freebsd-dev/sys/miscfs/procfs/procfs_mem.c
David Greenman 24a1cce34f NOTE: libkvm, w, ps, 'top', and any other utility which depends on struct
proc or any VM system structure will have to be rebuilt!!!

Much needed overhaul of the VM system. Included in this first round of
changes:

1) Improved pager interfaces: init, alloc, dealloc, getpages, putpages,
   haspage, and sync operations are supported. The haspage interface now
   provides information about clusterability. All pager routines now take
   struct vm_object's instead of "pagers".

2) Improved data structures. In the previous paradigm, there is constant
   confusion caused by pagers being both a data structure ("allocate a
   pager") and a collection of routines. The idea of a pager structure has
   escentially been eliminated. Objects now have types, and this type is
   used to index the appropriate pager. In most cases, items in the pager
   structure were duplicated in the object data structure and thus were
   unnecessary. In the few cases that remained, a un_pager structure union
   was created in the object to contain these items.

3) Because of the cleanup of #1 & #2, a lot of unnecessary layering can now
   be removed. For instance, vm_object_enter(), vm_object_lookup(),
   vm_object_remove(), and the associated object hash list were some of the
   things that were removed.

4) simple_lock's removed. Discussion with several people reveals that the
   SMP locking primitives used in the VM system aren't likely the mechanism
   that we'll be adopting. Even if it were, the locking that was in the code
   was very inadequate and would have to be mostly re-done anyway. The
   locking in a uni-processor kernel was a no-op but went a long way toward
   making the code difficult to read and debug.

5) Places that attempted to kludge-up the fact that we don't have kernel
   thread support have been fixed to reflect the reality that we are really
   dealing with processes, not threads. The VM system didn't have complete
   thread support, so the comments and mis-named routines were just wrong.
   We now use tsleep and wakeup directly in the lock routines, for instance.

6) Where appropriate, the pagers have been improved, especially in the
   pager_alloc routines. Most of the pager_allocs have been rewritten and
   are now faster and easier to maintain.

7) The pagedaemon pageout clustering algorithm has been rewritten and
   now tries harder to output an even number of pages before and after
   the requested page. This is sort of the reverse of the ideal pagein
   algorithm and should provide better overall performance.

8) Unnecessary (incorrect) casts to caddr_t in calls to tsleep & wakeup
   have been removed. Some other unnecessary casts have also been removed.

9) Some almost useless debugging code removed.

10) Terminology of shadow objects vs. backing objects straightened out.
    The fact that the vm_object data structure escentially had this
    backwards really confused things. The use of "shadow" and "backing
    object" throughout the code is now internally consistent and correct
    in the Mach terminology.

11) Several minor bug fixes, including one in the vm daemon that caused
    0 RSS objects to not get purged as intended.

12) A "default pager" has now been created which cleans up the transition
    of objects to the "swap" type. The previous checks throughout the code
    for swp->pg_data != NULL were really ugly. This change also provides
    the rudiments for future backing of "anonymous" memory by something
    other than the swap pager (via the vnode pager, for example), and it
    allows the decision about which of these pagers to use to be made
    dynamically (although will need some additional decision code to do
    this, of course).

13) (dyson) MAP_COPY has been deprecated and the corresponding "copy
    object" code has been removed. MAP_COPY was undocumented and non-
    standard. It was furthermore broken in several ways which caused its
    behavior to degrade to MAP_PRIVATE. Binaries that use MAP_COPY will
    continue to work correctly, but via the slightly different semantics
    of MAP_PRIVATE.

14) (dyson) Sharing maps have been removed. It's marginal usefulness in a
    threads design can be worked around in other ways. Both #12 and #13
    were done to simplify the code and improve readability and maintain-
    ability. (As were most all of these changes)

TODO:

1) Rewrite most of the vnode pager to use VOP_GETPAGES/PUTPAGES. Doing
   this will reduce the vnode pager to a mere fraction of its current size.

2) Rewrite vm_fault and the swap/vnode pagers to use the clustering
   information provided by the new haspage pager interface. This will
   substantially reduce the overhead by eliminating a large number of
   VOP_BMAP() calls. The VOP_BMAP() filesystem interface should be
   improved to provide both a "behind" and "ahead" indication of
   contiguousness.

3) Implement the extended features of pager_haspage in swap_pager_haspage().
   It currently just says 0 pages ahead/behind.

4) Re-implement the swap device (swstrategy) in a more elegant way, perhaps
   via a much more general mechanism that could also be used for disk
   striping of regular filesystems.

5) Do something to improve the architecture of vm_object_collapse(). The
   fact that it makes calls into the swap pager and knows too much about
   how the swap pager operates really bothers me. It also doesn't allow
   for collapsing of non-swap pager objects ("unnamed" objects backed by
   other pagers).
1995-07-13 08:48:48 +00:00

238 lines
6.4 KiB
C

/*
* 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 8.4 (Berkeley) 1/21/94
*
* $Id: procfs_mem.c,v 1.8 1995/06/28 04:51:06 davidg Exp $
*/
/*
* This is a lightly hacked and merged version
* of sef's pread/pwrite functions
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/time.h>
#include <sys/kernel.h>
#include <sys/proc.h>
#include <sys/vnode.h>
#include <miscfs/procfs/procfs.h>
#include <vm/vm.h>
#include <vm/vm_kern.h>
#include <vm/vm_page.h>
static int
procfs_rwmem(p, uio)
struct proc *p;
struct uio *uio;
{
int error;
int writing;
writing = uio->uio_rw == UIO_WRITE;
/*
* 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 map, tmap;
vm_object_t object;
vm_offset_t kva = 0;
vm_offset_t uva;
int page_offset; /* offset into page */
vm_offset_t pageno; /* page number */
vm_map_entry_t out_entry;
vm_prot_t out_prot;
vm_page_t m;
boolean_t wired, single_use;
vm_offset_t off;
u_int len;
int fix_prot;
uva = (vm_offset_t) uio->uio_offset;
if (uva >= VM_MAXUSER_ADDRESS) {
if (writing || (uva >= (VM_MAXUSER_ADDRESS + UPAGES * PAGE_SIZE))) {
error = 0;
break;
}
}
/*
* 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);
/*
* The map we want...
*/
map = &p->p_vmspace->vm_map;
/*
* Check the permissions for the area we're interested
* in.
*/
fix_prot = 0;
if (writing)
fix_prot = !vm_map_check_protection(map, pageno,
pageno + PAGE_SIZE, VM_PROT_WRITE);
if (fix_prot) {
/*
* If the page is not writable, we make it so.
* XXX It is possible that a page may *not* be
* read/executable, if a process changes that!
* We will assume, for now, that a page is either
* VM_PROT_ALL, or VM_PROT_READ|VM_PROT_EXECUTE.
*/
error = vm_map_protect(map, pageno,
pageno + PAGE_SIZE, VM_PROT_ALL, 0);
if (error)
break;
}
/*
* 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,
writing ? VM_PROT_WRITE : VM_PROT_READ,
&out_entry, &object, &off, &out_prot,
&wired, &single_use);
/*
* We're done with tmap now.
*/
if (!error)
vm_map_lookup_done(tmap, out_entry);
/*
* Fault the page in...
*/
if (!error && writing && object->backing_object) {
m = vm_page_lookup(object, off);
if (m == 0 || (m->flags & PG_COPYONWRITE))
error = vm_fault(map, pageno,
VM_PROT_WRITE, FALSE);
}
/* Find space in kernel_map for the page we're interested in */
if (!error)
error = vm_map_find(kernel_map, object, off, &kva,
PAGE_SIZE, 1);
if (!error) {
/*
* Neither vm_map_lookup() nor vm_map_find() appear
* to add a reference count to the object, so we do
* that here and now.
*/
vm_object_reference(object);
/*
* Mark the page we just found as pageable.
*/
error = vm_map_pageable(kernel_map, kva,
kva + PAGE_SIZE, 0);
/*
* Now do the i/o move.
*/
if (!error)
error = uiomove((caddr_t)(kva + page_offset),
len, uio);
vm_map_remove(kernel_map, kva, kva + PAGE_SIZE);
}
if (fix_prot)
vm_map_protect(map, pageno, pageno + PAGE_SIZE,
VM_PROT_READ|VM_PROT_EXECUTE, 0);
} while (error == 0 && uio->uio_resid > 0);
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;
{
int error;
if (uio->uio_resid == 0)
return (0);
error = procfs_rwmem(p, uio);
return (error);
}
/*
* Given process (p), find the vnode from which
* it's text segment is being executed.
*
* 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.
*/
struct vnode *
procfs_findtextvp(p)
struct proc *p;
{
return (p->p_textvp);
}