2017-11-01 22:08:43 +08:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
|
2012-10-13 17:46:48 +08:00
|
|
|
#ifndef _UAPI_LINUX_SECCOMP_H
|
|
|
|
|
#define _UAPI_LINUX_SECCOMP_H
|
|
|
|
|
|
|
|
|
|
#include <linux/compiler.h>
|
|
|
|
|
#include <linux/types.h>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/* Valid values for seccomp.mode and prctl(PR_SET_SECCOMP, <mode>) */
|
|
|
|
|
#define SECCOMP_MODE_DISABLED 0 /* seccomp is not in use. */
|
|
|
|
|
#define SECCOMP_MODE_STRICT 1 /* uses hard-coded filter. */
|
|
|
|
|
#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */
|
|
|
|
|
|
2014-06-26 07:08:24 +08:00
|
|
|
/* Valid operations for seccomp syscall. */
|
2017-08-11 12:33:53 +08:00
|
|
|
#define SECCOMP_SET_MODE_STRICT 0
|
|
|
|
|
#define SECCOMP_SET_MODE_FILTER 1
|
|
|
|
|
#define SECCOMP_GET_ACTION_AVAIL 2
|
seccomp: add a return code to trap to userspace
This patch introduces a means for syscalls matched in seccomp to notify
some other task that a particular filter has been triggered.
The motivation for this is primarily for use with containers. For example,
if a container does an init_module(), we obviously don't want to load this
untrusted code, which may be compiled for the wrong version of the kernel
anyway. Instead, we could parse the module image, figure out which module
the container is trying to load and load it on the host.
As another example, containers cannot mount() in general since various
filesystems assume a trusted image. However, if an orchestrator knows that
e.g. a particular block device has not been exposed to a container for
writing, it want to allow the container to mount that block device (that
is, handle the mount for it).
This patch adds functionality that is already possible via at least two
other means that I know about, both of which involve ptrace(): first, one
could ptrace attach, and then iterate through syscalls via PTRACE_SYSCALL.
Unfortunately this is slow, so a faster version would be to install a
filter that does SECCOMP_RET_TRACE, which triggers a PTRACE_EVENT_SECCOMP.
Since ptrace allows only one tracer, if the container runtime is that
tracer, users inside the container (or outside) trying to debug it will not
be able to use ptrace, which is annoying. It also means that older
distributions based on Upstart cannot boot inside containers using ptrace,
since upstart itself uses ptrace to monitor services while starting.
The actual implementation of this is fairly small, although getting the
synchronization right was/is slightly complex.
Finally, it's worth noting that the classic seccomp TOCTOU of reading
memory data from the task still applies here, but can be avoided with
careful design of the userspace handler: if the userspace handler reads all
of the task memory that is necessary before applying its security policy,
the tracee's subsequent memory edits will not be read by the tracer.
Signed-off-by: Tycho Andersen <tycho@tycho.ws>
CC: Kees Cook <keescook@chromium.org>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Oleg Nesterov <oleg@redhat.com>
CC: Eric W. Biederman <ebiederm@xmission.com>
CC: "Serge E. Hallyn" <serge@hallyn.com>
Acked-by: Serge Hallyn <serge@hallyn.com>
CC: Christian Brauner <christian@brauner.io>
CC: Tyler Hicks <tyhicks@canonical.com>
CC: Akihiro Suda <suda.akihiro@lab.ntt.co.jp>
Signed-off-by: Kees Cook <keescook@chromium.org>
2018-12-10 02:24:13 +08:00
|
|
|
#define SECCOMP_GET_NOTIF_SIZES 3
|
2014-06-26 07:08:24 +08:00
|
|
|
|
2014-06-05 15:23:17 +08:00
|
|
|
/* Valid flags for SECCOMP_SET_MODE_FILTER */
|
seccomp: add a return code to trap to userspace
This patch introduces a means for syscalls matched in seccomp to notify
some other task that a particular filter has been triggered.
The motivation for this is primarily for use with containers. For example,
if a container does an init_module(), we obviously don't want to load this
untrusted code, which may be compiled for the wrong version of the kernel
anyway. Instead, we could parse the module image, figure out which module
the container is trying to load and load it on the host.
As another example, containers cannot mount() in general since various
filesystems assume a trusted image. However, if an orchestrator knows that
e.g. a particular block device has not been exposed to a container for
writing, it want to allow the container to mount that block device (that
is, handle the mount for it).
This patch adds functionality that is already possible via at least two
other means that I know about, both of which involve ptrace(): first, one
could ptrace attach, and then iterate through syscalls via PTRACE_SYSCALL.
Unfortunately this is slow, so a faster version would be to install a
filter that does SECCOMP_RET_TRACE, which triggers a PTRACE_EVENT_SECCOMP.
Since ptrace allows only one tracer, if the container runtime is that
tracer, users inside the container (or outside) trying to debug it will not
be able to use ptrace, which is annoying. It also means that older
distributions based on Upstart cannot boot inside containers using ptrace,
since upstart itself uses ptrace to monitor services while starting.
The actual implementation of this is fairly small, although getting the
synchronization right was/is slightly complex.
Finally, it's worth noting that the classic seccomp TOCTOU of reading
memory data from the task still applies here, but can be avoided with
careful design of the userspace handler: if the userspace handler reads all
of the task memory that is necessary before applying its security policy,
the tracee's subsequent memory edits will not be read by the tracer.
Signed-off-by: Tycho Andersen <tycho@tycho.ws>
CC: Kees Cook <keescook@chromium.org>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Oleg Nesterov <oleg@redhat.com>
CC: Eric W. Biederman <ebiederm@xmission.com>
CC: "Serge E. Hallyn" <serge@hallyn.com>
Acked-by: Serge Hallyn <serge@hallyn.com>
CC: Christian Brauner <christian@brauner.io>
CC: Tyler Hicks <tyhicks@canonical.com>
CC: Akihiro Suda <suda.akihiro@lab.ntt.co.jp>
Signed-off-by: Kees Cook <keescook@chromium.org>
2018-12-10 02:24:13 +08:00
|
|
|
#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0)
|
|
|
|
|
#define SECCOMP_FILTER_FLAG_LOG (1UL << 1)
|
|
|
|
|
#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)
|
|
|
|
|
#define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3)
|
2014-06-05 15:23:17 +08:00
|
|
|
|
2012-10-13 17:46:48 +08:00
|
|
|
/*
|
|
|
|
|
* All BPF programs must return a 32-bit value.
|
|
|
|
|
* The bottom 16-bits are for optional return data.
|
2017-08-12 04:01:39 +08:00
|
|
|
* The upper 16-bits are ordered from least permissive values to most,
|
|
|
|
|
* as a signed value (so 0x8000000 is negative).
|
2012-10-13 17:46:48 +08:00
|
|
|
*
|
|
|
|
|
* The ordering ensures that a min_t() over composed return values always
|
|
|
|
|
* selects the least permissive choice.
|
|
|
|
|
*/
|
2017-08-12 04:01:39 +08:00
|
|
|
#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */
|
|
|
|
|
#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */
|
|
|
|
|
#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD
|
|
|
|
|
#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */
|
|
|
|
|
#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */
|
seccomp: add a return code to trap to userspace
This patch introduces a means for syscalls matched in seccomp to notify
some other task that a particular filter has been triggered.
The motivation for this is primarily for use with containers. For example,
if a container does an init_module(), we obviously don't want to load this
untrusted code, which may be compiled for the wrong version of the kernel
anyway. Instead, we could parse the module image, figure out which module
the container is trying to load and load it on the host.
As another example, containers cannot mount() in general since various
filesystems assume a trusted image. However, if an orchestrator knows that
e.g. a particular block device has not been exposed to a container for
writing, it want to allow the container to mount that block device (that
is, handle the mount for it).
This patch adds functionality that is already possible via at least two
other means that I know about, both of which involve ptrace(): first, one
could ptrace attach, and then iterate through syscalls via PTRACE_SYSCALL.
Unfortunately this is slow, so a faster version would be to install a
filter that does SECCOMP_RET_TRACE, which triggers a PTRACE_EVENT_SECCOMP.
Since ptrace allows only one tracer, if the container runtime is that
tracer, users inside the container (or outside) trying to debug it will not
be able to use ptrace, which is annoying. It also means that older
distributions based on Upstart cannot boot inside containers using ptrace,
since upstart itself uses ptrace to monitor services while starting.
The actual implementation of this is fairly small, although getting the
synchronization right was/is slightly complex.
Finally, it's worth noting that the classic seccomp TOCTOU of reading
memory data from the task still applies here, but can be avoided with
careful design of the userspace handler: if the userspace handler reads all
of the task memory that is necessary before applying its security policy,
the tracee's subsequent memory edits will not be read by the tracer.
Signed-off-by: Tycho Andersen <tycho@tycho.ws>
CC: Kees Cook <keescook@chromium.org>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Oleg Nesterov <oleg@redhat.com>
CC: Eric W. Biederman <ebiederm@xmission.com>
CC: "Serge E. Hallyn" <serge@hallyn.com>
Acked-by: Serge Hallyn <serge@hallyn.com>
CC: Christian Brauner <christian@brauner.io>
CC: Tyler Hicks <tyhicks@canonical.com>
CC: Akihiro Suda <suda.akihiro@lab.ntt.co.jp>
Signed-off-by: Kees Cook <keescook@chromium.org>
2018-12-10 02:24:13 +08:00
|
|
|
#define SECCOMP_RET_USER_NOTIF 0x7fc00000U /* notifies userspace */
|
2017-08-12 04:01:39 +08:00
|
|
|
#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */
|
|
|
|
|
#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */
|
|
|
|
|
#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */
|
2012-10-13 17:46:48 +08:00
|
|
|
|
|
|
|
|
/* Masks for the return value sections. */
|
seccomp: Implement SECCOMP_RET_KILL_PROCESS action
Right now, SECCOMP_RET_KILL_THREAD (neé SECCOMP_RET_KILL) kills the
current thread. There have been a few requests for this to kill the entire
process (the thread group). This cannot be just changed (discovered when
adding coredump support since coredumping kills the entire process)
because there are userspace programs depending on the thread-kill
behavior.
Instead, implement SECCOMP_RET_KILL_PROCESS, which is 0x80000000, and can
be processed as "-1" by the kernel, below the existing RET_KILL that is
ABI-set to "0". For userspace, SECCOMP_RET_ACTION_FULL is added to expand
the mask to the signed bit. Old userspace using the SECCOMP_RET_ACTION
mask will see SECCOMP_RET_KILL_PROCESS as 0 still, but this would only
be visible when examining the siginfo in a core dump from a RET_KILL_*,
where it will think it was thread-killed instead of process-killed.
Attempts to introduce this behavior via other ways (filter flags,
seccomp struct flags, masked RET_DATA bits) all come with weird
side-effects and baggage. This change preserves the central behavioral
expectations of the seccomp filter engine without putting too great
a burden on changes needed in userspace to use the new action.
The new action is discoverable by userspace through either the new
actions_avail sysctl or through the SECCOMP_GET_ACTION_AVAIL seccomp
operation. If used without checking for availability, old kernels
will treat RET_KILL_PROCESS as RET_KILL_THREAD (since the old mask
will produce RET_KILL_THREAD).
Cc: Paul Moore <paul@paul-moore.com>
Cc: Fabricio Voznika <fvoznika@google.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
2017-08-12 04:12:11 +08:00
|
|
|
#define SECCOMP_RET_ACTION_FULL 0xffff0000U
|
2012-10-13 17:46:48 +08:00
|
|
|
#define SECCOMP_RET_ACTION 0x7fff0000U
|
|
|
|
|
#define SECCOMP_RET_DATA 0x0000ffffU
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* struct seccomp_data - the format the BPF program executes over.
|
|
|
|
|
* @nr: the system call number
|
|
|
|
|
* @arch: indicates system call convention as an AUDIT_ARCH_* value
|
|
|
|
|
* as defined in <linux/audit.h>.
|
|
|
|
|
* @instruction_pointer: at the time of the system call.
|
|
|
|
|
* @args: up to 6 system call arguments always stored as 64-bit values
|
|
|
|
|
* regardless of the architecture.
|
|
|
|
|
*/
|
|
|
|
|
struct seccomp_data {
|
|
|
|
|
int nr;
|
|
|
|
|
__u32 arch;
|
|
|
|
|
__u64 instruction_pointer;
|
|
|
|
|
__u64 args[6];
|
|
|
|
|
};
|
|
|
|
|
|
seccomp: add a return code to trap to userspace
This patch introduces a means for syscalls matched in seccomp to notify
some other task that a particular filter has been triggered.
The motivation for this is primarily for use with containers. For example,
if a container does an init_module(), we obviously don't want to load this
untrusted code, which may be compiled for the wrong version of the kernel
anyway. Instead, we could parse the module image, figure out which module
the container is trying to load and load it on the host.
As another example, containers cannot mount() in general since various
filesystems assume a trusted image. However, if an orchestrator knows that
e.g. a particular block device has not been exposed to a container for
writing, it want to allow the container to mount that block device (that
is, handle the mount for it).
This patch adds functionality that is already possible via at least two
other means that I know about, both of which involve ptrace(): first, one
could ptrace attach, and then iterate through syscalls via PTRACE_SYSCALL.
Unfortunately this is slow, so a faster version would be to install a
filter that does SECCOMP_RET_TRACE, which triggers a PTRACE_EVENT_SECCOMP.
Since ptrace allows only one tracer, if the container runtime is that
tracer, users inside the container (or outside) trying to debug it will not
be able to use ptrace, which is annoying. It also means that older
distributions based on Upstart cannot boot inside containers using ptrace,
since upstart itself uses ptrace to monitor services while starting.
The actual implementation of this is fairly small, although getting the
synchronization right was/is slightly complex.
Finally, it's worth noting that the classic seccomp TOCTOU of reading
memory data from the task still applies here, but can be avoided with
careful design of the userspace handler: if the userspace handler reads all
of the task memory that is necessary before applying its security policy,
the tracee's subsequent memory edits will not be read by the tracer.
Signed-off-by: Tycho Andersen <tycho@tycho.ws>
CC: Kees Cook <keescook@chromium.org>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Oleg Nesterov <oleg@redhat.com>
CC: Eric W. Biederman <ebiederm@xmission.com>
CC: "Serge E. Hallyn" <serge@hallyn.com>
Acked-by: Serge Hallyn <serge@hallyn.com>
CC: Christian Brauner <christian@brauner.io>
CC: Tyler Hicks <tyhicks@canonical.com>
CC: Akihiro Suda <suda.akihiro@lab.ntt.co.jp>
Signed-off-by: Kees Cook <keescook@chromium.org>
2018-12-10 02:24:13 +08:00
|
|
|
struct seccomp_notif_sizes {
|
|
|
|
|
__u16 seccomp_notif;
|
|
|
|
|
__u16 seccomp_notif_resp;
|
|
|
|
|
__u16 seccomp_data;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct seccomp_notif {
|
|
|
|
|
__u64 id;
|
|
|
|
|
__u32 pid;
|
|
|
|
|
__u32 flags;
|
|
|
|
|
struct seccomp_data data;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct seccomp_notif_resp {
|
|
|
|
|
__u64 id;
|
|
|
|
|
__s64 val;
|
|
|
|
|
__s32 error;
|
|
|
|
|
__u32 flags;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
#define SECCOMP_IOC_MAGIC '!'
|
|
|
|
|
#define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr)
|
|
|
|
|
#define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type)
|
|
|
|
|
#define SECCOMP_IOW(nr, type) _IOW(SECCOMP_IOC_MAGIC, nr, type)
|
|
|
|
|
#define SECCOMP_IOWR(nr, type) _IOWR(SECCOMP_IOC_MAGIC, nr, type)
|
|
|
|
|
|
|
|
|
|
/* Flags for seccomp notification fd ioctl. */
|
|
|
|
|
#define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif)
|
|
|
|
|
#define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \
|
|
|
|
|
struct seccomp_notif_resp)
|
|
|
|
|
#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOR(2, __u64)
|
2012-10-13 17:46:48 +08:00
|
|
|
#endif /* _UAPI_LINUX_SECCOMP_H */
|
