NetBSD/sys/ufs/lfs/lfs_subr.c
perseant 4e3fced95b Merge the short-lived perseant-lfsv2 branch into the trunk.
Kernels and tools understand both v1 and v2 filesystems; newfs_lfs
generates v2 by default.  Changes for the v2 layout include:

- Segments of non-PO2 size and arbitrary block offset, so these can be
  matched to convenient physical characteristics of the partition (e.g.,
  stripe or track size and offset).

- Address by fragment instead of by disk sector, paving the way for
  non-512-byte-sector devices.  In theory fragments can be as large
  as you like, though in reality they must be smaller than MAXBSIZE in size.

- Use serial number and filesystem identifier to ensure that roll-forward
  doesn't get old data and think it's new.  Roll-forward is enabled for
  v2 filesystems, though not for v1 filesystems by default.

- The inode free list is now a tailq, paving the way for undelete (undelete
  is not yet implemented, but can be without further non-backwards-compatible
  changes to disk structures).

- Inode atime information is kept in the Ifile, instead of on the inode;
  that is, the inode is never written *just* because atime was changed.
  Because of this the inodes remain near the file data on the disk, rather
  than wandering all over as the disk is read repeatedly.  This speeds up
  repeated reads by a small but noticeable amount.

Other changes of note include:

- The ifile written by newfs_lfs can now be of arbitrary length, it is no
  longer restricted to a single indirect block.

- Fixed an old bug where ctime was changed every time a vnode was created.
  I need to look more closely to make sure that the times are only updated
  during write(2) and friends, not after-the-fact during a segment write,
  and certainly not by the cleaner.
2001-07-13 20:30:18 +00:00

284 lines
8.9 KiB
C

/* $NetBSD: lfs_subr.c,v 1.18 2001/07/13 20:30:24 perseant Exp $ */
/*-
* Copyright (c) 1999, 2000 The NetBSD Foundation, Inc.
* All rights reserved.
*
* This code is derived from software contributed to The NetBSD Foundation
* by Konrad E. Schroder <perseant@hhhh.org>.
*
* 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 NetBSD
* Foundation, Inc. and its contributors.
* 4. Neither the name of The NetBSD Foundation 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 NETBSD FOUNDATION, INC. 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 FOUNDATION 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.
*/
/*
* Copyright (c) 1991, 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.
*
* @(#)lfs_subr.c 8.4 (Berkeley) 5/8/95
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/namei.h>
#include <sys/vnode.h>
#include <sys/buf.h>
#include <sys/mount.h>
#include <sys/malloc.h>
#include <sys/proc.h>
#include <ufs/ufs/quota.h>
#include <ufs/ufs/inode.h>
#include <ufs/lfs/lfs.h>
#include <ufs/lfs/lfs_extern.h>
/*
* Return buffer with the contents of block "offset" from the beginning of
* directory "ip". If "res" is non-zero, fill it in with a pointer to the
* remaining space in the directory.
*/
int
lfs_blkatoff(void *v)
{
struct vop_blkatoff_args /* {
struct vnode *a_vp;
off_t a_offset;
char **a_res;
struct buf **a_bpp;
} */ *ap = v;
struct lfs *fs;
struct inode *ip;
struct buf *bp;
ufs_daddr_t lbn;
int bsize, error;
ip = VTOI(ap->a_vp);
fs = ip->i_lfs;
lbn = lblkno(fs, ap->a_offset);
bsize = blksize(fs, ip, lbn);
*ap->a_bpp = NULL;
if ((error = bread(ap->a_vp, lbn, bsize, NOCRED, &bp)) != 0) {
brelse(bp);
return (error);
}
if (ap->a_res)
*ap->a_res = (char *)bp->b_data + blkoff(fs, ap->a_offset);
*ap->a_bpp = bp;
return (0);
}
/*
* lfs_seglock --
* Single thread the segment writer.
*/
void
lfs_seglock(struct lfs *fs, unsigned long flags)
{
struct segment *sp;
int s;
if (fs->lfs_seglock) {
if (fs->lfs_lockpid == curproc->p_pid) {
++fs->lfs_seglock;
fs->lfs_sp->seg_flags |= flags;
return;
} else while (fs->lfs_seglock)
(void)tsleep(&fs->lfs_seglock, PRIBIO + 1,
"lfs seglock", 0);
}
fs->lfs_seglock = 1;
fs->lfs_lockpid = curproc->p_pid;
sp = fs->lfs_sp = malloc(sizeof(struct segment), M_SEGMENT, M_WAITOK);
sp->bpp = malloc(((fs->lfs_sumsize - SEGSUM_SIZE(fs)) /
sizeof(ufs_daddr_t) + 1) * sizeof(struct buf *),
M_SEGMENT, M_WAITOK);
sp->seg_flags = flags;
sp->vp = NULL;
(void) lfs_initseg(fs);
/*
* Keep a cumulative count of the outstanding I/O operations. If the
* disk drive catches up with us it could go to zero before we finish,
* so we artificially increment it by one until we've scheduled all of
* the writes we intend to do.
*/
s = splbio();
++fs->lfs_iocount;
splx(s);
}
/*
* lfs_segunlock --
* Single thread the segment writer.
*/
void
lfs_segunlock(struct lfs *fs)
{
struct segment *sp;
unsigned long sync, ckp;
int s;
struct vnode *vp;
struct mount *mp;
extern int lfs_dirvcount;
sp = fs->lfs_sp;
if (fs->lfs_seglock == 1 && !(sp->seg_flags & SEGM_PROT)) {
mp = fs->lfs_ivnode->v_mount;
/*
* Go through and unmark all DIROP vnodes, possibly
* calling VOP_INACTIVE (through vrele). This is
* delayed until now in order not to accidentally
* write a DIROP node through lfs_flush.
*/
#ifndef LFS_NO_BACKVP_HACK
/* BEGIN HACK */
#define VN_OFFSET (((caddr_t)&vp->v_mntvnodes.le_next) - (caddr_t)vp)
#define BACK_VP(VP) ((struct vnode *)(((caddr_t)VP->v_mntvnodes.le_prev) - VN_OFFSET))
#define BEG_OF_VLIST ((struct vnode *)(((caddr_t)&mp->mnt_vnodelist.lh_first) - VN_OFFSET))
/* Find last vnode. */
loop: for (vp = mp->mnt_vnodelist.lh_first;
vp && vp->v_mntvnodes.le_next != NULL;
vp = vp->v_mntvnodes.le_next);
for (; vp && vp != BEG_OF_VLIST; vp = BACK_VP(vp)) {
#else
loop:
for (vp = mp->mnt_vnodelist.lh_first;
vp != NULL;
vp = vp->v_mntvnodes.le_next) {
#endif
if (vp->v_mount != mp)
goto loop;
if (vp->v_type == VNON)
continue;
if (lfs_vref(vp))
continue;
if (VOP_ISLOCKED(vp) &&
vp->v_lock.lk_lockholder != curproc->p_pid) {
lfs_vunref(vp);
continue;
}
if ((vp->v_flag & VDIROP) &&
!(VTOI(vp)->i_flag & IN_ADIROP)) {
--lfs_dirvcount;
vp->v_flag &= ~VDIROP;
wakeup(&lfs_dirvcount);
fs->lfs_unlockvp = vp;
lfs_vunref(vp);
vrele(vp);
fs->lfs_unlockvp = NULL;
} else {
lfs_vunref(vp);
}
}
}
if (fs->lfs_seglock == 1) {
sync = sp->seg_flags & SEGM_SYNC;
ckp = sp->seg_flags & SEGM_CKP;
if (sp->bpp != sp->cbpp) {
/* Free allocated segment summary */
fs->lfs_offset -= btofsb(fs, fs->lfs_sumsize);
lfs_freebuf(*sp->bpp);
} else
printf ("unlock to 0 with no summary");
free(sp->bpp, M_SEGMENT);
sp->bpp = NULL;
free(sp, M_SEGMENT);
fs->lfs_sp = NULL;
/*
* If the I/O count is non-zero, sleep until it reaches zero.
* At the moment, the user's process hangs around so we can
* sleep.
*/
s = splbio();
--fs->lfs_iocount;
/*
* We let checkpoints happen asynchronously. That means
* that during recovery, we have to roll forward between
* the two segments described by the first and second
* superblocks to make sure that the checkpoint described
* by a superblock completed.
*/
while (sync && fs->lfs_iocount)
(void)tsleep(&fs->lfs_iocount, PRIBIO + 1,
"lfs vflush", 0);
splx(s);
if (ckp) {
fs->lfs_nactive = 0;
/* If we *know* everything's on disk, write both sbs */
if(sync)
lfs_writesuper(fs,fs->lfs_sboffs[fs->lfs_activesb]);
fs->lfs_activesb = 1 - fs->lfs_activesb;
lfs_writesuper(fs,fs->lfs_sboffs[fs->lfs_activesb]);
}
--fs->lfs_seglock;
fs->lfs_lockpid = 0;
wakeup(&fs->lfs_seglock);
} else if (fs->lfs_seglock == 0) {
panic ("Seglock not held");
} else {
--fs->lfs_seglock;
}
}