From: Ilias Apalodimas <ilias.apalodimas@linaro.org>
To: Yunsheng Lin <linyunsheng@huawei.com>
Cc: "David S. Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>,
Networking <netdev@vger.kernel.org>,
open list <linux-kernel@vger.kernel.org>,
linuxarm@openeuler.org, Jesper Dangaard Brouer <hawk@kernel.org>,
Jonathan Lemon <jonathan.lemon@gmail.com>,
Alexander Lobakin <alobakin@pm.me>,
Willem de Bruijn <willemb@google.com>,
Cong Wang <cong.wang@bytedance.com>,
Paolo Abeni <pabeni@redhat.com>, Kevin Hao <haokexin@gmail.com>,
Aleksandr Nogikh <nogikh@google.com>,
Marco Elver <elver@google.com>,
memxor@gmail.com, Eric Dumazet <edumazet@google.com>,
Alexander Duyck <alexander.duyck@gmail.com>,
David Ahern <dsahern@gmail.com>
Subject: Re: [PATCH net-next 3/7] pool_pool: avoid calling compound_head() for skb frag page
Date: Fri, 24 Sep 2021 10:44:47 +0300 [thread overview]
Message-ID: <CAC_iWj+utC54sGFKfOMFx34Jk1SQWANxbkBRD_E2TeSLKkZRUg@mail.gmail.com> (raw)
In-Reply-To: <39e62727-6d9f-a0db-39b2-296ebd6972b3@huawei.com>
On Fri, 24 Sept 2021 at 10:33, Yunsheng Lin <linyunsheng@huawei.com> wrote:
>
> On 2021/9/23 19:47, Ilias Apalodimas wrote:
> > On Thu, 23 Sept 2021 at 14:24, Yunsheng Lin <linyunsheng@huawei.com> wrote:
> >>
> >> On 2021/9/23 16:33, Ilias Apalodimas wrote:
> >>> On Wed, Sep 22, 2021 at 05:41:27PM +0800, Yunsheng Lin wrote:
> >>>> As the pp page for a skb frag is always a head page, so make
> >>>> sure skb_pp_recycle() passes a head page to avoid calling
> >>>> compound_head() for skb frag page case.
> >>>
> >>> Doesn't that rely on the driver mostly (i.e what's passed in skb_frag_set_page() ?
> >>> None of the current netstack code assumes bv_page is the head page of a
> >>> compound page. Since our page_pool allocator can will allocate compound
> >>> pages for order > 0, why should we rely on it ?
> >>
> >> As the page pool alloc function return 'struct page *' to the caller, which
> >> is the head page of a compound pages for order > 0, so I assume the caller
> >> will pass that to skb_frag_set_page().
> >
> > Yea that's exactly the assumption I was afraid of.
> > Sure not passing the head page might seem weird atm and the assumption
> > stands, but the point is we shouldn't blow up the entire network stack
> > if someone does that eventually.
> >
> >>
> >> For non-pp page, I assume it is ok whether the page is a head page or tail
> >> page, as the pp_magic for both of them are not set with PP_SIGNATURE.
> >
> > Yea that's true, although we removed the checking for coalescing
> > recyclable and non-recyclable SKBs, the next patch first checks the
> > signature before trying to do anything with the skb.
> >
> >>
> >> Or should we play safe here, and do the trick as skb_free_head() does in
> >> patch 6?
> >
> > I don't think the &1 will even be measurable, so I'd suggest just
> > dropping this and play safe?
>
> I am not sure what does '&1' mean above.
I meant the check compound_head() is doing before deciding on the head page.
>
> The one thing I am not sure about the trick done in patch 6 is that
> if __page_frag_cache_drain() is right API to use here, I used it because
> it is the only API that is expecting a head page.
Yea seemed a bit funny to me in the first place, until I figured out
what exactly it was doing.
Regards
/Ilias
>
> >
> > Cheers
> > /Ilias
> >>
> >>>
> >>> Thanks
> >>> /Ilias
> >>>>
> >>>> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> >>>> ---
> >>>> include/linux/skbuff.h | 2 +-
> >>>> net/core/page_pool.c | 2 --
> >>>> 2 files changed, 1 insertion(+), 3 deletions(-)
> >>>>
> >>>> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> >>>> index 6bdb0db3e825..35eebc2310a5 100644
> >>>> --- a/include/linux/skbuff.h
> >>>> +++ b/include/linux/skbuff.h
> >>>> @@ -4722,7 +4722,7 @@ static inline bool skb_pp_recycle(struct sk_buff *skb, void *data)
> >>>> {
> >>>> if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle)
> >>>> return false;
> >>>> - return page_pool_return_skb_page(virt_to_page(data));
> >>>> + return page_pool_return_skb_page(virt_to_head_page(data));
> >>>> }
> >>>>
> >>>> #endif /* __KERNEL__ */
> >>>> diff --git a/net/core/page_pool.c b/net/core/page_pool.c
> >>>> index f7e71dcb6a2e..357fb53343a0 100644
> >>>> --- a/net/core/page_pool.c
> >>>> +++ b/net/core/page_pool.c
> >>>> @@ -742,8 +742,6 @@ bool page_pool_return_skb_page(struct page *page)
> >>>> {
> >>>> struct page_pool *pp;
> >>>>
> >>>> - page = compound_head(page);
> >>>> -
> >>>> /* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation
> >>>> * in order to preserve any existing bits, such as bit 0 for the
> >>>> * head page of compound page and bit 1 for pfmemalloc page, so
> >>>> --
> >>>> 2.33.0
> >>>>
> >>> .
> >>>
> > .
> >
next prev parent reply other threads:[~2021-09-24 7:45 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-22 9:41 [PATCH net-next 0/7] some optimization for page pool Yunsheng Lin
2021-09-22 9:41 ` [PATCH net-next 1/7] page_pool: disable dma mapping support for 32-bit arch with 64-bit DMA Yunsheng Lin
2021-09-23 9:10 ` Ilias Apalodimas
2021-09-23 9:33 ` Jesper Dangaard Brouer
2021-09-23 10:02 ` Ilias Apalodimas
2021-09-23 11:13 ` Yunsheng Lin
2021-09-23 13:07 ` Ilias Apalodimas
2021-09-24 7:04 ` Yunsheng Lin
2021-09-24 7:25 ` Ilias Apalodimas
2021-09-24 8:01 ` Yunsheng Lin
2021-09-22 9:41 ` [PATCH net-next 2/7] page_pool: support non-split page with PP_FLAG_PAGE_FRAG Yunsheng Lin
2021-09-23 12:08 ` Jesper Dangaard Brouer
2021-09-24 7:23 ` Yunsheng Lin
2021-09-30 7:28 ` [Linuxarm] " Yunsheng Lin
2021-09-22 9:41 ` [PATCH net-next 3/7] pool_pool: avoid calling compound_head() for skb frag page Yunsheng Lin
2021-09-23 8:33 ` Ilias Apalodimas
2021-09-23 11:24 ` Yunsheng Lin
2021-09-23 11:47 ` Ilias Apalodimas
2021-09-24 7:33 ` Yunsheng Lin
2021-09-24 7:44 ` Ilias Apalodimas [this message]
2021-09-22 9:41 ` [PATCH net-next 4/7] page_pool: change BIAS_MAX to support incrementing Yunsheng Lin
2021-09-22 9:41 ` [PATCH net-next 5/7] skbuff: keep track of pp page when __skb_frag_ref() is called Yunsheng Lin
2021-09-22 9:41 ` [PATCH net-next 6/7] skbuff: only use pp_magic identifier for a skb' head page Yunsheng Lin
2021-09-22 9:41 ` [PATCH net-next 7/7] skbuff: remove unused skb->pp_recycle Yunsheng Lin
2021-09-23 7:07 ` [PATCH net-next 0/7] some optimization for page pool Ilias Apalodimas
2021-09-23 11:12 ` Yunsheng Lin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAC_iWj+utC54sGFKfOMFx34Jk1SQWANxbkBRD_E2TeSLKkZRUg@mail.gmail.com \
--to=ilias.apalodimas@linaro.org \
--cc=alexander.duyck@gmail.com \
--cc=alobakin@pm.me \
--cc=cong.wang@bytedance.com \
--cc=davem@davemloft.net \
--cc=dsahern@gmail.com \
--cc=edumazet@google.com \
--cc=elver@google.com \
--cc=haokexin@gmail.com \
--cc=hawk@kernel.org \
--cc=jonathan.lemon@gmail.com \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxarm@openeuler.org \
--cc=linyunsheng@huawei.com \
--cc=memxor@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=nogikh@google.com \
--cc=pabeni@redhat.com \
--cc=willemb@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).