mark.c 22.7 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
/*
 *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2, or (at your option)
 *  any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; see the file COPYING.  If not, write to
 *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
 */

/*
 * fsnotify inode mark locking/lifetime/and refcnting
 *
 * REFCNT:
 * The group->recnt and mark->refcnt tell how many "things" in the kernel
 * currently are referencing the objects. Both kind of objects typically will
 * live inside the kernel with a refcnt of 2, one for its creation and one for
 * the reference a group and a mark hold to each other.
 * If you are holding the appropriate locks, you can take a reference and the
 * object itself is guaranteed to survive until the reference is dropped.
 *
 * LOCKING:
 * There are 3 locks involved with fsnotify inode marks and they MUST be taken
 * in order as follows:
 *
 * group->mark_mutex
 * mark->lock
 * mark->connector->lock
 *
 * group->mark_mutex protects the marks_list anchored inside a given group and
 * each mark is hooked via the g_list.  It also protects the groups private
 * data (i.e group limits).

 * mark->lock protects the marks attributes like its masks and flags.
 * Furthermore it protects the access to a reference of the group that the mark
 * is assigned to as well as the access to a reference of the inode/vfsmount
 * that is being watched by the mark.
 *
 * mark->connector->lock protects the list of marks anchored inside an
 * inode / vfsmount and each mark is hooked via the i_list.
 *
 * A list of notification marks relating to inode / mnt is contained in
 * fsnotify_mark_connector. That structure is alive as long as there are any
 * marks in the list and is also protected by fsnotify_mark_srcu. A mark gets
 * detached from fsnotify_mark_connector when last reference to the mark is
 * dropped.  Thus having mark reference is enough to protect mark->connector
 * pointer and to make sure fsnotify_mark_connector cannot disappear. Also
 * because we remove mark from g_list before dropping mark reference associated
 * with that, any mark found through g_list is guaranteed to have
 * mark->connector set until we drop group->mark_mutex.
 *
 * LIFETIME:
 * Inode marks survive between when they are added to an inode and when their
 * refcnt==0. Marks are also protected by fsnotify_mark_srcu.
 *
 * The inode mark can be cleared for a number of different reasons including:
 * - The inode is unlinked for the last time.  (fsnotify_inode_remove)
 * - The inode is being evicted from cache. (fsnotify_inode_delete)
 * - The fs the inode is on is unmounted.  (fsnotify_inode_delete/fsnotify_unmount_inodes)
 * - Something explicitly requests that it be removed.  (fsnotify_destroy_mark)
 * - The fsnotify_group associated with the mark is going away and all such marks
 *   need to be cleaned up. (fsnotify_clear_marks_by_group)
 *
 * This has the very interesting property of being able to run concurrently with
 * any (or all) other directions.
 */

#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/srcu.h>

#include <linux/atomic.h>

#include <linux/fsnotify_backend.h>
#include "fsnotify.h"

#define FSNOTIFY_REAPER_DELAY	(1)	/* 1 jiffy */

struct srcu_struct fsnotify_mark_srcu;
struct kmem_cache *fsnotify_mark_connector_cachep;

static DEFINE_SPINLOCK(destroy_lock);
static LIST_HEAD(destroy_list);
static struct fsnotify_mark_connector *connector_destroy_list;

static void fsnotify_mark_destroy_workfn(struct work_struct *work);
static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn);

static void fsnotify_connector_destroy_workfn(struct work_struct *work);
static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn);

void fsnotify_get_mark(struct fsnotify_mark *mark)
{
	WARN_ON_ONCE(!atomic_read(&mark->refcnt));
	atomic_inc(&mark->refcnt);
}

static void __fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
{
	u32 new_mask = 0;
	struct fsnotify_mark *mark;

	assert_spin_locked(&conn->lock);
	hlist_for_each_entry(mark, &conn->list, obj_list) {
		if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)
			new_mask |= mark->mask;
	}
	if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE)
		conn->inode->i_fsnotify_mask = new_mask;
	else if (conn->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT)
		real_mount(conn->mnt)->mnt_fsnotify_mask = new_mask;
}

/*
 * Calculate mask of events for a list of marks. The caller must make sure
 * connector and connector->inode cannot disappear under us.  Callers achieve
 * this by holding a mark->lock or mark->group->mark_mutex for a mark on this
 * list.
 */
void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
{
	if (!conn)
		return;

	spin_lock(&conn->lock);
	__fsnotify_recalc_mask(conn);
	spin_unlock(&conn->lock);
	if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE)
		__fsnotify_update_child_dentry_flags(conn->inode);
}

/* Free all connectors queued for freeing once SRCU period ends */
static void fsnotify_connector_destroy_workfn(struct work_struct *work)
{
	struct fsnotify_mark_connector *conn, *free;

	spin_lock(&destroy_lock);
	conn = connector_destroy_list;
	connector_destroy_list = NULL;
	spin_unlock(&destroy_lock);

	synchronize_srcu(&fsnotify_mark_srcu);
	while (conn) {
		free = conn;
		conn = conn->destroy_next;
		kmem_cache_free(fsnotify_mark_connector_cachep, free);
	}
}

static struct inode *fsnotify_detach_connector_from_object(
					struct fsnotify_mark_connector *conn)
{
	struct inode *inode = NULL;

	if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE) {
		inode = conn->inode;
		rcu_assign_pointer(inode->i_fsnotify_marks, NULL);
		inode->i_fsnotify_mask = 0;
		conn->inode = NULL;
		conn->flags &= ~FSNOTIFY_OBJ_TYPE_INODE;
	} else if (conn->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
		rcu_assign_pointer(real_mount(conn->mnt)->mnt_fsnotify_marks,
				   NULL);
		real_mount(conn->mnt)->mnt_fsnotify_mask = 0;
		conn->mnt = NULL;
		conn->flags &= ~FSNOTIFY_OBJ_TYPE_VFSMOUNT;
	}

	return inode;
}

static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark)
{
	struct fsnotify_group *group = mark->group;

	if (WARN_ON_ONCE(!group))
		return;
	group->ops->free_mark(mark);
	fsnotify_put_group(group);
}

void fsnotify_put_mark(struct fsnotify_mark *mark)
{
	struct fsnotify_mark_connector *conn;
	struct inode *inode = NULL;
	bool free_conn = false;

	/* Catch marks that were actually never attached to object */
	if (!mark->connector) {
		if (atomic_dec_and_test(&mark->refcnt))
			fsnotify_final_mark_destroy(mark);
		return;
	}

	/*
	 * We have to be careful so that traversals of obj_list under lock can
	 * safely grab mark reference.
	 */
	if (!atomic_dec_and_lock(&mark->refcnt, &mark->connector->lock))
		return;

	conn = mark->connector;
	hlist_del_init_rcu(&mark->obj_list);
	if (hlist_empty(&conn->list)) {
		inode = fsnotify_detach_connector_from_object(conn);
		free_conn = true;
	} else {
		__fsnotify_recalc_mask(conn);
	}
	mark->connector = NULL;
	spin_unlock(&conn->lock);

	iput(inode);

	if (free_conn) {
		spin_lock(&destroy_lock);
		conn->destroy_next = connector_destroy_list;
		connector_destroy_list = conn;
		spin_unlock(&destroy_lock);
		queue_work(system_unbound_wq, &connector_reaper_work);
	}
	/*
	 * Note that we didn't update flags telling whether inode cares about
	 * what's happening with children. We update these flags from
	 * __fsnotify_parent() lazily when next event happens on one of our
	 * children.
	 */
	spin_lock(&destroy_lock);
	list_add(&mark->g_list, &destroy_list);
	spin_unlock(&destroy_lock);
	queue_delayed_work(system_unbound_wq, &reaper_work,
			   FSNOTIFY_REAPER_DELAY);
}

/*
 * Get mark reference when we found the mark via lockless traversal of object
 * list. Mark can be already removed from the list by now and on its way to be
 * destroyed once SRCU period ends.
 *
 * Also pin the group so it doesn't disappear under us.
 */
static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark)
{
	if (!mark)
		return true;

	if (atomic_inc_not_zero(&mark->refcnt)) {
		spin_lock(&mark->lock);
		if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) {
			/* mark is attached, group is still alive then */
			atomic_inc(&mark->group->user_waits);
			spin_unlock(&mark->lock);
			return true;
		}
		spin_unlock(&mark->lock);
		fsnotify_put_mark(mark);
	}
	return false;
}

/*
 * Puts marks and wakes up group destruction if necessary.
 *
 * Pairs with fsnotify_get_mark_safe()
 */
static void fsnotify_put_mark_wake(struct fsnotify_mark *mark)
{
	if (mark) {
		struct fsnotify_group *group = mark->group;

		fsnotify_put_mark(mark);
		/*
		 * We abuse notification_waitq on group shutdown for waiting for
		 * all marks pinned when waiting for userspace.
		 */
		if (atomic_dec_and_test(&group->user_waits) && group->shutdown)
			wake_up(&group->notification_waitq);
	}
}

bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info)
{
	/* This can fail if mark is being removed */
	if (!fsnotify_get_mark_safe(iter_info->inode_mark))
		return false;
	if (!fsnotify_get_mark_safe(iter_info->vfsmount_mark)) {
		fsnotify_put_mark_wake(iter_info->inode_mark);
		return false;
	}

	/*
	 * Now that both marks are pinned by refcount in the inode / vfsmount
	 * lists, we can drop SRCU lock, and safely resume the list iteration
	 * once userspace returns.
	 */
	srcu_read_unlock(&fsnotify_mark_srcu, iter_info->srcu_idx);

	return true;
}

void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info)
{
	iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
	fsnotify_put_mark_wake(iter_info->inode_mark);
	fsnotify_put_mark_wake(iter_info->vfsmount_mark);
}

/*
 * Mark mark as detached, remove it from group list. Mark still stays in object
 * list until its last reference is dropped. Note that we rely on mark being
 * removed from group list before corresponding reference to it is dropped. In
 * particular we rely on mark->connector being valid while we hold
 * group->mark_mutex if we found the mark through g_list.
 *
 * Must be called with group->mark_mutex held. The caller must either hold
 * reference to the mark or be protected by fsnotify_mark_srcu.
 */
void fsnotify_detach_mark(struct fsnotify_mark *mark)
{
	struct fsnotify_group *group = mark->group;

	WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex));
	WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) &&
		     atomic_read(&mark->refcnt) < 1 +
			!!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED));

	spin_lock(&mark->lock);
	/* something else already called this function on this mark */
	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
		spin_unlock(&mark->lock);
		return;
	}
	mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED;
	list_del_init(&mark->g_list);
	spin_unlock(&mark->lock);

	atomic_dec(&group->num_marks);

	/* Drop mark reference acquired in fsnotify_add_mark_locked() */
	fsnotify_put_mark(mark);
}

/*
 * Free fsnotify mark. The mark is actually only marked as being freed.  The
 * freeing is actually happening only once last reference to the mark is
 * dropped from a workqueue which first waits for srcu period end.
 *
 * Caller must have a reference to the mark or be protected by
 * fsnotify_mark_srcu.
 */
void fsnotify_free_mark(struct fsnotify_mark *mark)
{
	struct fsnotify_group *group = mark->group;

	spin_lock(&mark->lock);
	/* something else already called this function on this mark */
	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) {
		spin_unlock(&mark->lock);
		return;
	}
	mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
	spin_unlock(&mark->lock);

	/*
	 * Some groups like to know that marks are being freed.  This is a
	 * callback to the group function to let it know that this mark
	 * is being freed.
	 */
	if (group->ops->freeing_mark)
		group->ops->freeing_mark(mark, group);
}

void fsnotify_destroy_mark(struct fsnotify_mark *mark,
			   struct fsnotify_group *group)
{
	mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
	fsnotify_detach_mark(mark);
	mutex_unlock(&group->mark_mutex);
	fsnotify_free_mark(mark);
}

/*
 * Sorting function for lists of fsnotify marks.
 *
 * Fanotify supports different notification classes (reflected as priority of
 * notification group). Events shall be passed to notification groups in
 * decreasing priority order. To achieve this marks in notification lists for
 * inodes and vfsmounts are sorted so that priorities of corresponding groups
 * are descending.
 *
 * Furthermore correct handling of the ignore mask requires processing inode
 * and vfsmount marks of each group together. Using the group address as
 * further sort criterion provides a unique sorting order and thus we can
 * merge inode and vfsmount lists of marks in linear time and find groups
 * present in both lists.
 *
 * A return value of 1 signifies that b has priority over a.
 * A return value of 0 signifies that the two marks have to be handled together.
 * A return value of -1 signifies that a has priority over b.
 */
int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
{
	if (a == b)
		return 0;
	if (!a)
		return 1;
	if (!b)
		return -1;
	if (a->priority < b->priority)
		return 1;
	if (a->priority > b->priority)
		return -1;
	if (a < b)
		return 1;
	return -1;
}

static int fsnotify_attach_connector_to_object(
				struct fsnotify_mark_connector __rcu **connp,
				struct inode *inode,
				struct vfsmount *mnt)
{
	struct fsnotify_mark_connector *conn;

	conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_KERNEL);
	if (!conn)
		return -ENOMEM;
	spin_lock_init(&conn->lock);
	INIT_HLIST_HEAD(&conn->list);
	if (inode) {
		conn->flags = FSNOTIFY_OBJ_TYPE_INODE;
		conn->inode = igrab(inode);
	} else {
		conn->flags = FSNOTIFY_OBJ_TYPE_VFSMOUNT;
		conn->mnt = mnt;
	}
	/*
	 * cmpxchg() provides the barrier so that readers of *connp can see
	 * only initialized structure
	 */
	if (cmpxchg(connp, NULL, conn)) {
		/* Someone else created list structure for us */
		if (inode)
			iput(inode);
		kmem_cache_free(fsnotify_mark_connector_cachep, conn);
	}

	return 0;
}

/*
 * Get mark connector, make sure it is alive and return with its lock held.
 * This is for users that get connector pointer from inode or mount. Users that
 * hold reference to a mark on the list may directly lock connector->lock as
 * they are sure list cannot go away under them.
 */
static struct fsnotify_mark_connector *fsnotify_grab_connector(
				struct fsnotify_mark_connector __rcu **connp)
{
	struct fsnotify_mark_connector *conn;
	int idx;

	idx = srcu_read_lock(&fsnotify_mark_srcu);
	conn = srcu_dereference(*connp, &fsnotify_mark_srcu);
	if (!conn)
		goto out;
	spin_lock(&conn->lock);
	if (!(conn->flags & (FSNOTIFY_OBJ_TYPE_INODE |
			     FSNOTIFY_OBJ_TYPE_VFSMOUNT))) {
		spin_unlock(&conn->lock);
		srcu_read_unlock(&fsnotify_mark_srcu, idx);
		return NULL;
	}
out:
	srcu_read_unlock(&fsnotify_mark_srcu, idx);
	return conn;
}

/*
 * Add mark into proper place in given list of marks. These marks may be used
 * for the fsnotify backend to determine which event types should be delivered
 * to which group and for which inodes. These marks are ordered according to
 * priority, highest number first, and then by the group's location in memory.
 */
static int fsnotify_add_mark_list(struct fsnotify_mark *mark,
				  struct inode *inode, struct vfsmount *mnt,
				  int allow_dups)
{
	struct fsnotify_mark *lmark, *last = NULL;
	struct fsnotify_mark_connector *conn;
	struct fsnotify_mark_connector __rcu **connp;
	int cmp;
	int err = 0;

	if (WARN_ON(!inode && !mnt))
		return -EINVAL;
	if (inode)
		connp = &inode->i_fsnotify_marks;
	else
		connp = &real_mount(mnt)->mnt_fsnotify_marks;
restart:
	spin_lock(&mark->lock);
	conn = fsnotify_grab_connector(connp);
	if (!conn) {
		spin_unlock(&mark->lock);
		err = fsnotify_attach_connector_to_object(connp, inode, mnt);
		if (err)
			return err;
		goto restart;
	}

	/* is mark the first mark? */
	if (hlist_empty(&conn->list)) {
		hlist_add_head_rcu(&mark->obj_list, &conn->list);
		goto added;
	}

	/* should mark be in the middle of the current list? */
	hlist_for_each_entry(lmark, &conn->list, obj_list) {
		last = lmark;

		if ((lmark->group == mark->group) &&
		    (lmark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) &&
		    !allow_dups) {
			err = -EEXIST;
			goto out_err;
		}

		cmp = fsnotify_compare_groups(lmark->group, mark->group);
		if (cmp >= 0) {
			hlist_add_before_rcu(&mark->obj_list, &lmark->obj_list);
			goto added;
		}
	}

	BUG_ON(last == NULL);
	/* mark should be the last entry.  last is the current last entry */
	hlist_add_behind_rcu(&mark->obj_list, &last->obj_list);
added:
	mark->connector = conn;
out_err:
	spin_unlock(&conn->lock);
	spin_unlock(&mark->lock);
	return err;
}

/*
 * Attach an initialized mark to a given group and fs object.
 * These marks may be used for the fsnotify backend to determine which
 * event types should be delivered to which group.
 */
int fsnotify_add_mark_locked(struct fsnotify_mark *mark, struct inode *inode,
			     struct vfsmount *mnt, int allow_dups)
{
	struct fsnotify_group *group = mark->group;
	int ret = 0;

	BUG_ON(inode && mnt);
	BUG_ON(!inode && !mnt);
	BUG_ON(!mutex_is_locked(&group->mark_mutex));

	/*
	 * LOCKING ORDER!!!!
	 * group->mark_mutex
	 * mark->lock
	 * mark->connector->lock
	 */
	spin_lock(&mark->lock);
	mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED;

	list_add(&mark->g_list, &group->marks_list);
	atomic_inc(&group->num_marks);
	fsnotify_get_mark(mark); /* for g_list */
	spin_unlock(&mark->lock);

	ret = fsnotify_add_mark_list(mark, inode, mnt, allow_dups);
	if (ret)
		goto err;

	if (mark->mask)
		fsnotify_recalc_mask(mark->connector);

	return ret;
err:
	mark->flags &= ~(FSNOTIFY_MARK_FLAG_ALIVE |
			 FSNOTIFY_MARK_FLAG_ATTACHED);
	list_del_init(&mark->g_list);
	atomic_dec(&group->num_marks);

	fsnotify_put_mark(mark);
	return ret;
}

int fsnotify_add_mark(struct fsnotify_mark *mark, struct inode *inode,
		      struct vfsmount *mnt, int allow_dups)
{
	int ret;
	struct fsnotify_group *group = mark->group;

	mutex_lock(&group->mark_mutex);
	ret = fsnotify_add_mark_locked(mark, inode, mnt, allow_dups);
	mutex_unlock(&group->mark_mutex);
	return ret;
}

/*
 * Given a list of marks, find the mark associated with given group. If found
 * take a reference to that mark and return it, else return NULL.
 */
struct fsnotify_mark *fsnotify_find_mark(
				struct fsnotify_mark_connector __rcu **connp,
				struct fsnotify_group *group)
{
	struct fsnotify_mark_connector *conn;
	struct fsnotify_mark *mark;

	conn = fsnotify_grab_connector(connp);
	if (!conn)
		return NULL;

	hlist_for_each_entry(mark, &conn->list, obj_list) {
		if (mark->group == group &&
		    (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
			fsnotify_get_mark(mark);
			spin_unlock(&conn->lock);
			return mark;
		}
	}
	spin_unlock(&conn->lock);
	return NULL;
}

/* Clear any marks in a group with given type */
void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
				   unsigned int type)
{
	struct fsnotify_mark *lmark, *mark;
	LIST_HEAD(to_free);
	struct list_head *head = &to_free;

	/* Skip selection step if we want to clear all marks. */
	if (type == FSNOTIFY_OBJ_ALL_TYPES) {
		head = &group->marks_list;
		goto clear;
	}
	/*
	 * We have to be really careful here. Anytime we drop mark_mutex, e.g.
	 * fsnotify_clear_marks_by_inode() can come and free marks. Even in our
	 * to_free list so we have to use mark_mutex even when accessing that
	 * list. And freeing mark requires us to drop mark_mutex. So we can
	 * reliably free only the first mark in the list. That's why we first
	 * move marks to free to to_free list in one go and then free marks in
	 * to_free list one by one.
	 */
	mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
	list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
		if (mark->connector->flags & type)
			list_move(&mark->g_list, &to_free);
	}
	mutex_unlock(&group->mark_mutex);

clear:
	while (1) {
		mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
		if (list_empty(head)) {
			mutex_unlock(&group->mark_mutex);
			break;
		}
		mark = list_first_entry(head, struct fsnotify_mark, g_list);
		fsnotify_get_mark(mark);
		fsnotify_detach_mark(mark);
		mutex_unlock(&group->mark_mutex);
		fsnotify_free_mark(mark);
		fsnotify_put_mark(mark);
	}
}

/* Destroy all marks attached to inode / vfsmount */
void fsnotify_destroy_marks(struct fsnotify_mark_connector __rcu **connp)
{
	struct fsnotify_mark_connector *conn;
	struct fsnotify_mark *mark, *old_mark = NULL;
	struct inode *inode;

	conn = fsnotify_grab_connector(connp);
	if (!conn)
		return;
	/*
	 * We have to be careful since we can race with e.g.
	 * fsnotify_clear_marks_by_group() and once we drop the conn->lock, the
	 * list can get modified. However we are holding mark reference and
	 * thus our mark cannot be removed from obj_list so we can continue
	 * iteration after regaining conn->lock.
	 */
	hlist_for_each_entry(mark, &conn->list, obj_list) {
		fsnotify_get_mark(mark);
		spin_unlock(&conn->lock);
		if (old_mark)
			fsnotify_put_mark(old_mark);
		old_mark = mark;
		fsnotify_destroy_mark(mark, mark->group);
		spin_lock(&conn->lock);
	}
	/*
	 * Detach list from object now so that we don't pin inode until all
	 * mark references get dropped. It would lead to strange results such
	 * as delaying inode deletion or blocking unmount.
	 */
	inode = fsnotify_detach_connector_from_object(conn);
	spin_unlock(&conn->lock);
	if (old_mark)
		fsnotify_put_mark(old_mark);
	iput(inode);
}

/*
 * Nothing fancy, just initialize lists and locks and counters.
 */
void fsnotify_init_mark(struct fsnotify_mark *mark,
			struct fsnotify_group *group)
{
	memset(mark, 0, sizeof(*mark));
	spin_lock_init(&mark->lock);
	atomic_set(&mark->refcnt, 1);
	fsnotify_get_group(group);
	mark->group = group;
}

/*
 * Destroy all marks in destroy_list, waits for SRCU period to finish before
 * actually freeing marks.
 */
static void fsnotify_mark_destroy_workfn(struct work_struct *work)
{
	struct fsnotify_mark *mark, *next;
	struct list_head private_destroy_list;

	spin_lock(&destroy_lock);
	/* exchange the list head */
	list_replace_init(&destroy_list, &private_destroy_list);
	spin_unlock(&destroy_lock);

	synchronize_srcu(&fsnotify_mark_srcu);

	list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
		list_del_init(&mark->g_list);
		fsnotify_final_mark_destroy(mark);
	}
}

/* Wait for all marks queued for destruction to be actually destroyed */
void fsnotify_wait_marks_destroyed(void)
{
	flush_delayed_work(&reaper_work);
}