diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-28 20:28:11 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-28 20:28:11 +0300 |
commit | 6e17c6de3ddf3073741d9c91a796ee696914d8a0 (patch) | |
tree | 2c425707f78642625dbe2c824c7fded2021e3dc7 /tools/testing/selftests/mm/gup_longterm.c | |
parent | 6aeadf7896bff4ca230702daba8788455e6b866e (diff) | |
parent | acc72d59c7509540c27c49625cb4b5a8db1f1a84 (diff) | |
download | linux-6e17c6de3ddf3073741d9c91a796ee696914d8a0.tar.xz |
Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull mm updates from Andrew Morton:
- Yosry Ahmed brought back some cgroup v1 stats in OOM logs
- Yosry has also eliminated cgroup's atomic rstat flushing
- Nhat Pham adds the new cachestat() syscall. It provides userspace
with the ability to query pagecache status - a similar concept to
mincore() but more powerful and with improved usability
- Mel Gorman provides more optimizations for compaction, reducing the
prevalence of page rescanning
- Lorenzo Stoakes has done some maintanance work on the
get_user_pages() interface
- Liam Howlett continues with cleanups and maintenance work to the
maple tree code. Peng Zhang also does some work on maple tree
- Johannes Weiner has done some cleanup work on the compaction code
- David Hildenbrand has contributed additional selftests for
get_user_pages()
- Thomas Gleixner has contributed some maintenance and optimization
work for the vmalloc code
- Baolin Wang has provided some compaction cleanups,
- SeongJae Park continues maintenance work on the DAMON code
- Huang Ying has done some maintenance on the swap code's usage of
device refcounting
- Christoph Hellwig has some cleanups for the filemap/directio code
- Ryan Roberts provides two patch series which yield some
rationalization of the kernel's access to pte entries - use the
provided APIs rather than open-coding accesses
- Lorenzo Stoakes has some fixes to the interaction between pagecache
and directio access to file mappings
- John Hubbard has a series of fixes to the MM selftesting code
- ZhangPeng continues the folio conversion campaign
- Hugh Dickins has been working on the pagetable handling code, mainly
with a view to reducing the load on the mmap_lock
- Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
from 128 to 8
- Domenico Cerasuolo has improved the zswap reclaim mechanism by
reorganizing the LRU management
- Matthew Wilcox provides some fixups to make gfs2 work better with the
buffer_head code
- Vishal Moola also has done some folio conversion work
- Matthew Wilcox has removed the remnants of the pagevec code - their
functionality is migrated over to struct folio_batch
* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
mm/hugetlb: remove hugetlb_set_page_subpool()
mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
hugetlb: revert use of page_cache_next_miss()
Revert "page cache: fix page_cache_next/prev_miss off by one"
mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
mm: memcg: rename and document global_reclaim()
mm: kill [add|del]_page_to_lru_list()
mm: compaction: convert to use a folio in isolate_migratepages_block()
mm: zswap: fix double invalidate with exclusive loads
mm: remove unnecessary pagevec includes
mm: remove references to pagevec
mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
mm: remove struct pagevec
net: convert sunrpc from pagevec to folio_batch
i915: convert i915_gpu_error to use a folio_batch
pagevec: rename fbatch_count()
mm: remove check_move_unevictable_pages()
drm: convert drm_gem_put_pages() to use a folio_batch
i915: convert shmem_sg_free_table() to use a folio_batch
scatterlist: add sg_set_folio()
...
Diffstat (limited to 'tools/testing/selftests/mm/gup_longterm.c')
-rw-r--r-- | tools/testing/selftests/mm/gup_longterm.c | 459 |
1 files changed, 459 insertions, 0 deletions
diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c new file mode 100644 index 000000000000..d33d3e68ffab --- /dev/null +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -0,0 +1,459 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * GUP long-term page pinning tests. + * + * Copyright 2023, Red Hat, Inc. + * + * Author(s): David Hildenbrand <david@redhat.com> + */ +#define _GNU_SOURCE +#include <stdlib.h> +#include <string.h> +#include <stdbool.h> +#include <stdint.h> +#include <unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <assert.h> +#include <sys/mman.h> +#include <sys/ioctl.h> +#include <sys/vfs.h> +#include <linux/magic.h> +#include <linux/memfd.h> + +#include "local_config.h" +#ifdef LOCAL_CONFIG_HAVE_LIBURING +#include <liburing.h> +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ + +#include "../../../../mm/gup_test.h" +#include "../kselftest.h" +#include "vm_util.h" + +static size_t pagesize; +static int nr_hugetlbsizes; +static size_t hugetlbsizes[10]; +static int gup_fd; + +static __fsword_t get_fs_type(int fd) +{ + struct statfs fs; + int ret; + + do { + ret = fstatfs(fd, &fs); + } while (ret && errno == EINTR); + + return ret ? 0 : fs.f_type; +} + +static bool fs_is_unknown(__fsword_t fs_type) +{ + /* + * We only support some filesystems in our tests when dealing with + * R/W long-term pinning. For these filesystems, we can be fairly sure + * whether they support it or not. + */ + switch (fs_type) { + case TMPFS_MAGIC: + case HUGETLBFS_MAGIC: + case BTRFS_SUPER_MAGIC: + case EXT4_SUPER_MAGIC: + case XFS_SUPER_MAGIC: + return false; + default: + return true; + } +} + +static bool fs_supports_writable_longterm_pinning(__fsword_t fs_type) +{ + assert(!fs_is_unknown(fs_type)); + switch (fs_type) { + case TMPFS_MAGIC: + case HUGETLBFS_MAGIC: + return true; + default: + return false; + } +} + +enum test_type { + TEST_TYPE_RO, + TEST_TYPE_RO_FAST, + TEST_TYPE_RW, + TEST_TYPE_RW_FAST, +#ifdef LOCAL_CONFIG_HAVE_LIBURING + TEST_TYPE_IOURING, +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ +}; + +static void do_test(int fd, size_t size, enum test_type type, bool shared) +{ + __fsword_t fs_type = get_fs_type(fd); + bool should_work; + char *mem; + int ret; + + if (ftruncate(fd, size)) { + ksft_test_result_fail("ftruncate() failed\n"); + return; + } + + if (fallocate(fd, 0, 0, size)) { + if (size == pagesize) + ksft_test_result_fail("fallocate() failed\n"); + else + ksft_test_result_skip("need more free huge pages\n"); + return; + } + + mem = mmap(NULL, size, PROT_READ | PROT_WRITE, + shared ? MAP_SHARED : MAP_PRIVATE, fd, 0); + if (mem == MAP_FAILED) { + if (size == pagesize || shared) + ksft_test_result_fail("mmap() failed\n"); + else + ksft_test_result_skip("need more free huge pages\n"); + return; + } + + /* + * Fault in the page writable such that GUP-fast can eventually pin + * it immediately. + */ + memset(mem, 0, size); + + switch (type) { + case TEST_TYPE_RO: + case TEST_TYPE_RO_FAST: + case TEST_TYPE_RW: + case TEST_TYPE_RW_FAST: { + struct pin_longterm_test args; + const bool fast = type == TEST_TYPE_RO_FAST || + type == TEST_TYPE_RW_FAST; + const bool rw = type == TEST_TYPE_RW || + type == TEST_TYPE_RW_FAST; + + if (gup_fd < 0) { + ksft_test_result_skip("gup_test not available\n"); + break; + } + + if (rw && shared && fs_is_unknown(fs_type)) { + ksft_test_result_skip("Unknown filesystem\n"); + return; + } + /* + * R/O pinning or pinning in a private mapping is always + * expected to work. Otherwise, we expect long-term R/W pinning + * to only succeed for special fielesystems. + */ + should_work = !shared || !rw || + fs_supports_writable_longterm_pinning(fs_type); + + args.addr = (__u64)(uintptr_t)mem; + args.size = size; + args.flags = fast ? PIN_LONGTERM_TEST_FLAG_USE_FAST : 0; + args.flags |= rw ? PIN_LONGTERM_TEST_FLAG_USE_WRITE : 0; + ret = ioctl(gup_fd, PIN_LONGTERM_TEST_START, &args); + if (ret && errno == EINVAL) { + ksft_test_result_skip("PIN_LONGTERM_TEST_START failed\n"); + break; + } else if (ret && errno == EFAULT) { + ksft_test_result(!should_work, "Should have failed\n"); + break; + } else if (ret) { + ksft_test_result_fail("PIN_LONGTERM_TEST_START failed\n"); + break; + } + + if (ioctl(gup_fd, PIN_LONGTERM_TEST_STOP)) + ksft_print_msg("[INFO] PIN_LONGTERM_TEST_STOP failed\n"); + + /* + * TODO: if the kernel ever supports long-term R/W pinning on + * some previously unsupported filesystems, we might want to + * perform some additional tests for possible data corruptions. + */ + ksft_test_result(should_work, "Should have worked\n"); + break; + } +#ifdef LOCAL_CONFIG_HAVE_LIBURING + case TEST_TYPE_IOURING: { + struct io_uring ring; + struct iovec iov; + + /* io_uring always pins pages writable. */ + if (shared && fs_is_unknown(fs_type)) { + ksft_test_result_skip("Unknown filesystem\n"); + return; + } + should_work = !shared || + fs_supports_writable_longterm_pinning(fs_type); + + /* Skip on errors, as we might just lack kernel support. */ + ret = io_uring_queue_init(1, &ring, 0); + if (ret < 0) { + ksft_test_result_skip("io_uring_queue_init() failed\n"); + break; + } + /* + * Register the range as a fixed buffer. This will FOLL_WRITE | + * FOLL_PIN | FOLL_LONGTERM the range. + */ + iov.iov_base = mem; + iov.iov_len = size; + ret = io_uring_register_buffers(&ring, &iov, 1); + /* Only new kernels return EFAULT. */ + if (ret && (errno == ENOSPC || errno == EOPNOTSUPP || + errno == EFAULT)) { + ksft_test_result(!should_work, "Should have failed\n"); + } else if (ret) { + /* + * We might just lack support or have insufficient + * MEMLOCK limits. + */ + ksft_test_result_skip("io_uring_register_buffers() failed\n"); + } else { + ksft_test_result(should_work, "Should have worked\n"); + io_uring_unregister_buffers(&ring); + } + + io_uring_queue_exit(&ring); + break; + } +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ + default: + assert(false); + } + + munmap(mem, size); +} + +typedef void (*test_fn)(int fd, size_t size); + +static void run_with_memfd(test_fn fn, const char *desc) +{ + int fd; + + ksft_print_msg("[RUN] %s ... with memfd\n", desc); + + fd = memfd_create("test", 0); + if (fd < 0) { + ksft_test_result_fail("memfd_create() failed\n"); + return; + } + + fn(fd, pagesize); + close(fd); +} + +static void run_with_tmpfile(test_fn fn, const char *desc) +{ + FILE *file; + int fd; + + ksft_print_msg("[RUN] %s ... with tmpfile\n", desc); + + file = tmpfile(); + if (!file) { + ksft_test_result_fail("tmpfile() failed\n"); + return; + } + + fd = fileno(file); + if (fd < 0) { + ksft_test_result_fail("fileno() failed\n"); + return; + } + + fn(fd, pagesize); + fclose(file); +} + +static void run_with_local_tmpfile(test_fn fn, const char *desc) +{ + char filename[] = __FILE__"_tmpfile_XXXXXX"; + int fd; + + ksft_print_msg("[RUN] %s ... with local tmpfile\n", desc); + + fd = mkstemp(filename); + if (fd < 0) { + ksft_test_result_fail("mkstemp() failed\n"); + return; + } + + if (unlink(filename)) { + ksft_test_result_fail("unlink() failed\n"); + goto close; + } + + fn(fd, pagesize); +close: + close(fd); +} + +static void run_with_memfd_hugetlb(test_fn fn, const char *desc, + size_t hugetlbsize) +{ + int flags = MFD_HUGETLB; + int fd; + + ksft_print_msg("[RUN] %s ... with memfd hugetlb (%zu kB)\n", desc, + hugetlbsize / 1024); + + flags |= __builtin_ctzll(hugetlbsize) << MFD_HUGE_SHIFT; + + fd = memfd_create("test", flags); + if (fd < 0) { + ksft_test_result_skip("memfd_create() failed\n"); + return; + } + + fn(fd, hugetlbsize); + close(fd); +} + +struct test_case { + const char *desc; + test_fn fn; +}; + +static void test_shared_rw_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW, true); +} + +static void test_shared_rw_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW_FAST, true); +} + +static void test_shared_ro_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO, true); +} + +static void test_shared_ro_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO_FAST, true); +} + +static void test_private_rw_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW, false); +} + +static void test_private_rw_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW_FAST, false); +} + +static void test_private_ro_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO, false); +} + +static void test_private_ro_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO_FAST, false); +} + +#ifdef LOCAL_CONFIG_HAVE_LIBURING +static void test_shared_iouring(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_IOURING, true); +} + +static void test_private_iouring(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_IOURING, false); +} +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ + +static const struct test_case test_cases[] = { + { + "R/W longterm GUP pin in MAP_SHARED file mapping", + test_shared_rw_pin, + }, + { + "R/W longterm GUP-fast pin in MAP_SHARED file mapping", + test_shared_rw_fast_pin, + }, + { + "R/O longterm GUP pin in MAP_SHARED file mapping", + test_shared_ro_pin, + }, + { + "R/O longterm GUP-fast pin in MAP_SHARED file mapping", + test_shared_ro_fast_pin, + }, + { + "R/W longterm GUP pin in MAP_PRIVATE file mapping", + test_private_rw_pin, + }, + { + "R/W longterm GUP-fast pin in MAP_PRIVATE file mapping", + test_private_rw_fast_pin, + }, + { + "R/O longterm GUP pin in MAP_PRIVATE file mapping", + test_private_ro_pin, + }, + { + "R/O longterm GUP-fast pin in MAP_PRIVATE file mapping", + test_private_ro_fast_pin, + }, +#ifdef LOCAL_CONFIG_HAVE_LIBURING + { + "io_uring fixed buffer with MAP_SHARED file mapping", + test_shared_iouring, + }, + { + "io_uring fixed buffer with MAP_PRIVATE file mapping", + test_private_iouring, + }, +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ +}; + +static void run_test_case(struct test_case const *test_case) +{ + int i; + + run_with_memfd(test_case->fn, test_case->desc); + run_with_tmpfile(test_case->fn, test_case->desc); + run_with_local_tmpfile(test_case->fn, test_case->desc); + for (i = 0; i < nr_hugetlbsizes; i++) + run_with_memfd_hugetlb(test_case->fn, test_case->desc, + hugetlbsizes[i]); +} + +static int tests_per_test_case(void) +{ + return 3 + nr_hugetlbsizes; +} + +int main(int argc, char **argv) +{ + int i, err; + + pagesize = getpagesize(); + nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes, + ARRAY_SIZE(hugetlbsizes)); + + ksft_print_header(); + ksft_set_plan(ARRAY_SIZE(test_cases) * tests_per_test_case()); + + gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) + run_test_case(&test_cases[i]); + + err = ksft_get_fail_cnt(); + if (err) + ksft_exit_fail_msg("%d out of %d tests failed\n", + err, ksft_test_num()); + return ksft_exit_pass(); +} |