freebsd-dev/sys/miscfs/fifofs/fifo_vnops.c
Kirk McKusick f2a2857bb3 Add snapshots to the fast filesystem. Most of the changes support
the gating of system calls that cause modifications to the underlying
filesystem. The gating can be enabled by any filesystem that needs
to consistently suspend operations by adding the vop_stdgetwritemount
to their set of vnops. Once gating is enabled, the function
vfs_write_suspend stops all new write operations to a filesystem,
allows any filesystem modifying system calls already in progress
to complete, then sync's the filesystem to disk and returns. The
function vfs_write_resume allows the suspended write operations to
begin again. Gating is not added by default for all filesystems as
for SMP systems it adds two extra locks to such critical kernel
paths as the write system call. Thus, gating should only be added
as needed.

Details on the use and current status of snapshots in FFS can be
found in /sys/ufs/ffs/README.snapshot so for brevity and timelyness
is not included here. Unless and until you create a snapshot file,
these changes should have no effect on your system (famous last words).
2000-07-11 22:07:57 +00:00

624 lines
15 KiB
C

/*
* Copyright (c) 1990, 1993, 1995
* 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.
*
* @(#)fifo_vnops.c 8.10 (Berkeley) 5/27/95
* $FreeBSD$
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/unistd.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/vnode.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/filio.h>
#include <sys/fcntl.h>
#include <sys/file.h>
#include <sys/event.h>
#include <sys/poll.h>
#include <sys/un.h>
#include <miscfs/fifofs/fifo.h>
/*
* This structure is associated with the FIFO vnode and stores
* the state associated with the FIFO.
*/
struct fifoinfo {
struct socket *fi_readsock;
struct socket *fi_writesock;
long fi_readers;
long fi_writers;
};
static int fifo_badop __P((void));
static int fifo_print __P((struct vop_print_args *));
static int fifo_lookup __P((struct vop_lookup_args *));
static int fifo_open __P((struct vop_open_args *));
static int fifo_close __P((struct vop_close_args *));
static int fifo_read __P((struct vop_read_args *));
static int fifo_write __P((struct vop_write_args *));
static int fifo_ioctl __P((struct vop_ioctl_args *));
static int fifo_poll __P((struct vop_poll_args *));
static int fifo_inactive __P((struct vop_inactive_args *));
static int fifo_bmap __P((struct vop_bmap_args *));
static int fifo_pathconf __P((struct vop_pathconf_args *));
static int fifo_advlock __P((struct vop_advlock_args *));
static int filt_fiforattach(struct knote *kn);
static void filt_fifordetach(struct knote *kn);
static int filt_fiforead(struct knote *kn, long hint);
static int filt_fifowattach(struct knote *kn);
static void filt_fifowdetach(struct knote *kn);
static int filt_fifowrite(struct knote *kn, long hint);
struct filterops fifo_rwfiltops[] = {
{ 1, filt_fiforattach, filt_fifordetach, filt_fiforead },
{ 1, filt_fifowattach, filt_fifowdetach, filt_fifowrite },
};
vop_t **fifo_vnodeop_p;
static struct vnodeopv_entry_desc fifo_vnodeop_entries[] = {
{ &vop_default_desc, (vop_t *) vop_defaultop },
{ &vop_access_desc, (vop_t *) vop_ebadf },
{ &vop_advlock_desc, (vop_t *) fifo_advlock },
{ &vop_bmap_desc, (vop_t *) fifo_bmap },
{ &vop_close_desc, (vop_t *) fifo_close },
{ &vop_create_desc, (vop_t *) fifo_badop },
{ &vop_getattr_desc, (vop_t *) vop_ebadf },
{ &vop_inactive_desc, (vop_t *) fifo_inactive },
{ &vop_ioctl_desc, (vop_t *) fifo_ioctl },
{ &vop_lease_desc, (vop_t *) vop_null },
{ &vop_link_desc, (vop_t *) fifo_badop },
{ &vop_lookup_desc, (vop_t *) fifo_lookup },
{ &vop_mkdir_desc, (vop_t *) fifo_badop },
{ &vop_mknod_desc, (vop_t *) fifo_badop },
{ &vop_open_desc, (vop_t *) fifo_open },
{ &vop_pathconf_desc, (vop_t *) fifo_pathconf },
{ &vop_poll_desc, (vop_t *) fifo_poll },
{ &vop_getwritemount_desc, (vop_t *) vop_stdgetwritemount },
{ &vop_print_desc, (vop_t *) fifo_print },
{ &vop_read_desc, (vop_t *) fifo_read },
{ &vop_readdir_desc, (vop_t *) fifo_badop },
{ &vop_readlink_desc, (vop_t *) fifo_badop },
{ &vop_reallocblks_desc, (vop_t *) fifo_badop },
{ &vop_reclaim_desc, (vop_t *) vop_null },
{ &vop_remove_desc, (vop_t *) fifo_badop },
{ &vop_rename_desc, (vop_t *) fifo_badop },
{ &vop_rmdir_desc, (vop_t *) fifo_badop },
{ &vop_setattr_desc, (vop_t *) vop_ebadf },
{ &vop_symlink_desc, (vop_t *) fifo_badop },
{ &vop_write_desc, (vop_t *) fifo_write },
{ NULL, NULL }
};
static struct vnodeopv_desc fifo_vnodeop_opv_desc =
{ &fifo_vnodeop_p, fifo_vnodeop_entries };
VNODEOP_SET(fifo_vnodeop_opv_desc);
int
fifo_vnoperate(ap)
struct vop_generic_args /* {
struct vnodeop_desc *a_desc;
<other random data follows, presumably>
} */ *ap;
{
return (VOCALL(fifo_vnodeop_p, ap->a_desc->vdesc_offset, ap));
}
/*
* Trivial lookup routine that always fails.
*/
/* ARGSUSED */
static int
fifo_lookup(ap)
struct vop_lookup_args /* {
struct vnode * a_dvp;
struct vnode ** a_vpp;
struct componentname * a_cnp;
} */ *ap;
{
*ap->a_vpp = NULL;
return (ENOTDIR);
}
/*
* Open called to set up a new instance of a fifo or
* to find an active instance of a fifo.
*/
/* ARGSUSED */
static int
fifo_open(ap)
struct vop_open_args /* {
struct vnode *a_vp;
int a_mode;
struct ucred *a_cred;
struct proc *a_p;
} */ *ap;
{
struct vnode *vp = ap->a_vp;
struct fifoinfo *fip;
struct proc *p = ap->a_p;
struct socket *rso, *wso;
int error;
if ((fip = vp->v_fifoinfo) == NULL) {
MALLOC(fip, struct fifoinfo *, sizeof(*fip), M_VNODE, M_WAITOK);
vp->v_fifoinfo = fip;
error = socreate(AF_LOCAL, &rso, SOCK_STREAM, 0, ap->a_p);
if (error) {
free(fip, M_VNODE);
vp->v_fifoinfo = NULL;
return (error);
}
fip->fi_readsock = rso;
error = socreate(AF_LOCAL, &wso, SOCK_STREAM, 0, ap->a_p);
if (error) {
(void)soclose(rso);
free(fip, M_VNODE);
vp->v_fifoinfo = NULL;
return (error);
}
fip->fi_writesock = wso;
error = unp_connect2(wso, rso);
if (error) {
(void)soclose(wso);
(void)soclose(rso);
free(fip, M_VNODE);
vp->v_fifoinfo = NULL;
return (error);
}
fip->fi_readers = fip->fi_writers = 0;
wso->so_snd.sb_lowat = PIPE_BUF;
rso->so_state |= SS_CANTRCVMORE;
}
if (ap->a_mode & FREAD) {
fip->fi_readers++;
if (fip->fi_readers == 1) {
fip->fi_writesock->so_state &= ~SS_CANTSENDMORE;
if (fip->fi_writers > 0)
wakeup((caddr_t)&fip->fi_writers);
}
}
if (ap->a_mode & FWRITE) {
fip->fi_writers++;
if (fip->fi_writers == 1) {
fip->fi_readsock->so_state &= ~SS_CANTRCVMORE;
if (fip->fi_readers > 0)
wakeup((caddr_t)&fip->fi_readers);
}
}
if ((ap->a_mode & FREAD) && (ap->a_mode & O_NONBLOCK) == 0) {
while (fip->fi_writers == 0) {
VOP_UNLOCK(vp, 0, p);
error = tsleep((caddr_t)&fip->fi_readers,
PCATCH | PSOCK, "fifoor", 0);
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY, p);
if (error)
goto bad;
}
}
if (ap->a_mode & FWRITE) {
if (ap->a_mode & O_NONBLOCK) {
if (fip->fi_readers == 0) {
error = ENXIO;
goto bad;
}
} else {
while (fip->fi_readers == 0) {
VOP_UNLOCK(vp, 0, p);
error = tsleep((caddr_t)&fip->fi_writers,
PCATCH | PSOCK, "fifoow", 0);
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY, p);
if (error)
goto bad;
}
}
}
return (0);
bad:
VOP_CLOSE(vp, ap->a_mode, ap->a_cred, p);
return (error);
}
/*
* Vnode op for read
*/
/* ARGSUSED */
static int
fifo_read(ap)
struct vop_read_args /* {
struct vnode *a_vp;
struct uio *a_uio;
int a_ioflag;
struct ucred *a_cred;
} */ *ap;
{
struct uio *uio = ap->a_uio;
struct socket *rso = ap->a_vp->v_fifoinfo->fi_readsock;
struct proc *p = uio->uio_procp;
int error, startresid;
#ifdef DIAGNOSTIC
if (uio->uio_rw != UIO_READ)
panic("fifo_read mode");
#endif
if (uio->uio_resid == 0)
return (0);
if (ap->a_ioflag & IO_NDELAY)
rso->so_state |= SS_NBIO;
startresid = uio->uio_resid;
VOP_UNLOCK(ap->a_vp, 0, p);
error = soreceive(rso, (struct sockaddr **)0, uio, (struct mbuf **)0,
(struct mbuf **)0, (int *)0);
vn_lock(ap->a_vp, LK_EXCLUSIVE | LK_RETRY, p);
if (ap->a_ioflag & IO_NDELAY)
rso->so_state &= ~SS_NBIO;
return (error);
}
/*
* Vnode op for write
*/
/* ARGSUSED */
static int
fifo_write(ap)
struct vop_write_args /* {
struct vnode *a_vp;
struct uio *a_uio;
int a_ioflag;
struct ucred *a_cred;
} */ *ap;
{
struct socket *wso = ap->a_vp->v_fifoinfo->fi_writesock;
struct proc *p = ap->a_uio->uio_procp;
int error;
#ifdef DIAGNOSTIC
if (ap->a_uio->uio_rw != UIO_WRITE)
panic("fifo_write mode");
#endif
if (ap->a_ioflag & IO_NDELAY)
wso->so_state |= SS_NBIO;
VOP_UNLOCK(ap->a_vp, 0, p);
error = sosend(wso, (struct sockaddr *)0, ap->a_uio, 0,
(struct mbuf *)0, 0, p);
vn_lock(ap->a_vp, LK_EXCLUSIVE | LK_RETRY, p);
if (ap->a_ioflag & IO_NDELAY)
wso->so_state &= ~SS_NBIO;
return (error);
}
/*
* Device ioctl operation.
*/
/* ARGSUSED */
static int
fifo_ioctl(ap)
struct vop_ioctl_args /* {
struct vnode *a_vp;
int a_command;
caddr_t a_data;
int a_fflag;
struct ucred *a_cred;
struct proc *a_p;
} */ *ap;
{
struct file filetmp;
int error;
if (ap->a_command == FIONBIO)
return (0);
if (ap->a_fflag & FREAD) {
filetmp.f_data = (caddr_t)ap->a_vp->v_fifoinfo->fi_readsock;
error = soo_ioctl(&filetmp, ap->a_command, ap->a_data, ap->a_p);
if (error)
return (error);
}
if (ap->a_fflag & FWRITE) {
filetmp.f_data = (caddr_t)ap->a_vp->v_fifoinfo->fi_writesock;
error = soo_ioctl(&filetmp, ap->a_command, ap->a_data, ap->a_p);
if (error)
return (error);
}
return (0);
}
static int
filt_fiforattach(struct knote *kn)
{
struct vnode *vn = (struct vnode *)kn->kn_fp->f_data;
struct socket *so = (struct socket *)vn->v_fifoinfo->fi_readsock;
SLIST_INSERT_HEAD(&so->so_rcv.sb_sel.si_note, kn, kn_selnext);
so->so_rcv.sb_flags |= SB_KNOTE;
return (0);
}
static void
filt_fifordetach(struct knote *kn)
{
struct vnode *vn = (struct vnode *)kn->kn_fp->f_data;
struct socket *so = (struct socket *)vn->v_fifoinfo->fi_readsock;
SLIST_REMOVE(&so->so_rcv.sb_sel.si_note, kn, knote, kn_selnext);
if (SLIST_EMPTY(&so->so_rcv.sb_sel.si_note))
so->so_rcv.sb_flags &= ~SB_KNOTE;
}
static int
filt_fiforead(struct knote *kn, long hint)
{
struct vnode *vn = (struct vnode *)kn->kn_fp->f_data;
struct socket *so = (struct socket *)vn->v_fifoinfo->fi_readsock;
kn->kn_data = so->so_rcv.sb_cc;
if (so->so_state & SS_CANTRCVMORE) {
kn->kn_flags |= EV_EOF;
return (1);
}
kn->kn_flags &= ~EV_EOF;
return (kn->kn_data > 0);
}
static int
filt_fifowattach(struct knote *kn)
{
struct vnode *vn = (struct vnode *)kn->kn_fp->f_data;
struct socket *so = (struct socket *)vn->v_fifoinfo->fi_writesock;
SLIST_INSERT_HEAD(&so->so_snd.sb_sel.si_note, kn, kn_selnext);
so->so_rcv.sb_flags |= SB_KNOTE;
return (0);
}
static void
filt_fifowdetach(struct knote *kn)
{
struct vnode *vn = (struct vnode *)kn->kn_fp->f_data;
struct socket *so = (struct socket *)vn->v_fifoinfo->fi_readsock;
SLIST_REMOVE(&so->so_snd.sb_sel.si_note, kn, knote, kn_selnext);
if (SLIST_EMPTY(&so->so_snd.sb_sel.si_note))
so->so_snd.sb_flags &= ~SB_KNOTE;
}
static int
filt_fifowrite(struct knote *kn, long hint)
{
struct vnode *vn = (struct vnode *)kn->kn_fp->f_data;
struct socket *so = (struct socket *)vn->v_fifoinfo->fi_readsock;
kn->kn_data = sbspace(&so->so_snd);
if (so->so_state & SS_CANTSENDMORE) {
kn->kn_flags |= EV_EOF;
return (1);
}
kn->kn_flags &= ~EV_EOF;
return (kn->kn_data >= so->so_snd.sb_lowat);
}
/* ARGSUSED */
static int
fifo_poll(ap)
struct vop_poll_args /* {
struct vnode *a_vp;
int a_events;
struct ucred *a_cred;
struct proc *a_p;
} */ *ap;
{
struct file filetmp;
int revents = 0;
if (ap->a_events & (POLLIN | POLLPRI | POLLRDNORM | POLLRDBAND)) {
filetmp.f_data = (caddr_t)ap->a_vp->v_fifoinfo->fi_readsock;
if (filetmp.f_data)
revents |= soo_poll(&filetmp, ap->a_events, ap->a_cred,
ap->a_p);
}
if (ap->a_events & (POLLOUT | POLLWRNORM | POLLWRBAND)) {
filetmp.f_data = (caddr_t)ap->a_vp->v_fifoinfo->fi_writesock;
if (filetmp.f_data)
revents |= soo_poll(&filetmp, ap->a_events, ap->a_cred,
ap->a_p);
}
return (revents);
}
static int
fifo_inactive(ap)
struct vop_inactive_args /* {
struct vnode *a_vp;
struct proc *a_p;
} */ *ap;
{
VOP_UNLOCK(ap->a_vp, 0, ap->a_p);
return (0);
}
/*
* This is a noop, simply returning what one has been given.
*/
static int
fifo_bmap(ap)
struct vop_bmap_args /* {
struct vnode *a_vp;
daddr_t a_bn;
struct vnode **a_vpp;
daddr_t *a_bnp;
int *a_runp;
int *a_runb;
} */ *ap;
{
if (ap->a_vpp != NULL)
*ap->a_vpp = ap->a_vp;
if (ap->a_bnp != NULL)
*ap->a_bnp = ap->a_bn;
if (ap->a_runp != NULL)
*ap->a_runp = 0;
if (ap->a_runb != NULL)
*ap->a_runb = 0;
return (0);
}
/*
* Device close routine
*/
/* ARGSUSED */
static int
fifo_close(ap)
struct vop_close_args /* {
struct vnode *a_vp;
int a_fflag;
struct ucred *a_cred;
struct proc *a_p;
} */ *ap;
{
register struct vnode *vp = ap->a_vp;
register struct fifoinfo *fip = vp->v_fifoinfo;
int error1, error2;
if (ap->a_fflag & FREAD) {
fip->fi_readers--;
if (fip->fi_readers == 0)
socantsendmore(fip->fi_writesock);
}
if (ap->a_fflag & FWRITE) {
fip->fi_writers--;
if (fip->fi_writers == 0)
socantrcvmore(fip->fi_readsock);
}
if (vp->v_usecount > 1)
return (0);
error1 = soclose(fip->fi_readsock);
error2 = soclose(fip->fi_writesock);
FREE(fip, M_VNODE);
vp->v_fifoinfo = NULL;
if (error1)
return (error1);
return (error2);
}
/*
* Print out internal contents of a fifo vnode.
*/
int
fifo_printinfo(vp)
struct vnode *vp;
{
register struct fifoinfo *fip = vp->v_fifoinfo;
printf(", fifo with %ld readers and %ld writers",
fip->fi_readers, fip->fi_writers);
return (0);
}
/*
* Print out the contents of a fifo vnode.
*/
static int
fifo_print(ap)
struct vop_print_args /* {
struct vnode *a_vp;
} */ *ap;
{
printf("tag VT_NON");
fifo_printinfo(ap->a_vp);
printf("\n");
return (0);
}
/*
* Return POSIX pathconf information applicable to fifo's.
*/
int
fifo_pathconf(ap)
struct vop_pathconf_args /* {
struct vnode *a_vp;
int a_name;
int *a_retval;
} */ *ap;
{
switch (ap->a_name) {
case _PC_LINK_MAX:
*ap->a_retval = LINK_MAX;
return (0);
case _PC_PIPE_BUF:
*ap->a_retval = PIPE_BUF;
return (0);
case _PC_CHOWN_RESTRICTED:
*ap->a_retval = 1;
return (0);
default:
return (EINVAL);
}
/* NOTREACHED */
}
/*
* Fifo advisory byte-level locks.
*/
/* ARGSUSED */
static int
fifo_advlock(ap)
struct vop_advlock_args /* {
struct vnode *a_vp;
caddr_t a_id;
int a_op;
struct flock *a_fl;
int a_flags;
} */ *ap;
{
return (ap->a_flags & F_FLOCK ? EOPNOTSUPP : EINVAL);
}
/*
* Fifo bad operation
*/
static int
fifo_badop()
{
panic("fifo_badop called");
/* NOTREACHED */
}