mirror of
https://git.FreeBSD.org/src.git
synced 2024-12-22 11:17:19 +00:00
0d94caffca
much higher filesystem I/O performance, and much better paging performance. It represents the culmination of over 6 months of R&D. The majority of the merged VM/cache work is by John Dyson. The following highlights the most significant changes. Additionally, there are (mostly minor) changes to the various filesystem modules (nfs, msdosfs, etc) to support the new VM/buffer scheme. vfs_bio.c: Significant rewrite of most of vfs_bio to support the merged VM buffer cache scheme. The scheme is almost fully compatible with the old filesystem interface. Significant improvement in the number of opportunities for write clustering. vfs_cluster.c, vfs_subr.c Upgrade and performance enhancements in vfs layer code to support merged VM/buffer cache. Fixup of vfs_cluster to eliminate the bogus pagemove stuff. vm_object.c: Yet more improvements in the collapse code. Elimination of some windows that can cause list corruption. vm_pageout.c: Fixed it, it really works better now. Somehow in 2.0, some "enhancements" broke the code. This code has been reworked from the ground-up. vm_fault.c, vm_page.c, pmap.c, vm_object.c Support for small-block filesystems with merged VM/buffer cache scheme. pmap.c vm_map.c Dynamic kernel VM size, now we dont have to pre-allocate excessive numbers of kernel PTs. vm_glue.c Much simpler and more effective swapping code. No more gratuitous swapping. proc.h Fixed the problem that the p_lock flag was not being cleared on a fork. swap_pager.c, vnode_pager.c Removal of old vfs_bio cruft to support the past pseudo-coherency. Now the code doesn't need it anymore. machdep.c Changes to better support the parameter values for the merged VM/buffer cache scheme. machdep.c, kern_exec.c, vm_glue.c Implemented a seperate submap for temporary exec string space and another one to contain process upages. This eliminates all map fragmentation problems that previously existed. ffs_inode.c, ufs_inode.c, ufs_readwrite.c Changes for merged VM/buffer cache. Add "bypass" support for sneaking in on busy buffers. Submitted by: John Dyson and David Greenman
302 lines
11 KiB
C
302 lines
11 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 8.7 (Berkeley) 2/3/94
|
|
* $Id: ffs_vnops.c,v 1.7 1994/10/10 01:04:40 phk Exp $
|
|
*/
|
|
|
|
#include <sys/param.h>
|
|
#include <sys/systm.h>
|
|
#include <sys/resourcevar.h>
|
|
#include <sys/signalvar.h>
|
|
#include <sys/kernel.h>
|
|
#include <sys/file.h>
|
|
#include <sys/stat.h>
|
|
#include <sys/buf.h>
|
|
#include <sys/proc.h>
|
|
#include <sys/conf.h>
|
|
#include <sys/mount.h>
|
|
#include <sys/vnode.h>
|
|
#include <sys/malloc.h>
|
|
#include <sys/lockf.h>
|
|
|
|
#include <vm/vm.h>
|
|
|
|
#include <miscfs/specfs/specdev.h>
|
|
#include <miscfs/fifofs/fifo.h>
|
|
|
|
#include <ufs/ufs/quota.h>
|
|
#include <ufs/ufs/inode.h>
|
|
#include <ufs/ufs/dir.h>
|
|
#include <ufs/ufs/ufs_extern.h>
|
|
|
|
#include <ufs/ffs/fs.h>
|
|
#include <ufs/ffs/ffs_extern.h>
|
|
|
|
/* Global vfs data structures for ufs. */
|
|
int (**ffs_vnodeop_p)();
|
|
struct vnodeopv_entry_desc ffs_vnodeop_entries[] = {
|
|
{ &vop_default_desc, vn_default_error },
|
|
{ &vop_lookup_desc, ufs_lookup }, /* lookup */
|
|
{ &vop_create_desc, ufs_create }, /* create */
|
|
{ &vop_mknod_desc, ufs_mknod }, /* mknod */
|
|
{ &vop_open_desc, ufs_open }, /* open */
|
|
{ &vop_close_desc, ufs_close }, /* close */
|
|
{ &vop_access_desc, ufs_access }, /* access */
|
|
{ &vop_getattr_desc, ufs_getattr }, /* getattr */
|
|
{ &vop_setattr_desc, ufs_setattr }, /* setattr */
|
|
{ &vop_read_desc, ffs_read }, /* read */
|
|
{ &vop_write_desc, ffs_write }, /* write */
|
|
{ &vop_ioctl_desc, ufs_ioctl }, /* ioctl */
|
|
{ &vop_select_desc, ufs_select }, /* select */
|
|
{ &vop_mmap_desc, ufs_mmap }, /* mmap */
|
|
{ &vop_fsync_desc, ffs_fsync }, /* fsync */
|
|
{ &vop_seek_desc, ufs_seek }, /* seek */
|
|
{ &vop_remove_desc, ufs_remove }, /* remove */
|
|
{ &vop_link_desc, ufs_link }, /* link */
|
|
{ &vop_rename_desc, ufs_rename }, /* rename */
|
|
{ &vop_mkdir_desc, ufs_mkdir }, /* mkdir */
|
|
{ &vop_rmdir_desc, ufs_rmdir }, /* rmdir */
|
|
{ &vop_symlink_desc, ufs_symlink }, /* symlink */
|
|
{ &vop_readdir_desc, ufs_readdir }, /* readdir */
|
|
{ &vop_readlink_desc, ufs_readlink }, /* readlink */
|
|
{ &vop_abortop_desc, ufs_abortop }, /* abortop */
|
|
{ &vop_inactive_desc, ufs_inactive }, /* inactive */
|
|
{ &vop_reclaim_desc, ufs_reclaim }, /* reclaim */
|
|
{ &vop_lock_desc, ufs_lock }, /* lock */
|
|
{ &vop_unlock_desc, ufs_unlock }, /* unlock */
|
|
{ &vop_bmap_desc, ufs_bmap }, /* bmap */
|
|
{ &vop_strategy_desc, ufs_strategy }, /* strategy */
|
|
{ &vop_print_desc, ufs_print }, /* print */
|
|
{ &vop_islocked_desc, ufs_islocked }, /* islocked */
|
|
{ &vop_pathconf_desc, ufs_pathconf }, /* pathconf */
|
|
{ &vop_advlock_desc, ufs_advlock }, /* advlock */
|
|
{ &vop_blkatoff_desc, ffs_blkatoff }, /* blkatoff */
|
|
{ &vop_valloc_desc, ffs_valloc }, /* valloc */
|
|
{ &vop_reallocblks_desc, ffs_reallocblks }, /* reallocblks */
|
|
{ &vop_vfree_desc, ffs_vfree }, /* vfree */
|
|
{ &vop_truncate_desc, ffs_truncate }, /* truncate */
|
|
{ &vop_update_desc, ffs_update }, /* update */
|
|
{ &vop_bwrite_desc, vn_bwrite },
|
|
{ (struct vnodeop_desc*)NULL, (int(*)())NULL }
|
|
};
|
|
struct vnodeopv_desc ffs_vnodeop_opv_desc =
|
|
{ &ffs_vnodeop_p, ffs_vnodeop_entries };
|
|
|
|
int (**ffs_specop_p)();
|
|
struct vnodeopv_entry_desc ffs_specop_entries[] = {
|
|
{ &vop_default_desc, vn_default_error },
|
|
{ &vop_lookup_desc, spec_lookup }, /* lookup */
|
|
{ &vop_create_desc, spec_create }, /* create */
|
|
{ &vop_mknod_desc, spec_mknod }, /* mknod */
|
|
{ &vop_open_desc, spec_open }, /* open */
|
|
{ &vop_close_desc, ufsspec_close }, /* close */
|
|
{ &vop_access_desc, ufs_access }, /* access */
|
|
{ &vop_getattr_desc, ufs_getattr }, /* getattr */
|
|
{ &vop_setattr_desc, ufs_setattr }, /* setattr */
|
|
{ &vop_read_desc, ufsspec_read }, /* read */
|
|
{ &vop_write_desc, ufsspec_write }, /* write */
|
|
{ &vop_ioctl_desc, spec_ioctl }, /* ioctl */
|
|
{ &vop_select_desc, spec_select }, /* select */
|
|
{ &vop_mmap_desc, spec_mmap }, /* mmap */
|
|
{ &vop_fsync_desc, ffs_fsync }, /* fsync */
|
|
{ &vop_seek_desc, spec_seek }, /* seek */
|
|
{ &vop_remove_desc, spec_remove }, /* remove */
|
|
{ &vop_link_desc, spec_link }, /* link */
|
|
{ &vop_rename_desc, spec_rename }, /* rename */
|
|
{ &vop_mkdir_desc, spec_mkdir }, /* mkdir */
|
|
{ &vop_rmdir_desc, spec_rmdir }, /* rmdir */
|
|
{ &vop_symlink_desc, spec_symlink }, /* symlink */
|
|
{ &vop_readdir_desc, spec_readdir }, /* readdir */
|
|
{ &vop_readlink_desc, spec_readlink }, /* readlink */
|
|
{ &vop_abortop_desc, spec_abortop }, /* abortop */
|
|
{ &vop_inactive_desc, ufs_inactive }, /* inactive */
|
|
{ &vop_reclaim_desc, ufs_reclaim }, /* reclaim */
|
|
{ &vop_lock_desc, ufs_lock }, /* lock */
|
|
{ &vop_unlock_desc, ufs_unlock }, /* unlock */
|
|
{ &vop_bmap_desc, spec_bmap }, /* bmap */
|
|
{ &vop_strategy_desc, spec_strategy }, /* strategy */
|
|
{ &vop_print_desc, ufs_print }, /* print */
|
|
{ &vop_islocked_desc, ufs_islocked }, /* islocked */
|
|
{ &vop_pathconf_desc, spec_pathconf }, /* pathconf */
|
|
{ &vop_advlock_desc, spec_advlock }, /* advlock */
|
|
{ &vop_blkatoff_desc, spec_blkatoff }, /* blkatoff */
|
|
{ &vop_valloc_desc, spec_valloc }, /* valloc */
|
|
{ &vop_reallocblks_desc, spec_reallocblks }, /* reallocblks */
|
|
{ &vop_vfree_desc, ffs_vfree }, /* vfree */
|
|
{ &vop_truncate_desc, spec_truncate }, /* truncate */
|
|
{ &vop_update_desc, ffs_update }, /* update */
|
|
{ &vop_bwrite_desc, vn_bwrite },
|
|
{ (struct vnodeop_desc*)NULL, (int(*)())NULL }
|
|
};
|
|
struct vnodeopv_desc ffs_specop_opv_desc =
|
|
{ &ffs_specop_p, ffs_specop_entries };
|
|
|
|
int (**ffs_fifoop_p)();
|
|
struct vnodeopv_entry_desc ffs_fifoop_entries[] = {
|
|
{ &vop_default_desc, vn_default_error },
|
|
{ &vop_lookup_desc, fifo_lookup }, /* lookup */
|
|
{ &vop_create_desc, fifo_create }, /* create */
|
|
{ &vop_mknod_desc, fifo_mknod }, /* mknod */
|
|
{ &vop_open_desc, fifo_open }, /* open */
|
|
{ &vop_close_desc, ufsfifo_close }, /* close */
|
|
{ &vop_access_desc, ufs_access }, /* access */
|
|
{ &vop_getattr_desc, ufs_getattr }, /* getattr */
|
|
{ &vop_setattr_desc, ufs_setattr }, /* setattr */
|
|
{ &vop_read_desc, ufsfifo_read }, /* read */
|
|
{ &vop_write_desc, ufsfifo_write }, /* write */
|
|
{ &vop_ioctl_desc, fifo_ioctl }, /* ioctl */
|
|
{ &vop_select_desc, fifo_select }, /* select */
|
|
{ &vop_mmap_desc, fifo_mmap }, /* mmap */
|
|
{ &vop_fsync_desc, ffs_fsync }, /* fsync */
|
|
{ &vop_seek_desc, fifo_seek }, /* seek */
|
|
{ &vop_remove_desc, fifo_remove }, /* remove */
|
|
{ &vop_link_desc, fifo_link }, /* link */
|
|
{ &vop_rename_desc, fifo_rename }, /* rename */
|
|
{ &vop_mkdir_desc, fifo_mkdir }, /* mkdir */
|
|
{ &vop_rmdir_desc, fifo_rmdir }, /* rmdir */
|
|
{ &vop_symlink_desc, fifo_symlink }, /* symlink */
|
|
{ &vop_readdir_desc, fifo_readdir }, /* readdir */
|
|
{ &vop_readlink_desc, fifo_readlink }, /* readlink */
|
|
{ &vop_abortop_desc, fifo_abortop }, /* abortop */
|
|
{ &vop_inactive_desc, ufs_inactive }, /* inactive */
|
|
{ &vop_reclaim_desc, ufs_reclaim }, /* reclaim */
|
|
{ &vop_lock_desc, ufs_lock }, /* lock */
|
|
{ &vop_unlock_desc, ufs_unlock }, /* unlock */
|
|
{ &vop_bmap_desc, fifo_bmap }, /* bmap */
|
|
{ &vop_strategy_desc, fifo_strategy }, /* strategy */
|
|
{ &vop_print_desc, ufs_print }, /* print */
|
|
{ &vop_islocked_desc, ufs_islocked }, /* islocked */
|
|
{ &vop_pathconf_desc, fifo_pathconf }, /* pathconf */
|
|
{ &vop_advlock_desc, fifo_advlock }, /* advlock */
|
|
{ &vop_blkatoff_desc, fifo_blkatoff }, /* blkatoff */
|
|
{ &vop_valloc_desc, fifo_valloc }, /* valloc */
|
|
{ &vop_reallocblks_desc, fifo_reallocblks }, /* reallocblks */
|
|
{ &vop_vfree_desc, ffs_vfree }, /* vfree */
|
|
{ &vop_truncate_desc, fifo_truncate }, /* truncate */
|
|
{ &vop_update_desc, ffs_update }, /* update */
|
|
{ &vop_bwrite_desc, vn_bwrite },
|
|
{ (struct vnodeop_desc*)NULL, (int(*)())NULL }
|
|
};
|
|
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);
|
|
|
|
#ifdef DEBUG
|
|
/*
|
|
* Enabling cluster read/write operations.
|
|
*/
|
|
#include <sys/sysctl.h>
|
|
int doclusterread = 1;
|
|
struct ctldebug debug11 = { "doclusterread", &doclusterread };
|
|
int doclusterwrite = 1;
|
|
struct ctldebug debug12 = { "doclusterwrite", &doclusterwrite };
|
|
#else
|
|
/* XXX for ufs_readwrite */
|
|
#define doclusterread 1
|
|
#define doclusterwrite 1
|
|
#endif
|
|
|
|
#include <ufs/ufs/ufs_readwrite.c>
|
|
|
|
/*
|
|
* Synch an open file.
|
|
*/
|
|
/* ARGSUSED */
|
|
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 s;
|
|
|
|
/*
|
|
* 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))
|
|
continue;
|
|
if ((bp->b_flags & B_DELWRI) == 0)
|
|
panic("ffs_fsync: not dirty");
|
|
|
|
if (bp->b_vp != vp && ap->a_waitfor != MNT_NOWAIT) {
|
|
|
|
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)
|
|
(void) bawrite(bp);
|
|
else
|
|
(void) bwrite(bp);
|
|
} else {
|
|
vfs_bio_awrite(bp);
|
|
splx(s);
|
|
}
|
|
goto loop;
|
|
}
|
|
|
|
if (ap->a_waitfor == MNT_WAIT) {
|
|
while (vp->v_numoutput) {
|
|
vp->v_flag |= VBWAIT;
|
|
(void) tsleep((caddr_t)&vp->v_numoutput, PRIBIO + 1, "ffsfsn", 0);
|
|
}
|
|
#ifdef DIAGNOSTIC
|
|
if (vp->v_dirtyblkhd.lh_first) {
|
|
vprint("ffs_fsync: dirty", vp);
|
|
goto loop;
|
|
}
|
|
#endif
|
|
}
|
|
splx(s);
|
|
|
|
tv = time;
|
|
return (VOP_UPDATE(ap->a_vp, &tv, &tv, ap->a_waitfor == MNT_WAIT));
|
|
}
|