From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Date: Fri, 21 Jun 2013 20:42:49 +0900
Message-ID: <87y5a3666e.wl%satoru.takeuchi@gmail.com>
From: Satoru Takeuchi <satoru.takeuchi@gmail.com>
To: Greg Kroah-Hartman <greg@kroah.com>
Cc: Satoru Takeuchi <satoru.takeuchi@gmail.com>,
	linux-kernel@vger.kernel.org, stable@vger.kernel.org,
	Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>,
	Rik van Riel <riel@redhat.com>,
	Wanpeng Li <liwanp@linux.vnet.ibm.com>,
	Michal Hocko <mhocko@suse.cz>, Mel Gorman <mgorman@suse.de>,
	Andi Kleen <andi@firstfloor.org>,
	KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [ 29/48] mm: migration: add migrate_entry_wait_huge()
In-Reply-To: <20130620170213.GB21356@kroah.com>
References: <20130618161725.912524266@linuxfoundation.org>
	<20130618161730.095209184@linuxfoundation.org>
	<87a9ml3y8k.wl%satoru.takeuchi@gmail.com>
	<20130620170213.GB21356@kroah.com>
MIME-Version: 1.0 (generated by SEMI 1.14.6 - "Maruoka")
Content-Type: text/plain; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <stable.vger.kernel.org>

At Thu, 20 Jun 2013 10:02:13 -0700,
Greg Kroah-Hartman wrote:
> 
> On Thu, Jun 20, 2013 at 06:52:43PM +0900, Satoru Takeuchi wrote:
> > Hi Naoya,
> > 
> > At Tue, 18 Jun 2013 09:17:55 -0700,
> > Greg Kroah-Hartman wrote:
> > > 
> > > From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> > > 
> > > 3.9-stable review patch.  If anyone has any objections, please let me know.
> > > 
> > > ------------------
> > > 
> > > From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
> > > 
> > > commit 30dad30922ccc733cfdbfe232090cf674dc374dc upstream.
> > > 
> > > When we have a page fault for the address which is backed by a hugepage
> > > under migration, the kernel can't wait correctly and do busy looping on
> > > hugepage fault until the migration finishes.  As a result, users who try
> > > to kick hugepage migration (via soft offlining, for example) occasionally
> > > experience long delay or soft lockup.
> > > 
> > > This is because pte_offset_map_lock() can't get a correct migration entry
> > > or a correct page table lock for hugepage.  This patch introduces
> > > migration_entry_wait_huge() to solve this.
> > 
> > I suspect that this code doesn't work correctly on i686 box with CONFIG_HIGHPTE.
> > If we call hugetlb_fault() -> migration_entry_wait_huge() -> __migration_entry_wait(),
> > this function tries to kunmap pte, in this case pte is not-kmapped pmd, via pte_unmap_unlock().
> > If CONFIG_DEBUG_HIGHMEM is also enabled, it results in BUG_ON() at __kunmap_atomic().
> 
> Have you tried this?

Not yet. I'm now preparing the kernel to reproduce this problem.

> 
> Also, the same issue is still in 3.10-rc6, right?

Yes.

Thanks,
Satoru