Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20221103213641.7296-1-shy828301@gmail.com> <Y2TOAdHk97pPYwJY@dhcp22.suse.cz>
 <CAHbLzkpPioG8kiTHtepEtTC8sr8JAc2JTJk0s7WQH+fCh6YFKA@mail.gmail.com> <Y2VuRplhVmKiabR9@dhcp22.suse.cz>
In-Reply-To: <Y2VuRplhVmKiabR9@dhcp22.suse.cz>
From:   Yang Shi <shy828301@gmail.com>
Date:   Fri, 4 Nov 2022 13:40:46 -0700
Message-ID: <CAHbLzkqzHmRtk-46KuBGM6swQe4r20_LtSku-CZvmf+gxOhKCg@mail.gmail.com>
Subject: Re: [v2 PATCH 1/2] mm: khugepaged: allow page allocation fallback to
 eligible nodes
To:     Michal Hocko <mhocko@suse.com>
Cc:     zokeefe@google.com, akpm@linux-foundation.org, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Fri, Nov 4, 2022 at 12:55 PM Michal Hocko <mhocko@suse.com> wrote:
>
> On Fri 04-11-22 10:37:39, Yang Shi wrote:
> > On Fri, Nov 4, 2022 at 1:32 AM Michal Hocko <mhocko@suse.com> wrote:
> > >
> > > On Thu 03-11-22 14:36:40, Yang Shi wrote:
> > > [...]
> > > > So use nodemask to record the nodes which have the same hit record, the
> > > > hugepage allocation could fallback to those nodes.  And remove
> > > > __GFP_THISNODE since it does disallow fallback.  And if nodemask is
> > > > empty (no node is set), it means there is one single node has the most
> > > > hist record, the nodemask approach actually behaves like __GFP_THISNODE.
> > > >
> > > > Reported-by: syzbot+0044b22d177870ee974f@syzkaller.appspotmail.com
> > > > Suggested-by: Zach O'Keefe <zokeefe@google.com>
> > > > Suggested-by: Michal Hocko <mhocko@suse.com>
> > > > Signed-off-by: Yang Shi <shy828301@gmail.com>
> > > > ---
> > > >  mm/khugepaged.c | 32 ++++++++++++++------------------
> > > >  1 file changed, 14 insertions(+), 18 deletions(-)
> > > >
> > > > diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> > > > index ea0d186bc9d4..572ce7dbf4b0 100644
> > > > --- a/mm/khugepaged.c
> > > > +++ b/mm/khugepaged.c
> > > > @@ -97,8 +97,8 @@ struct collapse_control {
> > > >       /* Num pages scanned per node */
> > > >       u32 node_load[MAX_NUMNODES];
> > > >
> > > > -     /* Last target selected in hpage_collapse_find_target_node() */
> > > > -     int last_target_node;
> > > > +     /* nodemask for allocation fallback */
> > > > +     nodemask_t alloc_nmask;
> > >
> > > This will eat another 1k on the stack on most configurations
> > > (NODE_SHIFT=10). Along with 4k of node_load this is quite a lot even
> > > on shallow call chains like madvise resp. khugepaged.  I would just
> > > add a follow up patch which changes both node_load and alloc_nmask to
> > > dynamically allocated objects.
> >
> > The collapse_control is allocated by kmalloc dynamically for
> > MADV_COLLAPSE path, and defined as a global variable for khugepaged
> > (khugepaged_collapse_control). So it is not on stack.
>
> Dang, I must have been blind because I _think_ I have seen it as a local
> stack defined. Maybe I just implicitly put that to the same bucket as
> othe $foo_control (e.g. scan_control, oom_control etc) which leave on the
> stack usually. Sorry about the confusion. Sorry for the noise.

It doesn't matter. It was not put on the stack due to its size when
Zach was adding MADV_COLLAPSE.

>
> Acked-by: Michal Hocko <mhocko@suse.com>

Thanks.

> --
> Michal Hocko
> SUSE Labs