On Mon, Aug 18, 2025 at 12:29:13PM +0100, Giovanni Cabiddu wrote:
Hi Greg and Sasha,
On Tue, Jul 22, 2025 at 04:07:09PM +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 (cherry-picked from commit a238487f7965d102794ed9f8aff0b667cd2ae886) [Giovanni: backport to 6.1.y, conflict resolved simplifying the logic in the function get_ring_to_svc_map() as the QAT driver in v6.1 supports only limited configurations (crypto only and compression). Differs from upstream as the ring to service mapping is hardcoded rather than being dynamically computed.] Reviewed-by: Ahsan Atta ahsan.atta@intel.com Tested-by: Ahsan Atta ahsan.atta@intel.com Signed-off-by: Giovanni Cabiddu giovanni.cabiddu@intel.com
V1 -> V2: changed signed-off-by area:
- added (cherry-picked from ...) after last tag from upstream commit
- added a note explaining how this backport differs from the original patch
- added a new Signed-off-by tag for the backport author.
Just following up on this patch as I haven't seen any activity on it yet.
Was it possibly missed, or is there anything I should do to move it forward?
It's in a pending queue of hundreds of stable backports I have yet to get to. That's what I get for trying to take a vacation... :)
Don't worry, it's not lost, just that we have to process patches for the newer stable kernels first, as that's where we have the most users. This, and many others, will be gotten to in a week or so.
thanks,
greg k-h