From: Florian Westphal <fw@strlen.de>
To: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Florian Westphal <fw@strlen.de>, netdev@vger.kernel.org
Subject: Re: [PATCH net-next 13/13] net: switch secpath to use skb extension infrastructure
Date: Wed, 12 Dec 2018 12:52:58 +0100 [thread overview]
Message-ID: <20181212115258.txqgr7tnpnuuwyhi@breakpoint.cc> (raw)
In-Reply-To: <20181211102042.GT3581@gauss3.secunet.de>
Steffen Klassert <steffen.klassert@secunet.com> wrote:
> > I can run a few IPSEC benchmark tests to see if there is measureable
> > impact.
>
> That would be good, thanks!
Will do this later today.
One alternative would be to always allocate the entire maximum possible
extension length when the first extension is to be added.
In this case we could 'replace' secpath cache with a 'extension cache'.
The only downside is the increase in allocation size.
The upside is that it simplifies extension management -- no need
to reallocate, only action needed on 'extension add' is a possible
COW action.
Allocated memory is left un-initialized aside from 8 byte metadata
space.
We could later move to on-demand/reallocation if the full allocation
size would become too large in the future.
I will have a look at 'allocate everything' too, unless someone
tells me that this won't be acceptable (cost including future
mptcp extension would be ~160 bytes or so).
next prev parent reply other threads:[~2018-12-12 11:53 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-10 14:49 [PATCH net-next 0/13] sk_buff: add extension infrastructure Florian Westphal
2018-12-10 14:49 ` [PATCH net-next 01/13] netfilter: avoid using skb->nf_bridge directly Florian Westphal
2018-12-10 14:49 ` [PATCH net-next 02/13] sk_buff: add skb extension infrastructure Florian Westphal
[not found] ` <CAPUCuiADYwjY4kpq76-w9BKL3uiRvNjnmzKG29mCrb=b8YeesA@mail.gmail.com>
2018-12-12 0:07 ` Mat Martineau
2018-12-12 0:11 ` Florian Westphal
2018-12-12 11:59 ` Florian Westphal
2018-12-12 16:59 ` Mat Martineau
2018-12-12 14:44 ` Willem de Bruijn
2018-12-12 15:40 ` Florian Westphal
2018-12-12 15:45 ` Willem de Bruijn
2018-12-12 17:23 ` Eric Dumazet
2018-12-12 18:44 ` Florian Westphal
2018-12-12 20:17 ` Eric Dumazet
2018-12-12 20:52 ` Florian Westphal
2018-12-13 5:40 ` Eric Dumazet
2018-12-13 9:27 ` Florian Westphal
2018-12-13 10:18 ` Eric Dumazet
2018-12-13 10:39 ` Florian Westphal
2018-12-13 10:58 ` Eric Dumazet
2018-12-13 11:03 ` Florian Westphal
2018-12-13 11:16 ` Eric Dumazet
2018-12-13 11:44 ` Florian Westphal
2018-12-13 17:00 ` Christoph Paasch
2018-12-12 18:16 ` Stephen Suryaputra
2018-12-12 18:38 ` Florian Westphal
2018-12-13 0:38 ` David Miller
2018-12-10 14:49 ` [PATCH net-next 03/13] net: convert bridge_nf to use " Florian Westphal
2018-12-10 14:49 ` [PATCH net-next 04/13] xfrm: change secpath_set to return secpath struct, not error value Florian Westphal
2018-12-10 14:49 ` [PATCH net-next 05/13] net: move secpath_exist helper to sk_buff.h Florian Westphal
2018-12-10 14:49 ` [PATCH net-next 06/13] net: use skb_sec_path helper in more places Florian Westphal
2018-12-10 14:50 ` [PATCH net-next 07/13] drivers: net: intel: use secpath helpers " Florian Westphal
2018-12-10 14:50 ` [PATCH net-next 08/13] drivers: net: ethernet: mellanox: use skb_sec_path helper Florian Westphal
2018-12-10 14:50 ` [PATCH net-next 09/13] drivers: net: netdevsim: " Florian Westphal
2018-12-10 14:50 ` [PATCH net-next 10/13] xfrm: use secpath_exist where applicable Florian Westphal
2018-12-10 14:50 ` [PATCH net-next 11/13] drivers: chelsio: use skb_sec_path helper Florian Westphal
2018-12-10 14:50 ` [PATCH net-next 12/13] xfrm: prefer secpath_set over secpath_dup Florian Westphal
2018-12-10 14:50 ` [PATCH net-next 13/13] net: switch secpath to use skb extension infrastructure Florian Westphal
2018-12-11 8:06 ` Steffen Klassert
2018-12-11 10:18 ` Florian Westphal
2018-12-11 10:20 ` Steffen Klassert
2018-12-12 11:52 ` Florian Westphal [this message]
2018-12-13 4:08 ` [PATCH net-next 0/13] sk_buff: add " Shannon Nelson
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=20181212115258.txqgr7tnpnuuwyhi@breakpoint.cc \
--to=fw@strlen.de \
--cc=netdev@vger.kernel.org \
--cc=steffen.klassert@secunet.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).