Re: [PATCH 39 of 66] memcg huge memory

[KAMEZAWA Hiroyuki]

On Wed, 03 Nov 2010 16:28:14 +0100
Andrea Arcangeli <aarcange@xxxxxxxxxx> wrote:

> From: Andrea Arcangeli <aarcange@xxxxxxxxxx>
> 
> Add memcg charge/uncharge to hugepage faults in huge_memory.c.
> 
> Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx>
> Acked-by: Rik van Riel <riel@xxxxxxxxxx>
> ---
> 
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -233,6 +233,7 @@ static int __do_huge_pmd_anonymous_page(
>  	VM_BUG_ON(!PageCompound(page));
>  	pgtable = pte_alloc_one(mm, haddr);
>  	if (unlikely(!pgtable)) {
> +		mem_cgroup_uncharge_page(page);
>  		put_page(page);
>  		return VM_FAULT_OOM;
>  	}
> @@ -243,6 +244,7 @@ static int __do_huge_pmd_anonymous_page(
>  	spin_lock(&mm->page_table_lock);
>  	if (unlikely(!pmd_none(*pmd))) {
>  		spin_unlock(&mm->page_table_lock);
> +		mem_cgroup_uncharge_page(page);
>  		put_page(page);
>  		pte_free(mm, pgtable);
>  	} else {
> @@ -286,6 +288,10 @@ int do_huge_pmd_anonymous_page(struct mm
>  		page = alloc_hugepage(transparent_hugepage_defrag(vma));
>  		if (unlikely(!page))
>  			goto out;
> +		if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
> +			put_page(page);
> +			goto out;
> +		}
>  
>  		return __do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page);
>  	}
> @@ -402,9 +408,15 @@ static int do_huge_pmd_wp_page_fallback(
>  	for (i = 0; i < HPAGE_PMD_NR; i++) {
>  		pages[i] = alloc_page_vma(GFP_HIGHUSER_MOVABLE,
>  					  vma, address);
> -		if (unlikely(!pages[i])) {
> -			while (--i >= 0)
> +		if (unlikely(!pages[i] ||
> +			     mem_cgroup_newpage_charge(pages[i], mm,
> +						       GFP_KERNEL))) {
> +			if (pages[i])
>  				put_page(pages[i]);
> +			while (--i >= 0) {
> +				mem_cgroup_uncharge_page(pages[i]);
> +				put_page(pages[i]);
> +			}

Maybe you can use batched-uncharge here.
==
mem_cgroup_uncharge_start()
{
	do loop;
}
mem_cgroup_uncharge_end();
==
Then, many atomic ops can be reduced.


>  			kfree(pages);
>  			ret |= VM_FAULT_OOM;
>  			goto out;
> @@ -455,8 +467,10 @@ out:
>  
>  out_free_pages:
>  	spin_unlock(&mm->page_table_lock);
> -	for (i = 0; i < HPAGE_PMD_NR; i++)
> +	for (i = 0; i < HPAGE_PMD_NR; i++) {
> +		mem_cgroup_uncharge_page(pages[i]);
>  		put_page(pages[i]);
> +	}

here, too.

>  	kfree(pages);
>  	goto out;
>  }
> @@ -501,14 +515,22 @@ int do_huge_pmd_wp_page(struct mm_struct
>  		goto out;
>  	}
>  
> +	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
> +		put_page(new_page);
> +		put_page(page);
> +		ret |= VM_FAULT_OOM;
> +		goto out;
> +	}
> +
>  	copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
>  	__SetPageUptodate(new_page);
>  
>  	spin_lock(&mm->page_table_lock);
>  	put_page(page);
> -	if (unlikely(!pmd_same(*pmd, orig_pmd)))
> +	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
> +		mem_cgroup_uncharge_page(new_page);
>  		put_page(new_page);
> -	else {
> +	} else {
>  		pmd_t entry;
>  		VM_BUG_ON(!PageHead(page));
>  		entry = mk_pmd(new_page, vma->vm_page_prot);


Hmm...it seems there are no codes for move_account() hugepage in series.
I think it needs some complicated work to walk page table.

Thanks,
-Kame

--
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/