KVM: MMU: delay flush all tlbs on sync_page path

Quote from Avi:
| I don't think we need to flush immediately; set a "tlb dirty" bit somewhere
| that is cleareded when we flush the tlb.  kvm_mmu_notifier_invalidate_page()
| can consult the bit and force a flush if set.

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

1 files changed, 10 insertions, 2 deletions

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index a43f4ccd30bb..2b3d66c7b68d 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -746,6 +746,14 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu,
  * Using the cached information from sp->gfns is safe because:
  * - The spte has a reference to the struct page, so the pfn for a given gfn
  *   can't change unless all sptes pointing to it are nuked first.
+ *
+ * Note:
+ *   We should flush all tlbs if spte is dropped even though guest is
+ *   responsible for it. Since if we don't, kvm_mmu_notifier_invalidate_page
+ *   and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't
+ *   used by guest then tlbs are not flushed, so guest is allowed to access the
+ *   freed pages.
+ *   And we increase kvm->tlbs_dirty to delay tlbs flush in this case.
  */
 static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
@@ -781,14 +789,14 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
                 gfn = gpte_to_gfn(gpte);
 
                 if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
-                        kvm_flush_remote_tlbs(vcpu->kvm);
+                        vcpu->kvm->tlbs_dirty++;
                         continue;
                 }
 
                 if (gfn != sp->gfns[i]) {
                         drop_spte(vcpu->kvm, &sp->spt[i],
                                       shadow_trap_nonpresent_pte);
-                        kvm_flush_remote_tlbs(vcpu->kvm);
+                        vcpu->kvm->tlbs_dirty++;
                         continue;
                 }