vfs_syscalls.c

来自「基于组件方式开发操作系统的OSKIT源代码」· C语言 代码 · 共 2,115 行 · 第 1/4 页

/*	$NetBSD: vfs_syscalls.c,v 1.71 1996/04/23 10:29:02 mycroft Exp $	*/

/*
 * 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	8.28 (Berkeley) 12/10/94
 */

#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 <sys/syscallargs.h>

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

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

void checkdirs __P((struct vnode *));
int dounmount __P((struct mount *, int, struct proc *));

/*
 * Virtual File System System Calls
 */

/*
 * Mount a file system.
 */
/* ARGSUSED */
int
sys_mount(p, v, retval)
	struct proc *p;
	void *v;
	register_t *retval;
{
	register struct sys_mount_args /* {
		syscallarg(char *) type;
		syscallarg(char *) path;
		syscallarg(int) flags;
		syscallarg(caddr_t) data;
	} */ *uap = v;
	register struct vnode *vp;
	register struct mount *mp;
	int error, flag = 0;
	u_long fsindex = 0;
	char fstypename[MFSNAMELEN];
	struct vattr va;
	struct nameidata nd;

	/*
	 * Get vnode to be covered
	 */
	NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_USERSPACE,
	    SCARG(uap, path), p);
	if ((error = namei(&nd)) != 0)
		return (error);
	vp = nd.ni_vp;
	if (SCARG(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 ((SCARG(uap, flags) & MNT_RELOAD) &&
		    ((mp->mnt_flag & MNT_RDONLY) == 0)) {
			vput(vp);
			return (EOPNOTSUPP);	/* Needs translation */
		}
		mp->mnt_flag |=
		    SCARG(uap, flags) & (MNT_RELOAD | MNT_FORCE | MNT_UPDATE);
		/*
		 * Only root, or the user that did the original mount is
		 * permitted to update it.
		 */
		if (mp->mnt_stat.f_owner != p->p_ucred->cr_uid &&
		    (error = suser(p->p_ucred, &p->p_acflag))) {
			vput(vp);
			return (error);
		}
		/*
		 * Do not allow NFS export by non-root users. Silently
		 * enforce MNT_NOSUID and MNT_NODEV for non-root users.
		 */
		if (p->p_ucred->cr_uid != 0) {
			if (SCARG(uap, flags) & MNT_EXPORTED) {
				vput(vp);
				return (EPERM);
			}
			SCARG(uap, flags) |= MNT_NOSUID | MNT_NODEV;
		}
		VOP_UNLOCK(vp);
		goto update;
	}
	/*
	 * If the user is not root, ensure that they own the directory
	 * onto which we are attempting to mount.
	 */
	if ((error = VOP_GETATTR(vp, &va, p->p_ucred, p)) ||
	    (va.va_uid != p->p_ucred->cr_uid &&
	     (error = suser(p->p_ucred, &p->p_acflag)))) {
		vput(vp);
		return (error);
	}
	/*
	 * Do not allow NFS export by non-root users. Silently
	 * enforce MNT_NOSUID and MNT_NODEV for non-root users.
	 */
	if (p->p_ucred->cr_uid != 0) {
		if (SCARG(uap, flags) & MNT_EXPORTED) {
			vput(vp);
			return (EPERM);
		}
		SCARG(uap, flags) |= MNT_NOSUID | MNT_NODEV;
	}
	if ((error = vinvalbuf(vp, V_SAVE, p->p_ucred, p, 0, 0)) != 0)
		return (error);
	if (vp->v_type != VDIR) {
		vput(vp);
		return (ENOTDIR);
	}
	error = copyinstr(SCARG(uap, type), fstypename, MFSNAMELEN, NULL);
	if (error) {
#if defined(COMPAT_09) || defined(COMPAT_43)
		/*
		 * Historically filesystem types were identified by number.
		 * If we get an integer for the filesystem type instead of a
		 * string, we check to see if it matches one of the historic
		 * filesystem types.
		 */     
		fsindex = (u_long)SCARG(uap, type);
		if (fsindex >= nvfssw || vfssw[fsindex] == NULL) {
			vput(vp);
			return (ENODEV);
		}
		strncpy(fstypename, vfssw[fsindex]->vfs_name, MFSNAMELEN);
#else
		vput(vp);
		return (error);
#endif
	}
#ifdef	COMPAT_10
	/* Accept `ufs' as an alias for `ffs'. */
	if (!strncmp(fstypename, "ufs", MFSNAMELEN))
		strncpy(fstypename, "ffs", MFSNAMELEN);
#endif
	for (fsindex = 0; fsindex < nvfssw; fsindex++)
		if (vfssw[fsindex] != NULL &&
		    !strncmp(vfssw[fsindex]->vfs_name, fstypename, MFSNAMELEN))
			break;
	if (fsindex >= nvfssw) {
		vput(vp);
		return (ENODEV);
	}
	if (vp->v_mountedhere != NULL) {
		vput(vp);
		return (EBUSY);
	}

	/*
	 * 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[fsindex];
	if ((error = vfs_lock(mp)) != 0) {
		free((caddr_t)mp, M_MOUNT);
		vput(vp);
		return (error);
	}
	/* Do this early in case we block later. */
	vfssw[fsindex]->vfs_refcount++;
	vp->v_mountedhere = mp;
	mp->mnt_vnodecovered = vp;
	mp->mnt_stat.f_owner = p->p_ucred->cr_uid;
update:
	/*
	 * Set the mount level flags.
	 */
	if (SCARG(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 |= SCARG(uap, flags) & (MNT_NOSUID | MNT_NOEXEC |
	    MNT_NODEV | MNT_SYNCHRONOUS | MNT_UNION | MNT_ASYNC);
	/*
	 * Mount the filesystem.
	 */
	error = VFS_MOUNT(mp, SCARG(uap, path), SCARG(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) {
		CIRCLEQ_INSERT_TAIL(&mountlist, mp, mnt_list);
		checkdirs(vp);
		VOP_UNLOCK(vp);
		vfs_unlock(mp);
		(void) VFS_STATFS(mp, &mp->mnt_stat, p);
		error = VFS_START(mp, 0, p);
	} else {
		mp->mnt_vnodecovered->v_mountedhere = (struct mount *)0;
		vfssw[fsindex]->vfs_refcount--;
		vfs_unlock(mp);
		free((caddr_t)mp, M_MOUNT);
		vput(vp);
	}
	return (error);
}

/*
 * Scan all active processes to see if any of them have a current
 * or root directory onto which the new filesystem has just been
 * mounted. If so, replace them with the new mount point.
 */
void
checkdirs(olddp)
	struct vnode *olddp;
{
	struct filedesc *fdp;
	struct vnode *newdp;
	struct proc *p;

	if (olddp->v_usecount == 1)
		return;
	if (VFS_ROOT(olddp->v_mountedhere, &newdp))
		panic("mount: lost mount");
	for (p = allproc.lh_first; p != 0; p = p->p_list.le_next) {
		fdp = p->p_fd;
		if (fdp->fd_cdir == olddp) {
			vrele(fdp->fd_cdir);
			VREF(newdp);
			fdp->fd_cdir = newdp;
		}
		if (fdp->fd_rdir == olddp) {
			vrele(fdp->fd_rdir);
			VREF(newdp);
			fdp->fd_rdir = newdp;
		}
	}
	if (rootvnode == olddp) {
		vrele(rootvnode);
		VREF(newdp);
		rootvnode = newdp;
	}
	vput(newdp);
}

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

	NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_USERSPACE,
	    SCARG(uap, path), p);
	if ((error = namei(&nd)) != 0)
		return (error);
	vp = nd.ni_vp;
	mp = vp->v_mount;

	/*
	 * Only root, or the user that did the original mount is
	 * permitted to unmount this filesystem.
	 */
	if ((mp->mnt_stat.f_owner != p->p_ucred->cr_uid) &&
	    (error = suser(p->p_ucred, &p->p_acflag))) {
		vput(vp);
		return (error);
	}

	/*
	 * Don't allow unmounting the root file system.
	 */
	if (mp->mnt_flag & MNT_ROOTFS) {
		vput(vp);
		return (EINVAL);
	}

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

/*
 * Do the actual file system unmount.
 */
int
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)) != 0)
		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 {
		CIRCLEQ_REMOVE(&mountlist, mp, mnt_list);
		if (coveredvp != NULLVP) {
			vrele(coveredvp);
			coveredvp->v_mountedhere = (struct mount *)0;
		}
		mp->mnt_op->vfs_refcount--;
		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 DEBUG
int syncprt = 0;
struct ctldebug debug0 = { "syncprt", &syncprt };
#endif

/* ARGSUSED */
int
sys_sync(p, v, retval)
	struct proc *p;
	void *v;
	register_t *retval;
{
	register struct mount *mp, *nmp;
	int asyncflag;

	for (mp = mountlist.cqh_first; mp != (void *)&mountlist; mp = nmp) {
		/*
		 * Get the next pointer in case we hang on vfs_busy
		 * while we are being unmounted.
		 */
		nmp = mp->mnt_list.cqe_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;
			/*
			 * Get the next pointer again, as the next filesystem
			 * might have been unmounted while we were sync'ing.
			 */
			nmp = mp->mnt_list.cqe_next;
			vfs_unbusy(mp);
		}
	}
#ifdef DEBUG
	if (syncprt)
		vfs_bufstats();
#endif /* DEBUG */
	return (0);
}

/*
 * Change filesystem quotas.
 */
/* ARGSUSED */
int
sys_quotactl(p, v, retval)
	struct proc *p;
	void *v;
	register_t *retval;
{
	register struct sys_quotactl_args /* {
		syscallarg(char *) path;
		syscallarg(int) cmd;
		syscallarg(int) uid;
		syscallarg(caddr_t) arg;
	} */ *uap = v;
	register struct mount *mp;
	int error;
	struct nameidata nd;

	NDINIT(&nd, LOOKUP, FOLLOW, UIO_USERSPACE, SCARG(uap, path), p);
	if ((error = namei(&nd)) != 0)
		return (error);
	mp = nd.ni_vp->v_mount;
	vrele(nd.ni_vp);
	return (VFS_QUOTACTL(mp, SCARG(uap, cmd), SCARG(uap, uid),
	    SCARG(uap, arg), p));
}

/*
 * Get filesystem statistics.
 */
/* ARGSUSED */
int
sys_statfs(p, v, retval)
	struct proc *p;
	void *v;
	register_t *retval;
{
	register struct sys_statfs_args /* {
		syscallarg(char *) path;
		syscallarg(struct statfs *) buf;
	} */ *uap = v;
	register struct mount *mp;
	register struct statfs *sp;
	int error;
	struct nameidata nd;

	NDINIT(&nd, LOOKUP, FOLLOW, UIO_USERSPACE, SCARG(uap, path), p);
	if ((error = namei(&nd)) != 0)
		return (error);
	mp = nd.ni_vp->v_mount;
	sp = &mp->mnt_stat;
	vrele(nd.ni_vp);
	if ((error = VFS_STATFS(mp, sp, p)) != 0)
		return (error);
	sp->f_flags = mp->mnt_flag & MNT_VISFLAGMASK;
	return (copyout((caddr_t)sp, (caddr_t)SCARG(uap, buf), sizeof(*sp)));
}

/*
 * Get filesystem statistics.
 */
/* ARGSUSED */
int
sys_fstatfs(p, v, retval)
	struct proc *p;