On Fri, Nov 18, 2016 at 08:11:34PM +0530, Aneesh Kumar K.V wrote: > > @@ -3287,6 +3290,17 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) > > kvm->arch.lpcr = lpcr; > > > > /* > > + * Work out how many sets the TLB has, for the use of > > + * the TLB invalidation loop in book3s_hv_rmhandlers.S. > > + */ > > + if (cpu_has_feature(CPU_FTR_ARCH_300)) > > + kvm->arch.tlb_sets = 256; /* POWER9 */ > > + else if (cpu_has_feature(CPU_FTR_ARCH_207S)) > > + kvm->arch.tlb_sets = 512; /* POWER8 */ > > + else > > + kvm->arch.tlb_sets = 128; /* POWER7 */ > > + > > We have > > #define POWER7_TLB_SETS 128 /* # sets in POWER7 TLB */ > #define POWER8_TLB_SETS 512 /* # sets in POWER8 TLB */ > #define POWER9_TLB_SETS_HASH 256 /* # sets in POWER9 TLB Hash mode */ > #define POWER9_TLB_SETS_RADIX 128 /* # sets in POWER9 TLB Radix mode */ > > May be use that instead of opencoding ?
Doing that would make it easier to check that we're using the same values everywhere but harder to see what actual numbers we're getting. I guess I could use the symbols and put the values in the comments. In any case, in future these values are just going to be default values if we can't find a suitable device-tree property. Paul.
