freebsd-dev/sys/miscfs/procfs/procfs_mem.c

317 lines
8.2 KiB
C
Raw Normal View History

1994-05-24 10:09:53 +00:00
/*
* Copyright (c) 1993 Jan-Simon Pendry
* Copyright (c) 1993 Sean Eric Fagan
* 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 and Sean Eric Fagan.
*
* 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_mem.c 8.5 (Berkeley) 6/15/94
1994-05-24 10:09:53 +00:00
*
1999-08-28 01:08:13 +00:00
* $FreeBSD$
1994-05-24 10:09:53 +00:00
*/
/*
* This is a lightly hacked and merged version
* of sef's pread/pwrite functions
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/proc.h>
#include <sys/vnode.h>
#include <miscfs/procfs/procfs.h>
#include <vm/vm.h>
#include <vm/vm_param.h>
#include <sys/lock.h>
#include <vm/pmap.h>
#include <vm/vm_extern.h>
#include <vm/vm_map.h>
1994-05-24 10:09:53 +00:00
#include <vm/vm_kern.h>
#include <vm/vm_object.h>
1994-05-24 10:09:53 +00:00
#include <vm/vm_page.h>
#include <sys/user.h>
#include <sys/ptrace.h>
1994-05-24 10:09:53 +00:00
static int procfs_rwmem __P((struct proc *curp,
struct proc *p, struct uio *uio));
1994-05-24 10:09:53 +00:00
static int
procfs_rwmem(curp, p, uio)
struct proc *curp;
1994-05-24 10:09:53 +00:00
struct proc *p;
struct uio *uio;
{
int error;
int writing;
struct vmspace *vm;
vm_map_t map;
vm_object_t object = NULL;
vm_offset_t pageno = 0; /* page number */
vm_prot_t reqprot;
vm_offset_t kva;
/*
* if the vmspace is in the midst of being deallocated or the
* process is exiting, don't try to grab anything. The page table
* usage in that process can be messed up.
*/
vm = p->p_vmspace;
if ((p->p_flag & P_WEXIT) || (vm->vm_refcnt < 1))
return EFAULT;
++vm->vm_refcnt;
/*
* The map we want...
*/
map = &vm->vm_map;
1994-05-24 10:09:53 +00:00
writing = uio->uio_rw == UIO_WRITE;
reqprot = writing ? (VM_PROT_WRITE | VM_PROT_OVERRIDE_WRITE) : VM_PROT_READ;
kva = kmem_alloc_pageable(kernel_map, PAGE_SIZE);
1994-05-24 10:09:53 +00:00
/*
* Only map in one page at a time. We don't have to, but it
* makes things easier. This way is trivial - right?
*/
do {
vm_map_t tmap;
1994-05-24 10:09:53 +00:00
vm_offset_t uva;
int page_offset; /* offset into page */
vm_map_entry_t out_entry;
vm_prot_t out_prot;
VM level code cleanups. 1) Start using TSM. Struct procs continue to point to upages structure, after being freed. Struct vmspace continues to point to pte object and kva space for kstack. u_map is now superfluous. 2) vm_map's don't need to be reference counted. They always exist either in the kernel or in a vmspace. The vmspaces are managed by reference counts. 3) Remove the "wired" vm_map nonsense. 4) No need to keep a cache of kernel stack kva's. 5) Get rid of strange looking ++var, and change to var++. 6) Change more data structures to use our "zone" allocator. Added struct proc, struct vmspace and struct vnode. This saves a significant amount of kva space and physical memory. Additionally, this enables TSM for the zone managed memory. 7) Keep ioopt disabled for now. 8) Remove the now bogus "single use" map concept. 9) Use generation counts or id's for data structures residing in TSM, where it allows us to avoid unneeded restart overhead during traversals, where blocking might occur. 10) Account better for memory deficits, so the pageout daemon will be able to make enough memory available (experimental.) 11) Fix some vnode locking problems. (From Tor, I think.) 12) Add a check in ufs_lookup, to avoid lots of unneeded calls to bcmp. (experimental.) 13) Significantly shrink, cleanup, and make slightly faster the vm_fault.c code. Use generation counts, get rid of unneded collpase operations, and clean up the cluster code. 14) Make vm_zone more suitable for TSM. This commit is partially as a result of discussions and contributions from other people, including DG, Tor Egge, PHK, and probably others that I have forgotten to attribute (so let me know, if I forgot.) This is not the infamous, final cleanup of the vnode stuff, but a necessary step. Vnode mgmt should be correct, but things might still change, and there is still some missing stuff (like ioopt, and physical backing of non-merged cache files, debugging of layering concepts.)
1998-01-22 17:30:44 +00:00
boolean_t wired;
vm_pindex_t pindex;
1994-05-24 10:09:53 +00:00
u_int len;
vm_page_t m;
object = NULL;
1994-05-24 10:09:53 +00:00
uva = (vm_offset_t) uio->uio_offset;
/*
* Get the page number of this segment.
*/
pageno = trunc_page(uva);
page_offset = uva - pageno;
/*
* How many bytes to copy
*/
len = min(PAGE_SIZE - page_offset, uio->uio_resid);
/*
* Fault the page on behalf of the process
1994-05-24 10:09:53 +00:00
*/
error = vm_fault(map, pageno, reqprot, VM_FAULT_NORMAL);
if (error) {
error = EFAULT;
break;
1994-05-24 10:09:53 +00:00
}
/*
* Now we need to get the page. out_entry, out_prot, wired,
* and single_use aren't used. One would think the vm code
* would be a *bit* nicer... We use tmap because
* vm_map_lookup() can change the map argument.
*/
tmap = map;
error = vm_map_lookup(&tmap, pageno, reqprot,
&out_entry, &object, &pindex, &out_prot,
VM level code cleanups. 1) Start using TSM. Struct procs continue to point to upages structure, after being freed. Struct vmspace continues to point to pte object and kva space for kstack. u_map is now superfluous. 2) vm_map's don't need to be reference counted. They always exist either in the kernel or in a vmspace. The vmspaces are managed by reference counts. 3) Remove the "wired" vm_map nonsense. 4) No need to keep a cache of kernel stack kva's. 5) Get rid of strange looking ++var, and change to var++. 6) Change more data structures to use our "zone" allocator. Added struct proc, struct vmspace and struct vnode. This saves a significant amount of kva space and physical memory. Additionally, this enables TSM for the zone managed memory. 7) Keep ioopt disabled for now. 8) Remove the now bogus "single use" map concept. 9) Use generation counts or id's for data structures residing in TSM, where it allows us to avoid unneeded restart overhead during traversals, where blocking might occur. 10) Account better for memory deficits, so the pageout daemon will be able to make enough memory available (experimental.) 11) Fix some vnode locking problems. (From Tor, I think.) 12) Add a check in ufs_lookup, to avoid lots of unneeded calls to bcmp. (experimental.) 13) Significantly shrink, cleanup, and make slightly faster the vm_fault.c code. Use generation counts, get rid of unneded collpase operations, and clean up the cluster code. 14) Make vm_zone more suitable for TSM. This commit is partially as a result of discussions and contributions from other people, including DG, Tor Egge, PHK, and probably others that I have forgotten to attribute (so let me know, if I forgot.) This is not the infamous, final cleanup of the vnode stuff, but a necessary step. Vnode mgmt should be correct, but things might still change, and there is still some missing stuff (like ioopt, and physical backing of non-merged cache files, debugging of layering concepts.)
1998-01-22 17:30:44 +00:00
&wired);
if (error) {
error = EFAULT;
/*
* Make sure that there is no residue in 'object' from
* an error return on vm_map_lookup.
*/
object = NULL;
break;
}
m = vm_page_lookup(object, pindex);
/* Allow fallback to backing objects if we are reading */
while (m == NULL && !writing && object->backing_object) {
pindex += OFF_TO_IDX(object->backing_object_offset);
object = object->backing_object;
m = vm_page_lookup(object, pindex);
}
if (m == NULL) {
error = EFAULT;
/*
* Make sure that there is no residue in 'object' from
* an error return on vm_map_lookup.
*/
object = NULL;
vm_map_lookup_done(tmap, out_entry);
break;
}
/*
* Wire the page into memory
*/
vm_page_wire(m);
1994-05-24 10:09:53 +00:00
/*
* We're done with tmap now.
* But reference the object first, so that we won't loose
* it.
1994-05-24 10:09:53 +00:00
*/
vm_object_reference(object);
vm_map_lookup_done(tmap, out_entry);
1995-05-30 08:16:23 +00:00
pmap_kenter(kva, VM_PAGE_TO_PHYS(m));
/*
* Now do the i/o move.
*/
error = uiomove((caddr_t)(kva + page_offset), len, uio);
pmap_kremove(kva);
/*
* release the page and the object
*/
vm_page_unwire(m, 1);
vm_object_deallocate(object);
object = NULL;
1994-05-24 10:09:53 +00:00
} while (error == 0 && uio->uio_resid > 0);
if (object)
vm_object_deallocate(object);
kmem_free(kernel_map, kva, PAGE_SIZE);
vmspace_free(vm);
1994-05-24 10:09:53 +00:00
return (error);
}
/*
* Copy data in and out of the target process.
* We do this by mapping the process's page into
* the kernel and then doing a uiomove direct
* from the kernel address space.
*/
int
procfs_domem(curp, p, pfs, uio)
struct proc *curp;
struct proc *p;
struct pfsnode *pfs;
struct uio *uio;
{
if (uio->uio_resid == 0)
return (0);
/*
* XXX
* We need to check for KMEM_GROUP because ps is sgid kmem;
* not allowing it here causes ps to not work properly. Arguably,
* this is a bug with what ps does. We only need to do this
* for Pmem nodes, and only if it's reading. This is still not
* good, as it may still be possible to grab illicit data if
* a process somehow gets to be KMEM_GROUP. Note that this also
* means that KMEM_GROUP can't change without editing procfs.h!
* All in all, quite yucky.
*/
o Centralize inter-process access control, introducing: int p_can(p1, p2, operation, privused) which allows specification of subject process, object process, inter-process operation, and an optional call-by-reference privused flag, allowing the caller to determine if privilege was required for the call to succeed. This allows jail, kern.ps_showallprocs and regular credential-based interaction checks to occur in one block of code. Possible operations are P_CAN_SEE, P_CAN_SCHED, P_CAN_KILL, and P_CAN_DEBUG. p_can currently breaks out as a wrapper to a series of static function checks in kern_prot, which should not be invoked directly. o Commented out capabilities entries are included for some checks. o Update most inter-process authorization to make use of p_can() instead of manual checks, PRISON_CHECK(), P_TRESPASS(), and kern.ps_showallprocs. o Modify suser{,_xxx} to use const arguments, as it no longer modifies process flags due to the disabling of ASU. o Modify some checks/errors in procfs so that ENOENT is returned instead of ESRCH, further improving concealment of processes that should not be visible to other processes. Also introduce new access checks to improve hiding of processes for procfs_lookup(), procfs_getattr(), procfs_readdir(). Correct a bug reported by bp concerning not handling the CREATE case in procfs_lookup(). Remove volatile flag in procfs that caused apparently spurious qualifier warnigns (approved by bde). o Add comment noting that ktrace() has not been updated, as its access control checks are different from ptrace(), whereas they should probably be the same. Further discussion should happen on this topic. Reviewed by: bde, green, phk, freebsd-security, others Approved by: bde Obtained from: TrustedBSD Project
2000-08-30 04:49:09 +00:00
if (p_can(curp, p, P_CAN_DEBUG, NULL) &&
!(uio->uio_rw == UIO_READ &&
procfs_kmemaccess(curp)))
return EPERM;
return (procfs_rwmem(curp, p, uio));
1994-05-24 10:09:53 +00:00
}
/*
* Given process (p), find the vnode from which
* its text segment is being executed.
1994-05-24 10:09:53 +00:00
*
* It would be nice to grab this information from
* the VM system, however, there is no sure-fire
* way of doing that. Instead, fork(), exec() and
* wait() all maintain the p_textvp field in the
* process proc structure which contains a held
* reference to the exec'ed vnode.
*
* XXX - Currently, this is not not used, as the
* /proc/pid/file object exposes an information leak
* that shouldn't happen. Using a mount option would
* make it configurable on a per-system (or, at least,
* per-mount) basis; however, that's not really best.
* The best way to do it, I think, would be as an
* ioctl; this would restrict it to the uid running
* program, or root, which seems a reasonable compromise.
* However, the number of applications for this is
* minimal, if it can't be seen in the filesytem space,
* and doint it as an ioctl makes it somewhat less
* useful due to the, well, inelegance.
*
1994-05-24 10:09:53 +00:00
*/
struct vnode *
procfs_findtextvp(p)
struct proc *p;
{
1994-05-24 10:09:53 +00:00
return (p->p_textvp);
}
int procfs_kmemaccess(curp)
struct proc *curp;
{
int i;
struct ucred *cred;
1999-11-21 12:38:21 +00:00
cred = curp->p_ucred;
if (suser(curp))
return 1;
/* XXX: Why isn't this done with file-perms ??? */
for (i = 0; i < cred->cr_ngroups; i++)
if (cred->cr_groups[i] == KMEM_GROUP)
return 1;
return 0;
}