Le 13/02/2019 à 11:34, Rafael J. Wysocki a écrit : > So a single "no PCCH" message for this whole function should be sufficient.
Let's do that. [...] > And what did turn out to be the problem? > > Anyway, pr_info() should be sufficient IMO. You should be pretty aware of 95d6c0857e54b788982746071130d822a795026b ;) Depending if we have or not this patch, intel_pstate engage itself or not. When engaged, we have to perform some configuration that the other state doesn't imply. I'm updating the patch this way than send a v6. I just let intel_pstate_msrs_not_valid() in pr_warn() as this one is not supposed to be a "normal" case. Thanks for your time & reviews. > Many thanks for your contribution! My pleasure ! Erwan,
