KVM: selftests: aarch64: Add userfaultfd tests into page_fault_test

Add some userfaultfd tests into page_fault_test. Punch holes into the
data and/or page-table memslots, perform some accesses, and check that
the faults are taken (or not taken) when expected.
Signed-off-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221017195834.2295901-12-ricarkol@google.com

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

@@ -35,6 +35,12 @@ static uint64_t *guest_test_memory = (uint64_t *)TEST_GVA;
 #define PREPARE_FN_NR				10
 #define CHECK_FN_NR				10
 
+static struct event_cnt {
+	int uffd_faults;
+	/* uffd_faults is incremented from multiple threads. */
+	pthread_mutex_t uffd_faults_mutex;
+} events;
+
 struct test_desc {
 	const char *name;
 	uint64_t mem_mark_cmd;
@@ -42,11 +48,14 @@ struct test_desc {
 	bool (*guest_prepare[PREPARE_FN_NR])(void);
 	void (*guest_test)(void);
 	void (*guest_test_check[CHECK_FN_NR])(void);
+	uffd_handler_t uffd_pt_handler;
+	uffd_handler_t uffd_data_handler;
 	void (*dabt_handler)(struct ex_regs *regs);
 	void (*iabt_handler)(struct ex_regs *regs);
 	uint32_t pt_memslot_flags;
 	uint32_t data_memslot_flags;
 	bool skip;
+	struct event_cnt expected_events;
 };
 
 struct test_params {
@@ -263,7 +272,110 @@ static void no_iabt_handler(struct ex_regs *regs)
 	GUEST_ASSERT_1(false, regs->pc);
 }
 
+static struct uffd_args {
+	char *copy;
+	void *hva;
+	uint64_t paging_size;
+} pt_args, data_args;
+
 /* Returns true to continue the test, and false if it should be skipped. */
+static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg,
+				struct uffd_args *args, bool expect_write)
+{
+	uint64_t addr = msg->arg.pagefault.address;
+	uint64_t flags = msg->arg.pagefault.flags;
+	struct uffdio_copy copy;
+	int ret;
+
+	TEST_ASSERT(uffd_mode == UFFDIO_REGISTER_MODE_MISSING,
+		    "The only expected UFFD mode is MISSING");
+	ASSERT_EQ(!!(flags & UFFD_PAGEFAULT_FLAG_WRITE), expect_write);
+	ASSERT_EQ(addr, (uint64_t)args->hva);
+
+	pr_debug("uffd fault: addr=%p write=%d\n",
+		 (void *)addr, !!(flags & UFFD_PAGEFAULT_FLAG_WRITE));
+
+	copy.src = (uint64_t)args->copy;
+	copy.dst = addr;
+	copy.len = args->paging_size;
+	copy.mode = 0;
+
+	ret = ioctl(uffd, UFFDIO_COPY, &copy);
+	if (ret == -1) {
+		pr_info("Failed UFFDIO_COPY in 0x%lx with errno: %d\n",
+			addr, errno);
+		return ret;
+	}
+
+	pthread_mutex_lock(&events.uffd_faults_mutex);
+	events.uffd_faults += 1;
+	pthread_mutex_unlock(&events.uffd_faults_mutex);
+	return 0;
+}
+
+static int uffd_pt_write_handler(int mode, int uffd, struct uffd_msg *msg)
+{
+	return uffd_generic_handler(mode, uffd, msg, &pt_args, true);
+}
+
+static int uffd_data_write_handler(int mode, int uffd, struct uffd_msg *msg)
+{
+	return uffd_generic_handler(mode, uffd, msg, &data_args, true);
+}
+
+static int uffd_data_read_handler(int mode, int uffd, struct uffd_msg *msg)
+{
+	return uffd_generic_handler(mode, uffd, msg, &data_args, false);
+}
+
+static void setup_uffd_args(struct userspace_mem_region *region,
+			    struct uffd_args *args)
+{
+	args->hva = (void *)region->region.userspace_addr;
+	args->paging_size = region->region.memory_size;
+
+	args->copy = malloc(args->paging_size);
+	TEST_ASSERT(args->copy, "Failed to allocate data copy.");
+	memcpy(args->copy, args->hva, args->paging_size);
+}
+
+static void setup_uffd(struct kvm_vm *vm, struct test_params *p,
+		       struct uffd_desc **pt_uffd, struct uffd_desc **data_uffd)
+{
+	struct test_desc *test = p->test_desc;
+	int uffd_mode = UFFDIO_REGISTER_MODE_MISSING;
+
+	setup_uffd_args(vm_get_mem_region(vm, MEM_REGION_PT), &pt_args);
+	setup_uffd_args(vm_get_mem_region(vm, MEM_REGION_TEST_DATA), &data_args);
+
+	*pt_uffd = NULL;
+	if (test->uffd_pt_handler)
+		*pt_uffd = uffd_setup_demand_paging(uffd_mode, 0,
+						    pt_args.hva,
+						    pt_args.paging_size,
+						    test->uffd_pt_handler);
+
+	*data_uffd = NULL;
+	if (test->uffd_data_handler)
+		*data_uffd = uffd_setup_demand_paging(uffd_mode, 0,
+						      data_args.hva,
+						      data_args.paging_size,
+						      test->uffd_data_handler);
+}
+
+static void free_uffd(struct test_desc *test, struct uffd_desc *pt_uffd,
+		      struct uffd_desc *data_uffd)
+{
+	if (test->uffd_pt_handler)
+		uffd_stop_demand_paging(pt_uffd);
+	if (test->uffd_data_handler)
+		uffd_stop_demand_paging(data_uffd);
+
+	free(pt_args.copy);
+	free(data_args.copy);
+}
+
+/* Returns false if the test should be skipped. */
 static bool punch_hole_in_backing_store(struct kvm_vm *vm,
 					struct userspace_mem_region *region)
 {
@@ -404,6 +516,11 @@ static void setup_memslots(struct kvm_vm *vm, struct test_params *p)
 	vm->memslots[MEM_REGION_TEST_DATA] = TEST_DATA_MEMSLOT;
 }
 
+static void check_event_counts(struct test_desc *test)
+{
+	ASSERT_EQ(test->expected_events.uffd_faults, events.uffd_faults);
+}
+
 static void print_test_banner(enum vm_guest_mode mode, struct test_params *p)
 {
 	struct test_desc *test = p->test_desc;
@@ -414,6 +531,11 @@ static void print_test_banner(enum vm_guest_mode mode, struct test_params *p)
 		 vm_mem_backing_src_alias(p->src_type)->name);
 }
 
+static void reset_event_counts(void)
+{
+	memset(&events, 0, sizeof(events));
+}
+
 /*
  * This function either succeeds, skips the test (after setting test->skip), or
  * fails with a TEST_FAIL that aborts all tests.
@@ -453,6 +575,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	struct test_desc *test = p->test_desc;
 	struct kvm_vm *vm;
 	struct kvm_vcpu *vcpu;
+	struct uffd_desc *pt_uffd, *data_uffd;
 
 	print_test_banner(mode, p);
 
@@ -465,7 +588,16 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	ucall_init(vm, NULL);
 
+	reset_event_counts();
+
+	/*
+	 * Set some code in the data memslot for the guest to execute (only
+	 * applicable to the EXEC tests). This has to be done before
+	 * setup_uffd() as that function copies the memslot data for the uffd
+	 * handler.
+	 */
 	load_exec_code_for_test(vm);
+	setup_uffd(vm, p, &pt_uffd, &data_uffd);
 	setup_abort_handlers(vm, vcpu, test);
 	vcpu_args_set(vcpu, 1, test);
 
@@ -473,6 +605,14 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	ucall_uninit(vm);
 	kvm_vm_free(vm);
+	free_uffd(test, pt_uffd, data_uffd);
+
+	/*
+	 * Make sure we check the events after the uffd threads have exited,
+	 * which means they updated their respective event counters.
+	 */
+	if (!test->skip)
+		check_event_counts(test);
 }
 
 static void help(char *name)
@@ -488,6 +628,7 @@ static void help(char *name)
 #define SNAME(s)			#s
 #define SCAT2(a, b)			SNAME(a ## _ ## b)
 #define SCAT3(a, b, c)			SCAT2(a, SCAT2(b, c))
+#define SCAT4(a, b, c, d)		SCAT2(a, SCAT3(b, c, d))
 
 #define _CHECK(_test)			_CHECK_##_test
 #define _PREPARE(_test)			_PREPARE_##_test
@@ -515,6 +656,21 @@ static void help(char *name)
 	.mem_mark_cmd		= _mark_cmd,					\
 	.guest_test		= _access,					\
 	.guest_test_check	= { _CHECK(_with_af) },				\
+	.expected_events	= { 0 },					\
+}
+
+#define TEST_UFFD(_access, _with_af, _mark_cmd,					\
+		  _uffd_data_handler, _uffd_pt_handler, _uffd_faults)		\
+{										\
+	.name			= SCAT4(uffd, _access, _with_af, #_mark_cmd),	\
+	.guest_prepare		= { _PREPARE(_with_af),				\
+				    _PREPARE(_access) },			\
+	.guest_test		= _access,					\
+	.mem_mark_cmd		= _mark_cmd,					\
+	.guest_test_check	= { _CHECK(_with_af) },				\
+	.uffd_data_handler	= _uffd_data_handler,				\
+	.uffd_pt_handler	= _uffd_pt_handler,				\
+	.expected_events	= { .uffd_faults = _uffd_faults, },		\
 }
 
 static struct test_desc tests[] = {
@@ -545,6 +701,37 @@ static struct test_desc tests[] = {
 	TEST_ACCESS(guest_at, no_af, CMD_HOLE_DATA),
 	TEST_ACCESS(guest_dc_zva, no_af, CMD_HOLE_DATA),
 
+	/*
+	 * Punch holes in the data and PT backing stores and mark them for
+	 * userfaultfd handling. This should result in 2 faults: the access
+	 * on the data backing store, and its respective S1 page table walk
+	 * (S1PTW).
+	 */
+	TEST_UFFD(guest_read64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
+		  uffd_data_read_handler, uffd_pt_write_handler, 2),
+	/* no_af should also lead to a PT write. */
+	TEST_UFFD(guest_read64, no_af, CMD_HOLE_DATA | CMD_HOLE_PT,
+		  uffd_data_read_handler, uffd_pt_write_handler, 2),
+	/* Note how that cas invokes the read handler. */
+	TEST_UFFD(guest_cas, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
+		  uffd_data_read_handler, uffd_pt_write_handler, 2),
+	/*
+	 * Can't test guest_at with_af as it's IMPDEF whether the AF is set.
+	 * The S1PTW fault should still be marked as a write.
+	 */
+	TEST_UFFD(guest_at, no_af, CMD_HOLE_DATA | CMD_HOLE_PT,
+		  uffd_data_read_handler, uffd_pt_write_handler, 1),
+	TEST_UFFD(guest_ld_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
+		  uffd_data_read_handler, uffd_pt_write_handler, 2),
+	TEST_UFFD(guest_write64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
+		  uffd_data_write_handler, uffd_pt_write_handler, 2),
+	TEST_UFFD(guest_dc_zva, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
+		  uffd_data_write_handler, uffd_pt_write_handler, 2),
+	TEST_UFFD(guest_st_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
+		  uffd_data_write_handler, uffd_pt_write_handler, 2),
+	TEST_UFFD(guest_exec, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
+		  uffd_data_read_handler, uffd_pt_write_handler, 2),
+
 	{ 0 }
 };