[linux-2.6-block.git] / include / uapi / linux / seccomp.h

/* 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)
#define SECCOMP_FILTER_FLAG_TSYNC_ESRCH		(1UL << 4)
/* Received notifications wait in killable state (only respond to fatal signals) */
#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV	(1UL << 5)

/*
 * 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;
};

/*
 * Valid flags for struct seccomp_notif_resp
 *
 * Note, the SECCOMP_USER_NOTIF_FLAG_CONTINUE flag must be used with caution!
 * If set by the process supervising the syscalls of another process the
 * syscall will continue. This is problematic because of an inherent TOCTOU.
 * An attacker can exploit the time while the supervised process is waiting on
 * a response from the supervising process to rewrite syscall arguments which
 * are passed as pointers of the intercepted syscall.
 * It should be absolutely clear that this means that the seccomp notifier
 * _cannot_ be used to implement a security policy! It should only ever be used
 * in scenarios where a more privileged process supervises the syscalls of a
 * lesser privileged process to get around kernel-enforced security
 * restrictions when the privileged process deems this safe. In other words,
 * in order to continue a syscall the supervising process should be sure that
 * another security mechanism or the kernel itself will sufficiently block
 * syscalls if arguments are rewritten to something unsafe.
 *
 * Similar precautions should be applied when stacking SECCOMP_RET_USER_NOTIF
 * or SECCOMP_RET_TRACE. For SECCOMP_RET_USER_NOTIF filters acting on the
 * same syscall, the most recently added filter takes precedence. This means
 * that the new SECCOMP_RET_USER_NOTIF filter can override any
 * SECCOMP_IOCTL_NOTIF_SEND from earlier filters, essentially allowing all
 * such filtered syscalls to be executed by sending the response
 * SECCOMP_USER_NOTIF_FLAG_CONTINUE. Note that SECCOMP_RET_TRACE can equally
 * be overriden by SECCOMP_USER_NOTIF_FLAG_CONTINUE.
 */
#define SECCOMP_USER_NOTIF_FLAG_CONTINUE (1UL << 0)

struct seccomp_notif_resp {
	__u64 id;
	__s64 val;
	__s32 error;
	__u32 flags;
};

#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0)

/* valid flags for seccomp_notif_addfd */
#define SECCOMP_ADDFD_FLAG_SETFD	(1UL << 0) /* Specify remote fd */
#define SECCOMP_ADDFD_FLAG_SEND		(1UL << 1) /* Addfd and return it, atomically */

/**
 * struct seccomp_notif_addfd
 * @id: The ID of the seccomp notification
 * @flags: SECCOMP_ADDFD_FLAG_*
 * @srcfd: The local fd number
 * @newfd: Optional remote FD number if SETFD option is set, otherwise 0.
 * @newfd_flags: The O_* flags the remote FD should have applied
 */
struct seccomp_notif_addfd {
	__u64 id;
	__u32 flags;
	__u32 srcfd;
	__u32 newfd;
	__u32 newfd_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_IOW(2, __u64)
/* On success, the return value is the remote process's added fd number */
#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOW(3, \
						struct seccomp_notif_addfd)

#define SECCOMP_IOCTL_NOTIF_SET_FLAGS	SECCOMP_IOW(4, __u64)

#endif /* _UAPI_LINUX_SECCOMP_H */
Commit	Line	Data
	1	/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
	2	#ifndef _UAPI_LINUX_SECCOMP_H
	3	#define _UAPI_LINUX_SECCOMP_H
	4
	5	#include <linux/compiler.h>
	6	#include <linux/types.h>
	7
	8
	9	/* Valid values for seccomp.mode and prctl(PR_SET_SECCOMP, <mode>) */
	10	#define SECCOMP_MODE_DISABLED 0 /* seccomp is not in use. */
	11	#define SECCOMP_MODE_STRICT 1 /* uses hard-coded filter. */
	12	#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */
	13
	14	/* Valid operations for seccomp syscall. */
	15	#define SECCOMP_SET_MODE_STRICT 0
	16	#define SECCOMP_SET_MODE_FILTER 1
	17	#define SECCOMP_GET_ACTION_AVAIL 2
	18	#define SECCOMP_GET_NOTIF_SIZES 3
	19
	20	/* Valid flags for SECCOMP_SET_MODE_FILTER */
	21	#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0)
	22	#define SECCOMP_FILTER_FLAG_LOG (1UL << 1)
	23	#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)
	24	#define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3)
	25	#define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4)
	26	/* Received notifications wait in killable state (only respond to fatal signals) */
	27	#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5)
	28
	29	/*
	30	* All BPF programs must return a 32-bit value.
	31	* The bottom 16-bits are for optional return data.
	32	* The upper 16-bits are ordered from least permissive values to most,
	33	* as a signed value (so 0x8000000 is negative).
	34	*
	35	* The ordering ensures that a min_t() over composed return values always
	36	* selects the least permissive choice.
	37	*/
	38	#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */
	39	#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */
	40	#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD
	41	#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */
	42	#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */
	43	#define SECCOMP_RET_USER_NOTIF 0x7fc00000U /* notifies userspace */
	44	#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */
	45	#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */
	46	#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */
	47
	48	/* Masks for the return value sections. */
	49	#define SECCOMP_RET_ACTION_FULL 0xffff0000U
	50	#define SECCOMP_RET_ACTION 0x7fff0000U
	51	#define SECCOMP_RET_DATA 0x0000ffffU
	52
	53	/**
	54	* struct seccomp_data - the format the BPF program executes over.
	55	* @nr: the system call number
	56	* @arch: indicates system call convention as an AUDIT_ARCH_* value
	57	* as defined in <linux/audit.h>.
	58	* @instruction_pointer: at the time of the system call.
	59	* @args: up to 6 system call arguments always stored as 64-bit values
	60	* regardless of the architecture.
	61	*/
	62	struct seccomp_data {
	63	int nr;
	64	__u32 arch;
	65	__u64 instruction_pointer;
	66	__u64 args[6];
	67	};
	68
	69	struct seccomp_notif_sizes {
	70	__u16 seccomp_notif;
	71	__u16 seccomp_notif_resp;
	72	__u16 seccomp_data;
	73	};
	74
	75	struct seccomp_notif {
	76	__u64 id;
	77	__u32 pid;
	78	__u32 flags;
	79	struct seccomp_data data;
	80	};
	81
	82	/*
	83	* Valid flags for struct seccomp_notif_resp
	84	*
	85	* Note, the SECCOMP_USER_NOTIF_FLAG_CONTINUE flag must be used with caution!
	86	* If set by the process supervising the syscalls of another process the
	87	* syscall will continue. This is problematic because of an inherent TOCTOU.
	88	* An attacker can exploit the time while the supervised process is waiting on
	89	* a response from the supervising process to rewrite syscall arguments which
	90	* are passed as pointers of the intercepted syscall.
	91	* It should be absolutely clear that this means that the seccomp notifier
	92	* _cannot_ be used to implement a security policy! It should only ever be used
	93	* in scenarios where a more privileged process supervises the syscalls of a
	94	* lesser privileged process to get around kernel-enforced security
	95	* restrictions when the privileged process deems this safe. In other words,
	96	* in order to continue a syscall the supervising process should be sure that
	97	* another security mechanism or the kernel itself will sufficiently block
	98	* syscalls if arguments are rewritten to something unsafe.
	99	*
	100	* Similar precautions should be applied when stacking SECCOMP_RET_USER_NOTIF
	101	* or SECCOMP_RET_TRACE. For SECCOMP_RET_USER_NOTIF filters acting on the
	102	* same syscall, the most recently added filter takes precedence. This means
	103	* that the new SECCOMP_RET_USER_NOTIF filter can override any
	104	* SECCOMP_IOCTL_NOTIF_SEND from earlier filters, essentially allowing all
	105	* such filtered syscalls to be executed by sending the response
	106	* SECCOMP_USER_NOTIF_FLAG_CONTINUE. Note that SECCOMP_RET_TRACE can equally
	107	* be overriden by SECCOMP_USER_NOTIF_FLAG_CONTINUE.
	108	*/
	109	#define SECCOMP_USER_NOTIF_FLAG_CONTINUE (1UL << 0)
	110
	111	struct seccomp_notif_resp {
	112	__u64 id;
	113	__s64 val;
	114	__s32 error;
	115	__u32 flags;
	116	};
	117
	118	#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0)
	119
	120	/* valid flags for seccomp_notif_addfd */
	121	#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */
	122	#define SECCOMP_ADDFD_FLAG_SEND (1UL << 1) /* Addfd and return it, atomically */
	123
	124	/**
	125	* struct seccomp_notif_addfd
	126	* @id: The ID of the seccomp notification
	127	* @flags: SECCOMP_ADDFD_FLAG_*
	128	* @srcfd: The local fd number
	129	* @newfd: Optional remote FD number if SETFD option is set, otherwise 0.
	130	* @newfd_flags: The O_* flags the remote FD should have applied
	131	*/
	132	struct seccomp_notif_addfd {
	133	__u64 id;
	134	__u32 flags;
	135	__u32 srcfd;
	136	__u32 newfd;
	137	__u32 newfd_flags;
	138	};
	139
	140	#define SECCOMP_IOC_MAGIC '!'
	141	#define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr)
	142	#define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type)
	143	#define SECCOMP_IOW(nr, type) _IOW(SECCOMP_IOC_MAGIC, nr, type)
	144	#define SECCOMP_IOWR(nr, type) _IOWR(SECCOMP_IOC_MAGIC, nr, type)
	145
	146	/* Flags for seccomp notification fd ioctl. */
	147	#define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif)
	148	#define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \
	149	struct seccomp_notif_resp)
	150	#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64)
	151	/* On success, the return value is the remote process's added fd number */
	152	#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \
	153	struct seccomp_notif_addfd)
	154
	155	#define SECCOMP_IOCTL_NOTIF_SET_FLAGS SECCOMP_IOW(4, __u64)
	156
	157	#endif /* _UAPI_LINUX_SECCOMP_H */