From 91b66856b86fd2a3b38123cdbb7abf7fe37b8d72 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Thu, 18 Mar 2021 17:01:52 +1100 Subject: [PATCH] BACKPORT: FROMGIT: 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. Link: https://lkml.kernel.org/r/20210302000133.272579-5-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Cc: Alexander Viro Cc: Andrea Arcangeli Cc: Brian Geffon Cc: Cannon Matthews Cc: David Rientjes Cc: "Dr . David Alan Gilbert" Cc: Hugh Dickins Cc: Jerome Glisse Cc: Joe Perches Cc: Lokesh Gidra Cc: Michel Lespinasse Cc: Mike Rapoport Cc: Mina Almasry Cc: Oliver Upton Cc: Peter Xu Cc: Shaohua Li Cc: Shuah Khan Cc: Wang Qing Signed-off-by: Andrew Morton Signed-off-by: Stephen Rothwell (cherry picked from commit 0108aac75e6d6852e8bba20d5b94e29bf8dc9335 https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git akpm) Link: https://lore.kernel.org/patchwork/patch/1388145/ Conflicts: tools/testing/selftests/vm/userfaultfd.c (1. Manual rebase) Signed-off-by: Lokesh Gidra Bug: 160737021 Bug: 169683130 Change-Id: Icf57513cad6f6580114bc5452bfadc5e528434ed --- tools/testing/selftests/vm/userfaultfd.c | 247 ++++++++++++++--------- 1 file changed, 151 insertions(+), 96 deletions(-) diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 0c6df5b3c89b..470842187c89 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -87,7 +87,8 @@ 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; @@ -367,6 +368,146 @@ static struct uffd_test_ops hugetlb_uffd_test_ops = { static struct uffd_test_ops *uffd_test_ops; +static int userfaultfd_open(uint64_t *features) +{ + struct uffdio_api uffdio_api; + + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + 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 uffd_test_ctx_init_ext(uint64_t *features) +{ + unsigned long nr, cpu; + + 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 (uffd_test_ops->release_pages(area_src)) + return 1; + + if (uffd_test_ops->release_pages(area_dst)) + return 1; + + if (userfaultfd_open(features)) + 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; + } + } + + return 0; +} + +static inline int uffd_test_ctx_init(uint64_t features) +{ + return uffd_test_ctx_init_ext(&features); +} + +static inline int munmap_area(void **area) +{ + if (*area) { + if (munmap(*area, nr_pages * page_size)) { + perror("munmap"); + return 1; + } + } + + *area = NULL; + return 0; +} + +static int uffd_test_ctx_clear(void) +{ + int ret = 0; + size_t i; + + if (pipefd) { + for (i = 0; i < nr_cpus * 2; ++i) { + if (close(pipefd[i])) { + perror("close pipefd"); + ret = 1; + } + } + free(pipefd); + pipefd = NULL; + } + + if (count_verify) { + free(count_verify); + count_verify = NULL; + } + + if (uffd != -1) { + if (close(uffd)) { + perror("close uffd"); + ret = 1; + } + uffd = -1; + } + + huge_fd_off0 = NULL; + ret |= munmap_area((void **)&area_src); + ret |= munmap_area((void **)&area_src_alias); + ret |= munmap_area((void **)&area_dst); + ret |= munmap_area((void **)&area_dst_alias); + + return ret; +} + static int my_bcmp(char *str1, char *str2, size_t n) { unsigned long i; @@ -856,38 +997,6 @@ 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); - 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\n"); - return 1; - } - if (uffdio_api.api != UFFD_API) { - fprintf(stderr, "UFFDIO_API error %Lu\n", 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) @@ -1005,6 +1114,8 @@ static int faulting_process(int signal_test) perror("mremap"); exit(1); } + /* Reset area_src since we just clobbered it */ + area_src = NULL; for (; nr < nr_pages; nr++) { count = *area_count(area_dst, nr); @@ -1123,11 +1234,9 @@ static int userfaultfd_zeropage_test(void) printf("testing UFFDIO_ZEROPAGE: "); fflush(stdout); - if (uffd_test_ops->release_pages(area_dst)) + if (uffd_test_ctx_clear() || uffd_test_ctx_init(0)) return 1; - if (userfaultfd_open(0) < 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; @@ -1153,7 +1262,6 @@ static int userfaultfd_zeropage_test(void) } } - close(uffd); printf("done.\n"); return 0; } @@ -1171,13 +1279,11 @@ static int userfaultfd_events_test(void) printf("testing events (fork, remap, remove): "); fflush(stdout); - if (uffd_test_ops->release_pages(area_dst)) - return 1; - features = UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_EVENT_REMAP | UFFD_FEATURE_EVENT_REMOVE; - if (userfaultfd_open(features) < 0) + if (uffd_test_ctx_clear() || uffd_test_ctx_init(features)) return 1; + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); uffdio_register.range.start = (unsigned long) area_dst; @@ -1223,8 +1329,6 @@ 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; @@ -1244,12 +1348,10 @@ static int userfaultfd_sig_test(void) printf("testing signal delivery: "); fflush(stdout); - if (uffd_test_ops->release_pages(area_dst)) + features = UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_SIGBUS; + if (uffd_test_ctx_clear() || uffd_test_ctx_init(features)) return 1; - features = UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_SIGBUS; - if (userfaultfd_open(features) < 0) - return 1; fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); uffdio_register.range.start = (unsigned long) area_dst; @@ -1307,7 +1409,6 @@ static int userfaultfd_sig_test(void) if (userfaults) fprintf(stderr, "Signal test failed, userfaults: %ld\n", userfaults); - close(uffd); return userfaults != 0; } @@ -1329,10 +1430,7 @@ static int userfaultfd_minor_test(void) printf("testing minor faults: "); fflush(stdout); - if (uffd_test_ops->release_pages(area_dst)) - return 1; - - if (userfaultfd_open_ext(&features)) + if (uffd_test_ctx_clear() || uffd_test_ctx_init_ext(&features)) return 1; /* If kernel reports the feature isn't supported, skip the test. */ if (!(features & UFFD_FEATURE_MINOR_HUGETLBFS)) { @@ -1400,8 +1498,6 @@ 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; @@ -1413,51 +1509,11 @@ static int userfaultfd_stress(void) char *tmp_area; unsigned long nr; struct uffdio_register uffdio_register; - unsigned long cpu; int err; struct uffd_stats uffd_stats[nr_cpus]; - uffd_test_ops->allocate_area((void **)&area_src); - if (!area_src) + if (uffd_test_ctx_init(0)) return 1; - uffd_test_ops->allocate_area((void **)&area_dst); - if (!area_dst) - return 1; - - if (userfaultfd_open(0) < 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; - } - } if (posix_memalign(&area, page_size, page_size)) { fprintf(stderr, "out of memory\n"); @@ -1601,7 +1657,6 @@ static int userfaultfd_stress(void) if (err) return err; - close(uffd); return userfaultfd_zeropage_test() || userfaultfd_sig_test() || userfaultfd_events_test() || userfaultfd_minor_test(); }