5abb86e605
problems. Tor Egge and others have helped with various VM bugs lately, but don't blame him -- blame me!!! pmap.c: 1) Create an object for kernel page table allocations. This fixes a bogus allocation method previously used for such, by grabbing pages from the kernel object, using bogus pindexes. (This was a code cleanup, and perhaps a minor system stability issue.) pmap.c: 2) Pre-set the modify and accessed bits when prudent. This will decrease bus traffic under certain circumstances. vfs_bio.c, vfs_cluster.c: 3) Rather than calculating the beginning virtual byte offset multiple times, stick the offset into the buffer header, so that the calculated offset can be reused. (Long long multiplies are often expensive, and this is a probably unmeasurable performance improvement, and code cleanup.) vfs_bio.c: 4) Handle write recursion more intelligently (but not perfectly) so that it is less likely to cause a system panic, and is also much more robust. vfs_bio.c: 5) getblk incorrectly wrote out blocks that are incorrectly sized. The problem is fixed, and writes blocks out ONLY when B_DELWRI is true. vfs_bio.c: 6) Check that already constituted buffers have fully valid pages. If not, then make sure that the B_CACHE bit is not set. (This was a major source of Sig-11 type problems.) vfs_bio.c: 7) Fix a potential system deadlock due to an incorrectly specified sleep priority while waiting for a buffer write operation. The change that I made opens the system up to serious problems, and we need to examine the issue of process sleep priorities. vfs_cluster.c, vfs_bio.c: 8) Make clustered reads work more correctly (and more completely) when buffers are already constituted, but not fully valid. (This was another system reliability issue.) vfs_subr.c, ffs_inode.c: 9) Create a vtruncbuf function, which is used by filesystems that can truncate files. The vinvalbuf forced a file sync type operation, while vtruncbuf only invalidates the buffers past the new end of file, and also invalidates the appropriate pages. (This was a system reliabiliy and performance issue.) 10) Modify FFS to use vtruncbuf. vm_object.c: 11) Make the object rundown mechanism for OBJT_VNODE type objects work more correctly. Included in that fix, create pager entries for the OBJT_DEAD pager type, so that paging requests that might slip in during race conditions are properly handled. (This was a system reliability issue.) vm_page.c: 12) Make some of the page validation routines be a little less picky about arguments passed to them. Also, support page invalidation change the object generation count so that we handle generation counts a little more robustly. vm_pageout.c: 13) Further reduce pageout daemon activity when the system doesn't need help from it. There should be no additional performance decrease even when the pageout daemon is running. (This was a significant performance issue.) vnode_pager.c: 14) Teach the vnode pager to handle race conditions during vnode deallocations.
419 lines
9.7 KiB
C
419 lines
9.7 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_pager.c 8.6 (Berkeley) 1/12/94
|
|
*
|
|
*
|
|
* 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_pager.c,v 1.36 1998/03/07 21:37:21 dyson Exp $
|
|
*/
|
|
|
|
/*
|
|
* Paging space routine stubs. Emulates a matchmaker-like interface
|
|
* for builtin pagers.
|
|
*/
|
|
|
|
#include <sys/param.h>
|
|
#include <sys/systm.h>
|
|
#include <sys/buf.h>
|
|
#include <sys/ucred.h>
|
|
#include <sys/malloc.h>
|
|
|
|
#include <vm/vm.h>
|
|
#include <vm/vm_param.h>
|
|
#include <vm/vm_prot.h>
|
|
#include <vm/vm_object.h>
|
|
#include <vm/vm_page.h>
|
|
#include <vm/vm_pager.h>
|
|
#include <vm/vm_extern.h>
|
|
|
|
MALLOC_DEFINE(M_VMPGDATA, "VM pgdata", "XXX: VM pager private data");
|
|
|
|
extern struct pagerops defaultpagerops;
|
|
extern struct pagerops swappagerops;
|
|
extern struct pagerops vnodepagerops;
|
|
extern struct pagerops devicepagerops;
|
|
|
|
static int dead_pager_getpages __P((vm_object_t, vm_page_t *, int, int));
|
|
static vm_object_t dead_pager_alloc __P((void *, vm_size_t, vm_prot_t,
|
|
vm_ooffset_t));
|
|
static int dead_pager_putpages __P((vm_object_t, vm_page_t *, int, int, int *));
|
|
static boolean_t dead_pager_haspage __P((vm_object_t, vm_pindex_t, int *, int *));
|
|
static void dead_pager_dealloc __P((vm_object_t));
|
|
|
|
int
|
|
dead_pager_getpages(obj, ma, count, req)
|
|
vm_object_t obj;
|
|
vm_page_t *ma;
|
|
int count;
|
|
int req;
|
|
{
|
|
return VM_PAGER_FAIL;
|
|
}
|
|
|
|
vm_object_t
|
|
dead_pager_alloc(handle, size, prot, off)
|
|
void *handle;
|
|
vm_size_t size;
|
|
vm_prot_t prot;
|
|
vm_ooffset_t off;
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
int
|
|
dead_pager_putpages(object, m, count, flags, rtvals)
|
|
vm_object_t object;
|
|
vm_page_t *m;
|
|
int count;
|
|
int flags;
|
|
int *rtvals;
|
|
{
|
|
int i;
|
|
for (i = 0; i < count; i++) {
|
|
rtvals[i] = VM_PAGER_AGAIN;
|
|
}
|
|
return VM_PAGER_AGAIN;
|
|
}
|
|
|
|
int
|
|
dead_pager_haspage(object, pindex, prev, next)
|
|
vm_object_t object;
|
|
vm_pindex_t pindex;
|
|
int *prev;
|
|
int *next;
|
|
{
|
|
if (prev)
|
|
*prev = 0;
|
|
if (next)
|
|
*next = 0;
|
|
return FALSE;
|
|
}
|
|
|
|
void
|
|
dead_pager_dealloc(object)
|
|
vm_object_t object;
|
|
{
|
|
return;
|
|
}
|
|
|
|
struct pagerops deadpagerops = {
|
|
NULL,
|
|
dead_pager_alloc,
|
|
dead_pager_dealloc,
|
|
dead_pager_getpages,
|
|
dead_pager_putpages,
|
|
dead_pager_haspage,
|
|
NULL
|
|
};
|
|
|
|
static struct pagerops *pagertab[] = {
|
|
&defaultpagerops, /* OBJT_DEFAULT */
|
|
&swappagerops, /* OBJT_SWAP */
|
|
&vnodepagerops, /* OBJT_VNODE */
|
|
&devicepagerops, /* OBJT_DEVICE */
|
|
&deadpagerops /* OBJT_DEAD */
|
|
};
|
|
static int npagers = sizeof(pagertab) / sizeof(pagertab[0]);
|
|
|
|
/*
|
|
* Kernel address space for mapping pages.
|
|
* Used by pagers where KVAs are needed for IO.
|
|
*
|
|
* XXX needs to be large enough to support the number of pending async
|
|
* cleaning requests (NPENDINGIO == 64) * the maximum swap cluster size
|
|
* (MAXPHYS == 64k) if you want to get the most efficiency.
|
|
*/
|
|
#define PAGER_MAP_SIZE (8 * 1024 * 1024)
|
|
|
|
int pager_map_size = PAGER_MAP_SIZE;
|
|
vm_map_t pager_map;
|
|
static int bswneeded;
|
|
static vm_offset_t swapbkva; /* swap buffers kva */
|
|
|
|
void
|
|
vm_pager_init()
|
|
{
|
|
struct pagerops **pgops;
|
|
|
|
/*
|
|
* Initialize known pagers
|
|
*/
|
|
for (pgops = pagertab; pgops < &pagertab[npagers]; pgops++)
|
|
if (pgops && ((*pgops)->pgo_init != NULL))
|
|
(*(*pgops)->pgo_init) ();
|
|
}
|
|
|
|
void
|
|
vm_pager_bufferinit()
|
|
{
|
|
struct buf *bp;
|
|
int i;
|
|
|
|
bp = swbuf;
|
|
/*
|
|
* Now set up swap and physical I/O buffer headers.
|
|
*/
|
|
for (i = 0; i < nswbuf; i++, bp++) {
|
|
TAILQ_INSERT_HEAD(&bswlist, bp, b_freelist);
|
|
bp->b_rcred = bp->b_wcred = NOCRED;
|
|
bp->b_vnbufs.le_next = NOLIST;
|
|
}
|
|
|
|
swapbkva = kmem_alloc_pageable(pager_map, nswbuf * MAXPHYS);
|
|
if (!swapbkva)
|
|
panic("Not enough pager_map VM space for physical buffers");
|
|
}
|
|
|
|
/*
|
|
* Allocate an instance of a pager of the given type.
|
|
* Size, protection and offset parameters are passed in for pagers that
|
|
* need to perform page-level validation (e.g. the device pager).
|
|
*/
|
|
vm_object_t
|
|
vm_pager_allocate(objtype_t type, void *handle, vm_size_t size, vm_prot_t prot,
|
|
vm_ooffset_t off)
|
|
{
|
|
struct pagerops *ops;
|
|
|
|
ops = pagertab[type];
|
|
if (ops)
|
|
return ((*ops->pgo_alloc) (handle, size, prot, off));
|
|
return (NULL);
|
|
}
|
|
|
|
void
|
|
vm_pager_deallocate(object)
|
|
vm_object_t object;
|
|
{
|
|
(*pagertab[object->type]->pgo_dealloc) (object);
|
|
}
|
|
|
|
|
|
int
|
|
vm_pager_get_pages(object, m, count, reqpage)
|
|
vm_object_t object;
|
|
vm_page_t *m;
|
|
int count;
|
|
int reqpage;
|
|
{
|
|
return ((*pagertab[object->type]->pgo_getpages)(object, m, count, reqpage));
|
|
}
|
|
|
|
int
|
|
vm_pager_put_pages(object, m, count, flags, rtvals)
|
|
vm_object_t object;
|
|
vm_page_t *m;
|
|
int count;
|
|
int flags;
|
|
int *rtvals;
|
|
{
|
|
return ((*pagertab[object->type]->pgo_putpages)(object, m, count, flags, rtvals));
|
|
}
|
|
|
|
boolean_t
|
|
vm_pager_has_page(object, offset, before, after)
|
|
vm_object_t object;
|
|
vm_pindex_t offset;
|
|
int *before;
|
|
int *after;
|
|
{
|
|
return ((*pagertab[object->type]->pgo_haspage) (object, offset, before, after));
|
|
}
|
|
|
|
/*
|
|
* Called by pageout daemon before going back to sleep.
|
|
* Gives pagers a chance to clean up any completed async pageing operations.
|
|
*/
|
|
void
|
|
vm_pager_sync()
|
|
{
|
|
struct pagerops **pgops;
|
|
|
|
for (pgops = pagertab; pgops < &pagertab[npagers]; pgops++)
|
|
if (pgops && ((*pgops)->pgo_sync != NULL))
|
|
(*(*pgops)->pgo_sync) ();
|
|
}
|
|
|
|
vm_offset_t
|
|
vm_pager_map_page(m)
|
|
vm_page_t m;
|
|
{
|
|
vm_offset_t kva;
|
|
|
|
kva = kmem_alloc_wait(pager_map, PAGE_SIZE);
|
|
pmap_kenter(kva, VM_PAGE_TO_PHYS(m));
|
|
return (kva);
|
|
}
|
|
|
|
void
|
|
vm_pager_unmap_page(kva)
|
|
vm_offset_t kva;
|
|
{
|
|
pmap_kremove(kva);
|
|
kmem_free_wakeup(pager_map, kva, PAGE_SIZE);
|
|
}
|
|
|
|
vm_object_t
|
|
vm_pager_object_lookup(pg_list, handle)
|
|
register struct pagerlst *pg_list;
|
|
void *handle;
|
|
{
|
|
register vm_object_t object;
|
|
|
|
for (object = TAILQ_FIRST(pg_list); object != NULL; object = TAILQ_NEXT(object,pager_object_list))
|
|
if (object->handle == handle)
|
|
return (object);
|
|
return (NULL);
|
|
}
|
|
|
|
/*
|
|
* initialize a physical buffer
|
|
*/
|
|
|
|
static void
|
|
initpbuf(struct buf *bp) {
|
|
bzero(bp, sizeof *bp);
|
|
bp->b_rcred = NOCRED;
|
|
bp->b_wcred = NOCRED;
|
|
bp->b_qindex = QUEUE_NONE;
|
|
bp->b_data = (caddr_t) (MAXPHYS * (bp - swbuf)) + swapbkva;
|
|
bp->b_kvabase = bp->b_data;
|
|
bp->b_kvasize = MAXPHYS;
|
|
bp->b_vnbufs.le_next = NOLIST;
|
|
}
|
|
|
|
/*
|
|
* allocate a physical buffer
|
|
*/
|
|
struct buf *
|
|
getpbuf()
|
|
{
|
|
int s;
|
|
struct buf *bp;
|
|
|
|
s = splvm();
|
|
/* get a bp from the swap buffer header pool */
|
|
while ((bp = TAILQ_FIRST(&bswlist)) == NULL) {
|
|
bswneeded = 1;
|
|
tsleep(&bswneeded, PVM, "wswbuf", 0);
|
|
}
|
|
TAILQ_REMOVE(&bswlist, bp, b_freelist);
|
|
splx(s);
|
|
|
|
initpbuf(bp);
|
|
return bp;
|
|
}
|
|
|
|
/*
|
|
* allocate a physical buffer, if one is available
|
|
*/
|
|
struct buf *
|
|
trypbuf()
|
|
{
|
|
int s;
|
|
struct buf *bp;
|
|
|
|
s = splvm();
|
|
if ((bp = TAILQ_FIRST(&bswlist)) == NULL) {
|
|
splx(s);
|
|
return NULL;
|
|
}
|
|
TAILQ_REMOVE(&bswlist, bp, b_freelist);
|
|
splx(s);
|
|
|
|
initpbuf(bp);
|
|
|
|
return bp;
|
|
}
|
|
|
|
/*
|
|
* release a physical buffer
|
|
*/
|
|
void
|
|
relpbuf(bp)
|
|
struct buf *bp;
|
|
{
|
|
int s;
|
|
|
|
s = splvm();
|
|
|
|
if (bp->b_rcred != NOCRED) {
|
|
crfree(bp->b_rcred);
|
|
bp->b_rcred = NOCRED;
|
|
}
|
|
if (bp->b_wcred != NOCRED) {
|
|
crfree(bp->b_wcred);
|
|
bp->b_wcred = NOCRED;
|
|
}
|
|
if (bp->b_vp)
|
|
pbrelvp(bp);
|
|
|
|
if (bp->b_flags & B_WANTED)
|
|
wakeup(bp);
|
|
|
|
TAILQ_INSERT_HEAD(&bswlist, bp, b_freelist);
|
|
|
|
if (bswneeded) {
|
|
bswneeded = 0;
|
|
wakeup(&bswneeded);
|
|
}
|
|
splx(s);
|
|
}
|