KVM: pci-assign: do not map smm memory slot pages in vt-d page tables
or VM memory are not put thus leaked in kvm_iommu_unmap_memslots() when destroy VM. This is consistent with current vfio implementation. Signed-off-by: Nherongguang <herongguang.he@huawei.com> Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Showing
想要评论请 注册 或 登录