xref: /kernel/linux/linux-5.10/fs/cachefiles/namei.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0-or-later
2/* CacheFiles path walking and related routines
3 *
4 * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
5 * Written by David Howells (dhowells@redhat.com)
6 */
7
8#include <linux/module.h>
9#include <linux/sched.h>
10#include <linux/file.h>
11#include <linux/fs.h>
12#include <linux/fsnotify.h>
13#include <linux/quotaops.h>
14#include <linux/xattr.h>
15#include <linux/mount.h>
16#include <linux/namei.h>
17#include <linux/security.h>
18#include <linux/slab.h>
19#include "internal.h"
20
21#define CACHEFILES_KEYBUF_SIZE 512
22
23/*
24 * dump debugging info about an object
25 */
26static noinline
27void __cachefiles_printk_object(struct cachefiles_object *object,
28				const char *prefix)
29{
30	struct fscache_cookie *cookie;
31	const u8 *k;
32	unsigned loop;
33
34	pr_err("%sobject: OBJ%x\n", prefix, object->fscache.debug_id);
35	pr_err("%sobjstate=%s fl=%lx wbusy=%x ev=%lx[%lx]\n",
36	       prefix, object->fscache.state->name,
37	       object->fscache.flags, work_busy(&object->fscache.work),
38	       object->fscache.events, object->fscache.event_mask);
39	pr_err("%sops=%u inp=%u exc=%u\n",
40	       prefix, object->fscache.n_ops, object->fscache.n_in_progress,
41	       object->fscache.n_exclusive);
42	pr_err("%sparent=%p\n",
43	       prefix, object->fscache.parent);
44
45	spin_lock(&object->fscache.lock);
46	cookie = object->fscache.cookie;
47	if (cookie) {
48		pr_err("%scookie=%p [pr=%p nd=%p fl=%lx]\n",
49		       prefix,
50		       object->fscache.cookie,
51		       object->fscache.cookie->parent,
52		       object->fscache.cookie->netfs_data,
53		       object->fscache.cookie->flags);
54		pr_err("%skey=[%u] '", prefix, cookie->key_len);
55		k = (cookie->key_len <= sizeof(cookie->inline_key)) ?
56			cookie->inline_key : cookie->key;
57		for (loop = 0; loop < cookie->key_len; loop++)
58			pr_cont("%02x", k[loop]);
59		pr_cont("'\n");
60	} else {
61		pr_err("%scookie=NULL\n", prefix);
62	}
63	spin_unlock(&object->fscache.lock);
64}
65
66/*
67 * dump debugging info about a pair of objects
68 */
69static noinline void cachefiles_printk_object(struct cachefiles_object *object,
70					      struct cachefiles_object *xobject)
71{
72	if (object)
73		__cachefiles_printk_object(object, "");
74	if (xobject)
75		__cachefiles_printk_object(xobject, "x");
76}
77
78/*
79 * mark the owner of a dentry, if there is one, to indicate that that dentry
80 * has been preemptively deleted
81 * - the caller must hold the i_mutex on the dentry's parent as required to
82 *   call vfs_unlink(), vfs_rmdir() or vfs_rename()
83 */
84static void cachefiles_mark_object_buried(struct cachefiles_cache *cache,
85					  struct dentry *dentry,
86					  enum fscache_why_object_killed why)
87{
88	struct cachefiles_object *object;
89	struct rb_node *p;
90
91	_enter(",'%pd'", dentry);
92
93	write_lock(&cache->active_lock);
94
95	p = cache->active_nodes.rb_node;
96	while (p) {
97		object = rb_entry(p, struct cachefiles_object, active_node);
98		if (object->dentry > dentry)
99			p = p->rb_left;
100		else if (object->dentry < dentry)
101			p = p->rb_right;
102		else
103			goto found_dentry;
104	}
105
106	write_unlock(&cache->active_lock);
107	trace_cachefiles_mark_buried(NULL, dentry, why);
108	_leave(" [no owner]");
109	return;
110
111	/* found the dentry for  */
112found_dentry:
113	kdebug("preemptive burial: OBJ%x [%s] %p",
114	       object->fscache.debug_id,
115	       object->fscache.state->name,
116	       dentry);
117
118	trace_cachefiles_mark_buried(object, dentry, why);
119
120	if (fscache_object_is_live(&object->fscache)) {
121		pr_err("\n");
122		pr_err("Error: Can't preemptively bury live object\n");
123		cachefiles_printk_object(object, NULL);
124	} else {
125		if (why != FSCACHE_OBJECT_IS_STALE)
126			fscache_object_mark_killed(&object->fscache, why);
127	}
128
129	write_unlock(&cache->active_lock);
130	_leave(" [owner marked]");
131}
132
133/*
134 * record the fact that an object is now active
135 */
136static int cachefiles_mark_object_active(struct cachefiles_cache *cache,
137					 struct cachefiles_object *object)
138{
139	struct cachefiles_object *xobject;
140	struct rb_node **_p, *_parent = NULL;
141	struct dentry *dentry;
142
143	_enter(",%p", object);
144
145try_again:
146	write_lock(&cache->active_lock);
147
148	dentry = object->dentry;
149	trace_cachefiles_mark_active(object, dentry);
150
151	if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) {
152		pr_err("Error: Object already active\n");
153		cachefiles_printk_object(object, NULL);
154		BUG();
155	}
156
157	_p = &cache->active_nodes.rb_node;
158	while (*_p) {
159		_parent = *_p;
160		xobject = rb_entry(_parent,
161				   struct cachefiles_object, active_node);
162
163		ASSERT(xobject != object);
164
165		if (xobject->dentry > dentry)
166			_p = &(*_p)->rb_left;
167		else if (xobject->dentry < dentry)
168			_p = &(*_p)->rb_right;
169		else
170			goto wait_for_old_object;
171	}
172
173	rb_link_node(&object->active_node, _parent, _p);
174	rb_insert_color(&object->active_node, &cache->active_nodes);
175
176	write_unlock(&cache->active_lock);
177	_leave(" = 0");
178	return 0;
179
180	/* an old object from a previous incarnation is hogging the slot - we
181	 * need to wait for it to be destroyed */
182wait_for_old_object:
183	trace_cachefiles_wait_active(object, dentry, xobject);
184	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
185
186	if (fscache_object_is_live(&xobject->fscache)) {
187		pr_err("\n");
188		pr_err("Error: Unexpected object collision\n");
189		cachefiles_printk_object(object, xobject);
190	}
191	atomic_inc(&xobject->usage);
192	write_unlock(&cache->active_lock);
193
194	if (test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) {
195		wait_queue_head_t *wq;
196
197		signed long timeout = 60 * HZ;
198		wait_queue_entry_t wait;
199		bool requeue;
200
201		/* if the object we're waiting for is queued for processing,
202		 * then just put ourselves on the queue behind it */
203		if (work_pending(&xobject->fscache.work)) {
204			_debug("queue OBJ%x behind OBJ%x immediately",
205			       object->fscache.debug_id,
206			       xobject->fscache.debug_id);
207			goto requeue;
208		}
209
210		/* otherwise we sleep until either the object we're waiting for
211		 * is done, or the fscache_object is congested */
212		wq = bit_waitqueue(&xobject->flags, CACHEFILES_OBJECT_ACTIVE);
213		init_wait(&wait);
214		requeue = false;
215		do {
216			prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
217			if (!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags))
218				break;
219
220			requeue = fscache_object_sleep_till_congested(&timeout);
221		} while (timeout > 0 && !requeue);
222		finish_wait(wq, &wait);
223
224		if (requeue &&
225		    test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) {
226			_debug("queue OBJ%x behind OBJ%x after wait",
227			       object->fscache.debug_id,
228			       xobject->fscache.debug_id);
229			goto requeue;
230		}
231
232		if (timeout <= 0) {
233			pr_err("\n");
234			pr_err("Error: Overlong wait for old active object to go away\n");
235			cachefiles_printk_object(object, xobject);
236			goto requeue;
237		}
238	}
239
240	ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags));
241
242	cache->cache.ops->put_object(&xobject->fscache,
243		(enum fscache_obj_ref_trace)cachefiles_obj_put_wait_retry);
244	goto try_again;
245
246requeue:
247	cache->cache.ops->put_object(&xobject->fscache,
248		(enum fscache_obj_ref_trace)cachefiles_obj_put_wait_timeo);
249	_leave(" = -ETIMEDOUT");
250	return -ETIMEDOUT;
251}
252
253/*
254 * Mark an object as being inactive.
255 */
256void cachefiles_mark_object_inactive(struct cachefiles_cache *cache,
257				     struct cachefiles_object *object,
258				     blkcnt_t i_blocks)
259{
260	struct dentry *dentry = object->dentry;
261	struct inode *inode = d_backing_inode(dentry);
262
263	trace_cachefiles_mark_inactive(object, dentry, inode);
264
265	write_lock(&cache->active_lock);
266	rb_erase(&object->active_node, &cache->active_nodes);
267	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
268	write_unlock(&cache->active_lock);
269
270	wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
271
272	/* This object can now be culled, so we need to let the daemon know
273	 * that there is something it can remove if it needs to.
274	 */
275	atomic_long_add(i_blocks, &cache->b_released);
276	if (atomic_inc_return(&cache->f_released))
277		cachefiles_state_changed(cache);
278}
279
280/*
281 * delete an object representation from the cache
282 * - file backed objects are unlinked
283 * - directory backed objects are stuffed into the graveyard for userspace to
284 *   delete
285 * - unlocks the directory mutex
286 */
287static int cachefiles_bury_object(struct cachefiles_cache *cache,
288				  struct cachefiles_object *object,
289				  struct dentry *dir,
290				  struct dentry *rep,
291				  bool preemptive,
292				  enum fscache_why_object_killed why)
293{
294	struct dentry *grave, *trap;
295	struct path path, path_to_graveyard;
296	char nbuffer[8 + 8 + 1];
297	int ret;
298
299	_enter(",'%pd','%pd'", dir, rep);
300
301	_debug("remove %p from %p", rep, dir);
302
303	/* non-directories can just be unlinked */
304	if (!d_is_dir(rep)) {
305		_debug("unlink stale object");
306
307		path.mnt = cache->mnt;
308		path.dentry = dir;
309		ret = security_path_unlink(&path, rep);
310		if (ret < 0) {
311			cachefiles_io_error(cache, "Unlink security error");
312		} else {
313			trace_cachefiles_unlink(object, rep, why);
314			ret = vfs_unlink(d_inode(dir), rep, NULL);
315
316			if (preemptive)
317				cachefiles_mark_object_buried(cache, rep, why);
318		}
319
320		inode_unlock(d_inode(dir));
321
322		if (ret == -EIO)
323			cachefiles_io_error(cache, "Unlink failed");
324
325		_leave(" = %d", ret);
326		return ret;
327	}
328
329	/* directories have to be moved to the graveyard */
330	_debug("move stale object to graveyard");
331	inode_unlock(d_inode(dir));
332
333try_again:
334	/* first step is to make up a grave dentry in the graveyard */
335	sprintf(nbuffer, "%08x%08x",
336		(uint32_t) ktime_get_real_seconds(),
337		(uint32_t) atomic_inc_return(&cache->gravecounter));
338
339	/* do the multiway lock magic */
340	trap = lock_rename(cache->graveyard, dir);
341
342	/* do some checks before getting the grave dentry */
343	if (rep->d_parent != dir || IS_DEADDIR(d_inode(rep))) {
344		/* the entry was probably culled when we dropped the parent dir
345		 * lock */
346		unlock_rename(cache->graveyard, dir);
347		_leave(" = 0 [culled?]");
348		return 0;
349	}
350
351	if (!d_can_lookup(cache->graveyard)) {
352		unlock_rename(cache->graveyard, dir);
353		cachefiles_io_error(cache, "Graveyard no longer a directory");
354		return -EIO;
355	}
356
357	if (trap == rep) {
358		unlock_rename(cache->graveyard, dir);
359		cachefiles_io_error(cache, "May not make directory loop");
360		return -EIO;
361	}
362
363	if (d_mountpoint(rep)) {
364		unlock_rename(cache->graveyard, dir);
365		cachefiles_io_error(cache, "Mountpoint in cache");
366		return -EIO;
367	}
368
369	grave = lookup_one_len(nbuffer, cache->graveyard, strlen(nbuffer));
370	if (IS_ERR(grave)) {
371		unlock_rename(cache->graveyard, dir);
372
373		if (PTR_ERR(grave) == -ENOMEM) {
374			_leave(" = -ENOMEM");
375			return -ENOMEM;
376		}
377
378		cachefiles_io_error(cache, "Lookup error %ld",
379				    PTR_ERR(grave));
380		return -EIO;
381	}
382
383	if (d_is_positive(grave)) {
384		unlock_rename(cache->graveyard, dir);
385		dput(grave);
386		grave = NULL;
387		cond_resched();
388		goto try_again;
389	}
390
391	if (d_mountpoint(grave)) {
392		unlock_rename(cache->graveyard, dir);
393		dput(grave);
394		cachefiles_io_error(cache, "Mountpoint in graveyard");
395		return -EIO;
396	}
397
398	/* target should not be an ancestor of source */
399	if (trap == grave) {
400		unlock_rename(cache->graveyard, dir);
401		dput(grave);
402		cachefiles_io_error(cache, "May not make directory loop");
403		return -EIO;
404	}
405
406	/* attempt the rename */
407	path.mnt = cache->mnt;
408	path.dentry = dir;
409	path_to_graveyard.mnt = cache->mnt;
410	path_to_graveyard.dentry = cache->graveyard;
411	ret = security_path_rename(&path, rep, &path_to_graveyard, grave, 0);
412	if (ret < 0) {
413		cachefiles_io_error(cache, "Rename security error %d", ret);
414	} else {
415		trace_cachefiles_rename(object, rep, grave, why);
416		ret = vfs_rename(d_inode(dir), rep,
417				 d_inode(cache->graveyard), grave, NULL, 0);
418		if (ret != 0 && ret != -ENOMEM)
419			cachefiles_io_error(cache,
420					    "Rename failed with error %d", ret);
421
422		if (preemptive)
423			cachefiles_mark_object_buried(cache, rep, why);
424	}
425
426	unlock_rename(cache->graveyard, dir);
427	dput(grave);
428	_leave(" = 0");
429	return 0;
430}
431
432/*
433 * delete an object representation from the cache
434 */
435int cachefiles_delete_object(struct cachefiles_cache *cache,
436			     struct cachefiles_object *object)
437{
438	struct dentry *dir;
439	int ret;
440
441	_enter(",OBJ%x{%p}", object->fscache.debug_id, object->dentry);
442
443	ASSERT(object->dentry);
444	ASSERT(d_backing_inode(object->dentry));
445	ASSERT(object->dentry->d_parent);
446
447	dir = dget_parent(object->dentry);
448
449	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
450
451	if (test_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->fscache.flags)) {
452		/* object allocation for the same key preemptively deleted this
453		 * object's file so that it could create its own file */
454		_debug("object preemptively buried");
455		inode_unlock(d_inode(dir));
456		ret = 0;
457	} else {
458		/* we need to check that our parent is _still_ our parent - it
459		 * may have been renamed */
460		if (dir == object->dentry->d_parent) {
461			ret = cachefiles_bury_object(cache, object, dir,
462						     object->dentry, false,
463						     FSCACHE_OBJECT_WAS_RETIRED);
464		} else {
465			/* it got moved, presumably by cachefilesd culling it,
466			 * so it's no longer in the key path and we can ignore
467			 * it */
468			inode_unlock(d_inode(dir));
469			ret = 0;
470		}
471	}
472
473	dput(dir);
474	_leave(" = %d", ret);
475	return ret;
476}
477
478/*
479 * walk from the parent object to the child object through the backing
480 * filesystem, creating directories as we go
481 */
482int cachefiles_walk_to_object(struct cachefiles_object *parent,
483			      struct cachefiles_object *object,
484			      const char *key,
485			      struct cachefiles_xattr *auxdata)
486{
487	struct cachefiles_cache *cache;
488	struct dentry *dir, *next = NULL;
489	struct inode *inode;
490	struct path path;
491	unsigned long start;
492	const char *name;
493	int ret, nlen;
494
495	_enter("OBJ%x{%p},OBJ%x,%s,",
496	       parent->fscache.debug_id, parent->dentry,
497	       object->fscache.debug_id, key);
498
499	cache = container_of(parent->fscache.cache,
500			     struct cachefiles_cache, cache);
501	path.mnt = cache->mnt;
502
503	ASSERT(parent->dentry);
504	ASSERT(d_backing_inode(parent->dentry));
505
506	if (!(d_is_dir(parent->dentry))) {
507		// TODO: convert file to dir
508		_leave("looking up in none directory");
509		return -ENOBUFS;
510	}
511
512	dir = dget(parent->dentry);
513
514advance:
515	/* attempt to transit the first directory component */
516	name = key;
517	nlen = strlen(key);
518
519	/* key ends in a double NUL */
520	key = key + nlen + 1;
521	if (!*key)
522		key = NULL;
523
524lookup_again:
525	/* search the current directory for the element name */
526	_debug("lookup '%s'", name);
527
528	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
529
530	start = jiffies;
531	next = lookup_one_len(name, dir, nlen);
532	cachefiles_hist(cachefiles_lookup_histogram, start);
533	if (IS_ERR(next)) {
534		trace_cachefiles_lookup(object, next, NULL);
535		goto lookup_error;
536	}
537
538	inode = d_backing_inode(next);
539	trace_cachefiles_lookup(object, next, inode);
540	_debug("next -> %p %s", next, inode ? "positive" : "negative");
541
542	if (!key)
543		object->new = !inode;
544
545	/* if this element of the path doesn't exist, then the lookup phase
546	 * failed, and we can release any readers in the certain knowledge that
547	 * there's nothing for them to actually read */
548	if (d_is_negative(next))
549		fscache_object_lookup_negative(&object->fscache);
550
551	/* we need to create the object if it's negative */
552	if (key || object->type == FSCACHE_COOKIE_TYPE_INDEX) {
553		/* index objects and intervening tree levels must be subdirs */
554		if (d_is_negative(next)) {
555			ret = cachefiles_has_space(cache, 1, 0);
556			if (ret < 0)
557				goto no_space_error;
558
559			path.dentry = dir;
560			ret = security_path_mkdir(&path, next, 0);
561			if (ret < 0)
562				goto create_error;
563			start = jiffies;
564			ret = vfs_mkdir(d_inode(dir), next, 0);
565			cachefiles_hist(cachefiles_mkdir_histogram, start);
566			if (!key)
567				trace_cachefiles_mkdir(object, next, ret);
568			if (ret < 0)
569				goto create_error;
570
571			if (unlikely(d_unhashed(next))) {
572				dput(next);
573				inode_unlock(d_inode(dir));
574				goto lookup_again;
575			}
576			ASSERT(d_backing_inode(next));
577
578			_debug("mkdir -> %p{%p{ino=%lu}}",
579			       next, d_backing_inode(next), d_backing_inode(next)->i_ino);
580
581		} else if (!d_can_lookup(next)) {
582			pr_err("inode %lu is not a directory\n",
583			       d_backing_inode(next)->i_ino);
584			ret = -ENOBUFS;
585			goto error;
586		}
587
588	} else {
589		/* non-index objects start out life as files */
590		if (d_is_negative(next)) {
591			ret = cachefiles_has_space(cache, 1, 0);
592			if (ret < 0)
593				goto no_space_error;
594
595			path.dentry = dir;
596			ret = security_path_mknod(&path, next, S_IFREG, 0);
597			if (ret < 0)
598				goto create_error;
599			start = jiffies;
600			ret = vfs_create(d_inode(dir), next, S_IFREG, true);
601			cachefiles_hist(cachefiles_create_histogram, start);
602			trace_cachefiles_create(object, next, ret);
603			if (ret < 0)
604				goto create_error;
605
606			ASSERT(d_backing_inode(next));
607
608			_debug("create -> %p{%p{ino=%lu}}",
609			       next, d_backing_inode(next), d_backing_inode(next)->i_ino);
610
611		} else if (!d_can_lookup(next) &&
612			   !d_is_reg(next)
613			   ) {
614			pr_err("inode %lu is not a file or directory\n",
615			       d_backing_inode(next)->i_ino);
616			ret = -ENOBUFS;
617			goto error;
618		}
619	}
620
621	/* process the next component */
622	if (key) {
623		_debug("advance");
624		inode_unlock(d_inode(dir));
625		dput(dir);
626		dir = next;
627		next = NULL;
628		goto advance;
629	}
630
631	/* we've found the object we were looking for */
632	object->dentry = next;
633
634	/* if we've found that the terminal object exists, then we need to
635	 * check its attributes and delete it if it's out of date */
636	if (!object->new) {
637		_debug("validate '%pd'", next);
638
639		ret = cachefiles_check_object_xattr(object, auxdata);
640		if (ret == -ESTALE) {
641			/* delete the object (the deleter drops the directory
642			 * mutex) */
643			object->dentry = NULL;
644
645			ret = cachefiles_bury_object(cache, object, dir, next,
646						     true,
647						     FSCACHE_OBJECT_IS_STALE);
648			dput(next);
649			next = NULL;
650
651			if (ret < 0)
652				goto delete_error;
653
654			_debug("redo lookup");
655			fscache_object_retrying_stale(&object->fscache);
656			goto lookup_again;
657		}
658	}
659
660	/* note that we're now using this object */
661	ret = cachefiles_mark_object_active(cache, object);
662
663	inode_unlock(d_inode(dir));
664	dput(dir);
665	dir = NULL;
666
667	if (ret == -ETIMEDOUT)
668		goto mark_active_timed_out;
669
670	_debug("=== OBTAINED_OBJECT ===");
671
672	if (object->new) {
673		/* attach data to a newly constructed terminal object */
674		ret = cachefiles_set_object_xattr(object, auxdata);
675		if (ret < 0)
676			goto check_error;
677	} else {
678		/* always update the atime on an object we've just looked up
679		 * (this is used to keep track of culling, and atimes are only
680		 * updated by read, write and readdir but not lookup or
681		 * open) */
682		path.dentry = next;
683		touch_atime(&path);
684	}
685
686	/* open a file interface onto a data file */
687	if (object->type != FSCACHE_COOKIE_TYPE_INDEX) {
688		if (d_is_reg(object->dentry)) {
689			const struct address_space_operations *aops;
690
691			ret = -EPERM;
692			aops = d_backing_inode(object->dentry)->i_mapping->a_ops;
693			if (!aops->bmap)
694				goto check_error;
695			if (object->dentry->d_sb->s_blocksize > PAGE_SIZE)
696				goto check_error;
697
698			object->backer = object->dentry;
699		} else {
700			BUG(); // TODO: open file in data-class subdir
701		}
702	}
703
704	object->new = 0;
705	fscache_obtained_object(&object->fscache);
706
707	_leave(" = 0 [%lu]", d_backing_inode(object->dentry)->i_ino);
708	return 0;
709
710no_space_error:
711	fscache_object_mark_killed(&object->fscache, FSCACHE_OBJECT_NO_SPACE);
712create_error:
713	_debug("create error %d", ret);
714	if (ret == -EIO)
715		cachefiles_io_error(cache, "Create/mkdir failed");
716	goto error;
717
718mark_active_timed_out:
719	_debug("mark active timed out");
720	goto release_dentry;
721
722check_error:
723	_debug("check error %d", ret);
724	cachefiles_mark_object_inactive(
725		cache, object, d_backing_inode(object->dentry)->i_blocks);
726release_dentry:
727	dput(object->dentry);
728	object->dentry = NULL;
729	goto error_out;
730
731delete_error:
732	_debug("delete error %d", ret);
733	goto error_out2;
734
735lookup_error:
736	_debug("lookup error %ld", PTR_ERR(next));
737	ret = PTR_ERR(next);
738	if (ret == -EIO)
739		cachefiles_io_error(cache, "Lookup failed");
740	next = NULL;
741error:
742	inode_unlock(d_inode(dir));
743	dput(next);
744error_out2:
745	dput(dir);
746error_out:
747	_leave(" = error %d", -ret);
748	return ret;
749}
750
751/*
752 * get a subdirectory
753 */
754struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
755					struct dentry *dir,
756					const char *dirname)
757{
758	struct dentry *subdir;
759	unsigned long start;
760	struct path path;
761	int ret;
762
763	_enter(",,%s", dirname);
764
765	/* search the current directory for the element name */
766	inode_lock(d_inode(dir));
767
768retry:
769	start = jiffies;
770	subdir = lookup_one_len(dirname, dir, strlen(dirname));
771	cachefiles_hist(cachefiles_lookup_histogram, start);
772	if (IS_ERR(subdir)) {
773		if (PTR_ERR(subdir) == -ENOMEM)
774			goto nomem_d_alloc;
775		goto lookup_error;
776	}
777
778	_debug("subdir -> %p %s",
779	       subdir, d_backing_inode(subdir) ? "positive" : "negative");
780
781	/* we need to create the subdir if it doesn't exist yet */
782	if (d_is_negative(subdir)) {
783		ret = cachefiles_has_space(cache, 1, 0);
784		if (ret < 0)
785			goto mkdir_error;
786
787		_debug("attempt mkdir");
788
789		path.mnt = cache->mnt;
790		path.dentry = dir;
791		ret = security_path_mkdir(&path, subdir, 0700);
792		if (ret < 0)
793			goto mkdir_error;
794		ret = vfs_mkdir(d_inode(dir), subdir, 0700);
795		if (ret < 0)
796			goto mkdir_error;
797
798		if (unlikely(d_unhashed(subdir))) {
799			dput(subdir);
800			goto retry;
801		}
802		ASSERT(d_backing_inode(subdir));
803
804		_debug("mkdir -> %p{%p{ino=%lu}}",
805		       subdir,
806		       d_backing_inode(subdir),
807		       d_backing_inode(subdir)->i_ino);
808	}
809
810	inode_unlock(d_inode(dir));
811
812	/* we need to make sure the subdir is a directory */
813	ASSERT(d_backing_inode(subdir));
814
815	if (!d_can_lookup(subdir)) {
816		pr_err("%s is not a directory\n", dirname);
817		ret = -EIO;
818		goto check_error;
819	}
820
821	ret = -EPERM;
822	if (!(d_backing_inode(subdir)->i_opflags & IOP_XATTR) ||
823	    !d_backing_inode(subdir)->i_op->lookup ||
824	    !d_backing_inode(subdir)->i_op->mkdir ||
825	    !d_backing_inode(subdir)->i_op->create ||
826	    !d_backing_inode(subdir)->i_op->rename ||
827	    !d_backing_inode(subdir)->i_op->rmdir ||
828	    !d_backing_inode(subdir)->i_op->unlink)
829		goto check_error;
830
831	_leave(" = [%lu]", d_backing_inode(subdir)->i_ino);
832	return subdir;
833
834check_error:
835	dput(subdir);
836	_leave(" = %d [check]", ret);
837	return ERR_PTR(ret);
838
839mkdir_error:
840	inode_unlock(d_inode(dir));
841	dput(subdir);
842	pr_err("mkdir %s failed with error %d\n", dirname, ret);
843	return ERR_PTR(ret);
844
845lookup_error:
846	inode_unlock(d_inode(dir));
847	ret = PTR_ERR(subdir);
848	pr_err("Lookup %s failed with error %d\n", dirname, ret);
849	return ERR_PTR(ret);
850
851nomem_d_alloc:
852	inode_unlock(d_inode(dir));
853	_leave(" = -ENOMEM");
854	return ERR_PTR(-ENOMEM);
855}
856
857/*
858 * find out if an object is in use or not
859 * - if finds object and it's not in use:
860 *   - returns a pointer to the object and a reference on it
861 *   - returns with the directory locked
862 */
863static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache,
864					      struct dentry *dir,
865					      char *filename)
866{
867	struct cachefiles_object *object;
868	struct rb_node *_n;
869	struct dentry *victim;
870	unsigned long start;
871	int ret;
872
873	//_enter(",%pd/,%s",
874	//       dir, filename);
875
876	/* look up the victim */
877	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
878
879	start = jiffies;
880	victim = lookup_one_len(filename, dir, strlen(filename));
881	cachefiles_hist(cachefiles_lookup_histogram, start);
882	if (IS_ERR(victim))
883		goto lookup_error;
884
885	//_debug("victim -> %p %s",
886	//       victim, d_backing_inode(victim) ? "positive" : "negative");
887
888	/* if the object is no longer there then we probably retired the object
889	 * at the netfs's request whilst the cull was in progress
890	 */
891	if (d_is_negative(victim)) {
892		inode_unlock(d_inode(dir));
893		dput(victim);
894		_leave(" = -ENOENT [absent]");
895		return ERR_PTR(-ENOENT);
896	}
897
898	/* check to see if we're using this object */
899	read_lock(&cache->active_lock);
900
901	_n = cache->active_nodes.rb_node;
902
903	while (_n) {
904		object = rb_entry(_n, struct cachefiles_object, active_node);
905
906		if (object->dentry > victim)
907			_n = _n->rb_left;
908		else if (object->dentry < victim)
909			_n = _n->rb_right;
910		else
911			goto object_in_use;
912	}
913
914	read_unlock(&cache->active_lock);
915
916	//_leave(" = %p", victim);
917	return victim;
918
919object_in_use:
920	read_unlock(&cache->active_lock);
921	inode_unlock(d_inode(dir));
922	dput(victim);
923	//_leave(" = -EBUSY [in use]");
924	return ERR_PTR(-EBUSY);
925
926lookup_error:
927	inode_unlock(d_inode(dir));
928	ret = PTR_ERR(victim);
929	if (ret == -ENOENT) {
930		/* file or dir now absent - probably retired by netfs */
931		_leave(" = -ESTALE [absent]");
932		return ERR_PTR(-ESTALE);
933	}
934
935	if (ret == -EIO) {
936		cachefiles_io_error(cache, "Lookup failed");
937	} else if (ret != -ENOMEM) {
938		pr_err("Internal error: %d\n", ret);
939		ret = -EIO;
940	}
941
942	_leave(" = %d", ret);
943	return ERR_PTR(ret);
944}
945
946/*
947 * cull an object if it's not in use
948 * - called only by cache manager daemon
949 */
950int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir,
951		    char *filename)
952{
953	struct dentry *victim;
954	int ret;
955
956	_enter(",%pd/,%s", dir, filename);
957
958	victim = cachefiles_check_active(cache, dir, filename);
959	if (IS_ERR(victim))
960		return PTR_ERR(victim);
961
962	_debug("victim -> %p %s",
963	       victim, d_backing_inode(victim) ? "positive" : "negative");
964
965	/* okay... the victim is not being used so we can cull it
966	 * - start by marking it as stale
967	 */
968	_debug("victim is cullable");
969
970	ret = cachefiles_remove_object_xattr(cache, victim);
971	if (ret < 0)
972		goto error_unlock;
973
974	/*  actually remove the victim (drops the dir mutex) */
975	_debug("bury");
976
977	ret = cachefiles_bury_object(cache, NULL, dir, victim, false,
978				     FSCACHE_OBJECT_WAS_CULLED);
979	if (ret < 0)
980		goto error;
981
982	dput(victim);
983	_leave(" = 0");
984	return 0;
985
986error_unlock:
987	inode_unlock(d_inode(dir));
988error:
989	dput(victim);
990	if (ret == -ENOENT) {
991		/* file or dir now absent - probably retired by netfs */
992		_leave(" = -ESTALE [absent]");
993		return -ESTALE;
994	}
995
996	if (ret != -ENOMEM) {
997		pr_err("Internal error: %d\n", ret);
998		ret = -EIO;
999	}
1000
1001	_leave(" = %d", ret);
1002	return ret;
1003}
1004
1005/*
1006 * find out if an object is in use or not
1007 * - called only by cache manager daemon
1008 * - returns -EBUSY or 0 to indicate whether an object is in use or not
1009 */
1010int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir,
1011			    char *filename)
1012{
1013	struct dentry *victim;
1014
1015	//_enter(",%pd/,%s",
1016	//       dir, filename);
1017
1018	victim = cachefiles_check_active(cache, dir, filename);
1019	if (IS_ERR(victim))
1020		return PTR_ERR(victim);
1021
1022	inode_unlock(d_inode(dir));
1023	dput(victim);
1024	//_leave(" = 0");
1025	return 0;
1026}
1027