6a21cc50f0
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>
98 lines
3.2 KiB
C
98 lines
3.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
|
|
#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. */
|
|
|
|
/* Valid operations for seccomp syscall. */
|
|
#define SECCOMP_SET_MODE_STRICT 0
|
|
#define SECCOMP_SET_MODE_FILTER 1
|
|
#define SECCOMP_GET_ACTION_AVAIL 2
|
|
#define SECCOMP_GET_NOTIF_SIZES 3
|
|
|
|
/* Valid flags for SECCOMP_SET_MODE_FILTER */
|
|
#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)
|
|
|
|
/*
|
|
* All BPF programs must return a 32-bit value.
|
|
* The bottom 16-bits are for optional return data.
|
|
* The upper 16-bits are ordered from least permissive values to most,
|
|
* as a signed value (so 0x8000000 is negative).
|
|
*
|
|
* The ordering ensures that a min_t() over composed return values always
|
|
* selects the least permissive choice.
|
|
*/
|
|
#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 */
|
|
#define SECCOMP_RET_USER_NOTIF 0x7fc00000U /* notifies userspace */
|
|
#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 */
|
|
|
|
/* Masks for the return value sections. */
|
|
#define SECCOMP_RET_ACTION_FULL 0xffff0000U
|
|
#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];
|
|
};
|
|
|
|
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)
|
|
#endif /* _UAPI_LINUX_SECCOMP_H */
|