xref: /kernel/linux/linux-5.10/fs/erofs/zdata.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * Copyright (C) 2018 HUAWEI, Inc.
4 *             https://www.huawei.com/
5 * Created by Gao Xiang <gaoxiang25@huawei.com>
6 */
7#include "zdata.h"
8#include "compress.h"
9#include <linux/prefetch.h>
10
11#include <trace/events/erofs.h>
12
13/*
14 * a compressed_pages[] placeholder in order to avoid
15 * being filled with file pages for in-place decompression.
16 */
17#define PAGE_UNALLOCATED     ((void *)0x5F0E4B1D)
18
19/* how to allocate cached pages for a pcluster */
20enum z_erofs_cache_alloctype {
21	DONTALLOC,	/* don't allocate any cached pages */
22	DELAYEDALLOC,	/* delayed allocation (at the time of submitting io) */
23};
24
25/*
26 * tagged pointer with 1-bit tag for all compressed pages
27 * tag 0 - the page is just found with an extra page reference
28 */
29typedef tagptr1_t compressed_page_t;
30
31#define tag_compressed_page_justfound(page) \
32	tagptr_fold(compressed_page_t, page, 1)
33
34static struct workqueue_struct *z_erofs_workqueue __read_mostly;
35static struct kmem_cache *pcluster_cachep __read_mostly;
36
37void z_erofs_exit_zip_subsystem(void)
38{
39	destroy_workqueue(z_erofs_workqueue);
40	kmem_cache_destroy(pcluster_cachep);
41}
42
43static inline int z_erofs_init_workqueue(void)
44{
45	const unsigned int onlinecpus = num_possible_cpus();
46
47	/*
48	 * no need to spawn too many threads, limiting threads could minimum
49	 * scheduling overhead, perhaps per-CPU threads should be better?
50	 */
51	z_erofs_workqueue = alloc_workqueue("erofs_unzipd",
52					    WQ_UNBOUND | WQ_HIGHPRI,
53					    onlinecpus + onlinecpus / 4);
54	return z_erofs_workqueue ? 0 : -ENOMEM;
55}
56
57static void z_erofs_pcluster_init_once(void *ptr)
58{
59	struct z_erofs_pcluster *pcl = ptr;
60	struct z_erofs_collection *cl = z_erofs_primarycollection(pcl);
61	unsigned int i;
62
63	mutex_init(&cl->lock);
64	cl->nr_pages = 0;
65	cl->vcnt = 0;
66	for (i = 0; i < Z_EROFS_CLUSTER_MAX_PAGES; ++i)
67		pcl->compressed_pages[i] = NULL;
68}
69
70int __init z_erofs_init_zip_subsystem(void)
71{
72	pcluster_cachep = kmem_cache_create("erofs_compress",
73					    Z_EROFS_WORKGROUP_SIZE, 0,
74					    SLAB_RECLAIM_ACCOUNT,
75					    z_erofs_pcluster_init_once);
76	if (pcluster_cachep) {
77		if (!z_erofs_init_workqueue())
78			return 0;
79
80		kmem_cache_destroy(pcluster_cachep);
81	}
82	return -ENOMEM;
83}
84
85enum z_erofs_collectmode {
86	COLLECT_SECONDARY,
87	COLLECT_PRIMARY,
88	/*
89	 * The current collection was the tail of an exist chain, in addition
90	 * that the previous processed chained collections are all decided to
91	 * be hooked up to it.
92	 * A new chain will be created for the remaining collections which are
93	 * not processed yet, therefore different from COLLECT_PRIMARY_FOLLOWED,
94	 * the next collection cannot reuse the whole page safely in
95	 * the following scenario:
96	 *  ________________________________________________________________
97	 * |      tail (partial) page     |       head (partial) page       |
98	 * |   (belongs to the next cl)   |   (belongs to the current cl)   |
99	 * |_______PRIMARY_FOLLOWED_______|________PRIMARY_HOOKED___________|
100	 */
101	COLLECT_PRIMARY_HOOKED,
102	COLLECT_PRIMARY_FOLLOWED_NOINPLACE,
103	/*
104	 * The current collection has been linked with the owned chain, and
105	 * could also be linked with the remaining collections, which means
106	 * if the processing page is the tail page of the collection, thus
107	 * the current collection can safely use the whole page (since
108	 * the previous collection is under control) for in-place I/O, as
109	 * illustrated below:
110	 *  ________________________________________________________________
111	 * |  tail (partial) page |          head (partial) page           |
112	 * |  (of the current cl) |      (of the previous collection)      |
113	 * |  PRIMARY_FOLLOWED or |                                        |
114	 * |_____PRIMARY_HOOKED___|____________PRIMARY_FOLLOWED____________|
115	 *
116	 * [  (*) the above page can be used as inplace I/O.               ]
117	 */
118	COLLECT_PRIMARY_FOLLOWED,
119};
120
121struct z_erofs_collector {
122	struct z_erofs_pagevec_ctor vector;
123
124	struct z_erofs_pcluster *pcl, *tailpcl;
125	struct z_erofs_collection *cl;
126	struct page **compressedpages;
127	z_erofs_next_pcluster_t owned_head;
128
129	enum z_erofs_collectmode mode;
130};
131
132struct z_erofs_decompress_frontend {
133	struct inode *const inode;
134
135	struct z_erofs_collector clt;
136	struct erofs_map_blocks map;
137
138	bool readahead;
139	/* used for applying cache strategy on the fly */
140	bool backmost;
141	erofs_off_t headoffset;
142};
143
144#define COLLECTOR_INIT() { \
145	.owned_head = Z_EROFS_PCLUSTER_TAIL, \
146	.mode = COLLECT_PRIMARY_FOLLOWED }
147
148#define DECOMPRESS_FRONTEND_INIT(__i) { \
149	.inode = __i, .clt = COLLECTOR_INIT(), \
150	.backmost = true, }
151
152static struct page *z_pagemap_global[Z_EROFS_VMAP_GLOBAL_PAGES];
153static DEFINE_MUTEX(z_pagemap_global_lock);
154
155static void preload_compressed_pages(struct z_erofs_collector *clt,
156				     struct address_space *mc,
157				     enum z_erofs_cache_alloctype type)
158{
159	const struct z_erofs_pcluster *pcl = clt->pcl;
160	const unsigned int clusterpages = BIT(pcl->clusterbits);
161	struct page **pages = clt->compressedpages;
162	pgoff_t index = pcl->obj.index + (pages - pcl->compressed_pages);
163	bool standalone = true;
164
165	if (clt->mode < COLLECT_PRIMARY_FOLLOWED)
166		return;
167
168	for (; pages < pcl->compressed_pages + clusterpages; ++pages) {
169		struct page *page;
170		compressed_page_t t;
171
172		/* the compressed page was loaded before */
173		if (READ_ONCE(*pages))
174			continue;
175
176		page = find_get_page(mc, index);
177
178		if (page) {
179			t = tag_compressed_page_justfound(page);
180		} else if (type == DELAYEDALLOC) {
181			t = tagptr_init(compressed_page_t, PAGE_UNALLOCATED);
182		} else {	/* DONTALLOC */
183			if (standalone)
184				clt->compressedpages = pages;
185			standalone = false;
186			continue;
187		}
188
189		if (!cmpxchg_relaxed(pages, NULL, tagptr_cast_ptr(t)))
190			continue;
191
192		if (page)
193			put_page(page);
194	}
195
196	if (standalone)		/* downgrade to PRIMARY_FOLLOWED_NOINPLACE */
197		clt->mode = COLLECT_PRIMARY_FOLLOWED_NOINPLACE;
198}
199
200/* called by erofs_shrinker to get rid of all compressed_pages */
201int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
202				       struct erofs_workgroup *grp)
203{
204	struct z_erofs_pcluster *const pcl =
205		container_of(grp, struct z_erofs_pcluster, obj);
206	struct address_space *const mapping = MNGD_MAPPING(sbi);
207	const unsigned int clusterpages = BIT(pcl->clusterbits);
208	int i;
209
210	/*
211	 * refcount of workgroup is now freezed as 1,
212	 * therefore no need to worry about available decompression users.
213	 */
214	for (i = 0; i < clusterpages; ++i) {
215		struct page *page = pcl->compressed_pages[i];
216
217		if (!page)
218			continue;
219
220		/* block other users from reclaiming or migrating the page */
221		if (!trylock_page(page))
222			return -EBUSY;
223
224		if (page->mapping != mapping)
225			continue;
226
227		/* barrier is implied in the following 'unlock_page' */
228		WRITE_ONCE(pcl->compressed_pages[i], NULL);
229		set_page_private(page, 0);
230		ClearPagePrivate(page);
231
232		unlock_page(page);
233		put_page(page);
234	}
235	return 0;
236}
237
238int erofs_try_to_free_cached_page(struct address_space *mapping,
239				  struct page *page)
240{
241	struct z_erofs_pcluster *const pcl = (void *)page_private(page);
242	const unsigned int clusterpages = BIT(pcl->clusterbits);
243	int ret = 0;	/* 0 - busy */
244
245	if (erofs_workgroup_try_to_freeze(&pcl->obj, 1)) {
246		unsigned int i;
247
248		for (i = 0; i < clusterpages; ++i) {
249			if (pcl->compressed_pages[i] == page) {
250				WRITE_ONCE(pcl->compressed_pages[i], NULL);
251				ret = 1;
252				break;
253			}
254		}
255		erofs_workgroup_unfreeze(&pcl->obj, 1);
256
257		if (ret) {
258			ClearPagePrivate(page);
259			put_page(page);
260		}
261	}
262	return ret;
263}
264
265/* page_type must be Z_EROFS_PAGE_TYPE_EXCLUSIVE */
266static inline bool z_erofs_try_inplace_io(struct z_erofs_collector *clt,
267					  struct page *page)
268{
269	struct z_erofs_pcluster *const pcl = clt->pcl;
270	const unsigned int clusterpages = BIT(pcl->clusterbits);
271
272	while (clt->compressedpages < pcl->compressed_pages + clusterpages) {
273		if (!cmpxchg(clt->compressedpages++, NULL, page))
274			return true;
275	}
276	return false;
277}
278
279/* callers must be with collection lock held */
280static int z_erofs_attach_page(struct z_erofs_collector *clt,
281			       struct page *page, enum z_erofs_page_type type,
282			       bool pvec_safereuse)
283{
284	int ret;
285
286	/* give priority for inplaceio */
287	if (clt->mode >= COLLECT_PRIMARY &&
288	    type == Z_EROFS_PAGE_TYPE_EXCLUSIVE &&
289	    z_erofs_try_inplace_io(clt, page))
290		return 0;
291
292	ret = z_erofs_pagevec_enqueue(&clt->vector, page, type,
293				      pvec_safereuse);
294	clt->cl->vcnt += (unsigned int)ret;
295	return ret ? 0 : -EAGAIN;
296}
297
298static enum z_erofs_collectmode
299try_to_claim_pcluster(struct z_erofs_pcluster *pcl,
300		      z_erofs_next_pcluster_t *owned_head)
301{
302	/* let's claim these following types of pclusters */
303retry:
304	if (pcl->next == Z_EROFS_PCLUSTER_NIL) {
305		/* type 1, nil pcluster */
306		if (cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_NIL,
307			    *owned_head) != Z_EROFS_PCLUSTER_NIL)
308			goto retry;
309
310		*owned_head = &pcl->next;
311		/* lucky, I am the followee :) */
312		return COLLECT_PRIMARY_FOLLOWED;
313	} else if (pcl->next == Z_EROFS_PCLUSTER_TAIL) {
314		/*
315		 * type 2, link to the end of a existing open chain,
316		 * be careful that its submission itself is governed
317		 * by the original owned chain.
318		 */
319		if (cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL,
320			    *owned_head) != Z_EROFS_PCLUSTER_TAIL)
321			goto retry;
322		*owned_head = Z_EROFS_PCLUSTER_TAIL;
323		return COLLECT_PRIMARY_HOOKED;
324	}
325	return COLLECT_PRIMARY;	/* :( better luck next time */
326}
327
328static int z_erofs_lookup_collection(struct z_erofs_collector *clt,
329				     struct inode *inode,
330				     struct erofs_map_blocks *map)
331{
332	struct z_erofs_pcluster *pcl = clt->pcl;
333	struct z_erofs_collection *cl;
334	unsigned int length;
335
336	/* to avoid unexpected loop formed by corrupted images */
337	if (clt->owned_head == &pcl->next || pcl == clt->tailpcl) {
338		DBG_BUGON(1);
339		return -EFSCORRUPTED;
340	}
341
342	cl = z_erofs_primarycollection(pcl);
343	if (cl->pageofs != (map->m_la & ~PAGE_MASK)) {
344		DBG_BUGON(1);
345		return -EFSCORRUPTED;
346	}
347
348	length = READ_ONCE(pcl->length);
349	if (length & Z_EROFS_PCLUSTER_FULL_LENGTH) {
350		if ((map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) > length) {
351			DBG_BUGON(1);
352			return -EFSCORRUPTED;
353		}
354	} else {
355		unsigned int llen = map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT;
356
357		if (map->m_flags & EROFS_MAP_FULL_MAPPED)
358			llen |= Z_EROFS_PCLUSTER_FULL_LENGTH;
359
360		while (llen > length &&
361		       length != cmpxchg_relaxed(&pcl->length, length, llen)) {
362			cpu_relax();
363			length = READ_ONCE(pcl->length);
364		}
365	}
366	mutex_lock(&cl->lock);
367	/* used to check tail merging loop due to corrupted images */
368	if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL)
369		clt->tailpcl = pcl;
370	clt->mode = try_to_claim_pcluster(pcl, &clt->owned_head);
371	/* clean tailpcl if the current owned_head is Z_EROFS_PCLUSTER_TAIL */
372	if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL)
373		clt->tailpcl = NULL;
374	clt->cl = cl;
375	return 0;
376}
377
378static int z_erofs_register_collection(struct z_erofs_collector *clt,
379				       struct inode *inode,
380				       struct erofs_map_blocks *map)
381{
382	struct z_erofs_pcluster *pcl;
383	struct z_erofs_collection *cl;
384	struct erofs_workgroup *grp;
385	int err;
386
387	/* no available workgroup, let's allocate one */
388	pcl = kmem_cache_alloc(pcluster_cachep, GFP_NOFS);
389	if (!pcl)
390		return -ENOMEM;
391
392	atomic_set(&pcl->obj.refcount, 1);
393	pcl->obj.index = map->m_pa >> PAGE_SHIFT;
394
395	pcl->length = (map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) |
396		(map->m_flags & EROFS_MAP_FULL_MAPPED ?
397			Z_EROFS_PCLUSTER_FULL_LENGTH : 0);
398
399	if (map->m_flags & EROFS_MAP_ZIPPED)
400		pcl->algorithmformat = Z_EROFS_COMPRESSION_LZ4;
401	else
402		pcl->algorithmformat = Z_EROFS_COMPRESSION_SHIFTED;
403
404	pcl->clusterbits = EROFS_I(inode)->z_physical_clusterbits[0];
405	pcl->clusterbits -= PAGE_SHIFT;
406
407	/* new pclusters should be claimed as type 1, primary and followed */
408	pcl->next = clt->owned_head;
409	clt->mode = COLLECT_PRIMARY_FOLLOWED;
410
411	cl = z_erofs_primarycollection(pcl);
412
413	/* must be cleaned before freeing to slab */
414	DBG_BUGON(cl->nr_pages);
415	DBG_BUGON(cl->vcnt);
416
417	cl->pageofs = map->m_la & ~PAGE_MASK;
418
419	/*
420	 * lock all primary followed works before visible to others
421	 * and mutex_trylock *never* fails for a new pcluster.
422	 */
423	DBG_BUGON(!mutex_trylock(&cl->lock));
424
425	grp = erofs_insert_workgroup(inode->i_sb, &pcl->obj);
426	if (IS_ERR(grp)) {
427		err = PTR_ERR(grp);
428		goto err_out;
429	}
430
431	if (grp != &pcl->obj) {
432		clt->pcl = container_of(grp, struct z_erofs_pcluster, obj);
433		err = -EEXIST;
434		goto err_out;
435	}
436	/* used to check tail merging loop due to corrupted images */
437	if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL)
438		clt->tailpcl = pcl;
439	clt->owned_head = &pcl->next;
440	clt->pcl = pcl;
441	clt->cl = cl;
442	return 0;
443
444err_out:
445	mutex_unlock(&cl->lock);
446	kmem_cache_free(pcluster_cachep, pcl);
447	return err;
448}
449
450static int z_erofs_collector_begin(struct z_erofs_collector *clt,
451				   struct inode *inode,
452				   struct erofs_map_blocks *map)
453{
454	struct erofs_workgroup *grp;
455	int ret;
456
457	DBG_BUGON(clt->cl);
458
459	/* must be Z_EROFS_PCLUSTER_TAIL or pointed to previous collection */
460	DBG_BUGON(clt->owned_head == Z_EROFS_PCLUSTER_NIL);
461	DBG_BUGON(clt->owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
462
463	if (!PAGE_ALIGNED(map->m_pa)) {
464		DBG_BUGON(1);
465		return -EINVAL;
466	}
467
468	grp = erofs_find_workgroup(inode->i_sb, map->m_pa >> PAGE_SHIFT);
469	if (grp) {
470		clt->pcl = container_of(grp, struct z_erofs_pcluster, obj);
471	} else {
472		ret = z_erofs_register_collection(clt, inode, map);
473
474		if (!ret)
475			goto out;
476		if (ret != -EEXIST)
477			return ret;
478	}
479
480	ret = z_erofs_lookup_collection(clt, inode, map);
481	if (ret) {
482		erofs_workgroup_put(&clt->pcl->obj);
483		return ret;
484	}
485
486out:
487	z_erofs_pagevec_ctor_init(&clt->vector, Z_EROFS_NR_INLINE_PAGEVECS,
488				  clt->cl->pagevec, clt->cl->vcnt);
489
490	clt->compressedpages = clt->pcl->compressed_pages;
491	if (clt->mode <= COLLECT_PRIMARY) /* cannot do in-place I/O */
492		clt->compressedpages += Z_EROFS_CLUSTER_MAX_PAGES;
493	return 0;
494}
495
496/*
497 * keep in mind that no referenced pclusters will be freed
498 * only after a RCU grace period.
499 */
500static void z_erofs_rcu_callback(struct rcu_head *head)
501{
502	struct z_erofs_collection *const cl =
503		container_of(head, struct z_erofs_collection, rcu);
504
505	kmem_cache_free(pcluster_cachep,
506			container_of(cl, struct z_erofs_pcluster,
507				     primary_collection));
508}
509
510void erofs_workgroup_free_rcu(struct erofs_workgroup *grp)
511{
512	struct z_erofs_pcluster *const pcl =
513		container_of(grp, struct z_erofs_pcluster, obj);
514	struct z_erofs_collection *const cl = z_erofs_primarycollection(pcl);
515
516	call_rcu(&cl->rcu, z_erofs_rcu_callback);
517}
518
519static void z_erofs_collection_put(struct z_erofs_collection *cl)
520{
521	struct z_erofs_pcluster *const pcl =
522		container_of(cl, struct z_erofs_pcluster, primary_collection);
523
524	erofs_workgroup_put(&pcl->obj);
525}
526
527static bool z_erofs_collector_end(struct z_erofs_collector *clt)
528{
529	struct z_erofs_collection *cl = clt->cl;
530
531	if (!cl)
532		return false;
533
534	z_erofs_pagevec_ctor_exit(&clt->vector, false);
535	mutex_unlock(&cl->lock);
536
537	/*
538	 * if all pending pages are added, don't hold its reference
539	 * any longer if the pcluster isn't hosted by ourselves.
540	 */
541	if (clt->mode < COLLECT_PRIMARY_FOLLOWED_NOINPLACE)
542		z_erofs_collection_put(cl);
543
544	clt->cl = NULL;
545	return true;
546}
547
548static bool should_alloc_managed_pages(struct z_erofs_decompress_frontend *fe,
549				       unsigned int cachestrategy,
550				       erofs_off_t la)
551{
552	if (cachestrategy <= EROFS_ZIP_CACHE_DISABLED)
553		return false;
554
555	if (fe->backmost)
556		return true;
557
558	return cachestrategy >= EROFS_ZIP_CACHE_READAROUND &&
559		la < fe->headoffset;
560}
561
562static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
563				struct page *page)
564{
565	struct inode *const inode = fe->inode;
566	struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
567	struct erofs_map_blocks *const map = &fe->map;
568	struct z_erofs_collector *const clt = &fe->clt;
569	const loff_t offset = page_offset(page);
570	bool tight = true;
571
572	enum z_erofs_cache_alloctype cache_strategy;
573	enum z_erofs_page_type page_type;
574	unsigned int cur, end, spiltted, index;
575	int err = 0;
576
577	/* register locked file pages as online pages in pack */
578	z_erofs_onlinepage_init(page);
579
580	spiltted = 0;
581	end = PAGE_SIZE;
582repeat:
583	cur = end - 1;
584
585	/* lucky, within the range of the current map_blocks */
586	if (offset + cur >= map->m_la &&
587	    offset + cur < map->m_la + map->m_llen) {
588		/* didn't get a valid collection previously (very rare) */
589		if (!clt->cl)
590			goto restart_now;
591		goto hitted;
592	}
593
594	/* go ahead the next map_blocks */
595	erofs_dbg("%s: [out-of-range] pos %llu", __func__, offset + cur);
596
597	if (z_erofs_collector_end(clt))
598		fe->backmost = false;
599
600	map->m_la = offset + cur;
601	map->m_llen = 0;
602	err = z_erofs_map_blocks_iter(inode, map, 0);
603	if (err)
604		goto err_out;
605
606restart_now:
607	if (!(map->m_flags & EROFS_MAP_MAPPED))
608		goto hitted;
609
610	err = z_erofs_collector_begin(clt, inode, map);
611	if (err)
612		goto err_out;
613
614	/* preload all compressed pages (maybe downgrade role if necessary) */
615	if (should_alloc_managed_pages(fe, sbi->ctx.cache_strategy, map->m_la))
616		cache_strategy = DELAYEDALLOC;
617	else
618		cache_strategy = DONTALLOC;
619
620	preload_compressed_pages(clt, MNGD_MAPPING(sbi), cache_strategy);
621
622hitted:
623	/*
624	 * Ensure the current partial page belongs to this submit chain rather
625	 * than other concurrent submit chains or the noio(bypass) chain since
626	 * those chains are handled asynchronously thus the page cannot be used
627	 * for inplace I/O or pagevec (should be processed in strict order.)
628	 */
629	tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED &&
630		  clt->mode != COLLECT_PRIMARY_FOLLOWED_NOINPLACE);
631
632	cur = end - min_t(erofs_off_t, offset + end - map->m_la, end);
633	if (!(map->m_flags & EROFS_MAP_MAPPED)) {
634		zero_user_segment(page, cur, end);
635		++spiltted;
636		tight = false;
637		goto next_part;
638	}
639
640	/* let's derive page type */
641	page_type = cur ? Z_EROFS_VLE_PAGE_TYPE_HEAD :
642		(!spiltted ? Z_EROFS_PAGE_TYPE_EXCLUSIVE :
643			(tight ? Z_EROFS_PAGE_TYPE_EXCLUSIVE :
644				Z_EROFS_VLE_PAGE_TYPE_TAIL_SHARED));
645
646	if (cur)
647		tight &= (clt->mode >= COLLECT_PRIMARY_FOLLOWED);
648
649retry:
650	err = z_erofs_attach_page(clt, page, page_type,
651				  clt->mode >= COLLECT_PRIMARY_FOLLOWED);
652	/* should allocate an additional staging page for pagevec */
653	if (err == -EAGAIN) {
654		struct page *const newpage =
655				alloc_page(GFP_NOFS | __GFP_NOFAIL);
656
657		newpage->mapping = Z_EROFS_MAPPING_STAGING;
658		err = z_erofs_attach_page(clt, newpage,
659					  Z_EROFS_PAGE_TYPE_EXCLUSIVE, true);
660		if (!err)
661			goto retry;
662	}
663
664	if (err)
665		goto err_out;
666
667	index = page->index - (map->m_la >> PAGE_SHIFT);
668
669	z_erofs_onlinepage_fixup(page, index, true);
670
671	/* bump up the number of spiltted parts of a page */
672	++spiltted;
673	/* also update nr_pages */
674	clt->cl->nr_pages = max_t(pgoff_t, clt->cl->nr_pages, index + 1);
675next_part:
676	/* can be used for verification */
677	map->m_llen = offset + cur - map->m_la;
678
679	end = cur;
680	if (end > 0)
681		goto repeat;
682
683out:
684	z_erofs_onlinepage_endio(page);
685
686	erofs_dbg("%s, finish page: %pK spiltted: %u map->m_llen %llu",
687		  __func__, page, spiltted, map->m_llen);
688	return err;
689
690	/* if some error occurred while processing this page */
691err_out:
692	SetPageError(page);
693	goto out;
694}
695
696static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
697				       bool sync, int bios)
698{
699	/* wake up the caller thread for sync decompression */
700	if (sync) {
701		unsigned long flags;
702
703		spin_lock_irqsave(&io->u.wait.lock, flags);
704		if (!atomic_add_return(bios, &io->pending_bios))
705			wake_up_locked(&io->u.wait);
706		spin_unlock_irqrestore(&io->u.wait.lock, flags);
707		return;
708	}
709
710	if (!atomic_add_return(bios, &io->pending_bios))
711		queue_work(z_erofs_workqueue, &io->u.work);
712}
713
714static void z_erofs_decompressqueue_endio(struct bio *bio)
715{
716	tagptr1_t t = tagptr_init(tagptr1_t, bio->bi_private);
717	struct z_erofs_decompressqueue *q = tagptr_unfold_ptr(t);
718	blk_status_t err = bio->bi_status;
719	struct bio_vec *bvec;
720	struct bvec_iter_all iter_all;
721
722	bio_for_each_segment_all(bvec, bio, iter_all) {
723		struct page *page = bvec->bv_page;
724
725		DBG_BUGON(PageUptodate(page));
726		DBG_BUGON(!page->mapping);
727
728		if (err)
729			SetPageError(page);
730
731		if (erofs_page_is_managed(EROFS_SB(q->sb), page)) {
732			if (!err)
733				SetPageUptodate(page);
734			unlock_page(page);
735		}
736	}
737	z_erofs_decompress_kickoff(q, tagptr_unfold_tags(t), -1);
738	bio_put(bio);
739}
740
741static int z_erofs_decompress_pcluster(struct super_block *sb,
742				       struct z_erofs_pcluster *pcl,
743				       struct list_head *pagepool)
744{
745	struct erofs_sb_info *const sbi = EROFS_SB(sb);
746	const unsigned int clusterpages = BIT(pcl->clusterbits);
747	struct z_erofs_pagevec_ctor ctor;
748	unsigned int i, outputsize, llen, nr_pages;
749	struct page *pages_onstack[Z_EROFS_VMAP_ONSTACK_PAGES];
750	struct page **pages, **compressed_pages, *page;
751
752	enum z_erofs_page_type page_type;
753	bool overlapped, partial;
754	struct z_erofs_collection *cl;
755	int err;
756
757	might_sleep();
758	cl = z_erofs_primarycollection(pcl);
759	DBG_BUGON(!READ_ONCE(cl->nr_pages));
760
761	mutex_lock(&cl->lock);
762	nr_pages = cl->nr_pages;
763
764	if (nr_pages <= Z_EROFS_VMAP_ONSTACK_PAGES) {
765		pages = pages_onstack;
766	} else if (nr_pages <= Z_EROFS_VMAP_GLOBAL_PAGES &&
767		   mutex_trylock(&z_pagemap_global_lock)) {
768		pages = z_pagemap_global;
769	} else {
770		gfp_t gfp_flags = GFP_KERNEL;
771
772		if (nr_pages > Z_EROFS_VMAP_GLOBAL_PAGES)
773			gfp_flags |= __GFP_NOFAIL;
774
775		pages = kvmalloc_array(nr_pages, sizeof(struct page *),
776				       gfp_flags);
777
778		/* fallback to global pagemap for the lowmem scenario */
779		if (!pages) {
780			mutex_lock(&z_pagemap_global_lock);
781			pages = z_pagemap_global;
782		}
783	}
784
785	for (i = 0; i < nr_pages; ++i)
786		pages[i] = NULL;
787
788	err = 0;
789	z_erofs_pagevec_ctor_init(&ctor, Z_EROFS_NR_INLINE_PAGEVECS,
790				  cl->pagevec, 0);
791
792	for (i = 0; i < cl->vcnt; ++i) {
793		unsigned int pagenr;
794
795		page = z_erofs_pagevec_dequeue(&ctor, &page_type);
796
797		/* all pages in pagevec ought to be valid */
798		DBG_BUGON(!page);
799		DBG_BUGON(!page->mapping);
800
801		if (z_erofs_put_stagingpage(pagepool, page))
802			continue;
803
804		if (page_type == Z_EROFS_VLE_PAGE_TYPE_HEAD)
805			pagenr = 0;
806		else
807			pagenr = z_erofs_onlinepage_index(page);
808
809		DBG_BUGON(pagenr >= nr_pages);
810
811		/*
812		 * currently EROFS doesn't support multiref(dedup),
813		 * so here erroring out one multiref page.
814		 */
815		if (pages[pagenr]) {
816			DBG_BUGON(1);
817			SetPageError(pages[pagenr]);
818			z_erofs_onlinepage_endio(pages[pagenr]);
819			err = -EFSCORRUPTED;
820		}
821		pages[pagenr] = page;
822	}
823	z_erofs_pagevec_ctor_exit(&ctor, true);
824
825	overlapped = false;
826	compressed_pages = pcl->compressed_pages;
827
828	for (i = 0; i < clusterpages; ++i) {
829		unsigned int pagenr;
830
831		page = compressed_pages[i];
832
833		/* all compressed pages ought to be valid */
834		DBG_BUGON(!page);
835		DBG_BUGON(!page->mapping);
836
837		if (!z_erofs_page_is_staging(page)) {
838			if (erofs_page_is_managed(sbi, page)) {
839				if (!PageUptodate(page))
840					err = -EIO;
841				continue;
842			}
843
844			/*
845			 * only if non-head page can be selected
846			 * for inplace decompression
847			 */
848			pagenr = z_erofs_onlinepage_index(page);
849
850			DBG_BUGON(pagenr >= nr_pages);
851			if (pages[pagenr]) {
852				DBG_BUGON(1);
853				SetPageError(pages[pagenr]);
854				z_erofs_onlinepage_endio(pages[pagenr]);
855				err = -EFSCORRUPTED;
856			}
857			pages[pagenr] = page;
858
859			overlapped = true;
860		}
861
862		/* PG_error needs checking for inplaced and staging pages */
863		if (PageError(page)) {
864			DBG_BUGON(PageUptodate(page));
865			err = -EIO;
866		}
867	}
868
869	if (err)
870		goto out;
871
872	llen = pcl->length >> Z_EROFS_PCLUSTER_LENGTH_BIT;
873	if (nr_pages << PAGE_SHIFT >= cl->pageofs + llen) {
874		outputsize = llen;
875		partial = !(pcl->length & Z_EROFS_PCLUSTER_FULL_LENGTH);
876	} else {
877		outputsize = (nr_pages << PAGE_SHIFT) - cl->pageofs;
878		partial = true;
879	}
880
881	err = z_erofs_decompress(&(struct z_erofs_decompress_req) {
882					.sb = sb,
883					.in = compressed_pages,
884					.out = pages,
885					.pageofs_out = cl->pageofs,
886					.inputsize = PAGE_SIZE,
887					.outputsize = outputsize,
888					.alg = pcl->algorithmformat,
889					.inplace_io = overlapped,
890					.partial_decoding = partial
891				 }, pagepool);
892
893out:
894	/* must handle all compressed pages before endding pages */
895	for (i = 0; i < clusterpages; ++i) {
896		page = compressed_pages[i];
897
898		if (erofs_page_is_managed(sbi, page))
899			continue;
900
901		/* recycle all individual staging pages */
902		(void)z_erofs_put_stagingpage(pagepool, page);
903
904		WRITE_ONCE(compressed_pages[i], NULL);
905	}
906
907	for (i = 0; i < nr_pages; ++i) {
908		page = pages[i];
909		if (!page)
910			continue;
911
912		DBG_BUGON(!page->mapping);
913
914		/* recycle all individual staging pages */
915		if (z_erofs_put_stagingpage(pagepool, page))
916			continue;
917
918		if (err < 0)
919			SetPageError(page);
920
921		z_erofs_onlinepage_endio(page);
922	}
923
924	if (pages == z_pagemap_global)
925		mutex_unlock(&z_pagemap_global_lock);
926	else if (pages != pages_onstack)
927		kvfree(pages);
928
929	cl->nr_pages = 0;
930	cl->vcnt = 0;
931
932	/* all cl locks MUST be taken before the following line */
933	WRITE_ONCE(pcl->next, Z_EROFS_PCLUSTER_NIL);
934
935	/* all cl locks SHOULD be released right now */
936	mutex_unlock(&cl->lock);
937
938	z_erofs_collection_put(cl);
939	return err;
940}
941
942static void z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io,
943				     struct list_head *pagepool)
944{
945	z_erofs_next_pcluster_t owned = io->head;
946
947	while (owned != Z_EROFS_PCLUSTER_TAIL_CLOSED) {
948		struct z_erofs_pcluster *pcl;
949
950		/* no possible that 'owned' equals Z_EROFS_WORK_TPTR_TAIL */
951		DBG_BUGON(owned == Z_EROFS_PCLUSTER_TAIL);
952
953		/* no possible that 'owned' equals NULL */
954		DBG_BUGON(owned == Z_EROFS_PCLUSTER_NIL);
955
956		pcl = container_of(owned, struct z_erofs_pcluster, next);
957		owned = READ_ONCE(pcl->next);
958
959		z_erofs_decompress_pcluster(io->sb, pcl, pagepool);
960	}
961}
962
963static void z_erofs_decompressqueue_work(struct work_struct *work)
964{
965	struct z_erofs_decompressqueue *bgq =
966		container_of(work, struct z_erofs_decompressqueue, u.work);
967	LIST_HEAD(pagepool);
968
969	DBG_BUGON(bgq->head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
970	z_erofs_decompress_queue(bgq, &pagepool);
971
972	put_pages_list(&pagepool);
973	kvfree(bgq);
974}
975
976static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl,
977					       unsigned int nr,
978					       struct list_head *pagepool,
979					       struct address_space *mc,
980					       gfp_t gfp)
981{
982	const pgoff_t index = pcl->obj.index;
983	bool tocache = false;
984
985	struct address_space *mapping;
986	struct page *oldpage, *page;
987
988	compressed_page_t t;
989	int justfound;
990
991repeat:
992	page = READ_ONCE(pcl->compressed_pages[nr]);
993	oldpage = page;
994
995	if (!page)
996		goto out_allocpage;
997
998	/*
999	 * the cached page has not been allocated and
1000	 * an placeholder is out there, prepare it now.
1001	 */
1002	if (page == PAGE_UNALLOCATED) {
1003		tocache = true;
1004		goto out_allocpage;
1005	}
1006
1007	/* process the target tagged pointer */
1008	t = tagptr_init(compressed_page_t, page);
1009	justfound = tagptr_unfold_tags(t);
1010	page = tagptr_unfold_ptr(t);
1011
1012	mapping = READ_ONCE(page->mapping);
1013
1014	/*
1015	 * unmanaged (file) pages are all locked solidly,
1016	 * therefore it is impossible for `mapping' to be NULL.
1017	 */
1018	if (mapping && mapping != mc)
1019		/* ought to be unmanaged pages */
1020		goto out;
1021
1022	lock_page(page);
1023
1024	/* only true if page reclaim goes wrong, should never happen */
1025	DBG_BUGON(justfound && PagePrivate(page));
1026
1027	/* the page is still in manage cache */
1028	if (page->mapping == mc) {
1029		WRITE_ONCE(pcl->compressed_pages[nr], page);
1030
1031		ClearPageError(page);
1032		if (!PagePrivate(page)) {
1033			/*
1034			 * impossible to be !PagePrivate(page) for
1035			 * the current restriction as well if
1036			 * the page is already in compressed_pages[].
1037			 */
1038			DBG_BUGON(!justfound);
1039
1040			justfound = 0;
1041			set_page_private(page, (unsigned long)pcl);
1042			SetPagePrivate(page);
1043		}
1044
1045		/* no need to submit io if it is already up-to-date */
1046		if (PageUptodate(page)) {
1047			unlock_page(page);
1048			page = NULL;
1049		}
1050		goto out;
1051	}
1052
1053	/*
1054	 * the managed page has been truncated, it's unsafe to
1055	 * reuse this one, let's allocate a new cache-managed page.
1056	 */
1057	DBG_BUGON(page->mapping);
1058	DBG_BUGON(!justfound);
1059
1060	tocache = true;
1061	unlock_page(page);
1062	put_page(page);
1063out_allocpage:
1064	page = erofs_allocpage(pagepool, gfp | __GFP_NOFAIL);
1065	if (!tocache || add_to_page_cache_lru(page, mc, index + nr, gfp)) {
1066		/* non-LRU / non-movable temporary page is needed */
1067		page->mapping = Z_EROFS_MAPPING_STAGING;
1068		tocache = false;
1069	}
1070
1071	if (oldpage != cmpxchg(&pcl->compressed_pages[nr], oldpage, page)) {
1072		if (tocache) {
1073			/* since it added to managed cache successfully */
1074			unlock_page(page);
1075			put_page(page);
1076		} else {
1077			list_add(&page->lru, pagepool);
1078		}
1079		cond_resched();
1080		goto repeat;
1081	}
1082
1083	if (tocache) {
1084		set_page_private(page, (unsigned long)pcl);
1085		SetPagePrivate(page);
1086	}
1087out:	/* the only exit (for tracing and debugging) */
1088	return page;
1089}
1090
1091static struct z_erofs_decompressqueue *
1092jobqueue_init(struct super_block *sb,
1093	      struct z_erofs_decompressqueue *fgq, bool *fg)
1094{
1095	struct z_erofs_decompressqueue *q;
1096
1097	if (fg && !*fg) {
1098		q = kvzalloc(sizeof(*q), GFP_KERNEL | __GFP_NOWARN);
1099		if (!q) {
1100			*fg = true;
1101			goto fg_out;
1102		}
1103		INIT_WORK(&q->u.work, z_erofs_decompressqueue_work);
1104	} else {
1105fg_out:
1106		q = fgq;
1107		init_waitqueue_head(&fgq->u.wait);
1108		atomic_set(&fgq->pending_bios, 0);
1109	}
1110	q->sb = sb;
1111	q->head = Z_EROFS_PCLUSTER_TAIL_CLOSED;
1112	return q;
1113}
1114
1115/* define decompression jobqueue types */
1116enum {
1117	JQ_BYPASS,
1118	JQ_SUBMIT,
1119	NR_JOBQUEUES,
1120};
1121
1122static void *jobqueueset_init(struct super_block *sb,
1123			      struct z_erofs_decompressqueue *q[],
1124			      struct z_erofs_decompressqueue *fgq, bool *fg)
1125{
1126	/*
1127	 * if managed cache is enabled, bypass jobqueue is needed,
1128	 * no need to read from device for all pclusters in this queue.
1129	 */
1130	q[JQ_BYPASS] = jobqueue_init(sb, fgq + JQ_BYPASS, NULL);
1131	q[JQ_SUBMIT] = jobqueue_init(sb, fgq + JQ_SUBMIT, fg);
1132
1133	return tagptr_cast_ptr(tagptr_fold(tagptr1_t, q[JQ_SUBMIT], *fg));
1134}
1135
1136static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl,
1137				    z_erofs_next_pcluster_t qtail[],
1138				    z_erofs_next_pcluster_t owned_head)
1139{
1140	z_erofs_next_pcluster_t *const submit_qtail = qtail[JQ_SUBMIT];
1141	z_erofs_next_pcluster_t *const bypass_qtail = qtail[JQ_BYPASS];
1142
1143	DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
1144	if (owned_head == Z_EROFS_PCLUSTER_TAIL)
1145		owned_head = Z_EROFS_PCLUSTER_TAIL_CLOSED;
1146
1147	WRITE_ONCE(pcl->next, Z_EROFS_PCLUSTER_TAIL_CLOSED);
1148
1149	WRITE_ONCE(*submit_qtail, owned_head);
1150	WRITE_ONCE(*bypass_qtail, &pcl->next);
1151
1152	qtail[JQ_BYPASS] = &pcl->next;
1153}
1154
1155static void z_erofs_submit_queue(struct super_block *sb,
1156				 struct z_erofs_decompress_frontend *f,
1157				 struct list_head *pagepool,
1158				 struct z_erofs_decompressqueue *fgq,
1159				 bool *force_fg)
1160{
1161	struct erofs_sb_info *const sbi = EROFS_SB(sb);
1162	z_erofs_next_pcluster_t qtail[NR_JOBQUEUES];
1163	struct z_erofs_decompressqueue *q[NR_JOBQUEUES];
1164	void *bi_private;
1165	z_erofs_next_pcluster_t owned_head = f->clt.owned_head;
1166	/* since bio will be NULL, no need to initialize last_index */
1167	pgoff_t last_index;
1168	unsigned int nr_bios = 0;
1169	struct bio *bio = NULL;
1170
1171	bi_private = jobqueueset_init(sb, q, fgq, force_fg);
1172	qtail[JQ_BYPASS] = &q[JQ_BYPASS]->head;
1173	qtail[JQ_SUBMIT] = &q[JQ_SUBMIT]->head;
1174
1175	/* by default, all need io submission */
1176	q[JQ_SUBMIT]->head = owned_head;
1177
1178	do {
1179		struct z_erofs_pcluster *pcl;
1180		pgoff_t cur, end;
1181		unsigned int i = 0;
1182		bool bypass = true;
1183
1184		/* no possible 'owned_head' equals the following */
1185		DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
1186		DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_NIL);
1187
1188		pcl = container_of(owned_head, struct z_erofs_pcluster, next);
1189
1190		cur = pcl->obj.index;
1191		end = cur + BIT(pcl->clusterbits);
1192
1193		/* close the main owned chain at first */
1194		owned_head = cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL,
1195				     Z_EROFS_PCLUSTER_TAIL_CLOSED);
1196
1197		do {
1198			struct page *page;
1199
1200			page = pickup_page_for_submission(pcl, i++, pagepool,
1201							  MNGD_MAPPING(sbi),
1202							  GFP_NOFS);
1203			if (!page)
1204				continue;
1205
1206			if (bio && cur != last_index + 1) {
1207submit_bio_retry:
1208				submit_bio(bio);
1209				bio = NULL;
1210			}
1211
1212			if (!bio) {
1213				bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
1214
1215				bio->bi_end_io = z_erofs_decompressqueue_endio;
1216				bio_set_dev(bio, sb->s_bdev);
1217				bio->bi_iter.bi_sector = (sector_t)cur <<
1218					LOG_SECTORS_PER_BLOCK;
1219				bio->bi_private = bi_private;
1220				bio->bi_opf = REQ_OP_READ;
1221				if (f->readahead)
1222					bio->bi_opf |= REQ_RAHEAD;
1223				++nr_bios;
1224			}
1225
1226			if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
1227				goto submit_bio_retry;
1228
1229			last_index = cur;
1230			bypass = false;
1231		} while (++cur < end);
1232
1233		if (!bypass)
1234			qtail[JQ_SUBMIT] = &pcl->next;
1235		else
1236			move_to_bypass_jobqueue(pcl, qtail, owned_head);
1237	} while (owned_head != Z_EROFS_PCLUSTER_TAIL);
1238
1239	if (bio)
1240		submit_bio(bio);
1241
1242	/*
1243	 * although background is preferred, no one is pending for submission.
1244	 * don't issue workqueue for decompression but drop it directly instead.
1245	 */
1246	if (!*force_fg && !nr_bios) {
1247		kvfree(q[JQ_SUBMIT]);
1248		return;
1249	}
1250	z_erofs_decompress_kickoff(q[JQ_SUBMIT], *force_fg, nr_bios);
1251}
1252
1253static void z_erofs_runqueue(struct super_block *sb,
1254			     struct z_erofs_decompress_frontend *f,
1255			     struct list_head *pagepool, bool force_fg)
1256{
1257	struct z_erofs_decompressqueue io[NR_JOBQUEUES];
1258
1259	if (f->clt.owned_head == Z_EROFS_PCLUSTER_TAIL)
1260		return;
1261	z_erofs_submit_queue(sb, f, pagepool, io, &force_fg);
1262
1263	/* handle bypass queue (no i/o pclusters) immediately */
1264	z_erofs_decompress_queue(&io[JQ_BYPASS], pagepool);
1265
1266	if (!force_fg)
1267		return;
1268
1269	/* wait until all bios are completed */
1270	io_wait_event(io[JQ_SUBMIT].u.wait,
1271		      !atomic_read(&io[JQ_SUBMIT].pending_bios));
1272
1273	/* handle synchronous decompress queue in the caller context */
1274	z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool);
1275}
1276
1277static int z_erofs_readpage(struct file *file, struct page *page)
1278{
1279	struct inode *const inode = page->mapping->host;
1280	struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
1281	int err;
1282	LIST_HEAD(pagepool);
1283
1284	trace_erofs_readpage(page, false);
1285
1286	f.headoffset = (erofs_off_t)page->index << PAGE_SHIFT;
1287
1288	err = z_erofs_do_read_page(&f, page);
1289	(void)z_erofs_collector_end(&f.clt);
1290
1291	/* if some compressed cluster ready, need submit them anyway */
1292	z_erofs_runqueue(inode->i_sb, &f, &pagepool, true);
1293
1294	if (err)
1295		erofs_err(inode->i_sb, "failed to read, err [%d]", err);
1296
1297	if (f.map.mpage)
1298		put_page(f.map.mpage);
1299
1300	/* clean up the remaining free pages */
1301	put_pages_list(&pagepool);
1302	return err;
1303}
1304
1305static void z_erofs_readahead(struct readahead_control *rac)
1306{
1307	struct inode *const inode = rac->mapping->host;
1308	struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
1309
1310	unsigned int nr_pages = readahead_count(rac);
1311	bool sync = (nr_pages <= sbi->ctx.max_sync_decompress_pages);
1312	struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
1313	struct page *page, *head = NULL;
1314	LIST_HEAD(pagepool);
1315
1316	trace_erofs_readpages(inode, readahead_index(rac), nr_pages, false);
1317
1318	f.readahead = true;
1319	f.headoffset = readahead_pos(rac);
1320
1321	while ((page = readahead_page(rac))) {
1322		prefetchw(&page->flags);
1323
1324		/*
1325		 * A pure asynchronous readahead is indicated if
1326		 * a PG_readahead marked page is hitted at first.
1327		 * Let's also do asynchronous decompression for this case.
1328		 */
1329		sync &= !(PageReadahead(page) && !head);
1330
1331		set_page_private(page, (unsigned long)head);
1332		head = page;
1333	}
1334
1335	while (head) {
1336		struct page *page = head;
1337		int err;
1338
1339		/* traversal in reverse order */
1340		head = (void *)page_private(page);
1341
1342		err = z_erofs_do_read_page(&f, page);
1343		if (err)
1344			erofs_err(inode->i_sb,
1345				  "readahead error at page %lu @ nid %llu",
1346				  page->index, EROFS_I(inode)->nid);
1347		put_page(page);
1348	}
1349
1350	(void)z_erofs_collector_end(&f.clt);
1351
1352	z_erofs_runqueue(inode->i_sb, &f, &pagepool, sync);
1353
1354	if (f.map.mpage)
1355		put_page(f.map.mpage);
1356
1357	/* clean up the remaining free pages */
1358	put_pages_list(&pagepool);
1359}
1360
1361const struct address_space_operations z_erofs_aops = {
1362	.readpage = z_erofs_readpage,
1363	.readahead = z_erofs_readahead,
1364};
1365
1366