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: <20230329180502.1884307-1-kal.conley@dectris.com>
 <20230329180502.1884307-9-kal.conley@dectris.com> <CAJ8uoz330DWzHabpqd+HaeAxBi2gr+GOTtnS9WJFWrt=6DaeWQ@mail.gmail.com>
 <CAHApi-nfBM=i1WeZ-jtHN87AWPvURo0LygT9yYxF=cUeYthXBQ@mail.gmail.com>
 <CAJ8uoz0SEkcXQuoqYd94GreJqpCxQuf1QVgm9=Um6Wqk=s8GBw@mail.gmail.com>
 <CAHApi-=ui3JofMr7y+LvuYkXCU=h7vGiKXsfuV5gog-02u-u+Q@mail.gmail.com> <CAJ8uoz0GgzzfrgS0189=zwY-zzogZq+=v-NCY7O+RuWrwe1n6w@mail.gmail.com>
In-Reply-To: <CAJ8uoz0GgzzfrgS0189=zwY-zzogZq+=v-NCY7O+RuWrwe1n6w@mail.gmail.com>
From:   Kal Cutter Conley <kal.conley@dectris.com>
Date:   Tue, 4 Apr 2023 14:18:42 +0200
Message-ID: <CAHApi-kVF5dS=ym7PXttCVAz7jEod2cOhh27YYwkidCUogu6-A@mail.gmail.com>
Subject: Re: [PATCH bpf-next v2 08/10] xsk: Support UMEM chunk_size > PAGE_SIZE
To:     Magnus Karlsson <magnus.karlsson@gmail.com>
Cc:     =?UTF-8?B?QmrDtnJuIFTDtnBlbA==?= <bjorn@kernel.org>,
        Magnus Karlsson <magnus.karlsson@intel.com>,
        Maciej Fijalkowski <maciej.fijalkowski@intel.com>,
        Jonathan Lemon <jonathan.lemon@gmail.com>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>,
        Jonathan Corbet <corbet@lwn.net>,
        Alexei Starovoitov <ast@kernel.org>,
        Daniel Borkmann <daniel@iogearbox.net>,
        Jesper Dangaard Brouer <hawk@kernel.org>,
        John Fastabend <john.fastabend@gmail.com>,
        netdev@vger.kernel.org, bpf@vger.kernel.org,
        linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

> > > > > Is not the max 64K as you test against XDP_UMEM_MAX_CHUNK_SIZE in
> > > > > xdp_umem_reg()?
> > > >
> > > > The absolute max is 64K. In the case of HPAGE_SIZE < 64K, then it
> > > > would be HPAGE_SIZE.
> > >
> > > Is there such a case when HPAGE_SIZE would be less than 64K? If not,
> > > then just write 64K.
> >
> > Yes. While most platforms have HPAGE_SIZE defined to a compile-time
> > constant >= 64K (very often 2M) there are platforms (at least ia64 and
> > powerpc) where the hugepage size is configured at boot. Specifically,
> > in the case of Itanium (ia64), the hugepage size may be configured at
> > boot to any valid page size > PAGE_SIZE (e.g. 8K). See:
> > https://elixir.bootlin.com/linux/latest/source/arch/ia64/mm/hugetlbpage.c#L159
>
> So for all practical purposes it is max 64K. Let us just write that then.

What about when CONFIG_HUGETLB_PAGE is not defined? Should we keep it
set to PAGE_SIZE in that case, or would you like it to be a fixed
constant == 64K always?

>
> > >
> > > > > >  static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)
> > > > > >  {
> > > > > > +#ifdef CONFIG_HUGETLB_PAGE
> > > > >
> > > > > Let us try to get rid of most of these #ifdefs sprinkled around the
> > > > > code. How about hiding this inside xdp_umem_is_hugetlb() and get rid
> > > > > of these #ifdefs below? Since I believe it is quite uncommon not to
> > > > > have this config enabled, we could simplify things by always using the
> > > > > page_size in the pool, for example. And dito for the one in struct
> > > > > xdp_umem. What do you think?
> > > >
> > > > I used #ifdef for `page_size` in the pool for maximum performance when
> > > > huge pages are disabled. We could also not worry about optimizing this
> > > > uncommon case though since the performance impact is very small.
> > > > However, I don't find the #ifdefs excessive either.
> > >
> > > Keep them to a minimum please since there are few of them in the
> > > current code outside of some header files. And let us assume that
> > > CONFIG_HUGETLB_PAGE is the common case.
> > >
> >
> > Would you be OK if I just remove the ones from xsk_buff_pool? I think
> > the code in xdp_umem.c is quite readable and the #ifdefs are really
> > only used in xdp_umem_pin_pages.
>
> Please make an effort to remove the ones in xdp_umem.c too. The more
> ifdefs you add, the harder it will be to read.

OK