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@orac...
thanks,
greg k-h