Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20230609131740.7496-1-linyunsheng@huawei.com> <20230609131740.7496-4-linyunsheng@huawei.com>
In-Reply-To: <20230609131740.7496-4-linyunsheng@huawei.com>
From:   Alexander Duyck <alexander.duyck@gmail.com>
Date:   Tue, 13 Jun 2023 07:36:20 -0700
Message-ID: <CAKgT0UfVwQ=ri7ZDNnsATH2RQpEz+zDBBb6YprvniMEWGdw+dQ@mail.gmail.com>
Subject: Re: [PATCH net-next v3 3/4] page_pool: introduce page_pool_alloc() API
To:     Yunsheng Lin <linyunsheng@huawei.com>
Cc:     davem@davemloft.net, kuba@kernel.org, pabeni@redhat.com,
        netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
        Lorenzo Bianconi <lorenzo@kernel.org>,
        Jesper Dangaard Brouer <hawk@kernel.org>,
        Ilias Apalodimas <ilias.apalodimas@linaro.org>,
        Eric Dumazet <edumazet@google.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Fri, Jun 9, 2023 at 6:20=E2=80=AFAM Yunsheng Lin <linyunsheng@huawei.com=
> wrote:
>
> Currently page pool supports the below use cases:
> use case 1: allocate page without page splitting using
>             page_pool_alloc_pages() API if the driver knows
>             that the memory it need is always bigger than
>             half of the page allocated from page pool.
> use case 2: allocate page frag with page splitting using
>             page_pool_alloc_frag() API if the driver knows
>             that the memory it need is always smaller than
>             or equal to the half of the page allocated from
>             page pool.
>
> There is emerging use case [1] & [2] that is a mix of the
> above two case: the driver doesn't know the size of memory it
> need beforehand, so the driver may use something like below to
> allocate memory with least memory utilization and performance
> penalty:
>
> if (size << 1 > max_size)
>         page =3D page_pool_alloc_pages();
> else
>         page =3D page_pool_alloc_frag();
>
> To avoid the driver doing something like above, add the
> page_pool_alloc() API to support the above use case, and update
> the true size of memory that is acctually allocated by updating
> '*size' back to the driver in order to avoid the truesize
> underestimate problem.
>
> 1. https://lore.kernel.org/all/d3ae6bd3537fbce379382ac6a42f67e22f27ece2.1=
683896626.git.lorenzo@kernel.org/
> 2. https://lore.kernel.org/all/20230526054621.18371-3-liangchen.linux@gma=
il.com/
>
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> CC: Lorenzo Bianconi <lorenzo@kernel.org>
> CC: Alexander Duyck <alexander.duyck@gmail.com>
> ---
>  include/net/page_pool.h | 43 +++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 43 insertions(+)
>
> diff --git a/include/net/page_pool.h b/include/net/page_pool.h
> index 0b8cd2acc1d7..c135cd157cea 100644
> --- a/include/net/page_pool.h
> +++ b/include/net/page_pool.h
> @@ -260,6 +260,49 @@ static inline struct page *page_pool_dev_alloc_frag(=
struct page_pool *pool,
>         return page_pool_alloc_frag(pool, offset, size, gfp);
>  }
>
> +static inline struct page *page_pool_alloc(struct page_pool *pool,
> +                                          unsigned int *offset,
> +                                          unsigned int *size, gfp_t gfp)
> +{
> +       unsigned int max_size =3D PAGE_SIZE << pool->p.order;
> +       struct page *page;
> +
> +       *size =3D ALIGN(*size, dma_get_cache_alignment());
> +
> +       if (WARN_ON(*size > max_size))
> +               return NULL;
> +
> +       if ((*size << 1) > max_size || PAGE_POOL_DMA_USE_PP_FRAG_COUNT) {
> +               *size =3D max_size;
> +               *offset =3D 0;
> +               return page_pool_alloc_pages(pool, gfp);
> +       }
> +
> +       page =3D __page_pool_alloc_frag(pool, offset, *size, gfp);
> +       if (unlikely(!page))
> +               return NULL;
> +
> +       /* There is very likely not enough space for another frag, so app=
end the
> +        * remaining size to the current frag to avoid truesize underesti=
mate
> +        * problem.
> +        */
> +       if (pool->frag_offset + *size > max_size) {
> +               *size =3D max_size - *offset;
> +               pool->frag_offset =3D max_size;
> +       }
> +

Rather than preventing a truesize underestimation this will cause one.
You are adding memory to the size of the page reserved and not
accounting for it anywhere as this isn't reported up to the network
stack. I would suggest dropping this from your patch.

> +       return page;
> +}
> +
> +static inline struct page *page_pool_dev_alloc(struct page_pool *pool,
> +                                              unsigned int *offset,
> +                                              unsigned int *size)
> +{
> +       gfp_t gfp =3D (GFP_ATOMIC | __GFP_NOWARN);
> +
> +       return page_pool_alloc(pool, offset, size, gfp);
> +}
> +
>  /* get the stored dma direction. A driver might decide to treat this loc=
ally and
>   * avoid the extra cache line from page_pool to determine the direction
>   */
> --
> 2.33.0
>