> -----Original Message----- > From: Peter Xu [mailto:pet...@redhat.com] > Sent: Monday, March 27, 2017 5:12 PM > To: Liu, Yi L <yi.l....@intel.com> > Cc: alex.william...@redhat.com; Lan, Tianyu <tianyu....@intel.com>; Tian, > Kevin > <kevin.t...@intel.com>; m...@redhat.com; jan.kis...@siemens.com; > jasow...@redhat.com; bd.a...@gmail.com; David Gibson > <da...@gibson.dropbear.id.au>; qemu-devel@nongnu.org > 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:qemu-devel-bounces+yi.l.liu=intel....@nongnu.org] On Behalf > > > Of Peter Xu > > > Sent: Tuesday, February 7, 2017 4:28 PM > > > To: qemu-devel@nongnu.org > > > Cc: Lan, Tianyu <tianyu....@intel.com>; Tian, Kevin > > > <kevin.t...@intel.com>; m...@redhat.com; jan.kis...@siemens.com; > > > jasow...@redhat.com; pet...@redhat.com; alex.william...@redhat.com; > > > bd.a...@gmail.com; David Gibson <da...@gibson.dropbear.id.au> > > > 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 <pet...@redhat.com> > > > --- > > > 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.
