@@ -31,6 +31,7 @@ map_fixed_noreplace
write_to_hugetlbfs
hmm-tests
memfd_restricted
+memfd_restricted_usermnt
memfd_secret
soft-dirty
split_huge_page_test
@@ -46,6 +46,7 @@ TEST_GEN_FILES += map_fixed_noreplace
TEST_GEN_FILES += map_hugetlb
TEST_GEN_FILES += map_populate
TEST_GEN_FILES += memfd_restricted
+TEST_GEN_FILES += memfd_restricted_usermnt
TEST_GEN_FILES += memfd_secret
TEST_GEN_FILES += migration
TEST_GEN_FILES += mlock-random-test
new file mode 100644
@@ -0,0 +1,529 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define _GNU_SOURCE /* for O_PATH */
+#define _POSIX_C_SOURCE /* for PATH_MAX */
+#include <limits.h>
+#include <sys/syscall.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+
+#include "linux/restrictedmem.h"
+
+#include "../kselftest_harness.h"
+
+static int memfd_restricted(unsigned int flags, int fd)
+{
+ return syscall(__NR_memfd_restricted, flags, fd);
+}
+
+static int get_hpage_pmd_size(void)
+{
+ FILE *fp;
+ char buf[100];
+ char *ret;
+ int size;
+
+ fp = fopen("/sys/kernel/mm/transparent_hugepage/hpage_pmd_size", "r");
+ if (!fp)
+ return -1;
+
+ ret = fgets(buf, 100, fp);
+ if (ret != buf) {
+ size = -1;
+ goto out;
+ }
+
+ if (sscanf(buf, "%d\n", &size) != 1)
+ size = -1;
+
+out:
+ fclose(fp);
+
+ return size;
+}
+
+static int write_string_to_file(const char *path, const char *string)
+{
+ FILE *fp;
+ size_t len = strlen(string);
+ int ret = -1;
+
+ fp = fopen(path, "w");
+ if (!fp)
+ return ret;
+
+ if (fwrite(string, 1, len, fp) != len)
+ goto out;
+
+ ret = 0;
+
+out:
+ fclose(fp);
+ return ret;
+}
+
+/*
+ * Expect shmem thp policy to be one of always, within_size, advise, never,
+ * deny, force
+ */
+#define POLICY_BUF_SIZE 12
+
+static bool is_valid_shmem_thp_policy(char *policy)
+{
+ if (strcmp(policy, "always") == 0)
+ return true;
+ if (strcmp(policy, "within_size") == 0)
+ return true;
+ if (strcmp(policy, "advise") == 0)
+ return true;
+ if (strcmp(policy, "never") == 0)
+ return true;
+ if (strcmp(policy, "deny") == 0)
+ return true;
+ if (strcmp(policy, "force") == 0)
+ return true;
+
+ return false;
+}
+
+static int get_shmem_thp_policy(char *policy)
+{
+ FILE *fp;
+ char buf[100];
+ char *left = NULL;
+ char *right = NULL;
+ int ret = -1;
+
+ fp = fopen("/sys/kernel/mm/transparent_hugepage/shmem_enabled", "r");
+ if (!fp)
+ return -1;
+
+ if (fgets(buf, 100, fp) != buf)
+ goto out;
+
+ /*
+ * Expect shmem_enabled to be of format like "always within_size advise
+ * [never] deny force"
+ */
+ left = memchr(buf, '[', 100);
+ if (!left)
+ goto out;
+
+ right = memchr(buf, ']', 100);
+ if (!right)
+ goto out;
+
+ memcpy(policy, left + 1, right - left - 1);
+
+ ret = !is_valid_shmem_thp_policy(policy);
+
+out:
+ fclose(fp);
+ return ret;
+}
+
+static int set_shmem_thp_policy(char *policy)
+{
+ int ret = -1;
+ /* +1 for newline */
+ char to_write[POLICY_BUF_SIZE + 1] = { 0 };
+
+ if (!is_valid_shmem_thp_policy(policy))
+ return ret;
+
+ ret = snprintf(to_write, POLICY_BUF_SIZE + 1, "%s\n", policy);
+ if (ret != strlen(policy) + 1)
+ return -1;
+
+ ret = write_string_to_file(
+ "/sys/kernel/mm/transparent_hugepage/shmem_enabled", to_write);
+
+ return ret;
+}
+
+FIXTURE(reset_shmem_enabled)
+{
+ char shmem_enabled[POLICY_BUF_SIZE];
+};
+
+FIXTURE_SETUP(reset_shmem_enabled)
+{
+ memset(self->shmem_enabled, 0, POLICY_BUF_SIZE);
+ ASSERT_EQ(get_shmem_thp_policy(self->shmem_enabled), 0);
+}
+
+FIXTURE_TEARDOWN(reset_shmem_enabled)
+{
+ ASSERT_EQ(set_shmem_thp_policy(self->shmem_enabled), 0);
+}
+
+TEST_F(reset_shmem_enabled, restrictedmem_fstat_shmem_enabled_never)
+{
+ int fd = -1;
+ struct stat stat;
+
+ ASSERT_EQ(set_shmem_thp_policy("never"), 0);
+
+ fd = memfd_restricted(0, -1);
+ ASSERT_GT(fd, 0);
+
+ ASSERT_EQ(fstat(fd, &stat), 0);
+
+ /*
+ * st_blksize is set based on the superblock's s_blocksize_bits. For
+ * shmem, this is set to PAGE_SHIFT
+ */
+ ASSERT_EQ(stat.st_blksize, getpagesize());
+
+ close(fd);
+}
+
+TEST_F(reset_shmem_enabled, restrictedmem_fstat_shmem_enabled_always)
+{
+ int fd = -1;
+ struct stat stat;
+
+ ASSERT_EQ(set_shmem_thp_policy("always"), 0);
+
+ fd = memfd_restricted(0, -1);
+ ASSERT_GT(fd, 0);
+
+ ASSERT_EQ(fstat(fd, &stat), 0);
+
+ ASSERT_EQ(stat.st_blksize, get_hpage_pmd_size());
+
+ close(fd);
+}
+
+TEST(restrictedmem_tmpfile_invalid_fd)
+{
+ int fd = memfd_restricted(MEMFD_RSTD_USERMNT, -2);
+
+ ASSERT_EQ(fd, -1);
+ ASSERT_EQ(errno, EBADF);
+}
+
+TEST(restrictedmem_tmpfile_fd_not_a_mount)
+{
+ int fd = memfd_restricted(MEMFD_RSTD_USERMNT, STDOUT_FILENO);
+
+ ASSERT_EQ(fd, -1);
+ ASSERT_EQ(errno, EINVAL);
+}
+
+TEST(restrictedmem_tmpfile_not_tmpfs_mount)
+{
+ int fd = -1;
+ int mfd = -1;
+
+ mfd = open("/proc", O_PATH);
+ ASSERT_NE(mfd, -1);
+
+ fd = memfd_restricted(MEMFD_RSTD_USERMNT, mfd);
+
+ ASSERT_EQ(fd, -1);
+ ASSERT_EQ(errno, EINVAL);
+}
+
+FIXTURE(tmpfs_sfd)
+{
+ int sfd;
+};
+
+FIXTURE_SETUP(tmpfs_sfd)
+{
+ self->sfd = fsopen("tmpfs", 0);
+ ASSERT_NE(self->sfd, -1);
+}
+
+FIXTURE_TEARDOWN(tmpfs_sfd)
+{
+ EXPECT_EQ(close(self->sfd), 0);
+}
+
+TEST_F(tmpfs_sfd, restrictedmem_fstat_tmpfs_huge_always)
+{
+ int ret = -1;
+ int fd = -1;
+ int mfd = -1;
+ struct stat stat;
+
+ fsconfig(self->sfd, FSCONFIG_SET_STRING, "huge", "always", 0);
+ fsconfig(self->sfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
+
+ mfd = fsmount(self->sfd, 0, 0);
+ ASSERT_NE(mfd, -1);
+
+ fd = memfd_restricted(MEMFD_RSTD_USERMNT, mfd);
+ ASSERT_GT(fd, 0);
+
+ /* User can close reference to mount */
+ ret = close(mfd);
+ ASSERT_EQ(ret, 0);
+
+ ret = fstat(fd, &stat);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(stat.st_blksize, get_hpage_pmd_size());
+
+ close(fd);
+}
+
+TEST_F(tmpfs_sfd, restrictedmem_fstat_tmpfs_huge_never)
+{
+ int ret = -1;
+ int fd = -1;
+ int mfd = -1;
+ struct stat stat;
+
+ fsconfig(self->sfd, FSCONFIG_SET_STRING, "huge", "never", 0);
+ fsconfig(self->sfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
+
+ mfd = fsmount(self->sfd, 0, 0);
+ ASSERT_NE(mfd, -1);
+
+ fd = memfd_restricted(MEMFD_RSTD_USERMNT, mfd);
+ ASSERT_GT(fd, 0);
+
+ /* User can close reference to mount */
+ ret = close(mfd);
+ ASSERT_EQ(ret, 0);
+
+ ret = fstat(fd, &stat);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(stat.st_blksize, getpagesize());
+
+ close(fd);
+}
+
+TEST_F(tmpfs_sfd, restrictedmem_check_mount_flags)
+{
+ int ret = -1;
+ int fd = -1;
+ int mfd = -1;
+
+ fsconfig(self->sfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
+
+ mfd = fsmount(self->sfd, 0, MOUNT_ATTR_RDONLY);
+ ASSERT_NE(mfd, -1);
+
+ fd = memfd_restricted(MEMFD_RSTD_USERMNT, mfd);
+ ASSERT_EQ(fd, -1);
+ ASSERT_EQ(errno, EROFS);
+
+ ret = close(mfd);
+ ASSERT_EQ(ret, 0);
+}
+
+TEST_F(tmpfs_sfd, restrictedmem_check_superblock_flags)
+{
+ int ret = -1;
+ int fd = -1;
+ int mfd = -1;
+
+ fsconfig(self->sfd, FSCONFIG_SET_FLAG, "ro", NULL, 0);
+ fsconfig(self->sfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
+
+ mfd = fsmount(self->sfd, 0, 0);
+ ASSERT_NE(mfd, -1);
+
+ fd = memfd_restricted(MEMFD_RSTD_USERMNT, mfd);
+ ASSERT_EQ(fd, -1);
+ ASSERT_EQ(errno, EROFS);
+
+ ret = close(mfd);
+ ASSERT_EQ(ret, 0);
+}
+
+static bool directory_exists(const char *path)
+{
+ struct stat sb;
+
+ return stat(path, &sb) == 0 && S_ISDIR(sb.st_mode);
+}
+
+FIXTURE(restrictedmem_test_mount_path)
+{
+ char *mount_path;
+};
+
+FIXTURE_SETUP(restrictedmem_test_mount_path)
+{
+ int ret = -1;
+
+ /* /tmp is an FHS-mandated world-writable directory */
+ self->mount_path = "/tmp/restrictedmem-selftest-mnt";
+
+ if (!directory_exists(self->mount_path)) {
+ ret = mkdir(self->mount_path, 0777);
+ ASSERT_EQ(ret, 0);
+ }
+}
+
+FIXTURE_TEARDOWN(restrictedmem_test_mount_path)
+{
+ int ret = -1;
+
+ if (!directory_exists(self->mount_path))
+ return;
+
+ ret = umount2(self->mount_path, MNT_FORCE);
+ EXPECT_EQ(ret, 0);
+ if (ret == -1 && errno == EINVAL)
+ fprintf(stderr, " %s was not mounted\n", self->mount_path);
+
+ ret = rmdir(self->mount_path);
+ EXPECT_EQ(ret, 0);
+ if (ret == -1)
+ fprintf(stderr, " rmdir(%s) failed: %m\n", self->mount_path);
+}
+
+/*
+ * memfd_restricted() syscall can only be used with the fd of the root of the
+ * mount. When the restrictedmem's fd is open, a user should not be able to
+ * unmount or remove the mounted directory
+ */
+TEST_F(restrictedmem_test_mount_path, restrictedmem_umount_rmdir_while_file_open)
+{
+ int ret = -1;
+ int fd = -1;
+ int mfd = -1;
+ struct stat stat;
+
+ ret = mount("name", self->mount_path, "tmpfs", 0, "huge=always");
+ ASSERT_EQ(ret, 0);
+
+ mfd = open(self->mount_path, O_PATH);
+ ASSERT_NE(mfd, -1);
+
+ fd = memfd_restricted(MEMFD_RSTD_USERMNT, mfd);
+ ASSERT_GT(fd, 0);
+
+ /* We don't need this reference to the mount anymore */
+ ret = close(mfd);
+ ASSERT_EQ(ret, 0);
+
+ /* restrictedmem's fd should still be usable */
+ ret = fstat(fd, &stat);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(stat.st_blksize, get_hpage_pmd_size());
+
+ /* User should not be able to unmount directory */
+ ret = umount2(self->mount_path, MNT_FORCE);
+ ASSERT_EQ(ret, -1);
+ ASSERT_EQ(errno, EBUSY);
+
+ ret = rmdir(self->mount_path);
+ ASSERT_EQ(ret, -1);
+ ASSERT_EQ(errno, EBUSY);
+
+ close(fd);
+}
+
+/* The fd of a file on the mount cannot be provided as mount_fd */
+TEST_F(restrictedmem_test_mount_path, restrictedmem_provide_fd_of_file)
+{
+ int ret = -1;
+ int fd = -1;
+ int ffd = -1;
+ char tmp_file_path[PATH_MAX] = { 0 };
+
+ ret = mount("name", self->mount_path, "tmpfs", 0, "huge=always");
+ ASSERT_EQ(ret, 0);
+
+ snprintf(tmp_file_path, PATH_MAX, "%s/tmp-file", self->mount_path);
+ ret = write_string_to_file(tmp_file_path, "filler\n");
+ ASSERT_EQ(ret, 0);
+
+ ffd = open(tmp_file_path, O_RDWR);
+ ASSERT_GT(ffd, 0);
+
+ fd = memfd_restricted(MEMFD_RSTD_USERMNT, ffd);
+ ASSERT_LT(fd, 0);
+ ASSERT_EQ(errno, EINVAL);
+
+ ret = close(ffd);
+ ASSERT_EQ(ret, 0);
+
+ close(fd);
+ remove(tmp_file_path);
+}
+
+/* The fd of files on the mount cannot be provided as mount_fd */
+TEST_F(restrictedmem_test_mount_path, restrictedmem_provide_fd_of_file_in_subdir)
+{
+ int ret = -1;
+ int fd = -1;
+ int ffd = -1;
+ char tmp_dir_path[PATH_MAX] = { 0 };
+ char tmp_file_path[PATH_MAX] = { 0 };
+
+ ret = mount("name", self->mount_path, "tmpfs", 0, "huge=always");
+ ASSERT_EQ(ret, 0);
+
+ snprintf(tmp_dir_path, PATH_MAX, "%s/tmp-subdir", self->mount_path);
+ ret = mkdir(tmp_dir_path, 0777);
+ ASSERT_EQ(ret, 0);
+
+ snprintf(tmp_file_path, PATH_MAX, "%s/tmp-subdir/tmp-file",
+ self->mount_path);
+ ret = write_string_to_file(tmp_file_path, "filler\n");
+ ASSERT_EQ(ret, 0);
+
+ ffd = open(tmp_file_path, O_RDWR);
+ ASSERT_NE(ffd, -1);
+
+ fd = memfd_restricted(MEMFD_RSTD_USERMNT, ffd);
+ ASSERT_LT(fd, 0);
+ ASSERT_EQ(errno, EINVAL);
+
+ ret = close(ffd);
+ ASSERT_EQ(ret, 0);
+
+ remove(tmp_file_path);
+ rmdir(tmp_dir_path);
+}
+
+/*
+ * fds representing bind mounts must represent the root of the original
+ * filesystem
+ */
+TEST_F(restrictedmem_test_mount_path, restrictedmem_provide_fd_of_original_fs)
+{
+ int ret = -1;
+ int fd = -1;
+ int mfd = -1;
+ char tmp_dir_path_0[PATH_MAX] = { 0 };
+ char tmp_dir_path_1[PATH_MAX] = { 0 };
+
+ ret = mount("name", self->mount_path, "tmpfs", 0, "huge=always");
+ ASSERT_EQ(ret, 0);
+
+ snprintf(tmp_dir_path_0, PATH_MAX, "%s/tmp-subdir-0", self->mount_path);
+ ret = mkdir(tmp_dir_path_0, 0777);
+ ASSERT_EQ(ret, 0);
+
+ snprintf(tmp_dir_path_1, PATH_MAX, "%s/tmp-subdir-1", self->mount_path);
+ ret = mkdir(tmp_dir_path_1, 0777);
+ ASSERT_EQ(ret, 0);
+
+ ret = mount(tmp_dir_path_0, tmp_dir_path_1, "tmpfs", MS_BIND, NULL);
+ ASSERT_EQ(ret, 0);
+
+ mfd = open(tmp_dir_path_1, O_PATH);
+ ASSERT_NE(mfd, -1);
+
+ fd = memfd_restricted(MEMFD_RSTD_USERMNT, mfd);
+ ASSERT_LT(fd, 0);
+ ASSERT_EQ(errno, EINVAL);
+
+ ret = close(mfd);
+ ASSERT_EQ(ret, 0);
+
+ ret = umount2(tmp_dir_path_1, MNT_FORCE);
+ ASSERT_EQ(ret, 0);
+
+ rmdir(tmp_dir_path_0);
+ rmdir(tmp_dir_path_1);
+}
+
+TEST_HARNESS_MAIN
@@ -40,6 +40,8 @@ separated by spaces:
test memadvise(2) MADV_POPULATE_{READ,WRITE} options
- memfd_restricted_
test memfd_restricted(2)
+- memfd_restricted_usermnt
+ test memfd_restricted(2)'s handling of provided userspace mounts
- memfd_secret
test memfd_secret(2)
- process_mrelease
@@ -239,6 +241,7 @@ CATEGORY="hmm" run_test ./test_hmm.sh smoke
CATEGORY="madv_populate" run_test ./madv_populate
CATEGORY="memfd_restricted" run_test ./memfd_restricted
+CATEGORY="memfd_restricted_usermnt" run_test ./memfd_restricted_usermnt
CATEGORY="memfd_secret" run_test ./memfd_secret
For memfd_restricted() calls without a userspace mount, the backing file should be the shmem mount in the kernel, and the size of backing pages should be as defined by system-wide shmem configuration. If a userspace mount is provided, the size of backing pages should be as defined in the mount. Also includes negative tests for invalid inputs, including fds representing read-only superblocks/mounts. Signed-off-by: Ackerley Tng <ackerleytng@google.com> --- tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 1 + .../selftests/mm/memfd_restricted_usermnt.c | 529 ++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 3 + 4 files changed, 534 insertions(+) create mode 100644 tools/testing/selftests/mm/memfd_restricted_usermnt.c