Re: [PATCH v4 2/3] mm: handle poisoning of pfn without struct pages

[Michal Hocko]

On Sun 02-11-25 11:55:56, Ankit Agrawal wrote:
> >> >> +static void add_to_kill_pfn(struct task_struct *tsk,
> >> >> +                         struct vm_area_struct *vma,
> >> >> +                         struct list_head *to_kill,
> >> >> +                         unsigned long pfn)
> >> >> +{
> >> >> +     struct to_kill *tk;
> >> >> +
> >> >> +     tk = kmalloc(sizeof(*tk), GFP_ATOMIC);
> >> >> +     if (!tk)
> >> >> +             return;
> >> >
> >> > This is unfortunate.  GFP_ATOMIC is unreliable and we silently behave
> >> > as if it worked OK.
> >>
> >> Got it. I'll mark this as a failure case.
> >
> > why do you need to batch all processes and kill them at once? Can you
> > just kill one by one?
> 
> Hi Michal, I am trying to replicate what is being done today for non-PFNMAP
> memory failure in __add_to_kill
> (https://github.com/torvalds/linux/blob/master/mm/memory-failure.c#L376).
> For this series, I am inclined to keep it uniform.

Unless there is a very good reason for this code then I would rather not
rely on an atomic allocation. This just makes the behavior hard to
predict
-- 
Michal Hocko
SUSE Labs