userfaultfd: selftests: modify selftest to use /dev/userfaultfd

We clearly want to ensure both userfaultfd(2) and /dev/userfaultfd keep
working into the future, so just run the test twice, using each interface.

Instead of always testing both userfaultfd(2) and /dev/userfaultfd, let
the user choose which to test.

As with other test features, change the behavior based on a new command
line flag.  Introduce the idea of "test mods", which are generic (not
specific to a test type) modifications to the behavior of the test.  This
is sort of borrowed from this RFC patch series [1], but simplified a bit.

The benefit is, in "typical" configurations this test is somewhat slow
(say, 30sec or something).  Testing both clearly doubles it, so it may not
always be desirable, as users are likely to use one or the other, but
never both, in the "real world".

[1]: https://patchwork.kernel.org/project/linux-mm/patch/20201129004548.1619714-14-namit@vmware.com/

[axelrasmussen@google.com: modify selftest to exit with KSFT_SKIP *only* when features are unsupported, per Mike]
  Link: https://lkml.kernel.org/r/20220819205201.658693-4-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20220808175614.3885028-4-axelrasmussen@google.comSigned-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dmitry V. Levin <ldv@altlinux.org>
Cc: Gleb Fotengauer-Malinovskiy <glebfm@altlinux.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zhang Yi <yi.zhang@huawei.com>
Cc: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

tools/testing/selftests/vm/userfaultfd.c

@@ -77,6 +77,11 @@ static int bounces;
 #define TEST_SHMEM	3
 static int test_type;
 
+#define UFFD_FLAGS	(O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY)
+
+/* test using /dev/userfaultfd, instead of userfaultfd(2) */
+static bool test_dev_userfaultfd;
+
 /* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */
 #define ALARM_INTERVAL_SECS 10
 static volatile bool test_uffdio_copy_eexist = true;
@@ -125,6 +130,8 @@ struct uffd_stats {
 const char *examples =
     "# Run anonymous memory test on 100MiB region with 99999 bounces:\n"
     "./userfaultfd anon 100 99999\n\n"
+    "# Run the same anonymous memory test, but using /dev/userfaultfd:\n"
+    "./userfaultfd anon:dev 100 99999\n\n"
     "# Run share memory test on 1GiB region with 99 bounces:\n"
     "./userfaultfd shmem 1000 99\n\n"
     "# Run hugetlb memory test on 256MiB region with 50 bounces:\n"
@@ -141,6 +148,14 @@ static void usage(void)
 		"[hugetlbfs_file]\n\n");
 	fprintf(stderr, "Supported <test type>: anon, hugetlb, "
 		"hugetlb_shared, shmem\n\n");
+	fprintf(stderr, "'Test mods' can be joined to the test type string with a ':'. "
+		"Supported mods:\n");
+	fprintf(stderr, "\tsyscall - Use userfaultfd(2) (default)\n");
+	fprintf(stderr, "\tdev - Use /dev/userfaultfd instead of userfaultfd(2)\n");
+	fprintf(stderr, "\nExample test mod usage:\n");
+	fprintf(stderr, "# Run anonymous memory test with /dev/userfaultfd:\n");
+	fprintf(stderr, "./userfaultfd anon:dev 100 99999\n\n");
+
 	fprintf(stderr, "Examples:\n\n");
 	fprintf(stderr, "%s", examples);
 	exit(1);
@@ -154,12 +169,14 @@ static void usage(void)
 			ret, __LINE__);				\
 	} while (0)
 
-#define err(fmt, ...)				\
+#define errexit(exitcode, fmt, ...)		\
 	do {					\
 		_err(fmt, ##__VA_ARGS__);	\
-		exit(1);			\
+		exit(exitcode);			\
 	} while (0)
 
+#define err(fmt, ...) errexit(1, fmt, ##__VA_ARGS__)
+
 static void uffd_stats_reset(struct uffd_stats *uffd_stats,
 			     unsigned long n_cpus)
 {
@@ -383,13 +400,34 @@ static void assert_expected_ioctls_present(uint64_t mode, uint64_t ioctls)
 	}
 }
 
+static int __userfaultfd_open_dev(void)
+{
+	int fd, _uffd;
+
+	fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC);
+	if (fd < 0)
+		errexit(KSFT_SKIP, "opening /dev/userfaultfd failed");
+
+	_uffd = ioctl(fd, USERFAULTFD_IOC_NEW, UFFD_FLAGS);
+	if (_uffd < 0)
+		errexit(errno == ENOTTY ? KSFT_SKIP : 1,
+			"creating userfaultfd failed");
+	close(fd);
+	return _uffd;
+}
+
 static void userfaultfd_open(uint64_t *features)
 {
 	struct uffdio_api uffdio_api;
 
-	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY);
-	if (uffd < 0)
-		err("userfaultfd syscall not available in this kernel");
+	if (test_dev_userfaultfd)
+		uffd = __userfaultfd_open_dev();
+	else {
+		uffd = syscall(__NR_userfaultfd, UFFD_FLAGS);
+		if (uffd < 0)
+			errexit(errno == ENOSYS ? KSFT_SKIP : 1,
+				"creating userfaultfd failed");
+	}
 	uffd_flags = fcntl(uffd, F_GETFD, NULL);
 
 	uffdio_api.api = UFFD_API;
@@ -1584,8 +1622,6 @@ unsigned long default_huge_page_size(void)
 
 static void set_test_type(const char *type)
 {
-	uint64_t features = UFFD_API_FEATURES;
-
 	if (!strcmp(type, "anon")) {
 		test_type = TEST_ANON;
 		uffd_test_ops = &anon_uffd_test_ops;
@@ -1603,9 +1639,29 @@ static void set_test_type(const char *type)
 		test_type = TEST_SHMEM;
 		uffd_test_ops = &shmem_uffd_test_ops;
 		test_uffdio_minor = true;
-	} else {
-		err("Unknown test type: %s", type);
 	}
+}
+
+static void parse_test_type_arg(const char *raw_type)
+{
+	char *buf = strdup(raw_type);
+	uint64_t features = UFFD_API_FEATURES;
+
+	while (buf) {
+		const char *token = strsep(&buf, ":");
+
+		if (!test_type)
+			set_test_type(token);
+		else if (!strcmp(token, "dev"))
+			test_dev_userfaultfd = true;
+		else if (!strcmp(token, "syscall"))
+			test_dev_userfaultfd = false;
+		else
+			err("unrecognized test mod '%s'", token);
+	}
+
+	if (!test_type)
+		err("failed to parse test type argument: '%s'", raw_type);
 
 	if (test_type == TEST_HUGETLB)
 		page_size = default_huge_page_size();
@@ -1653,7 +1709,7 @@ int main(int argc, char **argv)
 		err("failed to arm SIGALRM");
 	alarm(ALARM_INTERVAL_SECS);
 
-	set_test_type(argv[1]);
+	parse_test_type_arg(argv[1]);
 
 	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
 	nr_pages_per_cpu = atol(argv[2]) * 1024*1024 / page_size /