Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1740018 > unrolled thread

Re: [PATCH 4.4 50/53] ntb_transport: fix qp count bug

Started byBen Hutchings <ben.hutchings@codethink.co.uk>
First post2017-09-26 18:40 +0200
Last post2017-09-28 10:20 +0200
Articles 5 — 3 participants

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.


Contents

  Re: [PATCH 4.4 50/53] ntb_transport: fix qp count bug Ben Hutchings <ben.hutchings@codethink.co.uk> - 2017-09-26 18:40 +0200
    Re: [PATCH 4.4 50/53] ntb_transport: fix qp count bug Logan Gunthorpe <logang@deltatee.com> - 2017-09-26 19:40 +0200
      Re: [PATCH 4.4 50/53] ntb_transport: fix qp count bug Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-09-27 10:50 +0200
        Re: [PATCH 4.4 50/53] ntb_transport: fix qp count bug Logan Gunthorpe <logang@deltatee.com> - 2017-09-27 18:00 +0200
          Re: [PATCH 4.4 50/53] ntb_transport: fix qp count bug Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-09-28 10:20 +0200

#1740018 — Re: [PATCH 4.4 50/53] ntb_transport: fix qp count bug

FromBen Hutchings <ben.hutchings@codethink.co.uk>
Date2017-09-26 18:40 +0200
SubjectRe: [PATCH 4.4 50/53] ntb_transport: fix qp count bug
Message-ID<uu13Q-7af-11@gated-at.bofh.it>
On Mon, 2017-08-28 at 10:05 +0200, Greg Kroah-Hartman wrote:
> 4.4-stable review patch.  If anyone has any objections, please let me know.
> 
> ------------------
> 
> From: Logan Gunthorpe <logang@deltatee.com>
> 
> commit cb827ee6ccc3e480f0d9c0e8e53eef55be5b0414 upstream.
> 
> In cases where there are more mw's than spads/2-2, the mw count gets
> reduced to match the limitation.
[...]

In 4.4-stable, it doesn't, so this patch doesn't fix anything.  It looks
like 4.4 would need a backport of:

commit b17faba03fc72091f4d040b879def004316952ec
Author: Shyam Sundar S K <ssundark@amd.com>
Date:   Wed Dec 7 22:37:05 2016 +0530

    ntb_transport: Limit memory windows based on available, scratchpads

Ben.

-- 
Ben Hutchings
Software Developer, Codethink Ltd.

[toc] | [next] | [standalone]


#1740054

FromLogan Gunthorpe <logang@deltatee.com>
Date2017-09-26 19:40 +0200
Message-ID<uu1ZU-7KQ-19@gated-at.bofh.it>
In reply to#1740018

On 26/09/17 10:32 AM, Ben Hutchings wrote:
> In 4.4-stable, it doesn't, so this patch doesn't fix anything.  It looks
> like 4.4 would need a backport of:

Yup, look like the Fixes tag should have been b17faba0 instead of 
cb827ee. In which case it doesn't apply to 4.4.

Thanks,

Logan

[toc] | [prev] | [next] | [standalone]


#1740514

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2017-09-27 10:50 +0200
Message-ID<uugcy-8qD-15@gated-at.bofh.it>
In reply to#1740054
On Tue, Sep 26, 2017 at 11:35:04AM -0600, Logan Gunthorpe wrote:
> 
> 
> On 26/09/17 10:32 AM, Ben Hutchings wrote:
> > In 4.4-stable, it doesn't, so this patch doesn't fix anything.  It looks
> > like 4.4 would need a backport of:
> 
> Yup, look like the Fixes tag should have been b17faba0 instead of cb827ee.
> In which case it doesn't apply to 4.4.

Ah, should this be reverted then from 4.4?

thanks,

greg k-h

[toc] | [prev] | [next] | [standalone]


#1740850

FromLogan Gunthorpe <logang@deltatee.com>
Date2017-09-27 18:00 +0200
Message-ID<uumUF-557-5@gated-at.bofh.it>
In reply to#1740514

On 27/09/17 02:40 AM, Greg Kroah-Hartman wrote:
> On Tue, Sep 26, 2017 at 11:35:04AM -0600, Logan Gunthorpe wrote:
>>
>>
>> On 26/09/17 10:32 AM, Ben Hutchings wrote:
>>> In 4.4-stable, it doesn't, so this patch doesn't fix anything.  It looks
>>> like 4.4 would need a backport of:
>>
>> Yup, look like the Fixes tag should have been b17faba0 instead of cb827ee.
>> In which case it doesn't apply to 4.4.
> 
> Ah, should this be reverted then from 4.4?

It probably doesn't matter. The patch changes mw_count to nt->mw_count, 
but in 4.4 these values are exactly the same. So the patch shouldn't 
hurt anything but it also didn't fix anything.

Logan

[toc] | [prev] | [next] | [standalone]


#1741264

FromGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Date2017-09-28 10:20 +0200
Message-ID<uuCd4-6xg-9@gated-at.bofh.it>
In reply to#1740850
On Wed, Sep 27, 2017 at 09:57:22AM -0600, Logan Gunthorpe wrote:
> 
> 
> On 27/09/17 02:40 AM, Greg Kroah-Hartman wrote:
> > On Tue, Sep 26, 2017 at 11:35:04AM -0600, Logan Gunthorpe wrote:
> > > 
> > > 
> > > On 26/09/17 10:32 AM, Ben Hutchings wrote:
> > > > In 4.4-stable, it doesn't, so this patch doesn't fix anything.  It looks
> > > > like 4.4 would need a backport of:
> > > 
> > > Yup, look like the Fixes tag should have been b17faba0 instead of cb827ee.
> > > In which case it doesn't apply to 4.4.
> > 
> > Ah, should this be reverted then from 4.4?
> 
> It probably doesn't matter. The patch changes mw_count to nt->mw_count, but
> in 4.4 these values are exactly the same. So the patch shouldn't hurt
> anything but it also didn't fix anything.

Ok, I'll leave it as-is, thanks for letting me know.

greg k-h

[toc] | [prev] | [standalone]


Back to top | Article view | linux.kernel


csiph-web