[RFC][KVM][PATCH 1/1] kvm:ppc:booke-64: soft-disable interrupts

tiejun.chen tiejun.chen at windriver.com
Thu May 9 18:17:31 EST 2013


On 05/09/2013 04:12 PM, Bhushan Bharat-R65777 wrote:
>
>
>> -----Original Message-----
>> From: Kevin Hao [mailto:haokexin at gmail.com]
>> Sent: Thursday, May 09, 2013 1:38 PM
>> To: Bhushan Bharat-R65777
>> Cc: tiejun.chen; Caraman Mihai Claudiu-B02008; kvm at vger.kernel.org; Wood Scott-
>> B07421; agraf at suse.de; kvm-ppc at vger.kernel.org; linuxppc-dev at lists.ozlabs.org
>> Subject: Re: [RFC][KVM][PATCH 1/1] kvm:ppc:booke-64: soft-disable interrupts
>>
>> On Thu, May 09, 2013 at 07:51:09AM +0000, Bhushan Bharat-R65777 wrote:
>>>
>>>
>>>> -----Original Message-----
>>>> From: tiejun.chen [mailto:tiejun.chen at windriver.com]
>>>> Sent: Thursday, May 09, 2013 1:18 PM
>>>> To: Bhushan Bharat-R65777
>>>> Cc: Caraman Mihai Claudiu-B02008; Wood Scott-B07421; linuxppc-
>>>> dev at lists.ozlabs.org; agraf at suse.de; kvm-ppc at vger.kernel.org;
>>>> kvm at vger.kernel.org
>>>> Subject: Re: [RFC][KVM][PATCH 1/1] kvm:ppc:booke-64: soft-disable
>>>> interrupts
>>>>
>>>> On 05/09/2013 03:33 PM, Bhushan Bharat-R65777 wrote:
>>>>>
>>>>>
>>>>>> -----Original Message-----
>>>>>> From: Linuxppc-dev [mailto:linuxppc-dev-
>>>>>> bounces+bharat.bhushan=freescale.com at lists.ozlabs.org] On Behalf
>>>>>> bounces+Of Caraman
>>>>>> Mihai Claudiu-B02008
>>>>>> Sent: Wednesday, May 08, 2013 6:44 PM
>>>>>> To: Wood Scott-B07421; tiejun.chen
>>>>>> Cc: linuxppc-dev at lists.ozlabs.org; agraf at suse.de;
>>>>>> kvm-ppc at vger.kernel.org; kvm at vger.kernel.org
>>>>>> Subject: RE: [RFC][KVM][PATCH 1/1] kvm:ppc:booke-64: soft-disable
>>>>>> interrupts
>>>>>>
>>>>>>>> This only disable soft interrupt for kvmppc_restart_interrupt()
>>>>>>>> that restarts interrupts if they were meant for the host:
>>>>>>>>
>>>>>>>> a. SOFT_DISABLE_INTS() only for BOOKE_INTERRUPT_EXTERNAL |
>>>>>>>> BOOKE_INTERRUPT_DECREMENTER | BOOKE_INTERRUPT_DOORBELL
>>>>>>>
>>>>>>> Those aren't the only exceptions that can end up going to the host.
>>>>>>> We could get a TLB miss that results in a heavyweight MMIO exit, etc.
>>>>>>>
>>>>>>>> And shouldn't we handle kvmppc_restart_interrupt() like the
>>>>>>>> original HOST flow?
>>>>>>>>
>>>>>>>> #define MASKABLE_EXCEPTION(trapnum, intnum, label, hdlr,
>>>>>>>> ack)           \
>>>>>>>>
>>>>>>>> START_EXCEPTION(label);                                         \
>>>>>>>>           NORMAL_EXCEPTION_PROLOG(trapnum, intnum,
>>>>>>>> PROLOG_ADDITION_MASKABLE)\
>>>>>>>>           EXCEPTION_COMMON(trapnum, PACA_EXGEN,
>>>>>>>> *INTS_DISABLE*)             \
>>>>>>>> 	...
>>>>>>>
>>>>>>> Could you elaborate on what you mean?
>>>>>>
>>>>>> I think Tiejun was saying that host has flags and replays only
>>>>>> EE/DEC/DBELL interrupts. There is special macro
>>>>>> masked_interrupt_book3e in those exception handlers that sets
>>>>>> paca-
>>>>> irq_happened.
>>>>>>
>>>>>> The list of replied interrupts is limited to asynchronous
>>>>>> noncritical interrupts which can be masked by MSR[EE] (therefore no TLB
>> miss).
>>>>>
>>>>> Embedded Perfmon interrupt is also asynchronous, Why that is not
>>>>> in the list
>>>> of masked interruts.
>>>>
>>>> Are you saying perfmon? If so, its also in that list:
>>>>
>>>>           START_EXCEPTION(perfmon);
>>>>           NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR,
>>>>                                   PROLOG_ADDITION_NONE)
>>>>           EXCEPTION_COMMON(0x260, PACA_EXGEN, INTS_DISABLE)
>>>
>>> Where it is recorded in paca->irq_happned to be replayed later ?
>>
>> Actually we don't want replay the perfmon interrupt later. We would run it even
>> soft irq is disabled and just treat it as NMI. Please see the following function
>> quoted from arch/powerpc/perf/core-fsl-emb.c:
>>    /*
>>     * If interrupts were soft-disabled when a PMU interrupt occurs, treat
>>     * it as an NMI.
>>     */
>>    static inline int perf_intr_is_nmi(struct pt_regs *regs)
>>    {
>>    #ifdef __powerpc64__
>>            return !regs->softe;
>>    #else
>>            return 0;
>>    #endif
>>    }
>
> Is it because that we cannot afford to lose perfmon interrupt for more accurate capturing of data ?

     powerpc/perf: e500 support

     This implements perf_event support for the Freescale embedded performance
     monitor, based on the existing perf_event.c that supports server/classic
     chips.

     Some limitations:
     - Performance monitor interrupts are regular EE interrupts, and thus you
       can't profile places with interrupts disabled.  We may want to implement
       soft IRQ-disabling, with perfmon interrupts exempted and treated as NMIs.

Tiejun

>
> -Bharat
>
>>
>> Thanks,
>> Kevin
>>
>>>
>>>>
>>>> Tiejun
>>>>
>>>>>
>>>>> -Bharat
>>>>>
>>>>>> Now on KVM book3e we
>>>>>> don't want to put them in the irq_happened lazy state but rather
>>>>>> to execute them directly, so there is no reason for exception
>>>>>> handling symmetry between host and guest.
>>>>>>
>>>>>> -Mike
>>>>
>>>
>>> _______________________________________________
>>> Linuxppc-dev mailing list
>>> Linuxppc-dev at lists.ozlabs.org
>>> https://lists.ozlabs.org/listinfo/linuxppc-dev
>
>
>



More information about the Linuxppc-dev mailing list