[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20181211163952.GB4020@quack2.suse.cz>
Date: Tue, 11 Dec 2018 17:39:52 +0100
From: Jan Kara <jack@...e.cz>
To: Michal Hocko <mhocko@...nel.org>
Cc: "Kirill A. Shutemov" <kirill@...temov.name>,
Andrew Morton <akpm@...ux-foundation.org>,
Liu Bo <bo.liu@...ux.alibaba.com>, Jan Kara <jack@...e.cz>,
Dave Chinner <david@...morbit.com>,
Theodore Ts'o <tytso@....edu>,
Johannes Weiner <hannes@...xchg.org>,
Vladimir Davydov <vdavydov.dev@...il.com>, linux-mm@...ck.org,
linux-fsdevel@...r.kernel.org, LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] mm, memcg: fix reclaim deadlock with writeback
On Tue 11-12-18 17:21:49, Michal Hocko wrote:
> On Tue 11-12-18 18:15:42, Kirill A. Shutemov wrote:
> > For instance, DAX page fault will setup page table entry on its own and
> > return VM_FAULT_NOPAGE. It uses vmf_insert_mixed() to setup the page table
> > and ignores your pre-allocated page table.
>
> Does this happen with a page locked and with __GFP_ACCOUNT allocation. I
> am not familiar with that code but I do not see it from a quick look.
DAX has no page to lock and also no writeback to do so the deadlock isn't
really possible when DAX is in use...
Honza
--
Jan Kara <jack@...e.com>
SUSE Labs, CR
Powered by blists - more mailing lists