From: Eli Cohen <eli@dev.mellanox.co.il>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: netdev@vger.kernel.org,
Yevgeny Petrilin <yevgenyp@mellanox.co.il>,
Eli Cohen <eli@mellanox.co.il>,
David Laight <David.Laight@ACULAB.COM>,
Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>,
linuxppc-dev@lists.ozlabs.org
Subject: Re: [PATCH] mlx4_en: fix transmit of packages when blue frame is enabled
Date: Mon, 10 Oct 2011 11:16:11 +0200 [thread overview]
Message-ID: <20111010091611.GN2681@mtldesk30> (raw)
In-Reply-To: <1318237284.29415.422.camel@pasglop>
On Mon, Oct 10, 2011 at 11:01:24AM +0200, Benjamin Herrenschmidt wrote:
>
> The case where things get a bit more nasty is when you try to use MMIO
> for low latency small-data type transfers instead of DMA, in which case
> you do want the ability for the chipset to write-combine and control the
> barriers more precisely.
>
> However, this is hard and Linux doesn't provide very good accessors to
> do so, thus you need to be extra careful (see my example about wmb()
>
> In the case of the iomap "copy" operations, my problem is that they
> don't properly advertise their lack of ordering since normal iomap does
> have full ordering.
>
> I believe they should provide ordering with a barrier before & a barrier
> after, eventually with _relaxed variants or _raw variants for those who
> "know what they are doing".
Until then I think we need to have the logic working right on ppc and
measure if blue flame buys us any improvement in ppc. If that's not
the case (e.g because write combining is not working), then maybe we
should avoid using blueflame in ppc.
Could any of the guys from IBM check this and give us feedback?
>
> Maybe it's time for us to revive those discussions about providing a
> good set of relaxed MMIO accessors with explicit barriers :-)
>
> Cheers,
> Ben.
>
next prev parent reply other threads:[~2011-10-10 9:16 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1317388995-411-1-git-send-email-cascardo@linux.vnet.ibm.com>
[not found] ` <953B660C027164448AE903364AC447D2235D9A8C@MTLDAG02.mtl.com>
[not found] ` <20111003143721.GA3596@oc1711230544.ibm.com>
[not found] ` <953B660C027164448AE903364AC447D2235DAA9D@MTLDAG02.mtl.com>
2011-10-03 20:53 ` [PATCH] mlx4_en: fix transmit of packages when blue frame is enabled Thadeu Lima de Souza Cascardo
2011-10-04 6:02 ` Benjamin Herrenschmidt
2011-10-04 20:26 ` Thadeu Lima de Souza Cascardo
2011-10-05 8:15 ` Eli Cohen
2011-10-06 13:57 ` Eli Cohen
2011-10-06 14:10 ` [PATCH] mlx4_en: fix transmit of packages when blue frame isenabled David Laight
2011-10-07 22:29 ` Thadeu Lima de Souza Cascardo
2011-10-09 7:28 ` Benjamin Herrenschmidt
2011-10-09 7:25 ` [PATCH] mlx4_en: fix transmit of packages when blue frame is enabled Benjamin Herrenschmidt
2011-10-09 7:35 ` Eli Cohen
2011-10-09 8:00 ` Benjamin Herrenschmidt
2011-10-09 8:07 ` Eli Cohen
2011-10-09 8:38 ` Benjamin Herrenschmidt
2011-10-09 9:21 ` Eli Cohen
2011-10-09 9:52 ` Benjamin Herrenschmidt
2011-10-09 10:30 ` Eli Cohen
2011-10-10 7:32 ` Benjamin Herrenschmidt
2011-10-10 16:42 ` [PATCH] mlx4_en: fix endianness with blue frame support Thadeu Lima de Souza Cascardo
2011-10-10 16:46 ` Thadeu Lima de Souza Cascardo
2011-10-10 18:10 ` David Miller
2011-10-10 8:20 ` [PATCH] mlx4_en: fix transmit of packages when blue frame is enabled David Laight
2011-10-10 8:29 ` Benjamin Herrenschmidt
2011-10-10 8:40 ` David Laight
2011-10-10 8:47 ` Eli Cohen
2011-10-10 9:01 ` Benjamin Herrenschmidt
2011-10-10 9:16 ` Eli Cohen [this message]
2011-10-10 9:24 ` Benjamin Herrenschmidt
2011-10-10 9:29 ` Eli Cohen
2011-10-10 10:18 ` Benjamin Herrenschmidt
2011-10-10 8:53 ` Benjamin Herrenschmidt
2011-10-09 7:21 ` Benjamin Herrenschmidt
2011-10-09 7:19 ` Benjamin Herrenschmidt
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=20111010091611.GN2681@mtldesk30 \
--to=eli@dev.mellanox.co.il \
--cc=David.Laight@ACULAB.COM \
--cc=benh@kernel.crashing.org \
--cc=cascardo@linux.vnet.ibm.com \
--cc=eli@mellanox.co.il \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=netdev@vger.kernel.org \
--cc=yevgenyp@mellanox.co.il \
/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).