Re: [Qemu-devel] [PATCH v7 14/17] memory: add MemoryRegionIOMMUOps.replay() callback

[Liu, Yi L]

> -----Original Message-----
> From: Peter Xu [mailto:address@hidden
> Sent: Monday, March 27, 2017 5:12 PM
> To: Liu, Yi L <address@hidden>
> Cc: address@hidden; Lan, Tianyu <address@hidden>; Tian, Kevin
> <address@hidden>; address@hidden; address@hidden;
> address@hidden; address@hidden; David Gibson
> <address@hidden>; address@hidden
> Subject: Re: [Qemu-devel] [PATCH v7 14/17] memory: add
> MemoryRegionIOMMUOps.replay() callback
> 
> On Mon, Mar 27, 2017 at 08:35:05AM +0000, Liu, Yi L wrote:
> > > -----Original Message-----
> > > From: Qemu-devel
> > > [mailto:address@hidden On Behalf
> > > Of Peter Xu
> > > Sent: Tuesday, February 7, 2017 4:28 PM
> > > To: address@hidden
> > > Cc: Lan, Tianyu <address@hidden>; Tian, Kevin
> > > <address@hidden>; address@hidden; address@hidden;
> > > address@hidden; address@hidden; address@hidden;
> > > address@hidden; David Gibson <address@hidden>
> > > Subject: [Qemu-devel] [PATCH v7 14/17] memory: add
> > > MemoryRegionIOMMUOps.replay() callback
> > >
> > > Originally we have one memory_region_iommu_replay() function, which
> > > is the default behavior to replay the translations of the whole
> > > IOMMU region. However, on some platform like x86, we may want our own
> replay logic for IOMMU regions.
> > > This patch add one more hook for IOMMUOps for the callback, and
> > > it'll override the default if set.
> > >
> > > Signed-off-by: Peter Xu <address@hidden>
> > > ---
> > >  include/exec/memory.h | 2 ++
> > >  memory.c              | 6 ++++++
> > >  2 files changed, 8 insertions(+)
> > >
> > > diff --git a/include/exec/memory.h b/include/exec/memory.h index
> > > 0767888..30b2a74 100644
> > > --- a/include/exec/memory.h
> > > +++ b/include/exec/memory.h
> > > @@ -191,6 +191,8 @@ struct MemoryRegionIOMMUOps {
> > >      void (*notify_flag_changed)(MemoryRegion *iommu,
> > >                                  IOMMUNotifierFlag old_flags,
> > >                                  IOMMUNotifierFlag new_flags);
> > > +    /* Set this up to provide customized IOMMU replay function */
> > > +    void (*replay)(MemoryRegion *iommu, IOMMUNotifier *notifier);
> > >  };
> > >
> > >  typedef struct CoalescedMemoryRange CoalescedMemoryRange; diff
> > > --git a/memory.c b/memory.c index 7a4f2f9..9c253cc 100644
> > > --- a/memory.c
> > > +++ b/memory.c
> > > @@ -1630,6 +1630,12 @@ void memory_region_iommu_replay(MemoryRegion
> > > *mr, IOMMUNotifier *n,
> > >      hwaddr addr, granularity;
> > >      IOMMUTLBEntry iotlb;
> > > +    /* If the IOMMU has its own replay callback, override */
> > > +    if (mr->iommu_ops->replay) {
> > > +        mr->iommu_ops->replay(mr, n);
> > > +        return;
> > > +    }
> >
> > Hi Alex, Peter,
> >
> > Will all the other vendors(e.g. PPC, s390, ARM) add their own replay
> > callback as well? I guess it depends on whether the original replay
> > algorithm work well for them? Do you have such knowledge?
> 
> I guess so. At least for VT-d we had this callback since the default replay 
> mechanism
> did not work well on x86 due to its extremely large memory region size. 
> Thanks,

thx. that would make sense.