KVM: MMU: Introduce drop_spte()

When we call rmap_remove(), we (almost) always immediately follow it by
an __set_spte() to a nonpresent pte.  Since we need to perform the two
operations atomically, to avoid losing the dirty and accessed bits, introduce
a helper drop_spte() and convert all call sites.

The operation is still nonatomic at this point.

Signed-off-by: Avi Kivity <avi@redhat.com>
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 59e750c..796a325 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -353,8 +353,7 @@
 		}
 
 		if (is_large_pte(*sptep)) {
-			rmap_remove(vcpu->kvm, sptep);
-			__set_spte(sptep, shadow_trap_nonpresent_pte);
+			drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte);
 			kvm_flush_remote_tlbs(vcpu->kvm);
 		}
 
@@ -516,12 +515,13 @@
 			pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
 
 			if (is_shadow_present_pte(*sptep)) {
-				rmap_remove(vcpu->kvm, sptep);
 				if (is_large_pte(*sptep))
 					--vcpu->kvm->stat.lpages;
+				drop_spte(vcpu->kvm, sptep,
+					  shadow_trap_nonpresent_pte);
 				need_flush = 1;
-			}
-			__set_spte(sptep, shadow_trap_nonpresent_pte);
+			} else
+				__set_spte(sptep, shadow_trap_nonpresent_pte);
 			break;
 		}
 
@@ -637,12 +637,11 @@
 		      !is_present_gpte(gpte) || !(gpte & PT_ACCESSED_MASK)) {
 			u64 nonpresent;
 
-			rmap_remove(vcpu->kvm, &sp->spt[i]);
 			if (is_present_gpte(gpte) || !clear_unsync)
 				nonpresent = shadow_trap_nonpresent_pte;
 			else
 				nonpresent = shadow_notrap_nonpresent_pte;
-			__set_spte(&sp->spt[i], nonpresent);
+			drop_spte(vcpu->kvm, &sp->spt[i], nonpresent);
 			continue;
 		}