diff --git a/tools/testing/selftests/kvm/mmu_stress_test.c b/tools/testing/selftests/kvm/mmu_stress_test.c
index c07c15d7cc9a..a7cced5c3e67 100644
--- a/tools/testing/selftests/kvm/mmu_stress_test.c
+++ b/tools/testing/selftests/kvm/mmu_stress_test.c
@@ -16,8 +16,13 @@
 #include "guest_modes.h"
 #include "processor.h"
 
+#if defined(__x86_64__) || defined(__aarch64__)
+extern void *skip_page;
+#endif
+
 static bool mprotect_ro_done;
 
+
 static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
 {
 	uint64_t gpa;
@@ -40,18 +45,21 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
 	 * prematurely.
 	 *
 	 * For architectures that support skipping the faulting instruction,
-	 * generate the store via inline assembly to ensure the exact length
-	 * of the instruction is known and stable (vcpu_arch_put_guest() on
-	 * fixed-length architectures should work, but the cost of paranoia
-	 * is low in this case).  For x86, hand-code the exact opcode so that
-	 * there is no room for variability in the generated instruction.
+	 * generate the store via inline assembly to ensure we can correctly
+	 * adjust the PC upon faulting.
 	 */
 	do {
 		for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
 #ifdef __x86_64__
-			asm volatile(".byte 0x48,0x89,0x00" :: "a"(gpa) : "memory"); /* mov %rax, (%rax) */
+			asm volatile(".global skip_page;"
+				     "mov %0, (%0);"
+				     "skip_page:;"
+				     :: "r" (gpa) : "memory");
 #elif defined(__aarch64__)
-			asm volatile("str %0, [%0]" :: "r" (gpa) : "memory");
+			asm volatile(".global skip_page;"
+				     "str %0, [%0];"
+				     "skip_page:;"
+				     :: "r" (gpa) : "memory");
 #else
 			vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa);
 #endif
@@ -170,10 +178,10 @@ static void *vcpu_worker(void *data)
 		TEST_ASSERT_EQ(errno, EFAULT);
 #if defined(__x86_64__)
 		WRITE_ONCE(vcpu->run->kvm_dirty_regs, KVM_SYNC_X86_REGS);
-		vcpu->run->s.regs.regs.rip += 3;
+		vcpu->run->s.regs.regs.rip = (vm_vaddr_t)&skip_page;
 #elif defined(__aarch64__)
 		vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc),
-			     vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)) + 4);
+			     (vm_vaddr_t)&skip_page);
 #endif
 
 	}