@@ -17,18 +17,10 @@
struct fs_pin;
#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
-/*
- * sysctl for vm.memfd_noexec
- * 0: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL
- * acts like MFD_EXEC was set.
- * 1: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL
- * acts like MFD_NOEXEC_SEAL was set.
- * 2: memfd_create() without MFD_NOEXEC_SEAL will be
- * rejected.
- */
-#define MEMFD_NOEXEC_SCOPE_EXEC 0
-#define MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL 1
-#define MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED 2
+/* modes for vm.memfd_noexec sysctl */
+#define MEMFD_NOEXEC_SCOPE_EXEC 0 /* MFD_EXEC implied if unset */
+#define MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL 1 /* MFD_NOEXEC_SEAL implied if unset */
+#define MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED 2 /* same as 1, except MFD_EXEC rejected */
#endif
struct pid_namespace {
@@ -271,30 +271,22 @@ long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg)
static int check_sysctl_memfd_noexec(unsigned int *flags)
{
#ifdef CONFIG_SYSCTL
- char comm[TASK_COMM_LEN];
- int sysctl = MEMFD_NOEXEC_SCOPE_EXEC;
- struct pid_namespace *ns;
-
- ns = task_active_pid_ns(current);
- if (ns)
- sysctl = ns->memfd_noexec_scope;
+ int sysctl = task_active_pid_ns(current)->memfd_noexec_scope;
if (!(*flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) {
- if (sysctl == MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL)
+ if (sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL)
*flags |= MFD_NOEXEC_SEAL;
else
*flags |= MFD_EXEC;
}
- if (*flags & MFD_EXEC && sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED) {
- pr_warn_once(
- "memfd_create(): MFD_NOEXEC_SEAL is enforced, pid=%d '%s'\n",
- task_pid_nr(current), get_task_comm(comm, current));
-
+ if (!(*flags & MFD_NOEXEC_SEAL) && sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED) {
+ pr_err_ratelimited(
+ "%s[%d]: memfd_create() requires MFD_NOEXEC_SEAL with vm.memfd_noexec=%d\n",
+ current->comm, task_pid_nr(current), sysctl);
return -EACCES;
}
#endif
-
return 0;
}
@@ -302,7 +294,6 @@ SYSCALL_DEFINE2(memfd_create,
const char __user *, uname,
unsigned int, flags)
{
- char comm[TASK_COMM_LEN];
unsigned int *file_seals;
struct file *file;
int fd, error;
@@ -325,12 +316,13 @@ SYSCALL_DEFINE2(memfd_create,
if (!(flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) {
pr_warn_once(
- "memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL, pid=%d '%s'\n",
- task_pid_nr(current), get_task_comm(comm, current));
+ "%s[%d]: memfd_create() called without MFD_EXEC or MFD_NOEXEC_SEAL set\n",
+ current->comm, task_pid_nr(current));
}
- if (check_sysctl_memfd_noexec(&flags) < 0)
- return -EACCES;
+ error = check_sysctl_memfd_noexec(&flags);
+ if (error < 0)
+ return error;
/* length includes terminating zero */
len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
@@ -1145,11 +1145,23 @@ static void test_sysctl_child(void)
printf("%s sysctl 2\n", memfd_str);
sysctl_assert_write("2");
- mfd_fail_new("kern_memfd_sysctl_2",
- MFD_CLOEXEC | MFD_ALLOW_SEALING);
- mfd_fail_new("kern_memfd_sysctl_2_MFD_EXEC",
- MFD_CLOEXEC | MFD_EXEC);
- fd = mfd_assert_new("", 0, MFD_NOEXEC_SEAL);
+ mfd_fail_new("kern_memfd_sysctl_2_exec",
+ MFD_EXEC | MFD_CLOEXEC | MFD_ALLOW_SEALING);
+
+ fd = mfd_assert_new("kern_memfd_sysctl_2_dfl",
+ mfd_def_size,
+ MFD_CLOEXEC | MFD_ALLOW_SEALING);
+ mfd_assert_mode(fd, 0666);
+ mfd_assert_has_seals(fd, F_SEAL_EXEC);
+ mfd_fail_chmod(fd, 0777);
+ close(fd);
+
+ fd = mfd_assert_new("kern_memfd_sysctl_2_noexec_seal",
+ mfd_def_size,
+ MFD_NOEXEC_SEAL | MFD_CLOEXEC | MFD_ALLOW_SEALING);
+ mfd_assert_mode(fd, 0666);
+ mfd_assert_has_seals(fd, F_SEAL_EXEC);
+ mfd_fail_chmod(fd, 0777);
close(fd);
sysctl_fail_write("0");
Given the difficulty of auditing all of userspace to figure out whether every memfd_create() user has switched to passing MFD_EXEC and MFD_NOEXEC_SEAL flags, it seems far less distruptive to make it possible for older programs that don't make use of executable memfds to run under vm.memfd_noexec=2. Otherwise, a small dependency change can result in spurious errors. For programs that don't use executable memfds, passing MFD_NOEXEC_SEAL is functionally a no-op and thus having the same In addition, every failure under vm.memfd_noexec=2 needs to print to the kernel log so that userspace can figure out where the error came from. The concerns about pr_warn_ratelimited() spam that caused the switch to pr_warn_once()[1,2] do not apply to the vm.memfd_noexec=2 case. This is a user-visible API change, but as it allows programs to do something that would be blocked before, and the sysctl itself was broken and recently released, it seems unlikely this will cause any issues. [1]: https://lore.kernel.org/Y5yS8wCnuYGLHMj4@x1n/ [2]: https://lore.kernel.org/202212161233.85C9783FB@keescook/ Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Christian Brauner <brauner@kernel.org> Cc: stable@vger.kernel.org # v6.3+ Fixes: 105ff5339f49 ("mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC") Signed-off-by: Aleksa Sarai <cyphar@cyphar.com> --- include/linux/pid_namespace.h | 16 ++++------------ mm/memfd.c | 30 +++++++++++------------------- tools/testing/selftests/memfd/memfd_test.c | 22 +++++++++++++++++----- 3 files changed, 32 insertions(+), 36 deletions(-)