24a1cce34f
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).
222 lines
7.4 KiB
C
222 lines
7.4 KiB
C
/*
|
|
* Copyright (c) 1991 Regents of the University of California.
|
|
* All rights reserved.
|
|
*
|
|
* This code is derived from software contributed to Berkeley by
|
|
* the Systems Programming Group of the University of Utah Computer
|
|
* Science Department and William Jolitz of UUNET Technologies Inc.
|
|
*
|
|
* 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.
|
|
*
|
|
* Derived from hp300 version by Mike Hibler, this version by William
|
|
* Jolitz uses a recursive map [a pde points to the page directory] to
|
|
* map the page tables using the pagetables themselves. This is done to
|
|
* reduce the impact on kernel virtual memory for lots of sparse address
|
|
* space, and to reduce the cost of memory to each process.
|
|
*
|
|
* from: hp300: @(#)pmap.h 7.2 (Berkeley) 12/16/90
|
|
* from: @(#)pmap.h 7.4 (Berkeley) 5/12/91
|
|
* $Id: pmap.h,v 1.26 1995/05/30 08:00:48 rgrimes Exp $
|
|
*/
|
|
|
|
#ifndef _MACHINE_PMAP_H_
|
|
#define _MACHINE_PMAP_H_
|
|
|
|
#include <machine/pte.h>
|
|
|
|
typedef unsigned int *pd_entry_t;
|
|
typedef unsigned int *pt_entry_t;
|
|
|
|
/*
|
|
* NKPDE controls the virtual space of the kernel, what ever is left, minus
|
|
* the alternate page table area is given to the user (NUPDE)
|
|
*/
|
|
/*
|
|
* NKPDE controls the virtual space of the kernel, what ever is left is
|
|
* given to the user (NUPDE)
|
|
*/
|
|
#ifndef NKPT
|
|
#if 0
|
|
#define NKPT 26 /* actual number of kernel page tables */
|
|
#else
|
|
#define NKPT 9 /* actual number of kernel page tables */
|
|
#endif
|
|
#endif
|
|
#ifndef NKPDE
|
|
#define NKPDE 63 /* addressable number of page tables/pde's */
|
|
#endif
|
|
|
|
#define NUPDE (NPTEPG-NKPDE) /* number of user pde's */
|
|
|
|
/*
|
|
* The *PTDI values control the layout of virtual memory
|
|
*
|
|
* XXX This works for now, but I am not real happy with it, I'll fix it
|
|
* right after I fix locore.s and the magic 28K hole
|
|
*/
|
|
#define APTDPTDI (NPTEPG-1) /* alt ptd entry that points to APTD */
|
|
#define KPTDI (APTDPTDI-NKPDE)/* start of kernel virtual pde's */
|
|
#define PTDPTDI (KPTDI-1) /* ptd entry that points to ptd! */
|
|
#define KSTKPTDI (PTDPTDI-1) /* ptd entry for u./kernel&user stack */
|
|
#define KSTKPTEOFF (NBPG/sizeof(pd_entry_t)-UPAGES) /* pte entry for kernel stack */
|
|
|
|
#define PDESIZE sizeof(pd_entry_t) /* for assembly files */
|
|
#define PTESIZE sizeof(pt_entry_t) /* for assembly files */
|
|
|
|
/*
|
|
* Address of current and alternate address space page table maps
|
|
* and directories.
|
|
*/
|
|
#ifdef KERNEL
|
|
extern pt_entry_t PTmap[], APTmap[], Upte;
|
|
extern pd_entry_t PTD[], APTD[], PTDpde, APTDpde, Upde;
|
|
|
|
extern int IdlePTD; /* physical address of "Idle" state directory */
|
|
#endif
|
|
|
|
/*
|
|
* virtual address to page table entry and
|
|
* to physical address. Likewise for alternate address space.
|
|
* Note: these work recursively, thus vtopte of a pte will give
|
|
* the corresponding pde that in turn maps it.
|
|
*/
|
|
#define vtopte(va) (PTmap + i386_btop(va))
|
|
#define kvtopte(va) vtopte(va)
|
|
#define ptetov(pt) (i386_ptob(pt - PTmap))
|
|
#define vtophys(va) (((int) (*vtopte(va))&PG_FRAME) | ((int)(va) & PGOFSET))
|
|
#define ispt(va) ((va) >= UPT_MIN_ADDRESS && (va) <= KPT_MAX_ADDRESS)
|
|
|
|
#define avtopte(va) (APTmap + i386_btop(va))
|
|
#define ptetoav(pt) (i386_ptob(pt - APTmap))
|
|
#define avtophys(va) (((int) (*avtopte(va))&PG_FRAME) | ((int)(va) & PGOFSET))
|
|
|
|
#ifdef KERNEL
|
|
/*
|
|
* Routine: pmap_kextract
|
|
* Function:
|
|
* Extract the physical page address associated
|
|
* kernel virtual address.
|
|
*/
|
|
static __inline vm_offset_t
|
|
pmap_kextract(vm_offset_t va)
|
|
{
|
|
vm_offset_t pa = *(int *)vtopte(va);
|
|
pa = (pa & PG_FRAME) | (va & ~PG_FRAME);
|
|
return pa;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* macros to generate page directory/table indicies
|
|
*/
|
|
|
|
#define pdei(va) (((va)&PD_MASK)>>PD_SHIFT)
|
|
#define ptei(va) (((va)&PT_MASK)>>PG_SHIFT)
|
|
|
|
/*
|
|
* Pmap stuff
|
|
*/
|
|
|
|
struct pmap {
|
|
pd_entry_t *pm_pdir; /* KVA of page directory */
|
|
boolean_t pm_pdchanged; /* pdir changed */
|
|
short pm_dref; /* page directory ref count */
|
|
short pm_count; /* pmap reference count */
|
|
struct pmap_statistics pm_stats; /* pmap statistics */
|
|
long pm_ptpages; /* more stats: PT pages */
|
|
};
|
|
|
|
typedef struct pmap *pmap_t;
|
|
|
|
#ifdef KERNEL
|
|
extern pmap_t kernel_pmap;
|
|
#endif
|
|
|
|
/*
|
|
* Macros for speed
|
|
*/
|
|
#define PMAP_ACTIVATE(pmapp, pcbp) \
|
|
if ((pmapp) != NULL /*&& (pmapp)->pm_pdchanged */) { \
|
|
(pcbp)->pcb_cr3 = \
|
|
pmap_extract(kernel_pmap, (vm_offset_t)(pmapp)->pm_pdir); \
|
|
if ((pmapp) == &curproc->p_vmspace->vm_pmap) \
|
|
load_cr3((pcbp)->pcb_cr3); \
|
|
(pmapp)->pm_pdchanged = FALSE; \
|
|
}
|
|
|
|
#define PMAP_DEACTIVATE(pmapp, pcbp)
|
|
|
|
/*
|
|
* For each vm_page_t, there is a list of all currently valid virtual
|
|
* mappings of that page. An entry is a pv_entry_t, the list is pv_table.
|
|
*/
|
|
typedef struct pv_entry {
|
|
struct pv_entry *pv_next; /* next pv_entry */
|
|
pmap_t pv_pmap; /* pmap where mapping lies */
|
|
vm_offset_t pv_va; /* virtual address for mapping */
|
|
} *pv_entry_t;
|
|
|
|
#define PV_ENTRY_NULL ((pv_entry_t) 0)
|
|
|
|
#define PV_CI 0x01 /* all entries must be cache inhibited */
|
|
#define PV_PTPAGE 0x02 /* entry maps a page table page */
|
|
|
|
#ifdef KERNEL
|
|
|
|
extern caddr_t CADDR1;
|
|
extern pt_entry_t *CMAP1;
|
|
extern vm_offset_t avail_end;
|
|
extern vm_offset_t avail_start;
|
|
extern vm_offset_t phys_avail[6];
|
|
extern pv_entry_t pv_table; /* array of entries, one per page */
|
|
extern vm_offset_t virtual_avail;
|
|
extern vm_offset_t virtual_end;
|
|
|
|
#define pa_index(pa) atop(pa - vm_first_phys)
|
|
#define pa_to_pvh(pa) (&pv_table[pa_index(pa)])
|
|
|
|
#define pmap_resident_count(pmap) ((pmap)->pm_stats.resident_count)
|
|
|
|
struct pcb;
|
|
|
|
void pmap_activate __P((pmap_t, struct pcb *));
|
|
pmap_t pmap_kernel __P((void));
|
|
boolean_t pmap_page_exists __P((pmap_t, vm_offset_t));
|
|
pt_entry_t *pmap_pte __P((pmap_t, vm_offset_t));
|
|
vm_page_t pmap_pte_vm_page __P((pmap_t, vm_offset_t));
|
|
void *pmap_mapdev __P((vm_offset_t, vm_size_t));
|
|
void pmap_growkernel __P((vm_offset_t));
|
|
void pmap_bootstrap __P(( vm_offset_t, vm_offset_t));
|
|
void pmap_use_pt __P((pmap_t, vm_offset_t));
|
|
void pmap_unuse_pt __P((pmap_t, vm_offset_t));
|
|
|
|
#endif /* KERNEL */
|
|
|
|
#endif /* !_MACHINE_PMAP_H_ */
|