> On Fri, Sep 19, 2025 at 10:17:00AM +0000, Eliav Farber wrote:
> > This series includes a total of 27 patches, to align minmax.h of
> > v5.15.y with v6.17-rc6.
> >
> > The set consists of 24 commits that directly update minmax.h:
> > 1) 92d23c6e9415 ("overflow, tracing: Define the is_signed_type() macro
> >    once")
>
> But this isn't in 5.15.y, so how is this syncing things up?
>
> I'm all for this, but I got confused here, at the first commit :)

It's a typo.
It should be 5.10.y and not 5.15.y.

> Some of these are also only in newer kernels, which, as you know, is
> generally a bad thing (i.e. I can't take patches only for older
> kernels.)
>
> I want these changes, as they are great, but can you perhaps provide
> patch series for newer kernels first so that I can then take these?

So you'd first like first to align 6.16 with 6.17, then 6.15 with 6.16,
then 6.12 with 6.15, then 6.6 with 6.12, and so on until we eventually
align 5.10 and even 5.4?

---
Regards, Eliav

On Sun, Sep 21, 2025 at 09:37:02PM +0000, Farber, Eliav wrote:
> > On Fri, Sep 19, 2025 at 10:17:00AM +0000, Eliav Farber wrote:
> > > This series includes a total of 27 patches, to align minmax.h of
> > > v5.15.y with v6.17-rc6.
> > >
> > > The set consists of 24 commits that directly update minmax.h:
> > > 1) 92d23c6e9415 ("overflow, tracing: Define the is_signed_type() macro
> > >    once")
> >
> > But this isn't in 5.15.y, so how is this syncing things up?
> >
> > I'm all for this, but I got confused here, at the first commit :)
> 
> It's a typo.
> It should be 5.10.y and not 5.15.y.
> 
> > Some of these are also only in newer kernels, which, as you know, is
> > generally a bad thing (i.e. I can't take patches only for older
> > kernels.)
> >
> > I want these changes, as they are great, but can you perhaps provide
> > patch series for newer kernels first so that I can then take these?
> 
> So you'd first like first to align 6.16 with 6.17, then 6.15 with 6.16,
> then 6.12 with 6.15, then 6.6 with 6.12, and so on until we eventually
> align 5.10 and even 5.4?

Yes please!

> On Sun, Sep 21, 2025 at 09:37:02PM +0000, Farber, Eliav wrote:
> > > On Fri, Sep 19, 2025 at 10:17:00AM +0000, Eliav Farber wrote:
> > > > This series includes a total of 27 patches, to align minmax.h of 
> > > > v5.15.y with v6.17-rc6.
> > > >
> > > > The set consists of 24 commits that directly update minmax.h:
> > > > 1) 92d23c6e9415 ("overflow, tracing: Define the is_signed_type() macro
> > > >    once")
> > >
> > > But this isn't in 5.15.y, so how is this syncing things up?
> > >
> > > I'm all for this, but I got confused here, at the first commit :)
> >
> > It's a typo.
> > It should be 5.10.y and not 5.15.y.
> >
> > > Some of these are also only in newer kernels, which, as you know, is 
> > > generally a bad thing (i.e. I can't take patches only for older
> > > kernels.)
> > >
> > > I want these changes, as they are great, but can you perhaps provide 
> > > patch series for newer kernels first so that I can then take these?
> >
> > So you'd first like first to align 6.16 with 6.17, then 6.15 with 
> > 6.16, then 6.12 with 6.15, then 6.6 with 6.12, and so on until we 
> > eventually align 5.10 and even 5.4?
>
> Yes please!

Stable 6.16.8 didn't require any changs.

I pulled the changes for 6.12.48:
https://lore.kernel.org/stable/20250922103123.14538-1-farbere@amazon.com/T/#t
and 6.6.107:
https://lore.kernel.org/stable/20250922103241.16213-1-farbere@amazon.com/T/#t

Once approved, I'll continue with other longterm branches.

---
Regards, Eliav