Re: [PATCH 6.1] crypto: qat - fix ring to service map for QAT GEN4

[Greg KH <gregkh@linuxfoundation.org>]

On Tue, Jul 22, 2025 at 02:29:32PM +0100, Giovanni Cabiddu wrote:
> On Tue, Jul 22, 2025 at 11:42:37AM +0200, Greg KH wrote:
> > On Thu, Jul 17, 2025 at 06:06:38PM +0100, Giovanni Cabiddu wrote:
> > > [ Upstream commit a238487f7965d102794ed9f8aff0b667cd2ae886 ]
> > > 
> > > The 4xxx drivers hardcode the ring to service mapping. However, when
> > > additional configurations where added to the driver, the mappings were
> > > not updated. This implies that an incorrect mapping might be reported
> > > through pfvf for certain configurations.
> > > 
> > > This is a backport of the upstream commit with modifications, as the
> > > original patch does not apply cleanly to kernel v6.1.x. The logic has
> > > been simplified to reflect the limited configurations of the QAT driver
> > > in this version: crypto-only and compression.
> > > 
> > > Instead of dynamically computing the ring to service mappings, these are
> > > now hardcoded to simplify the backport.
> > > 
> > > Fixes: 0cec19c761e5 ("crypto: qat - add support for compression for 4xxx")
> > > Signed-off-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
> > > Reviewed-by: Damian Muszynski <damian.muszynski@intel.com>
> > > Reviewed-by: Tero Kristo <tero.kristo@linux.intel.com>
> > > Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
> > > Cc: <stable@vger.kernel.org> # 6.1.x
> > > Reviewed-by: Ahsan Atta <ahsan.atta@intel.com>
> > > Tested-by: Ahsan Atta <ahsan.atta@intel.com>
> > 
> > You did not mention anywhere what changed from the original commit (and
> > it changed a lot...)  So this looks to me like an incorrect backport, so
> > I have to just delete it :(
> It is mentioned in the commit message:
> 
>   This is a backport of the upstream commit with modifications, as the
>   original patch does not apply cleanly to kernel v6.1.x. The logic has
>   been simplified to reflect the limited configurations of the QAT driver
>   in this version: crypto-only and compression.
> 
>   Instead of dynamically computing the ring to service mappings, these are
>   now hardcoded to simplify the backport.
> 
> I didn't port the original algorithm that builds the ring to service
> mapping as the QAT driver in v6.1 only supports two configurations
> (crypto and compression), therefore I simplified the logic in the
> function get_ring_to_svc_map() to just returns the mask associated to
> each configuration.
> 
> BTW, I'm also the author of the original patch.
> 
> > 
> > Please fix up and send it again.
> Is this sufficient or shall I resend?

Please resend and put the comments you made that differ from the
original changelog text down in the signed-off-by area like other
backports do.

Here is an example of that:
	https://lore.kernel.org/r/20250717124556.589696-2-harshit.m.mogalapalli@oracle.com

thanks,

greg k-h