1 files changed, 93 insertions, 87 deletions

diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 10ab56c2484a..8a09057d2f22 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -57,6 +57,7 @@
 #include <assert.h>
 #include <inttypes.h>
 #include <stdint.h>
+#include <sys/random.h>
 
 #include "../kselftest.h"
 
@@ -307,37 +308,24 @@ static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset)
 }
 
 struct uffd_test_ops {
-	unsigned long expected_ioctls;
 	void (*allocate_area)(void **alloc_area);
 	void (*release_pages)(char *rel_area);
 	void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset);
 };
 
-#define SHMEM_EXPECTED_IOCTLS		((1 << _UFFDIO_WAKE) | \
-					 (1 << _UFFDIO_COPY) | \
-					 (1 << _UFFDIO_ZEROPAGE))
-
-#define ANON_EXPECTED_IOCTLS		((1 << _UFFDIO_WAKE) | \
-					 (1 << _UFFDIO_COPY) | \
-					 (1 << _UFFDIO_ZEROPAGE) | \
-					 (1 << _UFFDIO_WRITEPROTECT))
-
 static struct uffd_test_ops anon_uffd_test_ops = {
-	.expected_ioctls = ANON_EXPECTED_IOCTLS,
 	.allocate_area	= anon_allocate_area,
 	.release_pages	= anon_release_pages,
 	.alias_mapping = noop_alias_mapping,
 };
 
 static struct uffd_test_ops shmem_uffd_test_ops = {
-	.expected_ioctls = SHMEM_EXPECTED_IOCTLS,
 	.allocate_area	= shmem_allocate_area,
 	.release_pages	= shmem_release_pages,
 	.alias_mapping = shmem_alias_mapping,
 };
 
 static struct uffd_test_ops hugetlb_uffd_test_ops = {
-	.expected_ioctls = UFFD_API_RANGE_IOCTLS_BASIC & ~(1 << _UFFDIO_CONTINUE),
 	.allocate_area	= hugetlb_allocate_area,
 	.release_pages	= hugetlb_release_pages,
 	.alias_mapping = hugetlb_alias_mapping,
@@ -345,6 +333,43 @@ static struct uffd_test_ops hugetlb_uffd_test_ops = {
 
 static struct uffd_test_ops *uffd_test_ops;
 
+static inline uint64_t uffd_minor_feature(void)
+{
+	if (test_type == TEST_HUGETLB && map_shared)
+		return UFFD_FEATURE_MINOR_HUGETLBFS;
+	else if (test_type == TEST_SHMEM)
+		return UFFD_FEATURE_MINOR_SHMEM;
+	else
+		return 0;
+}
+
+static uint64_t get_expected_ioctls(uint64_t mode)
+{
+	uint64_t ioctls = UFFD_API_RANGE_IOCTLS;
+
+	if (test_type == TEST_HUGETLB)
+		ioctls &= ~(1 << _UFFDIO_ZEROPAGE);
+
+	if (!((mode & UFFDIO_REGISTER_MODE_WP) && test_uffdio_wp))
+		ioctls &= ~(1 << _UFFDIO_WRITEPROTECT);
+
+	if (!((mode & UFFDIO_REGISTER_MODE_MINOR) && test_uffdio_minor))
+		ioctls &= ~(1 << _UFFDIO_CONTINUE);
+
+	return ioctls;
+}
+
+static void assert_expected_ioctls_present(uint64_t mode, uint64_t ioctls)
+{
+	uint64_t expected = get_expected_ioctls(mode);
+	uint64_t actual = ioctls & expected;
+
+	if (actual != expected) {
+		err("missing ioctl(s): expected %"PRIx64" actual: %"PRIx64,
+		    expected, actual);
+	}
+}
+
 static void userfaultfd_open(uint64_t *features)
 {
 	struct uffdio_api uffdio_api;
@@ -405,7 +430,7 @@ static void uffd_test_ctx_clear(void)
 	munmap_area((void **)&area_dst_alias);
 }
 
-static void uffd_test_ctx_init_ext(uint64_t *features)
+static void uffd_test_ctx_init(uint64_t features)
 {
 	unsigned long nr, cpu;
 
@@ -414,10 +439,7 @@ static void uffd_test_ctx_init_ext(uint64_t *features)
 	uffd_test_ops->allocate_area((void **)&area_src);
 	uffd_test_ops->allocate_area((void **)&area_dst);
 
-	uffd_test_ops->release_pages(area_src);
-	uffd_test_ops->release_pages(area_dst);
-
-	userfaultfd_open(features);
+	userfaultfd_open(&features);
 
 	count_verify = malloc(nr_pages * sizeof(unsigned long long));
 	if (!count_verify)
@@ -437,6 +459,26 @@ static void uffd_test_ctx_init_ext(uint64_t *features)
 		*(area_count(area_src, nr) + 1) = 1;
 	}
 
+	/*
+	 * After initialization of area_src, we must explicitly release pages
+	 * for area_dst to make sure it's fully empty.  Otherwise we could have
+	 * some area_dst pages be errornously initialized with zero pages,
+	 * hence we could hit memory corruption later in the test.
+	 *
+	 * One example is when THP is globally enabled, above allocate_area()
+	 * calls could have the two areas merged into a single VMA (as they
+	 * will have the same VMA flags so they're mergeable).  When we
+	 * initialize the area_src above, it's possible that some part of
+	 * area_dst could have been faulted in via one huge THP that will be
+	 * shared between area_src and area_dst.  It could cause some of the
+	 * area_dst won't be trapped by missing userfaults.
+	 *
+	 * This release_pages() will guarantee even if that happened, we'll
+	 * proactively split the thp and drop any accidentally initialized
+	 * pages within area_dst.
+	 */
+	uffd_test_ops->release_pages(area_dst);
+
 	pipefd = malloc(sizeof(int) * nr_cpus * 2);
 	if (!pipefd)
 		err("pipefd");
@@ -445,11 +487,6 @@ static void uffd_test_ctx_init_ext(uint64_t *features)
 			err("pipe");
 }
 
-static inline void uffd_test_ctx_init(uint64_t features)
-{
-	uffd_test_ctx_init_ext(&features);
-}
-
 static int my_bcmp(char *str1, char *str2, size_t n)
 {
 	unsigned long i;
@@ -501,22 +538,10 @@ static void continue_range(int ufd, __u64 start, __u64 len)
 static void *locking_thread(void *arg)
 {
 	unsigned long cpu = (unsigned long) arg;
-	struct random_data rand;
 	unsigned long page_nr = *(&(page_nr)); /* uninitialized warning */
-	int32_t rand_nr;
 	unsigned long long count;
-	char randstate[64];
-	unsigned int seed;
 
-	if (bounces & BOUNCE_RANDOM) {
-		seed = (unsigned int) time(NULL) - bounces;
-		if (!(bounces & BOUNCE_RACINGFAULTS))
-			seed += cpu;
-		bzero(&rand, sizeof(rand));
-		bzero(&randstate, sizeof(randstate));
-		if (initstate_r(seed, randstate, sizeof(randstate), &rand))
-			err("initstate_r failed");
-	} else {
+	if (!(bounces & BOUNCE_RANDOM)) {
 		page_nr = -bounces;
 		if (!(bounces & BOUNCE_RACINGFAULTS))
 			page_nr += cpu * nr_pages_per_cpu;
@@ -524,15 +549,8 @@ static void *locking_thread(void *arg)
 
 	while (!finished) {
 		if (bounces & BOUNCE_RANDOM) {
-			if (random_r(&rand, &rand_nr))
-				err("random_r failed");
-			page_nr = rand_nr;
-			if (sizeof(page_nr) > sizeof(rand_nr)) {
-				if (random_r(&rand, &rand_nr))
-					err("random_r failed");
-				page_nr |= (((unsigned long) rand_nr) << 16) <<
-					   16;
-			}
+			if (getrandom(&page_nr, sizeof(page_nr), 0) != sizeof(page_nr))
+				err("getrandom failed");
 		} else
 			page_nr += 1;
 		page_nr %= nr_pages;
@@ -1013,11 +1031,9 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
 {
 	struct uffdio_zeropage uffdio_zeropage;
 	int ret;
-	unsigned long has_zeropage;
+	bool has_zeropage = get_expected_ioctls(0) & (1 << _UFFDIO_ZEROPAGE);
 	__s64 res;
 
-	has_zeropage = uffd_test_ops->expected_ioctls & (1 << _UFFDIO_ZEROPAGE);
-
 	if (offset >= nr_pages * page_size)
 		err("unexpected offset %lu", offset);
 	uffdio_zeropage.range.start = (unsigned long) area_dst + offset;
@@ -1057,7 +1073,6 @@ static int uffdio_zeropage(int ufd, unsigned long offset)
 static int userfaultfd_zeropage_test(void)
 {
 	struct uffdio_register uffdio_register;
-	unsigned long expected_ioctls;
 
 	printf("testing UFFDIO_ZEROPAGE: ");
 	fflush(stdout);
@@ -1072,9 +1087,8 @@ static int userfaultfd_zeropage_test(void)
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 		err("register failure");
 
-	expected_ioctls = uffd_test_ops->expected_ioctls;
-	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls)
-		err("unexpected missing ioctl for anon memory");
+	assert_expected_ioctls_present(
+		uffdio_register.mode, uffdio_register.ioctls);
 
 	if (uffdio_zeropage(uffd, 0))
 		if (my_bcmp(area_dst, zeropage, page_size))
@@ -1087,7 +1101,6 @@ static int userfaultfd_zeropage_test(void)
 static int userfaultfd_events_test(void)
 {
 	struct uffdio_register uffdio_register;
-	unsigned long expected_ioctls;
 	pthread_t uffd_mon;
 	int err, features;
 	pid_t pid;
@@ -1111,9 +1124,8 @@ static int userfaultfd_events_test(void)
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 		err("register failure");
 
-	expected_ioctls = uffd_test_ops->expected_ioctls;
-	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls)
-		err("unexpected missing ioctl for anon memory");
+	assert_expected_ioctls_present(
+		uffdio_register.mode, uffdio_register.ioctls);
 
 	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats))
 		err("uffd_poll_thread create");
@@ -1141,7 +1153,6 @@ static int userfaultfd_events_test(void)
 static int userfaultfd_sig_test(void)
 {
 	struct uffdio_register uffdio_register;
-	unsigned long expected_ioctls;
 	unsigned long userfaults;
 	pthread_t uffd_mon;
 	int err, features;
@@ -1165,9 +1176,8 @@ static int userfaultfd_sig_test(void)
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 		err("register failure");
 
-	expected_ioctls = uffd_test_ops->expected_ioctls;
-	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls)
-		err("unexpected missing ioctl for anon memory");
+	assert_expected_ioctls_present(
+		uffdio_register.mode, uffdio_register.ioctls);
 
 	if (faulting_process(1))
 		err("faulting process failed");
@@ -1202,14 +1212,12 @@ static int userfaultfd_sig_test(void)
 static int userfaultfd_minor_test(void)
 {
 	struct uffdio_register uffdio_register;
-	unsigned long expected_ioctls;
 	unsigned long p;
 	pthread_t uffd_mon;
 	uint8_t expected_byte;
 	void *expected_page;
 	char c;
 	struct uffd_stats stats = { 0 };
-	uint64_t req_features, features_out;
 
 	if (!test_uffdio_minor)
 		return 0;
@@ -1217,21 +1225,7 @@ static int userfaultfd_minor_test(void)
 	printf("testing minor faults: ");
 	fflush(stdout);
 
-	if (test_type == TEST_HUGETLB)
-		req_features = UFFD_FEATURE_MINOR_HUGETLBFS;
-	else if (test_type == TEST_SHMEM)
-		req_features = UFFD_FEATURE_MINOR_SHMEM;
-	else
-		return 1;
-
-	features_out = req_features;
-	uffd_test_ctx_init_ext(&features_out);
-	/* If kernel reports required features aren't supported, skip test. */
-	if ((features_out & req_features) != req_features) {
-		printf("skipping test due to lack of feature support\n");
-		fflush(stdout);
-		return 0;
-	}
+	uffd_test_ctx_init(uffd_minor_feature());
 
 	uffdio_register.range.start = (unsigned long)area_dst_alias;
 	uffdio_register.range.len = nr_pages * page_size;
@@ -1239,10 +1233,8 @@ static int userfaultfd_minor_test(void)
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 		err("register failure");
 
-	expected_ioctls = uffd_test_ops->expected_ioctls;
-	expected_ioctls |= 1 << _UFFDIO_CONTINUE;
-	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls)
-		err("unexpected missing ioctl(s)");
+	assert_expected_ioctls_present(
+		uffdio_register.mode, uffdio_register.ioctls);
 
 	/*
 	 * After registering with UFFD, populate the non-UFFD-registered side of
@@ -1439,8 +1431,6 @@ static int userfaultfd_stress(void)
 	pthread_attr_setstacksize(&attr, 16*1024*1024);
 
 	while (bounces--) {
-		unsigned long expected_ioctls;
-
 		printf("bounces: %d, mode:", bounces);
 		if (bounces & BOUNCE_RANDOM)
 			printf(" rnd");
@@ -1468,10 +1458,8 @@ static int userfaultfd_stress(void)
 			uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
 		if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 			err("register failure");
-		expected_ioctls = uffd_test_ops->expected_ioctls;
-		if ((uffdio_register.ioctls & expected_ioctls) !=
-		    expected_ioctls)
-			err("unexpected missing ioctl for anon memory");
+		assert_expected_ioctls_present(
+			uffdio_register.mode, uffdio_register.ioctls);
 
 		if (area_dst_alias) {
 			uffdio_register.range.start = (unsigned long)
@@ -1592,6 +1580,8 @@ 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;
@@ -1625,6 +1615,22 @@ static void set_test_type(const char *type)
 	if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2
 	    > page_size)
 		err("Impossible to run this test");
+
+	/*
+	 * Whether we can test certain features depends not just on test type,
+	 * but also on whether or not this particular kernel supports the
+	 * feature.
+	 */
+
+	userfaultfd_open(&features);
+
+	test_uffdio_wp = test_uffdio_wp &&
+		(features & UFFD_FEATURE_PAGEFAULT_FLAG_WP);
+	test_uffdio_minor = test_uffdio_minor &&
+		(features & uffd_minor_feature());
+
+	close(uffd);
+	uffd = -1;
 }
 
 static void sigalrm(int sig)