f6b04d2bfb
Fixed remaining known bugs in the buffer IO and VM system. vfs_bio.c: Fixed some race conditions and locking bugs. Improved performance by removing some (now) unnecessary code and fixing some broken logic. Fixed process accounting of # of FS outputs. Properly handle NFS interrupts (B_EINTR). (various) Replaced calls to clrbuf() with calls to an optimized routine called vfs_bio_clrbuf(). (various FS sync) Sync out modified vnode_pager backed pages. ffs_vnops.c: Do two passes: Sync out file data first, then indirect blocks. vm_fault.c: Fixed deadly embrace caused by acquiring locks in the wrong order. vnode_pager.c: Changed to use buffer I/O system for writing out modified pages. This should fix the problem with the modification date previous not getting updated. Also dramatically simplifies the code. Note that this is going to change in the future and be implemented via VOP_PUTPAGES(). vm_object.c: Fixed a pile of bugs related to cleaning (vnode) objects. The performance of vm_object_page_clean() is terrible when dealing with huge objects, but this will change when we implement a binary tree to keep the object pages sorted. vm_pageout.c: Fixed broken clustering of pageouts. Fixed race conditions and other lockup style bugs in the scanning of pages. Improved performance.
293 lines
7.6 KiB
C
293 lines
7.6 KiB
C
/*
|
|
* Copyright (c) 1982, 1986, 1989, 1993
|
|
* The Regents of the University of California. 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 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.
|
|
*
|
|
* @(#)ffs_balloc.c 8.4 (Berkeley) 9/23/93
|
|
* $Id: ffs_balloc.c,v 1.6 1995/03/19 14:29:13 davidg Exp $
|
|
*/
|
|
|
|
#include <sys/param.h>
|
|
#include <sys/systm.h>
|
|
#include <sys/buf.h>
|
|
#include <sys/proc.h>
|
|
#include <sys/file.h>
|
|
#include <sys/vnode.h>
|
|
|
|
#include <vm/vm.h>
|
|
|
|
#include <ufs/ufs/quota.h>
|
|
#include <ufs/ufs/inode.h>
|
|
#include <ufs/ufs/ufs_extern.h>
|
|
|
|
#include <ufs/ffs/fs.h>
|
|
#include <ufs/ffs/ffs_extern.h>
|
|
|
|
/*
|
|
* Balloc defines the structure of file system storage
|
|
* by allocating the physical blocks on a device given
|
|
* the inode and the logical block number in a file.
|
|
*/
|
|
int
|
|
ffs_balloc(ip, bn, size, cred, bpp, flags)
|
|
register struct inode *ip;
|
|
register daddr_t bn;
|
|
int size;
|
|
struct ucred *cred;
|
|
struct buf **bpp;
|
|
int flags;
|
|
{
|
|
register struct fs *fs;
|
|
register daddr_t nb;
|
|
struct buf *bp, *nbp;
|
|
struct vnode *vp = ITOV(ip);
|
|
struct indir indirs[NIADDR + 2];
|
|
daddr_t newb, lbn, *bap, pref;
|
|
int osize, nsize, num, i, error;
|
|
|
|
*bpp = NULL;
|
|
if (bn < 0)
|
|
return (EFBIG);
|
|
fs = ip->i_fs;
|
|
lbn = bn;
|
|
|
|
/*
|
|
* If the next write will extend the file into a new block,
|
|
* and the file is currently composed of a fragment
|
|
* this fragment has to be extended to be a full block.
|
|
*/
|
|
nb = lblkno(fs, ip->i_size);
|
|
if (nb < NDADDR && nb < bn) {
|
|
osize = blksize(fs, ip, nb);
|
|
if (osize < fs->fs_bsize && osize > 0) {
|
|
error = ffs_realloccg(ip, nb,
|
|
ffs_blkpref(ip, nb, (int)nb, &ip->i_db[0]),
|
|
osize, (int)fs->fs_bsize, cred, &bp);
|
|
if (error)
|
|
return (error);
|
|
ip->i_size = (nb + 1) * fs->fs_bsize;
|
|
vnode_pager_setsize(vp, (u_long)ip->i_size);
|
|
ip->i_db[nb] = dbtofsb(fs, bp->b_blkno);
|
|
ip->i_flag |= IN_CHANGE | IN_UPDATE;
|
|
if (flags & B_SYNC)
|
|
bwrite(bp);
|
|
else
|
|
bawrite(bp);
|
|
}
|
|
}
|
|
/*
|
|
* The first NDADDR blocks are direct blocks
|
|
*/
|
|
if (bn < NDADDR) {
|
|
nb = ip->i_db[bn];
|
|
if (nb != 0 && ip->i_size >= (bn + 1) * fs->fs_bsize) {
|
|
error = bread(vp, bn, fs->fs_bsize, NOCRED, &bp);
|
|
if (error) {
|
|
brelse(bp);
|
|
return (error);
|
|
}
|
|
bp->b_blkno = fsbtodb(fs, nb);
|
|
*bpp = bp;
|
|
return (0);
|
|
}
|
|
if (nb != 0) {
|
|
/*
|
|
* Consider need to reallocate a fragment.
|
|
*/
|
|
osize = fragroundup(fs, blkoff(fs, ip->i_size));
|
|
nsize = fragroundup(fs, size);
|
|
if (nsize <= osize) {
|
|
error = bread(vp, bn, osize, NOCRED, &bp);
|
|
if (error) {
|
|
brelse(bp);
|
|
return (error);
|
|
}
|
|
bp->b_blkno = fsbtodb(fs, nb);
|
|
} else {
|
|
error = ffs_realloccg(ip, bn,
|
|
ffs_blkpref(ip, bn, (int)bn, &ip->i_db[0]),
|
|
osize, nsize, cred, &bp);
|
|
if (error)
|
|
return (error);
|
|
}
|
|
} else {
|
|
if (ip->i_size < (bn + 1) * fs->fs_bsize)
|
|
nsize = fragroundup(fs, size);
|
|
else
|
|
nsize = fs->fs_bsize;
|
|
error = ffs_alloc(ip, bn,
|
|
ffs_blkpref(ip, bn, (int)bn, &ip->i_db[0]),
|
|
nsize, cred, &newb);
|
|
if (error)
|
|
return (error);
|
|
bp = getblk(vp, bn, nsize, 0, 0);
|
|
bp->b_blkno = fsbtodb(fs, newb);
|
|
if (flags & B_CLRBUF)
|
|
vfs_bio_clrbuf(bp);
|
|
}
|
|
ip->i_db[bn] = dbtofsb(fs, bp->b_blkno);
|
|
ip->i_flag |= IN_CHANGE | IN_UPDATE;
|
|
*bpp = bp;
|
|
return (0);
|
|
}
|
|
/*
|
|
* Determine the number of levels of indirection.
|
|
*/
|
|
pref = 0;
|
|
error = ufs_getlbns(vp, bn, indirs, &num);
|
|
if (error)
|
|
return(error);
|
|
#ifdef DIAGNOSTIC
|
|
if (num < 1)
|
|
panic ("ffs_balloc: ufs_bmaparray returned indirect block");
|
|
#endif
|
|
/*
|
|
* Fetch the first indirect block allocating if necessary.
|
|
*/
|
|
--num;
|
|
nb = ip->i_ib[indirs[0].in_off];
|
|
if (nb == 0) {
|
|
pref = ffs_blkpref(ip, lbn, 0, (daddr_t *)0);
|
|
error = ffs_alloc(ip, lbn, pref,
|
|
(int)fs->fs_bsize, cred, &newb);
|
|
if (error)
|
|
return (error);
|
|
nb = newb;
|
|
bp = getblk(vp, indirs[1].in_lbn, fs->fs_bsize, 0, 0);
|
|
bp->b_blkno = fsbtodb(fs, newb);
|
|
vfs_bio_clrbuf(bp);
|
|
/*
|
|
* Write synchronously so that indirect blocks
|
|
* never point at garbage.
|
|
*/
|
|
error = bwrite(bp);
|
|
if (error) {
|
|
ffs_blkfree(ip, nb, fs->fs_bsize);
|
|
return (error);
|
|
}
|
|
ip->i_ib[indirs[0].in_off] = newb;
|
|
ip->i_flag |= IN_CHANGE | IN_UPDATE;
|
|
}
|
|
/*
|
|
* Fetch through the indirect blocks, allocating as necessary.
|
|
*/
|
|
for (i = 1;;) {
|
|
error = bread(vp,
|
|
indirs[i].in_lbn, (int)fs->fs_bsize, NOCRED, &bp);
|
|
if (error) {
|
|
brelse(bp);
|
|
return (error);
|
|
}
|
|
bap = (daddr_t *)bp->b_data;
|
|
nb = bap[indirs[i].in_off];
|
|
if (i == num)
|
|
break;
|
|
i += 1;
|
|
if (nb != 0) {
|
|
brelse(bp);
|
|
continue;
|
|
}
|
|
if (pref == 0)
|
|
pref = ffs_blkpref(ip, lbn, 0, (daddr_t *)0);
|
|
error =
|
|
ffs_alloc(ip, lbn, pref, (int)fs->fs_bsize, cred, &newb);
|
|
if (error) {
|
|
brelse(bp);
|
|
return (error);
|
|
}
|
|
nb = newb;
|
|
nbp = getblk(vp, indirs[i].in_lbn, fs->fs_bsize, 0, 0);
|
|
nbp->b_blkno = fsbtodb(fs, nb);
|
|
vfs_bio_clrbuf(nbp);
|
|
/*
|
|
* Write synchronously so that indirect blocks
|
|
* never point at garbage.
|
|
*/
|
|
error = bwrite(nbp);
|
|
if (error) {
|
|
ffs_blkfree(ip, nb, fs->fs_bsize);
|
|
brelse(bp);
|
|
return (error);
|
|
}
|
|
bap[indirs[i - 1].in_off] = nb;
|
|
/*
|
|
* If required, write synchronously, otherwise use
|
|
* delayed write.
|
|
*/
|
|
if (flags & B_SYNC) {
|
|
bwrite(bp);
|
|
} else {
|
|
bdwrite(bp);
|
|
}
|
|
}
|
|
/*
|
|
* Get the data block, allocating if necessary.
|
|
*/
|
|
if (nb == 0) {
|
|
pref = ffs_blkpref(ip, lbn, indirs[i].in_off, &bap[0]);
|
|
error = ffs_alloc(ip,
|
|
lbn, pref, (int)fs->fs_bsize, cred, &newb);
|
|
if (error) {
|
|
brelse(bp);
|
|
return (error);
|
|
}
|
|
nb = newb;
|
|
nbp = getblk(vp, lbn, fs->fs_bsize, 0, 0);
|
|
nbp->b_blkno = fsbtodb(fs, nb);
|
|
if (flags & B_CLRBUF)
|
|
vfs_bio_clrbuf(nbp);
|
|
bap[indirs[i].in_off] = nb;
|
|
/*
|
|
* If required, write synchronously, otherwise use
|
|
* delayed write.
|
|
*/
|
|
if (flags & B_SYNC) {
|
|
bwrite(bp);
|
|
} else {
|
|
bdwrite(bp);
|
|
}
|
|
*bpp = nbp;
|
|
return (0);
|
|
}
|
|
brelse(bp);
|
|
if (flags & B_CLRBUF) {
|
|
error = bread(vp, lbn, (int)fs->fs_bsize, NOCRED, &nbp);
|
|
if (error) {
|
|
brelse(nbp);
|
|
return (error);
|
|
}
|
|
} else {
|
|
nbp = getblk(vp, lbn, fs->fs_bsize, 0, 0);
|
|
nbp->b_blkno = fsbtodb(fs, nb);
|
|
}
|
|
*bpp = nbp;
|
|
return (0);
|
|
}
|