vfs_syscalls.c

早期freebsd实现

/*
 * Copyright (c) 1989, 1993
 *	The Regents of the University of California.  All rights reserved.
 * (c) UNIX System Laboratories, Inc.
 * All or some portions of this file are derived from material licensed
 * to the University of California by American Telephone and Telegraph
 * Co. or Unix System Laboratories, Inc. and are reproduced herein with
 * the permission of UNIX System Laboratories, Inc.
 *
 * 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.
 *
 *	@(#)vfs_syscalls.c	8.13 (Berkeley) 4/15/94
 */

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/namei.h>
#include <sys/filedesc.h>
#include <sys/kernel.h>
#include <sys/file.h>
#include <sys/stat.h>
#include <sys/vnode.h>
#include <sys/mount.h>
#include <sys/proc.h>
#include <sys/uio.h>
#include <sys/malloc.h>
#include <sys/dirent.h>

#include <vm/vm.h>
#include <sys/sysctl.h>

static int change_dir __P((struct nameidata *ndp, struct proc *p));

/*
 * Virtual File System System Calls
 */

/*
 * Mount a file system.
 */
struct mount_args {
	int	type;
	char	*path;
	int	flags;
	caddr_t	data;
};
/* ARGSUSED */
mount(p, uap, retval)
	struct proc *p;
	register struct mount_args *uap;
	int *retval;
{
	register struct vnode *vp;
	register struct mount *mp;
	int error, flag;
	struct nameidata nd;

	/*
	 * Must be super user
	 */
	if (error = suser(p->p_ucred, &p->p_acflag))
		return (error);
	/*
	 * Get vnode to be covered
	 */
	NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_USERSPACE, uap->path, p);
	if (error = namei(&nd))
		return (error);
	vp = nd.ni_vp;
	if (uap->flags & MNT_UPDATE) {
		if ((vp->v_flag & VROOT) == 0) {
			vput(vp);
			return (EINVAL);
		}
		mp = vp->v_mount;
		flag = mp->mnt_flag;
		/*
		 * We only allow the filesystem to be reloaded if it
		 * is currently mounted read-only.
		 */
		if ((uap->flags & MNT_RELOAD) &&
		    ((mp->mnt_flag & MNT_RDONLY) == 0)) {
			vput(vp);
			return (EOPNOTSUPP);	/* Needs translation */
		}
		mp->mnt_flag |=
		    uap->flags & (MNT_RELOAD | MNT_FORCE | MNT_UPDATE);
		VOP_UNLOCK(vp);
		goto update;
	}
	if (error = vinvalbuf(vp, V_SAVE, p->p_ucred, p, 0, 0))
		return (error);
	if (vp->v_type != VDIR) {
		vput(vp);
		return (ENOTDIR);
	}
	if ((u_long)uap->type > MOUNT_MAXTYPE || vfssw[uap->type] == NULL) {
		vput(vp);
		return (ENODEV);
	}

	/*
	 * Allocate and initialize the file system.
	 */
	mp = (struct mount *)malloc((u_long)sizeof(struct mount),
		M_MOUNT, M_WAITOK);
	bzero((char *)mp, (u_long)sizeof(struct mount));
	mp->mnt_op = vfssw[uap->type];
	if (error = vfs_lock(mp)) {
		free((caddr_t)mp, M_MOUNT);
		vput(vp);
		return (error);
	}
	if (vp->v_mountedhere != NULL) {
		vfs_unlock(mp);
		free((caddr_t)mp, M_MOUNT);
		vput(vp);
		return (EBUSY);
	}
	vp->v_mountedhere = mp;
	mp->mnt_vnodecovered = vp;
update:
	/*
	 * Set the mount level flags.
	 */
	if (uap->flags & MNT_RDONLY)
		mp->mnt_flag |= MNT_RDONLY;
	else if (mp->mnt_flag & MNT_RDONLY)
		mp->mnt_flag |= MNT_WANTRDWR;
	mp->mnt_flag &=~ (MNT_NOSUID | MNT_NOEXEC | MNT_NODEV |
	    MNT_SYNCHRONOUS | MNT_UNION | MNT_ASYNC);
	mp->mnt_flag |= uap->flags & (MNT_NOSUID | MNT_NOEXEC | MNT_NODEV |
	    MNT_SYNCHRONOUS | MNT_UNION | MNT_ASYNC);
	/*
	 * Mount the filesystem.
	 */
	error = VFS_MOUNT(mp, uap->path, uap->data, &nd, p);
	if (mp->mnt_flag & MNT_UPDATE) {
		vrele(vp);
		if (mp->mnt_flag & MNT_WANTRDWR)
			mp->mnt_flag &= ~MNT_RDONLY;
		mp->mnt_flag &=~
		    (MNT_UPDATE | MNT_RELOAD | MNT_FORCE | MNT_WANTRDWR);
		if (error)
			mp->mnt_flag = flag;
		return (error);
	}
	/*
	 * Put the new filesystem on the mount list after root.
	 */
	cache_purge(vp);
	if (!error) {
		TAILQ_INSERT_TAIL(&mountlist, mp, mnt_list);
		VOP_UNLOCK(vp);
		vfs_unlock(mp);
		error = VFS_START(mp, 0, p);
	} else {
		mp->mnt_vnodecovered->v_mountedhere = (struct mount *)0;
		vfs_unlock(mp);
		free((caddr_t)mp, M_MOUNT);
		vput(vp);
	}
	return (error);
}

/*
 * Unmount a file system.
 *
 * Note: unmount takes a path to the vnode mounted on as argument,
 * not special file (as before).
 */
struct unmount_args {
	char	*path;
	int	flags;
};
/* ARGSUSED */
unmount(p, uap, retval)
	struct proc *p;
	register struct unmount_args *uap;
	int *retval;
{
	register struct vnode *vp;
	struct mount *mp;
	int error;
	struct nameidata nd;

	NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_USERSPACE, uap->path, p);
	if (error = namei(&nd))
		return (error);
	vp = nd.ni_vp;

	/*
	 * Unless this is a user mount, then must
	 * have suser privilege.
	 */
	if (((vp->v_mount->mnt_flag & MNT_USER) == 0) &&
	    (error = suser(p->p_ucred, &p->p_acflag))) {
		vput(vp);
		return (error);
	}

	/*
	 * Must be the root of the filesystem
	 */
	if ((vp->v_flag & VROOT) == 0) {
		vput(vp);
		return (EINVAL);
	}
	mp = vp->v_mount;
	vput(vp);
	return (dounmount(mp, uap->flags, p));
}

/*
 * Do the actual file system unmount.
 */
dounmount(mp, flags, p)
	register struct mount *mp;
	int flags;
	struct proc *p;
{
	struct vnode *coveredvp;
	int error;

	coveredvp = mp->mnt_vnodecovered;
	if (vfs_busy(mp))
		return (EBUSY);
	mp->mnt_flag |= MNT_UNMOUNT;
	if (error = vfs_lock(mp))
		return (error);

	mp->mnt_flag &=~ MNT_ASYNC;
	vnode_pager_umount(mp);	/* release cached vnodes */
	cache_purgevfs(mp);	/* remove cache entries for this file sys */
	if ((error = VFS_SYNC(mp, MNT_WAIT, p->p_ucred, p)) == 0 ||
	    (flags & MNT_FORCE))
		error = VFS_UNMOUNT(mp, flags, p);
	mp->mnt_flag &= ~MNT_UNMOUNT;
	vfs_unbusy(mp);
	if (error) {
		vfs_unlock(mp);
	} else {
		vrele(coveredvp);
		TAILQ_REMOVE(&mountlist, mp, mnt_list);
		mp->mnt_vnodecovered->v_mountedhere = (struct mount *)0;
		vfs_unlock(mp);
		if (mp->mnt_vnodelist.lh_first != NULL)
			panic("unmount: dangling vnode");
		free((caddr_t)mp, M_MOUNT);
	}
	return (error);
}

/*
 * Sync each mounted filesystem.
 */
#ifdef DIAGNOSTIC
int syncprt = 0;
struct ctldebug debug0 = { "syncprt", &syncprt };
#endif

struct sync_args {
	int	dummy;
};
/* ARGSUSED */
sync(p, uap, retval)
	struct proc *p;
	struct sync_args *uap;
	int *retval;
{
	register struct mount *mp, *nmp;
	int asyncflag;

	for (mp = mountlist.tqh_first; mp != NULL; mp = nmp) {
		nmp = mp->mnt_list.tqe_next;
		/*
		 * The lock check below is to avoid races with mount
		 * and unmount.
		 */
		if ((mp->mnt_flag & (MNT_MLOCK|MNT_RDONLY|MNT_MPBUSY)) == 0 &&
		    !vfs_busy(mp)) {
			asyncflag = mp->mnt_flag & MNT_ASYNC;
			mp->mnt_flag &= ~MNT_ASYNC;
			VFS_SYNC(mp, MNT_NOWAIT, p->p_ucred, p);
			if (asyncflag)
				mp->mnt_flag |= MNT_ASYNC;
			vfs_unbusy(mp);
		}
	}
#ifdef DIAGNOSTIC
	if (syncprt)
		vfs_bufstats();
#endif /* DIAGNOSTIC */
	return (0);
}

/*
 * Change filesystem quotas.
 */
struct quotactl_args {
	char *path;
	int cmd;
	int uid;
	caddr_t arg;
};
/* ARGSUSED */
quotactl(p, uap, retval)
	struct proc *p;
	register struct quotactl_args *uap;
	int *retval;
{
	register struct mount *mp;
	int error;
	struct nameidata nd;

	NDINIT(&nd, LOOKUP, FOLLOW, UIO_USERSPACE, uap->path, p);
	if (error = namei(&nd))
		return (error);
	mp = nd.ni_vp->v_mount;
	vrele(nd.ni_vp);
	return (VFS_QUOTACTL(mp, uap->cmd, uap->uid, uap->arg, p));
}

/*
 * Get filesystem statistics.
 */
struct statfs_args {
	char *path;
	struct statfs *buf;
};
/* ARGSUSED */
statfs(p, uap, retval)
	struct proc *p;
	register struct statfs_args *uap;
	int *retval;
{
	register struct mount *mp;
	register struct statfs *sp;
	int error;
	struct nameidata nd;

	NDINIT(&nd, LOOKUP, FOLLOW, UIO_USERSPACE, uap->path, p);
	if (error = namei(&nd))
		return (error);
	mp = nd.ni_vp->v_mount;
	sp = &mp->mnt_stat;
	vrele(nd.ni_vp);
	if (error = VFS_STATFS(mp, sp, p))
		return (error);
	sp->f_flags = mp->mnt_flag & MNT_VISFLAGMASK;
	return (copyout((caddr_t)sp, (caddr_t)uap->buf, sizeof(*sp)));
}

/*
 * Get filesystem statistics.
 */
struct fstatfs_args {
	int fd;
	struct statfs *buf;
};
/* ARGSUSED */
fstatfs(p, uap, retval)
	struct proc *p;
	register struct fstatfs_args *uap;
	int *retval;
{
	struct file *fp;
	struct mount *mp;
	register struct statfs *sp;
	int error;

	if (error = getvnode(p->p_fd, uap->fd, &fp))
		return (error);
	mp = ((struct vnode *)fp->f_data)->v_mount;
	sp = &mp->mnt_stat;
	if (error = VFS_STATFS(mp, sp, p))
		return (error);
	sp->f_flags = mp->mnt_flag & MNT_VISFLAGMASK;
	return (copyout((caddr_t)sp, (caddr_t)uap->buf, sizeof(*sp)));
}

/*
 * Get statistics on all filesystems.
 */
struct getfsstat_args {
	struct statfs *buf;
	long bufsize;
	int flags;
};
getfsstat(p, uap, retval)
	struct proc *p;
	register struct getfsstat_args *uap;
	int *retval;
{
	register struct mount *mp, *nmp;
	register struct statfs *sp;
	caddr_t sfsp;
	long count, maxcount, error;

	maxcount = uap->bufsize / sizeof(struct statfs);
	sfsp = (caddr_t)uap->buf;
	for (count = 0, mp = mountlist.tqh_first; mp != NULL; mp = nmp) {
		nmp = mp->mnt_list.tqe_next;
		if (sfsp && count < maxcount &&
		    ((mp->mnt_flag & MNT_MLOCK) == 0)) {
			sp = &mp->mnt_stat;
			/*
			 * If MNT_NOWAIT is specified, do not refresh the
			 * fsstat cache. MNT_WAIT overrides MNT_NOWAIT.
			 */
			if (((uap->flags & MNT_NOWAIT) == 0 ||
			    (uap->flags & MNT_WAIT)) &&
			    (error = VFS_STATFS(mp, sp, p)))
				continue;
			sp->f_flags = mp->mnt_flag & MNT_VISFLAGMASK;
			if (error = copyout((caddr_t)sp, sfsp, sizeof(*sp)))
				return (error);
			sfsp += sizeof(*sp);
		}
		count++;
	}
	if (sfsp && count > maxcount)
		*retval = maxcount;
	else
		*retval = count;
	return (0);
}

/*
 * Change current working directory to a given file descriptor.
 */
struct fchdir_args {
	int	fd;
};
/* ARGSUSED */
fchdir(p, uap, retval)
	struct proc *p;
	struct fchdir_args *uap;
	int *retval;
{
	register struct filedesc *fdp = p->p_fd;
	register struct vnode *vp;
	struct file *fp;
	int error;

	if (error = getvnode(fdp, uap->fd, &fp))
		return (error);
	vp = (struct vnode *)fp->f_data;
	VOP_LOCK(vp);
	if (vp->v_type != VDIR)
		error = ENOTDIR;
	else
		error = VOP_ACCESS(vp, VEXEC, p->p_ucred, p);
	VOP_UNLOCK(vp);
	if (error)
		return (error);
	VREF(vp);
	vrele(fdp->fd_cdir);
	fdp->fd_cdir = vp;
	return (0);
}

/*
 * Change current working directory (``.'').
 */
struct chdir_args {
	char	*path;
};
/* ARGSUSED */
chdir(p, uap, retval)
	struct proc *p;
	struct chdir_args *uap;
	int *retval;
{
	register struct filedesc *fdp = p->p_fd;
	int error;
	struct nameidata nd;

	NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_USERSPACE, uap->path, p);
	if (error = change_dir(&nd, p))
		return (error);
	vrele(fdp->fd_cdir);
	fdp->fd_cdir = nd.ni_vp;
	return (0);
}

/*
 * Change notion of root (``/'') directory.
 */
struct chroot_args {
	char	*path;
};
/* ARGSUSED */
chroot(p, uap, retval)
	struct proc *p;
	struct chroot_args *uap;
	int *retval;
{
	register struct filedesc *fdp = p->p_fd;
	int error;
	struct nameidata nd;

	if (error = suser(p->p_ucred, &p->p_acflag))
		return (error);
	NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_USERSPACE, uap->path, p);
	if (error = change_dir(&nd, p))
		return (error);
	if (fdp->fd_rdir != NULL)
		vrele(fdp->fd_rdir);
	fdp->fd_rdir = nd.ni_vp;
	return (0);
}

/*
 * Common routine for chroot and chdir.
 */
static int
change_dir(ndp, p)
	register struct nameidata *ndp;
	struct proc *p;
{
	struct vnode *vp;
	int error;

	if (error = namei(ndp))
		return (error);
	vp = ndp->ni_vp;
	if (vp->v_type != VDIR)
		error = ENOTDIR;
	else
		error = VOP_ACCESS(vp, VEXEC, p->p_ucred, p);
	VOP_UNLOCK(vp);
	if (error)
		vrele(vp);
	return (error);
}

/*
 * Check permissions, allocate an open file structure,
 * and call the device open routine if any.
 */
struct open_args {
	char	*path;
	int	flags;
	int	mode;
};
open(p, uap, retval)
	struct proc *p;
	register struct open_args *uap;
	int *retval;
{
	register struct filedesc *fdp = p->p_fd;
	register struct file *fp;
	register struct vnode *vp;
	int flags, cmode;
	struct file *nfp;
	int type, indx, error;
	struct flock lf;
	struct nameidata nd;
	extern struct fileops vnops;

	if (error = falloc(p, &nfp, &indx))
		return (error);
	fp = nfp;
	flags = FFLAGS(uap->flags);
	cmode = ((uap->mode &~ fdp->fd_cmask) & ALLPERMS) &~ S_ISTXT;
	NDINIT(&nd, LOOKUP, FOLLOW, UIO_USERSPACE, uap->path, p);
	p->p_dupfd = -indx - 1;			/* XXX check for fdopen */
	if (error = vn_open(&nd, flags, cmode)) {
		ffree(fp);
		if ((error == ENODEV || error == ENXIO) &&
		    p->p_dupfd >= 0 && 			/* XXX from fdopen */
		    (error =
		        dupfdopen(fdp, indx, p->p_dupfd, flags, error)) == 0) {
			*retval = indx;
			return (0);
		}
		if (error == ERESTART)
			error = EINTR;
		fdp->fd_ofiles[indx] = NULL;
		return (error);
	}
	p->p_dupfd = 0;
	vp = nd.ni_vp;
	fp->f_flag = flags & FMASK;
	fp->f_type = DTYPE_VNODE;
	fp->f_ops = &vnops;
	fp->f_data = (caddr_t)vp;
	if (flags & (O_EXLOCK | O_SHLOCK)) {
		lf.l_whence = SEEK_SET;
		lf.l_start = 0;
		lf.l_len = 0;
		if (flags & O_EXLOCK)
			lf.l_type = F_WRLCK;
		else
			lf.l_type = F_RDLCK;
		type = F_FLOCK;
		if ((flags & FNONBLOCK) == 0)
			type |= F_WAIT;
		VOP_UNLOCK(vp);
		if (error = VOP_ADVLOCK(vp, (caddr_t)fp, F_SETLK, &lf, type)) {
			(void) vn_close(vp, fp->f_flag, fp->f_cred, p);
			ffree(fp);
			fdp->fd_ofiles[indx] = NULL;
			return (error);
		}
		VOP_LOCK(vp);
		fp->f_flag |= FHASLOCK;
	}
	VOP_UNLOCK(vp);
	*retval = indx;
	return (0);
}

#ifdef COMPAT_43
/*
 * Create a file.
 */
struct ocreat_args {
	char	*path;
	int	mode;
};
ocreat(p, uap, retval)
	struct proc *p;
	register struct ocreat_args *uap;
	int *retval;
{
	struct open_args openuap;

	openuap.path = uap->path;
	openuap.mode = uap->mode;
	openuap.flags = O_WRONLY | O_CREAT | O_TRUNC;
	return (open(p, &openuap, retval));
}
#endif /* COMPAT_43 */

/*
 * Create a special file.
 */
struct mknod_args {
	char	*path;
	int	mode;
	int	dev;
};
/* ARGSUSED */
mknod(p, uap, retval)
	struct proc *p;
	register struct mknod_args *uap;
	int *retval;
{
	register struct vnode *vp;
	struct vattr vattr;
	int error;
	struct nameidata nd;

	if (error = suser(p->p_ucred, &p->p_acflag))
		return (error);
	NDINIT(&nd, CREATE, LOCKPARENT, UIO_USERSPACE, uap->path, p);
	if (error = namei(&nd))
		return (error);
	vp = nd.ni_vp;
	if (vp != NULL)
		error = EEXIST;
	else {
		VATTR_NULL(&vattr);
		vattr.va_mode = (uap->mode & ALLPERMS) &~ p->p_fd->fd_cmask;
		vattr.va_rdev = uap->dev;

		switch (uap->mode & S_IFMT) {
		case S_IFMT:	/* used by badsect to flag bad sectors */
			vattr.va_type = VBAD;
			break;
		case S_IFCHR:
			vattr.va_type = VCHR;
			break;
		case S_IFBLK:
			vattr.va_type = VBLK;