[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CANn89i+iXXUjOJCOF1nodjVH4eX8P-B26Kg+Uu-iM2_Hc=5D5g@mail.gmail.com>
Date: Wed, 4 Sep 2024 17:29:44 +0200
From: Eric Dumazet <edumazet@...gle.com>
To: Mina Almasry <almasrymina@...gle.com>
Cc: Jakub Kicinski <kuba@...nel.org>, netdev@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-doc@...r.kernel.org, linux-alpha@...r.kernel.org,
linux-mips@...r.kernel.org, linux-parisc@...r.kernel.org,
sparclinux@...r.kernel.org, linux-trace-kernel@...r.kernel.org,
linux-arch@...r.kernel.org, bpf@...r.kernel.org,
linux-kselftest@...r.kernel.org, linux-media@...r.kernel.org,
dri-devel@...ts.freedesktop.org, Donald Hunter <donald.hunter@...il.com>,
"David S. Miller" <davem@...emloft.net>, Paolo Abeni <pabeni@...hat.com>,
Jonathan Corbet <corbet@....net>, Richard Henderson <richard.henderson@...aro.org>,
Ivan Kokshaysky <ink@...assic.park.msu.ru>, Matt Turner <mattst88@...il.com>,
Thomas Bogendoerfer <tsbogend@...ha.franken.de>,
"James E.J. Bottomley" <James.Bottomley@...senpartnership.com>, Helge Deller <deller@....de>,
Andreas Larsson <andreas@...sler.com>, Jesper Dangaard Brouer <hawk@...nel.org>,
Ilias Apalodimas <ilias.apalodimas@...aro.org>, Steven Rostedt <rostedt@...dmis.org>,
Masami Hiramatsu <mhiramat@...nel.org>, Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Arnd Bergmann <arnd@...db.de>, Steffen Klassert <steffen.klassert@...unet.com>,
Herbert Xu <herbert@...dor.apana.org.au>, David Ahern <dsahern@...nel.org>,
Willem de Bruijn <willemdebruijn.kernel@...il.com>, Björn Töpel <bjorn@...nel.org>,
Magnus Karlsson <magnus.karlsson@...el.com>,
Maciej Fijalkowski <maciej.fijalkowski@...el.com>, Jonathan Lemon <jonathan.lemon@...il.com>,
Shuah Khan <shuah@...nel.org>, Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>, John Fastabend <john.fastabend@...il.com>,
Sumit Semwal <sumit.semwal@...aro.org>, Christian König <christian.koenig@....com>,
Pavel Begunkov <asml.silence@...il.com>, David Wei <dw@...idwei.uk>, Jason Gunthorpe <jgg@...pe.ca>,
Yunsheng Lin <linyunsheng@...wei.com>, Shailend Chand <shailend@...gle.com>,
Harshitha Ramamurthy <hramamurthy@...gle.com>, Shakeel Butt <shakeel.butt@...ux.dev>,
Jeroen de Borst <jeroendb@...gle.com>, Praveen Kaligineedi <pkaligineedi@...gle.com>,
Bagas Sanjaya <bagasdotme@...il.com>, Christoph Hellwig <hch@...radead.org>,
Nikolay Aleksandrov <razor@...ckwall.org>, Taehee Yoo <ap420073@...il.com>,
Willem de Bruijn <willemb@...gle.com>, Kaiyuan Zhang <kaiyuanz@...gle.com>
Subject: Re: [PATCH net-next v24 08/13] net: add support for skbs with
unreadable frags
On Wed, Sep 4, 2024 at 5:18 PM Mina Almasry <almasrymina@...gle.com> wrote:
>
> On Tue, Sep 3, 2024 at 2:40 PM Jakub Kicinski <kuba@...nel.org> wrote:
> >
> > On Sat, 31 Aug 2024 00:43:08 +0000 Mina Almasry wrote:
> > > static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb)
> > > {
> > > - return likely(!TCP_SKB_CB(skb)->eor);
> > > + return likely(!TCP_SKB_CB(skb)->eor && skb_frags_readable(skb));
> >
> > Do you remember why this is here?
>
> Yeah, to be honest, when I first implemented some of these checks I
> erred on the side of caution, and added checks around anything that
> looked concerning, some of these unnecessary checks got removed, but
> looks like this one didn't.
>
> > Both for Rx and Tx what should matter
> > is whether the "readability" matches, right? We can merge two unreadable
> > messages.
>
> Yes, you're right, only 'readability matches' should be the criteria
> here. `tcp_skb_can_collapse` already checks readability is matching
> correctly, so no issue there. The `tcp_skb_can_collapse_to` check
> you're commenting on here looks unnecessary. I will remove it and run
> that through some testing.
>
> As an aside, it looks to me like that tcp_skb_can_collapse_to
> callsites don't seem to be doing any collapsing. Unless I misread the
> code. It looks like tcp_skb_can_collapse_to is used as an eor check. I
> can rename the function to tcp_skb_is_eor() or something if that makes
> sense (in a separate patch). I think the name of the function confused
> me slightly and made me think I need to do a readability check.
>
Please do not use tcp_skb_is_eor()
tcp_skb_can_collapse_to() could be renamed to tcp_skb_can_aggregate_to()
or tcp_skb_can_append_to(), but EOR would not help at all.
Powered by blists - more mailing lists