1 files changed, 84 insertions, 55 deletions

diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 0671184d9cf1..792f20888a8f 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -79,9 +79,6 @@ struct z_erofs_pcluster {
 	/* L: whether partial decompression or not */
 	bool partial;
 
-	/* L: indicate several pageofs_outs or not */
-	bool multibases;
-
 	/* L: whether extra buffer allocations are best-effort */
 	bool besteffort;
 
@@ -291,6 +288,7 @@ static struct workqueue_struct *z_erofs_workqueue __read_mostly;
 
 #ifdef CONFIG_EROFS_FS_PCPU_KTHREAD
 static struct kthread_worker __rcu **z_erofs_pcpu_workers;
+static atomic_t erofs_percpu_workers_initialized = ATOMIC_INIT(0);
 
 static void erofs_destroy_percpu_workers(void)
 {
@@ -336,12 +334,8 @@ static int erofs_init_percpu_workers(void)
 	}
 	return 0;
 }
-#else
-static inline void erofs_destroy_percpu_workers(void) {}
-static inline int erofs_init_percpu_workers(void) { return 0; }
-#endif
 
-#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_EROFS_FS_PCPU_KTHREAD)
+#ifdef CONFIG_HOTPLUG_CPU
 static DEFINE_SPINLOCK(z_erofs_pcpu_worker_lock);
 static enum cpuhp_state erofs_cpuhp_state;
 
@@ -398,17 +392,56 @@ static void erofs_cpu_hotplug_destroy(void)
 	if (erofs_cpuhp_state)
 		cpuhp_remove_state_nocalls(erofs_cpuhp_state);
 }
-#else /* !CONFIG_HOTPLUG_CPU || !CONFIG_EROFS_FS_PCPU_KTHREAD */
+#else /* !CONFIG_HOTPLUG_CPU  */
 static inline int erofs_cpu_hotplug_init(void) { return 0; }
 static inline void erofs_cpu_hotplug_destroy(void) {}
-#endif
+#endif/* CONFIG_HOTPLUG_CPU */
+static int z_erofs_init_pcpu_workers(struct super_block *sb)
+{
+	int err;
 
-void z_erofs_exit_subsystem(void)
+	if (atomic_xchg(&erofs_percpu_workers_initialized, 1))
+		return 0;
+
+	err = erofs_init_percpu_workers();
+	if (err) {
+		erofs_err(sb, "per-cpu workers: failed to allocate.");
+		goto err_init_percpu_workers;
+	}
+
+	err = erofs_cpu_hotplug_init();
+	if (err < 0) {
+		erofs_err(sb, "per-cpu workers: failed CPU hotplug init.");
+		goto err_cpuhp_init;
+	}
+	erofs_info(sb, "initialized per-cpu workers successfully.");
+	return err;
+
+err_cpuhp_init:
+	erofs_destroy_percpu_workers();
+err_init_percpu_workers:
+	atomic_set(&erofs_percpu_workers_initialized, 0);
+	return err;
+}
+
+static void z_erofs_destroy_pcpu_workers(void)
 {
+	if (!atomic_xchg(&erofs_percpu_workers_initialized, 0))
+		return;
 	erofs_cpu_hotplug_destroy();
 	erofs_destroy_percpu_workers();
+}
+#else /* !CONFIG_EROFS_FS_PCPU_KTHREAD */
+static inline int z_erofs_init_pcpu_workers(struct super_block *sb) { return 0; }
+static inline void z_erofs_destroy_pcpu_workers(void) {}
+#endif/* CONFIG_EROFS_FS_PCPU_KTHREAD */
+
+void z_erofs_exit_subsystem(void)
+{
+	z_erofs_destroy_pcpu_workers();
 	destroy_workqueue(z_erofs_workqueue);
 	z_erofs_destroy_pcluster_pool();
+	z_erofs_crypto_disable_all_engines();
 	z_erofs_exit_decompressor();
 }
 
@@ -430,19 +463,8 @@ int __init z_erofs_init_subsystem(void)
 		goto err_workqueue_init;
 	}
 
-	err = erofs_init_percpu_workers();
-	if (err)
-		goto err_pcpu_worker;
-
-	err = erofs_cpu_hotplug_init();
-	if (err < 0)
-		goto err_cpuhp_init;
 	return err;
 
-err_cpuhp_init:
-	erofs_destroy_percpu_workers();
-err_pcpu_worker:
-	destroy_workqueue(z_erofs_workqueue);
 err_workqueue_init:
 	z_erofs_destroy_pcluster_pool();
 err_pcluster_pool:
@@ -644,8 +666,14 @@ static const struct address_space_operations z_erofs_cache_aops = {
 
 int z_erofs_init_super(struct super_block *sb)
 {
-	struct inode *const inode = new_inode(sb);
+	struct inode *inode;
+	int err;
+
+	err = z_erofs_init_pcpu_workers(sb);
+	if (err)
+		return err;
 
+	inode = new_inode(sb);
 	if (!inode)
 		return -ENOMEM;
 	set_nlink(inode, 1);
@@ -725,7 +753,6 @@ static int z_erofs_register_pcluster(struct z_erofs_frontend *fe)
 	lockref_init(&pcl->lockref); /* one ref for this request */
 	pcl->algorithmformat = map->m_algorithmformat;
 	pcl->pclustersize = map->m_plen;
-	pcl->pageofs_in = pageofs_in;
 	pcl->length = 0;
 	pcl->partial = true;
 	pcl->next = fe->head;
@@ -778,6 +805,7 @@ static int z_erofs_pcluster_begin(struct z_erofs_frontend *fe)
 	struct erofs_map_blocks *map = &fe->map;
 	struct super_block *sb = fe->inode->i_sb;
 	struct z_erofs_pcluster *pcl = NULL;
+	void *ptr;
 	int ret;
 
 	DBG_BUGON(fe->pcl);
@@ -827,15 +855,17 @@ static int z_erofs_pcluster_begin(struct z_erofs_frontend *fe)
 		/* bind cache first when cached decompression is preferred */
 		z_erofs_bind_cache(fe);
 	} else {
-		void *mptr;
-
-		mptr = erofs_read_metabuf(&map->buf, sb, map->m_pa, false);
-		if (IS_ERR(mptr)) {
-			ret = PTR_ERR(mptr);
-			erofs_err(sb, "failed to get inline data %d", ret);
+		ret = erofs_init_metabuf(&map->buf, sb,
+					 erofs_inode_in_metabox(fe->inode));
+		if (ret)
+			return ret;
+		ptr = erofs_bread(&map->buf, map->m_pa, false);
+		if (IS_ERR(ptr)) {
+			ret = PTR_ERR(ptr);
+			erofs_err(sb, "failed to get inline folio %d", ret);
 			return ret;
 		}
-		get_page(map->buf.page);
+		folio_get(page_folio(map->buf.page));
 		WRITE_ONCE(fe->pcl->compressed_bvecs[0].page, map->buf.page);
 		fe->pcl->pageofs_in = map->m_pa & ~PAGE_MASK;
 		fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE;
@@ -1007,7 +1037,7 @@ static int z_erofs_scan_folio(struct z_erofs_frontend *f,
 		if (!(map->m_flags & EROFS_MAP_MAPPED)) {
 			folio_zero_segment(folio, cur, end);
 			tight = false;
-		} else if (map->m_flags & EROFS_MAP_FRAGMENT) {
+		} else if (map->m_flags & __EROFS_MAP_FRAGMENT) {
 			erofs_off_t fpos = offset + cur - map->m_la;
 
 			err = z_erofs_read_fragment(inode->i_sb, folio, cur,
@@ -1047,8 +1077,6 @@ static int z_erofs_scan_folio(struct z_erofs_frontend *f,
 				break;
 
 			erofs_onlinefolio_split(folio);
-			if (f->pcl->pageofs_out != (map->m_la & ~PAGE_MASK))
-				f->pcl->multibases = true;
 			if (f->pcl->length < offset + end - map->m_la) {
 				f->pcl->length = offset + end - map->m_la;
 				f->pcl->pageofs_out = map->m_la & ~PAGE_MASK;
@@ -1066,7 +1094,7 @@ static int z_erofs_scan_folio(struct z_erofs_frontend *f,
 			tight = (bs == PAGE_SIZE);
 		}
 	} while ((end = cur) > 0);
-	erofs_onlinefolio_end(folio, err);
+	erofs_onlinefolio_end(folio, err, false);
 	return err;
 }
 
@@ -1094,7 +1122,6 @@ struct z_erofs_backend {
 	struct page *onstack_pages[Z_EROFS_ONSTACK_PAGES];
 	struct super_block *sb;
 	struct z_erofs_pcluster *pcl;
-
 	/* pages with the longest decompressed length for deduplication */
 	struct page **decompressed_pages;
 	/* pages to keep the compressed data */
@@ -1103,6 +1130,8 @@ struct z_erofs_backend {
 	struct list_head decompressed_secondary_bvecs;
 	struct page **pagepool;
 	unsigned int onstack_used, nr_pages;
+	/* indicate if temporary copies should be preserved for later use */
+	bool keepxcpy;
 };
 
 struct z_erofs_bvec_item {
@@ -1113,18 +1142,20 @@ struct z_erofs_bvec_item {
 static void z_erofs_do_decompressed_bvec(struct z_erofs_backend *be,
 					 struct z_erofs_bvec *bvec)
 {
+	int poff = bvec->offset + be->pcl->pageofs_out;
 	struct z_erofs_bvec_item *item;
-	unsigned int pgnr;
-
-	if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK) &&
-	    (bvec->end == PAGE_SIZE ||
-	     bvec->offset + bvec->end == be->pcl->length)) {
-		pgnr = (bvec->offset + be->pcl->pageofs_out) >> PAGE_SHIFT;
-		DBG_BUGON(pgnr >= be->nr_pages);
-		if (!be->decompressed_pages[pgnr]) {
-			be->decompressed_pages[pgnr] = bvec->page;
+	struct page **page;
+
+	if (!(poff & ~PAGE_MASK) && (bvec->end == PAGE_SIZE ||
+			bvec->offset + bvec->end == be->pcl->length)) {
+		DBG_BUGON((poff >> PAGE_SHIFT) >= be->nr_pages);
+		page = be->decompressed_pages + (poff >> PAGE_SHIFT);
+		if (!*page) {
+			*page = bvec->page;
 			return;
 		}
+	} else {
+		be->keepxcpy = true;
 	}
 
 	/* (cold path) one pcluster is requested multiple times */
@@ -1168,7 +1199,7 @@ static void z_erofs_fill_other_copies(struct z_erofs_backend *be, int err)
 			cur += len;
 		}
 		kunmap_local(dst);
-		erofs_onlinefolio_end(page_folio(bvi->bvec.page), err);
+		erofs_onlinefolio_end(page_folio(bvi->bvec.page), err, true);
 		list_del(p);
 		kfree(bvi);
 	}
@@ -1290,16 +1321,15 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
 					.alg = pcl->algorithmformat,
 					.inplace_io = overlapped,
 					.partial_decoding = pcl->partial,
-					.fillgaps = pcl->multibases,
+					.fillgaps = be->keepxcpy,
 					.gfp = pcl->besteffort ? GFP_KERNEL :
 						GFP_NOWAIT | __GFP_NORETRY
 				 }, be->pagepool);
 
 	/* must handle all compressed pages before actual file pages */
 	if (pcl->from_meta) {
-		page = pcl->compressed_bvecs[0].page;
+		folio_put(page_folio(pcl->compressed_bvecs[0].page));
 		WRITE_ONCE(pcl->compressed_bvecs[0].page, NULL);
-		put_page(page);
 	} else {
 		/* managed folios are still left in compressed_bvecs[] */
 		for (i = 0; i < pclusterpages; ++i) {
@@ -1327,7 +1357,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
 
 		DBG_BUGON(z_erofs_page_is_invalidated(page));
 		if (!z_erofs_is_shortlived_page(page)) {
-			erofs_onlinefolio_end(page_folio(page), err);
+			erofs_onlinefolio_end(page_folio(page), err, true);
 			continue;
 		}
 		if (pcl->algorithmformat != Z_EROFS_COMPRESSION_LZ4) {
@@ -1347,7 +1377,6 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
 
 	pcl->length = 0;
 	pcl->partial = true;
-	pcl->multibases = false;
 	pcl->besteffort = false;
 	pcl->bvset.nextpage = NULL;
 	pcl->vcnt = 0;
@@ -1711,7 +1740,8 @@ drain_io:
 					bio = bio_alloc(mdev.m_bdev, BIO_MAX_VECS,
 							REQ_OP_READ, GFP_NOIO);
 				bio->bi_end_io = z_erofs_endio;
-				bio->bi_iter.bi_sector = cur >> 9;
+				bio->bi_iter.bi_sector =
+						(mdev.m_dif->fsoff + cur) >> 9;
 				bio->bi_private = q[JQ_SUBMIT];
 				if (readahead)
 					bio->bi_opf |= REQ_RAHEAD;
@@ -1859,13 +1889,12 @@ static void z_erofs_readahead(struct readahead_control *rac)
 {
 	struct inode *const inode = rac->mapping->host;
 	Z_EROFS_DEFINE_FRONTEND(f, inode, readahead_pos(rac));
-	struct folio *head = NULL, *folio;
 	unsigned int nrpages = readahead_count(rac);
+	struct folio *head = NULL, *folio;
 	int err;
 
+	trace_erofs_readahead(inode, readahead_index(rac), nrpages, false);
 	z_erofs_pcluster_readmore(&f, rac, true);
-	nrpages = readahead_count(rac);
-	trace_erofs_readpages(inode, readahead_index(rac), nrpages, false);
 	while ((folio = readahead_folio(rac))) {
 		folio->private = head;
 		head = folio;