Re: [patch] thp, memcg: split hugepage for memcg oom on cow

[KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>]

(2012/04/04 10:56), David Rientjes wrote:

> On COW, a new hugepage is allocated and charged to the memcg.  If the
> memcg is oom, however, this charge will fail and will return VM_FAULT_OOM
> to the page fault handler which results in an oom kill.
> 
> Instead, it's possible to fallback to splitting the hugepage so that the
> COW results only in an order-0 page being charged to the memcg which has
> a higher liklihood to succeed.  This is expensive because the hugepage
> must be split in the page fault handler, but it is much better than
> unnecessarily oom killing a process.
> 
> Signed-off-by: David Rientjes <rientjes@xxxxxxxxxx>
> ---
>  mm/huge_memory.c |    1 +
>  mm/memory.c      |   18 +++++++++++++++---
>  2 files changed, 16 insertions(+), 3 deletions(-)
> 
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -959,6 +959,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
>  
>  	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
>  		put_page(new_page);
> +		split_huge_page(page);
>  		put_page(page);
>  		ret |= VM_FAULT_OOM;
>  		goto out;
> diff --git a/mm/memory.c b/mm/memory.c
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -3489,6 +3489,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
>  	if (unlikely(is_vm_hugetlb_page(vma)))
>  		return hugetlb_fault(mm, vma, address, flags);
>  
> +retry:
>  	pgd = pgd_offset(mm, address);
>  	pud = pud_alloc(mm, pgd, address);
>  	if (!pud)
> @@ -3502,13 +3503,24 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
>  							  pmd, flags);
>  	} else {
>  		pmd_t orig_pmd = *pmd;
> +		int ret;
> +
>  		barrier();
>  		if (pmd_trans_huge(orig_pmd)) {
>  			if (flags & FAULT_FLAG_WRITE &&
>  			    !pmd_write(orig_pmd) &&
> -			    !pmd_trans_splitting(orig_pmd))
> -				return do_huge_pmd_wp_page(mm, vma, address,
> -							   pmd, orig_pmd);
> +			    !pmd_trans_splitting(orig_pmd)) {
> +				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
> +							  orig_pmd);
> +				/*
> +				 * If COW results in an oom memcg, the huge pmd
> +				 * will already have been split, so retry the
> +				 * fault on the pte for a smaller charge.
> +				 */


IIUC, do_huge_pmd_wp_page_fallback() can return VM_FAULT_OOM. So, this check
is not related only to memcg.

> +				if (unlikely(ret & VM_FAULT_OOM))
> +					goto retry;
> +				return ret;
> +			}
>  			return 0;


Anyway, seems reasonable to me.

Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>