KVM: selftests: Move per-VM/per-vCPU nr pages calculation to __vm_create()

Handle all memslot0 size adjustments in __vm_create().  Currently, the
adjustments reside in __vm_create_with_vcpus(), which means tests that
call vm_create() or __vm_create() directly are left to their own devices.
Some tests just pass DEFAULT_GUEST_PHY_PAGES and don't bother with any
adjustments, while others mimic the per-vCPU calculations.

For vm_create(), and thus __vm_create(), take the number of vCPUs that
will be runnable to calculate that number of per-vCPU pages needed for
memslot0.  To give readers a hint that neither vm_create() nor
__vm_create() create vCPUs, name the parameter @nr_runnable_vcpus instead
of @nr_vcpus.  That also gives readers a hint as to why tests that create
larger numbers of vCPUs but never actually run those vCPUs can skip
straight to the vm_create_barebones() variant.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

tools/testing/selftests/kvm/aarch64/psci_test.c

@@ -76,7 +76,7 @@ static struct kvm_vm *setup_vm(void *guest_code, struct kvm_vcpu **source,
 	struct kvm_vcpu_init init;
 	struct kvm_vm *vm;
 
-	vm = vm_create(DEFAULT_GUEST_PHY_PAGES);
+	vm = vm_create(2);
 	ucall_init(vm, NULL);
 
 	vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init);

tools/testing/selftests/kvm/aarch64/vgic_init.c

@@ -419,7 +419,7 @@ static void test_v3_typer_accesses(void)
 	uint64_t addr;
 	int ret, i;
 
-	v.vm = vm_create(DEFAULT_GUEST_PHY_PAGES);
+	v.vm = vm_create(NR_VCPUS);
 	(void)vm_vcpu_add(v.vm, 0, guest_code);
 
 	v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3);
@@ -479,7 +479,7 @@ static struct vm_gic vm_gic_v3_create_with_vcpuids(int nr_vcpus,
 	struct vm_gic v;
 	int i;
 
-	v.vm = vm_create(DEFAULT_GUEST_PHY_PAGES);
+	v.vm = vm_create(nr_vcpus);
 	for (i = 0; i < nr_vcpus; i++)
 		vm_vcpu_add(v.vm, vcpuids[i], guest_code);
 

tools/testing/selftests/kvm/dirty_log_test.c

@@ -669,11 +669,10 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, struct kvm_vcpu **vcpu,
 				uint64_t extra_mem_pages, void *guest_code)
 {
 	struct kvm_vm *vm;
-	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	vm = __vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages);
+	vm = __vm_create(mode, 1, extra_mem_pages);
 
 	log_mode_create_vm_done(vm);
 	*vcpu = vm_vcpu_add(vm, 0, guest_code);

tools/testing/selftests/kvm/hardware_disable_test.c

@@ -98,7 +98,7 @@ static void run_test(uint32_t run)
 	for (i = 0; i < VCPU_NUM; i++)
 		CPU_SET(i, &cpu_set);
 
-	vm = vm_create(DEFAULT_GUEST_PHY_PAGES);
+	vm = vm_create(VCPU_NUM);
 
 	pr_debug("%s: [%d] start vcpus\n", __func__, run);
 	for (i = 0; i < VCPU_NUM; ++i) {

tools/testing/selftests/kvm/include/kvm_util_base.h

@@ -547,18 +547,21 @@ vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm);
 /*
  * ____vm_create() does KVM_CREATE_VM and little else.  __vm_create() also
  * loads the test binary into guest memory and creates an IRQ chip (x86 only).
+ * __vm_create() does NOT create vCPUs, @nr_runnable_vcpus is used purely to
+ * calculate the amount of memory needed for per-vCPU data, e.g. stacks.
  */
 struct kvm_vm *____vm_create(enum vm_guest_mode mode, uint64_t nr_pages);
-struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint64_t nr_pages);
+struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
+			   uint64_t nr_extra_pages);
 
 static inline struct kvm_vm *vm_create_barebones(void)
 {
 	return ____vm_create(VM_MODE_DEFAULT, 0);
 }
 
-static inline struct kvm_vm *vm_create(uint64_t nr_pages)
+static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus)
 {
-	return __vm_create(VM_MODE_DEFAULT, nr_pages);
+	return __vm_create(VM_MODE_DEFAULT, nr_runnable_vcpus, 0);
 }
 
 struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -258,11 +258,45 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode, uint64_t nr_pages)
 	return vm;
 }
 
-struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint64_t nr_pages)
+static uint64_t vm_nr_pages_required(enum vm_guest_mode mode,
+				     uint32_t nr_runnable_vcpus,
+				     uint64_t extra_mem_pages)
 {
-	struct kvm_vm *vm;
+	uint64_t nr_pages;
 
-	nr_pages = vm_adjust_num_guest_pages(mode, nr_pages);
+	TEST_ASSERT(nr_runnable_vcpus,
+		    "Use vm_create_barebones() for VMs that _never_ have vCPUs\n");
+
+	TEST_ASSERT(nr_runnable_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS),
+		    "nr_vcpus = %d too large for host, max-vcpus = %d",
+		    nr_runnable_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS));
+
+	nr_pages = DEFAULT_GUEST_PHY_PAGES;
+	nr_pages += nr_runnable_vcpus * DEFAULT_STACK_PGS;
+
+	/*
+	 * Account for the number of pages needed for the page tables.  The
+	 * maximum page table size for a memory region will be when the
+	 * smallest page size is used. Considering each page contains x page
+	 * table descriptors, the total extra size for page tables (for extra
+	 * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller
+	 * than N/x*2.
+	 */
+	nr_pages += (nr_pages + extra_mem_pages) / PTES_PER_MIN_PAGE * 2;
+
+	TEST_ASSERT(nr_runnable_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS),
+		    "Host doesn't support %d vCPUs, max-vcpus = %d",
+		    nr_runnable_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS));
+
+	return vm_adjust_num_guest_pages(mode, nr_pages);
+}
+
+struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
+			   uint64_t nr_extra_pages)
+{
+	uint64_t nr_pages = vm_nr_pages_required(mode, nr_runnable_vcpus,
+						 nr_extra_pages);
+	struct kvm_vm *vm;
 
 	vm = ____vm_create(mode, nr_pages);
 
@@ -297,27 +331,12 @@ struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus
 				      uint64_t extra_mem_pages,
 				      void *guest_code, struct kvm_vcpu *vcpus[])
 {
-	uint64_t vcpu_pages, extra_pg_pages, pages;
 	struct kvm_vm *vm;
 	int i;
 
 	TEST_ASSERT(!nr_vcpus || vcpus, "Must provide vCPU array");
 
-	/* The maximum page table size for a memory region will be when the
-	 * smallest pages are used. Considering each page contains x page
-	 * table descriptors, the total extra size for page tables (for extra
-	 * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller
-	 * than N/x*2.
-	 */
-	vcpu_pages = nr_vcpus * DEFAULT_STACK_PGS;
-	extra_pg_pages = (DEFAULT_GUEST_PHY_PAGES + extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2;
-	pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages;
-
-	TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS),
-		    "nr_vcpus = %d too large for host, max-vcpus = %d",
-		    nr_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS));
-
-	vm = __vm_create(mode, pages);
+	vm = __vm_create(mode, nr_vcpus, extra_mem_pages);
 
 	for (i = 0; i < nr_vcpus; ++i)
 		vcpus[i] = vm_vcpu_add(vm, i, guest_code);

tools/testing/selftests/kvm/s390x/resets.c

@@ -206,7 +206,7 @@ static struct kvm_vm *create_vm(struct kvm_vcpu **vcpu)
 {
 	struct kvm_vm *vm;
 
-	vm = vm_create(DEFAULT_GUEST_PHY_PAGES);
+	vm = vm_create(1);
 
 	*vcpu = vm_vcpu_add(vm, ARBITRARY_NON_ZERO_VCPU_ID, guest_code_initial);
 

tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c

@@ -365,7 +365,7 @@ static void test_pmu_config_disable(void (*guest_code)(void))
 	if (!(r & KVM_PMU_CAP_DISABLE))
 		return;
 
-	vm = vm_create(DEFAULT_GUEST_PHY_PAGES);
+	vm = vm_create(1);
 
 	vm_enable_cap(vm, KVM_CAP_PMU_CAPABILITY, KVM_PMU_CAP_DISABLE);
 

tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c

@@ -78,13 +78,10 @@ static void run_vcpu(struct kvm_vcpu *vcpu)
 static struct kvm_vm *create_vm(uint32_t nr_vcpus, uint32_t bsp_vcpu_id,
 				struct kvm_vcpu *vcpus[])
 {
-	uint64_t vcpu_pages = (DEFAULT_STACK_PGS) * nr_vcpus;
-	uint64_t extra_pg_pages = vcpu_pages / PTES_PER_MIN_PAGE * nr_vcpus;
-	uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages;
 	struct kvm_vm *vm;
 	uint32_t i;
 
-	vm = vm_create(pages);
+	vm = vm_create(nr_vcpus);
 
 	vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *)(unsigned long)bsp_vcpu_id);
 

tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c

@@ -98,7 +98,7 @@ int main(int argc, char *argv[])
 		exit(KSFT_SKIP);
 	}
 
-	vm = vm_create(DEFAULT_GUEST_PHY_PAGES + DEFAULT_STACK_PGS * NR_TEST_VCPUS);
+	vm = vm_create(NR_TEST_VCPUS);
 	vm_ioctl(vm, KVM_SET_TSC_KHZ, (void *) TEST_TSC_KHZ);
 
 	pthread_spin_init(&create_lock, PTHREAD_PROCESS_PRIVATE);