KVM: MMU: Fix potential race setting upper shadow ptes on nonpae hosts

The direct mapped shadow code (used for real mode and two dimensional paging)
sets upper-level ptes using direct assignment rather than calling
set_shadow_pte().  A nonpae host will split this into two writes, which opens
up a race if another vcpu accesses the same memory area.

Fix by calling set_shadow_pte() instead of assigning directly.

Noticed by Izik Eidus.
Signed-off-by: Avi Kivity <avi@qumranet.com>

arch/x86/kvm/mmu.c

@@ -1189,9 +1189,10 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 				return -ENOMEM;
 			}
 
-			table[index] = __pa(new_table->spt)
+			set_shadow_pte(&table[index],
+				       __pa(new_table->spt)
 				       | PT_PRESENT_MASK | PT_WRITABLE_MASK
-				| shadow_user_mask | shadow_x_mask;
+				       | shadow_user_mask | shadow_x_mask);
 		}
 		table_addr = table[index] & PT64_BASE_ADDR_MASK;
 	}