opnsense-src/sys/sys/file.h
Pawel Jakub Dawidek 2609222ab4 Merge Capsicum overhaul:
- Capability is no longer separate descriptor type. Now every descriptor
  has set of its own capability rights.

- The cap_new(2) system call is left, but it is no longer documented and
  should not be used in new code.

- The new syscall cap_rights_limit(2) should be used instead of
  cap_new(2), which limits capability rights of the given descriptor
  without creating a new one.

- The cap_getrights(2) syscall is renamed to cap_rights_get(2).

- If CAP_IOCTL capability right is present we can further reduce allowed
  ioctls list with the new cap_ioctls_limit(2) syscall. List of allowed
  ioctls can be retrived with cap_ioctls_get(2) syscall.

- If CAP_FCNTL capability right is present we can further reduce fcntls
  that can be used with the new cap_fcntls_limit(2) syscall and retrive
  them with cap_fcntls_get(2).

- To support ioctl and fcntl white-listing the filedesc structure was
  heavly modified.

- The audit subsystem, kdump and procstat tools were updated to
  recognize new syscalls.

- Capability rights were revised and eventhough I tried hard to provide
  backward API and ABI compatibility there are some incompatible changes
  that are described in detail below:

	CAP_CREATE old behaviour:
	- Allow for openat(2)+O_CREAT.
	- Allow for linkat(2).
	- Allow for symlinkat(2).
	CAP_CREATE new behaviour:
	- Allow for openat(2)+O_CREAT.

	Added CAP_LINKAT:
	- Allow for linkat(2). ABI: Reuses CAP_RMDIR bit.
	- Allow to be target for renameat(2).

	Added CAP_SYMLINKAT:
	- Allow for symlinkat(2).

	Removed CAP_DELETE. Old behaviour:
	- Allow for unlinkat(2) when removing non-directory object.
	- Allow to be source for renameat(2).

	Removed CAP_RMDIR. Old behaviour:
	- Allow for unlinkat(2) when removing directory.

	Added CAP_RENAMEAT:
	- Required for source directory for the renameat(2) syscall.

	Added CAP_UNLINKAT (effectively it replaces CAP_DELETE and CAP_RMDIR):
	- Allow for unlinkat(2) on any object.
	- Required if target of renameat(2) exists and will be removed by this
	  call.

	Removed CAP_MAPEXEC.

	CAP_MMAP old behaviour:
	- Allow for mmap(2) with any combination of PROT_NONE, PROT_READ and
	  PROT_WRITE.
	CAP_MMAP new behaviour:
	- Allow for mmap(2)+PROT_NONE.

	Added CAP_MMAP_R:
	- Allow for mmap(PROT_READ).
	Added CAP_MMAP_W:
	- Allow for mmap(PROT_WRITE).
	Added CAP_MMAP_X:
	- Allow for mmap(PROT_EXEC).
	Added CAP_MMAP_RW:
	- Allow for mmap(PROT_READ | PROT_WRITE).
	Added CAP_MMAP_RX:
	- Allow for mmap(PROT_READ | PROT_EXEC).
	Added CAP_MMAP_WX:
	- Allow for mmap(PROT_WRITE | PROT_EXEC).
	Added CAP_MMAP_RWX:
	- Allow for mmap(PROT_READ | PROT_WRITE | PROT_EXEC).

	Renamed CAP_MKDIR to CAP_MKDIRAT.
	Renamed CAP_MKFIFO to CAP_MKFIFOAT.
	Renamed CAP_MKNODE to CAP_MKNODEAT.

	CAP_READ old behaviour:
	- Allow pread(2).
	- Disallow read(2), readv(2) (if there is no CAP_SEEK).
	CAP_READ new behaviour:
	- Allow read(2), readv(2).
	- Disallow pread(2) (CAP_SEEK was also required).

	CAP_WRITE old behaviour:
	- Allow pwrite(2).
	- Disallow write(2), writev(2) (if there is no CAP_SEEK).
	CAP_WRITE new behaviour:
	- Allow write(2), writev(2).
	- Disallow pwrite(2) (CAP_SEEK was also required).

	Added convinient defines:

	#define	CAP_PREAD		(CAP_SEEK | CAP_READ)
	#define	CAP_PWRITE		(CAP_SEEK | CAP_WRITE)
	#define	CAP_MMAP_R		(CAP_MMAP | CAP_SEEK | CAP_READ)
	#define	CAP_MMAP_W		(CAP_MMAP | CAP_SEEK | CAP_WRITE)
	#define	CAP_MMAP_X		(CAP_MMAP | CAP_SEEK | 0x0000000000000008ULL)
	#define	CAP_MMAP_RW		(CAP_MMAP_R | CAP_MMAP_W)
	#define	CAP_MMAP_RX		(CAP_MMAP_R | CAP_MMAP_X)
	#define	CAP_MMAP_WX		(CAP_MMAP_W | CAP_MMAP_X)
	#define	CAP_MMAP_RWX		(CAP_MMAP_R | CAP_MMAP_W | CAP_MMAP_X)
	#define	CAP_RECV		CAP_READ
	#define	CAP_SEND		CAP_WRITE

	#define	CAP_SOCK_CLIENT \
		(CAP_CONNECT | CAP_GETPEERNAME | CAP_GETSOCKNAME | CAP_GETSOCKOPT | \
		 CAP_PEELOFF | CAP_RECV | CAP_SEND | CAP_SETSOCKOPT | CAP_SHUTDOWN)
	#define	CAP_SOCK_SERVER \
		(CAP_ACCEPT | CAP_BIND | CAP_GETPEERNAME | CAP_GETSOCKNAME | \
		 CAP_GETSOCKOPT | CAP_LISTEN | CAP_PEELOFF | CAP_RECV | CAP_SEND | \
		 CAP_SETSOCKOPT | CAP_SHUTDOWN)

	Added defines for backward API compatibility:

	#define	CAP_MAPEXEC		CAP_MMAP_X
	#define	CAP_DELETE		CAP_UNLINKAT
	#define	CAP_MKDIR		CAP_MKDIRAT
	#define	CAP_RMDIR		CAP_UNLINKAT
	#define	CAP_MKFIFO		CAP_MKFIFOAT
	#define	CAP_MKNOD		CAP_MKNODAT
	#define	CAP_SOCK_ALL		(CAP_SOCK_CLIENT | CAP_SOCK_SERVER)

Sponsored by:	The FreeBSD Foundation
Reviewed by:	Christoph Mallon <christoph.mallon@gmx.de>
Many aspects discussed with:	rwatson, benl, jonathan
ABI compatibility discussed with:	kib
2013-03-02 00:53:12 +00:00

357 lines
11 KiB
C

/*-
* Copyright (c) 1982, 1986, 1989, 1993
* The Regents of the University of California. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)file.h 8.3 (Berkeley) 1/9/95
* $FreeBSD$
*/
#ifndef _SYS_FILE_H_
#define _SYS_FILE_H_
#ifndef _KERNEL
#include <sys/types.h> /* XXX */
#include <sys/fcntl.h>
#include <sys/unistd.h>
#else
#include <sys/queue.h>
#include <sys/refcount.h>
#include <sys/_lock.h>
#include <sys/_mutex.h>
struct stat;
struct thread;
struct uio;
struct knote;
struct vnode;
struct socket;
#endif /* _KERNEL */
#define DTYPE_VNODE 1 /* file */
#define DTYPE_SOCKET 2 /* communications endpoint */
#define DTYPE_PIPE 3 /* pipe */
#define DTYPE_FIFO 4 /* fifo (named pipe) */
#define DTYPE_KQUEUE 5 /* event queue */
#define DTYPE_CRYPTO 6 /* crypto */
#define DTYPE_MQUEUE 7 /* posix message queue */
#define DTYPE_SHM 8 /* swap-backed shared memory */
#define DTYPE_SEM 9 /* posix semaphore */
#define DTYPE_PTS 10 /* pseudo teletype master device */
#define DTYPE_DEV 11 /* Device specific fd type */
#define DTYPE_PROCDESC 12 /* process descriptor */
#ifdef _KERNEL
struct file;
struct filecaps;
struct ucred;
#define FOF_OFFSET 0x01 /* Use the offset in uio argument */
#define FOF_NOLOCK 0x02 /* Do not take FOFFSET_LOCK */
#define FOF_NEXTOFF 0x04 /* Also update f_nextoff */
#define FOF_NOUPDATE 0x10 /* Do not update f_offset */
off_t foffset_lock(struct file *fp, int flags);
void foffset_lock_uio(struct file *fp, struct uio *uio, int flags);
void foffset_unlock(struct file *fp, off_t val, int flags);
void foffset_unlock_uio(struct file *fp, struct uio *uio, int flags);
static inline off_t
foffset_get(struct file *fp)
{
return (foffset_lock(fp, FOF_NOLOCK));
}
typedef int fo_rdwr_t(struct file *fp, struct uio *uio,
struct ucred *active_cred, int flags,
struct thread *td);
typedef int fo_truncate_t(struct file *fp, off_t length,
struct ucred *active_cred, struct thread *td);
typedef int fo_ioctl_t(struct file *fp, u_long com, void *data,
struct ucred *active_cred, struct thread *td);
typedef int fo_poll_t(struct file *fp, int events,
struct ucred *active_cred, struct thread *td);
typedef int fo_kqfilter_t(struct file *fp, struct knote *kn);
typedef int fo_stat_t(struct file *fp, struct stat *sb,
struct ucred *active_cred, struct thread *td);
typedef int fo_close_t(struct file *fp, struct thread *td);
typedef int fo_chmod_t(struct file *fp, mode_t mode,
struct ucred *active_cred, struct thread *td);
typedef int fo_chown_t(struct file *fp, uid_t uid, gid_t gid,
struct ucred *active_cred, struct thread *td);
typedef int fo_flags_t;
struct fileops {
fo_rdwr_t *fo_read;
fo_rdwr_t *fo_write;
fo_truncate_t *fo_truncate;
fo_ioctl_t *fo_ioctl;
fo_poll_t *fo_poll;
fo_kqfilter_t *fo_kqfilter;
fo_stat_t *fo_stat;
fo_close_t *fo_close;
fo_chmod_t *fo_chmod;
fo_chown_t *fo_chown;
fo_flags_t fo_flags; /* DFLAG_* below */
};
#define DFLAG_PASSABLE 0x01 /* may be passed via unix sockets. */
#define DFLAG_SEEKABLE 0x02 /* seekable / nonsequential */
#endif /* _KERNEL */
#if defined(_KERNEL) || defined(_WANT_FILE)
/*
* Kernel descriptor table.
* One entry for each open kernel vnode and socket.
*
* Below is the list of locks that protects members in struct file.
*
* (f) protected with mtx_lock(mtx_pool_find(fp))
* (d) cdevpriv_mtx
* none not locked
*/
struct fadvise_info {
int fa_advice; /* (f) FADV_* type. */
off_t fa_start; /* (f) Region start. */
off_t fa_end; /* (f) Region end. */
off_t fa_prevstart; /* (f) Previous NOREUSE start. */
off_t fa_prevend; /* (f) Previous NOREUSE end. */
};
struct file {
void *f_data; /* file descriptor specific data */
struct fileops *f_ops; /* File operations */
struct ucred *f_cred; /* associated credentials. */
struct vnode *f_vnode; /* NULL or applicable vnode */
short f_type; /* descriptor type */
short f_vnread_flags; /* (f) Sleep lock for f_offset */
volatile u_int f_flag; /* see fcntl.h */
volatile u_int f_count; /* reference count */
/*
* DTYPE_VNODE specific fields.
*/
int f_seqcount; /* Count of sequential accesses. */
off_t f_nextoff; /* next expected read/write offset. */
union {
struct cdev_privdata *fvn_cdevpriv;
/* (d) Private data for the cdev. */
struct fadvise_info *fvn_advice;
} f_vnun;
/*
* DFLAG_SEEKABLE specific fields
*/
off_t f_offset;
/*
* Mandatory Access control information.
*/
void *f_label; /* Place-holder for MAC label. */
};
#define f_cdevpriv f_vnun.fvn_cdevpriv
#define f_advice f_vnun.fvn_advice
#define FOFFSET_LOCKED 0x1
#define FOFFSET_LOCK_WAITING 0x2
#define FDEVFS_VNODE 0x4
#endif /* _KERNEL || _WANT_FILE */
/*
* Userland version of struct file, for sysctl
*/
struct xfile {
size_t xf_size; /* size of struct xfile */
pid_t xf_pid; /* owning process */
uid_t xf_uid; /* effective uid of owning process */
int xf_fd; /* descriptor number */
void *xf_file; /* address of struct file */
short xf_type; /* descriptor type */
int xf_count; /* reference count */
int xf_msgcount; /* references from message queue */
off_t xf_offset; /* file offset */
void *xf_data; /* file descriptor specific data */
void *xf_vnode; /* vnode pointer */
u_int xf_flag; /* flags (see fcntl.h) */
};
#ifdef _KERNEL
extern struct fileops vnops;
extern struct fileops badfileops;
extern struct fileops socketops;
extern int maxfiles; /* kernel limit on number of open files */
extern int maxfilesperproc; /* per process limit on number of open files */
extern volatile int openfiles; /* actual number of open files */
int fget(struct thread *td, int fd, cap_rights_t rights, struct file **fpp);
int fget_mmap(struct thread *td, int fd, cap_rights_t rights,
u_char *maxprotp, struct file **fpp);
int fget_read(struct thread *td, int fd, cap_rights_t rights,
struct file **fpp);
int fget_write(struct thread *td, int fd, cap_rights_t rights,
struct file **fpp);
int _fdrop(struct file *fp, struct thread *td);
/*
* The socket operations are used a couple of places.
* XXX: This is wrong, they should go through the operations vector for
* XXX: sockets instead of going directly for the individual functions. /phk
*/
fo_rdwr_t soo_read;
fo_rdwr_t soo_write;
fo_truncate_t soo_truncate;
fo_ioctl_t soo_ioctl;
fo_poll_t soo_poll;
fo_kqfilter_t soo_kqfilter;
fo_stat_t soo_stat;
fo_close_t soo_close;
fo_chmod_t invfo_chmod;
fo_chown_t invfo_chown;
void finit(struct file *, u_int, short, void *, struct fileops *);
int fgetvp(struct thread *td, int fd, cap_rights_t rights, struct vnode **vpp);
int fgetvp_exec(struct thread *td, int fd, cap_rights_t rights,
struct vnode **vpp);
int fgetvp_rights(struct thread *td, int fd, cap_rights_t need,
struct filecaps *havecaps, struct vnode **vpp);
int fgetvp_read(struct thread *td, int fd, cap_rights_t rights,
struct vnode **vpp);
int fgetvp_write(struct thread *td, int fd, cap_rights_t rights,
struct vnode **vpp);
int fgetsock(struct thread *td, int fd, cap_rights_t rights,
struct socket **spp, u_int *fflagp);
void fputsock(struct socket *sp);
static __inline int
_fnoop(void)
{
return (0);
}
#define fhold(fp) \
(refcount_acquire(&(fp)->f_count))
#define fdrop(fp, td) \
(refcount_release(&(fp)->f_count) ? _fdrop((fp), (td)) : _fnoop())
static __inline fo_rdwr_t fo_read;
static __inline fo_rdwr_t fo_write;
static __inline fo_truncate_t fo_truncate;
static __inline fo_ioctl_t fo_ioctl;
static __inline fo_poll_t fo_poll;
static __inline fo_kqfilter_t fo_kqfilter;
static __inline fo_stat_t fo_stat;
static __inline fo_close_t fo_close;
static __inline fo_chmod_t fo_chmod;
static __inline fo_chown_t fo_chown;
static __inline int
fo_read(struct file *fp, struct uio *uio, struct ucred *active_cred,
int flags, struct thread *td)
{
return ((*fp->f_ops->fo_read)(fp, uio, active_cred, flags, td));
}
static __inline int
fo_write(struct file *fp, struct uio *uio, struct ucred *active_cred,
int flags, struct thread *td)
{
return ((*fp->f_ops->fo_write)(fp, uio, active_cred, flags, td));
}
static __inline int
fo_truncate(struct file *fp, off_t length, struct ucred *active_cred,
struct thread *td)
{
return ((*fp->f_ops->fo_truncate)(fp, length, active_cred, td));
}
static __inline int
fo_ioctl(struct file *fp, u_long com, void *data, struct ucred *active_cred,
struct thread *td)
{
return ((*fp->f_ops->fo_ioctl)(fp, com, data, active_cred, td));
}
static __inline int
fo_poll(struct file *fp, int events, struct ucred *active_cred,
struct thread *td)
{
return ((*fp->f_ops->fo_poll)(fp, events, active_cred, td));
}
static __inline int
fo_stat(struct file *fp, struct stat *sb, struct ucred *active_cred,
struct thread *td)
{
return ((*fp->f_ops->fo_stat)(fp, sb, active_cred, td));
}
static __inline int
fo_close(struct file *fp, struct thread *td)
{
return ((*fp->f_ops->fo_close)(fp, td));
}
static __inline int
fo_kqfilter(struct file *fp, struct knote *kn)
{
return ((*fp->f_ops->fo_kqfilter)(fp, kn));
}
static __inline int
fo_chmod(struct file *fp, mode_t mode, struct ucred *active_cred,
struct thread *td)
{
return ((*fp->f_ops->fo_chmod)(fp, mode, active_cred, td));
}
static __inline int
fo_chown(struct file *fp, uid_t uid, gid_t gid, struct ucred *active_cred,
struct thread *td)
{
return ((*fp->f_ops->fo_chown)(fp, uid, gid, active_cred, td));
}
#endif /* _KERNEL */
#endif /* !SYS_FILE_H */