9f0819bc54
Re-enables the RSS limiting, and the routine is now tail-recursive, making it much more safe (eliminates the possiblity of kernel stack overflow.) Also, the RSS limiting is a little more intelligent about finding the likely objects that are pushing the process over the limit. Added some sysctls that help with VM system tuning. New sysctl features: 1) Enable/disable lru pageout algorithm. vm.pageout_algorithm = 0, default algorithm that works well, especially using X windows and heavy memory loading. Can have adverse effects, sometimes slowing down program loading. vm.pageout_algorithm = 1, close to true LRU. Works much better than clock, etc. Does not work as well as the default algorithm in general. Certain memory "malloc" type benchmarks work a little better with this setting. Please give me feedback on the performance results associated with these. 2) Enable/disable swapping. vm.swapping_enabled = 1, default. vm.swapping_enabled = 0, useful for cases where swapping degrades performance. The config option "NO_SWAPPING" is still operative, and takes precedence over the sysctl. If "NO_SWAPPING" is specified, the sysctl still exists, but "vm.swapping_enabled" is hard-wired to "0". Each of these can be changed "on the fly."
335 lines
10 KiB
C
335 lines
10 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 1.28 1996/06/08 06:48:35 dyson 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_pindex_t pindex; /* offset into object (O,P) */
|
|
vm_offset_t phys_addr; /* physical address of page */
|
|
u_short queue:4, /* page queue index */
|
|
flags:12; /* see below */
|
|
u_short wire_count; /* wired down maps refs (P) */
|
|
short hold_count; /* page hold count */
|
|
u_char act_count; /* page usage count */
|
|
u_char busy; /* page busy count */
|
|
/* NOTE that these must support one bit per DEV_BSIZE in a page!!! */
|
|
/* so, on normal X86 kernels, they must be at least 8 bits wide */
|
|
u_char valid; /* map of valid DEV_BSIZE chunks */
|
|
u_char dirty; /* map of dirty DEV_BSIZE chunks */
|
|
};
|
|
|
|
#define PQ_NONE 0
|
|
#define PQ_FREE 1
|
|
#define PQ_ZERO 2
|
|
#define PQ_INACTIVE 3
|
|
#define PQ_ACTIVE 4
|
|
#define PQ_CACHE 5
|
|
|
|
/*
|
|
* These are the flags defined for vm_page.
|
|
*
|
|
* Note: PG_FILLED and PG_DIRTY are added for the filesystems.
|
|
*/
|
|
#define PG_BUSY 0x01 /* page is in transit (O) */
|
|
#define PG_WANTED 0x02 /* someone is waiting for page (O) */
|
|
#define PG_TABLED 0x04 /* page is in VP table (O) */
|
|
#define PG_FICTITIOUS 0x08 /* physical page doesn't exist (O) */
|
|
#define PG_WRITEABLE 0x10 /* page is mapped writeable */
|
|
#define PG_MAPPED 0x20 /* page is mapped */
|
|
#define PG_ZERO 0x40 /* page is zeroed */
|
|
#define PG_REFERENCED 0x80 /* page has been referenced */
|
|
#define PG_CLEANCHK 0x100 /* page has been checked for cleaning */
|
|
|
|
/*
|
|
* Misc constants.
|
|
*/
|
|
|
|
#define ACT_DECLINE 1
|
|
#define ACT_ADVANCE 3
|
|
#define ACT_INIT 5
|
|
#define ACT_MAX 32
|
|
#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 reclamation.
|
|
* This is the list of pages that should be
|
|
* paged out next.
|
|
*
|
|
* active
|
|
* Pages that are "active" i.e. they have been
|
|
* recently referenced.
|
|
*
|
|
* zero
|
|
* Pages that are really free and have been pre-zeroed
|
|
*
|
|
*/
|
|
|
|
extern struct pglist vm_page_queue_free; /* memory free queue */
|
|
extern struct pglist vm_page_queue_zero; /* zeroed 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 int vm_page_zero_count;
|
|
|
|
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
|
|
#define VM_ALLOC_ZERO 3
|
|
|
|
void vm_page_activate __P((vm_page_t));
|
|
vm_page_t vm_page_alloc __P((vm_object_t, vm_pindex_t, int));
|
|
void vm_page_cache __P((register vm_page_t));
|
|
static __inline 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_free_zero __P((vm_page_t));
|
|
void vm_page_insert __P((vm_page_t, vm_object_t, vm_pindex_t));
|
|
vm_page_t vm_page_lookup __P((vm_object_t, vm_pindex_t));
|
|
void vm_page_remove __P((vm_page_t));
|
|
void vm_page_rename __P((vm_page_t, vm_object_t, vm_pindex_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));
|
|
void vm_page_unqueue __P((vm_page_t));
|
|
void vm_page_unqueue_nowakeup __P((vm_page_t));
|
|
void vm_page_set_validclean __P((vm_page_t, int, int));
|
|
void vm_page_set_invalid __P((vm_page_t, int, int));
|
|
static __inline boolean_t vm_page_zero_fill __P((vm_page_t));
|
|
int vm_page_is_valid __P((vm_page_t, int, int));
|
|
void vm_page_test_dirty __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;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* vm_page_zero_fill:
|
|
*
|
|
* Zero-fill the specified page.
|
|
* Written as a standard pagein routine, to
|
|
* be used by the zero-fill object.
|
|
*/
|
|
static __inline boolean_t
|
|
vm_page_zero_fill(m)
|
|
vm_page_t m;
|
|
{
|
|
pmap_zero_page(VM_PAGE_TO_PHYS(m));
|
|
return (TRUE);
|
|
}
|
|
|
|
/*
|
|
* vm_page_copy:
|
|
*
|
|
* Copy one page to another
|
|
*/
|
|
static __inline void
|
|
vm_page_copy(src_m, dest_m)
|
|
vm_page_t src_m;
|
|
vm_page_t dest_m;
|
|
{
|
|
pmap_copy_page(VM_PAGE_TO_PHYS(src_m), VM_PAGE_TO_PHYS(dest_m));
|
|
dest_m->valid = VM_PAGE_BITS_ALL;
|
|
}
|
|
|
|
#endif /* KERNEL */
|
|
#endif /* !_VM_PAGE_ */
|