Re: [PATCH] mm: hugetlb: fix hugetlb allocation failure when handling freed or in-use hugetlb

[Baolin Wang]

On 2/5/2024 5:31 PM, Michal Hocko wrote:
> On Mon 05-02-24 11:54:17, Baolin Wang wrote:
> > When handling the freed hugetlb or in-use hugetlb, we should ignore the
> > failure of alloc_buddy_hugetlb_folio() to dissolve the old hugetlb successfully,
> > since we did not use the new allocated hugetlb in this 2 cases.
> >
> > Signed-off-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
> > ---
> >   mm/hugetlb.c | 18 ++++++++++++------
> >   1 file changed, 12 insertions(+), 6 deletions(-)
> >
> > diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> > index 9d996fe4ecd9..212ab331d355 100644
> > --- a/mm/hugetlb.c
> > +++ b/mm/hugetlb.c
> > @@ -3042,9 +3042,8 @@ static int alloc_and_dissolve_hugetlb_folio(struct hstate *h,
> >   	 * under the lock.
> >   	 */
> >   	new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, NULL, NULL);
> > -	if (!new_folio)
> > -		return -ENOMEM;
> > -	__prep_new_hugetlb_folio(h, new_folio);
> > +	if (new_folio)
> > +		__prep_new_hugetlb_folio(h, new_folio);
>
> Is there any reason why you haven't moved the allocation to the only
> branch that actually needs it? I know that we hold hugetlb lock but you

Nope, just did a simple patch to ignore the allocation failure.

> could have easily dropped the lock, allocate a page and then goto retry.
> This would actually save an allocation.

Yes, will do. Thanks.

> Something like this:
>
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index ed1581b670d4..db5f72b94422 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -3029,21 +3029,9 @@ static int alloc_and_dissolve_hugetlb_folio(struct hstate *h,
>   {
>   	gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
>   	int nid = folio_nid(old_folio);
> -	struct folio *new_folio;
> +	struct folio *new_folio = NULL;
>   	int ret = 0;
>   
> -	/*
> -	 * Before dissolving the folio, we need to allocate a new one for the
> -	 * pool to remain stable.  Here, we allocate the folio and 'prep' it
> -	 * by doing everything but actually updating counters and adding to
> -	 * the pool.  This simplifies and let us do most of the processing
> -	 * under the lock.
> -	 */
> -	new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, NULL, NULL);
> -	if (!new_folio)
> -		return -ENOMEM;
> -	__prep_new_hugetlb_folio(h, new_folio);
> -
>   retry:
>   	spin_lock_irq(&hugetlb_lock);
>   	if (!folio_test_hugetlb(old_folio)) {
> @@ -3073,6 +3061,15 @@ static int alloc_and_dissolve_hugetlb_folio(struct hstate *h,
>   		cond_resched();
>   		goto retry;
>   	} else {
> +
> +		if (!new_folio) {
> +			spin_unlock_irq(&hugetlb_lock);
> +			new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, NULL, NULL);
> +			if (!new_folio)
> +				return -ENOMEM;
> +			__prep_new_hugetlb_folio(h, new_folio);
> +			goto retry;
> +		}
>   		/*
>   		 * Ok, old_folio is still a genuine free hugepage. Remove it from
>   		 * the freelist and decrease the counters. These will be
> @@ -3100,9 +3097,11 @@ static int alloc_and_dissolve_hugetlb_folio(struct hstate *h,
>   
>   free_new:
>   	spin_unlock_irq(&hugetlb_lock);
> -	/* Folio has a zero ref count, but needs a ref to be freed */
> -	folio_ref_unfreeze(new_folio, 1);
> -	update_and_free_hugetlb_folio(h, new_folio, false);
> +	if (new_folio) {
> +		/* Folio has a zero ref count, but needs a ref to be freed */
> +		folio_ref_unfreeze(new_folio, 1);
> +		update_and_free_hugetlb_folio(h, new_folio, false);
> +	}
>   
>   	return ret;
>   }