The new MFD_NOEXEC_SEAL and MFD_EXEC flags allows application to set
executable bit at creation time (memfd_create).
When MFD_NOEXEC_SEAL is set, memfd is created without executable bit
(mode:0666), and sealed with F_SEAL_EXEC, so it can't be chmod to be
executable (mode: 0777) after creation.
when MFD_EXEC flag is set, memfd is created with executable bit
(mode:0777), this is the same as the old behavior of memfd_create.
The new pid namespaced sysctl vm.memfd_noexec has 3 values:
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.
The sysctl allows finer control of memfd_create for old-software that
doesn't set the executable bit, for example, a container with
vm.memfd_noexec=1 means the old-software will create non-executable memfd
by default. Also, the value of memfd_noexec is passed to child namespace
at creation time. For example, if the init namespace has
vm.memfd_noexec=2, all its children namespaces will be created with 2.
[akpm@linux-foundation.org: add stub functions to fix build]
[akpm@linux-foundation.org: remove unneeded register_pid_ns_ctl_table_vm() stub, per Jeff]
[akpm@linux-foundation.org: s/pr_warn_ratelimited/pr_warn_once/, per review]
[akpm@linux-foundation.org: fix CONFIG_SYSCTL=n warning]
Link: https://lkml.kernel.org/r/20221215001205.51969-4-jeffxu@google.com
Signed-off-by: Jeff Xu <jeffxu@google.com>
Co-developed-by: Daniel Verkamp <dverkamp@chromium.org>
Signed-off-by: Daniel Verkamp <dverkamp@chromium.org>
Reported-by: kernel test robot <lkp@intel.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: David Herrmann <dh.herrmann@gmail.com>
Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jorge Lucangeli Obes <jorgelo@chromium.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
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
+#endif
+
struct pid_namespace {
struct idr idr;
struct rcu_head rcu;
struct ucounts *ucounts;
int reboot; /* group exit code if this pidns was rebooted */
struct ns_common ns;
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
+ /* sysctl for vm.memfd_noexec */
+ int memfd_noexec_scope;
+#endif
} __randomize_layout;
extern struct pid_namespace init_pid_ns;
#define MFD_CLOEXEC 0x0001U
#define MFD_ALLOW_SEALING 0x0002U
#define MFD_HUGETLB 0x0004U
+/* not executable and sealed to prevent changing to executable. */
+#define MFD_NOEXEC_SEAL 0x0008U
+/* executable */
+#define MFD_EXEC 0x0010U
/*
* Huge page size encoding when MFD_HUGETLB is specified, and a huge page
#include <linux/sched/task.h>
#include <linux/sched/signal.h>
#include <linux/idr.h>
+#include "pid_sysctl.h"
static DEFINE_MUTEX(pid_caches_mutex);
static struct kmem_cache *pid_ns_cachep;
ns->ucounts = ucounts;
ns->pid_allocated = PIDNS_ADDING;
+ initialize_memfd_noexec_scope(ns);
+
return ns;
out_free_idr:
#ifdef CONFIG_CHECKPOINT_RESTORE
register_sysctl_paths(kern_path, pid_ns_ctl_table);
#endif
+
+ register_pid_ns_sysctl_table_vm();
return 0;
}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LINUX_PID_SYSCTL_H
+#define LINUX_PID_SYSCTL_H
+
+#include <linux/pid_namespace.h>
+
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
+static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns)
+{
+ ns->memfd_noexec_scope =
+ task_active_pid_ns(current)->memfd_noexec_scope;
+}
+
+static int pid_mfd_noexec_dointvec_minmax(struct ctl_table *table,
+ int write, void *buf, size_t *lenp, loff_t *ppos)
+{
+ struct pid_namespace *ns = task_active_pid_ns(current);
+ struct ctl_table table_copy;
+
+ if (write && !ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ table_copy = *table;
+ if (ns != &init_pid_ns)
+ table_copy.data = &ns->memfd_noexec_scope;
+
+ /*
+ * set minimum to current value, the effect is only bigger
+ * value is accepted.
+ */
+ if (*(int *)table_copy.data > *(int *)table_copy.extra1)
+ table_copy.extra1 = table_copy.data;
+
+ return proc_dointvec_minmax(&table_copy, write, buf, lenp, ppos);
+}
+
+static struct ctl_table pid_ns_ctl_table_vm[] = {
+ {
+ .procname = "memfd_noexec",
+ .data = &init_pid_ns.memfd_noexec_scope,
+ .maxlen = sizeof(init_pid_ns.memfd_noexec_scope),
+ .mode = 0644,
+ .proc_handler = pid_mfd_noexec_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_TWO,
+ },
+ { }
+};
+static struct ctl_path vm_path[] = { { .procname = "vm", }, { } };
+static inline void register_pid_ns_sysctl_table_vm(void)
+{
+ register_sysctl_paths(vm_path, pid_ns_ctl_table_vm);
+}
+#else
+static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) {}
+static inline void set_memfd_noexec_scope(struct pid_namespace *ns) {}
+static inline void register_pid_ns_sysctl_table_vm(void) {}
+#endif
+
+#endif /* LINUX_PID_SYSCTL_H */
#include <linux/hugetlb.h>
#include <linux/shmem_fs.h>
#include <linux/memfd.h>
+#include <linux/pid_namespace.h>
#include <uapi/linux/memfd.h>
/*
#define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1)
#define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN)
-#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB)
+#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB | MFD_NOEXEC_SEAL | MFD_EXEC)
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;
return -EINVAL;
}
+ /* Invalid if both EXEC and NOEXEC_SEAL are set.*/
+ if ((flags & MFD_EXEC) && (flags & MFD_NOEXEC_SEAL))
+ return -EINVAL;
+
+ if (!(flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) {
+#ifdef CONFIG_SYSCTL
+ int sysctl = MEMFD_NOEXEC_SCOPE_EXEC;
+ struct pid_namespace *ns;
+
+ ns = task_active_pid_ns(current);
+ if (ns)
+ sysctl = ns->memfd_noexec_scope;
+
+ switch (sysctl) {
+ case MEMFD_NOEXEC_SCOPE_EXEC:
+ flags |= MFD_EXEC;
+ break;
+ case MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL:
+ flags |= MFD_NOEXEC_SEAL;
+ break;
+ default:
+ pr_warn_once(
+ "memfd_create(): MFD_NOEXEC_SEAL is enforced, pid=%d '%s'\n",
+ task_pid_nr(current), get_task_comm(comm, current));
+ return -EINVAL;
+ }
+#else
+ flags |= MFD_EXEC;
+#endif
+ 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));
+ }
+
/* length includes terminating zero */
len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
if (len <= 0)
file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
file->f_flags |= O_LARGEFILE;
- if (flags & MFD_ALLOW_SEALING) {
+ if (flags & MFD_NOEXEC_SEAL) {
+ struct inode *inode = file_inode(file);
+
+ inode->i_mode &= ~0111;
+ file_seals = memfd_file_seals_ptr(file);
+ *file_seals &= ~F_SEAL_SEAL;
+ *file_seals |= F_SEAL_EXEC;
+ } else if (flags & MFD_ALLOW_SEALING) {
+ /* MFD_EXEC and MFD_ALLOW_SEALING are set */
file_seals = memfd_file_seals_ptr(file);
*file_seals &= ~F_SEAL_SEAL;
}