Re: [PATCH 2/4] KVM: PPC: BOOK3S: PR: Doorbell support

["Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>]

Alexander Graf <agraf@suse.de> writes:

> On 05.06.14 14:08, Aneesh Kumar K.V wrote:
>> We don't have SMT support yet, hence we should not find a doorbell
>> message generated
>>
>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
>> ---
>>   arch/powerpc/kvm/book3s_emulate.c | 18 ++++++++++++++++++
>>   1 file changed, 18 insertions(+)
>>
>> diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
>> index 1bb16a59dcbc..d6c87d085182 100644
>> --- a/arch/powerpc/kvm/book3s_emulate.c
>> +++ b/arch/powerpc/kvm/book3s_emulate.c
>> @@ -28,7 +28,9 @@
>>   #define OP_19_XOP_RFI		50
>>   
>>   #define OP_31_XOP_MFMSR		83
>> +#define OP_31_XOP_MSGSNDP	142
>>   #define OP_31_XOP_MTMSR		146
>> +#define OP_31_XOP_MSGCLRP	174
>>   #define OP_31_XOP_MTMSRD	178
>>   #define OP_31_XOP_MTSR		210
>>   #define OP_31_XOP_MTSRIN	242
>> @@ -303,6 +305,22 @@ int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
>>   
>>   			break;
>>   		}
>> +		case OP_31_XOP_MSGSNDP:
>> +		{
>> +			/*
>> +			 * PR KVM still don't support SMT mode. So we should
>
> still?
>
>> +			 * not see a MSGSNDP/MSGCLRP used with PR KVM
>> +			 */
>> +			pr_info("KVM: MSGSNDP used in non SMT case\n");
>> +			emulated = EMULATE_FAIL;
>
> What would happen on an HV guest with only 1 thread that MSGSNDs to 
> thread 0? Would the guest get an illegal instruction trap, a 
> self-interrupt or would this be a simple nop?
>

We do get a self-interrupt. I tried the below

tag = mfspr(SPRN_TIR) & 0x7f;
ppc_msgsnd(5, 0, tag);

And that results in doorbell exception. That implies we will have to
have full implementation of doorbell. You can drop patch 2 and 3 from
this series. I will rework them.

NOTE: This is not an issue for Linux guest, because we don't send ipi
to self. But to complete the emulation of msgsndp we will need to
emulate it properly.

-aneesh