From: okaya@codeaurora.org <okaya@codeaurora.org>
To: intel-wired-lan@osuosl.org
Subject: [Intel-wired-lan] [PATCH 7/7] ixgbevf: eliminate duplicate barriers on weakly-ordered archs
Date: Wed, 14 Mar 2018 08:13:05 -0400 [thread overview]
Message-ID: <2a4f4dec64b7462ae64152f6c2df9754@codeaurora.org> (raw)
In-Reply-To: <12150aa0-77ba-878e-31f4-d4f8d6a28ccb@codeaurora.org>
On 2018-03-14 01:08, Timur Tabi wrote:
> On 3/13/18 10:20 PM, Sinan Kaya wrote:
>> +/* Assumes caller has executed a write barrier to order memory and
>> device
>> + * requests.
>> + */
>> static inline void ixgbevf_write_tail(struct ixgbevf_ring *ring, u32
>> value)
>> {
>> - writel(value, ring->tail);
>> + writel_relaxed(value, ring->tail);
>> }
>
> Why not put the wmb() in this function, or just get rid of the wmb()
> in the rest of the file and keep this as writel? That way, you can
> avoid the comment and the risk that comes with it.
Sure, both solutions will work. I want to see what the maintainer
prefers. I can repost accordingly.
WARNING: multiple messages have this Message-ID (diff)
From: okaya@codeaurora.org
To: Timur Tabi <timur@codeaurora.org>
Cc: netdev@vger.kernel.org, sulrich@codeaurora.org,
linux-arm-msm@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
Jeff Kirsher <jeffrey.t.kirsher@intel.com>,
intel-wired-lan@lists.osuosl.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 7/7] ixgbevf: eliminate duplicate barriers on weakly-ordered archs
Date: Wed, 14 Mar 2018 08:13:05 -0400 [thread overview]
Message-ID: <2a4f4dec64b7462ae64152f6c2df9754@codeaurora.org> (raw)
In-Reply-To: <12150aa0-77ba-878e-31f4-d4f8d6a28ccb@codeaurora.org>
On 2018-03-14 01:08, Timur Tabi wrote:
> On 3/13/18 10:20 PM, Sinan Kaya wrote:
>> +/* Assumes caller has executed a write barrier to order memory and
>> device
>> + * requests.
>> + */
>> static inline void ixgbevf_write_tail(struct ixgbevf_ring *ring, u32
>> value)
>> {
>> - writel(value, ring->tail);
>> + writel_relaxed(value, ring->tail);
>> }
>
> Why not put the wmb() in this function, or just get rid of the wmb()
> in the rest of the file and keep this as writel? That way, you can
> avoid the comment and the risk that comes with it.
Sure, both solutions will work. I want to see what the maintainer
prefers. I can repost accordingly.
WARNING: multiple messages have this Message-ID (diff)
From: okaya@codeaurora.org (okaya at codeaurora.org)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH 7/7] ixgbevf: eliminate duplicate barriers on weakly-ordered archs
Date: Wed, 14 Mar 2018 08:13:05 -0400 [thread overview]
Message-ID: <2a4f4dec64b7462ae64152f6c2df9754@codeaurora.org> (raw)
In-Reply-To: <12150aa0-77ba-878e-31f4-d4f8d6a28ccb@codeaurora.org>
On 2018-03-14 01:08, Timur Tabi wrote:
> On 3/13/18 10:20 PM, Sinan Kaya wrote:
>> +/* Assumes caller has executed a write barrier to order memory and
>> device
>> + * requests.
>> + */
>> static inline void ixgbevf_write_tail(struct ixgbevf_ring *ring, u32
>> value)
>> {
>> - writel(value, ring->tail);
>> + writel_relaxed(value, ring->tail);
>> }
>
> Why not put the wmb() in this function, or just get rid of the wmb()
> in the rest of the file and keep this as writel? That way, you can
> avoid the comment and the risk that comes with it.
Sure, both solutions will work. I want to see what the maintainer
prefers. I can repost accordingly.
next prev parent reply other threads:[~2018-03-14 12:13 UTC|newest]
Thread overview: 81+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-14 3:20 [Intel-wired-lan] [PATCH 1/7] i40e/i40evf: Eliminate duplicate barriers on weakly-ordered archs Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-14 3:20 ` [Intel-wired-lan] [PATCH 2/7] ixgbe: eliminate " Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-15 1:47 ` [Intel-wired-lan] " Alexander Duyck
2018-03-15 1:47 ` Alexander Duyck
2018-03-15 1:47 ` Alexander Duyck
2018-03-14 3:20 ` [PATCH 3/7] RDMA/qedr: " Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-14 4:12 ` Jason Gunthorpe
2018-03-14 4:12 ` Jason Gunthorpe
2018-03-14 12:06 ` okaya
2018-03-14 12:06 ` okaya at codeaurora.org
2018-03-15 22:23 ` Jason Gunthorpe
2018-03-15 22:23 ` Jason Gunthorpe
2018-03-14 3:20 ` [Intel-wired-lan] [PATCH 4/7] igbvf: " Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-15 1:48 ` [Intel-wired-lan] " Alexander Duyck
2018-03-15 1:48 ` Alexander Duyck
2018-03-15 1:48 ` Alexander Duyck
2018-03-14 3:20 ` [Intel-wired-lan] [PATCH 5/7] igb: " Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-15 1:50 ` [Intel-wired-lan] " Alexander Duyck
2018-03-15 1:50 ` Alexander Duyck
2018-03-15 1:50 ` Alexander Duyck
2018-03-14 3:20 ` [Intel-wired-lan] [PATCH 6/7] e1000: " Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-15 1:41 ` [Intel-wired-lan] " Alexander Duyck
2018-03-15 1:41 ` Alexander Duyck
2018-03-15 1:41 ` Alexander Duyck
2018-03-15 23:30 ` [Intel-wired-lan] " Sinan Kaya
2018-03-15 23:30 ` Sinan Kaya
2018-03-15 23:30 ` Sinan Kaya
2018-03-16 0:25 ` [Intel-wired-lan] " Alexander Duyck
2018-03-16 0:25 ` Alexander Duyck
2018-03-16 0:25 ` Alexander Duyck
2018-03-16 0:50 ` [Intel-wired-lan] " Sinan Kaya
2018-03-16 0:50 ` Sinan Kaya
2018-03-16 0:50 ` Sinan Kaya
2018-03-14 3:20 ` [Intel-wired-lan] [PATCH 7/7] ixgbevf: " Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-14 3:20 ` Sinan Kaya
2018-03-14 5:08 ` [Intel-wired-lan] " Timur Tabi
2018-03-14 5:08 ` Timur Tabi
2018-03-14 5:08 ` Timur Tabi
2018-03-14 12:13 ` okaya [this message]
2018-03-14 12:13 ` okaya at codeaurora.org
2018-03-14 12:13 ` okaya
2018-03-14 21:49 ` [Intel-wired-lan] " Alexander Duyck
2018-03-14 21:49 ` Alexander Duyck
2018-03-14 21:49 ` Alexander Duyck
2018-03-14 22:57 ` [Intel-wired-lan] " Sinan Kaya
2018-03-14 22:57 ` Sinan Kaya
2018-03-14 22:57 ` Sinan Kaya
2018-03-15 1:44 ` [Intel-wired-lan] " Alexander Duyck
2018-03-15 1:44 ` Alexander Duyck
2018-03-15 1:44 ` Alexander Duyck
2018-03-15 2:17 ` [Intel-wired-lan] " Sinan Kaya
2018-03-15 2:17 ` Sinan Kaya
2018-03-15 2:17 ` Sinan Kaya
2018-03-15 14:32 ` [Intel-wired-lan] " Alexander Duyck
2018-03-15 14:32 ` Alexander Duyck
2018-03-15 14:32 ` Alexander Duyck
2018-03-15 16:21 ` [Intel-wired-lan] " Sinan Kaya
2018-03-15 16:21 ` Sinan Kaya
2018-03-15 16:21 ` Sinan Kaya
2018-03-15 16:27 ` [Intel-wired-lan] " Sinan Kaya
2018-03-15 16:27 ` Sinan Kaya
2018-03-15 16:27 ` Sinan Kaya
2018-03-15 16:58 ` [Intel-wired-lan] " Alexander Duyck
2018-03-15 16:58 ` Alexander Duyck
2018-03-15 16:58 ` Alexander Duyck
2018-03-15 1:45 ` [Intel-wired-lan] " Alexander Duyck
2018-03-15 1:45 ` Alexander Duyck
2018-03-15 1:45 ` Alexander Duyck
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=2a4f4dec64b7462ae64152f6c2df9754@codeaurora.org \
--to=okaya@codeaurora.org \
--cc=intel-wired-lan@osuosl.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.