According to the test environment, the mount point of the test's working directory may be shared or not, which changes the visibility of the nested "tmp" mount point for the test's parent process calling umount("tmp").

This was spotted while running tests in containers [1], where mount points are private.

Cc: Günther Noack gnoack@google.com Cc: Shuah Khan skhan@linuxfoundation.org Link: https://github.com/landlock-lsm/landlock-test-tools/pull/4 [1] Fixes: 41cca0542d7c ("selftests/harness: Fix TEST_F()'s vfork handling") Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Mickaël Salaün mic@digikod.net Link: https://lore.kernel.org/r/20240511171445.904356-3-mic@digikod.net ---

Changes since v1: * Update commit description. --- tools/testing/selftests/landlock/fs_test.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 9a6036fbf289..46b9effd53e4 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -293,7 +293,15 @@ static void prepare_layout(struct __test_metadata *const _metadata) static void cleanup_layout(struct __test_metadata *const _metadata) { set_cap(_metadata, CAP_SYS_ADMIN); - EXPECT_EQ(0, umount(TMP_DIR)); + if (umount(TMP_DIR)) { + /* + * According to the test environment, the mount point of the + * current directory may be shared or not, which changes the + * visibility of the nested TMP_DIR mount point for the test's + * parent process doing this cleanup. + */ + ASSERT_EQ(EINVAL, errno); + } clear_cap(_metadata, CAP_SYS_ADMIN); EXPECT_EQ(0, remove_path(TMP_DIR)); }

Fix a race condition when running several FIXTURE_TEARDOWN() managing the same resource. This fixes a race condition in the Landlock file system tests when creating or unmounting the same directory.

Using clone3() with CLONE_VFORK guarantees that the child and grandchild test processes are sequentially scheduled. This is implemented with a new clone3_vfork() helper replacing the fork() call.

This avoids triggering this error in __wait_for_test(): Test ended in some other way [127]

Cc: Christian Brauner brauner@kernel.org Cc: David S. Miller davem@davemloft.net Cc: Günther Noack gnoack@google.com Cc: Jakub Kicinski kuba@kernel.org Cc: Mark Brown broonie@kernel.org Cc: Shuah Khan shuah@kernel.org Cc: Will Drewry wad@chromium.org Fixes: 41cca0542d7c ("selftests/harness: Fix TEST_F()'s vfork handling") Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Mickaël Salaün mic@digikod.net Link: https://lore.kernel.org/r/20240511171445.904356-5-mic@digikod.net ---

Changes since v2: * Replace __attribute__((__unused__)) with inline for clone3_vfork() (suggested by Kees and Jakub) --- tools/testing/selftests/kselftest_harness.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 55699a762c45..9d7178a71c2c 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -66,6 +66,8 @@ #include <sys/wait.h> #include <unistd.h> #include <setjmp.h> +#include <syscall.h> +#include <linux/sched.h>

#include "kselftest.h"

@@ -80,6 +82,17 @@ # define TH_LOG_ENABLED 1 #endif

+/* Wait for the child process to end but without sharing memory mapping. */ +static inline pid_t clone3_vfork(void) +{ + struct clone_args args = { + .flags = CLONE_VFORK, + .exit_signal = SIGCHLD, + }; + + return syscall(__NR_clone3, &args, sizeof(args)); +} + /** * TH_LOG() * @@ -1183,7 +1196,7 @@ void __run_test(struct __fixture_metadata *f, fflush(stdout); fflush(stderr);

- t->pid = fork(); + t->pid = clone3_vfork(); if (t->pid < 0) { ksft_print_msg("ERROR SPAWNING TEST CHILD\n"); t->exit_code = KSFT_FAIL;

Do not allocate self->dir_path in the test process because this would not be visible in the FIXTURE_TEARDOWN() process when relying on fork()/clone3() instead of vfork().

This change is required for a following commit removing vfork() call to not break the layout3_fs.* test cases.

Cc: Günther Noack gnoack@google.com Cc: Shuah Khan skhan@linuxfoundation.org Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Mickaël Salaün mic@digikod.net Link: https://lore.kernel.org/r/20240511171445.904356-6-mic@digikod.net ---

Changes since v1: * Extract change from a bigger patch (suggested by Kees). --- tools/testing/selftests/landlock/fs_test.c | 57 +++++++++++++--------- 1 file changed, 35 insertions(+), 22 deletions(-)

diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 46b9effd53e4..1e2cffde02b5 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -9,6 +9,7 @@

#define _GNU_SOURCE #include <fcntl.h> +#include <libgen.h> #include <linux/landlock.h> #include <linux/magic.h> #include <sched.h> @@ -4624,7 +4625,6 @@ FIXTURE(layout3_fs) { bool has_created_dir; bool has_created_file; - char *dir_path; bool skip_test; };

@@ -4683,11 +4683,24 @@ FIXTURE_VARIANT_ADD(layout3_fs, hostfs) { .cwd_fs_magic = HOSTFS_SUPER_MAGIC, };

+static char *dirname_alloc(const char *path) +{ + char *dup; + + if (!path) + return NULL; + + dup = strdup(path); + if (!dup) + return NULL; + + return dirname(dup); +} + FIXTURE_SETUP(layout3_fs) { struct stat statbuf; - const char *slash; - size_t dir_len; + char *dir_path = dirname_alloc(variant->file_path);

if (!supports_filesystem(variant->mnt.type) || !cwd_matches_fs(variant->cwd_fs_magic)) { @@ -4697,25 +4710,15 @@ FIXTURE_SETUP(layout3_fs)

_metadata->teardown_parent = true;

- slash = strrchr(variant->file_path, '/'); - ASSERT_NE(slash, NULL); - dir_len = (size_t)slash - (size_t)variant->file_path; - ASSERT_LT(0, dir_len); - self->dir_path = malloc(dir_len + 1); - self->dir_path[dir_len] = '\0'; - strncpy(self->dir_path, variant->file_path, dir_len); - prepare_layout_opt(_metadata, &variant->mnt);

/* Creates directory when required. */ - if (stat(self->dir_path, &statbuf)) { + if (stat(dir_path, &statbuf)) { set_cap(_metadata, CAP_DAC_OVERRIDE); - EXPECT_EQ(0, mkdir(self->dir_path, 0700)) + EXPECT_EQ(0, mkdir(dir_path, 0700)) { TH_LOG("Failed to create directory "%s": %s", - self->dir_path, strerror(errno)); - free(self->dir_path); - self->dir_path = NULL; + dir_path, strerror(errno)); } self->has_created_dir = true; clear_cap(_metadata, CAP_DAC_OVERRIDE); @@ -4736,6 +4739,8 @@ FIXTURE_SETUP(layout3_fs) self->has_created_file = true; clear_cap(_metadata, CAP_DAC_OVERRIDE); } + + free(dir_path); }

FIXTURE_TEARDOWN(layout3_fs) @@ -4754,16 +4759,17 @@ FIXTURE_TEARDOWN(layout3_fs) }

if (self->has_created_dir) { + char *dir_path = dirname_alloc(variant->file_path); + set_cap(_metadata, CAP_DAC_OVERRIDE); /* * Don't check for error because the directory might already * have been removed (cf. release_inode test). */ - rmdir(self->dir_path); + rmdir(dir_path); clear_cap(_metadata, CAP_DAC_OVERRIDE); + free(dir_path); } - free(self->dir_path); - self->dir_path = NULL;

cleanup_layout(_metadata); } @@ -4830,7 +4836,10 @@ TEST_F_FORK(layout3_fs, tag_inode_dir_mnt)

TEST_F_FORK(layout3_fs, tag_inode_dir_child) { - layer3_fs_tag_inode(_metadata, self, variant, self->dir_path); + char *dir_path = dirname_alloc(variant->file_path); + + layer3_fs_tag_inode(_metadata, self, variant, dir_path); + free(dir_path); }

TEST_F_FORK(layout3_fs, tag_inode_file) @@ -4857,9 +4866,13 @@ TEST_F_FORK(layout3_fs, release_inodes) if (self->has_created_file) EXPECT_EQ(0, remove_path(variant->file_path));

- if (self->has_created_dir) + if (self->has_created_dir) { + char *dir_path = dirname_alloc(variant->file_path); + /* Don't check for error because of cgroup specificities. */ - remove_path(self->dir_path); + remove_path(dir_path); + free(dir_path); + }

ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_DIR, layer1);

Replace a wrong EXPECT_GT(self->child_pid_exited, 0) with EXPECT_GE(), which will be actually tested on the parent and child sides with a following commit.

Cc: Shuah Khan skhan@linuxfoundation.org Reviewed-by: Kees Cook keescook@chromium.org Reviewed-by: Christian Brauner brauner@kernel.org Signed-off-by: Mickaël Salaün mic@digikod.net Link: https://lore.kernel.org/r/20240511171445.904356-8-mic@digikod.net ---

Changes since v1: * Extract change from a bigger patch (suggested by Kees). --- tools/testing/selftests/pidfd/pidfd_setns_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c index 6e2f2cd400ca..47746b0c6acd 100644 --- a/tools/testing/selftests/pidfd/pidfd_setns_test.c +++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c @@ -158,7 +158,7 @@ FIXTURE_SETUP(current_nsset) /* Create task that exits right away. */ self->child_pid_exited = create_child(&self->child_pidfd_exited, CLONE_NEWUSER | CLONE_NEWNET); - EXPECT_GT(self->child_pid_exited, 0); + EXPECT_GE(self->child_pid_exited, 0);

if (self->child_pid_exited == 0) _exit(EXIT_SUCCESS);

Setting the time namespace with CLONE_NEWTIME returns -EUSERS if the calling thread shares memory with another thread (because of the shared vDSO), which is the case when it is created with vfork().

Fix pidfd_setns_test by replacing test harness's vfork() call with a clone3() call with CLONE_VFORK, and an explicit sharing of the _metadata and self objects.

Replace _metadata->teardown_parent with a new FIXTURE_TEARDOWN_PARENT() helper that can replace FIXTURE_TEARDOWN(). This is a cleaner approach and it enables to selectively share the fixture data between the child process running tests and the parent process running the fixture teardown. This also avoids updating several tests to not rely on the self object's copy-on-write property (e.g. storing the returned value of a fork() call).

Cc: Christian Brauner brauner@kernel.org Cc: David S. Miller davem@davemloft.net Cc: Günther Noack gnoack@google.com Cc: Jakub Kicinski kuba@kernel.org Cc: Mark Brown broonie@kernel.org Cc: Shuah Khan shuah@kernel.org Cc: Will Drewry wad@chromium.org Reported-by: kernel test robot oliver.sang@intel.com Closes: https://lore.kernel.org/oe-lkp/202403291015.1fcfa957-oliver.sang@intel.com Fixes: 0710a1a73fb4 ("selftests/harness: Merge TEST_F_FORK() into TEST_F()") Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Mickaël Salaün mic@digikod.net Link: https://lore.kernel.org/r/20240511171445.904356-10-mic@digikod.net ---

Changes since v1: * Split changes (suggested by Kees). * Improve documentation. * Remove the static fixture_name##_teardown_parent initialisation to false (as suggested by checkpatch.pl). --- tools/testing/selftests/kselftest_harness.h | 66 ++++++++++++++++----- tools/testing/selftests/landlock/fs_test.c | 16 ++--- 2 files changed, 57 insertions(+), 25 deletions(-)

diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 28415798fa60..cbedb4a6cf7b 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -294,6 +294,32 @@ static inline pid_t clone3_vfork(void) * A bare "return;" statement may be used to return early. */ #define FIXTURE_TEARDOWN(fixture_name) \ + static const bool fixture_name##_teardown_parent; \ + __FIXTURE_TEARDOWN(fixture_name) + +/** + * FIXTURE_TEARDOWN_PARENT() + * *_metadata* is included so that EXPECT_*, ASSERT_* etc. work correctly. + * + * @fixture_name: fixture name + * + * .. code-block:: c + * + * FIXTURE_TEARDOWN_PARENT(fixture_name) { implementation } + * + * Same as FIXTURE_TEARDOWN() but run this code in a parent process. This + * enables the test process to drop its privileges without impacting the + * related FIXTURE_TEARDOWN_PARENT() (e.g. to remove files from a directory + * where write access was dropped). + * + * To make it possible for the parent process to use *self*, share (MAP_SHARED) + * the fixture data between all forked processes. + */ +#define FIXTURE_TEARDOWN_PARENT(fixture_name) \ + static const bool fixture_name##_teardown_parent = true; \ + __FIXTURE_TEARDOWN(fixture_name) + +#define __FIXTURE_TEARDOWN(fixture_name) \ void fixture_name##_teardown( \ struct __test_metadata __attribute__((unused)) *_metadata, \ FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \ @@ -368,10 +394,11 @@ static inline pid_t clone3_vfork(void) * Very similar to TEST() except that *self* is the setup instance of fixture's * datatype exposed for use by the implementation. * - * The @test_name code is run in a separate process sharing the same memory - * (i.e. vfork), which means that the test process can update its privileges - * without impacting the related FIXTURE_TEARDOWN() (e.g. to remove files from - * a directory where write access was dropped). + * The _metadata object is shared (MAP_SHARED) with all the potential forked + * processes, which enables them to use EXCEPT_*() and ASSERT_*(). + * + * The *self* object is only shared with the potential forked processes if + * FIXTURE_TEARDOWN_PARENT() is used instead of FIXTURE_TEARDOWN(). */ #define TEST_F(fixture_name, test_name) \ __TEST_F_IMPL(fixture_name, test_name, -1, TEST_TIMEOUT_DEFAULT) @@ -392,39 +419,49 @@ static inline pid_t clone3_vfork(void) struct __fixture_variant_metadata *variant) \ { \ /* fixture data is alloced, setup, and torn down per call. */ \ - FIXTURE_DATA(fixture_name) self; \ + FIXTURE_DATA(fixture_name) self_private, *self = NULL; \ pid_t child = 1; \ int status = 0; \ /* Makes sure there is only one teardown, even when child forks again. */ \ bool *teardown = mmap(NULL, sizeof(*teardown), \ PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); \ *teardown = false; \ - memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \ + if (sizeof(*self) > 0) { \ + if (fixture_name##_teardown_parent) { \ + self = mmap(NULL, sizeof(*self), PROT_READ | PROT_WRITE, \ + MAP_SHARED | MAP_ANONYMOUS, -1, 0); \ + } else { \ + memset(&self_private, 0, sizeof(self_private)); \ + self = &self_private; \ + } \ + } \ if (setjmp(_metadata->env) == 0) { \ - /* Use the same _metadata. */ \ - child = vfork(); \ + /* _metadata and potentially self are shared with all forks. */ \ + child = clone3_vfork(); \ if (child == 0) { \ - fixture_name##_setup(_metadata, &self, variant->data); \ + fixture_name##_setup(_metadata, self, variant->data); \ /* Let setup failure terminate early. */ \ if (_metadata->exit_code) \ _exit(0); \ _metadata->setup_completed = true; \ - fixture_name##_##test_name(_metadata, &self, variant->data); \ + fixture_name##_##test_name(_metadata, self, variant->data); \ } else if (child < 0 || child != waitpid(child, &status, 0)) { \ ksft_print_msg("ERROR SPAWNING TEST GRANDCHILD\n"); \ _metadata->exit_code = KSFT_FAIL; \ } \ } \ if (child == 0) { \ - if (_metadata->setup_completed && !_metadata->teardown_parent && \ + if (_metadata->setup_completed && !fixture_name##_teardown_parent && \ __sync_bool_compare_and_swap(teardown, false, true)) \ - fixture_name##_teardown(_metadata, &self, variant->data); \ + fixture_name##_teardown(_metadata, self, variant->data); \ _exit(0); \ } \ - if (_metadata->setup_completed && _metadata->teardown_parent && \ + if (_metadata->setup_completed && fixture_name##_teardown_parent && \ __sync_bool_compare_and_swap(teardown, false, true)) \ - fixture_name##_teardown(_metadata, &self, variant->data); \ + fixture_name##_teardown(_metadata, self, variant->data); \ munmap(teardown, sizeof(*teardown)); \ + if (self && fixture_name##_teardown_parent) \ + munmap(self, sizeof(*self)); \ if (!WIFEXITED(status) && WIFSIGNALED(status)) \ /* Forward signal to __wait_for_test(). */ \ kill(getpid(), WTERMSIG(status)); \ @@ -898,7 +935,6 @@ struct __test_metadata { bool timed_out; /* did this test timeout instead of exiting? */ bool aborted; /* stopped test due to failed ASSERT */ bool setup_completed; /* did setup finish? */ - bool teardown_parent; /* run teardown in a parent process */ jmp_buf env; /* for exiting out of test early */ struct __test_results *results; struct __test_metadata *prev, *next; diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 1e2cffde02b5..27744524df51 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -286,8 +286,6 @@ static void prepare_layout_opt(struct __test_metadata *const _metadata,

static void prepare_layout(struct __test_metadata *const _metadata) { - _metadata->teardown_parent = true; - prepare_layout_opt(_metadata, &mnt_tmp); }

@@ -316,7 +314,7 @@ FIXTURE_SETUP(layout0) prepare_layout(_metadata); }

-FIXTURE_TEARDOWN(layout0) +FIXTURE_TEARDOWN_PARENT(layout0) { cleanup_layout(_metadata); } @@ -379,7 +377,7 @@ FIXTURE_SETUP(layout1) create_layout1(_metadata); }

-FIXTURE_TEARDOWN(layout1) +FIXTURE_TEARDOWN_PARENT(layout1) { remove_layout1(_metadata);

@@ -3692,7 +3690,7 @@ FIXTURE_SETUP(ftruncate) create_file(_metadata, file1_s1d1); }

-FIXTURE_TEARDOWN(ftruncate) +FIXTURE_TEARDOWN_PARENT(ftruncate) { EXPECT_EQ(0, remove_path(file1_s1d1)); cleanup_layout(_metadata); @@ -3870,7 +3868,7 @@ FIXTURE_SETUP(layout1_bind) clear_cap(_metadata, CAP_SYS_ADMIN); }

-FIXTURE_TEARDOWN(layout1_bind) +FIXTURE_TEARDOWN_PARENT(layout1_bind) { /* umount(dir_s2d2)) is handled by namespace lifetime. */

@@ -4275,7 +4273,7 @@ FIXTURE_SETUP(layout2_overlay) clear_cap(_metadata, CAP_SYS_ADMIN); }

-FIXTURE_TEARDOWN(layout2_overlay) +FIXTURE_TEARDOWN_PARENT(layout2_overlay) { if (self->skip_test) SKIP(return, "overlayfs is not supported (teardown)"); @@ -4708,8 +4706,6 @@ FIXTURE_SETUP(layout3_fs) SKIP(return, "this filesystem is not supported (setup)"); }

- _metadata->teardown_parent = true; - prepare_layout_opt(_metadata, &variant->mnt);

/* Creates directory when required. */ @@ -4743,7 +4739,7 @@ FIXTURE_SETUP(layout3_fs) free(dir_path); }

-FIXTURE_TEARDOWN(layout3_fs) +FIXTURE_TEARDOWN_PARENT(layout3_fs) { if (self->skip_test) SKIP(return, "this filesystem is not supported (teardown)");