forked from mirrors/linux
105ff5339f
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>
113 lines
2.8 KiB
C
113 lines
2.8 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_PID_NS_H
|
|
#define _LINUX_PID_NS_H
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/bug.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/threads.h>
|
|
#include <linux/nsproxy.h>
|
|
#include <linux/ns_common.h>
|
|
#include <linux/idr.h>
|
|
|
|
/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
|
|
#define MAX_PID_NS_LEVEL 32
|
|
|
|
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;
|
|
unsigned int pid_allocated;
|
|
struct task_struct *child_reaper;
|
|
struct kmem_cache *pid_cachep;
|
|
unsigned int level;
|
|
struct pid_namespace *parent;
|
|
#ifdef CONFIG_BSD_PROCESS_ACCT
|
|
struct fs_pin *bacct;
|
|
#endif
|
|
struct user_namespace *user_ns;
|
|
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 PIDNS_ADDING (1U << 31)
|
|
|
|
#ifdef CONFIG_PID_NS
|
|
static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
|
|
{
|
|
if (ns != &init_pid_ns)
|
|
refcount_inc(&ns->ns.count);
|
|
return ns;
|
|
}
|
|
|
|
extern struct pid_namespace *copy_pid_ns(unsigned long flags,
|
|
struct user_namespace *user_ns, struct pid_namespace *ns);
|
|
extern void zap_pid_ns_processes(struct pid_namespace *pid_ns);
|
|
extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd);
|
|
extern void put_pid_ns(struct pid_namespace *ns);
|
|
|
|
#else /* !CONFIG_PID_NS */
|
|
#include <linux/err.h>
|
|
|
|
static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
|
|
{
|
|
return ns;
|
|
}
|
|
|
|
static inline struct pid_namespace *copy_pid_ns(unsigned long flags,
|
|
struct user_namespace *user_ns, struct pid_namespace *ns)
|
|
{
|
|
if (flags & CLONE_NEWPID)
|
|
ns = ERR_PTR(-EINVAL);
|
|
return ns;
|
|
}
|
|
|
|
static inline void put_pid_ns(struct pid_namespace *ns)
|
|
{
|
|
}
|
|
|
|
static inline void zap_pid_ns_processes(struct pid_namespace *ns)
|
|
{
|
|
BUG();
|
|
}
|
|
|
|
static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_PID_NS */
|
|
|
|
extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk);
|
|
void pidhash_init(void);
|
|
void pid_idr_init(void);
|
|
|
|
static inline bool task_is_in_init_pid_ns(struct task_struct *tsk)
|
|
{
|
|
return task_active_pid_ns(tsk) == &init_pid_ns;
|
|
}
|
|
|
|
#endif /* _LINUX_PID_NS_H */
|