Received-SPF: pass (google.com: domain of linux-kernel+bounces-134601-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Message-ID: <43d99616cd4a2a6fce6a6b97f73d08ebc5361a61.camel@gmail.com>
Subject: Re: [PATCH net-next v1 02/12] mm: page_frag: use initial zero
 offset for page_frag_alloc_align()
From: Alexander H Duyck <alexander.duyck@gmail.com>
To: Yunsheng Lin <linyunsheng@huawei.com>, davem@davemloft.net,
 kuba@kernel.org,  pabeni@redhat.com
Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org, Andrew Morton
	 <akpm@linux-foundation.org>, linux-mm@kvack.org
Date: Sun, 07 Apr 2024 10:52:34 -0700
In-Reply-To: <20240407130850.19625-3-linyunsheng@huawei.com>
References: <20240407130850.19625-1-linyunsheng@huawei.com>
	 <20240407130850.19625-3-linyunsheng@huawei.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
User-Agent: Evolution 3.48.4 (3.48.4-1.fc38) 
Precedence: bulk
MIME-Version: 1.0

On Sun, 2024-04-07 at 21:08 +0800, Yunsheng Lin wrote:
> We are above to use page_frag_alloc_*() API to not just
> allocate memory for skb->data, but also use them to do
> the memory allocation for skb frag too. Currently the
> implementation of page_frag in mm subsystem is running
> the offset as a countdown rather than count-up value,
> there may have several advantages to that as mentioned
> in [1], but it may have some disadvantages, for example,
> it may disable skb frag coaleasing and more correct cache
> prefetching
>=20
> We have a trade-off to make in order to have a unified
> implementation and API for page_frag, so use a initial zero
> offset in this patch, and the following patch will try to
> make some optimization to aovid the disadvantages as much
> as possible.
>=20
> 1. https://lore.kernel.org/all/f4abe71b3439b39d17a6fb2d410180f367cadf5c.c=
amel@gmail.com/
>=20
> CC: Alexander Duyck <alexander.duyck@gmail.com>
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> ---
>  mm/page_frag_cache.c | 31 ++++++++++++++-----------------
>  1 file changed, 14 insertions(+), 17 deletions(-)
>=20
> diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
> index a0f90ba25200..3e3e88d9af90 100644
> --- a/mm/page_frag_cache.c
> +++ b/mm/page_frag_cache.c
> @@ -67,9 +67,8 @@ void *__page_frag_alloc_align(struct page_frag_cache *n=
c,
>  			      unsigned int fragsz, gfp_t gfp_mask,
>  			      unsigned int align_mask)
>  {
> -	unsigned int size =3D PAGE_SIZE;
> +	unsigned int size, offset;
>  	struct page *page;
> -	int offset;
> =20
>  	if (unlikely(!nc->va)) {
>  refill:
> @@ -77,10 +76,6 @@ void *__page_frag_alloc_align(struct page_frag_cache *=
nc,
>  		if (!page)
>  			return NULL;
> =20
> -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
> -		/* if size can vary use size else just use PAGE_SIZE */
> -		size =3D nc->size;
> -#endif
>  		/* Even if we own the page, we do not use atomic_set().
>  		 * This would break get_page_unless_zero() users.
>  		 */
> @@ -89,11 +84,18 @@ void *__page_frag_alloc_align(struct page_frag_cache =
*nc,
>  		/* reset page count bias and offset to start of new frag */
>  		nc->pfmemalloc =3D page_is_pfmemalloc(page);
>  		nc->pagecnt_bias =3D PAGE_FRAG_CACHE_MAX_SIZE + 1;
> -		nc->offset =3D size;
> +		nc->offset =3D 0;
>  	}
> =20
> -	offset =3D nc->offset - fragsz;
> -	if (unlikely(offset < 0)) {
> +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
> +	/* if size can vary use size else just use PAGE_SIZE */
> +	size =3D nc->size;
> +#else
> +	size =3D PAGE_SIZE;
> +#endif
> +
> +	offset =3D ALIGN(nc->offset, -align_mask);
> +	if (unlikely(offset + fragsz > size)) {

Rather than using "ALIGN" with a negative value it would probably make
more sense to use __ALIGN_KERNEL_MASK with ~align_mask. I am not sure
how well the compiler sorts out the use of negatives to flip values
that are then converted to masks with the "(a) - 1".

>  		page =3D virt_to_page(nc->va);
> =20
>  		if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
> @@ -104,17 +106,13 @@ void *__page_frag_alloc_align(struct page_frag_cach=
e *nc,
>  			goto refill;
>  		}
> =20
> -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
> -		/* if size can vary use size else just use PAGE_SIZE */
> -		size =3D nc->size;
> -#endif
>  		/* OK, page count is 0, we can safely set it */
>  		set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);
> =20
>  		/* reset page count bias and offset to start of new frag */
>  		nc->pagecnt_bias =3D PAGE_FRAG_CACHE_MAX_SIZE + 1;
> -		offset =3D size - fragsz;
> -		if (unlikely(offset < 0)) {
> +		offset =3D 0;
> +		if (unlikely(fragsz > size)) {
>  			/*
>  			 * The caller is trying to allocate a fragment
>  			 * with fragsz > PAGE_SIZE but the cache isn't big
> @@ -129,8 +127,7 @@ void *__page_frag_alloc_align(struct page_frag_cache =
*nc,
>  	}
> =20
>  	nc->pagecnt_bias--;
> -	offset &=3D align_mask;
> -	nc->offset =3D offset;
> +	nc->offset =3D offset + fragsz;
> =20
>  	return nc->va + offset;
>  }