From: Paolo Abeni <pabeni@redhat.com>
To: David Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org, eric.dumazet@gmail.com, pjt@google.com,
linux-kernel@vger.kernel.org, ecree@solarflare.com,
dwmw2@infradead.org
Subject: Re: [PATCH net-next v3 0/4] net: mitigate retpoline overhead
Date: Sun, 16 Dec 2018 19:55:40 +0100 [thread overview]
Message-ID: <2444a44091ae292166c6cad1e31fd85ed2b77fe7.camel@redhat.com> (raw)
In-Reply-To: <20181215.132333.867660599141318055.davem@davemloft.net>
On Sat, 2018-12-15 at 13:23 -0800, David Miller wrote:
> From: Paolo Abeni <pabeni@redhat.com>
> Date: Fri, 14 Dec 2018 11:51:56 +0100
>
> > The spectre v2 counter-measures, aka retpolines, are a source of measurable
> > overhead[1]. We can partially address that when the function pointer refers to
> > a builtin symbol resorting to a list of tests vs well-known builtin function and
> > direct calls.
> >
> > Experimental results show that replacing a single indirect call via
> > retpoline with several branches and a direct call gives performance gains
> > even when multiple branches are added - 5 or more, as reported in [2].
> >
> > This may lead to some uglification around the indirect calls. In netconf 2018
> > Eric Dumazet described a technique to hide the most relevant part of the needed
> > boilerplate with some macro help.
> >
> > This series is a [re-]implementation of such idea, exposing the introduced
> > helpers in a new header file. They are later leveraged to avoid the indirect
> > call overhead in the GRO path, when possible.
> >
> > Overall this gives > 10% performance improvement for UDP GRO benchmark and
> > smaller but measurable for TCP syn flood.
> >
> > The added infra can be used in follow-up patches to cope with retpoline overhead
> > in other points of the networking stack (e.g. at the qdisc layer) and possibly
> > even in other subsystems.
> ...
>
> Series applied, I'll push this out after a build check completes.
Again, I messed it! I'm really sorry to waste everybody's time.
I was unable to give proper coverage with different configs. I tested
vs.:
CONFIG_IPV6=ymn
CONFIG_INET=yn
but
# CONFIG_RETPOLINE is not set
fooled me. The following patch should fix. I'll try more
configurations. Is there any way to try/tests all kbuild robot configs?
Please feel free to give me an hard stop if this sounds too much a
trial and error thing.
Paolo
--
diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h
index 7c8b7f4..00d7e8e9 100644
--- a/include/linux/indirect_call_wrapper.h
+++ b/include/linux/indirect_call_wrapper.h
@@ -28,8 +28,8 @@
#define INDIRECT_CALLABLE_SCOPE
#else
-#define INDIRECT_CALL_1(f, name, ...) f(__VA_ARGS__)
-#define INDIRECT_CALL_2(f, name, ...) f(__VA_ARGS__)
+#define INDIRECT_CALL_1(f, f1, ...) f(__VA_ARGS__)
+#define INDIRECT_CALL_2(f, f2, f1, ...) f(__VA_ARGS__)
#define INDIRECT_CALLABLE_DECLARE(f)
#define INDIRECT_CALLABLE_SCOPE static
#endif
next prev parent reply other threads:[~2018-12-16 18:55 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-14 10:51 Paolo Abeni
2018-12-14 10:51 ` [PATCH net-next v3 1/4] indirect call wrappers: helpers to speed-up indirect calls of builtin Paolo Abeni
2018-12-14 10:51 ` [PATCH net-next v3 2/4] net: use indirect call wrappers at GRO network layer Paolo Abeni
2018-12-14 10:51 ` [PATCH net-next v3 3/4] net: use indirect call wrappers at GRO transport layer Paolo Abeni
2018-12-14 10:52 ` [PATCH net-next v3 4/4] udp: use indirect call wrappers for GRO socket lookup Paolo Abeni
2018-12-15 21:23 ` [PATCH net-next v3 0/4] net: mitigate retpoline overhead David Miller
2018-12-16 18:55 ` Paolo Abeni [this message]
2018-12-16 19:13 ` David Miller
2018-12-16 20:05 ` Willem de Bruijn
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=2444a44091ae292166c6cad1e31fd85ed2b77fe7.camel@redhat.com \
--to=pabeni@redhat.com \
--cc=davem@davemloft.net \
--cc=dwmw2@infradead.org \
--cc=ecree@solarflare.com \
--cc=eric.dumazet@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pjt@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
all inboxes | Powered by JetHome®