Re: [PATCH RFC 1/4] mm: throttle MADV_FREE

[Michal Hocko <mhocko@suse.cz>]

On Wed 25-02-15 16:11:18, Minchan Kim wrote:
[...]
> diff --git a/mm/madvise.c b/mm/madvise.c
> index 6d0fcb8921c2..d41ae76d3e54 100644
> --- a/mm/madvise.c
> +++ b/mm/madvise.c
> @@ -274,7 +274,9 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
>  	spinlock_t *ptl;
>  	pte_t *pte, ptent;
>  	struct page *page;
> +	swp_entry_t entry;
>  	unsigned long next;
> +	int rss = 0;
>  
>  	next = pmd_addr_end(addr, end);
>  	if (pmd_trans_huge(*pmd)) {
> @@ -293,9 +295,19 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
>  	for (; addr != end; pte++, addr += PAGE_SIZE) {
>  		ptent = *pte;
>  
> -		if (!pte_present(ptent))
> +		if (pte_none(ptent))
>  			continue;
>  
> +		if (!pte_present(ptent)) {
> +			entry = pte_to_swp_entry(ptent);
> +			if (non_swap_entry(entry))
> +				continue;
> +			rss--;
> +			free_swap_and_cache(entry);
> +			pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
> +			continue;
> +		}

Yes this makes sense. rss is a bit confusing because those pages are not
resident.

> +
>  		page = vm_normal_page(vma, addr, ptent);
>  		if (!page)
>  			continue;
> @@ -326,6 +338,14 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
>  		set_pte_at(mm, addr, pte, ptent);
>  		tlb_remove_tlb_entry(tlb, pte, addr);
>  	}
> +
> +	if (rss) {
> +		if (current->mm == mm)
> +			sync_mm_rss(mm);
> +
> +		add_mm_counter(mm, MM_SWAPENTS, rss);
> +	}
> +
>  	arch_leave_lazy_mmu_mode();
>  	pte_unmap_unlock(pte - 1, ptl);
>  next:
> -- 
> 1.9.1
-- 
Michal Hocko
SUSE Labs