userfaultfd/selftests: reinitialize test context in each test

Currently, the context (fds, mmap-ed areas, etc.) are global.  Each test
mutates this state in some way, in some cases really "clobbering it"
(e.g., the events test mremap-ing area_dst over the top of area_src, or
the minor faults tests overwriting the count_verify values in the test
areas).  We run the tests in a particular order, each test is careful to
make the right assumptions about its starting state, etc.

But, this is fragile.  It's better for a test's success or failure to not
depend on what some other prior test case did to the global state.

To that end, clear and reinitialize the test context at the start of each
test case, so whatever prior test cases did doesn't affect future tests.

This is particularly relevant to this series because the events test's
mremap of area_dst screws up assumptions the minor fault test was relying
on.  This wasn't a problem for hugetlb, as we don't mremap in that case.

[peterx@redhat.com: fix conflict between this patch and the uffd pagemap series]
  Link: https://lkml.kernel.org/r/YKQqKrl+/cQ1utrb@t490s

Link: https://lkml.kernel.org/r/20210503180737.2487560-10-axelrasmussen@google.comSigned-off-by: Axel Rasmussen <axelrasmussen@google.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Joe Perches <joe@perches.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Wang Qing <wangqing@vivo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

tools/testing/selftests/vm/userfaultfd.c

@@ -89,7 +89,8 @@ static int shm_fd;
 static int huge_fd;
 static char *huge_fd_off0;
 static unsigned long long *count_verify;
-static int uffd, uffd_flags, finished, *pipefd;
+static int uffd = -1;
+static int uffd_flags, finished, *pipefd;
 static char *area_src, *area_src_alias, *area_dst, *area_dst_alias;
 static char *zeropage;
 pthread_attr_t attr;
@@ -342,6 +343,111 @@ static struct uffd_test_ops hugetlb_uffd_test_ops = {
 
 static struct uffd_test_ops *uffd_test_ops;
 
+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");
+	uffd_flags = fcntl(uffd, F_GETFD, NULL);
+
+	uffdio_api.api = UFFD_API;
+	uffdio_api.features = *features;
+	if (ioctl(uffd, UFFDIO_API, &uffdio_api))
+		err("UFFDIO_API failed.\nPlease make sure to "
+		    "run with either root or ptrace capability.");
+	if (uffdio_api.api != UFFD_API)
+		err("UFFDIO_API error: %" PRIu64, (uint64_t)uffdio_api.api);
+
+	*features = uffdio_api.features;
+}
+
+static inline void munmap_area(void **area)
+{
+	if (*area)
+		if (munmap(*area, nr_pages * page_size))
+			err("munmap");
+
+	*area = NULL;
+}
+
+static void uffd_test_ctx_clear(void)
+{
+	size_t i;
+
+	if (pipefd) {
+		for (i = 0; i < nr_cpus * 2; ++i) {
+			if (close(pipefd[i]))
+				err("close pipefd");
+		}
+		free(pipefd);
+		pipefd = NULL;
+	}
+
+	if (count_verify) {
+		free(count_verify);
+		count_verify = NULL;
+	}
+
+	if (uffd != -1) {
+		if (close(uffd))
+			err("close uffd");
+		uffd = -1;
+	}
+
+	huge_fd_off0 = NULL;
+	munmap_area((void **)&area_src);
+	munmap_area((void **)&area_src_alias);
+	munmap_area((void **)&area_dst);
+	munmap_area((void **)&area_dst_alias);
+}
+
+static void uffd_test_ctx_init_ext(uint64_t *features)
+{
+	unsigned long nr, cpu;
+
+	uffd_test_ctx_clear();
+
+	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);
+
+	count_verify = malloc(nr_pages * sizeof(unsigned long long));
+	if (!count_verify)
+		err("count_verify");
+
+	for (nr = 0; nr < nr_pages; nr++) {
+		*area_mutex(area_src, nr) =
+			(pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER;
+		count_verify[nr] = *area_count(area_src, nr) = 1;
+		/*
+		 * In the transition between 255 to 256, powerpc will
+		 * read out of order in my_bcmp and see both bytes as
+		 * zero, so leave a placeholder below always non-zero
+		 * after the count, to avoid my_bcmp to trigger false
+		 * positives.
+		 */
+		*(area_count(area_src, nr) + 1) = 1;
+	}
+
+	pipefd = malloc(sizeof(int) * nr_cpus * 2);
+	if (!pipefd)
+		err("pipefd");
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK))
+			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;
@@ -726,40 +832,6 @@ static int stress(struct uffd_stats *uffd_stats)
 	return 0;
 }
 
-static int userfaultfd_open_ext(uint64_t *features)
-{
-	struct uffdio_api uffdio_api;
-
-	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY);
-	if (uffd < 0) {
-		fprintf(stderr,
-			"userfaultfd syscall not available in this kernel\n");
-		return 1;
-	}
-	uffd_flags = fcntl(uffd, F_GETFD, NULL);
-
-	uffdio_api.api = UFFD_API;
-	uffdio_api.features = *features;
-	if (ioctl(uffd, UFFDIO_API, &uffdio_api)) {
-		fprintf(stderr, "UFFDIO_API failed.\nPlease make sure to "
-			"run with either root or ptrace capability.\n");
-		return 1;
-	}
-	if (uffdio_api.api != UFFD_API) {
-		fprintf(stderr, "UFFDIO_API error: %" PRIu64 "\n",
-			(uint64_t)uffdio_api.api);
-		return 1;
-	}
-
-	*features = uffdio_api.features;
-	return 0;
-}
-
-static int userfaultfd_open(uint64_t features)
-{
-	return userfaultfd_open_ext(&features);
-}
-
 sigjmp_buf jbuf, *sigbuf;
 
 static void sighndl(int sig, siginfo_t *siginfo, void *ptr)
@@ -868,6 +940,8 @@ static int faulting_process(int signal_test)
 			  MREMAP_MAYMOVE | MREMAP_FIXED, area_src);
 	if (area_dst == MAP_FAILED)
 		err("mremap");
+	/* Reset area_src since we just clobbered it */
+	area_src = NULL;
 
 	for (; nr < nr_pages; nr++) {
 		count = *area_count(area_dst, nr);
@@ -961,10 +1035,8 @@ static int userfaultfd_zeropage_test(void)
 	printf("testing UFFDIO_ZEROPAGE: ");
 	fflush(stdout);
 
-	uffd_test_ops->release_pages(area_dst);
+	uffd_test_ctx_init(0);
 
-	if (userfaultfd_open(0))
-		return 1;
 	uffdio_register.range.start = (unsigned long) area_dst;
 	uffdio_register.range.len = nr_pages * page_size;
 	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
@@ -981,7 +1053,6 @@ static int userfaultfd_zeropage_test(void)
 		if (my_bcmp(area_dst, zeropage, page_size))
 			err("zeropage is not zero");
 
-	close(uffd);
 	printf("done.\n");
 	return 0;
 }
@@ -999,12 +1070,10 @@ static int userfaultfd_events_test(void)
 	printf("testing events (fork, remap, remove): ");
 	fflush(stdout);
 
-	uffd_test_ops->release_pages(area_dst);
-
 	features = UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_EVENT_REMAP |
 		UFFD_FEATURE_EVENT_REMOVE;
-	if (userfaultfd_open(features))
-		return 1;
+	uffd_test_ctx_init(features);
+
 	fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
 
 	uffdio_register.range.start = (unsigned long) area_dst;
@@ -1037,8 +1106,6 @@ static int userfaultfd_events_test(void)
 	if (pthread_join(uffd_mon, NULL))
 		return 1;
 
-	close(uffd);
-
 	uffd_stats_report(&stats, 1);
 
 	return stats.missing_faults != nr_pages;
@@ -1058,11 +1125,9 @@ static int userfaultfd_sig_test(void)
 	printf("testing signal delivery: ");
 	fflush(stdout);
 
-	uffd_test_ops->release_pages(area_dst);
-
 	features = UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_SIGBUS;
-	if (userfaultfd_open(features))
-		return 1;
+	uffd_test_ctx_init(features);
+
 	fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
 
 	uffdio_register.range.start = (unsigned long) area_dst;
@@ -1103,7 +1168,6 @@ static int userfaultfd_sig_test(void)
 	printf("done.\n");
 	if (userfaults)
 		err("Signal test failed, userfaults: %ld", userfaults);
-	close(uffd);
 
 	return userfaults != 0;
 }
@@ -1126,10 +1190,7 @@ static int userfaultfd_minor_test(void)
 	printf("testing minor faults: ");
 	fflush(stdout);
 
-	uffd_test_ops->release_pages(area_dst);
-
-	if (userfaultfd_open_ext(&features))
-		return 1;
+	uffd_test_ctx_init_ext(&features);
 	/* If kernel reports the feature isn't supported, skip the test. */
 	if (!(features & UFFD_FEATURE_MINOR_HUGETLBFS)) {
 		printf("skipping test due to lack of feature support\n");
@@ -1183,8 +1244,6 @@ static int userfaultfd_minor_test(void)
 	if (pthread_join(uffd_mon, NULL))
 		return 1;
 
-	close(uffd);
-
 	uffd_stats_report(&stats, 1);
 
 	return stats.missing_faults != 0 || stats.minor_faults != nr_pages;
@@ -1267,7 +1326,7 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize)
 	/* Flush so it doesn't flush twice in parent/child later */
 	fflush(stdout);
 
-	uffd_test_ops->release_pages(area_dst);
+	uffd_test_ctx_init(0);
 
 	if (test_pgsize > page_size) {
 		/* This is a thp test */
@@ -1279,9 +1338,6 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize)
 			err("madvise(MADV_NOHUGEPAGE) failed");
 	}
 
-	if (userfaultfd_open(0))
-		err("userfaultfd_open");
-
 	uffdio_register.range.start = (unsigned long) area_dst;
 	uffdio_register.range.len = nr_pages * page_size;
 	uffdio_register.mode = UFFDIO_REGISTER_MODE_WP;
@@ -1324,7 +1380,6 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize)
 	pagemap_check_wp(value, false);
 
 	close(pagemap_fd);
-	close(uffd);
 	printf("done\n");
 }
 
@@ -1334,50 +1389,9 @@ static int userfaultfd_stress(void)
 	char *tmp_area;
 	unsigned long nr;
 	struct uffdio_register uffdio_register;
-	unsigned long cpu;
 	struct uffd_stats uffd_stats[nr_cpus];
 
-	uffd_test_ops->allocate_area((void **)&area_src);
-	if (!area_src)
-		return 1;
-	uffd_test_ops->allocate_area((void **)&area_dst);
-	if (!area_dst)
-		return 1;
-
-	if (userfaultfd_open(0))
-		return 1;
-
-	count_verify = malloc(nr_pages * sizeof(unsigned long long));
-	if (!count_verify) {
-		perror("count_verify");
-		return 1;
-	}
-
-	for (nr = 0; nr < nr_pages; nr++) {
-		*area_mutex(area_src, nr) = (pthread_mutex_t)
-			PTHREAD_MUTEX_INITIALIZER;
-		count_verify[nr] = *area_count(area_src, nr) = 1;
-		/*
-		 * In the transition between 255 to 256, powerpc will
-		 * read out of order in my_bcmp and see both bytes as
-		 * zero, so leave a placeholder below always non-zero
-		 * after the count, to avoid my_bcmp to trigger false
-		 * positives.
-		 */
-		*(area_count(area_src, nr) + 1) = 1;
-	}
-
-	pipefd = malloc(sizeof(int) * nr_cpus * 2);
-	if (!pipefd) {
-		perror("pipefd");
-		return 1;
-	}
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		if (pipe2(&pipefd[cpu*2], O_CLOEXEC | O_NONBLOCK)) {
-			perror("pipe");
-			return 1;
-		}
-	}
+	uffd_test_ctx_init(0);
 
 	if (posix_memalign(&area, page_size, page_size))
 		err("out of memory");
@@ -1498,8 +1512,6 @@ static int userfaultfd_stress(void)
 		uffd_stats_report(uffd_stats, nr_cpus);
 	}
 
-	close(uffd);
-
 	if (test_type == TEST_ANON) {
 		/*
 		 * shmem/hugetlb won't be able to run since they have different