On Sat, 18 Dec 2021 05:31:28 +0000, Hector Martin <marcan@xxxxxxxxx> wrote: > > >> + u64 idx = FIELD_GET(MPIDR_CPU, mpidr); > >> + > >> + if (FIELD_GET(MPIDR_CLUSTER, my_mpidr) == cluster) > >> + write_sysreg_s(FIELD_PREP(IPI_RR_CPU, idx), > >> + SYS_IMP_APL_IPI_RR_LOCAL_EL1); > >> + else > >> + write_sysreg_s(FIELD_PREP(IPI_RR_CPU, idx) | FIELD_PREP(IPI_RR_CLUSTER, cluster), > >> + SYS_IMP_APL_IPI_RR_GLOBAL_EL1); > > > > Don't you need an ISB, either here or in the two callers? At the > > moment, I don't see what will force the execution of these writes, and > > they could be arbitrarily delayed. > > Is there any requirement for timeliness sending IPIs? They're going to > another CPU after all, they could be arbitrarily delayed because it has > FIQs masked. They absolutely could, but this has a potential impact on the scheduling if you delay it (the vast majority of these IPIs are to indicate to the remote CPU that it needs to go and schedule something else). So there is an incentive for making it happen ASAP. Thanks, M. -- Without deviation from the norm, progress is not possible.
