On Fri 04-11-22 10:37:39, Yang Shi wrote:
> On Fri, Nov 4, 2022 at 1:32 AM Michal Hocko <mhocko@xxxxxxxx> 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@xxxxxxxxxxxxxxxxxxxxxxxxx
> > > Suggested-by: Zach O'Keefe <zokeefe@xxxxxxxxxx>
> > > Suggested-by: Michal Hocko <mhocko@xxxxxxxx>
> > > Signed-off-by: Yang Shi <shy828301@xxxxxxxxx>
> > > ---
> > > 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.
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
--
Michal Hocko
SUSE Labs
