Re: [PATCH v7 0/7] netdev: intel: Eliminate duplicate barriers on weakly-ordered archs

Jeff,

On 3/23/2018 10:34 PM, okaya@codeaurora.org wrote:

On 2018-03-23 19:58, Jeff Kirsher wrote:

quoted

On Fri, 2018-03-23 at 14:53 -0700, Alexander Duyck wrote:

quoted

On Fri, Mar 23, 2018 at 11:52 AM, Sinan Kaya [off-list ref]
wrote:

quoted

Code includes wmb() followed by writel() in multiple places. 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().

I did a regex search for wmb() followed by writel() in each drivers
directory.
I scrubbed the ones I care about in this series.

I considered "ease of change", "popular usage" and "performance
critical
path" as the determining criteria for my filtering.

We used relaxed API heavily on ARM for a long time but
it did not exist on other architectures. For this reason, relaxed
architectures have been paying double penalty in order to use the
common
drivers.

Now that relaxed API is present on all architectures, we can go and
scrub
all drivers to see what needs to change and what can remain.

We start with mostly used ones and hope to increase the coverage over
time.
It will take a while to cover all drivers.

Feel free to apply patches individually.

I looked over the set and they seem good.

Reviewed-by: Alexander Duyck <redacted>

Grrr, patch 1 does not apply cleanly to my next-queue tree (dev-queue
branch).  I will deal with this series in a day or two, after I have dealt
with my driver pull requests.

Sorry, you will have to replace the ones you took from me.

Double sorry now.

I don't know if you have been following "RFC on writel and writel_relaxed" thread
or not but there are some new developments about wmb() requirement. 

Basically, wmb() should never be used before writel() as writel() seem to
provide coherency and observability guarantee.

wmb()+writel_relaxed() is slower on some architectures than plain writel()

I'll have to rework these patches to have writel() only. 

Are you able to drop the applied ones so that I can post V8 or is it too late?


Sinan

-- 
Sinan Kaya
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.