Re: [PATCH v2 2/5] spi: spi-fsl-dspi: Exit the ISR with IRQ_NONE when it's not ours

From: Vladimir Oltean
Date: Fri Aug 23 2019 - 08:07:08 EST

Hi Mark,

On Fri, 23 Aug 2019 at 13:59, Mark Brown <broonie@xxxxxxxxxx> wrote:
> On Fri, Aug 23, 2019 at 11:50:44AM +0100, Mark Brown wrote:
> > On Fri, Aug 23, 2019 at 01:30:27PM +0300, Vladimir Oltean wrote:
> > > Did you see this?
> > >
> > I'm not online enough to readily follow that link right now, I
> > did apply another patch for a similar issue though. If that's
> > a different version of the same change please don't do that,
> > sending multiple conflicting versions of the same thing creates
> > conflicts and makes everything harder to work with.
> Oh, I guess this was due to there being an existing refactoring
> in -next that meant the fix wouldn't apply directly. I sorted
> that out now I think, but in general the same thing applies -
> it's better to put fixes before anything else in the series,
> it'll flag up when reviewing.

I try to require as little attention span as possible from you and I
apologize that I'm sending patches like a noob, but I'm not used to
this sort of interaction with a maintainer. It's taking me some time
to adjust expectations.
- You left change requests in the initial patchset I submitted, but
you partially applied the series anyway. You didn't give me a chance
to respin the whole series and put the shared IRQ fix on top, so it
applies on old trees as well. No problem, I sent two versions of the
- On my previous series you left this comment:

> Please don't include all the extra tags you've got in your subject
> lines. In my inbox this series looks like:
> 790 N T 08/18 Vladimir Oltean ( 16K) ââ>[PATCH spi for-5.4 01/14] spi: spi-f
> so I can't tell what it's actually about just from looking at it. Just
> [PATCH 01/14] would be enough, putting a target version in or versioning
> the patch series can be OK but you usually don't use a target version
> for -next and adding spi in there is redundant given that it's also in
> the changelog.

So I didn't put any target version in the patch titles this time,
although arguably it would have been clearer to you that there's a
patch for-5.4 and another version of it for-4.20 (which i *think* is
how I should submit a fix, I don't see any branch for inclusion in
stable trees per se).
No problem, I explained in the cover letters that one patchset is for
-next and the other is for inclusion in stable trees. Maintainers do
read cover letters, right?
Message from the -next cover letter:

> The series also contains a bug fix for the shared IRQ of the DSPI
> driver. I am going to respin a version of it as a separate patch for
> inclusion in stable trees, independent of this patchset.

Message from the fix's cover letter:

> This patch is taken out of the "Poll mode for NXP DSPI driver" series
> and respun against the "for-4.20" branch.
> $(git describe --tags 13aed2392741) shows:
> v4.20-rc1-18-g13aed2392741

Yes, I did send a cover letter for a single patch. I thought it's
harder to miss than a note hidden under patch 2/5 of one series, and
in the note section of the other's. I think you could have also made
an argument about me not doing it the other way around. In the end,
you can not read a note just as well as not read a cover letter, and
there's little I can do.

No problem, you missed the link between the two. I sent you a link to
the lkml archive. You said "I'm not online enough to readily follow
that link right now". Please teach me - I really don't know - how can
I make links between patchsets easier for you to follow, if you don't
read cover letters and you can't access lkml? I promise I'll use that
method next time.

> I do frequently catch up on my mail on flights or while otherwise
> travelling so this is even more pressing for me than just being about
> making things a bit easier to read.

Maybe you simply should do something else while traveling, just saying.