>>> On 26.02.19 at 18:06, <igor.druzhi...@citrix.com> wrote: > @@ -323,6 +326,13 @@ static void setup_p6_watchdog(unsigned counter) > unsigned int evntsel; > > nmi_perfctr_msr = MSR_P6_PERFCTR(0); > + if ( !nmi_p6_event_width ) > + nmi_p6_event_width = (current_cpu_data.cpuid_level >= 0xa ) ?
Stray blank before closing paren. > + MASK_EXTR(cpuid_eax(0xa), P6_EVENT_WIDTH_MASK) : > + P6_EVENT_WIDTH_MIN; > + if ( nmi_p6_event_width < P6_EVENT_WIDTH_MIN || > + nmi_p6_event_width > BITS_PER_LONG ) > + return; I'm almost okay with this, but I'd really like the zero field case to be handled identical to the max-leaf-too-small one. A higher non-blank leaf existing does not mean the leaf here is meaningful. Or taking it the other way around, max-leaf-too-small should be no different from an all-blank leaf. Jan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xenproject.org https://lists.xenproject.org/mailman/listinfo/xen-devel
