Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <20190207053740.26915-1-dave@stgolabs.net> <20190207053740.26915-2-dave@stgolabs.net>
In-Reply-To: <20190207053740.26915-2-dave@stgolabs.net>
From:   =?UTF-8?B?QmrDtnJuIFTDtnBlbA==?= <bjorn.topel@gmail.com>
Date:   Thu, 7 Feb 2019 08:43:02 +0100
Message-ID: <CAJ+HfNg=Wikc_uY9W1QiVCONq3c1GyS44-xbrq-J4gqfth2kwQ@mail.gmail.com>
Subject: Re: [PATCH 1/2] xsk: do not use mmap_sem
To:     Davidlohr Bueso <dave@stgolabs.net>
Cc:     akpm@linux-foundation.org, linux-mm@kvack.org,
        LKML <linux-kernel@vger.kernel.org>,
        "David S . Miller" <davem@davemloft.net>,
        Bjorn Topel <bjorn.topel@intel.com>,
        Magnus Karlsson <magnus.karlsson@intel.com>,
        Netdev <netdev@vger.kernel.org>, Davidlohr Bueso <dbueso@suse.de>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Den tors 7 feb. 2019 kl 06:38 skrev Davidlohr Bueso <dave@stgolabs.net>:
>
> Holding mmap_sem exclusively for a gup() is an overkill.
> Lets replace the call for gup_fast() and let the mm take
> it if necessary.
>
> Cc: David S. Miller <davem@davemloft.net>
> Cc: Bjorn Topel <bjorn.topel@intel.com>
> Cc: Magnus Karlsson <magnus.karlsson@intel.com>
> CC: netdev@vger.kernel.org
> Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
> ---
>  net/xdp/xdp_umem.c | 6 ++----
>  1 file changed, 2 insertions(+), 4 deletions(-)
>
> diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
> index 5ab236c5c9a5..25e1e76654a8 100644
> --- a/net/xdp/xdp_umem.c
> +++ b/net/xdp/xdp_umem.c
> @@ -265,10 +265,8 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem)
>         if (!umem->pgs)
>                 return -ENOMEM;
>
> -       down_write(&current->mm->mmap_sem);
> -       npgs =3D get_user_pages(umem->address, umem->npgs,
> -                             gup_flags, &umem->pgs[0], NULL);
> -       up_write(&current->mm->mmap_sem);
> +       npgs =3D get_user_pages_fast(umem->address, umem->npgs,
> +                                  gup_flags, &umem->pgs[0]);
>

Thanks for the patch!

The lifetime of the pinning is similar to RDMA umem mapping, so isn't
gup_longterm preferred?


Bj=C3=B6rn

>         if (npgs !=3D umem->npgs) {
>                 if (npgs >=3D 0) {
> --
> 2.16.4
>