From: Eric Dumazet <eric.dumazet@gmail.com>
To: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>,
netdev@vger.kernel.org, "David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>
Subject: Re: [PATCH] netlink: enable skb header refcounting before sending first broadcast
Date: Mon, 13 Jul 2015 10:22:34 +0200 [thread overview]
Message-ID: <1436775754.9402.6.camel@edumazet-glaptop2.roam.corp.google.com> (raw)
In-Reply-To: <20150713081040.GB8971@gondor.apana.org.au>
On Mon, 2015-07-13 at 16:10 +0800, Herbert Xu wrote:
> On Mon, Jul 13, 2015 at 10:05:42AM +0200, Eric Dumazet wrote:
> >
> > Herbert, UDP peek support is very buggy anyway, because of deferred
> > checksums
> >
> > __skb_checksum_complete() will happily manipulate csum, ip_summed,
> > csum_complete_sw & csum_valid
> >
> > Ideally, peek should never touch skb (but skb->users)
>
> I think UDP should be OK because the main creator of shared skbs
> is af_packet and in that cast the IP stack will clone the skb upon
> entry. AFAIK there aren't any entities doing the shared skb trick
> within the IP stack.
>
> IOW the UDP stack does not have to worry about share skbs, unlike
> netlink.
It should worry, in case multiple threads are using MSG_PEEK on same udp
socket ;)
Problem here is not the producer (might be unicast packets btw),
but multiple 'consumers'
It turns out your patch would also solve this problem.
next prev parent reply other threads:[~2015-07-13 8:22 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-07-10 11:51 [PATCH] netlink: enable skb header refcounting before sending first broadcast Konstantin Khlebnikov
2015-07-10 13:49 ` Eric Dumazet
2015-07-10 14:08 ` Konstantin Khlebnikov
2015-07-13 7:23 ` Herbert Xu
2015-07-13 8:04 ` net: Clone skb before setting peeked flag Herbert Xu
2015-07-15 23:13 ` David Miller
2015-07-13 8:05 ` [PATCH] netlink: enable skb header refcounting before sending first broadcast Eric Dumazet
2015-07-13 8:10 ` Herbert Xu
2015-07-13 8:22 ` Eric Dumazet [this message]
2015-07-13 8:25 ` Herbert Xu
2015-07-13 8:28 ` Eric Dumazet
2015-07-13 8:31 ` Herbert Xu
2015-07-13 12:01 ` net: Fix skb csum races when peeking Herbert Xu
2015-07-13 14:25 ` Herbert Xu
2015-07-14 6:11 ` Eric Dumazet
2015-07-15 23:14 ` David Miller
2015-07-13 8:54 ` [PATCH] netlink: enable skb header refcounting before sending first broadcast Konstantin Khlebnikov
2015-07-13 9:04 ` Herbert Xu
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=1436775754.9402.6.camel@edumazet-glaptop2.roam.corp.google.com \
--to=eric.dumazet@gmail.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=herbert@gondor.apana.org.au \
--cc=khlebnikov@yandex-team.ru \
--cc=netdev@vger.kernel.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.