diff options
Diffstat (limited to 'tools')
40 files changed, 1585 insertions, 326 deletions
diff --git a/tools/include/linux/atomic.h b/tools/include/linux/atomic.h index 01907b33537e..50c66ba9ada5 100644 --- a/tools/include/linux/atomic.h +++ b/tools/include/linux/atomic.h @@ -12,4 +12,26 @@ void atomic_long_set(atomic_long_t *v, long i); #define atomic_cmpxchg_release atomic_cmpxchg #endif /* atomic_cmpxchg_relaxed */ +static inline bool atomic_try_cmpxchg(atomic_t *ptr, int *oldp, int new) +{ + int ret, old = *oldp; + + ret = atomic_cmpxchg(ptr, old, new); + if (ret != old) + *oldp = ret; + return ret == old; +} + +static inline bool atomic_inc_unless_negative(atomic_t *v) +{ + int c = atomic_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!atomic_try_cmpxchg(v, &c, c + 1)); + + return true; +} + #endif /* __TOOLS_LINUX_ATOMIC_H */ diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 172700fb7784..05714c22994e 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -36327,13 +36327,18 @@ extern void test_kmem_cache_bulk(void); static inline void check_spanning_store_height(struct maple_tree *mt) { int index = 0; + int last = 140; MA_STATE(mas, mt, 0, 0); mas_lock(&mas); while (mt_height(mt) != 3) { mas_store_gfp(&mas, xa_mk_value(index), GFP_KERNEL); mas_set(&mas, ++index); } - mas_set_range(&mas, 90, 140); + + if (MAPLE_32BIT) + last = 155; /* 32 bit higher branching factor. */ + + mas_set_range(&mas, 90, last); mas_store_gfp(&mas, xa_mk_value(index), GFP_KERNEL); MT_BUG_ON(mt, mas_mt_height(&mas) != 2); mas_unlock(&mas); @@ -36428,6 +36433,7 @@ static void check_nomem_writer_race(struct maple_tree *mt) */ static inline int check_vma_modification(struct maple_tree *mt) { +#if defined(CONFIG_64BIT) MA_STATE(mas, mt, 0, 0); mtree_lock(mt); @@ -36451,6 +36457,8 @@ static inline int check_vma_modification(struct maple_tree *mt) mas_destroy(&mas); mtree_unlock(mt); +#endif + return 0; } diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 9a3499827d4b..2180c328a825 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -5,6 +5,7 @@ TEST_GEN_FILES += access_memory access_memory_even TEST_FILES = _damon_sysfs.py TEST_FILES += drgn_dump_damon_status.py +TEST_FILES += _common.sh # functionality tests TEST_PROGS += sysfs.sh @@ -18,6 +19,7 @@ TEST_PROGS += reclaim.sh lru_sort.sh TEST_PROGS += sysfs_update_removed_scheme_dir.sh TEST_PROGS += sysfs_update_schemes_tried_regions_hang.py TEST_PROGS += sysfs_memcg_path_leak.sh +TEST_PROGS += sysfs_no_op_commit_break.py EXTRA_CLEAN = __pycache__ diff --git a/tools/testing/selftests/damon/access_memory_even.c b/tools/testing/selftests/damon/access_memory_even.c index a9f4e9aaf3a9..93f3a71bcfd4 100644 --- a/tools/testing/selftests/damon/access_memory_even.c +++ b/tools/testing/selftests/damon/access_memory_even.c @@ -9,7 +9,6 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include <time.h> int main(int argc, char *argv[]) { diff --git a/tools/testing/selftests/damon/sysfs_no_op_commit_break.py b/tools/testing/selftests/damon/sysfs_no_op_commit_break.py new file mode 100755 index 000000000000..2c65cffe6b54 --- /dev/null +++ b/tools/testing/selftests/damon/sysfs_no_op_commit_break.py @@ -0,0 +1,72 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import json +import os +import subprocess +import sys + +import _damon_sysfs + +def dump_damon_status_dict(pid): + try: + subprocess.check_output(['which', 'drgn'], stderr=subprocess.DEVNULL) + except: + return None, 'drgn not found' + file_dir = os.path.dirname(os.path.abspath(__file__)) + dump_script = os.path.join(file_dir, 'drgn_dump_damon_status.py') + rc = subprocess.call(['drgn', dump_script, pid, 'damon_dump_output'], + stderr=subprocess.DEVNULL) + + if rc != 0: + return None, f'drgn fail: return code({rc})' + try: + with open('damon_dump_output', 'r') as f: + return json.load(f), None + except Exception as e: + return None, 'json.load fail (%s)' % e + +def main(): + kdamonds = _damon_sysfs.Kdamonds( + [_damon_sysfs.Kdamond( + contexts=[_damon_sysfs.DamonCtx( + schemes=[_damon_sysfs.Damos( + ops_filters=[ + _damon_sysfs.DamosFilter( + type_='anon', + matching=True, + allow=True, + ) + ] + )], + )])] + ) + + err = kdamonds.start() + if err is not None: + print('kdamond start failed: %s' % err) + exit(1) + + before_commit_status, err = \ + dump_damon_status_dict(kdamonds.kdamonds[0].pid) + if err is not None: + print('before-commit status dump failed: %s' % err) + exit(1) + + kdamonds.kdamonds[0].commit() + + after_commit_status, err = \ + dump_damon_status_dict(kdamonds.kdamonds[0].pid) + if err is not None: + print('after-commit status dump failed: %s' % err) + exit(1) + + if before_commit_status != after_commit_status: + print(f'before: {json.dumps(before_commit_status, indent=2)}') + print(f'after: {json.dumps(after_commit_status, indent=2)}') + exit(1) + + kdamonds.stop() + +if __name__ == '__main__': + main() diff --git a/tools/testing/selftests/kho/init.c b/tools/testing/selftests/kho/init.c index 8034e24c6bf6..6d9e91d55d68 100644 --- a/tools/testing/selftests/kho/init.c +++ b/tools/testing/selftests/kho/init.c @@ -1,22 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 -#ifndef NOLIBC -#include <errno.h> #include <stdio.h> #include <unistd.h> #include <fcntl.h> -#include <syscall.h> +#include <sys/syscall.h> #include <sys/mount.h> #include <sys/reboot.h> -#endif +#include <linux/kexec.h> /* from arch/x86/include/asm/setup.h */ #define COMMAND_LINE_SIZE 2048 -/* from include/linux/kexex.h */ -#define KEXEC_FILE_NO_INITRAMFS 0x00000004 - -#define KHO_FINILIZE "/debugfs/kho/out/finalize" +#define KHO_FINALIZE "/debugfs/kho/out/finalize" #define KERNEL_IMAGE "/kernel" static int mount_filesystems(void) @@ -32,7 +27,7 @@ static int kho_enable(void) const char enable[] = "1"; int fd; - fd = open(KHO_FINILIZE, O_RDWR); + fd = open(KHO_FINALIZE, O_RDWR); if (fd < 0) return -1; diff --git a/tools/testing/selftests/kho/vmtest.sh b/tools/testing/selftests/kho/vmtest.sh index ec70a17bd476..3f6c17166846 100755 --- a/tools/testing/selftests/kho/vmtest.sh +++ b/tools/testing/selftests/kho/vmtest.sh @@ -10,7 +10,6 @@ kernel_dir=$(realpath "$test_dir/../../../..") tmp_dir=$(mktemp -d /tmp/kho-test.XXXXXXXX) headers_dir="$tmp_dir/usr" -initrd_dir="$tmp_dir/initrd" initrd="$tmp_dir/initrd.cpio" source "$test_dir/../kselftest/ktap_helpers.sh" @@ -81,19 +80,22 @@ EOF function mkinitrd() { local kernel=$1 - mkdir -p "$initrd_dir"/{dev,debugfs,proc} - sudo mknod "$initrd_dir/dev/console" c 5 1 - - "$CROSS_COMPILE"gcc -s -static -Os -nostdinc -I"$headers_dir/include" \ - -fno-asynchronous-unwind-tables -fno-ident -nostdlib \ - -include "$test_dir/../../../include/nolibc/nolibc.h" \ - -o "$initrd_dir/init" "$test_dir/init.c" \ - - cp "$kernel" "$initrd_dir/kernel" + "$CROSS_COMPILE"gcc -s -static -Os -nostdinc -nostdlib \ + -fno-asynchronous-unwind-tables -fno-ident \ + -I "$headers_dir/include" \ + -I "$kernel_dir/tools/include/nolibc" \ + -o "$tmp_dir/init" "$test_dir/init.c" + + cat > "$tmp_dir/cpio_list" <<EOF +dir /dev 0755 0 0 +dir /proc 0755 0 0 +dir /debugfs 0755 0 0 +nod /dev/console 0600 0 0 c 5 1 +file /init $tmp_dir/init 0755 0 0 +file /kernel $kernel 0644 0 0 +EOF - pushd "$initrd_dir" &>/dev/null - find . | cpio -H newc --create > "$initrd" 2>/dev/null - popd &>/dev/null + "$build_dir/usr/gen_init_cpio" "$tmp_dir/cpio_list" > "$initrd" } function run_qemu() { diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index c3b6d2604b1e..661d31c4b558 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -92,6 +92,10 @@ #endif #define __printf(a, b) __attribute__((format(printf, a, b))) +#ifndef __maybe_unused +#define __maybe_unused __attribute__((__unused__)) +#endif + /* counters */ struct ksft_count { unsigned int ksft_pass; diff --git a/tools/testing/selftests/landlock/audit.h b/tools/testing/selftests/landlock/audit.h index b16986aa6442..02fd1393947a 100644 --- a/tools/testing/selftests/landlock/audit.h +++ b/tools/testing/selftests/landlock/audit.h @@ -20,14 +20,12 @@ #include <sys/time.h> #include <unistd.h> +#include "../kselftest.h" + #ifndef ARRAY_SIZE #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) #endif -#ifndef __maybe_unused -#define __maybe_unused __attribute__((__unused__)) -#endif - #define REGEX_LANDLOCK_PREFIX "^audit([0-9.:]\\+): domain=\\([0-9a-f]\\+\\)" struct audit_filter { diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h index 88a3c78f5d98..9acecae36f51 100644 --- a/tools/testing/selftests/landlock/common.h +++ b/tools/testing/selftests/landlock/common.h @@ -22,10 +22,6 @@ #define TMP_DIR "tmp" -#ifndef __maybe_unused -#define __maybe_unused __attribute__((__unused__)) -#endif - /* TEST_F_FORK() should not be used for new tests. */ #define TEST_F_FORK(fixture_name, test_name) TEST_F(fixture_name, test_name) diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index e7b23a8a05fe..c2a8586e51a1 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -58,3 +58,5 @@ pkey_sighandler_tests_32 pkey_sighandler_tests_64 guard-regions merge +prctl_thp_disable +rmap diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index d13b3cef2a2b..5a1dee50b898 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -86,6 +86,7 @@ TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += pfnmap TEST_GEN_FILES += process_madv +TEST_GEN_FILES += prctl_thp_disable TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += uffd-stress @@ -101,6 +102,7 @@ TEST_GEN_FILES += hugetlb_dio TEST_GEN_FILES += droppable TEST_GEN_FILES += guard-regions TEST_GEN_FILES += merge +TEST_GEN_FILES += rmap ifneq ($(ARCH),arm64) TEST_GEN_FILES += soft-dirty @@ -228,6 +230,8 @@ $(OUTPUT)/ksm_tests: LDLIBS += -lnuma $(OUTPUT)/migration: LDLIBS += -lnuma +$(OUTPUT)/rmap: LDLIBS += -lnuma + local_config.mk local_config.h: check_config.sh /bin/sh ./check_config.sh $(CC) diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index c744c603d688..6560c26f47d1 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -41,11 +41,6 @@ static size_t hugetlbsizes[10]; static int gup_fd; static bool has_huge_zeropage; -static int sz2ord(size_t size) -{ - return __builtin_ctzll(size / pagesize); -} - static int detect_thp_sizes(size_t sizes[], int max) { int count = 0; @@ -57,7 +52,7 @@ static int detect_thp_sizes(size_t sizes[], int max) if (!pmdsize) return 0; - orders = 1UL << sz2ord(pmdsize); + orders = 1UL << sz2ord(pmdsize, pagesize); orders |= thp_supported_orders(); for (i = 0; orders && count < max; i++) { @@ -1216,8 +1211,8 @@ static void run_anon_test_case(struct test_case const *test_case) size_t size = thpsizes[i]; struct thp_settings settings = *thp_current_settings(); - settings.hugepages[sz2ord(pmdsize)].enabled = THP_NEVER; - settings.hugepages[sz2ord(size)].enabled = THP_ALWAYS; + settings.hugepages[sz2ord(pmdsize, pagesize)].enabled = THP_NEVER; + settings.hugepages[sz2ord(size, pagesize)].enabled = THP_ALWAYS; thp_push_settings(&settings); if (size == pmdsize) { @@ -1868,7 +1863,7 @@ int main(int argc, char **argv) if (pmdsize) { /* Only if THP is supported. */ thp_read_settings(&default_settings); - default_settings.hugepages[sz2ord(pmdsize)].enabled = THP_INHERIT; + default_settings.hugepages[sz2ord(pmdsize, pagesize)].enabled = THP_INHERIT; thp_save_settings(); thp_push_settings(&default_settings); diff --git a/tools/testing/selftests/mm/hugepage-mremap.c b/tools/testing/selftests/mm/hugepage-mremap.c index c463d1c09c9b..2bd1dac75c3f 100644 --- a/tools/testing/selftests/mm/hugepage-mremap.c +++ b/tools/testing/selftests/mm/hugepage-mremap.c @@ -65,10 +65,20 @@ static void register_region_with_uffd(char *addr, size_t len) struct uffdio_api uffdio_api; /* Create and enable userfaultfd object. */ - uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); - if (uffd == -1) - ksft_exit_fail_msg("userfaultfd: %s\n", strerror(errno)); + if (uffd == -1) { + switch (errno) { + case EPERM: + ksft_exit_skip("Insufficient permissions, try running as root.\n"); + break; + case ENOSYS: + ksft_exit_skip("userfaultfd is not supported/not enabled.\n"); + break; + default: + ksft_exit_fail_msg("userfaultfd failed with %s\n", strerror(errno)); + break; + } + } uffdio_api.api = UFFD_API; uffdio_api.features = 0; diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index d8bd1911dfc0..712f43c87736 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -38,14 +38,11 @@ enum ksm_merge_mode { }; static int mem_fd; -static int ksm_fd; -static int ksm_full_scans_fd; -static int proc_self_ksm_stat_fd; -static int proc_self_ksm_merging_pages_fd; -static int ksm_use_zero_pages_fd; static int pagemap_fd; static size_t pagesize; +static void init_global_file_handles(void); + static bool range_maps_duplicates(char *addr, unsigned long size) { unsigned long offs_a, offs_b, pfn_a, pfn_b; @@ -73,88 +70,6 @@ static bool range_maps_duplicates(char *addr, unsigned long size) return false; } -static long get_my_ksm_zero_pages(void) -{ - char buf[200]; - char *substr_ksm_zero; - size_t value_pos; - ssize_t read_size; - unsigned long my_ksm_zero_pages; - - if (!proc_self_ksm_stat_fd) - return 0; - - read_size = pread(proc_self_ksm_stat_fd, buf, sizeof(buf) - 1, 0); - if (read_size < 0) - return -errno; - - buf[read_size] = 0; - - substr_ksm_zero = strstr(buf, "ksm_zero_pages"); - if (!substr_ksm_zero) - return 0; - - value_pos = strcspn(substr_ksm_zero, "0123456789"); - my_ksm_zero_pages = strtol(substr_ksm_zero + value_pos, NULL, 10); - - return my_ksm_zero_pages; -} - -static long get_my_merging_pages(void) -{ - char buf[10]; - ssize_t ret; - - if (proc_self_ksm_merging_pages_fd < 0) - return proc_self_ksm_merging_pages_fd; - - ret = pread(proc_self_ksm_merging_pages_fd, buf, sizeof(buf) - 1, 0); - if (ret <= 0) - return -errno; - buf[ret] = 0; - - return strtol(buf, NULL, 10); -} - -static long ksm_get_full_scans(void) -{ - char buf[10]; - ssize_t ret; - - ret = pread(ksm_full_scans_fd, buf, sizeof(buf) - 1, 0); - if (ret <= 0) - return -errno; - buf[ret] = 0; - - return strtol(buf, NULL, 10); -} - -static int ksm_merge(void) -{ - long start_scans, end_scans; - - /* Wait for two full scans such that any possible merging happened. */ - start_scans = ksm_get_full_scans(); - if (start_scans < 0) - return start_scans; - if (write(ksm_fd, "1", 1) != 1) - return -errno; - do { - end_scans = ksm_get_full_scans(); - if (end_scans < 0) - return end_scans; - } while (end_scans < start_scans + 2); - - return 0; -} - -static int ksm_unmerge(void) -{ - if (write(ksm_fd, "2", 1) != 1) - return -errno; - return 0; -} - static char *__mmap_and_merge_range(char val, unsigned long size, int prot, enum ksm_merge_mode mode) { @@ -163,12 +78,12 @@ static char *__mmap_and_merge_range(char val, unsigned long size, int prot, int ret; /* Stabilize accounting by disabling KSM completely. */ - if (ksm_unmerge()) { + if (ksm_stop() < 0) { ksft_print_msg("Disabling (unmerging) KSM failed\n"); return err_map; } - if (get_my_merging_pages() > 0) { + if (ksm_get_self_merging_pages() > 0) { ksft_print_msg("Still pages merged\n"); return err_map; } @@ -218,7 +133,7 @@ static char *__mmap_and_merge_range(char val, unsigned long size, int prot, } /* Run KSM to trigger merging and wait. */ - if (ksm_merge()) { + if (ksm_start() < 0) { ksft_print_msg("Running KSM failed\n"); goto unmap; } @@ -227,7 +142,7 @@ static char *__mmap_and_merge_range(char val, unsigned long size, int prot, * Check if anything was merged at all. Ignore the zero page that is * accounted differently (depending on kernel support). */ - if (val && !get_my_merging_pages()) { + if (val && !ksm_get_self_merging_pages()) { ksft_print_msg("No pages got merged\n"); goto unmap; } @@ -274,6 +189,7 @@ static void test_unmerge(void) ksft_test_result(!range_maps_duplicates(map, size), "Pages were unmerged\n"); unmap: + ksm_stop(); munmap(map, size); } @@ -286,15 +202,12 @@ static void test_unmerge_zero_pages(void) ksft_print_msg("[RUN] %s\n", __func__); - if (proc_self_ksm_stat_fd < 0) { - ksft_test_result_skip("open(\"/proc/self/ksm_stat\") failed\n"); - return; - } - if (ksm_use_zero_pages_fd < 0) { - ksft_test_result_skip("open \"/sys/kernel/mm/ksm/use_zero_pages\" failed\n"); + if (ksm_get_self_zero_pages() < 0) { + ksft_test_result_skip("accessing \"/proc/self/ksm_stat\" failed\n"); return; } - if (write(ksm_use_zero_pages_fd, "1", 1) != 1) { + + if (ksm_use_zero_pages() < 0) { ksft_test_result_skip("write \"/sys/kernel/mm/ksm/use_zero_pages\" failed\n"); return; } @@ -306,7 +219,7 @@ static void test_unmerge_zero_pages(void) /* Check if ksm_zero_pages is updated correctly after KSM merging */ pages_expected = size / pagesize; - if (pages_expected != get_my_ksm_zero_pages()) { + if (pages_expected != ksm_get_self_zero_pages()) { ksft_test_result_fail("'ksm_zero_pages' updated after merging\n"); goto unmap; } @@ -319,7 +232,7 @@ static void test_unmerge_zero_pages(void) /* Check if ksm_zero_pages is updated correctly after unmerging */ pages_expected /= 2; - if (pages_expected != get_my_ksm_zero_pages()) { + if (pages_expected != ksm_get_self_zero_pages()) { ksft_test_result_fail("'ksm_zero_pages' updated after unmerging\n"); goto unmap; } @@ -329,7 +242,7 @@ static void test_unmerge_zero_pages(void) *((unsigned int *)&map[offs]) = offs; /* Now we should have no zeropages remaining. */ - if (get_my_ksm_zero_pages()) { + if (ksm_get_self_zero_pages()) { ksft_test_result_fail("'ksm_zero_pages' updated after write fault\n"); goto unmap; } @@ -338,6 +251,7 @@ static void test_unmerge_zero_pages(void) ksft_test_result(!range_maps_duplicates(map, size), "KSM zero pages were unmerged\n"); unmap: + ksm_stop(); munmap(map, size); } @@ -366,6 +280,7 @@ static void test_unmerge_discarded(void) ksft_test_result(!range_maps_duplicates(map, size), "Pages were unmerged\n"); unmap: + ksm_stop(); munmap(map, size); } @@ -452,6 +367,7 @@ static void test_unmerge_uffd_wp(void) close_uffd: close(uffd); unmap: + ksm_stop(); munmap(map, size); } #endif @@ -506,27 +422,30 @@ static int test_child_ksm(void) /* Test if KSM is enabled for the process. */ if (prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0) != 1) - return -1; + return 1; /* Test if merge could really happen. */ map = __mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_NONE); if (map == MAP_MERGE_FAIL) - return -2; + return 2; else if (map == MAP_MERGE_SKIP) - return -3; + return 3; + ksm_stop(); munmap(map, size); return 0; } static void test_child_ksm_err(int status) { - if (status == -1) + if (status == 1) ksft_test_result_fail("unexpected PR_GET_MEMORY_MERGE result in child\n"); - else if (status == -2) + else if (status == 2) ksft_test_result_fail("Merge in child failed\n"); - else if (status == -3) + else if (status == 3) ksft_test_result_skip("Merge in child skipped\n"); + else if (status == 4) + ksft_test_result_fail("Binary not found\n"); } /* Verify that prctl ksm flag is inherited. */ @@ -548,6 +467,7 @@ static void test_prctl_fork(void) child_pid = fork(); if (!child_pid) { + init_global_file_handles(); exit(test_child_ksm()); } else if (child_pid < 0) { ksft_test_result_fail("fork() failed\n"); @@ -595,10 +515,10 @@ static void test_prctl_fork_exec(void) return; } else if (child_pid == 0) { char *prg_name = "./ksm_functional_tests"; - char *argv_for_program[] = { prg_name, FORK_EXEC_CHILD_PRG_NAME }; + char *argv_for_program[] = { prg_name, FORK_EXEC_CHILD_PRG_NAME, NULL }; execv(prg_name, argv_for_program); - return; + exit(4); } if (waitpid(child_pid, &status, 0) > 0) { @@ -644,6 +564,7 @@ static void test_prctl_unmerge(void) ksft_test_result(!range_maps_duplicates(map, size), "Pages were unmerged\n"); unmap: + ksm_stop(); munmap(map, size); } @@ -677,6 +598,7 @@ static void test_prot_none(void) ksft_test_result(!range_maps_duplicates(map, size), "Pages were unmerged\n"); unmap: + ksm_stop(); munmap(map, size); } @@ -685,19 +607,15 @@ static void init_global_file_handles(void) mem_fd = open("/proc/self/mem", O_RDWR); if (mem_fd < 0) ksft_exit_fail_msg("opening /proc/self/mem failed\n"); - ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR); - if (ksm_fd < 0) - ksft_exit_skip("open(\"/sys/kernel/mm/ksm/run\") failed\n"); - ksm_full_scans_fd = open("/sys/kernel/mm/ksm/full_scans", O_RDONLY); - if (ksm_full_scans_fd < 0) - ksft_exit_skip("open(\"/sys/kernel/mm/ksm/full_scans\") failed\n"); + if (ksm_stop() < 0) + ksft_exit_skip("accessing \"/sys/kernel/mm/ksm/run\") failed\n"); + if (ksm_get_full_scans() < 0) + ksft_exit_skip("accessing \"/sys/kernel/mm/ksm/full_scans\") failed\n"); pagemap_fd = open("/proc/self/pagemap", O_RDONLY); if (pagemap_fd < 0) ksft_exit_skip("open(\"/proc/self/pagemap\") failed\n"); - proc_self_ksm_stat_fd = open("/proc/self/ksm_stat", O_RDONLY); - proc_self_ksm_merging_pages_fd = open("/proc/self/ksm_merging_pages", - O_RDONLY); - ksm_use_zero_pages_fd = open("/sys/kernel/mm/ksm/use_zero_pages", O_RDWR); + if (ksm_get_self_merging_pages() < 0) + ksft_exit_skip("accessing \"/proc/self/ksm_merging_pages\") failed\n"); } int main(int argc, char **argv) diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 5bd52a951cbd..bf2863b102e3 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -846,7 +846,7 @@ static void mremap_move_multi_invalid_vmas(FILE *maps_fp, } if (err != EFAULT) { errno = err; - perror("mrmeap() unexpected error"); + perror("mremap() unexpected error"); success = false; goto out_unmap; } @@ -899,7 +899,7 @@ static void mremap_move_multi_invalid_vmas(FILE *maps_fp, } if (err != EFAULT) { errno = err; - perror("mrmeap() unexpected error"); + perror("mremap() unexpected error"); success = false; goto out_unmap; } @@ -948,7 +948,7 @@ static void mremap_move_multi_invalid_vmas(FILE *maps_fp, } if (err != EFAULT) { errno = err; - perror("mrmeap() unexpected error"); + perror("mremap() unexpected error"); success = false; goto out_unmap; } diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index e6face7c0166..4fc8e578ec7c 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -209,7 +209,7 @@ int userfaultfd_tests(void) wp_addr_range(mem, mem_size); vec_size = mem_size/page_size; - vec = malloc(sizeof(struct page_region) * vec_size); + vec = calloc(vec_size, sizeof(struct page_region)); written = pagemap_ioctl(mem, mem_size, vec, 1, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, vec_size - 2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); @@ -247,11 +247,11 @@ int sanity_tests_sd(void) vec_size = num_pages/2; mem_size = num_pages * page_size; - vec = malloc(sizeof(struct page_region) * vec_size); + vec = calloc(vec_size, sizeof(struct page_region)); if (!vec) ksft_exit_fail_msg("error nomem\n"); - vec2 = malloc(sizeof(struct page_region) * vec_size); + vec2 = calloc(vec_size, sizeof(struct page_region)); if (!vec2) ksft_exit_fail_msg("error nomem\n"); @@ -436,7 +436,7 @@ int sanity_tests_sd(void) mem_size = 1050 * page_size; vec_size = mem_size/(page_size*2); - vec = malloc(sizeof(struct page_region) * vec_size); + vec = calloc(vec_size, sizeof(struct page_region)); if (!vec) ksft_exit_fail_msg("error nomem\n"); @@ -491,7 +491,7 @@ int sanity_tests_sd(void) mem_size = 10000 * page_size; vec_size = 50; - vec = malloc(sizeof(struct page_region) * vec_size); + vec = calloc(vec_size, sizeof(struct page_region)); if (!vec) ksft_exit_fail_msg("error nomem\n"); @@ -541,7 +541,7 @@ int sanity_tests_sd(void) vec_size = 1000; mem_size = vec_size * page_size; - vec = malloc(sizeof(struct page_region) * vec_size); + vec = calloc(vec_size, sizeof(struct page_region)); if (!vec) ksft_exit_fail_msg("error nomem\n"); @@ -695,8 +695,8 @@ int base_tests(char *prefix, char *mem, unsigned long long mem_size, int skip) } vec_size = mem_size/page_size; - vec = malloc(sizeof(struct page_region) * vec_size); - vec2 = malloc(sizeof(struct page_region) * vec_size); + vec = calloc(vec_size, sizeof(struct page_region)); + vec2 = calloc(vec_size, sizeof(struct page_region)); /* 1. all new pages must be not be written (dirty) */ written = pagemap_ioctl(mem, mem_size, vec, 1, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, @@ -807,8 +807,8 @@ int hpage_unit_tests(void) unsigned long long vec_size = map_size/page_size; struct page_region *vec, *vec2; - vec = malloc(sizeof(struct page_region) * vec_size); - vec2 = malloc(sizeof(struct page_region) * vec_size); + vec = calloc(vec_size, sizeof(struct page_region)); + vec2 = calloc(vec_size, sizeof(struct page_region)); if (!vec || !vec2) ksft_exit_fail_msg("malloc failed\n"); @@ -997,7 +997,7 @@ int unmapped_region_tests(void) void *start = (void *)0x10000000; int written, len = 0x00040000; long vec_size = len / page_size; - struct page_region *vec = malloc(sizeof(struct page_region) * vec_size); + struct page_region *vec = calloc(vec_size, sizeof(struct page_region)); /* 1. Get written pages */ written = pagemap_ioctl(start, len, vec, vec_size, 0, 0, @@ -1062,7 +1062,7 @@ int sanity_tests(void) mem_size = 10 * page_size; vec_size = mem_size / page_size; - vec = malloc(sizeof(struct page_region) * vec_size); + vec = calloc(vec_size, sizeof(struct page_region)); mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0); if (mem == MAP_FAILED || vec == MAP_FAILED) ksft_exit_fail_msg("error nomem\n"); diff --git a/tools/testing/selftests/mm/pfnmap.c b/tools/testing/selftests/mm/pfnmap.c index 866ac023baf5..88659f0a90ea 100644 --- a/tools/testing/selftests/mm/pfnmap.c +++ b/tools/testing/selftests/mm/pfnmap.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Basic VM_PFNMAP tests relying on mmap() of '/dev/mem' + * Basic VM_PFNMAP tests relying on mmap() of input file provided. + * Use '/dev/mem' as default. * * Copyright 2025, Red Hat, Inc. * @@ -25,6 +26,7 @@ #include "vm_util.h" static sigjmp_buf sigjmp_buf_env; +static char *file = "/dev/mem"; static void signal_handler(int sig) { @@ -51,7 +53,7 @@ static int test_read_access(char *addr, size_t size, size_t pagesize) return ret; } -static int find_ram_target(off_t *phys_addr, +static int find_ram_target(off_t *offset, unsigned long long pagesize) { unsigned long long start, end; @@ -91,7 +93,7 @@ static int find_ram_target(off_t *phys_addr, /* We need two pages. */ if (end > start + 2 * pagesize) { fclose(file); - *phys_addr = start; + *offset = start; return 0; } } @@ -100,7 +102,7 @@ static int find_ram_target(off_t *phys_addr, FIXTURE(pfnmap) { - off_t phys_addr; + off_t offset; size_t pagesize; int dev_mem_fd; char *addr1; @@ -113,23 +115,31 @@ FIXTURE_SETUP(pfnmap) { self->pagesize = getpagesize(); - /* We'll require two physical pages throughout our tests ... */ - if (find_ram_target(&self->phys_addr, self->pagesize)) - SKIP(return, "Cannot find ram target in '/proc/iomem'\n"); + if (strncmp(file, "/dev/mem", strlen("/dev/mem")) == 0) { + /* We'll require two physical pages throughout our tests ... */ + if (find_ram_target(&self->offset, self->pagesize)) + SKIP(return, + "Cannot find ram target in '/proc/iomem'\n"); + } else { + self->offset = 0; + } - self->dev_mem_fd = open("/dev/mem", O_RDONLY); + self->dev_mem_fd = open(file, O_RDONLY); if (self->dev_mem_fd < 0) - SKIP(return, "Cannot open '/dev/mem'\n"); + SKIP(return, "Cannot open '%s'\n", file); self->size1 = self->pagesize * 2; self->addr1 = mmap(NULL, self->size1, PROT_READ, MAP_SHARED, - self->dev_mem_fd, self->phys_addr); + self->dev_mem_fd, self->offset); if (self->addr1 == MAP_FAILED) - SKIP(return, "Cannot mmap '/dev/mem'\n"); + SKIP(return, "Cannot mmap '%s'\n", file); + + if (!check_vmflag_pfnmap(self->addr1)) + SKIP(return, "Invalid file: '%s'. Not pfnmap'ed\n", file); /* ... and want to be able to read from them. */ if (test_read_access(self->addr1, self->size1, self->pagesize)) - SKIP(return, "Cannot read-access mmap'ed '/dev/mem'\n"); + SKIP(return, "Cannot read-access mmap'ed '%s'\n", file); self->size2 = 0; self->addr2 = MAP_FAILED; @@ -182,7 +192,7 @@ TEST_F(pfnmap, munmap_split) */ self->size2 = self->pagesize; self->addr2 = mmap(NULL, self->pagesize, PROT_READ, MAP_SHARED, - self->dev_mem_fd, self->phys_addr); + self->dev_mem_fd, self->offset); ASSERT_NE(self->addr2, MAP_FAILED); } @@ -246,4 +256,14 @@ TEST_F(pfnmap, fork) ASSERT_EQ(ret, 0); } -TEST_HARNESS_MAIN +int main(int argc, char **argv) +{ + for (int i = 1; i < argc; i++) { + if (strcmp(argv[i], "--") == 0) { + if (i + 1 < argc && strlen(argv[i + 1]) > 0) + file = argv[i + 1]; + return test_harness_run(i, argv); + } + } + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/mm/pkey-helpers.h b/tools/testing/selftests/mm/pkey-helpers.h index ea404f80e6cb..fa15f006fa68 100644 --- a/tools/testing/selftests/mm/pkey-helpers.h +++ b/tools/testing/selftests/mm/pkey-helpers.h @@ -84,9 +84,6 @@ extern void abort_hooks(void); #ifndef noinline # define noinline __attribute__((noinline)) #endif -#ifndef __maybe_unused -# define __maybe_unused __attribute__((__unused__)) -#endif int sys_pkey_alloc(unsigned long flags, unsigned long init_val); int sys_pkey_free(unsigned long pkey); diff --git a/tools/testing/selftests/mm/prctl_thp_disable.c b/tools/testing/selftests/mm/prctl_thp_disable.c new file mode 100644 index 000000000000..84b4a4b345af --- /dev/null +++ b/tools/testing/selftests/mm/prctl_thp_disable.c @@ -0,0 +1,291 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Basic tests for PR_GET/SET_THP_DISABLE prctl calls + * + * Author(s): Usama Arif <usamaarif642@gmail.com> + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/mman.h> +#include <linux/mman.h> +#include <sys/prctl.h> +#include <sys/wait.h> + +#include "../kselftest_harness.h" +#include "thp_settings.h" +#include "vm_util.h" + +#ifndef PR_THP_DISABLE_EXCEPT_ADVISED +#define PR_THP_DISABLE_EXCEPT_ADVISED (1 << 1) +#endif + +enum thp_collapse_type { + THP_COLLAPSE_NONE, + THP_COLLAPSE_MADV_NOHUGEPAGE, + THP_COLLAPSE_MADV_HUGEPAGE, /* MADV_HUGEPAGE before access */ + THP_COLLAPSE_MADV_COLLAPSE, /* MADV_COLLAPSE after access */ +}; + +/* + * Function to mmap a buffer, fault it in, madvise it appropriately (before + * page fault for MADV_HUGE, and after for MADV_COLLAPSE), and check if the + * mmap region is huge. + * Returns: + * 0 if test doesn't give hugepage + * 1 if test gives a hugepage + * -errno if mmap fails + */ +static int test_mmap_thp(enum thp_collapse_type madvise_buf, size_t pmdsize) +{ + char *mem, *mmap_mem; + size_t mmap_size; + int ret; + + /* For alignment purposes, we need twice the THP size. */ + mmap_size = 2 * pmdsize; + mmap_mem = (char *)mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (mmap_mem == MAP_FAILED) + return -errno; + + /* We need a THP-aligned memory area. */ + mem = (char *)(((uintptr_t)mmap_mem + pmdsize) & ~(pmdsize - 1)); + + if (madvise_buf == THP_COLLAPSE_MADV_HUGEPAGE) + madvise(mem, pmdsize, MADV_HUGEPAGE); + else if (madvise_buf == THP_COLLAPSE_MADV_NOHUGEPAGE) + madvise(mem, pmdsize, MADV_NOHUGEPAGE); + + /* Ensure memory is allocated */ + memset(mem, 1, pmdsize); + + if (madvise_buf == THP_COLLAPSE_MADV_COLLAPSE) + madvise(mem, pmdsize, MADV_COLLAPSE); + + /* HACK: make sure we have a separate VMA that we can check reliably. */ + mprotect(mem, pmdsize, PROT_READ); + + ret = check_huge_anon(mem, 1, pmdsize); + munmap(mmap_mem, mmap_size); + return ret; +} + +static void prctl_thp_disable_completely_test(struct __test_metadata *const _metadata, + size_t pmdsize, + enum thp_enabled thp_policy) +{ + ASSERT_EQ(prctl(PR_GET_THP_DISABLE, NULL, NULL, NULL, NULL), 1); + + /* tests after prctl overrides global policy */ + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 0); + + /* Reset to global policy */ + ASSERT_EQ(prctl(PR_SET_THP_DISABLE, 0, NULL, NULL, NULL), 0); + + /* tests after prctl is cleared, and only global policy is effective */ + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize), + thp_policy == THP_ALWAYS ? 1 : 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize), + thp_policy == THP_NEVER ? 0 : 1); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 1); +} + +FIXTURE(prctl_thp_disable_completely) +{ + struct thp_settings settings; + size_t pmdsize; +}; + +FIXTURE_VARIANT(prctl_thp_disable_completely) +{ + enum thp_enabled thp_policy; +}; + +FIXTURE_VARIANT_ADD(prctl_thp_disable_completely, never) +{ + .thp_policy = THP_NEVER, +}; + +FIXTURE_VARIANT_ADD(prctl_thp_disable_completely, madvise) +{ + .thp_policy = THP_MADVISE, +}; + +FIXTURE_VARIANT_ADD(prctl_thp_disable_completely, always) +{ + .thp_policy = THP_ALWAYS, +}; + +FIXTURE_SETUP(prctl_thp_disable_completely) +{ + if (!thp_available()) + SKIP(return, "Transparent Hugepages not available\n"); + + self->pmdsize = read_pmd_pagesize(); + if (!self->pmdsize) + SKIP(return, "Unable to read PMD size\n"); + + if (prctl(PR_SET_THP_DISABLE, 1, NULL, NULL, NULL)) + SKIP(return, "Unable to disable THPs completely for the process\n"); + + thp_save_settings(); + thp_read_settings(&self->settings); + self->settings.thp_enabled = variant->thp_policy; + self->settings.hugepages[sz2ord(self->pmdsize, getpagesize())].enabled = THP_INHERIT; + thp_write_settings(&self->settings); +} + +FIXTURE_TEARDOWN(prctl_thp_disable_completely) +{ + thp_restore_settings(); +} + +TEST_F(prctl_thp_disable_completely, nofork) +{ + prctl_thp_disable_completely_test(_metadata, self->pmdsize, variant->thp_policy); +} + +TEST_F(prctl_thp_disable_completely, fork) +{ + int ret = 0; + pid_t pid; + + /* Make sure prctl changes are carried across fork */ + pid = fork(); + ASSERT_GE(pid, 0); + + if (!pid) { + prctl_thp_disable_completely_test(_metadata, self->pmdsize, variant->thp_policy); + return; + } + + wait(&ret); + if (WIFEXITED(ret)) + ret = WEXITSTATUS(ret); + else + ret = -EINVAL; + ASSERT_EQ(ret, 0); +} + +static void prctl_thp_disable_except_madvise_test(struct __test_metadata *const _metadata, + size_t pmdsize, + enum thp_enabled thp_policy) +{ + ASSERT_EQ(prctl(PR_GET_THP_DISABLE, NULL, NULL, NULL, NULL), 3); + + /* tests after prctl overrides global policy */ + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize), + thp_policy == THP_NEVER ? 0 : 1); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 1); + + /* Reset to global policy */ + ASSERT_EQ(prctl(PR_SET_THP_DISABLE, 0, NULL, NULL, NULL), 0); + + /* tests after prctl is cleared, and only global policy is effective */ + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_NONE, pmdsize), + thp_policy == THP_ALWAYS ? 1 : 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_NOHUGEPAGE, pmdsize), 0); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_HUGEPAGE, pmdsize), + thp_policy == THP_NEVER ? 0 : 1); + + ASSERT_EQ(test_mmap_thp(THP_COLLAPSE_MADV_COLLAPSE, pmdsize), 1); +} + +FIXTURE(prctl_thp_disable_except_madvise) +{ + struct thp_settings settings; + size_t pmdsize; +}; + +FIXTURE_VARIANT(prctl_thp_disable_except_madvise) +{ + enum thp_enabled thp_policy; +}; + +FIXTURE_VARIANT_ADD(prctl_thp_disable_except_madvise, never) +{ + .thp_policy = THP_NEVER, +}; + +FIXTURE_VARIANT_ADD(prctl_thp_disable_except_madvise, madvise) +{ + .thp_policy = THP_MADVISE, +}; + +FIXTURE_VARIANT_ADD(prctl_thp_disable_except_madvise, always) +{ + .thp_policy = THP_ALWAYS, +}; + +FIXTURE_SETUP(prctl_thp_disable_except_madvise) +{ + if (!thp_available()) + SKIP(return, "Transparent Hugepages not available\n"); + + self->pmdsize = read_pmd_pagesize(); + if (!self->pmdsize) + SKIP(return, "Unable to read PMD size\n"); + + if (prctl(PR_SET_THP_DISABLE, 1, PR_THP_DISABLE_EXCEPT_ADVISED, NULL, NULL)) + SKIP(return, "Unable to set PR_THP_DISABLE_EXCEPT_ADVISED\n"); + + thp_save_settings(); + thp_read_settings(&self->settings); + self->settings.thp_enabled = variant->thp_policy; + self->settings.hugepages[sz2ord(self->pmdsize, getpagesize())].enabled = THP_INHERIT; + thp_write_settings(&self->settings); +} + +FIXTURE_TEARDOWN(prctl_thp_disable_except_madvise) +{ + thp_restore_settings(); +} + +TEST_F(prctl_thp_disable_except_madvise, nofork) +{ + prctl_thp_disable_except_madvise_test(_metadata, self->pmdsize, variant->thp_policy); +} + +TEST_F(prctl_thp_disable_except_madvise, fork) +{ + int ret = 0; + pid_t pid; + + /* Make sure prctl changes are carried across fork */ + pid = fork(); + ASSERT_GE(pid, 0); + + if (!pid) { + prctl_thp_disable_except_madvise_test(_metadata, self->pmdsize, + variant->thp_policy); + return; + } + + wait(&ret); + if (WIFEXITED(ret)) + ret = WEXITSTATUS(ret); + else + ret = -EINVAL; + ASSERT_EQ(ret, 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/rmap.c b/tools/testing/selftests/mm/rmap.c new file mode 100644 index 000000000000..13f7bccfd0a9 --- /dev/null +++ b/tools/testing/selftests/mm/rmap.c @@ -0,0 +1,433 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RMAP functional tests + * + * Author(s): Wei Yang <richard.weiyang@gmail.com> + */ + +#include "../kselftest_harness.h" +#include <strings.h> +#include <pthread.h> +#include <numa.h> +#include <numaif.h> +#include <sys/mman.h> +#include <sys/prctl.h> +#include <sys/types.h> +#include <signal.h> +#include <time.h> +#include <sys/sem.h> +#include <unistd.h> +#include <fcntl.h> + +#include "vm_util.h" + +#define TOTAL_LEVEL 5 +#define MAX_CHILDREN 3 + +#define FAIL_ON_CHECK (1 << 0) +#define FAIL_ON_WORK (1 << 1) + +struct sembuf sem_wait = {0, -1, 0}; +struct sembuf sem_signal = {0, 1, 0}; + +enum backend_type { + ANON, + SHM, + NORM_FILE, +}; + +#define PREFIX "kst_rmap" +#define MAX_FILENAME_LEN 256 +const char *suffixes[] = { + "", + "_shm", + "_file", +}; + +struct global_data; +typedef int (*work_fn)(struct global_data *data); +typedef int (*check_fn)(struct global_data *data); +typedef void (*prepare_fn)(struct global_data *data); + +struct global_data { + int worker_level; + + int semid; + int pipefd[2]; + + unsigned int mapsize; + unsigned int rand_seed; + char *region; + + prepare_fn do_prepare; + work_fn do_work; + check_fn do_check; + + enum backend_type backend; + char filename[MAX_FILENAME_LEN]; + + unsigned long *expected_pfn; +}; + +/* + * Create a process tree with TOTAL_LEVEL height and at most MAX_CHILDREN + * children for each. + * + * It will randomly select one process as 'worker' process which will + * 'do_work' until all processes are created. And all other processes will + * wait until 'worker' finish its work. + */ +void propagate_children(struct __test_metadata *_metadata, struct global_data *data) +{ + pid_t root_pid, pid; + unsigned int num_child; + int status; + int ret = 0; + int curr_child, worker_child; + int curr_level = 1; + bool is_worker = true; + + root_pid = getpid(); +repeat: + num_child = rand_r(&data->rand_seed) % MAX_CHILDREN + 1; + worker_child = is_worker ? rand_r(&data->rand_seed) % num_child : -1; + + for (curr_child = 0; curr_child < num_child; curr_child++) { + pid = fork(); + + if (pid < 0) { + perror("Error: fork\n"); + } else if (pid == 0) { + curr_level++; + + if (curr_child != worker_child) + is_worker = false; + + if (curr_level == TOTAL_LEVEL) + break; + + data->rand_seed += curr_child; + goto repeat; + } + } + + if (data->do_prepare) + data->do_prepare(data); + + close(data->pipefd[1]); + + if (is_worker && curr_level == data->worker_level) { + /* This is the worker process, first wait last process created */ + char buf; + + while (read(data->pipefd[0], &buf, 1) > 0) + ; + + if (data->do_work) + ret = data->do_work(data); + + /* Kick others */ + semctl(data->semid, 0, IPC_RMID); + } else { + /* Wait worker finish */ + semop(data->semid, &sem_wait, 1); + if (data->do_check) + ret = data->do_check(data); + } + + /* Wait all child to quit */ + while (wait(&status) > 0) { + if (WIFEXITED(status)) + ret |= WEXITSTATUS(status); + } + + if (getpid() == root_pid) { + if (ret & FAIL_ON_WORK) + SKIP(return, "Failed in worker"); + + ASSERT_EQ(ret, 0); + } else { + exit(ret); + } +} + +FIXTURE(migrate) +{ + struct global_data data; +}; + +FIXTURE_SETUP(migrate) +{ + struct global_data *data = &self->data; + + if (numa_available() < 0) + SKIP(return, "NUMA not available"); + if (numa_bitmask_weight(numa_all_nodes_ptr) <= 1) + SKIP(return, "Not enough NUMA nodes available"); + + data->mapsize = getpagesize(); + + data->expected_pfn = mmap(0, sizeof(unsigned long), + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(data->expected_pfn, MAP_FAILED); + + /* Prepare semaphore */ + data->semid = semget(IPC_PRIVATE, 1, 0666 | IPC_CREAT); + ASSERT_NE(data->semid, -1); + ASSERT_NE(semctl(data->semid, 0, SETVAL, 0), -1); + + /* Prepare pipe */ + ASSERT_NE(pipe(data->pipefd), -1); + + data->rand_seed = time(NULL); + srand(data->rand_seed); + + data->worker_level = rand() % TOTAL_LEVEL + 1; + + data->do_prepare = NULL; + data->do_work = NULL; + data->do_check = NULL; + + data->backend = ANON; +}; + +FIXTURE_TEARDOWN(migrate) +{ + struct global_data *data = &self->data; + + if (data->region != MAP_FAILED) + munmap(data->region, data->mapsize); + data->region = MAP_FAILED; + if (data->expected_pfn != MAP_FAILED) + munmap(data->expected_pfn, sizeof(unsigned long)); + data->expected_pfn = MAP_FAILED; + semctl(data->semid, 0, IPC_RMID); + data->semid = -1; + + close(data->pipefd[0]); + + switch (data->backend) { + case ANON: + break; + case SHM: + shm_unlink(data->filename); + break; + case NORM_FILE: + unlink(data->filename); + break; + } +} + +void access_region(struct global_data *data) +{ + /* + * Force read "region" to make sure page fault in. + */ + FORCE_READ(*data->region); +} + +int try_to_move_page(char *region) +{ + int ret; + int node; + int status = 0; + int failures = 0; + + ret = move_pages(0, 1, (void **)®ion, NULL, &status, MPOL_MF_MOVE_ALL); + if (ret != 0) { + perror("Failed to get original numa"); + return FAIL_ON_WORK; + } + + /* Pick up a different target node */ + for (node = 0; node <= numa_max_node(); node++) { + if (numa_bitmask_isbitset(numa_all_nodes_ptr, node) && node != status) + break; + } + + if (node > numa_max_node()) { + ksft_print_msg("Couldn't find available numa node for testing\n"); + return FAIL_ON_WORK; + } + + while (1) { + ret = move_pages(0, 1, (void **)®ion, &node, &status, MPOL_MF_MOVE_ALL); + + /* migrate successfully */ + if (!ret) + break; + + /* error happened */ + if (ret < 0) { + ksft_perror("Failed to move pages"); + return FAIL_ON_WORK; + } + + /* migration is best effort; try again */ + if (++failures >= 100) + return FAIL_ON_WORK; + } + + return 0; +} + +int move_region(struct global_data *data) +{ + int ret; + int pagemap_fd; + + ret = try_to_move_page(data->region); + if (ret != 0) + return ret; + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd == -1) + return FAIL_ON_WORK; + *data->expected_pfn = pagemap_get_pfn(pagemap_fd, data->region); + + return 0; +} + +int has_same_pfn(struct global_data *data) +{ + unsigned long pfn; + int pagemap_fd; + + if (data->region == MAP_FAILED) + return 0; + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd == -1) + return FAIL_ON_CHECK; + + pfn = pagemap_get_pfn(pagemap_fd, data->region); + if (pfn != *data->expected_pfn) + return FAIL_ON_CHECK; + + return 0; +} + +TEST_F(migrate, anon) +{ + struct global_data *data = &self->data; + + /* Map an area and fault in */ + data->region = mmap(0, data->mapsize, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(data->region, MAP_FAILED); + memset(data->region, 0xcf, data->mapsize); + + data->do_prepare = access_region; + data->do_work = move_region; + data->do_check = has_same_pfn; + + propagate_children(_metadata, data); +} + +TEST_F(migrate, shm) +{ + int shm_fd; + struct global_data *data = &self->data; + + snprintf(data->filename, MAX_FILENAME_LEN, "%s%s", PREFIX, suffixes[SHM]); + shm_fd = shm_open(data->filename, O_CREAT | O_RDWR, 0666); + ASSERT_NE(shm_fd, -1); + ftruncate(shm_fd, data->mapsize); + data->backend = SHM; + + /* Map a shared area and fault in */ + data->region = mmap(0, data->mapsize, PROT_READ | PROT_WRITE, + MAP_SHARED, shm_fd, 0); + ASSERT_NE(data->region, MAP_FAILED); + memset(data->region, 0xcf, data->mapsize); + close(shm_fd); + + data->do_prepare = access_region; + data->do_work = move_region; + data->do_check = has_same_pfn; + + propagate_children(_metadata, data); +} + +TEST_F(migrate, file) +{ + int fd; + struct global_data *data = &self->data; + + snprintf(data->filename, MAX_FILENAME_LEN, "%s%s", PREFIX, suffixes[NORM_FILE]); + fd = open(data->filename, O_CREAT | O_RDWR | O_EXCL, 0666); + ASSERT_NE(fd, -1); + ftruncate(fd, data->mapsize); + data->backend = NORM_FILE; + + /* Map a shared area and fault in */ + data->region = mmap(0, data->mapsize, PROT_READ | PROT_WRITE, + MAP_SHARED, fd, 0); + ASSERT_NE(data->region, MAP_FAILED); + memset(data->region, 0xcf, data->mapsize); + close(fd); + + data->do_prepare = access_region; + data->do_work = move_region; + data->do_check = has_same_pfn; + + propagate_children(_metadata, data); +} + +void prepare_local_region(struct global_data *data) +{ + /* Allocate range and set the same data */ + data->region = mmap(NULL, data->mapsize, PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANON, -1, 0); + if (data->region == MAP_FAILED) + return; + + memset(data->region, 0xcf, data->mapsize); +} + +int merge_and_migrate(struct global_data *data) +{ + int pagemap_fd; + int ret = 0; + + if (data->region == MAP_FAILED) + return FAIL_ON_WORK; + + if (ksm_start() < 0) + return FAIL_ON_WORK; + + ret = try_to_move_page(data->region); + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd == -1) + return FAIL_ON_WORK; + *data->expected_pfn = pagemap_get_pfn(pagemap_fd, data->region); + + return ret; +} + +TEST_F(migrate, ksm) +{ + int ret; + struct global_data *data = &self->data; + + if (ksm_stop() < 0) + SKIP(return, "accessing \"/sys/kernel/mm/ksm/run\") failed"); + if (ksm_get_full_scans() < 0) + SKIP(return, "accessing \"/sys/kernel/mm/ksm/full_scan\") failed"); + + ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); + if (ret < 0 && errno == EINVAL) + SKIP(return, "PR_SET_MEMORY_MERGE not supported"); + else if (ret) + ksft_exit_fail_perror("PR_SET_MEMORY_MERGE=1 failed"); + + data->do_prepare = prepare_local_region; + data->do_work = merge_and_migrate; + data->do_check = has_same_pfn; + + propagate_children(_metadata, data); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 471e539d82b8..9e88cc25b9df 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -85,6 +85,8 @@ separated by spaces: test handling of page fragment allocation and freeing - vma_merge test VMA merge cases behave as expected +- rmap + test rmap behaves as expected example: ./run_vmtests.sh -t "hmm mmap ksm" EOF @@ -322,11 +324,15 @@ CATEGORY="gup_test" run_test ./gup_longterm CATEGORY="userfaultfd" run_test ./uffd-unit-tests uffd_stress_bin=./uffd-stress CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16 -# Hugetlb tests require source and destination huge pages. Pass in half -# the size of the free pages we have, which is used for *each*. +# Hugetlb tests require source and destination huge pages. Pass in almost half +# the size of the free pages we have, which is used for *each*. An adjustment +# of (nr_parallel - 1) is done (see nr_parallel in uffd-stress.c) to have some +# extra hugepages - this is done to prevent the test from failing by racily +# reserving more hugepages than strictly required. # uffd-stress expects a region expressed in MiB, so we adjust # half_ufd_size_MB accordingly. -half_ufd_size_MB=$(((freepgs * hpgsize_KB) / 1024 / 2)) +adjustment=$(( (31 < (nr_cpus - 1)) ? 31 : (nr_cpus - 1) )) +half_ufd_size_MB=$((((freepgs - adjustment) * hpgsize_KB) / 1024 / 2)) CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 32 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16 @@ -532,6 +538,8 @@ CATEGORY="page_frag" run_test ./test_page_frag.sh aligned CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned +CATEGORY="rmap" run_test ./rmap + echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix echo "1..${count_total}" | tap_output diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 44a3f8a58806..10ae65ea032f 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -25,6 +25,8 @@ uint64_t pagesize; unsigned int pageshift; uint64_t pmd_pagesize; +unsigned int pmd_order; +int *expected_orders; #define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages" #define SMAP_PATH "/proc/self/smaps" @@ -34,28 +36,226 @@ uint64_t pmd_pagesize; #define PID_FMT_OFFSET "%d,0x%lx,0x%lx,%d,%d" #define PATH_FMT "%s,0x%lx,0x%lx,%d" -#define PFN_MASK ((1UL<<55)-1) -#define KPF_THP (1UL<<22) +const char *pagemap_proc = "/proc/self/pagemap"; +const char *kpageflags_proc = "/proc/kpageflags"; +int pagemap_fd; +int kpageflags_fd; -int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file) +static bool is_backed_by_folio(char *vaddr, int order, int pagemap_fd, + int kpageflags_fd) { - uint64_t paddr; - uint64_t page_flags; + const unsigned long nr_pages = 1UL << order; + unsigned long pfn_head; + uint64_t pfn_flags; + unsigned long pfn; + unsigned long i; - if (pagemap_file) { - pread(pagemap_file, &paddr, sizeof(paddr), - ((long)vaddr >> pageshift) * sizeof(paddr)); + pfn = pagemap_get_pfn(pagemap_fd, vaddr); - if (kpageflags_file) { - pread(kpageflags_file, &page_flags, sizeof(page_flags), - (paddr & PFN_MASK) * sizeof(page_flags)); + /* non present page */ + if (pfn == -1UL) + return false; + + if (pageflags_get(pfn, kpageflags_fd, &pfn_flags)) + goto fail; + + /* check for order-0 pages */ + if (!order) { + if (pfn_flags & (KPF_THP | KPF_COMPOUND_HEAD | KPF_COMPOUND_TAIL)) + return false; + return true; + } + + /* non THP folio */ + if (!(pfn_flags & KPF_THP)) + return false; + + pfn_head = pfn & ~(nr_pages - 1); + + if (pageflags_get(pfn_head, kpageflags_fd, &pfn_flags)) + goto fail; + + /* head PFN has no compound_head flag set */ + if (!(pfn_flags & (KPF_THP | KPF_COMPOUND_HEAD))) + return false; + + /* check all tail PFN flags */ + for (i = 1; i < nr_pages; i++) { + if (pageflags_get(pfn_head + i, kpageflags_fd, &pfn_flags)) + goto fail; + if (!(pfn_flags & (KPF_THP | KPF_COMPOUND_TAIL))) + return false; + } + + /* + * check the PFN after this folio, but if its flags cannot be obtained, + * assume this folio has the expected order + */ + if (pageflags_get(pfn_head + nr_pages, kpageflags_fd, &pfn_flags)) + return true; + + /* this folio is bigger than the given order */ + if (pfn_flags & (KPF_THP | KPF_COMPOUND_TAIL)) + return false; + + return true; +fail: + ksft_exit_fail_msg("Failed to get folio info\n"); + return false; +} + +static int vaddr_pageflags_get(char *vaddr, int pagemap_fd, int kpageflags_fd, + uint64_t *flags) +{ + unsigned long pfn; + + pfn = pagemap_get_pfn(pagemap_fd, vaddr); + + /* non-present PFN */ + if (pfn == -1UL) + return 1; + + if (pageflags_get(pfn, kpageflags_fd, flags)) + return -1; - return !!(page_flags & KPF_THP); + return 0; +} + +/* + * gather_after_split_folio_orders - scan through [vaddr_start, len) and record + * folio orders + * + * @vaddr_start: start vaddr + * @len: range length + * @pagemap_fd: file descriptor to /proc/<pid>/pagemap + * @kpageflags_fd: file descriptor to /proc/kpageflags + * @orders: output folio order array + * @nr_orders: folio order array size + * + * gather_after_split_folio_orders() scan through [vaddr_start, len) and check + * all folios within the range and record their orders. All order-0 pages will + * be recorded. Non-present vaddr is skipped. + * + * NOTE: the function is used to check folio orders after a split is performed, + * so it assumes [vaddr_start, len) fully maps to after-split folios within that + * range. + * + * Return: 0 - no error, -1 - unhandled cases + */ +static int gather_after_split_folio_orders(char *vaddr_start, size_t len, + int pagemap_fd, int kpageflags_fd, int orders[], int nr_orders) +{ + uint64_t page_flags = 0; + int cur_order = -1; + char *vaddr; + + if (pagemap_fd == -1 || kpageflags_fd == -1) + return -1; + if (!orders) + return -1; + if (nr_orders <= 0) + return -1; + + for (vaddr = vaddr_start; vaddr < vaddr_start + len;) { + char *next_folio_vaddr; + int status; + + status = vaddr_pageflags_get(vaddr, pagemap_fd, kpageflags_fd, + &page_flags); + if (status < 0) + return -1; + + /* skip non present vaddr */ + if (status == 1) { + vaddr += psize(); + continue; + } + + /* all order-0 pages with possible false postive (non folio) */ + if (!(page_flags & (KPF_COMPOUND_HEAD | KPF_COMPOUND_TAIL))) { + orders[0]++; + vaddr += psize(); + continue; + } + + /* skip non thp compound pages */ + if (!(page_flags & KPF_THP)) { + vaddr += psize(); + continue; + } + + /* vpn points to part of a THP at this point */ + if (page_flags & KPF_COMPOUND_HEAD) + cur_order = 1; + else { + vaddr += psize(); + continue; + } + + next_folio_vaddr = vaddr + (1UL << (cur_order + pshift())); + + if (next_folio_vaddr >= vaddr_start + len) + break; + + while ((status = vaddr_pageflags_get(next_folio_vaddr, + pagemap_fd, kpageflags_fd, + &page_flags)) >= 0) { + /* + * non present vaddr, next compound head page, or + * order-0 page + */ + if (status == 1 || + (page_flags & KPF_COMPOUND_HEAD) || + !(page_flags & (KPF_COMPOUND_HEAD | KPF_COMPOUND_TAIL))) { + if (cur_order < nr_orders) { + orders[cur_order]++; + cur_order = -1; + vaddr = next_folio_vaddr; + } + break; + } + + cur_order++; + next_folio_vaddr = vaddr + (1UL << (cur_order + pshift())); } + + if (status < 0) + return status; } + if (cur_order > 0 && cur_order < nr_orders) + orders[cur_order]++; return 0; } +static int check_after_split_folio_orders(char *vaddr_start, size_t len, + int pagemap_fd, int kpageflags_fd, int orders[], int nr_orders) +{ + int *vaddr_orders; + int status; + int i; + + vaddr_orders = (int *)malloc(sizeof(int) * nr_orders); + + if (!vaddr_orders) + ksft_exit_fail_msg("Cannot allocate memory for vaddr_orders"); + + memset(vaddr_orders, 0, sizeof(int) * nr_orders); + status = gather_after_split_folio_orders(vaddr_start, len, pagemap_fd, + kpageflags_fd, vaddr_orders, nr_orders); + if (status) + ksft_exit_fail_msg("gather folio info failed\n"); + + for (i = 0; i < nr_orders; i++) + if (vaddr_orders[i] != orders[i]) { + ksft_print_msg("order %d: expected: %d got %d\n", i, + orders[i], vaddr_orders[i]); + status = -1; + } + + free(vaddr_orders); + return status; +} + static void write_file(const char *path, const char *buf, size_t buflen) { int fd; @@ -111,7 +311,7 @@ static void verify_rss_anon_split_huge_page_all_zeroes(char *one_page, int nr_hp unsigned long rss_anon_before, rss_anon_after; size_t i; - if (!check_huge_anon(one_page, 4, pmd_pagesize)) + if (!check_huge_anon(one_page, nr_hpages, pmd_pagesize)) ksft_exit_fail_msg("No THP is allocated\n"); rss_anon_before = rss_anon(); @@ -135,7 +335,7 @@ static void verify_rss_anon_split_huge_page_all_zeroes(char *one_page, int nr_hp rss_anon_before, rss_anon_after); } -void split_pmd_zero_pages(void) +static void split_pmd_zero_pages(void) { char *one_page; int nr_hpages = 4; @@ -147,7 +347,7 @@ void split_pmd_zero_pages(void) free(one_page); } -void split_pmd_thp_to_order(int order) +static void split_pmd_thp_to_order(int order) { char *one_page; size_t len = 4 * pmd_pagesize; @@ -173,6 +373,13 @@ void split_pmd_thp_to_order(int order) if (one_page[i] != (char)i) ksft_exit_fail_msg("%ld byte corrupted\n", i); + memset(expected_orders, 0, sizeof(int) * (pmd_order + 1)); + expected_orders[order] = 4 << (pmd_order - order); + + if (check_after_split_folio_orders(one_page, len, pagemap_fd, + kpageflags_fd, expected_orders, + (pmd_order + 1))) + ksft_exit_fail_msg("Unexpected THP split\n"); if (!check_huge_anon(one_page, 0, pmd_pagesize)) ksft_exit_fail_msg("Still AnonHugePages not split\n"); @@ -181,28 +388,12 @@ void split_pmd_thp_to_order(int order) free(one_page); } -void split_pte_mapped_thp(void) +static void split_pte_mapped_thp(void) { char *one_page, *pte_mapped, *pte_mapped2; size_t len = 4 * pmd_pagesize; uint64_t thp_size; size_t i; - const char *pagemap_template = "/proc/%d/pagemap"; - const char *kpageflags_proc = "/proc/kpageflags"; - char pagemap_proc[255]; - int pagemap_fd; - int kpageflags_fd; - - if (snprintf(pagemap_proc, 255, pagemap_template, getpid()) < 0) - ksft_exit_fail_msg("get pagemap proc error: %s\n", strerror(errno)); - - pagemap_fd = open(pagemap_proc, O_RDONLY); - if (pagemap_fd == -1) - ksft_exit_fail_msg("read pagemap: %s\n", strerror(errno)); - - kpageflags_fd = open(kpageflags_proc, O_RDONLY); - if (kpageflags_fd == -1) - ksft_exit_fail_msg("read kpageflags: %s\n", strerror(errno)); one_page = mmap((void *)(1UL << 30), len, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); @@ -234,7 +425,7 @@ void split_pte_mapped_thp(void) thp_size = 0; for (i = 0; i < pagesize * 4; i++) if (i % pagesize == 0 && - is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) + is_backed_by_folio(&pte_mapped[i], pmd_order, pagemap_fd, kpageflags_fd)) thp_size++; if (thp_size != 4) @@ -251,7 +442,7 @@ void split_pte_mapped_thp(void) ksft_exit_fail_msg("%ld byte corrupted\n", i); if (i % pagesize == 0 && - is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd)) + !is_backed_by_folio(&pte_mapped[i], 0, pagemap_fd, kpageflags_fd)) thp_size++; } @@ -260,11 +451,9 @@ void split_pte_mapped_thp(void) ksft_test_result_pass("Split PTE-mapped huge pages successful\n"); munmap(one_page, len); - close(pagemap_fd); - close(kpageflags_fd); } -void split_file_backed_thp(int order) +static void split_file_backed_thp(int order) { int status; int fd; @@ -366,7 +555,7 @@ out: ksft_exit_fail_msg("Error occurred\n"); } -bool prepare_thp_fs(const char *xfs_path, char *thp_fs_template, +static bool prepare_thp_fs(const char *xfs_path, char *thp_fs_template, const char **thp_fs_loc) { if (xfs_path) { @@ -382,7 +571,7 @@ bool prepare_thp_fs(const char *xfs_path, char *thp_fs_template, return true; } -void cleanup_thp_fs(const char *thp_fs_loc, bool created_tmp) +static void cleanup_thp_fs(const char *thp_fs_loc, bool created_tmp) { int status; @@ -395,8 +584,8 @@ void cleanup_thp_fs(const char *thp_fs_loc, bool created_tmp) strerror(errno)); } -int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd, - char **addr) +static int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, + int *fd, char **addr) { size_t i; unsigned char buf[1024]; @@ -462,10 +651,11 @@ err_out_unlink: return -1; } -void split_thp_in_pagecache_to_order_at(size_t fd_size, const char *fs_loc, - int order, int offset) +static void split_thp_in_pagecache_to_order_at(size_t fd_size, + const char *fs_loc, int order, int offset) { int fd; + char *split_addr; char *addr; size_t i; char testfile[INPUT_MAX]; @@ -479,14 +669,33 @@ void split_thp_in_pagecache_to_order_at(size_t fd_size, const char *fs_loc, err = create_pagecache_thp_and_fd(testfile, fd_size, &fd, &addr); if (err) return; + err = 0; - if (offset == -1) - write_debugfs(PID_FMT, getpid(), (uint64_t)addr, - (uint64_t)addr + fd_size, order); - else - write_debugfs(PID_FMT_OFFSET, getpid(), (uint64_t)addr, - (uint64_t)addr + fd_size, order, offset); + memset(expected_orders, 0, sizeof(int) * (pmd_order + 1)); + /* + * use [split_addr, split_addr + pagesize) range to split THPs, since + * the debugfs function always split a range with pagesize step and + * providing a full [addr, addr + fd_size) range can trigger multiple + * splits, complicating after-split result checking. + */ + if (offset == -1) { + for (split_addr = addr; split_addr < addr + fd_size; split_addr += pmd_pagesize) + write_debugfs(PID_FMT, getpid(), (uint64_t)split_addr, + (uint64_t)split_addr + pagesize, order); + + expected_orders[order] = fd_size / (pagesize << order); + } else { + int times = fd_size / pmd_pagesize; + + for (split_addr = addr; split_addr < addr + fd_size; split_addr += pmd_pagesize) + write_debugfs(PID_FMT_OFFSET, getpid(), (uint64_t)split_addr, + (uint64_t)split_addr + pagesize, order, offset); + + for (i = order + 1; i < pmd_order; i++) + expected_orders[i] = times; + expected_orders[order] = 2 * times; + } for (i = 0; i < fd_size; i++) if (*(addr + i) != (char)i) { @@ -495,6 +704,14 @@ void split_thp_in_pagecache_to_order_at(size_t fd_size, const char *fs_loc, goto out; } + if (check_after_split_folio_orders(addr, fd_size, pagemap_fd, + kpageflags_fd, expected_orders, + (pmd_order + 1))) { + ksft_print_msg("Unexpected THP split\n"); + err = 1; + goto out; + } + if (!check_huge_file(addr, 0, pmd_pagesize)) { ksft_print_msg("Still FilePmdMapped not split\n"); err = EXIT_FAILURE; @@ -525,6 +742,8 @@ int main(int argc, char **argv) const char *fs_loc; bool created_tmp; int offset; + unsigned int nr_pages; + unsigned int tests; ksft_print_header(); @@ -536,38 +755,58 @@ int main(int argc, char **argv) if (argc > 1) optional_xfs_path = argv[1]; - ksft_set_plan(1+8+1+9+9+8*4+2); - pagesize = getpagesize(); pageshift = ffs(pagesize) - 1; pmd_pagesize = read_pmd_pagesize(); if (!pmd_pagesize) ksft_exit_fail_msg("Reading PMD pagesize failed\n"); + nr_pages = pmd_pagesize / pagesize; + pmd_order = sz2ord(pmd_pagesize, pagesize); + + expected_orders = (int *)malloc(sizeof(int) * (pmd_order + 1)); + if (!expected_orders) + ksft_exit_fail_msg("Fail to allocate memory: %s\n", strerror(errno)); + + tests = 2 + (pmd_order - 1) + (2 * pmd_order) + (pmd_order - 1) * 4 + 2; + ksft_set_plan(tests); + + pagemap_fd = open(pagemap_proc, O_RDONLY); + if (pagemap_fd == -1) + ksft_exit_fail_msg("read pagemap: %s\n", strerror(errno)); + + kpageflags_fd = open(kpageflags_proc, O_RDONLY); + if (kpageflags_fd == -1) + ksft_exit_fail_msg("read kpageflags: %s\n", strerror(errno)); + fd_size = 2 * pmd_pagesize; split_pmd_zero_pages(); - for (i = 0; i < 9; i++) + for (i = 0; i < pmd_order; i++) if (i != 1) split_pmd_thp_to_order(i); split_pte_mapped_thp(); - for (i = 0; i < 9; i++) + for (i = 0; i < pmd_order; i++) split_file_backed_thp(i); created_tmp = prepare_thp_fs(optional_xfs_path, fs_loc_template, &fs_loc); - for (i = 8; i >= 0; i--) + for (i = pmd_order - 1; i >= 0; i--) split_thp_in_pagecache_to_order_at(fd_size, fs_loc, i, -1); - for (i = 0; i < 9; i++) + for (i = 0; i < pmd_order; i++) for (offset = 0; - offset < pmd_pagesize / pagesize; - offset += MAX(pmd_pagesize / pagesize / 4, 1 << i)) + offset < nr_pages; + offset += MAX(nr_pages / 4, 1 << i)) split_thp_in_pagecache_to_order_at(fd_size, fs_loc, i, offset); cleanup_thp_fs(fs_loc, created_tmp); + close(pagemap_fd); + close(kpageflags_fd); + free(expected_orders); + ksft_finished(); return 0; diff --git a/tools/testing/selftests/mm/test_vmalloc.sh b/tools/testing/selftests/mm/test_vmalloc.sh index d73b846736f1..d39096723fca 100755 --- a/tools/testing/selftests/mm/test_vmalloc.sh +++ b/tools/testing/selftests/mm/test_vmalloc.sh @@ -47,14 +47,14 @@ check_test_requirements() fi } -run_perfformance_check() +run_performance_check() { echo "Run performance tests to evaluate how fast vmalloc allocation is." echo "It runs all test cases on one single CPU with sequential order." modprobe $DRIVER $PERF_PARAM > /dev/null 2>&1 echo "Done." - echo "Ccheck the kernel message buffer to see the summary." + echo "Check the kernel message buffer to see the summary." } run_stability_check() @@ -160,7 +160,7 @@ function run_test() usage else if [[ "$1" = "performance" ]]; then - run_perfformance_check + run_performance_check elif [[ "$1" = "stress" ]]; then run_stability_check elif [[ "$1" = "smoke" ]]; then diff --git a/tools/testing/selftests/mm/thp_settings.c b/tools/testing/selftests/mm/thp_settings.c index bad60ac52874..574bd0f8ae48 100644 --- a/tools/testing/selftests/mm/thp_settings.c +++ b/tools/testing/selftests/mm/thp_settings.c @@ -382,10 +382,17 @@ unsigned long thp_shmem_supported_orders(void) return __thp_supported_orders(true); } -bool thp_is_enabled(void) +bool thp_available(void) { if (access(THP_SYSFS, F_OK) != 0) return false; + return true; +} + +bool thp_is_enabled(void) +{ + if (!thp_available()) + return false; int mode = thp_read_string("enabled", thp_enabled_strings); diff --git a/tools/testing/selftests/mm/thp_settings.h b/tools/testing/selftests/mm/thp_settings.h index 6c07f70beee9..76eeb712e5f1 100644 --- a/tools/testing/selftests/mm/thp_settings.h +++ b/tools/testing/selftests/mm/thp_settings.h @@ -84,6 +84,7 @@ void thp_set_read_ahead_path(char *path); unsigned long thp_supported_orders(void); unsigned long thp_shmem_supported_orders(void); +bool thp_available(void); bool thp_is_enabled(void); #endif /* __THP_SETTINGS_H__ */ diff --git a/tools/testing/selftests/mm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c index 8e2b08dc5762..4f5e290ff1a6 100644 --- a/tools/testing/selftests/mm/thuge-gen.c +++ b/tools/testing/selftests/mm/thuge-gen.c @@ -177,13 +177,16 @@ void find_pagesizes(void) globfree(&g); read_sysfs("/proc/sys/kernel/shmmax", &shmmax_val); - if (shmmax_val < NUM_PAGES * largest) - ksft_exit_fail_msg("Please do echo %lu > /proc/sys/kernel/shmmax", - largest * NUM_PAGES); + if (shmmax_val < NUM_PAGES * largest) { + ksft_print_msg("WARNING: shmmax is too small to run this test.\n"); + ksft_print_msg("Please run the following command to increase shmmax:\n"); + ksft_print_msg("echo %lu > /proc/sys/kernel/shmmax\n", largest * NUM_PAGES); + ksft_exit_skip("Test skipped due to insufficient shmmax value.\n"); + } #if defined(__x86_64__) if (largest != 1U<<30) { - ksft_exit_fail_msg("No GB pages available on x86-64\n" + ksft_exit_skip("No GB pages available on x86-64\n" "Please boot with hugepagesz=1G hugepages=%d\n", NUM_PAGES); } #endif diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index 40af7f67c407..ecd016329935 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -51,7 +51,7 @@ static char *zeropage; pthread_attr_t attr; #define swap(a, b) \ - do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) + do { __auto_type __tmp = (a); (a) = (b); (b) = __tmp; } while (0) const char *examples = "# Run anonymous memory test on 100MiB region with 99999 bounces:\n" @@ -448,12 +448,6 @@ int main(int argc, char **argv) parse_test_type_arg(argv[1]); bytes = atol(argv[2]) * 1024 * 1024; - if (test_type == TEST_HUGETLB && - get_free_hugepages() < bytes / page_size) { - printf("skip: Skipping userfaultfd... not enough hugepages\n"); - return KSFT_SKIP; - } - nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); if (nr_cpus > 32) { /* Don't let calculation below go to zero. */ @@ -464,6 +458,17 @@ int main(int argc, char **argv) nr_parallel = nr_cpus; } + /* + * src and dst each require bytes / page_size number of hugepages. + * Ensure nr_parallel - 1 hugepages on top of that to account + * for racy extra reservation of hugepages. + */ + if (test_type == TEST_HUGETLB && + get_free_hugepages() < 2 * (bytes / page_size) + nr_parallel - 1) { + printf("skip: Skipping userfaultfd... not enough hugepages\n"); + return KSFT_SKIP; + } + nr_pages_per_cpu = bytes / page_size / nr_parallel; if (!nr_pages_per_cpu) { _err("pages_per_cpu = 0, cannot test (%lu / %lu / %lu)", diff --git a/tools/testing/selftests/mm/uffd-wp-mremap.c b/tools/testing/selftests/mm/uffd-wp-mremap.c index c2ba7d46c7b4..78038c40aaaf 100644 --- a/tools/testing/selftests/mm/uffd-wp-mremap.c +++ b/tools/testing/selftests/mm/uffd-wp-mremap.c @@ -19,11 +19,6 @@ static size_t thpsizes[20]; static int nr_hugetlbsizes; static size_t hugetlbsizes[10]; -static int sz2ord(size_t size) -{ - return __builtin_ctzll(size / pagesize); -} - static int detect_thp_sizes(size_t sizes[], int max) { int count = 0; @@ -87,9 +82,9 @@ static void *alloc_one_folio(size_t size, bool private, bool hugetlb) struct thp_settings settings = *thp_current_settings(); if (private) - settings.hugepages[sz2ord(size)].enabled = THP_ALWAYS; + settings.hugepages[sz2ord(size, pagesize)].enabled = THP_ALWAYS; else - settings.shmem_hugepages[sz2ord(size)].enabled = SHMEM_ALWAYS; + settings.shmem_hugepages[sz2ord(size, pagesize)].enabled = SHMEM_ALWAYS; thp_push_settings(&settings); diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index 169dbd692bf5..81b33d8f78f4 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -44,12 +44,18 @@ * On Arm64 the address space is 256TB and support for * high mappings up to 4PB virtual address space has * been added. + * + * On PowerPC64, the address space up to 128TB can be + * mapped without a hint. Addresses beyond 128TB, up to + * 4PB, can be mapped with a hint. + * */ #define NR_CHUNKS_128TB ((128 * SZ_1TB) / MAP_CHUNK_SIZE) /* Number of chunks for 128TB */ #define NR_CHUNKS_256TB (NR_CHUNKS_128TB * 2UL) #define NR_CHUNKS_384TB (NR_CHUNKS_128TB * 3UL) #define NR_CHUNKS_3840TB (NR_CHUNKS_128TB * 30UL) +#define NR_CHUNKS_3968TB (NR_CHUNKS_128TB * 31UL) #define ADDR_MARK_128TB (1UL << 47) /* First address beyond 128TB */ #define ADDR_MARK_256TB (1UL << 48) /* First address beyond 256TB */ @@ -59,6 +65,11 @@ #define HIGH_ADDR_SHIFT 49 #define NR_CHUNKS_LOW NR_CHUNKS_256TB #define NR_CHUNKS_HIGH NR_CHUNKS_3840TB +#elif defined(__PPC64__) +#define HIGH_ADDR_MARK ADDR_MARK_128TB +#define HIGH_ADDR_SHIFT 48 +#define NR_CHUNKS_LOW NR_CHUNKS_128TB +#define NR_CHUNKS_HIGH NR_CHUNKS_3968TB #else #define HIGH_ADDR_MARK ADDR_MARK_128TB #define HIGH_ADDR_SHIFT 48 @@ -227,7 +238,7 @@ int main(int argc, char *argv[]) if (hptr[i] == MAP_FAILED) break; - mark_range(ptr[i], MAP_CHUNK_SIZE); + mark_range(hptr[i], MAP_CHUNK_SIZE); validate_addr(hptr[i], 1); } hchunks = i; diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 9dafa7669ef9..56e9bd541edd 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -338,6 +338,19 @@ int detect_hugetlb_page_sizes(size_t sizes[], int max) return count; } +int pageflags_get(unsigned long pfn, int kpageflags_fd, uint64_t *flags) +{ + size_t count; + + count = pread(kpageflags_fd, flags, sizeof(*flags), + pfn * sizeof(*flags)); + + if (count != sizeof(*flags)) + return -1; + + return 0; +} + /* If `ioctls' non-NULL, the allowed ioctls will be returned into the var */ int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor, uint64_t *ioctls) @@ -402,7 +415,7 @@ unsigned long get_free_hugepages(void) return fhp; } -bool check_vmflag_io(void *addr) +static bool check_vmflag(void *addr, const char *flag) { char buffer[MAX_LINE_LENGTH]; const char *flags; @@ -419,13 +432,23 @@ bool check_vmflag_io(void *addr) if (!flaglen) return false; - if (flaglen == strlen("io") && !memcmp(flags, "io", flaglen)) + if (flaglen == strlen(flag) && !memcmp(flags, flag, flaglen)) return true; flags += flaglen; } } +bool check_vmflag_io(void *addr) +{ + return check_vmflag(addr, "io"); +} + +bool check_vmflag_pfnmap(void *addr) +{ + return check_vmflag(addr, "pf"); +} + /* * Open an fd at /proc/$pid/maps and configure procmap_out ready for * PROCMAP_QUERY query. Returns 0 on success, or an error code otherwise. @@ -555,3 +578,126 @@ bool detect_huge_zeropage(void) close(fd); return enabled; } + +long ksm_get_self_zero_pages(void) +{ + int proc_self_ksm_stat_fd; + char buf[200]; + char *substr_ksm_zero; + size_t value_pos; + ssize_t read_size; + + proc_self_ksm_stat_fd = open("/proc/self/ksm_stat", O_RDONLY); + if (proc_self_ksm_stat_fd < 0) + return -errno; + + read_size = pread(proc_self_ksm_stat_fd, buf, sizeof(buf) - 1, 0); + close(proc_self_ksm_stat_fd); + if (read_size < 0) + return -errno; + + buf[read_size] = 0; + + substr_ksm_zero = strstr(buf, "ksm_zero_pages"); + if (!substr_ksm_zero) + return 0; + + value_pos = strcspn(substr_ksm_zero, "0123456789"); + return strtol(substr_ksm_zero + value_pos, NULL, 10); +} + +long ksm_get_self_merging_pages(void) +{ + int proc_self_ksm_merging_pages_fd; + char buf[10]; + ssize_t ret; + + proc_self_ksm_merging_pages_fd = open("/proc/self/ksm_merging_pages", + O_RDONLY); + if (proc_self_ksm_merging_pages_fd < 0) + return -errno; + + ret = pread(proc_self_ksm_merging_pages_fd, buf, sizeof(buf) - 1, 0); + close(proc_self_ksm_merging_pages_fd); + if (ret <= 0) + return -errno; + buf[ret] = 0; + + return strtol(buf, NULL, 10); +} + +long ksm_get_full_scans(void) +{ + int ksm_full_scans_fd; + char buf[10]; + ssize_t ret; + + ksm_full_scans_fd = open("/sys/kernel/mm/ksm/full_scans", O_RDONLY); + if (ksm_full_scans_fd < 0) + return -errno; + + ret = pread(ksm_full_scans_fd, buf, sizeof(buf) - 1, 0); + close(ksm_full_scans_fd); + if (ret <= 0) + return -errno; + buf[ret] = 0; + + return strtol(buf, NULL, 10); +} + +int ksm_use_zero_pages(void) +{ + int ksm_use_zero_pages_fd; + ssize_t ret; + + ksm_use_zero_pages_fd = open("/sys/kernel/mm/ksm/use_zero_pages", O_RDWR); + if (ksm_use_zero_pages_fd < 0) + return -errno; + + ret = write(ksm_use_zero_pages_fd, "1", 1); + close(ksm_use_zero_pages_fd); + return ret == 1 ? 0 : -errno; +} + +int ksm_start(void) +{ + int ksm_fd; + ssize_t ret; + long start_scans, end_scans; + + ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR); + if (ksm_fd < 0) + return -errno; + + /* Wait for two full scans such that any possible merging happened. */ + start_scans = ksm_get_full_scans(); + if (start_scans < 0) { + close(ksm_fd); + return start_scans; + } + ret = write(ksm_fd, "1", 1); + close(ksm_fd); + if (ret != 1) + return -errno; + do { + end_scans = ksm_get_full_scans(); + if (end_scans < 0) + return end_scans; + } while (end_scans < start_scans + 2); + + return 0; +} + +int ksm_stop(void) +{ + int ksm_fd; + ssize_t ret; + + ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR); + if (ksm_fd < 0) + return -errno; + + ret = write(ksm_fd, "2", 1); + close(ksm_fd); + return ret == 1 ? 0 : -errno; +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index b55d1809debc..07c4acfd84b6 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -18,6 +18,9 @@ #define PM_SWAP BIT_ULL(62) #define PM_PRESENT BIT_ULL(63) +#define KPF_COMPOUND_HEAD BIT_ULL(15) +#define KPF_COMPOUND_TAIL BIT_ULL(16) +#define KPF_THP BIT_ULL(22) /* * Ignore the checkpatch warning, we must read from x but don't want to do * anything with it in order to trigger a read page fault. We therefore must use @@ -85,6 +88,7 @@ bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size); int64_t allocate_transhuge(void *ptr, int pagemap_fd); unsigned long default_huge_page_size(void); int detect_hugetlb_page_sizes(size_t sizes[], int max); +int pageflags_get(unsigned long pfn, int kpageflags_fd, uint64_t *flags); int uffd_register(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor); @@ -93,6 +97,7 @@ int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor, uint64_t *ioctls); unsigned long get_free_hugepages(void); bool check_vmflag_io(void *addr); +bool check_vmflag_pfnmap(void *addr); int open_procmap(pid_t pid, struct procmap_fd *procmap_out); int query_procmap(struct procmap_fd *procmap); bool find_vma_procmap(struct procmap_fd *procmap, void *address); @@ -126,9 +131,21 @@ static inline void log_test_result(int result) ksft_test_result_report(result, "%s\n", test_name); } +static inline int sz2ord(size_t size, size_t pagesize) +{ + return __builtin_ctzll(size / pagesize); +} + void *sys_mremap(void *old_address, unsigned long old_size, unsigned long new_size, int flags, void *new_address); +long ksm_get_self_zero_pages(void); +long ksm_get_self_merging_pages(void); +long ksm_get_full_scans(void); +int ksm_use_zero_pages(void); +int ksm_start(void); +int ksm_stop(void); + /* * On ppc64 this will only work with radix 2M hugepage size */ diff --git a/tools/testing/selftests/net/psock_lib.h b/tools/testing/selftests/net/psock_lib.h index 6e4fef560873..067265b0a554 100644 --- a/tools/testing/selftests/net/psock_lib.h +++ b/tools/testing/selftests/net/psock_lib.h @@ -22,10 +22,6 @@ #define PORT_BASE 8000 -#ifndef __maybe_unused -# define __maybe_unused __attribute__ ((__unused__)) -#endif - static __maybe_unused void pair_udp_setfilter(int fd) { /* the filter below checks for all of the following conditions that diff --git a/tools/testing/selftests/perf_events/watermark_signal.c b/tools/testing/selftests/perf_events/watermark_signal.c index e03fe1b9bba2..b3a72f0ac522 100644 --- a/tools/testing/selftests/perf_events/watermark_signal.c +++ b/tools/testing/selftests/perf_events/watermark_signal.c @@ -17,8 +17,6 @@ #include "../kselftest_harness.h" -#define __maybe_unused __attribute__((__unused__)) - static int sigio_count; static void handle_sigio(int signum __maybe_unused, diff --git a/tools/testing/selftests/proc/proc-maps-race.c b/tools/testing/selftests/proc/proc-maps-race.c index 94bba4553130..a546475db550 100644 --- a/tools/testing/selftests/proc/proc-maps-race.c +++ b/tools/testing/selftests/proc/proc-maps-race.c @@ -32,6 +32,8 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> +#include <linux/fs.h> +#include <sys/ioctl.h> #include <sys/mman.h> #include <sys/stat.h> #include <sys/types.h> @@ -317,6 +319,25 @@ static bool capture_mod_pattern(FIXTURE_DATA(proc_maps_race) *self, strcmp(restored_first_line->text, self->first_line.text) == 0; } +static bool query_addr_at(int maps_fd, void *addr, + unsigned long *vma_start, unsigned long *vma_end) +{ + struct procmap_query q; + + memset(&q, 0, sizeof(q)); + q.size = sizeof(q); + /* Find the VMA at the split address */ + q.query_addr = (unsigned long long)addr; + q.query_flags = 0; + if (ioctl(maps_fd, PROCMAP_QUERY, &q)) + return false; + + *vma_start = q.vma_start; + *vma_end = q.vma_end; + + return true; +} + static inline bool split_vma(FIXTURE_DATA(proc_maps_race) *self) { return mmap(self->mod_info->addr, self->page_size, self->mod_info->prot | PROT_EXEC, @@ -559,6 +580,8 @@ TEST_F(proc_maps_race, test_maps_tearing_from_split) do { bool last_line_changed; bool first_line_changed; + unsigned long vma_start; + unsigned long vma_end; ASSERT_TRUE(read_boundary_lines(self, &new_last_line, &new_first_line)); @@ -595,6 +618,19 @@ TEST_F(proc_maps_race, test_maps_tearing_from_split) first_line_changed = strcmp(new_first_line.text, self->first_line.text) != 0; ASSERT_EQ(last_line_changed, first_line_changed); + /* Check if PROCMAP_QUERY ioclt() finds the right VMA */ + ASSERT_TRUE(query_addr_at(self->maps_fd, mod_info->addr + self->page_size, + &vma_start, &vma_end)); + /* + * The vma at the split address can be either the same as + * original one (if read before the split) or the same as the + * first line in the second page (if read after the split). + */ + ASSERT_TRUE((vma_start == self->last_line.start_addr && + vma_end == self->last_line.end_addr) || + (vma_start == split_first_line.start_addr && + vma_end == split_first_line.end_addr)); + clock_gettime(CLOCK_MONOTONIC_COARSE, &end_ts); end_test_iteration(&end_ts, self->verbose); } while (end_ts.tv_sec - start_ts.tv_sec < self->duration_sec); @@ -636,6 +672,9 @@ TEST_F(proc_maps_race, test_maps_tearing_from_resize) clock_gettime(CLOCK_MONOTONIC_COARSE, &start_ts); start_test_loop(&start_ts, self->verbose); do { + unsigned long vma_start; + unsigned long vma_end; + ASSERT_TRUE(read_boundary_lines(self, &new_last_line, &new_first_line)); /* Check if we read vmas after shrinking it */ @@ -662,6 +701,16 @@ TEST_F(proc_maps_race, test_maps_tearing_from_resize) "Expand result invalid", self)); } + /* Check if PROCMAP_QUERY ioclt() finds the right VMA */ + ASSERT_TRUE(query_addr_at(self->maps_fd, mod_info->addr, &vma_start, &vma_end)); + /* + * The vma should stay at the same address and have either the + * original size of 3 pages or 1 page if read after shrinking. + */ + ASSERT_TRUE(vma_start == self->last_line.start_addr && + (vma_end - vma_start == self->page_size * 3 || + vma_end - vma_start == self->page_size)); + clock_gettime(CLOCK_MONOTONIC_COARSE, &end_ts); end_test_iteration(&end_ts, self->verbose); } while (end_ts.tv_sec - start_ts.tv_sec < self->duration_sec); @@ -703,6 +752,9 @@ TEST_F(proc_maps_race, test_maps_tearing_from_remap) clock_gettime(CLOCK_MONOTONIC_COARSE, &start_ts); start_test_loop(&start_ts, self->verbose); do { + unsigned long vma_start; + unsigned long vma_end; + ASSERT_TRUE(read_boundary_lines(self, &new_last_line, &new_first_line)); /* Check if we read vmas after remapping it */ @@ -729,6 +781,19 @@ TEST_F(proc_maps_race, test_maps_tearing_from_remap) "Remap restore result invalid", self)); } + /* Check if PROCMAP_QUERY ioclt() finds the right VMA */ + ASSERT_TRUE(query_addr_at(self->maps_fd, mod_info->addr + self->page_size, + &vma_start, &vma_end)); + /* + * The vma should either stay at the same address and have the + * original size of 3 pages or we should find the remapped vma + * at the remap destination address with size of 1 page. + */ + ASSERT_TRUE((vma_start == self->last_line.start_addr && + vma_end - vma_start == self->page_size * 3) || + (vma_start == self->last_line.start_addr + self->page_size && + vma_end - vma_start == self->page_size)); + clock_gettime(CLOCK_MONOTONIC_COARSE, &end_ts); end_test_iteration(&end_ts, self->verbose); } while (end_ts.tv_sec - start_ts.tv_sec < self->duration_sec); diff --git a/tools/testing/selftests/ublk/utils.h b/tools/testing/selftests/ublk/utils.h index 36545d1567f1..a852e0b7153e 100644 --- a/tools/testing/selftests/ublk/utils.h +++ b/tools/testing/selftests/ublk/utils.h @@ -2,8 +2,6 @@ #ifndef KUBLK_UTILS_H #define KUBLK_UTILS_H -#define __maybe_unused __attribute__((unused)) - #ifndef min #define min(a, b) ((a) < (b) ? (a) : (b)) #endif diff --git a/tools/testing/shared/linux/maple_tree.h b/tools/testing/shared/linux/maple_tree.h index f67d47d32857..7d0fadef0f11 100644 --- a/tools/testing/shared/linux/maple_tree.h +++ b/tools/testing/shared/linux/maple_tree.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0+ */ -#define atomic_t int32_t -#define atomic_inc(x) uatomic_inc(x) -#define atomic_read(x) uatomic_read(x) -#define atomic_set(x, y) uatomic_set(x, y) +#include <linux/atomic.h> + #define U8_MAX UCHAR_MAX #include "../../../../include/linux/maple_tree.h" diff --git a/tools/testing/shared/shared.mk b/tools/testing/shared/shared.mk index 923ee2492256..5bcdf26c8a9d 100644 --- a/tools/testing/shared/shared.mk +++ b/tools/testing/shared/shared.mk @@ -1,7 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 +include ../../scripts/Makefile.arch -CFLAGS += -I../shared -I. -I../../include -I../../../lib -g -Og -Wall \ +CFLAGS += -I../shared -I. -I../../include -I../../arch/$(SRCARCH)/include \ + -I../../../lib -g -Og -Wall \ -D_LGPL_SOURCE -fsanitize=address -fsanitize=undefined +CFLAGS += $(EXTRA_CFLAGS) LDFLAGS += -fsanitize=address -fsanitize=undefined LDLIBS += -lpthread -lurcu LIBS := slab.o find_bit.o bitmap.o hweight.o vsprintf.o @@ -11,6 +14,7 @@ SHARED_DEPS = Makefile ../shared/shared.mk ../shared/*.h generated/map-shift.h \ generated/bit-length.h generated/autoconf.h \ ../../include/linux/*.h \ ../../include/asm/*.h \ + ../../arch/$(SRCARCH)/include/asm/*.h \ ../../../include/linux/xarray.h \ ../../../include/linux/maple_tree.h \ ../../../include/linux/radix-tree.h \ diff --git a/tools/testing/vma/linux/atomic.h b/tools/testing/vma/linux/atomic.h deleted file mode 100644 index 788c597c4fde..000000000000 --- a/tools/testing/vma/linux/atomic.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ - -#ifndef _LINUX_ATOMIC_H -#define _LINUX_ATOMIC_H - -#define atomic_t int32_t -#define atomic_inc(x) uatomic_inc(x) -#define atomic_read(x) uatomic_read(x) -#define atomic_set(x, y) uatomic_set(x, y) -#define U8_MAX UCHAR_MAX - -#ifndef atomic_cmpxchg_relaxed -#define atomic_cmpxchg_relaxed uatomic_cmpxchg -#define atomic_cmpxchg_release uatomic_cmpxchg -#endif /* atomic_cmpxchg_relaxed */ - -#endif /* _LINUX_ATOMIC_H */ diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h index 3639aa8dd2b0..437d2a1013be 100644 --- a/tools/testing/vma/vma_internal.h +++ b/tools/testing/vma/vma_internal.h @@ -21,6 +21,7 @@ #include <stdlib.h> +#include <linux/atomic.h> #include <linux/list.h> #include <linux/maple_tree.h> #include <linux/mm.h> @@ -249,6 +250,14 @@ struct mutex {}; #define DEFINE_MUTEX(mutexname) \ struct mutex mutexname = {} +#define DECLARE_BITMAP(name, bits) \ + unsigned long name[BITS_TO_LONGS(bits)] + +#define NUM_MM_FLAG_BITS (64) +typedef struct { + __private DECLARE_BITMAP(__mm_flags, NUM_MM_FLAG_BITS); +} mm_flags_t; + struct mm_struct { struct maple_tree mm_mt; int map_count; /* number of VMAs */ @@ -260,7 +269,7 @@ struct mm_struct { unsigned long def_flags; - unsigned long flags; /* Must use atomic bitops to access */ + mm_flags_t flags; /* Must use mm_flags_* helpers to access */ }; struct vm_area_struct; @@ -467,13 +476,21 @@ struct vm_operations_struct { struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); #endif +#ifdef CONFIG_FIND_NORMAL_PAGE /* - * Called by vm_normal_page() for special PTEs to find the - * page for @addr. This is useful if the default behavior - * (using pte_page()) would not find the correct page. + * Called by vm_normal_page() for special PTEs in @vma at @addr. This + * allows for returning a "normal" page from vm_normal_page() even + * though the PTE indicates that the "struct page" either does not exist + * or should not be touched: "special". + * + * Do not add new users: this really only works when a "normal" page + * was mapped, but then the PTE got changed to something weird (+ + * marked special) that would not make pte_pfn() identify the originally + * inserted page. */ - struct page *(*find_special_page)(struct vm_area_struct *vma, - unsigned long addr); + struct page *(*find_normal_page)(struct vm_area_struct *vma, + unsigned long addr); +#endif /* CONFIG_FIND_NORMAL_PAGE */ }; struct vm_unmapped_area_info { @@ -1325,6 +1342,13 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm, { } +# define ACCESS_PRIVATE(p, member) ((p)->member) + +static inline bool mm_flags_test(int flag, const struct mm_struct *mm) +{ + return test_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); +} + /* * Denies creating a writable executable mapping or gaining executable permissions. * @@ -1355,7 +1379,7 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm, static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { /* If MDWE is disabled, we have nothing to deny. */ - if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) + if (mm_flags_test(MMF_HAS_MDWE, current->mm)) return false; /* If the new VMA is not executable, we have nothing to deny. */ @@ -1375,15 +1399,8 @@ static inline bool map_deny_write_exec(unsigned long old, unsigned long new) static inline int mapping_map_writable(struct address_space *mapping) { - int c = atomic_read(&mapping->i_mmap_writable); - - /* Derived from the raw_atomic_inc_unless_negative() implementation. */ - do { - if (c < 0) - return -EPERM; - } while (!__sync_bool_compare_and_swap(&mapping->i_mmap_writable, c, c+1)); - - return 0; + return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? + 0 : -EPERM; } static inline unsigned long move_page_tables(struct pagetable_move_control *pmc) |