On 11/11/2024 2:22 PM, Ahmad Fatoum wrote: > Hello Guarav, > > Thanks for your patch. > > On 11.11.24 13:10, Gaurav Jain wrote: [...] >> #define pr_fmt(fmt) "caam blob_gen: " fmt >> @@ -104,7 +105,7 @@ int caam_process_blob(struct caam_blob_priv *priv, >> } >> >> ctrlpriv = dev_get_drvdata(jrdev->parent); >> - moo = FIELD_GET(CSTA_MOO, rd_reg32(&ctrlpriv->ctrl->perfmon.status)); >> + moo = FIELD_GET(CSTA_MOO, rd_reg32(&ctrlpriv->jr[0]->perfmon.status)); > > I believe your change is correct, but I would prefer that ctrlpriv gets a perfmon > member that is initialized in caam_probe to either &ctrlpriv->ctrl->perfmon.status > or &ctrlpriv->jr[0]->perfmon.status and then the code here would just use > &ctrlpriv->perfmon->status. > > This would simplify code not only here, but also in caam_ctrl_rng_init. > Agree. But maybe this refactoring deserves a separate patch, given that is should also cover the case when the Job Ring device corresponding to "ctrlpriv->jr[0]" is unbounded from the driver. Thanks, Horia
