On 09/11/2017 12:01, Wanpeng Li wrote: > 2017-11-09 18:48 GMT+08:00 Paolo Bonzini <pbonzini@xxxxxxxxxx>: >> On 09/11/2017 03:02, Wanpeng Li wrote: >>> @@ -484,6 +511,8 @@ void __init kvm_guest_init(void) >>> pv_time_ops.steal_clock = kvm_steal_clock; >>> } >>> >>> + pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others; >> >> This needs to be keyed on a new CPUID feature bit. Eduardo is also > > Will do. > >> adding a new "PV_DEDICATED" hint and you might disable PV TLB flush when >> PV_DEDICATED is set. > > Why disable PV TLB flush for PV_DEDICATED(qspinlock)? PV_DEDICATED says pretty much that it is very unlikely to have a preempted vCPU. Therefore, the cpumask loop is unnecessary. Paolo
