1 files changed, 531 insertions, 382 deletions

diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 915eefe0d7e2..937a215f626c 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -4,15 +4,13 @@
  *             https://www.huawei.com/
  * Copyright (C) 2021, Alibaba Cloud
  */
-#include <linux/module.h>
-#include <linux/buffer_head.h>
 #include <linux/statfs.h>
-#include <linux/parser.h>
 #include <linux/seq_file.h>
 #include <linux/crc32c.h>
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
-#include <linux/dax.h>
+#include <linux/exportfs.h>
+#include <linux/backing-dev.h>
 #include "xattr.h"
 
 #define CREATE_TRACE_POINTS
@@ -20,58 +18,42 @@
 
 static struct kmem_cache *erofs_inode_cachep __read_mostly;
 
-void _erofs_err(struct super_block *sb, const char *function,
-		const char *fmt, ...)
+void _erofs_printk(struct super_block *sb, const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
+	int level;
 
 	va_start(args, fmt);
 
-	vaf.fmt = fmt;
+	level = printk_get_level(fmt);
+	vaf.fmt = printk_skip_level(fmt);
 	vaf.va = &args;
-
-	pr_err("(device %s): %s: %pV", sb->s_id, function, &vaf);
-	va_end(args);
-}
-
-void _erofs_info(struct super_block *sb, const char *function,
-		 const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-
-	va_start(args, fmt);
-
-	vaf.fmt = fmt;
-	vaf.va = &args;
-
-	pr_info("(device %s): %pV", sb->s_id, &vaf);
+	if (sb)
+		printk("%c%cerofs (device %s): %pV",
+				KERN_SOH_ASCII, level, sb->s_id, &vaf);
+	else
+		printk("%c%cerofs: %pV", KERN_SOH_ASCII, level, &vaf);
 	va_end(args);
 }
 
 static int erofs_superblock_csum_verify(struct super_block *sb, void *sbdata)
 {
-	struct erofs_super_block *dsb;
-	u32 expected_crc, crc;
+	struct erofs_super_block *dsb = sbdata + EROFS_SUPER_OFFSET;
+	u32 len = 1 << EROFS_SB(sb)->blkszbits, crc;
 
-	dsb = kmemdup(sbdata + EROFS_SUPER_OFFSET,
-		      EROFS_BLKSIZ - EROFS_SUPER_OFFSET, GFP_KERNEL);
-	if (!dsb)
-		return -ENOMEM;
-
-	expected_crc = le32_to_cpu(dsb->checksum);
-	dsb->checksum = 0;
-	/* to allow for x86 boot sectors and other oddities. */
-	crc = crc32c(~0, dsb, EROFS_BLKSIZ - EROFS_SUPER_OFFSET);
-	kfree(dsb);
+	if (len > EROFS_SUPER_OFFSET)
+		len -= EROFS_SUPER_OFFSET;
+	len -= offsetof(struct erofs_super_block, checksum) +
+			sizeof(dsb->checksum);
 
-	if (crc != expected_crc) {
-		erofs_err(sb, "invalid checksum 0x%08x, 0x%08x expected",
-			  crc, expected_crc);
-		return -EBADMSG;
-	}
-	return 0;
+	/* skip .magic(pre-verified) and .checksum(0) fields */
+	crc = crc32c(0x5045B54A, (&dsb->checksum) + 1, len);
+	if (crc == le32_to_cpu(dsb->checksum))
+		return 0;
+	erofs_err(sb, "invalid checksum 0x%08x, 0x%08x expected",
+		  crc, le32_to_cpu(dsb->checksum));
+	return -EBADMSG;
 }
 
 static void erofs_inode_init_once(void *ptr)
@@ -84,7 +66,7 @@ static void erofs_inode_init_once(void *ptr)
 static struct inode *erofs_alloc_inode(struct super_block *sb)
 {
 	struct erofs_inode *vi =
-		kmem_cache_alloc(erofs_inode_cachep, GFP_KERNEL);
+		alloc_inode_sb(sb, erofs_inode_cachep, GFP_KERNEL);
 
 	if (!vi)
 		return NULL;
@@ -98,45 +80,25 @@ static void erofs_free_inode(struct inode *inode)
 {
 	struct erofs_inode *vi = EROFS_I(inode);
 
-	/* be careful of RCU symlink path */
 	if (inode->i_op == &erofs_fast_symlink_iops)
 		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 *dsb)
-{
-	const unsigned int feature = le32_to_cpu(dsb->feature_incompat);
-
-	EROFS_SB(sb)->feature_incompat = feature;
-
-	/* check if current kernel meets all mandatory requirements */
-	if (feature & (~EROFS_ALL_FEATURE_INCOMPAT)) {
-		erofs_err(sb,
-			  "unidentified incompatible feature %x, please upgrade kernel version",
-			   feature & ~EROFS_ALL_FEATURE_INCOMPAT);
-		return false;
-	}
-	return true;
-}
-
-#ifdef CONFIG_EROFS_FS_ZIP
 /* read variable-sized metadata, offset will be aligned by 4-byte */
-static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
-				 erofs_off_t *offset, int *lengthp)
+void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
+			  erofs_off_t *offset, int *lengthp)
 {
 	u8 *buffer, *ptr;
 	int len, i, cnt;
 
 	*offset = round_up(*offset, 4);
-	ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*offset), EROFS_KMAP);
+	ptr = erofs_bread(buf, *offset, true);
 	if (IS_ERR(ptr))
 		return ptr;
 
-	len = le16_to_cpu(*(__le16 *)&ptr[erofs_blkoff(*offset)]);
+	len = le16_to_cpu(*(__le16 *)ptr);
 	if (!len)
 		len = U16_MAX + 1;
 	buffer = kmalloc(len, GFP_KERNEL);
@@ -146,80 +108,92 @@ static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
 	*lengthp = len;
 
 	for (i = 0; i < len; i += cnt) {
-		cnt = min(EROFS_BLKSIZ - (int)erofs_blkoff(*offset), len - i);
-		ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*offset),
-					 EROFS_KMAP);
+		cnt = min_t(int, sb->s_blocksize - erofs_blkoff(sb, *offset),
+			    len - i);
+		ptr = erofs_bread(buf, *offset, true);
 		if (IS_ERR(ptr)) {
 			kfree(buffer);
 			return ptr;
 		}
-		memcpy(buffer + i, ptr + erofs_blkoff(*offset), cnt);
+		memcpy(buffer + i, ptr, cnt);
 		*offset += cnt;
 	}
 	return buffer;
 }
 
-static int erofs_load_compr_cfgs(struct super_block *sb,
-				 struct erofs_super_block *dsb)
+#ifndef CONFIG_EROFS_FS_ZIP
+static int z_erofs_parse_cfgs(struct super_block *sb,
+			      struct erofs_super_block *dsb)
+{
+	if (!dsb->u1.available_compr_algs)
+		return 0;
+
+	erofs_err(sb, "compression disabled, unable to mount compressed EROFS");
+	return -EOPNOTSUPP;
+}
+#endif
+
+static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
+			     struct erofs_device_info *dif, erofs_off_t *pos)
 {
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
-	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
-	unsigned int algs, alg;
-	erofs_off_t offset;
-	int size, ret = 0;
-
-	sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs);
-	if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) {
-		erofs_err(sb, "try to load compressed fs with unsupported algorithms %x",
-			  sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS);
-		return -EINVAL;
-	}
+	struct erofs_fscache *fscache;
+	struct erofs_deviceslot *dis;
+	struct file *file;
 
-	offset = EROFS_SUPER_OFFSET + sbi->sb_size;
-	alg = 0;
-	for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) {
-		void *data;
+	dis = erofs_read_metabuf(buf, sb, *pos, false);
+	if (IS_ERR(dis))
+		return PTR_ERR(dis);
 
-		if (!(algs & 1))
-			continue;
+	if (!sbi->devs->flatdev && !dif->path) {
+		if (!dis->tag[0]) {
+			erofs_err(sb, "empty device tag @ pos %llu", *pos);
+			return -EINVAL;
+		}
+		dif->path = kmemdup_nul(dis->tag, sizeof(dis->tag), GFP_KERNEL);
+		if (!dif->path)
+			return -ENOMEM;
+	}
 
-		data = erofs_read_metadata(sb, &buf, &offset, &size);
-		if (IS_ERR(data)) {
-			ret = PTR_ERR(data);
-			break;
+	if (erofs_is_fscache_mode(sb)) {
+		fscache = erofs_fscache_register_cookie(sb, dif->path, 0);
+		if (IS_ERR(fscache))
+			return PTR_ERR(fscache);
+		dif->fscache = fscache;
+	} else if (!sbi->devs->flatdev) {
+		file = erofs_is_fileio_mode(sbi) ?
+				filp_open(dif->path, O_RDONLY | O_LARGEFILE, 0) :
+				bdev_file_open_by_path(dif->path,
+						BLK_OPEN_READ, sb->s_type, NULL);
+		if (IS_ERR(file)) {
+			if (file == ERR_PTR(-ENOTBLK))
+				return -EINVAL;
+			return PTR_ERR(file);
 		}
 
-		switch (alg) {
-		case Z_EROFS_COMPRESSION_LZ4:
-			ret = z_erofs_load_lz4_config(sb, dsb, data, size);
-			break;
-		case Z_EROFS_COMPRESSION_LZMA:
-			ret = z_erofs_load_lzma_config(sb, dsb, data, size);
-			break;
-		default:
-			DBG_BUGON(1);
-			ret = -EFAULT;
+		if (!erofs_is_fileio_mode(sbi)) {
+			dif->dax_dev = fs_dax_get_by_bdev(file_bdev(file),
+					&dif->dax_part_off, NULL, NULL);
+		} else if (!S_ISREG(file_inode(file)->i_mode)) {
+			fput(file);
+			return -EINVAL;
 		}
-		kfree(data);
-		if (ret)
-			break;
-	}
-	erofs_put_metabuf(&buf);
-	return ret;
-}
-#else
-static int erofs_load_compr_cfgs(struct super_block *sb,
-				 struct erofs_super_block *dsb)
-{
-	if (dsb->u1.available_compr_algs) {
-		erofs_err(sb, "try to load compressed fs when compression is disabled");
-		return -EINVAL;
+		if (!dif->dax_dev && test_opt(&sbi->opt, DAX_ALWAYS)) {
+			erofs_info(sb, "DAX unsupported by %s. Turning off DAX.",
+				   dif->path);
+			clear_opt(&sbi->opt, DAX_ALWAYS);
+		}
+		dif->file = file;
 	}
+
+	dif->blocks = le32_to_cpu(dis->blocks_lo);
+	dif->uniaddr = le32_to_cpu(dis->uniaddr_lo);
+	sbi->total_blocks += dif->blocks;
+	*pos += EROFS_DEVT_SLOT_SIZE;
 	return 0;
 }
-#endif
 
-static int erofs_init_devices(struct super_block *sb,
+static int erofs_scan_devices(struct super_block *sb,
 			      struct erofs_super_block *dsb)
 {
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
@@ -227,51 +201,59 @@ static int erofs_init_devices(struct super_block *sb,
 	erofs_off_t pos;
 	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
 	struct erofs_device_info *dif;
-	struct erofs_deviceslot *dis;
-	void *ptr;
 	int id, err = 0;
 
-	sbi->total_blocks = sbi->primarydevice_blocks;
+	sbi->total_blocks = sbi->dif0.blocks;
 	if (!erofs_sb_has_device_table(sbi))
 		ondisk_extradevs = 0;
 	else
 		ondisk_extradevs = le16_to_cpu(dsb->extra_devices);
 
-	if (ondisk_extradevs != sbi->devs->extra_devices) {
+	if (sbi->devs->extra_devices &&
+	    ondisk_extradevs != sbi->devs->extra_devices) {
 		erofs_err(sb, "extra devices don't match (ondisk %u, given %u)",
 			  ondisk_extradevs, sbi->devs->extra_devices);
 		return -EINVAL;
 	}
+
+	if (test_opt(&sbi->opt, DAX_ALWAYS) && !sbi->dif0.dax_dev) {
+		erofs_info(sb, "DAX unsupported by block device. Turning off DAX.");
+		clear_opt(&sbi->opt, DAX_ALWAYS);
+	}
 	if (!ondisk_extradevs)
 		return 0;
 
+	if (!sbi->devs->extra_devices && !erofs_is_fscache_mode(sb))
+		sbi->devs->flatdev = true;
+
 	sbi->device_id_mask = roundup_pow_of_two(ondisk_extradevs + 1) - 1;
 	pos = le16_to_cpu(dsb->devt_slotoff) * EROFS_DEVT_SLOT_SIZE;
 	down_read(&sbi->devs->rwsem);
-	idr_for_each_entry(&sbi->devs->tree, dif, id) {
-		struct block_device *bdev;
-
-		ptr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos),
-					 EROFS_KMAP);
-		if (IS_ERR(ptr)) {
-			err = PTR_ERR(ptr);
-			break;
+	if (sbi->devs->extra_devices) {
+		idr_for_each_entry(&sbi->devs->tree, dif, id) {
+			err = erofs_init_device(&buf, sb, dif, &pos);
+			if (err)
+				break;
 		}
-		dis = ptr + erofs_blkoff(pos);
-
-		bdev = blkdev_get_by_path(dif->path,
-					  FMODE_READ | FMODE_EXCL,
-					  sb->s_type);
-		if (IS_ERR(bdev)) {
-			err = PTR_ERR(bdev);
-			break;
+	} else {
+		for (id = 0; id < ondisk_extradevs; id++) {
+			dif = kzalloc(sizeof(*dif), GFP_KERNEL);
+			if (!dif) {
+				err = -ENOMEM;
+				break;
+			}
+
+			err = idr_alloc(&sbi->devs->tree, dif, 0, 0, GFP_KERNEL);
+			if (err < 0) {
+				kfree(dif);
+				break;
+			}
+			++sbi->devs->extra_devices;
+
+			err = erofs_init_device(&buf, sb, dif, &pos);
+			if (err)
+				break;
 		}
-		dif->bdev = bdev;
-		dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off);
-		dif->blocks = le32_to_cpu(dis->blocks);
-		dif->mapped_blkaddr = le32_to_cpu(dis->mapped_blkaddr);
-		sbi->total_blocks += dif->blocks;
-		pos += EROFS_DEVT_SLOT_SIZE;
 	}
 	up_read(&sbi->devs->rwsem);
 	erofs_put_metabuf(&buf);
@@ -280,30 +262,35 @@ static int erofs_init_devices(struct super_block *sb,
 
 static int erofs_read_superblock(struct super_block *sb)
 {
-	struct erofs_sb_info *sbi;
-	struct page *page;
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
 	struct erofs_super_block *dsb;
-	unsigned int blkszbits;
 	void *data;
 	int ret;
 
-	page = read_mapping_page(sb->s_bdev->bd_inode->i_mapping, 0, NULL);
-	if (IS_ERR(page)) {
+	data = erofs_read_metabuf(&buf, sb, 0, false);
+	if (IS_ERR(data)) {
 		erofs_err(sb, "cannot read erofs superblock");
-		return PTR_ERR(page);
+		return PTR_ERR(data);
 	}
 
-	sbi = EROFS_SB(sb);
-
-	data = kmap(page);
 	dsb = (struct erofs_super_block *)(data + EROFS_SUPER_OFFSET);
-
 	ret = -EINVAL;
 	if (le32_to_cpu(dsb->magic) != EROFS_SUPER_MAGIC_V1) {
 		erofs_err(sb, "cannot find valid erofs superblock");
 		goto out;
 	}
 
+	sbi->blkszbits = dsb->blkszbits;
+	if (sbi->blkszbits < 9 || sbi->blkszbits > PAGE_SHIFT) {
+		erofs_err(sb, "blkszbits %u isn't supported", sbi->blkszbits);
+		goto out;
+	}
+	if (dsb->dirblkbits) {
+		erofs_err(sb, "dirblkbits %u isn't supported", dsb->dirblkbits);
+		goto out;
+	}
+
 	sbi->feature_compat = le32_to_cpu(dsb->feature_compat);
 	if (erofs_sb_has_sb_chksum(sbi)) {
 		ret = erofs_superblock_csum_verify(sb, data);
@@ -312,88 +299,93 @@ static int erofs_read_superblock(struct super_block *sb)
 	}
 
 	ret = -EINVAL;
-	blkszbits = dsb->blkszbits;
-	/* 9(512 bytes) + LOG_SECTORS_PER_BLOCK == LOG_BLOCK_SIZE */
-	if (blkszbits != LOG_BLOCK_SIZE) {
-		erofs_err(sb, "blkszbits %u isn't supported on this platform",
-			  blkszbits);
+	sbi->feature_incompat = le32_to_cpu(dsb->feature_incompat);
+	if (sbi->feature_incompat & ~EROFS_ALL_FEATURE_INCOMPAT) {
+		erofs_err(sb, "unidentified incompatible feature %x, please upgrade kernel",
+			  sbi->feature_incompat & ~EROFS_ALL_FEATURE_INCOMPAT);
 		goto out;
 	}
 
-	if (!check_layout_compatibility(sb, dsb))
-		goto out;
-
 	sbi->sb_size = 128 + dsb->sb_extslots * EROFS_SB_EXTSLOT_SIZE;
-	if (sbi->sb_size > EROFS_BLKSIZ) {
+	if (sbi->sb_size > PAGE_SIZE - EROFS_SUPER_OFFSET) {
 		erofs_err(sb, "invalid sb_extslots %u (more than a fs block)",
 			  sbi->sb_size);
 		goto out;
 	}
-	sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks);
+	sbi->dif0.blocks = le32_to_cpu(dsb->blocks_lo);
 	sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr);
 #ifdef CONFIG_EROFS_FS_XATTR
 	sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr);
+	sbi->xattr_prefix_start = le32_to_cpu(dsb->xattr_prefix_start);
+	sbi->xattr_prefix_count = dsb->xattr_prefix_count;
+	sbi->xattr_filter_reserved = dsb->xattr_filter_reserved;
 #endif
 	sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact));
-	sbi->root_nid = le16_to_cpu(dsb->root_nid);
+	if (erofs_sb_has_48bit(sbi) && dsb->rootnid_8b) {
+		sbi->root_nid = le64_to_cpu(dsb->rootnid_8b);
+		sbi->dif0.blocks = sbi->dif0.blocks |
+				((u64)le16_to_cpu(dsb->rb.blocks_hi) << 32);
+	} else {
+		sbi->root_nid = le16_to_cpu(dsb->rb.rootnid_2b);
+	}
+	sbi->packed_nid = le64_to_cpu(dsb->packed_nid);
+	if (erofs_sb_has_metabox(sbi)) {
+		if (sbi->sb_size <= offsetof(struct erofs_super_block,
+					     metabox_nid))
+			return -EFSCORRUPTED;
+		sbi->metabox_nid = le64_to_cpu(dsb->metabox_nid);
+		if (sbi->metabox_nid & BIT_ULL(EROFS_DIRENT_NID_METABOX_BIT))
+			return -EFSCORRUPTED;	/* self-loop detection */
+	}
 	sbi->inos = le64_to_cpu(dsb->inos);
 
-	sbi->build_time = le64_to_cpu(dsb->build_time);
-	sbi->build_time_nsec = le32_to_cpu(dsb->build_time_nsec);
+	sbi->epoch = (s64)le64_to_cpu(dsb->epoch);
+	sbi->fixed_nsec = le32_to_cpu(dsb->fixed_nsec);
+	super_set_uuid(sb, (void *)dsb->uuid, sizeof(dsb->uuid));
 
-	memcpy(&sb->s_uuid, dsb->uuid, sizeof(dsb->uuid));
-
-	ret = strscpy(sbi->volume_name, dsb->volume_name,
-		      sizeof(dsb->volume_name));
-	if (ret < 0) {	/* -E2BIG */
-		erofs_err(sb, "bad volume name without NIL terminator");
-		ret = -EFSCORRUPTED;
-		goto out;
+	if (dsb->volume_name[0]) {
+		sbi->volume_name = kstrndup(dsb->volume_name,
+					    sizeof(dsb->volume_name), GFP_KERNEL);
+		if (!sbi->volume_name)
+			return -ENOMEM;
 	}
 
 	/* parse on-disk compression configurations */
-	if (erofs_sb_has_compr_cfgs(sbi))
-		ret = erofs_load_compr_cfgs(sb, dsb);
-	else
-		ret = z_erofs_load_lz4_config(sb, dsb, NULL, 0);
+	ret = z_erofs_parse_cfgs(sb, dsb);
 	if (ret < 0)
 		goto out;
 
-	/* handle multiple devices */
-	ret = erofs_init_devices(sb, dsb);
+	ret = erofs_scan_devices(sb, dsb);
 
-	if (erofs_sb_has_ztailpacking(sbi))
-		erofs_info(sb, "EXPERIMENTAL compressed inline data feature in use. Use at your own risk!");
+	if (erofs_sb_has_48bit(sbi))
+		erofs_info(sb, "EXPERIMENTAL 48-bit layout support in use. Use at your own risk!");
+	if (erofs_sb_has_metabox(sbi))
+		erofs_info(sb, "EXPERIMENTAL metadata compression support in use. Use at your own risk!");
+	if (erofs_is_fscache_mode(sb))
+		erofs_info(sb, "[deprecated] fscache-based on-demand read feature in use. Use at your own risk!");
 out:
-	kunmap(page);
-	put_page(page);
+	erofs_put_metabuf(&buf);
 	return ret;
 }
 
-/* set up default EROFS parameters */
-static void erofs_default_options(struct erofs_fs_context *ctx)
+static void erofs_default_options(struct erofs_sb_info *sbi)
 {
 #ifdef CONFIG_EROFS_FS_ZIP
-	ctx->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND;
-	ctx->opt.max_sync_decompress_pages = 3;
-	ctx->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_AUTO;
+	sbi->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND;
+	sbi->opt.max_sync_decompress_pages = 3;
+	sbi->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_AUTO;
 #endif
 #ifdef CONFIG_EROFS_FS_XATTR
-	set_opt(&ctx->opt, XATTR_USER);
+	set_opt(&sbi->opt, XATTR_USER);
 #endif
 #ifdef CONFIG_EROFS_FS_POSIX_ACL
-	set_opt(&ctx->opt, POSIX_ACL);
+	set_opt(&sbi->opt, POSIX_ACL);
 #endif
 }
 
 enum {
-	Opt_user_xattr,
-	Opt_acl,
-	Opt_cache_strategy,
-	Opt_dax,
-	Opt_dax_enum,
-	Opt_device,
-	Opt_err
+	Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum,
+	Opt_device, Opt_fsid, Opt_domain_id, Opt_directio, Opt_fsoffset,
 };
 
 static const struct constant_table erofs_param_cache_strategy[] = {
@@ -417,23 +409,26 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = {
 	fsparam_flag("dax",             Opt_dax),
 	fsparam_enum("dax",		Opt_dax_enum, erofs_dax_param_enums),
 	fsparam_string("device",	Opt_device),
+	fsparam_string("fsid",		Opt_fsid),
+	fsparam_string("domain_id",	Opt_domain_id),
+	fsparam_flag_no("directio",	Opt_directio),
+	fsparam_u64("fsoffset",		Opt_fsoffset),
 	{}
 };
 
 static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode)
 {
 #ifdef CONFIG_FS_DAX
-	struct erofs_fs_context *ctx = fc->fs_private;
+	struct erofs_sb_info *sbi = fc->s_fs_info;
 
 	switch (mode) {
 	case EROFS_MOUNT_DAX_ALWAYS:
-		warnfc(fc, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
-		set_opt(&ctx->opt, DAX_ALWAYS);
-		clear_opt(&ctx->opt, DAX_NEVER);
+		set_opt(&sbi->opt, DAX_ALWAYS);
+		clear_opt(&sbi->opt, DAX_NEVER);
 		return true;
 	case EROFS_MOUNT_DAX_NEVER:
-		set_opt(&ctx->opt, DAX_NEVER);
-		clear_opt(&ctx->opt, DAX_ALWAYS);
+		set_opt(&sbi->opt, DAX_NEVER);
+		clear_opt(&sbi->opt, DAX_ALWAYS);
 		return true;
 	default:
 		DBG_BUGON(1);
@@ -448,7 +443,7 @@ static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode)
 static int erofs_fc_parse_param(struct fs_context *fc,
 				struct fs_parameter *param)
 {
-	struct erofs_fs_context *ctx = fc->fs_private;
+	struct erofs_sb_info *sbi = fc->s_fs_info;
 	struct fs_parse_result result;
 	struct erofs_device_info *dif;
 	int opt, ret;
@@ -461,9 +456,9 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 	case Opt_user_xattr:
 #ifdef CONFIG_EROFS_FS_XATTR
 		if (result.boolean)
-			set_opt(&ctx->opt, XATTR_USER);
+			set_opt(&sbi->opt, XATTR_USER);
 		else
-			clear_opt(&ctx->opt, XATTR_USER);
+			clear_opt(&sbi->opt, XATTR_USER);
 #else
 		errorfc(fc, "{,no}user_xattr options not supported");
 #endif
@@ -471,16 +466,16 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 	case Opt_acl:
 #ifdef CONFIG_EROFS_FS_POSIX_ACL
 		if (result.boolean)
-			set_opt(&ctx->opt, POSIX_ACL);
+			set_opt(&sbi->opt, POSIX_ACL);
 		else
-			clear_opt(&ctx->opt, POSIX_ACL);
+			clear_opt(&sbi->opt, POSIX_ACL);
 #else
 		errorfc(fc, "{,no}acl options not supported");
 #endif
 		break;
 	case Opt_cache_strategy:
 #ifdef CONFIG_EROFS_FS_ZIP
-		ctx->opt.cache_strategy = result.uint_32;
+		sbi->opt.cache_strategy = result.uint_32;
 #else
 		errorfc(fc, "compression not supported, cache_strategy ignored");
 #endif
@@ -502,182 +497,319 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 			kfree(dif);
 			return -ENOMEM;
 		}
-		down_write(&ctx->devs->rwsem);
-		ret = idr_alloc(&ctx->devs->tree, dif, 0, 0, GFP_KERNEL);
-		up_write(&ctx->devs->rwsem);
+		down_write(&sbi->devs->rwsem);
+		ret = idr_alloc(&sbi->devs->tree, dif, 0, 0, GFP_KERNEL);
+		up_write(&sbi->devs->rwsem);
 		if (ret < 0) {
 			kfree(dif->path);
 			kfree(dif);
 			return ret;
 		}
-		++ctx->devs->extra_devices;
+		++sbi->devs->extra_devices;
+		break;
+#ifdef CONFIG_EROFS_FS_ONDEMAND
+	case Opt_fsid:
+		kfree(sbi->fsid);
+		sbi->fsid = kstrdup(param->string, GFP_KERNEL);
+		if (!sbi->fsid)
+			return -ENOMEM;
+		break;
+	case Opt_domain_id:
+		kfree(sbi->domain_id);
+		sbi->domain_id = kstrdup(param->string, GFP_KERNEL);
+		if (!sbi->domain_id)
+			return -ENOMEM;
+		break;
+#else
+	case Opt_fsid:
+	case Opt_domain_id:
+		errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
+		break;
+#endif
+	case Opt_directio:
+#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
+		if (result.boolean)
+			set_opt(&sbi->opt, DIRECT_IO);
+		else
+			clear_opt(&sbi->opt, DIRECT_IO);
+#else
+		errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
+#endif
+		break;
+	case Opt_fsoffset:
+		sbi->dif0.fsoff = result.uint_64;
 		break;
-	default:
-		return -ENOPARAM;
 	}
 	return 0;
 }
 
-#ifdef CONFIG_EROFS_FS_ZIP
-static const struct address_space_operations managed_cache_aops;
-
-static int erofs_managed_cache_releasepage(struct page *page, gfp_t gfp_mask)
+static int erofs_encode_fh(struct inode *inode, u32 *fh, int *max_len,
+			   struct inode *parent)
 {
-	int ret = 1;	/* 0 - busy */
-	struct address_space *const mapping = page->mapping;
+	erofs_nid_t nid = EROFS_I(inode)->nid;
+	int len = parent ? 6 : 3;
 
-	DBG_BUGON(!PageLocked(page));
-	DBG_BUGON(mapping->a_ops != &managed_cache_aops);
+	if (*max_len < len) {
+		*max_len = len;
+		return FILEID_INVALID;
+	}
 
-	if (PagePrivate(page))
-		ret = erofs_try_to_free_cached_page(page);
+	fh[0] = (u32)(nid >> 32);
+	fh[1] = (u32)(nid & 0xffffffff);
+	fh[2] = inode->i_generation;
 
-	return ret;
+	if (parent) {
+		nid = EROFS_I(parent)->nid;
+
+		fh[3] = (u32)(nid >> 32);
+		fh[4] = (u32)(nid & 0xffffffff);
+		fh[5] = parent->i_generation;
+	}
+
+	*max_len = len;
+	return parent ? FILEID_INO64_GEN_PARENT : FILEID_INO64_GEN;
 }
 
-static void erofs_managed_cache_invalidatepage(struct page *page,
-					       unsigned int offset,
-					       unsigned int length)
+static struct dentry *erofs_fh_to_dentry(struct super_block *sb,
+		struct fid *fid, int fh_len, int fh_type)
 {
-	const unsigned int stop = length + offset;
+	if ((fh_type != FILEID_INO64_GEN &&
+	     fh_type != FILEID_INO64_GEN_PARENT) || fh_len < 3)
+		return NULL;
 
-	DBG_BUGON(!PageLocked(page));
+	return d_obtain_alias(erofs_iget(sb,
+		((u64)fid->raw[0] << 32) | fid->raw[1]));
+}
 
-	/* Check for potential overflow in debug mode */
-	DBG_BUGON(stop > PAGE_SIZE || stop < length);
+static struct dentry *erofs_fh_to_parent(struct super_block *sb,
+		struct fid *fid, int fh_len, int fh_type)
+{
+	if (fh_type != FILEID_INO64_GEN_PARENT || fh_len < 6)
+		return NULL;
 
-	if (offset == 0 && stop == PAGE_SIZE)
-		while (!erofs_managed_cache_releasepage(page, GFP_NOFS))
-			cond_resched();
+	return d_obtain_alias(erofs_iget(sb,
+		((u64)fid->raw[3] << 32) | fid->raw[4]));
 }
 
-static const struct address_space_operations managed_cache_aops = {
-	.releasepage = erofs_managed_cache_releasepage,
-	.invalidatepage = erofs_managed_cache_invalidatepage,
-};
-
-static int erofs_init_managed_cache(struct super_block *sb)
+static struct dentry *erofs_get_parent(struct dentry *child)
 {
-	struct erofs_sb_info *const sbi = EROFS_SB(sb);
-	struct inode *const inode = new_inode(sb);
+	erofs_nid_t nid;
+	unsigned int d_type;
+	int err;
 
-	if (!inode)
-		return -ENOMEM;
+	err = erofs_namei(d_inode(child), &dotdot_name, &nid, &d_type);
+	if (err)
+		return ERR_PTR(err);
+	return d_obtain_alias(erofs_iget(child->d_sb, nid));
+}
 
-	set_nlink(inode, 1);
-	inode->i_size = OFFSET_MAX;
+static const struct export_operations erofs_export_ops = {
+	.encode_fh = erofs_encode_fh,
+	.fh_to_dentry = erofs_fh_to_dentry,
+	.fh_to_parent = erofs_fh_to_parent,
+	.get_parent = erofs_get_parent,
+};
 
-	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;
+static void erofs_set_sysfs_name(struct super_block *sb)
+{
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+
+	if (sbi->domain_id)
+		super_set_sysfs_name_generic(sb, "%s,%s", sbi->domain_id,
+					     sbi->fsid);
+	else if (sbi->fsid)
+		super_set_sysfs_name_generic(sb, "%s", sbi->fsid);
+	else if (erofs_is_fileio_mode(sbi))
+		super_set_sysfs_name_generic(sb, "%s",
+					     bdi_dev_name(sb->s_bdi));
+	else
+		super_set_sysfs_name_id(sb);
 }
-#else
-static int erofs_init_managed_cache(struct super_block *sb) { return 0; }
-#endif
 
 static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	struct inode *inode;
-	struct erofs_sb_info *sbi;
-	struct erofs_fs_context *ctx = fc->fs_private;
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
 	int err;
 
 	sb->s_magic = EROFS_SUPER_MAGIC;
+	sb->s_flags |= SB_RDONLY | SB_NOATIME;
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+	sb->s_op = &erofs_sops;
 
-	if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) {
-		erofs_err(sb, "failed to set erofs blksize");
-		return -EINVAL;
-	}
+	sbi->blkszbits = PAGE_SHIFT;
+	if (!sb->s_bdev) {
+		/*
+		 * (File-backed mounts) EROFS claims it's safe to nest other
+		 * fs contexts (including its own) due to self-controlled RO
+		 * accesses/contexts and no side-effect changes that need to
+		 * context save & restore so it can reuse the current thread
+		 * context.  However, it still needs to bump `s_stack_depth` to
+		 * avoid kernel stack overflow from nested filesystems.
+		 */
+		if (erofs_is_fileio_mode(sbi)) {
+			sb->s_stack_depth =
+				file_inode(sbi->dif0.file)->i_sb->s_stack_depth + 1;
+			if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
+				erofs_err(sb, "maximum fs stacking depth exceeded");
+				return -ENOTBLK;
+			}
+		}
+		sb->s_blocksize = PAGE_SIZE;
+		sb->s_blocksize_bits = PAGE_SHIFT;
 
-	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
-	if (!sbi)
-		return -ENOMEM;
+		if (erofs_is_fscache_mode(sb)) {
+			err = erofs_fscache_register_fs(sb);
+			if (err)
+				return err;
+		}
+		err = super_setup_bdi(sb);
+		if (err)
+			return err;
+	} else {
+		if (!sb_set_blocksize(sb, PAGE_SIZE)) {
+			errorfc(fc, "failed to set initial blksize");
+			return -EINVAL;
+		}
 
-	sb->s_fs_info = sbi;
-	sbi->opt = ctx->opt;
-	sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->dax_part_off);
-	sbi->devs = ctx->devs;
-	ctx->devs = NULL;
+		sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev,
+				&sbi->dif0.dax_part_off, NULL, NULL);
+	}
 
 	err = erofs_read_superblock(sb);
 	if (err)
 		return err;
 
-	if (test_opt(&sbi->opt, DAX_ALWAYS)) {
-		BUILD_BUG_ON(EROFS_BLKSIZ != PAGE_SIZE);
+	if (sb->s_blocksize_bits != sbi->blkszbits) {
+		if (erofs_is_fscache_mode(sb)) {
+			errorfc(fc, "unsupported blksize for fscache mode");
+			return -EINVAL;
+		}
 
-		if (!sbi->dax_dev) {
-			errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
-			clear_opt(&sbi->opt, DAX_ALWAYS);
+		if (erofs_is_fileio_mode(sbi)) {
+			sb->s_blocksize = 1 << sbi->blkszbits;
+			sb->s_blocksize_bits = sbi->blkszbits;
+		} else if (!sb_set_blocksize(sb, 1 << sbi->blkszbits)) {
+			errorfc(fc, "failed to set erofs blksize");
+			return -EINVAL;
 		}
 	}
-	sb->s_flags |= SB_RDONLY | SB_NOATIME;
-	sb->s_maxbytes = MAX_LFS_FILESIZE;
-	sb->s_time_gran = 1;
 
-	sb->s_op = &erofs_sops;
+	if (sbi->dif0.fsoff) {
+		if (sbi->dif0.fsoff & (sb->s_blocksize - 1))
+			return invalfc(fc, "fsoffset %llu is not aligned to block size %lu",
+				       sbi->dif0.fsoff, sb->s_blocksize);
+		if (erofs_is_fscache_mode(sb))
+			return invalfc(fc, "cannot use fsoffset in fscache mode");
+	}
+
+	if (test_opt(&sbi->opt, DAX_ALWAYS) && sbi->blkszbits != PAGE_SHIFT) {
+		erofs_info(sb, "unsupported blocksize for DAX");
+		clear_opt(&sbi->opt, DAX_ALWAYS);
+	}
+
+	sb->s_time_gran = 1;
 	sb->s_xattr = erofs_xattr_handlers;
+	sb->s_export_op = &erofs_export_ops;
 
 	if (test_opt(&sbi->opt, POSIX_ACL))
 		sb->s_flags |= SB_POSIXACL;
 	else
 		sb->s_flags &= ~SB_POSIXACL;
 
-#ifdef CONFIG_EROFS_FS_ZIP
-	xa_init(&sbi->managed_pslots);
-#endif
+	err = z_erofs_init_super(sb);
+	if (err)
+		return err;
+
+	if (erofs_sb_has_fragments(sbi) && sbi->packed_nid) {
+		inode = erofs_iget(sb, sbi->packed_nid);
+		if (IS_ERR(inode))
+			return PTR_ERR(inode);
+		sbi->packed_inode = inode;
+	}
+	if (erofs_sb_has_metabox(sbi)) {
+		inode = erofs_iget(sb, sbi->metabox_nid);
+		if (IS_ERR(inode))
+			return PTR_ERR(inode);
+		sbi->metabox_inode = inode;
+	}
 
-	/* get the root inode */
-	inode = erofs_iget(sb, ROOT_NID(sbi), true);
+	inode = erofs_iget(sb, sbi->root_nid);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
 	if (!S_ISDIR(inode->i_mode)) {
 		erofs_err(sb, "rootino(nid %llu) is not a directory(i_mode %o)",
-			  ROOT_NID(sbi), inode->i_mode);
+			  sbi->root_nid, inode->i_mode);
 		iput(inode);
 		return -EINVAL;
 	}
-
 	sb->s_root = d_make_root(inode);
 	if (!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);
+	err = erofs_xattr_prefixes_init(sb);
 	if (err)
 		return err;
 
+	erofs_set_sysfs_name(sb);
 	err = erofs_register_sysfs(sb);
 	if (err)
 		return err;
 
-	erofs_info(sb, "mounted with root inode @ nid %llu.", ROOT_NID(sbi));
+	sbi->dir_ra_bytes = EROFS_DIR_RA_BYTES;
+	erofs_info(sb, "mounted with root inode @ nid %llu.", sbi->root_nid);
 	return 0;
 }
 
 static int erofs_fc_get_tree(struct fs_context *fc)
 {
-	return get_tree_bdev(fc, erofs_fc_fill_super);
+	struct erofs_sb_info *sbi = fc->s_fs_info;
+	int ret;
+
+	if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid)
+		return get_tree_nodev(fc, erofs_fc_fill_super);
+
+	ret = get_tree_bdev_flags(fc, erofs_fc_fill_super,
+		IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) ?
+			GET_TREE_BDEV_QUIET_LOOKUP : 0);
+#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
+	if (ret == -ENOTBLK) {
+		struct file *file;
+
+		if (!fc->source)
+			return invalf(fc, "No source specified");
+		file = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0);
+		if (IS_ERR(file))
+			return PTR_ERR(file);
+		sbi->dif0.file = file;
+
+		if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) &&
+		    sbi->dif0.file->f_mapping->a_ops->read_folio)
+			return get_tree_nodev(fc, erofs_fc_fill_super);
+	}
+#endif
+	return ret;
 }
 
 static int erofs_fc_reconfigure(struct fs_context *fc)
 {
 	struct super_block *sb = fc->root->d_sb;
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
-	struct erofs_fs_context *ctx = fc->fs_private;
+	struct erofs_sb_info *new_sbi = fc->s_fs_info;
 
 	DBG_BUGON(!sb_rdonly(sb));
 
-	if (test_opt(&ctx->opt, POSIX_ACL))
+	if (new_sbi->fsid || new_sbi->domain_id)
+		erofs_info(sb, "ignoring reconfiguration for fsid|domain_id.");
+
+	if (test_opt(&new_sbi->opt, POSIX_ACL))
 		fc->sb_flags |= SB_POSIXACL;
 	else
 		fc->sb_flags &= ~SB_POSIXACL;
 
-	sbi->opt = ctx->opt;
+	sbi->opt = new_sbi->opt;
 
 	fc->sb_flags |= SB_RDONLY;
 	return 0;
@@ -687,9 +819,11 @@ static int erofs_release_device_info(int id, void *ptr, void *data)
 {
 	struct erofs_device_info *dif = ptr;
 
-	fs_put_dax(dif->dax_dev);
-	if (dif->bdev)
-		blkdev_put(dif->bdev, FMODE_READ | FMODE_EXCL);
+	fs_put_dax(dif->dax_dev, NULL);
+	if (dif->file)
+		fput(dif->file);
+	erofs_fscache_unregister_cookie(dif->fscache);
+	dif->fscache = NULL;
 	kfree(dif->path);
 	kfree(dif);
 	return 0;
@@ -704,12 +838,23 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs)
 	kfree(devs);
 }
 
+static void erofs_sb_free(struct erofs_sb_info *sbi)
+{
+	erofs_free_dev_context(sbi->devs);
+	kfree(sbi->fsid);
+	kfree(sbi->domain_id);
+	if (sbi->dif0.file)
+		fput(sbi->dif0.file);
+	kfree(sbi->volume_name);
+	kfree(sbi);
+}
+
 static void erofs_fc_free(struct fs_context *fc)
 {
-	struct erofs_fs_context *ctx = fc->fs_private;
+	struct erofs_sb_info *sbi = fc->s_fs_info;
 
-	erofs_free_dev_context(ctx->devs);
-	kfree(ctx);
+	if (sbi) /* free here if an error occurs before transferring to sb */
+		erofs_sb_free(sbi);
 }
 
 static const struct fs_context_operations erofs_context_ops = {
@@ -721,59 +866,65 @@ static const struct fs_context_operations erofs_context_ops = {
 
 static int erofs_init_fs_context(struct fs_context *fc)
 {
-	struct erofs_fs_context *ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	struct erofs_sb_info *sbi;
 
-	if (!ctx)
+	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
+	if (!sbi)
 		return -ENOMEM;
-	ctx->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL);
-	if (!ctx->devs) {
-		kfree(ctx);
+
+	sbi->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL);
+	if (!sbi->devs) {
+		kfree(sbi);
 		return -ENOMEM;
 	}
-	fc->fs_private = ctx;
+	fc->s_fs_info = sbi;
 
-	idr_init(&ctx->devs->tree);
-	init_rwsem(&ctx->devs->rwsem);
-	erofs_default_options(ctx);
+	idr_init(&sbi->devs->tree);
+	init_rwsem(&sbi->devs->rwsem);
+	erofs_default_options(sbi);
 	fc->ops = &erofs_context_ops;
 	return 0;
 }
 
-/*
- * 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)
+static void erofs_drop_internal_inodes(struct erofs_sb_info *sbi)
 {
-	struct erofs_sb_info *sbi;
-
-	WARN_ON(sb->s_magic != EROFS_SUPER_MAGIC);
-
-	kill_block_super(sb);
+	iput(sbi->packed_inode);
+	sbi->packed_inode = NULL;
+	iput(sbi->metabox_inode);
+	sbi->metabox_inode = NULL;
+#ifdef CONFIG_EROFS_FS_ZIP
+	iput(sbi->managed_cache);
+	sbi->managed_cache = NULL;
+#endif
+}
 
-	sbi = EROFS_SB(sb);
-	if (!sbi)
-		return;
+static void erofs_kill_sb(struct super_block *sb)
+{
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
 
-	erofs_free_dev_context(sbi->devs);
-	fs_put_dax(sbi->dax_dev);
-	kfree(sbi);
+	if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) ||
+	    sbi->dif0.file)
+		kill_anon_super(sb);
+	else
+		kill_block_super(sb);
+	erofs_drop_internal_inodes(sbi);
+	fs_put_dax(sbi->dif0.dax_dev, NULL);
+	erofs_fscache_unregister_fs(sb);
+	erofs_sb_free(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_unregister_sysfs(sb);
 	erofs_shrinker_unregister(sb);
-#ifdef CONFIG_EROFS_FS_ZIP
-	iput(sbi->managed_cache);
-	sbi->managed_cache = NULL;
-#endif
+	erofs_xattr_prefixes_cleanup(sb);
+	erofs_drop_internal_inodes(sbi);
+	erofs_free_dev_context(sbi->devs);
+	sbi->devs = NULL;
+	erofs_fscache_unregister_fs(sb);
 }
 
 static struct file_system_type erofs_fs_type = {
@@ -781,7 +932,7 @@ static struct file_system_type erofs_fs_type = {
 	.name           = "erofs",
 	.init_fs_context = erofs_init_fs_context,
 	.kill_sb        = erofs_kill_sb,
-	.fs_flags       = FS_REQUIRES_DEV,
+	.fs_flags       = FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
 };
 MODULE_ALIAS_FS("erofs");
 
@@ -792,24 +943,17 @@ static int __init erofs_module_init(void)
 	erofs_check_ondisk_layout_definitions();
 
 	erofs_inode_cachep = kmem_cache_create("erofs_inode",
-					       sizeof(struct erofs_inode), 0,
-					       SLAB_RECLAIM_ACCOUNT,
-					       erofs_inode_init_once);
-	if (!erofs_inode_cachep) {
-		err = -ENOMEM;
-		goto icache_err;
-	}
+			sizeof(struct erofs_inode), 0,
+			SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT,
+			erofs_inode_init_once);
+	if (!erofs_inode_cachep)
+		return -ENOMEM;
 
 	err = erofs_init_shrinker();
 	if (err)
 		goto shrinker_err;
 
-	err = z_erofs_lzma_init();
-	if (err)
-		goto lzma_err;
-
-	erofs_pcpubuf_init();
-	err = z_erofs_init_zip_subsystem();
+	err = z_erofs_init_subsystem();
 	if (err)
 		goto zip_err;
 
@@ -826,14 +970,11 @@ static int __init erofs_module_init(void)
 fs_err:
 	erofs_exit_sysfs();
 sysfs_err:
-	z_erofs_exit_zip_subsystem();
+	z_erofs_exit_subsystem();
 zip_err:
-	z_erofs_lzma_exit();
-lzma_err:
 	erofs_exit_shrinker();
 shrinker_err:
 	kmem_cache_destroy(erofs_inode_cachep);
-icache_err:
 	return err;
 }
 
@@ -845,31 +986,29 @@ static void __exit erofs_module_exit(void)
 	rcu_barrier();
 
 	erofs_exit_sysfs();
-	z_erofs_exit_zip_subsystem();
-	z_erofs_lzma_exit();
+	z_erofs_exit_subsystem();
 	erofs_exit_shrinker();
 	kmem_cache_destroy(erofs_inode_cachep);
-	erofs_pcpubuf_exit();
 }
 
-/* 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_bsize = sb->s_blocksize;
 	buf->f_blocks = sbi->total_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    = u64_to_fsid(id);
+	if (uuid_is_null(&sb->s_uuid))
+		buf->f_fsid = u64_to_fsid(!sb->s_bdev ? 0 :
+				huge_encode_dev(sb->s_bdev->bd_dev));
+	else
+		buf->f_fsid = uuid_to_fsid(sb->s_uuid.b);
 	return 0;
 }
 
@@ -878,37 +1017,47 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root)
 	struct erofs_sb_info *sbi = EROFS_SB(root->d_sb);
 	struct erofs_mount_opts *opt = &sbi->opt;
 
-#ifdef CONFIG_EROFS_FS_XATTR
-	if (test_opt(opt, XATTR_USER))
-		seq_puts(seq, ",user_xattr");
-	else
-		seq_puts(seq, ",nouser_xattr");
-#endif
-#ifdef CONFIG_EROFS_FS_POSIX_ACL
-	if (test_opt(opt, POSIX_ACL))
-		seq_puts(seq, ",acl");
-	else
-		seq_puts(seq, ",noacl");
-#endif
-#ifdef CONFIG_EROFS_FS_ZIP
-	if (opt->cache_strategy == EROFS_ZIP_CACHE_DISABLED)
-		seq_puts(seq, ",cache_strategy=disabled");
-	else if (opt->cache_strategy == EROFS_ZIP_CACHE_READAHEAD)
-		seq_puts(seq, ",cache_strategy=readahead");
-	else if (opt->cache_strategy == EROFS_ZIP_CACHE_READAROUND)
-		seq_puts(seq, ",cache_strategy=readaround");
-#endif
+	if (IS_ENABLED(CONFIG_EROFS_FS_XATTR))
+		seq_puts(seq, test_opt(opt, XATTR_USER) ?
+				",user_xattr" : ",nouser_xattr");
+	if (IS_ENABLED(CONFIG_EROFS_FS_POSIX_ACL))
+		seq_puts(seq, test_opt(opt, POSIX_ACL) ? ",acl" : ",noacl");
+	if (IS_ENABLED(CONFIG_EROFS_FS_ZIP))
+		seq_printf(seq, ",cache_strategy=%s",
+			  erofs_param_cache_strategy[opt->cache_strategy].name);
 	if (test_opt(opt, DAX_ALWAYS))
 		seq_puts(seq, ",dax=always");
 	if (test_opt(opt, DAX_NEVER))
 		seq_puts(seq, ",dax=never");
+	if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO))
+		seq_puts(seq, ",directio");
+#ifdef CONFIG_EROFS_FS_ONDEMAND
+	if (sbi->fsid)
+		seq_printf(seq, ",fsid=%s", sbi->fsid);
+	if (sbi->domain_id)
+		seq_printf(seq, ",domain_id=%s", sbi->domain_id);
+#endif
+	if (sbi->dif0.fsoff)
+		seq_printf(seq, ",fsoffset=%llu", sbi->dif0.fsoff);
 	return 0;
 }
 
+static void erofs_evict_inode(struct inode *inode)
+{
+#ifdef CONFIG_FS_DAX
+	if (IS_DAX(inode))
+		dax_break_layout_final(inode);
+#endif
+
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+}
+
 const struct super_operations erofs_sops = {
 	.put_super = erofs_put_super,
 	.alloc_inode = erofs_alloc_inode,
 	.free_inode = erofs_free_inode,
+	.evict_inode = erofs_evict_inode,
 	.statfs = erofs_statfs,
 	.show_options = erofs_show_options,
 };