namei.c 24.6 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
/* CacheFiles path walking and related routines
 *
 * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public Licence
 * as published by the Free Software Foundation; either version
 * 2 of the Licence, or (at your option) any later version.
 */

#include <linux/module.h>
#include <linux/sched.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/fsnotify.h>
#include <linux/quotaops.h>
#include <linux/xattr.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/slab.h>
#include "internal.h"

#define CACHEFILES_KEYBUF_SIZE 512

/*
 * dump debugging info about an object
 */
static noinline
void __cachefiles_printk_object(struct cachefiles_object *object,
				const char *prefix,
				u8 *keybuf)
{
	struct fscache_cookie *cookie;
	unsigned keylen, loop;

	printk(KERN_ERR "%sobject: OBJ%x\n",
	       prefix, object->fscache.debug_id);
	printk(KERN_ERR "%sobjstate=%s fl=%lx wbusy=%x ev=%lx[%lx]\n",
	       prefix, object->fscache.state->name,
	       object->fscache.flags, work_busy(&object->fscache.work),
	       object->fscache.events, object->fscache.event_mask);
	printk(KERN_ERR "%sops=%u inp=%u exc=%u\n",
	       prefix, object->fscache.n_ops, object->fscache.n_in_progress,
	       object->fscache.n_exclusive);
	printk(KERN_ERR "%sparent=%p\n",
	       prefix, object->fscache.parent);

	spin_lock(&object->fscache.lock);
	cookie = object->fscache.cookie;
	if (cookie) {
		printk(KERN_ERR "%scookie=%p [pr=%p nd=%p fl=%lx]\n",
		       prefix,
		       object->fscache.cookie,
		       object->fscache.cookie->parent,
		       object->fscache.cookie->netfs_data,
		       object->fscache.cookie->flags);
		if (keybuf && cookie->def)
			keylen = cookie->def->get_key(cookie->netfs_data, keybuf,
						      CACHEFILES_KEYBUF_SIZE);
		else
			keylen = 0;
	} else {
		printk(KERN_ERR "%scookie=NULL\n", prefix);
		keylen = 0;
	}
	spin_unlock(&object->fscache.lock);

	if (keylen) {
		printk(KERN_ERR "%skey=[%u] '", prefix, keylen);
		for (loop = 0; loop < keylen; loop++)
			printk("%02x", keybuf[loop]);
		printk("'\n");
	}
}

/*
 * dump debugging info about a pair of objects
 */
static noinline void cachefiles_printk_object(struct cachefiles_object *object,
					      struct cachefiles_object *xobject)
{
	u8 *keybuf;

	keybuf = kmalloc(CACHEFILES_KEYBUF_SIZE, GFP_NOIO);
	if (object)
		__cachefiles_printk_object(object, "", keybuf);
	if (xobject)
		__cachefiles_printk_object(xobject, "x", keybuf);
	kfree(keybuf);
}

/*
 * mark the owner of a dentry, if there is one, to indicate that that dentry
 * has been preemptively deleted
 * - the caller must hold the i_mutex on the dentry's parent as required to
 *   call vfs_unlink(), vfs_rmdir() or vfs_rename()
 */
static void cachefiles_mark_object_buried(struct cachefiles_cache *cache,
					  struct dentry *dentry)
{
	struct cachefiles_object *object;
	struct rb_node *p;

	_enter(",'%*.*s'",
	       dentry->d_name.len, dentry->d_name.len, dentry->d_name.name);

	write_lock(&cache->active_lock);

	p = cache->active_nodes.rb_node;
	while (p) {
		object = rb_entry(p, struct cachefiles_object, active_node);
		if (object->dentry > dentry)
			p = p->rb_left;
		else if (object->dentry < dentry)
			p = p->rb_right;
		else
			goto found_dentry;
	}

	write_unlock(&cache->active_lock);
	_leave(" [no owner]");
	return;

	/* found the dentry for  */
found_dentry:
	kdebug("preemptive burial: OBJ%x [%s] %p",
	       object->fscache.debug_id,
	       object->fscache.state->name,
	       dentry);

	if (fscache_object_is_live(&object->fscache)) {
		printk(KERN_ERR "\n");
		printk(KERN_ERR "CacheFiles: Error:"
		       " Can't preemptively bury live object\n");
		cachefiles_printk_object(object, NULL);
	} else if (test_and_set_bit(CACHEFILES_OBJECT_BURIED, &object->flags)) {
		printk(KERN_ERR "CacheFiles: Error:"
		       " Object already preemptively buried\n");
	}

	write_unlock(&cache->active_lock);
	_leave(" [owner marked]");
}

/*
 * record the fact that an object is now active
 */
static int cachefiles_mark_object_active(struct cachefiles_cache *cache,
					 struct cachefiles_object *object)
{
	struct cachefiles_object *xobject;
	struct rb_node **_p, *_parent = NULL;
	struct dentry *dentry;

	_enter(",%p", object);

try_again:
	write_lock(&cache->active_lock);

	if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) {
		printk(KERN_ERR "CacheFiles: Error: Object already active\n");
		cachefiles_printk_object(object, NULL);
		BUG();
	}

	dentry = object->dentry;
	_p = &cache->active_nodes.rb_node;
	while (*_p) {
		_parent = *_p;
		xobject = rb_entry(_parent,
				   struct cachefiles_object, active_node);

		ASSERT(xobject != object);

		if (xobject->dentry > dentry)
			_p = &(*_p)->rb_left;
		else if (xobject->dentry < dentry)
			_p = &(*_p)->rb_right;
		else
			goto wait_for_old_object;
	}

	rb_link_node(&object->active_node, _parent, _p);
	rb_insert_color(&object->active_node, &cache->active_nodes);

	write_unlock(&cache->active_lock);
	_leave(" = 0");
	return 0;

	/* an old object from a previous incarnation is hogging the slot - we
	 * need to wait for it to be destroyed */
wait_for_old_object:
	if (fscache_object_is_live(&object->fscache)) {
		printk(KERN_ERR "\n");
		printk(KERN_ERR "CacheFiles: Error:"
		       " Unexpected object collision\n");
		cachefiles_printk_object(object, xobject);
		BUG();
	}
	atomic_inc(&xobject->usage);
	write_unlock(&cache->active_lock);

	if (test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) {
		wait_queue_head_t *wq;

		signed long timeout = 60 * HZ;
		wait_queue_t wait;
		bool requeue;

		/* if the object we're waiting for is queued for processing,
		 * then just put ourselves on the queue behind it */
		if (work_pending(&xobject->fscache.work)) {
			_debug("queue OBJ%x behind OBJ%x immediately",
			       object->fscache.debug_id,
			       xobject->fscache.debug_id);
			goto requeue;
		}

		/* otherwise we sleep until either the object we're waiting for
		 * is done, or the fscache_object is congested */
		wq = bit_waitqueue(&xobject->flags, CACHEFILES_OBJECT_ACTIVE);
		init_wait(&wait);
		requeue = false;
		do {
			prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
			if (!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags))
				break;

			requeue = fscache_object_sleep_till_congested(&timeout);
		} while (timeout > 0 && !requeue);
		finish_wait(wq, &wait);

		if (requeue &&
		    test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) {
			_debug("queue OBJ%x behind OBJ%x after wait",
			       object->fscache.debug_id,
			       xobject->fscache.debug_id);
			goto requeue;
		}

		if (timeout <= 0) {
			printk(KERN_ERR "\n");
			printk(KERN_ERR "CacheFiles: Error: Overlong"
			       " wait for old active object to go away\n");
			cachefiles_printk_object(object, xobject);
			goto requeue;
		}
	}

	ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags));

	cache->cache.ops->put_object(&xobject->fscache);
	goto try_again;

requeue:
	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
	cache->cache.ops->put_object(&xobject->fscache);
	_leave(" = -ETIMEDOUT");
	return -ETIMEDOUT;
}

/*
 * delete an object representation from the cache
 * - file backed objects are unlinked
 * - directory backed objects are stuffed into the graveyard for userspace to
 *   delete
 * - unlocks the directory mutex
 */
static int cachefiles_bury_object(struct cachefiles_cache *cache,
				  struct dentry *dir,
				  struct dentry *rep,
				  bool preemptive)
{
	struct dentry *grave, *trap;
	struct path path, path_to_graveyard;
	char nbuffer[8 + 8 + 1];
	int ret;

	_enter(",'%*.*s','%*.*s'",
	       dir->d_name.len, dir->d_name.len, dir->d_name.name,
	       rep->d_name.len, rep->d_name.len, rep->d_name.name);

	_debug("remove %p from %p", rep, dir);

	/* non-directories can just be unlinked */
	if (!S_ISDIR(rep->d_inode->i_mode)) {
		_debug("unlink stale object");

		path.mnt = cache->mnt;
		path.dentry = dir;
		ret = security_path_unlink(&path, rep);
		if (ret < 0) {
			cachefiles_io_error(cache, "Unlink security error");
		} else {
			ret = vfs_unlink(dir->d_inode, rep, NULL);

			if (preemptive)
				cachefiles_mark_object_buried(cache, rep);
		}

		mutex_unlock(&dir->d_inode->i_mutex);

		if (ret == -EIO)
			cachefiles_io_error(cache, "Unlink failed");

		_leave(" = %d", ret);
		return ret;
	}

	/* directories have to be moved to the graveyard */
	_debug("move stale object to graveyard");
	mutex_unlock(&dir->d_inode->i_mutex);

try_again:
	/* first step is to make up a grave dentry in the graveyard */
	sprintf(nbuffer, "%08x%08x",
		(uint32_t) get_seconds(),
		(uint32_t) atomic_inc_return(&cache->gravecounter));

	/* do the multiway lock magic */
	trap = lock_rename(cache->graveyard, dir);

	/* do some checks before getting the grave dentry */
	if (rep->d_parent != dir) {
		/* the entry was probably culled when we dropped the parent dir
		 * lock */
		unlock_rename(cache->graveyard, dir);
		_leave(" = 0 [culled?]");
		return 0;
	}

	if (!S_ISDIR(cache->graveyard->d_inode->i_mode)) {
		unlock_rename(cache->graveyard, dir);
		cachefiles_io_error(cache, "Graveyard no longer a directory");
		return -EIO;
	}

	if (trap == rep) {
		unlock_rename(cache->graveyard, dir);
		cachefiles_io_error(cache, "May not make directory loop");
		return -EIO;
	}

	if (d_mountpoint(rep)) {
		unlock_rename(cache->graveyard, dir);
		cachefiles_io_error(cache, "Mountpoint in cache");
		return -EIO;
	}

	grave = lookup_one_len(nbuffer, cache->graveyard, strlen(nbuffer));
	if (IS_ERR(grave)) {
		unlock_rename(cache->graveyard, dir);

		if (PTR_ERR(grave) == -ENOMEM) {
			_leave(" = -ENOMEM");
			return -ENOMEM;
		}

		cachefiles_io_error(cache, "Lookup error %ld",
				    PTR_ERR(grave));
		return -EIO;
	}

	if (grave->d_inode) {
		unlock_rename(cache->graveyard, dir);
		dput(grave);
		grave = NULL;
		cond_resched();
		goto try_again;
	}

	if (d_mountpoint(grave)) {
		unlock_rename(cache->graveyard, dir);
		dput(grave);
		cachefiles_io_error(cache, "Mountpoint in graveyard");
		return -EIO;
	}

	/* target should not be an ancestor of source */
	if (trap == grave) {
		unlock_rename(cache->graveyard, dir);
		dput(grave);
		cachefiles_io_error(cache, "May not make directory loop");
		return -EIO;
	}

	/* attempt the rename */
	path.mnt = cache->mnt;
	path.dentry = dir;
	path_to_graveyard.mnt = cache->mnt;
	path_to_graveyard.dentry = cache->graveyard;
	ret = security_path_rename(&path, rep, &path_to_graveyard, grave);
	if (ret < 0) {
		cachefiles_io_error(cache, "Rename security error %d", ret);
	} else {
		ret = vfs_rename(dir->d_inode, rep,
				 cache->graveyard->d_inode, grave, NULL);
		if (ret != 0 && ret != -ENOMEM)
			cachefiles_io_error(cache,
					    "Rename failed with error %d", ret);

		if (preemptive)
			cachefiles_mark_object_buried(cache, rep);
	}

	unlock_rename(cache->graveyard, dir);
	dput(grave);
	_leave(" = 0");
	return 0;
}

/*
 * delete an object representation from the cache
 */
int cachefiles_delete_object(struct cachefiles_cache *cache,
			     struct cachefiles_object *object)
{
	struct dentry *dir;
	int ret;

	_enter(",OBJ%x{%p}", object->fscache.debug_id, object->dentry);

	ASSERT(object->dentry);
	ASSERT(object->dentry->d_inode);
	ASSERT(object->dentry->d_parent);

	dir = dget_parent(object->dentry);

	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);

	if (test_bit(CACHEFILES_OBJECT_BURIED, &object->flags)) {
		/* object allocation for the same key preemptively deleted this
		 * object's file so that it could create its own file */
		_debug("object preemptively buried");
		mutex_unlock(&dir->d_inode->i_mutex);
		ret = 0;
	} else {
		/* we need to check that our parent is _still_ our parent - it
		 * may have been renamed */
		if (dir == object->dentry->d_parent) {
			ret = cachefiles_bury_object(cache, dir,
						     object->dentry, false);
		} else {
			/* it got moved, presumably by cachefilesd culling it,
			 * so it's no longer in the key path and we can ignore
			 * it */
			mutex_unlock(&dir->d_inode->i_mutex);
			ret = 0;
		}
	}

	dput(dir);
	_leave(" = %d", ret);
	return ret;
}

/*
 * walk from the parent object to the child object through the backing
 * filesystem, creating directories as we go
 */
int cachefiles_walk_to_object(struct cachefiles_object *parent,
			      struct cachefiles_object *object,
			      const char *key,
			      struct cachefiles_xattr *auxdata)
{
	struct cachefiles_cache *cache;
	struct dentry *dir, *next = NULL;
	struct path path;
	unsigned long start;
	const char *name;
	int ret, nlen;

	_enter("OBJ%x{%p},OBJ%x,%s,",
	       parent->fscache.debug_id, parent->dentry,
	       object->fscache.debug_id, key);

	cache = container_of(parent->fscache.cache,
			     struct cachefiles_cache, cache);
	path.mnt = cache->mnt;

	ASSERT(parent->dentry);
	ASSERT(parent->dentry->d_inode);

	if (!(S_ISDIR(parent->dentry->d_inode->i_mode))) {
		// TODO: convert file to dir
		_leave("looking up in none directory");
		return -ENOBUFS;
	}

	dir = dget(parent->dentry);

advance:
	/* attempt to transit the first directory component */
	name = key;
	nlen = strlen(key);

	/* key ends in a double NUL */
	key = key + nlen + 1;
	if (!*key)
		key = NULL;

lookup_again:
	/* search the current directory for the element name */
	_debug("lookup '%s'", name);

	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);

	start = jiffies;
	next = lookup_one_len(name, dir, nlen);
	cachefiles_hist(cachefiles_lookup_histogram, start);
	if (IS_ERR(next))
		goto lookup_error;

	_debug("next -> %p %s", next, next->d_inode ? "positive" : "negative");

	if (!key)
		object->new = !next->d_inode;

	/* if this element of the path doesn't exist, then the lookup phase
	 * failed, and we can release any readers in the certain knowledge that
	 * there's nothing for them to actually read */
	if (!next->d_inode)
		fscache_object_lookup_negative(&object->fscache);

	/* we need to create the object if it's negative */
	if (key || object->type == FSCACHE_COOKIE_TYPE_INDEX) {
		/* index objects and intervening tree levels must be subdirs */
		if (!next->d_inode) {
			ret = cachefiles_has_space(cache, 1, 0);
			if (ret < 0)
				goto create_error;

			path.dentry = dir;
			ret = security_path_mkdir(&path, next, 0);
			if (ret < 0)
				goto create_error;
			start = jiffies;
			ret = vfs_mkdir(dir->d_inode, next, 0);
			cachefiles_hist(cachefiles_mkdir_histogram, start);
			if (ret < 0)
				goto create_error;

			ASSERT(next->d_inode);

			_debug("mkdir -> %p{%p{ino=%lu}}",
			       next, next->d_inode, next->d_inode->i_ino);

		} else if (!S_ISDIR(next->d_inode->i_mode)) {
			kerror("inode %lu is not a directory",
			       next->d_inode->i_ino);
			ret = -ENOBUFS;
			goto error;
		}

	} else {
		/* non-index objects start out life as files */
		if (!next->d_inode) {
			ret = cachefiles_has_space(cache, 1, 0);
			if (ret < 0)
				goto create_error;

			path.dentry = dir;
			ret = security_path_mknod(&path, next, S_IFREG, 0);
			if (ret < 0)
				goto create_error;
			start = jiffies;
			ret = vfs_create(dir->d_inode, next, S_IFREG, true);
			cachefiles_hist(cachefiles_create_histogram, start);
			if (ret < 0)
				goto create_error;

			ASSERT(next->d_inode);

			_debug("create -> %p{%p{ino=%lu}}",
			       next, next->d_inode, next->d_inode->i_ino);

		} else if (!S_ISDIR(next->d_inode->i_mode) &&
			   !S_ISREG(next->d_inode->i_mode)
			   ) {
			kerror("inode %lu is not a file or directory",
			       next->d_inode->i_ino);
			ret = -ENOBUFS;
			goto error;
		}
	}

	/* process the next component */
	if (key) {
		_debug("advance");
		mutex_unlock(&dir->d_inode->i_mutex);
		dput(dir);
		dir = next;
		next = NULL;
		goto advance;
	}

	/* we've found the object we were looking for */
	object->dentry = next;

	/* if we've found that the terminal object exists, then we need to
	 * check its attributes and delete it if it's out of date */
	if (!object->new) {
		_debug("validate '%*.*s'",
		       next->d_name.len, next->d_name.len, next->d_name.name);

		ret = cachefiles_check_object_xattr(object, auxdata);
		if (ret == -ESTALE) {
			/* delete the object (the deleter drops the directory
			 * mutex) */
			object->dentry = NULL;

			ret = cachefiles_bury_object(cache, dir, next, true);
			dput(next);
			next = NULL;

			if (ret < 0)
				goto delete_error;

			_debug("redo lookup");
			goto lookup_again;
		}
	}

	/* note that we're now using this object */
	ret = cachefiles_mark_object_active(cache, object);

	mutex_unlock(&dir->d_inode->i_mutex);
	dput(dir);
	dir = NULL;

	if (ret == -ETIMEDOUT)
		goto mark_active_timed_out;

	_debug("=== OBTAINED_OBJECT ===");

	if (object->new) {
		/* attach data to a newly constructed terminal object */
		ret = cachefiles_set_object_xattr(object, auxdata);
		if (ret < 0)
			goto check_error;
	} else {
		/* always update the atime on an object we've just looked up
		 * (this is used to keep track of culling, and atimes are only
		 * updated by read, write and readdir but not lookup or
		 * open) */
		path.dentry = next;
		touch_atime(&path);
	}

	/* open a file interface onto a data file */
	if (object->type != FSCACHE_COOKIE_TYPE_INDEX) {
		if (S_ISREG(object->dentry->d_inode->i_mode)) {
			const struct address_space_operations *aops;

			ret = -EPERM;
			aops = object->dentry->d_inode->i_mapping->a_ops;
			if (!aops->bmap)
				goto check_error;

			object->backer = object->dentry;
		} else {
			BUG(); // TODO: open file in data-class subdir
		}
	}

	object->new = 0;
	fscache_obtained_object(&object->fscache);

	_leave(" = 0 [%lu]", object->dentry->d_inode->i_ino);
	return 0;

create_error:
	_debug("create error %d", ret);
	if (ret == -EIO)
		cachefiles_io_error(cache, "Create/mkdir failed");
	goto error;

mark_active_timed_out:
	_debug("mark active timed out");
	goto release_dentry;

check_error:
	_debug("check error %d", ret);
	write_lock(&cache->active_lock);
	rb_erase(&object->active_node, &cache->active_nodes);
	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
	wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
	write_unlock(&cache->active_lock);
release_dentry:
	dput(object->dentry);
	object->dentry = NULL;
	goto error_out;

delete_error:
	_debug("delete error %d", ret);
	goto error_out2;

lookup_error:
	_debug("lookup error %ld", PTR_ERR(next));
	ret = PTR_ERR(next);
	if (ret == -EIO)
		cachefiles_io_error(cache, "Lookup failed");
	next = NULL;
error:
	mutex_unlock(&dir->d_inode->i_mutex);
	dput(next);
error_out2:
	dput(dir);
error_out:
	_leave(" = error %d", -ret);
	return ret;
}

/*
 * get a subdirectory
 */
struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
					struct dentry *dir,
					const char *dirname)
{
	struct dentry *subdir;
	unsigned long start;
	struct path path;
	int ret;

	_enter(",,%s", dirname);

	/* search the current directory for the element name */
	mutex_lock(&dir->d_inode->i_mutex);

	start = jiffies;
	subdir = lookup_one_len(dirname, dir, strlen(dirname));
	cachefiles_hist(cachefiles_lookup_histogram, start);
	if (IS_ERR(subdir)) {
		if (PTR_ERR(subdir) == -ENOMEM)
			goto nomem_d_alloc;
		goto lookup_error;
	}

	_debug("subdir -> %p %s",
	       subdir, subdir->d_inode ? "positive" : "negative");

	/* we need to create the subdir if it doesn't exist yet */
	if (!subdir->d_inode) {
		ret = cachefiles_has_space(cache, 1, 0);
		if (ret < 0)
			goto mkdir_error;

		_debug("attempt mkdir");

		path.mnt = cache->mnt;
		path.dentry = dir;
		ret = security_path_mkdir(&path, subdir, 0700);
		if (ret < 0)
			goto mkdir_error;
		ret = vfs_mkdir(dir->d_inode, subdir, 0700);
		if (ret < 0)
			goto mkdir_error;

		ASSERT(subdir->d_inode);

		_debug("mkdir -> %p{%p{ino=%lu}}",
		       subdir,
		       subdir->d_inode,
		       subdir->d_inode->i_ino);
	}

	mutex_unlock(&dir->d_inode->i_mutex);

	/* we need to make sure the subdir is a directory */
	ASSERT(subdir->d_inode);

	if (!S_ISDIR(subdir->d_inode->i_mode)) {
		kerror("%s is not a directory", dirname);
		ret = -EIO;
		goto check_error;
	}

	ret = -EPERM;
	if (!subdir->d_inode->i_op ||
	    !subdir->d_inode->i_op->setxattr ||
	    !subdir->d_inode->i_op->getxattr ||
	    !subdir->d_inode->i_op->lookup ||
	    !subdir->d_inode->i_op->mkdir ||
	    !subdir->d_inode->i_op->create ||
	    !subdir->d_inode->i_op->rename ||
	    !subdir->d_inode->i_op->rmdir ||
	    !subdir->d_inode->i_op->unlink)
		goto check_error;

	_leave(" = [%lu]", subdir->d_inode->i_ino);
	return subdir;

check_error:
	dput(subdir);
	_leave(" = %d [check]", ret);
	return ERR_PTR(ret);

mkdir_error:
	mutex_unlock(&dir->d_inode->i_mutex);
	dput(subdir);
	kerror("mkdir %s failed with error %d", dirname, ret);
	return ERR_PTR(ret);

lookup_error:
	mutex_unlock(&dir->d_inode->i_mutex);
	ret = PTR_ERR(subdir);
	kerror("Lookup %s failed with error %d", dirname, ret);
	return ERR_PTR(ret);

nomem_d_alloc:
	mutex_unlock(&dir->d_inode->i_mutex);
	_leave(" = -ENOMEM");
	return ERR_PTR(-ENOMEM);
}

/*
 * find out if an object is in use or not
 * - if finds object and it's not in use:
 *   - returns a pointer to the object and a reference on it
 *   - returns with the directory locked
 */
static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache,
					      struct dentry *dir,
					      char *filename)
{
	struct cachefiles_object *object;
	struct rb_node *_n;
	struct dentry *victim;
	unsigned long start;
	int ret;

	//_enter(",%*.*s/,%s",
	//       dir->d_name.len, dir->d_name.len, dir->d_name.name, filename);

	/* look up the victim */
	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);

	start = jiffies;
	victim = lookup_one_len(filename, dir, strlen(filename));
	cachefiles_hist(cachefiles_lookup_histogram, start);
	if (IS_ERR(victim))
		goto lookup_error;

	//_debug("victim -> %p %s",
	//       victim, victim->d_inode ? "positive" : "negative");

	/* if the object is no longer there then we probably retired the object
	 * at the netfs's request whilst the cull was in progress
	 */
	if (!victim->d_inode) {
		mutex_unlock(&dir->d_inode->i_mutex);
		dput(victim);
		_leave(" = -ENOENT [absent]");
		return ERR_PTR(-ENOENT);
	}

	/* check to see if we're using this object */
	read_lock(&cache->active_lock);

	_n = cache->active_nodes.rb_node;

	while (_n) {
		object = rb_entry(_n, struct cachefiles_object, active_node);

		if (object->dentry > victim)
			_n = _n->rb_left;
		else if (object->dentry < victim)
			_n = _n->rb_right;
		else
			goto object_in_use;
	}

	read_unlock(&cache->active_lock);

	//_leave(" = %p", victim);
	return victim;

object_in_use:
	read_unlock(&cache->active_lock);
	mutex_unlock(&dir->d_inode->i_mutex);
	dput(victim);
	//_leave(" = -EBUSY [in use]");
	return ERR_PTR(-EBUSY);

lookup_error:
	mutex_unlock(&dir->d_inode->i_mutex);
	ret = PTR_ERR(victim);
	if (ret == -ENOENT) {
		/* file or dir now absent - probably retired by netfs */
		_leave(" = -ESTALE [absent]");
		return ERR_PTR(-ESTALE);
	}

	if (ret == -EIO) {
		cachefiles_io_error(cache, "Lookup failed");
	} else if (ret != -ENOMEM) {
		kerror("Internal error: %d", ret);
		ret = -EIO;
	}

	_leave(" = %d", ret);
	return ERR_PTR(ret);
}

/*
 * cull an object if it's not in use
 * - called only by cache manager daemon
 */
int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir,
		    char *filename)
{
	struct dentry *victim;
	int ret;

	_enter(",%*.*s/,%s",
	       dir->d_name.len, dir->d_name.len, dir->d_name.name, filename);

	victim = cachefiles_check_active(cache, dir, filename);
	if (IS_ERR(victim))
		return PTR_ERR(victim);

	_debug("victim -> %p %s",
	       victim, victim->d_inode ? "positive" : "negative");

	/* okay... the victim is not being used so we can cull it
	 * - start by marking it as stale
	 */
	_debug("victim is cullable");

	ret = cachefiles_remove_object_xattr(cache, victim);
	if (ret < 0)
		goto error_unlock;

	/*  actually remove the victim (drops the dir mutex) */
	_debug("bury");

	ret = cachefiles_bury_object(cache, dir, victim, false);
	if (ret < 0)
		goto error;

	dput(victim);
	_leave(" = 0");
	return 0;

error_unlock:
	mutex_unlock(&dir->d_inode->i_mutex);
error:
	dput(victim);
	if (ret == -ENOENT) {
		/* file or dir now absent - probably retired by netfs */
		_leave(" = -ESTALE [absent]");
		return -ESTALE;
	}

	if (ret != -ENOMEM) {
		kerror("Internal error: %d", ret);
		ret = -EIO;
	}

	_leave(" = %d", ret);
	return ret;
}

/*
 * find out if an object is in use or not
 * - called only by cache manager daemon
 * - returns -EBUSY or 0 to indicate whether an object is in use or not
 */
int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir,
			    char *filename)
{
	struct dentry *victim;

	//_enter(",%*.*s/,%s",
	//       dir->d_name.len, dir->d_name.len, dir->d_name.name, filename);

	victim = cachefiles_check_active(cache, dir, filename);
	if (IS_ERR(victim))
		return PTR_ERR(victim);

	mutex_unlock(&dir->d_inode->i_mutex);
	dput(victim);
	//_leave(" = 0");
	return 0;
}