Muli Ben-Yehuda wrote: > On Sat, Sep 27, 2008 at 02:28:03PM +0800, Han, Weidong wrote: >>> From f2f722515135d95016f2d2ab55cc2aaf23d2fd80 Mon Sep 17 00:00:00 >>> 2001 >> From: Weidong Han <[EMAIL PROTECTED]> >> Date: Sat, 27 Sep 2008 14:28:07 +0800 >> Subject: [PATCH] Support multiple device assignment to one guest >> >> Current VT-d patches in kvm only support one device assignment to one >> guest due to dmar_domain is per device. >> >> In order to support multiple device assignemnt, this patch wraps >> dmar_domain with a reference count (kvm_vtd_domain), and also adds a >> pointer in kvm_assigned_dev_kernel to link to a kvm_vtd_domain. >> >> Each dmar_domain owns one VT-d page table, in order to reduce page >> tables and improve IOTLB utility, the devices assigned to the same >> guest and under the same IOMMU share the same kvm_vtd_domain. > > I guess this approach is OK as since we only support direct mapping at > the moment. Once we move to pvdma, each BDF will need its own domain > for intra-guest protection. Additionally, I think this approach will > actually reduce IOTLB utility, since you will have unrelated devices > with unrelated buffers competing for the same resource (IOTLB > space). But for now it's OK. >
Muli, I don't understand why this approach reduces IOTLB utility. How to say unrelated devices with unrelated buffers competing for the same resource? Multiple devices shares one page table should improve IOTLB utility, because some entries in IOTLB can be used for all of them. Randy (Weidong) > Cheers, > Muli > -- > The First Workshop on I/O Virtualization (WIOV '08) > Dec 2008, San Diego, CA, http://www.usenix.org/wiov08/ > xxx > SYSTOR 2009---The Israeli Experimental Systems Conference > http://www.haifa.il.ibm.com/conferences/systor2009/ -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
