diff options
Diffstat (limited to 'tools/testing/selftests/filesystems')
54 files changed, 9837 insertions, 103 deletions
diff --git a/tools/testing/selftests/filesystems/.gitignore b/tools/testing/selftests/filesystems/.gitignore index 64ac0dfa46b7..9eb185fb2f9d 100644 --- a/tools/testing/selftests/filesystems/.gitignore +++ b/tools/testing/selftests/filesystems/.gitignore @@ -5,3 +5,5 @@ fclog file_stressor anon_inode_test kernfs_test +idmapped_tmpfile +ustat_test diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile index 85427d7f19b9..03be337c1f35 100644 --- a/tools/testing/selftests/filesystems/Makefile +++ b/tools/testing/selftests/filesystems/Makefile @@ -1,7 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += $(KHDR_INCLUDES) -TEST_GEN_PROGS := devpts_pts file_stressor anon_inode_test kernfs_test fclog +TEST_GEN_PROGS := devpts_pts file_stressor anon_inode_test kernfs_test fclog ustat_test +TEST_GEN_PROGS += idmapped_tmpfile TEST_GEN_PROGS_EXTENDED := dnotify_test include ../lib.mk + +$(OUTPUT)/idmapped_tmpfile: LDLIBS += -lcap +$(OUTPUT)/idmapped_tmpfile: utils.c diff --git a/tools/testing/selftests/filesystems/anon_inode_test.c b/tools/testing/selftests/filesystems/anon_inode_test.c index 94c6c81c2301..2c4c50500116 100644 --- a/tools/testing/selftests/filesystems/anon_inode_test.c +++ b/tools/testing/selftests/filesystems/anon_inode_test.c @@ -42,7 +42,10 @@ TEST(anon_inode_no_exec) fd_context = sys_fsopen("tmpfs", 0); ASSERT_GE(fd_context, 0); - ASSERT_LT(execveat(fd_context, "", NULL, NULL, AT_EMPTY_PATH), 0); + char *const empty_argv[] = {NULL}; + char *const empty_envp[] = {NULL}; + + ASSERT_LT(execveat(fd_context, "", empty_argv, empty_envp, AT_EMPTY_PATH), 0); ASSERT_EQ(errno, EACCES); EXPECT_EQ(close(fd_context), 0); diff --git a/tools/testing/selftests/filesystems/devpts_pts.c b/tools/testing/selftests/filesystems/devpts_pts.c index 54fea349204e..aa8d5324f2a6 100644 --- a/tools/testing/selftests/filesystems/devpts_pts.c +++ b/tools/testing/selftests/filesystems/devpts_pts.c @@ -119,9 +119,7 @@ static int do_tiocgptpeer(char *ptmx, char *expected_procfd_contents) goto do_cleanup; } -#ifdef TIOCGPTPEER slave = ioctl(master, TIOCGPTPEER, O_RDWR | O_NOCTTY | O_CLOEXEC); -#endif if (slave < 0) { if (errno == EINVAL) { fprintf(stderr, "TIOCGPTPEER is not supported. " diff --git a/tools/testing/selftests/filesystems/empty_mntns/.gitignore b/tools/testing/selftests/filesystems/empty_mntns/.gitignore new file mode 100644 index 000000000000..99f89d329db2 --- /dev/null +++ b/tools/testing/selftests/filesystems/empty_mntns/.gitignore @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only +clone3_empty_mntns_test +empty_mntns_test +overmount_chroot_test diff --git a/tools/testing/selftests/filesystems/empty_mntns/Makefile b/tools/testing/selftests/filesystems/empty_mntns/Makefile new file mode 100644 index 000000000000..22e3fb915e81 --- /dev/null +++ b/tools/testing/selftests/filesystems/empty_mntns/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0-or-later + +CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES) +LDLIBS += -lcap + +TEST_GEN_PROGS := empty_mntns_test overmount_chroot_test clone3_empty_mntns_test + +include ../../lib.mk + +$(OUTPUT)/empty_mntns_test: ../utils.c +$(OUTPUT)/overmount_chroot_test: ../utils.c +$(OUTPUT)/clone3_empty_mntns_test: ../utils.c diff --git a/tools/testing/selftests/filesystems/empty_mntns/clone3_empty_mntns_test.c b/tools/testing/selftests/filesystems/empty_mntns/clone3_empty_mntns_test.c new file mode 100644 index 000000000000..6370086f886d --- /dev/null +++ b/tools/testing/selftests/filesystems/empty_mntns/clone3_empty_mntns_test.c @@ -0,0 +1,938 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Tests for empty mount namespace creation via clone3() CLONE_EMPTY_MNTNS + * + * These tests exercise the clone3() code path for creating empty mount + * namespaces, which is distinct from the unshare() path tested in + * empty_mntns_test.c. With clone3(), CLONE_EMPTY_MNTNS (0x2000000000ULL) + * is a 64-bit flag that implies CLONE_NEWNS. The implication happens in + * kernel_clone() before copy_process(), unlike unshare() where it goes + * through UNSHARE_EMPTY_MNTNS -> CLONE_EMPTY_MNTNS conversion in + * unshare_nsproxy_namespaces(). + * + * Copyright (c) 2024 Christian Brauner <brauner@kernel.org> + */ + +#define _GNU_SOURCE +#include <fcntl.h> +#include <linux/mount.h> +#include <linux/stat.h> +#include <stdio.h> +#include <string.h> +#include <sys/mount.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> + +#include "../utils.h" +#include "../wrappers.h" +#include "clone3/clone3_selftests.h" +#include "empty_mntns.h" +#include "kselftest_harness.h" + +static pid_t clone3_empty_mntns(uint64_t extra_flags) +{ + struct __clone_args args = { + .flags = CLONE_EMPTY_MNTNS | extra_flags, + .exit_signal = SIGCHLD, + }; + + return sys_clone3(&args, sizeof(args)); +} + +static bool clone3_empty_mntns_supported(void) +{ + pid_t pid; + int status; + + pid = fork(); + if (pid < 0) + return false; + + if (pid == 0) { + if (enter_userns()) + _exit(1); + + pid = clone3_empty_mntns(0); + if (pid < 0) + _exit(1); + + if (pid == 0) + _exit(0); + + _exit(wait_for_pid(pid) != 0); + } + + if (waitpid(pid, &status, 0) != pid) + return false; + + if (!WIFEXITED(status)) + return false; + + return WEXITSTATUS(status) == 0; +} + +FIXTURE(clone3_empty_mntns) {}; + +FIXTURE_SETUP(clone3_empty_mntns) +{ + if (!clone3_empty_mntns_supported()) + SKIP(return, "CLONE_EMPTY_MNTNS via clone3 not supported"); +} + +FIXTURE_TEARDOWN(clone3_empty_mntns) {} + +/* + * Basic clone3() with CLONE_EMPTY_MNTNS: child gets empty mount namespace + * with exactly 1 mount and root == cwd. + */ +TEST_F(clone3_empty_mntns, basic) +{ + pid_t pid, inner; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + if (enter_userns()) + _exit(1); + + inner = clone3_empty_mntns(0); + if (inner < 0) + _exit(2); + + if (inner == 0) { + uint64_t root_id, cwd_id; + + if (count_mounts() != 1) + _exit(3); + + root_id = get_unique_mnt_id("/"); + cwd_id = get_unique_mnt_id("."); + if (root_id == 0 || cwd_id == 0) + _exit(4); + + if (root_id != cwd_id) + _exit(5); + + _exit(0); + } + + _exit(wait_for_pid(inner)); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * CLONE_EMPTY_MNTNS implies CLONE_NEWNS. Verify that it works without + * explicitly setting CLONE_NEWNS (tests fork.c:2627-2630). + */ +TEST_F(clone3_empty_mntns, implies_newns) +{ + pid_t pid, inner; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ssize_t parent_mounts; + + if (enter_userns()) + _exit(1); + + /* Verify we have mounts in our current namespace. */ + parent_mounts = count_mounts(); + if (parent_mounts < 1) + _exit(2); + + /* Only CLONE_EMPTY_MNTNS, no explicit CLONE_NEWNS. */ + inner = clone3_empty_mntns(0); + if (inner < 0) + _exit(3); + + if (inner == 0) { + if (count_mounts() != 1) + _exit(4); + + _exit(0); + } + + /* Parent still has its mounts. */ + if (count_mounts() != parent_mounts) + _exit(5); + + _exit(wait_for_pid(inner)); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * Helper macro: generate a test that clones with CLONE_EMPTY_MNTNS | + * @extra_flags and verifies the child has exactly one mount. + */ +#define TEST_CLONE3_FLAGS(test_name, extra_flags) \ +TEST_F(clone3_empty_mntns, test_name) \ +{ \ + pid_t pid, inner; \ + \ + pid = fork(); \ + ASSERT_GE(pid, 0); \ + \ + if (pid == 0) { \ + if (enter_userns()) \ + _exit(1); \ + \ + inner = clone3_empty_mntns(extra_flags); \ + if (inner < 0) \ + _exit(2); \ + \ + if (inner == 0) { \ + if (count_mounts() != 1) \ + _exit(3); \ + _exit(0); \ + } \ + \ + _exit(wait_for_pid(inner)); \ + } \ + \ + ASSERT_EQ(wait_for_pid(pid), 0); \ +} + +/* Redundant CLONE_NEWNS | CLONE_EMPTY_MNTNS should succeed. */ +TEST_CLONE3_FLAGS(with_explicit_newns, CLONE_NEWNS) + +/* CLONE_EMPTY_MNTNS combined with CLONE_NEWUSER. */ +TEST_CLONE3_FLAGS(with_newuser, CLONE_NEWUSER) + +/* CLONE_EMPTY_MNTNS combined with other namespace flags. */ +TEST_CLONE3_FLAGS(with_other_ns_flags, CLONE_NEWUTS | CLONE_NEWIPC) + +/* + * CLONE_EMPTY_MNTNS combined with CLONE_NEWPID. + */ +TEST_F(clone3_empty_mntns, with_newpid) +{ + pid_t pid, inner; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + if (enter_userns()) + _exit(1); + + inner = clone3_empty_mntns(CLONE_NEWPID); + if (inner < 0) + _exit(2); + + if (inner == 0) { + if (count_mounts() != 1) + _exit(3); + + /* In a new PID namespace, getpid() returns 1. */ + if (getpid() != 1) + _exit(4); + + _exit(0); + } + + _exit(wait_for_pid(inner)); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * CLONE_EMPTY_MNTNS | CLONE_FS must fail because the implied CLONE_NEWNS + * and CLONE_FS are mutually exclusive (fork.c:1981). + */ +TEST_F(clone3_empty_mntns, with_clone_fs_fails) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + struct __clone_args args = { + .flags = CLONE_EMPTY_MNTNS | CLONE_FS, + .exit_signal = SIGCHLD, + }; + pid_t ret; + + if (enter_userns()) + _exit(1); + + ret = sys_clone3(&args, sizeof(args)); + if (ret >= 0) { + if (ret == 0) + _exit(0); + wait_for_pid(ret); + _exit(2); + } + + if (errno != EINVAL) + _exit(3); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * CLONE_EMPTY_MNTNS combined with CLONE_PIDFD returns a valid pidfd. + */ +TEST_F(clone3_empty_mntns, with_pidfd) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + struct __clone_args args = { + .flags = CLONE_EMPTY_MNTNS | CLONE_PIDFD, + .exit_signal = SIGCHLD, + }; + int pidfd = -1; + pid_t inner; + + if (enter_userns()) + _exit(1); + + args.pidfd = (uintptr_t)&pidfd; + + inner = sys_clone3(&args, sizeof(args)); + if (inner < 0) + _exit(2); + + if (inner == 0) { + if (count_mounts() != 1) + _exit(3); + + _exit(0); + } + + /* Verify we got a valid pidfd. */ + if (pidfd < 0) + _exit(4); + + close(pidfd); + _exit(wait_for_pid(inner)); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * clone3 without CAP_SYS_ADMIN must fail with EPERM. + */ +TEST_F(clone3_empty_mntns, eperm_without_caps) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + pid_t ret; + + /* Skip if already root. */ + if (getuid() == 0) + _exit(0); + + ret = clone3_empty_mntns(0); + if (ret >= 0) { + if (ret == 0) + _exit(0); + wait_for_pid(ret); + _exit(1); + } + + if (errno != EPERM) + _exit(2); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * Parent's mount namespace is unaffected after clone3 with CLONE_EMPTY_MNTNS. + */ +TEST_F(clone3_empty_mntns, parent_unchanged) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ssize_t nr_before, nr_after; + pid_t inner; + + if (enter_userns()) + _exit(1); + + nr_before = count_mounts(); + if (nr_before < 1) + _exit(2); + + inner = clone3_empty_mntns(0); + if (inner < 0) + _exit(3); + + if (inner == 0) + _exit(0); + + if (wait_for_pid(inner) != 0) + _exit(4); + + nr_after = count_mounts(); + if (nr_after != nr_before) + _exit(5); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * Parent with many mounts: child still gets exactly 1 mount. + */ +TEST_F(clone3_empty_mntns, many_parent_mounts) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + char tmpdir[] = "/tmp/clone3_mntns_test.XXXXXX"; + pid_t inner; + int i; + + if (enter_userns()) + _exit(1); + + if (unshare(CLONE_NEWNS)) + _exit(2); + + if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL)) + _exit(3); + + if (!mkdtemp(tmpdir)) + _exit(4); + + if (mount("tmpfs", tmpdir, "tmpfs", 0, "size=1M")) + _exit(5); + + for (i = 0; i < 5; i++) { + char subdir[256]; + + snprintf(subdir, sizeof(subdir), "%s/sub%d", tmpdir, i); + if (mkdir(subdir, 0755) && errno != EEXIST) + _exit(6); + if (mount(subdir, subdir, NULL, MS_BIND, NULL)) + _exit(7); + } + + if (count_mounts() < 5) + _exit(8); + + inner = clone3_empty_mntns(0); + if (inner < 0) + _exit(9); + + if (inner == 0) { + if (count_mounts() != 1) + _exit(10); + + _exit(0); + } + + _exit(wait_for_pid(inner)); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * Verify the child's root mount is nullfs with expected statmount properties. + */ +TEST_F(clone3_empty_mntns, mount_properties) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + pid_t inner; + + if (enter_userns()) + _exit(1); + + inner = clone3_empty_mntns(0); + if (inner < 0) + _exit(2); + + if (inner == 0) { + struct statmount *sm; + uint64_t root_id; + + root_id = get_unique_mnt_id("/"); + if (!root_id) + _exit(3); + + sm = statmount_alloc(root_id, 0, + STATMOUNT_MNT_BASIC | + STATMOUNT_MNT_POINT | + STATMOUNT_FS_TYPE, 0); + if (!sm) + _exit(4); + + /* Root mount point is "/". */ + if (!(sm->mask & STATMOUNT_MNT_POINT)) + _exit(5); + if (strcmp(sm->str + sm->mnt_point, "/") != 0) + _exit(6); + + /* Filesystem type is nullfs. */ + if (!(sm->mask & STATMOUNT_FS_TYPE)) + _exit(7); + if (strcmp(sm->str + sm->fs_type, "nullfs") != 0) + _exit(8); + + /* Root mount is its own parent. */ + if (!(sm->mask & STATMOUNT_MNT_BASIC)) + _exit(9); + if (sm->mnt_parent_id != sm->mnt_id) + _exit(10); + + free(sm); + _exit(0); + } + + _exit(wait_for_pid(inner)); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * Listmount returns only the root mount in the child's empty namespace. + */ +TEST_F(clone3_empty_mntns, listmount_single_entry) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + pid_t inner; + + if (enter_userns()) + _exit(1); + + inner = clone3_empty_mntns(0); + if (inner < 0) + _exit(2); + + if (inner == 0) { + uint64_t list[16]; + ssize_t nr_mounts; + uint64_t root_id; + + nr_mounts = listmount(LSMT_ROOT, 0, 0, list, 16, 0); + if (nr_mounts != 1) + _exit(3); + + root_id = get_unique_mnt_id("/"); + if (!root_id) + _exit(4); + + if (list[0] != root_id) + _exit(5); + + _exit(0); + } + + _exit(wait_for_pid(inner)); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * Child can mount tmpfs over nullfs root (the primary container use case). + * + * Uses the new mount API (fsopen/fsmount/move_mount) because resolving + * "/" returns the process root directly without following overmounts. + * The mount fd from fsmount lets us fchdir + chroot into the new tmpfs. + */ +TEST_F(clone3_empty_mntns, child_overmount_tmpfs) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + pid_t inner; + + if (enter_userns()) + _exit(1); + + inner = clone3_empty_mntns(0); + if (inner < 0) + _exit(2); + + if (inner == 0) { + struct statmount *sm; + uint64_t root_id; + int fd, fsfd, mntfd; + + if (count_mounts() != 1) + _exit(3); + + /* Verify root is nullfs. */ + root_id = get_unique_mnt_id("/"); + if (!root_id) + _exit(4); + + sm = statmount_alloc(root_id, 0, STATMOUNT_FS_TYPE, 0); + if (!sm) + _exit(5); + if (!(sm->mask & STATMOUNT_FS_TYPE)) + _exit(6); + if (strcmp(sm->str + sm->fs_type, "nullfs") != 0) + _exit(7); + free(sm); + + /* Create tmpfs via the new mount API. */ + fsfd = sys_fsopen("tmpfs", 0); + if (fsfd < 0) + _exit(8); + + if (sys_fsconfig(fsfd, FSCONFIG_SET_STRING, + "size", "1M", 0)) { + close(fsfd); + _exit(9); + } + + if (sys_fsconfig(fsfd, FSCONFIG_CMD_CREATE, + NULL, NULL, 0)) { + close(fsfd); + _exit(10); + } + + mntfd = sys_fsmount(fsfd, 0, 0); + close(fsfd); + if (mntfd < 0) + _exit(11); + + /* Attach tmpfs to "/". */ + if (sys_move_mount(mntfd, "", AT_FDCWD, "/", + MOVE_MOUNT_F_EMPTY_PATH)) { + close(mntfd); + _exit(12); + } + + if (count_mounts() != 2) { + close(mntfd); + _exit(13); + } + + /* Enter the tmpfs. */ + if (fchdir(mntfd)) { + close(mntfd); + _exit(14); + } + + if (chroot(".")) { + close(mntfd); + _exit(15); + } + + close(mntfd); + + /* Verify "/" is now tmpfs. */ + root_id = get_unique_mnt_id("/"); + if (!root_id) + _exit(16); + + sm = statmount_alloc(root_id, 0, STATMOUNT_FS_TYPE, 0); + if (!sm) + _exit(17); + if (!(sm->mask & STATMOUNT_FS_TYPE)) + _exit(18); + if (strcmp(sm->str + sm->fs_type, "tmpfs") != 0) + _exit(19); + free(sm); + + /* Verify tmpfs is writable. */ + fd = open("/testfile", O_CREAT | O_RDWR, 0644); + if (fd < 0) + _exit(20); + + if (write(fd, "test", 4) != 4) { + close(fd); + _exit(21); + } + close(fd); + + if (access("/testfile", F_OK)) + _exit(22); + + _exit(0); + } + + _exit(wait_for_pid(inner)); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * Multiple clone3 calls with CLONE_EMPTY_MNTNS produce children with + * distinct mount namespace root mount IDs. + */ +TEST_F(clone3_empty_mntns, repeated) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + int pipe1[2], pipe2[2]; + uint64_t id1 = 0, id2 = 0; + pid_t inner1, inner2; + + if (enter_userns()) + _exit(1); + + if (pipe(pipe1) || pipe(pipe2)) + _exit(2); + + inner1 = clone3_empty_mntns(0); + if (inner1 < 0) + _exit(3); + + if (inner1 == 0) { + uint64_t root_id; + + close(pipe1[0]); + root_id = get_unique_mnt_id("/"); + if (write(pipe1[1], &root_id, sizeof(root_id)) != sizeof(root_id)) + _exit(1); + close(pipe1[1]); + _exit(0); + } + + inner2 = clone3_empty_mntns(0); + if (inner2 < 0) + _exit(4); + + if (inner2 == 0) { + uint64_t root_id; + + close(pipe2[0]); + root_id = get_unique_mnt_id("/"); + if (write(pipe2[1], &root_id, sizeof(root_id)) != sizeof(root_id)) + _exit(1); + close(pipe2[1]); + _exit(0); + } + + close(pipe1[1]); + close(pipe2[1]); + + if (read(pipe1[0], &id1, sizeof(id1)) != sizeof(id1)) + _exit(5); + if (read(pipe2[0], &id2, sizeof(id2)) != sizeof(id2)) + _exit(6); + + close(pipe1[0]); + close(pipe2[0]); + + if (wait_for_pid(inner1) || wait_for_pid(inner2)) + _exit(7); + + /* Each child must have a distinct root mount ID. */ + if (id1 == 0 || id2 == 0) + _exit(8); + if (id1 == id2) + _exit(9); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * Verify setns() into a child's empty mount namespace works. + */ +TEST_F(clone3_empty_mntns, setns_into_child_mntns) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + int pipe_fd[2]; + pid_t inner; + char c; + + if (enter_userns()) + _exit(1); + + if (pipe(pipe_fd)) + _exit(2); + + inner = clone3_empty_mntns(0); + if (inner < 0) + _exit(3); + + if (inner == 0) { + /* Signal parent we're ready. */ + close(pipe_fd[0]); + if (write(pipe_fd[1], "r", 1) != 1) + _exit(1); + + /* + * Wait for parent to finish. Reading from our + * write end will block until the parent closes + * its read end, giving us an implicit barrier. + */ + if (read(pipe_fd[1], &c, 1) < 0) + ; + close(pipe_fd[1]); + _exit(0); + } + + close(pipe_fd[1]); + + /* Wait for child to be ready. */ + if (read(pipe_fd[0], &c, 1) != 1) + _exit(4); + + /* Open child's mount namespace. */ + { + char path[64]; + int mntns_fd; + + snprintf(path, sizeof(path), "/proc/%d/ns/mnt", inner); + mntns_fd = open(path, O_RDONLY); + if (mntns_fd < 0) + _exit(5); + + if (setns(mntns_fd, CLONE_NEWNS)) + _exit(6); + + close(mntns_fd); + } + + /* Now we should be in the child's empty mntns. */ + if (count_mounts() != 1) + _exit(7); + + close(pipe_fd[0]); + _exit(wait_for_pid(inner)); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * Tests below do not require CLONE_EMPTY_MNTNS support. + */ + +/* + * Unknown 64-bit flags beyond the known set are rejected. + */ +TEST(unknown_flags_rejected) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + struct __clone_args args = { + .flags = 0x800000000ULL, + .exit_signal = SIGCHLD, + }; + pid_t ret; + + ret = sys_clone3(&args, sizeof(args)); + if (ret >= 0) { + if (ret == 0) + _exit(0); + wait_for_pid(ret); + _exit(1); + } + + if (errno != EINVAL) + _exit(2); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * Regular clone3 with CLONE_NEWNS (without CLONE_EMPTY_MNTNS) still + * copies the full mount tree. + */ +TEST(clone3_newns_full_copy) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + struct __clone_args args = { + .flags = CLONE_NEWNS, + .exit_signal = SIGCHLD, + }; + ssize_t parent_mounts; + pid_t inner; + + if (enter_userns()) + _exit(1); + + parent_mounts = count_mounts(); + if (parent_mounts < 1) + _exit(2); + + inner = sys_clone3(&args, sizeof(args)); + if (inner < 0) + _exit(3); + + if (inner == 0) { + /* Full copy should have at least as many mounts. */ + if (count_mounts() < parent_mounts) + _exit(1); + + _exit(0); + } + + _exit(wait_for_pid(inner)); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/empty_mntns/empty_mntns.h b/tools/testing/selftests/filesystems/empty_mntns/empty_mntns.h new file mode 100644 index 000000000000..3d9c6b14bbef --- /dev/null +++ b/tools/testing/selftests/filesystems/empty_mntns/empty_mntns.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef EMPTY_MNTNS_H +#define EMPTY_MNTNS_H + +#include <errno.h> +#include <stdlib.h> + +#include "../statmount/statmount.h" + +#ifndef UNSHARE_EMPTY_MNTNS +#define UNSHARE_EMPTY_MNTNS 0x00100000 +#endif + +#ifndef CLONE_EMPTY_MNTNS +#define CLONE_EMPTY_MNTNS (1ULL << 37) +#endif + +static inline ssize_t count_mounts(void) +{ + uint64_t list[4096]; + + return listmount(LSMT_ROOT, 0, 0, list, sizeof(list) / sizeof(list[0]), 0); +} + +#endif /* EMPTY_MNTNS_H */ diff --git a/tools/testing/selftests/filesystems/empty_mntns/empty_mntns_test.c b/tools/testing/selftests/filesystems/empty_mntns/empty_mntns_test.c new file mode 100644 index 000000000000..43e296b97d84 --- /dev/null +++ b/tools/testing/selftests/filesystems/empty_mntns/empty_mntns_test.c @@ -0,0 +1,725 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Tests for empty mount namespace creation via UNSHARE_EMPTY_MNTNS + * + * Copyright (c) 2024 Christian Brauner <brauner@kernel.org> + */ + +#define _GNU_SOURCE +#include <fcntl.h> +#include <linux/mount.h> +#include <linux/stat.h> +#include <sched.h> +#include <stdio.h> +#include <string.h> +#include <sys/mount.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "../utils.h" +#include "../wrappers.h" +#include "empty_mntns.h" +#include "kselftest_harness.h" + +static bool unshare_empty_mntns_supported(void) +{ + pid_t pid; + int status; + + pid = fork(); + if (pid < 0) + return false; + + if (pid == 0) { + if (enter_userns()) + _exit(1); + + if (unshare(UNSHARE_EMPTY_MNTNS) && errno == EINVAL) + _exit(1); + _exit(0); + } + + if (waitpid(pid, &status, 0) != pid) + return false; + + if (!WIFEXITED(status)) + return false; + + return WEXITSTATUS(status) == 0; +} + + +FIXTURE(empty_mntns) {}; + +FIXTURE_SETUP(empty_mntns) +{ + if (!unshare_empty_mntns_supported()) + SKIP(return, "UNSHARE_EMPTY_MNTNS not supported"); +} + +FIXTURE_TEARDOWN(empty_mntns) {} + +/* Verify unshare succeeds, produces exactly 1 mount, and root == cwd */ +TEST_F(empty_mntns, basic) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + uint64_t root_id, cwd_id; + + if (enter_userns()) + _exit(1); + + if (unshare(UNSHARE_EMPTY_MNTNS)) + _exit(2); + + if (count_mounts() != 1) + _exit(3); + + root_id = get_unique_mnt_id("/"); + cwd_id = get_unique_mnt_id("."); + if (root_id == 0 || cwd_id == 0) + _exit(4); + + if (root_id != cwd_id) + _exit(5); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * UNSHARE_EMPTY_MNTNS combined with CLONE_NEWUSER. + * + * The user namespace must be created first so /proc is still accessible + * for writing uid_map/gid_map. The empty mount namespace is created + * afterwards. + */ +TEST_F(empty_mntns, with_clone_newuser) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + uid_t uid = getuid(); + gid_t gid = getgid(); + char map[100]; + + if (unshare(CLONE_NEWUSER)) + _exit(1); + + snprintf(map, sizeof(map), "0 %d 1", uid); + if (write_file("/proc/self/uid_map", map)) + _exit(2); + + if (write_file("/proc/self/setgroups", "deny")) + _exit(3); + + snprintf(map, sizeof(map), "0 %d 1", gid); + if (write_file("/proc/self/gid_map", map)) + _exit(4); + + if (unshare(UNSHARE_EMPTY_MNTNS)) + _exit(5); + + if (count_mounts() != 1) + _exit(6); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* UNSHARE_EMPTY_MNTNS combined with other namespace flags */ +TEST_F(empty_mntns, with_other_ns_flags) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + if (enter_userns()) + _exit(1); + + if (unshare(UNSHARE_EMPTY_MNTNS | CLONE_NEWUTS | CLONE_NEWIPC)) + _exit(2); + + if (count_mounts() != 1) + _exit(3); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* EPERM without proper capabilities */ +TEST_F(empty_mntns, eperm_without_caps) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + /* Skip if already root */ + if (getuid() == 0) + _exit(0); + + if (unshare(UNSHARE_EMPTY_MNTNS) == 0) + _exit(1); + + if (errno != EPERM) + _exit(2); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* Many source mounts still result in exactly 1 mount */ +TEST_F(empty_mntns, many_source_mounts) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + char tmpdir[] = "/tmp/empty_mntns_test.XXXXXX"; + int i; + + if (enter_userns()) + _exit(1); + + if (unshare(CLONE_NEWNS)) + _exit(2); + + if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL)) + _exit(3); + + if (!mkdtemp(tmpdir)) + _exit(4); + + if (mount("tmpfs", tmpdir, "tmpfs", 0, "size=1M")) + _exit(5); + + for (i = 0; i < 5; i++) { + char subdir[256]; + + snprintf(subdir, sizeof(subdir), "%s/sub%d", tmpdir, i); + if (mkdir(subdir, 0755) && errno != EEXIST) + _exit(6); + if (mount(subdir, subdir, NULL, MS_BIND, NULL)) + _exit(7); + } + + if (count_mounts() < 5) + _exit(8); + + if (unshare(UNSHARE_EMPTY_MNTNS)) + _exit(9); + + if (count_mounts() != 1) + _exit(10); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* CWD on a different mount gets reset to root */ +TEST_F(empty_mntns, cwd_reset) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + char tmpdir[] = "/tmp/empty_mntns_cwd.XXXXXX"; + uint64_t root_id, cwd_id; + struct statmount *sm; + + if (enter_userns()) + _exit(1); + + if (unshare(CLONE_NEWNS)) + _exit(2); + + if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL)) + _exit(3); + + if (!mkdtemp(tmpdir)) + _exit(4); + + if (mount("tmpfs", tmpdir, "tmpfs", 0, "size=1M")) + _exit(5); + + if (chdir(tmpdir)) + _exit(6); + + if (unshare(UNSHARE_EMPTY_MNTNS)) + _exit(7); + + root_id = get_unique_mnt_id("/"); + cwd_id = get_unique_mnt_id("."); + if (root_id == 0 || cwd_id == 0) + _exit(8); + + if (root_id != cwd_id) + _exit(9); + + sm = statmount_alloc(root_id, 0, STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT, 0); + if (!sm) + _exit(10); + + if (strcmp(sm->str + sm->mnt_point, "/") != 0) + _exit(11); + + free(sm); + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* Verify statmount properties of the root mount */ +TEST_F(empty_mntns, mount_properties) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + struct statmount *sm; + uint64_t root_id; + + if (enter_userns()) + _exit(1); + + if (unshare(UNSHARE_EMPTY_MNTNS)) + _exit(2); + + root_id = get_unique_mnt_id("/"); + if (!root_id) + _exit(3); + + sm = statmount_alloc(root_id, 0, STATMOUNT_MNT_BASIC | STATMOUNT_MNT_ROOT | + STATMOUNT_MNT_POINT | STATMOUNT_FS_TYPE, 0); + if (!sm) + _exit(4); + + if (!(sm->mask & STATMOUNT_MNT_POINT)) + _exit(5); + + if (strcmp(sm->str + sm->mnt_point, "/") != 0) + _exit(6); + + if (!(sm->mask & STATMOUNT_MNT_BASIC)) + _exit(7); + + if (sm->mnt_id != root_id) + _exit(8); + + free(sm); + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* Consecutive UNSHARE_EMPTY_MNTNS calls produce new namespaces */ +TEST_F(empty_mntns, repeated_unshare) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + uint64_t first_root_id, second_root_id; + + if (enter_userns()) + _exit(1); + + if (unshare(UNSHARE_EMPTY_MNTNS)) + _exit(2); + + if (count_mounts() != 1) + _exit(3); + + first_root_id = get_unique_mnt_id("/"); + + if (unshare(UNSHARE_EMPTY_MNTNS)) + _exit(4); + + if (count_mounts() != 1) + _exit(5); + + second_root_id = get_unique_mnt_id("/"); + + if (first_root_id == second_root_id) + _exit(6); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* Root mount's parent is itself */ +TEST_F(empty_mntns, root_is_own_parent) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + struct statmount sm; + uint64_t root_id; + + if (enter_userns()) + _exit(1); + + if (unshare(UNSHARE_EMPTY_MNTNS)) + _exit(2); + + root_id = get_unique_mnt_id("/"); + if (!root_id) + _exit(3); + + if (statmount(root_id, 0, 0, STATMOUNT_MNT_BASIC, &sm, sizeof(sm), 0) < 0) + _exit(4); + + if (!(sm.mask & STATMOUNT_MNT_BASIC)) + _exit(5); + + if (sm.mnt_parent_id != sm.mnt_id) + _exit(6); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* Listmount returns only the root mount */ +TEST_F(empty_mntns, listmount_single_entry) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + uint64_t list[16]; + ssize_t nr_mounts; + uint64_t root_id; + + if (enter_userns()) + _exit(1); + + if (unshare(UNSHARE_EMPTY_MNTNS)) + _exit(2); + + nr_mounts = listmount(LSMT_ROOT, 0, 0, list, 16, 0); + if (nr_mounts != 1) + _exit(3); + + root_id = get_unique_mnt_id("/"); + if (!root_id) + _exit(4); + + if (list[0] != root_id) + _exit(5); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * Mount tmpfs over nullfs root to build a writable filesystem from scratch. + * This exercises the intended usage pattern: create an empty mount namespace + * (which has a nullfs root), then mount a real filesystem over it. + * + * Because resolving "/" returns the process root directly (via nd_jump_root) + * without following overmounts, we use the new mount API (fsopen/fsmount) + * to obtain a mount fd, then fchdir + chroot to enter the new filesystem. + */ +TEST_F(empty_mntns, overmount_tmpfs) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + struct statmount *sm; + uint64_t root_id, cwd_id; + int fd, fsfd, mntfd; + + if (enter_userns()) + _exit(1); + + if (unshare(UNSHARE_EMPTY_MNTNS)) + _exit(2); + + if (count_mounts() != 1) + _exit(3); + + root_id = get_unique_mnt_id("/"); + if (!root_id) + _exit(4); + + /* Verify root is nullfs */ + sm = statmount_alloc(root_id, 0, STATMOUNT_FS_TYPE, 0); + if (!sm) + _exit(5); + + if (!(sm->mask & STATMOUNT_FS_TYPE)) + _exit(6); + + if (strcmp(sm->str + sm->fs_type, "nullfs") != 0) + _exit(7); + + free(sm); + + cwd_id = get_unique_mnt_id("."); + if (!cwd_id || root_id != cwd_id) + _exit(8); + + /* + * nullfs root is immutable. open(O_CREAT) returns ENOENT + * because empty_dir_lookup() returns -ENOENT before the + * IS_IMMUTABLE permission check in may_o_create() is reached. + */ + fd = open("/test", O_CREAT | O_RDWR, 0644); + if (fd >= 0) { + close(fd); + _exit(9); + } + if (errno != ENOENT) + _exit(10); + + /* + * Use the new mount API to create tmpfs and get a mount fd. + * We need the fd because after attaching the tmpfs on top of + * "/", path resolution of "/" still returns the process root + * (nullfs) without following the overmount. The mount fd + * lets us fchdir + chroot into the tmpfs. + */ + fsfd = sys_fsopen("tmpfs", 0); + if (fsfd < 0) + _exit(11); + + if (sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "size", "1M", 0)) { + close(fsfd); + _exit(12); + } + + if (sys_fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0)) { + close(fsfd); + _exit(13); + } + + mntfd = sys_fsmount(fsfd, 0, 0); + close(fsfd); + if (mntfd < 0) + _exit(14); + + if (sys_move_mount(mntfd, "", AT_FDCWD, "/", + MOVE_MOUNT_F_EMPTY_PATH)) { + close(mntfd); + _exit(15); + } + + if (count_mounts() != 2) { + close(mntfd); + _exit(16); + } + + /* Enter the tmpfs via the mount fd */ + if (fchdir(mntfd)) { + close(mntfd); + _exit(17); + } + + if (chroot(".")) { + close(mntfd); + _exit(18); + } + + close(mntfd); + + /* Verify "/" now resolves to tmpfs */ + root_id = get_unique_mnt_id("/"); + if (!root_id) + _exit(19); + + sm = statmount_alloc(root_id, 0, STATMOUNT_FS_TYPE, 0); + if (!sm) + _exit(20); + + if (!(sm->mask & STATMOUNT_FS_TYPE)) + _exit(21); + + if (strcmp(sm->str + sm->fs_type, "tmpfs") != 0) + _exit(22); + + free(sm); + + /* Verify tmpfs is writable */ + fd = open("/testfile", O_CREAT | O_RDWR, 0644); + if (fd < 0) + _exit(23); + + if (write(fd, "test", 4) != 4) { + close(fd); + _exit(24); + } + + close(fd); + + if (access("/testfile", F_OK)) + _exit(25); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* + * Tests below do not require UNSHARE_EMPTY_MNTNS support. + */ + +/* Invalid unshare flags return EINVAL */ +TEST(invalid_flags) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + if (enter_userns()) + _exit(1); + + if (unshare(0x80000000) == 0) + _exit(2); + + if (errno != EINVAL) + _exit(3); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* Regular CLONE_NEWNS still copies the full mount tree */ +TEST(clone_newns_full_copy) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ssize_t nr_mounts_before, nr_mounts_after; + char tmpdir[] = "/tmp/empty_mntns_regr.XXXXXX"; + int i; + + if (enter_userns()) + _exit(1); + + if (unshare(CLONE_NEWNS)) + _exit(2); + + if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL)) + _exit(3); + + if (!mkdtemp(tmpdir)) + _exit(4); + + if (mount("tmpfs", tmpdir, "tmpfs", 0, "size=1M")) + _exit(5); + + for (i = 0; i < 3; i++) { + char subdir[256]; + + snprintf(subdir, sizeof(subdir), "%s/sub%d", tmpdir, i); + if (mkdir(subdir, 0755) && errno != EEXIST) + _exit(6); + if (mount(subdir, subdir, NULL, MS_BIND, NULL)) + _exit(7); + } + + nr_mounts_before = count_mounts(); + if (nr_mounts_before < 3) + _exit(8); + + if (unshare(CLONE_NEWNS)) + _exit(9); + + nr_mounts_after = count_mounts(); + if (nr_mounts_after < nr_mounts_before) + _exit(10); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +/* Other namespace unshares are unaffected */ +TEST(other_ns_unaffected) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + char hostname[256]; + + if (enter_userns()) + _exit(1); + + if (unshare(CLONE_NEWUTS)) + _exit(2); + + if (sethostname("test-empty-mntns", 16)) + _exit(3); + + if (gethostname(hostname, sizeof(hostname))) + _exit(4); + + if (strcmp(hostname, "test-empty-mntns") != 0) + _exit(5); + + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/empty_mntns/overmount_chroot_test.c b/tools/testing/selftests/filesystems/empty_mntns/overmount_chroot_test.c new file mode 100644 index 000000000000..6e21c58258c3 --- /dev/null +++ b/tools/testing/selftests/filesystems/empty_mntns/overmount_chroot_test.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Test: rootfs overmounted multiple times with chroot into topmost + * + * This test creates a scenario where: + * 1. A new mount namespace is created with a tmpfs root (via pivot_root) + * 2. A mountpoint is created and overmounted multiple times + * 3. The caller chroots into the topmost mount layer + * + * The test verifies that: + * - Multiple overmounts create separate mount layers + * - Each layer's files are isolated + * - chroot correctly sets the process's root to the topmost layer + * - After chroot, only the topmost layer's files are visible + * + * Copyright (c) 2024 Christian Brauner <brauner@kernel.org> + */ + +#define _GNU_SOURCE +#include <fcntl.h> +#include <linux/mount.h> +#include <linux/stat.h> +#include <sched.h> +#include <stdio.h> +#include <string.h> +#include <sys/mount.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "../utils.h" +#include "empty_mntns.h" +#include "kselftest_harness.h" + +#define NR_OVERMOUNTS 5 + +/* + * Setup a proper root filesystem using pivot_root. + * This ensures we own the root directory in our user namespace. + */ +static int setup_root(void) +{ + char tmpdir[] = "/tmp/overmount_test.XXXXXX"; + char oldroot[256]; + + if (!mkdtemp(tmpdir)) + return -1; + + /* Mount tmpfs at the temporary directory */ + if (mount("tmpfs", tmpdir, "tmpfs", 0, "size=10M")) + return -1; + + /* Create directory for old root */ + snprintf(oldroot, sizeof(oldroot), "%s/oldroot", tmpdir); + if (mkdir(oldroot, 0755)) + return -1; + + /* pivot_root to use the tmpfs as new root */ + if (syscall(SYS_pivot_root, tmpdir, oldroot)) + return -1; + + if (chdir("/")) + return -1; + + /* Unmount old root */ + if (umount2("/oldroot", MNT_DETACH)) + return -1; + + /* Remove oldroot directory */ + if (rmdir("/oldroot")) + return -1; + + return 0; +} + +/* + * Test scenario: + * 1. Enter a user namespace to gain CAP_SYS_ADMIN + * 2. Create a new mount namespace + * 3. Setup a tmpfs root via pivot_root + * 4. Create a mountpoint /newroot and overmount it multiple times + * 5. Create a marker file in each layer + * 6. Chroot into /newroot (the topmost overmount) + * 7. Verify we're in the topmost layer (only topmost marker visible) + */ +TEST(overmount_chroot) +{ + pid_t pid; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ssize_t nr_mounts; + uint64_t mnt_ids[NR_OVERMOUNTS + 1]; + uint64_t root_id_before, root_id_after; + struct statmount *sm; + char marker[64]; + int fd, i; + + /* Step 1: Enter user namespace for privileges */ + if (enter_userns()) + _exit(1); + + /* Step 2: Create a new mount namespace */ + if (unshare(CLONE_NEWNS)) + _exit(2); + + /* Step 3: Make the mount tree private */ + if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL)) + _exit(3); + + /* Step 4: Setup a proper tmpfs root via pivot_root */ + if (setup_root()) + _exit(4); + + /* Create the base mount point for overmounting */ + if (mkdir("/newroot", 0755)) + _exit(5); + + /* Mount base tmpfs on /newroot */ + if (mount("tmpfs", "/newroot", "tmpfs", 0, "size=1M")) + _exit(6); + + /* Record base mount ID */ + mnt_ids[0] = get_unique_mnt_id("/newroot"); + if (!mnt_ids[0]) + _exit(7); + + /* Create marker in base layer */ + fd = open("/newroot/layer_0", O_CREAT | O_RDWR, 0644); + if (fd < 0) + _exit(8); + if (write(fd, "layer_0", 7) != 7) { + close(fd); + _exit(9); + } + close(fd); + + /* Step 5: Overmount /newroot multiple times with tmpfs */ + for (i = 0; i < NR_OVERMOUNTS; i++) { + if (mount("tmpfs", "/newroot", "tmpfs", 0, "size=1M")) + _exit(10); + + /* Record mount ID for this layer */ + mnt_ids[i + 1] = get_unique_mnt_id("/newroot"); + if (!mnt_ids[i + 1]) + _exit(11); + + /* Create a marker file in each layer */ + snprintf(marker, sizeof(marker), "/newroot/layer_%d", i + 1); + fd = open(marker, O_CREAT | O_RDWR, 0644); + if (fd < 0) + _exit(12); + + if (write(fd, marker, strlen(marker)) != (ssize_t)strlen(marker)) { + close(fd); + _exit(13); + } + close(fd); + } + + /* Verify mount count increased */ + nr_mounts = count_mounts(); + if (nr_mounts < NR_OVERMOUNTS + 2) + _exit(14); + + /* Record root mount ID before chroot */ + root_id_before = get_unique_mnt_id("/newroot"); + + /* Verify this is the topmost layer's mount */ + if (root_id_before != mnt_ids[NR_OVERMOUNTS]) + _exit(15); + + /* Step 6: Chroot into /newroot (the topmost overmount) */ + if (chroot("/newroot")) + _exit(16); + + /* Change to root directory within the chroot */ + if (chdir("/")) + _exit(17); + + /* Step 7: Verify we're in the topmost layer */ + root_id_after = get_unique_mnt_id("/"); + + /* The mount ID should be the same as the topmost layer */ + if (root_id_after != mnt_ids[NR_OVERMOUNTS]) + _exit(18); + + /* Verify the topmost layer's marker file exists */ + snprintf(marker, sizeof(marker), "/layer_%d", NR_OVERMOUNTS); + if (access(marker, F_OK)) + _exit(19); + + /* Verify we cannot see markers from lower layers (they're hidden) */ + for (i = 0; i < NR_OVERMOUNTS; i++) { + snprintf(marker, sizeof(marker), "/layer_%d", i); + if (access(marker, F_OK) == 0) + _exit(20); + } + + /* Verify the root mount is tmpfs */ + sm = statmount_alloc(root_id_after, 0, + STATMOUNT_MNT_BASIC | STATMOUNT_MNT_ROOT | + STATMOUNT_MNT_POINT | STATMOUNT_FS_TYPE, 0); + if (!sm) + _exit(21); + + if (sm->mask & STATMOUNT_FS_TYPE) { + if (strcmp(sm->str + sm->fs_type, "tmpfs") != 0) { + free(sm); + _exit(22); + } + } + + free(sm); + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c index 8bc57a2ef966..81a994943e12 100644 --- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c +++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c @@ -3493,4 +3493,72 @@ TEST(epoll64) close(ctx.sfd[1]); } +static void *epoll65_wait(void *ctx_) +{ + struct epoll_mtcontext *ctx = ctx_; + struct epoll_event event; + + for (int i = 0; i < 100000; ++i) { + if (!epoll_wait(ctx->efd[0], &event, 1, 0)) + return (void *)ENODATA; + } + + return (void *)0; +} + +TEST(epoll65) +{ + struct epoll_mtcontext ctx; + struct epoll_event event; + int64_t dummy_data = 99; + pthread_t threads[64]; + uintptr_t ret; + int i, err; + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + ctx.efd[1] = eventfd(0, 0); + ASSERT_GE(ctx.efd[1], 0); + + event.events = EPOLLIN; + err = epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &event); + ASSERT_EQ(err, 0); + + write(ctx.efd[1], &dummy_data, sizeof(dummy_data)); + + for (i = 0; i < ARRAY_SIZE(threads); ++i) + ASSERT_EQ(pthread_create(&threads[i], NULL, epoll65_wait, &ctx), 0); + + for (i = 0; i < ARRAY_SIZE(threads); ++i) { + ASSERT_EQ(pthread_join(threads[i], (void **)&ret), 0); + ASSERT_EQ(ret, 0); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); +} + +TEST(epoll66) +{ + struct epoll_event event; + int pfd[2], efd; + + ASSERT_EQ(pipe(pfd), 0); + + efd = epoll_create1(0); + ASSERT_GE(efd, 0); + + event.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, pfd[0], &event), 0); + + for (int i = 0; i < 2; ++i) { + ASSERT_EQ(write(pfd[1], "", 1), 1); + EXPECT_EQ(epoll_wait(efd, &event, 1, 0), 1); + } + + close(pfd[0]); + close(pfd[1]); + close(efd); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/failfs/.gitignore b/tools/testing/selftests/filesystems/failfs/.gitignore new file mode 100644 index 000000000000..cd3b5d884d7e --- /dev/null +++ b/tools/testing/selftests/filesystems/failfs/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +failfs_test diff --git a/tools/testing/selftests/filesystems/failfs/Makefile b/tools/testing/selftests/filesystems/failfs/Makefile new file mode 100644 index 000000000000..3c5d98b4fe72 --- /dev/null +++ b/tools/testing/selftests/filesystems/failfs/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) +TEST_GEN_PROGS := failfs_test + +include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/failfs/failfs_test.c b/tools/testing/selftests/filesystems/failfs/failfs_test.c new file mode 100644 index 000000000000..29a3c294127e --- /dev/null +++ b/tools/testing/selftests/filesystems/failfs/failfs_test.c @@ -0,0 +1,585 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <link.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mount.h> +#include <sys/prctl.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/vfs.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "../../kselftest_harness.h" + +#ifndef __NR_fchroot +#define __NR_fchroot 472 +#endif + +#ifndef FD_PIDFS_ROOT +#define FD_PIDFS_ROOT -10002 +#endif + +#ifndef FD_NSFS_ROOT +#define FD_NSFS_ROOT -10003 +#endif + +#ifndef FD_FAILFS_ROOT +#define FD_FAILFS_ROOT -10004 +#endif + +#define NOBODY_UID 65534 + +/* Child sentinel exit code: the exec was blocked as expected. */ +#define FAILFS_EXEC_BLOCKED 99 + +/* Stack for the CLONE_FS helper in fchroot_sentinel_shared_fs_struct. */ +#define FAILFS_CLONE_STACK (64 * 1024) + +static int sys_fchroot(int fd, unsigned int flags) +{ + return syscall(__NR_fchroot, fd, flags); +} + +/* + * Raw syscall: glibc's getcwd() rejects the kernel's "(unreachable)" + * result and falls back to a generic implementation. + */ +static long sys_getcwd(char *buf, size_t size) +{ + return syscall(__NR_getcwd, buf, size); +} + +static int drop_to_nobody(void) +{ + return setresuid(NOBODY_UID, NOBODY_UID, NOBODY_UID); +} + +/* Parked CLONE_FS child; dies with its parent so it never leaks. */ +static int failfs_park(void *arg) +{ + pid_t parent = (pid_t)(long)arg; + + prctl(PR_SET_PDEATHSIG, SIGKILL); + /* The parent may have died before the death signal was armed. */ + if (getppid() != parent) + _exit(0); + pause(); + return 0; +} + +/* Is fd a dynamically linked ELF with an absolute PT_INTERP interpreter? */ +static int elf_has_absolute_interp(int fd) +{ + ElfW(Ehdr) ehdr; + ElfW(Phdr) phdr; + char interp; + int i; + + if (pread(fd, &ehdr, sizeof(ehdr), 0) != sizeof(ehdr)) + return 0; + if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0) + return 0; + + for (i = 0; i < ehdr.e_phnum; i++) { + if (pread(fd, &phdr, sizeof(phdr), + ehdr.e_phoff + i * sizeof(phdr)) != sizeof(phdr)) + return 0; + if (phdr.p_type != PT_INTERP) + continue; + if (pread(fd, &interp, 1, phdr.p_offset) != 1) + return 0; + return interp == '/'; + } + + return 0; +} + +TEST(fchdir_sentinel) +{ + char buf[PATH_MAX]; + int fd; + + ASSERT_EQ(fchdir(FD_FAILFS_ROOT), 0); + + /* The working directory is unreachable from the process root. */ + ASSERT_GT(sys_getcwd(buf, sizeof(buf)), 0); + ASSERT_EQ(strncmp(buf, "(unreachable)", 13), 0); + + /* Every AT_FDCWD-relative lookup fails. */ + ASSERT_EQ(openat(AT_FDCWD, "foo", O_RDONLY), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + ASSERT_EQ(openat(AT_FDCWD, ".", O_RDONLY), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + ASSERT_EQ(openat(AT_FDCWD, "..", O_RDONLY), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + ASSERT_EQ(openat(AT_FDCWD, "foo", O_WRONLY | O_CREAT, 0600), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + + /* The cwd cannot be pinned by following /proc/self/cwd into it. */ + ASSERT_EQ(open("/proc/self/cwd", O_PATH), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + + /* The root is untouched so absolute lookups keep working... */ + fd = open("/", O_RDONLY | O_DIRECTORY); + ASSERT_GE(fd, 0); + ASSERT_EQ(close(fd), 0); + + /* ... and the working directory can be recovered. */ + ASSERT_EQ(chdir("/"), 0); + ASSERT_GT(sys_getcwd(buf, sizeof(buf)), 0); + ASSERT_EQ(strcmp(buf, "/"), 0); +} + +TEST(fchdir_rejects_other_sentinels) +{ + ASSERT_EQ(fchdir(FD_PIDFS_ROOT), -1); + ASSERT_EQ(errno, EBADF); + ASSERT_EQ(fchdir(FD_NSFS_ROOT), -1); + ASSERT_EQ(errno, EBADF); + ASSERT_EQ(fchdir(-10009), -1); + ASSERT_EQ(errno, EBADF); +} + +TEST(fchroot_flags) +{ + int fd; + + ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 1), -1); + ASSERT_EQ(errno, EINVAL); + + fd = open("/", O_PATH | O_DIRECTORY); + ASSERT_GE(fd, 0); + ASSERT_EQ(sys_fchroot(fd, 1), -1); + ASSERT_EQ(errno, EINVAL); + ASSERT_EQ(close(fd), 0); +} + +TEST(fchroot_bad_fd) +{ + ASSERT_EQ(sys_fchroot(-1, 0), -1); + ASSERT_EQ(errno, EBADF); + + /* Only FD_FAILFS_ROOT is a valid sentinel. */ + ASSERT_EQ(sys_fchroot(FD_PIDFS_ROOT, 0), -1); + ASSERT_EQ(errno, EBADF); + ASSERT_EQ(sys_fchroot(FD_NSFS_ROOT, 0), -1); + ASSERT_EQ(errno, EBADF); +} + +TEST(fchroot_notdir) +{ + int fd; + + fd = open("/proc/self/status", O_RDONLY); + ASSERT_GE(fd, 0); + ASSERT_EQ(sys_fchroot(fd, 0), -1); + ASSERT_EQ(errno, ENOTDIR); + ASSERT_EQ(close(fd), 0); +} + +TEST(fchroot_realfd_requires_cap) +{ + int fd; + + if (geteuid() == 0) + ASSERT_EQ(drop_to_nobody(), 0); + + fd = open("/", O_PATH | O_DIRECTORY); + ASSERT_GE(fd, 0); + ASSERT_EQ(sys_fchroot(fd, 0), -1); + ASSERT_EQ(errno, EPERM); + ASSERT_EQ(close(fd), 0); +} + +TEST(fchroot_realfd) +{ + char template[] = "/tmp/failfs_test.XXXXXX"; + char path[PATH_MAX]; + struct stat st; + int tmpfd, dfd, fd; + + if (geteuid() != 0) + SKIP(return, "fchroot() with a regular fd requires CAP_SYS_CHROOT"); + + tmpfd = open("/tmp", O_PATH | O_DIRECTORY); + ASSERT_GE(tmpfd, 0); + + ASSERT_NE(mkdtemp(template), NULL); + snprintf(path, sizeof(path), "%s/canary", template); + fd = open(path, O_WRONLY | O_CREAT, 0600); + ASSERT_GE(fd, 0); + ASSERT_EQ(close(fd), 0); + + dfd = open(template, O_PATH | O_DIRECTORY); + ASSERT_GE(dfd, 0); + ASSERT_EQ(sys_fchroot(dfd, 0), 0); + ASSERT_EQ(close(dfd), 0); + + ASSERT_EQ(stat("/canary", &st), 0); + + /* Best-effort cleanup: dirfd-anchored I/O works with the new root. */ + snprintf(path, sizeof(path), "%s/canary", template + strlen("/tmp/")); + unlinkat(tmpfd, path, 0); + unlinkat(tmpfd, template + strlen("/tmp/"), AT_REMOVEDIR); +} + +TEST(fchroot_sentinel) +{ + char template[] = "/tmp/failfs_test.XXXXXX"; + struct stat realroot, st; + struct statfs sfs; + char buf[PATH_MAX]; + int procfd, tmpfd, dfd, fd; + struct { + struct file_handle handle; + unsigned char f_handle[MAX_HANDLE_SZ]; + } fh; + int mntid; + ssize_t ret; + + if (geteuid() != 0) + SKIP(return, "privileged fchroot(FD_FAILFS_ROOT) requires CAP_SYS_CHROOT"); + + ASSERT_EQ(stat("/", &realroot), 0); + procfd = open("/proc", O_PATH | O_DIRECTORY); + ASSERT_GE(procfd, 0); + tmpfd = open("/tmp", O_PATH | O_DIRECTORY); + ASSERT_GE(tmpfd, 0); + ASSERT_NE(mkdtemp(template), NULL); + dfd = open(template, O_RDONLY | O_DIRECTORY); + ASSERT_GE(dfd, 0); + + ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0); + + /* Absolute lookups fail. */ + ASSERT_EQ(open("/etc/passwd", O_RDONLY), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + ASSERT_EQ(mkdir("/foo", 0700), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + + /* + * The root cannot be referenced at all - not even an O_PATH open, + * which skips ->permission(), because it lands on the root as a + * jumped walk terminal that ->d_weak_revalidate() refuses. + */ + ASSERT_EQ(open("/", O_RDONLY | O_DIRECTORY), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + ASSERT_EQ(open("/", O_PATH), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + ASSERT_EQ(statfs("/", &sfs), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + + /* + * It cannot be pinned by following /proc/self/root into it either + * (only the root is in failfs here, so self/cwd is still real). + */ + ASSERT_EQ(openat(procfd, "self/root", O_PATH), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + + /* Nor encoded into a file handle. */ + fh.handle.handle_bytes = MAX_HANDLE_SZ; + ASSERT_EQ(name_to_handle_at(AT_FDCWD, "/", &fh.handle, &mntid, 0), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + + /* The working directory is now unreachable from the root. */ + ASSERT_GT(sys_getcwd(buf, sizeof(buf)), 0); + ASSERT_EQ(strncmp(buf, "(unreachable)", 13), 0); + + /* Lookups anchored at real directories keep working. */ + fd = openat(AT_FDCWD, ".", O_RDONLY | O_DIRECTORY); + ASSERT_GE(fd, 0); + ASSERT_EQ(close(fd), 0); + fd = openat(dfd, "canary", O_WRONLY | O_CREAT, 0600); + ASSERT_GE(fd, 0); + ASSERT_EQ(write(fd, "x", 1), 1); + ASSERT_EQ(close(fd), 0); + fd = openat(dfd, "canary", O_RDONLY); + ASSERT_GE(fd, 0); + ASSERT_EQ(close(fd), 0); + + /* ".." walks clamp at the top of the mount tree, not at failfs. */ + fd = openat(AT_FDCWD, "../../../../../../../../../..", O_PATH); + ASSERT_GE(fd, 0); + ASSERT_EQ(fstat(fd, &st), 0); + ASSERT_EQ(st.st_dev, realroot.st_dev); + ASSERT_EQ(st.st_ino, realroot.st_ino); + ASSERT_EQ(close(fd), 0); + + /* readlink of the magic link still works: it does not follow. */ + ret = readlinkat(procfd, "self/root", buf, sizeof(buf) - 1); + ASSERT_GT(ret, 0); + buf[ret] = '\0'; + TH_LOG("/proc/self/root points to '%s'", buf); + /* d_path() names the failfs root synthetically, never as a real path. */ + ASSERT_EQ(strcmp(buf, "failfs:/"), 0); + + /* But following it into failfs is refused. */ + ASSERT_EQ(fstatat(procfd, "self/root", &st, 0), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + + /* Best-effort cleanup via the pre-opened dirfds. */ + unlinkat(dfd, "canary", 0); + unlinkat(tmpfd, template + strlen("/tmp/"), AT_REMOVEDIR); +} + +TEST(fchroot_sentinel_absolute_symlink) +{ + char template[] = "/tmp/failfs_test.XXXXXX"; + int tmpfd, dfd, fd; + + if (geteuid() != 0) + SKIP(return, "privileged fchroot(FD_FAILFS_ROOT) requires CAP_SYS_CHROOT"); + + tmpfd = open("/tmp", O_PATH | O_DIRECTORY); + ASSERT_GE(tmpfd, 0); + ASSERT_NE(mkdtemp(template), NULL); + dfd = open(template, O_RDONLY | O_DIRECTORY); + ASSERT_GE(dfd, 0); + + fd = openat(dfd, "target", O_WRONLY | O_CREAT, 0600); + ASSERT_GE(fd, 0); + ASSERT_EQ(close(fd), 0); + ASSERT_EQ(symlinkat("target", dfd, "rel"), 0); + ASSERT_EQ(symlinkat("/etc", dfd, "abs"), 0); + + ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0); + + /* Relative symlinks keep resolving within the dirfd-anchored walk... */ + fd = openat(dfd, "rel", O_RDONLY); + ASSERT_GE(fd, 0); + ASSERT_EQ(close(fd), 0); + + /* ... absolute symlinks restart the walk at the failfs root. */ + ASSERT_EQ(openat(dfd, "abs", O_RDONLY), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + + /* Best-effort cleanup via the pre-opened dirfds. */ + unlinkat(dfd, "abs", 0); + unlinkat(dfd, "rel", 0); + unlinkat(dfd, "target", 0); + unlinkat(tmpfd, template + strlen("/tmp/"), AT_REMOVEDIR); +} + +TEST(fchroot_sentinel_unprivileged) +{ + char buf[PATH_MAX]; + + if (geteuid() == 0) + ASSERT_EQ(drop_to_nobody(), 0); + + /* Without no_new_privs entering failfs is not allowed... */ + ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), -1); + ASSERT_EQ(errno, EPERM); + + /* ... with no_new_privs set it is allowed. */ + ASSERT_EQ(prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0), 0); + ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0); + + ASSERT_EQ(open("/etc/passwd", O_RDONLY), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + + /* The task counts as chrooted: no user namespaces anymore. */ + ASSERT_EQ(unshare(CLONE_NEWUSER), -1); + ASSERT_EQ(errno, EPERM); + + /* With both root and cwd in failfs getcwd() reports "/". */ + ASSERT_EQ(fchdir(FD_FAILFS_ROOT), 0); + ASSERT_GT(sys_getcwd(buf, sizeof(buf)), 0); + ASSERT_EQ(strcmp(buf, "/"), 0); +} + +TEST(fchroot_sentinel_rejected_when_chrooted) +{ + char template[] = "/tmp/failfs_test.XXXXXX"; + int tmpfd; + + if (geteuid() != 0) + SKIP(return, "chroot() requires CAP_SYS_CHROOT"); + + tmpfd = open("/tmp", O_PATH | O_DIRECTORY); + ASSERT_GE(tmpfd, 0); + ASSERT_NE(mkdtemp(template), NULL); + ASSERT_EQ(chroot(template), 0); + ASSERT_EQ(chdir("/"), 0); + + /* Remove the jail while still privileged; sticky /tmp blocks nobody. */ + unlinkat(tmpfd, template + strlen("/tmp/"), AT_REMOVEDIR); + + ASSERT_EQ(drop_to_nobody(), 0); + ASSERT_EQ(prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0), 0); + + /* An unprivileged chrooted task must not lift its ".." barrier. */ + ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), -1); + ASSERT_EQ(errno, EPERM); +} + +TEST(fchroot_sentinel_shared_fs_struct) +{ + char stack[FAILFS_CLONE_STACK]; + pid_t pid; + + if (geteuid() == 0) + ASSERT_EQ(drop_to_nobody(), 0); + + /* A CLONE_FS sibling shares the fs_struct: bump fs->users to 2. */ + pid = clone(failfs_park, stack + sizeof(stack), CLONE_FS | SIGCHLD, + (void *)(long)getpid()); + ASSERT_GE(pid, 0); + + ASSERT_EQ(prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0), 0); + + /* + * A sibling without no_new_privs could exec a setuid binary with + * the failfs root, so a shared fs_struct is refused even with + * no_new_privs set. + */ + ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), -1); + ASSERT_EQ(errno, EINVAL); + + ASSERT_EQ(kill(pid, SIGKILL), 0); + ASSERT_EQ(waitpid(pid, NULL, 0), pid); +} + +TEST(fchroot_sentinel_no_overmount) +{ + if (geteuid() != 0) + SKIP(return, "mounting requires privileges"); + + /* + * Contain the blast radius: if failfs ever regressed and "/" + * resolved to the real root, the tmpfs mount below must not touch + * the host. A private mount namespace keeps it local to this child. + */ + ASSERT_EQ(unshare(CLONE_NEWNS), 0); + ASSERT_EQ(mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL), 0); + + ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0); + + /* + * Nothing can be mounted on top of the failfs root. It cannot even + * be named as a mount target: resolving "/" is refused before the + * mount machinery (which, failfs being in no mount namespace, would + * reject it anyway) is ever reached. open_tree(OPEN_TREE_CLONE) is + * likewise moot since no fd to the root can be obtained. + */ + ASSERT_EQ(mount("none", "/", "tmpfs", 0, NULL), -1); + ASSERT_EQ(errno, EOPNOTSUPP); +} + +TEST(fchroot_sentinel_setns_escape) +{ + struct stat realroot, st; + int nsfd; + + if (geteuid() != 0) + SKIP(return, "setns() to a mount namespace requires privileges"); + + ASSERT_EQ(stat("/", &realroot), 0); + nsfd = open("/proc/self/ns/mnt", O_RDONLY); + ASSERT_GE(nsfd, 0); + + ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0); + ASSERT_EQ(open("/etc", O_PATH), -1); + ASSERT_EQ(errno, EOPNOTSUPP); + + /* A mount namespace fd is the key out: it resets root and cwd. */ + ASSERT_EQ(setns(nsfd, CLONE_NEWNS), 0); + ASSERT_EQ(close(nsfd), 0); + + ASSERT_EQ(stat("/", &st), 0); + ASSERT_EQ(st.st_dev, realroot.st_dev); + ASSERT_EQ(st.st_ino, realroot.st_ino); +} + +TEST(fchroot_sentinel_exec) +{ + pid_t pid; + int status; + + if (geteuid() != 0) + SKIP(return, "privileged fchroot(FD_FAILFS_ROOT) requires CAP_SYS_CHROOT"); + + ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0); + + /* + * Exec in a child: a wrongly successful exec would replace the test + * image and its exit code would not match the sentinel below. + */ + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) { + execl("/bin/true", "true", NULL); + _exit(errno == EOPNOTSUPP ? FAILFS_EXEC_BLOCKED : 1); + } + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + ASSERT_EQ(WEXITSTATUS(status), FAILFS_EXEC_BLOCKED); +} + +TEST(fchroot_sentinel_exec_interpreter) +{ + static const char * const argv[] = { "failfs_test", NULL }; + static const char * const envp[] = { NULL }; + pid_t pid; + int status, exefd; + + if (geteuid() != 0) + SKIP(return, "privileged fchroot(FD_FAILFS_ROOT) requires CAP_SYS_CHROOT"); + + /* Exec ourselves: the one binary guaranteed to be around. */ + exefd = open("/proc/self/exe", O_RDONLY); + ASSERT_GE(exefd, 0); + if (!elf_has_absolute_interp(exefd)) + SKIP(return, "test binary has no absolute PT_INTERP interpreter"); + + ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0); + + /* + * The binary itself needs no path lookup - it is executed by fd - + * but loading it fails on opening the absolute PT_INTERP + * interpreter. Run it in a child so a wrongly successful exec does + * not replace the test image and masquerade as a pass. + */ + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) { + syscall(__NR_execveat, exefd, "", argv, envp, AT_EMPTY_PATH); + _exit(errno == EOPNOTSUPP ? FAILFS_EXEC_BLOCKED : 1); + } + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + ASSERT_EQ(WEXITSTATUS(status), FAILFS_EXEC_BLOCKED); +} + +TEST(fchroot_sentinel_inherited) +{ + pid_t pid; + int status; + + if (geteuid() != 0) + SKIP(return, "privileged fchroot(FD_FAILFS_ROOT) requires CAP_SYS_CHROOT"); + + ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) { + if (open("/etc", O_PATH) != -1 || errno != EOPNOTSUPP) + _exit(1); + _exit(0); + } + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + ASSERT_EQ(WEXITSTATUS(status), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/fclog.c b/tools/testing/selftests/filesystems/fclog.c index 551c4a0f395a..593a5136e991 100644 --- a/tools/testing/selftests/filesystems/fclog.c +++ b/tools/testing/selftests/filesystems/fclog.c @@ -6,10 +6,8 @@ #include <assert.h> #include <errno.h> +#include <fcntl.h> #include <sched.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> #include <unistd.h> #include <sys/mount.h> diff --git a/tools/testing/selftests/filesystems/fscontext_ns/Makefile b/tools/testing/selftests/filesystems/fscontext_ns/Makefile new file mode 100644 index 000000000000..7e3506294757 --- /dev/null +++ b/tools/testing/selftests/filesystems/fscontext_ns/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +TEST_GEN_PROGS := fscontext_ns_test + +CFLAGS += -Wall -O0 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES) +LDLIBS := -lcap + +include ../../lib.mk + +$(OUTPUT)/fscontext_ns_test: fscontext_ns_test.c ../utils.c + $(CC) $(CFLAGS) -o $@ $^ $(LDLIBS) diff --git a/tools/testing/selftests/filesystems/fscontext_ns/fscontext_ns_test.c b/tools/testing/selftests/filesystems/fscontext_ns/fscontext_ns_test.c new file mode 100644 index 000000000000..0f30a3e6e197 --- /dev/null +++ b/tools/testing/selftests/filesystems/fscontext_ns/fscontext_ns_test.c @@ -0,0 +1,239 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2026 Christian Brauner <brauner@kernel.org> + * + * Test that completing a filesystem context from another user namespace + * doesn't warn. + * + * fsopen() records the caller's user namespace in fc->user_ns and hands + * back an ordinary file descriptor. The task that issues + * FSCONFIG_CMD_CREATE need not be the one that created the context: the fd + * is inherited across fork() and exec() and it can be passed over a unix + * socket. vfs_cmd_create() authorizes the create with mount_capable(), + * which for FS_USERNS_MOUNT checks ns_capable(fc->user_ns, CAP_SYS_ADMIN), + * and that succeeds for a task holding CAP_SYS_ADMIN in an ancestor of + * fc->user_ns. + * + * binfmt_misc and overlayfs used to WARN_ON() that mismatch, which let an + * unprivileged user taint the kernel, flood the log and panic a kernel + * booted with panic_on_warn. The mount must still be refused, but it must + * not warn. + */ +#define _GNU_SOURCE + +#include <errno.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "../wrappers.h" +#include "../utils.h" +#include "../../kselftest_harness.h" + +#ifndef FSCONFIG_CMD_CREATE +#define FSCONFIG_CMD_CREATE 6 +#endif + +/* TAINT_WARN, i.e. bit 9 of /proc/sys/kernel/tainted. */ +#define TAINT_WARN_BIT 9 + +static bool taint_warn_set(void) +{ + unsigned long taint = 0; + FILE *f; + + f = fopen("/proc/sys/kernel/tainted", "r"); + if (!f) + return false; + if (fscanf(f, "%lu", &taint) != 1) + taint = 0; + fclose(f); + + return taint & (1UL << TAINT_WARN_BIT); +} + +static int send_fd(int sock, int fd) +{ + char cmsgbuf[CMSG_SPACE(sizeof(int))] = {}; + char b[1] = { 'x' }; + struct iovec iov = { .iov_base = b, .iov_len = sizeof(b) }; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_control = cmsgbuf, + .msg_controllen = sizeof(cmsgbuf), + }; + struct cmsghdr *cmsg; + + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(int)); + memcpy(CMSG_DATA(cmsg), &fd, sizeof(int)); + + return sendmsg(sock, &msg, 0) < 0 ? -1 : 0; +} + +static int recv_fd(int sock) +{ + char cmsgbuf[CMSG_SPACE(sizeof(int))] = {}; + char b[1]; + struct iovec iov = { .iov_base = b, .iov_len = sizeof(b) }; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_control = cmsgbuf, + .msg_controllen = sizeof(cmsgbuf), + }; + struct cmsghdr *cmsg; + int fd = -1; + + if (recvmsg(sock, &msg, 0) <= 0) + return -1; + + cmsg = CMSG_FIRSTHDR(&msg); + if (!cmsg || cmsg->cmsg_type != SCM_RIGHTS) + return -1; + memcpy(&fd, CMSG_DATA(cmsg), sizeof(int)); + + return fd; +} + +/* + * Create a context for @fsname in a child and complete it here. With @nest + * the child first creates its own user namespace, so that the context is + * created in a descendant of the namespace completing it. The child needs a + * mount namespace of its own as well: fsopen() gates on may_mount(), which + * asks for CAP_SYS_ADMIN in the user namespace owning the caller's mount + * namespace. + * + * Returns the result of FSCONFIG_CMD_CREATE with errno set, or -ENODATA if + * the child could not create the context at all. + */ +static int create_from_child(const char *fsname, bool nest) +{ + int sock[2], fd, ret, status; + pid_t pid; + + if (socketpair(AF_UNIX, SOCK_STREAM, 0, sock)) + return -ENODATA; + + pid = fork(); + if (pid < 0) { + close(sock[0]); + close(sock[1]); + return -ENODATA; + } + + if (pid == 0) { + close(sock[0]); + + if (nest && unshare(CLONE_NEWUSER | CLONE_NEWNS)) + _exit(1); + + fd = sys_fsopen(fsname, 0); + if (fd < 0) + _exit(1); + if (send_fd(sock[1], fd)) + _exit(1); + _exit(0); + } + + close(sock[1]); + fd = recv_fd(sock[0]); + close(sock[0]); + wait_for_pid(pid); + waitpid(pid, &status, WNOHANG); + + if (fd < 0) + return -ENODATA; + + errno = 0; + ret = sys_fsconfig(fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); + status = errno; + close(fd); + errno = status; + + return ret; +} + +FIXTURE(fscontext_ns) { + bool warn_before; +}; + +FIXTURE_SETUP(fscontext_ns) +{ + self->warn_before = taint_warn_set(); + + if (setup_userns() != 0) + SKIP(return, "setup_userns failed"); +} + +FIXTURE_TEARDOWN(fscontext_ns) +{ +} + +/* + * The condition the kernel used to WARN about. It has to be refused, and it + * has to be refused quietly: an unprivileged task reaches this. + */ +FIXTURE_VARIANT(fscontext_ns) { + const char *fsname; + int expected_errno; +}; + +FIXTURE_VARIANT_ADD(fscontext_ns, binfmt_misc) { + .fsname = "binfmt_misc", + .expected_errno = EINVAL, +}; + +FIXTURE_VARIANT_ADD(fscontext_ns, overlay) { + .fsname = "overlay", + .expected_errno = EIO, +}; + +TEST_F(fscontext_ns, create_from_descendant_userns) +{ + int ret; + + ret = create_from_child(variant->fsname, true); + if (ret == -ENODATA) + SKIP(return, "%s unavailable", variant->fsname); + + ASSERT_EQ(-1, ret); + ASSERT_EQ(variant->expected_errno, errno); + + /* + * Only meaningful if nothing had warned before us. Note that an + * unrelated warning racing this test would look like a failure. + */ + if (self->warn_before) + TH_LOG("TAINT_WARN already set, not checking for a new warning"); + else + ASSERT_FALSE(taint_warn_set()); +} + +/* + * The same handover within one user namespace is a supported thing to do and + * has to keep working. binfmt_misc takes no options, so the create succeeds + * outright and this also shows the test really drives the create path. + */ +TEST(create_from_same_userns) +{ + int ret; + + if (setup_userns() != 0) + SKIP(return, "setup_userns failed"); + + ret = create_from_child("binfmt_misc", false); + if (ret == -ENODATA) + SKIP(return, "binfmt_misc unavailable"); + + ASSERT_EQ(0, ret); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/fsmount_ns/.gitignore b/tools/testing/selftests/filesystems/fsmount_ns/.gitignore new file mode 100644 index 000000000000..f1ecf6c6e37b --- /dev/null +++ b/tools/testing/selftests/filesystems/fsmount_ns/.gitignore @@ -0,0 +1 @@ +fsmount_ns_test diff --git a/tools/testing/selftests/filesystems/fsmount_ns/Makefile b/tools/testing/selftests/filesystems/fsmount_ns/Makefile new file mode 100644 index 000000000000..d9647efc0739 --- /dev/null +++ b/tools/testing/selftests/filesystems/fsmount_ns/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +TEST_GEN_PROGS := fsmount_ns_test + +CFLAGS += -Wall -O0 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES) +LDLIBS := -lcap + +include ../../lib.mk + +$(OUTPUT)/fsmount_ns_test: fsmount_ns_test.c ../utils.c + $(CC) $(CFLAGS) -o $@ $^ $(LDLIBS) diff --git a/tools/testing/selftests/filesystems/fsmount_ns/fsmount_ns_test.c b/tools/testing/selftests/filesystems/fsmount_ns/fsmount_ns_test.c new file mode 100644 index 000000000000..b70b3051eed4 --- /dev/null +++ b/tools/testing/selftests/filesystems/fsmount_ns/fsmount_ns_test.c @@ -0,0 +1,1135 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2026 Christian Brauner <brauner@kernel.org> + * + * Test for FSMOUNT_NAMESPACE flag. + * + * Test that fsmount() with FSMOUNT_NAMESPACE creates a new mount + * namespace containing the specified mount. + */ +#define _GNU_SOURCE + +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <linux/nsfs.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/mount.h> +#include <sys/stat.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "../wrappers.h" +#include "../statmount/statmount.h" +#include "../utils.h" +#include "../../kselftest_harness.h" + +#ifndef FSMOUNT_NAMESPACE +#define FSMOUNT_NAMESPACE 0x00000002 +#endif + +#ifndef FSMOUNT_CLOEXEC +#define FSMOUNT_CLOEXEC 0x00000001 +#endif + +#ifndef FSCONFIG_CMD_CREATE +#define FSCONFIG_CMD_CREATE 6 +#endif + +static int get_mnt_ns_id(int fd, uint64_t *mnt_ns_id) +{ + if (ioctl(fd, NS_GET_MNTNS_ID, mnt_ns_id) < 0) + return -errno; + return 0; +} + +static int get_mnt_ns_id_from_path(const char *path, uint64_t *mnt_ns_id) +{ + int fd, ret; + + fd = open(path, O_RDONLY); + if (fd < 0) + return -errno; + + ret = get_mnt_ns_id(fd, mnt_ns_id); + close(fd); + return ret; +} + +static void log_mount(struct __test_metadata *_metadata, struct statmount *sm) +{ + const char *fs_type = ""; + const char *mnt_root = ""; + const char *mnt_point = ""; + + if (sm->mask & STATMOUNT_FS_TYPE) + fs_type = sm->str + sm->fs_type; + if (sm->mask & STATMOUNT_MNT_ROOT) + mnt_root = sm->str + sm->mnt_root; + if (sm->mask & STATMOUNT_MNT_POINT) + mnt_point = sm->str + sm->mnt_point; + + TH_LOG(" mnt_id: %llu, parent_id: %llu, fs_type: %s, root: %s, point: %s", + (unsigned long long)sm->mnt_id, + (unsigned long long)sm->mnt_parent_id, + fs_type, mnt_root, mnt_point); +} + +static void dump_mounts(struct __test_metadata *_metadata, uint64_t mnt_ns_id) +{ + uint64_t list[256]; + ssize_t nr_mounts; + + nr_mounts = listmount(LSMT_ROOT, mnt_ns_id, 0, list, 256, 0); + if (nr_mounts < 0) { + TH_LOG("listmount failed: %s", strerror(errno)); + return; + } + + TH_LOG("Mount namespace %llu contains %zd mount(s):", + (unsigned long long)mnt_ns_id, nr_mounts); + + for (ssize_t i = 0; i < nr_mounts; i++) { + struct statmount *sm; + + sm = statmount_alloc(list[i], mnt_ns_id, + STATMOUNT_MNT_BASIC | + STATMOUNT_FS_TYPE | + STATMOUNT_MNT_ROOT | + STATMOUNT_MNT_POINT, 0); + if (!sm) { + TH_LOG(" [%zd] mnt_id %llu: statmount failed: %s", + i, (unsigned long long)list[i], strerror(errno)); + continue; + } + + log_mount(_metadata, sm); + free(sm); + } +} + +static int create_tmpfs_fd(void) +{ + int fs_fd, ret; + + fs_fd = sys_fsopen("tmpfs", FSOPEN_CLOEXEC); + if (fs_fd < 0) + return -errno; + + ret = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); + if (ret < 0) { + close(fs_fd); + return -errno; + } + + return fs_fd; +} + +FIXTURE(fsmount_ns) +{ + int fd; + int fs_fd; + uint64_t current_ns_id; +}; + +FIXTURE_VARIANT(fsmount_ns) +{ + const char *fstype; + unsigned int flags; + bool expect_success; + bool expect_different_ns; + int min_mounts; +}; + +FIXTURE_VARIANT_ADD(fsmount_ns, basic_tmpfs) +{ + .fstype = "tmpfs", + .flags = FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC, + .expect_success = true, + .expect_different_ns = true, + .min_mounts = 1, +}; + +FIXTURE_VARIANT_ADD(fsmount_ns, cloexec_only) +{ + .fstype = "tmpfs", + .flags = FSMOUNT_CLOEXEC, + .expect_success = true, + .expect_different_ns = false, + .min_mounts = 1, +}; + +FIXTURE_VARIANT_ADD(fsmount_ns, namespace_only) +{ + .fstype = "tmpfs", + .flags = FSMOUNT_NAMESPACE, + .expect_success = true, + .expect_different_ns = true, + .min_mounts = 1, +}; + +FIXTURE_SETUP(fsmount_ns) +{ + int ret; + + self->fd = -1; + self->fs_fd = -1; + + /* Check if fsopen syscall is supported */ + ret = sys_fsopen("tmpfs", 0); + if (ret == -1 && errno == ENOSYS) + SKIP(return, "fsopen() syscall not supported"); + if (ret >= 0) + close(ret); + + /* Check if statmount/listmount are supported */ + ret = statmount(0, 0, 0, 0, NULL, 0, 0); + if (ret == -1 && errno == ENOSYS) + SKIP(return, "statmount() syscall not supported"); + + /* Get current mount namespace ID for comparison */ + ret = get_mnt_ns_id_from_path("/proc/self/ns/mnt", &self->current_ns_id); + if (ret < 0) + SKIP(return, "Failed to get current mount namespace ID"); +} + +FIXTURE_TEARDOWN(fsmount_ns) +{ + if (self->fd >= 0) + close(self->fd); + if (self->fs_fd >= 0) + close(self->fs_fd); +} + +TEST_F(fsmount_ns, create_namespace) +{ + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int ret; + + self->fs_fd = create_tmpfs_fd(); + ASSERT_GE(self->fs_fd, 0); + + self->fd = sys_fsmount(self->fs_fd, variant->flags, 0); + + if (!variant->expect_success) { + ASSERT_LT(self->fd, 0); + return; + } + + if (self->fd < 0 && errno == EINVAL) + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + + ASSERT_GE(self->fd, 0); + + if (variant->expect_different_ns) { + /* Verify we can get the namespace ID from the fd */ + ret = get_mnt_ns_id(self->fd, &new_ns_id); + ASSERT_EQ(ret, 0); + + /* Verify it's a different namespace */ + ASSERT_NE(new_ns_id, self->current_ns_id); + + /* List mounts in the new namespace */ + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + ASSERT_GE(nr_mounts, 0) { + TH_LOG("%m - listmount failed"); + } + + /* Verify minimum expected mounts */ + ASSERT_GE(nr_mounts, variant->min_mounts); + TH_LOG("Namespace contains %zd mounts", nr_mounts); + } +} + +TEST_F(fsmount_ns, setns_into_namespace) +{ + uint64_t new_ns_id; + pid_t pid; + int status; + int ret; + + /* Only test with FSMOUNT_NAMESPACE flag */ + if (!(variant->flags & FSMOUNT_NAMESPACE)) + SKIP(return, "setns test only for FSMOUNT_NAMESPACE case"); + + self->fs_fd = create_tmpfs_fd(); + ASSERT_GE(self->fs_fd, 0); + + self->fd = sys_fsmount(self->fs_fd, variant->flags, 0); + if (self->fd < 0 && errno == EINVAL) + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + + ASSERT_GE(self->fd, 0); + + /* Get namespace ID and dump all mounts */ + ret = get_mnt_ns_id(self->fd, &new_ns_id); + ASSERT_EQ(ret, 0); + + dump_mounts(_metadata, new_ns_id); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + /* Child: try to enter the namespace */ + if (setns(self->fd, CLONE_NEWNS) < 0) + _exit(1); + _exit(0); + } + + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + ASSERT_EQ(WEXITSTATUS(status), 0); +} + +TEST_F(fsmount_ns, verify_mount_properties) +{ + struct statmount sm; + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int ret; + + /* Only test with basic FSMOUNT_NAMESPACE flags */ + if (variant->flags != (FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC)) + SKIP(return, "mount properties test only for basic case"); + + self->fs_fd = create_tmpfs_fd(); + ASSERT_GE(self->fs_fd, 0); + + self->fd = sys_fsmount(self->fs_fd, FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC, 0); + if (self->fd < 0 && errno == EINVAL) + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + + ASSERT_GE(self->fd, 0); + + ret = get_mnt_ns_id(self->fd, &new_ns_id); + ASSERT_EQ(ret, 0); + + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + ASSERT_GE(nr_mounts, 1); + + /* Get info about the root mount */ + ret = statmount(list[0], new_ns_id, 0, STATMOUNT_MNT_BASIC, &sm, sizeof(sm), 0); + ASSERT_EQ(ret, 0); + + TH_LOG("Root mount id: %llu, parent: %llu", + (unsigned long long)sm.mnt_id, + (unsigned long long)sm.mnt_parent_id); +} + +TEST_F(fsmount_ns, verify_tmpfs_type) +{ + struct statmount *sm; + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + const char *fs_type; + int ret; + + /* Only test with basic FSMOUNT_NAMESPACE flags */ + if (variant->flags != (FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC)) + SKIP(return, "fs type test only for basic case"); + + self->fs_fd = create_tmpfs_fd(); + ASSERT_GE(self->fs_fd, 0); + + self->fd = sys_fsmount(self->fs_fd, FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC, 0); + if (self->fd < 0 && errno == EINVAL) + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + + ASSERT_GE(self->fd, 0); + + ret = get_mnt_ns_id(self->fd, &new_ns_id); + ASSERT_EQ(ret, 0); + + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + ASSERT_GE(nr_mounts, 1); + + sm = statmount_alloc(list[0], new_ns_id, STATMOUNT_FS_TYPE, 0); + ASSERT_NE(sm, NULL); + + fs_type = sm->str + sm->fs_type; + ASSERT_STREQ(fs_type, "tmpfs"); + + free(sm); +} + +FIXTURE(fsmount_ns_caps) +{ + bool has_caps; +}; + +FIXTURE_SETUP(fsmount_ns_caps) +{ + int ret; + + /* Check if fsopen syscall is supported */ + ret = sys_fsopen("tmpfs", 0); + if (ret == -1 && errno == ENOSYS) + SKIP(return, "fsopen() syscall not supported"); + if (ret >= 0) + close(ret); + + self->has_caps = (geteuid() == 0); +} + +FIXTURE_TEARDOWN(fsmount_ns_caps) +{ +} + +TEST_F(fsmount_ns_caps, requires_cap_sys_admin) +{ + pid_t pid; + int status; + int fs_fd; + + /* + * Prepare the configured filesystem fd as root before forking. + * fsopen() requires CAP_SYS_ADMIN in the mount namespace's + * user_ns, which won't be available after enter_userns(). + */ + fs_fd = sys_fsopen("tmpfs", FSOPEN_CLOEXEC); + ASSERT_GE(fs_fd, 0); + + ASSERT_EQ(sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + int fd; + + /* Child: drop privileges using utils.h helper */ + if (enter_userns() != 0) + _exit(2); + + /* Drop all caps using utils.h helper */ + if (caps_down() == 0) + _exit(3); + + fd = sys_fsmount(fs_fd, FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC, 0); + close(fs_fd); + + if (fd >= 0) { + close(fd); + /* Should have failed without caps */ + _exit(1); + } + + if (errno == EPERM) + _exit(0); + + /* EINVAL means FSMOUNT_NAMESPACE not supported */ + if (errno == EINVAL) + _exit(6); + + /* Unexpected error */ + _exit(7); + } + + close(fs_fd); + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + + switch (WEXITSTATUS(status)) { + case 0: + /* Expected: EPERM without caps */ + break; + case 1: + ASSERT_FALSE(true) TH_LOG("FSMOUNT_NAMESPACE succeeded without caps"); + break; + case 2: + SKIP(return, "enter_userns failed"); + break; + case 3: + SKIP(return, "caps_down failed"); + break; + case 6: + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + break; + default: + ASSERT_FALSE(true) TH_LOG("Unexpected error in child (exit %d)", + WEXITSTATUS(status)); + break; + } +} + +FIXTURE(fsmount_ns_userns) +{ + int fd; + int fs_fd; +}; + +FIXTURE_SETUP(fsmount_ns_userns) +{ + int ret; + + self->fd = -1; + self->fs_fd = -1; + + /* Check if fsopen syscall is supported */ + ret = sys_fsopen("tmpfs", 0); + if (ret == -1 && errno == ENOSYS) + SKIP(return, "fsopen() syscall not supported"); + if (ret >= 0) + close(ret); + + /* Check if statmount/listmount are supported */ + ret = statmount(0, 0, 0, 0, NULL, 0, 0); + if (ret == -1 && errno == ENOSYS) + SKIP(return, "statmount() syscall not supported"); +} + +FIXTURE_TEARDOWN(fsmount_ns_userns) +{ + if (self->fd >= 0) + close(self->fd); + if (self->fs_fd >= 0) + close(self->fs_fd); +} + +TEST_F(fsmount_ns_userns, create_in_userns) +{ + pid_t pid; + int status; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int fs_fd, fd; + + /* Create new user namespace (also creates mount namespace) */ + if (setup_userns() != 0) + _exit(2); + + /* Now we have CAP_SYS_ADMIN in the user namespace */ + fs_fd = sys_fsopen("tmpfs", FSOPEN_CLOEXEC); + if (fs_fd < 0) + _exit(3); + + if (sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0) < 0) { + close(fs_fd); + _exit(4); + } + + fd = sys_fsmount(fs_fd, FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC, 0); + close(fs_fd); + + if (fd < 0) { + if (errno == EINVAL) + _exit(6); /* FSMOUNT_NAMESPACE not supported */ + _exit(1); + } + + /* Verify we can get the namespace ID */ + if (get_mnt_ns_id(fd, &new_ns_id) != 0) + _exit(7); + + /* Verify we can list mounts in the new namespace */ + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + if (nr_mounts < 0) + _exit(8); + + /* Should have at least 1 mount (the tmpfs) */ + if (nr_mounts < 1) + _exit(9); + + close(fd); + _exit(0); + } + + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + + switch (WEXITSTATUS(status)) { + case 0: + /* Success */ + break; + case 1: + ASSERT_FALSE(true) TH_LOG("fsmount(FSMOUNT_NAMESPACE) failed in userns"); + break; + case 2: + SKIP(return, "setup_userns failed"); + break; + case 3: + SKIP(return, "fsopen failed in userns"); + break; + case 4: + SKIP(return, "fsconfig CMD_CREATE failed in userns"); + break; + case 6: + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + break; + case 7: + ASSERT_FALSE(true) TH_LOG("Failed to get mount namespace ID"); + break; + case 8: + ASSERT_FALSE(true) TH_LOG("listmount failed in new namespace"); + break; + case 9: + ASSERT_FALSE(true) TH_LOG("New namespace has no mounts"); + break; + default: + ASSERT_FALSE(true) TH_LOG("Unexpected error in child (exit %d)", + WEXITSTATUS(status)); + break; + } +} + +TEST_F(fsmount_ns_userns, setns_in_userns) +{ + pid_t pid; + int status; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + uint64_t new_ns_id; + int fs_fd, fd; + pid_t inner_pid; + int inner_status; + + /* Create new user namespace */ + if (setup_userns() != 0) + _exit(2); + + fs_fd = sys_fsopen("tmpfs", FSOPEN_CLOEXEC); + if (fs_fd < 0) + _exit(3); + + if (sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0) < 0) { + close(fs_fd); + _exit(4); + } + + fd = sys_fsmount(fs_fd, FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC, 0); + close(fs_fd); + + if (fd < 0) { + if (errno == EINVAL) + _exit(6); + _exit(1); + } + + if (get_mnt_ns_id(fd, &new_ns_id) != 0) + _exit(7); + + /* Fork again to test setns into the new namespace */ + inner_pid = fork(); + if (inner_pid < 0) + _exit(10); + + if (inner_pid == 0) { + /* Inner child: enter the new namespace */ + if (setns(fd, CLONE_NEWNS) < 0) + _exit(1); + _exit(0); + } + + if (waitpid(inner_pid, &inner_status, 0) != inner_pid) + _exit(11); + + if (!WIFEXITED(inner_status) || WEXITSTATUS(inner_status) != 0) + _exit(12); + + close(fd); + _exit(0); + } + + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + + switch (WEXITSTATUS(status)) { + case 0: + /* Success */ + break; + case 1: + ASSERT_FALSE(true) TH_LOG("fsmount or setns failed in userns"); + break; + case 2: + SKIP(return, "setup_userns failed"); + break; + case 3: + SKIP(return, "fsopen failed in userns"); + break; + case 4: + SKIP(return, "fsconfig CMD_CREATE failed in userns"); + break; + case 6: + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + break; + case 7: + ASSERT_FALSE(true) TH_LOG("Failed to get mount namespace ID"); + break; + case 10: + ASSERT_FALSE(true) TH_LOG("Inner fork failed"); + break; + case 11: + ASSERT_FALSE(true) TH_LOG("Inner waitpid failed"); + break; + case 12: + ASSERT_FALSE(true) TH_LOG("setns into new namespace failed"); + break; + default: + ASSERT_FALSE(true) TH_LOG("Unexpected error in child (exit %d)", + WEXITSTATUS(status)); + break; + } +} + +TEST_F(fsmount_ns_userns, umount_fails_einval) +{ + pid_t pid; + int status; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int fs_fd, fd; + ssize_t i; + + /* Create new user namespace */ + if (setup_userns() != 0) + _exit(2); + + fs_fd = sys_fsopen("tmpfs", FSOPEN_CLOEXEC); + if (fs_fd < 0) + _exit(3); + + if (sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0) < 0) { + close(fs_fd); + _exit(4); + } + + fd = sys_fsmount(fs_fd, FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC, 0); + close(fs_fd); + + if (fd < 0) { + if (errno == EINVAL) + _exit(6); + _exit(1); + } + + if (get_mnt_ns_id(fd, &new_ns_id) != 0) + _exit(7); + + /* Get all mounts in the new namespace */ + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, LISTMOUNT_REVERSE); + if (nr_mounts < 0) + _exit(13); + + if (nr_mounts < 1) + _exit(14); + + /* Enter the new namespace */ + if (setns(fd, CLONE_NEWNS) < 0) + _exit(8); + + for (i = 0; i < nr_mounts; i++) { + struct statmount *sm; + const char *mnt_point; + + sm = statmount_alloc(list[i], new_ns_id, + STATMOUNT_MNT_POINT, 0); + if (!sm) + _exit(15); + + mnt_point = sm->str + sm->mnt_point; + + if (umount2(mnt_point, MNT_DETACH) == 0) { + free(sm); + _exit(9); + } + + if (errno != EINVAL) { + /* Wrong error */ + free(sm); + _exit(10); + } + + free(sm); + } + + close(fd); + _exit(0); + } + + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + + switch (WEXITSTATUS(status)) { + case 0: + break; + case 1: + ASSERT_FALSE(true) TH_LOG("fsmount(FSMOUNT_NAMESPACE) failed"); + break; + case 2: + SKIP(return, "setup_userns failed"); + break; + case 3: + SKIP(return, "fsopen failed in userns"); + break; + case 4: + SKIP(return, "fsconfig CMD_CREATE failed in userns"); + break; + case 6: + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + break; + case 7: + ASSERT_FALSE(true) TH_LOG("Failed to get mount namespace ID"); + break; + case 8: + ASSERT_FALSE(true) TH_LOG("setns into new namespace failed"); + break; + case 9: + ASSERT_FALSE(true) TH_LOG("umount succeeded but should have failed with EINVAL"); + break; + case 10: + ASSERT_FALSE(true) TH_LOG("umount failed with wrong error (expected EINVAL)"); + break; + case 13: + ASSERT_FALSE(true) TH_LOG("listmount failed"); + break; + case 14: + ASSERT_FALSE(true) TH_LOG("No mounts in new namespace"); + break; + case 15: + ASSERT_FALSE(true) TH_LOG("statmount_alloc failed"); + break; + default: + ASSERT_FALSE(true) TH_LOG("Unexpected error in child (exit %d)", + WEXITSTATUS(status)); + break; + } +} + +TEST_F(fsmount_ns_userns, umount_succeeds) +{ + pid_t pid; + int status; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int fs_fd, fd; + ssize_t i; + + if (unshare(CLONE_NEWNS)) + _exit(1); + + if (sys_mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) != 0) + _exit(1); + + fs_fd = sys_fsopen("tmpfs", FSOPEN_CLOEXEC); + if (fs_fd < 0) + _exit(3); + + if (sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0) < 0) { + close(fs_fd); + _exit(4); + } + + fd = sys_fsmount(fs_fd, FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC, 0); + close(fs_fd); + + if (fd < 0) { + if (errno == EINVAL) + _exit(6); + _exit(1); + } + + if (get_mnt_ns_id(fd, &new_ns_id) != 0) + _exit(7); + + /* Get all mounts in the new namespace */ + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, LISTMOUNT_REVERSE); + if (nr_mounts < 0) + _exit(13); + + if (nr_mounts < 1) + _exit(14); + + /* Enter the new namespace */ + if (setns(fd, CLONE_NEWNS) < 0) + _exit(8); + + for (i = 0; i < nr_mounts; i++) { + struct statmount *sm; + const char *mnt_point; + + sm = statmount_alloc(list[i], new_ns_id, + STATMOUNT_MNT_POINT, 0); + if (!sm) + _exit(15); + + mnt_point = sm->str + sm->mnt_point; + + if (umount2(mnt_point, MNT_DETACH) != 0) { + free(sm); + _exit(9); + } + + free(sm); + } + + close(fd); + _exit(0); + } + + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + + switch (WEXITSTATUS(status)) { + case 0: + break; + case 1: + ASSERT_FALSE(true) TH_LOG("fsmount(FSMOUNT_NAMESPACE) failed or unshare failed"); + break; + case 3: + SKIP(return, "fsopen failed"); + break; + case 4: + SKIP(return, "fsconfig CMD_CREATE failed"); + break; + case 6: + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + break; + case 7: + ASSERT_FALSE(true) TH_LOG("Failed to get mount namespace ID"); + break; + case 8: + ASSERT_FALSE(true) TH_LOG("setns into new namespace failed"); + break; + case 9: + ASSERT_FALSE(true) TH_LOG("umount failed but should have succeeded"); + break; + case 13: + ASSERT_FALSE(true) TH_LOG("listmount failed"); + break; + case 14: + ASSERT_FALSE(true) TH_LOG("No mounts in new namespace"); + break; + case 15: + ASSERT_FALSE(true) TH_LOG("statmount_alloc failed"); + break; + default: + ASSERT_FALSE(true) TH_LOG("Unexpected error in child (exit %d)", + WEXITSTATUS(status)); + break; + } +} + +FIXTURE(fsmount_ns_mount_attrs) +{ + int fd; + int fs_fd; +}; + +FIXTURE_SETUP(fsmount_ns_mount_attrs) +{ + int ret; + + self->fd = -1; + self->fs_fd = -1; + + /* Check if fsopen syscall is supported */ + ret = sys_fsopen("tmpfs", 0); + if (ret == -1 && errno == ENOSYS) + SKIP(return, "fsopen() syscall not supported"); + if (ret >= 0) + close(ret); + + /* Check if statmount/listmount are supported */ + ret = statmount(0, 0, 0, 0, NULL, 0, 0); + if (ret == -1 && errno == ENOSYS) + SKIP(return, "statmount() syscall not supported"); +} + +FIXTURE_TEARDOWN(fsmount_ns_mount_attrs) +{ + if (self->fd >= 0) + close(self->fd); + if (self->fs_fd >= 0) + close(self->fs_fd); +} + +TEST_F(fsmount_ns_mount_attrs, readonly) +{ + struct statmount sm; + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int ret; + + self->fs_fd = create_tmpfs_fd(); + ASSERT_GE(self->fs_fd, 0); + + self->fd = sys_fsmount(self->fs_fd, FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC, + MOUNT_ATTR_RDONLY); + if (self->fd < 0 && errno == EINVAL) + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + + ASSERT_GE(self->fd, 0); + + ret = get_mnt_ns_id(self->fd, &new_ns_id); + ASSERT_EQ(ret, 0); + + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + ASSERT_GE(nr_mounts, 1); + + ret = statmount(list[0], new_ns_id, 0, STATMOUNT_MNT_BASIC, &sm, sizeof(sm), 0); + ASSERT_EQ(ret, 0); + + /* Verify the mount is read-only */ + ASSERT_TRUE(sm.mnt_attr & MOUNT_ATTR_RDONLY); +} + +TEST_F(fsmount_ns_mount_attrs, noexec) +{ + struct statmount sm; + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int ret; + + self->fs_fd = create_tmpfs_fd(); + ASSERT_GE(self->fs_fd, 0); + + self->fd = sys_fsmount(self->fs_fd, FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC, + MOUNT_ATTR_NOEXEC); + if (self->fd < 0 && errno == EINVAL) + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + + ASSERT_GE(self->fd, 0); + + ret = get_mnt_ns_id(self->fd, &new_ns_id); + ASSERT_EQ(ret, 0); + + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + ASSERT_GE(nr_mounts, 1); + + ret = statmount(list[0], new_ns_id, 0, STATMOUNT_MNT_BASIC, &sm, sizeof(sm), 0); + ASSERT_EQ(ret, 0); + + /* Verify the mount is noexec */ + ASSERT_TRUE(sm.mnt_attr & MOUNT_ATTR_NOEXEC); +} + +TEST_F(fsmount_ns_mount_attrs, nosuid) +{ + struct statmount sm; + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int ret; + + self->fs_fd = create_tmpfs_fd(); + ASSERT_GE(self->fs_fd, 0); + + self->fd = sys_fsmount(self->fs_fd, FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC, + MOUNT_ATTR_NOSUID); + if (self->fd < 0 && errno == EINVAL) + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + + ASSERT_GE(self->fd, 0); + + ret = get_mnt_ns_id(self->fd, &new_ns_id); + ASSERT_EQ(ret, 0); + + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + ASSERT_GE(nr_mounts, 1); + + ret = statmount(list[0], new_ns_id, 0, STATMOUNT_MNT_BASIC, &sm, sizeof(sm), 0); + ASSERT_EQ(ret, 0); + + /* Verify the mount is nosuid */ + ASSERT_TRUE(sm.mnt_attr & MOUNT_ATTR_NOSUID); +} + +TEST_F(fsmount_ns_mount_attrs, noatime) +{ + struct statmount sm; + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int ret; + + self->fs_fd = create_tmpfs_fd(); + ASSERT_GE(self->fs_fd, 0); + + self->fd = sys_fsmount(self->fs_fd, FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC, + MOUNT_ATTR_NOATIME); + if (self->fd < 0 && errno == EINVAL) + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + + ASSERT_GE(self->fd, 0); + + ret = get_mnt_ns_id(self->fd, &new_ns_id); + ASSERT_EQ(ret, 0); + + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + ASSERT_GE(nr_mounts, 1); + + ret = statmount(list[0], new_ns_id, 0, STATMOUNT_MNT_BASIC, &sm, sizeof(sm), 0); + ASSERT_EQ(ret, 0); + + /* Verify the mount is noatime */ + ASSERT_TRUE(sm.mnt_attr & MOUNT_ATTR_NOATIME); +} + +TEST_F(fsmount_ns_mount_attrs, combined) +{ + struct statmount sm; + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int ret; + + self->fs_fd = create_tmpfs_fd(); + ASSERT_GE(self->fs_fd, 0); + + self->fd = sys_fsmount(self->fs_fd, FSMOUNT_NAMESPACE | FSMOUNT_CLOEXEC, + MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOEXEC | + MOUNT_ATTR_NOSUID | MOUNT_ATTR_NOATIME); + if (self->fd < 0 && errno == EINVAL) + SKIP(return, "FSMOUNT_NAMESPACE not supported"); + + ASSERT_GE(self->fd, 0); + + ret = get_mnt_ns_id(self->fd, &new_ns_id); + ASSERT_EQ(ret, 0); + + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + ASSERT_GE(nr_mounts, 1); + + ret = statmount(list[0], new_ns_id, 0, STATMOUNT_MNT_BASIC, &sm, sizeof(sm), 0); + ASSERT_EQ(ret, 0); + + /* Verify all attributes are set */ + ASSERT_TRUE(sm.mnt_attr & MOUNT_ATTR_RDONLY); + ASSERT_TRUE(sm.mnt_attr & MOUNT_ATTR_NOEXEC); + ASSERT_TRUE(sm.mnt_attr & MOUNT_ATTR_NOSUID); + ASSERT_TRUE(sm.mnt_attr & MOUNT_ATTR_NOATIME); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/fuse/.gitignore b/tools/testing/selftests/filesystems/fuse/.gitignore index 3e72e742d08e..fb51603fe419 100644 --- a/tools/testing/selftests/filesystems/fuse/.gitignore +++ b/tools/testing/selftests/filesystems/fuse/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only fuse_mnt fusectl_test +write_extend_eof_test diff --git a/tools/testing/selftests/filesystems/fuse/Makefile b/tools/testing/selftests/filesystems/fuse/Makefile index 612aad69a93a..95a1ee947ca7 100644 --- a/tools/testing/selftests/filesystems/fuse/Makefile +++ b/tools/testing/selftests/filesystems/fuse/Makefile @@ -3,10 +3,20 @@ CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) TEST_GEN_PROGS := fusectl_test +TEST_GEN_PROGS += write_extend_eof_test TEST_GEN_FILES := fuse_mnt +# fuse_acl_cache_test requires libfuse3; add it only when the library is present. +ACL_CFLAGS := $(shell pkg-config fuse3 --cflags 2>/dev/null) +ACL_LDLIBS := $(shell pkg-config fuse3 --libs 2>/dev/null) +ifneq ($(ACL_CFLAGS),) +TEST_GEN_PROGS += fuse_acl_cache_test +endif + include ../../lib.mk +$(OUTPUT)/write_extend_eof_test: LDLIBS += -lpthread + VAR_CFLAGS := $(shell pkg-config fuse --cflags 2>/dev/null) ifeq ($(VAR_CFLAGS),) VAR_CFLAGS := -D_FILE_OFFSET_BITS=64 -I/usr/include/fuse @@ -19,3 +29,6 @@ endif $(OUTPUT)/fuse_mnt: CFLAGS += $(VAR_CFLAGS) $(OUTPUT)/fuse_mnt: LDLIBS += $(VAR_LDLIBS) + +$(OUTPUT)/fuse_acl_cache_test: CFLAGS += $(ACL_CFLAGS) +$(OUTPUT)/fuse_acl_cache_test: LDLIBS += $(ACL_LDLIBS) diff --git a/tools/testing/selftests/filesystems/fuse/fuse_acl_cache_test.c b/tools/testing/selftests/filesystems/fuse/fuse_acl_cache_test.c new file mode 100644 index 000000000000..2411a6e285f1 --- /dev/null +++ b/tools/testing/selftests/filesystems/fuse/fuse_acl_cache_test.c @@ -0,0 +1,347 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test: FUSE ACL caching bug triggered by AT_STATX_FORCE_SYNC + * + * A FUSE mount that does not negotiate FUSE_POSIX_ACL initialises every inode + * with i_acl = i_default_acl = ACL_DONT_CACHE. When a fresh stat is needed + * (e.g. AT_STATX_FORCE_SYNC), fuse_update_get_attr() calls + * forget_all_cached_acls() before issuing FUSE_GETATTR. On an unfixed kernel, + * __forget_cached_acl() replaces ACL_DONT_CACHE with ACL_NOT_CACHED, + * inadvertently enabling the kernel ACL cache for that inode. The next + * getxattr populates the cache. Because fuse_set_acl() skips + * forget_all_cached_acls() for !fc->posix_acl mounts, any subsequent change to + * the ACL leaves the stale kernel entry in place, and the next getxattr returns + * wrong data without ever reaching the FUSE daemon. + * + * Fix (fs/posix_acl.c): __forget_cached_acl() returns early when *p is + * ACL_DONT_CACHE, preserving the "never cache" invariant for the inode's + * lifetime. + * + * Test outline: + * 1. Mount a minimal FUSE fs (no FUSE_POSIX_ACL negotiated). + * 2. lgetxattr -> daemon called, ACL_A returned, NOT cached (ACL_DONT_CACHE). + * 3. statx(AT_STATX_FORCE_SYNC) -> forget_all_cached_acls() called. + * Buggy: ACL_DONT_CACHE -> ACL_NOT_CACHED (cache enabled). + * Fixed: ACL_DONT_CACHE preserved. + * 4. lgetxattr -> daemon called, ACL_A returned. + * Buggy: result now cached (ACL_NOT_CACHED -> cached). + * Fixed: result still not cached. + * 5. Daemon switches to ACL_B internally (different size). + * 6. lgetxattr -> should return ACL_B (44 bytes). + * Buggy: cache hit, returns stale ACL_A (28 bytes). FAIL. + * Fixed: no cache, daemon called, returns ACL_B (44 bytes). PASS. + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <linux/limits.h> +#include <pthread.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/xattr.h> +#include <unistd.h> + +#define FUSE_USE_VERSION 31 +#include <fuse_lowlevel.h> + +#include "kselftest_harness.h" + +/* ---- ACL binary encoding ------------------------------------------------ */ +/* + * POSIX ACL v2 xattr format (little-endian): + * header: u32 version (= 0x00000002) + * entry: u16 tag | u16 perm | u32 id + * + * Entries must appear in tag-ascending order; named USER/GROUP entries + * require a MASK entry. Both ACLs pass posix_acl_from_xattr() validation. + */ + +/* ACL_A: 3 entries (USER_OBJ:rwx, GROUP_OBJ:r-x, OTHER:r-x) = 28 bytes */ +static const uint8_t acl_a[] = { + 0x02, 0x00, 0x00, 0x00, /* v2 header */ + 0x01, 0x00, 0x07, 0x00, 0xff, 0xff, 0xff, 0xff, /* USER_OBJ rwx */ + 0x04, 0x00, 0x05, 0x00, 0xff, 0xff, 0xff, 0xff, /* GROUP_OBJ r-x */ + 0x20, 0x00, 0x05, 0x00, 0xff, 0xff, 0xff, 0xff, /* OTHER r-x */ +}; + +/* + * ACL_B: 5 entries — adds USER uid=1 and MASK = 44 bytes. + * A named USER entry requires a MASK; all tags in ascending order. + */ +static const uint8_t acl_b[] = { + 0x02, 0x00, 0x00, 0x00, /* v2 header */ + 0x01, 0x00, 0x07, 0x00, 0xff, 0xff, 0xff, 0xff, /* USER_OBJ rwx */ + 0x02, 0x00, 0x07, 0x00, 0x01, 0x00, 0x00, 0x00, /* USER uid=1 rwx */ + 0x04, 0x00, 0x05, 0x00, 0xff, 0xff, 0xff, 0xff, /* GROUP_OBJ r-x */ + 0x10, 0x00, 0x07, 0x00, 0xff, 0xff, 0xff, 0xff, /* MASK rwx */ + 0x20, 0x00, 0x05, 0x00, 0xff, 0xff, 0xff, 0xff, /* OTHER r-x */ +}; + +/* ---- Shared state (daemon thread <-> test thread) ----------------------- */ + +#define FILE_INO 2 +#define FILE_NAME "testfile" + +struct daemon_state { + pthread_mutex_t lock; + const uint8_t *acl; + size_t acl_size; + int getxattr_count; +}; + +/* + * Global: callbacks are stateless fns so we use a single global. + * Safe because only one test instance runs at a time. + */ +static struct daemon_state g_ds = { + .lock = PTHREAD_MUTEX_INITIALIZER, +}; + +/* ---- FUSE lowlevel callbacks -------------------------------------------- */ + +static void fs_lookup(fuse_req_t req, fuse_ino_t parent, const char *name) +{ + if (parent != FUSE_ROOT_ID || strcmp(name, FILE_NAME)) { + fuse_reply_err(req, ENOENT); + return; + } + struct fuse_entry_param e = {}; + + /* + * Long attr/entry timeouts so that normal stat() calls do not + * expire and trigger forget_all_cached_acls() on their own; + * only the explicit AT_STATX_FORCE_SYNC should trigger it. + */ + e.ino = FILE_INO; + e.generation = 1; + e.attr_timeout = 10.0; + e.entry_timeout = 10.0; + e.attr.st_ino = FILE_INO; + e.attr.st_mode = S_IFREG | 0644; + e.attr.st_nlink = 1; + fuse_reply_entry(req, &e); +} + +static void fs_getattr(fuse_req_t req, fuse_ino_t ino, + struct fuse_file_info *fi) +{ + struct stat st = {}; + + (void)fi; + if (ino == FUSE_ROOT_ID) { + st.st_ino = FUSE_ROOT_ID; + st.st_mode = S_IFDIR | 0755; + st.st_nlink = 2; + } else if (ino == FILE_INO) { + st.st_ino = FILE_INO; + st.st_mode = S_IFREG | 0644; + st.st_nlink = 1; + } else { + fuse_reply_err(req, ENOENT); + return; + } + fuse_reply_attr(req, &st, 10); +} + +static void fs_getxattr(fuse_req_t req, fuse_ino_t ino, const char *name, + size_t size) +{ + if (ino != FILE_INO || + strcmp(name, "system.posix_acl_access") != 0) { + fuse_reply_err(req, ENODATA); + return; + } + + pthread_mutex_lock(&g_ds.lock); + const uint8_t *acl = g_ds.acl; + size_t acl_size = g_ds.acl_size; + g_ds.getxattr_count++; + pthread_mutex_unlock(&g_ds.lock); + + if (size == 0) + fuse_reply_xattr(req, acl_size); + else if (size < acl_size) + fuse_reply_err(req, ERANGE); + else + fuse_reply_buf(req, (const char *)acl, acl_size); +} + +static const struct fuse_lowlevel_ops fs_ops = { + .lookup = fs_lookup, + .getattr = fs_getattr, + .getxattr = fs_getxattr, +}; + +/* ---- Daemon thread ------------------------------------------------------- */ + +static void *run_daemon(void *arg) +{ + fuse_session_loop((struct fuse_session *)arg); + return NULL; +} + +/* ---- kselftest harness --------------------------------------------------- */ + +FIXTURE(acl_cache) { + struct fuse_session *se; + char mountpoint[PATH_MAX]; + char file_path[PATH_MAX]; + pthread_t thread; +}; + +FIXTURE_SETUP(acl_cache) +{ + char *fuse_argv[] = { "fuse_acl_cache_test", NULL }; + struct fuse_args args = FUSE_ARGS_INIT(1, fuse_argv); + + g_ds.acl = acl_a; + g_ds.acl_size = sizeof(acl_a); + g_ds.getxattr_count = 0; + + strcpy(self->mountpoint, "/tmp/acl_cache_test_XXXXXX"); + if (!mkdtemp(self->mountpoint)) + SKIP(return, "mkdtemp: %s", strerror(errno)); + + snprintf(self->file_path, sizeof(self->file_path), + "%s/" FILE_NAME, self->mountpoint); + + self->se = fuse_session_new(&args, &fs_ops, sizeof(fs_ops), NULL); + if (!self->se) { + rmdir(self->mountpoint); + SKIP(return, "fuse_session_new failed"); + } + + if (fuse_session_mount(self->se, self->mountpoint)) { + fuse_session_destroy(self->se); + rmdir(self->mountpoint); + SKIP(return, "fuse_session_mount failed " + "(missing fusermount3 or insufficient privileges)"); + } + + if (pthread_create(&self->thread, NULL, run_daemon, self->se)) { + fuse_session_unmount(self->se); + fuse_session_destroy(self->se); + rmdir(self->mountpoint); + SKIP(return, "pthread_create: %s", strerror(errno)); + } + + fuse_opt_free_args(&args); +} + +FIXTURE_TEARDOWN(acl_cache) +{ + fuse_session_exit(self->se); + fuse_session_unmount(self->se); + pthread_join(self->thread, NULL); + fuse_session_destroy(self->se); + rmdir(self->mountpoint); +} + +static int do_force_statx(const char *path) +{ + struct statx stx; + + return statx(AT_FDCWD, path, AT_STATX_FORCE_SYNC, STATX_BASIC_STATS, + &stx); +} + +TEST_F(acl_cache, stale_after_force_sync) +{ + char buf[512]; + ssize_t sz; + int count; + + /* + * Step 1: two getxattr calls before any statx(FORCE_SYNC). + * i_acl == ACL_DONT_CACHE. __get_acl's cmpxchg(p, ACL_NOT_CACHED, + * sentinel) finds *p != ACL_NOT_CACHED on every call, so the sentinel + * is never placed and the result is never cached. Both calls must + * reach the daemon, proving ACL_DONT_CACHE suppresses caching. + */ + sz = lgetxattr(self->file_path, "system.posix_acl_access", + buf, sizeof(buf)); + ASSERT_EQ(sz, (ssize_t)sizeof(acl_a)); + + sz = lgetxattr(self->file_path, "system.posix_acl_access", + buf, sizeof(buf)); + ASSERT_EQ(sz, (ssize_t)sizeof(acl_a)); + + pthread_mutex_lock(&g_ds.lock); + count = g_ds.getxattr_count; + pthread_mutex_unlock(&g_ds.lock); + + ASSERT_EQ(count, 2); + TH_LOG("step 1 OK: both pre-trigger getxattrs reached daemon (count=%d), " + "ACL_DONT_CACHE is working", count); + + /* + * Step 2: statx(AT_STATX_FORCE_SYNC). + * fuse_update_get_attr() calls forget_all_cached_acls() before sending + * FUSE_GETATTR. + * Buggy kernel: ACL_DONT_CACHE -> ACL_NOT_CACHED (cache enabled) + * Fixed kernel: ACL_DONT_CACHE preserved (no effect) + */ + ASSERT_EQ(do_force_statx(self->file_path), 0); + TH_LOG("step 2 OK: statx(AT_STATX_FORCE_SYNC) succeeded"); + + /* + * Step 3: getxattr — cache population attempt after the trigger. + * Buggy: *p == ACL_NOT_CACHED -> sentinel placed -> fuse_get_inode_acl + * called -> ACL_A parsed and stored in the kernel cache. + * Fixed: *p == ACL_DONT_CACHE -> sentinel placement skipped -> + * fuse_get_inode_acl called but result not cached. + * Either way the correct ACL_A is returned here. + */ + sz = lgetxattr(self->file_path, "system.posix_acl_access", + buf, sizeof(buf)); + ASSERT_EQ(sz, (ssize_t)sizeof(acl_a)); + + pthread_mutex_lock(&g_ds.lock); + count = g_ds.getxattr_count; + pthread_mutex_unlock(&g_ds.lock); + + ASSERT_EQ(count, 3); + TH_LOG("step 3 OK: post-trigger getxattr reached daemon (count=%d), " + "returned correct ACL_A (%zd bytes)", count, sz); + + /* + * Step 4: switch daemon to ACL_B (different size: 44 vs 28 bytes). + * Simulates an ACL change that fuse_set_acl() would NOT invalidate for + * !fc->posix_acl mounts (it skips forget_all_cached_acls in that case). + * On a fixed kernel the ACL was never cached, so this is moot. + */ + pthread_mutex_lock(&g_ds.lock); + g_ds.acl = acl_b; + g_ds.acl_size = sizeof(acl_b); + pthread_mutex_unlock(&g_ds.lock); + TH_LOG("step 4: daemon switched to ACL_B (%zu bytes)", sizeof(acl_b)); + + /* + * Step 5: getxattr — the decisive check. + * Buggy kernel: cache hit -> stale ACL_A (28 bytes), count stays 3. + * Fixed kernel: no cache -> daemon called -> ACL_B (44 bytes), count 4. + */ + sz = lgetxattr(self->file_path, "system.posix_acl_access", + buf, sizeof(buf)); + + pthread_mutex_lock(&g_ds.lock); + count = g_ds.getxattr_count; + pthread_mutex_unlock(&g_ds.lock); + + if (sz == (ssize_t)sizeof(acl_a)) + TH_LOG("step 5 BUG: stale ACL_A (%zd bytes) from kernel cache " + "(count=%d); ACL_DONT_CACHE corrupted by " + "forget_all_cached_acls()", sz, count); + else + TH_LOG("step 5 OK: daemon reached (count=%d), " + "fresh ACL_B (%zd bytes)", count, sz); + + EXPECT_EQ(sz, (ssize_t)sizeof(acl_b)); + EXPECT_EQ(count, 4); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/fuse/write_extend_eof_test.c b/tools/testing/selftests/filesystems/fuse/write_extend_eof_test.c new file mode 100644 index 000000000000..ca6ce6eca382 --- /dev/null +++ b/tools/testing/selftests/filesystems/fuse/write_extend_eof_test.c @@ -0,0 +1,368 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Regression test for the fuse write-extend partial-EOF-page zeroing bug. + * + * A buffered write that extends i_size past a non-page-aligned EOF must zero + * the tail of the old last page. If an application has mmap'd that page and + * stored into the post-EOF region (undefined until the file grows), the + * now-in-bounds tail must read back as zero, not as the stale stored bytes. + * + * The bug is exposed on a non-writeback_cache server that keeps the page cache + * across the write (FOPEN_KEEP_CACHE without FOPEN_DIRECT_IO). This test is a + * raw /dev/fuse server in that mode; the backing data is always zero in the + * hole, so any non-zero byte a read sees is stale page-cache data. + * + * Requires root to mount fuse. + */ +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <linux/falloc.h> +#include <pthread.h> +#include <stdint.h> +#include <string.h> +#include <unistd.h> +#include <sys/mman.h> +#include <sys/mount.h> +#include <sys/stat.h> +#include <sys/uio.h> +#include <linux/fuse.h> + +#include "../../kselftest_harness.h" + +#define FUSE_ROOT_ID 1 +#define FILE_INO 2 +#define MAX_WRITE (128 * 1024) +#define BACKING_SIZE (4 * 1024 * 1024) +#define POLLUTE 0xee + +/* Server-side state, shared with the responder thread. */ +struct server { + int fd; + unsigned char backing[BACKING_SIZE]; /* authoritative bytes */ + uint64_t size; +}; + +static void reply(int fd, uint64_t unique, int error, void *data, size_t len) +{ + struct fuse_out_header oh = { + .len = sizeof(oh) + (data ? len : 0), + .error = error, + .unique = unique, + }; + struct iovec iov[2] = { { &oh, sizeof(oh) }, { data, len } }; + + /* Errors here are teardown races (device closed on unmount); ignore. */ + if (writev(fd, iov, data ? 2 : 1) < 0) + return; +} + +static void fill_attr(struct fuse_attr *a, uint64_t ino, uint32_t mode, + uint64_t size) +{ + memset(a, 0, sizeof(*a)); + a->ino = ino; + a->mode = mode; + a->nlink = 1; + a->size = size; + a->blksize = sysconf(_SC_PAGESIZE); +} + +static void *server_thread(void *arg) +{ + struct server *s = arg; + static char buf[MAX_WRITE + 4096]; + + for (;;) { + ssize_t n = read(s->fd, buf, sizeof(buf)); + struct fuse_in_header *ih = (void *)buf; + + if (n < 0) { + if (errno == EINTR || errno == EAGAIN) + continue; + return NULL; /* device closed on unmount */ + } + if (n < (ssize_t)sizeof(*ih)) + continue; + + switch (ih->opcode) { + case FUSE_INIT: { + struct fuse_init_in *in = (void *)(ih + 1); + struct fuse_init_out out = {0}; + + /* No FUSE_WRITEBACK_CACHE: the exposed configuration. */ + out.major = FUSE_KERNEL_VERSION; + out.minor = FUSE_KERNEL_MINOR_VERSION; + out.max_readahead = in->max_readahead; + out.max_write = MAX_WRITE; + out.max_background = 16; + out.congestion_threshold = 12; + out.flags = FUSE_MAX_PAGES; + out.max_pages = MAX_WRITE / sysconf(_SC_PAGESIZE); + reply(s->fd, ih->unique, 0, &out, sizeof(out)); + break; + } + case FUSE_GETATTR: { + struct fuse_attr_out out = {0}; + int root = ih->nodeid == FUSE_ROOT_ID; + + out.attr_valid = 3600; + fill_attr(&out.attr, ih->nodeid, + root ? (S_IFDIR | 0755) : (S_IFREG | 0644), + root ? 0 : s->size); + reply(s->fd, ih->unique, 0, &out, sizeof(out)); + break; + } + case FUSE_LOOKUP: { + struct fuse_entry_out out = {0}; + + out.nodeid = FILE_INO; + out.attr_valid = 3600; + out.entry_valid = 3600; + fill_attr(&out.attr, FILE_INO, S_IFREG | 0644, s->size); + reply(s->fd, ih->unique, 0, &out, sizeof(out)); + break; + } + case FUSE_OPEN: + case FUSE_OPENDIR: { + struct fuse_open_out out = {0}; + + /* Keep the cache across the write, but not direct I/O. */ + out.open_flags = FOPEN_KEEP_CACHE; + reply(s->fd, ih->unique, 0, &out, sizeof(out)); + break; + } + case FUSE_READ: { + struct fuse_read_in *in = (void *)(ih + 1); + uint64_t off = in->offset; + uint32_t size = in->size; + + if (off >= BACKING_SIZE) + size = 0; + else if (off + size > BACKING_SIZE) + size = BACKING_SIZE - off; + reply(s->fd, ih->unique, 0, s->backing + off, size); + break; + } + case FUSE_WRITE: { + struct fuse_write_in *in = (void *)(ih + 1); + struct fuse_write_out out = {0}; + uint64_t off = in->offset; + uint32_t size = in->size; + + if (off < BACKING_SIZE) { + uint32_t c = size; + + if (off + c > BACKING_SIZE) + c = BACKING_SIZE - off; + memcpy(s->backing + off, in + 1, c); + if (off + c > s->size) + s->size = off + c; + } + out.size = size; + reply(s->fd, ih->unique, 0, &out, sizeof(out)); + break; + } + case FUSE_SETATTR: { + struct fuse_setattr_in *in = (void *)(ih + 1); + struct fuse_attr_out out = {0}; + + if ((in->valid & FATTR_SIZE) && in->size <= BACKING_SIZE) { + if (in->size > s->size) + memset(s->backing + s->size, 0, + in->size - s->size); + s->size = in->size; + } + out.attr_valid = 3600; + fill_attr(&out.attr, ih->nodeid, S_IFREG | 0644, s->size); + reply(s->fd, ih->unique, 0, &out, sizeof(out)); + break; + } + case FUSE_FALLOCATE: { + struct fuse_fallocate_in *in = (void *)(ih + 1); + uint64_t end = in->offset + in->length; + + /* Only plain (size-extending) fallocate is used here. */ + if (!(in->mode & FALLOC_FL_KEEP_SIZE) && + end <= BACKING_SIZE && end > s->size) { + memset(s->backing + s->size, 0, end - s->size); + s->size = end; + } + reply(s->fd, ih->unique, 0, NULL, 0); + break; + } + case FUSE_FLUSH: + case FUSE_RELEASE: + case FUSE_RELEASEDIR: + case FUSE_FSYNC: + case FUSE_ACCESS: + reply(s->fd, ih->unique, 0, NULL, 0); + break; + case FUSE_FORGET: + break; + default: + reply(s->fd, ih->unique, -EOPNOTSUPP, NULL, 0); + break; + } + } +} + +FIXTURE(fuse) +{ + struct server *srv; + pthread_t thread; + char dir[64]; + long page; /* runtime page size */ + off_t eof; /* mid-page EOF, page-relative */ + int fd; /* open test file */ + char *map; /* mmap of the EOF page */ + int mounted; +}; + +FIXTURE_SETUP(fuse) +{ + char opts[128]; + pthread_t t; + + if (geteuid() != 0) + SKIP(return, "need root to mount fuse"); + + self->page = sysconf(_SC_PAGESIZE); + self->fd = -1; + self->map = MAP_FAILED; + + self->srv = mmap(NULL, sizeof(*self->srv), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(MAP_FAILED, self->srv); + + self->srv->fd = open("/dev/fuse", O_RDWR); + ASSERT_GE(self->srv->fd, 0); + + strcpy(self->dir, "/tmp/fuse_weof_XXXXXX"); + ASSERT_NE(NULL, mkdtemp(self->dir)); + + snprintf(opts, sizeof(opts), + "fd=%d,rootmode=40000,user_id=0,group_id=0", + self->srv->fd); + ASSERT_EQ(0, mount("fuse", self->dir, "fuse", 0, opts)); + self->mounted = 1; + + ASSERT_EQ(0, pthread_create(&t, NULL, server_thread, self->srv)); + self->thread = t; +} + +FIXTURE_TEARDOWN(fuse) +{ + if (self->map != MAP_FAILED) + munmap(self->map, self->page); + if (self->fd >= 0) + close(self->fd); + if (self->mounted) + umount2(self->dir, MNT_DETACH); + if (self->srv && self->srv != MAP_FAILED) { + if (self->srv->fd > 0) + close(self->srv->fd); + munmap(self->srv, sizeof(*self->srv)); + } + if (self->dir[0]) + rmdir(self->dir); +} + +/* + * Create the test file with a mid-page EOF and mmap-store POLLUTE into its + * post-EOF tail (a legal store, undefined until the file grows). Leaves the + * file open and the EOF page mapped in the fixture for the caller to extend. + */ +static void pollute_eof_tail(struct __test_metadata *_metadata, + FIXTURE_DATA(fuse) * self) +{ + off_t eof = 2 * self->page + self->page / 4; + char path[128]; + char *buf; + + snprintf(path, sizeof(path), "%s/file", self->dir); + self->fd = open(path, O_RDWR | O_CREAT | O_TRUNC, 0644); + ASSERT_GE(self->fd, 0); + self->eof = eof; + + buf = malloc(eof); + ASSERT_NE(NULL, buf); + memset(buf, 'A', eof); + ASSERT_EQ(eof, pwrite(self->fd, buf, eof, 0)); + free(buf); + + self->map = mmap(NULL, self->page, PROT_READ | PROT_WRITE, MAP_SHARED, + self->fd, eof & ~(self->page - 1)); + ASSERT_NE(MAP_FAILED, self->map); + memset(self->map + (eof & (self->page - 1)), POLLUTE, + self->page - (eof & (self->page - 1))); +} + +/* Assert the old post-EOF tail [eof, end of its page) now reads back as zero. */ +static void assert_tail_zeroed(struct __test_metadata *_metadata, + FIXTURE_DATA(fuse) * self) +{ + off_t base = self->eof & ~(self->page - 1); + char *tail = malloc(self->page); + int i; + + ASSERT_NE(NULL, tail); + ASSERT_EQ(self->page, pread(self->fd, tail, self->page, base)); + for (i = self->eof & (self->page - 1); i < self->page; i++) + ASSERT_EQ(0, tail[i]); + free(tail); +} + +/* Basic: pollute the post-EOF tail, extend past it by a later write. */ +TEST_F(fuse, write_extend) +{ + pollute_eof_tail(_metadata, self); + ASSERT_EQ(4, pwrite(self->fd, "data", 4, 5 * self->page + self->page / 3)); + assert_tail_zeroed(_metadata, self); +} + +/* Extend via ftruncate() rather than a write. */ +TEST_F(fuse, ftruncate_extend) +{ + pollute_eof_tail(_metadata, self); + ASSERT_EQ(0, ftruncate(self->fd, 8 * self->page)); + assert_tail_zeroed(_metadata, self); +} + +/* Extend via fallocate() starting at the old EOF. */ +TEST_F(fuse, fallocate_extend) +{ + pollute_eof_tail(_metadata, self); + ASSERT_EQ(0, fallocate(self->fd, 0, self->eof, 4 * self->page)); + assert_tail_zeroed(_metadata, self); +} + +/* A write landing inside the old EOF page must not clobber its own data. */ +TEST_F(fuse, extend_into_eof_page_preserves_data) +{ + off_t base, wr; + char *buf, *rd; + int i; + + pollute_eof_tail(_metadata, self); + base = self->eof & ~(self->page - 1); + wr = base + 3 * self->page / 4; /* starts in the EOF page */ + + buf = malloc(2 * self->page); + ASSERT_NE(NULL, buf); + memset(buf, 'B', 2 * self->page); + ASSERT_EQ(2 * self->page, pwrite(self->fd, buf, 2 * self->page, wr)); + free(buf); + + rd = malloc(self->page); + ASSERT_NE(NULL, rd); + ASSERT_EQ(self->page, pread(self->fd, rd, self->page, base)); + /* [eof, wr) is hole -> zero; [wr, page) is written data -> 'B'. */ + for (i = self->eof & (self->page - 1); i < wr - base; i++) + ASSERT_EQ(0, rd[i]); + for (i = wr - base; i < self->page; i++) + ASSERT_EQ('B', rd[i]); + free(rd); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/idmapped_tmpfile.c b/tools/testing/selftests/filesystems/idmapped_tmpfile.c new file mode 100644 index 000000000000..bc411ab8281e --- /dev/null +++ b/tools/testing/selftests/filesystems/idmapped_tmpfile.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <sched.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/fsuid.h> +#include <sys/stat.h> +#include <sys/syscall.h> + +#include <linux/mount.h> +#include <linux/types.h> + +#include "kselftest_harness.h" +#include "wrappers.h" +#include "utils.h" + +/* + * The test mount maps caller-visible ids [0, MAP_RANGE) onto the on-disk range + * [MAP_HOST, MAP_HOST + MAP_RANGE). An id outside [0, MAP_RANGE) therefore has + * no mapping in the mount and is not representable in the filesystem. + */ +#define MAP_HOST 10000 +#define MAP_RANGE 10000 +#define UNMAPPED 50000 + +#ifndef MOUNT_ATTR_IDMAP +#define MOUNT_ATTR_IDMAP 0x00100000 +#endif + +#ifndef __NR_mount_setattr +#define __NR_mount_setattr 442 +#endif + +static inline int sys_mount_setattr(int dfd, const char *path, + unsigned int flags, + struct mount_attr *attr, size_t size) +{ + return syscall(__NR_mount_setattr, dfd, path, flags, attr, size); +} + +/* + * Clone @path into a detached mount idmapped so that caller-visible ids + * [0, MAP_RANGE) map onto the on-disk ids [MAP_HOST, MAP_HOST + MAP_RANGE). + * Returns the mount fd, or -1 if idmapped mounts are not available. + */ +static int idmapped_clone(const char *path) +{ + struct mount_attr attr = { + .attr_set = MOUNT_ATTR_IDMAP, + }; + int fd_tree, userns_fd, ret; + + fd_tree = sys_open_tree(AT_FDCWD, path, + OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + if (fd_tree < 0) + return -1; + + userns_fd = get_userns_fd(MAP_HOST, 0, MAP_RANGE); + if (userns_fd < 0) { + close(fd_tree); + return -1; + } + + attr.userns_fd = userns_fd; + ret = sys_mount_setattr(fd_tree, "", AT_EMPTY_PATH, &attr, sizeof(attr)); + close(userns_fd); + if (ret) { + close(fd_tree); + return -1; + } + + return fd_tree; +} + +FIXTURE(idmapped_tmpfile) { + char dir[64]; /* non-idmapped path to the layer directory */ +}; + +FIXTURE_SETUP(idmapped_tmpfile) +{ + /* Private mount namespace so test mounts need no cleanup. */ + ASSERT_EQ(unshare(CLONE_NEWNS), 0); + ASSERT_EQ(sys_mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL), 0); + ASSERT_EQ(sys_mount("tmpfs", "/tmp", "tmpfs", 0, NULL), 0); + + snprintf(self->dir, sizeof(self->dir), "/tmp/d"); + ASSERT_EQ(mkdir(self->dir, 0777), 0); + /* World-writable so an unmapped caller still passes permission(). */ + ASSERT_EQ(chmod(self->dir, 0777), 0); +} + +FIXTURE_TEARDOWN(idmapped_tmpfile) +{ +} + +/* + * A caller whose fsuid/fsgid have no mapping in the idmapped mount must not be + * able to create an O_TMPFILE. Without the check in vfs_tmpfile() the inode + * would be created owned by (uid_t)-1 and could then be linked into the + * namespace. + */ +TEST_F(idmapped_tmpfile, unmapped_caller_is_refused) +{ + int mfd, fd; + + mfd = idmapped_clone(self->dir); + if (mfd < 0) + SKIP(return, "idmapped mounts not supported"); + + /* Become a caller outside the mount's [0, MAP_RANGE) range. */ + setfsgid(UNMAPPED); + setfsuid(UNMAPPED); + ASSERT_EQ(setfsuid(-1), UNMAPPED); + + fd = openat(mfd, ".", O_TMPFILE | O_WRONLY, 0644); + ASSERT_LT(fd, 0); + EXPECT_EQ(errno, EOVERFLOW); + if (fd >= 0) + close(fd); + + EXPECT_EQ(close(mfd), 0); +} + +/* + * A mapped caller can create an O_TMPFILE and link it into the namespace; the + * ownership round-trips through the mount idmap. This is what makes refusing + * the unmapped case above necessary in the first place. + */ +TEST_F(idmapped_tmpfile, mapped_caller_creates_and_links) +{ + char path[PATH_MAX]; + struct stat st; + int mfd, fd; + + mfd = idmapped_clone(self->dir); + if (mfd < 0) + SKIP(return, "idmapped mounts not supported"); + + /* Caller is uid/gid 0, which maps to MAP_HOST through the mount. */ + fd = openat(mfd, ".", O_TMPFILE | O_RDWR, 0600); + ASSERT_GE(fd, 0); + + ASSERT_EQ(fstat(fd, &st), 0); + EXPECT_EQ(st.st_uid, 0); + EXPECT_EQ(st.st_gid, 0); + + /* The tmpfile is linkable: splice it into the directory. */ + ASSERT_EQ(linkat(fd, "", mfd, "linked", AT_EMPTY_PATH), 0); + EXPECT_EQ(close(fd), 0); + + ASSERT_EQ(fstatat(mfd, "linked", &st, 0), 0); + EXPECT_EQ(st.st_uid, 0); + EXPECT_EQ(st.st_gid, 0); + + /* On the underlying, non-idmapped tmpfs it is stored as MAP_HOST. */ + snprintf(path, sizeof(path), "%s/linked", self->dir); + ASSERT_EQ(stat(path, &st), 0); + EXPECT_EQ(st.st_uid, MAP_HOST); + EXPECT_EQ(st.st_gid, MAP_HOST); + + EXPECT_EQ(close(mfd), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/move_mount/.gitignore b/tools/testing/selftests/filesystems/move_mount/.gitignore new file mode 100644 index 000000000000..c7557db30671 --- /dev/null +++ b/tools/testing/selftests/filesystems/move_mount/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +move_mount_test diff --git a/tools/testing/selftests/filesystems/move_mount/Makefile b/tools/testing/selftests/filesystems/move_mount/Makefile new file mode 100644 index 000000000000..5c5b199b464b --- /dev/null +++ b/tools/testing/selftests/filesystems/move_mount/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-or-later + +CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES) +LDLIBS += -lcap + +TEST_GEN_PROGS := move_mount_test + +include ../../lib.mk + +$(OUTPUT)/move_mount_test: ../utils.c diff --git a/tools/testing/selftests/filesystems/move_mount/move_mount_test.c b/tools/testing/selftests/filesystems/move_mount/move_mount_test.c new file mode 100644 index 000000000000..f08f94b1f0ec --- /dev/null +++ b/tools/testing/selftests/filesystems/move_mount/move_mount_test.c @@ -0,0 +1,492 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2026 Christian Brauner <brauner@kernel.org> + +#define _GNU_SOURCE + +#include <errno.h> +#include <fcntl.h> +#include <sched.h> +#include <stdio.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/mount.h> +#include <unistd.h> +#include <sys/syscall.h> + +#include "../wrappers.h" +#include "../utils.h" +#include "../statmount/statmount.h" +#include "../../kselftest_harness.h" + +#include <linux/stat.h> + +#ifndef MOVE_MOUNT_BENEATH +#define MOVE_MOUNT_BENEATH 0x00000200 +#endif + +static uint64_t get_unique_mnt_id_fd(int fd) +{ + struct statx sx; + int ret; + + ret = statx(fd, "", AT_EMPTY_PATH, STATX_MNT_ID_UNIQUE, &sx); + if (ret) + return 0; + + if (!(sx.stx_mask & STATX_MNT_ID_UNIQUE)) + return 0; + + return sx.stx_mnt_id; +} + +/* + * Create a locked overmount stack at /mnt_dir for testing MNT_LOCKED + * transfer on non-rootfs mounts. + * + * Mounts tmpfs A at /mnt_dir, overmounts with tmpfs B, then enters a + * new user+mount namespace where both become locked. Returns the exit + * code to use on failure, or 0 on success. + */ +static int setup_locked_overmount(void) +{ + /* Isolate so mounts don't leak. */ + if (unshare(CLONE_NEWNS)) + return 1; + if (mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL)) + return 2; + + /* + * Create mounts while still in the initial user namespace so + * they become locked after the subsequent user namespace + * unshare. + */ + rmdir("/mnt_dir"); + if (mkdir("/mnt_dir", 0755)) + return 3; + + /* Mount tmpfs A */ + if (mount("tmpfs", "/mnt_dir", "tmpfs", 0, NULL)) + return 4; + + /* Overmount with tmpfs B */ + if (mount("tmpfs", "/mnt_dir", "tmpfs", 0, NULL)) + return 5; + + /* + * Create user+mount namespace. Mounts A and B become locked + * because they might be covering something that is not supposed + * to be revealed. + */ + if (setup_userns()) + return 6; + + /* Sanity check: B must be locked */ + if (!umount2("/mnt_dir", MNT_DETACH) || errno != EINVAL) + return 7; + + return 0; +} + +/* + * Create a detached tmpfs mount and return its fd, or -1 on failure. + */ +static int create_detached_tmpfs(void) +{ + int fs_fd, mnt_fd; + + fs_fd = sys_fsopen("tmpfs", FSOPEN_CLOEXEC); + if (fs_fd < 0) + return -1; + + if (sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0)) { + close(fs_fd); + return -1; + } + + mnt_fd = sys_fsmount(fs_fd, FSMOUNT_CLOEXEC, 0); + close(fs_fd); + return mnt_fd; +} + +FIXTURE(move_mount) { + uint64_t orig_root_id; +}; + +FIXTURE_SETUP(move_mount) +{ + ASSERT_EQ(unshare(CLONE_NEWNS), 0); + + ASSERT_EQ(mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL), 0); + + self->orig_root_id = get_unique_mnt_id("/"); + ASSERT_NE(self->orig_root_id, 0); +} + +FIXTURE_TEARDOWN(move_mount) +{ +} + +/* + * Test successful MOVE_MOUNT_BENEATH on the rootfs. + * Mount a clone beneath /, fchdir to the clone, chroot to switch root, + * then detach the old root. + */ +TEST_F(move_mount, beneath_rootfs_success) +{ + int fd_tree, ret; + uint64_t clone_id, root_id; + + fd_tree = sys_open_tree(AT_FDCWD, "/", + OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + ASSERT_GE(fd_tree, 0); + + clone_id = get_unique_mnt_id_fd(fd_tree); + ASSERT_NE(clone_id, 0); + ASSERT_NE(clone_id, self->orig_root_id); + + ASSERT_EQ(fchdir(fd_tree), 0); + + ret = sys_move_mount(fd_tree, "", AT_FDCWD, "/", + MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_BENEATH); + ASSERT_EQ(ret, 0); + + close(fd_tree); + + /* Switch root to the clone */ + ASSERT_EQ(chroot("."), 0); + + /* Verify "/" is now the clone */ + root_id = get_unique_mnt_id("/"); + ASSERT_NE(root_id, 0); + ASSERT_EQ(root_id, clone_id); + + /* Detach old root */ + ASSERT_EQ(umount2(".", MNT_DETACH), 0); +} + +/* + * Test that after MOVE_MOUNT_BENEATH on the rootfs the old root is + * stacked on top of the clone. Verify via statmount that the old + * root's parent is the clone. + */ +TEST_F(move_mount, beneath_rootfs_old_root_stacked) +{ + int fd_tree, ret; + uint64_t clone_id; + struct statmount sm; + + fd_tree = sys_open_tree(AT_FDCWD, "/", + OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + ASSERT_GE(fd_tree, 0); + + clone_id = get_unique_mnt_id_fd(fd_tree); + ASSERT_NE(clone_id, 0); + ASSERT_NE(clone_id, self->orig_root_id); + + ASSERT_EQ(fchdir(fd_tree), 0); + + ret = sys_move_mount(fd_tree, "", AT_FDCWD, "/", + MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_BENEATH); + ASSERT_EQ(ret, 0); + + close(fd_tree); + + ASSERT_EQ(chroot("."), 0); + + /* Old root's parent should now be the clone */ + ASSERT_EQ(statmount(self->orig_root_id, 0, 0, + STATMOUNT_MNT_BASIC, &sm, sizeof(sm), 0), 0); + ASSERT_EQ(sm.mnt_parent_id, clone_id); + + ASSERT_EQ(umount2(".", MNT_DETACH), 0); +} + +/* + * Test that MOVE_MOUNT_BENEATH on rootfs fails when chroot'd into a + * subdirectory of the same mount. The caller's fs->root.dentry doesn't + * match mnt->mnt_root so the kernel rejects it. + */ +TEST_F(move_mount, beneath_rootfs_in_chroot_fail) +{ + int fd_tree, ret; + uint64_t chroot_id, clone_id; + + rmdir("/chroot_dir"); + ASSERT_EQ(mkdir("/chroot_dir", 0755), 0); + + chroot_id = get_unique_mnt_id("/chroot_dir"); + ASSERT_NE(chroot_id, 0); + ASSERT_EQ(self->orig_root_id, chroot_id); + + ASSERT_EQ(chdir("/chroot_dir"), 0); + ASSERT_EQ(chroot("."), 0); + + fd_tree = sys_open_tree(AT_FDCWD, "/", + OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + ASSERT_GE(fd_tree, 0); + + clone_id = get_unique_mnt_id_fd(fd_tree); + ASSERT_NE(clone_id, 0); + ASSERT_NE(clone_id, chroot_id); + + ASSERT_EQ(fchdir(fd_tree), 0); + + /* + * Should fail: fs->root.dentry (/chroot_dir) doesn't match + * the mount's mnt_root (/). + */ + ret = sys_move_mount(fd_tree, "", AT_FDCWD, "/", + MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_BENEATH); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + close(fd_tree); +} + +/* + * Test that MOVE_MOUNT_BENEATH on rootfs succeeds when chroot'd into a + * separate tmpfs mount. The caller's root dentry matches the mount's + * mnt_root since it's a dedicated mount. + */ +TEST_F(move_mount, beneath_rootfs_in_chroot_success) +{ + int fd_tree, ret; + uint64_t chroot_id, clone_id, root_id; + struct statmount sm; + + rmdir("/chroot_dir"); + ASSERT_EQ(mkdir("/chroot_dir", 0755), 0); + ASSERT_EQ(mount("tmpfs", "/chroot_dir", "tmpfs", 0, NULL), 0); + + chroot_id = get_unique_mnt_id("/chroot_dir"); + ASSERT_NE(chroot_id, 0); + + ASSERT_EQ(chdir("/chroot_dir"), 0); + ASSERT_EQ(chroot("."), 0); + + ASSERT_EQ(get_unique_mnt_id("/"), chroot_id); + + fd_tree = sys_open_tree(AT_FDCWD, "/", + OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + ASSERT_GE(fd_tree, 0); + + clone_id = get_unique_mnt_id_fd(fd_tree); + ASSERT_NE(clone_id, 0); + ASSERT_NE(clone_id, chroot_id); + + ASSERT_EQ(fchdir(fd_tree), 0); + + ret = sys_move_mount(fd_tree, "", AT_FDCWD, "/", + MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_BENEATH); + ASSERT_EQ(ret, 0); + + close(fd_tree); + + ASSERT_EQ(chroot("."), 0); + + root_id = get_unique_mnt_id("/"); + ASSERT_NE(root_id, 0); + ASSERT_EQ(root_id, clone_id); + + ASSERT_EQ(statmount(chroot_id, 0, 0, + STATMOUNT_MNT_BASIC, &sm, sizeof(sm), 0), 0); + ASSERT_EQ(sm.mnt_parent_id, clone_id); + + ASSERT_EQ(umount2(".", MNT_DETACH), 0); +} + +/* + * Test MNT_LOCKED transfer when mounting beneath rootfs in a user+mount + * namespace. After mount-beneath the new root gets MNT_LOCKED and the + * old root has MNT_LOCKED cleared so it can be unmounted. + */ +TEST_F(move_mount, beneath_rootfs_locked_transfer) +{ + int fd_tree, ret; + uint64_t clone_id, root_id; + + ASSERT_EQ(setup_userns(), 0); + + ASSERT_EQ(mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL), 0); + + fd_tree = sys_open_tree(AT_FDCWD, "/", + OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC | + AT_RECURSIVE); + ASSERT_GE(fd_tree, 0); + + clone_id = get_unique_mnt_id_fd(fd_tree); + ASSERT_NE(clone_id, 0); + + ASSERT_EQ(fchdir(fd_tree), 0); + + ret = sys_move_mount(fd_tree, "", AT_FDCWD, "/", + MOVE_MOUNT_F_EMPTY_PATH | + MOVE_MOUNT_BENEATH); + ASSERT_EQ(ret, 0); + + close(fd_tree); + + ASSERT_EQ(chroot("."), 0); + + root_id = get_unique_mnt_id("/"); + ASSERT_EQ(root_id, clone_id); + + /* + * The old root should be unmountable (MNT_LOCKED was + * transferred to the clone). If MNT_LOCKED wasn't + * cleared, this would fail with EINVAL. + */ + ASSERT_EQ(umount2(".", MNT_DETACH), 0); + + /* Verify "/" is still the clone after detaching old root */ + root_id = get_unique_mnt_id("/"); + ASSERT_EQ(root_id, clone_id); +} + +/* + * Test containment invariant: after mount-beneath rootfs in a user+mount + * namespace, the new root must be MNT_LOCKED. The lock transfer from the + * old root preserves containment -- the process cannot unmount the new root + * to escape the namespace. + */ +TEST_F(move_mount, beneath_rootfs_locked_containment) +{ + int fd_tree, ret; + uint64_t clone_id, root_id; + + ASSERT_EQ(setup_userns(), 0); + + ASSERT_EQ(mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL), 0); + + /* Sanity: rootfs must be locked in the new userns */ + ASSERT_EQ(umount2("/", MNT_DETACH), -1); + ASSERT_EQ(errno, EINVAL); + + fd_tree = sys_open_tree(AT_FDCWD, "/", + OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC | + AT_RECURSIVE); + ASSERT_GE(fd_tree, 0); + + clone_id = get_unique_mnt_id_fd(fd_tree); + ASSERT_NE(clone_id, 0); + + ASSERT_EQ(fchdir(fd_tree), 0); + + ret = sys_move_mount(fd_tree, "", AT_FDCWD, "/", + MOVE_MOUNT_F_EMPTY_PATH | + MOVE_MOUNT_BENEATH); + ASSERT_EQ(ret, 0); + + close(fd_tree); + + ASSERT_EQ(chroot("."), 0); + + root_id = get_unique_mnt_id("/"); + ASSERT_EQ(root_id, clone_id); + + /* Detach old root (MNT_LOCKED was cleared from it) */ + ASSERT_EQ(umount2(".", MNT_DETACH), 0); + + /* Verify "/" is still the clone after detaching old root */ + root_id = get_unique_mnt_id("/"); + ASSERT_EQ(root_id, clone_id); + + /* + * The new root must be locked (MNT_LOCKED was transferred + * from the old root). Attempting to unmount it must fail + * with EINVAL, preserving the containment invariant. + */ + ASSERT_EQ(umount2("/", MNT_DETACH), -1); + ASSERT_EQ(errno, EINVAL); +} + +/* + * Test MNT_LOCKED transfer when mounting beneath a non-rootfs locked mount. + * Mounts created before unshare(CLONE_NEWUSER | CLONE_NEWNS) become locked + * in the new namespace. Mount-beneath transfers the lock from the displaced + * mount to the new mount, so the displaced mount can be unmounted. + */ +TEST_F(move_mount, beneath_non_rootfs_locked_transfer) +{ + int mnt_fd, ret; + uint64_t mnt_new_id, mnt_visible_id; + + ASSERT_EQ(setup_locked_overmount(), 0); + + mnt_fd = create_detached_tmpfs(); + ASSERT_GE(mnt_fd, 0); + + mnt_new_id = get_unique_mnt_id_fd(mnt_fd); + ASSERT_NE(mnt_new_id, 0); + + /* Move mount beneath B (which is locked) */ + ret = sys_move_mount(mnt_fd, "", AT_FDCWD, "/mnt_dir", + MOVE_MOUNT_F_EMPTY_PATH | + MOVE_MOUNT_BENEATH); + ASSERT_EQ(ret, 0); + + close(mnt_fd); + + /* + * B should now be unmountable (MNT_LOCKED was transferred + * to the new mount beneath it). If MNT_LOCKED wasn't + * cleared from B, this would fail with EINVAL. + */ + ASSERT_EQ(umount2("/mnt_dir", MNT_DETACH), 0); + + /* Verify the new mount is now visible */ + mnt_visible_id = get_unique_mnt_id("/mnt_dir"); + ASSERT_EQ(mnt_visible_id, mnt_new_id); +} + +/* + * Test MNT_LOCKED containment when mounting beneath a non-rootfs mount + * that was locked during unshare(CLONE_NEWUSER | CLONE_NEWNS). + * Mounts created before unshare become locked in the new namespace. + * Mount-beneath transfers the lock, preserving containment: the new + * mount cannot be unmounted, but the displaced mount can. + */ +TEST_F(move_mount, beneath_non_rootfs_locked_containment) +{ + int mnt_fd, ret; + uint64_t mnt_new_id, mnt_visible_id; + + ASSERT_EQ(setup_locked_overmount(), 0); + + mnt_fd = create_detached_tmpfs(); + ASSERT_GE(mnt_fd, 0); + + mnt_new_id = get_unique_mnt_id_fd(mnt_fd); + ASSERT_NE(mnt_new_id, 0); + + /* + * Move new tmpfs beneath B at /mnt_dir. + * Stack becomes: A -> new -> B + * Lock transfers from B to new. + */ + ret = sys_move_mount(mnt_fd, "", AT_FDCWD, "/mnt_dir", + MOVE_MOUNT_F_EMPTY_PATH | + MOVE_MOUNT_BENEATH); + ASSERT_EQ(ret, 0); + + close(mnt_fd); + + /* + * B lost MNT_LOCKED -- unmounting it must succeed. + * This reveals the new mount at /mnt_dir. + */ + ASSERT_EQ(umount2("/mnt_dir", MNT_DETACH), 0); + + /* Verify the new mount is now visible */ + mnt_visible_id = get_unique_mnt_id("/mnt_dir"); + ASSERT_EQ(mnt_visible_id, mnt_new_id); + + /* + * The new mount gained MNT_LOCKED -- unmounting it must + * fail with EINVAL, preserving the containment invariant. + */ + ASSERT_EQ(umount2("/mnt_dir", MNT_DETACH), -1); + ASSERT_EQ(errno, EINVAL); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c index 61e55dfbf121..e19ff8168baf 100644 --- a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c +++ b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c @@ -37,17 +37,20 @@ FIXTURE(iterate_mount_namespaces) { __u64 mnt_ns_id[MNT_NS_COUNT]; }; +static inline bool mntns_in_list(__u64 *mnt_ns_id, struct mnt_ns_info *info) +{ + for (int i = 0; i < MNT_NS_COUNT; i++) { + if (mnt_ns_id[i] == info->mnt_ns_id) + return true; + } + return false; +} + FIXTURE_SETUP(iterate_mount_namespaces) { for (int i = 0; i < MNT_NS_COUNT; i++) self->fd_mnt_ns[i] = -EBADF; - /* - * Creating a new user namespace let's us guarantee that we only see - * mount namespaces that we did actually create. - */ - ASSERT_EQ(unshare(CLONE_NEWUSER), 0); - for (int i = 0; i < MNT_NS_COUNT; i++) { struct mnt_ns_info info = {}; @@ -75,13 +78,15 @@ TEST_F(iterate_mount_namespaces, iterate_all_forward) fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[0], F_DUPFD_CLOEXEC); ASSERT_GE(fd_mnt_ns_cur, 0); - for (;; count++) { + for (;;) { struct mnt_ns_info info = {}; int fd_mnt_ns_next; fd_mnt_ns_next = ioctl(fd_mnt_ns_cur, NS_MNT_GET_NEXT, &info); if (fd_mnt_ns_next < 0 && errno == ENOENT) break; + if (mntns_in_list(self->mnt_ns_id, &info)) + count++; ASSERT_GE(fd_mnt_ns_next, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_next; @@ -96,13 +101,15 @@ TEST_F(iterate_mount_namespaces, iterate_all_backwards) fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[MNT_NS_LAST_INDEX], F_DUPFD_CLOEXEC); ASSERT_GE(fd_mnt_ns_cur, 0); - for (;; count++) { + for (;;) { struct mnt_ns_info info = {}; int fd_mnt_ns_prev; fd_mnt_ns_prev = ioctl(fd_mnt_ns_cur, NS_MNT_GET_PREV, &info); if (fd_mnt_ns_prev < 0 && errno == ENOENT) break; + if (mntns_in_list(self->mnt_ns_id, &info)) + count++; ASSERT_GE(fd_mnt_ns_prev, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_prev; @@ -125,7 +132,6 @@ TEST_F(iterate_mount_namespaces, iterate_forward) ASSERT_GE(fd_mnt_ns_next, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_next; - ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]); } } @@ -144,7 +150,6 @@ TEST_F(iterate_mount_namespaces, iterate_backward) ASSERT_GE(fd_mnt_ns_prev, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_prev; - ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]); } } diff --git a/tools/testing/selftests/filesystems/open_tree_ns/.gitignore b/tools/testing/selftests/filesystems/open_tree_ns/.gitignore new file mode 100644 index 000000000000..fb12b93fbcaa --- /dev/null +++ b/tools/testing/selftests/filesystems/open_tree_ns/.gitignore @@ -0,0 +1 @@ +open_tree_ns_test diff --git a/tools/testing/selftests/filesystems/open_tree_ns/Makefile b/tools/testing/selftests/filesystems/open_tree_ns/Makefile new file mode 100644 index 000000000000..4976ed1d7d4a --- /dev/null +++ b/tools/testing/selftests/filesystems/open_tree_ns/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +TEST_GEN_PROGS := open_tree_ns_test + +CFLAGS += -Wall -O0 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES) +LDLIBS := -lcap + +include ../../lib.mk + +$(OUTPUT)/open_tree_ns_test: open_tree_ns_test.c ../utils.c + $(CC) $(CFLAGS) -o $@ $^ $(LDLIBS) diff --git a/tools/testing/selftests/filesystems/open_tree_ns/open_tree_ns_test.c b/tools/testing/selftests/filesystems/open_tree_ns/open_tree_ns_test.c new file mode 100644 index 000000000000..82f3c8c02c9a --- /dev/null +++ b/tools/testing/selftests/filesystems/open_tree_ns/open_tree_ns_test.c @@ -0,0 +1,1007 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2026 Christian Brauner <brauner@kernel.org> + * + * Test for OPEN_TREE_NAMESPACE flag. + * + * Test that open_tree() with OPEN_TREE_NAMESPACE creates a new mount + * namespace containing the specified mount tree. + */ +#define _GNU_SOURCE + +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <linux/nsfs.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/mount.h> +#include <sys/stat.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "../wrappers.h" +#include "../statmount/statmount.h" +#include "../utils.h" +#include "../../kselftest_harness.h" + +#ifndef OPEN_TREE_NAMESPACE +#define OPEN_TREE_NAMESPACE (1 << 1) +#endif + +static int get_mnt_ns_id(int fd, uint64_t *mnt_ns_id) +{ + if (ioctl(fd, NS_GET_MNTNS_ID, mnt_ns_id) < 0) + return -errno; + return 0; +} + +static int get_mnt_ns_id_from_path(const char *path, uint64_t *mnt_ns_id) +{ + int fd, ret; + + fd = open(path, O_RDONLY); + if (fd < 0) + return -errno; + + ret = get_mnt_ns_id(fd, mnt_ns_id); + close(fd); + return ret; +} + +static void log_mount(struct __test_metadata *_metadata, struct statmount *sm) +{ + const char *fs_type = ""; + const char *mnt_root = ""; + const char *mnt_point = ""; + + if (sm->mask & STATMOUNT_FS_TYPE) + fs_type = sm->str + sm->fs_type; + if (sm->mask & STATMOUNT_MNT_ROOT) + mnt_root = sm->str + sm->mnt_root; + if (sm->mask & STATMOUNT_MNT_POINT) + mnt_point = sm->str + sm->mnt_point; + + TH_LOG(" mnt_id: %llu, parent_id: %llu, fs_type: %s, root: %s, point: %s", + (unsigned long long)sm->mnt_id, + (unsigned long long)sm->mnt_parent_id, + fs_type, mnt_root, mnt_point); +} + +static void dump_mounts(struct __test_metadata *_metadata, uint64_t mnt_ns_id) +{ + uint64_t list[256]; + ssize_t nr_mounts; + + nr_mounts = listmount(LSMT_ROOT, mnt_ns_id, 0, list, 256, 0); + if (nr_mounts < 0) { + TH_LOG("listmount failed: %s", strerror(errno)); + return; + } + + TH_LOG("Mount namespace %llu contains %zd mount(s):", + (unsigned long long)mnt_ns_id, nr_mounts); + + for (ssize_t i = 0; i < nr_mounts; i++) { + struct statmount *sm; + + sm = statmount_alloc(list[i], mnt_ns_id, + STATMOUNT_MNT_BASIC | + STATMOUNT_FS_TYPE | + STATMOUNT_MNT_ROOT | + STATMOUNT_MNT_POINT, 0); + if (!sm) { + TH_LOG(" [%zd] mnt_id %llu: statmount failed: %s", + i, (unsigned long long)list[i], strerror(errno)); + continue; + } + + log_mount(_metadata, sm); + free(sm); + } +} + +FIXTURE(open_tree_ns) +{ + int fd; + uint64_t current_ns_id; +}; + +FIXTURE_VARIANT(open_tree_ns) +{ + const char *path; + unsigned int flags; + bool expect_success; + bool expect_different_ns; + int min_mounts; +}; + +FIXTURE_VARIANT_ADD(open_tree_ns, basic_root) +{ + .path = "/", + .flags = OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC, + .expect_success = true, + .expect_different_ns = true, + /* + * The empty rootfs is hidden from listmount()/mountinfo, + * so we only see the bind mount on top of it. + */ + .min_mounts = 1, +}; + +FIXTURE_VARIANT_ADD(open_tree_ns, recursive_root) +{ + .path = "/", + .flags = OPEN_TREE_NAMESPACE | AT_RECURSIVE | OPEN_TREE_CLOEXEC, + .expect_success = true, + .expect_different_ns = true, + .min_mounts = 1, +}; + +FIXTURE_VARIANT_ADD(open_tree_ns, subdir_tmp) +{ + .path = "/tmp", + .flags = OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC, + .expect_success = true, + .expect_different_ns = true, + .min_mounts = 1, +}; + +FIXTURE_VARIANT_ADD(open_tree_ns, subdir_proc) +{ + .path = "/proc", + .flags = OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC, + .expect_success = true, + .expect_different_ns = true, + .min_mounts = 1, +}; + +FIXTURE_VARIANT_ADD(open_tree_ns, recursive_tmp) +{ + .path = "/tmp", + .flags = OPEN_TREE_NAMESPACE | AT_RECURSIVE | OPEN_TREE_CLOEXEC, + .expect_success = true, + .expect_different_ns = true, + .min_mounts = 1, +}; + +FIXTURE_VARIANT_ADD(open_tree_ns, recursive_run) +{ + .path = "/run", + .flags = OPEN_TREE_NAMESPACE | AT_RECURSIVE | OPEN_TREE_CLOEXEC, + .expect_success = true, + .expect_different_ns = true, + .min_mounts = 1, +}; + +FIXTURE_VARIANT_ADD(open_tree_ns, invalid_recursive_alone) +{ + .path = "/", + .flags = AT_RECURSIVE | OPEN_TREE_CLOEXEC, + .expect_success = false, + .expect_different_ns = false, + .min_mounts = 0, +}; + +FIXTURE_SETUP(open_tree_ns) +{ + int ret; + + self->fd = -1; + + /* Check if open_tree syscall is supported */ + ret = sys_open_tree(-1, NULL, 0); + if (ret == -1 && errno == ENOSYS) + SKIP(return, "open_tree() syscall not supported"); + + /* Check if statmount/listmount are supported */ + ret = statmount(0, 0, 0, 0, NULL, 0, 0); + if (ret == -1 && errno == ENOSYS) + SKIP(return, "statmount() syscall not supported"); + + /* Get current mount namespace ID for comparison */ + ret = get_mnt_ns_id_from_path("/proc/self/ns/mnt", &self->current_ns_id); + if (ret < 0) + SKIP(return, "Failed to get current mount namespace ID"); +} + +FIXTURE_TEARDOWN(open_tree_ns) +{ + if (self->fd >= 0) + close(self->fd); +} + +TEST_F(open_tree_ns, create_namespace) +{ + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int ret; + + self->fd = sys_open_tree(AT_FDCWD, variant->path, variant->flags); + + if (!variant->expect_success) { + ASSERT_LT(self->fd, 0); + ASSERT_EQ(errno, EINVAL); + return; + } + + if (self->fd < 0 && errno == EINVAL) + SKIP(return, "OPEN_TREE_NAMESPACE not supported"); + + ASSERT_GE(self->fd, 0); + + /* Verify we can get the namespace ID */ + ret = get_mnt_ns_id(self->fd, &new_ns_id); + ASSERT_EQ(ret, 0); + + /* Verify it's a different namespace */ + if (variant->expect_different_ns) + ASSERT_NE(new_ns_id, self->current_ns_id); + + /* List mounts in the new namespace */ + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + ASSERT_GE(nr_mounts, 0) { + TH_LOG("%m - listmount failed"); + } + + /* Verify minimum expected mounts */ + ASSERT_GE(nr_mounts, variant->min_mounts); + TH_LOG("Namespace contains %zd mounts", nr_mounts); +} + +TEST_F(open_tree_ns, setns_into_namespace) +{ + uint64_t new_ns_id; + pid_t pid; + int status; + int ret; + + /* Only test with basic flags */ + if (!(variant->flags & OPEN_TREE_NAMESPACE)) + SKIP(return, "setns test only for basic / case"); + + self->fd = sys_open_tree(AT_FDCWD, variant->path, variant->flags); + if (self->fd < 0 && errno == EINVAL) + SKIP(return, "OPEN_TREE_NAMESPACE not supported"); + + ASSERT_GE(self->fd, 0); + + /* Get namespace ID and dump all mounts */ + ret = get_mnt_ns_id(self->fd, &new_ns_id); + ASSERT_EQ(ret, 0); + + dump_mounts(_metadata, new_ns_id); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + /* Child: try to enter the namespace */ + if (setns(self->fd, CLONE_NEWNS) < 0) + _exit(1); + _exit(0); + } + + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + ASSERT_EQ(WEXITSTATUS(status), 0); +} + +TEST_F(open_tree_ns, verify_mount_properties) +{ + struct statmount sm; + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int ret; + + /* Only test with basic flags on root */ + if (variant->flags != (OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC) || + strcmp(variant->path, "/") != 0) + SKIP(return, "mount properties test only for basic / case"); + + self->fd = sys_open_tree(AT_FDCWD, "/", OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC); + if (self->fd < 0 && errno == EINVAL) + SKIP(return, "OPEN_TREE_NAMESPACE not supported"); + + ASSERT_GE(self->fd, 0); + + ret = get_mnt_ns_id(self->fd, &new_ns_id); + ASSERT_EQ(ret, 0); + + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + ASSERT_GE(nr_mounts, 1); + + /* Get info about the root mount (the bind mount, rootfs is hidden) */ + ret = statmount(list[0], new_ns_id, 0, STATMOUNT_MNT_BASIC, &sm, sizeof(sm), 0); + ASSERT_EQ(ret, 0); + + ASSERT_NE(sm.mnt_id, sm.mnt_parent_id); + + TH_LOG("Root mount id: %llu, parent: %llu", + (unsigned long long)sm.mnt_id, + (unsigned long long)sm.mnt_parent_id); +} + +FIXTURE(open_tree_ns_caps) +{ + bool has_caps; +}; + +FIXTURE_SETUP(open_tree_ns_caps) +{ + int ret; + + /* Check if open_tree syscall is supported */ + ret = sys_open_tree(-1, NULL, 0); + if (ret == -1 && errno == ENOSYS) + SKIP(return, "open_tree() syscall not supported"); + + self->has_caps = (geteuid() == 0); +} + +FIXTURE_TEARDOWN(open_tree_ns_caps) +{ +} + +TEST_F(open_tree_ns_caps, requires_cap_sys_admin) +{ + pid_t pid; + int status; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + int fd; + + /* Child: drop privileges using utils.h helper */ + if (enter_userns() != 0) + _exit(2); + + /* Drop all caps using utils.h helper */ + if (caps_down() == 0) + _exit(3); + + fd = sys_open_tree(AT_FDCWD, "/", + OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC); + if (fd >= 0) { + close(fd); + /* Should have failed without caps */ + _exit(1); + } + + if (errno == EPERM) + _exit(0); + + /* EINVAL means OPEN_TREE_NAMESPACE not supported */ + if (errno == EINVAL) + _exit(4); + + /* Unexpected error */ + _exit(5); + } + + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + + switch (WEXITSTATUS(status)) { + case 0: + /* Expected: EPERM without caps */ + break; + case 1: + ASSERT_FALSE(true) TH_LOG("OPEN_TREE_NAMESPACE succeeded without caps"); + break; + case 2: + SKIP(return, "setup_userns failed"); + break; + case 3: + SKIP(return, "caps_down failed"); + break; + case 4: + SKIP(return, "OPEN_TREE_NAMESPACE not supported"); + break; + default: + ASSERT_FALSE(true) TH_LOG("Unexpected error in child (exit %d)", + WEXITSTATUS(status)); + break; + } +} + +FIXTURE(open_tree_ns_userns) +{ + int fd; +}; + +FIXTURE_SETUP(open_tree_ns_userns) +{ + int ret; + + self->fd = -1; + + /* Check if open_tree syscall is supported */ + ret = sys_open_tree(-1, NULL, 0); + if (ret == -1 && errno == ENOSYS) + SKIP(return, "open_tree() syscall not supported"); + + /* Check if statmount/listmount are supported */ + ret = statmount(0, 0, 0, 0, NULL, 0, 0); + if (ret == -1 && errno == ENOSYS) + SKIP(return, "statmount() syscall not supported"); +} + +FIXTURE_TEARDOWN(open_tree_ns_userns) +{ + if (self->fd >= 0) + close(self->fd); +} + +TEST_F(open_tree_ns_userns, create_in_userns) +{ + pid_t pid; + int status; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int fd; + + /* Create new user namespace (also creates mount namespace) */ + if (enter_userns() != 0) + _exit(2); + + /* Now we have CAP_SYS_ADMIN in the user namespace */ + fd = sys_open_tree(AT_FDCWD, "/", + OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC); + if (fd < 0) { + if (errno == EINVAL) + _exit(4); /* OPEN_TREE_NAMESPACE not supported */ + _exit(1); + } + + /* Verify we can get the namespace ID */ + if (get_mnt_ns_id(fd, &new_ns_id) != 0) + _exit(5); + + /* Verify we can list mounts in the new namespace */ + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + if (nr_mounts < 0) + _exit(6); + + /* Should have at least 1 mount */ + if (nr_mounts < 1) + _exit(7); + + close(fd); + _exit(0); + } + + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + + switch (WEXITSTATUS(status)) { + case 0: + /* Success */ + break; + case 1: + ASSERT_FALSE(true) TH_LOG("open_tree(OPEN_TREE_NAMESPACE) failed in userns"); + break; + case 2: + SKIP(return, "setup_userns failed"); + break; + case 4: + SKIP(return, "OPEN_TREE_NAMESPACE not supported"); + break; + case 5: + ASSERT_FALSE(true) TH_LOG("Failed to get mount namespace ID"); + break; + case 6: + ASSERT_FALSE(true) TH_LOG("listmount failed in new namespace"); + break; + case 7: + ASSERT_FALSE(true) TH_LOG("New namespace has no mounts"); + break; + default: + ASSERT_FALSE(true) TH_LOG("Unexpected error in child (exit %d)", + WEXITSTATUS(status)); + break; + } +} + +TEST_F(open_tree_ns_userns, setns_in_userns) +{ + pid_t pid; + int status; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + uint64_t new_ns_id; + int fd; + pid_t inner_pid; + int inner_status; + + /* Create new user namespace */ + if (enter_userns() != 0) + _exit(2); + + fd = sys_open_tree(AT_FDCWD, "/", + OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC); + if (fd < 0) { + if (errno == EINVAL) + _exit(4); + _exit(1); + } + + if (get_mnt_ns_id(fd, &new_ns_id) != 0) + _exit(5); + + /* Fork again to test setns into the new namespace */ + inner_pid = fork(); + if (inner_pid < 0) + _exit(8); + + if (inner_pid == 0) { + /* Inner child: enter the new namespace */ + if (setns(fd, CLONE_NEWNS) < 0) + _exit(1); + _exit(0); + } + + if (waitpid(inner_pid, &inner_status, 0) != inner_pid) + _exit(9); + + if (!WIFEXITED(inner_status) || WEXITSTATUS(inner_status) != 0) + _exit(10); + + close(fd); + _exit(0); + } + + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + + switch (WEXITSTATUS(status)) { + case 0: + /* Success */ + break; + case 1: + ASSERT_FALSE(true) TH_LOG("open_tree or setns failed in userns"); + break; + case 2: + SKIP(return, "setup_userns failed"); + break; + case 4: + SKIP(return, "OPEN_TREE_NAMESPACE not supported"); + break; + case 5: + ASSERT_FALSE(true) TH_LOG("Failed to get mount namespace ID"); + break; + case 8: + ASSERT_FALSE(true) TH_LOG("Inner fork failed"); + break; + case 9: + ASSERT_FALSE(true) TH_LOG("Inner waitpid failed"); + break; + case 10: + ASSERT_FALSE(true) TH_LOG("setns into new namespace failed"); + break; + default: + ASSERT_FALSE(true) TH_LOG("Unexpected error in child (exit %d)", + WEXITSTATUS(status)); + break; + } +} + +TEST_F(open_tree_ns_userns, recursive_in_userns) +{ + pid_t pid; + int status; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int fd; + + /* Create new user namespace */ + if (enter_userns() != 0) + _exit(2); + + /* Test recursive flag in userns */ + fd = sys_open_tree(AT_FDCWD, "/", + OPEN_TREE_NAMESPACE | AT_RECURSIVE | OPEN_TREE_CLOEXEC); + if (fd < 0) { + if (errno == EINVAL) + _exit(4); + _exit(1); + } + + if (get_mnt_ns_id(fd, &new_ns_id) != 0) + _exit(5); + + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + if (nr_mounts < 0) + _exit(6); + + /* Recursive should copy submounts too */ + if (nr_mounts < 1) + _exit(7); + + close(fd); + _exit(0); + } + + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + + switch (WEXITSTATUS(status)) { + case 0: + /* Success */ + break; + case 1: + ASSERT_FALSE(true) TH_LOG("open_tree(OPEN_TREE_NAMESPACE|AT_RECURSIVE) failed in userns"); + break; + case 2: + SKIP(return, "setup_userns failed"); + break; + case 4: + SKIP(return, "OPEN_TREE_NAMESPACE not supported"); + break; + case 5: + ASSERT_FALSE(true) TH_LOG("Failed to get mount namespace ID"); + break; + case 6: + ASSERT_FALSE(true) TH_LOG("listmount failed in new namespace"); + break; + case 7: + ASSERT_FALSE(true) TH_LOG("New namespace has no mounts"); + break; + default: + ASSERT_FALSE(true) TH_LOG("Unexpected error in child (exit %d)", + WEXITSTATUS(status)); + break; + } +} + +TEST_F(open_tree_ns_userns, umount_fails_einval) +{ + pid_t pid; + int status; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int fd; + ssize_t i; + + /* Create new user namespace */ + if (enter_userns() != 0) + _exit(2); + + fd = sys_open_tree(AT_FDCWD, "/", + OPEN_TREE_NAMESPACE | AT_RECURSIVE | OPEN_TREE_CLOEXEC); + if (fd < 0) { + if (errno == EINVAL) + _exit(4); + _exit(1); + } + + if (get_mnt_ns_id(fd, &new_ns_id) != 0) + _exit(5); + + /* Get all mounts in the new namespace */ + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, LISTMOUNT_REVERSE); + if (nr_mounts < 0) + _exit(9); + + if (nr_mounts < 1) + _exit(10); + + /* Enter the new namespace */ + if (setns(fd, CLONE_NEWNS) < 0) + _exit(6); + + for (i = 0; i < nr_mounts; i++) { + struct statmount *sm; + const char *mnt_point; + + sm = statmount_alloc(list[i], new_ns_id, + STATMOUNT_MNT_POINT, 0); + if (!sm) + _exit(11); + + mnt_point = sm->str + sm->mnt_point; + + TH_LOG("Trying to umount %s", mnt_point); + if (umount2(mnt_point, MNT_DETACH) == 0) { + free(sm); + _exit(7); + } + + if (errno != EINVAL) { + /* Wrong error */ + free(sm); + _exit(8); + } + + free(sm); + } + + close(fd); + _exit(0); + } + + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + + switch (WEXITSTATUS(status)) { + case 0: + break; + case 1: + ASSERT_FALSE(true) TH_LOG("open_tree(OPEN_TREE_NAMESPACE) failed"); + break; + case 2: + SKIP(return, "setup_userns failed"); + break; + case 4: + SKIP(return, "OPEN_TREE_NAMESPACE not supported"); + break; + case 5: + ASSERT_FALSE(true) TH_LOG("Failed to get mount namespace ID"); + break; + case 6: + ASSERT_FALSE(true) TH_LOG("setns into new namespace failed"); + break; + case 7: + ASSERT_FALSE(true) TH_LOG("umount succeeded but should have failed with EINVAL"); + break; + case 8: + ASSERT_FALSE(true) TH_LOG("umount failed with wrong error (expected EINVAL)"); + break; + case 9: + ASSERT_FALSE(true) TH_LOG("listmount failed"); + break; + case 10: + ASSERT_FALSE(true) TH_LOG("No mounts in new namespace"); + break; + case 11: + ASSERT_FALSE(true) TH_LOG("statmount_alloc failed"); + break; + default: + ASSERT_FALSE(true) TH_LOG("Unexpected error in child (exit %d)", + WEXITSTATUS(status)); + break; + } +} + +TEST_F(open_tree_ns_userns, umount_succeeds) +{ + pid_t pid; + int status; + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int fd; + ssize_t i; + + if (unshare(CLONE_NEWNS)) + _exit(1); + + if (sys_mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) != 0) + _exit(1); + + fd = sys_open_tree(AT_FDCWD, "/", + OPEN_TREE_NAMESPACE | AT_RECURSIVE | OPEN_TREE_CLOEXEC); + if (fd < 0) { + if (errno == EINVAL) + _exit(4); + _exit(1); + } + + if (get_mnt_ns_id(fd, &new_ns_id) != 0) + _exit(5); + + /* Get all mounts in the new namespace */ + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, LISTMOUNT_REVERSE); + if (nr_mounts < 0) + _exit(9); + + if (nr_mounts < 1) + _exit(10); + + /* Enter the new namespace */ + if (setns(fd, CLONE_NEWNS) < 0) + _exit(6); + + for (i = 0; i < nr_mounts; i++) { + struct statmount *sm; + const char *mnt_point; + + sm = statmount_alloc(list[i], new_ns_id, + STATMOUNT_MNT_POINT, 0); + if (!sm) + _exit(11); + + mnt_point = sm->str + sm->mnt_point; + + TH_LOG("Trying to umount %s", mnt_point); + if (umount2(mnt_point, MNT_DETACH) != 0) { + free(sm); + _exit(7); + } + + free(sm); + } + + close(fd); + _exit(0); + } + + ASSERT_EQ(waitpid(pid, &status, 0), pid); + ASSERT_TRUE(WIFEXITED(status)); + + switch (WEXITSTATUS(status)) { + case 0: + break; + case 1: + ASSERT_FALSE(true) TH_LOG("open_tree(OPEN_TREE_NAMESPACE) failed"); + break; + case 2: + SKIP(return, "setup_userns failed"); + break; + case 4: + SKIP(return, "OPEN_TREE_NAMESPACE not supported"); + break; + case 5: + ASSERT_FALSE(true) TH_LOG("Failed to get mount namespace ID"); + break; + case 6: + ASSERT_FALSE(true) TH_LOG("setns into new namespace failed"); + break; + case 7: + ASSERT_FALSE(true) TH_LOG("umount failed but should have succeeded"); + break; + case 9: + ASSERT_FALSE(true) TH_LOG("listmount failed"); + break; + case 10: + ASSERT_FALSE(true) TH_LOG("No mounts in new namespace"); + break; + case 11: + ASSERT_FALSE(true) TH_LOG("statmount_alloc failed"); + break; + default: + ASSERT_FALSE(true) TH_LOG("Unexpected error in child (exit %d)", + WEXITSTATUS(status)); + break; + } +} + +FIXTURE(open_tree_ns_unbindable) +{ + char tmpdir[PATH_MAX]; + bool mounted; +}; + +FIXTURE_SETUP(open_tree_ns_unbindable) +{ + int ret; + + self->mounted = false; + + /* Check if open_tree syscall is supported */ + ret = sys_open_tree(-1, NULL, 0); + if (ret == -1 && errno == ENOSYS) + SKIP(return, "open_tree() syscall not supported"); + + /* Create a temporary directory for the test mount */ + snprintf(self->tmpdir, sizeof(self->tmpdir), + "/tmp/open_tree_ns_test.XXXXXX"); + ASSERT_NE(mkdtemp(self->tmpdir), NULL); + + /* Mount tmpfs there */ + ret = mount("tmpfs", self->tmpdir, "tmpfs", 0, NULL); + if (ret < 0) { + rmdir(self->tmpdir); + SKIP(return, "Failed to mount tmpfs"); + } + self->mounted = true; + + ret = mount(NULL, self->tmpdir, NULL, MS_UNBINDABLE, NULL); + if (ret < 0) { + rmdir(self->tmpdir); + SKIP(return, "Failed to make tmpfs unbindable"); + } +} + +FIXTURE_TEARDOWN(open_tree_ns_unbindable) +{ + if (self->mounted) + umount2(self->tmpdir, MNT_DETACH); + rmdir(self->tmpdir); +} + +TEST_F(open_tree_ns_unbindable, fails_on_unbindable) +{ + int fd; + + fd = sys_open_tree(AT_FDCWD, self->tmpdir, + OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC); + ASSERT_LT(fd, 0); +} + +TEST_F(open_tree_ns_unbindable, recursive_skips_on_unbindable) +{ + uint64_t new_ns_id; + uint64_t list[256]; + ssize_t nr_mounts; + int fd; + ssize_t i; + bool found_unbindable = false; + + fd = sys_open_tree(AT_FDCWD, "/", + OPEN_TREE_NAMESPACE | AT_RECURSIVE | OPEN_TREE_CLOEXEC); + ASSERT_GT(fd, 0); + + ASSERT_EQ(get_mnt_ns_id(fd, &new_ns_id), 0); + + nr_mounts = listmount(LSMT_ROOT, new_ns_id, 0, list, 256, 0); + ASSERT_GE(nr_mounts, 0) { + TH_LOG("listmount failed: %m"); + } + + /* + * Iterate through all mounts in the new namespace and verify + * the unbindable tmpfs mount was silently dropped. + */ + for (i = 0; i < nr_mounts; i++) { + struct statmount *sm; + const char *mnt_point; + + sm = statmount_alloc(list[i], new_ns_id, STATMOUNT_MNT_POINT, 0); + ASSERT_NE(sm, NULL) { + TH_LOG("statmount_alloc failed for mnt_id %llu", + (unsigned long long)list[i]); + } + + mnt_point = sm->str + sm->mnt_point; + + if (strcmp(mnt_point, self->tmpdir) == 0) { + TH_LOG("Found unbindable mount at %s (should have been dropped)", + mnt_point); + found_unbindable = true; + } + + free(sm); + } + + ASSERT_FALSE(found_unbindable) { + TH_LOG("Unbindable mount at %s was not dropped", self->tmpdir); + } + + close(fd); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/openat2/.gitignore b/tools/testing/selftests/filesystems/openat2/.gitignore new file mode 100644 index 000000000000..82a4846cbc4b --- /dev/null +++ b/tools/testing/selftests/filesystems/openat2/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +/*_test diff --git a/tools/testing/selftests/filesystems/openat2/Makefile b/tools/testing/selftests/filesystems/openat2/Makefile new file mode 100644 index 000000000000..d848aac96bde --- /dev/null +++ b/tools/testing/selftests/filesystems/openat2/Makefile @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0-or-later + +CFLAGS += $(KHDR_INCLUDES) +CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined $(TOOLS_INCLUDES) +TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test emptypath_test + +# gcc requires -static-libasan in order to ensure that Address Sanitizer's +# library is the first one loaded. However, clang already statically links the +# Address Sanitizer if -fsanitize is specified. Therefore, simply omit +# -static-libasan for clang builds. +ifeq ($(LLVM),) + CFLAGS += -static-libasan +endif + +LOCAL_HDRS += helpers.h + +include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/openat2/emptypath_test.c b/tools/testing/selftests/filesystems/openat2/emptypath_test.c new file mode 100644 index 000000000000..be37ccba57ec --- /dev/null +++ b/tools/testing/selftests/filesystems/openat2/emptypath_test.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ +#include <fcntl.h> +#include <unistd.h> +#include <errno.h> +#include <string.h> +#include <sys/stat.h> + +#include "kselftest_harness.h" + +#ifndef O_EMPTYPATH +#define O_EMPTYPATH (1 << 26) +#endif + +#define EMPTYPATH_TEST_FILE "/tmp/emptypath_test" + +FIXTURE(emptypath) { + int opath_fd; +}; + +FIXTURE_SETUP(emptypath) +{ + int fd; + + self->opath_fd = -1; + + fd = open(EMPTYPATH_TEST_FILE, O_CREAT | O_WRONLY, S_IRWXU); + ASSERT_GE(fd, 0) { + TH_LOG("create %s: %s", EMPTYPATH_TEST_FILE, strerror(errno)); + } + close(fd); + + self->opath_fd = open(EMPTYPATH_TEST_FILE, O_PATH); + ASSERT_GE(self->opath_fd, 0) { + TH_LOG("open %s O_PATH: %s", EMPTYPATH_TEST_FILE, strerror(errno)); + } +} + +FIXTURE_TEARDOWN(emptypath) +{ + if (self->opath_fd >= 0) + close(self->opath_fd); + unlink(EMPTYPATH_TEST_FILE); +} + +/* An empty path is rejected with ENOENT unless O_EMPTYPATH is set. */ +TEST_F(emptypath, without_flag_returns_enoent) +{ + int fd = openat(self->opath_fd, "", O_RDONLY); + + if (fd >= 0) + close(fd); + ASSERT_LT(fd, 0) { + TH_LOG("empty path without O_EMPTYPATH unexpectedly succeeded"); + } + EXPECT_EQ(errno, ENOENT) { + TH_LOG("expected ENOENT, got %s", strerror(errno)); + } +} + +/* O_EMPTYPATH reopens the O_PATH fd through an empty path. */ +TEST_F(emptypath, reopens_opath_fd) +{ + int fd = openat(self->opath_fd, "", O_RDONLY | O_EMPTYPATH); + + if (fd < 0 && errno == EINVAL) + SKIP(return, "O_EMPTYPATH not supported"); + + ASSERT_GE(fd, 0) { + TH_LOG("O_EMPTYPATH failed: %s", strerror(errno)); + } + close(fd); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/openat2/helpers.h b/tools/testing/selftests/filesystems/openat2/helpers.h new file mode 100644 index 000000000000..3f01fb68c5a6 --- /dev/null +++ b/tools/testing/selftests/filesystems/openat2/helpers.h @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Author: Aleksa Sarai <cyphar@cyphar.com> + * Copyright (C) 2018-2019 SUSE LLC. + * Copyright (C) 2026 Amutable GmbH + */ + +#ifndef __RESOLVEAT_H__ +#define __RESOLVEAT_H__ + +#define _GNU_SOURCE +#include <stdint.h> +#include <stdbool.h> +#include <errno.h> +#include <limits.h> +#include <linux/types.h> +#include <linux/unistd.h> +#include <linux/openat2.h> +#include "kselftest_harness.h" + +#define BUILD_BUG_ON(e) ((void)(sizeof(struct { int:(-!!(e)); }))) + +#define OPEN_HOW_SIZE_VER0 24 /* sizeof first published struct */ +#define OPEN_HOW_SIZE_LATEST OPEN_HOW_SIZE_VER0 + +__maybe_unused +static bool needs_openat2(const struct open_how *how) +{ + return how->resolve != 0; +} + +__maybe_unused +static int raw_openat2(int dfd, const char *path, void *how, size_t size) +{ + int ret = syscall(__NR_openat2, dfd, path, how, size); + + return ret >= 0 ? ret : -errno; +} + +__maybe_unused +static int sys_openat2(int dfd, const char *path, struct open_how *how) +{ + return raw_openat2(dfd, path, how, sizeof(*how)); +} + +__maybe_unused +static int sys_openat(int dfd, const char *path, struct open_how *how) +{ + int ret = openat(dfd, path, how->flags, how->mode); + + return ret >= 0 ? ret : -errno; +} + +__maybe_unused +static int sys_renameat2(int olddirfd, const char *oldpath, + int newdirfd, const char *newpath, unsigned int flags) +{ + int ret = syscall(__NR_renameat2, olddirfd, oldpath, + newdirfd, newpath, flags); + + return ret >= 0 ? ret : -errno; +} + +__maybe_unused +static int touchat(int dfd, const char *path) +{ + int fd = openat(dfd, path, O_CREAT, 0700); + + if (fd >= 0) + close(fd); + return fd; +} + +__maybe_unused +static char *fdreadlink(struct __test_metadata *_metadata, int fd) +{ + char *target, *tmp; + + ASSERT_GT(asprintf(&tmp, "/proc/self/fd/%d", fd), 0); + + target = malloc(PATH_MAX); + ASSERT_NE(target, NULL); + memset(target, 0, PATH_MAX); + + ASSERT_GT(readlink(tmp, target, PATH_MAX), 0); + + free(tmp); + return target; +} + +__maybe_unused +static bool fdequal(struct __test_metadata *_metadata, int fd, + int dfd, const char *path) +{ + char *fdpath, *dfdpath, *other; + bool cmp; + + fdpath = fdreadlink(_metadata, fd); + dfdpath = fdreadlink(_metadata, dfd); + + if (!path) { + ASSERT_GT(asprintf(&other, "%s", dfdpath), 0); + } else if (*path == '/') { + ASSERT_GT(asprintf(&other, "%s", path), 0); + } else { + ASSERT_GT(asprintf(&other, "%s/%s", dfdpath, path), 0); + } + + cmp = !strcmp(fdpath, other); + + free(fdpath); + free(dfdpath); + free(other); + return cmp; +} + +static bool openat2_supported = false; + +__attribute__((constructor)) +static void __detect_openat2_supported(void) +{ + struct open_how how = {}; + int fd; + + BUILD_BUG_ON(sizeof(struct open_how) != OPEN_HOW_SIZE_VER0); + + /* Check openat2(2) support. */ + fd = sys_openat2(AT_FDCWD, ".", &how); + openat2_supported = (fd >= 0); + + if (fd >= 0) + close(fd); +} + +#endif /* __RESOLVEAT_H__ */ diff --git a/tools/testing/selftests/filesystems/openat2/openat2_test.c b/tools/testing/selftests/filesystems/openat2/openat2_test.c new file mode 100644 index 000000000000..6f5afbe2d8d3 --- /dev/null +++ b/tools/testing/selftests/filesystems/openat2/openat2_test.c @@ -0,0 +1,362 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Author: Aleksa Sarai <cyphar@cyphar.com> + * Copyright (C) 2018-2019 SUSE LLC. + */ + +#define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ // Use ll64 +#include <fcntl.h> +#include <sched.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/mount.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> + +#include "helpers.h" +#include "kselftest_harness.h" + +/* + * O_LARGEFILE is set to 0 by glibc. + * XXX: This is wrong on {mips, parisc, powerpc, sparc}. + */ +#undef O_LARGEFILE +#ifdef __aarch64__ +#define O_LARGEFILE 0x20000 +#else +#define O_LARGEFILE 0x8000 +#endif + +struct open_how_ext { + struct open_how inner; + uint32_t extra1; + char pad1[128]; + uint32_t extra2; + char pad2[128]; + uint32_t extra3; +}; + +struct struct_test { + const char *name; + struct open_how_ext arg; + size_t size; + int err; +}; + +struct flag_test { + const char *name; + struct open_how how; + int err; +}; + +FIXTURE(openat2) {}; + +FIXTURE_SETUP(openat2) +{ + if (!openat2_supported) + SKIP(return, "openat2(2) not supported"); +} + +FIXTURE_TEARDOWN(openat2) {} + +/* + * Verify that the struct size and misalignment handling for openat2(2) is + * correct, including that is_zeroed_user() works. + */ +TEST_F(openat2, struct_argument_sizes) +{ + int misalignments[] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 17, 87 }; + struct struct_test tests[] = { + /* Normal struct. */ + { .name = "normal struct", + .arg.inner.flags = O_RDONLY, + .size = sizeof(struct open_how) }, + /* Bigger struct, with zeroed out end. */ + { .name = "bigger struct (zeroed out)", + .arg.inner.flags = O_RDONLY, + .size = sizeof(struct open_how_ext) }, + + /* TODO: Once expanded, check zero-padding. */ + + /* Smaller than version-0 struct. */ + { .name = "zero-sized 'struct'", + .arg.inner.flags = O_RDONLY, .size = 0, .err = -EINVAL }, + { .name = "smaller-than-v0 struct", + .arg.inner.flags = O_RDONLY, + .size = OPEN_HOW_SIZE_VER0 - 1, .err = -EINVAL }, + + /* Bigger struct, with non-zero trailing bytes. */ + { .name = "bigger struct (non-zero data in first 'future field')", + .arg.inner.flags = O_RDONLY, .arg.extra1 = 0xdeadbeef, + .size = sizeof(struct open_how_ext), .err = -E2BIG }, + { .name = "bigger struct (non-zero data in middle of 'future fields')", + .arg.inner.flags = O_RDONLY, .arg.extra2 = 0xfeedcafe, + .size = sizeof(struct open_how_ext), .err = -E2BIG }, + { .name = "bigger struct (non-zero data at end of 'future fields')", + .arg.inner.flags = O_RDONLY, .arg.extra3 = 0xabad1dea, + .size = sizeof(struct open_how_ext), .err = -E2BIG }, + }; + + for (int i = 0; i < ARRAY_SIZE(tests); i++) { + struct struct_test *test = &tests[i]; + struct open_how_ext how_ext = test->arg; + + for (int j = 0; j < ARRAY_SIZE(misalignments); j++) { + int fd, misalign = misalignments[j]; + void *copy = NULL, *how_copy = &how_ext; + char *fdpath = NULL; + + if (misalign) { + /* + * Explicitly misalign the structure copying it with the given + * (mis)alignment offset. The other data is set to be non-zero to + * make sure that non-zero bytes outside the struct aren't checked + * + * This is effectively to check that is_zeroed_user() works. + */ + copy = malloc(misalign + sizeof(how_ext)); + how_copy = copy + misalign; + memset(copy, 0xff, misalign); + memcpy(how_copy, &how_ext, sizeof(how_ext)); + } + + fd = raw_openat2(AT_FDCWD, ".", how_copy, test->size); + if (fd >= 0) { + fdpath = fdreadlink(_metadata, fd); + close(fd); + } + + if (test->err >= 0) { + EXPECT_GE(fd, 0) { + TH_LOG("openat2 with %s [misalign=%d] should succeed, got %d (%s)", + test->name, misalign, + fd, strerror(-fd)); + } + } else { + EXPECT_EQ(test->err, fd) { + if (fdpath) + TH_LOG("openat2 with %s [misalign=%d] should fail with %d (%s), got %d['%s']", + test->name, misalign, + test->err, + strerror(-test->err), + fd, fdpath); + else + TH_LOG("openat2 with %s [misalign=%d] should fail with %d (%s), got %d (%s)", + test->name, misalign, + test->err, + strerror(-test->err), + fd, strerror(-fd)); + } + } + + free(copy); + free(fdpath); + } + } +} + +/* Verify openat2(2) flag and mode validation. */ +TEST_F(openat2, flag_validation) +{ + struct flag_test tests[] = { + /* O_TMPFILE is incompatible with O_PATH and O_CREAT. */ + { .name = "incompatible flags (O_TMPFILE | O_PATH)", + .how.flags = O_TMPFILE | O_PATH | O_RDWR, .err = -EINVAL }, + { .name = "incompatible flags (O_TMPFILE | O_CREAT)", + .how.flags = O_TMPFILE | O_CREAT | O_RDWR, .err = -EINVAL }, + + /* O_PATH only permits certain other flags to be set ... */ + { .name = "compatible flags (O_PATH | O_CLOEXEC)", + .how.flags = O_PATH | O_CLOEXEC }, + { .name = "compatible flags (O_PATH | O_DIRECTORY)", + .how.flags = O_PATH | O_DIRECTORY }, + { .name = "compatible flags (O_PATH | O_NOFOLLOW)", + .how.flags = O_PATH | O_NOFOLLOW }, + /* ... and others are absolutely not permitted. */ + { .name = "incompatible flags (O_PATH | O_RDWR)", + .how.flags = O_PATH | O_RDWR, .err = -EINVAL }, + { .name = "incompatible flags (O_PATH | O_CREAT)", + .how.flags = O_PATH | O_CREAT, .err = -EINVAL }, + { .name = "incompatible flags (O_PATH | O_EXCL)", + .how.flags = O_PATH | O_EXCL, .err = -EINVAL }, + { .name = "incompatible flags (O_PATH | O_NOCTTY)", + .how.flags = O_PATH | O_NOCTTY, .err = -EINVAL }, + { .name = "incompatible flags (O_PATH | O_DIRECT)", + .how.flags = O_PATH | O_DIRECT, .err = -EINVAL }, + { .name = "incompatible flags (O_PATH | O_LARGEFILE)", + .how.flags = O_PATH | O_LARGEFILE, .err = -EINVAL }, + + /* ->mode must only be set with O_{CREAT,TMPFILE}. */ + { .name = "non-zero how.mode and O_RDONLY", + .how.flags = O_RDONLY, .how.mode = 0600, .err = -EINVAL }, + { .name = "non-zero how.mode and O_PATH", + .how.flags = O_PATH, .how.mode = 0600, .err = -EINVAL }, + { .name = "valid how.mode and O_CREAT", + .how.flags = O_CREAT, .how.mode = 0600 }, + { .name = "valid how.mode and O_TMPFILE", + .how.flags = O_TMPFILE | O_RDWR, .how.mode = 0600 }, + /* ->mode must only contain 0777 bits. */ + { .name = "invalid how.mode and O_CREAT", + .how.flags = O_CREAT, + .how.mode = 0xFFFF, .err = -EINVAL }, + { .name = "invalid (very large) how.mode and O_CREAT", + .how.flags = O_CREAT, + .how.mode = 0xC000000000000000ULL, .err = -EINVAL }, + { .name = "invalid how.mode and O_TMPFILE", + .how.flags = O_TMPFILE | O_RDWR, + .how.mode = 0x1337, .err = -EINVAL }, + { .name = "invalid (very large) how.mode and O_TMPFILE", + .how.flags = O_TMPFILE | O_RDWR, + .how.mode = 0x0000A00000000000ULL, .err = -EINVAL }, + + /* ->resolve flags must not conflict. */ + { .name = "incompatible resolve flags (BENEATH | IN_ROOT)", + .how.flags = O_RDONLY, + .how.resolve = RESOLVE_BENEATH | RESOLVE_IN_ROOT, + .err = -EINVAL }, + + /* ->resolve must only contain RESOLVE_* flags. */ + { .name = "invalid how.resolve and O_RDONLY", + .how.flags = O_RDONLY, + .how.resolve = 0x1337, .err = -EINVAL }, + { .name = "invalid how.resolve and O_CREAT", + .how.flags = O_CREAT, + .how.resolve = 0x1337, .err = -EINVAL }, + { .name = "invalid how.resolve and O_TMPFILE", + .how.flags = O_TMPFILE | O_RDWR, + .how.resolve = 0x1337, .err = -EINVAL }, + { .name = "invalid how.resolve and O_PATH", + .how.flags = O_PATH, + .how.resolve = 0x1337, .err = -EINVAL }, + + /* currently unknown upper 32 bit rejected. */ + { .name = "currently unknown bit (1 << 63)", + .how.flags = O_RDONLY | (1ULL << 63), + .how.resolve = 0, .err = -EINVAL }, + }; + + for (int i = 0; i < ARRAY_SIZE(tests); i++) { + int fd, fdflags = -1; + char *path, *fdpath = NULL; + struct flag_test *test = &tests[i]; + + path = (test->how.flags & O_CREAT) ? "/tmp/ksft.openat2_tmpfile" : "."; + unlink(path); + + fd = sys_openat2(AT_FDCWD, path, &test->how); + if (fd < 0 && fd == -EOPNOTSUPP) { + /* + * Skip the testcase if it failed because not supported + * by FS. (e.g. a valid O_TMPFILE combination on NFS) + */ + TH_LOG("openat2 with %s not supported by FS -- skipping", + test->name); + continue; + } + + if (test->err >= 0) { + EXPECT_GE(fd, 0) { + TH_LOG("openat2 with %s should succeed, got %d (%s)", + test->name, fd, strerror(-fd)); + } + if (fd >= 0) { + int otherflags; + + fdpath = fdreadlink(_metadata, fd); + fdflags = fcntl(fd, F_GETFL); + otherflags = fcntl(fd, F_GETFD); + close(fd); + + ASSERT_GE(fdflags, 0); + ASSERT_GE(otherflags, 0); + + /* O_CLOEXEC isn't shown in F_GETFL. */ + if (otherflags & FD_CLOEXEC) + fdflags |= O_CLOEXEC; + /* O_CREAT is hidden from F_GETFL. */ + if (test->how.flags & O_CREAT) + fdflags |= O_CREAT; + if (!(test->how.flags & O_LARGEFILE)) + fdflags &= ~O_LARGEFILE; + + EXPECT_EQ(fdflags, (int)test->how.flags) { + TH_LOG("openat2 with %s: flags mismatch %X != %llX", + test->name, fdflags, + (unsigned long long)test->how.flags); + } + } + } else { + EXPECT_EQ(test->err, fd) { + if (fd >= 0) { + fdpath = fdreadlink(_metadata, fd); + TH_LOG("openat2 with %s should fail with %d (%s), got %d['%s']", + test->name, test->err, + strerror(-test->err), + fd, fdpath); + } else { + TH_LOG("openat2 with %s should fail with %d (%s), got %d (%s)", + test->name, test->err, + strerror(-test->err), + fd, strerror(-fd)); + } + } + if (fd >= 0) + close(fd); + } + + free(fdpath); + } +} + +#ifndef OPENAT2_REGULAR +#define OPENAT2_REGULAR ((__u64)1 << 32) +#endif + +#ifndef EFTYPE +#define EFTYPE 134 +#endif + +/* Kernel-internal carrier for OPENAT2_REGULAR (see __O_REGULAR in fcntl.h). */ +#ifndef __O_REGULAR +#define __O_REGULAR (1 << 30) +#endif + +/* Verify that OPENAT2_REGULAR rejects non-regular files with EFTYPE. */ +TEST_F(openat2, regular_flag) +{ + struct open_how how = { + .flags = OPENAT2_REGULAR | O_RDONLY, + }; + int fd; + + fd = sys_openat2(AT_FDCWD, "/dev/null", &how); + if (fd == -ENOENT) + SKIP(return, "/dev/null does not exist"); + + EXPECT_EQ(-EFTYPE, fd) { + TH_LOG("openat2 with OPENAT2_REGULAR should fail with %d (%s), got %d (%s)", + -EFTYPE, strerror(EFTYPE), fd, strerror(-fd)); + } + if (fd >= 0) + close(fd); +} + +/* open()/openat() must keep ignoring the internal __O_REGULAR bit. */ +TEST(legacy_openat_ignores_o_regular) +{ + int fd; + + fd = openat(AT_FDCWD, "/dev/null", O_RDONLY | __O_REGULAR); + if (fd < 0 && errno == ENOENT) + SKIP(return, "/dev/null does not exist"); + + ASSERT_GE(fd, 0) { + TH_LOG("legacy openat() must ignore the __O_REGULAR carrier bit, got errno %d (%s)", + errno, strerror(errno)); + } + close(fd); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/openat2/rename_attack_test.c b/tools/testing/selftests/filesystems/openat2/rename_attack_test.c new file mode 100644 index 000000000000..1f33c34f56be --- /dev/null +++ b/tools/testing/selftests/filesystems/openat2/rename_attack_test.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Author: Aleksa Sarai <cyphar@cyphar.com> + * Copyright (C) 2018-2019 SUSE LLC. + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <sched.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/mount.h> +#include <sys/mman.h> +#include <sys/prctl.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <syscall.h> +#include <limits.h> +#include <unistd.h> + +#include "helpers.h" +#include "kselftest_harness.h" + +#define ROUNDS 400000 + +/* Swap @dirfd/@a and @dirfd/@b constantly. Parent must kill this process. */ +pid_t spawn_attack(struct __test_metadata *_metadata, + int dirfd, char *a, char *b) +{ + pid_t child = fork(); + if (child != 0) + return child; + + /* If the parent (the test process) dies, kill ourselves too. */ + ASSERT_EQ(prctl(PR_SET_PDEATHSIG, SIGKILL), 0); + + /* Swap @a and @b. */ + for (;;) + renameat2(dirfd, a, dirfd, b, RENAME_EXCHANGE); + exit(1); +} + +/* + * Construct a test directory with the following structure: + * + * root/ + * |-- a/ + * | `-- c/ + * `-- b/ + */ +FIXTURE(rename_attack) { + int dfd; + int afd; + pid_t child; +}; + +FIXTURE_SETUP(rename_attack) +{ + char dirname[] = "/tmp/ksft-openat2-rename-attack.XXXXXX"; + + self->dfd = -1; + self->afd = -1; + self->child = 0; + + /* Make the top-level directory. */ + ASSERT_NE(mkdtemp(dirname), NULL); + self->dfd = open(dirname, O_PATH | O_DIRECTORY); + ASSERT_GE(self->dfd, 0); + + ASSERT_EQ(mkdirat(self->dfd, "a", 0755), 0); + ASSERT_EQ(mkdirat(self->dfd, "b", 0755), 0); + ASSERT_EQ(mkdirat(self->dfd, "a/c", 0755), 0); + + self->afd = openat(self->dfd, "a", O_PATH); + ASSERT_GE(self->afd, 0); + + self->child = spawn_attack(_metadata, self->dfd, "a/c", "b"); + ASSERT_GT(self->child, 0); +} + +FIXTURE_TEARDOWN(rename_attack) +{ + if (self->child > 0) + kill(self->child, SIGKILL); + if (self->afd >= 0) + close(self->afd); + if (self->dfd >= 0) + close(self->dfd); +} + +FIXTURE_VARIANT(rename_attack) { + int resolve; + const char *name; +}; + +FIXTURE_VARIANT_ADD(rename_attack, resolve_beneath) { + .resolve = RESOLVE_BENEATH, + .name = "RESOLVE_BENEATH", +}; + +FIXTURE_VARIANT_ADD(rename_attack, resolve_in_root) { + .resolve = RESOLVE_IN_ROOT, + .name = "RESOLVE_IN_ROOT", +}; + +TEST_F_TIMEOUT(rename_attack, test, 120) +{ + int escapes = 0, successes = 0, other_errs = 0, exdevs = 0, eagains = 0; + char *victim_path = "c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../.."; + struct open_how how = { + .flags = O_PATH, + .resolve = variant->resolve, + }; + + if (!openat2_supported) { + how.resolve = 0; + TH_LOG("openat2(2) unsupported -- using openat(2) instead"); + } + + for (int i = 0; i < ROUNDS; i++) { + int fd; + + if (openat2_supported) + fd = sys_openat2(self->afd, victim_path, &how); + else + fd = sys_openat(self->afd, victim_path, &how); + + if (fd < 0) { + if (fd == -EAGAIN) + eagains++; + else if (fd == -EXDEV) + exdevs++; + else if (fd == -ENOENT) + escapes++; /* escaped outside and got ENOENT... */ + else + other_errs++; /* unexpected error */ + } else { + if (fdequal(_metadata, fd, self->afd, NULL)) + successes++; + else + escapes++; /* we got an unexpected fd */ + } + if (fd >= 0) + close(fd); + } + + TH_LOG("non-escapes: EAGAIN=%d EXDEV=%d E<other>=%d success=%d", + eagains, exdevs, other_errs, successes); + ASSERT_EQ(escapes, 0) { + TH_LOG("rename attack with %s (%d runs, got %d escapes)", + variant->name, ROUNDS, escapes); + } +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/openat2/resolve_test.c b/tools/testing/selftests/filesystems/openat2/resolve_test.c new file mode 100644 index 000000000000..eacde59ce158 --- /dev/null +++ b/tools/testing/selftests/filesystems/openat2/resolve_test.c @@ -0,0 +1,561 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Author: Aleksa Sarai <cyphar@cyphar.com> + * Copyright (C) 2018-2019 SUSE LLC. + */ + +#define _GNU_SOURCE +#include <fcntl.h> +#include <sched.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/mount.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> + +#include "helpers.h" +#include "kselftest_harness.h" + +struct resolve_test { + const char *name; + const char *dir; + const char *path; + struct open_how how; + bool pass; + union { + int err; + const char *path; + } out; +}; + +/* + * Verify a single resolve test case. This must be called from within a TEST_F + * function with _metadata in scope. + */ +static void verify_resolve_test(struct __test_metadata *_metadata, + int rootfd, int hardcoded_fd, + const struct resolve_test *test) +{ + struct open_how how = test->how; + int dfd, fd; + char *fdpath = NULL; + + /* Auto-set O_PATH. */ + if (!(how.flags & O_CREAT)) + how.flags |= O_PATH; + + if (test->dir) + dfd = openat(rootfd, test->dir, O_PATH | O_DIRECTORY); + else + dfd = dup(rootfd); + ASSERT_GE(dfd, 0) TH_LOG("failed to open dir '%s': %m", test->dir ?: "."); + ASSERT_EQ(dup2(dfd, hardcoded_fd), hardcoded_fd); + + fd = sys_openat2(dfd, test->path, &how); + + if (test->pass) { + EXPECT_GE(fd, 0) { + TH_LOG("%s: expected success, got %d (%s)", + test->name, fd, strerror(-fd)); + } + if (fd >= 0) { + EXPECT_TRUE(fdequal(_metadata, fd, rootfd, test->out.path)) { + fdpath = fdreadlink(_metadata, fd); + TH_LOG("%s: wrong path '%s', expected '%s'", + test->name, fdpath, + test->out.path ?: "."); + free(fdpath); + } + } + } else { + EXPECT_EQ(test->out.err, fd) { + if (fd >= 0) { + fdpath = fdreadlink(_metadata, fd); + TH_LOG("%s: expected %d (%s), got %d['%s']", + test->name, test->out.err, + strerror(-test->out.err), fd, fdpath); + free(fdpath); + } else { + TH_LOG("%s: expected %d (%s), got %d (%s)", + test->name, test->out.err, + strerror(-test->out.err), + fd, strerror(-fd)); + } + } + } + + if (fd >= 0) + close(fd); + close(dfd); +} + +/* + * Construct a test directory with the following structure: + * + * root/ + * |-- procexe -> /proc/self/exe + * |-- procroot -> /proc/self/root + * |-- root/ + * |-- mnt/ [mountpoint] + * | |-- self -> ../mnt/ + * | `-- absself -> /mnt/ + * |-- etc/ + * | `-- passwd + * |-- creatlink -> /newfile3 + * |-- reletc -> etc/ + * |-- relsym -> etc/passwd + * |-- absetc -> /etc/ + * |-- abssym -> /etc/passwd + * |-- abscheeky -> /cheeky + * `-- cheeky/ + * |-- absself -> / + * |-- self -> ../../root/ + * |-- garbageself -> /../../root/ + * |-- passwd -> ../cheeky/../etc/../etc/passwd + * |-- abspasswd -> /../cheeky/../etc/../etc/passwd + * |-- dotdotlink -> ../../../../../../../../../../../../../../etc/passwd + * `-- garbagelink -> /../../../../../../../../../../../../../../etc/passwd + */ +FIXTURE(openat2_resolve) { + int rootfd; + int hardcoded_fd; + char *hardcoded_fdpath; + char *procselfexe; +}; + +FIXTURE_SETUP(openat2_resolve) +{ + char dirname[] = "/tmp/ksft-openat2-testdir.XXXXXX"; + int dfd, tmpfd; + + self->rootfd = -1; + self->hardcoded_fd = -1; + self->hardcoded_fdpath = NULL; + self->procselfexe = NULL; + + /* NOTE: We should be checking for CAP_SYS_ADMIN here... */ + if (geteuid() != 0) + SKIP(return, "all tests require euid == 0"); + if (!openat2_supported) + SKIP(return, "openat2(2) not supported"); + + /* Unshare and make /tmp a new directory. */ + ASSERT_EQ(unshare(CLONE_NEWNS), 0); + ASSERT_EQ(mount("", "/tmp", "", MS_PRIVATE, ""), 0); + + /* Make the top-level directory. */ + ASSERT_NE(mkdtemp(dirname), NULL); + dfd = open(dirname, O_PATH | O_DIRECTORY); + ASSERT_GE(dfd, 0); + + /* A sub-directory which is actually used for tests. */ + ASSERT_EQ(mkdirat(dfd, "root", 0755), 0); + tmpfd = openat(dfd, "root", O_PATH | O_DIRECTORY); + ASSERT_GE(tmpfd, 0); + close(dfd); + dfd = tmpfd; + + ASSERT_EQ(symlinkat("/proc/self/exe", dfd, "procexe"), 0); + ASSERT_EQ(symlinkat("/proc/self/root", dfd, "procroot"), 0); + ASSERT_EQ(mkdirat(dfd, "root", 0755), 0); + + /* There is no mountat(2), so use chdir. */ + ASSERT_EQ(mkdirat(dfd, "mnt", 0755), 0); + ASSERT_EQ(fchdir(dfd), 0); + ASSERT_EQ(mount("tmpfs", "./mnt", "tmpfs", MS_NOSUID | MS_NODEV, ""), 0); + ASSERT_EQ(symlinkat("../mnt/", dfd, "mnt/self"), 0); + ASSERT_EQ(symlinkat("/mnt/", dfd, "mnt/absself"), 0); + + ASSERT_EQ(mkdirat(dfd, "etc", 0755), 0); + ASSERT_GE(touchat(dfd, "etc/passwd"), 0); + + ASSERT_EQ(symlinkat("/newfile3", dfd, "creatlink"), 0); + ASSERT_EQ(symlinkat("etc/", dfd, "reletc"), 0); + ASSERT_EQ(symlinkat("etc/passwd", dfd, "relsym"), 0); + ASSERT_EQ(symlinkat("/etc/", dfd, "absetc"), 0); + ASSERT_EQ(symlinkat("/etc/passwd", dfd, "abssym"), 0); + ASSERT_EQ(symlinkat("/cheeky", dfd, "abscheeky"), 0); + + ASSERT_EQ(mkdirat(dfd, "cheeky", 0755), 0); + + ASSERT_EQ(symlinkat("/", dfd, "cheeky/absself"), 0); + ASSERT_EQ(symlinkat("../../root/", dfd, "cheeky/self"), 0); + ASSERT_EQ(symlinkat("/../../root/", dfd, "cheeky/garbageself"), 0); + + ASSERT_EQ(symlinkat("../cheeky/../etc/../etc/passwd", + dfd, "cheeky/passwd"), 0); + ASSERT_EQ(symlinkat("/../cheeky/../etc/../etc/passwd", + dfd, "cheeky/abspasswd"), 0); + + ASSERT_EQ(symlinkat("../../../../../../../../../../../../../../etc/passwd", + dfd, "cheeky/dotdotlink"), 0); + ASSERT_EQ(symlinkat("/../../../../../../../../../../../../../../etc/passwd", + dfd, "cheeky/garbagelink"), 0); + + self->rootfd = dfd; + + self->hardcoded_fd = open("/dev/null", O_RDONLY); + ASSERT_GE(self->hardcoded_fd, 0); + ASSERT_GE(asprintf(&self->hardcoded_fdpath, "self/fd/%d", + self->hardcoded_fd), 0); + ASSERT_GE(asprintf(&self->procselfexe, "/proc/%d/exe", getpid()), 0); +} + +FIXTURE_TEARDOWN(openat2_resolve) +{ + free(self->procselfexe); + free(self->hardcoded_fdpath); + if (self->hardcoded_fd >= 0) + close(self->hardcoded_fd); + if (self->rootfd >= 0) + close(self->rootfd); +} + +/* Attempts to cross the dirfd should be blocked with -EXDEV. */ +TEST_F(openat2_resolve, resolve_beneath) +{ + struct resolve_test tests[] = { + /* Attempts to cross dirfd should be blocked. */ + { .name = "[beneath] jump to /", + .path = "/", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] absolute link to $root", + .path = "cheeky/absself", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] chained absolute links to $root", + .path = "abscheeky/absself", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] jump outside $root", + .path = "..", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] temporary jump outside $root", + .path = "../root/", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] symlink temporary jump outside $root", + .path = "cheeky/self", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] chained symlink temporary jump outside $root", + .path = "abscheeky/self", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] garbage links to $root", + .path = "cheeky/garbageself", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] chained garbage links to $root", + .path = "abscheeky/garbageself", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + /* Only relative paths that stay inside dirfd should work. */ + { .name = "[beneath] ordinary path to 'root'", + .path = "root", .how.resolve = RESOLVE_BENEATH, + .out.path = "root", .pass = true }, + { .name = "[beneath] ordinary path to 'etc'", + .path = "etc", .how.resolve = RESOLVE_BENEATH, + .out.path = "etc", .pass = true }, + { .name = "[beneath] ordinary path to 'etc/passwd'", + .path = "etc/passwd", .how.resolve = RESOLVE_BENEATH, + .out.path = "etc/passwd", .pass = true }, + { .name = "[beneath] relative symlink inside $root", + .path = "relsym", .how.resolve = RESOLVE_BENEATH, + .out.path = "etc/passwd", .pass = true }, + { .name = "[beneath] chained-'..' relative symlink inside $root", + .path = "cheeky/passwd", .how.resolve = RESOLVE_BENEATH, + .out.path = "etc/passwd", .pass = true }, + { .name = "[beneath] absolute symlink component outside $root", + .path = "abscheeky/passwd", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] absolute symlink target outside $root", + .path = "abssym", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] absolute path outside $root", + .path = "/etc/passwd", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] cheeky absolute path outside $root", + .path = "cheeky/abspasswd", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] chained cheeky absolute path outside $root", + .path = "abscheeky/abspasswd", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + /* Tricky paths should fail. */ + { .name = "[beneath] tricky '..'-chained symlink outside $root", + .path = "cheeky/dotdotlink", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] tricky absolute + '..'-chained symlink outside $root", + .path = "abscheeky/dotdotlink", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] tricky garbage link outside $root", + .path = "cheeky/garbagelink", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] tricky absolute + garbage link outside $root", + .path = "abscheeky/garbagelink", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + }; + + for (int i = 0; i < ARRAY_SIZE(tests); i++) + verify_resolve_test(_metadata, self->rootfd, + self->hardcoded_fd, &tests[i]); +} + +/* All attempts to cross the dirfd will be scoped-to-root. */ +TEST_F(openat2_resolve, resolve_in_root) +{ + struct resolve_test tests[] = { + { .name = "[in_root] jump to /", + .path = "/", .how.resolve = RESOLVE_IN_ROOT, + .out.path = NULL, .pass = true }, + { .name = "[in_root] absolute symlink to /root", + .path = "cheeky/absself", .how.resolve = RESOLVE_IN_ROOT, + .out.path = NULL, .pass = true }, + { .name = "[in_root] chained absolute symlinks to /root", + .path = "abscheeky/absself", .how.resolve = RESOLVE_IN_ROOT, + .out.path = NULL, .pass = true }, + { .name = "[in_root] '..' at root", + .path = "..", .how.resolve = RESOLVE_IN_ROOT, + .out.path = NULL, .pass = true }, + { .name = "[in_root] '../root' at root", + .path = "../root/", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "root", .pass = true }, + { .name = "[in_root] relative symlink containing '..' above root", + .path = "cheeky/self", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "root", .pass = true }, + { .name = "[in_root] garbage link to /root", + .path = "cheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "root", .pass = true }, + { .name = "[in_root] chained garbage links to /root", + .path = "abscheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "root", .pass = true }, + { .name = "[in_root] relative path to 'root'", + .path = "root", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "root", .pass = true }, + { .name = "[in_root] relative path to 'etc'", + .path = "etc", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc", .pass = true }, + { .name = "[in_root] relative path to 'etc/passwd'", + .path = "etc/passwd", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] relative symlink to 'etc/passwd'", + .path = "relsym", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] chained-'..' relative symlink to 'etc/passwd'", + .path = "cheeky/passwd", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] chained-'..' absolute + relative symlink to 'etc/passwd'", + .path = "abscheeky/passwd", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] absolute symlink to 'etc/passwd'", + .path = "abssym", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] absolute path 'etc/passwd'", + .path = "/etc/passwd", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] cheeky absolute path 'etc/passwd'", + .path = "cheeky/abspasswd", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] chained cheeky absolute path 'etc/passwd'", + .path = "abscheeky/abspasswd", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] tricky '..'-chained symlink outside $root", + .path = "cheeky/dotdotlink", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] tricky absolute + '..'-chained symlink outside $root", + .path = "abscheeky/dotdotlink", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] tricky absolute path + absolute + '..'-chained symlink outside $root", + .path = "/../../../../abscheeky/dotdotlink", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] tricky garbage link outside $root", + .path = "cheeky/garbagelink", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] tricky absolute + garbage link outside $root", + .path = "abscheeky/garbagelink", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] tricky absolute path + absolute + garbage link outside $root", + .path = "/../../../../abscheeky/garbagelink", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + /* O_CREAT should handle trailing symlinks correctly. */ + { .name = "[in_root] O_CREAT of relative path inside $root", + .path = "newfile1", .how.flags = O_CREAT, + .how.mode = 0700, + .how.resolve = RESOLVE_IN_ROOT, + .out.path = "newfile1", .pass = true }, + { .name = "[in_root] O_CREAT of absolute path", + .path = "/newfile2", .how.flags = O_CREAT, + .how.mode = 0700, + .how.resolve = RESOLVE_IN_ROOT, + .out.path = "newfile2", .pass = true }, + { .name = "[in_root] O_CREAT of tricky symlink outside root", + .path = "/creatlink", .how.flags = O_CREAT, + .how.mode = 0700, + .how.resolve = RESOLVE_IN_ROOT, + .out.path = "newfile3", .pass = true }, + }; + + for (int i = 0; i < ARRAY_SIZE(tests); i++) + verify_resolve_test(_metadata, self->rootfd, + self->hardcoded_fd, &tests[i]); +} + +/* Crossing mount boundaries should be blocked. */ +TEST_F(openat2_resolve, resolve_no_xdev) +{ + struct resolve_test tests[] = { + /* Crossing *down* into a mountpoint is disallowed. */ + { .name = "[no_xdev] cross into $mnt", + .path = "mnt", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] cross into $mnt/", + .path = "mnt/", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] cross into $mnt/.", + .path = "mnt/.", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + /* Crossing *up* out of a mountpoint is disallowed. */ + { .name = "[no_xdev] goto mountpoint root", + .dir = "mnt", .path = ".", .how.resolve = RESOLVE_NO_XDEV, + .out.path = "mnt", .pass = true }, + { .name = "[no_xdev] cross up through '..'", + .dir = "mnt", .path = "..", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] temporary cross up through '..'", + .dir = "mnt", .path = "../mnt", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] temporary relative symlink cross up", + .dir = "mnt", .path = "self", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] temporary absolute symlink cross up", + .dir = "mnt", .path = "absself", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + /* Jumping to "/" is ok, but later components cannot cross. */ + { .name = "[no_xdev] jump to / directly", + .dir = "mnt", .path = "/", .how.resolve = RESOLVE_NO_XDEV, + .out.path = "/", .pass = true }, + { .name = "[no_xdev] jump to / (from /) directly", + .dir = "/", .path = "/", .how.resolve = RESOLVE_NO_XDEV, + .out.path = "/", .pass = true }, + { .name = "[no_xdev] jump to / then proc", + .path = "/proc/1", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] jump to / then tmp", + .path = "/tmp", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + /* Magic-links are blocked since they can switch vfsmounts. */ + { .name = "[no_xdev] cross through magic-link to self/root", + .dir = "/proc", .path = "self/root", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] cross through magic-link to self/cwd", + .dir = "/proc", .path = "self/cwd", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + /* Except magic-link jumps inside the same vfsmount. */ + { .name = "[no_xdev] jump through magic-link to same procfs", + .dir = "/proc", .path = self->hardcoded_fdpath, .how.resolve = RESOLVE_NO_XDEV, + .out.path = "/proc", .pass = true, }, + }; + + for (int i = 0; i < ARRAY_SIZE(tests); i++) + verify_resolve_test(_metadata, self->rootfd, + self->hardcoded_fd, &tests[i]); +} + +/* Procfs-style magic-link resolution should be blocked. */ +TEST_F(openat2_resolve, resolve_no_magiclinks) +{ + struct resolve_test tests[] = { + /* Regular symlinks should work. */ + { .name = "[no_magiclinks] ordinary relative symlink", + .path = "relsym", .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.path = "etc/passwd", .pass = true }, + /* Magic-links should not work. */ + { .name = "[no_magiclinks] symlink to magic-link", + .path = "procexe", .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_magiclinks] normal path to magic-link", + .path = "/proc/self/exe", .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_magiclinks] normal path to magic-link with O_NOFOLLOW", + .path = "/proc/self/exe", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.path = self->procselfexe, .pass = true }, + { .name = "[no_magiclinks] symlink to magic-link path component", + .path = "procroot/etc", .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_magiclinks] magic-link path component", + .path = "/proc/self/root/etc", .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_magiclinks] magic-link path component with O_NOFOLLOW", + .path = "/proc/self/root/etc", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.err = -ELOOP, .pass = false }, + }; + + for (int i = 0; i < ARRAY_SIZE(tests); i++) + verify_resolve_test(_metadata, self->rootfd, + self->hardcoded_fd, &tests[i]); +} + +/* All symlink resolution should be blocked. */ +TEST_F(openat2_resolve, resolve_no_symlinks) +{ + struct resolve_test tests[] = { + /* Normal paths should work. */ + { .name = "[no_symlinks] ordinary path to '.'", + .path = ".", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = NULL, .pass = true }, + { .name = "[no_symlinks] ordinary path to 'root'", + .path = "root", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = "root", .pass = true }, + { .name = "[no_symlinks] ordinary path to 'etc'", + .path = "etc", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = "etc", .pass = true }, + { .name = "[no_symlinks] ordinary path to 'etc/passwd'", + .path = "etc/passwd", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = "etc/passwd", .pass = true }, + /* Regular symlinks are blocked. */ + { .name = "[no_symlinks] relative symlink target", + .path = "relsym", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] relative symlink component", + .path = "reletc/passwd", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] absolute symlink target", + .path = "abssym", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] absolute symlink component", + .path = "absetc/passwd", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] cheeky garbage link", + .path = "cheeky/garbagelink", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] cheeky absolute + garbage link", + .path = "abscheeky/garbagelink", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] cheeky absolute + absolute symlink", + .path = "abscheeky/absself", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + /* Trailing symlinks with NO_FOLLOW. */ + { .name = "[no_symlinks] relative symlink with O_NOFOLLOW", + .path = "relsym", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = "relsym", .pass = true }, + { .name = "[no_symlinks] absolute symlink with O_NOFOLLOW", + .path = "abssym", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = "abssym", .pass = true }, + { .name = "[no_symlinks] trailing symlink with O_NOFOLLOW", + .path = "cheeky/garbagelink", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = "cheeky/garbagelink", .pass = true }, + { .name = "[no_symlinks] multiple symlink components with O_NOFOLLOW", + .path = "abscheeky/absself", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] multiple symlink (and garbage link) components with O_NOFOLLOW", + .path = "abscheeky/garbagelink", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + }; + + for (int i = 0; i < ARRAY_SIZE(tests); i++) + verify_resolve_test(_metadata, self->rootfd, + self->hardcoded_fd, &tests[i]); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/overlayfs/.gitignore b/tools/testing/selftests/filesystems/overlayfs/.gitignore index e23a18c8b37f..077f7a128168 100644 --- a/tools/testing/selftests/filesystems/overlayfs/.gitignore +++ b/tools/testing/selftests/filesystems/overlayfs/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only dev_in_maps set_layers_via_fds +idmapped_mounts diff --git a/tools/testing/selftests/filesystems/overlayfs/Makefile b/tools/testing/selftests/filesystems/overlayfs/Makefile index d3ad4a77db9b..b3185f684add 100644 --- a/tools/testing/selftests/filesystems/overlayfs/Makefile +++ b/tools/testing/selftests/filesystems/overlayfs/Makefile @@ -8,7 +8,9 @@ LOCAL_HDRS += ../wrappers.h log.h TEST_GEN_PROGS := dev_in_maps TEST_GEN_PROGS += set_layers_via_fds +TEST_GEN_PROGS += idmapped_mounts include ../../lib.mk $(OUTPUT)/set_layers_via_fds: ../utils.c +$(OUTPUT)/idmapped_mounts: ../utils.c diff --git a/tools/testing/selftests/filesystems/overlayfs/idmapped_mounts.c b/tools/testing/selftests/filesystems/overlayfs/idmapped_mounts.c new file mode 100644 index 000000000000..44a75839f4ed --- /dev/null +++ b/tools/testing/selftests/filesystems/overlayfs/idmapped_mounts.c @@ -0,0 +1,501 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <fcntl.h> +#include <limits.h> +#include <sched.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/stat.h> +#include <sys/syscall.h> + +#include <linux/mount.h> +#include <linux/types.h> + +#include "kselftest_harness.h" +#include "../wrappers.h" +#include "../utils.h" + +/* + * An idmapping that maps the mount-visible id range [0, ID_RANGE) onto the + * host/overlay-final id range [ID_HOST, ID_HOST + ID_RANGE). Through such an + * idmapped overlay mount, an overlay-final id of ID_HOST + n is reported as n, + * and an id of n requested through the mount is stored as ID_HOST + n. + */ +#define ID_NS 0 +#define ID_HOST 10000 +#define ID_RANGE 10000 + +/* + * For the composition test the lower layer's on-disk ids live in a + * separate range and are mapped by an idmapped lower layer onto the + * overlay-final range [ID_HOST, ID_HOST + ID_RANGE). + */ +#define LAYER_HOST 20000 + +#ifndef MOUNT_ATTR_IDMAP +#define MOUNT_ATTR_IDMAP 0x00100000 +#endif + +#ifndef __NR_mount_setattr +#define __NR_mount_setattr 442 +#endif + +static inline int sys_mount_setattr(int dfd, const char *path, + unsigned int flags, + struct mount_attr *attr, size_t size) +{ + return syscall(__NR_mount_setattr, dfd, path, flags, attr, size); +} + +static bool ovl_supported(void) +{ + int fd = sys_fsopen("overlay", 0); + + if (fd < 0) + return false; + close(fd); + return true; +} + +/* base/{l,u,w} owned by ID_HOST so they map to ID_NS through the idmap. */ +static int setup_layers(const char *base) +{ + static const char *sub[] = { "", "/l", "/u", "/w" }; + char path[PATH_MAX]; + + for (size_t i = 0; i < ARRAY_SIZE(sub); i++) { + snprintf(path, sizeof(path), "%s%s", base, sub[i]); + if (mkdir(path, 0755) && errno != EEXIST) + return -1; + if (i && chown(path, ID_HOST, ID_HOST)) + return -1; + } + return 0; +} + +static int ovl_mount(const char *base, bool nfs_export) +{ + char lower[PATH_MAX], upper[PATH_MAX], work[PATH_MAX]; + int fsfd, ovl; + + snprintf(lower, sizeof(lower), "%s/l", base); + snprintf(upper, sizeof(upper), "%s/u", base); + snprintf(work, sizeof(work), "%s/w", base); + + fsfd = sys_fsopen("overlay", 0); + if (fsfd < 0) + return -1; + + if (sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "source", "test", 0) || + sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "lowerdir", lower, 0) || + sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "upperdir", upper, 0) || + sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "workdir", work, 0)) + goto err; + if (nfs_export && + (sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "index", "on", 0) || + sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "nfs_export", "on", 0))) + goto err; + if (sys_fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0)) + goto err; + + ovl = sys_fsmount(fsfd, 0, 0); + close(fsfd); + return ovl; +err: + close(fsfd); + return -1; +} + +/* Idmap the (still detached, not yet visible) overlay mount @mfd. */ +static int ovl_idmap(int mfd) +{ + struct mount_attr attr = { + .attr_set = MOUNT_ATTR_IDMAP, + }; + int ret, userns_fd; + + /* + * get_userns_fd(fs_id, mount_id, range): a file whose filesystem id + * is fs_id + n is shown through the idmapped mount as mount_id + n. + * Here the overlay-final (fs side) range is [ID_HOST, ..) and the + * caller-visible (mount side) range is [ID_NS, ..). + */ + userns_fd = get_userns_fd(ID_HOST, ID_NS, ID_RANGE); + if (userns_fd < 0) + return -1; + + attr.userns_fd = userns_fd; + ret = sys_mount_setattr(mfd, "", AT_EMPTY_PATH, &attr, sizeof(attr)); + close(userns_fd); + return ret; +} + +/* Clone @path into a detached, idmapped mount usable as an overlay layer. */ +static int idmapped_layer_fd(const char *path, int nsid, int hostid, int range) +{ + struct mount_attr attr = { + .attr_set = MOUNT_ATTR_IDMAP, + }; + int fd_tree, userns_fd; + + fd_tree = sys_open_tree(AT_FDCWD, path, + OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + if (fd_tree < 0) + return -1; + userns_fd = get_userns_fd(nsid, hostid, range); + if (userns_fd < 0) { + close(fd_tree); + return -1; + } + attr.userns_fd = userns_fd; + if (sys_mount_setattr(fd_tree, "", AT_EMPTY_PATH, &attr, + sizeof(attr))) { + close(userns_fd); + close(fd_tree); + return -1; + } + close(userns_fd); + return fd_tree; +} + +/* Overlay with a layer passed by fd (idmapped) plus a plain upper/work. */ +static int ovl_mount_lower_fd(const char *upper, const char *work, int fd_lower) +{ + int fsfd, ovl; + + fsfd = sys_fsopen("overlay", 0); + if (fsfd < 0) + return -1; + + if (sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "source", "test", 0) || + sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "upperdir", upper, 0) || + sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "workdir", work, 0) || + sys_fsconfig(fsfd, FSCONFIG_SET_FD, "lowerdir+", NULL, fd_lower) || + sys_fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0)) + goto err; + + ovl = sys_fsmount(fsfd, 0, 0); + close(fsfd); + return ovl; +err: + close(fsfd); + return -1; +} + +/* + * Mount an overlay inside user namespace @u1 (so the overlay sb's s_user_ns is + * not the initial namespace) and idmap that overlay mount with @u2. Runs in a + * child that joins @u1; returns 0 on success. + */ +static int userns_overlay_child(int u1) +{ + struct mount_attr attr = { + .attr_set = MOUNT_ATTR_IDMAP, + }; + struct stat st; + int ovl, u2; + + /* Become root in the overlay sb's user namespace u1. */ + if (!switch_userns(u1, 0, 0, false)) + return fprintf(stderr, "userns: switch_userns: %m\n"), -1; + if (unshare(CLONE_NEWNS) || + sys_mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL)) + return fprintf(stderr, "userns: unshare/slave: %m\n"), -1; + if (sys_mount("tmpfs", "/tmp", "tmpfs", 0, NULL)) + return fprintf(stderr, "userns: mount tmpfs: %m\n"), -1; + if (setup_layers("/tmp/ovl")) + return fprintf(stderr, "userns: setup_layers: %m\n"), -1; + if (mknod("/tmp/ovl/l/file", S_IFREG | 0644, 0) || + chown("/tmp/ovl/l/file", ID_HOST + 5, ID_HOST + 5)) + return fprintf(stderr, "userns: lower file: %m\n"), -1; + + ovl = ovl_mount("/tmp/ovl", false); + if (ovl < 0) + return fprintf(stderr, "userns: ovl_mount: %m\n"), -1; + + /* + * mount_setattr() requires CAP_SYS_ADMIN over the idmap user + * namespace, so it must be a child of u1. Create it now, from + * inside u1. + */ + u2 = get_userns_fd(ID_HOST, ID_NS, ID_RANGE); + if (u2 < 0) + return fprintf(stderr, "userns: get_userns_fd: %m\n"), -1; + attr.userns_fd = u2; + if (sys_mount_setattr(ovl, "", AT_EMPTY_PATH, &attr, sizeof(attr))) + return fprintf(stderr, "userns: mount_setattr: %m\n"), -1; + close(u2); + + if (fstatat(ovl, "file", &st, 0)) + return fprintf(stderr, "userns: fstatat: %m\n"), -1; + if (st.st_uid != ID_NS + 5 || st.st_gid != ID_NS + 5) { + fprintf(stderr, "userns: got %u:%u expected %u:%u\n", + st.st_uid, st.st_gid, ID_NS + 5, ID_NS + 5); + return -1; + } + return 0; +} + +FIXTURE(idmapped_overlay) { + char base[64]; +}; + +FIXTURE_SETUP(idmapped_overlay) +{ + /* Private mount namespace so test mounts need no cleanup. */ + ASSERT_EQ(unshare(CLONE_NEWNS), 0); + ASSERT_EQ(sys_mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL), 0); + + /* tmpfs for the layers so we can chown them to arbitrary ids. */ + ASSERT_EQ(sys_mount("tmpfs", "/tmp", "tmpfs", 0, NULL), 0); + + snprintf(self->base, sizeof(self->base), "/tmp/ovl"); + ASSERT_EQ(setup_layers(self->base), 0); +} + +FIXTURE_TEARDOWN(idmapped_overlay) +{ +} + +/* A file owned by ID_HOST + 5 is reported as ID_NS + 5 through the idmap. */ +TEST_F(idmapped_overlay, getattr) +{ + char path[PATH_MAX]; + struct stat st; + int ovl; + + if (!ovl_supported()) + SKIP(return, "overlayfs not supported"); + + snprintf(path, sizeof(path), "%s/l/file", self->base); + ASSERT_EQ(mknod(path, S_IFREG | 0644, 0), 0); + ASSERT_EQ(chown(path, ID_HOST + 5, ID_HOST + 5), 0); + + ovl = ovl_mount(self->base, false); + ASSERT_GE(ovl, 0); + ASSERT_EQ(ovl_idmap(ovl), 0); + + ASSERT_EQ(fstatat(ovl, "file", &st, 0), 0); + EXPECT_EQ(st.st_uid, ID_NS + 5); + EXPECT_EQ(st.st_gid, ID_NS + 5); + + EXPECT_EQ(close(ovl), 0); +} + +/* + * Every creation path initializes the new owner through the mount idmap: + * created as caller id ID_NS, stored on the upper layer as overlay-final + * ID_HOST. Covers ovl_create() (regular file), ovl_mkdir(), ovl_mknod() + * and ovl_symlink() (which share ovl_create_object()), plus the separate + * ovl_tmpfile() path. + */ +TEST_F(idmapped_overlay, create) +{ + static const char *names[] = { "reg", "dir", "fifo", "lnk" }; + char path[PATH_MAX]; + struct stat st; + int ovl, fd; + + if (!ovl_supported()) + SKIP(return, "overlayfs not supported"); + + ovl = ovl_mount(self->base, false); + ASSERT_GE(ovl, 0); + ASSERT_EQ(ovl_idmap(ovl), 0); + + /* One object per creation operation, all as caller id ID_NS. */ + fd = openat(ovl, "reg", O_CREAT | O_WRONLY | O_EXCL, 0644); + ASSERT_GE(fd, 0); + EXPECT_EQ(close(fd), 0); + ASSERT_EQ(mkdirat(ovl, "dir", 0755), 0); + ASSERT_EQ(mknodat(ovl, "fifo", S_IFIFO | 0644, 0), 0); + ASSERT_EQ(symlinkat("target", ovl, "lnk"), 0); + + for (size_t i = 0; i < ARRAY_SIZE(names); i++) { + /* Reported as ID_NS through the idmapped mount ... */ + ASSERT_EQ(fstatat(ovl, names[i], &st, AT_SYMLINK_NOFOLLOW), 0); + EXPECT_EQ(st.st_uid, ID_NS); + EXPECT_EQ(st.st_gid, ID_NS); + /* ... and stored as ID_HOST on the upper layer. */ + snprintf(path, sizeof(path), "%s/u/%s", self->base, names[i]); + ASSERT_EQ(lstat(path, &st), 0); + EXPECT_EQ(st.st_uid, ID_HOST); + EXPECT_EQ(st.st_gid, ID_HOST); + } + + /* O_TMPFILE goes through the separate ovl_tmpfile() path. */ + fd = openat(ovl, ".", O_TMPFILE | O_WRONLY, 0644); + ASSERT_GE(fd, 0); + /* Inside the mount: caller id ID_NS. */ + ASSERT_EQ(fstat(fd, &st), 0); + EXPECT_EQ(st.st_uid, ID_NS); + EXPECT_EQ(st.st_gid, ID_NS); + /* Link it in so the upper backing file can be inspected too. */ + ASSERT_EQ(linkat(fd, "", ovl, "tmp", AT_EMPTY_PATH), 0); + EXPECT_EQ(close(fd), 0); + snprintf(path, sizeof(path), "%s/u/tmp", self->base); + ASSERT_EQ(lstat(path, &st), 0); + EXPECT_EQ(st.st_uid, ID_HOST); + EXPECT_EQ(st.st_gid, ID_HOST); + + EXPECT_EQ(close(ovl), 0); +} + +/* chown through the idmapped mount round-trips: ID_NS + 5 <-> ID_HOST + 5. */ +TEST_F(idmapped_overlay, chown) +{ + char path[PATH_MAX]; + struct stat st; + int ovl, fd; + + if (!ovl_supported()) + SKIP(return, "overlayfs not supported"); + + ovl = ovl_mount(self->base, false); + ASSERT_GE(ovl, 0); + ASSERT_EQ(ovl_idmap(ovl), 0); + + fd = openat(ovl, "f", O_CREAT | O_WRONLY | O_EXCL, 0644); + ASSERT_GE(fd, 0); + EXPECT_EQ(close(fd), 0); + + ASSERT_EQ(fchownat(ovl, "f", ID_NS + 5, ID_NS + 5, 0), 0); + + ASSERT_EQ(fstatat(ovl, "f", &st, 0), 0); + EXPECT_EQ(st.st_uid, ID_NS + 5); + EXPECT_EQ(st.st_gid, ID_NS + 5); + + snprintf(path, sizeof(path), "%s/u/f", self->base); + ASSERT_EQ(stat(path, &st), 0); + EXPECT_EQ(st.st_uid, ID_HOST + 5); + EXPECT_EQ(st.st_gid, ID_HOST + 5); + + EXPECT_EQ(close(ovl), 0); +} + +/* + * Composition: an idmapped lower layer underneath an idmapped overlay mount. + * An on-disk id is mapped by the layer idmap into the overlay-final range and + * then by the mount idmap into the caller's range: + * + * on-disk LAYER_HOST+7 --layer--> ID_HOST+7 --mount--> ID_NS+7 + */ +TEST_F(idmapped_overlay, composition) +{ + char lower[PATH_MAX], upper[PATH_MAX], work[PATH_MAX], path[PATH_MAX]; + struct stat st; + int ovl, fd_lower; + + if (!ovl_supported()) + SKIP(return, "overlayfs not supported"); + + snprintf(lower, sizeof(lower), "%s/l", self->base); + snprintf(upper, sizeof(upper), "%s/u", self->base); + snprintf(work, sizeof(work), "%s/w", self->base); + + /* Put the lower layer's ids in the on-disk [LAYER_HOST, ..) range. */ + ASSERT_EQ(chown(lower, LAYER_HOST, LAYER_HOST), 0); + snprintf(path, sizeof(path), "%s/l/file", self->base); + ASSERT_EQ(mknod(path, S_IFREG | 0644, 0), 0); + ASSERT_EQ(chown(path, LAYER_HOST + 7, LAYER_HOST + 7), 0); + + /* Idmapped lower: on-disk LAYER_HOST <-> overlay-final ID_HOST. */ + fd_lower = idmapped_layer_fd(lower, LAYER_HOST, ID_HOST, ID_RANGE); + ASSERT_GE(fd_lower, 0); + + ovl = ovl_mount_lower_fd(upper, work, fd_lower); + ASSERT_GE(ovl, 0); + EXPECT_EQ(close(fd_lower), 0); + + /* Idmap the overlay mount: overlay-final ID_HOST <-> caller ID_NS. */ + ASSERT_EQ(ovl_idmap(ovl), 0); + + ASSERT_EQ(fstatat(ovl, "file", &st, 0), 0); + EXPECT_EQ(st.st_uid, ID_NS + 7); + EXPECT_EQ(st.st_gid, ID_NS + 7); + + EXPECT_EQ(close(ovl), 0); +} + +/* An idmapped overlay mount whose sb lives inside a user namespace. */ +TEST_F(idmapped_overlay, userns) +{ + int u1; + pid_t pid; + + if (!ovl_supported()) + SKIP(return, "overlayfs not supported"); + + /* u1 backs the overlay sb: identity-mapped, but not the init ns. */ + u1 = get_userns_fd(0, 0, 65536); + if (u1 < 0) + SKIP(return, "user namespaces not available"); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) { + int ret = userns_overlay_child(u1); + + _exit(ret ? EXIT_FAILURE : EXIT_SUCCESS); + } + EXPECT_EQ(wait_for_pid(pid), 0); + + EXPECT_EQ(close(u1), 0); +} + +/* + * An nfs_export overlay can be idmapped, and decodable file handles round-trip + * through the idmapped mount with correctly mapped ownership. Overlay file + * handles encode object identity, not ownership, so the mount idmap does not + * affect them; it only maps the owner reported once a handle is reopened. + */ +TEST_F(idmapped_overlay, nfs_export_handles) +{ + char path[PATH_MAX], mnt[128]; + union { + struct file_handle fh; + char buf[sizeof(struct file_handle) + MAX_HANDLE_SZ]; + } fhu; + struct file_handle *fh = &fhu.fh; + struct stat st; + int ovl, mfd, fd, mount_id; + + if (!ovl_supported()) + SKIP(return, "overlayfs not supported"); + + snprintf(path, sizeof(path), "%s/l/file", self->base); + ASSERT_EQ(mknod(path, S_IFREG | 0644, 0), 0); + ASSERT_EQ(chown(path, ID_HOST + 7, ID_HOST + 7), 0); + + /* nfs_export=on gives decodable overlay file handles. */ + ovl = ovl_mount(self->base, true); + if (ovl < 0) + SKIP(return, "overlayfs nfs_export not supported"); + ASSERT_EQ(ovl_idmap(ovl), 0); + + /* Attach the idmapped mount so handles can be resolved against it. */ + snprintf(mnt, sizeof(mnt), "%s/mnt", self->base); + ASSERT_EQ(mkdir(mnt, 0755), 0); + ASSERT_EQ(sys_move_mount(ovl, "", AT_FDCWD, mnt, + MOVE_MOUNT_F_EMPTY_PATH), 0); + + snprintf(path, sizeof(path), "%s/file", mnt); + fh->handle_bytes = MAX_HANDLE_SZ; + ASSERT_EQ(name_to_handle_at(AT_FDCWD, path, fh, &mount_id, 0), 0); + + mfd = open(mnt, O_RDONLY | O_DIRECTORY); + ASSERT_GE(mfd, 0); + fd = open_by_handle_at(mfd, fh, O_RDONLY); + EXPECT_EQ(close(mfd), 0); + ASSERT_GE(fd, 0); + + ASSERT_EQ(fstat(fd, &st), 0); + EXPECT_EQ(st.st_uid, ID_NS + 7); + EXPECT_EQ(st.st_gid, ID_NS + 7); + + EXPECT_EQ(close(fd), 0); + EXPECT_EQ(close(ovl), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c b/tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c index 3c0b93183348..7a293544233d 100644 --- a/tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c +++ b/tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c @@ -624,7 +624,7 @@ TEST_F(set_layers_via_fds, set_layers_via_detached_mount_fds) ASSERT_EQ(sys_move_mount(fd_tmpfs, "", -EBADF, "/set_layers_via_fds_tmpfs", MOVE_MOUNT_F_EMPTY_PATH), 0); - fd_tmp = open_tree(fd_tmpfs, "u", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + fd_tmp = sys_open_tree(fd_tmpfs, "u", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); ASSERT_GE(fd_tmp, 0); layer_fds[0] = openat(fd_tmp, "upper", O_CLOEXEC | O_DIRECTORY | O_PATH); @@ -633,25 +633,25 @@ TEST_F(set_layers_via_fds, set_layers_via_detached_mount_fds) layer_fds[1] = openat(fd_tmp, "work", O_CLOEXEC | O_DIRECTORY | O_PATH); ASSERT_GE(layer_fds[1], 0); - layer_fds[2] = open_tree(fd_tmpfs, "l1", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + layer_fds[2] = sys_open_tree(fd_tmpfs, "l1", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); ASSERT_GE(layer_fds[2], 0); - layer_fds[3] = open_tree(fd_tmpfs, "l2", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + layer_fds[3] = sys_open_tree(fd_tmpfs, "l2", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); ASSERT_GE(layer_fds[3], 0); - layer_fds[4] = open_tree(fd_tmpfs, "l3", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + layer_fds[4] = sys_open_tree(fd_tmpfs, "l3", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); ASSERT_GE(layer_fds[4], 0); - layer_fds[5] = open_tree(fd_tmpfs, "l4", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + layer_fds[5] = sys_open_tree(fd_tmpfs, "l4", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); ASSERT_GE(layer_fds[5], 0); - layer_fds[6] = open_tree(fd_tmpfs, "d1", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + layer_fds[6] = sys_open_tree(fd_tmpfs, "d1", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); ASSERT_GE(layer_fds[6], 0); - layer_fds[7] = open_tree(fd_tmpfs, "d2", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + layer_fds[7] = sys_open_tree(fd_tmpfs, "d2", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); ASSERT_GE(layer_fds[7], 0); - layer_fds[8] = open_tree(fd_tmpfs, "d3", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); + layer_fds[8] = sys_open_tree(fd_tmpfs, "d3", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC); ASSERT_GE(layer_fds[8], 0); ASSERT_EQ(close(fd_tmpfs), 0); diff --git a/tools/testing/selftests/filesystems/statmount/statmount.h b/tools/testing/selftests/filesystems/statmount/statmount.h index 99e5ad082fb1..675f7cc00076 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount.h +++ b/tools/testing/selftests/filesystems/statmount/statmount.h @@ -3,10 +3,14 @@ #ifndef __STATMOUNT_H #define __STATMOUNT_H +#include <errno.h> #include <stdint.h> +#include <stdlib.h> #include <linux/mount.h> #include <asm/unistd.h> +#define STATMOUNT_BUFSIZE (1 << 15) + #ifndef __NR_statmount #if defined __alpha__ #define __NR_statmount 567 @@ -43,19 +47,24 @@ #endif #endif -static inline int statmount(uint64_t mnt_id, uint64_t mnt_ns_id, uint64_t mask, - struct statmount *buf, size_t bufsize, +static inline int statmount(uint64_t mnt_id, uint64_t mnt_ns_id, uint32_t fd, + uint64_t mask, struct statmount *buf, size_t bufsize, unsigned int flags) { struct mnt_id_req req = { .size = MNT_ID_REQ_SIZE_VER0, - .mnt_id = mnt_id, .param = mask, }; - if (mnt_ns_id) { + if (flags & STATMOUNT_BY_FD) { req.size = MNT_ID_REQ_SIZE_VER1; - req.mnt_ns_id = mnt_ns_id; + req.mnt_fd = fd; + } else { + req.mnt_id = mnt_id; + if (mnt_ns_id) { + req.size = MNT_ID_REQ_SIZE_VER1; + req.mnt_ns_id = mnt_ns_id; + } } return syscall(__NR_statmount, &req, buf, bufsize, flags); @@ -79,4 +88,51 @@ static inline ssize_t listmount(uint64_t mnt_id, uint64_t mnt_ns_id, return syscall(__NR_listmount, &req, list, num, flags); } +static inline struct statmount *statmount_alloc(uint64_t mnt_id, uint64_t mnt_ns_id, + uint64_t mask, unsigned int flags) +{ + struct statmount *buf; + size_t bufsize = STATMOUNT_BUFSIZE; + int ret; + + for (;;) { + buf = malloc(bufsize); + if (!buf) + return NULL; + + ret = statmount(mnt_id, mnt_ns_id, 0, mask, buf, bufsize, flags); + if (ret == 0) + return buf; + + free(buf); + if (errno != EOVERFLOW) + return NULL; + + bufsize <<= 1; + } +} + +static inline struct statmount *statmount_alloc_by_fd(int fd, uint64_t mask) +{ + struct statmount *buf; + size_t bufsize = STATMOUNT_BUFSIZE; + int ret; + + for (;;) { + buf = malloc(bufsize); + if (!buf) + return NULL; + + ret = statmount(0, 0, fd, mask, buf, bufsize, STATMOUNT_BY_FD); + if (ret == 0) + return buf; + + free(buf); + if (errno != EOVERFLOW) + return NULL; + + bufsize <<= 1; + } +} + #endif /* __STATMOUNT_H */ diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test.c b/tools/testing/selftests/filesystems/statmount/statmount_test.c index 6e53430423d2..60c2c544db6a 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount_test.c +++ b/tools/testing/selftests/filesystems/statmount/statmount_test.c @@ -33,36 +33,6 @@ static const char *const known_fs[] = { "sysv", "tmpfs", "tracefs", "ubifs", "udf", "ufs", "v7", "vboxsf", "vfat", "virtiofs", "vxfs", "xenfs", "xfs", "zonefs", NULL }; -static struct statmount *statmount_alloc(uint64_t mnt_id, uint64_t mask, unsigned int flags) -{ - size_t bufsize = 1 << 15; - struct statmount *buf = NULL, *tmp = alloca(bufsize); - int tofree = 0; - int ret; - - for (;;) { - ret = statmount(mnt_id, 0, mask, tmp, bufsize, flags); - if (ret != -1) - break; - if (tofree) - free(tmp); - if (errno != EOVERFLOW) - return NULL; - bufsize <<= 1; - tofree = 1; - tmp = malloc(bufsize); - if (!tmp) - return NULL; - } - buf = malloc(tmp->size); - if (buf) - memcpy(buf, tmp, tmp->size); - if (tofree) - free(tmp); - - return buf; -} - static void write_file(const char *path, const char *val) { int fd = open(path, O_WRONLY); @@ -112,6 +82,9 @@ static void cleanup_namespace(void) { int ret; + if (f_mountinfo) + fclose(f_mountinfo); + ret = fchdir(orig_root); if (ret == -1) ksft_perror("fchdir to original root"); @@ -237,7 +210,7 @@ static void test_statmount_zero_mask(void) struct statmount sm; int ret; - ret = statmount(root_id, 0, 0, &sm, sizeof(sm), 0); + ret = statmount(root_id, 0, 0, 0, &sm, sizeof(sm), 0); if (ret == -1) { ksft_test_result_fail("statmount zero mask: %s\n", strerror(errno)); @@ -263,7 +236,7 @@ static void test_statmount_mnt_basic(void) int ret; uint64_t mask = STATMOUNT_MNT_BASIC; - ret = statmount(root_id, 0, mask, &sm, sizeof(sm), 0); + ret = statmount(root_id, 0, 0, mask, &sm, sizeof(sm), 0); if (ret == -1) { ksft_test_result_fail("statmount mnt basic: %s\n", strerror(errno)); @@ -323,7 +296,7 @@ static void test_statmount_sb_basic(void) struct statx sx; struct statfs sf; - ret = statmount(root_id, 0, mask, &sm, sizeof(sm), 0); + ret = statmount(root_id, 0, 0, mask, &sm, sizeof(sm), 0); if (ret == -1) { ksft_test_result_fail("statmount sb basic: %s\n", strerror(errno)); @@ -375,7 +348,7 @@ static void test_statmount_mnt_point(void) { struct statmount *sm; - sm = statmount_alloc(root_id, STATMOUNT_MNT_POINT, 0); + sm = statmount_alloc(root_id, 0, STATMOUNT_MNT_POINT, 0); if (!sm) { ksft_test_result_fail("statmount mount point: %s\n", strerror(errno)); @@ -405,7 +378,7 @@ static void test_statmount_mnt_root(void) assert(last_dir); last_dir++; - sm = statmount_alloc(root_id, STATMOUNT_MNT_ROOT, 0); + sm = statmount_alloc(root_id, 0, STATMOUNT_MNT_ROOT, 0); if (!sm) { ksft_test_result_fail("statmount mount root: %s\n", strerror(errno)); @@ -438,7 +411,7 @@ static void test_statmount_fs_type(void) const char *fs_type; const char *const *s; - sm = statmount_alloc(root_id, STATMOUNT_FS_TYPE, 0); + sm = statmount_alloc(root_id, 0, STATMOUNT_FS_TYPE, 0); if (!sm) { ksft_test_result_fail("statmount fs type: %s\n", strerror(errno)); @@ -467,7 +440,7 @@ static void test_statmount_mnt_opts(void) char *line = NULL; size_t len = 0; - sm = statmount_alloc(root_id, STATMOUNT_MNT_BASIC | STATMOUNT_MNT_OPTS, + sm = statmount_alloc(root_id, 0, STATMOUNT_MNT_BASIC | STATMOUNT_MNT_OPTS, 0); if (!sm) { ksft_test_result_fail("statmount mnt opts: %s\n", @@ -545,7 +518,7 @@ static void test_statmount_mnt_opts(void) return; } - ksft_test_result_fail("didnt't find mount entry\n"); + ksft_test_result_fail("didn't find mount entry\n"); free(sm); free(line); } @@ -557,7 +530,7 @@ static void test_statmount_string(uint64_t mask, size_t off, const char *name) uint32_t start, i; int ret; - sm = statmount_alloc(root_id, mask, 0); + sm = statmount_alloc(root_id, 0, mask, 0); if (!sm) { ksft_test_result_fail("statmount %s: %s\n", name, strerror(errno)); @@ -586,14 +559,14 @@ static void test_statmount_string(uint64_t mask, size_t off, const char *name) exactsize = sm->size; shortsize = sizeof(*sm) + i; - ret = statmount(root_id, 0, mask, sm, exactsize, 0); + ret = statmount(root_id, 0, 0, mask, sm, exactsize, 0); if (ret == -1) { ksft_test_result_fail("statmount exact size: %s\n", strerror(errno)); goto out; } errno = 0; - ret = statmount(root_id, 0, mask, sm, shortsize, 0); + ret = statmount(root_id, 0, 0, mask, sm, shortsize, 0); if (ret != -1 || errno != EOVERFLOW) { ksft_test_result_fail("should have failed with EOVERFLOW: %s\n", strerror(errno)); @@ -658,6 +631,226 @@ static void test_listmount_tree(void) ksft_test_result_pass("listmount tree\n"); } +static void test_statmount_by_fd(void) +{ + struct statmount *sm = NULL; + char tmpdir[] = "/statmount.fd.XXXXXX"; + const char root[] = "/test"; + char subdir[PATH_MAX], tmproot[PATH_MAX]; + int fd; + + if (!mkdtemp(tmpdir)) { + ksft_perror("mkdtemp"); + return; + } + + if (mount("statmount.test", tmpdir, "tmpfs", 0, NULL)) { + ksft_perror("mount"); + rmdir(tmpdir); + return; + } + + snprintf(subdir, PATH_MAX, "%s%s", tmpdir, root); + snprintf(tmproot, PATH_MAX, "%s/%s", tmpdir, "chroot"); + + if (mkdir(subdir, 0755)) { + ksft_perror("mkdir"); + goto err_tmpdir; + } + + if (mount(subdir, subdir, NULL, MS_BIND, 0)) { + ksft_perror("mount"); + goto err_subdir; + } + + if (mkdir(tmproot, 0755)) { + ksft_perror("mkdir"); + goto err_subdir; + } + + fd = open(subdir, O_PATH); + if (fd < 0) { + ksft_perror("open"); + goto err_tmproot; + } + + if (chroot(tmproot)) { + ksft_perror("chroot"); + goto err_fd; + } + + sm = statmount_alloc_by_fd(fd, STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT); + if (!sm) { + ksft_test_result_fail("statmount by fd failed: %s\n", strerror(errno)); + goto err_chroot; + } + + if (sm->size < sizeof(*sm)) { + ksft_test_result_fail("unexpected size: %u < %u\n", + sm->size, (uint32_t) sizeof(*sm)); + goto err_chroot; + } + + if (sm->mask & STATMOUNT_MNT_POINT) { + ksft_test_result_fail("STATMOUNT_MNT_POINT unexpectedly set in statmount\n"); + goto err_chroot; + } + + if (!(sm->mask & STATMOUNT_MNT_ROOT)) { + ksft_test_result_fail("STATMOUNT_MNT_ROOT not set in statmount\n"); + goto err_chroot; + } + + if (strcmp(root, sm->str + sm->mnt_root) != 0) { + ksft_test_result_fail("statmount returned incorrect mnt_root," + "statmount mnt_root: %s != %s\n", + sm->str + sm->mnt_root, root); + goto err_chroot; + } + + if (chroot(".")) { + ksft_perror("chroot"); + goto out; + } + + free(sm); + sm = statmount_alloc_by_fd(fd, STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT); + if (!sm) { + ksft_test_result_fail("statmount by fd failed: %s\n", strerror(errno)); + goto err_fd; + } + + if (sm->size < sizeof(*sm)) { + ksft_test_result_fail("unexpected size: %u < %u\n", + sm->size, (uint32_t) sizeof(*sm)); + goto out; + } + + if (!(sm->mask & STATMOUNT_MNT_POINT)) { + ksft_test_result_fail("STATMOUNT_MNT_POINT not set in statmount\n"); + goto out; + } + + if (!(sm->mask & STATMOUNT_MNT_ROOT)) { + ksft_test_result_fail("STATMOUNT_MNT_ROOT not set in statmount\n"); + goto out; + } + + if (strcmp(subdir, sm->str + sm->mnt_point) != 0) { + ksft_test_result_fail("statmount returned incorrect mnt_point," + "statmount mnt_point: %s != %s\n", sm->str + sm->mnt_point, subdir); + goto out; + } + + if (strcmp(root, sm->str + sm->mnt_root) != 0) { + ksft_test_result_fail("statmount returned incorrect mnt_root," + "statmount mnt_root: %s != %s\n", sm->str + sm->mnt_root, root); + goto out; + } + + ksft_test_result_pass("statmount by fd\n"); + goto out; +err_chroot: + chroot("."); +out: + free(sm); +err_fd: + close(fd); +err_tmproot: + rmdir(tmproot); +err_subdir: + umount2(subdir, MNT_DETACH); + rmdir(subdir); +err_tmpdir: + umount2(tmpdir, MNT_DETACH); + rmdir(tmpdir); +} + +static void test_statmount_by_fd_unmounted(void) +{ + const char root[] = "/test.unmounted"; + char tmpdir[] = "/statmount.fd.XXXXXX"; + char subdir[PATH_MAX]; + int fd; + struct statmount *sm = NULL; + + if (!mkdtemp(tmpdir)) { + ksft_perror("mkdtemp"); + return; + } + + if (mount("statmount.test", tmpdir, "tmpfs", 0, NULL)) { + ksft_perror("mount"); + rmdir(tmpdir); + return; + } + + snprintf(subdir, PATH_MAX, "%s%s", tmpdir, root); + + if (mkdir(subdir, 0755)) { + ksft_perror("mkdir"); + goto err_tmpdir; + } + + if (mount(subdir, subdir, 0, MS_BIND, NULL)) { + ksft_perror("mount"); + goto err_subdir; + } + + fd = open(subdir, O_PATH); + if (fd < 0) { + ksft_perror("open"); + goto err_subdir; + } + + if (umount2(tmpdir, MNT_DETACH)) { + ksft_perror("umount2"); + goto err_fd; + } + + sm = statmount_alloc_by_fd(fd, STATMOUNT_MNT_POINT | STATMOUNT_MNT_ROOT); + if (!sm) { + ksft_test_result_fail("statmount by fd unmounted: %s\n", + strerror(errno)); + goto err_sm; + } + + if (sm->size < sizeof(*sm)) { + ksft_test_result_fail("unexpected size: %u < %u\n", + sm->size, (uint32_t) sizeof(*sm)); + goto err_sm; + } + + if (sm->mask & STATMOUNT_MNT_POINT) { + ksft_test_result_fail("STATMOUNT_MNT_POINT unexpectedly set in mask\n"); + goto err_sm; + } + + if (!(sm->mask & STATMOUNT_MNT_ROOT)) { + ksft_test_result_fail("STATMOUNT_MNT_ROOT not set in mask\n"); + goto err_sm; + } + + if (strcmp(sm->str + sm->mnt_root, root) != 0) { + ksft_test_result_fail("statmount returned incorrect mnt_root," + "statmount mnt_root: %s != %s\n", + sm->str + sm->mnt_root, root); + goto err_sm; + } + + ksft_test_result_pass("statmount by fd on unmounted mount\n"); +err_sm: + free(sm); +err_fd: + close(fd); +err_subdir: + umount2(subdir, MNT_DETACH); + rmdir(subdir); +err_tmpdir: + umount2(tmpdir, MNT_DETACH); + rmdir(tmpdir); +} + #define str_off(memb) (offsetof(struct statmount, memb) / sizeof(uint32_t)) int main(void) @@ -669,14 +862,14 @@ int main(void) ksft_print_header(); - ret = statmount(0, 0, 0, NULL, 0, 0); + ret = statmount(0, 0, 0, 0, NULL, 0, 0); assert(ret == -1); if (errno == ENOSYS) ksft_exit_skip("statmount() syscall not supported\n"); setup_namespace(); - ksft_set_plan(15); + ksft_set_plan(17); test_listmount_empty_root(); test_statmount_zero_mask(); test_statmount_mnt_basic(); @@ -693,6 +886,8 @@ int main(void) test_statmount_string(all_mask, str_off(fs_type), "fs type & all"); test_listmount_tree(); + test_statmount_by_fd_unmounted(); + test_statmount_by_fd(); if (ksft_get_fail_cnt() + ksft_get_error_cnt() > 0) diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c b/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c index d56d4103182f..e500905e4c07 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c +++ b/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c @@ -34,31 +34,6 @@ static void handle_result(int ret, const char *testname) ksft_test_result_skip("%s\n", testname); } -static inline int wait_for_pid(pid_t pid) -{ - int status, ret; - -again: - ret = waitpid(pid, &status, 0); - if (ret == -1) { - if (errno == EINTR) - goto again; - - ksft_print_msg("waitpid returned -1, errno=%d\n", errno); - return -1; - } - - if (!WIFEXITED(status)) { - ksft_print_msg( - "waitpid !WIFEXITED, WIFSIGNALED=%d, WTERMSIG=%d\n", - WIFSIGNALED(status), WTERMSIG(status)); - return -1; - } - - ret = WEXITSTATUS(status); - return ret; -} - static int get_mnt_ns_id(const char *mnt_ns, uint64_t *mnt_ns_id) { int fd = open(mnt_ns, O_RDONLY); @@ -102,7 +77,7 @@ static int _test_statmount_mnt_ns_id(void) if (!root_id) return NSID_ERROR; - ret = statmount(root_id, 0, STATMOUNT_MNT_NS_ID, &sm, sizeof(sm), 0); + ret = statmount(root_id, 0, 0, STATMOUNT_MNT_NS_ID, &sm, sizeof(sm), 0); if (ret == -1) { ksft_print_msg("statmount mnt ns id: %s\n", strerror(errno)); return NSID_ERROR; @@ -128,6 +103,98 @@ static int _test_statmount_mnt_ns_id(void) return NSID_PASS; } +static int _test_statmount_mnt_ns_id_by_fd(void) +{ + struct statmount sm; + uint64_t mnt_ns_id; + int ret, fd, mounted = 1, status = NSID_ERROR; + char mnt[] = "/statmount.fd.XXXXXX"; + + ret = get_mnt_ns_id("/proc/self/ns/mnt", &mnt_ns_id); + if (ret != NSID_PASS) + return ret; + + if (!mkdtemp(mnt)) { + ksft_print_msg("statmount by fd mnt ns id mkdtemp: %s\n", strerror(errno)); + return NSID_ERROR; + } + + if (mount(mnt, mnt, NULL, MS_BIND, 0)) { + ksft_print_msg("statmount by fd mnt ns id mount: %s\n", strerror(errno)); + status = NSID_ERROR; + goto err; + } + + fd = open(mnt, O_PATH); + if (fd < 0) { + ksft_print_msg("statmount by fd mnt ns id open: %s\n", strerror(errno)); + goto err; + } + + ret = statmount(0, 0, fd, STATMOUNT_MNT_NS_ID, &sm, sizeof(sm), STATMOUNT_BY_FD); + if (ret == -1) { + ksft_print_msg("statmount mnt ns id statmount: %s\n", strerror(errno)); + status = NSID_ERROR; + goto out; + } + + if (sm.size != sizeof(sm)) { + ksft_print_msg("unexpected size: %u != %u\n", sm.size, + (uint32_t)sizeof(sm)); + status = NSID_FAIL; + goto out; + } + if (sm.mask != STATMOUNT_MNT_NS_ID) { + ksft_print_msg("statmount mnt ns id unavailable\n"); + status = NSID_SKIP; + goto out; + } + + if (sm.mnt_ns_id != mnt_ns_id) { + ksft_print_msg("unexpected mnt ns ID: 0x%llx != 0x%llx\n", + (unsigned long long)sm.mnt_ns_id, + (unsigned long long)mnt_ns_id); + status = NSID_FAIL; + goto out; + } + + mounted = 0; + if (umount2(mnt, MNT_DETACH)) { + ksft_print_msg("statmount by fd mnt ns id umount2: %s\n", strerror(errno)); + goto out; + } + + ret = statmount(0, 0, fd, STATMOUNT_MNT_NS_ID, &sm, sizeof(sm), STATMOUNT_BY_FD); + if (ret == -1) { + ksft_print_msg("statmount mnt ns id statmount: %s\n", strerror(errno)); + status = NSID_ERROR; + goto out; + } + + if (sm.size != sizeof(sm)) { + ksft_print_msg("unexpected size: %u != %u\n", sm.size, + (uint32_t)sizeof(sm)); + status = NSID_FAIL; + goto out; + } + + if (sm.mask == STATMOUNT_MNT_NS_ID) { + ksft_print_msg("unexpected STATMOUNT_MNT_NS_ID in mask\n"); + status = NSID_FAIL; + goto out; + } + + status = NSID_PASS; +out: + close(fd); + if (mounted) + umount2(mnt, MNT_DETACH); +err: + rmdir(mnt); + return status; +} + + static void test_statmount_mnt_ns_id(void) { pid_t pid; @@ -148,6 +215,9 @@ static void test_statmount_mnt_ns_id(void) if (ret != NSID_PASS) exit(ret); ret = _test_statmount_mnt_ns_id(); + if (ret != NSID_PASS) + exit(ret); + ret = _test_statmount_mnt_ns_id_by_fd(); exit(ret); } @@ -179,7 +249,7 @@ static int validate_external_listmount(pid_t pid, uint64_t child_nr_mounts) for (int i = 0; i < nr_mounts; i++) { struct statmount sm; - ret = statmount(list[i], mnt_ns_id, STATMOUNT_MNT_NS_ID, &sm, + ret = statmount(list[i], mnt_ns_id, 0, STATMOUNT_MNT_NS_ID, &sm, sizeof(sm), 0); if (ret < 0) { ksft_print_msg("statmount mnt ns id: %s\n", strerror(errno)); @@ -275,7 +345,7 @@ int main(void) int ret; ksft_print_header(); - ret = statmount(0, 0, 0, NULL, 0, 0); + ret = statmount(0, 0, 0, 0, NULL, 0, 0); assert(ret == -1); if (errno == ENOSYS) ksft_exit_skip("statmount() syscall not supported\n"); diff --git a/tools/testing/selftests/filesystems/ustat_test.c b/tools/testing/selftests/filesystems/ustat_test.c new file mode 100644 index 000000000000..d429fd18d779 --- /dev/null +++ b/tools/testing/selftests/filesystems/ustat_test.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test ustat(2): looking up superblocks by device number. + * + * ustat() resolves a device number to a mounted superblock via + * user_get_super(). Check that the device number of a mounted tmpfs (an + * anonymous device) resolves, that it stops resolving once the filesystem + * is unmounted and that bogus device numbers report EINVAL. + */ +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mount.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <unistd.h> + +#include "../kselftest_harness.h" + +/* struct ustat is not exported through UAPI, mirror include/linux/types.h. */ +struct ustat_buf { + int f_tfree; + unsigned long f_tinode; + char f_fname[6]; + char f_fpack[6]; + /* slack in case an architecture lays the struct out differently */ + char pad[64]; +}; + +#ifdef __NR_ustat + +/* + * The kernel decodes @dev with new_decode_dev(), which matches the low 32 + * bits of the st_dev encoding stat(2) returns for any major below 4096. + */ +static int sys_ustat(unsigned int dev, struct ustat_buf *buf) +{ + return syscall(__NR_ustat, dev, buf); +} + +static int write_string(const char *path, const char *string) +{ + ssize_t len = strlen(string); + int fd; + + fd = open(path, O_WRONLY); + if (fd < 0) + return -1; + if (write(fd, string, len) != len) { + close(fd); + return -1; + } + return close(fd); +} + +/* Enter namespaces in which mounting a tmpfs instance is allowed. */ +static int setup_namespaces(void) +{ + uid_t uid = getuid(); + gid_t gid = getgid(); + char map[64]; + + if (unshare(CLONE_NEWNS | (uid ? CLONE_NEWUSER : 0))) + return -1; + + if (uid) { + if (write_string("/proc/self/setgroups", "deny")) + return -1; + snprintf(map, sizeof(map), "0 %d 1", uid); + if (write_string("/proc/self/uid_map", map)) + return -1; + snprintf(map, sizeof(map), "0 %d 1", gid); + if (write_string("/proc/self/gid_map", map)) + return -1; + } + + return mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL); +} + +TEST(resolves_mounted_superblock) +{ + char dir[] = "/tmp/ustat_test.XXXXXX"; + struct ustat_buf ub; + struct stat st; + + ASSERT_NE(NULL, mkdtemp(dir)); + + if (setup_namespaces()) { + rmdir(dir); + SKIP(return, "cannot set up namespaces: %s", strerror(errno)); + } + + ASSERT_EQ(0, mount("ustat_test", dir, "tmpfs", 0, NULL)); + ASSERT_EQ(0, stat(dir, &st)); + + memset(&ub, 0xff, sizeof(ub)); + ASSERT_EQ(0, sys_ustat(st.st_dev, &ub)) + TH_LOG("ustat(%u): %s", (unsigned int)st.st_dev, + strerror(errno)); + + ASSERT_EQ(0, umount(dir)); + + /* The unmount removed the superblock, the device is gone. */ + ASSERT_EQ(-1, sys_ustat(st.st_dev, &ub)); + ASSERT_EQ(EINVAL, errno); + + rmdir(dir); +} + +TEST(bogus_device_numbers) +{ + struct ustat_buf ub; + + ASSERT_EQ(-1, sys_ustat(0, &ub)); + ASSERT_EQ(EINVAL, errno); + + /* major 4095, minor 1048575: nothing plausible lives there */ + ASSERT_EQ(-1, sys_ustat((0xfffu << 8) | 0xffu | (0xfff00u << 12), &ub)); + ASSERT_EQ(EINVAL, errno); +} + +#else /* !__NR_ustat */ + +TEST(unsupported) +{ + SKIP(return, "ustat(2) is not available on this architecture"); +} + +#endif /* __NR_ustat */ + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/utils.c b/tools/testing/selftests/filesystems/utils.c index c9dd5412b37b..d73d7d8171db 100644 --- a/tools/testing/selftests/filesystems/utils.c +++ b/tools/testing/selftests/filesystems/utils.c @@ -158,7 +158,7 @@ static int get_userns_fd_cb(void *data) _exit(0); } -static int wait_for_pid(pid_t pid) +int wait_for_pid(pid_t pid) { int status, ret; @@ -450,7 +450,7 @@ out_close: return fret; } -static int write_file(const char *path, const char *val) +int write_file(const char *path, const char *val) { int fd = open(path, O_WRONLY); size_t len = strlen(val); @@ -515,6 +515,32 @@ int setup_userns(void) return 0; } +int enter_userns(void) +{ + int ret; + char buf[32]; + uid_t uid = getuid(); + gid_t gid = getgid(); + + ret = unshare(CLONE_NEWUSER); + if (ret) + return ret; + + sprintf(buf, "0 %d 1", uid); + ret = write_file("/proc/self/uid_map", buf); + if (ret) + return ret; + ret = write_file("/proc/self/setgroups", "deny"); + if (ret) + return ret; + sprintf(buf, "0 %d 1", gid); + ret = write_file("/proc/self/gid_map", buf); + if (ret) + return ret; + + return 0; +} + /* caps_down - lower all effective caps */ int caps_down(void) { diff --git a/tools/testing/selftests/filesystems/utils.h b/tools/testing/selftests/filesystems/utils.h index 70f7ccc607f4..d03085cef5cb 100644 --- a/tools/testing/selftests/filesystems/utils.h +++ b/tools/testing/selftests/filesystems/utils.h @@ -28,6 +28,7 @@ extern int cap_down(cap_value_t down); extern bool switch_ids(uid_t uid, gid_t gid); extern int setup_userns(void); +extern int enter_userns(void); static inline bool switch_userns(int fd, uid_t uid, gid_t gid, bool drop_caps) { @@ -43,6 +44,8 @@ static inline bool switch_userns(int fd, uid_t uid, gid_t gid, bool drop_caps) return true; } +extern int wait_for_pid(pid_t pid); +extern int write_file(const char *path, const char *val); extern uint64_t get_unique_mnt_id(const char *path); #endif /* __IDMAP_UTILS_H */ diff --git a/tools/testing/selftests/filesystems/xattr/.gitignore b/tools/testing/selftests/filesystems/xattr/.gitignore new file mode 100644 index 000000000000..092d14094c0f --- /dev/null +++ b/tools/testing/selftests/filesystems/xattr/.gitignore @@ -0,0 +1,3 @@ +xattr_socket_test +xattr_sockfs_test +xattr_socket_types_test diff --git a/tools/testing/selftests/filesystems/xattr/Makefile b/tools/testing/selftests/filesystems/xattr/Makefile new file mode 100644 index 000000000000..95364ffb10e9 --- /dev/null +++ b/tools/testing/selftests/filesystems/xattr/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +CFLAGS += $(KHDR_INCLUDES) +TEST_GEN_PROGS := xattr_socket_test xattr_sockfs_test xattr_socket_types_test + +include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/xattr/xattr_socket_test.c b/tools/testing/selftests/filesystems/xattr/xattr_socket_test.c new file mode 100644 index 000000000000..fac0a4c6bc05 --- /dev/null +++ b/tools/testing/selftests/filesystems/xattr/xattr_socket_test.c @@ -0,0 +1,470 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2026 Christian Brauner <brauner@kernel.org> +/* + * Test extended attributes on path-based Unix domain sockets. + * + * Path-based Unix domain sockets are bound to a filesystem path and their + * inodes live on the underlying filesystem (e.g. tmpfs). These tests verify + * that user.* and trusted.* xattr operations work correctly on them using + * path-based syscalls (setxattr, getxattr, etc.). + * + * Covers SOCK_STREAM, SOCK_DGRAM, and SOCK_SEQPACKET socket types. + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <limits.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/un.h> +#include <sys/xattr.h> +#include <unistd.h> + +#include "../../kselftest_harness.h" + +#define TEST_XATTR_NAME "user.testattr" +#define TEST_XATTR_VALUE "testvalue" +#define TEST_XATTR_VALUE2 "newvalue" + +/* + * Fixture for path-based Unix domain socket tests. + * Creates a SOCK_STREAM socket bound to a path in /tmp (typically tmpfs). + */ +FIXTURE(xattr_socket) +{ + char socket_path[PATH_MAX]; + int sockfd; +}; + +FIXTURE_VARIANT(xattr_socket) +{ + int sock_type; + const char *name; +}; + +FIXTURE_VARIANT_ADD(xattr_socket, stream) { + .sock_type = SOCK_STREAM, + .name = "stream", +}; + +FIXTURE_VARIANT_ADD(xattr_socket, dgram) { + .sock_type = SOCK_DGRAM, + .name = "dgram", +}; + +FIXTURE_VARIANT_ADD(xattr_socket, seqpacket) { + .sock_type = SOCK_SEQPACKET, + .name = "seqpacket", +}; + +FIXTURE_SETUP(xattr_socket) +{ + struct sockaddr_un addr; + int ret; + + self->sockfd = -1; + + snprintf(self->socket_path, sizeof(self->socket_path), + "/tmp/xattr_socket_test_%s.%d", variant->name, getpid()); + unlink(self->socket_path); + + self->sockfd = socket(AF_UNIX, variant->sock_type, 0); + ASSERT_GE(self->sockfd, 0) { + TH_LOG("Failed to create socket: %s", strerror(errno)); + } + + memset(&addr, 0, sizeof(addr)); + addr.sun_family = AF_UNIX; + strncpy(addr.sun_path, self->socket_path, sizeof(addr.sun_path) - 1); + + ret = bind(self->sockfd, (struct sockaddr *)&addr, sizeof(addr)); + ASSERT_EQ(ret, 0) { + TH_LOG("Failed to bind socket to %s: %s", + self->socket_path, strerror(errno)); + } +} + +FIXTURE_TEARDOWN(xattr_socket) +{ + if (self->sockfd >= 0) + close(self->sockfd); + unlink(self->socket_path); +} + +TEST_F(xattr_socket, set_user_xattr) +{ + int ret; + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0) { + TH_LOG("setxattr failed: %s (errno=%d)", strerror(errno), errno); + } +} + +TEST_F(xattr_socket, get_user_xattr) +{ + char buf[256]; + ssize_t ret; + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0) { + TH_LOG("setxattr failed: %s", strerror(errno)); + } + + memset(buf, 0, sizeof(buf)); + ret = getxattr(self->socket_path, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, (ssize_t)strlen(TEST_XATTR_VALUE)) { + TH_LOG("getxattr returned %zd, expected %zu: %s", + ret, strlen(TEST_XATTR_VALUE), strerror(errno)); + } + ASSERT_STREQ(buf, TEST_XATTR_VALUE); +} + +TEST_F(xattr_socket, list_user_xattr) +{ + char list[1024]; + ssize_t ret; + bool found = false; + char *ptr; + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0) { + TH_LOG("setxattr failed: %s", strerror(errno)); + } + + memset(list, 0, sizeof(list)); + ret = listxattr(self->socket_path, list, sizeof(list)); + ASSERT_GT(ret, 0) { + TH_LOG("listxattr failed: %s", strerror(errno)); + } + + for (ptr = list; ptr < list + ret; ptr += strlen(ptr) + 1) { + if (strcmp(ptr, TEST_XATTR_NAME) == 0) { + found = true; + break; + } + } + ASSERT_TRUE(found) { + TH_LOG("xattr %s not found in list", TEST_XATTR_NAME); + } +} + +TEST_F(xattr_socket, remove_user_xattr) +{ + char buf[256]; + ssize_t ret; + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0) { + TH_LOG("setxattr failed: %s", strerror(errno)); + } + + ret = removexattr(self->socket_path, TEST_XATTR_NAME); + ASSERT_EQ(ret, 0) { + TH_LOG("removexattr failed: %s", strerror(errno)); + } + + ret = getxattr(self->socket_path, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENODATA) { + TH_LOG("Expected ENODATA, got %s", strerror(errno)); + } +} + +/* + * Test that xattrs persist across socket close and reopen. + * The xattr is on the filesystem inode, not the socket fd. + */ +TEST_F(xattr_socket, xattr_persistence) +{ + char buf[256]; + ssize_t ret; + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0) { + TH_LOG("setxattr failed: %s", strerror(errno)); + } + + close(self->sockfd); + self->sockfd = -1; + + memset(buf, 0, sizeof(buf)); + ret = getxattr(self->socket_path, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, (ssize_t)strlen(TEST_XATTR_VALUE)) { + TH_LOG("getxattr after close failed: %s", strerror(errno)); + } + ASSERT_STREQ(buf, TEST_XATTR_VALUE); +} + +TEST_F(xattr_socket, update_user_xattr) +{ + char buf[256]; + ssize_t ret; + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0); + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, + TEST_XATTR_VALUE2, strlen(TEST_XATTR_VALUE2), 0); + ASSERT_EQ(ret, 0); + + memset(buf, 0, sizeof(buf)); + ret = getxattr(self->socket_path, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, (ssize_t)strlen(TEST_XATTR_VALUE2)); + ASSERT_STREQ(buf, TEST_XATTR_VALUE2); +} + +TEST_F(xattr_socket, xattr_create_flag) +{ + int ret; + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0); + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, + TEST_XATTR_VALUE2, strlen(TEST_XATTR_VALUE2), XATTR_CREATE); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EEXIST); +} + +TEST_F(xattr_socket, xattr_replace_flag) +{ + int ret; + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), XATTR_REPLACE); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENODATA); +} + +TEST_F(xattr_socket, multiple_xattrs) +{ + char buf[256]; + ssize_t ret; + int i; + char name[64], value[64]; + const int num_xattrs = 5; + + for (i = 0; i < num_xattrs; i++) { + snprintf(name, sizeof(name), "user.test%d", i); + snprintf(value, sizeof(value), "value%d", i); + ret = setxattr(self->socket_path, name, value, strlen(value), 0); + ASSERT_EQ(ret, 0) { + TH_LOG("setxattr %s failed: %s", name, strerror(errno)); + } + } + + for (i = 0; i < num_xattrs; i++) { + snprintf(name, sizeof(name), "user.test%d", i); + snprintf(value, sizeof(value), "value%d", i); + memset(buf, 0, sizeof(buf)); + ret = getxattr(self->socket_path, name, buf, sizeof(buf)); + ASSERT_EQ(ret, (ssize_t)strlen(value)); + ASSERT_STREQ(buf, value); + } +} + +TEST_F(xattr_socket, xattr_empty_value) +{ + char buf[256]; + ssize_t ret; + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, "", 0, 0); + ASSERT_EQ(ret, 0); + + ret = getxattr(self->socket_path, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, 0); +} + +TEST_F(xattr_socket, xattr_get_size) +{ + ssize_t ret; + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0); + + ret = getxattr(self->socket_path, TEST_XATTR_NAME, NULL, 0); + ASSERT_EQ(ret, (ssize_t)strlen(TEST_XATTR_VALUE)); +} + +TEST_F(xattr_socket, xattr_buffer_too_small) +{ + char buf[2]; + ssize_t ret; + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0); + + ret = getxattr(self->socket_path, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ERANGE); +} + +TEST_F(xattr_socket, xattr_nonexistent) +{ + char buf[256]; + ssize_t ret; + + ret = getxattr(self->socket_path, "user.nonexistent", buf, sizeof(buf)); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENODATA); +} + +TEST_F(xattr_socket, remove_nonexistent_xattr) +{ + int ret; + + ret = removexattr(self->socket_path, "user.nonexistent"); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENODATA); +} + +TEST_F(xattr_socket, large_xattr_value) +{ + char large_value[4096]; + char read_buf[4096]; + ssize_t ret; + + memset(large_value, 'A', sizeof(large_value)); + + ret = setxattr(self->socket_path, TEST_XATTR_NAME, + large_value, sizeof(large_value), 0); + ASSERT_EQ(ret, 0) { + TH_LOG("setxattr with large value failed: %s", strerror(errno)); + } + + memset(read_buf, 0, sizeof(read_buf)); + ret = getxattr(self->socket_path, TEST_XATTR_NAME, + read_buf, sizeof(read_buf)); + ASSERT_EQ(ret, (ssize_t)sizeof(large_value)); + ASSERT_EQ(memcmp(large_value, read_buf, sizeof(large_value)), 0); +} + +/* + * Test lsetxattr/lgetxattr (don't follow symlinks). + * Socket files aren't symlinks, so this should work the same. + */ +TEST_F(xattr_socket, lsetxattr_lgetxattr) +{ + char buf[256]; + ssize_t ret; + + ret = lsetxattr(self->socket_path, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0) { + TH_LOG("lsetxattr failed: %s", strerror(errno)); + } + + memset(buf, 0, sizeof(buf)); + ret = lgetxattr(self->socket_path, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, (ssize_t)strlen(TEST_XATTR_VALUE)); + ASSERT_STREQ(buf, TEST_XATTR_VALUE); +} + +/* + * Fixture for trusted.* xattr tests. + * These require CAP_SYS_ADMIN. + */ +FIXTURE(xattr_socket_trusted) +{ + char socket_path[PATH_MAX]; + int sockfd; +}; + +FIXTURE_VARIANT(xattr_socket_trusted) +{ + int sock_type; + const char *name; +}; + +FIXTURE_VARIANT_ADD(xattr_socket_trusted, stream) { + .sock_type = SOCK_STREAM, + .name = "stream", +}; + +FIXTURE_VARIANT_ADD(xattr_socket_trusted, dgram) { + .sock_type = SOCK_DGRAM, + .name = "dgram", +}; + +FIXTURE_VARIANT_ADD(xattr_socket_trusted, seqpacket) { + .sock_type = SOCK_SEQPACKET, + .name = "seqpacket", +}; + +FIXTURE_SETUP(xattr_socket_trusted) +{ + struct sockaddr_un addr; + int ret; + + self->sockfd = -1; + + snprintf(self->socket_path, sizeof(self->socket_path), + "/tmp/xattr_socket_trusted_%s.%d", variant->name, getpid()); + unlink(self->socket_path); + + self->sockfd = socket(AF_UNIX, variant->sock_type, 0); + ASSERT_GE(self->sockfd, 0); + + memset(&addr, 0, sizeof(addr)); + addr.sun_family = AF_UNIX; + strncpy(addr.sun_path, self->socket_path, sizeof(addr.sun_path) - 1); + + ret = bind(self->sockfd, (struct sockaddr *)&addr, sizeof(addr)); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(xattr_socket_trusted) +{ + if (self->sockfd >= 0) + close(self->sockfd); + unlink(self->socket_path); +} + +TEST_F(xattr_socket_trusted, set_trusted_xattr) +{ + char buf[256]; + ssize_t len; + int ret; + + ret = setxattr(self->socket_path, "trusted.testattr", + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + if (ret == -1 && errno == EPERM) + SKIP(return, "Need CAP_SYS_ADMIN for trusted.* xattrs"); + ASSERT_EQ(ret, 0) { + TH_LOG("setxattr trusted.testattr failed: %s", strerror(errno)); + } + + memset(buf, 0, sizeof(buf)); + len = getxattr(self->socket_path, "trusted.testattr", + buf, sizeof(buf)); + ASSERT_EQ(len, (ssize_t)strlen(TEST_XATTR_VALUE)); + ASSERT_STREQ(buf, TEST_XATTR_VALUE); +} + +TEST_F(xattr_socket_trusted, get_trusted_xattr_unprivileged) +{ + char buf[256]; + ssize_t ret; + + ret = getxattr(self->socket_path, "trusted.testattr", buf, sizeof(buf)); + ASSERT_EQ(ret, -1); + ASSERT_TRUE(errno == ENODATA || errno == EPERM) { + TH_LOG("Expected ENODATA or EPERM, got %s", strerror(errno)); + } +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/xattr/xattr_socket_types_test.c b/tools/testing/selftests/filesystems/xattr/xattr_socket_types_test.c new file mode 100644 index 000000000000..bfabe91b2ed1 --- /dev/null +++ b/tools/testing/selftests/filesystems/xattr/xattr_socket_types_test.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2026 Christian Brauner <brauner@kernel.org> +/* + * Test user.* xattrs on various socket families. + * + * All socket types use sockfs for their inodes, so user.* xattrs should + * work on any socket regardless of address family. This tests AF_INET, + * AF_INET6, AF_NETLINK, AF_PACKET, and abstract namespace AF_UNIX sockets. + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <sys/un.h> +#include <sys/xattr.h> +#include <linux/netlink.h> +#include <unistd.h> + +#include "../../kselftest_harness.h" + +#define TEST_XATTR_NAME "user.testattr" +#define TEST_XATTR_VALUE "testvalue" + +FIXTURE(xattr_socket_types) +{ + int sockfd; +}; + +FIXTURE_VARIANT(xattr_socket_types) +{ + int family; + int type; + int protocol; +}; + +FIXTURE_VARIANT_ADD(xattr_socket_types, inet) { + .family = AF_INET, + .type = SOCK_STREAM, + .protocol = 0, +}; + +FIXTURE_VARIANT_ADD(xattr_socket_types, inet6) { + .family = AF_INET6, + .type = SOCK_STREAM, + .protocol = 0, +}; + +FIXTURE_VARIANT_ADD(xattr_socket_types, netlink) { + .family = AF_NETLINK, + .type = SOCK_RAW, + .protocol = NETLINK_USERSOCK, +}; + +FIXTURE_VARIANT_ADD(xattr_socket_types, packet) { + .family = AF_PACKET, + .type = SOCK_DGRAM, + .protocol = 0, +}; + +FIXTURE_SETUP(xattr_socket_types) +{ + self->sockfd = socket(variant->family, variant->type, + variant->protocol); + if (self->sockfd < 0 && + (errno == EAFNOSUPPORT || errno == EPERM || errno == EACCES)) + SKIP(return, "socket(%d, %d, %d) not available: %s", + variant->family, variant->type, variant->protocol, + strerror(errno)); + ASSERT_GE(self->sockfd, 0) { + TH_LOG("Failed to create socket(%d, %d, %d): %s", + variant->family, variant->type, variant->protocol, + strerror(errno)); + } +} + +FIXTURE_TEARDOWN(xattr_socket_types) +{ + if (self->sockfd >= 0) + close(self->sockfd); +} + +TEST_F(xattr_socket_types, set_get_list_remove) +{ + char buf[256], list[4096], *ptr; + ssize_t ret; + bool found; + + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0) { + TH_LOG("fsetxattr failed: %s", strerror(errno)); + } + + memset(buf, 0, sizeof(buf)); + ret = fgetxattr(self->sockfd, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, (ssize_t)strlen(TEST_XATTR_VALUE)); + ASSERT_STREQ(buf, TEST_XATTR_VALUE); + + memset(list, 0, sizeof(list)); + ret = flistxattr(self->sockfd, list, sizeof(list)); + ASSERT_GT(ret, 0); + found = false; + for (ptr = list; ptr < list + ret; ptr += strlen(ptr) + 1) { + if (strcmp(ptr, TEST_XATTR_NAME) == 0) + found = true; + } + ASSERT_TRUE(found); + + ret = fremovexattr(self->sockfd, TEST_XATTR_NAME); + ASSERT_EQ(ret, 0); + + ret = fgetxattr(self->sockfd, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENODATA); +} + +/* + * Test abstract namespace AF_UNIX socket. + * Abstract sockets don't have a filesystem path; their inodes live in + * sockfs so user.* xattrs should work via fsetxattr/fgetxattr. + */ +FIXTURE(xattr_abstract) +{ + int sockfd; +}; + +FIXTURE_SETUP(xattr_abstract) +{ + struct sockaddr_un addr; + char name[64]; + int ret, len; + + self->sockfd = socket(AF_UNIX, SOCK_STREAM, 0); + ASSERT_GE(self->sockfd, 0); + + len = snprintf(name, sizeof(name), "xattr_test_abstract_%d", getpid()); + + memset(&addr, 0, sizeof(addr)); + addr.sun_family = AF_UNIX; + addr.sun_path[0] = '\0'; + memcpy(&addr.sun_path[1], name, len); + + ret = bind(self->sockfd, (struct sockaddr *)&addr, + offsetof(struct sockaddr_un, sun_path) + 1 + len); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(xattr_abstract) +{ + if (self->sockfd >= 0) + close(self->sockfd); +} + +TEST_F(xattr_abstract, set_get) +{ + char buf[256]; + ssize_t ret; + + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0) { + TH_LOG("fsetxattr on abstract socket failed: %s", + strerror(errno)); + } + + memset(buf, 0, sizeof(buf)); + ret = fgetxattr(self->sockfd, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, (ssize_t)strlen(TEST_XATTR_VALUE)); + ASSERT_STREQ(buf, TEST_XATTR_VALUE); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/xattr/xattr_sockfs_test.c b/tools/testing/selftests/filesystems/xattr/xattr_sockfs_test.c new file mode 100644 index 000000000000..b4824b01a86d --- /dev/null +++ b/tools/testing/selftests/filesystems/xattr/xattr_sockfs_test.c @@ -0,0 +1,363 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2026 Christian Brauner <brauner@kernel.org> +/* + * Test extended attributes on sockfs sockets. + * + * Sockets created via socket() have their inodes in sockfs, which supports + * user.* xattrs with per-inode limits: up to 128 xattrs and 128KB total + * value size. These tests verify xattr operations via fsetxattr/fgetxattr/ + * flistxattr/fremovexattr on the socket fd, as well as limit enforcement. + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <sys/xattr.h> +#include <unistd.h> + +#include "../../kselftest_harness.h" + +#define TEST_XATTR_NAME "user.testattr" +#define TEST_XATTR_VALUE "testvalue" +#define TEST_XATTR_VALUE2 "newvalue" + +/* Per-inode limits for user.* xattrs on sockfs (from include/linux/xattr.h) */ +#define SIMPLE_XATTR_MAX_NR 128 +#define SIMPLE_XATTR_MAX_SIZE (128 << 10) /* 128 KB */ + +#ifndef XATTR_SIZE_MAX +#define XATTR_SIZE_MAX 65536 +#endif + +/* + * Fixture for sockfs socket xattr tests. + * Creates an AF_UNIX socket (lives in sockfs, not bound to any path). + */ +FIXTURE(xattr_sockfs) +{ + int sockfd; +}; + +FIXTURE_SETUP(xattr_sockfs) +{ + self->sockfd = socket(AF_UNIX, SOCK_STREAM, 0); + ASSERT_GE(self->sockfd, 0) { + TH_LOG("Failed to create socket: %s", strerror(errno)); + } +} + +FIXTURE_TEARDOWN(xattr_sockfs) +{ + if (self->sockfd >= 0) + close(self->sockfd); +} + +TEST_F(xattr_sockfs, set_get_user_xattr) +{ + char buf[256]; + ssize_t ret; + + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0) { + TH_LOG("fsetxattr failed: %s", strerror(errno)); + } + + memset(buf, 0, sizeof(buf)); + ret = fgetxattr(self->sockfd, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, (ssize_t)strlen(TEST_XATTR_VALUE)) { + TH_LOG("fgetxattr returned %zd: %s", ret, strerror(errno)); + } + ASSERT_STREQ(buf, TEST_XATTR_VALUE); +} + +/* + * Test listing xattrs on a sockfs socket. + * Should include user.* xattrs and system.sockprotoname. + */ +TEST_F(xattr_sockfs, list_user_xattr) +{ + char list[4096]; + ssize_t ret; + char *ptr; + bool found_user = false; + bool found_proto = false; + + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0) { + TH_LOG("fsetxattr failed: %s", strerror(errno)); + } + + memset(list, 0, sizeof(list)); + ret = flistxattr(self->sockfd, list, sizeof(list)); + ASSERT_GT(ret, 0) { + TH_LOG("flistxattr failed: %s", strerror(errno)); + } + + for (ptr = list; ptr < list + ret; ptr += strlen(ptr) + 1) { + if (strcmp(ptr, TEST_XATTR_NAME) == 0) + found_user = true; + if (strcmp(ptr, "system.sockprotoname") == 0) + found_proto = true; + } + ASSERT_TRUE(found_user) { + TH_LOG("user xattr not found in list"); + } + ASSERT_TRUE(found_proto) { + TH_LOG("system.sockprotoname not found in list"); + } +} + +TEST_F(xattr_sockfs, remove_user_xattr) +{ + char buf[256]; + ssize_t ret; + + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0); + + ret = fremovexattr(self->sockfd, TEST_XATTR_NAME); + ASSERT_EQ(ret, 0) { + TH_LOG("fremovexattr failed: %s", strerror(errno)); + } + + ret = fgetxattr(self->sockfd, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENODATA); +} + +TEST_F(xattr_sockfs, update_user_xattr) +{ + char buf[256]; + ssize_t ret; + + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0); + + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, + TEST_XATTR_VALUE2, strlen(TEST_XATTR_VALUE2), 0); + ASSERT_EQ(ret, 0); + + memset(buf, 0, sizeof(buf)); + ret = fgetxattr(self->sockfd, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, (ssize_t)strlen(TEST_XATTR_VALUE2)); + ASSERT_STREQ(buf, TEST_XATTR_VALUE2); +} + +TEST_F(xattr_sockfs, xattr_create_flag) +{ + int ret; + + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0); + + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, + TEST_XATTR_VALUE2, strlen(TEST_XATTR_VALUE2), + XATTR_CREATE); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EEXIST); +} + +TEST_F(xattr_sockfs, xattr_replace_flag) +{ + int ret; + + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), + XATTR_REPLACE); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENODATA); +} + +TEST_F(xattr_sockfs, get_nonexistent) +{ + char buf[256]; + ssize_t ret; + + ret = fgetxattr(self->sockfd, "user.nonexistent", buf, sizeof(buf)); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENODATA); +} + +TEST_F(xattr_sockfs, empty_value) +{ + ssize_t ret; + + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, "", 0, 0); + ASSERT_EQ(ret, 0); + + ret = fgetxattr(self->sockfd, TEST_XATTR_NAME, NULL, 0); + ASSERT_EQ(ret, 0); +} + +TEST_F(xattr_sockfs, get_size) +{ + ssize_t ret; + + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0); + + ret = fgetxattr(self->sockfd, TEST_XATTR_NAME, NULL, 0); + ASSERT_EQ(ret, (ssize_t)strlen(TEST_XATTR_VALUE)); +} + +TEST_F(xattr_sockfs, buffer_too_small) +{ + char buf[2]; + ssize_t ret; + + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0); + + ret = fgetxattr(self->sockfd, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ERANGE); +} + +/* + * Test maximum number of user.* xattrs per socket. + * The kernel enforces SIMPLE_XATTR_MAX_NR (128), so the 129th should + * fail with ENOSPC. + */ +TEST_F(xattr_sockfs, max_nr_xattrs) +{ + char name[32]; + int i, ret; + + for (i = 0; i < SIMPLE_XATTR_MAX_NR; i++) { + snprintf(name, sizeof(name), "user.test%03d", i); + ret = fsetxattr(self->sockfd, name, "v", 1, 0); + ASSERT_EQ(ret, 0) { + TH_LOG("fsetxattr %s failed at i=%d: %s", + name, i, strerror(errno)); + } + } + + ret = fsetxattr(self->sockfd, "user.overflow", "v", 1, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENOSPC) { + TH_LOG("Expected ENOSPC for xattr %d, got %s", + SIMPLE_XATTR_MAX_NR + 1, strerror(errno)); + } +} + +/* + * Test maximum total value size for user.* xattrs. + * The kernel enforces SIMPLE_XATTR_MAX_SIZE (128KB). Individual xattr + * values are limited to XATTR_SIZE_MAX (64KB) by the VFS, so we need + * at least two xattrs to hit the total limit. + */ +TEST_F(xattr_sockfs, max_xattr_size) +{ + char *value; + int ret; + + value = malloc(XATTR_SIZE_MAX); + ASSERT_NE(value, NULL); + memset(value, 'A', XATTR_SIZE_MAX); + + /* First 64KB xattr - total = 64KB */ + ret = fsetxattr(self->sockfd, "user.big1", value, XATTR_SIZE_MAX, 0); + ASSERT_EQ(ret, 0) { + TH_LOG("first large xattr failed: %s", strerror(errno)); + } + + /* Second 64KB xattr - total = 128KB (exactly at limit) */ + ret = fsetxattr(self->sockfd, "user.big2", value, XATTR_SIZE_MAX, 0); + free(value); + ASSERT_EQ(ret, 0) { + TH_LOG("second large xattr failed: %s", strerror(errno)); + } + + /* Third xattr with 1 byte - total > 128KB, should fail */ + ret = fsetxattr(self->sockfd, "user.big3", "v", 1, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENOSPC) { + TH_LOG("Expected ENOSPC when exceeding size limit, got %s", + strerror(errno)); + } +} + +/* + * Test that removing an xattr frees limit space, allowing re-addition. + */ +TEST_F(xattr_sockfs, limit_remove_readd) +{ + char name[32]; + int i, ret; + + /* Fill up to the maximum count */ + for (i = 0; i < SIMPLE_XATTR_MAX_NR; i++) { + snprintf(name, sizeof(name), "user.test%03d", i); + ret = fsetxattr(self->sockfd, name, "v", 1, 0); + ASSERT_EQ(ret, 0); + } + + /* Verify we're at the limit */ + ret = fsetxattr(self->sockfd, "user.overflow", "v", 1, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENOSPC); + + /* Remove one xattr */ + ret = fremovexattr(self->sockfd, "user.test000"); + ASSERT_EQ(ret, 0); + + /* Now we should be able to add one more */ + ret = fsetxattr(self->sockfd, "user.newattr", "v", 1, 0); + ASSERT_EQ(ret, 0) { + TH_LOG("re-add after remove failed: %s", strerror(errno)); + } +} + +/* + * Test that two different sockets have independent xattr limits. + */ +TEST_F(xattr_sockfs, limits_per_inode) +{ + char buf[256]; + int sock2; + ssize_t ret; + + sock2 = socket(AF_UNIX, SOCK_STREAM, 0); + ASSERT_GE(sock2, 0); + + /* Set xattr on first socket */ + ret = fsetxattr(self->sockfd, TEST_XATTR_NAME, + TEST_XATTR_VALUE, strlen(TEST_XATTR_VALUE), 0); + ASSERT_EQ(ret, 0); + + /* First socket's xattr should not be visible on second socket */ + ret = fgetxattr(sock2, TEST_XATTR_NAME, NULL, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENODATA); + + /* Second socket should independently accept xattrs */ + ret = fsetxattr(sock2, TEST_XATTR_NAME, + TEST_XATTR_VALUE2, strlen(TEST_XATTR_VALUE2), 0); + ASSERT_EQ(ret, 0); + + /* Verify each socket has its own value */ + memset(buf, 0, sizeof(buf)); + ret = fgetxattr(self->sockfd, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, (ssize_t)strlen(TEST_XATTR_VALUE)); + ASSERT_STREQ(buf, TEST_XATTR_VALUE); + + memset(buf, 0, sizeof(buf)); + ret = fgetxattr(sock2, TEST_XATTR_NAME, buf, sizeof(buf)); + ASSERT_EQ(ret, (ssize_t)strlen(TEST_XATTR_VALUE2)); + ASSERT_STREQ(buf, TEST_XATTR_VALUE2); + + close(sock2); +} + +TEST_HARNESS_MAIN |