Star64_linux/include/linux/seccomp.h
Christian Brauner 3a15fb6ed9 seccomp: release filter after task is fully dead
The seccomp filter used to be released in free_task() which is called
asynchronously via call_rcu() and assorted mechanisms. Since we need
to inform tasks waiting on the seccomp notifier when a filter goes empty
we will notify them as soon as a task has been marked fully dead in
release_task(). To not split seccomp cleanup into two parts, move
filter release out of free_task() and into release_task() after we've
unhashed struct task from struct pid, exited signals, and unlinked it
from the threadgroups' thread list. We'll put the empty filter
notification infrastructure into it in a follow up patch.

This also renames put_seccomp_filter() to seccomp_filter_release() which
is a more descriptive name of what we're doing here especially once
we've added the empty filter notification mechanism in there.

We're also NULL-ing the task's filter tree entrypoint which seems
cleaner than leaving a dangling pointer in there. Note that this shouldn't
need any memory barriers since we're calling this when the task is in
release_task() which means it's EXIT_DEAD. So it can't modify its seccomp
filters anymore. You can also see this from the point where we're calling
seccomp_filter_release(). It's after __exit_signal() and at this point,
tsk->sighand will already have been NULLed which is required for
thread-sync and filter installation alike.

Cc: Tycho Andersen <tycho@tycho.ws>
Cc: Kees Cook <keescook@chromium.org>
Cc: Matt Denton <mpdenton@google.com>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Jann Horn <jannh@google.com>
Cc: Chris Palmer <palmer@google.com>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Robert Sesek <rsesek@google.com>
Cc: Jeffrey Vander Stoep <jeffv@google.com>
Cc: Linux Containers <containers@lists.linux-foundation.org>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20200531115031.391515-2-christian.brauner@ubuntu.com
Signed-off-by: Kees Cook <keescook@chromium.org>
2020-07-10 16:01:51 -07:00

118 lines
3 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SECCOMP_H
#define _LINUX_SECCOMP_H
#include <uapi/linux/seccomp.h>
#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \
SECCOMP_FILTER_FLAG_LOG | \
SECCOMP_FILTER_FLAG_SPEC_ALLOW | \
SECCOMP_FILTER_FLAG_NEW_LISTENER | \
SECCOMP_FILTER_FLAG_TSYNC_ESRCH)
#ifdef CONFIG_SECCOMP
#include <linux/thread_info.h>
#include <linux/atomic.h>
#include <asm/seccomp.h>
struct seccomp_filter;
/**
* struct seccomp - the state of a seccomp'ed process
*
* @mode: indicates one of the valid values above for controlled
* system calls available to a process.
* @filter: must always point to a valid seccomp-filter or NULL as it is
* accessed without locking during system call entry.
*
* @filter must only be accessed from the context of current as there
* is no read locking.
*/
struct seccomp {
int mode;
atomic_t filter_count;
struct seccomp_filter *filter;
};
#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
extern int __secure_computing(const struct seccomp_data *sd);
static inline int secure_computing(void)
{
if (unlikely(test_thread_flag(TIF_SECCOMP)))
return __secure_computing(NULL);
return 0;
}
#else
extern void secure_computing_strict(int this_syscall);
#endif
extern long prctl_get_seccomp(void);
extern long prctl_set_seccomp(unsigned long, void __user *);
static inline int seccomp_mode(struct seccomp *s)
{
return s->mode;
}
#else /* CONFIG_SECCOMP */
#include <linux/errno.h>
struct seccomp { };
struct seccomp_filter { };
#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
static inline int secure_computing(void) { return 0; }
#else
static inline void secure_computing_strict(int this_syscall) { return; }
#endif
static inline long prctl_get_seccomp(void)
{
return -EINVAL;
}
static inline long prctl_set_seccomp(unsigned long arg2, char __user *arg3)
{
return -EINVAL;
}
static inline int seccomp_mode(struct seccomp *s)
{
return SECCOMP_MODE_DISABLED;
}
#endif /* CONFIG_SECCOMP */
#ifdef CONFIG_SECCOMP_FILTER
extern void seccomp_filter_release(struct task_struct *tsk);
extern void get_seccomp_filter(struct task_struct *tsk);
#else /* CONFIG_SECCOMP_FILTER */
static inline void seccomp_filter_release(struct task_struct *tsk)
{
return;
}
static inline void get_seccomp_filter(struct task_struct *tsk)
{
return;
}
#endif /* CONFIG_SECCOMP_FILTER */
#if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE)
extern long seccomp_get_filter(struct task_struct *task,
unsigned long filter_off, void __user *data);
extern long seccomp_get_metadata(struct task_struct *task,
unsigned long filter_off, void __user *data);
#else
static inline long seccomp_get_filter(struct task_struct *task,
unsigned long n, void __user *data)
{
return -EINVAL;
}
static inline long seccomp_get_metadata(struct task_struct *task,
unsigned long filter_off,
void __user *data)
{
return -EINVAL;
}
#endif /* CONFIG_SECCOMP_FILTER && CONFIG_CHECKPOINT_RESTORE */
#endif /* _LINUX_SECCOMP_H */