vfs.c

嵌入式系统设计与实例开发实验教材二源码 多线程应用程序设计 串行端口程序设计 AD接口实验 CAN总线通信实验 GPS通信实验 Linux内核移植与编译实验 IC卡读写实验 SD驱动使

#define MSNFS	/* HACK HACK */
/*
 * linux/fs/nfsd/vfs.c
 *
 * File operations used by nfsd. Some of these have been ripped from
 * other parts of the kernel because they weren't in ksyms.c, others
 * are partial duplicates with added or changed functionality.
 *
 * Note that several functions dget() the dentry upon which they want
 * to act, most notably those that create directory entries. Response
 * dentry's are dput()'d if necessary in the release callback.
 * So if you notice code paths that apparently fail to dput() the
 * dentry, don't worry--they have been taken care of.
 *
 * Copyright (C) 1995-1999 Olaf Kirch <[e-mail]>
 */

#include <linux/config.h>
#include <linux/version.h>
#include <linux/string.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/locks.h>
#include <linux/fs.h>
#include <linux/major.h>
#include <linux/ext2_fs.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/net.h>
#include <linux/unistd.h>
#include <linux/slab.h>
#include <linux/in.h>
#define __NO_VERSION__
#include <linux/module.h>

#include <linux/sunrpc/svc.h>
#include <linux/nfsd/nfsd.h>
#ifdef CONFIG_NFSD_V3
#include <linux/nfs3.h>
#include <linux/nfsd/xdr3.h>
#endif /* CONFIG_NFSD_V3 */
#include <linux/nfsd/nfsfh.h>
#include <linux/quotaops.h>

#include <asm/uaccess.h>

#define NFSDDBG_FACILITY		NFSDDBG_FILEOP
#define NFSD_PARANOIA


/* We must ignore files (but only files) which might have mandatory
 * locks on them because there is no way to know if the accesser has
 * the lock.
 */
#define IS_ISMNDLK(i)	(S_ISREG((i)->i_mode) && MANDATORY_LOCK(i))

/*
 * This is a cache of readahead params that help us choose the proper
 * readahead strategy. Initially, we set all readahead parameters to 0
 * and let the VFS handle things.
 * If you increase the number of cached files very much, you'll need to
 * add a hash table here.
 */
struct raparms {
	struct raparms		*p_next;
	unsigned int		p_count;
	ino_t			p_ino;
	dev_t			p_dev;
	unsigned long		p_reada,
				p_ramax,
				p_raend,
				p_ralen,
				p_rawin;
};

static struct raparms *		raparml;
static struct raparms *		raparm_cache;

/*
 * Look up one component of a pathname.
 * N.B. After this call _both_ fhp and resfh need an fh_put
 *
 * If the lookup would cross a mountpoint, and the mounted filesystem
 * is exported to the client with NFSEXP_CROSSMNT, then the lookup is
 * accepted as it stands and the mounted directory is
 * returned. Otherwise the covered directory is returned.
 * NOTE: this mountpoint crossing is not supported properly by all
 *   clients and is explicitly disallowed for NFSv3
 *      NeilBrown <[e-mail]>
 */
int
nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
					int len, struct svc_fh *resfh)
{
	struct svc_export	*exp;
	struct dentry		*dparent;
	struct dentry		*dentry;
	int			err;

	dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);

	/* Obtain dentry and export. */
	err = fh_verify(rqstp, fhp, S_IFDIR, MAY_EXEC);
	if (err)
		goto out;

	dparent = fhp->fh_dentry;
	exp  = fhp->fh_export;

	err = nfserr_acces;

	/* Lookup the name, but don't follow links */
	if (isdotent(name, len)) {
		if (len==1)
			dentry = dget(dparent);
		else  { /* must be ".." */
			/* checking mountpoint crossing is very different when stepping up */
			if (dparent == exp->ex_dentry) {
				if (!EX_CROSSMNT(exp))
					dentry = dget(dparent); /* .. == . just like at / */
				else
				{
					struct svc_export *exp2 = NULL;
					struct dentry *dp;
					struct vfsmount *mnt = mntget(exp->ex_mnt);
					dentry = dget(dparent);
					while(follow_up(&mnt, &dentry))
						;
					dp = dget(dentry->d_parent);
					dput(dentry);
					dentry = dp;
					for ( ; exp2 == NULL && dp->d_parent != dp;
					      dp=dp->d_parent)
						exp2 = exp_get(exp->ex_client, dp->d_inode->i_dev, dp->d_inode->i_ino);
					if (exp2==NULL) {
						dput(dentry);
						dentry = dget(dparent);
					} else {
						exp = exp2;
					}
					mntput(mnt);
				}
			} else
				dentry = dget(dparent->d_parent);
		}
	} else {
		fh_lock(fhp);
		dentry = lookup_one_len(name, dparent, len);
		err = PTR_ERR(dentry);
		if (IS_ERR(dentry))
			goto out_nfserr;
		/*
		 * check if we have crossed a mount point ...
		 */
		if (d_mountpoint(dentry)) {
			struct svc_export *exp2 = NULL;
			struct vfsmount *mnt = mntget(exp->ex_mnt);
			struct dentry *mounts = dget(dentry);
			while (follow_down(&mnt,&mounts)&&d_mountpoint(mounts))
				;
			exp2 = exp_get(rqstp->rq_client,
				       mounts->d_inode->i_dev,
				       mounts->d_inode->i_ino);
			if (exp2 && EX_CROSSMNT(exp2)) {
				/* successfully crossed mount point */
				exp = exp2;
				dput(dentry);
				dentry = mounts;
			} else
				dput(mounts);
			mntput(mnt);
		}
	}
	/*
	 * Note: we compose the file handle now, but as the
	 * dentry may be negative, it may need to be updated.
	 */
	err = fh_compose(resfh, exp, dentry, fhp);
	if (!err && !dentry->d_inode)
		err = nfserr_noent;
out:
	return err;

out_nfserr:
	err = nfserrno(err);
	goto out;
}

/*
 * Set various file attributes.
 * N.B. After this call fhp needs an fh_put
 */
int
nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
	     int check_guard, time_t guardtime)
{
	struct dentry	*dentry;
	struct inode	*inode;
	int		accmode = MAY_SATTR;
	int		ftype = 0;
	int		imode;
	int		err;
	int		size_change = 0;

	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
		accmode |= MAY_WRITE|MAY_OWNER_OVERRIDE;
	if (iap->ia_valid & ATTR_SIZE)
		ftype = S_IFREG;

	/* Get inode */
	err = fh_verify(rqstp, fhp, ftype, accmode);
	if (err || !iap->ia_valid)
		goto out;

	dentry = fhp->fh_dentry;
	inode = dentry->d_inode;

	err = inode_change_ok(inode, iap);
	/* could be a "touch" (utimes) request where the user is not the owner but does
	 * have write permission. In this case the user should be allowed to set
	 * both times to the current time.  We could just assume any such SETATTR
	 * is intended to set the times to "now", but we do a couple of simple tests
	 * to increase our confidence.
	 */
#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
#define	MAX_TOUCH_TIME_ERROR (30*60)
	if (err
	    && (iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET
	    && iap->ia_mtime == iap->ia_atime
	    ) {
	    /* looks good.  now just make sure time is in the right ballpark.
	     * solaris, at least, doesn't seem to care what the time request is
	     */
	    time_t delta = iap->ia_atime - CURRENT_TIME;
	    if (delta<0) delta = -delta;
	    if (delta < MAX_TOUCH_TIME_ERROR) {
		/* turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME
		 * this will cause notify_change to set these times to "now"
		 */
		iap->ia_valid &= ~BOTH_TIME_SET;
		err = inode_change_ok(inode, iap);
	    }
	}
	    
	if (err)
		goto out_nfserr;

	/* The size case is special. It changes the file as well as the attributes.  */
	if (iap->ia_valid & ATTR_SIZE) {
		if (iap->ia_size < inode->i_size) {
			err = nfsd_permission(fhp->fh_export, dentry, MAY_TRUNC|MAY_OWNER_OVERRIDE);
			if (err)
				goto out;
		}

		/*
		 * If we are changing the size of the file, then
		 * we need to break all leases.
		 */
		err = get_lease(inode, FMODE_WRITE);
		if (err)
			goto out_nfserr;

		err = get_write_access(inode);
		if (err)
			goto out_nfserr;

		err = locks_verify_truncate(inode, NULL, iap->ia_size);
		if (err) {
			put_write_access(inode);
			goto out_nfserr;
		}
		DQUOT_INIT(inode);
	}

	imode = inode->i_mode;
	if (iap->ia_valid & ATTR_MODE) {
		iap->ia_mode &= S_IALLUGO;
		imode = iap->ia_mode |= (imode & ~S_IALLUGO);
	}

	/* Revoke setuid/setgid bit on chown/chgrp */
	if ((iap->ia_valid & ATTR_UID) && (imode & S_ISUID)
	 && iap->ia_uid != inode->i_uid) {
		iap->ia_valid |= ATTR_MODE;
		iap->ia_mode = imode &= ~S_ISUID;
	}
	if ((iap->ia_valid & ATTR_GID) && (imode & S_ISGID)
	 && iap->ia_gid != inode->i_gid) {
		iap->ia_valid |= ATTR_MODE;
		iap->ia_mode = imode &= ~S_ISGID;
	}

	/* Change the attributes. */


	iap->ia_valid |= ATTR_CTIME;

	if (iap->ia_valid & ATTR_SIZE) {
		fh_lock(fhp);
		size_change = 1;
	}
	err = nfserr_notsync;
	if (!check_guard || guardtime == inode->i_ctime) {
		err = notify_change(dentry, iap);
		err = nfserrno(err);
	}
	if (size_change) {
		fh_unlock(fhp);
		put_write_access(inode);
	}
	if (!err)
		if (EX_ISSYNC(fhp->fh_export))
			write_inode_now(inode, 1);
out:
	return err;

out_nfserr:
	err = nfserrno(err);
	goto out;
}

#ifdef CONFIG_NFSD_V3
/*
 * Check server access rights to a file system object
 */
struct accessmap {
	u32		access;
	int		how;
};
static struct accessmap	nfs3_regaccess[] = {
    {	NFS3_ACCESS_READ,	MAY_READ			},
    {	NFS3_ACCESS_EXECUTE,	MAY_EXEC			},
    {	NFS3_ACCESS_MODIFY,	MAY_WRITE|MAY_TRUNC		},
    {	NFS3_ACCESS_EXTEND,	MAY_WRITE			},

    {	0,			0				}
};

static struct accessmap	nfs3_diraccess[] = {
    {	NFS3_ACCESS_READ,	MAY_READ			},
    {	NFS3_ACCESS_LOOKUP,	MAY_EXEC			},
    {	NFS3_ACCESS_MODIFY,	MAY_EXEC|MAY_WRITE|MAY_TRUNC	},
    {	NFS3_ACCESS_EXTEND,	MAY_EXEC|MAY_WRITE		},
    {	NFS3_ACCESS_DELETE,	MAY_REMOVE			},

    {	0,			0				}
};

static struct accessmap	nfs3_anyaccess[] = {
	/* Some clients - Solaris 2.6 at least, make an access call
	 * to the server to check for access for things like /dev/null
	 * (which really, the server doesn't care about).  So
	 * We provide simple access checking for them, looking
	 * mainly at mode bits
	 */
    {	NFS3_ACCESS_READ,	MAY_READ			},
    {	NFS3_ACCESS_EXECUTE,	MAY_EXEC			},
    {	NFS3_ACCESS_MODIFY,	MAY_WRITE			},
    {	NFS3_ACCESS_EXTEND,	MAY_WRITE			},

    {	0,			0				}
};

int
nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access)
{
	struct accessmap	*map;
	struct svc_export	*export;
	struct dentry		*dentry;
	u32			query, result = 0;
	unsigned int		error;

	error = fh_verify(rqstp, fhp, 0, MAY_NOP);
	if (error)
		goto out;

	export = fhp->fh_export;
	dentry = fhp->fh_dentry;

	if (S_ISREG(dentry->d_inode->i_mode))
		map = nfs3_regaccess;
	else if (S_ISDIR(dentry->d_inode->i_mode))
		map = nfs3_diraccess;
	else
		map = nfs3_anyaccess;


	query = *access;
	for  (; map->access; map++) {
		if (map->access & query) {
			unsigned int err2;
			err2 = nfsd_permission(export, dentry, map->how);
			switch (err2) {
			case nfs_ok:
				result |= map->access;
				break;
				
			/* the following error codes just mean the access was not allowed,
			 * rather than an error occurred */
			case nfserr_rofs:
			case nfserr_acces:
			case nfserr_perm:
				/* simply don't "or" in the access bit. */
				break;
			default:
				error = err2;
				goto out;
			}
		}
	}
	*access = result;

 out:
	return error;
}
#endif /* CONFIG_NFSD_V3 */



/*
 * Open an existing file or directory.
 * The access argument indicates the type of open (read/write/lock)
 * N.B. After this call fhp needs an fh_put
 */
int
nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
			int access, struct file *filp)
{
	struct dentry	*dentry;
	struct inode	*inode;
	int		err;

	/* If we get here, then the client has already done an "open", and (hopefully)
	 * checked permission - so allow OWNER_OVERRIDE in case a chmod has now revoked
	 * permission */
	err = fh_verify(rqstp, fhp, type, access | MAY_OWNER_OVERRIDE);
	if (err)
		goto out;

	dentry = fhp->fh_dentry;
	inode = dentry->d_inode;

	/* Disallow access to files with the append-only bit set or
	 * with mandatory locking enabled
	 */
	err = nfserr_perm;
	if (IS_APPEND(inode) || IS_ISMNDLK(inode))
		goto out;
	if (!inode->i_fop)
		goto out;

	/*
	 * Check to see if there are any leases on this file.
	 * This may block while leases are broken.
	 */
	err = get_lease(inode, (access & MAY_WRITE) ? FMODE_WRITE : 0);
	if (err)
		goto out_nfserr;

	if ((access & MAY_WRITE) && (err = get_write_access(inode)) != 0)
		goto out_nfserr;

	memset(filp, 0, sizeof(*filp));
	filp->f_op    = fops_get(inode->i_fop);
	atomic_set(&filp->f_count, 1);
	filp->f_dentry = dentry;
	filp->f_vfsmnt = fhp->fh_export->ex_mnt;
	if (access & MAY_WRITE) {
		filp->f_flags = O_WRONLY|O_LARGEFILE;
		filp->f_mode  = FMODE_WRITE;
		DQUOT_INIT(inode);
	} else {
		filp->f_flags = O_RDONLY|O_LARGEFILE;
		filp->f_mode  = FMODE_READ;
	}

	err = 0;
	if (filp->f_op && filp->f_op->open) {
		err = filp->f_op->open(inode, filp);
		if (err) {
			fops_put(filp->f_op);
			if (access & MAY_WRITE)
				put_write_access(inode);

			/* I nearly added put_filp() call here, but this filp
			 * is really on callers stack frame. -DaveM
			 */
			atomic_dec(&filp->f_count);
		}
	}
out_nfserr:
	if (err)
		err = nfserrno(err);
out:
	return err;
}

/*
 * Close a file.
 */
void
nfsd_close(struct file *filp)
{
	struct dentry	*dentry = filp->f_dentry;
	struct inode	*inode = dentry->d_inode;

	if (filp->f_op && filp->f_op->release)
		filp->f_op->release(inode, filp);
	fops_put(filp->f_op);
	if (filp->f_mode & FMODE_WRITE)
		put_write_access(inode);
}

/*
 * Sync a file
 * As this calls fsync (not fdatasync) there is no need for a write_inode
 * after it.
 */
void
nfsd_sync(struct file *filp)
{
	dprintk("nfsd: sync file %s\n", filp->f_dentry->d_name.name);
	down(&filp->f_dentry->d_inode->i_sem);
	filp->f_op->fsync(filp, filp->f_dentry, 0);
	up(&filp->f_dentry->d_inode->i_sem);
}

void
nfsd_sync_dir(struct dentry *dp)
{