Re: [PATCH 0/5] MADV_FREE refactoring and fix KSM page

[Andrew Morton]

On Tue, 20 Oct 2015 16:21:09 +0900 Minchan Kim <minchan@xxxxxxxxxx> wrote:

> 
> I reviewed THP refcount redesign patch and It seems below patch fixes
> MADV_FREE problem. It works well for hours.
> 
> >From 104a0940b4c0f97e61de9fee0fd602926ff28312 Mon Sep 17 00:00:00 2001
> From: Minchan Kim <minchan@xxxxxxxxxx>
> Date: Tue, 20 Oct 2015 16:00:52 +0900
> Subject: [PATCH] mm: mark head page dirty in split_huge_page
> 
> In thp split in old THP refcount, we mappped all of pages
> (ie, head + tails) to pte_mkdirty and mark PG_flags to every
> tail pages.
> 
> But with THP refcount redesign, we can lose dirty bit in page table
> and PG_dirty for head page if we want to free the THP page using
> migration_entry.
> 
> It ends up discarding head page by madvise_free suddenly.
> This patch fixes it by mark the head page PG_dirty when VM splits
> the THP page.
> 
> Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>
> ---
>  mm/huge_memory.c | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index adccfb48ce57..7fbbd42554a1 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -3258,6 +3258,7 @@ static void __split_huge_page(struct page *page, struct list_head *list)
>  	atomic_sub(tail_mapcount, &head->_count);
>  
>  	ClearPageCompound(head);
> +	SetPageDirty(head);
>  	spin_unlock_irq(&zone->lru_lock);
>  
>  	unfreeze_page(page_anon_vma(head), head);

This appears to be a bugfix against Kirill's "thp: reintroduce
split_huge_page()"?

Yes, __split_huge_page() is marking the tail pages dirty but forgot
about the head page

You say "we can lose dirty bit in page table" but I don't see how the
above patch fixes that?


Why does __split_huge_page() unconditionally mark the pages dirty, btw?
Is it because the THP page was known to be dirty?  If so, the head
page already had PG_dirty, so this patch doesn't do anything.

freeze_page(), unfreeze_page() and their callees desperately need some
description of what they're doing.  Kirill, could you cook somethnig up
please?


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/