erofs: move erofs out of staging

EROFS filesystem has been merged into linux-staging for a year.

EROFS is designed to be a better solution of saving extra storage
space with guaranteed end-to-end performance for read-only files
with the help of reduced metadata, fixed-sized output compression
and decompression inplace technologies.

In the past year, EROFS was greatly improved by many people as
a staging driver, self-tested, betaed by a large number of our
internal users, successfully applied to almost all in-service
HUAWEI smartphones as the part of EMUI 9.1 and proven to be stable
enough to be moved out of staging.

EROFS is a self-contained filesystem driver. Although there are
still some TODOs to be more generic, we have a dedicated team
actively keeping on working on EROFS in order to make it better
with the evolution of Linux kernel as the other in-kernel filesystems.

As Pavel suggested, it's better to do as one commit since git
can do moves and all histories will be saved in this way.

Let's promote it from staging and enhance it more actively as
a "real" part of kernel for more wider scenarios!

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Pavel Machek <pavel@denx.de>
Cc: David Sterba <dsterba@suse.cz>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Darrick J . Wong <darrick.wong@oracle.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Richard Weinberger <richard@nod.at>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Chao Yu <yuchao0@huawei.com>
Cc: Miao Xie <miaoxie@huawei.com>
Cc: Li Guifu <bluce.liguifu@huawei.com>
Cc: Fang Wei <fangwei1@huawei.com>
Signed-off-by: Gao Xiang <gaoxiang25@huawei.com>
Link: https://lore.kernel.org/r/20190822213659.5501-1-hsiangkao@aol.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

19 files changed, 6687 insertions, 0 deletions

diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig
new file mode 100644
index 000000000000..16316d1adca3
--- /dev/null
+++ b/fs/erofs/Kconfig
@@ -0,0 +1,98 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config EROFS_FS
+	tristate "EROFS filesystem support"
+	depends on BLOCK
+	help
+	  EROFS (Enhanced Read-Only File System) is a lightweight
+	  read-only file system with modern designs (eg. page-sized
+	  blocks, inline xattrs/data, etc.) for scenarios which need
+	  high-performance read-only requirements, e.g. Android OS
+	  for mobile phones and LIVECDs.
+
+	  It also provides fixed-sized output compression support,
+	  which improves storage density, keeps relatively higher
+	  compression ratios, which is more useful to achieve high
+	  performance for embedded devices with limited memory.
+
+	  If unsure, say N.
+
+config EROFS_FS_DEBUG
+	bool "EROFS debugging feature"
+	depends on EROFS_FS
+	help
+	  Print debugging messages and enable more BUG_ONs which check
+	  filesystem consistency and find potential issues aggressively,
+	  which can be used for Android eng build, for example.
+
+	  For daily use, say N.
+
+config EROFS_FAULT_INJECTION
+	bool "EROFS fault injection facility"
+	depends on EROFS_FS
+	help
+	  Test EROFS to inject faults such as ENOMEM, EIO, and so on.
+	  If unsure, say N.
+
+config EROFS_FS_XATTR
+	bool "EROFS extended attributes"
+	depends on EROFS_FS
+	default y
+	help
+	  Extended attributes are name:value pairs associated with inodes by
+	  the kernel or by users (see the attr(5) manual page, or visit
+	  <http://acl.bestbits.at/> for details).
+
+	  If unsure, say N.
+
+config EROFS_FS_POSIX_ACL
+	bool "EROFS Access Control Lists"
+	depends on EROFS_FS_XATTR
+	select FS_POSIX_ACL
+	default y
+	help
+	  Posix Access Control Lists (ACLs) support permissions for users and
+	  groups beyond the owner/group/world scheme.
+
+	  To learn more about Access Control Lists, visit the POSIX ACLs for
+	  Linux website <http://acl.bestbits.at/>.
+
+	  If you don't know what Access Control Lists are, say N.
+
+config EROFS_FS_SECURITY
+	bool "EROFS Security Labels"
+	depends on EROFS_FS_XATTR
+	default y
+	help
+	  Security labels provide an access control facility to support Linux
+	  Security Models (LSMs) accepted by AppArmor, SELinux, Smack and TOMOYO
+	  Linux. This option enables an extended attribute handler for file
+	  security labels in the erofs filesystem, so that it requires enabling
+	  the extended attribute support in advance.
+
+	  If you are not using a security module, say N.
+
+config EROFS_FS_ZIP
+	bool "EROFS Data Compression Support"
+	depends on EROFS_FS
+	select LZ4_DECOMPRESS
+	default y
+	help
+	  Enable fixed-sized output compression for EROFS.
+
+	  If you don't want to enable compression feature, say N.
+
+config EROFS_FS_CLUSTER_PAGE_LIMIT
+	int "EROFS Cluster Pages Hard Limit"
+	depends on EROFS_FS_ZIP
+	range 1 256
+	default "1"
+	help
+	  Indicates maximum # of pages of a compressed
+	  physical cluster.
+
+	  For example, if files in a image were compressed
+	  into 8k-unit, hard limit should not be configured
+	  less than 2. Otherwise, the image will be refused
+	  to mount on this kernel.
+
diff --git a/fs/erofs/Makefile b/fs/erofs/Makefile
new file mode 100644
index 000000000000..46f2aa4ba46c
--- /dev/null
+++ b/fs/erofs/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+EROFS_VERSION = "1.0"
+
+ccflags-y += -DEROFS_VERSION=\"$(EROFS_VERSION)\"
+
+obj-$(CONFIG_EROFS_FS) += erofs.o
+erofs-objs := super.o inode.o data.o namei.o dir.o utils.o
+erofs-$(CONFIG_EROFS_FS_XATTR) += xattr.o
+erofs-$(CONFIG_EROFS_FS_ZIP) += decompressor.o zmap.o zdata.o
+
diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h
new file mode 100644
index 000000000000..07d279fd5d67
--- /dev/null
+++ b/fs/erofs/compress.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2019 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#ifndef __EROFS_FS_COMPRESS_H
+#define __EROFS_FS_COMPRESS_H
+
+#include "internal.h"
+
+enum {
+	Z_EROFS_COMPRESSION_SHIFTED = Z_EROFS_COMPRESSION_MAX,
+	Z_EROFS_COMPRESSION_RUNTIME_MAX
+};
+
+struct z_erofs_decompress_req {
+	struct super_block *sb;
+	struct page **in, **out;
+
+	unsigned short pageofs_out;
+	unsigned int inputsize, outputsize;
+
+	/* indicate the algorithm will be used for decompression */
+	unsigned int alg;
+	bool inplace_io, partial_decoding;
+};
+
+/*
+ * - 0x5A110C8D ('sallocated', Z_EROFS_MAPPING_STAGING) -
+ * used to mark temporary allocated pages from other
+ * file/cached pages and NULL mapping pages.
+ */
+#define Z_EROFS_MAPPING_STAGING         ((void *)0x5A110C8D)
+
+/* check if a page is marked as staging */
+static inline bool z_erofs_page_is_staging(struct page *page)
+{
+	return page->mapping == Z_EROFS_MAPPING_STAGING;
+}
+
+static inline bool z_erofs_put_stagingpage(struct list_head *pagepool,
+					   struct page *page)
+{
+	if (!z_erofs_page_is_staging(page))
+		return false;
+
+	/* staging pages should not be used by others at the same time */
+	if (page_ref_count(page) > 1)
+		put_page(page);
+	else
+		list_add(&page->lru, pagepool);
+	return true;
+}
+
+int z_erofs_decompress(struct z_erofs_decompress_req *rq,
+		       struct list_head *pagepool);
+
+#endif
+
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
new file mode 100644
index 000000000000..fda16ec8863e
--- /dev/null
+++ b/fs/erofs/data.c
@@ -0,0 +1,423 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017-2018 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#include "internal.h"
+#include <linux/prefetch.h>
+
+#include <trace/events/erofs.h>
+
+static inline void read_endio(struct bio *bio)
+{
+	struct super_block *const sb = bio->bi_private;
+	struct bio_vec *bvec;
+	blk_status_t err = bio->bi_status;
+	struct bvec_iter_all iter_all;
+
+	if (time_to_inject(EROFS_SB(sb), FAULT_READ_IO)) {
+		erofs_show_injection_info(FAULT_READ_IO);
+		err = BLK_STS_IOERR;
+	}
+
+	bio_for_each_segment_all(bvec, bio, iter_all) {
+		struct page *page = bvec->bv_page;
+
+		/* page is already locked */
+		DBG_BUGON(PageUptodate(page));
+
+		if (unlikely(err))
+			SetPageError(page);
+		else
+			SetPageUptodate(page);
+
+		unlock_page(page);
+		/* page could be reclaimed now */
+	}
+	bio_put(bio);
+}
+
+/* prio -- true is used for dir */
+struct page *__erofs_get_meta_page(struct super_block *sb,
+				   erofs_blk_t blkaddr, bool prio, bool nofail)
+{
+	struct inode *const bd_inode = sb->s_bdev->bd_inode;
+	struct address_space *const mapping = bd_inode->i_mapping;
+	/* prefer retrying in the allocator to blindly looping below */
+	const gfp_t gfp = mapping_gfp_constraint(mapping, ~__GFP_FS) |
+		(nofail ? __GFP_NOFAIL : 0);
+	unsigned int io_retries = nofail ? EROFS_IO_MAX_RETRIES_NOFAIL : 0;
+	struct page *page;
+	int err;
+
+repeat:
+	page = find_or_create_page(mapping, blkaddr, gfp);
+	if (unlikely(!page)) {
+		DBG_BUGON(nofail);
+		return ERR_PTR(-ENOMEM);
+	}
+	DBG_BUGON(!PageLocked(page));
+
+	if (!PageUptodate(page)) {
+		struct bio *bio;
+
+		bio = erofs_grab_bio(sb, blkaddr, 1, sb, read_endio, nofail);
+		if (IS_ERR(bio)) {
+			DBG_BUGON(nofail);
+			err = PTR_ERR(bio);
+			goto err_out;
+		}
+
+		err = bio_add_page(bio, page, PAGE_SIZE, 0);
+		if (unlikely(err != PAGE_SIZE)) {
+			err = -EFAULT;
+			goto err_out;
+		}
+
+		__submit_bio(bio, REQ_OP_READ,
+			     REQ_META | (prio ? REQ_PRIO : 0));
+
+		lock_page(page);
+
+		/* this page has been truncated by others */
+		if (unlikely(page->mapping != mapping)) {
+unlock_repeat:
+			unlock_page(page);
+			put_page(page);
+			goto repeat;
+		}
+
+		/* more likely a read error */
+		if (unlikely(!PageUptodate(page))) {
+			if (io_retries) {
+				--io_retries;
+				goto unlock_repeat;
+			}
+			err = -EIO;
+			goto err_out;
+		}
+	}
+	return page;
+
+err_out:
+	unlock_page(page);
+	put_page(page);
+	return ERR_PTR(err);
+}
+
+static int erofs_map_blocks_flatmode(struct inode *inode,
+				     struct erofs_map_blocks *map,
+				     int flags)
+{
+	int err = 0;
+	erofs_blk_t nblocks, lastblk;
+	u64 offset = map->m_la;
+	struct erofs_vnode *vi = EROFS_V(inode);
+
+	trace_erofs_map_blocks_flatmode_enter(inode, map, flags);
+
+	nblocks = DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
+	lastblk = nblocks - is_inode_flat_inline(inode);
+
+	if (unlikely(offset >= inode->i_size)) {
+		/* leave out-of-bound access unmapped */
+		map->m_flags = 0;
+		map->m_plen = 0;
+		goto out;
+	}
+
+	/* there is no hole in flatmode */
+	map->m_flags = EROFS_MAP_MAPPED;
+
+	if (offset < blknr_to_addr(lastblk)) {
+		map->m_pa = blknr_to_addr(vi->raw_blkaddr) + map->m_la;
+		map->m_plen = blknr_to_addr(lastblk) - offset;
+	} else if (is_inode_flat_inline(inode)) {
+		/* 2 - inode inline B: inode, [xattrs], inline last blk... */
+		struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
+
+		map->m_pa = iloc(sbi, vi->nid) + vi->inode_isize +
+			vi->xattr_isize + erofs_blkoff(map->m_la);
+		map->m_plen = inode->i_size - offset;
+
+		/* inline data should be located in one meta block */
+		if (erofs_blkoff(map->m_pa) + map->m_plen > PAGE_SIZE) {
+			errln("inline data cross block boundary @ nid %llu",
+			      vi->nid);
+			DBG_BUGON(1);
+			err = -EFSCORRUPTED;
+			goto err_out;
+		}
+
+		map->m_flags |= EROFS_MAP_META;
+	} else {
+		errln("internal error @ nid: %llu (size %llu), m_la 0x%llx",
+		      vi->nid, inode->i_size, map->m_la);
+		DBG_BUGON(1);
+		err = -EIO;
+		goto err_out;
+	}
+
+out:
+	map->m_llen = map->m_plen;
+
+err_out:
+	trace_erofs_map_blocks_flatmode_exit(inode, map, flags, 0);
+	return err;
+}
+
+int erofs_map_blocks(struct inode *inode,
+		     struct erofs_map_blocks *map, int flags)
+{
+	if (unlikely(is_inode_layout_compression(inode))) {
+		int err = z_erofs_map_blocks_iter(inode, map, flags);
+
+		if (map->mpage) {
+			put_page(map->mpage);
+			map->mpage = NULL;
+		}
+		return err;
+	}
+	return erofs_map_blocks_flatmode(inode, map, flags);
+}
+
+static inline struct bio *erofs_read_raw_page(struct bio *bio,
+					      struct address_space *mapping,
+					      struct page *page,
+					      erofs_off_t *last_block,
+					      unsigned int nblocks,
+					      bool ra)
+{
+	struct inode *const inode = mapping->host;
+	struct super_block *const sb = inode->i_sb;
+	erofs_off_t current_block = (erofs_off_t)page->index;
+	int err;
+
+	DBG_BUGON(!nblocks);
+
+	if (PageUptodate(page)) {
+		err = 0;
+		goto has_updated;
+	}
+
+	/* note that for readpage case, bio also equals to NULL */
+	if (bio &&
+	    /* not continuous */
+	    *last_block + 1 != current_block) {
+submit_bio_retry:
+		__submit_bio(bio, REQ_OP_READ, 0);
+		bio = NULL;
+	}
+
+	if (!bio) {
+		struct erofs_map_blocks map = {
+			.m_la = blknr_to_addr(current_block),
+		};
+		erofs_blk_t blknr;
+		unsigned int blkoff;
+
+		err = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
+		if (unlikely(err))
+			goto err_out;
+
+		/* zero out the holed page */
+		if (unlikely(!(map.m_flags & EROFS_MAP_MAPPED))) {
+			zero_user_segment(page, 0, PAGE_SIZE);
+			SetPageUptodate(page);
+
+			/* imply err = 0, see erofs_map_blocks */
+			goto has_updated;
+		}
+
+		/* for RAW access mode, m_plen must be equal to m_llen */
+		DBG_BUGON(map.m_plen != map.m_llen);
+
+		blknr = erofs_blknr(map.m_pa);
+		blkoff = erofs_blkoff(map.m_pa);
+
+		/* deal with inline page */
+		if (map.m_flags & EROFS_MAP_META) {
+			void *vsrc, *vto;
+			struct page *ipage;
+
+			DBG_BUGON(map.m_plen > PAGE_SIZE);
+
+			ipage = erofs_get_meta_page(inode->i_sb, blknr, 0);
+
+			if (IS_ERR(ipage)) {
+				err = PTR_ERR(ipage);
+				goto err_out;
+			}
+
+			vsrc = kmap_atomic(ipage);
+			vto = kmap_atomic(page);
+			memcpy(vto, vsrc + blkoff, map.m_plen);
+			memset(vto + map.m_plen, 0, PAGE_SIZE - map.m_plen);
+			kunmap_atomic(vto);
+			kunmap_atomic(vsrc);
+			flush_dcache_page(page);
+
+			SetPageUptodate(page);
+			/* TODO: could we unlock the page earlier? */
+			unlock_page(ipage);
+			put_page(ipage);
+
+			/* imply err = 0, see erofs_map_blocks */
+			goto has_updated;
+		}
+
+		/* pa must be block-aligned for raw reading */
+		DBG_BUGON(erofs_blkoff(map.m_pa));
+
+		/* max # of continuous pages */
+		if (nblocks > DIV_ROUND_UP(map.m_plen, PAGE_SIZE))
+			nblocks = DIV_ROUND_UP(map.m_plen, PAGE_SIZE);
+		if (nblocks > BIO_MAX_PAGES)
+			nblocks = BIO_MAX_PAGES;
+
+		bio = erofs_grab_bio(sb, blknr, nblocks, sb,
+				     read_endio, false);
+		if (IS_ERR(bio)) {
+			err = PTR_ERR(bio);
+			bio = NULL;
+			goto err_out;
+		}
+	}
+
+	err = bio_add_page(bio, page, PAGE_SIZE, 0);
+	/* out of the extent or bio is full */
+	if (err < PAGE_SIZE)
+		goto submit_bio_retry;
+
+	*last_block = current_block;
+
+	/* shift in advance in case of it followed by too many gaps */
+	if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) {
+		/* err should reassign to 0 after submitting */
+		err = 0;
+		goto submit_bio_out;
+	}
+
+	return bio;
+
+err_out:
+	/* for sync reading, set page error immediately */
+	if (!ra) {
+		SetPageError(page);
+		ClearPageUptodate(page);
+	}
+has_updated:
+	unlock_page(page);
+
+	/* if updated manually, continuous pages has a gap */
+	if (bio)
+submit_bio_out:
+		__submit_bio(bio, REQ_OP_READ, 0);
+
+	return unlikely(err) ? ERR_PTR(err) : NULL;
+}
+
+/*
+ * since we dont have write or truncate flows, so no inode
+ * locking needs to be held at the moment.
+ */
+static int erofs_raw_access_readpage(struct file *file, struct page *page)
+{
+	erofs_off_t last_block;
+	struct bio *bio;
+
+	trace_erofs_readpage(page, true);
+
+	bio = erofs_read_raw_page(NULL, page->mapping,
+				  page, &last_block, 1, false);
+
+	if (IS_ERR(bio))
+		return PTR_ERR(bio);
+
+	DBG_BUGON(bio);	/* since we have only one bio -- must be NULL */
+	return 0;
+}
+
+static int erofs_raw_access_readpages(struct file *filp,
+				      struct address_space *mapping,
+				      struct list_head *pages,
+				      unsigned int nr_pages)
+{
+	erofs_off_t last_block;
+	struct bio *bio = NULL;
+	gfp_t gfp = readahead_gfp_mask(mapping);
+	struct page *page = list_last_entry(pages, struct page, lru);
+
+	trace_erofs_readpages(mapping->host, page, nr_pages, true);
+
+	for (; nr_pages; --nr_pages) {
+		page = list_entry(pages->prev, struct page, lru);
+
+		prefetchw(&page->flags);
+		list_del(&page->lru);
+
+		if (!add_to_page_cache_lru(page, mapping, page->index, gfp)) {
+			bio = erofs_read_raw_page(bio, mapping, page,
+						  &last_block, nr_pages, true);
+
+			/* all the page errors are ignored when readahead */
+			if (IS_ERR(bio)) {
+				pr_err("%s, readahead error at page %lu of nid %llu\n",
+				       __func__, page->index,
+				       EROFS_V(mapping->host)->nid);
+
+				bio = NULL;
+			}
+		}
+
+		/* pages could still be locked */
+		put_page(page);
+	}
+	DBG_BUGON(!list_empty(pages));
+
+	/* the rare case (end in gaps) */
+	if (unlikely(bio))
+		__submit_bio(bio, REQ_OP_READ, 0);
+	return 0;
+}
+
+static int erofs_get_block(struct inode *inode, sector_t iblock,
+			   struct buffer_head *bh, int create)
+{
+	struct erofs_map_blocks map = {
+		.m_la = iblock << 9,
+	};
+	int err;
+
+	err = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
+	if (err)
+		return err;
+
+	if (map.m_flags & EROFS_MAP_MAPPED)
+		bh->b_blocknr = erofs_blknr(map.m_pa);
+
+	return err;
+}
+
+static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
+{
+	struct inode *inode = mapping->host;
+
+	if (is_inode_flat_inline(inode)) {
+		erofs_blk_t blks = i_size_read(inode) >> LOG_BLOCK_SIZE;
+
+		if (block >> LOG_SECTORS_PER_BLOCK >= blks)
+			return 0;
+	}
+
+	return generic_block_bmap(mapping, block, erofs_get_block);
+}
+
+/* for uncompressed (aligned) files and raw access for other files */
+const struct address_space_operations erofs_raw_access_aops = {
+	.readpage = erofs_raw_access_readpage,
+	.readpages = erofs_raw_access_readpages,
+	.bmap = erofs_bmap,
+};
+
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
new file mode 100644
index 000000000000..5f4b7f302863
--- /dev/null
+++ b/fs/erofs/decompressor.c
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2019 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#include "compress.h"
+#include <linux/module.h>
+#include <linux/lz4.h>
+
+#ifndef LZ4_DISTANCE_MAX	/* history window size */
+#define LZ4_DISTANCE_MAX 65535	/* set to maximum value by default */
+#endif
+
+#define LZ4_MAX_DISTANCE_PAGES	(DIV_ROUND_UP(LZ4_DISTANCE_MAX, PAGE_SIZE) + 1)
+#ifndef LZ4_DECOMPRESS_INPLACE_MARGIN
+#define LZ4_DECOMPRESS_INPLACE_MARGIN(srcsize)  (((srcsize) >> 8) + 32)
+#endif
+
+struct z_erofs_decompressor {
+	/*
+	 * if destpages have sparsed pages, fill them with bounce pages.
+	 * it also check whether destpages indicate continuous physical memory.
+	 */
+	int (*prepare_destpages)(struct z_erofs_decompress_req *rq,
+				 struct list_head *pagepool);
+	int (*decompress)(struct z_erofs_decompress_req *rq, u8 *out);
+	char *name;
+};
+
+static bool use_vmap;
+module_param(use_vmap, bool, 0444);
+MODULE_PARM_DESC(use_vmap, "Use vmap() instead of vm_map_ram() (default 0)");
+
+static int lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
+				 struct list_head *pagepool)
+{
+	const unsigned int nr =
+		PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
+	struct page *availables[LZ4_MAX_DISTANCE_PAGES] = { NULL };
+	unsigned long bounced[DIV_ROUND_UP(LZ4_MAX_DISTANCE_PAGES,
+					   BITS_PER_LONG)] = { 0 };
+	void *kaddr = NULL;
+	unsigned int i, j, top;
+
+	top = 0;
+	for (i = j = 0; i < nr; ++i, ++j) {
+		struct page *const page = rq->out[i];
+		struct page *victim;
+
+		if (j >= LZ4_MAX_DISTANCE_PAGES)
+			j = 0;
+
+		/* 'valid' bounced can only be tested after a complete round */
+		if (test_bit(j, bounced)) {
+			DBG_BUGON(i < LZ4_MAX_DISTANCE_PAGES);
+			DBG_BUGON(top >= LZ4_MAX_DISTANCE_PAGES);
+			availables[top++] = rq->out[i - LZ4_MAX_DISTANCE_PAGES];
+		}
+
+		if (page) {
+			__clear_bit(j, bounced);
+			if (kaddr) {
+				if (kaddr + PAGE_SIZE == page_address(page))
+					kaddr += PAGE_SIZE;
+				else
+					kaddr = NULL;
+			} else if (!i) {
+				kaddr = page_address(page);
+			}
+			continue;
+		}
+		kaddr = NULL;
+		__set_bit(j, bounced);
+
+		if (top) {
+			victim = availables[--top];
+			get_page(victim);
+		} else {
+			victim = erofs_allocpage(pagepool, GFP_KERNEL, false);
+			if (unlikely(!victim))
+				return -ENOMEM;
+			victim->mapping = Z_EROFS_MAPPING_STAGING;
+		}
+		rq->out[i] = victim;
+	}
+	return kaddr ? 1 : 0;
+}
+
+static void *generic_copy_inplace_data(struct z_erofs_decompress_req *rq,
+				       u8 *src, unsigned int pageofs_in)
+{
+	/*
+	 * if in-place decompression is ongoing, those decompressed
+	 * pages should be copied in order to avoid being overlapped.
+	 */
+	struct page **in = rq->in;
+	u8 *const tmp = erofs_get_pcpubuf(0);
+	u8 *tmpp = tmp;
+	unsigned int inlen = rq->inputsize - pageofs_in;
+	unsigned int count = min_t(uint, inlen, PAGE_SIZE - pageofs_in);
+
+	while (tmpp < tmp + inlen) {
+		if (!src)
+			src = kmap_atomic(*in);
+		memcpy(tmpp, src + pageofs_in, count);
+		kunmap_atomic(src);
+		src = NULL;
+		tmpp += count;
+		pageofs_in = 0;
+		count = PAGE_SIZE;
+		++in;
+	}
+	return tmp;
+}
+
+static int lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
+{
+	unsigned int inputmargin, inlen;
+	u8 *src;
+	bool copied, support_0padding;
+	int ret;
+
+	if (rq->inputsize > PAGE_SIZE)
+		return -EOPNOTSUPP;
+
+	src = kmap_atomic(*rq->in);
+	inputmargin = 0;
+	support_0padding = false;
+
+	/* decompression inplace is only safe when 0padding is enabled */
+	if (EROFS_SB(rq->sb)->requirements & EROFS_REQUIREMENT_LZ4_0PADDING) {
+		support_0padding = true;
+
+		while (!src[inputmargin & ~PAGE_MASK])
+			if (!(++inputmargin & ~PAGE_MASK))
+				break;
+
+		if (inputmargin >= rq->inputsize) {
+			kunmap_atomic(src);
+			return -EIO;
+		}
+	}
+
+	copied = false;
+	inlen = rq->inputsize - inputmargin;
+	if (rq->inplace_io) {
+		const uint oend = (rq->pageofs_out +
+				   rq->outputsize) & ~PAGE_MASK;
+		const uint nr = PAGE_ALIGN(rq->pageofs_out +
+					   rq->outputsize) >> PAGE_SHIFT;
+
+		if (rq->partial_decoding || !support_0padding ||
+		    rq->out[nr - 1] != rq->in[0] ||
+		    rq->inputsize - oend <
+		      LZ4_DECOMPRESS_INPLACE_MARGIN(inlen)) {
+			src = generic_copy_inplace_data(rq, src, inputmargin);
+			inputmargin = 0;
+			copied = true;
+		}
+	}
+
+	ret = LZ4_decompress_safe_partial(src + inputmargin, out,
+					  inlen, rq->outputsize,
+					  rq->outputsize);
+	if (ret < 0) {
+		errln("%s, failed to decompress, in[%p, %u, %u] out[%p, %u]",
+		      __func__, src + inputmargin, inlen, inputmargin,
+		      out, rq->outputsize);
+		WARN_ON(1);
+		print_hex_dump(KERN_DEBUG, "[ in]: ", DUMP_PREFIX_OFFSET,
+			       16, 1, src + inputmargin, inlen, true);
+		print_hex_dump(KERN_DEBUG, "[out]: ", DUMP_PREFIX_OFFSET,
+			       16, 1, out, rq->outputsize, true);
+		ret = -EIO;
+	}
+
+	if (copied)
+		erofs_put_pcpubuf(src);
+	else
+		kunmap_atomic(src);
+	return ret;
+}
+
+static struct z_erofs_decompressor decompressors[] = {
+	[Z_EROFS_COMPRESSION_SHIFTED] = {
+		.name = "shifted"
+	},
+	[Z_EROFS_COMPRESSION_LZ4] = {
+		.prepare_destpages = lz4_prepare_destpages,
+		.decompress = lz4_decompress,
+		.name = "lz4"
+	},
+};
+
+static void copy_from_pcpubuf(struct page **out, const char *dst,
+			      unsigned short pageofs_out,
+			      unsigned int outputsize)
+{
+	const char *end = dst + outputsize;
+	const unsigned int righthalf = PAGE_SIZE - pageofs_out;
+	const char *cur = dst - pageofs_out;
+
+	while (cur < end) {
+		struct page *const page = *out++;
+
+		if (page) {
+			char *buf = kmap_atomic(page);
+
+			if (cur >= dst) {
+				memcpy(buf, cur, min_t(uint, PAGE_SIZE,
+						       end - cur));
+			} else {
+				memcpy(buf + pageofs_out, cur + pageofs_out,
+				       min_t(uint, righthalf, end - cur));
+			}
+			kunmap_atomic(buf);
+		}
+		cur += PAGE_SIZE;
+	}
+}
+
+static void *erofs_vmap(struct page **pages, unsigned int count)
+{
+	int i = 0;
+
+	if (use_vmap)
+		return vmap(pages, count, VM_MAP, PAGE_KERNEL);
+
+	while (1) {
+		void *addr = vm_map_ram(pages, count, -1, PAGE_KERNEL);
+
+		/* retry two more times (totally 3 times) */
+		if (addr || ++i >= 3)
+			return addr;
+		vm_unmap_aliases();
+	}
+	return NULL;
+}
+
+static void erofs_vunmap(const void *mem, unsigned int count)
+{
+	if (!use_vmap)
+		vm_unmap_ram(mem, count);
+	else
+		vunmap(mem);
+}
+
+static int decompress_generic(struct z_erofs_decompress_req *rq,
+			      struct list_head *pagepool)
+{
+	const unsigned int nrpages_out =
+		PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
+	const struct z_erofs_decompressor *alg = decompressors + rq->alg;
+	unsigned int dst_maptype;
+	void *dst;
+	int ret;
+
+	if (nrpages_out == 1 && !rq->inplace_io) {
+		DBG_BUGON(!*rq->out);
+		dst = kmap_atomic(*rq->out);
+		dst_maptype = 0;
+		goto dstmap_out;
+	}
+
+	/*
+	 * For the case of small output size (especially much less
+	 * than PAGE_SIZE), memcpy the decompressed data rather than
+	 * compressed data is preferred.
+	 */
+	if (rq->outputsize <= PAGE_SIZE * 7 / 8) {
+		dst = erofs_get_pcpubuf(0);
+		if (IS_ERR(dst))
+			return PTR_ERR(dst);
+
+		rq->inplace_io = false;
+		ret = alg->decompress(rq, dst);
+		if (!ret)
+			copy_from_pcpubuf(rq->out, dst, rq->pageofs_out,
+					  rq->outputsize);
+
+		erofs_put_pcpubuf(dst);
+		return ret;
+	}
+
+	ret = alg->prepare_destpages(rq, pagepool);
+	if (ret < 0) {
+		return ret;
+	} else if (ret) {
+		dst = page_address(*rq->out);
+		dst_maptype = 1;
+		goto dstmap_out;
+	}
+
+	dst = erofs_vmap(rq->out, nrpages_out);
+	if (!dst)
+		return -ENOMEM;
+	dst_maptype = 2;
+
+dstmap_out:
+	ret = alg->decompress(rq, dst + rq->pageofs_out);
+
+	if (!dst_maptype)
+		kunmap_atomic(dst);
+	else if (dst_maptype == 2)
+		erofs_vunmap(dst, nrpages_out);
+	return ret;
+}
+
+static int shifted_decompress(const struct z_erofs_decompress_req *rq,
+			      struct list_head *pagepool)
+{
+	const unsigned int nrpages_out =
+		PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
+	const unsigned int righthalf = PAGE_SIZE - rq->pageofs_out;
+	unsigned char *src, *dst;
+
+	if (nrpages_out > 2) {
+		DBG_BUGON(1);
+		return -EIO;
+	}
+
+	if (rq->out[0] == *rq->in) {
+		DBG_BUGON(nrpages_out != 1);
+		return 0;
+	}
+
+	src = kmap_atomic(*rq->in);
+	if (!rq->out[0]) {
+		dst = NULL;
+	} else {
+		dst = kmap_atomic(rq->out[0]);
+		memcpy(dst + rq->pageofs_out, src, righthalf);
+	}
+
+	if (rq->out[1] == *rq->in) {
+		memmove(src, src + righthalf, rq->pageofs_out);
+	} else if (nrpages_out == 2) {
+		if (dst)
+			kunmap_atomic(dst);
+		DBG_BUGON(!rq->out[1]);
+		dst = kmap_atomic(rq->out[1]);
+		memcpy(dst, src + righthalf, rq->pageofs_out);
+	}
+	if (dst)
+		kunmap_atomic(dst);
+	kunmap_atomic(src);
+	return 0;
+}
+
+int z_erofs_decompress(struct z_erofs_decompress_req *rq,
+		       struct list_head *pagepool)
+{
+	if (rq->alg == Z_EROFS_COMPRESSION_SHIFTED)
+		return shifted_decompress(rq, pagepool);
+	return decompress_generic(rq, pagepool);
+}
+
diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c
new file mode 100644
index 000000000000..1976e60e5174
--- /dev/null
+++ b/fs/erofs/dir.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017-2018 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#include "internal.h"
+
+static void debug_one_dentry(unsigned char d_type, const char *de_name,
+			     unsigned int de_namelen)
+{
+#ifdef CONFIG_EROFS_FS_DEBUG
+	/* since the on-disk name could not have the trailing '\0' */
+	unsigned char dbg_namebuf[EROFS_NAME_LEN + 1];
+
+	memcpy(dbg_namebuf, de_name, de_namelen);
+	dbg_namebuf[de_namelen] = '\0';
+
+	debugln("found dirent %s de_len %u d_type %d", dbg_namebuf,
+		de_namelen, d_type);
+#endif
+}
+
+static int erofs_fill_dentries(struct inode *dir, struct dir_context *ctx,
+			       void *dentry_blk, unsigned int *ofs,
+			       unsigned int nameoff, unsigned int maxsize)
+{
+	struct erofs_dirent *de = dentry_blk + *ofs;
+	const struct erofs_dirent *end = dentry_blk + nameoff;
+
+	while (de < end) {
+		const char *de_name;
+		unsigned int de_namelen;
+		unsigned char d_type;
+
+		d_type = fs_ftype_to_dtype(de->file_type);
+
+		nameoff = le16_to_cpu(de->nameoff);
+		de_name = (char *)dentry_blk + nameoff;
+
+		/* the last dirent in the block? */
+		if (de + 1 >= end)
+			de_namelen = strnlen(de_name, maxsize - nameoff);
+		else
+			de_namelen = le16_to_cpu(de[1].nameoff) - nameoff;
+
+		/* a corrupted entry is found */
+		if (unlikely(nameoff + de_namelen > maxsize ||
+			     de_namelen > EROFS_NAME_LEN)) {
+			errln("bogus dirent @ nid %llu", EROFS_V(dir)->nid);
+			DBG_BUGON(1);
+			return -EFSCORRUPTED;
+		}
+
+		debug_one_dentry(d_type, de_name, de_namelen);
+		if (!dir_emit(ctx, de_name, de_namelen,
+			      le64_to_cpu(de->nid), d_type))
+			/* stopped by some reason */
+			return 1;
+		++de;
+		*ofs += sizeof(struct erofs_dirent);
+	}
+	*ofs = maxsize;
+	return 0;
+}
+
+static int erofs_readdir(struct file *f, struct dir_context *ctx)
+{
+	struct inode *dir = file_inode(f);
+	struct address_space *mapping = dir->i_mapping;
+	const size_t dirsize = i_size_read(dir);
+	unsigned int i = ctx->pos / EROFS_BLKSIZ;
+	unsigned int ofs = ctx->pos % EROFS_BLKSIZ;
+	int err = 0;
+	bool initial = true;
+
+	while (ctx->pos < dirsize) {
+		struct page *dentry_page;
+		struct erofs_dirent *de;
+		unsigned int nameoff, maxsize;
+
+		dentry_page = read_mapping_page(mapping, i, NULL);
+		if (dentry_page == ERR_PTR(-ENOMEM)) {
+			err = -ENOMEM;
+			break;
+		} else if (IS_ERR(dentry_page)) {
+			errln("fail to readdir of logical block %u of nid %llu",
+			      i, EROFS_V(dir)->nid);
+			err = -EFSCORRUPTED;
+			break;
+		}
+
+		de = (struct erofs_dirent *)kmap(dentry_page);
+
+		nameoff = le16_to_cpu(de->nameoff);
+
+		if (unlikely(nameoff < sizeof(struct erofs_dirent) ||
+			     nameoff >= PAGE_SIZE)) {
+			errln("%s, invalid de[0].nameoff %u @ nid %llu",
+			      __func__, nameoff, EROFS_V(dir)->nid);
+			err = -EFSCORRUPTED;
+			goto skip_this;
+		}
+
+		maxsize = min_t(unsigned int,
+				dirsize - ctx->pos + ofs, PAGE_SIZE);
+
+		/* search dirents at the arbitrary position */
+		if (unlikely(initial)) {
+			initial = false;
+
+			ofs = roundup(ofs, sizeof(struct erofs_dirent));
+			if (unlikely(ofs >= nameoff))
+				goto skip_this;
+		}
+
+		err = erofs_fill_dentries(dir, ctx, de, &ofs,
+					  nameoff, maxsize);
+skip_this:
+		kunmap(dentry_page);
+
+		put_page(dentry_page);
+
+		ctx->pos = blknr_to_addr(i) + ofs;
+
+		if (unlikely(err))
+			break;
+		++i;
+		ofs = 0;
+	}
+	return err < 0 ? err : 0;
+}
+
+const struct file_operations erofs_dir_fops = {
+	.llseek		= generic_file_llseek,
+	.read		= generic_read_dir,
+	.iterate_shared	= erofs_readdir,
+};
+
diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
new file mode 100644
index 000000000000..afa7d45ca958
--- /dev/null
+++ b/fs/erofs/erofs_fs.h
@@ -0,0 +1,307 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR Apache-2.0 */
+/*
+ * Copyright (C) 2017-2018 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#ifndef __EROFS_FS_H
+#define __EROFS_FS_H
+
+/* Enhanced(Extended) ROM File System */
+#define EROFS_SUPER_OFFSET      1024
+
+/*
+ * Any bits that aren't in EROFS_ALL_REQUIREMENTS should be
+ * incompatible with this kernel version.
+ */
+#define EROFS_REQUIREMENT_LZ4_0PADDING	0x00000001
+#define EROFS_ALL_REQUIREMENTS		EROFS_REQUIREMENT_LZ4_0PADDING
+
+struct erofs_super_block {
+/*  0 */__le32 magic;           /* in the little endian */
+/*  4 */__le32 checksum;        /* crc32c(super_block) */
+/*  8 */__le32 features;        /* (aka. feature_compat) */
+/* 12 */__u8 blkszbits;         /* support block_size == PAGE_SIZE only */
+/* 13 */__u8 reserved;
+
+/* 14 */__le16 root_nid;
+/* 16 */__le64 inos;            /* total valid ino # (== f_files - f_favail) */
+
+/* 24 */__le64 build_time;      /* inode v1 time derivation */
+/* 32 */__le32 build_time_nsec;
+/* 36 */__le32 blocks;          /* used for statfs */
+/* 40 */__le32 meta_blkaddr;
+/* 44 */__le32 xattr_blkaddr;
+/* 48 */__u8 uuid[16];          /* 128-bit uuid for volume */
+/* 64 */__u8 volume_name[16];   /* volume name */
+/* 80 */__le32 requirements;    /* (aka. feature_incompat) */
+
+/* 84 */__u8 reserved2[44];
+} __packed;                     /* 128 bytes */
+
+/*
+ * erofs inode data mapping:
+ * 0 - inode plain without inline data A:
+ * inode, [xattrs], ... | ... | no-holed data
+ * 1 - inode VLE compression B (legacy):
+ * inode, [xattrs], extents ... | ...
+ * 2 - inode plain with inline data C:
+ * inode, [xattrs], last_inline_data, ... | ... | no-holed data
+ * 3 - inode compression D:
+ * inode, [xattrs], map_header, extents ... | ...
+ * 4~7 - reserved
+ */
+enum {
+	EROFS_INODE_FLAT_PLAIN,
+	EROFS_INODE_FLAT_COMPRESSION_LEGACY,
+	EROFS_INODE_FLAT_INLINE,
+	EROFS_INODE_FLAT_COMPRESSION,
+	EROFS_INODE_LAYOUT_MAX
+};
+
+static inline bool erofs_inode_is_data_compressed(unsigned int datamode)
+{
+	if (datamode == EROFS_INODE_FLAT_COMPRESSION)
+		return true;
+	return datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY;
+}
+
+/* bit definitions of inode i_advise */
+#define EROFS_I_VERSION_BITS            1
+#define EROFS_I_DATA_MAPPING_BITS       3
+
+#define EROFS_I_VERSION_BIT             0
+#define EROFS_I_DATA_MAPPING_BIT        1
+
+struct erofs_inode_v1 {
+/*  0 */__le16 i_advise;
+
+/* 1 header + n-1 * 4 bytes inline xattr to keep continuity */
+/*  2 */__le16 i_xattr_icount;
+/*  4 */__le16 i_mode;
+/*  6 */__le16 i_nlink;
+/*  8 */__le32 i_size;
+/* 12 */__le32 i_reserved;
+/* 16 */union {
+		/* file total compressed blocks for data mapping 1 */
+		__le32 compressed_blocks;
+		__le32 raw_blkaddr;
+
+		/* for device files, used to indicate old/new device # */
+		__le32 rdev;
+	} i_u __packed;
+/* 20 */__le32 i_ino;           /* only used for 32-bit stat compatibility */
+/* 24 */__le16 i_uid;
+/* 26 */__le16 i_gid;
+/* 28 */__le32 i_reserved2;
+} __packed;
+
+/* 32 bytes on-disk inode */
+#define EROFS_INODE_LAYOUT_V1   0
+/* 64 bytes on-disk inode */
+#define EROFS_INODE_LAYOUT_V2   1
+
+struct erofs_inode_v2 {
+/*  0 */__le16 i_advise;
+
+/* 1 header + n-1 * 4 bytes inline xattr to keep continuity */
+/*  2 */__le16 i_xattr_icount;
+/*  4 */__le16 i_mode;
+/*  6 */__le16 i_reserved;
+/*  8 */__le64 i_size;
+/* 16 */union {
+		/* file total compressed blocks for data mapping 1 */
+		__le32 compressed_blocks;
+		__le32 raw_blkaddr;
+
+		/* for device files, used to indicate old/new device # */
+		__le32 rdev;
+	} i_u __packed;
+
+	/* only used for 32-bit stat compatibility */
+/* 20 */__le32 i_ino;
+
+/* 24 */__le32 i_uid;
+/* 28 */__le32 i_gid;
+/* 32 */__le64 i_ctime;
+/* 40 */__le32 i_ctime_nsec;
+/* 44 */__le32 i_nlink;
+/* 48 */__u8   i_reserved2[16];
+} __packed;                     /* 64 bytes */
+
+#define EROFS_MAX_SHARED_XATTRS         (128)
+/* h_shared_count between 129 ... 255 are special # */
+#define EROFS_SHARED_XATTR_EXTENT       (255)
+
+/*
+ * inline xattrs (n == i_xattr_icount):
+ * erofs_xattr_ibody_header(1) + (n - 1) * 4 bytes
+ *          12 bytes           /                   \
+ *                            /                     \
+ *                           /-----------------------\
+ *                           |  erofs_xattr_entries+ |
+ *                           +-----------------------+
+ * inline xattrs must starts in erofs_xattr_ibody_header,
+ * for read-only fs, no need to introduce h_refcount
+ */
+struct erofs_xattr_ibody_header {
+	__le32 h_reserved;
+	__u8   h_shared_count;
+	__u8   h_reserved2[7];
+	__le32 h_shared_xattrs[0];      /* shared xattr id array */
+} __packed;
+
+/* Name indexes */
+#define EROFS_XATTR_INDEX_USER              1
+#define EROFS_XATTR_INDEX_POSIX_ACL_ACCESS  2
+#define EROFS_XATTR_INDEX_POSIX_ACL_DEFAULT 3
+#define EROFS_XATTR_INDEX_TRUSTED           4
+#define EROFS_XATTR_INDEX_LUSTRE            5
+#define EROFS_XATTR_INDEX_SECURITY          6
+
+/* xattr entry (for both inline & shared xattrs) */
+struct erofs_xattr_entry {
+	__u8   e_name_len;      /* length of name */
+	__u8   e_name_index;    /* attribute name index */
+	__le16 e_value_size;    /* size of attribute value */
+	/* followed by e_name and e_value */
+	char   e_name[0];       /* attribute name */
+} __packed;
+
+#define ondisk_xattr_ibody_size(count)	({\
+	u32 __count = le16_to_cpu(count); \
+	((__count) == 0) ? 0 : \
+	sizeof(struct erofs_xattr_ibody_header) + \
+		sizeof(__u32) * ((__count) - 1); })
+
+#define EROFS_XATTR_ALIGN(size) round_up(size, sizeof(struct erofs_xattr_entry))
+#define EROFS_XATTR_ENTRY_SIZE(entry) EROFS_XATTR_ALIGN( \
+	sizeof(struct erofs_xattr_entry) + \
+	(entry)->e_name_len + le16_to_cpu((entry)->e_value_size))
+
+/* available compression algorithm types */
+enum {
+	Z_EROFS_COMPRESSION_LZ4,
+	Z_EROFS_COMPRESSION_MAX
+};
+
+/*
+ * bit 0 : COMPACTED_2B indexes (0 - off; 1 - on)
+ *  e.g. for 4k logical cluster size,      4B        if compacted 2B is off;
+ *                                  (4B) + 2B + (4B) if compacted 2B is on.
+ */
+#define Z_EROFS_ADVISE_COMPACTED_2B_BIT         0
+
+#define Z_EROFS_ADVISE_COMPACTED_2B     (1 << Z_EROFS_ADVISE_COMPACTED_2B_BIT)
+
+struct z_erofs_map_header {
+	__le32	h_reserved1;
+	__le16	h_advise;
+	/*
+	 * bit 0-3 : algorithm type of head 1 (logical cluster type 01);
+	 * bit 4-7 : algorithm type of head 2 (logical cluster type 11).
+	 */
+	__u8	h_algorithmtype;
+	/*
+	 * bit 0-2 : logical cluster bits - 12, e.g. 0 for 4096;
+	 * bit 3-4 : (physical - logical) cluster bits of head 1:
+	 *       For example, if logical clustersize = 4096, 1 for 8192.
+	 * bit 5-7 : (physical - logical) cluster bits of head 2.
+	 */
+	__u8	h_clusterbits;
+};
+
+#define Z_EROFS_VLE_LEGACY_HEADER_PADDING       8
+
+/*
+ * Z_EROFS Variable-sized Logical Extent cluster type:
+ *    0 - literal (uncompressed) cluster
+ *    1 - compressed cluster (for the head logical cluster)
+ *    2 - compressed cluster (for the other logical clusters)
+ *
+ * In detail,
+ *    0 - literal (uncompressed) cluster,
+ *        di_advise = 0
+ *        di_clusterofs = the literal data offset of the cluster
+ *        di_blkaddr = the blkaddr of the literal cluster
+ *
+ *    1 - compressed cluster (for the head logical cluster)
+ *        di_advise = 1
+ *        di_clusterofs = the decompressed data offset of the cluster
+ *        di_blkaddr = the blkaddr of the compressed cluster
+ *
+ *    2 - compressed cluster (for the other logical clusters)
+ *        di_advise = 2
+ *        di_clusterofs =
+ *           the decompressed data offset in its own head cluster
+ *        di_u.delta[0] = distance to its corresponding head cluster
+ *        di_u.delta[1] = distance to its corresponding tail cluster
+ *                (di_advise could be 0, 1 or 2)
+ */
+enum {
+	Z_EROFS_VLE_CLUSTER_TYPE_PLAIN,
+	Z_EROFS_VLE_CLUSTER_TYPE_HEAD,
+	Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD,
+	Z_EROFS_VLE_CLUSTER_TYPE_RESERVED,
+	Z_EROFS_VLE_CLUSTER_TYPE_MAX
+};
+
+#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS        2
+#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT         0
+
+struct z_erofs_vle_decompressed_index {
+	__le16 di_advise;
+	/* where to decompress in the head cluster */
+	__le16 di_clusterofs;
+
+	union {
+		/* for the head cluster */
+		__le32 blkaddr;
+		/*
+		 * for the rest clusters
+		 * eg. for 4k page-sized cluster, maximum 4K*64k = 256M)
+		 * [0] - pointing to the head cluster
+		 * [1] - pointing to the tail cluster
+		 */
+		__le16 delta[2];
+	} di_u __packed;		/* 8 bytes */
+} __packed;
+
+#define Z_EROFS_VLE_LEGACY_INDEX_ALIGN(size) \
+	(round_up(size, sizeof(struct z_erofs_vle_decompressed_index)) + \
+	 sizeof(struct z_erofs_map_header) + Z_EROFS_VLE_LEGACY_HEADER_PADDING)
+
+/* dirent sorts in alphabet order, thus we can do binary search */
+struct erofs_dirent {
+	__le64 nid;     /*  0, node number */
+	__le16 nameoff; /*  8, start offset of file name */
+	__u8 file_type; /* 10, file type */
+	__u8 reserved;  /* 11, reserved */
+} __packed;
+
+/*
+ * EROFS file types should match generic FT_* types and
+ * it seems no need to add BUILD_BUG_ONs since potential
+ * unmatchness will break other fses as well...
+ */
+
+#define EROFS_NAME_LEN      255
+
+/* check the EROFS on-disk layout strictly at compile time */
+static inline void erofs_check_ondisk_layout_definitions(void)
+{
+	BUILD_BUG_ON(sizeof(struct erofs_super_block) != 128);
+	BUILD_BUG_ON(sizeof(struct erofs_inode_v1) != 32);
+	BUILD_BUG_ON(sizeof(struct erofs_inode_v2) != 64);
+	BUILD_BUG_ON(sizeof(struct erofs_xattr_ibody_header) != 12);
+	BUILD_BUG_ON(sizeof(struct erofs_xattr_entry) != 4);
+	BUILD_BUG_ON(sizeof(struct z_erofs_map_header) != 8);
+	BUILD_BUG_ON(sizeof(struct z_erofs_vle_decompressed_index) != 8);
+	BUILD_BUG_ON(sizeof(struct erofs_dirent) != 12);
+
+	BUILD_BUG_ON(BIT(Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS) <
+		     Z_EROFS_VLE_CLUSTER_TYPE_MAX - 1);
+}
+
+#endif
+
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
new file mode 100644
index 000000000000..80f4fe919ee7
--- /dev/null
+++ b/fs/erofs/inode.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017-2018 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#include "xattr.h"
+
+#include <trace/events/erofs.h>
+
+/* no locking */
+static int read_inode(struct inode *inode, void *data)
+{
+	struct erofs_vnode *vi = EROFS_V(inode);
+	struct erofs_inode_v1 *v1 = data;
+	const unsigned int advise = le16_to_cpu(v1->i_advise);
+	erofs_blk_t nblks = 0;
+
+	vi->datamode = __inode_data_mapping(advise);
+
+	if (unlikely(vi->datamode >= EROFS_INODE_LAYOUT_MAX)) {
+		errln("unsupported data mapping %u of nid %llu",
+		      vi->datamode, vi->nid);
+		DBG_BUGON(1);
+		return -EOPNOTSUPP;
+	}
+
+	if (__inode_version(advise) == EROFS_INODE_LAYOUT_V2) {
+		struct erofs_inode_v2 *v2 = data;
+
+		vi->inode_isize = sizeof(struct erofs_inode_v2);
+		vi->xattr_isize = ondisk_xattr_ibody_size(v2->i_xattr_icount);
+
+		inode->i_mode = le16_to_cpu(v2->i_mode);
+		if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+		    S_ISLNK(inode->i_mode))
+			vi->raw_blkaddr = le32_to_cpu(v2->i_u.raw_blkaddr);
+		else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
+			inode->i_rdev =
+				new_decode_dev(le32_to_cpu(v2->i_u.rdev));
+		else if (S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode))
+			inode->i_rdev = 0;
+		else
+			goto bogusimode;
+
+		i_uid_write(inode, le32_to_cpu(v2->i_uid));
+		i_gid_write(inode, le32_to_cpu(v2->i_gid));
+		set_nlink(inode, le32_to_cpu(v2->i_nlink));
+
+		/* ns timestamp */
+		inode->i_mtime.tv_sec = inode->i_ctime.tv_sec =
+			le64_to_cpu(v2->i_ctime);
+		inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec =
+			le32_to_cpu(v2->i_ctime_nsec);
+
+		inode->i_size = le64_to_cpu(v2->i_size);
+
+		/* total blocks for compressed files */
+		if (is_inode_layout_compression(inode))
+			nblks = le32_to_cpu(v2->i_u.compressed_blocks);
+	} else if (__inode_version(advise) == EROFS_INODE_LAYOUT_V1) {
+		struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
+
+		vi->inode_isize = sizeof(struct erofs_inode_v1);
+		vi->xattr_isize = ondisk_xattr_ibody_size(v1->i_xattr_icount);
+
+		inode->i_mode = le16_to_cpu(v1->i_mode);
+		if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+		    S_ISLNK(inode->i_mode))
+			vi->raw_blkaddr = le32_to_cpu(v1->i_u.raw_blkaddr);
+		else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
+			inode->i_rdev =
+				new_decode_dev(le32_to_cpu(v1->i_u.rdev));
+		else if (S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode))
+			inode->i_rdev = 0;
+		else
+			goto bogusimode;
+
+		i_uid_write(inode, le16_to_cpu(v1->i_uid));
+		i_gid_write(inode, le16_to_cpu(v1->i_gid));
+		set_nlink(inode, le16_to_cpu(v1->i_nlink));
+
+		/* use build time to derive all file time */
+		inode->i_mtime.tv_sec = inode->i_ctime.tv_sec =
+			sbi->build_time;
+		inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec =
+			sbi->build_time_nsec;
+
+		inode->i_size = le32_to_cpu(v1->i_size);
+		if (is_inode_layout_compression(inode))
+			nblks = le32_to_cpu(v1->i_u.compressed_blocks);
+	} else {
+		errln("unsupported on-disk inode version %u of nid %llu",
+		      __inode_version(advise), vi->nid);
+		DBG_BUGON(1);
+		return -EOPNOTSUPP;
+	}
+
+	if (!nblks)
+		/* measure inode.i_blocks as generic filesystems */
+		inode->i_blocks = roundup(inode->i_size, EROFS_BLKSIZ) >> 9;
+	else
+		inode->i_blocks = nblks << LOG_SECTORS_PER_BLOCK;
+	return 0;
+
+bogusimode:
+	errln("bogus i_mode (%o) @ nid %llu", inode->i_mode, vi->nid);
+	DBG_BUGON(1);
+	return -EFSCORRUPTED;
+}
+
+/*
+ * try_lock can be required since locking order is:
+ *   file data(fs_inode)
+ *        meta(bd_inode)
+ * but the majority of the callers is "iget",
+ * in that case we are pretty sure no deadlock since
+ * no data operations exist. However I tend to
+ * try_lock since it takes no much overhead and
+ * will success immediately.
+ */
+static int fill_inline_data(struct inode *inode, void *data,
+			    unsigned int m_pofs)
+{
+	struct erofs_vnode *vi = EROFS_V(inode);
+	struct erofs_sb_info *sbi = EROFS_I_SB(inode);
+
+	/* should be inode inline C */
+	if (!is_inode_flat_inline(inode))
+		return 0;
+
+	/* fast symlink (following ext4) */
+	if (S_ISLNK(inode->i_mode) && inode->i_size < PAGE_SIZE) {
+		char *lnk = erofs_kmalloc(sbi, inode->i_size + 1, GFP_KERNEL);
+
+		if (unlikely(!lnk))
+			return -ENOMEM;
+
+		m_pofs += vi->inode_isize + vi->xattr_isize;
+
+		/* inline symlink data shouldn't across page boundary as well */
+		if (unlikely(m_pofs + inode->i_size > PAGE_SIZE)) {
+			kfree(lnk);
+			errln("inline data cross block boundary @ nid %llu",
+			      vi->nid);
+			DBG_BUGON(1);
+			return -EFSCORRUPTED;
+		}
+
+		/* get in-page inline data */
+		memcpy(lnk, data + m_pofs, inode->i_size);
+		lnk[inode->i_size] = '\0';
+
+		inode->i_link = lnk;
+		set_inode_fast_symlink(inode);
+	}
+	return 0;
+}
+
+static int fill_inode(struct inode *inode, int isdir)
+{
+	struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
+	struct erofs_vnode *vi = EROFS_V(inode);
+	struct page *page;
+	void *data;
+	int err;
+	erofs_blk_t blkaddr;
+	unsigned int ofs;
+	erofs_off_t inode_loc;
+
+	trace_erofs_fill_inode(inode, isdir);
+	inode_loc = iloc(sbi, vi->nid);
+	blkaddr = erofs_blknr(inode_loc);
+	ofs = erofs_blkoff(inode_loc);
+
+	debugln("%s, reading inode nid %llu at %u of blkaddr %u",
+		__func__, vi->nid, ofs, blkaddr);
+
+	page = erofs_get_meta_page(inode->i_sb, blkaddr, isdir);
+
+	if (IS_ERR(page)) {
+		errln("failed to get inode (nid: %llu) page, err %ld",
+		      vi->nid, PTR_ERR(page));
+		return PTR_ERR(page);
+	}
+
+	DBG_BUGON(!PageUptodate(page));
+	data = page_address(page);
+
+	err = read_inode(inode, data + ofs);
+	if (!err) {
+		/* setup the new inode */
+		if (S_ISREG(inode->i_mode)) {
+			inode->i_op = &erofs_generic_iops;
+			inode->i_fop = &generic_ro_fops;
+		} else if (S_ISDIR(inode->i_mode)) {
+			inode->i_op = &erofs_dir_iops;
+			inode->i_fop = &erofs_dir_fops;
+		} else if (S_ISLNK(inode->i_mode)) {
+			/* by default, page_get_link is used for symlink */
+			inode->i_op = &erofs_symlink_iops;
+			inode_nohighmem(inode);
+		} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
+			S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
+			inode->i_op = &erofs_generic_iops;
+			init_special_inode(inode, inode->i_mode, inode->i_rdev);
+			goto out_unlock;
+		} else {
+			err = -EFSCORRUPTED;
+			goto out_unlock;
+		}
+
+		if (is_inode_layout_compression(inode)) {
+			err = z_erofs_fill_inode(inode);
+			goto out_unlock;
+		}
+
+		inode->i_mapping->a_ops = &erofs_raw_access_aops;
+
+		/* fill last page if inline data is available */
+		err = fill_inline_data(inode, data, ofs);
+	}
+
+out_unlock:
+	unlock_page(page);
+	put_page(page);
+	return err;
+}
+
+/*
+ * erofs nid is 64bits, but i_ino is 'unsigned long', therefore
+ * we should do more for 32-bit platform to find the right inode.
+ */
+#if BITS_PER_LONG == 32
+static int erofs_ilookup_test_actor(struct inode *inode, void *opaque)
+{
+	const erofs_nid_t nid = *(erofs_nid_t *)opaque;
+
+	return EROFS_V(inode)->nid == nid;
+}
+
+static int erofs_iget_set_actor(struct inode *inode, void *opaque)
+{
+	const erofs_nid_t nid = *(erofs_nid_t *)opaque;
+
+	inode->i_ino = erofs_inode_hash(nid);
+	return 0;
+}
+#endif
+
+static inline struct inode *erofs_iget_locked(struct super_block *sb,
+					      erofs_nid_t nid)
+{
+	const unsigned long hashval = erofs_inode_hash(nid);
+
+#if BITS_PER_LONG >= 64
+	/* it is safe to use iget_locked for >= 64-bit platform */
+	return iget_locked(sb, hashval);
+#else
+	return iget5_locked(sb, hashval, erofs_ilookup_test_actor,
+		erofs_iget_set_actor, &nid);
+#endif
+}
+
+struct inode *erofs_iget(struct super_block *sb,
+			 erofs_nid_t nid,
+			 bool isdir)
+{
+	struct inode *inode = erofs_iget_locked(sb, nid);
+
+	if (unlikely(!inode))
+		return ERR_PTR(-ENOMEM);
+
+	if (inode->i_state & I_NEW) {
+		int err;
+		struct erofs_vnode *vi = EROFS_V(inode);
+
+		vi->nid = nid;
+
+		err = fill_inode(inode, isdir);
+		if (likely(!err))
+			unlock_new_inode(inode);
+		else {
+			iget_failed(inode);
+			inode = ERR_PTR(err);
+		}
+	}
+	return inode;
+}
+
+int erofs_getattr(const struct path *path, struct kstat *stat,
+		  u32 request_mask, unsigned int query_flags)
+{
+	struct inode *const inode = d_inode(path->dentry);
+
+	if (is_inode_layout_compression(inode))
+		stat->attributes |= STATX_ATTR_COMPRESSED;
+
+	stat->attributes |= STATX_ATTR_IMMUTABLE;
+	stat->attributes_mask |= (STATX_ATTR_COMPRESSED |
+				  STATX_ATTR_IMMUTABLE);
+
+	generic_fillattr(inode, stat);
+	return 0;
+}
+
+const struct inode_operations erofs_generic_iops = {
+	.getattr = erofs_getattr,
+#ifdef CONFIG_EROFS_FS_XATTR
+	.listxattr = erofs_listxattr,
+#endif
+	.get_acl = erofs_get_acl,
+};
+
+const struct inode_operations erofs_symlink_iops = {
+	.get_link = page_get_link,
+	.getattr = erofs_getattr,
+#ifdef CONFIG_EROFS_FS_XATTR
+	.listxattr = erofs_listxattr,
+#endif
+	.get_acl = erofs_get_acl,
+};
+
+const struct inode_operations erofs_fast_symlink_iops = {
+	.get_link = simple_get_link,
+	.getattr = erofs_getattr,
+#ifdef CONFIG_EROFS_FS_XATTR
+	.listxattr = erofs_listxattr,
+#endif
+	.get_acl = erofs_get_acl,
+};
+
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
new file mode 100644
index 000000000000..620b73fcc416
--- /dev/null
+++ b/fs/erofs/internal.h
@@ -0,0 +1,553 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017-2018 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#ifndef __EROFS_INTERNAL_H
+#define __EROFS_INTERNAL_H
+
+#include <linux/fs.h>
+#include <linux/dcache.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/bio.h>
+#include <linux/buffer_head.h>
+#include <linux/magic.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include "erofs_fs.h"
+
+/* redefine pr_fmt "erofs: " */
+#undef pr_fmt
+#define pr_fmt(fmt) "erofs: " fmt
+
+#define errln(x, ...)   pr_err(x "\n", ##__VA_ARGS__)
+#define infoln(x, ...)  pr_info(x "\n", ##__VA_ARGS__)
+#ifdef CONFIG_EROFS_FS_DEBUG
+#define debugln(x, ...) pr_debug(x "\n", ##__VA_ARGS__)
+#define DBG_BUGON               BUG_ON
+#else
+#define debugln(x, ...)         ((void)0)
+#define DBG_BUGON(x)            ((void)(x))
+#endif	/* !CONFIG_EROFS_FS_DEBUG */
+
+enum {
+	FAULT_KMALLOC,
+	FAULT_READ_IO,
+	FAULT_MAX,
+};
+
+#ifdef CONFIG_EROFS_FAULT_INJECTION
+extern const char *erofs_fault_name[FAULT_MAX];
+#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type)))
+
+struct erofs_fault_info {
+	atomic_t inject_ops;
+	unsigned int inject_rate;
+	unsigned int inject_type;
+};
+#endif	/* CONFIG_EROFS_FAULT_INJECTION */
+
+/* EROFS_SUPER_MAGIC_V1 to represent the whole file system */
+#define EROFS_SUPER_MAGIC   EROFS_SUPER_MAGIC_V1
+
+typedef u64 erofs_nid_t;
+typedef u64 erofs_off_t;
+/* data type for filesystem-wide blocks number */
+typedef u32 erofs_blk_t;
+
+struct erofs_sb_info {
+#ifdef CONFIG_EROFS_FS_ZIP
+	/* list for all registered superblocks, mainly for shrinker */
+	struct list_head list;
+	struct mutex umount_mutex;
+
+	/* the dedicated workstation for compression */
+	struct radix_tree_root workstn_tree;
+
+	/* threshold for decompression synchronously */
+	unsigned int max_sync_decompress_pages;
+
+	unsigned int shrinker_run_no;
+
+	/* current strategy of how to use managed cache */
+	unsigned char cache_strategy;
+
+	/* pseudo inode to manage cached pages */
+	struct inode *managed_cache;
+#endif	/* CONFIG_EROFS_FS_ZIP */
+	u32 blocks;
+	u32 meta_blkaddr;
+#ifdef CONFIG_EROFS_FS_XATTR
+	u32 xattr_blkaddr;
+#endif
+
+	/* inode slot unit size in bit shift */
+	unsigned char islotbits;
+
+	u32 build_time_nsec;
+	u64 build_time;
+
+	/* what we really care is nid, rather than ino.. */
+	erofs_nid_t root_nid;
+	/* used for statfs, f_files - f_favail */
+	u64 inos;
+
+	u8 uuid[16];                    /* 128-bit uuid for volume */
+	u8 volume_name[16];             /* volume name */
+	u32 requirements;
+
+	unsigned int mount_opt;
+
+#ifdef CONFIG_EROFS_FAULT_INJECTION
+	struct erofs_fault_info fault_info;	/* For fault injection */
+#endif
+};
+
+#ifdef CONFIG_EROFS_FAULT_INJECTION
+#define erofs_show_injection_info(type)					\
+	infoln("inject %s in %s of %pS", erofs_fault_name[type],        \
+		__func__, __builtin_return_address(0))
+
+static inline bool time_to_inject(struct erofs_sb_info *sbi, int type)
+{
+	struct erofs_fault_info *ffi = &sbi->fault_info;
+
+	if (!ffi->inject_rate)
+		return false;
+
+	if (!IS_FAULT_SET(ffi, type))
+		return false;
+
+	atomic_inc(&ffi->inject_ops);
+	if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) {
+		atomic_set(&ffi->inject_ops, 0);
+		return true;
+	}
+	return false;
+}
+#else
+static inline bool time_to_inject(struct erofs_sb_info *sbi, int type)
+{
+	return false;
+}
+
+static inline void erofs_show_injection_info(int type)
+{
+}
+#endif	/* !CONFIG_EROFS_FAULT_INJECTION */
+
+static inline void *erofs_kmalloc(struct erofs_sb_info *sbi,
+					size_t size, gfp_t flags)
+{
+	if (time_to_inject(sbi, FAULT_KMALLOC)) {
+		erofs_show_injection_info(FAULT_KMALLOC);
+		return NULL;
+	}
+	return kmalloc(size, flags);
+}
+
+#define EROFS_SB(sb) ((struct erofs_sb_info *)(sb)->s_fs_info)
+#define EROFS_I_SB(inode) ((struct erofs_sb_info *)(inode)->i_sb->s_fs_info)
+
+/* Mount flags set via mount options or defaults */
+#define EROFS_MOUNT_XATTR_USER		0x00000010
+#define EROFS_MOUNT_POSIX_ACL		0x00000020
+#define EROFS_MOUNT_FAULT_INJECTION	0x00000040
+
+#define clear_opt(sbi, option)	((sbi)->mount_opt &= ~EROFS_MOUNT_##option)
+#define set_opt(sbi, option)	((sbi)->mount_opt |= EROFS_MOUNT_##option)
+#define test_opt(sbi, option)	((sbi)->mount_opt & EROFS_MOUNT_##option)
+
+#ifdef CONFIG_EROFS_FS_ZIP
+enum {
+	EROFS_ZIP_CACHE_DISABLED,
+	EROFS_ZIP_CACHE_READAHEAD,
+	EROFS_ZIP_CACHE_READAROUND
+};
+
+#define EROFS_LOCKED_MAGIC     (INT_MIN | 0xE0F510CCL)
+
+/* basic unit of the workstation of a super_block */
+struct erofs_workgroup {
+	/* the workgroup index in the workstation */
+	pgoff_t index;
+
+	/* overall workgroup reference count */
+	atomic_t refcount;
+};
+
+#if defined(CONFIG_SMP)
+static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
+						 int val)
+{
+	preempt_disable();
+	if (val != atomic_cmpxchg(&grp->refcount, val, EROFS_LOCKED_MAGIC)) {
+		preempt_enable();
+		return false;
+	}
+	return true;
+}
+
+static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp,
+					    int orig_val)
+{
+	/*
+	 * other observers should notice all modifications
+	 * in the freezing period.
+	 */
+	smp_mb();
+	atomic_set(&grp->refcount, orig_val);
+	preempt_enable();
+}
+
+static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
+{
+	return atomic_cond_read_relaxed(&grp->refcount,
+					VAL != EROFS_LOCKED_MAGIC);
+}
+#else
+static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
+						 int val)
+{
+	preempt_disable();
+	/* no need to spin on UP platforms, let's just disable preemption. */
+	if (val != atomic_read(&grp->refcount)) {
+		preempt_enable();
+		return false;
+	}
+	return true;
+}
+
+static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp,
+					    int orig_val)
+{
+	preempt_enable();
+}
+
+static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
+{
+	int v = atomic_read(&grp->refcount);
+
+	/* workgroup is never freezed on uniprocessor systems */
+	DBG_BUGON(v == EROFS_LOCKED_MAGIC);
+	return v;
+}
+#endif	/* !CONFIG_SMP */
+
+/* hard limit of pages per compressed cluster */
+#define Z_EROFS_CLUSTER_MAX_PAGES       (CONFIG_EROFS_FS_CLUSTER_PAGE_LIMIT)
+#define EROFS_PCPUBUF_NR_PAGES          Z_EROFS_CLUSTER_MAX_PAGES
+#else
+#define EROFS_PCPUBUF_NR_PAGES          0
+#endif	/* !CONFIG_EROFS_FS_ZIP */
+
+/* we strictly follow PAGE_SIZE and no buffer head yet */
+#define LOG_BLOCK_SIZE		PAGE_SHIFT
+
+#undef LOG_SECTORS_PER_BLOCK
+#define LOG_SECTORS_PER_BLOCK	(PAGE_SHIFT - 9)
+
+#undef SECTORS_PER_BLOCK
+#define SECTORS_PER_BLOCK	(1 << SECTORS_PER_BLOCK)
+
+#define EROFS_BLKSIZ		(1 << LOG_BLOCK_SIZE)
+
+#if (EROFS_BLKSIZ % 4096 || !EROFS_BLKSIZ)
+#error erofs cannot be used in this platform
+#endif
+
+#define EROFS_IO_MAX_RETRIES_NOFAIL     5
+
+#define ROOT_NID(sb)		((sb)->root_nid)
+
+#define erofs_blknr(addr)       ((addr) / EROFS_BLKSIZ)
+#define erofs_blkoff(addr)      ((addr) % EROFS_BLKSIZ)
+#define blknr_to_addr(nr)       ((erofs_off_t)(nr) * EROFS_BLKSIZ)
+
+static inline erofs_off_t iloc(struct erofs_sb_info *sbi, erofs_nid_t nid)
+{
+	return blknr_to_addr(sbi->meta_blkaddr) + (nid << sbi->islotbits);
+}
+
+/* atomic flag definitions */
+#define EROFS_V_EA_INITED_BIT	0
+#define EROFS_V_Z_INITED_BIT	1
+
+/* bitlock definitions (arranged in reverse order) */
+#define EROFS_V_BL_XATTR_BIT	(BITS_PER_LONG - 1)
+#define EROFS_V_BL_Z_BIT	(BITS_PER_LONG - 2)
+
+struct erofs_vnode {
+	erofs_nid_t nid;
+
+	/* atomic flags (including bitlocks) */
+	unsigned long flags;
+
+	unsigned char datamode;
+	unsigned char inode_isize;
+	unsigned short xattr_isize;
+
+	unsigned int xattr_shared_count;
+	unsigned int *xattr_shared_xattrs;
+
+	union {
+		erofs_blk_t raw_blkaddr;
+#ifdef CONFIG_EROFS_FS_ZIP
+		struct {
+			unsigned short z_advise;
+			unsigned char  z_algorithmtype[2];
+			unsigned char  z_logical_clusterbits;
+			unsigned char  z_physical_clusterbits[2];
+		};
+#endif	/* CONFIG_EROFS_FS_ZIP */
+	};
+	/* the corresponding vfs inode */
+	struct inode vfs_inode;
+};
+
+#define EROFS_V(ptr)	\
+	container_of(ptr, struct erofs_vnode, vfs_inode)
+
+#define __inode_advise(x, bit, bits) \
+	(((x) >> (bit)) & ((1 << (bits)) - 1))
+
+#define __inode_version(advise)	\
+	__inode_advise(advise, EROFS_I_VERSION_BIT,	\
+		EROFS_I_VERSION_BITS)
+
+#define __inode_data_mapping(advise)	\
+	__inode_advise(advise, EROFS_I_DATA_MAPPING_BIT,\
+		EROFS_I_DATA_MAPPING_BITS)
+
+static inline unsigned long inode_datablocks(struct inode *inode)
+{
+	/* since i_size cannot be changed */
+	return DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ);
+}
+
+static inline bool is_inode_layout_compression(struct inode *inode)
+{
+	return erofs_inode_is_data_compressed(EROFS_V(inode)->datamode);
+}
+
+static inline bool is_inode_flat_inline(struct inode *inode)
+{
+	return EROFS_V(inode)->datamode == EROFS_INODE_FLAT_INLINE;
+}
+
+extern const struct super_operations erofs_sops;
+
+extern const struct address_space_operations erofs_raw_access_aops;
+#ifdef CONFIG_EROFS_FS_ZIP
+extern const struct address_space_operations z_erofs_vle_normalaccess_aops;
+#endif
+
+/*
+ * Logical to physical block mapping, used by erofs_map_blocks()
+ *
+ * Different with other file systems, it is used for 2 access modes:
+ *
+ * 1) RAW access mode:
+ *
+ * Users pass a valid (m_lblk, m_lofs -- usually 0) pair,
+ * and get the valid m_pblk, m_pofs and the longest m_len(in bytes).
+ *
+ * Note that m_lblk in the RAW access mode refers to the number of
+ * the compressed ondisk block rather than the uncompressed
+ * in-memory block for the compressed file.
+ *
+ * m_pofs equals to m_lofs except for the inline data page.
+ *
+ * 2) Normal access mode:
+ *
+ * If the inode is not compressed, it has no difference with
+ * the RAW access mode. However, if the inode is compressed,
+ * users should pass a valid (m_lblk, m_lofs) pair, and get
+ * the needed m_pblk, m_pofs, m_len to get the compressed data
+ * and the updated m_lblk, m_lofs which indicates the start
+ * of the corresponding uncompressed data in the file.
+ */
+enum {
+	BH_Zipped = BH_PrivateStart,
+	BH_FullMapped,
+};
+
+/* Has a disk mapping */
+#define EROFS_MAP_MAPPED	(1 << BH_Mapped)
+/* Located in metadata (could be copied from bd_inode) */
+#define EROFS_MAP_META		(1 << BH_Meta)
+/* The extent has been compressed */
+#define EROFS_MAP_ZIPPED	(1 << BH_Zipped)
+/* The length of extent is full */
+#define EROFS_MAP_FULL_MAPPED	(1 << BH_FullMapped)
+
+struct erofs_map_blocks {
+	erofs_off_t m_pa, m_la;
+	u64 m_plen, m_llen;
+
+	unsigned int m_flags;
+
+	struct page *mpage;
+};
+
+/* Flags used by erofs_map_blocks() */
+#define EROFS_GET_BLOCKS_RAW    0x0001
+
+/* zmap.c */
+#ifdef CONFIG_EROFS_FS_ZIP
+int z_erofs_fill_inode(struct inode *inode);
+int z_erofs_map_blocks_iter(struct inode *inode,
+			    struct erofs_map_blocks *map,
+			    int flags);
+#else
+static inline int z_erofs_fill_inode(struct inode *inode) { return -EOPNOTSUPP; }
+static inline int z_erofs_map_blocks_iter(struct inode *inode,
+					  struct erofs_map_blocks *map,
+					  int flags)
+{
+	return -EOPNOTSUPP;
+}
+#endif	/* !CONFIG_EROFS_FS_ZIP */
+
+/* data.c */
+static inline struct bio *erofs_grab_bio(struct super_block *sb,
+					 erofs_blk_t blkaddr,
+					 unsigned int nr_pages,
+					 void *bi_private, bio_end_io_t endio,
+					 bool nofail)
+{
+	const gfp_t gfp = GFP_NOIO;
+	struct bio *bio;
+
+	do {
+		if (nr_pages == 1) {
+			bio = bio_alloc(gfp | (nofail ? __GFP_NOFAIL : 0), 1);
+			if (unlikely(!bio)) {
+				DBG_BUGON(nofail);
+				return ERR_PTR(-ENOMEM);
+			}
+			break;
+		}
+		bio = bio_alloc(gfp, nr_pages);
+		nr_pages /= 2;
+	} while (unlikely(!bio));
+
+	bio->bi_end_io = endio;
+	bio_set_dev(bio, sb->s_bdev);
+	bio->bi_iter.bi_sector = (sector_t)blkaddr << LOG_SECTORS_PER_BLOCK;
+	bio->bi_private = bi_private;
+	return bio;
+}
+
+static inline void __submit_bio(struct bio *bio, unsigned int op,
+				unsigned int op_flags)
+{
+	bio_set_op_attrs(bio, op, op_flags);
+	submit_bio(bio);
+}
+
+struct page *__erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr,
+				   bool prio, bool nofail);
+
+static inline struct page *erofs_get_meta_page(struct super_block *sb,
+	erofs_blk_t blkaddr, bool prio)
+{
+	return __erofs_get_meta_page(sb, blkaddr, prio, false);
+}
+
+int erofs_map_blocks(struct inode *, struct erofs_map_blocks *, int);
+
+static inline struct page *erofs_get_inline_page(struct inode *inode,
+						 erofs_blk_t blkaddr)
+{
+	return erofs_get_meta_page(inode->i_sb, blkaddr,
+				   S_ISDIR(inode->i_mode));
+}
+
+/* inode.c */
+static inline unsigned long erofs_inode_hash(erofs_nid_t nid)
+{
+#if BITS_PER_LONG == 32
+	return (nid >> 32) ^ (nid & 0xffffffff);
+#else
+	return nid;
+#endif
+}
+
+extern const struct inode_operations erofs_generic_iops;
+extern const struct inode_operations erofs_symlink_iops;
+extern const struct inode_operations erofs_fast_symlink_iops;
+
+static inline void set_inode_fast_symlink(struct inode *inode)
+{
+	inode->i_op = &erofs_fast_symlink_iops;
+}
+
+static inline bool is_inode_fast_symlink(struct inode *inode)
+{
+	return inode->i_op == &erofs_fast_symlink_iops;
+}
+
+struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid, bool dir);
+int erofs_getattr(const struct path *path, struct kstat *stat,
+		  u32 request_mask, unsigned int query_flags);
+
+/* namei.c */
+extern const struct inode_operations erofs_dir_iops;
+
+int erofs_namei(struct inode *dir, struct qstr *name,
+		erofs_nid_t *nid, unsigned int *d_type);
+
+/* dir.c */
+extern const struct file_operations erofs_dir_fops;
+
+/* utils.c / zdata.c */
+struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp, bool nofail);
+
+#if (EROFS_PCPUBUF_NR_PAGES > 0)
+void *erofs_get_pcpubuf(unsigned int pagenr);
+#define erofs_put_pcpubuf(buf) do { \
+	(void)&(buf);	\
+	preempt_enable();	\
+} while (0)
+#else
+static inline void *erofs_get_pcpubuf(unsigned int pagenr)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+#define erofs_put_pcpubuf(buf) do {} while (0)
+#endif
+
+#ifdef CONFIG_EROFS_FS_ZIP
+int erofs_workgroup_put(struct erofs_workgroup *grp);
+struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb,
+					     pgoff_t index, bool *tag);
+int erofs_register_workgroup(struct super_block *sb,
+			     struct erofs_workgroup *grp, bool tag);
+void erofs_workgroup_free_rcu(struct erofs_workgroup *grp);
+void erofs_shrinker_register(struct super_block *sb);
+void erofs_shrinker_unregister(struct super_block *sb);
+int __init erofs_init_shrinker(void);
+void erofs_exit_shrinker(void);
+int __init z_erofs_init_zip_subsystem(void);
+void z_erofs_exit_zip_subsystem(void);
+int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
+				       struct erofs_workgroup *egrp);
+int erofs_try_to_free_cached_page(struct address_space *mapping,
+				  struct page *page);
+#else
+static inline void erofs_shrinker_register(struct super_block *sb) {}
+static inline void erofs_shrinker_unregister(struct super_block *sb) {}
+static inline int erofs_init_shrinker(void) { return 0; }
+static inline void erofs_exit_shrinker(void) {}
+static inline int z_erofs_init_zip_subsystem(void) { return 0; }
+static inline void z_erofs_exit_zip_subsystem(void) {}
+#endif	/* !CONFIG_EROFS_FS_ZIP */
+
+#define EFSCORRUPTED    EUCLEAN         /* Filesystem is corrupted */
+
+#endif	/* __EROFS_INTERNAL_H */
+
diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c
new file mode 100644
index 000000000000..8832b5d95d91
--- /dev/null
+++ b/fs/erofs/namei.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017-2018 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#include "xattr.h"
+
+#include <trace/events/erofs.h>
+
+struct erofs_qstr {
+	const unsigned char *name;
+	const unsigned char *end;
+};
+
+/* based on the end of qn is accurate and it must have the trailing '\0' */
+static inline int dirnamecmp(const struct erofs_qstr *qn,
+			     const struct erofs_qstr *qd,
+			     unsigned int *matched)
+{
+	unsigned int i = *matched;
+
+	/*
+	 * on-disk error, let's only BUG_ON in the debugging mode.
+	 * otherwise, it will return 1 to just skip the invalid name
+	 * and go on (in consideration of the lookup performance).
+	 */
+	DBG_BUGON(qd->name > qd->end);
+
+	/* qd could not have trailing '\0' */
+	/* However it is absolutely safe if < qd->end */
+	while (qd->name + i < qd->end && qd->name[i] != '\0') {
+		if (qn->name[i] != qd->name[i]) {
+			*matched = i;
+			return qn->name[i] > qd->name[i] ? 1 : -1;
+		}
+		++i;
+	}
+	*matched = i;
+	/* See comments in __d_alloc on the terminating NUL character */
+	return qn->name[i] == '\0' ? 0 : 1;
+}
+
+#define nameoff_from_disk(off, sz)	(le16_to_cpu(off) & ((sz) - 1))
+
+static struct erofs_dirent *find_target_dirent(struct erofs_qstr *name,
+					       u8 *data,
+					       unsigned int dirblksize,
+					       const int ndirents)
+{
+	int head, back;
+	unsigned int startprfx, endprfx;
+	struct erofs_dirent *const de = (struct erofs_dirent *)data;
+
+	/* since the 1st dirent has been evaluated previously */
+	head = 1;
+	back = ndirents - 1;
+	startprfx = endprfx = 0;
+
+	while (head <= back) {
+		const int mid = head + (back - head) / 2;
+		const int nameoff = nameoff_from_disk(de[mid].nameoff,
+						      dirblksize);
+		unsigned int matched = min(startprfx, endprfx);
+		struct erofs_qstr dname = {
+			.name = data + nameoff,
+			.end = unlikely(mid >= ndirents - 1) ?
+				data + dirblksize :
+				data + nameoff_from_disk(de[mid + 1].nameoff,
+							 dirblksize)
+		};
+
+		/* string comparison without already matched prefix */
+		int ret = dirnamecmp(name, &dname, &matched);
+
+		if (unlikely(!ret)) {
+			return de + mid;
+		} else if (ret > 0) {
+			head = mid + 1;
+			startprfx = matched;
+		} else {
+			back = mid - 1;
+			endprfx = matched;
+		}
+	}
+
+	return ERR_PTR(-ENOENT);
+}
+
+static struct page *find_target_block_classic(struct inode *dir,
+					      struct erofs_qstr *name,
+					      int *_ndirents)
+{
+	unsigned int startprfx, endprfx;
+	int head, back;
+	struct address_space *const mapping = dir->i_mapping;
+	struct page *candidate = ERR_PTR(-ENOENT);
+
+	startprfx = endprfx = 0;
+	head = 0;
+	back = inode_datablocks(dir) - 1;
+
+	while (head <= back) {
+		const int mid = head + (back - head) / 2;
+		struct page *page = read_mapping_page(mapping, mid, NULL);
+
+		if (!IS_ERR(page)) {
+			struct erofs_dirent *de = kmap_atomic(page);
+			const int nameoff = nameoff_from_disk(de->nameoff,
+							      EROFS_BLKSIZ);
+			const int ndirents = nameoff / sizeof(*de);
+			int diff;
+			unsigned int matched;
+			struct erofs_qstr dname;
+
+			if (unlikely(!ndirents)) {
+				kunmap_atomic(de);
+				put_page(page);
+				errln("corrupted dir block %d @ nid %llu",
+				      mid, EROFS_V(dir)->nid);
+				DBG_BUGON(1);
+				page = ERR_PTR(-EFSCORRUPTED);
+				goto out;
+			}
+
+			matched = min(startprfx, endprfx);
+
+			dname.name = (u8 *)de + nameoff;
+			if (ndirents == 1)
+				dname.end = (u8 *)de + EROFS_BLKSIZ;
+			else
+				dname.end = (u8 *)de +
+					nameoff_from_disk(de[1].nameoff,
+							  EROFS_BLKSIZ);
+
+			/* string comparison without already matched prefix */
+			diff = dirnamecmp(name, &dname, &matched);
+			kunmap_atomic(de);
+
+			if (unlikely(!diff)) {
+				*_ndirents = 0;
+				goto out;
+			} else if (diff > 0) {
+				head = mid + 1;
+				startprfx = matched;
+
+				if (!IS_ERR(candidate))
+					put_page(candidate);
+				candidate = page;
+				*_ndirents = ndirents;
+			} else {
+				put_page(page);
+
+				back = mid - 1;
+				endprfx = matched;
+			}
+			continue;
+		}
+out:		/* free if the candidate is valid */
+		if (!IS_ERR(candidate))
+			put_page(candidate);
+		return page;
+	}
+	return candidate;
+}
+
+int erofs_namei(struct inode *dir,
+		struct qstr *name,
+		erofs_nid_t *nid, unsigned int *d_type)
+{
+	int ndirents;
+	struct page *page;
+	void *data;
+	struct erofs_dirent *de;
+	struct erofs_qstr qn;
+
+	if (unlikely(!dir->i_size))
+		return -ENOENT;
+
+	qn.name = name->name;
+	qn.end = name->name + name->len;
+
+	ndirents = 0;
+	page = find_target_block_classic(dir, &qn, &ndirents);
+
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+
+	data = kmap_atomic(page);
+	/* the target page has been mapped */
+	if (ndirents)
+		de = find_target_dirent(&qn, data, EROFS_BLKSIZ, ndirents);
+	else
+		de = (struct erofs_dirent *)data;
+
+	if (!IS_ERR(de)) {
+		*nid = le64_to_cpu(de->nid);
+		*d_type = de->file_type;
+	}
+
+	kunmap_atomic(data);
+	put_page(page);
+
+	return PTR_ERR_OR_ZERO(de);
+}
+
+/* NOTE: i_mutex is already held by vfs */
+static struct dentry *erofs_lookup(struct inode *dir,
+				   struct dentry *dentry,
+				   unsigned int flags)
+{
+	int err;
+	erofs_nid_t nid;
+	unsigned int d_type;
+	struct inode *inode;
+
+	DBG_BUGON(!d_really_is_negative(dentry));
+	/* dentry must be unhashed in lookup, no need to worry about */
+	DBG_BUGON(!d_unhashed(dentry));
+
+	trace_erofs_lookup(dir, dentry, flags);
+
+	/* file name exceeds fs limit */
+	if (unlikely(dentry->d_name.len > EROFS_NAME_LEN))
+		return ERR_PTR(-ENAMETOOLONG);
+
+	/* false uninitialized warnings on gcc 4.8.x */
+	err = erofs_namei(dir, &dentry->d_name, &nid, &d_type);
+
+	if (err == -ENOENT) {
+		/* negative dentry */
+		inode = NULL;
+	} else if (unlikely(err)) {
+		inode = ERR_PTR(err);
+	} else {
+		debugln("%s, %s (nid %llu) found, d_type %u", __func__,
+			dentry->d_name.name, nid, d_type);
+		inode = erofs_iget(dir->i_sb, nid, d_type == FT_DIR);
+	}
+	return d_splice_alias(inode, dentry);
+}
+
+const struct inode_operations erofs_dir_iops = {
+	.lookup = erofs_lookup,
+	.getattr = erofs_getattr,
+#ifdef CONFIG_EROFS_FS_XATTR
+	.listxattr = erofs_listxattr,
+#endif
+	.get_acl = erofs_get_acl,
+};
+
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
new file mode 100644
index 000000000000..6d3a9bcb8daa
--- /dev/null
+++ b/fs/erofs/super.c
@@ -0,0 +1,669 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017-2018 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#include <linux/module.h>
+#include <linux/buffer_head.h>
+#include <linux/statfs.h>
+#include <linux/parser.h>
+#include <linux/seq_file.h>
+#include "xattr.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/erofs.h>
+
+static struct kmem_cache *erofs_inode_cachep __read_mostly;
+
+static void init_once(void *ptr)
+{
+	struct erofs_vnode *vi = ptr;
+
+	inode_init_once(&vi->vfs_inode);
+}
+
+static int __init erofs_init_inode_cache(void)
+{
+	erofs_inode_cachep = kmem_cache_create("erofs_inode",
+					       sizeof(struct erofs_vnode), 0,
+					       SLAB_RECLAIM_ACCOUNT,
+					       init_once);
+
+	return erofs_inode_cachep ? 0 : -ENOMEM;
+}
+
+static void erofs_exit_inode_cache(void)
+{
+	kmem_cache_destroy(erofs_inode_cachep);
+}
+
+static struct inode *alloc_inode(struct super_block *sb)
+{
+	struct erofs_vnode *vi =
+		kmem_cache_alloc(erofs_inode_cachep, GFP_KERNEL);
+
+	if (!vi)
+		return NULL;
+
+	/* zero out everything except vfs_inode */
+	memset(vi, 0, offsetof(struct erofs_vnode, vfs_inode));
+	return &vi->vfs_inode;
+}
+
+static void free_inode(struct inode *inode)
+{
+	struct erofs_vnode *vi = EROFS_V(inode);
+
+	/* be careful RCU symlink path (see ext4_inode_info->i_data)! */
+	if (is_inode_fast_symlink(inode))
+		kfree(inode->i_link);
+
+	kfree(vi->xattr_shared_xattrs);
+
+	kmem_cache_free(erofs_inode_cachep, vi);
+}
+
+static bool check_layout_compatibility(struct super_block *sb,
+				       struct erofs_super_block *layout)
+{
+	const unsigned int requirements = le32_to_cpu(layout->requirements);
+
+	EROFS_SB(sb)->requirements = requirements;
+
+	/* check if current kernel meets all mandatory requirements */
+	if (requirements & (~EROFS_ALL_REQUIREMENTS)) {
+		errln("unidentified requirements %x, please upgrade kernel version",
+		      requirements & ~EROFS_ALL_REQUIREMENTS);
+		return false;
+	}
+	return true;
+}
+
+static int superblock_read(struct super_block *sb)
+{
+	struct erofs_sb_info *sbi;
+	struct buffer_head *bh;
+	struct erofs_super_block *layout;
+	unsigned int blkszbits;
+	int ret;
+
+	bh = sb_bread(sb, 0);
+
+	if (!bh) {
+		errln("cannot read erofs superblock");
+		return -EIO;
+	}
+
+	sbi = EROFS_SB(sb);
+	layout = (struct erofs_super_block *)((u8 *)bh->b_data
+		 + EROFS_SUPER_OFFSET);
+
+	ret = -EINVAL;
+	if (le32_to_cpu(layout->magic) != EROFS_SUPER_MAGIC_V1) {
+		errln("cannot find valid erofs superblock");
+		goto out;
+	}
+
+	blkszbits = layout->blkszbits;
+	/* 9(512 bytes) + LOG_SECTORS_PER_BLOCK == LOG_BLOCK_SIZE */
+	if (unlikely(blkszbits != LOG_BLOCK_SIZE)) {
+		errln("blksize %u isn't supported on this platform",
+		      1 << blkszbits);
+		goto out;
+	}
+
+	if (!check_layout_compatibility(sb, layout))
+		goto out;
+
+	sbi->blocks = le32_to_cpu(layout->blocks);
+	sbi->meta_blkaddr = le32_to_cpu(layout->meta_blkaddr);
+#ifdef CONFIG_EROFS_FS_XATTR
+	sbi->xattr_blkaddr = le32_to_cpu(layout->xattr_blkaddr);
+#endif
+	sbi->islotbits = ffs(sizeof(struct erofs_inode_v1)) - 1;
+	sbi->root_nid = le16_to_cpu(layout->root_nid);
+	sbi->inos = le64_to_cpu(layout->inos);
+
+	sbi->build_time = le64_to_cpu(layout->build_time);
+	sbi->build_time_nsec = le32_to_cpu(layout->build_time_nsec);
+
+	memcpy(&sb->s_uuid, layout->uuid, sizeof(layout->uuid));
+
+	ret = strscpy(sbi->volume_name, layout->volume_name,
+		      sizeof(layout->volume_name));
+	if (ret < 0) {	/* -E2BIG */
+		errln("bad volume name without NIL terminator");
+		ret = -EFSCORRUPTED;
+		goto out;
+	}
+	ret = 0;
+out:
+	brelse(bh);
+	return ret;
+}
+
+#ifdef CONFIG_EROFS_FAULT_INJECTION
+const char *erofs_fault_name[FAULT_MAX] = {
+	[FAULT_KMALLOC]		= "kmalloc",
+	[FAULT_READ_IO]		= "read IO error",
+};
+
+static void __erofs_build_fault_attr(struct erofs_sb_info *sbi,
+				     unsigned int rate)
+{
+	struct erofs_fault_info *ffi = &sbi->fault_info;
+
+	if (rate) {
+		atomic_set(&ffi->inject_ops, 0);
+		ffi->inject_rate = rate;
+		ffi->inject_type = (1 << FAULT_MAX) - 1;
+	} else {
+		memset(ffi, 0, sizeof(struct erofs_fault_info));
+	}
+
+	set_opt(sbi, FAULT_INJECTION);
+}
+
+static int erofs_build_fault_attr(struct erofs_sb_info *sbi,
+				  substring_t *args)
+{
+	int rate = 0;
+
+	if (args->from && match_int(args, &rate))
+		return -EINVAL;
+
+	__erofs_build_fault_attr(sbi, rate);
+	return 0;
+}
+
+static unsigned int erofs_get_fault_rate(struct erofs_sb_info *sbi)
+{
+	return sbi->fault_info.inject_rate;
+}
+#else
+static void __erofs_build_fault_attr(struct erofs_sb_info *sbi,
+				     unsigned int rate)
+{
+}
+
+static int erofs_build_fault_attr(struct erofs_sb_info *sbi,
+				  substring_t *args)
+{
+	infoln("fault_injection options not supported");
+	return 0;
+}
+
+static unsigned int erofs_get_fault_rate(struct erofs_sb_info *sbi)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_EROFS_FS_ZIP
+static int erofs_build_cache_strategy(struct erofs_sb_info *sbi,
+				      substring_t *args)
+{
+	const char *cs = match_strdup(args);
+	int err = 0;
+
+	if (!cs) {
+		errln("Not enough memory to store cache strategy");
+		return -ENOMEM;
+	}
+
+	if (!strcmp(cs, "disabled")) {
+		sbi->cache_strategy = EROFS_ZIP_CACHE_DISABLED;
+	} else if (!strcmp(cs, "readahead")) {
+		sbi->cache_strategy = EROFS_ZIP_CACHE_READAHEAD;
+	} else if (!strcmp(cs, "readaround")) {
+		sbi->cache_strategy = EROFS_ZIP_CACHE_READAROUND;
+	} else {
+		errln("Unrecognized cache strategy \"%s\"", cs);
+		err = -EINVAL;
+	}
+	kfree(cs);
+	return err;
+}
+#else
+static int erofs_build_cache_strategy(struct erofs_sb_info *sbi,
+				      substring_t *args)
+{
+	infoln("EROFS compression is disabled, so cache strategy is ignored");
+	return 0;
+}
+#endif
+
+/* set up default EROFS parameters */
+static void default_options(struct erofs_sb_info *sbi)
+{
+#ifdef CONFIG_EROFS_FS_ZIP
+	sbi->cache_strategy = EROFS_ZIP_CACHE_READAROUND;
+	sbi->max_sync_decompress_pages = 3;
+#endif
+#ifdef CONFIG_EROFS_FS_XATTR
+	set_opt(sbi, XATTR_USER);
+#endif
+#ifdef CONFIG_EROFS_FS_POSIX_ACL
+	set_opt(sbi, POSIX_ACL);
+#endif
+}
+
+enum {
+	Opt_user_xattr,
+	Opt_nouser_xattr,
+	Opt_acl,
+	Opt_noacl,
+	Opt_fault_injection,
+	Opt_cache_strategy,
+	Opt_err
+};
+
+static match_table_t erofs_tokens = {
+	{Opt_user_xattr, "user_xattr"},
+	{Opt_nouser_xattr, "nouser_xattr"},
+	{Opt_acl, "acl"},
+	{Opt_noacl, "noacl"},
+	{Opt_fault_injection, "fault_injection=%u"},
+	{Opt_cache_strategy, "cache_strategy=%s"},
+	{Opt_err, NULL}
+};
+
+static int parse_options(struct super_block *sb, char *options)
+{
+	substring_t args[MAX_OPT_ARGS];
+	char *p;
+	int err;
+
+	if (!options)
+		return 0;
+
+	while ((p = strsep(&options, ","))) {
+		int token;
+
+		if (!*p)
+			continue;
+
+		args[0].to = args[0].from = NULL;
+		token = match_token(p, erofs_tokens, args);
+
+		switch (token) {
+#ifdef CONFIG_EROFS_FS_XATTR
+		case Opt_user_xattr:
+			set_opt(EROFS_SB(sb), XATTR_USER);
+			break;
+		case Opt_nouser_xattr:
+			clear_opt(EROFS_SB(sb), XATTR_USER);
+			break;
+#else
+		case Opt_user_xattr:
+			infoln("user_xattr options not supported");
+			break;
+		case Opt_nouser_xattr:
+			infoln("nouser_xattr options not supported");
+			break;
+#endif
+#ifdef CONFIG_EROFS_FS_POSIX_ACL
+		case Opt_acl:
+			set_opt(EROFS_SB(sb), POSIX_ACL);
+			break;
+		case Opt_noacl:
+			clear_opt(EROFS_SB(sb), POSIX_ACL);
+			break;
+#else
+		case Opt_acl:
+			infoln("acl options not supported");
+			break;
+		case Opt_noacl:
+			infoln("noacl options not supported");
+			break;
+#endif
+		case Opt_fault_injection:
+			err = erofs_build_fault_attr(EROFS_SB(sb), args);
+			if (err)
+				return err;
+			break;
+		case Opt_cache_strategy:
+			err = erofs_build_cache_strategy(EROFS_SB(sb), args);
+			if (err)
+				return err;
+			break;
+		default:
+			errln("Unrecognized mount option \"%s\" or missing value", p);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+#ifdef CONFIG_EROFS_FS_ZIP
+static const struct address_space_operations managed_cache_aops;
+
+static int managed_cache_releasepage(struct page *page, gfp_t gfp_mask)
+{
+	int ret = 1;	/* 0 - busy */
+	struct address_space *const mapping = page->mapping;
+
+	DBG_BUGON(!PageLocked(page));
+	DBG_BUGON(mapping->a_ops != &managed_cache_aops);
+
+	if (PagePrivate(page))
+		ret = erofs_try_to_free_cached_page(mapping, page);
+
+	return ret;
+}
+
+static void managed_cache_invalidatepage(struct page *page,
+					 unsigned int offset,
+					 unsigned int length)
+{
+	const unsigned int stop = length + offset;
+
+	DBG_BUGON(!PageLocked(page));
+
+	/* Check for potential overflow in debug mode */
+	DBG_BUGON(stop > PAGE_SIZE || stop < length);
+
+	if (offset == 0 && stop == PAGE_SIZE)
+		while (!managed_cache_releasepage(page, GFP_NOFS))
+			cond_resched();
+}
+
+static const struct address_space_operations managed_cache_aops = {
+	.releasepage = managed_cache_releasepage,
+	.invalidatepage = managed_cache_invalidatepage,
+};
+
+static int erofs_init_managed_cache(struct super_block *sb)
+{
+	struct erofs_sb_info *const sbi = EROFS_SB(sb);
+	struct inode *const inode = new_inode(sb);
+
+	if (unlikely(!inode))
+		return -ENOMEM;
+
+	set_nlink(inode, 1);
+	inode->i_size = OFFSET_MAX;
+
+	inode->i_mapping->a_ops = &managed_cache_aops;
+	mapping_set_gfp_mask(inode->i_mapping,
+			     GFP_NOFS | __GFP_HIGHMEM | __GFP_MOVABLE);
+	sbi->managed_cache = inode;
+	return 0;
+}
+#else
+static int erofs_init_managed_cache(struct super_block *sb) { return 0; }
+#endif
+
+static int erofs_fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct inode *inode;
+	struct erofs_sb_info *sbi;
+	int err;
+
+	infoln("fill_super, device -> %s", sb->s_id);
+	infoln("options -> %s", (char *)data);
+
+	sb->s_magic = EROFS_SUPER_MAGIC;
+
+	if (unlikely(!sb_set_blocksize(sb, EROFS_BLKSIZ))) {
+		errln("failed to set erofs blksize");
+		return -EINVAL;
+	}
+
+	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
+	if (unlikely(!sbi))
+		return -ENOMEM;
+
+	sb->s_fs_info = sbi;
+	err = superblock_read(sb);
+	if (err)
+		return err;
+
+	sb->s_flags |= SB_RDONLY | SB_NOATIME;
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+	sb->s_time_gran = 1;
+
+	sb->s_op = &erofs_sops;
+
+#ifdef CONFIG_EROFS_FS_XATTR
+	sb->s_xattr = erofs_xattr_handlers;
+#endif
+	/* set erofs default mount options */
+	default_options(sbi);
+
+	err = parse_options(sb, data);
+	if (unlikely(err))
+		return err;
+
+	if (!silent)
+		infoln("root inode @ nid %llu", ROOT_NID(sbi));
+
+	if (test_opt(sbi, POSIX_ACL))
+		sb->s_flags |= SB_POSIXACL;
+	else
+		sb->s_flags &= ~SB_POSIXACL;
+
+#ifdef CONFIG_EROFS_FS_ZIP
+	INIT_RADIX_TREE(&sbi->workstn_tree, GFP_ATOMIC);
+#endif
+
+	/* get the root inode */
+	inode = erofs_iget(sb, ROOT_NID(sbi), true);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	if (unlikely(!S_ISDIR(inode->i_mode))) {
+		errln("rootino(nid %llu) is not a directory(i_mode %o)",
+		      ROOT_NID(sbi), inode->i_mode);
+		iput(inode);
+		return -EINVAL;
+	}
+
+	sb->s_root = d_make_root(inode);
+	if (unlikely(!sb->s_root))
+		return -ENOMEM;
+
+	erofs_shrinker_register(sb);
+	/* sb->s_umount is already locked, SB_ACTIVE and SB_BORN are not set */
+	err = erofs_init_managed_cache(sb);
+	if (unlikely(err))
+		return err;
+
+	if (!silent)
+		infoln("mounted on %s with opts: %s.", sb->s_id, (char *)data);
+	return 0;
+}
+
+static struct dentry *erofs_mount(struct file_system_type *fs_type, int flags,
+				  const char *dev_name, void *data)
+{
+	return mount_bdev(fs_type, flags, dev_name, data, erofs_fill_super);
+}
+
+/*
+ * could be triggered after deactivate_locked_super()
+ * is called, thus including umount and failed to initialize.
+ */
+static void erofs_kill_sb(struct super_block *sb)
+{
+	struct erofs_sb_info *sbi;
+
+	WARN_ON(sb->s_magic != EROFS_SUPER_MAGIC);
+	infoln("unmounting for %s", sb->s_id);
+
+	kill_block_super(sb);
+
+	sbi = EROFS_SB(sb);
+	if (!sbi)
+		return;
+	kfree(sbi);
+	sb->s_fs_info = NULL;
+}
+
+/* called when ->s_root is non-NULL */
+static void erofs_put_super(struct super_block *sb)
+{
+	struct erofs_sb_info *const sbi = EROFS_SB(sb);
+
+	DBG_BUGON(!sbi);
+
+	erofs_shrinker_unregister(sb);
+#ifdef CONFIG_EROFS_FS_ZIP
+	iput(sbi->managed_cache);
+	sbi->managed_cache = NULL;
+#endif
+}
+
+static struct file_system_type erofs_fs_type = {
+	.owner          = THIS_MODULE,
+	.name           = "erofs",
+	.mount          = erofs_mount,
+	.kill_sb        = erofs_kill_sb,
+	.fs_flags       = FS_REQUIRES_DEV,
+};
+MODULE_ALIAS_FS("erofs");
+
+static int __init erofs_module_init(void)
+{
+	int err;
+
+	erofs_check_ondisk_layout_definitions();
+	infoln("initializing erofs " EROFS_VERSION);
+
+	err = erofs_init_inode_cache();
+	if (err)
+		goto icache_err;
+
+	err = erofs_init_shrinker();
+	if (err)
+		goto shrinker_err;
+
+	err = z_erofs_init_zip_subsystem();
+	if (err)
+		goto zip_err;
+
+	err = register_filesystem(&erofs_fs_type);
+	if (err)
+		goto fs_err;
+
+	infoln("successfully to initialize erofs");
+	return 0;
+
+fs_err:
+	z_erofs_exit_zip_subsystem();
+zip_err:
+	erofs_exit_shrinker();
+shrinker_err:
+	erofs_exit_inode_cache();
+icache_err:
+	return err;
+}
+
+static void __exit erofs_module_exit(void)
+{
+	unregister_filesystem(&erofs_fs_type);
+	z_erofs_exit_zip_subsystem();
+	erofs_exit_shrinker();
+	erofs_exit_inode_cache();
+	infoln("successfully finalize erofs");
+}
+
+/* get filesystem statistics */
+static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct super_block *sb = dentry->d_sb;
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
+
+	buf->f_type = sb->s_magic;
+	buf->f_bsize = EROFS_BLKSIZ;
+	buf->f_blocks = sbi->blocks;
+	buf->f_bfree = buf->f_bavail = 0;
+
+	buf->f_files = ULLONG_MAX;
+	buf->f_ffree = ULLONG_MAX - sbi->inos;
+
+	buf->f_namelen = EROFS_NAME_LEN;
+
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
+	return 0;
+}
+
+static int erofs_show_options(struct seq_file *seq, struct dentry *root)
+{
+	struct erofs_sb_info *sbi __maybe_unused = EROFS_SB(root->d_sb);
+
+#ifdef CONFIG_EROFS_FS_XATTR
+	if (test_opt(sbi, XATTR_USER))
+		seq_puts(seq, ",user_xattr");
+	else
+		seq_puts(seq, ",nouser_xattr");
+#endif
+#ifdef CONFIG_EROFS_FS_POSIX_ACL
+	if (test_opt(sbi, POSIX_ACL))
+		seq_puts(seq, ",acl");
+	else
+		seq_puts(seq, ",noacl");
+#endif
+	if (test_opt(sbi, FAULT_INJECTION))
+		seq_printf(seq, ",fault_injection=%u",
+			   erofs_get_fault_rate(sbi));
+#ifdef CONFIG_EROFS_FS_ZIP
+	if (sbi->cache_strategy == EROFS_ZIP_CACHE_DISABLED) {
+		seq_puts(seq, ",cache_strategy=disabled");
+	} else if (sbi->cache_strategy == EROFS_ZIP_CACHE_READAHEAD) {
+		seq_puts(seq, ",cache_strategy=readahead");
+	} else if (sbi->cache_strategy == EROFS_ZIP_CACHE_READAROUND) {
+		seq_puts(seq, ",cache_strategy=readaround");
+	} else {
+		seq_puts(seq, ",cache_strategy=(unknown)");
+		DBG_BUGON(1);
+	}
+#endif
+	return 0;
+}
+
+static int erofs_remount(struct super_block *sb, int *flags, char *data)
+{
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+	unsigned int org_mnt_opt = sbi->mount_opt;
+	unsigned int org_inject_rate = erofs_get_fault_rate(sbi);
+	int err;
+
+	DBG_BUGON(!sb_rdonly(sb));
+	err = parse_options(sb, data);
+	if (err)
+		goto out;
+
+	if (test_opt(sbi, POSIX_ACL))
+		sb->s_flags |= SB_POSIXACL;
+	else
+		sb->s_flags &= ~SB_POSIXACL;
+
+	*flags |= SB_RDONLY;
+	return 0;
+out:
+	__erofs_build_fault_attr(sbi, org_inject_rate);
+	sbi->mount_opt = org_mnt_opt;
+
+	return err;
+}
+
+const struct super_operations erofs_sops = {
+	.put_super = erofs_put_super,
+	.alloc_inode = alloc_inode,
+	.free_inode = free_inode,
+	.statfs = erofs_statfs,
+	.show_options = erofs_show_options,
+	.remount_fs = erofs_remount,
+};
+
+module_init(erofs_module_init);
+module_exit(erofs_module_exit);
+
+MODULE_DESCRIPTION("Enhanced ROM File System");
+MODULE_AUTHOR("Gao Xiang, Chao Yu, Miao Xie, CONSUMER BG, HUAWEI Inc.");
+MODULE_LICENSE("GPL");
+
diff --git a/fs/erofs/tagptr.h b/fs/erofs/tagptr.h
new file mode 100644
index 000000000000..a72897c86744
--- /dev/null
+++ b/fs/erofs/tagptr.h
@@ -0,0 +1,110 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * A tagged pointer implementation
+ *
+ * Copyright (C) 2018 Gao Xiang <gaoxiang25@huawei.com>
+ */
+#ifndef __EROFS_FS_TAGPTR_H
+#define __EROFS_FS_TAGPTR_H
+
+#include <linux/types.h>
+#include <linux/build_bug.h>
+
+/*
+ * the name of tagged pointer types are tagptr{1, 2, 3...}_t
+ * avoid directly using the internal structs __tagptr{1, 2, 3...}
+ */
+#define __MAKE_TAGPTR(n) \
+typedef struct __tagptr##n {	\
+	uintptr_t v;	\
+} tagptr##n##_t;
+
+__MAKE_TAGPTR(1)
+__MAKE_TAGPTR(2)
+__MAKE_TAGPTR(3)
+__MAKE_TAGPTR(4)
+
+#undef __MAKE_TAGPTR
+
+extern void __compiletime_error("bad tagptr tags")
+	__bad_tagptr_tags(void);
+
+extern void __compiletime_error("bad tagptr type")
+	__bad_tagptr_type(void);
+
+/* fix the broken usage of "#define tagptr2_t tagptr3_t" by users */
+#define __tagptr_mask_1(ptr, n)	\
+	__builtin_types_compatible_p(typeof(ptr), struct __tagptr##n) ? \
+		(1UL << (n)) - 1 :
+
+#define __tagptr_mask(ptr)	(\
+	__tagptr_mask_1(ptr, 1) ( \
+	__tagptr_mask_1(ptr, 2) ( \
+	__tagptr_mask_1(ptr, 3) ( \
+	__tagptr_mask_1(ptr, 4) ( \
+	__bad_tagptr_type(), 0)))))
+
+/* generate a tagged pointer from a raw value */
+#define tagptr_init(type, val) \
+	((typeof(type)){ .v = (uintptr_t)(val) })
+
+/*
+ * directly cast a tagged pointer to the native pointer type, which
+ * could be used for backward compatibility of existing code.
+ */
+#define tagptr_cast_ptr(tptr) ((void *)(tptr).v)
+
+/* encode tagged pointers */
+#define tagptr_fold(type, ptr, _tags) ({ \
+	const typeof(_tags) tags = (_tags); \
+	if (__builtin_constant_p(tags) && (tags & ~__tagptr_mask(type))) \
+		__bad_tagptr_tags(); \
+tagptr_init(type, (uintptr_t)(ptr) | tags); })
+
+/* decode tagged pointers */
+#define tagptr_unfold_ptr(tptr) \
+	((void *)((tptr).v & ~__tagptr_mask(tptr)))
+
+#define tagptr_unfold_tags(tptr) \
+	((tptr).v & __tagptr_mask(tptr))
+
+/* operations for the tagger pointer */
+#define tagptr_eq(_tptr1, _tptr2) ({ \
+	typeof(_tptr1) tptr1 = (_tptr1); \
+	typeof(_tptr2) tptr2 = (_tptr2); \
+	(void)(&tptr1 == &tptr2); \
+(tptr1).v == (tptr2).v; })
+
+/* lock-free CAS operation */
+#define tagptr_cmpxchg(_ptptr, _o, _n) ({ \
+	typeof(_ptptr) ptptr = (_ptptr); \
+	typeof(_o) o = (_o); \
+	typeof(_n) n = (_n); \
+	(void)(&o == &n); \
+	(void)(&o == ptptr); \
+tagptr_init(o, cmpxchg(&ptptr->v, o.v, n.v)); })
+
+/* wrap WRITE_ONCE if atomic update is needed */
+#define tagptr_replace_tags(_ptptr, tags) ({ \
+	typeof(_ptptr) ptptr = (_ptptr); \
+	*ptptr = tagptr_fold(*ptptr, tagptr_unfold_ptr(*ptptr), tags); \
+*ptptr; })
+
+#define tagptr_set_tags(_ptptr, _tags) ({ \
+	typeof(_ptptr) ptptr = (_ptptr); \
+	const typeof(_tags) tags = (_tags); \
+	if (__builtin_constant_p(tags) && (tags & ~__tagptr_mask(*ptptr))) \
+		__bad_tagptr_tags(); \
+	ptptr->v |= tags; \
+*ptptr; })
+
+#define tagptr_clear_tags(_ptptr, _tags) ({ \
+	typeof(_ptptr) ptptr = (_ptptr); \
+	const typeof(_tags) tags = (_tags); \
+	if (__builtin_constant_p(tags) && (tags & ~__tagptr_mask(*ptptr))) \
+		__bad_tagptr_tags(); \
+	ptptr->v &= ~tags; \
+*ptptr; })
+
+#endif	/* __EROFS_FS_TAGPTR_H */
+
diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c
new file mode 100644
index 000000000000..1dd041aa0f5a
--- /dev/null
+++ b/fs/erofs/utils.c
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2018 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#include "internal.h"
+#include <linux/pagevec.h>
+
+struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp, bool nofail)
+{
+	struct page *page;
+
+	if (!list_empty(pool)) {
+		page = lru_to_page(pool);
+		DBG_BUGON(page_ref_count(page) != 1);
+		list_del(&page->lru);
+	} else {
+		page = alloc_pages(gfp | (nofail ? __GFP_NOFAIL : 0), 0);
+	}
+	return page;
+}
+
+#if (EROFS_PCPUBUF_NR_PAGES > 0)
+static struct {
+	u8 data[PAGE_SIZE * EROFS_PCPUBUF_NR_PAGES];
+} ____cacheline_aligned_in_smp erofs_pcpubuf[NR_CPUS];
+
+void *erofs_get_pcpubuf(unsigned int pagenr)
+{
+	preempt_disable();
+	return &erofs_pcpubuf[smp_processor_id()].data[pagenr * PAGE_SIZE];
+}
+#endif
+
+#ifdef CONFIG_EROFS_FS_ZIP
+/* global shrink count (for all mounted EROFS instances) */
+static atomic_long_t erofs_global_shrink_cnt;
+
+#define __erofs_workgroup_get(grp)	atomic_inc(&(grp)->refcount)
+#define __erofs_workgroup_put(grp)	atomic_dec(&(grp)->refcount)
+
+static int erofs_workgroup_get(struct erofs_workgroup *grp)
+{
+	int o;
+
+repeat:
+	o = erofs_wait_on_workgroup_freezed(grp);
+	if (unlikely(o <= 0))
+		return -1;
+
+	if (unlikely(atomic_cmpxchg(&grp->refcount, o, o + 1) != o))
+		goto repeat;
+
+	/* decrease refcount paired by erofs_workgroup_put */
+	if (unlikely(o == 1))
+		atomic_long_dec(&erofs_global_shrink_cnt);
+	return 0;
+}
+
+struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb,
+					     pgoff_t index, bool *tag)
+{
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+	struct erofs_workgroup *grp;
+
+repeat:
+	rcu_read_lock();
+	grp = radix_tree_lookup(&sbi->workstn_tree, index);
+	if (grp) {
+		*tag = xa_pointer_tag(grp);
+		grp = xa_untag_pointer(grp);
+
+		if (erofs_workgroup_get(grp)) {
+			/* prefer to relax rcu read side */
+			rcu_read_unlock();
+			goto repeat;
+		}
+
+		DBG_BUGON(index != grp->index);
+	}
+	rcu_read_unlock();
+	return grp;
+}
+
+int erofs_register_workgroup(struct super_block *sb,
+			     struct erofs_workgroup *grp,
+			     bool tag)
+{
+	struct erofs_sb_info *sbi;
+	int err;
+
+	/* grp shouldn't be broken or used before */
+	if (unlikely(atomic_read(&grp->refcount) != 1)) {
+		DBG_BUGON(1);
+		return -EINVAL;
+	}
+
+	err = radix_tree_preload(GFP_NOFS);
+	if (err)
+		return err;
+
+	sbi = EROFS_SB(sb);
+	xa_lock(&sbi->workstn_tree);
+
+	grp = xa_tag_pointer(grp, tag);
+
+	/*
+	 * Bump up reference count before making this workgroup
+	 * visible to other users in order to avoid potential UAF
+	 * without serialized by workstn_lock.
+	 */
+	__erofs_workgroup_get(grp);
+
+	err = radix_tree_insert(&sbi->workstn_tree, grp->index, grp);
+	if (unlikely(err))
+		/*
+		 * it's safe to decrease since the workgroup isn't visible
+		 * and refcount >= 2 (cannot be freezed).
+		 */
+		__erofs_workgroup_put(grp);
+
+	xa_unlock(&sbi->workstn_tree);
+	radix_tree_preload_end();
+	return err;
+}
+
+static void  __erofs_workgroup_free(struct erofs_workgroup *grp)
+{
+	atomic_long_dec(&erofs_global_shrink_cnt);
+	erofs_workgroup_free_rcu(grp);
+}
+
+int erofs_workgroup_put(struct erofs_workgroup *grp)
+{
+	int count = atomic_dec_return(&grp->refcount);
+
+	if (count == 1)
+		atomic_long_inc(&erofs_global_shrink_cnt);
+	else if (!count)
+		__erofs_workgroup_free(grp);
+	return count;
+}
+
+static void erofs_workgroup_unfreeze_final(struct erofs_workgroup *grp)
+{
+	erofs_workgroup_unfreeze(grp, 0);
+	__erofs_workgroup_free(grp);
+}
+
+static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi,
+					   struct erofs_workgroup *grp,
+					   bool cleanup)
+{
+	/*
+	 * If managed cache is on, refcount of workgroups
+	 * themselves could be < 0 (freezed). In other words,
+	 * there is no guarantee that all refcounts > 0.
+	 */
+	if (!erofs_workgroup_try_to_freeze(grp, 1))
+		return false;
+
+	/*
+	 * Note that all cached pages should be unattached
+	 * before deleted from the radix tree. Otherwise some
+	 * cached pages could be still attached to the orphan
+	 * old workgroup when the new one is available in the tree.
+	 */
+	if (erofs_try_to_free_all_cached_pages(sbi, grp)) {
+		erofs_workgroup_unfreeze(grp, 1);
+		return false;
+	}
+
+	/*
+	 * It's impossible to fail after the workgroup is freezed,
+	 * however in order to avoid some race conditions, add a
+	 * DBG_BUGON to observe this in advance.
+	 */
+	DBG_BUGON(xa_untag_pointer(radix_tree_delete(&sbi->workstn_tree,
+						     grp->index)) != grp);
+
+	/*
+	 * If managed cache is on, last refcount should indicate
+	 * the related workstation.
+	 */
+	erofs_workgroup_unfreeze_final(grp);
+	return true;
+}
+
+static unsigned long erofs_shrink_workstation(struct erofs_sb_info *sbi,
+					      unsigned long nr_shrink,
+					      bool cleanup)
+{
+	pgoff_t first_index = 0;
+	void *batch[PAGEVEC_SIZE];
+	unsigned int freed = 0;
+
+	int i, found;
+repeat:
+	xa_lock(&sbi->workstn_tree);
+
+	found = radix_tree_gang_lookup(&sbi->workstn_tree,
+				       batch, first_index, PAGEVEC_SIZE);
+
+	for (i = 0; i < found; ++i) {
+		struct erofs_workgroup *grp = xa_untag_pointer(batch[i]);
+
+		first_index = grp->index + 1;
+
+		/* try to shrink each valid workgroup */
+		if (!erofs_try_to_release_workgroup(sbi, grp, cleanup))
+			continue;
+
+		++freed;
+		if (unlikely(!--nr_shrink))
+			break;
+	}
+	xa_unlock(&sbi->workstn_tree);
+
+	if (i && nr_shrink)
+		goto repeat;
+	return freed;
+}
+
+/* protected by 'erofs_sb_list_lock' */
+static unsigned int shrinker_run_no;
+
+/* protects the mounted 'erofs_sb_list' */
+static DEFINE_SPINLOCK(erofs_sb_list_lock);
+static LIST_HEAD(erofs_sb_list);
+
+void erofs_shrinker_register(struct super_block *sb)
+{
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+
+	mutex_init(&sbi->umount_mutex);
+
+	spin_lock(&erofs_sb_list_lock);
+	list_add(&sbi->list, &erofs_sb_list);
+	spin_unlock(&erofs_sb_list_lock);
+}
+
+void erofs_shrinker_unregister(struct super_block *sb)
+{
+	struct erofs_sb_info *const sbi = EROFS_SB(sb);
+
+	mutex_lock(&sbi->umount_mutex);
+	erofs_shrink_workstation(sbi, ~0UL, true);
+
+	spin_lock(&erofs_sb_list_lock);
+	list_del(&sbi->list);
+	spin_unlock(&erofs_sb_list_lock);
+	mutex_unlock(&sbi->umount_mutex);
+}
+
+static unsigned long erofs_shrink_count(struct shrinker *shrink,
+					struct shrink_control *sc)
+{
+	return atomic_long_read(&erofs_global_shrink_cnt);
+}
+
+static unsigned long erofs_shrink_scan(struct shrinker *shrink,
+				       struct shrink_control *sc)
+{
+	struct erofs_sb_info *sbi;
+	struct list_head *p;
+
+	unsigned long nr = sc->nr_to_scan;
+	unsigned int run_no;
+	unsigned long freed = 0;
+
+	spin_lock(&erofs_sb_list_lock);
+	do {
+		run_no = ++shrinker_run_no;
+	} while (run_no == 0);
+
+	/* Iterate over all mounted superblocks and try to shrink them */
+	p = erofs_sb_list.next;
+	while (p != &erofs_sb_list) {
+		sbi = list_entry(p, struct erofs_sb_info, list);
+
+		/*
+		 * We move the ones we do to the end of the list, so we stop
+		 * when we see one we have already done.
+		 */
+		if (sbi->shrinker_run_no == run_no)
+			break;
+
+		if (!mutex_trylock(&sbi->umount_mutex)) {
+			p = p->next;
+			continue;
+		}
+
+		spin_unlock(&erofs_sb_list_lock);
+		sbi->shrinker_run_no = run_no;
+
+		freed += erofs_shrink_workstation(sbi, nr, false);
+
+		spin_lock(&erofs_sb_list_lock);
+		/* Get the next list element before we move this one */
+		p = p->next;
+
+		/*
+		 * Move this one to the end of the list to provide some
+		 * fairness.
+		 */
+		list_move_tail(&sbi->list, &erofs_sb_list);
+		mutex_unlock(&sbi->umount_mutex);
+
+		if (freed >= nr)
+			break;
+	}
+	spin_unlock(&erofs_sb_list_lock);
+	return freed;
+}
+
+static struct shrinker erofs_shrinker_info = {
+	.scan_objects = erofs_shrink_scan,
+	.count_objects = erofs_shrink_count,
+	.seeks = DEFAULT_SEEKS,
+};
+
+int __init erofs_init_shrinker(void)
+{
+	return register_shrinker(&erofs_shrinker_info);
+}
+
+void erofs_exit_shrinker(void)
+{
+	unregister_shrinker(&erofs_shrinker_info);
+}
+#endif	/* !CONFIG_EROFS_FS_ZIP */
+
diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c
new file mode 100644
index 000000000000..a8286998a079
--- /dev/null
+++ b/fs/erofs/xattr.c
@@ -0,0 +1,703 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017-2018 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#include <linux/security.h>
+#include "xattr.h"
+
+struct xattr_iter {
+	struct super_block *sb;
+	struct page *page;
+	void *kaddr;
+
+	erofs_blk_t blkaddr;
+	unsigned int ofs;
+};
+
+static inline void xattr_iter_end(struct xattr_iter *it, bool atomic)
+{
+	/* the only user of kunmap() is 'init_inode_xattrs' */
+	if (unlikely(!atomic))
+		kunmap(it->page);
+	else
+		kunmap_atomic(it->kaddr);
+
+	unlock_page(it->page);
+	put_page(it->page);
+}
+
+static inline void xattr_iter_end_final(struct xattr_iter *it)
+{
+	if (!it->page)
+		return;
+
+	xattr_iter_end(it, true);
+}
+
+static int init_inode_xattrs(struct inode *inode)
+{
+	struct erofs_vnode *const vi = EROFS_V(inode);
+	struct xattr_iter it;
+	unsigned int i;
+	struct erofs_xattr_ibody_header *ih;
+	struct super_block *sb;
+	struct erofs_sb_info *sbi;
+	bool atomic_map;
+	int ret = 0;
+
+	/* the most case is that xattrs of this inode are initialized. */
+	if (test_bit(EROFS_V_EA_INITED_BIT, &vi->flags))
+		return 0;
+
+	if (wait_on_bit_lock(&vi->flags, EROFS_V_BL_XATTR_BIT, TASK_KILLABLE))
+		return -ERESTARTSYS;
+
+	/* someone has initialized xattrs for us? */
+	if (test_bit(EROFS_V_EA_INITED_BIT, &vi->flags))
+		goto out_unlock;
+
+	/*
+	 * bypass all xattr operations if ->xattr_isize is not greater than
+	 * sizeof(struct erofs_xattr_ibody_header), in detail:
+	 * 1) it is not enough to contain erofs_xattr_ibody_header then
+	 *    ->xattr_isize should be 0 (it means no xattr);
+	 * 2) it is just to contain erofs_xattr_ibody_header, which is on-disk
+	 *    undefined right now (maybe use later with some new sb feature).
+	 */
+	if (vi->xattr_isize == sizeof(struct erofs_xattr_ibody_header)) {
+		errln("xattr_isize %d of nid %llu is not supported yet",
+		      vi->xattr_isize, vi->nid);
+		ret = -EOPNOTSUPP;
+		goto out_unlock;
+	} else if (vi->xattr_isize < sizeof(struct erofs_xattr_ibody_header)) {
+		if (unlikely(vi->xattr_isize)) {
+			errln("bogus xattr ibody @ nid %llu", vi->nid);
+			DBG_BUGON(1);
+			ret = -EFSCORRUPTED;
+			goto out_unlock;	/* xattr ondisk layout error */
+		}
+		ret = -ENOATTR;
+		goto out_unlock;
+	}
+
+	sb = inode->i_sb;
+	sbi = EROFS_SB(sb);
+	it.blkaddr = erofs_blknr(iloc(sbi, vi->nid) + vi->inode_isize);
+	it.ofs = erofs_blkoff(iloc(sbi, vi->nid) + vi->inode_isize);
+
+	it.page = erofs_get_inline_page(inode, it.blkaddr);
+	if (IS_ERR(it.page)) {
+		ret = PTR_ERR(it.page);
+		goto out_unlock;
+	}
+
+	/* read in shared xattr array (non-atomic, see kmalloc below) */
+	it.kaddr = kmap(it.page);
+	atomic_map = false;
+
+	ih = (struct erofs_xattr_ibody_header *)(it.kaddr + it.ofs);
+
+	vi->xattr_shared_count = ih->h_shared_count;
+	vi->xattr_shared_xattrs = kmalloc_array(vi->xattr_shared_count,
+						sizeof(uint), GFP_KERNEL);
+	if (!vi->xattr_shared_xattrs) {
+		xattr_iter_end(&it, atomic_map);
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+
+	/* let's skip ibody header */
+	it.ofs += sizeof(struct erofs_xattr_ibody_header);
+
+	for (i = 0; i < vi->xattr_shared_count; ++i) {
+		if (unlikely(it.ofs >= EROFS_BLKSIZ)) {
+			/* cannot be unaligned */
+			DBG_BUGON(it.ofs != EROFS_BLKSIZ);
+			xattr_iter_end(&it, atomic_map);
+
+			it.page = erofs_get_meta_page(sb, ++it.blkaddr,
+						      S_ISDIR(inode->i_mode));
+			if (IS_ERR(it.page)) {
+				kfree(vi->xattr_shared_xattrs);
+				vi->xattr_shared_xattrs = NULL;
+				ret = PTR_ERR(it.page);
+				goto out_unlock;
+			}
+
+			it.kaddr = kmap_atomic(it.page);
+			atomic_map = true;
+			it.ofs = 0;
+		}
+		vi->xattr_shared_xattrs[i] =
+			le32_to_cpu(*(__le32 *)(it.kaddr + it.ofs));
+		it.ofs += sizeof(__le32);
+	}
+	xattr_iter_end(&it, atomic_map);
+
+	set_bit(EROFS_V_EA_INITED_BIT, &vi->flags);
+
+out_unlock:
+	clear_and_wake_up_bit(EROFS_V_BL_XATTR_BIT, &vi->flags);
+	return ret;
+}
+
+/*
+ * the general idea for these return values is
+ * if    0 is returned, go on processing the current xattr;
+ *       1 (> 0) is returned, skip this round to process the next xattr;
+ *    -err (< 0) is returned, an error (maybe ENOXATTR) occurred
+ *                            and need to be handled
+ */
+struct xattr_iter_handlers {
+	int (*entry)(struct xattr_iter *_it, struct erofs_xattr_entry *entry);
+	int (*name)(struct xattr_iter *_it, unsigned int processed, char *buf,
+		    unsigned int len);
+	int (*alloc_buffer)(struct xattr_iter *_it, unsigned int value_sz);
+	void (*value)(struct xattr_iter *_it, unsigned int processed, char *buf,
+		      unsigned int len);
+};
+
+static inline int xattr_iter_fixup(struct xattr_iter *it)
+{
+	if (it->ofs < EROFS_BLKSIZ)
+		return 0;
+
+	xattr_iter_end(it, true);
+
+	it->blkaddr += erofs_blknr(it->ofs);
+
+	it->page = erofs_get_meta_page(it->sb, it->blkaddr, false);
+	if (IS_ERR(it->page)) {
+		int err = PTR_ERR(it->page);
+
+		it->page = NULL;
+		return err;
+	}
+
+	it->kaddr = kmap_atomic(it->page);
+	it->ofs = erofs_blkoff(it->ofs);
+	return 0;
+}
+
+static int inline_xattr_iter_begin(struct xattr_iter *it,
+				   struct inode *inode)
+{
+	struct erofs_vnode *const vi = EROFS_V(inode);
+	struct erofs_sb_info *const sbi = EROFS_SB(inode->i_sb);
+	unsigned int xattr_header_sz, inline_xattr_ofs;
+
+	xattr_header_sz = inlinexattr_header_size(inode);
+	if (unlikely(xattr_header_sz >= vi->xattr_isize)) {
+		DBG_BUGON(xattr_header_sz > vi->xattr_isize);
+		return -ENOATTR;
+	}
+
+	inline_xattr_ofs = vi->inode_isize + xattr_header_sz;
+
+	it->blkaddr = erofs_blknr(iloc(sbi, vi->nid) + inline_xattr_ofs);
+	it->ofs = erofs_blkoff(iloc(sbi, vi->nid) + inline_xattr_ofs);
+
+	it->page = erofs_get_inline_page(inode, it->blkaddr);
+	if (IS_ERR(it->page))
+		return PTR_ERR(it->page);
+
+	it->kaddr = kmap_atomic(it->page);
+	return vi->xattr_isize - xattr_header_sz;
+}
+
+/*
+ * Regardless of success or failure, `xattr_foreach' will end up with
+ * `ofs' pointing to the next xattr item rather than an arbitrary position.
+ */
+static int xattr_foreach(struct xattr_iter *it,
+			 const struct xattr_iter_handlers *op,
+			 unsigned int *tlimit)
+{
+	struct erofs_xattr_entry entry;
+	unsigned int value_sz, processed, slice;
+	int err;
+
+	/* 0. fixup blkaddr, ofs, ipage */
+	err = xattr_iter_fixup(it);
+	if (err)
+		return err;
+
+	/*
+	 * 1. read xattr entry to the memory,
+	 *    since we do EROFS_XATTR_ALIGN
+	 *    therefore entry should be in the page
+	 */
+	entry = *(struct erofs_xattr_entry *)(it->kaddr + it->ofs);
+	if (tlimit) {
+		unsigned int entry_sz = EROFS_XATTR_ENTRY_SIZE(&entry);
+
+		/* xattr on-disk corruption: xattr entry beyond xattr_isize */
+		if (unlikely(*tlimit < entry_sz)) {
+			DBG_BUGON(1);
+			return -EFSCORRUPTED;
+		}
+		*tlimit -= entry_sz;
+	}
+
+	it->ofs += sizeof(struct erofs_xattr_entry);
+	value_sz = le16_to_cpu(entry.e_value_size);
+
+	/* handle entry */
+	err = op->entry(it, &entry);
+	if (err) {
+		it->ofs += entry.e_name_len + value_sz;
+		goto out;
+	}
+
+	/* 2. handle xattr name (ofs will finally be at the end of name) */
+	processed = 0;
+
+	while (processed < entry.e_name_len) {
+		if (it->ofs >= EROFS_BLKSIZ) {
+			DBG_BUGON(it->ofs > EROFS_BLKSIZ);
+
+			err = xattr_iter_fixup(it);
+			if (err)
+				goto out;
+			it->ofs = 0;
+		}
+
+		slice = min_t(unsigned int, PAGE_SIZE - it->ofs,
+			      entry.e_name_len - processed);
+
+		/* handle name */
+		err = op->name(it, processed, it->kaddr + it->ofs, slice);
+		if (err) {
+			it->ofs += entry.e_name_len - processed + value_sz;
+			goto out;
+		}
+
+		it->ofs += slice;
+		processed += slice;
+	}
+
+	/* 3. handle xattr value */
+	processed = 0;
+
+	if (op->alloc_buffer) {
+		err = op->alloc_buffer(it, value_sz);
+		if (err) {
+			it->ofs += value_sz;
+			goto out;
+		}
+	}
+
+	while (processed < value_sz) {
+		if (it->ofs >= EROFS_BLKSIZ) {
+			DBG_BUGON(it->ofs > EROFS_BLKSIZ);
+
+			err = xattr_iter_fixup(it);
+			if (err)
+				goto out;
+			it->ofs = 0;
+		}
+
+		slice = min_t(unsigned int, PAGE_SIZE - it->ofs,
+			      value_sz - processed);
+		op->value(it, processed, it->kaddr + it->ofs, slice);
+		it->ofs += slice;
+		processed += slice;
+	}
+
+out:
+	/* xattrs should be 4-byte aligned (on-disk constraint) */
+	it->ofs = EROFS_XATTR_ALIGN(it->ofs);
+	return err < 0 ? err : 0;
+}
+
+struct getxattr_iter {
+	struct xattr_iter it;
+
+	char *buffer;
+	int buffer_size, index;
+	struct qstr name;
+};
+
+static int xattr_entrymatch(struct xattr_iter *_it,
+			    struct erofs_xattr_entry *entry)
+{
+	struct getxattr_iter *it = container_of(_it, struct getxattr_iter, it);
+
+	return (it->index != entry->e_name_index ||
+		it->name.len != entry->e_name_len) ? -ENOATTR : 0;
+}
+
+static int xattr_namematch(struct xattr_iter *_it,
+			   unsigned int processed, char *buf, unsigned int len)
+{
+	struct getxattr_iter *it = container_of(_it, struct getxattr_iter, it);
+
+	return memcmp(buf, it->name.name + processed, len) ? -ENOATTR : 0;
+}
+
+static int xattr_checkbuffer(struct xattr_iter *_it,
+			     unsigned int value_sz)
+{
+	struct getxattr_iter *it = container_of(_it, struct getxattr_iter, it);
+	int err = it->buffer_size < value_sz ? -ERANGE : 0;
+
+	it->buffer_size = value_sz;
+	return !it->buffer ? 1 : err;
+}
+
+static void xattr_copyvalue(struct xattr_iter *_it,
+			    unsigned int processed,
+			    char *buf, unsigned int len)
+{
+	struct getxattr_iter *it = container_of(_it, struct getxattr_iter, it);
+
+	memcpy(it->buffer + processed, buf, len);
+}
+
+static const struct xattr_iter_handlers find_xattr_handlers = {
+	.entry = xattr_entrymatch,
+	.name = xattr_namematch,
+	.alloc_buffer = xattr_checkbuffer,
+	.value = xattr_copyvalue
+};
+
+static int inline_getxattr(struct inode *inode, struct getxattr_iter *it)
+{
+	int ret;
+	unsigned int remaining;
+
+	ret = inline_xattr_iter_begin(&it->it, inode);
+	if (ret < 0)
+		return ret;
+
+	remaining = ret;
+	while (remaining) {
+		ret = xattr_foreach(&it->it, &find_xattr_handlers, &remaining);
+		if (ret != -ENOATTR)
+			break;
+	}
+	xattr_iter_end_final(&it->it);
+
+	return ret ? ret : it->buffer_size;
+}
+
+static int shared_getxattr(struct inode *inode, struct getxattr_iter *it)
+{
+	struct erofs_vnode *const vi = EROFS_V(inode);
+	struct super_block *const sb = inode->i_sb;
+	struct erofs_sb_info *const sbi = EROFS_SB(sb);
+	unsigned int i;
+	int ret = -ENOATTR;
+
+	for (i = 0; i < vi->xattr_shared_count; ++i) {
+		erofs_blk_t blkaddr =
+			xattrblock_addr(sbi, vi->xattr_shared_xattrs[i]);
+
+		it->it.ofs = xattrblock_offset(sbi, vi->xattr_shared_xattrs[i]);
+
+		if (!i || blkaddr != it->it.blkaddr) {
+			if (i)
+				xattr_iter_end(&it->it, true);
+
+			it->it.page = erofs_get_meta_page(sb, blkaddr, false);
+			if (IS_ERR(it->it.page))
+				return PTR_ERR(it->it.page);
+
+			it->it.kaddr = kmap_atomic(it->it.page);
+			it->it.blkaddr = blkaddr;
+		}
+
+		ret = xattr_foreach(&it->it, &find_xattr_handlers, NULL);
+		if (ret != -ENOATTR)
+			break;
+	}
+	if (vi->xattr_shared_count)
+		xattr_iter_end_final(&it->it);
+
+	return ret ? ret : it->buffer_size;
+}
+
+static bool erofs_xattr_user_list(struct dentry *dentry)
+{
+	return test_opt(EROFS_SB(dentry->d_sb), XATTR_USER);
+}
+
+static bool erofs_xattr_trusted_list(struct dentry *dentry)
+{
+	return capable(CAP_SYS_ADMIN);
+}
+
+int erofs_getxattr(struct inode *inode, int index,
+		   const char *name,
+		   void *buffer, size_t buffer_size)
+{
+	int ret;
+	struct getxattr_iter it;
+
+	if (unlikely(!name))
+		return -EINVAL;
+
+	ret = init_inode_xattrs(inode);
+	if (ret)
+		return ret;
+
+	it.index = index;
+
+	it.name.len = strlen(name);
+	if (it.name.len > EROFS_NAME_LEN)
+		return -ERANGE;
+	it.name.name = name;
+
+	it.buffer = buffer;
+	it.buffer_size = buffer_size;
+
+	it.it.sb = inode->i_sb;
+	ret = inline_getxattr(inode, &it);
+	if (ret == -ENOATTR)
+		ret = shared_getxattr(inode, &it);
+	return ret;
+}
+
+static int erofs_xattr_generic_get(const struct xattr_handler *handler,
+				   struct dentry *unused, struct inode *inode,
+				   const char *name, void *buffer, size_t size)
+{
+	struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
+
+	switch (handler->flags) {
+	case EROFS_XATTR_INDEX_USER:
+		if (!test_opt(sbi, XATTR_USER))
+			return -EOPNOTSUPP;
+		break;
+	case EROFS_XATTR_INDEX_TRUSTED:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		break;
+	case EROFS_XATTR_INDEX_SECURITY:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return erofs_getxattr(inode, handler->flags, name, buffer, size);
+}
+
+const struct xattr_handler erofs_xattr_user_handler = {
+	.prefix	= XATTR_USER_PREFIX,
+	.flags	= EROFS_XATTR_INDEX_USER,
+	.list	= erofs_xattr_user_list,
+	.get	= erofs_xattr_generic_get,
+};
+
+const struct xattr_handler erofs_xattr_trusted_handler = {
+	.prefix	= XATTR_TRUSTED_PREFIX,
+	.flags	= EROFS_XATTR_INDEX_TRUSTED,
+	.list	= erofs_xattr_trusted_list,
+	.get	= erofs_xattr_generic_get,
+};
+
+#ifdef CONFIG_EROFS_FS_SECURITY
+const struct xattr_handler __maybe_unused erofs_xattr_security_handler = {
+	.prefix	= XATTR_SECURITY_PREFIX,
+	.flags	= EROFS_XATTR_INDEX_SECURITY,
+	.get	= erofs_xattr_generic_get,
+};
+#endif
+
+const struct xattr_handler *erofs_xattr_handlers[] = {
+	&erofs_xattr_user_handler,
+#ifdef CONFIG_EROFS_FS_POSIX_ACL
+	&posix_acl_access_xattr_handler,
+	&posix_acl_default_xattr_handler,
+#endif
+	&erofs_xattr_trusted_handler,
+#ifdef CONFIG_EROFS_FS_SECURITY
+	&erofs_xattr_security_handler,
+#endif
+	NULL,
+};
+
+struct listxattr_iter {
+	struct xattr_iter it;
+
+	struct dentry *dentry;
+	char *buffer;
+	int buffer_size, buffer_ofs;
+};
+
+static int xattr_entrylist(struct xattr_iter *_it,
+			   struct erofs_xattr_entry *entry)
+{
+	struct listxattr_iter *it =
+		container_of(_it, struct listxattr_iter, it);
+	unsigned int prefix_len;
+	const char *prefix;
+
+	const struct xattr_handler *h =
+		erofs_xattr_handler(entry->e_name_index);
+
+	if (!h || (h->list && !h->list(it->dentry)))
+		return 1;
+
+	prefix = xattr_prefix(h);
+	prefix_len = strlen(prefix);
+
+	if (!it->buffer) {
+		it->buffer_ofs += prefix_len + entry->e_name_len + 1;
+		return 1;
+	}
+
+	if (it->buffer_ofs + prefix_len
+		+ entry->e_name_len + 1 > it->buffer_size)
+		return -ERANGE;
+
+	memcpy(it->buffer + it->buffer_ofs, prefix, prefix_len);
+	it->buffer_ofs += prefix_len;
+	return 0;
+}
+
+static int xattr_namelist(struct xattr_iter *_it,
+			  unsigned int processed, char *buf, unsigned int len)
+{
+	struct listxattr_iter *it =
+		container_of(_it, struct listxattr_iter, it);
+
+	memcpy(it->buffer + it->buffer_ofs, buf, len);
+	it->buffer_ofs += len;
+	return 0;
+}
+
+static int xattr_skipvalue(struct xattr_iter *_it,
+			   unsigned int value_sz)
+{
+	struct listxattr_iter *it =
+		container_of(_it, struct listxattr_iter, it);
+
+	it->buffer[it->buffer_ofs++] = '\0';
+	return 1;
+}
+
+static const struct xattr_iter_handlers list_xattr_handlers = {
+	.entry = xattr_entrylist,
+	.name = xattr_namelist,
+	.alloc_buffer = xattr_skipvalue,
+	.value = NULL
+};
+
+static int inline_listxattr(struct listxattr_iter *it)
+{
+	int ret;
+	unsigned int remaining;
+
+	ret = inline_xattr_iter_begin(&it->it, d_inode(it->dentry));
+	if (ret < 0)
+		return ret;
+
+	remaining = ret;
+	while (remaining) {
+		ret = xattr_foreach(&it->it, &list_xattr_handlers, &remaining);
+		if (ret)
+			break;
+	}
+	xattr_iter_end_final(&it->it);
+	return ret ? ret : it->buffer_ofs;
+}
+
+static int shared_listxattr(struct listxattr_iter *it)
+{
+	struct inode *const inode = d_inode(it->dentry);
+	struct erofs_vnode *const vi = EROFS_V(inode);
+	struct super_block *const sb = inode->i_sb;
+	struct erofs_sb_info *const sbi = EROFS_SB(sb);
+	unsigned int i;
+	int ret = 0;
+
+	for (i = 0; i < vi->xattr_shared_count; ++i) {
+		erofs_blk_t blkaddr =
+			xattrblock_addr(sbi, vi->xattr_shared_xattrs[i]);
+
+		it->it.ofs = xattrblock_offset(sbi, vi->xattr_shared_xattrs[i]);
+		if (!i || blkaddr != it->it.blkaddr) {
+			if (i)
+				xattr_iter_end(&it->it, true);
+
+			it->it.page = erofs_get_meta_page(sb, blkaddr, false);
+			if (IS_ERR(it->it.page))
+				return PTR_ERR(it->it.page);
+
+			it->it.kaddr = kmap_atomic(it->it.page);
+			it->it.blkaddr = blkaddr;
+		}
+
+		ret = xattr_foreach(&it->it, &list_xattr_handlers, NULL);
+		if (ret)
+			break;
+	}
+	if (vi->xattr_shared_count)
+		xattr_iter_end_final(&it->it);
+
+	return ret ? ret : it->buffer_ofs;
+}
+
+ssize_t erofs_listxattr(struct dentry *dentry,
+			char *buffer, size_t buffer_size)
+{
+	int ret;
+	struct listxattr_iter it;
+
+	ret = init_inode_xattrs(d_inode(dentry));
+	if (ret)
+		return ret;
+
+	it.dentry = dentry;
+	it.buffer = buffer;
+	it.buffer_size = buffer_size;
+	it.buffer_ofs = 0;
+
+	it.it.sb = dentry->d_sb;
+
+	ret = inline_listxattr(&it);
+	if (ret < 0 && ret != -ENOATTR)
+		return ret;
+	return shared_listxattr(&it);
+}
+
+#ifdef CONFIG_EROFS_FS_POSIX_ACL
+struct posix_acl *erofs_get_acl(struct inode *inode, int type)
+{
+	struct posix_acl *acl;
+	int prefix, rc;
+	char *value = NULL;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		prefix = EROFS_XATTR_INDEX_POSIX_ACL_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		prefix = EROFS_XATTR_INDEX_POSIX_ACL_DEFAULT;
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	rc = erofs_getxattr(inode, prefix, "", NULL, 0);
+	if (rc > 0) {
+		value = kmalloc(rc, GFP_KERNEL);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		rc = erofs_getxattr(inode, prefix, "", value, rc);
+	}
+
+	if (rc == -ENOATTR)
+		acl = NULL;
+	else if (rc < 0)
+		acl = ERR_PTR(rc);
+	else
+		acl = posix_acl_from_xattr(&init_user_ns, value, rc);
+	kfree(value);
+	return acl;
+}
+#endif
+
diff --git a/fs/erofs/xattr.h b/fs/erofs/xattr.h
new file mode 100644
index 000000000000..c5ca47d814dd
--- /dev/null
+++ b/fs/erofs/xattr.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017-2018 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#ifndef __EROFS_XATTR_H
+#define __EROFS_XATTR_H
+
+#include "internal.h"
+#include <linux/posix_acl_xattr.h>
+#include <linux/xattr.h>
+
+/* Attribute not found */
+#define ENOATTR         ENODATA
+
+static inline unsigned int inlinexattr_header_size(struct inode *inode)
+{
+	return sizeof(struct erofs_xattr_ibody_header)
+		+ sizeof(u32) * EROFS_V(inode)->xattr_shared_count;
+}
+
+static inline erofs_blk_t xattrblock_addr(struct erofs_sb_info *sbi,
+					  unsigned int xattr_id)
+{
+#ifdef CONFIG_EROFS_FS_XATTR
+	return sbi->xattr_blkaddr +
+		xattr_id * sizeof(__u32) / EROFS_BLKSIZ;
+#else
+	return 0;
+#endif
+}
+
+static inline unsigned int xattrblock_offset(struct erofs_sb_info *sbi,
+					     unsigned int xattr_id)
+{
+	return (xattr_id * sizeof(__u32)) % EROFS_BLKSIZ;
+}
+
+#ifdef CONFIG_EROFS_FS_XATTR
+extern const struct xattr_handler erofs_xattr_user_handler;
+extern const struct xattr_handler erofs_xattr_trusted_handler;
+#ifdef CONFIG_EROFS_FS_SECURITY
+extern const struct xattr_handler erofs_xattr_security_handler;
+#endif
+
+static inline const struct xattr_handler *erofs_xattr_handler(unsigned int idx)
+{
+static const struct xattr_handler *xattr_handler_map[] = {
+	[EROFS_XATTR_INDEX_USER] = &erofs_xattr_user_handler,
+#ifdef CONFIG_EROFS_FS_POSIX_ACL
+	[EROFS_XATTR_INDEX_POSIX_ACL_ACCESS] = &posix_acl_access_xattr_handler,
+	[EROFS_XATTR_INDEX_POSIX_ACL_DEFAULT] =
+		&posix_acl_default_xattr_handler,
+#endif
+	[EROFS_XATTR_INDEX_TRUSTED] = &erofs_xattr_trusted_handler,
+#ifdef CONFIG_EROFS_FS_SECURITY
+	[EROFS_XATTR_INDEX_SECURITY] = &erofs_xattr_security_handler,
+#endif
+};
+
+	return idx && idx < ARRAY_SIZE(xattr_handler_map) ?
+		xattr_handler_map[idx] : NULL;
+}
+
+extern const struct xattr_handler *erofs_xattr_handlers[];
+
+int erofs_getxattr(struct inode *, int, const char *, void *, size_t);
+ssize_t erofs_listxattr(struct dentry *, char *, size_t);
+#else
+static inline int erofs_getxattr(struct inode *inode, int index,
+				 const char *name, void *buffer,
+				 size_t buffer_size)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline ssize_t erofs_listxattr(struct dentry *dentry,
+				      char *buffer, size_t buffer_size)
+{
+	return -EOPNOTSUPP;
+}
+#endif	/* !CONFIG_EROFS_FS_XATTR */
+
+#ifdef CONFIG_EROFS_FS_POSIX_ACL
+struct posix_acl *erofs_get_acl(struct inode *inode, int type);
+#else
+#define erofs_get_acl	(NULL)
+#endif
+
+#endif
+
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
new file mode 100644
index 000000000000..b32ad585237c
--- /dev/null
+++ b/fs/erofs/zdata.c
@@ -0,0 +1,1432 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2018 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#include "zdata.h"
+#include "compress.h"
+#include <linux/prefetch.h>
+
+#include <trace/events/erofs.h>
+
+/*
+ * a compressed_pages[] placeholder in order to avoid
+ * being filled with file pages for in-place decompression.
+ */
+#define PAGE_UNALLOCATED     ((void *)0x5F0E4B1D)
+
+/* how to allocate cached pages for a pcluster */
+enum z_erofs_cache_alloctype {
+	DONTALLOC,	/* don't allocate any cached pages */
+	DELAYEDALLOC,	/* delayed allocation (at the time of submitting io) */
+};
+
+/*
+ * tagged pointer with 1-bit tag for all compressed pages
+ * tag 0 - the page is just found with an extra page reference
+ */
+typedef tagptr1_t compressed_page_t;
+
+#define tag_compressed_page_justfound(page) \
+	tagptr_fold(compressed_page_t, page, 1)
+
+static struct workqueue_struct *z_erofs_workqueue __read_mostly;
+static struct kmem_cache *pcluster_cachep __read_mostly;
+
+void z_erofs_exit_zip_subsystem(void)
+{
+	destroy_workqueue(z_erofs_workqueue);
+	kmem_cache_destroy(pcluster_cachep);
+}
+
+static inline int init_unzip_workqueue(void)
+{
+	const unsigned int onlinecpus = num_possible_cpus();
+	const unsigned int flags = WQ_UNBOUND | WQ_HIGHPRI | WQ_CPU_INTENSIVE;
+
+	/*
+	 * no need to spawn too many threads, limiting threads could minimum
+	 * scheduling overhead, perhaps per-CPU threads should be better?
+	 */
+	z_erofs_workqueue = alloc_workqueue("erofs_unzipd", flags,
+					    onlinecpus + onlinecpus / 4);
+	return z_erofs_workqueue ? 0 : -ENOMEM;
+}
+
+static void init_once(void *ptr)
+{
+	struct z_erofs_pcluster *pcl = ptr;
+	struct z_erofs_collection *cl = z_erofs_primarycollection(pcl);
+	unsigned int i;
+
+	mutex_init(&cl->lock);
+	cl->nr_pages = 0;
+	cl->vcnt = 0;
+	for (i = 0; i < Z_EROFS_CLUSTER_MAX_PAGES; ++i)
+		pcl->compressed_pages[i] = NULL;
+}
+
+static void init_always(struct z_erofs_pcluster *pcl)
+{
+	struct z_erofs_collection *cl = z_erofs_primarycollection(pcl);
+
+	atomic_set(&pcl->obj.refcount, 1);
+
+	DBG_BUGON(cl->nr_pages);
+	DBG_BUGON(cl->vcnt);
+}
+
+int __init z_erofs_init_zip_subsystem(void)
+{
+	pcluster_cachep = kmem_cache_create("erofs_compress",
+					    Z_EROFS_WORKGROUP_SIZE, 0,
+					    SLAB_RECLAIM_ACCOUNT, init_once);
+	if (pcluster_cachep) {
+		if (!init_unzip_workqueue())
+			return 0;
+
+		kmem_cache_destroy(pcluster_cachep);
+	}
+	return -ENOMEM;
+}
+
+enum z_erofs_collectmode {
+	COLLECT_SECONDARY,
+	COLLECT_PRIMARY,
+	/*
+	 * The current collection was the tail of an exist chain, in addition
+	 * that the previous processed chained collections are all decided to
+	 * be hooked up to it.
+	 * A new chain will be created for the remaining collections which are
+	 * not processed yet, therefore different from COLLECT_PRIMARY_FOLLOWED,
+	 * the next collection cannot reuse the whole page safely in
+	 * the following scenario:
+	 *  ________________________________________________________________
+	 * |      tail (partial) page     |       head (partial) page       |
+	 * |   (belongs to the next cl)   |   (belongs to the current cl)   |
+	 * |_______PRIMARY_FOLLOWED_______|________PRIMARY_HOOKED___________|
+	 */
+	COLLECT_PRIMARY_HOOKED,
+	COLLECT_PRIMARY_FOLLOWED_NOINPLACE,
+	/*
+	 * The current collection has been linked with the owned chain, and
+	 * could also be linked with the remaining collections, which means
+	 * if the processing page is the tail page of the collection, thus
+	 * the current collection can safely use the whole page (since
+	 * the previous collection is under control) for in-place I/O, as
+	 * illustrated below:
+	 *  ________________________________________________________________
+	 * |  tail (partial) page |          head (partial) page           |
+	 * |  (of the current cl) |      (of the previous collection)      |
+	 * |  PRIMARY_FOLLOWED or |                                        |
+	 * |_____PRIMARY_HOOKED___|____________PRIMARY_FOLLOWED____________|
+	 *
+	 * [  (*) the above page can be used as inplace I/O.               ]
+	 */
+	COLLECT_PRIMARY_FOLLOWED,
+};
+
+struct z_erofs_collector {
+	struct z_erofs_pagevec_ctor vector;
+
+	struct z_erofs_pcluster *pcl, *tailpcl;
+	struct z_erofs_collection *cl;
+	struct page **compressedpages;
+	z_erofs_next_pcluster_t owned_head;
+
+	enum z_erofs_collectmode mode;
+};
+
+struct z_erofs_decompress_frontend {
+	struct inode *const inode;
+
+	struct z_erofs_collector clt;
+	struct erofs_map_blocks map;
+
+	/* used for applying cache strategy on the fly */
+	bool backmost;
+	erofs_off_t headoffset;
+};
+
+#define COLLECTOR_INIT() { \
+	.owned_head = Z_EROFS_PCLUSTER_TAIL, \
+	.mode = COLLECT_PRIMARY_FOLLOWED }
+
+#define DECOMPRESS_FRONTEND_INIT(__i) { \
+	.inode = __i, .clt = COLLECTOR_INIT(), \
+	.backmost = true, }
+
+static struct page *z_pagemap_global[Z_EROFS_VMAP_GLOBAL_PAGES];
+static DEFINE_MUTEX(z_pagemap_global_lock);
+
+static void preload_compressed_pages(struct z_erofs_collector *clt,
+				     struct address_space *mc,
+				     enum z_erofs_cache_alloctype type,
+				     struct list_head *pagepool)
+{
+	const struct z_erofs_pcluster *pcl = clt->pcl;
+	const unsigned int clusterpages = BIT(pcl->clusterbits);
+	struct page **pages = clt->compressedpages;
+	pgoff_t index = pcl->obj.index + (pages - pcl->compressed_pages);
+	bool standalone = true;
+
+	if (clt->mode < COLLECT_PRIMARY_FOLLOWED)
+		return;
+
+	for (; pages < pcl->compressed_pages + clusterpages; ++pages) {
+		struct page *page;
+		compressed_page_t t;
+
+		/* the compressed page was loaded before */
+		if (READ_ONCE(*pages))
+			continue;
+
+		page = find_get_page(mc, index);
+
+		if (page) {
+			t = tag_compressed_page_justfound(page);
+		} else if (type == DELAYEDALLOC) {
+			t = tagptr_init(compressed_page_t, PAGE_UNALLOCATED);
+		} else {	/* DONTALLOC */
+			if (standalone)
+				clt->compressedpages = pages;
+			standalone = false;
+			continue;
+		}
+
+		if (!cmpxchg_relaxed(pages, NULL, tagptr_cast_ptr(t)))
+			continue;
+
+		if (page)
+			put_page(page);
+	}
+
+	if (standalone)		/* downgrade to PRIMARY_FOLLOWED_NOINPLACE */
+		clt->mode = COLLECT_PRIMARY_FOLLOWED_NOINPLACE;
+}
+
+/* called by erofs_shrinker to get rid of all compressed_pages */
+int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
+				       struct erofs_workgroup *grp)
+{
+	struct z_erofs_pcluster *const pcl =
+		container_of(grp, struct z_erofs_pcluster, obj);
+	struct address_space *const mapping = MNGD_MAPPING(sbi);
+	const unsigned int clusterpages = BIT(pcl->clusterbits);
+	int i;
+
+	/*
+	 * refcount of workgroup is now freezed as 1,
+	 * therefore no need to worry about available decompression users.
+	 */
+	for (i = 0; i < clusterpages; ++i) {
+		struct page *page = pcl->compressed_pages[i];
+
+		if (!page)
+			continue;
+
+		/* block other users from reclaiming or migrating the page */
+		if (!trylock_page(page))
+			return -EBUSY;
+
+		if (unlikely(page->mapping != mapping))
+			continue;
+
+		/* barrier is implied in the following 'unlock_page' */
+		WRITE_ONCE(pcl->compressed_pages[i], NULL);
+		set_page_private(page, 0);
+		ClearPagePrivate(page);
+
+		unlock_page(page);
+		put_page(page);
+	}
+	return 0;
+}
+
+int erofs_try_to_free_cached_page(struct address_space *mapping,
+				  struct page *page)
+{
+	struct z_erofs_pcluster *const pcl = (void *)page_private(page);
+	const unsigned int clusterpages = BIT(pcl->clusterbits);
+	int ret = 0;	/* 0 - busy */
+
+	if (erofs_workgroup_try_to_freeze(&pcl->obj, 1)) {
+		unsigned int i;
+
+		for (i = 0; i < clusterpages; ++i) {
+			if (pcl->compressed_pages[i] == page) {
+				WRITE_ONCE(pcl->compressed_pages[i], NULL);
+				ret = 1;
+				break;
+			}
+		}
+		erofs_workgroup_unfreeze(&pcl->obj, 1);
+
+		if (ret) {
+			ClearPagePrivate(page);
+			put_page(page);
+		}
+	}
+	return ret;
+}
+
+/* page_type must be Z_EROFS_PAGE_TYPE_EXCLUSIVE */
+static inline bool try_inplace_io(struct z_erofs_collector *clt,
+				  struct page *page)
+{
+	struct z_erofs_pcluster *const pcl = clt->pcl;
+	const unsigned int clusterpages = BIT(pcl->clusterbits);
+
+	while (clt->compressedpages < pcl->compressed_pages + clusterpages) {
+		if (!cmpxchg(clt->compressedpages++, NULL, page))
+			return true;
+	}
+	return false;
+}
+
+/* callers must be with collection lock held */
+static int z_erofs_attach_page(struct z_erofs_collector *clt,
+			       struct page *page,
+			       enum z_erofs_page_type type)
+{
+	int ret;
+	bool occupied;
+
+	/* give priority for inplaceio */
+	if (clt->mode >= COLLECT_PRIMARY &&
+	    type == Z_EROFS_PAGE_TYPE_EXCLUSIVE &&
+	    try_inplace_io(clt, page))
+		return 0;
+
+	ret = z_erofs_pagevec_enqueue(&clt->vector,
+				      page, type, &occupied);
+	clt->cl->vcnt += (unsigned int)ret;
+
+	return ret ? 0 : -EAGAIN;
+}
+
+static enum z_erofs_collectmode
+try_to_claim_pcluster(struct z_erofs_pcluster *pcl,
+		      z_erofs_next_pcluster_t *owned_head)
+{
+	/* let's claim these following types of pclusters */
+retry:
+	if (pcl->next == Z_EROFS_PCLUSTER_NIL) {
+		/* type 1, nil pcluster */
+		if (cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_NIL,
+			    *owned_head) != Z_EROFS_PCLUSTER_NIL)
+			goto retry;
+
+		*owned_head = &pcl->next;
+		/* lucky, I am the followee :) */
+		return COLLECT_PRIMARY_FOLLOWED;
+	} else if (pcl->next == Z_EROFS_PCLUSTER_TAIL) {
+		/*
+		 * type 2, link to the end of a existing open chain,
+		 * be careful that its submission itself is governed
+		 * by the original owned chain.
+		 */
+		if (cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL,
+			    *owned_head) != Z_EROFS_PCLUSTER_TAIL)
+			goto retry;
+		*owned_head = Z_EROFS_PCLUSTER_TAIL;
+		return COLLECT_PRIMARY_HOOKED;
+	}
+	return COLLECT_PRIMARY;	/* :( better luck next time */
+}
+
+static struct z_erofs_collection *cllookup(struct z_erofs_collector *clt,
+					   struct inode *inode,
+					   struct erofs_map_blocks *map)
+{
+	struct erofs_workgroup *grp;
+	struct z_erofs_pcluster *pcl;
+	struct z_erofs_collection *cl;
+	unsigned int length;
+	bool tag;
+
+	grp = erofs_find_workgroup(inode->i_sb, map->m_pa >> PAGE_SHIFT, &tag);
+	if (!grp)
+		return NULL;
+
+	pcl = container_of(grp, struct z_erofs_pcluster, obj);
+	if (clt->owned_head == &pcl->next || pcl == clt->tailpcl) {
+		DBG_BUGON(1);
+		erofs_workgroup_put(grp);
+		return ERR_PTR(-EFSCORRUPTED);
+	}
+
+	cl = z_erofs_primarycollection(pcl);
+	if (unlikely(cl->pageofs != (map->m_la & ~PAGE_MASK))) {
+		DBG_BUGON(1);
+		erofs_workgroup_put(grp);
+		return ERR_PTR(-EFSCORRUPTED);
+	}
+
+	length = READ_ONCE(pcl->length);
+	if (length & Z_EROFS_PCLUSTER_FULL_LENGTH) {
+		if ((map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) > length) {
+			DBG_BUGON(1);
+			erofs_workgroup_put(grp);
+			return ERR_PTR(-EFSCORRUPTED);
+		}
+	} else {
+		unsigned int llen = map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT;
+
+		if (map->m_flags & EROFS_MAP_FULL_MAPPED)
+			llen |= Z_EROFS_PCLUSTER_FULL_LENGTH;
+
+		while (llen > length &&
+		       length != cmpxchg_relaxed(&pcl->length, length, llen)) {
+			cpu_relax();
+			length = READ_ONCE(pcl->length);
+		}
+	}
+	mutex_lock(&cl->lock);
+	/* used to check tail merging loop due to corrupted images */
+	if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL)
+		clt->tailpcl = pcl;
+	clt->mode = try_to_claim_pcluster(pcl, &clt->owned_head);
+	/* clean tailpcl if the current owned_head is Z_EROFS_PCLUSTER_TAIL */
+	if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL)
+		clt->tailpcl = NULL;
+	clt->pcl = pcl;
+	clt->cl = cl;
+	return cl;
+}
+
+static struct z_erofs_collection *clregister(struct z_erofs_collector *clt,
+					     struct inode *inode,
+					     struct erofs_map_blocks *map)
+{
+	struct z_erofs_pcluster *pcl;
+	struct z_erofs_collection *cl;
+	int err;
+
+	/* no available workgroup, let's allocate one */
+	pcl = kmem_cache_alloc(pcluster_cachep, GFP_NOFS);
+	if (unlikely(!pcl))
+		return ERR_PTR(-ENOMEM);
+
+	init_always(pcl);
+	pcl->obj.index = map->m_pa >> PAGE_SHIFT;
+
+	pcl->length = (map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) |
+		(map->m_flags & EROFS_MAP_FULL_MAPPED ?
+			Z_EROFS_PCLUSTER_FULL_LENGTH : 0);
+
+	if (map->m_flags & EROFS_MAP_ZIPPED)
+		pcl->algorithmformat = Z_EROFS_COMPRESSION_LZ4;
+	else
+		pcl->algorithmformat = Z_EROFS_COMPRESSION_SHIFTED;
+
+	pcl->clusterbits = EROFS_V(inode)->z_physical_clusterbits[0];
+	pcl->clusterbits -= PAGE_SHIFT;
+
+	/* new pclusters should be claimed as type 1, primary and followed */
+	pcl->next = clt->owned_head;
+	clt->mode = COLLECT_PRIMARY_FOLLOWED;
+
+	cl = z_erofs_primarycollection(pcl);
+	cl->pageofs = map->m_la & ~PAGE_MASK;
+
+	/*
+	 * lock all primary followed works before visible to others
+	 * and mutex_trylock *never* fails for a new pcluster.
+	 */
+	mutex_trylock(&cl->lock);
+
+	err = erofs_register_workgroup(inode->i_sb, &pcl->obj, 0);
+	if (err) {
+		mutex_unlock(&cl->lock);
+		kmem_cache_free(pcluster_cachep, pcl);
+		return ERR_PTR(-EAGAIN);
+	}
+	/* used to check tail merging loop due to corrupted images */
+	if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL)
+		clt->tailpcl = pcl;
+	clt->owned_head = &pcl->next;
+	clt->pcl = pcl;
+	clt->cl = cl;
+	return cl;
+}
+
+static int z_erofs_collector_begin(struct z_erofs_collector *clt,
+				   struct inode *inode,
+				   struct erofs_map_blocks *map)
+{
+	struct z_erofs_collection *cl;
+
+	DBG_BUGON(clt->cl);
+
+	/* must be Z_EROFS_PCLUSTER_TAIL or pointed to previous collection */
+	DBG_BUGON(clt->owned_head == Z_EROFS_PCLUSTER_NIL);
+	DBG_BUGON(clt->owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
+
+	if (!PAGE_ALIGNED(map->m_pa)) {
+		DBG_BUGON(1);
+		return -EINVAL;
+	}
+
+repeat:
+	cl = cllookup(clt, inode, map);
+	if (!cl) {
+		cl = clregister(clt, inode, map);
+
+		if (unlikely(cl == ERR_PTR(-EAGAIN)))
+			goto repeat;
+	}
+
+	if (IS_ERR(cl))
+		return PTR_ERR(cl);
+
+	z_erofs_pagevec_ctor_init(&clt->vector, Z_EROFS_NR_INLINE_PAGEVECS,
+				  cl->pagevec, cl->vcnt);
+
+	clt->compressedpages = clt->pcl->compressed_pages;
+	if (clt->mode <= COLLECT_PRIMARY) /* cannot do in-place I/O */
+		clt->compressedpages += Z_EROFS_CLUSTER_MAX_PAGES;
+	return 0;
+}
+
+/*
+ * keep in mind that no referenced pclusters will be freed
+ * only after a RCU grace period.
+ */
+static void z_erofs_rcu_callback(struct rcu_head *head)
+{
+	struct z_erofs_collection *const cl =
+		container_of(head, struct z_erofs_collection, rcu);
+
+	kmem_cache_free(pcluster_cachep,
+			container_of(cl, struct z_erofs_pcluster,
+				     primary_collection));
+}
+
+void erofs_workgroup_free_rcu(struct erofs_workgroup *grp)
+{
+	struct z_erofs_pcluster *const pcl =
+		container_of(grp, struct z_erofs_pcluster, obj);
+	struct z_erofs_collection *const cl = z_erofs_primarycollection(pcl);
+
+	call_rcu(&cl->rcu, z_erofs_rcu_callback);
+}
+
+static void z_erofs_collection_put(struct z_erofs_collection *cl)
+{
+	struct z_erofs_pcluster *const pcl =
+		container_of(cl, struct z_erofs_pcluster, primary_collection);
+
+	erofs_workgroup_put(&pcl->obj);
+}
+
+static bool z_erofs_collector_end(struct z_erofs_collector *clt)
+{
+	struct z_erofs_collection *cl = clt->cl;
+
+	if (!cl)
+		return false;
+
+	z_erofs_pagevec_ctor_exit(&clt->vector, false);
+	mutex_unlock(&cl->lock);
+
+	/*
+	 * if all pending pages are added, don't hold its reference
+	 * any longer if the pcluster isn't hosted by ourselves.
+	 */
+	if (clt->mode < COLLECT_PRIMARY_FOLLOWED_NOINPLACE)
+		z_erofs_collection_put(cl);
+
+	clt->cl = NULL;
+	return true;
+}
+
+static inline struct page *__stagingpage_alloc(struct list_head *pagepool,
+					       gfp_t gfp)
+{
+	struct page *page = erofs_allocpage(pagepool, gfp, true);
+
+	page->mapping = Z_EROFS_MAPPING_STAGING;
+	return page;
+}
+
+static bool should_alloc_managed_pages(struct z_erofs_decompress_frontend *fe,
+				       unsigned int cachestrategy,
+				       erofs_off_t la)
+{
+	if (cachestrategy <= EROFS_ZIP_CACHE_DISABLED)
+		return false;
+
+	if (fe->backmost)
+		return true;
+
+	return cachestrategy >= EROFS_ZIP_CACHE_READAROUND &&
+		la < fe->headoffset;
+}
+
+static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
+				struct page *page,
+				struct list_head *pagepool)
+{
+	struct inode *const inode = fe->inode;
+	struct erofs_sb_info *const sbi __maybe_unused = EROFS_I_SB(inode);
+	struct erofs_map_blocks *const map = &fe->map;
+	struct z_erofs_collector *const clt = &fe->clt;
+	const loff_t offset = page_offset(page);
+	bool tight = (clt->mode >= COLLECT_PRIMARY_HOOKED);
+
+	enum z_erofs_cache_alloctype cache_strategy;
+	enum z_erofs_page_type page_type;
+	unsigned int cur, end, spiltted, index;
+	int err = 0;
+
+	/* register locked file pages as online pages in pack */
+	z_erofs_onlinepage_init(page);
+
+	spiltted = 0;
+	end = PAGE_SIZE;
+repeat:
+	cur = end - 1;
+
+	/* lucky, within the range of the current map_blocks */
+	if (offset + cur >= map->m_la &&
+	    offset + cur < map->m_la + map->m_llen) {
+		/* didn't get a valid collection previously (very rare) */
+		if (!clt->cl)
+			goto restart_now;
+		goto hitted;
+	}
+
+	/* go ahead the next map_blocks */
+	debugln("%s: [out-of-range] pos %llu", __func__, offset + cur);
+
+	if (z_erofs_collector_end(clt))
+		fe->backmost = false;
+
+	map->m_la = offset + cur;
+	map->m_llen = 0;
+	err = z_erofs_map_blocks_iter(inode, map, 0);
+	if (unlikely(err))
+		goto err_out;
+
+restart_now:
+	if (unlikely(!(map->m_flags & EROFS_MAP_MAPPED)))
+		goto hitted;
+
+	err = z_erofs_collector_begin(clt, inode, map);
+	if (unlikely(err))
+		goto err_out;
+
+	/* preload all compressed pages (maybe downgrade role if necessary) */
+	if (should_alloc_managed_pages(fe, sbi->cache_strategy, map->m_la))
+		cache_strategy = DELAYEDALLOC;
+	else
+		cache_strategy = DONTALLOC;
+
+	preload_compressed_pages(clt, MNGD_MAPPING(sbi),
+				 cache_strategy, pagepool);
+
+	tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED);
+hitted:
+	cur = end - min_t(unsigned int, offset + end - map->m_la, end);
+	if (unlikely(!(map->m_flags & EROFS_MAP_MAPPED))) {
+		zero_user_segment(page, cur, end);
+		goto next_part;
+	}
+
+	/* let's derive page type */
+	page_type = cur ? Z_EROFS_VLE_PAGE_TYPE_HEAD :
+		(!spiltted ? Z_EROFS_PAGE_TYPE_EXCLUSIVE :
+			(tight ? Z_EROFS_PAGE_TYPE_EXCLUSIVE :
+				Z_EROFS_VLE_PAGE_TYPE_TAIL_SHARED));
+
+	if (cur)
+		tight &= (clt->mode >= COLLECT_PRIMARY_FOLLOWED);
+
+retry:
+	err = z_erofs_attach_page(clt, page, page_type);
+	/* should allocate an additional staging page for pagevec */
+	if (err == -EAGAIN) {
+		struct page *const newpage =
+			__stagingpage_alloc(pagepool, GFP_NOFS);
+
+		err = z_erofs_attach_page(clt, newpage,
+					  Z_EROFS_PAGE_TYPE_EXCLUSIVE);
+		if (likely(!err))
+			goto retry;
+	}
+
+	if (unlikely(err))
+		goto err_out;
+
+	index = page->index - (map->m_la >> PAGE_SHIFT);
+
+	z_erofs_onlinepage_fixup(page, index, true);
+
+	/* bump up the number of spiltted parts of a page */
+	++spiltted;
+	/* also update nr_pages */
+	clt->cl->nr_pages = max_t(pgoff_t, clt->cl->nr_pages, index + 1);
+next_part:
+	/* can be used for verification */
+	map->m_llen = offset + cur - map->m_la;
+
+	end = cur;
+	if (end > 0)
+		goto repeat;
+
+out:
+	z_erofs_onlinepage_endio(page);
+
+	debugln("%s, finish page: %pK spiltted: %u map->m_llen %llu",
+		__func__, page, spiltted, map->m_llen);
+	return err;
+
+	/* if some error occurred while processing this page */
+err_out:
+	SetPageError(page);
+	goto out;
+}
+
+static void z_erofs_vle_unzip_kickoff(void *ptr, int bios)
+{
+	tagptr1_t t = tagptr_init(tagptr1_t, ptr);
+	struct z_erofs_unzip_io *io = tagptr_unfold_ptr(t);
+	bool background = tagptr_unfold_tags(t);
+
+	if (!background) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&io->u.wait.lock, flags);
+		if (!atomic_add_return(bios, &io->pending_bios))
+			wake_up_locked(&io->u.wait);
+		spin_unlock_irqrestore(&io->u.wait.lock, flags);
+		return;
+	}
+
+	if (!atomic_add_return(bios, &io->pending_bios))
+		queue_work(z_erofs_workqueue, &io->u.work);
+}
+
+static inline void z_erofs_vle_read_endio(struct bio *bio)
+{
+	struct erofs_sb_info *sbi = NULL;
+	blk_status_t err = bio->bi_status;
+	struct bio_vec *bvec;
+	struct bvec_iter_all iter_all;
+
+	bio_for_each_segment_all(bvec, bio, iter_all) {
+		struct page *page = bvec->bv_page;
+		bool cachemngd = false;
+
+		DBG_BUGON(PageUptodate(page));
+		DBG_BUGON(!page->mapping);
+
+		if (unlikely(!sbi && !z_erofs_page_is_staging(page))) {
+			sbi = EROFS_SB(page->mapping->host->i_sb);
+
+			if (time_to_inject(sbi, FAULT_READ_IO)) {
+				erofs_show_injection_info(FAULT_READ_IO);
+				err = BLK_STS_IOERR;
+			}
+		}
+
+		/* sbi should already be gotten if the page is managed */
+		if (sbi)
+			cachemngd = erofs_page_is_managed(sbi, page);
+
+		if (unlikely(err))
+			SetPageError(page);
+		else if (cachemngd)
+			SetPageUptodate(page);
+
+		if (cachemngd)
+			unlock_page(page);
+	}
+
+	z_erofs_vle_unzip_kickoff(bio->bi_private, -1);
+	bio_put(bio);
+}
+
+static int z_erofs_decompress_pcluster(struct super_block *sb,
+				       struct z_erofs_pcluster *pcl,
+				       struct list_head *pagepool)
+{
+	struct erofs_sb_info *const sbi = EROFS_SB(sb);
+	const unsigned int clusterpages = BIT(pcl->clusterbits);
+	struct z_erofs_pagevec_ctor ctor;
+	unsigned int i, outputsize, llen, nr_pages;
+	struct page *pages_onstack[Z_EROFS_VMAP_ONSTACK_PAGES];
+	struct page **pages, **compressed_pages, *page;
+
+	enum z_erofs_page_type page_type;
+	bool overlapped, partial;
+	struct z_erofs_collection *cl;
+	int err;
+
+	might_sleep();
+	cl = z_erofs_primarycollection(pcl);
+	DBG_BUGON(!READ_ONCE(cl->nr_pages));
+
+	mutex_lock(&cl->lock);
+	nr_pages = cl->nr_pages;
+
+	if (likely(nr_pages <= Z_EROFS_VMAP_ONSTACK_PAGES)) {
+		pages = pages_onstack;
+	} else if (nr_pages <= Z_EROFS_VMAP_GLOBAL_PAGES &&
+		   mutex_trylock(&z_pagemap_global_lock)) {
+		pages = z_pagemap_global;
+	} else {
+		gfp_t gfp_flags = GFP_KERNEL;
+
+		if (nr_pages > Z_EROFS_VMAP_GLOBAL_PAGES)
+			gfp_flags |= __GFP_NOFAIL;
+
+		pages = kvmalloc_array(nr_pages, sizeof(struct page *),
+				       gfp_flags);
+
+		/* fallback to global pagemap for the lowmem scenario */
+		if (unlikely(!pages)) {
+			mutex_lock(&z_pagemap_global_lock);
+			pages = z_pagemap_global;
+		}
+	}
+
+	for (i = 0; i < nr_pages; ++i)
+		pages[i] = NULL;
+
+	err = 0;
+	z_erofs_pagevec_ctor_init(&ctor, Z_EROFS_NR_INLINE_PAGEVECS,
+				  cl->pagevec, 0);
+
+	for (i = 0; i < cl->vcnt; ++i) {
+		unsigned int pagenr;
+
+		page = z_erofs_pagevec_dequeue(&ctor, &page_type);
+
+		/* all pages in pagevec ought to be valid */
+		DBG_BUGON(!page);
+		DBG_BUGON(!page->mapping);
+
+		if (z_erofs_put_stagingpage(pagepool, page))
+			continue;
+
+		if (page_type == Z_EROFS_VLE_PAGE_TYPE_HEAD)
+			pagenr = 0;
+		else
+			pagenr = z_erofs_onlinepage_index(page);
+
+		DBG_BUGON(pagenr >= nr_pages);
+
+		/*
+		 * currently EROFS doesn't support multiref(dedup),
+		 * so here erroring out one multiref page.
+		 */
+		if (unlikely(pages[pagenr])) {
+			DBG_BUGON(1);
+			SetPageError(pages[pagenr]);
+			z_erofs_onlinepage_endio(pages[pagenr]);
+			err = -EFSCORRUPTED;
+		}
+		pages[pagenr] = page;
+	}
+	z_erofs_pagevec_ctor_exit(&ctor, true);
+
+	overlapped = false;
+	compressed_pages = pcl->compressed_pages;
+
+	for (i = 0; i < clusterpages; ++i) {
+		unsigned int pagenr;
+
+		page = compressed_pages[i];
+
+		/* all compressed pages ought to be valid */
+		DBG_BUGON(!page);
+		DBG_BUGON(!page->mapping);
+
+		if (!z_erofs_page_is_staging(page)) {
+			if (erofs_page_is_managed(sbi, page)) {
+				if (unlikely(!PageUptodate(page)))
+					err = -EIO;
+				continue;
+			}
+
+			/*
+			 * only if non-head page can be selected
+			 * for inplace decompression
+			 */
+			pagenr = z_erofs_onlinepage_index(page);
+
+			DBG_BUGON(pagenr >= nr_pages);
+			if (unlikely(pages[pagenr])) {
+				DBG_BUGON(1);
+				SetPageError(pages[pagenr]);
+				z_erofs_onlinepage_endio(pages[pagenr]);
+				err = -EFSCORRUPTED;
+			}
+			pages[pagenr] = page;
+
+			overlapped = true;
+		}
+
+		/* PG_error needs checking for inplaced and staging pages */
+		if (unlikely(PageError(page))) {
+			DBG_BUGON(PageUptodate(page));
+			err = -EIO;
+		}
+	}
+
+	if (unlikely(err))
+		goto out;
+
+	llen = pcl->length >> Z_EROFS_PCLUSTER_LENGTH_BIT;
+	if (nr_pages << PAGE_SHIFT >= cl->pageofs + llen) {
+		outputsize = llen;
+		partial = !(pcl->length & Z_EROFS_PCLUSTER_FULL_LENGTH);
+	} else {
+		outputsize = (nr_pages << PAGE_SHIFT) - cl->pageofs;
+		partial = true;
+	}
+
+	err = z_erofs_decompress(&(struct z_erofs_decompress_req) {
+					.sb = sb,
+					.in = compressed_pages,
+					.out = pages,
+					.pageofs_out = cl->pageofs,
+					.inputsize = PAGE_SIZE,
+					.outputsize = outputsize,
+					.alg = pcl->algorithmformat,
+					.inplace_io = overlapped,
+					.partial_decoding = partial
+				 }, pagepool);
+
+out:
+	/* must handle all compressed pages before endding pages */
+	for (i = 0; i < clusterpages; ++i) {
+		page = compressed_pages[i];
+
+		if (erofs_page_is_managed(sbi, page))
+			continue;
+
+		/* recycle all individual staging pages */
+		(void)z_erofs_put_stagingpage(pagepool, page);
+
+		WRITE_ONCE(compressed_pages[i], NULL);
+	}
+
+	for (i = 0; i < nr_pages; ++i) {
+		page = pages[i];
+		if (!page)
+			continue;
+
+		DBG_BUGON(!page->mapping);
+
+		/* recycle all individual staging pages */
+		if (z_erofs_put_stagingpage(pagepool, page))
+			continue;
+
+		if (unlikely(err < 0))
+			SetPageError(page);
+
+		z_erofs_onlinepage_endio(page);
+	}
+
+	if (pages == z_pagemap_global)
+		mutex_unlock(&z_pagemap_global_lock);
+	else if (unlikely(pages != pages_onstack))
+		kvfree(pages);
+
+	cl->nr_pages = 0;
+	cl->vcnt = 0;
+
+	/* all cl locks MUST be taken before the following line */
+	WRITE_ONCE(pcl->next, Z_EROFS_PCLUSTER_NIL);
+
+	/* all cl locks SHOULD be released right now */
+	mutex_unlock(&cl->lock);
+
+	z_erofs_collection_put(cl);
+	return err;
+}
+
+static void z_erofs_vle_unzip_all(struct super_block *sb,
+				  struct z_erofs_unzip_io *io,
+				  struct list_head *pagepool)
+{
+	z_erofs_next_pcluster_t owned = io->head;
+
+	while (owned != Z_EROFS_PCLUSTER_TAIL_CLOSED) {
+		struct z_erofs_pcluster *pcl;
+
+		/* no possible that 'owned' equals Z_EROFS_WORK_TPTR_TAIL */
+		DBG_BUGON(owned == Z_EROFS_PCLUSTER_TAIL);
+
+		/* no possible that 'owned' equals NULL */
+		DBG_BUGON(owned == Z_EROFS_PCLUSTER_NIL);
+
+		pcl = container_of(owned, struct z_erofs_pcluster, next);
+		owned = READ_ONCE(pcl->next);
+
+		z_erofs_decompress_pcluster(sb, pcl, pagepool);
+	}
+}
+
+static void z_erofs_vle_unzip_wq(struct work_struct *work)
+{
+	struct z_erofs_unzip_io_sb *iosb =
+		container_of(work, struct z_erofs_unzip_io_sb, io.u.work);
+	LIST_HEAD(pagepool);
+
+	DBG_BUGON(iosb->io.head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
+	z_erofs_vle_unzip_all(iosb->sb, &iosb->io, &pagepool);
+
+	put_pages_list(&pagepool);
+	kvfree(iosb);
+}
+
+static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl,
+					       unsigned int nr,
+					       struct list_head *pagepool,
+					       struct address_space *mc,
+					       gfp_t gfp)
+{
+	/* determined at compile time to avoid too many #ifdefs */
+	const bool nocache = __builtin_constant_p(mc) ? !mc : false;
+	const pgoff_t index = pcl->obj.index;
+	bool tocache = false;
+
+	struct address_space *mapping;
+	struct page *oldpage, *page;
+
+	compressed_page_t t;
+	int justfound;
+
+repeat:
+	page = READ_ONCE(pcl->compressed_pages[nr]);
+	oldpage = page;
+
+	if (!page)
+		goto out_allocpage;
+
+	/*
+	 * the cached page has not been allocated and
+	 * an placeholder is out there, prepare it now.
+	 */
+	if (!nocache && page == PAGE_UNALLOCATED) {
+		tocache = true;
+		goto out_allocpage;
+	}
+
+	/* process the target tagged pointer */
+	t = tagptr_init(compressed_page_t, page);
+	justfound = tagptr_unfold_tags(t);
+	page = tagptr_unfold_ptr(t);
+
+	mapping = READ_ONCE(page->mapping);
+
+	/*
+	 * if managed cache is disabled, it's no way to
+	 * get such a cached-like page.
+	 */
+	if (nocache) {
+		/* if managed cache is disabled, it is impossible `justfound' */
+		DBG_BUGON(justfound);
+
+		/* and it should be locked, not uptodate, and not truncated */
+		DBG_BUGON(!PageLocked(page));
+		DBG_BUGON(PageUptodate(page));
+		DBG_BUGON(!mapping);
+		goto out;
+	}
+
+	/*
+	 * unmanaged (file) pages are all locked solidly,
+	 * therefore it is impossible for `mapping' to be NULL.
+	 */
+	if (mapping && mapping != mc)
+		/* ought to be unmanaged pages */
+		goto out;
+
+	lock_page(page);
+
+	/* only true if page reclaim goes wrong, should never happen */
+	DBG_BUGON(justfound && PagePrivate(page));
+
+	/* the page is still in manage cache */
+	if (page->mapping == mc) {
+		WRITE_ONCE(pcl->compressed_pages[nr], page);
+
+		ClearPageError(page);
+		if (!PagePrivate(page)) {
+			/*
+			 * impossible to be !PagePrivate(page) for
+			 * the current restriction as well if
+			 * the page is already in compressed_pages[].
+			 */
+			DBG_BUGON(!justfound);
+
+			justfound = 0;
+			set_page_private(page, (unsigned long)pcl);
+			SetPagePrivate(page);
+		}
+
+		/* no need to submit io if it is already up-to-date */
+		if (PageUptodate(page)) {
+			unlock_page(page);
+			page = NULL;
+		}
+		goto out;
+	}
+
+	/*
+	 * the managed page has been truncated, it's unsafe to
+	 * reuse this one, let's allocate a new cache-managed page.
+	 */
+	DBG_BUGON(page->mapping);
+	DBG_BUGON(!justfound);
+
+	tocache = true;
+	unlock_page(page);
+	put_page(page);
+out_allocpage:
+	page = __stagingpage_alloc(pagepool, gfp);
+	if (oldpage != cmpxchg(&pcl->compressed_pages[nr], oldpage, page)) {
+		list_add(&page->lru, pagepool);
+		cpu_relax();
+		goto repeat;
+	}
+	if (nocache || !tocache)
+		goto out;
+	if (add_to_page_cache_lru(page, mc, index + nr, gfp)) {
+		page->mapping = Z_EROFS_MAPPING_STAGING;
+		goto out;
+	}
+
+	set_page_private(page, (unsigned long)pcl);
+	SetPagePrivate(page);
+out:	/* the only exit (for tracing and debugging) */
+	return page;
+}
+
+static struct z_erofs_unzip_io *jobqueue_init(struct super_block *sb,
+					      struct z_erofs_unzip_io *io,
+					      bool foreground)
+{
+	struct z_erofs_unzip_io_sb *iosb;
+
+	if (foreground) {
+		/* waitqueue available for foreground io */
+		DBG_BUGON(!io);
+
+		init_waitqueue_head(&io->u.wait);
+		atomic_set(&io->pending_bios, 0);
+		goto out;
+	}
+
+	iosb = kvzalloc(sizeof(*iosb), GFP_KERNEL | __GFP_NOFAIL);
+	DBG_BUGON(!iosb);
+
+	/* initialize fields in the allocated descriptor */
+	io = &iosb->io;
+	iosb->sb = sb;
+	INIT_WORK(&io->u.work, z_erofs_vle_unzip_wq);
+out:
+	io->head = Z_EROFS_PCLUSTER_TAIL_CLOSED;
+	return io;
+}
+
+/* define decompression jobqueue types */
+enum {
+	JQ_BYPASS,
+	JQ_SUBMIT,
+	NR_JOBQUEUES,
+};
+
+static void *jobqueueset_init(struct super_block *sb,
+			      z_erofs_next_pcluster_t qtail[],
+			      struct z_erofs_unzip_io *q[],
+			      struct z_erofs_unzip_io *fgq,
+			      bool forcefg)
+{
+	/*
+	 * if managed cache is enabled, bypass jobqueue is needed,
+	 * no need to read from device for all pclusters in this queue.
+	 */
+	q[JQ_BYPASS] = jobqueue_init(sb, fgq + JQ_BYPASS, true);
+	qtail[JQ_BYPASS] = &q[JQ_BYPASS]->head;
+
+	q[JQ_SUBMIT] = jobqueue_init(sb, fgq + JQ_SUBMIT, forcefg);
+	qtail[JQ_SUBMIT] = &q[JQ_SUBMIT]->head;
+
+	return tagptr_cast_ptr(tagptr_fold(tagptr1_t, q[JQ_SUBMIT], !forcefg));
+}
+
+static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl,
+				    z_erofs_next_pcluster_t qtail[],
+				    z_erofs_next_pcluster_t owned_head)
+{
+	z_erofs_next_pcluster_t *const submit_qtail = qtail[JQ_SUBMIT];
+	z_erofs_next_pcluster_t *const bypass_qtail = qtail[JQ_BYPASS];
+
+	DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
+	if (owned_head == Z_EROFS_PCLUSTER_TAIL)
+		owned_head = Z_EROFS_PCLUSTER_TAIL_CLOSED;
+
+	WRITE_ONCE(pcl->next, Z_EROFS_PCLUSTER_TAIL_CLOSED);
+
+	WRITE_ONCE(*submit_qtail, owned_head);
+	WRITE_ONCE(*bypass_qtail, &pcl->next);
+
+	qtail[JQ_BYPASS] = &pcl->next;
+}
+
+static bool postsubmit_is_all_bypassed(struct z_erofs_unzip_io *q[],
+				       unsigned int nr_bios,
+				       bool force_fg)
+{
+	/*
+	 * although background is preferred, no one is pending for submission.
+	 * don't issue workqueue for decompression but drop it directly instead.
+	 */
+	if (force_fg || nr_bios)
+		return false;
+
+	kvfree(container_of(q[JQ_SUBMIT], struct z_erofs_unzip_io_sb, io));
+	return true;
+}
+
+static bool z_erofs_vle_submit_all(struct super_block *sb,
+				   z_erofs_next_pcluster_t owned_head,
+				   struct list_head *pagepool,
+				   struct z_erofs_unzip_io *fgq,
+				   bool force_fg)
+{
+	struct erofs_sb_info *const sbi __maybe_unused = EROFS_SB(sb);
+	z_erofs_next_pcluster_t qtail[NR_JOBQUEUES];
+	struct z_erofs_unzip_io *q[NR_JOBQUEUES];
+	struct bio *bio;
+	void *bi_private;
+	/* since bio will be NULL, no need to initialize last_index */
+	pgoff_t uninitialized_var(last_index);
+	bool force_submit = false;
+	unsigned int nr_bios;
+
+	if (unlikely(owned_head == Z_EROFS_PCLUSTER_TAIL))
+		return false;
+
+	force_submit = false;
+	bio = NULL;
+	nr_bios = 0;
+	bi_private = jobqueueset_init(sb, qtail, q, fgq, force_fg);
+
+	/* by default, all need io submission */
+	q[JQ_SUBMIT]->head = owned_head;
+
+	do {
+		struct z_erofs_pcluster *pcl;
+		unsigned int clusterpages;
+		pgoff_t first_index;
+		struct page *page;
+		unsigned int i = 0, bypass = 0;
+		int err;
+
+		/* no possible 'owned_head' equals the following */
+		DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
+		DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_NIL);
+
+		pcl = container_of(owned_head, struct z_erofs_pcluster, next);
+
+		clusterpages = BIT(pcl->clusterbits);
+
+		/* close the main owned chain at first */
+		owned_head = cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL,
+				     Z_EROFS_PCLUSTER_TAIL_CLOSED);
+
+		first_index = pcl->obj.index;
+		force_submit |= (first_index != last_index + 1);
+
+repeat:
+		page = pickup_page_for_submission(pcl, i, pagepool,
+						  MNGD_MAPPING(sbi),
+						  GFP_NOFS);
+		if (!page) {
+			force_submit = true;
+			++bypass;
+			goto skippage;
+		}
+
+		if (bio && force_submit) {
+submit_bio_retry:
+			__submit_bio(bio, REQ_OP_READ, 0);
+			bio = NULL;
+		}
+
+		if (!bio) {
+			bio = erofs_grab_bio(sb, first_index + i,
+					     BIO_MAX_PAGES, bi_private,
+					     z_erofs_vle_read_endio, true);
+			++nr_bios;
+		}
+
+		err = bio_add_page(bio, page, PAGE_SIZE, 0);
+		if (err < PAGE_SIZE)
+			goto submit_bio_retry;
+
+		force_submit = false;
+		last_index = first_index + i;
+skippage:
+		if (++i < clusterpages)
+			goto repeat;
+
+		if (bypass < clusterpages)
+			qtail[JQ_SUBMIT] = &pcl->next;
+		else
+			move_to_bypass_jobqueue(pcl, qtail, owned_head);
+	} while (owned_head != Z_EROFS_PCLUSTER_TAIL);
+
+	if (bio)
+		__submit_bio(bio, REQ_OP_READ, 0);
+
+	if (postsubmit_is_all_bypassed(q, nr_bios, force_fg))
+		return true;
+
+	z_erofs_vle_unzip_kickoff(bi_private, nr_bios);
+	return true;
+}
+
+static void z_erofs_submit_and_unzip(struct super_block *sb,
+				     struct z_erofs_collector *clt,
+				     struct list_head *pagepool,
+				     bool force_fg)
+{
+	struct z_erofs_unzip_io io[NR_JOBQUEUES];
+
+	if (!z_erofs_vle_submit_all(sb, clt->owned_head,
+				    pagepool, io, force_fg))
+		return;
+
+	/* decompress no I/O pclusters immediately */
+	z_erofs_vle_unzip_all(sb, &io[JQ_BYPASS], pagepool);
+
+	if (!force_fg)
+		return;
+
+	/* wait until all bios are completed */
+	wait_event(io[JQ_SUBMIT].u.wait,
+		   !atomic_read(&io[JQ_SUBMIT].pending_bios));
+
+	/* let's synchronous decompression */
+	z_erofs_vle_unzip_all(sb, &io[JQ_SUBMIT], pagepool);
+}
+
+static int z_erofs_vle_normalaccess_readpage(struct file *file,
+					     struct page *page)
+{
+	struct inode *const inode = page->mapping->host;
+	struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
+	int err;
+	LIST_HEAD(pagepool);
+
+	trace_erofs_readpage(page, false);
+
+	f.headoffset = (erofs_off_t)page->index << PAGE_SHIFT;
+
+	err = z_erofs_do_read_page(&f, page, &pagepool);
+	(void)z_erofs_collector_end(&f.clt);
+
+	/* if some compressed cluster ready, need submit them anyway */
+	z_erofs_submit_and_unzip(inode->i_sb, &f.clt, &pagepool, true);
+
+	if (err)
+		errln("%s, failed to read, err [%d]", __func__, err);
+
+	if (f.map.mpage)
+		put_page(f.map.mpage);
+
+	/* clean up the remaining free pages */
+	put_pages_list(&pagepool);
+	return err;
+}
+
+static bool should_decompress_synchronously(struct erofs_sb_info *sbi,
+					    unsigned int nr)
+{
+	return nr <= sbi->max_sync_decompress_pages;
+}
+
+static int z_erofs_vle_normalaccess_readpages(struct file *filp,
+					      struct address_space *mapping,
+					      struct list_head *pages,
+					      unsigned int nr_pages)
+{
+	struct inode *const inode = mapping->host;
+	struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
+
+	bool sync = should_decompress_synchronously(sbi, nr_pages);
+	struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
+	gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
+	struct page *head = NULL;
+	LIST_HEAD(pagepool);
+
+	trace_erofs_readpages(mapping->host, lru_to_page(pages),
+			      nr_pages, false);
+
+	f.headoffset = (erofs_off_t)lru_to_page(pages)->index << PAGE_SHIFT;
+
+	for (; nr_pages; --nr_pages) {
+		struct page *page = lru_to_page(pages);
+
+		prefetchw(&page->flags);
+		list_del(&page->lru);
+
+		/*
+		 * A pure asynchronous readahead is indicated if
+		 * a PG_readahead marked page is hitted at first.
+		 * Let's also do asynchronous decompression for this case.
+		 */
+		sync &= !(PageReadahead(page) && !head);
+
+		if (add_to_page_cache_lru(page, mapping, page->index, gfp)) {
+			list_add(&page->lru, &pagepool);
+			continue;
+		}
+
+		set_page_private(page, (unsigned long)head);
+		head = page;
+	}
+
+	while (head) {
+		struct page *page = head;
+		int err;
+
+		/* traversal in reverse order */
+		head = (void *)page_private(page);
+
+		err = z_erofs_do_read_page(&f, page, &pagepool);
+		if (err) {
+			struct erofs_vnode *vi = EROFS_V(inode);
+
+			errln("%s, readahead error at page %lu of nid %llu",
+			      __func__, page->index, vi->nid);
+		}
+		put_page(page);
+	}
+
+	(void)z_erofs_collector_end(&f.clt);
+
+	z_erofs_submit_and_unzip(inode->i_sb, &f.clt, &pagepool, sync);
+
+	if (f.map.mpage)
+		put_page(f.map.mpage);
+
+	/* clean up the remaining free pages */
+	put_pages_list(&pagepool);
+	return 0;
+}
+
+const struct address_space_operations z_erofs_vle_normalaccess_aops = {
+	.readpage = z_erofs_vle_normalaccess_readpage,
+	.readpages = z_erofs_vle_normalaccess_readpages,
+};
+
diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h
new file mode 100644
index 000000000000..4fc547bc01f9
--- /dev/null
+++ b/fs/erofs/zdata.h
@@ -0,0 +1,193 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2018 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#ifndef __EROFS_FS_ZDATA_H
+#define __EROFS_FS_ZDATA_H
+
+#include "internal.h"
+#include "zpvec.h"
+
+#define Z_EROFS_NR_INLINE_PAGEVECS      3
+
+/*
+ * Structure fields follow one of the following exclusion rules.
+ *
+ * I: Modifiable by initialization/destruction paths and read-only
+ *    for everyone else;
+ *
+ * L: Field should be protected by pageset lock;
+ *
+ * A: Field should be accessed / updated in atomic for parallelized code.
+ */
+struct z_erofs_collection {
+	struct mutex lock;
+
+	/* I: page offset of start position of decompression */
+	unsigned short pageofs;
+
+	/* L: maximum relative page index in pagevec[] */
+	unsigned short nr_pages;
+
+	/* L: total number of pages in pagevec[] */
+	unsigned int vcnt;
+
+	union {
+		/* L: inline a certain number of pagevecs for bootstrap */
+		erofs_vtptr_t pagevec[Z_EROFS_NR_INLINE_PAGEVECS];
+
+		/* I: can be used to free the pcluster by RCU. */
+		struct rcu_head rcu;
+	};
+};
+
+#define Z_EROFS_PCLUSTER_FULL_LENGTH    0x00000001
+#define Z_EROFS_PCLUSTER_LENGTH_BIT     1
+
+/*
+ * let's leave a type here in case of introducing
+ * another tagged pointer later.
+ */
+typedef void *z_erofs_next_pcluster_t;
+
+struct z_erofs_pcluster {
+	struct erofs_workgroup obj;
+	struct z_erofs_collection primary_collection;
+
+	/* A: point to next chained pcluster or TAILs */
+	z_erofs_next_pcluster_t next;
+
+	/* A: compressed pages (including multi-usage pages) */
+	struct page *compressed_pages[Z_EROFS_CLUSTER_MAX_PAGES];
+
+	/* A: lower limit of decompressed length and if full length or not */
+	unsigned int length;
+
+	/* I: compression algorithm format */
+	unsigned char algorithmformat;
+	/* I: bit shift of physical cluster size */
+	unsigned char clusterbits;
+};
+
+#define z_erofs_primarycollection(pcluster) (&(pcluster)->primary_collection)
+
+/* let's avoid the valid 32-bit kernel addresses */
+
+/* the chained workgroup has't submitted io (still open) */
+#define Z_EROFS_PCLUSTER_TAIL           ((void *)0x5F0ECAFE)
+/* the chained workgroup has already submitted io */
+#define Z_EROFS_PCLUSTER_TAIL_CLOSED    ((void *)0x5F0EDEAD)
+
+#define Z_EROFS_PCLUSTER_NIL            (NULL)
+
+#define Z_EROFS_WORKGROUP_SIZE  sizeof(struct z_erofs_pcluster)
+
+struct z_erofs_unzip_io {
+	atomic_t pending_bios;
+	z_erofs_next_pcluster_t head;
+
+	union {
+		wait_queue_head_t wait;
+		struct work_struct work;
+	} u;
+};
+
+struct z_erofs_unzip_io_sb {
+	struct z_erofs_unzip_io io;
+	struct super_block *sb;
+};
+
+#define MNGD_MAPPING(sbi)	((sbi)->managed_cache->i_mapping)
+static inline bool erofs_page_is_managed(const struct erofs_sb_info *sbi,
+					 struct page *page)
+{
+	return page->mapping == MNGD_MAPPING(sbi);
+}
+
+#define Z_EROFS_ONLINEPAGE_COUNT_BITS   2
+#define Z_EROFS_ONLINEPAGE_COUNT_MASK   ((1 << Z_EROFS_ONLINEPAGE_COUNT_BITS) - 1)
+#define Z_EROFS_ONLINEPAGE_INDEX_SHIFT  (Z_EROFS_ONLINEPAGE_COUNT_BITS)
+
+/*
+ * waiters (aka. ongoing_packs): # to unlock the page
+ * sub-index: 0 - for partial page, >= 1 full page sub-index
+ */
+typedef atomic_t z_erofs_onlinepage_t;
+
+/* type punning */
+union z_erofs_onlinepage_converter {
+	z_erofs_onlinepage_t *o;
+	unsigned long *v;
+};
+
+static inline unsigned int z_erofs_onlinepage_index(struct page *page)
+{
+	union z_erofs_onlinepage_converter u;
+
+	DBG_BUGON(!PagePrivate(page));
+	u.v = &page_private(page);
+
+	return atomic_read(u.o) >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT;
+}
+
+static inline void z_erofs_onlinepage_init(struct page *page)
+{
+	union {
+		z_erofs_onlinepage_t o;
+		unsigned long v;
+	/* keep from being unlocked in advance */
+	} u = { .o = ATOMIC_INIT(1) };
+
+	set_page_private(page, u.v);
+	smp_wmb();
+	SetPagePrivate(page);
+}
+
+static inline void z_erofs_onlinepage_fixup(struct page *page,
+	uintptr_t index, bool down)
+{
+	unsigned long *p, o, v, id;
+repeat:
+	p = &page_private(page);
+	o = READ_ONCE(*p);
+
+	id = o >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT;
+	if (id) {
+		if (!index)
+			return;
+
+		DBG_BUGON(id != index);
+	}
+
+	v = (index << Z_EROFS_ONLINEPAGE_INDEX_SHIFT) |
+		((o & Z_EROFS_ONLINEPAGE_COUNT_MASK) + (unsigned int)down);
+	if (cmpxchg(p, o, v) != o)
+		goto repeat;
+}
+
+static inline void z_erofs_onlinepage_endio(struct page *page)
+{
+	union z_erofs_onlinepage_converter u;
+	unsigned int v;
+
+	DBG_BUGON(!PagePrivate(page));
+	u.v = &page_private(page);
+
+	v = atomic_dec_return(u.o);
+	if (!(v & Z_EROFS_ONLINEPAGE_COUNT_MASK)) {
+		ClearPagePrivate(page);
+		if (!PageError(page))
+			SetPageUptodate(page);
+		unlock_page(page);
+	}
+	debugln("%s, page %p value %x", __func__, page, atomic_read(u.o));
+}
+
+#define Z_EROFS_VMAP_ONSTACK_PAGES	\
+	min_t(unsigned int, THREAD_SIZE / 8 / sizeof(struct page *), 96U)
+#define Z_EROFS_VMAP_GLOBAL_PAGES	2048
+
+#endif
+
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
new file mode 100644
index 000000000000..4dc9cec01297
--- /dev/null
+++ b/fs/erofs/zmap.c
@@ -0,0 +1,466 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2018-2019 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#include "internal.h"
+#include <asm/unaligned.h>
+#include <trace/events/erofs.h>
+
+int z_erofs_fill_inode(struct inode *inode)
+{
+	struct erofs_vnode *const vi = EROFS_V(inode);
+
+	if (vi->datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY) {
+		vi->z_advise = 0;
+		vi->z_algorithmtype[0] = 0;
+		vi->z_algorithmtype[1] = 0;
+		vi->z_logical_clusterbits = LOG_BLOCK_SIZE;
+		vi->z_physical_clusterbits[0] = vi->z_logical_clusterbits;
+		vi->z_physical_clusterbits[1] = vi->z_logical_clusterbits;
+		set_bit(EROFS_V_Z_INITED_BIT, &vi->flags);
+	}
+
+	inode->i_mapping->a_ops = &z_erofs_vle_normalaccess_aops;
+	return 0;
+}
+
+static int fill_inode_lazy(struct inode *inode)
+{
+	struct erofs_vnode *const vi = EROFS_V(inode);
+	struct super_block *const sb = inode->i_sb;
+	int err;
+	erofs_off_t pos;
+	struct page *page;
+	void *kaddr;
+	struct z_erofs_map_header *h;
+
+	if (test_bit(EROFS_V_Z_INITED_BIT, &vi->flags))
+		return 0;
+
+	if (wait_on_bit_lock(&vi->flags, EROFS_V_BL_Z_BIT, TASK_KILLABLE))
+		return -ERESTARTSYS;
+
+	err = 0;
+	if (test_bit(EROFS_V_Z_INITED_BIT, &vi->flags))
+		goto out_unlock;
+
+	DBG_BUGON(vi->datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY);
+
+	pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize +
+		    vi->xattr_isize, 8);
+	page = erofs_get_meta_page(sb, erofs_blknr(pos), false);
+	if (IS_ERR(page)) {
+		err = PTR_ERR(page);
+		goto out_unlock;
+	}
+
+	kaddr = kmap_atomic(page);
+
+	h = kaddr + erofs_blkoff(pos);
+	vi->z_advise = le16_to_cpu(h->h_advise);
+	vi->z_algorithmtype[0] = h->h_algorithmtype & 15;
+	vi->z_algorithmtype[1] = h->h_algorithmtype >> 4;
+
+	if (vi->z_algorithmtype[0] >= Z_EROFS_COMPRESSION_MAX) {
+		errln("unknown compression format %u for nid %llu, please upgrade kernel",
+		      vi->z_algorithmtype[0], vi->nid);
+		err = -EOPNOTSUPP;
+		goto unmap_done;
+	}
+
+	vi->z_logical_clusterbits = LOG_BLOCK_SIZE + (h->h_clusterbits & 7);
+	vi->z_physical_clusterbits[0] = vi->z_logical_clusterbits +
+					((h->h_clusterbits >> 3) & 3);
+
+	if (vi->z_physical_clusterbits[0] != LOG_BLOCK_SIZE) {
+		errln("unsupported physical clusterbits %u for nid %llu, please upgrade kernel",
+		      vi->z_physical_clusterbits[0], vi->nid);
+		err = -EOPNOTSUPP;
+		goto unmap_done;
+	}
+
+	vi->z_physical_clusterbits[1] = vi->z_logical_clusterbits +
+					((h->h_clusterbits >> 5) & 7);
+	set_bit(EROFS_V_Z_INITED_BIT, &vi->flags);
+unmap_done:
+	kunmap_atomic(kaddr);
+	unlock_page(page);
+	put_page(page);
+out_unlock:
+	clear_and_wake_up_bit(EROFS_V_BL_Z_BIT, &vi->flags);
+	return err;
+}
+
+struct z_erofs_maprecorder {
+	struct inode *inode;
+	struct erofs_map_blocks *map;
+	void *kaddr;
+
+	unsigned long lcn;
+	/* compression extent information gathered */
+	u8  type;
+	u16 clusterofs;
+	u16 delta[2];
+	erofs_blk_t pblk;
+};
+
+static int z_erofs_reload_indexes(struct z_erofs_maprecorder *m,
+				  erofs_blk_t eblk)
+{
+	struct super_block *const sb = m->inode->i_sb;
+	struct erofs_map_blocks *const map = m->map;
+	struct page *mpage = map->mpage;
+
+	if (mpage) {
+		if (mpage->index == eblk) {
+			if (!m->kaddr)
+				m->kaddr = kmap_atomic(mpage);
+			return 0;
+		}
+
+		if (m->kaddr) {
+			kunmap_atomic(m->kaddr);
+			m->kaddr = NULL;
+		}
+		put_page(mpage);
+	}
+
+	mpage = erofs_get_meta_page(sb, eblk, false);
+	if (IS_ERR(mpage)) {
+		map->mpage = NULL;
+		return PTR_ERR(mpage);
+	}
+	m->kaddr = kmap_atomic(mpage);
+	unlock_page(mpage);
+	map->mpage = mpage;
+	return 0;
+}
+
+static int vle_legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
+					     unsigned long lcn)
+{
+	struct inode *const inode = m->inode;
+	struct erofs_vnode *const vi = EROFS_V(inode);
+	const erofs_off_t ibase = iloc(EROFS_I_SB(inode), vi->nid);
+	const erofs_off_t pos =
+		Z_EROFS_VLE_LEGACY_INDEX_ALIGN(ibase + vi->inode_isize +
+					       vi->xattr_isize) +
+		lcn * sizeof(struct z_erofs_vle_decompressed_index);
+	struct z_erofs_vle_decompressed_index *di;
+	unsigned int advise, type;
+	int err;
+
+	err = z_erofs_reload_indexes(m, erofs_blknr(pos));
+	if (err)
+		return err;
+
+	m->lcn = lcn;
+	di = m->kaddr + erofs_blkoff(pos);
+
+	advise = le16_to_cpu(di->di_advise);
+	type = (advise >> Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT) &
+		((1 << Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS) - 1);
+	switch (type) {
+	case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
+		m->clusterofs = 1 << vi->z_logical_clusterbits;
+		m->delta[0] = le16_to_cpu(di->di_u.delta[0]);
+		m->delta[1] = le16_to_cpu(di->di_u.delta[1]);
+		break;
+	case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
+	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
+		m->clusterofs = le16_to_cpu(di->di_clusterofs);
+		m->pblk = le32_to_cpu(di->di_u.blkaddr);
+		break;
+	default:
+		DBG_BUGON(1);
+		return -EOPNOTSUPP;
+	}
+	m->type = type;
+	return 0;
+}
+
+static unsigned int decode_compactedbits(unsigned int lobits,
+					 unsigned int lomask,
+					 u8 *in, unsigned int pos, u8 *type)
+{
+	const unsigned int v = get_unaligned_le32(in + pos / 8) >> (pos & 7);
+	const unsigned int lo = v & lomask;
+
+	*type = (v >> lobits) & 3;
+	return lo;
+}
+
+static int unpack_compacted_index(struct z_erofs_maprecorder *m,
+				  unsigned int amortizedshift,
+				  unsigned int eofs)
+{
+	struct erofs_vnode *const vi = EROFS_V(m->inode);
+	const unsigned int lclusterbits = vi->z_logical_clusterbits;
+	const unsigned int lomask = (1 << lclusterbits) - 1;
+	unsigned int vcnt, base, lo, encodebits, nblk;
+	int i;
+	u8 *in, type;
+
+	if (1 << amortizedshift == 4)
+		vcnt = 2;
+	else if (1 << amortizedshift == 2 && lclusterbits == 12)
+		vcnt = 16;
+	else
+		return -EOPNOTSUPP;
+
+	encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt;
+	base = round_down(eofs, vcnt << amortizedshift);
+	in = m->kaddr + base;
+
+	i = (eofs - base) >> amortizedshift;
+
+	lo = decode_compactedbits(lclusterbits, lomask,
+				  in, encodebits * i, &type);
+	m->type = type;
+	if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
+		m->clusterofs = 1 << lclusterbits;
+		if (i + 1 != vcnt) {
+			m->delta[0] = lo;
+			return 0;
+		}
+		/*
+		 * since the last lcluster in the pack is special,
+		 * of which lo saves delta[1] rather than delta[0].
+		 * Hence, get delta[0] by the previous lcluster indirectly.
+		 */
+		lo = decode_compactedbits(lclusterbits, lomask,
+					  in, encodebits * (i - 1), &type);
+		if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
+			lo = 0;
+		m->delta[0] = lo + 1;
+		return 0;
+	}
+	m->clusterofs = lo;
+	m->delta[0] = 0;
+	/* figout out blkaddr (pblk) for HEAD lclusters */
+	nblk = 1;
+	while (i > 0) {
+		--i;
+		lo = decode_compactedbits(lclusterbits, lomask,
+					  in, encodebits * i, &type);
+		if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
+			i -= lo;
+
+		if (i >= 0)
+			++nblk;
+	}
+	in += (vcnt << amortizedshift) - sizeof(__le32);
+	m->pblk = le32_to_cpu(*(__le32 *)in) + nblk;
+	return 0;
+}
+
+static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m,
+					    unsigned long lcn)
+{
+	struct inode *const inode = m->inode;
+	struct erofs_vnode *const vi = EROFS_V(inode);
+	const unsigned int lclusterbits = vi->z_logical_clusterbits;
+	const erofs_off_t ebase = ALIGN(iloc(EROFS_I_SB(inode), vi->nid) +
+					vi->inode_isize + vi->xattr_isize, 8) +
+		sizeof(struct z_erofs_map_header);
+	const unsigned int totalidx = DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ);
+	unsigned int compacted_4b_initial, compacted_2b;
+	unsigned int amortizedshift;
+	erofs_off_t pos;
+	int err;
+
+	if (lclusterbits != 12)
+		return -EOPNOTSUPP;
+
+	if (lcn >= totalidx)
+		return -EINVAL;
+
+	m->lcn = lcn;
+	/* used to align to 32-byte (compacted_2b) alignment */
+	compacted_4b_initial = (32 - ebase % 32) / 4;
+	if (compacted_4b_initial == 32 / 4)
+		compacted_4b_initial = 0;
+
+	if (vi->z_advise & Z_EROFS_ADVISE_COMPACTED_2B)
+		compacted_2b = rounddown(totalidx - compacted_4b_initial, 16);
+	else
+		compacted_2b = 0;
+
+	pos = ebase;
+	if (lcn < compacted_4b_initial) {
+		amortizedshift = 2;
+		goto out;
+	}
+	pos += compacted_4b_initial * 4;
+	lcn -= compacted_4b_initial;
+
+	if (lcn < compacted_2b) {
+		amortizedshift = 1;
+		goto out;
+	}
+	pos += compacted_2b * 2;
+	lcn -= compacted_2b;
+	amortizedshift = 2;
+out:
+	pos += lcn * (1 << amortizedshift);
+	err = z_erofs_reload_indexes(m, erofs_blknr(pos));
+	if (err)
+		return err;
+	return unpack_compacted_index(m, amortizedshift, erofs_blkoff(pos));
+}
+
+static int vle_load_cluster_from_disk(struct z_erofs_maprecorder *m,
+				      unsigned int lcn)
+{
+	const unsigned int datamode = EROFS_V(m->inode)->datamode;
+
+	if (datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY)
+		return vle_legacy_load_cluster_from_disk(m, lcn);
+
+	if (datamode == EROFS_INODE_FLAT_COMPRESSION)
+		return compacted_load_cluster_from_disk(m, lcn);
+
+	return -EINVAL;
+}
+
+static int vle_extent_lookback(struct z_erofs_maprecorder *m,
+			       unsigned int lookback_distance)
+{
+	struct erofs_vnode *const vi = EROFS_V(m->inode);
+	struct erofs_map_blocks *const map = m->map;
+	const unsigned int lclusterbits = vi->z_logical_clusterbits;
+	unsigned long lcn = m->lcn;
+	int err;
+
+	if (lcn < lookback_distance) {
+		errln("bogus lookback distance @ nid %llu", vi->nid);
+		DBG_BUGON(1);
+		return -EFSCORRUPTED;
+	}
+
+	/* load extent head logical cluster if needed */
+	lcn -= lookback_distance;
+	err = vle_load_cluster_from_disk(m, lcn);
+	if (err)
+		return err;
+
+	switch (m->type) {
+	case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
+		if (unlikely(!m->delta[0])) {
+			errln("invalid lookback distance 0 at nid %llu",
+			      vi->nid);
+			DBG_BUGON(1);
+			return -EFSCORRUPTED;
+		}
+		return vle_extent_lookback(m, m->delta[0]);
+	case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
+		map->m_flags &= ~EROFS_MAP_ZIPPED;
+		/* fallthrough */
+	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
+		map->m_la = (lcn << lclusterbits) | m->clusterofs;
+		break;
+	default:
+		errln("unknown type %u at lcn %lu of nid %llu",
+		      m->type, lcn, vi->nid);
+		DBG_BUGON(1);
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+int z_erofs_map_blocks_iter(struct inode *inode,
+			    struct erofs_map_blocks *map,
+			    int flags)
+{
+	struct erofs_vnode *const vi = EROFS_V(inode);
+	struct z_erofs_maprecorder m = {
+		.inode = inode,
+		.map = map,
+	};
+	int err = 0;
+	unsigned int lclusterbits, endoff;
+	unsigned long long ofs, end;
+
+	trace_z_erofs_map_blocks_iter_enter(inode, map, flags);
+
+	/* when trying to read beyond EOF, leave it unmapped */
+	if (unlikely(map->m_la >= inode->i_size)) {
+		map->m_llen = map->m_la + 1 - inode->i_size;
+		map->m_la = inode->i_size;
+		map->m_flags = 0;
+		goto out;
+	}
+
+	err = fill_inode_lazy(inode);
+	if (err)
+		goto out;
+
+	lclusterbits = vi->z_logical_clusterbits;
+	ofs = map->m_la;
+	m.lcn = ofs >> lclusterbits;
+	endoff = ofs & ((1 << lclusterbits) - 1);
+
+	err = vle_load_cluster_from_disk(&m, m.lcn);
+	if (err)
+		goto unmap_out;
+
+	map->m_flags = EROFS_MAP_ZIPPED;	/* by default, compressed */
+	end = (m.lcn + 1ULL) << lclusterbits;
+
+	switch (m.type) {
+	case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
+		if (endoff >= m.clusterofs)
+			map->m_flags &= ~EROFS_MAP_ZIPPED;
+		/* fallthrough */
+	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
+		if (endoff >= m.clusterofs) {
+			map->m_la = (m.lcn << lclusterbits) | m.clusterofs;
+			break;
+		}
+		/* m.lcn should be >= 1 if endoff < m.clusterofs */
+		if (unlikely(!m.lcn)) {
+			errln("invalid logical cluster 0 at nid %llu",
+			      vi->nid);
+			err = -EFSCORRUPTED;
+			goto unmap_out;
+		}
+		end = (m.lcn << lclusterbits) | m.clusterofs;
+		map->m_flags |= EROFS_MAP_FULL_MAPPED;
+		m.delta[0] = 1;
+		/* fallthrough */
+	case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
+		/* get the correspoinding first chunk */
+		err = vle_extent_lookback(&m, m.delta[0]);
+		if (unlikely(err))
+			goto unmap_out;
+		break;
+	default:
+		errln("unknown type %u at offset %llu of nid %llu",
+		      m.type, ofs, vi->nid);
+		err = -EOPNOTSUPP;
+		goto unmap_out;
+	}
+
+	map->m_llen = end - map->m_la;
+	map->m_plen = 1 << lclusterbits;
+	map->m_pa = blknr_to_addr(m.pblk);
+	map->m_flags |= EROFS_MAP_MAPPED;
+
+unmap_out:
+	if (m.kaddr)
+		kunmap_atomic(m.kaddr);
+
+out:
+	debugln("%s, m_la %llu m_pa %llu m_llen %llu m_plen %llu m_flags 0%o",
+		__func__, map->m_la, map->m_pa,
+		map->m_llen, map->m_plen, map->m_flags);
+
+	trace_z_erofs_map_blocks_iter_exit(inode, map, flags, err);
+
+	/* aggressively BUG_ON iff CONFIG_EROFS_FS_DEBUG is on */
+	DBG_BUGON(err < 0 && err != -ENOMEM);
+	return err;
+}
+
diff --git a/fs/erofs/zpvec.h b/fs/erofs/zpvec.h
new file mode 100644
index 000000000000..bd3cee16491c
--- /dev/null
+++ b/fs/erofs/zpvec.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2018 HUAWEI, Inc.
+ *             http://www.huawei.com/
+ * Created by Gao Xiang <gaoxiang25@huawei.com>
+ */
+#ifndef __EROFS_FS_ZPVEC_H
+#define __EROFS_FS_ZPVEC_H
+
+#include "tagptr.h"
+
+/* page type in pagevec for decompress subsystem */
+enum z_erofs_page_type {
+	/* including Z_EROFS_VLE_PAGE_TAIL_EXCLUSIVE */
+	Z_EROFS_PAGE_TYPE_EXCLUSIVE,
+
+	Z_EROFS_VLE_PAGE_TYPE_TAIL_SHARED,
+
+	Z_EROFS_VLE_PAGE_TYPE_HEAD,
+	Z_EROFS_VLE_PAGE_TYPE_MAX
+};
+
+extern void __compiletime_error("Z_EROFS_PAGE_TYPE_EXCLUSIVE != 0")
+	__bad_page_type_exclusive(void);
+
+/* pagevec tagged pointer */
+typedef tagptr2_t	erofs_vtptr_t;
+
+/* pagevec collector */
+struct z_erofs_pagevec_ctor {
+	struct page *curr, *next;
+	erofs_vtptr_t *pages;
+
+	unsigned int nr, index;
+};
+
+static inline void z_erofs_pagevec_ctor_exit(struct z_erofs_pagevec_ctor *ctor,
+					     bool atomic)
+{
+	if (!ctor->curr)
+		return;
+
+	if (atomic)
+		kunmap_atomic(ctor->pages);
+	else
+		kunmap(ctor->curr);
+}
+
+static inline struct page *
+z_erofs_pagevec_ctor_next_page(struct z_erofs_pagevec_ctor *ctor,
+			       unsigned int nr)
+{
+	unsigned int index;
+
+	/* keep away from occupied pages */
+	if (ctor->next)
+		return ctor->next;
+
+	for (index = 0; index < nr; ++index) {
+		const erofs_vtptr_t t = ctor->pages[index];
+		const unsigned int tags = tagptr_unfold_tags(t);
+
+		if (tags == Z_EROFS_PAGE_TYPE_EXCLUSIVE)
+			return tagptr_unfold_ptr(t);
+	}
+	DBG_BUGON(nr >= ctor->nr);
+	return NULL;
+}
+
+static inline void
+z_erofs_pagevec_ctor_pagedown(struct z_erofs_pagevec_ctor *ctor,
+			      bool atomic)
+{
+	struct page *next = z_erofs_pagevec_ctor_next_page(ctor, ctor->nr);
+
+	z_erofs_pagevec_ctor_exit(ctor, atomic);
+
+	ctor->curr = next;
+	ctor->next = NULL;
+	ctor->pages = atomic ?
+		kmap_atomic(ctor->curr) : kmap(ctor->curr);
+
+	ctor->nr = PAGE_SIZE / sizeof(struct page *);
+	ctor->index = 0;
+}
+
+static inline void z_erofs_pagevec_ctor_init(struct z_erofs_pagevec_ctor *ctor,
+					     unsigned int nr,
+					     erofs_vtptr_t *pages,
+					     unsigned int i)
+{
+	ctor->nr = nr;
+	ctor->curr = ctor->next = NULL;
+	ctor->pages = pages;
+
+	if (i >= nr) {
+		i -= nr;
+		z_erofs_pagevec_ctor_pagedown(ctor, false);
+		while (i > ctor->nr) {
+			i -= ctor->nr;
+			z_erofs_pagevec_ctor_pagedown(ctor, false);
+		}
+	}
+	ctor->next = z_erofs_pagevec_ctor_next_page(ctor, i);
+	ctor->index = i;
+}
+
+static inline bool z_erofs_pagevec_enqueue(struct z_erofs_pagevec_ctor *ctor,
+					   struct page *page,
+					   enum z_erofs_page_type type,
+					   bool *occupied)
+{
+	*occupied = false;
+	if (unlikely(!ctor->next && type))
+		if (ctor->index + 1 == ctor->nr)
+			return false;
+
+	if (unlikely(ctor->index >= ctor->nr))
+		z_erofs_pagevec_ctor_pagedown(ctor, false);
+
+	/* exclusive page type must be 0 */
+	if (Z_EROFS_PAGE_TYPE_EXCLUSIVE != (uintptr_t)NULL)
+		__bad_page_type_exclusive();
+
+	/* should remind that collector->next never equal to 1, 2 */
+	if (type == (uintptr_t)ctor->next) {
+		ctor->next = page;
+		*occupied = true;
+	}
+	ctor->pages[ctor->index++] = tagptr_fold(erofs_vtptr_t, page, type);
+	return true;
+}
+
+static inline struct page *
+z_erofs_pagevec_dequeue(struct z_erofs_pagevec_ctor *ctor,
+			enum z_erofs_page_type *type)
+{
+	erofs_vtptr_t t;
+
+	if (unlikely(ctor->index >= ctor->nr)) {
+		DBG_BUGON(!ctor->next);
+		z_erofs_pagevec_ctor_pagedown(ctor, true);
+	}
+
+	t = ctor->pages[ctor->index];
+
+	*type = tagptr_unfold_tags(t);
+
+	/* should remind that collector->next never equal to 1, 2 */
+	if (*type == (uintptr_t)ctor->next)
+		ctor->next = tagptr_unfold_ptr(t);
+
+	ctor->pages[ctor->index++] = tagptr_fold(erofs_vtptr_t, NULL, 0);
+	return tagptr_unfold_ptr(t);
+}
+#endif
+