Balbir Singh <bsinghar...@gmail.com> writes:
> On 16/11/16 21:51, Michael Ellerman wrote:
>> Michael Neuling <mi...@neuling.org> writes:
>>> diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
>>> index bda8c43be7..4a19cdd8a0 100644
>>> --- a/arch/powerpc/mm/tlb-radix.c
>>> +++ b/arch/powerpc/mm/tlb-radix.c
>>> @@ -50,6 +50,9 @@ static inline void _tlbiel_pid(unsigned long pid,
>>> unsigned long ric)
>>> for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
>>> __tlbiel_pid(pid, set, ric);
>>> }
>>> + if (cpu_has_feature(CPU_FTR_POWER9_DD1))
>>> + asm volatile(PPC_SLBIA(0x7)
>>> + : : :"memory");
>>
>> Ah of course I'll use slbia to invalidate the ERAT.
>>
>> How about we do:
>>
>> #define PPC_INVALIDATE_ERAT PPC_SLBIA(0x7)
>>
>
> While you are at it, could you also add a TODO
> to use a HCALL when LPCR_GTSE is not set
> (when running in guest mode)
In what config we use that ? With radix we always run with GTSE = 1 and
with hash we don't use tlbiel in guest.
-aneesh
