mm: deduct the number of pages reclaimed by madvise from workingset

  From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>

The pages reclaimed by madvise_pageout are made of inactive and dropped from LRU
forcefully, which lead to the coming up refault pages possess a large refault
distance than it should be. These could affect the accuracy of thrashing when
madvise_pageout is used as a common way of memory reclaiming as ANDROID does now.

Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
---
 include/linux/swap.h | 2 +-
 mm/madvise.c         | 4 ++--
 mm/vmscan.c          | 8 +++++++-
 3 files changed, 10 insertions(+), 4 deletions(-)
  

On Wed, May 24, 2023 at 2:13 AM zhaoyang.huang
<zhaoyang.huang@unisoc.com> wrote:
>
> From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
>
> The pages reclaimed by madvise_pageout are made of inactive and dropped from LRU
> forcefully, which lead to the coming up refault pages possess a large refault
> distance than it should be. These could affect the accuracy of thrashing when
> madvise_pageout is used as a common way of memory reclaiming as ANDROID does now.

Doesn't workingset_eviction() in the following call chain already
handle nonresident page aging?:

reclaim_pages
  reclaim_folio_list
    shrink_folio_list
      __remove_mapping
        workingset_eviction
          workingset_age_nonresident


>
> Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
> ---
>  include/linux/swap.h | 2 +-
>  mm/madvise.c         | 4 ++--
>  mm/vmscan.c          | 8 +++++++-
>  3 files changed, 10 insertions(+), 4 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 2787b84..0312142 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -428,7 +428,7 @@ extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
>  extern int vm_swappiness;
>  long remove_mapping(struct address_space *mapping, struct folio *folio);
>
> -extern unsigned long reclaim_pages(struct list_head *page_list);
> +extern unsigned long reclaim_pages(struct mm_struct *mm, struct list_head *page_list);
>  #ifdef CONFIG_NUMA
>  extern int node_reclaim_mode;
>  extern int sysctl_min_unmapped_ratio;
> diff --git a/mm/madvise.c b/mm/madvise.c
> index b6ea204..61c8d7b 100644
> --- a/mm/madvise.c
> +++ b/mm/madvise.c
> @@ -420,7 +420,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
>  huge_unlock:
>                 spin_unlock(ptl);
>                 if (pageout)
> -                       reclaim_pages(&page_list);
> +                       reclaim_pages(mm, &page_list);
>                 return 0;
>         }
>
> @@ -516,7 +516,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
>         arch_leave_lazy_mmu_mode();
>         pte_unmap_unlock(orig_pte, ptl);
>         if (pageout)
> -               reclaim_pages(&page_list);
> +               reclaim_pages(mm, &page_list);
>         cond_resched();
>
>         return 0;
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 20facec..048c10b 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2741,12 +2741,14 @@ static unsigned int reclaim_folio_list(struct list_head *folio_list,
>         return nr_reclaimed;
>  }
>
> -unsigned long reclaim_pages(struct list_head *folio_list)
> +unsigned long reclaim_pages(struct mm_struct *mm, struct list_head *folio_list)

You would also need to change Damon usage of reclaim_pages() here:
https://elixir.bootlin.com/linux/v6.4-rc1/source/mm/damon/paddr.c#L253

>  {
>         int nid;
>         unsigned int nr_reclaimed = 0;
>         LIST_HEAD(node_folio_list);
>         unsigned int noreclaim_flag;
> +       struct lruvec *lruvec;
> +       struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
>
>         if (list_empty(folio_list))
>                 return nr_reclaimed;
> @@ -2764,10 +2766,14 @@ unsigned long reclaim_pages(struct list_head *folio_list)
>                 }
>
>                 nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
> +               lruvec = &memcg->nodeinfo[nid]->lruvec;
> +               workingset_age_nonresident(lruvec, -nr_reclaimed);
>                 nid = folio_nid(lru_to_folio(folio_list));
>         } while (!list_empty(folio_list));
>
>         nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
> +       lruvec = &memcg->nodeinfo[nid]->lruvec;
> +       workingset_age_nonresident(lruvec, -nr_reclaimed);
>
>         memalloc_noreclaim_restore(noreclaim_flag);
>
> --
> 1.9.1
>
  

On Thu, May 25, 2023 at 4:41 AM Suren Baghdasaryan <surenb@google.com> wrote:
>
> On Wed, May 24, 2023 at 2:13 AM zhaoyang.huang
> <zhaoyang.huang@unisoc.com> wrote:
> >
> > From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
> >
> > The pages reclaimed by madvise_pageout are made of inactive and dropped from LRU
> > forcefully, which lead to the coming up refault pages possess a large refault
> > distance than it should be. These could affect the accuracy of thrashing when
> > madvise_pageout is used as a common way of memory reclaiming as ANDROID does now.
>
> Doesn't workingset_eviction() in the following call chain already
> handle nonresident page aging?:
>
> reclaim_pages
>   reclaim_folio_list
>     shrink_folio_list
>       __remove_mapping
>         workingset_eviction
>           workingset_age_nonresident
Yes. What I suggest is to minor this pages from non-resident as they
are dropped forcefully
>
>
> >
> > Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
> > ---
> >  include/linux/swap.h | 2 +-
> >  mm/madvise.c         | 4 ++--
> >  mm/vmscan.c          | 8 +++++++-
> >  3 files changed, 10 insertions(+), 4 deletions(-)
> >
> > diff --git a/include/linux/swap.h b/include/linux/swap.h
> > index 2787b84..0312142 100644
> > --- a/include/linux/swap.h
> > +++ b/include/linux/swap.h
> > @@ -428,7 +428,7 @@ extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
> >  extern int vm_swappiness;
> >  long remove_mapping(struct address_space *mapping, struct folio *folio);
> >
> > -extern unsigned long reclaim_pages(struct list_head *page_list);
> > +extern unsigned long reclaim_pages(struct mm_struct *mm, struct list_head *page_list);
> >  #ifdef CONFIG_NUMA
> >  extern int node_reclaim_mode;
> >  extern int sysctl_min_unmapped_ratio;
> > diff --git a/mm/madvise.c b/mm/madvise.c
> > index b6ea204..61c8d7b 100644
> > --- a/mm/madvise.c
> > +++ b/mm/madvise.c
> > @@ -420,7 +420,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> >  huge_unlock:
> >                 spin_unlock(ptl);
> >                 if (pageout)
> > -                       reclaim_pages(&page_list);
> > +                       reclaim_pages(mm, &page_list);
> >                 return 0;
> >         }
> >
> > @@ -516,7 +516,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> >         arch_leave_lazy_mmu_mode();
> >         pte_unmap_unlock(orig_pte, ptl);
> >         if (pageout)
> > -               reclaim_pages(&page_list);
> > +               reclaim_pages(mm, &page_list);
> >         cond_resched();
> >
> >         return 0;
> > diff --git a/mm/vmscan.c b/mm/vmscan.c
> > index 20facec..048c10b 100644
> > --- a/mm/vmscan.c
> > +++ b/mm/vmscan.c
> > @@ -2741,12 +2741,14 @@ static unsigned int reclaim_folio_list(struct list_head *folio_list,
> >         return nr_reclaimed;
> >  }
> >
> > -unsigned long reclaim_pages(struct list_head *folio_list)
> > +unsigned long reclaim_pages(struct mm_struct *mm, struct list_head *folio_list)
>
> You would also need to change Damon usage of reclaim_pages() here:
> https://elixir.bootlin.com/linux/v6.4-rc1/source/mm/damon/paddr.c#L253
ok, thanks for reminding
>
> >  {
> >         int nid;
> >         unsigned int nr_reclaimed = 0;
> >         LIST_HEAD(node_folio_list);
> >         unsigned int noreclaim_flag;
> > +       struct lruvec *lruvec;
> > +       struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
> >
> >         if (list_empty(folio_list))
> >                 return nr_reclaimed;
> > @@ -2764,10 +2766,14 @@ unsigned long reclaim_pages(struct list_head *folio_list)
> >                 }
> >
> >                 nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
> > +               lruvec = &memcg->nodeinfo[nid]->lruvec;
> > +               workingset_age_nonresident(lruvec, -nr_reclaimed);
> >                 nid = folio_nid(lru_to_folio(folio_list));
> >         } while (!list_empty(folio_list));
> >
> >         nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
> > +       lruvec = &memcg->nodeinfo[nid]->lruvec;
> > +       workingset_age_nonresident(lruvec, -nr_reclaimed);
> >
> >         memalloc_noreclaim_restore(noreclaim_flag);
> >
> > --
> > 1.9.1
> >
  

On Wed, May 24, 2023 at 05:12:54PM +0800, zhaoyang.huang wrote:
> From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
> 
> The pages reclaimed by madvise_pageout are made of inactive and dropped from LRU
> forcefully, which lead to the coming up refault pages possess a large refault
> distance than it should be. These could affect the accuracy of thrashing when
> madvise_pageout is used as a common way of memory reclaiming as ANDROID does now.

This alludes to, but doesn't explain, a real world usecase.

Yes, madvise_pageout() will record non-resident entries today. This
means refault and thrash detection is on for user-driven reclaim.

So why is that undesirable?

Today we measure and report the cost of reclaim and memory pressure
for physical memory shortages, cgroup limits, and user-driven cgroup
reclaim. Why should we not do the same for madv_pageout()? If the
userspace code that drives pageout has a bug and the result is extreme
thrashing, wouldn't you want to know that?

Please explain the idea here better.

> Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
> ---
>  include/linux/swap.h | 2 +-
>  mm/madvise.c         | 4 ++--
>  mm/vmscan.c          | 8 +++++++-
>  3 files changed, 10 insertions(+), 4 deletions(-)
> 
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 2787b84..0312142 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -428,7 +428,7 @@ extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
>  extern int vm_swappiness;
>  long remove_mapping(struct address_space *mapping, struct folio *folio);
>  
> -extern unsigned long reclaim_pages(struct list_head *page_list);
> +extern unsigned long reclaim_pages(struct mm_struct *mm, struct list_head *page_list);
>  #ifdef CONFIG_NUMA
>  extern int node_reclaim_mode;
>  extern int sysctl_min_unmapped_ratio;
> diff --git a/mm/madvise.c b/mm/madvise.c
> index b6ea204..61c8d7b 100644
> --- a/mm/madvise.c
> +++ b/mm/madvise.c
> @@ -420,7 +420,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
>  huge_unlock:
>  		spin_unlock(ptl);
>  		if (pageout)
> -			reclaim_pages(&page_list);
> +			reclaim_pages(mm, &page_list);
>  		return 0;
>  	}
>  
> @@ -516,7 +516,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
>  	arch_leave_lazy_mmu_mode();
>  	pte_unmap_unlock(orig_pte, ptl);
>  	if (pageout)
> -		reclaim_pages(&page_list);
> +		reclaim_pages(mm, &page_list);
>  	cond_resched();
>  
>  	return 0;
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 20facec..048c10b 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2741,12 +2741,14 @@ static unsigned int reclaim_folio_list(struct list_head *folio_list,
>  	return nr_reclaimed;
>  }
>  
> -unsigned long reclaim_pages(struct list_head *folio_list)
> +unsigned long reclaim_pages(struct mm_struct *mm, struct list_head *folio_list)
>  {
>  	int nid;
>  	unsigned int nr_reclaimed = 0;
>  	LIST_HEAD(node_folio_list);
>  	unsigned int noreclaim_flag;
> +	struct lruvec *lruvec;
> +	struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
>  
>  	if (list_empty(folio_list))
>  		return nr_reclaimed;
> @@ -2764,10 +2766,14 @@ unsigned long reclaim_pages(struct list_head *folio_list)
>  		}
>  
>  		nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
> +		lruvec = &memcg->nodeinfo[nid]->lruvec;
> +		workingset_age_nonresident(lruvec, -nr_reclaimed);
>  		nid = folio_nid(lru_to_folio(folio_list));
>  	} while (!list_empty(folio_list));
>  
>  	nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
> +	lruvec = &memcg->nodeinfo[nid]->lruvec;
> +	workingset_age_nonresident(lruvec, -nr_reclaimed);

The task might have moved cgroups in between, who knows what kind of
artifacts it will introduce if you wind back the wrong clock.

If there are reclaim passes that shouldn't participate in non-resident
tracking, that should be plumbed through the stack to __remove_mapping
(which already has that bool reclaimed param to not record entries).
  

On Thu, May 25, 2023 at 9:54 PM Johannes Weiner <hannes@cmpxchg.org> wrote:
>
> On Wed, May 24, 2023 at 05:12:54PM +0800, zhaoyang.huang wrote:
> > From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
> >
> > The pages reclaimed by madvise_pageout are made of inactive and dropped from LRU
> > forcefully, which lead to the coming up refault pages possess a large refault
> > distance than it should be. These could affect the accuracy of thrashing when
> > madvise_pageout is used as a common way of memory reclaiming as ANDROID does now.
>
> This alludes to, but doesn't explain, a real world usecase.
More block io(wait_on_page_bit_common) observed during APP start in
latest android version where user space memory reclaiming changes from
in-kernel PPR to madvise_pageout. We believe that it could be related
with inaccuracy of workingset.
>
> Yes, madvise_pageout() will record non-resident entries today. This
> means refault and thrash detection is on for user-driven reclaim.
>
> So why is that undesirable?
Let's raise an extreme scenario, that is, the tail page of LRU could
experience a given refault distance without any in-kernel reclaiming
and be wrongly deemed as inactive and get less protection.
>
> Today we measure and report the cost of reclaim and memory pressure
> for physical memory shortages, cgroup limits, and user-driven cgroup
> reclaim. Why should we not do the same for madv_pageout()? If the
> userspace code that drives pageout has a bug and the result is extreme
> thrashing, wouldn't you want to know that?
Actually, the pages evicted by madv_cold/pageout from active_lru are
not marked as WORKINGSET, which will surpass the thrashing account
when it faults back and gets struck by IO. I think they should be
treated in the same way in terms of SetPageWorkingset and
lruvec->non-resident. Please refer to my previous patch "mm: mark
folio as workingset in lru_deactivate_fn index 70e2063..4d1c14f
100644"


>
> Please explain the idea here better.
>
> > Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
> > ---
> >  include/linux/swap.h | 2 +-
> >  mm/madvise.c         | 4 ++--
> >  mm/vmscan.c          | 8 +++++++-
> >  3 files changed, 10 insertions(+), 4 deletions(-)
> >
> > diff --git a/include/linux/swap.h b/include/linux/swap.h
> > index 2787b84..0312142 100644
> > --- a/include/linux/swap.h
> > +++ b/include/linux/swap.h
> > @@ -428,7 +428,7 @@ extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
> >  extern int vm_swappiness;
> >  long remove_mapping(struct address_space *mapping, struct folio *folio);
> >
> > -extern unsigned long reclaim_pages(struct list_head *page_list);
> > +extern unsigned long reclaim_pages(struct mm_struct *mm, struct list_head *page_list);
> >  #ifdef CONFIG_NUMA
> >  extern int node_reclaim_mode;
> >  extern int sysctl_min_unmapped_ratio;
> > diff --git a/mm/madvise.c b/mm/madvise.c
> > index b6ea204..61c8d7b 100644
> > --- a/mm/madvise.c
> > +++ b/mm/madvise.c
> > @@ -420,7 +420,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> >  huge_unlock:
> >               spin_unlock(ptl);
> >               if (pageout)
> > -                     reclaim_pages(&page_list);
> > +                     reclaim_pages(mm, &page_list);
> >               return 0;
> >       }
> >
> > @@ -516,7 +516,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> >       arch_leave_lazy_mmu_mode();
> >       pte_unmap_unlock(orig_pte, ptl);
> >       if (pageout)
> > -             reclaim_pages(&page_list);
> > +             reclaim_pages(mm, &page_list);
> >       cond_resched();
> >
> >       return 0;
> > diff --git a/mm/vmscan.c b/mm/vmscan.c
> > index 20facec..048c10b 100644
> > --- a/mm/vmscan.c
> > +++ b/mm/vmscan.c
> > @@ -2741,12 +2741,14 @@ static unsigned int reclaim_folio_list(struct list_head *folio_list,
> >       return nr_reclaimed;
> >  }
> >
> > -unsigned long reclaim_pages(struct list_head *folio_list)
> > +unsigned long reclaim_pages(struct mm_struct *mm, struct list_head *folio_list)
> >  {
> >       int nid;
> >       unsigned int nr_reclaimed = 0;
> >       LIST_HEAD(node_folio_list);
> >       unsigned int noreclaim_flag;
> > +     struct lruvec *lruvec;
> > +     struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
> >
> >       if (list_empty(folio_list))
> >               return nr_reclaimed;
> > @@ -2764,10 +2766,14 @@ unsigned long reclaim_pages(struct list_head *folio_list)
> >               }
> >
> >               nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
> > +             lruvec = &memcg->nodeinfo[nid]->lruvec;
> > +             workingset_age_nonresident(lruvec, -nr_reclaimed);
> >               nid = folio_nid(lru_to_folio(folio_list));
> >       } while (!list_empty(folio_list));
> >
> >       nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
> > +     lruvec = &memcg->nodeinfo[nid]->lruvec;
> > +     workingset_age_nonresident(lruvec, -nr_reclaimed);
>
> The task might have moved cgroups in between, who knows what kind of
> artifacts it will introduce if you wind back the wrong clock.
>
> If there are reclaim passes that shouldn't participate in non-resident
> tracking, that should be plumbed through the stack to __remove_mapping
> (which already has that bool reclaimed param to not record entries).
  

On Thu, May 25, 2023 at 11:39 PM Zhaoyang Huang <huangzhaoyang@gmail.com> wrote:
>
> On Thu, May 25, 2023 at 9:54 PM Johannes Weiner <hannes@cmpxchg.org> wrote:
> >
> > On Wed, May 24, 2023 at 05:12:54PM +0800, zhaoyang.huang wrote:
> > > From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
> > >
> > > The pages reclaimed by madvise_pageout are made of inactive and dropped from LRU
> > > forcefully, which lead to the coming up refault pages possess a large refault
> > > distance than it should be. These could affect the accuracy of thrashing when
> > > madvise_pageout is used as a common way of memory reclaiming as ANDROID does now.
> >
> > This alludes to, but doesn't explain, a real world usecase.
> More block io(wait_on_page_bit_common) observed during APP start in
> latest android version where user space memory reclaiming changes from
> in-kernel PPR to madvise_pageout. We believe that it could be related
> with inaccuracy of workingset.

Do you mean the userspace incorrectly treats the active workingset as
inactive and purges it? If so, it sounds like the fix should be in the
userspace, not in the kernel.

> >
> > Yes, madvise_pageout() will record non-resident entries today. This
> > means refault and thrash detection is on for user-driven reclaim.
> >
> > So why is that undesirable?
> Let's raise an extreme scenario, that is, the tail page of LRU could
> experience a given refault distance without any in-kernel reclaiming
> and be wrongly deemed as inactive and get less protection.

madvise_pageout is a hint to the kernel that this page should be
treated as inactive, which it does. Why is that wrong?

> >
> > Today we measure and report the cost of reclaim and memory pressure
> > for physical memory shortages, cgroup limits, and user-driven cgroup
> > reclaim. Why should we not do the same for madv_pageout()? If the
> > userspace code that drives pageout has a bug and the result is extreme
> > thrashing, wouldn't you want to know that?
> Actually, the pages evicted by madv_cold/pageout from active_lru are
> not marked as WORKINGSET, which will surpass the thrashing account
> when it faults back and gets struck by IO. I think they should be
> treated in the same way in terms of SetPageWorkingset and
> lruvec->non-resident. Please refer to my previous patch "mm: mark
> folio as workingset in lru_deactivate_fn index 70e2063..4d1c14f
> 100644"

I see your point but it's debatable. If madvise_pageout is a hint to
treat the page as inactive, then why should the kernel treat it as
part of the active workingset when evicting?
I guess it boils down to whether the kernel should try fixing a wrong
hint from the userspace. I think not but I would be interested in the
opinions of others.
Thanks,
Suren.

>
>
> >
> > Please explain the idea here better.
> >
> > > Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
> > > ---
> > >  include/linux/swap.h | 2 +-
> > >  mm/madvise.c         | 4 ++--
> > >  mm/vmscan.c          | 8 +++++++-
> > >  3 files changed, 10 insertions(+), 4 deletions(-)
> > >
> > > diff --git a/include/linux/swap.h b/include/linux/swap.h
> > > index 2787b84..0312142 100644
> > > --- a/include/linux/swap.h
> > > +++ b/include/linux/swap.h
> > > @@ -428,7 +428,7 @@ extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
> > >  extern int vm_swappiness;
> > >  long remove_mapping(struct address_space *mapping, struct folio *folio);
> > >
> > > -extern unsigned long reclaim_pages(struct list_head *page_list);
> > > +extern unsigned long reclaim_pages(struct mm_struct *mm, struct list_head *page_list);
> > >  #ifdef CONFIG_NUMA
> > >  extern int node_reclaim_mode;
> > >  extern int sysctl_min_unmapped_ratio;
> > > diff --git a/mm/madvise.c b/mm/madvise.c
> > > index b6ea204..61c8d7b 100644
> > > --- a/mm/madvise.c
> > > +++ b/mm/madvise.c
> > > @@ -420,7 +420,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> > >  huge_unlock:
> > >               spin_unlock(ptl);
> > >               if (pageout)
> > > -                     reclaim_pages(&page_list);
> > > +                     reclaim_pages(mm, &page_list);
> > >               return 0;
> > >       }
> > >
> > > @@ -516,7 +516,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> > >       arch_leave_lazy_mmu_mode();
> > >       pte_unmap_unlock(orig_pte, ptl);
> > >       if (pageout)
> > > -             reclaim_pages(&page_list);
> > > +             reclaim_pages(mm, &page_list);
> > >       cond_resched();
> > >
> > >       return 0;
> > > diff --git a/mm/vmscan.c b/mm/vmscan.c
> > > index 20facec..048c10b 100644
> > > --- a/mm/vmscan.c
> > > +++ b/mm/vmscan.c
> > > @@ -2741,12 +2741,14 @@ static unsigned int reclaim_folio_list(struct list_head *folio_list,
> > >       return nr_reclaimed;
> > >  }
> > >
> > > -unsigned long reclaim_pages(struct list_head *folio_list)
> > > +unsigned long reclaim_pages(struct mm_struct *mm, struct list_head *folio_list)
> > >  {
> > >       int nid;
> > >       unsigned int nr_reclaimed = 0;
> > >       LIST_HEAD(node_folio_list);
> > >       unsigned int noreclaim_flag;
> > > +     struct lruvec *lruvec;
> > > +     struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
> > >
> > >       if (list_empty(folio_list))
> > >               return nr_reclaimed;
> > > @@ -2764,10 +2766,14 @@ unsigned long reclaim_pages(struct list_head *folio_list)
> > >               }
> > >
> > >               nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
> > > +             lruvec = &memcg->nodeinfo[nid]->lruvec;
> > > +             workingset_age_nonresident(lruvec, -nr_reclaimed);
> > >               nid = folio_nid(lru_to_folio(folio_list));
> > >       } while (!list_empty(folio_list));
> > >
> > >       nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
> > > +     lruvec = &memcg->nodeinfo[nid]->lruvec;
> > > +     workingset_age_nonresident(lruvec, -nr_reclaimed);
> >
> > The task might have moved cgroups in between, who knows what kind of
> > artifacts it will introduce if you wind back the wrong clock.
> >
> > If there are reclaim passes that shouldn't participate in non-resident
> > tracking, that should be plumbed through the stack to __remove_mapping
> > (which already has that bool reclaimed param to not record entries).