On 13.03.2020 17:18, Andrew Cooper wrote: > On 13/03/2020 09:26, Jan Beulich wrote: >> All CPUs get an equal setting of EOI broadcast suppression; no need to >> log one message per CPU, even if it's only in verbose APIC mode. >> >> Only the BSP is eligible to possibly get ExtINT enabled; no need to log >> that it gets disabled on all APs, even if - again - it's only in verbose >> APIC mode. > > How true is this in practice?
I guess you read "eligible" as "in theory", whereas it is meant as "with how our [and in particular this] code is working right now". Even if we decided to switch the CPU to handle ExtINT, it still wouldn't need to be one message per CPU - it would suffice to issue the message for the one CPU getting ExtINT enabled. Jan > I know it is certainly the recommended configuration, but interrupt > remapping can definitely point ExtINT at arbitrary CPUs, and IIRC, the > MP spec simply says that "only one CPU should be configured to receive > ExtINT". > > I know we definitely have bugs with ExiINT handling, but I haven't had > time to debug further. > > ~Andrew > _______________________________________________ Xen-devel mailing list Xen-devel@lists.xenproject.org https://lists.xenproject.org/mailman/listinfo/xen-devel
