vfs.c

linux 内核源代码

		 * work:-)
		 */
		if (EX_WGATHER(exp)) {
			if (atomic_read(&inode->i_writecount) > 1
			    || (last_ino == inode->i_ino && last_dev == inode->i_sb->s_dev)) {
				dprintk("nfsd: write defer %d\n", task_pid_nr(current));
				msleep(10);
				dprintk("nfsd: write resume %d\n", task_pid_nr(current));
			}

			if (inode->i_state & I_DIRTY) {
				dprintk("nfsd: write sync %d\n", task_pid_nr(current));
				host_err=nfsd_sync(file);
			}
#if 0
			wake_up(&inode->i_wait);
#endif
		}
		last_ino = inode->i_ino;
		last_dev = inode->i_sb->s_dev;
	}

	dprintk("nfsd: write complete host_err=%d\n", host_err);
	if (host_err >= 0)
		err = 0;
	else 
		err = nfserrno(host_err);
out:
	return err;
}

/*
 * Read data from a file. count must contain the requested read count
 * on entry. On return, *count contains the number of bytes actually read.
 * N.B. After this call fhp needs an fh_put
 */
__be32
nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
		loff_t offset, struct kvec *vec, int vlen,
		unsigned long *count)
{
	__be32		err;

	if (file) {
		err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
				MAY_READ|MAY_OWNER_OVERRIDE);
		if (err)
			goto out;
		err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
	} else {
		err = nfsd_open(rqstp, fhp, S_IFREG, MAY_READ, &file);
		if (err)
			goto out;
		err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
		nfsd_close(file);
	}
out:
	return err;
}

/*
 * Write data to a file.
 * The stable flag requests synchronous writes.
 * N.B. After this call fhp needs an fh_put
 */
__be32
nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
		loff_t offset, struct kvec *vec, int vlen, unsigned long cnt,
		int *stablep)
{
	__be32			err = 0;

	if (file) {
		err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
				MAY_WRITE|MAY_OWNER_OVERRIDE);
		if (err)
			goto out;
		err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen, cnt,
				stablep);
	} else {
		err = nfsd_open(rqstp, fhp, S_IFREG, MAY_WRITE, &file);
		if (err)
			goto out;

		if (cnt)
			err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen,
					     cnt, stablep);
		nfsd_close(file);
	}
out:
	return err;
}

#ifdef CONFIG_NFSD_V3
/*
 * Commit all pending writes to stable storage.
 * Strictly speaking, we could sync just the indicated file region here,
 * but there's currently no way we can ask the VFS to do so.
 *
 * Unfortunately we cannot lock the file to make sure we return full WCC
 * data to the client, as locking happens lower down in the filesystem.
 */
__be32
nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
               loff_t offset, unsigned long count)
{
	struct file	*file;
	__be32		err;

	if ((u64)count > ~(u64)offset)
		return nfserr_inval;

	if ((err = nfsd_open(rqstp, fhp, S_IFREG, MAY_WRITE, &file)) != 0)
		return err;
	if (EX_ISSYNC(fhp->fh_export)) {
		if (file->f_op && file->f_op->fsync) {
			err = nfserrno(nfsd_sync(file));
		} else {
			err = nfserr_notsupp;
		}
	}

	nfsd_close(file);
	return err;
}
#endif /* CONFIG_NFSD_V3 */

/*
 * Create a file (regular, directory, device, fifo); UNIX sockets 
 * not yet implemented.
 * If the response fh has been verified, the parent directory should
 * already be locked. Note that the parent directory is left locked.
 *
 * N.B. Every call to nfsd_create needs an fh_put for _both_ fhp and resfhp
 */
__be32
nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
		char *fname, int flen, struct iattr *iap,
		int type, dev_t rdev, struct svc_fh *resfhp)
{
	struct dentry	*dentry, *dchild = NULL;
	struct inode	*dirp;
	__be32		err;
	int		host_err;

	err = nfserr_perm;
	if (!flen)
		goto out;
	err = nfserr_exist;
	if (isdotent(fname, flen))
		goto out;

	err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
	if (err)
		goto out;

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

	err = nfserr_notdir;
	if(!dirp->i_op || !dirp->i_op->lookup)
		goto out;
	/*
	 * Check whether the response file handle has been verified yet.
	 * If it has, the parent directory should already be locked.
	 */
	if (!resfhp->fh_dentry) {
		/* called from nfsd_proc_mkdir, or possibly nfsd3_proc_create */
		fh_lock_nested(fhp, I_MUTEX_PARENT);
		dchild = lookup_one_len(fname, dentry, flen);
		host_err = PTR_ERR(dchild);
		if (IS_ERR(dchild))
			goto out_nfserr;
		err = fh_compose(resfhp, fhp->fh_export, dchild, fhp);
		if (err)
			goto out;
	} else {
		/* called from nfsd_proc_create */
		dchild = dget(resfhp->fh_dentry);
		if (!fhp->fh_locked) {
			/* not actually possible */
			printk(KERN_ERR
				"nfsd_create: parent %s/%s not locked!\n",
				dentry->d_parent->d_name.name,
				dentry->d_name.name);
			err = nfserr_io;
			goto out;
		}
	}
	/*
	 * Make sure the child dentry is still negative ...
	 */
	err = nfserr_exist;
	if (dchild->d_inode) {
		dprintk("nfsd_create: dentry %s/%s not negative!\n",
			dentry->d_name.name, dchild->d_name.name);
		goto out; 
	}

	if (!(iap->ia_valid & ATTR_MODE))
		iap->ia_mode = 0;
	iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type;

	/*
	 * Get the dir op function pointer.
	 */
	err = 0;
	switch (type) {
	case S_IFREG:
		host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
		break;
	case S_IFDIR:
		host_err = vfs_mkdir(dirp, dchild, iap->ia_mode);
		break;
	case S_IFCHR:
	case S_IFBLK:
	case S_IFIFO:
	case S_IFSOCK:
		host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev);
		break;
	default:
	        printk("nfsd: bad file type %o in nfsd_create\n", type);
		host_err = -EINVAL;
	}
	if (host_err < 0)
		goto out_nfserr;

	if (EX_ISSYNC(fhp->fh_export)) {
		err = nfserrno(nfsd_sync_dir(dentry));
		write_inode_now(dchild->d_inode, 1);
	}


	/* Set file attributes. Mode has already been set and
	 * setting uid/gid works only for root. Irix appears to
	 * send along the gid when it tries to implement setgid
	 * directories via NFS.
	 */
	if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID|ATTR_MODE)) != 0) {
		__be32 err2 = nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0);
		if (err2)
			err = err2;
	}
	/*
	 * Update the file handle to get the new inode info.
	 */
	if (!err)
		err = fh_update(resfhp);
out:
	if (dchild && !IS_ERR(dchild))
		dput(dchild);
	return err;

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

#ifdef CONFIG_NFSD_V3
/*
 * NFSv3 version of nfsd_create
 */
__be32
nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
		char *fname, int flen, struct iattr *iap,
		struct svc_fh *resfhp, int createmode, u32 *verifier,
	        int *truncp, int *created)
{
	struct dentry	*dentry, *dchild = NULL;
	struct inode	*dirp;
	__be32		err;
	int		host_err;
	__u32		v_mtime=0, v_atime=0;

	err = nfserr_perm;
	if (!flen)
		goto out;
	err = nfserr_exist;
	if (isdotent(fname, flen))
		goto out;
	if (!(iap->ia_valid & ATTR_MODE))
		iap->ia_mode = 0;
	err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
	if (err)
		goto out;

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

	/* Get all the sanity checks out of the way before
	 * we lock the parent. */
	err = nfserr_notdir;
	if(!dirp->i_op || !dirp->i_op->lookup)
		goto out;
	fh_lock_nested(fhp, I_MUTEX_PARENT);

	/*
	 * Compose the response file handle.
	 */
	dchild = lookup_one_len(fname, dentry, flen);
	host_err = PTR_ERR(dchild);
	if (IS_ERR(dchild))
		goto out_nfserr;

	err = fh_compose(resfhp, fhp->fh_export, dchild, fhp);
	if (err)
		goto out;

	if (createmode == NFS3_CREATE_EXCLUSIVE) {
		/* solaris7 gets confused (bugid 4218508) if these have
		 * the high bit set, so just clear the high bits. If this is
		 * ever changed to use different attrs for storing the
		 * verifier, then do_open_lookup() will also need to be fixed
		 * accordingly.
		 */
		v_mtime = verifier[0]&0x7fffffff;
		v_atime = verifier[1]&0x7fffffff;
	}
	
	if (dchild->d_inode) {
		err = 0;

		switch (createmode) {
		case NFS3_CREATE_UNCHECKED:
			if (! S_ISREG(dchild->d_inode->i_mode))
				err = nfserr_exist;
			else if (truncp) {
				/* in nfsv4, we need to treat this case a little
				 * differently.  we don't want to truncate the
				 * file now; this would be wrong if the OPEN
				 * fails for some other reason.  furthermore,
				 * if the size is nonzero, we should ignore it
				 * according to spec!
				 */
				*truncp = (iap->ia_valid & ATTR_SIZE) && !iap->ia_size;
			}
			else {
				iap->ia_valid &= ATTR_SIZE;
				goto set_attr;
			}
			break;
		case NFS3_CREATE_EXCLUSIVE:
			if (   dchild->d_inode->i_mtime.tv_sec == v_mtime
			    && dchild->d_inode->i_atime.tv_sec == v_atime
			    && dchild->d_inode->i_size  == 0 )
				break;
			 /* fallthru */
		case NFS3_CREATE_GUARDED:
			err = nfserr_exist;
		}
		goto out;
	}

	host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
	if (host_err < 0)
		goto out_nfserr;
	if (created)
		*created = 1;

	if (EX_ISSYNC(fhp->fh_export)) {
		err = nfserrno(nfsd_sync_dir(dentry));
		/* setattr will sync the child (or not) */
	}

	if (createmode == NFS3_CREATE_EXCLUSIVE) {
		/* Cram the verifier into atime/mtime */
		iap->ia_valid = ATTR_MTIME|ATTR_ATIME
			| ATTR_MTIME_SET|ATTR_ATIME_SET;
		/* XXX someone who knows this better please fix it for nsec */ 
		iap->ia_mtime.tv_sec = v_mtime;
		iap->ia_atime.tv_sec = v_atime;
		iap->ia_mtime.tv_nsec = 0;
		iap->ia_atime.tv_nsec = 0;
	}

	/* Set file attributes.
	 * Irix appears to send along the gid when it tries to
	 * implement setgid directories via NFS. Clear out all that cruft.
	 */
 set_attr:
	if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID|ATTR_MODE)) != 0) {
 		__be32 err2 = nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0);
		if (err2)
			err = err2;
	}

	/*
	 * Update the filehandle to get the new inode info.
	 */
	if (!err)
		err = fh_update(resfhp);

 out:
	fh_unlock(fhp);
	if (dchild && !IS_ERR(dchild))
		dput(dchild);
 	return err;
 
 out_nfserr:
	err = nfserrno(host_err);
	goto out;
}
#endif /* CONFIG_NFSD_V3 */

/*
 * Read a symlink. On entry, *lenp must contain the maximum path length that
 * fits into the buffer. On return, it contains the true length.
 * N.B. After this call fhp needs an fh_put
 */
__be32
nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp)
{
	struct dentry	*dentry;
	struct inode	*inode;
	mm_segment_t	oldfs;
	__be32		err;
	int		host_err;

	err = fh_verify(rqstp, fhp, S_IFLNK, MAY_NOP);
	if (err)
		goto out;

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

	err = nfserr_inval;
	if (!inode->i_op || !inode->i_op->readlink)
		goto out;

	touch_atime(fhp->fh_export->ex_mnt, dentry);
	/* N.B. Why does this call need a get_fs()??
	 * Remove the set_fs and watch the fireworks:-) --okir
	 */

	oldfs = get_fs(); set_fs(KERNEL_DS);
	host_err = inode->i_op->readlink(dentry, buf, *lenp);
	set_fs(oldfs);

	if (host_err < 0)
		goto out_nfserr;
	*lenp = host_err;
	err = 0;
out:
	return err;

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

/*
 * Create a symlink and look up its inode
 * N.B. After this call _both_ fhp and resfhp need an fh_put
 */
__be32
nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
				char *fname, int flen,
				char *path,  int plen,
				struct svc_fh *resfhp,
				struct iattr *iap)
{
	struct dentry	*dentry, *dnew;
	__be32		err, cerr;
	int		host_err;
	umode_t		mode;

	err = nfserr_noent;
	if (!flen || !plen)
		goto out;
	err = nfserr_exist;
	if (isdotent(fname, flen))
		goto out;

	err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
	if (err)
		goto out;
	fh_lock(fhp);
	dentry = fhp->fh_dentry;
	dnew = lookup_one_len(fname, dentry, flen);
	host_err = PTR_ERR(dnew);
	if (IS_ERR(dnew))
		goto out_nfserr;

	mode = S_IALLUGO;
	/* Only the MODE ATTRibute is even vaguely meaningful */
	if (iap && (iap->ia_valid & ATTR_MODE))
		mode = iap->ia_mode & S_IALLUGO;

	if (unlikely(path[plen] != 0)) {
		char *path_alloced = kmalloc(plen+1, GFP_KERNEL);
		if (path_alloced == NULL)
			host_err = -ENOMEM;
		else {
			strncpy(path_alloced, path, plen);
			path_alloced[plen] = 0;
			host_err = vfs_symlink(dentry->d_inode, dnew, path_alloced, mode);
			kfree(path_alloced);
		}
	} else
		host_err = vfs_symlink(dentry->d_inode, dnew, path, mode);

	if (!host_err) {
		if (EX_ISSYNC(fhp->fh_export))
			host_err = nfsd_sync_dir(dentry);
	}
	err = nfserrno(host_err);
	fh_unlock(fhp);

	cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp);
	dput(dnew);
	if (err==0) err = cerr;
out:
	return err;