freebsd-dev/sys/ufs/ffs/ffs_vnops.c
John Dyson 95e5e988e0 Make our v_usecount vnode reference count work identically to the
original BSD code.  The association between the vnode and the vm_object
no longer includes reference counts.  The major difference is that
vm_object's are no longer freed gratuitiously from the vnode, and so
once an object is created for the vnode, it will last as long as the
vnode does.

When a vnode object reference count is incremented, then the underlying
vnode reference count is incremented also.  The two "objects" are now
more intimately related, and so the interactions are now much less
complex.

When vnodes are now normally placed onto the free queue with an object still
attached.  The rundown of the object happens at vnode rundown time, and
happens with exactly the same filesystem semantics of the original VFS
code.  There is absolutely no need for vnode_pager_uncache and other
travesties like that anymore.

A side-effect of these changes is that SMP locking should be much simpler,
the I/O copyin/copyout optimizations work, NFS should be more ponderable,
and further work on layered filesystems should be less frustrating, because
of the totally coherent management of the vnode objects and vnodes.

Please be careful with your system while running this code, but I would
greatly appreciate feedback as soon a reasonably possible.
1998-01-06 05:26:17 +00:00

211 lines
5.9 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_vnops.c 8.15 (Berkeley) 5/14/95
* $Id: ffs_vnops.c,v 1.37 1997/10/27 13:33:45 bde Exp $
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/resourcevar.h>
#include <sys/signalvar.h>
#include <sys/kernel.h>
#include <sys/stat.h>
#include <sys/buf.h>
#include <sys/proc.h>
#include <sys/mount.h>
#include <sys/sysctl.h>
#include <sys/vnode.h>
#include <vm/vm.h>
#include <vm/vm_prot.h>
#include <vm/vm_page.h>
#include <vm/vm_object.h>
#include <vm/vm_extern.h>
#include <ufs/ufs/quota.h>
#include <ufs/ufs/inode.h>
#include <ufs/ufs/ufsmount.h>
#include <ufs/ufs/ufs_extern.h>
#include <ufs/ffs/fs.h>
#include <ufs/ffs/ffs_extern.h>
static int ffs_fsync __P((struct vop_fsync_args *));
static int ffs_getpages __P((struct vop_getpages_args *));
static int ffs_read __P((struct vop_read_args *));
static int ffs_write __P((struct vop_write_args *));
/* Global vfs data structures for ufs. */
vop_t **ffs_vnodeop_p;
static struct vnodeopv_entry_desc ffs_vnodeop_entries[] = {
{ &vop_default_desc, (vop_t *) ufs_vnoperate },
{ &vop_fsync_desc, (vop_t *) ffs_fsync },
{ &vop_getpages_desc, (vop_t *) ffs_getpages },
{ &vop_read_desc, (vop_t *) ffs_read },
{ &vop_reallocblks_desc, (vop_t *) ffs_reallocblks },
{ &vop_write_desc, (vop_t *) ffs_write },
{ NULL, NULL }
};
static struct vnodeopv_desc ffs_vnodeop_opv_desc =
{ &ffs_vnodeop_p, ffs_vnodeop_entries };
vop_t **ffs_specop_p;
static struct vnodeopv_entry_desc ffs_specop_entries[] = {
{ &vop_default_desc, (vop_t *) ufs_vnoperatespec },
{ &vop_fsync_desc, (vop_t *) ffs_fsync },
{ NULL, NULL }
};
static struct vnodeopv_desc ffs_specop_opv_desc =
{ &ffs_specop_p, ffs_specop_entries };
vop_t **ffs_fifoop_p;
static struct vnodeopv_entry_desc ffs_fifoop_entries[] = {
{ &vop_default_desc, (vop_t *) ufs_vnoperatefifo },
{ &vop_fsync_desc, (vop_t *) ffs_fsync },
{ NULL, NULL }
};
static struct vnodeopv_desc ffs_fifoop_opv_desc =
{ &ffs_fifoop_p, ffs_fifoop_entries };
VNODEOP_SET(ffs_vnodeop_opv_desc);
VNODEOP_SET(ffs_specop_opv_desc);
VNODEOP_SET(ffs_fifoop_opv_desc);
SYSCTL_NODE(_vfs, MOUNT_UFS, ffs, CTLFLAG_RW, 0, "FFS filesystem");
#include <ufs/ufs/ufs_readwrite.c>
/*
* Synch an open file.
*/
/* ARGSUSED */
static int
ffs_fsync(ap)
struct vop_fsync_args /* {
struct vnode *a_vp;
struct ucred *a_cred;
int a_waitfor;
struct proc *a_p;
} */ *ap;
{
register struct vnode *vp = ap->a_vp;
register struct buf *bp;
struct timeval tv;
struct buf *nbp;
int pass;
int s;
daddr_t lbn;
if (vp->v_type == VBLK) {
lbn = INT_MAX;
} else {
struct inode *ip;
ip = VTOI(vp);
lbn = lblkno(ip->i_fs, (ip->i_size + ip->i_fs->fs_bsize - 1));
}
pass = 0;
/*
* Flush all dirty buffers associated with a vnode.
*/
loop:
s = splbio();
for (bp = vp->v_dirtyblkhd.lh_first; bp; bp = nbp) {
nbp = bp->b_vnbufs.le_next;
if ((bp->b_flags & B_BUSY) || (pass == 0 && (bp->b_lblkno < 0)))
continue;
if ((bp->b_flags & B_DELWRI) == 0)
panic("ffs_fsync: not dirty");
if (((bp->b_vp != vp) || (ap->a_waitfor != MNT_NOWAIT)) ||
((vp->v_type != VREG) && (vp->v_type != VBLK))) {
bremfree(bp);
bp->b_flags |= B_BUSY;
splx(s);
/*
* Wait for I/O associated with indirect blocks to complete,
* since there is no way to quickly wait for them below.
*/
if ((bp->b_vp == vp) && (ap->a_waitfor == MNT_NOWAIT)) {
if (bp->b_flags & B_CLUSTEROK) {
bdwrite(bp);
(void) vfs_bio_awrite(bp);
} else {
(void) bawrite(bp);
}
} else {
(void) bwrite(bp);
}
} else if ((vp->v_type == VREG) && (bp->b_lblkno >= lbn)) {
bremfree(bp);
bp->b_flags |= B_BUSY | B_INVAL | B_NOCACHE;
brelse(bp);
splx(s);
} else {
vfs_bio_awrite(bp);
splx(s);
}
goto loop;
}
splx(s);
if (pass == 0) {
pass = 1;
goto loop;
}
if (ap->a_waitfor == MNT_WAIT) {
s = splbio();
while (vp->v_numoutput) {
vp->v_flag |= VBWAIT;
(void) tsleep((caddr_t)&vp->v_numoutput, PRIBIO + 1, "ffsfsn", 0);
}
splx(s);
#ifdef DIAGNOSTIC
if (vp->v_dirtyblkhd.lh_first) {
vprint("ffs_fsync: dirty", vp);
goto loop;
}
#endif
}
gettime(&tv);
return (UFS_UPDATE(ap->a_vp, &tv, &tv, ap->a_waitfor == MNT_WAIT));
}