On Mon, Sep 19, 2022 at 04:31:42PM +0200, Frederic Weisbecker wrote: > On Mon, Sep 19, 2022 at 11:59:48AM +0200, Peter Zijlstra wrote: > > Doing RCU-idle outside the driver, only to then teporarily enable it > > again before going idle is daft. > > That doesn't tell where those calls are. cpu_pm_enter/exit and the power domain stuff, possibly also the clock domain stuff. It's all over :/ I suppose I can add a blub and copy/paste it around the various patches if you want.
