KVM: MMU: fix direct sp's access corrupted

commit 9e7b0e7fba45ca3c6357aeb7091ebc281f1de365 upstream.

If the mapping is writable but the dirty flag is not set, we will find
the read-only direct sp and setup the mapping, then if the write #PF
occur, we will mark this mapping writable in the read-only direct sp,
now, other real read-only mapping will happily write it without #PF.

It may hurt guest's COW

Fixed by re-install the mapping when write #PF occur.

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 2331bdc2b549569e56f7dcec275c72bf06275928..e34452b929286db5cbc9359b908d4a01b43e2850 100644 (file)
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -324,8 +324,32 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
                        break;
                }
 
-               if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep))
-                       continue;
+               if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) {
+                       struct kvm_mmu_page *child;
+                       unsigned direct_access;
+
+                       if (level != gw->level)
+                               continue;
+
+                       /*
+                        * For the direct sp, if the guest pte's dirty bit
+                        * changed form clean to dirty, it will corrupt the
+                        * sp's access: allow writable in the read-only sp,
+                        * so we should update the spte at this point to get
+                        * a new sp with the correct access.
+                        */
+                       direct_access = gw->pt_access & gw->pte_access;
+                       if (!is_dirty_gpte(gw->ptes[gw->level - 1]))
+                               direct_access &= ~ACC_WRITE_MASK;
+
+                       child = page_header(*sptep & PT64_BASE_ADDR_MASK);
+                       if (child->role.access == direct_access)
+                               continue;
+
+                       mmu_page_remove_parent_pte(child, sptep);
+                       __set_spte(sptep, shadow_trap_nonpresent_pte);
+                       kvm_flush_remote_tlbs(vcpu->kvm);
+               }
 
                if (is_large_pte(*sptep)) {
                        rmap_remove(vcpu->kvm, sptep);