c8b0a7332c
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).
295 lines
9.5 KiB
C
295 lines
9.5 KiB
C
/*
|
|
* Copyright (c) 1991, 1993
|
|
* The Regents of the University of California. All rights reserved.
|
|
*
|
|
* This code is derived from software contributed to Berkeley by
|
|
* The Mach Operating System project at Carnegie-Mellon University.
|
|
*
|
|
* 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.
|
|
*
|
|
* from: @(#)vm_page.h 8.2 (Berkeley) 12/13/93
|
|
*
|
|
*
|
|
* Copyright (c) 1987, 1990 Carnegie-Mellon University.
|
|
* All rights reserved.
|
|
*
|
|
* Authors: Avadis Tevanian, Jr., Michael Wayne Young
|
|
*
|
|
* Permission to use, copy, modify and distribute this software and
|
|
* its documentation is hereby granted, provided that both the copyright
|
|
* notice and this permission notice appear in all copies of the
|
|
* software, derivative works or modified versions, and any portions
|
|
* thereof, and that both notices appear in supporting documentation.
|
|
*
|
|
* CARNEGIE MELLON ALLOWS FREE USE OF THIS SOFTWARE IN ITS "AS IS"
|
|
* CONDITION. CARNEGIE MELLON DISCLAIMS ANY LIABILITY OF ANY KIND
|
|
* FOR ANY DAMAGES WHATSOEVER RESULTING FROM THE USE OF THIS SOFTWARE.
|
|
*
|
|
* Carnegie Mellon requests users of this software to return to
|
|
*
|
|
* Software Distribution Coordinator or Software.Distribution@CS.CMU.EDU
|
|
* School of Computer Science
|
|
* Carnegie Mellon University
|
|
* Pittsburgh PA 15213-3890
|
|
*
|
|
* any improvements or extensions that they make and grant Carnegie the
|
|
* rights to redistribute these changes.
|
|
*
|
|
* $Id: vm_page.h,v 1.18 1995/04/23 08:05:49 bde Exp $
|
|
*/
|
|
|
|
/*
|
|
* Resident memory system definitions.
|
|
*/
|
|
|
|
#ifndef _VM_PAGE_
|
|
#define _VM_PAGE_
|
|
|
|
#include <vm/pmap.h>
|
|
/*
|
|
* Management of resident (logical) pages.
|
|
*
|
|
* A small structure is kept for each resident
|
|
* page, indexed by page number. Each structure
|
|
* is an element of several lists:
|
|
*
|
|
* A hash table bucket used to quickly
|
|
* perform object/offset lookups
|
|
*
|
|
* A list of all pages for a given object,
|
|
* so they can be quickly deactivated at
|
|
* time of deallocation.
|
|
*
|
|
* An ordered list of pages due for pageout.
|
|
*
|
|
* In addition, the structure contains the object
|
|
* and offset to which this page belongs (for pageout),
|
|
* and sundry status bits.
|
|
*
|
|
* Fields in this structure are locked either by the lock on the
|
|
* object that the page belongs to (O) or by the lock on the page
|
|
* queues (P).
|
|
*/
|
|
|
|
TAILQ_HEAD(pglist, vm_page);
|
|
|
|
struct vm_page {
|
|
TAILQ_ENTRY(vm_page) pageq; /* queue info for FIFO queue or free list (P) */
|
|
TAILQ_ENTRY(vm_page) hashq; /* hash table links (O) */
|
|
TAILQ_ENTRY(vm_page) listq; /* pages in same object (O) */
|
|
|
|
vm_object_t object; /* which object am I in (O,P) */
|
|
vm_offset_t offset; /* offset into object (O,P) */
|
|
vm_offset_t phys_addr; /* physical address of page */
|
|
|
|
u_short wire_count; /* wired down maps refs (P) */
|
|
u_short flags; /* see below */
|
|
short hold_count; /* page hold count */
|
|
u_short act_count; /* page usage count */
|
|
u_short bmapped; /* number of buffers mapped */
|
|
u_short busy; /* page busy count */
|
|
u_short valid; /* map of valid DEV_BSIZE chunks */
|
|
u_short dirty; /* map of dirty DEV_BSIZE chunks */
|
|
};
|
|
|
|
/*
|
|
* These are the flags defined for vm_page.
|
|
*
|
|
* Note: PG_FILLED and PG_DIRTY are added for the filesystems.
|
|
*/
|
|
#define PG_INACTIVE 0x0001 /* page is in inactive list (P) */
|
|
#define PG_ACTIVE 0x0002 /* page is in active list (P) */
|
|
#define PG_BUSY 0x0010 /* page is in transit (O) */
|
|
#define PG_WANTED 0x0020 /* someone is waiting for page (O) */
|
|
#define PG_TABLED 0x0040 /* page is in VP table (O) */
|
|
#define PG_COPYONWRITE 0x0080 /* must copy page before changing (O) */
|
|
#define PG_FICTITIOUS 0x0100 /* physical page doesn't exist (O) */
|
|
#define PG_WRITEABLE 0x0200 /* page is mapped writeable */
|
|
#define PG_MAPPED 0x0400 /* page is mapped */
|
|
#define PG_REFERENCED 0x1000 /* page has been referenced */
|
|
#define PG_CACHE 0x4000 /* On VMIO cache */
|
|
#define PG_FREE 0x8000 /* page is in free list */
|
|
|
|
/*
|
|
* Misc constants.
|
|
*/
|
|
|
|
#define ACT_DECLINE 1
|
|
#define ACT_ADVANCE 3
|
|
#define ACT_MAX 100
|
|
#define PFCLUSTER_BEHIND 3
|
|
#define PFCLUSTER_AHEAD 3
|
|
|
|
#ifdef KERNEL
|
|
/*
|
|
* Each pageable resident page falls into one of four lists:
|
|
*
|
|
* free
|
|
* Available for allocation now.
|
|
*
|
|
* The following are all LRU sorted:
|
|
*
|
|
* cache
|
|
* Almost available for allocation. Still in an
|
|
* object, but clean and immediately freeable at
|
|
* non-interrupt times.
|
|
*
|
|
* inactive
|
|
* Low activity, candidates for reclaimation.
|
|
* This is the list of pages that should be
|
|
* paged out next.
|
|
*
|
|
* active
|
|
* Pages that are "active" i.e. they have been
|
|
* recently referenced.
|
|
*/
|
|
|
|
extern struct pglist vm_page_queue_free; /* memory free queue */
|
|
extern struct pglist vm_page_queue_active; /* active memory queue */
|
|
extern struct pglist vm_page_queue_inactive; /* inactive memory queue */
|
|
extern struct pglist vm_page_queue_cache; /* cache memory queue */
|
|
|
|
extern vm_page_t vm_page_array; /* First resident page in table */
|
|
extern long first_page; /* first physical page number */
|
|
|
|
/* ... represented in vm_page_array */
|
|
extern long last_page; /* last physical page number */
|
|
|
|
/* ... represented in vm_page_array */
|
|
/* [INCLUSIVE] */
|
|
extern vm_offset_t first_phys_addr; /* physical address for first_page */
|
|
extern vm_offset_t last_phys_addr; /* physical address for last_page */
|
|
|
|
#define VM_PAGE_TO_PHYS(entry) ((entry)->phys_addr)
|
|
|
|
#define IS_VM_PHYSADDR(pa) \
|
|
((pa) >= first_phys_addr && (pa) <= last_phys_addr)
|
|
|
|
#define PHYS_TO_VM_PAGE(pa) \
|
|
(&vm_page_array[atop(pa) - first_page ])
|
|
|
|
/*
|
|
* Functions implemented as macros
|
|
*/
|
|
|
|
#define PAGE_ASSERT_WAIT(m, interruptible) { \
|
|
(m)->flags |= PG_WANTED; \
|
|
assert_wait((int) (m), (interruptible)); \
|
|
}
|
|
|
|
#define PAGE_WAKEUP(m) { \
|
|
(m)->flags &= ~PG_BUSY; \
|
|
if ((m)->flags & PG_WANTED) { \
|
|
(m)->flags &= ~PG_WANTED; \
|
|
wakeup((caddr_t) (m)); \
|
|
} \
|
|
}
|
|
|
|
#if PAGE_SIZE == 4096
|
|
#define VM_PAGE_BITS_ALL 0xff
|
|
#endif
|
|
|
|
#if PAGE_SIZE == 8192
|
|
#define VM_PAGE_BITS_ALL 0xffff
|
|
#endif
|
|
|
|
#define VM_ALLOC_NORMAL 0
|
|
#define VM_ALLOC_INTERRUPT 1
|
|
#define VM_ALLOC_SYSTEM 2
|
|
|
|
void vm_page_activate __P((vm_page_t));
|
|
vm_page_t vm_page_alloc __P((vm_object_t, vm_offset_t, int));
|
|
void vm_page_cache __P((register vm_page_t));
|
|
void vm_page_copy __P((vm_page_t, vm_page_t));
|
|
void vm_page_deactivate __P((vm_page_t));
|
|
void vm_page_free __P((vm_page_t));
|
|
void vm_page_insert __P((vm_page_t, vm_object_t, vm_offset_t));
|
|
vm_page_t vm_page_lookup __P((vm_object_t, vm_offset_t));
|
|
void vm_page_remove __P((vm_page_t));
|
|
void vm_page_rename __P((vm_page_t, vm_object_t, vm_offset_t));
|
|
vm_offset_t vm_page_startup __P((vm_offset_t, vm_offset_t, vm_offset_t));
|
|
void vm_page_unwire __P((vm_page_t));
|
|
void vm_page_wire __P((vm_page_t));
|
|
boolean_t vm_page_zero_fill __P((vm_page_t));
|
|
void vm_page_set_dirty __P((vm_page_t, int, int));
|
|
void vm_page_set_clean __P((vm_page_t, int, int));
|
|
int vm_page_is_clean __P((vm_page_t, int, int));
|
|
void vm_page_set_valid __P((vm_page_t, int, int));
|
|
void vm_page_set_invalid __P((vm_page_t, int, int));
|
|
int vm_page_is_valid __P((vm_page_t, int, int));
|
|
void vm_page_test_dirty __P((vm_page_t));
|
|
void vm_page_unqueue __P((vm_page_t ));
|
|
int vm_page_bits __P((int, int));
|
|
|
|
|
|
/*
|
|
* Keep page from being freed by the page daemon
|
|
* much of the same effect as wiring, except much lower
|
|
* overhead and should be used only for *very* temporary
|
|
* holding ("wiring").
|
|
*/
|
|
static __inline void
|
|
vm_page_hold(vm_page_t mem)
|
|
{
|
|
mem->hold_count++;
|
|
}
|
|
|
|
#ifdef DIAGNOSTIC
|
|
#include <sys/systm.h> /* make GCC shut up */
|
|
#endif
|
|
|
|
static __inline void
|
|
vm_page_unhold(vm_page_t mem)
|
|
{
|
|
#ifdef DIAGNOSTIC
|
|
if (--mem->hold_count < 0)
|
|
panic("vm_page_unhold: hold count < 0!!!");
|
|
#else
|
|
--mem->hold_count;
|
|
#endif
|
|
}
|
|
|
|
static __inline void
|
|
vm_page_protect(vm_page_t mem, int prot)
|
|
{
|
|
if (prot == VM_PROT_NONE) {
|
|
if (mem->flags & (PG_WRITEABLE|PG_MAPPED)) {
|
|
pmap_page_protect(VM_PAGE_TO_PHYS(mem), prot);
|
|
mem->flags &= ~(PG_WRITEABLE|PG_MAPPED);
|
|
}
|
|
} else if ((prot == VM_PROT_READ) && (mem->flags & PG_WRITEABLE)) {
|
|
pmap_page_protect(VM_PAGE_TO_PHYS(mem), prot);
|
|
mem->flags &= ~PG_WRITEABLE;
|
|
}
|
|
}
|
|
|
|
|
|
#endif /* KERNEL */
|
|
#endif /* !_VM_PAGE_ */
|