freebsd-dev/sys/miscfs/procfs/procfs.h
Poul-Henning Kamp 75c1354190 This Implements the mumbled about "Jail" feature.
This is a seriously beefed up chroot kind of thing.  The process
is jailed along the same lines as a chroot does it, but with
additional tough restrictions imposed on what the superuser can do.

For all I know, it is safe to hand over the root bit inside a
prison to the customer living in that prison, this is what
it was developed for in fact:  "real virtual servers".

Each prison has an ip number associated with it, which all IP
communications will be coerced to use and each prison has its own
hostname.

Needless to say, you need more RAM this way, but the advantage is
that each customer can run their own particular version of apache
and not stomp on the toes of their neighbors.

It generally does what one would expect, but setting up a jail
still takes a little knowledge.

A few notes:

   I have no scripts for setting up a jail, don't ask me for them.

   The IP number should be an alias on one of the interfaces.

   mount a /proc in each jail, it will make ps more useable.

   /proc/<pid>/status tells the hostname of the prison for
   jailed processes.

   Quotas are only sensible if you have a mountpoint per prison.

   There are no privisions for stopping resource-hogging.

   Some "#ifdef INET" and similar may be missing (send patches!)

If somebody wants to take it from here and develop it into
more of a "virtual machine" they should be most welcome!

Tools, comments, patches & documentation most welcome.

Have fun...

Sponsored by:   http://www.rndassociates.com/
Run for almost a year by:       http://www.servetheweb.com/
1999-04-28 11:38:52 +00:00

178 lines
6.5 KiB
C

/*
* Copyright (c) 1993 Jan-Simon Pendry
* Copyright (c) 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Jan-Simon Pendry.
*
* 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.
* 3. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by the University of
* California, Berkeley and its contributors.
* 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.
*
* @(#)procfs.h 8.9 (Berkeley) 5/14/95
*
* From:
* $Id: procfs.h,v 1.22 1999/04/27 11:16:35 phk Exp $
*/
/*
* The different types of node in a procfs filesystem
*/
typedef enum {
Proot, /* the filesystem root */
Pcurproc, /* symbolic link for curproc */
Pproc, /* a process-specific sub-directory */
Pfile, /* the executable file */
Pmem, /* the process's memory image */
Pregs, /* the process's register set */
Pfpregs, /* the process's FP register set */
Pctl, /* process control */
Pstatus, /* process status */
Pnote, /* process notifier */
Pnotepg, /* process group notifier */
Pmap, /* memory map */
Ptype, /* executable type */
Pcmdline /* command line */
} pfstype;
/*
* control data for the proc file system.
*/
struct pfsnode {
struct pfsnode *pfs_next; /* next on list */
struct vnode *pfs_vnode; /* vnode associated with this pfsnode */
pfstype pfs_type; /* type of procfs node */
pid_t pfs_pid; /* associated process */
u_short pfs_mode; /* mode bits for stat() */
u_long pfs_flags; /* open flags */
u_long pfs_fileno; /* unique file id */
pid_t pfs_lockowner; /* pfs lock owner */
};
#define PROCFS_NOTELEN 64 /* max length of a note (/proc/$pid/note) */
#define PROCFS_CTLLEN 8 /* max length of a ctl msg (/proc/$pid/ctl */
/*
* Kernel stuff follows
*/
#ifdef KERNEL
#define CNEQ(cnp, s, len) \
((cnp)->cn_namelen == (len) && \
(bcmp((s), (cnp)->cn_nameptr, (len)) == 0))
#define KMEM_GROUP 2
/*
* Check to see whether access to target process is allowed
* Evaluates to 1 if access is allowed.
*/
#define CHECKIO(p1, p2) \
(PRISON_CHECK(p1, p2) && \
(((p1)->p_cred->pc_ucred->cr_uid == (p2)->p_cred->p_ruid) && \
((p1)->p_cred->p_ruid == (p2)->p_cred->p_ruid) && \
((p1)->p_cred->p_svuid == (p2)->p_cred->p_ruid) && \
((p2)->p_flag & P_SUGID) == 0) || (suser((p1)) == 0))
/*
* Format of a directory entry in /proc, ...
* This must map onto struct dirent (see <dirent.h>)
*/
#define PROCFS_NAMELEN 8
struct pfsdent {
u_int32_t d_fileno;
u_int16_t d_reclen;
u_int8_t d_type;
u_int8_t d_namlen;
char d_name[PROCFS_NAMELEN];
};
#define UIO_MX sizeof(struct pfsdent)
#define PROCFS_FILENO(pid, type) \
(((type) < Pproc) ? \
((type) + 2) : \
((((pid)+1) << 4) + ((int) (type))))
/*
* Convert between pfsnode vnode
*/
#define VTOPFS(vp) ((struct pfsnode *)(vp)->v_data)
#define PFSTOV(pfs) ((pfs)->pfs_vnode)
typedef struct vfs_namemap vfs_namemap_t;
struct vfs_namemap {
const char *nm_name;
int nm_val;
};
int vfs_getuserstr __P((struct uio *, char *, int *));
vfs_namemap_t *vfs_findname __P((vfs_namemap_t *, char *, int));
/* <machine/reg.h> */
struct reg;
struct fpreg;
#define PFIND(pid) ((pid) ? pfind(pid) : &proc0)
void procfs_exit __P((struct proc *));
int procfs_freevp __P((struct vnode *));
int procfs_allocvp __P((struct mount *, struct vnode **, long, pfstype));
struct vnode *procfs_findtextvp __P((struct proc *));
int procfs_sstep __P((struct proc *));
void procfs_fix_sstep __P((struct proc *));
int procfs_read_regs __P((struct proc *, struct reg *));
int procfs_write_regs __P((struct proc *, struct reg *));
int procfs_read_fpregs __P((struct proc *, struct fpreg *));
int procfs_write_fpregs __P((struct proc *, struct fpreg *));
int procfs_donote __P((struct proc *, struct proc *, struct pfsnode *pfsp, struct uio *uio));
int procfs_doregs __P((struct proc *, struct proc *, struct pfsnode *pfsp, struct uio *uio));
int procfs_dofpregs __P((struct proc *, struct proc *, struct pfsnode *pfsp, struct uio *uio));
int procfs_domem __P((struct proc *, struct proc *, struct pfsnode *pfsp, struct uio *uio));
int procfs_doctl __P((struct proc *, struct proc *, struct pfsnode *pfsp, struct uio *uio));
int procfs_dostatus __P((struct proc *, struct proc *, struct pfsnode *pfsp, struct uio *uio));
int procfs_domap __P((struct proc *, struct proc *, struct pfsnode *pfsp, struct uio *uio));
int procfs_dotype __P((struct proc *, struct proc *, struct pfsnode *pfsp, struct uio *uio));
int procfs_docmdline __P((struct proc *, struct proc *, struct pfsnode *pfsp, struct uio *uio));
/* Return 1 if process has special kernel digging privileges */
int procfs_kmemaccess __P((struct proc *));
/* functions to check whether or not files should be displayed */
int procfs_validfile __P((struct proc *));
int procfs_validfpregs __P((struct proc *));
int procfs_validregs __P((struct proc *));
int procfs_validmap __P((struct proc *));
int procfs_validtype __P((struct proc *));
#define PROCFS_LOCKED 0x01
#define PROCFS_WANT 0x02
extern vop_t **procfs_vnodeop_p;
int procfs_root __P((struct mount *, struct vnode **));
int procfs_rw __P((struct vop_read_args *));
#endif /* KERNEL */