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

Kevin Hao haokexin at gmail.com
Thu May 9 18:21:12 EST 2013


On Thu, May 09, 2013 at 08:12:51AM +0000, 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 ?

Yes, I think this will definitely improve the perf sample quality.

Thanks,
Kevin

> 
> -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
> 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 490 bytes
Desc: not available
URL: <http://lists.ozlabs.org/pipermail/linuxppc-dev/attachments/20130509/e3ed913b/attachment.sig>


More information about the Linuxppc-dev mailing list