From: Jason Gunthorpe <jgg@ziepe.ca>
To: Steve Wise <swise@opengridcomputing.com>
Cc: 'Sinan Kaya' <okaya@codeaurora.org>,
netdev@vger.kernel.org, timur@codeaurora.org,
sulrich@codeaurora.org, linux-arm-msm@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
'Steve Wise' <swise@chelsio.com>,
'Doug Ledford' <dledford@redhat.com>,
linux-rdma@vger.kernel.org, linux-kernel@vger.kernel.org,
'Michael Werner' <werner@chelsio.com>,
'Casey Leedom' <leedom@chelsio.com>
Subject: Re: [PATCH v3 18/18] infiniband: cxgb4: Eliminate duplicate barriers on weakly-ordered archs
Date: Fri, 16 Mar 2018 16:13:47 -0600 [thread overview]
Message-ID: <20180316221347.GA958@ziepe.ca> (raw)
In-Reply-To: <003601d3bd6a$783d6970$68b83c50$@opengridcomputing.com>
On Fri, Mar 16, 2018 at 04:05:10PM -0500, Steve Wise wrote:
> > Code includes wmb() followed by writel(). writel() already has a barrier
> on
> > some architectures like arm64.
> >
> > This ends up CPU observing two barriers back to back before executing the
> > register write.
> >
> > Since code already has an explicit barrier call, changing writel() to
> > writel_relaxed().
> >
> > Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
>
> NAK - This isn't correct for PowerPC. For PowerPC, writeX_relaxed() is just
> writeX().
?? Why is changing writex() to writeX() a NAK then?
> I was just looking at this with Chelsio developers, and they said the
> writeX() should be replaced with __raw_writeX(), not writeX_relaxed(), to
> get rid of the extra barrier for all architectures.
That doesn't seem semanticaly sane.
__raw_writeX() should not appear in driver code, IMHO. Only the arch
code can know what the exact semantics of that accessor are..
If ppc can't use writel_relaxed to optimize then we probably need yet
another io accessor semantic defined :(
Jason
WARNING: multiple messages have this Message-ID (diff)
From: jgg@ziepe.ca (Jason Gunthorpe)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v3 18/18] infiniband: cxgb4: Eliminate duplicate barriers on weakly-ordered archs
Date: Fri, 16 Mar 2018 16:13:47 -0600 [thread overview]
Message-ID: <20180316221347.GA958@ziepe.ca> (raw)
In-Reply-To: <003601d3bd6a$783d6970$68b83c50$@opengridcomputing.com>
On Fri, Mar 16, 2018 at 04:05:10PM -0500, Steve Wise wrote:
> > Code includes wmb() followed by writel(). writel() already has a barrier
> on
> > some architectures like arm64.
> >
> > This ends up CPU observing two barriers back to back before executing the
> > register write.
> >
> > Since code already has an explicit barrier call, changing writel() to
> > writel_relaxed().
> >
> > Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
>
> NAK - This isn't correct for PowerPC. For PowerPC, writeX_relaxed() is just
> writeX().
?? Why is changing writex() to writeX() a NAK then?
> I was just looking at this with Chelsio developers, and they said the
> writeX() should be replaced with __raw_writeX(), not writeX_relaxed(), to
> get rid of the extra barrier for all architectures.
That doesn't seem semanticaly sane.
__raw_writeX() should not appear in driver code, IMHO. Only the arch
code can know what the exact semantics of that accessor are..
If ppc can't use writel_relaxed to optimize then we probably need yet
another io accessor semantic defined :(
Jason
next prev parent reply other threads:[~2018-03-16 22:13 UTC|newest]
Thread overview: 87+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-16 16:16 [PATCH v3 00/18] Eliminate duplicate barriers on weakly-ordered archs Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [Intel-wired-lan] [PATCH v3 01/18] i40e/i40evf: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [Intel-wired-lan] [PATCH v3 02/18] ixgbe: eliminate " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [Intel-wired-lan] [PATCH v3 03/18] igbvf: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [Intel-wired-lan] [PATCH v3 04/18] igb: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [Intel-wired-lan] [PATCH v3 05/18] ixgbevf: keep writel() closer to wmb() Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [Intel-wired-lan] [PATCH v3 06/18] ixgbevf: eliminate duplicate barriers on weakly-ordered archs Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [PATCH v3 07/18] drivers: net: cxgb: Eliminate " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [PATCH v3 08/18] scsi: hpsa: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [Intel-wired-lan] [PATCH v3 09/18] fm10k: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:30 ` [Intel-wired-lan] " Alexander Duyck
2018-03-16 16:30 ` Alexander Duyck
2018-03-16 16:30 ` Alexander Duyck
2018-03-16 16:33 ` Sinan Kaya
2018-03-16 16:33 ` Sinan Kaya
2018-03-16 16:33 ` Sinan Kaya
2018-03-16 16:16 ` [PATCH v3 10/18] net: qla3xxx: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [PATCH v3 11/18] qlcnic: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-19 20:10 ` Chopra, Manish
2018-03-19 20:10 ` Chopra, Manish
2018-03-16 16:16 ` [PATCH v3 12/18] bnx2x: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [PATCH v3 13/18] net: cxgb4/cxgb4vf: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [PATCH v3 14/18] net: cxgb3: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [PATCH v3 15/18] RDMA/bnxt_re: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [PATCH v3 16/18] IB/mlx4: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [PATCH v3 17/18] RDMA/i40iw: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 16:16 ` [PATCH v3 18/18] infiniband: cxgb4: " Sinan Kaya
2018-03-16 16:16 ` Sinan Kaya
2018-03-16 21:05 ` Steve Wise
2018-03-16 21:05 ` Steve Wise
2018-03-16 21:05 ` Steve Wise
2018-03-16 21:46 ` Sinan Kaya
2018-03-16 21:46 ` Sinan Kaya
2018-03-16 23:05 ` Steve Wise
2018-03-16 23:05 ` Steve Wise
2018-03-16 23:05 ` Steve Wise
2018-03-17 3:40 ` Sinan Kaya
2018-03-17 3:40 ` Sinan Kaya
2018-03-17 4:03 ` Sinan Kaya
2018-03-17 4:03 ` Sinan Kaya
2018-03-17 4:25 ` Sinan Kaya
2018-03-17 4:25 ` Sinan Kaya
2018-03-17 4:30 ` Timur Tabi
2018-03-17 4:30 ` Timur Tabi
2018-03-17 13:23 ` Steve Wise
2018-03-17 13:23 ` Steve Wise
2018-03-17 13:23 ` Steve Wise
2018-03-17 13:27 ` David Miller
2018-03-17 13:27 ` David Miller
2018-03-17 15:05 ` Jason Gunthorpe
2018-03-17 15:05 ` Jason Gunthorpe
2018-03-17 18:30 ` Sinan Kaya
2018-03-17 18:30 ` Sinan Kaya
2018-03-19 1:48 ` Jason Gunthorpe
2018-03-19 1:48 ` Jason Gunthorpe
2018-03-16 22:13 ` Jason Gunthorpe [this message]
2018-03-16 22:13 ` Jason Gunthorpe
2018-03-16 23:04 ` Steve Wise
2018-03-16 23:04 ` Steve Wise
2018-03-16 23:04 ` Steve Wise
2018-03-17 4:08 ` Timur Tabi
2018-03-17 4:08 ` Timur Tabi
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=20180316221347.GA958@ziepe.ca \
--to=jgg@ziepe.ca \
--cc=dledford@redhat.com \
--cc=leedom@chelsio.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-arm-msm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=okaya@codeaurora.org \
--cc=sulrich@codeaurora.org \
--cc=swise@chelsio.com \
--cc=swise@opengridcomputing.com \
--cc=timur@codeaurora.org \
--cc=werner@chelsio.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 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.