Davydov Subject: Re: [PATCH] sched/numa: fix unsafe get_task_struct() in task_numa_assign() Message-ID: <20141019192437.GA842@redhat.com> References: <1413376300.24793.55.camel@tkhai> <20141017213641.GB32576@redhat.com> <4323181413620101@web21o.yandex.ru> <20141018205614.GA15934@redhat.com> <33631413674011@web7o.yandex.ru> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <33631413674011@web7o.yandex.ru> User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 10/19, Kirill Tkhai wrote: > > 19.10.2014, 00:59, "Oleg Nesterov" : > > >  No, I don't think this can work. Let's look at the current code: > > > >          rcu_read_lock(); > >          cur = ACCESS_ONCE(dst_rq->curr); > >          if (cur->pid == 0) /* idle */ > > > >  And any dereference, even reading ->pid is not safe. This memory can be > >  freed, unmapped, reused, etc. > > > >  Looks like, task_numa_compare() needs to take dst_rq->lock and get the > >  refernce first. > > Yeah, detection of idle is not save. If we reorder the checks almost all > problems will be gone. All except unmapping. JFI, is it possible with > such kernel structures as task_struct? Yes, if DEBUG_PAGEALLOC. See kernel_map_pages() in arch/x86/mm/pageattr.c kernel_map_pages(enable => false) clears PAGE_PRESENT if slab returns the pages to system. > --- a/kernel/sched/fair.c > +++ b/kernel/sched/fair.c > @@ -1165,7 +1165,30 @@ static void task_numa_compare(struct task_numa_env *env, > > rcu_read_lock(); > cur = ACCESS_ONCE(dst_rq->curr); > - if (cur->pid == 0) /* idle */ > + /* > + * No need to move the exiting task, and this ensures that ->curr > + * wasn't reaped and thus get_task_struct() in task_numa_assign() > + * is safe; note that rcu_read_lock() can't protect from the final > + * put_task_struct() after the last schedule(). > + */ > + if (cur->flags & PF_EXITING) > + cur = NULL; so this needs probe_kernel_read(&cur->flags). > + if (cur != ACCESS_ONCE(dst_rq->curr)) > + cur = NULL; Yes, if this task_struct was freed in between we do not care if this memory was reused (except PF_EXITING can be false positive). If it was freed and now the same memory is ->curr again we know that delayed_put_task_struct() can't be called until we drop rcu lock, even if PF_EXITING is already set again. I won't argue, but you need to convince Peter to accept this hack ;) > >  Or, perhaps, we need to change the rules to ensure that any "task_struct *" > >  pointer is rcu-safe. Perhaps we have more similar problems... I'd like to > >  avoid this if possible. > > RT tree has: > > https://git.kernel.org/cgit/linux/kernel/git/paulg/3.10-rt-patches.git/ > tree/patches/sched-delay-put-task.patch Yes, and this obviously implies more rcu callbacks in flight, and another gp before __put_task_struct(). but may be we will need to do this anyway... Oleg.