2001-06-10 02:39:37 +00:00
|
|
|
/*-
|
|
|
|
|
* Copyright (C) 1995, 1996 Wolfgang Solfrank.
|
|
|
|
|
* Copyright (C) 1995, 1996 TooLs GmbH.
|
|
|
|
|
* All rights reserved.
|
|
|
|
|
*
|
|
|
|
|
* 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 TooLs GmbH.
|
|
|
|
|
* 4. The name of TooLs GmbH may not be used to endorse or promote products
|
|
|
|
|
* derived from this software without specific prior written permission.
|
|
|
|
|
*
|
|
|
|
|
* THIS SOFTWARE IS PROVIDED BY TOOLS GMBH ``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 TOOLS GMBH 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.
|
|
|
|
|
*
|
|
|
|
|
* $NetBSD: vmparam.h,v 1.11 2000/02/11 19:25:16 thorpej Exp $
|
|
|
|
|
* $FreeBSD$
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#ifndef _MACHINE_VMPARAM_H_
|
|
|
|
|
#define _MACHINE_VMPARAM_H_
|
|
|
|
|
|
|
|
|
|
#define USRSTACK VM_MAXUSER_ADDRESS
|
|
|
|
|
|
|
|
|
|
#ifndef MAXTSIZ
|
|
|
|
|
#define MAXTSIZ (16*1024*1024) /* max text size */
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#ifndef DFLDSIZ
|
|
|
|
|
#define DFLDSIZ (32*1024*1024) /* default data size */
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#ifndef MAXDSIZ
|
|
|
|
|
#define MAXDSIZ (512*1024*1024) /* max data size */
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#ifndef DFLSSIZ
|
|
|
|
|
#define DFLSSIZ (1*1024*1024) /* default stack size */
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#ifndef MAXSSIZ
|
|
|
|
|
#define MAXSSIZ (32*1024*1024) /* max stack size */
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Size of shared memory map
|
|
|
|
|
*/
|
|
|
|
|
#ifndef SHMMAXPGS
|
|
|
|
|
#define SHMMAXPGS 1024
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* The time for a process to be blocked before being very swappable.
|
|
|
|
|
* This is a number of seconds which the system takes as being a non-trivial
|
|
|
|
|
* amount of real time. You probably shouldn't change this;
|
|
|
|
|
* it is used in subtle ways (fractions and multiples of it are, that is, like
|
|
|
|
|
* half of a ``long time'', almost a long time, etc.)
|
|
|
|
|
* It is related to human patience and other factors which don't really
|
|
|
|
|
* change over time.
|
|
|
|
|
*/
|
|
|
|
|
#define MAXSLP 20
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Would like to have MAX addresses = 0, but this doesn't (currently) work
|
|
|
|
|
*/
|
2008-03-03 13:20:52 +00:00
|
|
|
#if !defined(LOCORE)
|
2001-06-10 02:39:37 +00:00
|
|
|
#define VM_MIN_ADDRESS ((vm_offset_t)0)
|
2008-03-03 13:20:52 +00:00
|
|
|
|
2001-06-10 02:39:37 +00:00
|
|
|
#define VM_MAXUSER_ADDRESS ((vm_offset_t)0x7ffff000)
|
2008-03-03 13:20:52 +00:00
|
|
|
|
|
|
|
|
#else
|
|
|
|
|
#define VM_MIN_ADDRESS 0
|
|
|
|
|
|
|
|
|
|
#define VM_MAXUSER_ADDRESS 0x7ffff000
|
|
|
|
|
|
|
|
|
|
#endif /* LOCORE */
|
|
|
|
|
|
2001-06-10 02:39:37 +00:00
|
|
|
#define VM_MAX_ADDRESS VM_MAXUSER_ADDRESS
|
2008-03-03 13:20:52 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
#if defined(AIM) /* AIM */
|
|
|
|
|
|
|
|
|
|
#define KERNBASE 0x00100000 /* start of kernel virtual */
|
|
|
|
|
|
2001-06-10 02:39:37 +00:00
|
|
|
#define VM_MIN_KERNEL_ADDRESS ((vm_offset_t)(KERNEL_SR << ADDR_SR_SHFT))
|
2004-03-02 06:49:21 +00:00
|
|
|
#define VM_MAX_KERNEL_ADDRESS (VM_MIN_KERNEL_ADDRESS + 2*SEGMENT_LENGTH - 1)
|
2001-06-10 02:39:37 +00:00
|
|
|
|
2008-03-03 13:20:52 +00:00
|
|
|
/*
|
|
|
|
|
* Use the direct-mapped BAT registers for UMA small allocs. This
|
|
|
|
|
* takes pressure off the small amount of available KVA.
|
|
|
|
|
*/
|
|
|
|
|
#define UMA_MD_SMALL_ALLOC
|
|
|
|
|
|
|
|
|
|
#else
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Kernel CCSRBAR location. We make this the reset location.
|
|
|
|
|
*/
|
|
|
|
|
#define CCSRBAR_VA 0xfef00000
|
|
|
|
|
#define CCSRBAR_SIZE 0x00100000
|
|
|
|
|
|
|
|
|
|
#define KERNBASE 0xc0000000 /* start of kernel virtual */
|
|
|
|
|
|
|
|
|
|
#define VM_MIN_KERNEL_ADDRESS KERNBASE
|
|
|
|
|
#define VM_MAX_KERNEL_ADDRESS CCSRBAR_VA
|
|
|
|
|
|
|
|
|
|
#endif /* AIM/E500 */
|
2004-02-11 07:27:34 +00:00
|
|
|
|
2001-06-10 02:39:37 +00:00
|
|
|
/* XXX max. amount of KVM to be used by buffers. */
|
|
|
|
|
#ifndef VM_MAX_KERNEL_BUF
|
|
|
|
|
#define VM_MAX_KERNEL_BUF (SEGMENT_LENGTH * 7 / 10)
|
|
|
|
|
#endif
|
|
|
|
|
|
2008-03-03 13:20:52 +00:00
|
|
|
#if !defined(LOCORE)
|
2001-06-10 02:39:37 +00:00
|
|
|
struct pmap_physseg {
|
|
|
|
|
struct pv_entry *pvent;
|
|
|
|
|
char *attrs;
|
|
|
|
|
};
|
2008-03-03 13:20:52 +00:00
|
|
|
#endif
|
2001-06-10 02:39:37 +00:00
|
|
|
|
|
|
|
|
#define VM_PHYSSEG_MAX 16 /* 1? */
|
|
|
|
|
|
2007-05-05 19:50:28 +00:00
|
|
|
/*
|
|
|
|
|
* The physical address space is densely populated.
|
|
|
|
|
*/
|
|
|
|
|
#define VM_PHYSSEG_DENSE
|
|
|
|
|
|
Enable the new physical memory allocator.
This allocator uses a binary buddy system with a twist. First and
foremost, this allocator is required to support the implementation of
superpages. As a side effect, it enables a more robust implementation
of contigmalloc(9). Moreover, this reimplementation of
contigmalloc(9) eliminates the acquisition of Giant by
contigmalloc(..., M_NOWAIT, ...).
The twist is that this allocator tries to reduce the number of TLB
misses incurred by accesses through a direct map to small, UMA-managed
objects and page table pages. Roughly speaking, the physical pages
that are allocated for such purposes are clustered together in the
physical address space. The performance benefits vary. In the most
extreme case, a uniprocessor kernel running on an Opteron, I measured
an 18% reduction in system time during a buildworld.
This allocator does not implement page coloring. The reason is that
superpages have much the same effect. The contiguous physical memory
allocation necessary for a superpage is inherently colored.
Finally, the one caveat is that this allocator does not effectively
support prezeroed pages. I hope this is temporary. On i386, this is
a slight pessimization. However, on amd64, the beneficial effects of
the direct-map optimization outweigh the ill effects. I speculate
that this is true in general of machines with a direct map.
Approved by: re
2007-06-16 04:57:06 +00:00
|
|
|
/*
|
Change the management of cached pages (PQ_CACHE) in two fundamental
ways:
(1) Cached pages are no longer kept in the object's resident page
splay tree and memq. Instead, they are kept in a separate per-object
splay tree of cached pages. However, access to this new per-object
splay tree is synchronized by the _free_ page queues lock, not to be
confused with the heavily contended page queues lock. Consequently, a
cached page can be reclaimed by vm_page_alloc(9) without acquiring the
object's lock or the page queues lock.
This solves a problem independently reported by tegge@ and Isilon.
Specifically, they observed the page daemon consuming a great deal of
CPU time because of pages bouncing back and forth between the cache
queue (PQ_CACHE) and the inactive queue (PQ_INACTIVE). The source of
this problem turned out to be a deadlock avoidance strategy employed
when selecting a cached page to reclaim in vm_page_select_cache().
However, the root cause was really that reclaiming a cached page
required the acquisition of an object lock while the page queues lock
was already held. Thus, this change addresses the problem at its
root, by eliminating the need to acquire the object's lock.
Moreover, keeping cached pages in the object's primary splay tree and
memq was, in effect, optimizing for the uncommon case. Cached pages
are reclaimed far, far more often than they are reactivated. Instead,
this change makes reclamation cheaper, especially in terms of
synchronization overhead, and reactivation more expensive, because
reactivated pages will have to be reentered into the object's primary
splay tree and memq.
(2) Cached pages are now stored alongside free pages in the physical
memory allocator's buddy queues, increasing the likelihood that large
allocations of contiguous physical memory (i.e., superpages) will
succeed.
Finally, as a result of this change long-standing restrictions on when
and where a cached page can be reclaimed and returned by
vm_page_alloc(9) are eliminated. Specifically, calls to
vm_page_alloc(9) specifying VM_ALLOC_INTERRUPT can now reclaim and
return a formerly cached page. Consequently, a call to malloc(9)
specifying M_NOWAIT is less likely to fail.
Discussed with: many over the course of the summer, including jeff@,
Justin Husted @ Isilon, peter@, tegge@
Tested by: an earlier version by kris@
Approved by: re (kensmith)
2007-09-25 06:25:06 +00:00
|
|
|
* Create three free page pools: VM_FREEPOOL_DEFAULT is the default pool
|
Enable the new physical memory allocator.
This allocator uses a binary buddy system with a twist. First and
foremost, this allocator is required to support the implementation of
superpages. As a side effect, it enables a more robust implementation
of contigmalloc(9). Moreover, this reimplementation of
contigmalloc(9) eliminates the acquisition of Giant by
contigmalloc(..., M_NOWAIT, ...).
The twist is that this allocator tries to reduce the number of TLB
misses incurred by accesses through a direct map to small, UMA-managed
objects and page table pages. Roughly speaking, the physical pages
that are allocated for such purposes are clustered together in the
physical address space. The performance benefits vary. In the most
extreme case, a uniprocessor kernel running on an Opteron, I measured
an 18% reduction in system time during a buildworld.
This allocator does not implement page coloring. The reason is that
superpages have much the same effect. The contiguous physical memory
allocation necessary for a superpage is inherently colored.
Finally, the one caveat is that this allocator does not effectively
support prezeroed pages. I hope this is temporary. On i386, this is
a slight pessimization. However, on amd64, the beneficial effects of
the direct-map optimization outweigh the ill effects. I speculate
that this is true in general of machines with a direct map.
Approved by: re
2007-06-16 04:57:06 +00:00
|
|
|
* from which physical pages are allocated and VM_FREEPOOL_DIRECT is
|
|
|
|
|
* the pool from which physical pages for small UMA objects are
|
|
|
|
|
* allocated.
|
|
|
|
|
*/
|
Change the management of cached pages (PQ_CACHE) in two fundamental
ways:
(1) Cached pages are no longer kept in the object's resident page
splay tree and memq. Instead, they are kept in a separate per-object
splay tree of cached pages. However, access to this new per-object
splay tree is synchronized by the _free_ page queues lock, not to be
confused with the heavily contended page queues lock. Consequently, a
cached page can be reclaimed by vm_page_alloc(9) without acquiring the
object's lock or the page queues lock.
This solves a problem independently reported by tegge@ and Isilon.
Specifically, they observed the page daemon consuming a great deal of
CPU time because of pages bouncing back and forth between the cache
queue (PQ_CACHE) and the inactive queue (PQ_INACTIVE). The source of
this problem turned out to be a deadlock avoidance strategy employed
when selecting a cached page to reclaim in vm_page_select_cache().
However, the root cause was really that reclaiming a cached page
required the acquisition of an object lock while the page queues lock
was already held. Thus, this change addresses the problem at its
root, by eliminating the need to acquire the object's lock.
Moreover, keeping cached pages in the object's primary splay tree and
memq was, in effect, optimizing for the uncommon case. Cached pages
are reclaimed far, far more often than they are reactivated. Instead,
this change makes reclamation cheaper, especially in terms of
synchronization overhead, and reactivation more expensive, because
reactivated pages will have to be reentered into the object's primary
splay tree and memq.
(2) Cached pages are now stored alongside free pages in the physical
memory allocator's buddy queues, increasing the likelihood that large
allocations of contiguous physical memory (i.e., superpages) will
succeed.
Finally, as a result of this change long-standing restrictions on when
and where a cached page can be reclaimed and returned by
vm_page_alloc(9) are eliminated. Specifically, calls to
vm_page_alloc(9) specifying VM_ALLOC_INTERRUPT can now reclaim and
return a formerly cached page. Consequently, a call to malloc(9)
specifying M_NOWAIT is less likely to fail.
Discussed with: many over the course of the summer, including jeff@,
Justin Husted @ Isilon, peter@, tegge@
Tested by: an earlier version by kris@
Approved by: re (kensmith)
2007-09-25 06:25:06 +00:00
|
|
|
#define VM_NFREEPOOL 3
|
|
|
|
|
#define VM_FREEPOOL_CACHE 2
|
Enable the new physical memory allocator.
This allocator uses a binary buddy system with a twist. First and
foremost, this allocator is required to support the implementation of
superpages. As a side effect, it enables a more robust implementation
of contigmalloc(9). Moreover, this reimplementation of
contigmalloc(9) eliminates the acquisition of Giant by
contigmalloc(..., M_NOWAIT, ...).
The twist is that this allocator tries to reduce the number of TLB
misses incurred by accesses through a direct map to small, UMA-managed
objects and page table pages. Roughly speaking, the physical pages
that are allocated for such purposes are clustered together in the
physical address space. The performance benefits vary. In the most
extreme case, a uniprocessor kernel running on an Opteron, I measured
an 18% reduction in system time during a buildworld.
This allocator does not implement page coloring. The reason is that
superpages have much the same effect. The contiguous physical memory
allocation necessary for a superpage is inherently colored.
Finally, the one caveat is that this allocator does not effectively
support prezeroed pages. I hope this is temporary. On i386, this is
a slight pessimization. However, on amd64, the beneficial effects of
the direct-map optimization outweigh the ill effects. I speculate
that this is true in general of machines with a direct map.
Approved by: re
2007-06-16 04:57:06 +00:00
|
|
|
#define VM_FREEPOOL_DEFAULT 0
|
|
|
|
|
#define VM_FREEPOOL_DIRECT 1
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Create one free page list.
|
|
|
|
|
*/
|
2001-06-10 02:39:37 +00:00
|
|
|
#define VM_NFREELIST 1
|
|
|
|
|
#define VM_FREELIST_DEFAULT 0
|
|
|
|
|
|
Enable the new physical memory allocator.
This allocator uses a binary buddy system with a twist. First and
foremost, this allocator is required to support the implementation of
superpages. As a side effect, it enables a more robust implementation
of contigmalloc(9). Moreover, this reimplementation of
contigmalloc(9) eliminates the acquisition of Giant by
contigmalloc(..., M_NOWAIT, ...).
The twist is that this allocator tries to reduce the number of TLB
misses incurred by accesses through a direct map to small, UMA-managed
objects and page table pages. Roughly speaking, the physical pages
that are allocated for such purposes are clustered together in the
physical address space. The performance benefits vary. In the most
extreme case, a uniprocessor kernel running on an Opteron, I measured
an 18% reduction in system time during a buildworld.
This allocator does not implement page coloring. The reason is that
superpages have much the same effect. The contiguous physical memory
allocation necessary for a superpage is inherently colored.
Finally, the one caveat is that this allocator does not effectively
support prezeroed pages. I hope this is temporary. On i386, this is
a slight pessimization. However, on amd64, the beneficial effects of
the direct-map optimization outweigh the ill effects. I speculate
that this is true in general of machines with a direct map.
Approved by: re
2007-06-16 04:57:06 +00:00
|
|
|
/*
|
|
|
|
|
* The largest allocation size is 4MB.
|
|
|
|
|
*/
|
|
|
|
|
#define VM_NFREEORDER 11
|
|
|
|
|
|
2007-12-27 16:45:39 +00:00
|
|
|
/*
|
|
|
|
|
* Disable superpage reservations.
|
|
|
|
|
*/
|
|
|
|
|
#ifndef VM_NRESERVLEVEL
|
|
|
|
|
#define VM_NRESERVLEVEL 0
|
|
|
|
|
#endif
|
|
|
|
|
|
2001-06-10 02:39:37 +00:00
|
|
|
#ifndef VM_INITIAL_PAGEIN
|
|
|
|
|
#define VM_INITIAL_PAGEIN 16
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#ifndef SGROWSIZ
|
|
|
|
|
#define SGROWSIZ (128UL*1024) /* amount to grow stack */
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#ifndef VM_KMEM_SIZE
|
|
|
|
|
#define VM_KMEM_SIZE (12 * 1024 * 1024)
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#endif /* _MACHINE_VMPARAM_H_ */
|
