rpc_pipe.c 25.4 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108
/*
 * net/sunrpc/rpc_pipe.c
 *
 * Userland/kernel interface for rpcauth_gss.
 * Code shamelessly plagiarized from fs/nfsd/nfsctl.c
 * and fs/sysfs/inode.c
 *
 * Copyright (c) 2002, Trond Myklebust <trond.myklebust@fys.uio.no>
 *
 */
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/pagemap.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/fsnotify.h>
#include <linux/kernel.h>

#include <asm/ioctls.h>
#include <linux/fs.h>
#include <linux/poll.h>
#include <linux/wait.h>
#include <linux/seq_file.h>

#include <linux/sunrpc/clnt.h>
#include <linux/workqueue.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
#include <linux/sunrpc/cache.h>

static struct vfsmount *rpc_mnt __read_mostly;
static int rpc_mount_count;

static struct file_system_type rpc_pipe_fs_type;


static struct kmem_cache *rpc_inode_cachep __read_mostly;

#define RPC_UPCALL_TIMEOUT (30*HZ)

static void rpc_purge_list(struct rpc_inode *rpci, struct list_head *head,
		void (*destroy_msg)(struct rpc_pipe_msg *), int err)
{
	struct rpc_pipe_msg *msg;

	if (list_empty(head))
		return;
	do {
		msg = list_entry(head->next, struct rpc_pipe_msg, list);
		list_del_init(&msg->list);
		msg->errno = err;
		destroy_msg(msg);
	} while (!list_empty(head));
	wake_up(&rpci->waitq);
}

static void
rpc_timeout_upcall_queue(struct work_struct *work)
{
	LIST_HEAD(free_list);
	struct rpc_inode *rpci =
		container_of(work, struct rpc_inode, queue_timeout.work);
	struct inode *inode = &rpci->vfs_inode;
	void (*destroy_msg)(struct rpc_pipe_msg *);

	spin_lock(&inode->i_lock);
	if (rpci->ops == NULL) {
		spin_unlock(&inode->i_lock);
		return;
	}
	destroy_msg = rpci->ops->destroy_msg;
	if (rpci->nreaders == 0) {
		list_splice_init(&rpci->pipe, &free_list);
		rpci->pipelen = 0;
	}
	spin_unlock(&inode->i_lock);
	rpc_purge_list(rpci, &free_list, destroy_msg, -ETIMEDOUT);
}

ssize_t rpc_pipe_generic_upcall(struct file *filp, struct rpc_pipe_msg *msg,
				char __user *dst, size_t buflen)
{
	char *data = (char *)msg->data + msg->copied;
	size_t mlen = min(msg->len - msg->copied, buflen);
	unsigned long left;

	left = copy_to_user(dst, data, mlen);
	if (left == mlen) {
		msg->errno = -EFAULT;
		return -EFAULT;
	}

	mlen -= left;
	msg->copied += mlen;
	msg->errno = 0;
	return mlen;
}
EXPORT_SYMBOL_GPL(rpc_pipe_generic_upcall);

/**
 * rpc_queue_upcall - queue an upcall message to userspace
 * @inode: inode of upcall pipe on which to queue given message
 * @msg: message to queue
 *
 * Call with an @inode created by rpc_mkpipe() to queue an upcall.
 * A userspace process may then later read the upcall by performing a
 * read on an open file for this inode.  It is up to the caller to
 * initialize the fields of @msg (other than @msg->list) appropriately.
 */
int
rpc_queue_upcall(struct inode *inode, struct rpc_pipe_msg *msg)
{
	struct rpc_inode *rpci = RPC_I(inode);
	int res = -EPIPE;

	spin_lock(&inode->i_lock);
	if (rpci->ops == NULL)
		goto out;
	if (rpci->nreaders) {
		list_add_tail(&msg->list, &rpci->pipe);
		rpci->pipelen += msg->len;
		res = 0;
	} else if (rpci->flags & RPC_PIPE_WAIT_FOR_OPEN) {
		if (list_empty(&rpci->pipe))
			queue_delayed_work(rpciod_workqueue,
					&rpci->queue_timeout,
					RPC_UPCALL_TIMEOUT);
		list_add_tail(&msg->list, &rpci->pipe);
		rpci->pipelen += msg->len;
		res = 0;
	}
out:
	spin_unlock(&inode->i_lock);
	wake_up(&rpci->waitq);
	return res;
}
EXPORT_SYMBOL_GPL(rpc_queue_upcall);

static inline void
rpc_inode_setowner(struct inode *inode, void *private)
{
	RPC_I(inode)->private = private;
}

static void
rpc_close_pipes(struct inode *inode)
{
	struct rpc_inode *rpci = RPC_I(inode);
	const struct rpc_pipe_ops *ops;
	int need_release;

	mutex_lock(&inode->i_mutex);
	ops = rpci->ops;
	if (ops != NULL) {
		LIST_HEAD(free_list);
		spin_lock(&inode->i_lock);
		need_release = rpci->nreaders != 0 || rpci->nwriters != 0;
		rpci->nreaders = 0;
		list_splice_init(&rpci->in_upcall, &free_list);
		list_splice_init(&rpci->pipe, &free_list);
		rpci->pipelen = 0;
		rpci->ops = NULL;
		spin_unlock(&inode->i_lock);
		rpc_purge_list(rpci, &free_list, ops->destroy_msg, -EPIPE);
		rpci->nwriters = 0;
		if (need_release && ops->release_pipe)
			ops->release_pipe(inode);
		cancel_delayed_work_sync(&rpci->queue_timeout);
	}
	rpc_inode_setowner(inode, NULL);
	mutex_unlock(&inode->i_mutex);
}

static struct inode *
rpc_alloc_inode(struct super_block *sb)
{
	struct rpc_inode *rpci;
	rpci = (struct rpc_inode *)kmem_cache_alloc(rpc_inode_cachep, GFP_KERNEL);
	if (!rpci)
		return NULL;
	return &rpci->vfs_inode;
}

static void
rpc_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	kmem_cache_free(rpc_inode_cachep, RPC_I(inode));
}

static void
rpc_destroy_inode(struct inode *inode)
{
	call_rcu(&inode->i_rcu, rpc_i_callback);
}

static int
rpc_pipe_open(struct inode *inode, struct file *filp)
{
	struct rpc_inode *rpci = RPC_I(inode);
	int first_open;
	int res = -ENXIO;

	mutex_lock(&inode->i_mutex);
	if (rpci->ops == NULL)
		goto out;
	first_open = rpci->nreaders == 0 && rpci->nwriters == 0;
	if (first_open && rpci->ops->open_pipe) {
		res = rpci->ops->open_pipe(inode);
		if (res)
			goto out;
	}
	if (filp->f_mode & FMODE_READ)
		rpci->nreaders++;
	if (filp->f_mode & FMODE_WRITE)
		rpci->nwriters++;
	res = 0;
out:
	mutex_unlock(&inode->i_mutex);
	return res;
}

static int
rpc_pipe_release(struct inode *inode, struct file *filp)
{
	struct rpc_inode *rpci = RPC_I(inode);
	struct rpc_pipe_msg *msg;
	int last_close;

	mutex_lock(&inode->i_mutex);
	if (rpci->ops == NULL)
		goto out;
	msg = filp->private_data;
	if (msg != NULL) {
		spin_lock(&inode->i_lock);
		msg->errno = -EAGAIN;
		list_del_init(&msg->list);
		spin_unlock(&inode->i_lock);
		rpci->ops->destroy_msg(msg);
	}
	if (filp->f_mode & FMODE_WRITE)
		rpci->nwriters --;
	if (filp->f_mode & FMODE_READ) {
		rpci->nreaders --;
		if (rpci->nreaders == 0) {
			LIST_HEAD(free_list);
			spin_lock(&inode->i_lock);
			list_splice_init(&rpci->pipe, &free_list);
			rpci->pipelen = 0;
			spin_unlock(&inode->i_lock);
			rpc_purge_list(rpci, &free_list,
					rpci->ops->destroy_msg, -EAGAIN);
		}
	}
	last_close = rpci->nwriters == 0 && rpci->nreaders == 0;
	if (last_close && rpci->ops->release_pipe)
		rpci->ops->release_pipe(inode);
out:
	mutex_unlock(&inode->i_mutex);
	return 0;
}

static ssize_t
rpc_pipe_read(struct file *filp, char __user *buf, size_t len, loff_t *offset)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct rpc_inode *rpci = RPC_I(inode);
	struct rpc_pipe_msg *msg;
	int res = 0;

	mutex_lock(&inode->i_mutex);
	if (rpci->ops == NULL) {
		res = -EPIPE;
		goto out_unlock;
	}
	msg = filp->private_data;
	if (msg == NULL) {
		spin_lock(&inode->i_lock);
		if (!list_empty(&rpci->pipe)) {
			msg = list_entry(rpci->pipe.next,
					struct rpc_pipe_msg,
					list);
			list_move(&msg->list, &rpci->in_upcall);
			rpci->pipelen -= msg->len;
			filp->private_data = msg;
			msg->copied = 0;
		}
		spin_unlock(&inode->i_lock);
		if (msg == NULL)
			goto out_unlock;
	}
	/* NOTE: it is up to the callback to update msg->copied */
	res = rpci->ops->upcall(filp, msg, buf, len);
	if (res < 0 || msg->len == msg->copied) {
		filp->private_data = NULL;
		spin_lock(&inode->i_lock);
		list_del_init(&msg->list);
		spin_unlock(&inode->i_lock);
		rpci->ops->destroy_msg(msg);
	}
out_unlock:
	mutex_unlock(&inode->i_mutex);
	return res;
}

static ssize_t
rpc_pipe_write(struct file *filp, const char __user *buf, size_t len, loff_t *offset)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct rpc_inode *rpci = RPC_I(inode);
	int res;

	mutex_lock(&inode->i_mutex);
	res = -EPIPE;
	if (rpci->ops != NULL)
		res = rpci->ops->downcall(filp, buf, len);
	mutex_unlock(&inode->i_mutex);
	return res;
}

static unsigned int
rpc_pipe_poll(struct file *filp, struct poll_table_struct *wait)
{
	struct rpc_inode *rpci;
	unsigned int mask = 0;

	rpci = RPC_I(filp->f_path.dentry->d_inode);
	poll_wait(filp, &rpci->waitq, wait);

	mask = POLLOUT | POLLWRNORM;
	if (rpci->ops == NULL)
		mask |= POLLERR | POLLHUP;
	if (filp->private_data || !list_empty(&rpci->pipe))
		mask |= POLLIN | POLLRDNORM;
	return mask;
}

static long
rpc_pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct rpc_inode *rpci = RPC_I(inode);
	int len;

	switch (cmd) {
	case FIONREAD:
		spin_lock(&inode->i_lock);
		if (rpci->ops == NULL) {
			spin_unlock(&inode->i_lock);
			return -EPIPE;
		}
		len = rpci->pipelen;
		if (filp->private_data) {
			struct rpc_pipe_msg *msg;
			msg = filp->private_data;
			len += msg->len - msg->copied;
		}
		spin_unlock(&inode->i_lock);
		return put_user(len, (int __user *)arg);
	default:
		return -EINVAL;
	}
}

static const struct file_operations rpc_pipe_fops = {
	.owner		= THIS_MODULE,
	.llseek		= no_llseek,
	.read		= rpc_pipe_read,
	.write		= rpc_pipe_write,
	.poll		= rpc_pipe_poll,
	.unlocked_ioctl	= rpc_pipe_ioctl,
	.open		= rpc_pipe_open,
	.release	= rpc_pipe_release,
};

static int
rpc_show_info(struct seq_file *m, void *v)
{
	struct rpc_clnt *clnt = m->private;

	seq_printf(m, "RPC server: %s\n", clnt->cl_server);
	seq_printf(m, "service: %s (%d) version %d\n", clnt->cl_protname,
			clnt->cl_prog, clnt->cl_vers);
	seq_printf(m, "address: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR));
	seq_printf(m, "protocol: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_PROTO));
	seq_printf(m, "port: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_PORT));
	return 0;
}

static int
rpc_info_open(struct inode *inode, struct file *file)
{
	struct rpc_clnt *clnt = NULL;
	int ret = single_open(file, rpc_show_info, NULL);

	if (!ret) {
		struct seq_file *m = file->private_data;

		spin_lock(&file->f_path.dentry->d_lock);
		if (!d_unhashed(file->f_path.dentry))
			clnt = RPC_I(inode)->private;
		if (clnt != NULL && atomic_inc_not_zero(&clnt->cl_count)) {
			spin_unlock(&file->f_path.dentry->d_lock);
			m->private = clnt;
		} else {
			spin_unlock(&file->f_path.dentry->d_lock);
			single_release(inode, file);
			ret = -EINVAL;
		}
	}
	return ret;
}

static int
rpc_info_release(struct inode *inode, struct file *file)
{
	struct seq_file *m = file->private_data;
	struct rpc_clnt *clnt = (struct rpc_clnt *)m->private;

	if (clnt)
		rpc_release_client(clnt);
	return single_release(inode, file);
}

static const struct file_operations rpc_info_operations = {
	.owner		= THIS_MODULE,
	.open		= rpc_info_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= rpc_info_release,
};


/*
 * Description of fs contents.
 */
struct rpc_filelist {
	const char *name;
	const struct file_operations *i_fop;
	umode_t mode;
};

struct vfsmount *rpc_get_mount(void)
{
	int err;

	err = simple_pin_fs(&rpc_pipe_fs_type, &rpc_mnt, &rpc_mount_count);
	if (err != 0)
		return ERR_PTR(err);
	return rpc_mnt;
}
EXPORT_SYMBOL_GPL(rpc_get_mount);

void rpc_put_mount(void)
{
	simple_release_fs(&rpc_mnt, &rpc_mount_count);
}
EXPORT_SYMBOL_GPL(rpc_put_mount);

static int rpc_delete_dentry(const struct dentry *dentry)
{
	return 1;
}

static const struct dentry_operations rpc_dentry_operations = {
	.d_delete = rpc_delete_dentry,
};

static struct inode *
rpc_get_inode(struct super_block *sb, umode_t mode)
{
	struct inode *inode = new_inode(sb);
	if (!inode)
		return NULL;
	inode->i_ino = get_next_ino();
	inode->i_mode = mode;
	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	switch (mode & S_IFMT) {
	case S_IFDIR:
		inode->i_fop = &simple_dir_operations;
		inode->i_op = &simple_dir_inode_operations;
		inc_nlink(inode);
	default:
		break;
	}
	return inode;
}

static int __rpc_create_common(struct inode *dir, struct dentry *dentry,
			       umode_t mode,
			       const struct file_operations *i_fop,
			       void *private)
{
	struct inode *inode;

	d_drop(dentry);
	inode = rpc_get_inode(dir->i_sb, mode);
	if (!inode)
		goto out_err;
	inode->i_ino = iunique(dir->i_sb, 100);
	if (i_fop)
		inode->i_fop = i_fop;
	if (private)
		rpc_inode_setowner(inode, private);
	d_add(dentry, inode);
	return 0;
out_err:
	printk(KERN_WARNING "%s: %s failed to allocate inode for dentry %s\n",
			__FILE__, __func__, dentry->d_name.name);
	dput(dentry);
	return -ENOMEM;
}

static int __rpc_create(struct inode *dir, struct dentry *dentry,
			umode_t mode,
			const struct file_operations *i_fop,
			void *private)
{
	int err;

	err = __rpc_create_common(dir, dentry, S_IFREG | mode, i_fop, private);
	if (err)
		return err;
	fsnotify_create(dir, dentry);
	return 0;
}

static int __rpc_mkdir(struct inode *dir, struct dentry *dentry,
		       umode_t mode,
		       const struct file_operations *i_fop,
		       void *private)
{
	int err;

	err = __rpc_create_common(dir, dentry, S_IFDIR | mode, i_fop, private);
	if (err)
		return err;
	inc_nlink(dir);
	fsnotify_mkdir(dir, dentry);
	return 0;
}

static int __rpc_mkpipe(struct inode *dir, struct dentry *dentry,
			umode_t mode,
			const struct file_operations *i_fop,
			void *private,
			const struct rpc_pipe_ops *ops,
			int flags)
{
	struct rpc_inode *rpci;
	int err;

	err = __rpc_create_common(dir, dentry, S_IFIFO | mode, i_fop, private);
	if (err)
		return err;
	rpci = RPC_I(dentry->d_inode);
	rpci->nkern_readwriters = 1;
	rpci->private = private;
	rpci->flags = flags;
	rpci->ops = ops;
	fsnotify_create(dir, dentry);
	return 0;
}

static int __rpc_rmdir(struct inode *dir, struct dentry *dentry)
{
	int ret;

	dget(dentry);
	ret = simple_rmdir(dir, dentry);
	d_delete(dentry);
	dput(dentry);
	return ret;
}

static int __rpc_unlink(struct inode *dir, struct dentry *dentry)
{
	int ret;

	dget(dentry);
	ret = simple_unlink(dir, dentry);
	d_delete(dentry);
	dput(dentry);
	return ret;
}

static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = dentry->d_inode;
	struct rpc_inode *rpci = RPC_I(inode);

	rpci->nkern_readwriters--;
	if (rpci->nkern_readwriters != 0)
		return 0;
	rpc_close_pipes(inode);
	return __rpc_unlink(dir, dentry);
}

static struct dentry *__rpc_lookup_create(struct dentry *parent,
					  struct qstr *name)
{
	struct dentry *dentry;

	dentry = d_lookup(parent, name);
	if (!dentry) {
		dentry = d_alloc(parent, name);
		if (!dentry) {
			dentry = ERR_PTR(-ENOMEM);
			goto out_err;
		}
	}
	if (!dentry->d_inode)
		d_set_d_op(dentry, &rpc_dentry_operations);
out_err:
	return dentry;
}

static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent,
					  struct qstr *name)
{
	struct dentry *dentry;

	dentry = __rpc_lookup_create(parent, name);
	if (IS_ERR(dentry))
		return dentry;
	if (dentry->d_inode == NULL)
		return dentry;
	dput(dentry);
	return ERR_PTR(-EEXIST);
}

/*
 * FIXME: This probably has races.
 */
static void __rpc_depopulate(struct dentry *parent,
			     const struct rpc_filelist *files,
			     int start, int eof)
{
	struct inode *dir = parent->d_inode;
	struct dentry *dentry;
	struct qstr name;
	int i;

	for (i = start; i < eof; i++) {
		name.name = files[i].name;
		name.len = strlen(files[i].name);
		name.hash = full_name_hash(name.name, name.len);
		dentry = d_lookup(parent, &name);

		if (dentry == NULL)
			continue;
		if (dentry->d_inode == NULL)
			goto next;
		switch (dentry->d_inode->i_mode & S_IFMT) {
			default:
				BUG();
			case S_IFREG:
				__rpc_unlink(dir, dentry);
				break;
			case S_IFDIR:
				__rpc_rmdir(dir, dentry);
		}
next:
		dput(dentry);
	}
}

static void rpc_depopulate(struct dentry *parent,
			   const struct rpc_filelist *files,
			   int start, int eof)
{
	struct inode *dir = parent->d_inode;

	mutex_lock_nested(&dir->i_mutex, I_MUTEX_CHILD);
	__rpc_depopulate(parent, files, start, eof);
	mutex_unlock(&dir->i_mutex);
}

static int rpc_populate(struct dentry *parent,
			const struct rpc_filelist *files,
			int start, int eof,
			void *private)
{
	struct inode *dir = parent->d_inode;
	struct dentry *dentry;
	int i, err;

	mutex_lock(&dir->i_mutex);
	for (i = start; i < eof; i++) {
		struct qstr q;

		q.name = files[i].name;
		q.len = strlen(files[i].name);
		q.hash = full_name_hash(q.name, q.len);
		dentry = __rpc_lookup_create_exclusive(parent, &q);
		err = PTR_ERR(dentry);
		if (IS_ERR(dentry))
			goto out_bad;
		switch (files[i].mode & S_IFMT) {
			default:
				BUG();
			case S_IFREG:
				err = __rpc_create(dir, dentry,
						files[i].mode,
						files[i].i_fop,
						private);
				break;
			case S_IFDIR:
				err = __rpc_mkdir(dir, dentry,
						files[i].mode,
						NULL,
						private);
		}
		if (err != 0)
			goto out_bad;
	}
	mutex_unlock(&dir->i_mutex);
	return 0;
out_bad:
	__rpc_depopulate(parent, files, start, eof);
	mutex_unlock(&dir->i_mutex);
	printk(KERN_WARNING "%s: %s failed to populate directory %s\n",
			__FILE__, __func__, parent->d_name.name);
	return err;
}

static struct dentry *rpc_mkdir_populate(struct dentry *parent,
		struct qstr *name, umode_t mode, void *private,
		int (*populate)(struct dentry *, void *), void *args_populate)
{
	struct dentry *dentry;
	struct inode *dir = parent->d_inode;
	int error;

	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
	dentry = __rpc_lookup_create_exclusive(parent, name);
	if (IS_ERR(dentry))
		goto out;
	error = __rpc_mkdir(dir, dentry, mode, NULL, private);
	if (error != 0)
		goto out_err;
	if (populate != NULL) {
		error = populate(dentry, args_populate);
		if (error)
			goto err_rmdir;
	}
out:
	mutex_unlock(&dir->i_mutex);
	return dentry;
err_rmdir:
	__rpc_rmdir(dir, dentry);
out_err:
	dentry = ERR_PTR(error);
	goto out;
}

static int rpc_rmdir_depopulate(struct dentry *dentry,
		void (*depopulate)(struct dentry *))
{
	struct dentry *parent;
	struct inode *dir;
	int error;

	parent = dget_parent(dentry);
	dir = parent->d_inode;
	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
	if (depopulate != NULL)
		depopulate(dentry);
	error = __rpc_rmdir(dir, dentry);
	mutex_unlock(&dir->i_mutex);
	dput(parent);
	return error;
}

/**
 * rpc_mkpipe - make an rpc_pipefs file for kernel<->userspace communication
 * @parent: dentry of directory to create new "pipe" in
 * @name: name of pipe
 * @private: private data to associate with the pipe, for the caller's use
 * @ops: operations defining the behavior of the pipe: upcall, downcall,
 *	release_pipe, open_pipe, and destroy_msg.
 * @flags: rpc_inode flags
 *
 * Data is made available for userspace to read by calls to
 * rpc_queue_upcall().  The actual reads will result in calls to
 * @ops->upcall, which will be called with the file pointer,
 * message, and userspace buffer to copy to.
 *
 * Writes can come at any time, and do not necessarily have to be
 * responses to upcalls.  They will result in calls to @msg->downcall.
 *
 * The @private argument passed here will be available to all these methods
 * from the file pointer, via RPC_I(file->f_dentry->d_inode)->private.
 */
struct dentry *rpc_mkpipe(struct dentry *parent, const char *name,
			  void *private, const struct rpc_pipe_ops *ops,
			  int flags)
{
	struct dentry *dentry;
	struct inode *dir = parent->d_inode;
	umode_t umode = S_IFIFO | S_IRUSR | S_IWUSR;
	struct qstr q;
	int err;

	if (ops->upcall == NULL)
		umode &= ~S_IRUGO;
	if (ops->downcall == NULL)
		umode &= ~S_IWUGO;

	q.name = name;
	q.len = strlen(name);
	q.hash = full_name_hash(q.name, q.len),

	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
	dentry = __rpc_lookup_create(parent, &q);
	if (IS_ERR(dentry))
		goto out;
	if (dentry->d_inode) {
		struct rpc_inode *rpci = RPC_I(dentry->d_inode);
		if (rpci->private != private ||
				rpci->ops != ops ||
				rpci->flags != flags) {
			dput (dentry);
			err = -EBUSY;
			goto out_err;
		}
		rpci->nkern_readwriters++;
		goto out;
	}

	err = __rpc_mkpipe(dir, dentry, umode, &rpc_pipe_fops,
			   private, ops, flags);
	if (err)
		goto out_err;
out:
	mutex_unlock(&dir->i_mutex);
	return dentry;
out_err:
	dentry = ERR_PTR(err);
	printk(KERN_WARNING "%s: %s() failed to create pipe %s/%s (errno = %d)\n",
			__FILE__, __func__, parent->d_name.name, name,
			err);
	goto out;
}
EXPORT_SYMBOL_GPL(rpc_mkpipe);

/**
 * rpc_unlink - remove a pipe
 * @dentry: dentry for the pipe, as returned from rpc_mkpipe
 *
 * After this call, lookups will no longer find the pipe, and any
 * attempts to read or write using preexisting opens of the pipe will
 * return -EPIPE.
 */
int
rpc_unlink(struct dentry *dentry)
{
	struct dentry *parent;
	struct inode *dir;
	int error = 0;

	parent = dget_parent(dentry);
	dir = parent->d_inode;
	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
	error = __rpc_rmpipe(dir, dentry);
	mutex_unlock(&dir->i_mutex);
	dput(parent);
	return error;
}
EXPORT_SYMBOL_GPL(rpc_unlink);

enum {
	RPCAUTH_info,
	RPCAUTH_EOF
};

static const struct rpc_filelist authfiles[] = {
	[RPCAUTH_info] = {
		.name = "info",
		.i_fop = &rpc_info_operations,
		.mode = S_IFREG | S_IRUSR,
	},
};

static int rpc_clntdir_populate(struct dentry *dentry, void *private)
{
	return rpc_populate(dentry,
			    authfiles, RPCAUTH_info, RPCAUTH_EOF,
			    private);
}

static void rpc_clntdir_depopulate(struct dentry *dentry)
{
	rpc_depopulate(dentry, authfiles, RPCAUTH_info, RPCAUTH_EOF);
}

/**
 * rpc_create_client_dir - Create a new rpc_client directory in rpc_pipefs
 * @dentry: dentry from the rpc_pipefs root to the new directory
 * @name: &struct qstr for the name
 * @rpc_client: rpc client to associate with this directory
 *
 * This creates a directory at the given @path associated with
 * @rpc_clnt, which will contain a file named "info" with some basic
 * information about the client, together with any "pipes" that may
 * later be created using rpc_mkpipe().
 */
struct dentry *rpc_create_client_dir(struct dentry *dentry,
				   struct qstr *name,
				   struct rpc_clnt *rpc_client)
{
	return rpc_mkdir_populate(dentry, name, S_IRUGO | S_IXUGO, NULL,
			rpc_clntdir_populate, rpc_client);
}

/**
 * rpc_remove_client_dir - Remove a directory created with rpc_create_client_dir()
 * @dentry: directory to remove
 */
int rpc_remove_client_dir(struct dentry *dentry)
{
	return rpc_rmdir_depopulate(dentry, rpc_clntdir_depopulate);
}

static const struct rpc_filelist cache_pipefs_files[3] = {
	[0] = {
		.name = "channel",
		.i_fop = &cache_file_operations_pipefs,
		.mode = S_IFREG|S_IRUSR|S_IWUSR,
	},
	[1] = {
		.name = "content",
		.i_fop = &content_file_operations_pipefs,
		.mode = S_IFREG|S_IRUSR,
	},
	[2] = {
		.name = "flush",
		.i_fop = &cache_flush_operations_pipefs,
		.mode = S_IFREG|S_IRUSR|S_IWUSR,
	},
};

static int rpc_cachedir_populate(struct dentry *dentry, void *private)
{
	return rpc_populate(dentry,
			    cache_pipefs_files, 0, 3,
			    private);
}

static void rpc_cachedir_depopulate(struct dentry *dentry)
{
	rpc_depopulate(dentry, cache_pipefs_files, 0, 3);
}

struct dentry *rpc_create_cache_dir(struct dentry *parent, struct qstr *name,
				    umode_t umode, struct cache_detail *cd)
{
	return rpc_mkdir_populate(parent, name, umode, NULL,
			rpc_cachedir_populate, cd);
}

void rpc_remove_cache_dir(struct dentry *dentry)
{
	rpc_rmdir_depopulate(dentry, rpc_cachedir_depopulate);
}

/*
 * populate the filesystem
 */
static const struct super_operations s_ops = {
	.alloc_inode	= rpc_alloc_inode,
	.destroy_inode	= rpc_destroy_inode,
	.statfs		= simple_statfs,
};

#define RPCAUTH_GSSMAGIC 0x67596969

/*
 * We have a single directory with 1 node in it.
 */
enum {
	RPCAUTH_lockd,
	RPCAUTH_mount,
	RPCAUTH_nfs,
	RPCAUTH_portmap,
	RPCAUTH_statd,
	RPCAUTH_nfsd4_cb,
	RPCAUTH_cache,
	RPCAUTH_RootEOF
};

static const struct rpc_filelist files[] = {
	[RPCAUTH_lockd] = {
		.name = "lockd",
		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
	},
	[RPCAUTH_mount] = {
		.name = "mount",
		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
	},
	[RPCAUTH_nfs] = {
		.name = "nfs",
		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
	},
	[RPCAUTH_portmap] = {
		.name = "portmap",
		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
	},
	[RPCAUTH_statd] = {
		.name = "statd",
		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
	},
	[RPCAUTH_nfsd4_cb] = {
		.name = "nfsd4_cb",
		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
	},
	[RPCAUTH_cache] = {
		.name = "cache",
		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
	},
};

static int
rpc_fill_super(struct super_block *sb, void *data, int silent)
{
	struct inode *inode;
	struct dentry *root;

	sb->s_blocksize = PAGE_CACHE_SIZE;
	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
	sb->s_magic = RPCAUTH_GSSMAGIC;
	sb->s_op = &s_ops;
	sb->s_time_gran = 1;

	inode = rpc_get_inode(sb, S_IFDIR | 0755);
	if (!inode)
		return -ENOMEM;
	sb->s_root = root = d_alloc_root(inode);
	if (!root) {
		iput(inode);
		return -ENOMEM;
	}
	if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL))
		return -ENOMEM;
	return 0;
}

static struct dentry *
rpc_mount(struct file_system_type *fs_type,
		int flags, const char *dev_name, void *data)
{
	return mount_single(fs_type, flags, data, rpc_fill_super);
}

static struct file_system_type rpc_pipe_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "rpc_pipefs",
	.mount		= rpc_mount,
	.kill_sb	= kill_litter_super,
};

static void
init_once(void *foo)
{
	struct rpc_inode *rpci = (struct rpc_inode *) foo;

	inode_init_once(&rpci->vfs_inode);
	rpci->private = NULL;
	rpci->nreaders = 0;
	rpci->nwriters = 0;
	INIT_LIST_HEAD(&rpci->in_upcall);
	INIT_LIST_HEAD(&rpci->in_downcall);
	INIT_LIST_HEAD(&rpci->pipe);
	rpci->pipelen = 0;
	init_waitqueue_head(&rpci->waitq);
	INIT_DELAYED_WORK(&rpci->queue_timeout,
			    rpc_timeout_upcall_queue);
	rpci->ops = NULL;
}

int register_rpc_pipefs(void)
{
	int err;

	rpc_inode_cachep = kmem_cache_create("rpc_inode_cache",
				sizeof(struct rpc_inode),
				0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
						SLAB_MEM_SPREAD),
				init_once);
	if (!rpc_inode_cachep)
		return -ENOMEM;
	err = register_filesystem(&rpc_pipe_fs_type);
	if (err) {
		kmem_cache_destroy(rpc_inode_cachep);
		return err;
	}

	return 0;
}

void unregister_rpc_pipefs(void)
{
	kmem_cache_destroy(rpc_inode_cachep);
	unregister_filesystem(&rpc_pipe_fs_type);
}

/* Make 'mount -t rpc_pipefs ...' autoload this module. */
MODULE_ALIAS("rpc_pipefs");