On 12/01/2023 11:36, Sebastian Andrzej Siewior wrote: > On 2023-01-06 15:52:57 [+0100], Krzysztof Kozlowski wrote: >>> Just so I don't get this wrong, since the cpuidle-psci also calls >>> pm_runtime_* functions so it isn't PREEMPT_RT safe, at least not yet? >> >> You are correct. Patch 3 here addresses it by... just not doing runtime >> PM. This is a hacky workaround but: >> 1. I don't have any other idea, >> 2. It's not a big problem because RT systems are not supposed to have >> any CPU idle (one of first things during RT system tuning is to disable >> cpuidle). > > so you say you use idle=poll instead? This was generic comment that system is not supposed to go into deeper idle states. Best regards, Krzysztof
