Merge 815409a12c ("Merge tag 'ovl-update-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs") into android-mainline

Steps on the way to 5.15-rc1

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Ia61d00e6e4f49501323c3f4769793529c78d3713

Documentation/filesystems/erofs.rst

@@ -84,6 +84,9 @@ cache_strategy=%s      Select a strategy for cached decompression from now on:
                                    It still does in-place I/O decompression
                                    for the rest compressed physical clusters.
 		       ==========  =============================================
+dax={always,never}     Use direct access (no page cache).  See
+                       Documentation/filesystems/dax.rst.
+dax                    A legacy option which is an alias for ``dax=always``.
 ===================    =========================================================
 
 On-disk details
@@ -153,13 +156,14 @@ may not. All metadatas can be now observed in two different spaces (views):
 
     Xattrs, extents, data inline are followed by the corresponding inode with
     proper alignment, and they could be optional for different data mappings.
-    _currently_ total 4 valid data mappings are supported:
+    _currently_ total 5 data layouts are supported:
 
     ==  ====================================================================
      0  flat file data without data inline (no extent);
      1  fixed-sized output data compression (with non-compacted indexes);
      2  flat file data with tail packing data inline (no extent);
-     3  fixed-sized output data compression (with compacted indexes, v5.3+).
+     3  fixed-sized output data compression (with compacted indexes, v5.3+);
+     4  chunk-based file (v5.15+).
     ==  ====================================================================
 
     The size of the optional xattrs is indicated by i_xattr_count in inode
@@ -210,6 +214,17 @@ Note that apart from the offset of the first filename, nameoff0 also indicates
 the total number of directory entries in this block since it is no need to
 introduce another on-disk field at all.
 
+Chunk-based file
+----------------
+In order to support chunk-based data deduplication, a new inode data layout has
+been supported since Linux v5.15: Files are split in equal-sized data chunks
+with ``extents`` area of the inode metadata indicating how to get the chunk
+data: these can be simply as a 4-byte block address array or in the 8-byte
+chunk index form (see struct erofs_inode_chunk_index in erofs_fs.h for more
+details.)
+
+By the way, chunk-based files are all uncompressed for now.
+
 Data compression
 ----------------
 EROFS implements LZ4 fixed-sized output compression which generates fixed-sized

Documentation/filesystems/locking.rst

@@ -70,7 +70,7 @@ prototypes::
 	const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *);
 	void (*truncate) (struct inode *);
 	int (*permission) (struct inode *, int, unsigned int);
-	int (*get_acl)(struct inode *, int);
+	struct posix_acl * (*get_acl)(struct inode *, int, bool);
 	int (*setattr) (struct dentry *, struct iattr *);
 	int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);

Documentation/filesystems/overlayfs.rst

@@ -427,6 +427,9 @@ b) If a file residing on a lower layer is opened for read-only and then
 memory mapped with MAP_SHARED, then subsequent changes to the file are not
 reflected in the memory mapping.
 
+c) If a file residing on a lower layer is being executed, then opening that
+file for write or truncating the file will not be denied with ETXTBSY.
+
 The following options allow overlayfs to act more like a standards
 compliant filesystem:
 

Documentation/filesystems/vfs.rst

@@ -432,7 +432,7 @@ As of kernel 2.6.22, the following members are defined:
 		const char *(*get_link) (struct dentry *, struct inode *,
 					 struct delayed_call *);
 		int (*permission) (struct user_namespace *, struct inode *, int);
-		int (*get_acl)(struct inode *, int);
+		struct posix_acl * (*get_acl)(struct inode *, int, bool);
 		int (*setattr) (struct user_namespace *, struct dentry *, struct iattr *);
 		int (*getattr) (struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int);
 		ssize_t (*listxattr) (struct dentry *, char *, size_t);

fs/9p/acl.c

@@ -97,10 +97,13 @@ static struct posix_acl *v9fs_get_cached_acl(struct inode *inode, int type)
 	return acl;
 }
 
-struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type)
+struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type, bool rcu)
 {
 	struct v9fs_session_info *v9ses;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	v9ses = v9fs_inode2v9ses(inode);
 	if (((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) ||
 			((v9ses->flags & V9FS_ACL_MASK) != V9FS_POSIX_ACL)) {

fs/9p/acl.h

@@ -16,7 +16,7 @@
 
 #ifdef CONFIG_9P_FS_POSIX_ACL
 extern int v9fs_get_acl(struct inode *, struct p9_fid *);
-extern struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type);
+extern struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type, bool rcu);
 extern int v9fs_acl_chmod(struct inode *, struct p9_fid *);
 extern int v9fs_set_create_acl(struct inode *, struct p9_fid *,
 			       struct posix_acl *, struct posix_acl *);

fs/bad_inode.c

@@ -121,7 +121,7 @@ static const char *bad_inode_get_link(struct dentry *dentry,
 	return ERR_PTR(-EIO);
 }
 
-static struct posix_acl *bad_inode_get_acl(struct inode *inode, int type)
+static struct posix_acl *bad_inode_get_acl(struct inode *inode, int type, bool rcu)
 {
 	return ERR_PTR(-EIO);
 }

fs/btrfs/acl.c

@@ -16,13 +16,16 @@
 #include "btrfs_inode.h"
 #include "xattr.h"
 
-struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
+struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu)
 {
 	int size;
 	const char *name;
 	char *value = NULL;
 	struct posix_acl *acl;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name = XATTR_NAME_POSIX_ACL_ACCESS;

fs/btrfs/ctree.h

@@ -3706,7 +3706,7 @@ static inline int __btrfs_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag)
 
 /* acl.c */
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
-struct posix_acl *btrfs_get_acl(struct inode *inode, int type);
+struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu);
 int btrfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		  struct posix_acl *acl, int type);
 int btrfs_init_acl(struct btrfs_trans_handle *trans,

fs/ceph/acl.c

@@ -29,7 +29,7 @@ static inline void ceph_set_cached_acl(struct inode *inode,
 	spin_unlock(&ci->i_ceph_lock);
 }
 
-struct posix_acl *ceph_get_acl(struct inode *inode, int type)
+struct posix_acl *ceph_get_acl(struct inode *inode, int type, bool rcu)
 {
 	int size;
 	unsigned int retry_cnt = 0;
@@ -37,6 +37,9 @@ struct posix_acl *ceph_get_acl(struct inode *inode, int type)
 	char *value = NULL;
 	struct posix_acl *acl;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name = XATTR_NAME_POSIX_ACL_ACCESS;

fs/ceph/super.h

@@ -1088,7 +1088,7 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx);
 /* acl.c */
 #ifdef CONFIG_CEPH_FS_POSIX_ACL
 
-struct posix_acl *ceph_get_acl(struct inode *, int);
+struct posix_acl *ceph_get_acl(struct inode *, int, bool);
 int ceph_set_acl(struct user_namespace *mnt_userns,
 		 struct inode *inode, struct posix_acl *acl, int type);
 int ceph_pre_init_acls(struct inode *dir, umode_t *mode,

fs/erofs/Kconfig

@@ -3,6 +3,7 @@
 config EROFS_FS
 	tristate "EROFS filesystem support"
 	depends on BLOCK
+	select FS_IOMAP
 	select LIBCRC32C
 	help
 	  EROFS (Enhanced Read-Only File System) is a lightweight

fs/erofs/data.c

@@ -2,35 +2,13 @@
 /*
  * Copyright (C) 2017-2018 HUAWEI, Inc.
  *             https://www.huawei.com/
+ * Copyright (C) 2021, Alibaba Cloud
  */
 #include "internal.h"
 #include <linux/prefetch.h>
-
+#include <linux/dax.h>
 #include <trace/events/erofs.h>
 
-static void erofs_readendio(struct bio *bio)
-{
-	struct bio_vec *bvec;
-	blk_status_t err = bio->bi_status;
-	struct bvec_iter_all iter_all;
-
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
-
-		/* page is already locked */
-		DBG_BUGON(PageUptodate(page));
-
-		if (err)
-			SetPageError(page);
-		else
-			SetPageUptodate(page);
-
-		unlock_page(page);
-		/* page could be reclaimed now */
-	}
-	bio_put(bio);
-}
-
 struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr)
 {
 	struct address_space *const mapping = sb->s_bdev->bd_inode->i_mapping;
@@ -59,13 +37,6 @@ static int erofs_map_blocks_flatmode(struct inode *inode,
 	nblocks = DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
 	lastblk = nblocks - tailendpacking;
 
-	if (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;
 
@@ -100,217 +71,273 @@ static int erofs_map_blocks_flatmode(struct inode *inode,
 		goto err_out;
 	}
 
-out:
 	map->m_llen = map->m_plen;
-
 err_out:
 	trace_erofs_map_blocks_flatmode_exit(inode, map, flags, 0);
 	return err;
 }
 
-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,
-					      unsigned int *eblks,
-					      bool ra)
+static int erofs_map_blocks(struct inode *inode,
+			    struct erofs_map_blocks *map, int flags)
 {
-	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;
+	struct super_block *sb = inode->i_sb;
+	struct erofs_inode *vi = EROFS_I(inode);
+	struct erofs_inode_chunk_index *idx;
+	struct page *page;
+	u64 chunknr;
+	unsigned int unit;
+	erofs_off_t pos;
+	int err = 0;
 
-	DBG_BUGON(!nblocks);
-
-	if (PageUptodate(page)) {
-		err = 0;
-		goto has_updated;
+	if (map->m_la >= inode->i_size) {
+		/* leave out-of-bound access unmapped */
+		map->m_flags = 0;
+		map->m_plen = 0;
+		goto out;
 	}
 
-	/* note that for readpage case, bio also equals to NULL */
-	if (bio &&
-	    (*last_block + 1 != current_block || !*eblks)) {
-submit_bio_retry:
-		submit_bio(bio);
-		bio = NULL;
-	}
+	if (vi->datalayout != EROFS_INODE_CHUNK_BASED)
+		return erofs_map_blocks_flatmode(inode, map, flags);
 
-	if (!bio) {
-		struct erofs_map_blocks map = {
-			.m_la = blknr_to_addr(current_block),
-		};
-		erofs_blk_t blknr;
-		unsigned int blkoff;
+	if (vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES)
+		unit = sizeof(*idx);			/* chunk index */
+	else
+		unit = EROFS_BLOCK_MAP_ENTRY_SIZE;	/* block map */
 
-		err = erofs_map_blocks_flatmode(inode, &map, EROFS_GET_BLOCKS_RAW);
-		if (err)
-			goto err_out;
+	chunknr = map->m_la >> vi->chunkbits;
+	pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize +
+		    vi->xattr_isize, unit) + unit * chunknr;
 
-		/* zero out the holed page */
-		if (!(map.m_flags & EROFS_MAP_MAPPED)) {
-			zero_user_segment(page, 0, PAGE_SIZE);
-			SetPageUptodate(page);
+	page = erofs_get_meta_page(inode->i_sb, erofs_blknr(pos));
+	if (IS_ERR(page))
+		return PTR_ERR(page);
 
-			/* imply err = 0, see erofs_map_blocks */
-			goto has_updated;
+	map->m_la = chunknr << vi->chunkbits;
+	map->m_plen = min_t(erofs_off_t, 1UL << vi->chunkbits,
+			    roundup(inode->i_size - map->m_la, EROFS_BLKSIZ));
+
+	/* handle block map */
+	if (!(vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES)) {
+		__le32 *blkaddr = page_address(page) + erofs_blkoff(pos);
+
+		if (le32_to_cpu(*blkaddr) == EROFS_NULL_ADDR) {
+			map->m_flags = 0;
+		} else {
+			map->m_pa = blknr_to_addr(le32_to_cpu(*blkaddr));
+			map->m_flags = EROFS_MAP_MAPPED;
 		}
-
-		/* 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);
-
-			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;
+		goto out_unlock;
+	}
+	/* parse chunk indexes */
+	idx = page_address(page) + erofs_blkoff(pos);
+	switch (le32_to_cpu(idx->blkaddr)) {
+	case EROFS_NULL_ADDR:
+		map->m_flags = 0;
+		break;
+	default:
+		/* only one device is supported for now */
+		if (idx->device_id) {
+			erofs_err(sb, "invalid device id %u @ %llu for nid %llu",
+				  le16_to_cpu(idx->device_id),
+				  chunknr, vi->nid);
+			err = -EFSCORRUPTED;
+			goto out_unlock;
 		}
-
-		/* 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);
-
-		*eblks = bio_max_segs(nblocks);
-		bio = bio_alloc(GFP_NOIO, *eblks);
-
-		bio->bi_end_io = erofs_readendio;
-		bio_set_dev(bio, sb->s_bdev);
-		bio->bi_iter.bi_sector = (sector_t)blknr <<
-			LOG_SECTORS_PER_BLOCK;
-		bio->bi_opf = REQ_OP_READ | (ra ? REQ_RAHEAD : 0);
+		map->m_pa = blknr_to_addr(le32_to_cpu(idx->blkaddr));
+		map->m_flags = EROFS_MAP_MAPPED;
+		break;
 	}
-
-	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;
-	--*eblks;
-	*last_block = current_block;
-	return bio;
-
-err_out:
-	/* for sync reading, set page error immediately */
-	if (!ra) {
-		SetPageError(page);
-		ClearPageUptodate(page);
-	}
-has_updated:
+out_unlock:
 	unlock_page(page);
+	put_page(page);
+out:
+	map->m_llen = map->m_plen;
+	return err;
+}
 
-	/* if updated manually, continuous pages has a gap */
-	if (bio)
-		submit_bio(bio);
-	return err ? ERR_PTR(err) : NULL;
+static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+		unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
+{
+	int ret;
+	struct erofs_map_blocks map;
+
+	map.m_la = offset;
+	map.m_llen = length;
+
+	ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
+	if (ret < 0)
+		return ret;
+
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->dax_dev = EROFS_I_SB(inode)->dax_dev;
+	iomap->offset = map.m_la;
+	iomap->length = map.m_llen;
+	iomap->flags = 0;
+	iomap->private = NULL;
+
+	if (!(map.m_flags & EROFS_MAP_MAPPED)) {
+		iomap->type = IOMAP_HOLE;
+		iomap->addr = IOMAP_NULL_ADDR;
+		if (!iomap->length)
+			iomap->length = length;
+		return 0;
+	}
+
+	if (map.m_flags & EROFS_MAP_META) {
+		struct page *ipage;
+
+		iomap->type = IOMAP_INLINE;
+		ipage = erofs_get_meta_page(inode->i_sb,
+					    erofs_blknr(map.m_pa));
+		if (IS_ERR(ipage))
+			return PTR_ERR(ipage);
+		iomap->inline_data = page_address(ipage) +
+					erofs_blkoff(map.m_pa);
+		iomap->private = ipage;
+	} else {
+		iomap->type = IOMAP_MAPPED;
+		iomap->addr = map.m_pa;
+	}
+	return 0;
+}
+
+static int erofs_iomap_end(struct inode *inode, loff_t pos, loff_t length,
+		ssize_t written, unsigned int flags, struct iomap *iomap)
+{
+	struct page *ipage = iomap->private;
+
+	if (ipage) {
+		DBG_BUGON(iomap->type != IOMAP_INLINE);
+		unlock_page(ipage);
+		put_page(ipage);
+	} else {
+		DBG_BUGON(iomap->type == IOMAP_INLINE);
+	}
+	return written;
+}
+
+static const struct iomap_ops erofs_iomap_ops = {
+	.iomap_begin = erofs_iomap_begin,
+	.iomap_end = erofs_iomap_end,
+};
+
+int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		 u64 start, u64 len)
+{
+	if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout)) {
+#ifdef CONFIG_EROFS_FS_ZIP
+		return iomap_fiemap(inode, fieinfo, start, len,
+				    &z_erofs_iomap_report_ops);
+#else
+		return -EOPNOTSUPP;
+#endif
+	}
+	return iomap_fiemap(inode, fieinfo, start, len, &erofs_iomap_ops);
 }
 
 /*
  * 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)
+static int erofs_readpage(struct file *file, struct page *page)
 {
-	erofs_off_t last_block;
-	unsigned int eblks;
-	struct bio *bio;
-
-	trace_erofs_readpage(page, true);
-
-	bio = erofs_read_raw_page(NULL, page->mapping,
-				  page, &last_block, 1, &eblks, false);
-
-	if (IS_ERR(bio))
-		return PTR_ERR(bio);
-
-	if (bio)
-		submit_bio(bio);
-	return 0;
+	return iomap_readpage(page, &erofs_iomap_ops);
 }
 
-static void erofs_raw_access_readahead(struct readahead_control *rac)
+static void erofs_readahead(struct readahead_control *rac)
 {
-	erofs_off_t last_block;
-	unsigned int eblks;
-	struct bio *bio = NULL;
-	struct page *page;
-
-	trace_erofs_readpages(rac->mapping->host, readahead_index(rac),
-			readahead_count(rac), true);
-
-	while ((page = readahead_page(rac))) {
-		prefetchw(&page->flags);
-
-		bio = erofs_read_raw_page(bio, rac->mapping, page, &last_block,
-				readahead_count(rac), &eblks, 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_I(rac->mapping->host)->nid);
-
-			bio = NULL;
-		}
-
-		put_page(page);
-	}
-
-	if (bio)
-		submit_bio(bio);
+	return iomap_readahead(rac, &erofs_iomap_ops);
 }
 
 static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
 {
-	struct inode *inode = mapping->host;
-	struct erofs_map_blocks map = {
-		.m_la = blknr_to_addr(block),
-	};
+	return iomap_bmap(mapping, block, &erofs_iomap_ops);
+}
 
-	if (EROFS_I(inode)->datalayout == EROFS_INODE_FLAT_INLINE) {
-		erofs_blk_t blks = i_size_read(inode) >> LOG_BLOCK_SIZE;
+static int erofs_prepare_dio(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	loff_t align = iocb->ki_pos | iov_iter_count(to) |
+		iov_iter_alignment(to);
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	unsigned int blksize_mask;
 
-		if (block >> LOG_SECTORS_PER_BLOCK >= blks)
-			return 0;
-	}
-
-	if (!erofs_map_blocks_flatmode(inode, &map, EROFS_GET_BLOCKS_RAW))
-		return erofs_blknr(map.m_pa);
+	if (bdev)
+		blksize_mask = (1 << ilog2(bdev_logical_block_size(bdev))) - 1;
+	else
+		blksize_mask = (1 << inode->i_blkbits) - 1;
 
+	if (align & blksize_mask)
+		return -EINVAL;
 	return 0;
 }
 
+static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	/* no need taking (shared) inode lock since it's a ro filesystem */
+	if (!iov_iter_count(to))
+		return 0;
+
+#ifdef CONFIG_FS_DAX
+	if (IS_DAX(iocb->ki_filp->f_mapping->host))
+		return dax_iomap_rw(iocb, to, &erofs_iomap_ops);
+#endif
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		int err = erofs_prepare_dio(iocb, to);
+
+		if (!err)
+			return iomap_dio_rw(iocb, to, &erofs_iomap_ops,
+					    NULL, 0);
+		if (err < 0)
+			return err;
+	}
+	return filemap_read(iocb, to, 0);
+}
+
 /* for uncompressed (aligned) files and raw access for other files */
 const struct address_space_operations erofs_raw_access_aops = {
-	.readpage = erofs_raw_access_readpage,
-	.readahead = erofs_raw_access_readahead,
+	.readpage = erofs_readpage,
+	.readahead = erofs_readahead,
 	.bmap = erofs_bmap,
+	.direct_IO = noop_direct_IO,
+};
+
+#ifdef CONFIG_FS_DAX
+static vm_fault_t erofs_dax_huge_fault(struct vm_fault *vmf,
+		enum page_entry_size pe_size)
+{
+	return dax_iomap_fault(vmf, pe_size, NULL, NULL, &erofs_iomap_ops);
+}
+
+static vm_fault_t erofs_dax_fault(struct vm_fault *vmf)
+{
+	return erofs_dax_huge_fault(vmf, PE_SIZE_PTE);
+}
+
+static const struct vm_operations_struct erofs_dax_vm_ops = {
+	.fault		= erofs_dax_fault,
+	.huge_fault	= erofs_dax_huge_fault,
+};
+
+static int erofs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!IS_DAX(file_inode(file)))
+		return generic_file_readonly_mmap(file, vma);
+
+	if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
+		return -EINVAL;
+
+	vma->vm_ops = &erofs_dax_vm_ops;
+	vma->vm_flags |= VM_HUGEPAGE;
+	return 0;
+}
+#else
+#define erofs_file_mmap	generic_file_readonly_mmap
+#endif
+
+const struct file_operations erofs_file_fops = {
+	.llseek		= generic_file_llseek,
+	.read_iter	= erofs_file_read_iter,
+	.mmap		= erofs_file_mmap,
+	.splice_read	= generic_file_splice_read,
 };

fs/erofs/erofs_fs.h

@@ -4,6 +4,7 @@
  *
  * Copyright (C) 2017-2018 HUAWEI, Inc.
  *             https://www.huawei.com/
+ * Copyright (C) 2021, Alibaba Cloud
  */
 #ifndef __EROFS_FS_H
 #define __EROFS_FS_H
@@ -19,10 +20,12 @@
 #define EROFS_FEATURE_INCOMPAT_LZ4_0PADDING	0x00000001
 #define EROFS_FEATURE_INCOMPAT_COMPR_CFGS	0x00000002
 #define EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER	0x00000002
+#define EROFS_FEATURE_INCOMPAT_CHUNKED_FILE	0x00000004
 #define EROFS_ALL_FEATURE_INCOMPAT		\
 	(EROFS_FEATURE_INCOMPAT_LZ4_0PADDING | \
 	 EROFS_FEATURE_INCOMPAT_COMPR_CFGS | \
-	 EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER)
+	 EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER | \
+	 EROFS_FEATURE_INCOMPAT_CHUNKED_FILE)
 
 #define EROFS_SB_EXTSLOT_SIZE	16
 
@@ -64,13 +67,16 @@ struct erofs_super_block {
  * inode, [xattrs], last_inline_data, ... | ... | no-holed data
  * 3 - inode compression D:
  * inode, [xattrs], map_header, extents ... | ...
- * 4~7 - reserved
+ * 4 - inode chunk-based E:
+ * inode, [xattrs], chunk indexes ... | ...
+ * 5~7 - reserved
  */
 enum {
 	EROFS_INODE_FLAT_PLAIN			= 0,
 	EROFS_INODE_FLAT_COMPRESSION_LEGACY	= 1,
 	EROFS_INODE_FLAT_INLINE			= 2,
 	EROFS_INODE_FLAT_COMPRESSION		= 3,
+	EROFS_INODE_CHUNK_BASED			= 4,
 	EROFS_INODE_DATALAYOUT_MAX
 };
 
@@ -90,6 +96,19 @@ static inline bool erofs_inode_is_data_compressed(unsigned int datamode)
 #define EROFS_I_ALL	\
 	((1 << (EROFS_I_DATALAYOUT_BIT + EROFS_I_DATALAYOUT_BITS)) - 1)
 
+/* indicate chunk blkbits, thus 'chunksize = blocksize << chunk blkbits' */
+#define EROFS_CHUNK_FORMAT_BLKBITS_MASK		0x001F
+/* with chunk indexes or just a 4-byte blkaddr array */
+#define EROFS_CHUNK_FORMAT_INDEXES		0x0020
+
+#define EROFS_CHUNK_FORMAT_ALL	\
+	(EROFS_CHUNK_FORMAT_BLKBITS_MASK | EROFS_CHUNK_FORMAT_INDEXES)
+
+struct erofs_inode_chunk_info {
+	__le16 format;		/* chunk blkbits, etc. */
+	__le16 reserved;
+};
+
 /* 32-byte reduced form of an ondisk inode */
 struct erofs_inode_compact {
 	__le16 i_format;	/* inode format hints */
@@ -107,6 +126,9 @@ struct erofs_inode_compact {
 
 		/* for device files, used to indicate old/new device # */
 		__le32 rdev;
+
+		/* for chunk-based files, it contains the summary info */
+		struct erofs_inode_chunk_info c;
 	} i_u;
 	__le32 i_ino;           /* only used for 32-bit stat compatibility */
 	__le16 i_uid;
@@ -135,6 +157,9 @@ struct erofs_inode_extended {
 
 		/* for device files, used to indicate old/new device # */
 		__le32 rdev;
+
+		/* for chunk-based files, it contains the summary info */
+		struct erofs_inode_chunk_info c;
 	} i_u;
 
 	/* only used for 32-bit stat compatibility */
@@ -204,6 +229,19 @@ static inline unsigned int erofs_xattr_entry_size(struct erofs_xattr_entry *e)
 				 e->e_name_len + le16_to_cpu(e->e_value_size));
 }
 
+/* represent a zeroed chunk (hole) */
+#define EROFS_NULL_ADDR			-1
+
+/* 4-byte block address array */
+#define EROFS_BLOCK_MAP_ENTRY_SIZE	sizeof(__le32)
+
+/* 8-byte inode chunk indexes */
+struct erofs_inode_chunk_index {
+	__le16 advise;		/* always 0, don't care for now */
+	__le16 device_id;	/* back-end storage id, always 0 for now */
+	__le32 blkaddr;		/* start block address of this inode chunk */
+};
+
 /* maximum supported size of a physical compression cluster */
 #define Z_EROFS_PCLUSTER_MAX_SIZE	(1024 * 1024)
 
@@ -338,9 +376,14 @@ static inline void erofs_check_ondisk_layout_definitions(void)
 	BUILD_BUG_ON(sizeof(struct erofs_inode_extended) != 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 erofs_inode_chunk_info) != 4);
+	BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_index) != 8);
 	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);
+	/* keep in sync between 2 index structures for better extendibility */
+	BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_index) !=
+		     sizeof(struct z_erofs_vle_decompressed_index));
 
 	BUILD_BUG_ON(BIT(Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS) <
 		     Z_EROFS_VLE_CLUSTER_TYPE_MAX - 1);

fs/erofs/inode.c

@@ -2,6 +2,7 @@
 /*
  * Copyright (C) 2017-2018 HUAWEI, Inc.
  *             https://www.huawei.com/
+ * Copyright (C) 2021, Alibaba Cloud
  */
 #include "xattr.h"
 
@@ -122,8 +123,11 @@ static struct page *erofs_read_inode(struct inode *inode,
 		/* total blocks for compressed files */
 		if (erofs_inode_is_data_compressed(vi->datalayout))
 			nblks = le32_to_cpu(die->i_u.compressed_blocks);
-
+		else if (vi->datalayout == EROFS_INODE_CHUNK_BASED)
+			/* fill chunked inode summary info */
+			vi->chunkformat = le16_to_cpu(die->i_u.c.format);
 		kfree(copied);
+		copied = NULL;
 		break;
 	case EROFS_INODE_LAYOUT_COMPACT:
 		vi->inode_isize = sizeof(struct erofs_inode_compact);
@@ -160,6 +164,8 @@ static struct page *erofs_read_inode(struct inode *inode,
 		inode->i_size = le32_to_cpu(dic->i_size);
 		if (erofs_inode_is_data_compressed(vi->datalayout))
 			nblks = le32_to_cpu(dic->i_u.compressed_blocks);
+		else if (vi->datalayout == EROFS_INODE_CHUNK_BASED)
+			vi->chunkformat = le16_to_cpu(dic->i_u.c.format);
 		break;
 	default:
 		erofs_err(inode->i_sb,
@@ -169,11 +175,26 @@ static struct page *erofs_read_inode(struct inode *inode,
 		goto err_out;
 	}
 
+	if (vi->datalayout == EROFS_INODE_CHUNK_BASED) {
+		if (!(vi->chunkformat & EROFS_CHUNK_FORMAT_ALL)) {
+			erofs_err(inode->i_sb,
+				  "unsupported chunk format %x of nid %llu",
+				  vi->chunkformat, vi->nid);
+			err = -EOPNOTSUPP;
+			goto err_out;
+		}
+		vi->chunkbits = LOG_BLOCK_SIZE +
+			(vi->chunkformat & EROFS_CHUNK_FORMAT_BLKBITS_MASK);
+	}
 	inode->i_mtime.tv_sec = inode->i_ctime.tv_sec;
 	inode->i_atime.tv_sec = inode->i_ctime.tv_sec;
 	inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec;
 	inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec;
 
+	inode->i_flags &= ~S_DAX;
+	if (test_opt(&sbi->ctx, DAX_ALWAYS) && S_ISREG(inode->i_mode) &&
+	    vi->datalayout == EROFS_INODE_FLAT_PLAIN)
+		inode->i_flags |= S_DAX;
 	if (!nblks)
 		/* measure inode.i_blocks as generic filesystems */
 		inode->i_blocks = roundup(inode->i_size, EROFS_BLKSIZ) >> 9;
@@ -247,7 +268,10 @@ static int erofs_fill_inode(struct inode *inode, int isdir)
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
 		inode->i_op = &erofs_generic_iops;
-		inode->i_fop = &generic_ro_fops;
+		if (erofs_inode_is_data_compressed(vi->datalayout))
+			inode->i_fop = &generic_ro_fops;
+		else
+			inode->i_fop = &erofs_file_fops;
 		break;
 	case S_IFDIR:
 		inode->i_op = &erofs_dir_iops;
@@ -358,6 +382,7 @@ const struct inode_operations erofs_generic_iops = {
 	.getattr = erofs_getattr,
 	.listxattr = erofs_listxattr,
 	.get_acl = erofs_get_acl,
+	.fiemap = erofs_fiemap,
 };
 
 const struct inode_operations erofs_symlink_iops = {

fs/erofs/internal.h

@@ -2,6 +2,7 @@
 /*
  * Copyright (C) 2017-2018 HUAWEI, Inc.
  *             https://www.huawei.com/
+ * Copyright (C) 2021, Alibaba Cloud
  */
 #ifndef __EROFS_INTERNAL_H
 #define __EROFS_INTERNAL_H
@@ -15,6 +16,7 @@
 #include <linux/magic.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/iomap.h>
 #include "erofs_fs.h"
 
 /* redefine pr_fmt "erofs: " */
@@ -83,6 +85,7 @@ struct erofs_sb_info {
 
 	struct erofs_sb_lz4_info lz4;
 #endif	/* CONFIG_EROFS_FS_ZIP */
+	struct dax_device *dax_dev;
 	u32 blocks;
 	u32 meta_blkaddr;
 #ifdef CONFIG_EROFS_FS_XATTR
@@ -115,6 +118,8 @@ struct erofs_sb_info {
 /* Mount flags set via mount options or defaults */
 #define EROFS_MOUNT_XATTR_USER		0x00000010
 #define EROFS_MOUNT_POSIX_ACL		0x00000020
+#define EROFS_MOUNT_DAX_ALWAYS		0x00000040
+#define EROFS_MOUNT_DAX_NEVER		0x00000080
 
 #define clear_opt(ctx, option)	((ctx)->mount_opt &= ~EROFS_MOUNT_##option)
 #define set_opt(ctx, option)	((ctx)->mount_opt |= EROFS_MOUNT_##option)
@@ -257,6 +262,10 @@ struct erofs_inode {
 
 	union {
 		erofs_blk_t raw_blkaddr;
+		struct {
+			unsigned short	chunkformat;
+			unsigned char	chunkbits;
+		};
 #ifdef CONFIG_EROFS_FS_ZIP
 		struct {
 			unsigned short z_advise;
@@ -353,8 +362,15 @@ struct erofs_map_blocks {
 
 /* Flags used by erofs_map_blocks_flatmode() */
 #define EROFS_GET_BLOCKS_RAW    0x0001
+/*
+ * Used to get the exact decompressed length, e.g. fiemap (consider lookback
+ * approach instead if possible since it's more metadata lightweight.)
+ */
+#define EROFS_GET_BLOCKS_FIEMAP	0x0002
 
 /* zmap.c */
+extern const struct iomap_ops z_erofs_iomap_report_ops;
+
 #ifdef CONFIG_EROFS_FS_ZIP
 int z_erofs_fill_inode(struct inode *inode);
 int z_erofs_map_blocks_iter(struct inode *inode,
@@ -371,7 +387,10 @@ static inline int z_erofs_map_blocks_iter(struct inode *inode,
 #endif	/* !CONFIG_EROFS_FS_ZIP */
 
 /* data.c */
+extern const struct file_operations erofs_file_fops;
 struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr);
+int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		 u64 start, u64 len);
 
 /* inode.c */
 static inline unsigned long erofs_inode_hash(erofs_nid_t nid)
@@ -441,8 +460,7 @@ 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);
+int erofs_try_to_free_cached_page(struct page *page);
 int z_erofs_load_lz4_config(struct super_block *sb,
 			    struct erofs_super_block *dsb,
 			    struct z_erofs_lz4_cfgs *lz4, int len);

fs/erofs/namei.c

@@ -245,4 +245,5 @@ const struct inode_operations erofs_dir_iops = {
 	.getattr = erofs_getattr,
 	.listxattr = erofs_listxattr,
 	.get_acl = erofs_get_acl,
+	.fiemap = erofs_fiemap,
 };

fs/erofs/super.c

@@ -11,6 +11,7 @@
 #include <linux/crc32c.h>
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
+#include <linux/dax.h>
 #include "xattr.h"
 
 #define CREATE_TRACE_POINTS
@@ -355,6 +356,8 @@ enum {
 	Opt_user_xattr,
 	Opt_acl,
 	Opt_cache_strategy,
+	Opt_dax,
+	Opt_dax_enum,
 	Opt_err
 };
 
@@ -365,14 +368,47 @@ static const struct constant_table erofs_param_cache_strategy[] = {
 	{}
 };
 
+static const struct constant_table erofs_dax_param_enums[] = {
+	{"always",	EROFS_MOUNT_DAX_ALWAYS},
+	{"never",	EROFS_MOUNT_DAX_NEVER},
+	{}
+};
+
 static const struct fs_parameter_spec erofs_fs_parameters[] = {
 	fsparam_flag_no("user_xattr",	Opt_user_xattr),
 	fsparam_flag_no("acl",		Opt_acl),
 	fsparam_enum("cache_strategy",	Opt_cache_strategy,
 		     erofs_param_cache_strategy),
+	fsparam_flag("dax",             Opt_dax),
+	fsparam_enum("dax",		Opt_dax_enum, erofs_dax_param_enums),
 	{}
 };
 
+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;
+
+	switch (mode) {
+	case EROFS_MOUNT_DAX_ALWAYS:
+		warnfc(fc, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+		set_opt(ctx, DAX_ALWAYS);
+		clear_opt(ctx, DAX_NEVER);
+		return true;
+	case EROFS_MOUNT_DAX_NEVER:
+		set_opt(ctx, DAX_NEVER);
+		clear_opt(ctx, DAX_ALWAYS);
+		return true;
+	default:
+		DBG_BUGON(1);
+		return false;
+	}
+#else
+	errorfc(fc, "dax options not supported");
+	return false;
+#endif
+}
+
 static int erofs_fc_parse_param(struct fs_context *fc,
 				struct fs_parameter *param)
 {
@@ -412,6 +448,14 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 		errorfc(fc, "compression not supported, cache_strategy ignored");
 #endif
 		break;
+	case Opt_dax:
+		if (!erofs_fc_set_dax_mode(fc, EROFS_MOUNT_DAX_ALWAYS))
+			return -EINVAL;
+		break;
+	case Opt_dax_enum:
+		if (!erofs_fc_set_dax_mode(fc, result.uint_32))
+			return -EINVAL;
+		break;
 	default:
 		return -ENOPARAM;
 	}
@@ -430,7 +474,7 @@ static int erofs_managed_cache_releasepage(struct page *page, gfp_t gfp_mask)
 	DBG_BUGON(mapping->a_ops != &managed_cache_aops);
 
 	if (PagePrivate(page))
-		ret = erofs_try_to_free_cached_page(mapping, page);
+		ret = erofs_try_to_free_cached_page(page);
 
 	return ret;
 }
@@ -496,10 +540,16 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 		return -ENOMEM;
 
 	sb->s_fs_info = sbi;
+	sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
 	err = erofs_read_superblock(sb);
 	if (err)
 		return err;
 
+	if (test_opt(ctx, DAX_ALWAYS) &&
+	    !bdev_dax_supported(sb->s_bdev, EROFS_BLKSIZ)) {
+		errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
+		clear_opt(ctx, DAX_ALWAYS);
+	}
 	sb->s_flags |= SB_RDONLY | SB_NOATIME;
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_time_gran = 1;
@@ -609,6 +659,7 @@ static void erofs_kill_sb(struct super_block *sb)
 	sbi = EROFS_SB(sb);
 	if (!sbi)
 		return;
+	fs_put_dax(sbi->dax_dev);
 	kfree(sbi);
 	sb->s_fs_info = NULL;
 }
@@ -711,8 +762,8 @@ static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 static int erofs_show_options(struct seq_file *seq, struct dentry *root)
 {
-	struct erofs_sb_info *sbi __maybe_unused = EROFS_SB(root->d_sb);
-	struct erofs_fs_context *ctx __maybe_unused = &sbi->ctx;
+	struct erofs_sb_info *sbi = EROFS_SB(root->d_sb);
+	struct erofs_fs_context *ctx = &sbi->ctx;
 
 #ifdef CONFIG_EROFS_FS_XATTR
 	if (test_opt(ctx, XATTR_USER))
@@ -734,6 +785,10 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root)
 	else if (ctx->cache_strategy == EROFS_ZIP_CACHE_READAROUND)
 		seq_puts(seq, ",cache_strategy=readaround");
 #endif
+	if (test_opt(ctx, DAX_ALWAYS))
+		seq_puts(seq, ",dax=always");
+	if (test_opt(ctx, DAX_NEVER))
+		seq_puts(seq, ",dax=never");
 	return 0;
 }
 

fs/erofs/xattr.c

@@ -673,12 +673,15 @@ ssize_t erofs_listxattr(struct dentry *dentry,
 }
 
 #ifdef CONFIG_EROFS_FS_POSIX_ACL
-struct posix_acl *erofs_get_acl(struct inode *inode, int type)
+struct posix_acl *erofs_get_acl(struct inode *inode, int type, bool rcu)
 {
 	struct posix_acl *acl;
 	int prefix, rc;
 	char *value = NULL;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		prefix = EROFS_XATTR_INDEX_POSIX_ACL_ACCESS;

fs/erofs/xattr.h

@@ -80,7 +80,7 @@ static inline int erofs_getxattr(struct inode *inode, int index,
 #endif	/* !CONFIG_EROFS_FS_XATTR */
 
 #ifdef CONFIG_EROFS_FS_POSIX_ACL
-struct posix_acl *erofs_get_acl(struct inode *inode, int type);
+struct posix_acl *erofs_get_acl(struct inode *inode, int type, bool rcu);
 #else
 #define erofs_get_acl	(NULL)
 #endif

fs/erofs/zdata.c

@@ -309,7 +309,6 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
 {
 	struct z_erofs_pcluster *const pcl =
 		container_of(grp, struct z_erofs_pcluster, obj);
-	struct address_space *const mapping = MNGD_MAPPING(sbi);
 	int i;
 
 	/*
@@ -326,7 +325,7 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
 		if (!trylock_page(page))
 			return -EBUSY;
 
-		if (page->mapping != mapping)
+		if (!erofs_page_is_managed(sbi, page))
 			continue;
 
 		/* barrier is implied in the following 'unlock_page' */
@@ -337,8 +336,7 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
 	return 0;
 }
 
-int erofs_try_to_free_cached_page(struct address_space *mapping,
-				  struct page *page)
+int erofs_try_to_free_cached_page(struct page *page)
 {
 	struct z_erofs_pcluster *const pcl = (void *)page_private(page);
 	int ret = 0;	/* 0 - busy */

fs/erofs/zmap.c

@@ -212,9 +212,34 @@ static unsigned int decode_compactedbits(unsigned int lobits,
 	return lo;
 }
 
+static int get_compacted_la_distance(unsigned int lclusterbits,
+				     unsigned int encodebits,
+				     unsigned int vcnt, u8 *in, int i)
+{
+	const unsigned int lomask = (1 << lclusterbits) - 1;
+	unsigned int lo, d1 = 0;
+	u8 type;
+
+	DBG_BUGON(i >= vcnt);
+
+	do {
+		lo = decode_compactedbits(lclusterbits, lomask,
+					  in, encodebits * i, &type);
+
+		if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
+			return d1;
+		++d1;
+	} while (++i < vcnt);
+
+	/* vcnt - 1 (Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) item */
+	if (!(lo & Z_EROFS_VLE_DI_D0_CBLKCNT))
+		d1 += lo - 1;
+	return d1;
+}
+
 static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 				  unsigned int amortizedshift,
-				  unsigned int eofs)
+				  unsigned int eofs, bool lookahead)
 {
 	struct erofs_inode *const vi = EROFS_I(m->inode);
 	const unsigned int lclusterbits = vi->z_logical_clusterbits;
@@ -243,6 +268,11 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 	m->type = type;
 	if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
 		m->clusterofs = 1 << lclusterbits;
+
+		/* figure out lookahead_distance: delta[1] if needed */
+		if (lookahead)
+			m->delta[1] = get_compacted_la_distance(lclusterbits,
+						encodebits, vcnt, in, i);
 		if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) {
 			if (!big_pcluster) {
 				DBG_BUGON(1);
@@ -313,7 +343,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 }
 
 static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m,
-					    unsigned long lcn)
+					    unsigned long lcn, bool lookahead)
 {
 	struct inode *const inode = m->inode;
 	struct erofs_inode *const vi = EROFS_I(inode);
@@ -364,11 +394,12 @@ out:
 	err = z_erofs_reload_indexes(m, erofs_blknr(pos));
 	if (err)
 		return err;
-	return unpack_compacted_index(m, amortizedshift, erofs_blkoff(pos));
+	return unpack_compacted_index(m, amortizedshift, erofs_blkoff(pos),
+				      lookahead);
 }
 
 static int z_erofs_load_cluster_from_disk(struct z_erofs_maprecorder *m,
-					  unsigned int lcn)
+					  unsigned int lcn, bool lookahead)
 {
 	const unsigned int datamode = EROFS_I(m->inode)->datalayout;
 
@@ -376,7 +407,7 @@ static int z_erofs_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 		return legacy_load_cluster_from_disk(m, lcn);
 
 	if (datamode == EROFS_INODE_FLAT_COMPRESSION)
-		return compacted_load_cluster_from_disk(m, lcn);
+		return compacted_load_cluster_from_disk(m, lcn, lookahead);
 
 	return -EINVAL;
 }
@@ -399,7 +430,7 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m,
 
 	/* load extent head logical cluster if needed */
 	lcn -= lookback_distance;
-	err = z_erofs_load_cluster_from_disk(m, lcn);
+	err = z_erofs_load_cluster_from_disk(m, lcn, false);
 	if (err)
 		return err;
 
@@ -450,7 +481,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 	if (m->compressedlcs)
 		goto out;
 
-	err = z_erofs_load_cluster_from_disk(m, lcn);
+	err = z_erofs_load_cluster_from_disk(m, lcn, false);
 	if (err)
 		return err;
 
@@ -498,6 +529,48 @@ err_bonus_cblkcnt:
 	return -EFSCORRUPTED;
 }
 
+static int z_erofs_get_extent_decompressedlen(struct z_erofs_maprecorder *m)
+{
+	struct inode *inode = m->inode;
+	struct erofs_inode *vi = EROFS_I(inode);
+	struct erofs_map_blocks *map = m->map;
+	unsigned int lclusterbits = vi->z_logical_clusterbits;
+	u64 lcn = m->lcn, headlcn = map->m_la >> lclusterbits;
+	int err;
+
+	do {
+		/* handle the last EOF pcluster (no next HEAD lcluster) */
+		if ((lcn << lclusterbits) >= inode->i_size) {
+			map->m_llen = inode->i_size - map->m_la;
+			return 0;
+		}
+
+		err = z_erofs_load_cluster_from_disk(m, lcn, true);
+		if (err)
+			return err;
+
+		if (m->type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
+			DBG_BUGON(!m->delta[1] &&
+				  m->clusterofs != 1 << lclusterbits);
+		} else if (m->type == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN ||
+			   m->type == Z_EROFS_VLE_CLUSTER_TYPE_HEAD) {
+			/* go on until the next HEAD lcluster */
+			if (lcn != headlcn)
+				break;
+			m->delta[1] = 1;
+		} else {
+			erofs_err(inode->i_sb, "unknown type %u @ lcn %llu of nid %llu",
+				  m->type, lcn, vi->nid);
+			DBG_BUGON(1);
+			return -EOPNOTSUPP;
+		}
+		lcn += m->delta[1];
+	} while (m->delta[1]);
+
+	map->m_llen = (lcn << lclusterbits) + m->clusterofs - map->m_la;
+	return 0;
+}
+
 int z_erofs_map_blocks_iter(struct inode *inode,
 			    struct erofs_map_blocks *map,
 			    int flags)
@@ -531,7 +604,7 @@ int z_erofs_map_blocks_iter(struct inode *inode,
 	initial_lcn = ofs >> lclusterbits;
 	endoff = ofs & ((1 << lclusterbits) - 1);
 
-	err = z_erofs_load_cluster_from_disk(&m, initial_lcn);
+	err = z_erofs_load_cluster_from_disk(&m, initial_lcn, false);
 	if (err)
 		goto unmap_out;
 
@@ -581,6 +654,12 @@ int z_erofs_map_blocks_iter(struct inode *inode,
 	err = z_erofs_get_extent_compressedlen(&m, initial_lcn);
 	if (err)
 		goto out;
+
+	if (flags & EROFS_GET_BLOCKS_FIEMAP) {
+		err = z_erofs_get_extent_decompressedlen(&m);
+		if (!err)
+			map->m_flags |= EROFS_MAP_FULL_MAPPED;
+	}
 unmap_out:
 	if (m.kaddr)
 		kunmap_atomic(m.kaddr);
@@ -596,3 +675,41 @@ out:
 	DBG_BUGON(err < 0 && err != -ENOMEM);
 	return err;
 }
+
+static int z_erofs_iomap_begin_report(struct inode *inode, loff_t offset,
+				loff_t length, unsigned int flags,
+				struct iomap *iomap, struct iomap *srcmap)
+{
+	int ret;
+	struct erofs_map_blocks map = { .m_la = offset };
+
+	ret = z_erofs_map_blocks_iter(inode, &map, EROFS_GET_BLOCKS_FIEMAP);
+	if (map.mpage)
+		put_page(map.mpage);
+	if (ret < 0)
+		return ret;
+
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->offset = map.m_la;
+	iomap->length = map.m_llen;
+	if (map.m_flags & EROFS_MAP_MAPPED) {
+		iomap->type = IOMAP_MAPPED;
+		iomap->addr = map.m_pa;
+	} else {
+		iomap->type = IOMAP_HOLE;
+		iomap->addr = IOMAP_NULL_ADDR;
+		/*
+		 * No strict rule how to describe extents for post EOF, yet
+		 * we need do like below. Otherwise, iomap itself will get
+		 * into an endless loop on post EOF.
+		 */
+		if (iomap->offset >= inode->i_size)
+			iomap->length = length + map.m_la - offset;
+	}
+	iomap->flags = 0;
+	return 0;
+}
+
+const struct iomap_ops z_erofs_iomap_report_ops = {
+	.iomap_begin = z_erofs_iomap_begin_report,
+};

fs/ext2/acl.c

@@ -141,13 +141,16 @@ fail:
  * inode->i_mutex: don't care
  */
 struct posix_acl *
-ext2_get_acl(struct inode *inode, int type)
+ext2_get_acl(struct inode *inode, int type, bool rcu)
 {
 	int name_index;
 	char *value = NULL;
 	struct posix_acl *acl;
 	int retval;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS;

fs/ext2/acl.h

@@ -55,7 +55,7 @@ static inline int ext2_acl_count(size_t size)
 #ifdef CONFIG_EXT2_FS_POSIX_ACL
 
 /* acl.c */
-extern struct posix_acl *ext2_get_acl(struct inode *inode, int type);
+extern struct posix_acl *ext2_get_acl(struct inode *inode, int type, bool rcu);
 extern int ext2_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 			struct posix_acl *acl, int type);
 extern int ext2_init_acl (struct inode *, struct inode *);

fs/ext4/acl.c

@@ -142,13 +142,16 @@ fail:
  * inode->i_mutex: don't care
  */
 struct posix_acl *
-ext4_get_acl(struct inode *inode, int type)
+ext4_get_acl(struct inode *inode, int type, bool rcu)
 {
 	int name_index;
 	char *value = NULL;
 	struct posix_acl *acl;
 	int retval;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;

fs/ext4/acl.h

@@ -55,7 +55,7 @@ static inline int ext4_acl_count(size_t size)
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 
 /* acl.c */
-struct posix_acl *ext4_get_acl(struct inode *inode, int type);
+struct posix_acl *ext4_get_acl(struct inode *inode, int type, bool rcu);
 int ext4_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		 struct posix_acl *acl, int type);
 extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);

fs/f2fs/acl.c

@@ -196,8 +196,11 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
 	return acl;
 }
 
-struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
+struct posix_acl *f2fs_get_acl(struct inode *inode, int type, bool rcu)
 {
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	return __f2fs_get_acl(inode, type, NULL);
 }
 

fs/f2fs/acl.h

@@ -33,7 +33,7 @@ struct f2fs_acl_header {
 
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
 
-extern struct posix_acl *f2fs_get_acl(struct inode *, int);
+extern struct posix_acl *f2fs_get_acl(struct inode *, int, bool);
 extern int f2fs_set_acl(struct user_namespace *, struct inode *,
 			struct posix_acl *, int);
 extern int f2fs_init_acl(struct inode *, struct inode *, struct page *,

fs/fuse/acl.c

@@ -11,7 +11,7 @@
 #include <linux/posix_acl.h>
 #include <linux/posix_acl_xattr.h>
 
-struct posix_acl *fuse_get_acl(struct inode *inode, int type)
+struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu)
 {
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	int size;
@@ -19,6 +19,9 @@ struct posix_acl *fuse_get_acl(struct inode *inode, int type)
 	void *value = NULL;
 	struct posix_acl *acl;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	if (fuse_is_bad(inode))
 		return ERR_PTR(-EIO);
 

fs/fuse/fuse_i.h

@@ -1233,7 +1233,7 @@ extern const struct xattr_handler *fuse_acl_xattr_handlers[];
 extern const struct xattr_handler *fuse_no_acl_xattr_handlers[];
 
 struct posix_acl;
-struct posix_acl *fuse_get_acl(struct inode *inode, int type);
+struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu);
 int fuse_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		 struct posix_acl *acl, int type);
 

fs/gfs2/acl.c

@@ -57,13 +57,16 @@ static struct posix_acl *__gfs2_get_acl(struct inode *inode, int type)
 	return acl;
 }
 
-struct posix_acl *gfs2_get_acl(struct inode *inode, int type)
+struct posix_acl *gfs2_get_acl(struct inode *inode, int type, bool rcu)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
 	bool need_unlock = false;
 	struct posix_acl *acl;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
 		int ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
 					     LM_FLAG_ANY, &gh);

fs/gfs2/acl.h

@@ -11,7 +11,7 @@
 
 #define GFS2_ACL_MAX_ENTRIES(sdp) ((300 << (sdp)->sd_sb.sb_bsize_shift) >> 12)
 
-extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type);
+extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type, bool rcu);
 extern int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type);
 extern int gfs2_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 			struct posix_acl *acl, int type);

fs/jffs2/acl.c

@@ -173,12 +173,15 @@ static void *jffs2_acl_to_medium(const struct posix_acl *acl, size_t *size)
 	return ERR_PTR(-EINVAL);
 }
 
-struct posix_acl *jffs2_get_acl(struct inode *inode, int type)
+struct posix_acl *jffs2_get_acl(struct inode *inode, int type, bool rcu)
 {
 	struct posix_acl *acl;
 	char *value = NULL;
 	int rc, xprefix;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		xprefix = JFFS2_XPREFIX_ACL_ACCESS;

fs/jffs2/acl.h

@@ -27,7 +27,7 @@ struct jffs2_acl_header {
 
 #ifdef CONFIG_JFFS2_FS_POSIX_ACL
 
-struct posix_acl *jffs2_get_acl(struct inode *inode, int type);
+struct posix_acl *jffs2_get_acl(struct inode *inode, int type, bool rcu);
 int jffs2_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		  struct posix_acl *acl, int type);
 extern int jffs2_init_acl_pre(struct inode *, struct inode *, umode_t *);

fs/jfs/acl.c

@@ -14,13 +14,16 @@
 #include "jfs_xattr.h"
 #include "jfs_acl.h"
 
-struct posix_acl *jfs_get_acl(struct inode *inode, int type)
+struct posix_acl *jfs_get_acl(struct inode *inode, int type, bool rcu)
 {
 	struct posix_acl *acl;
 	char *ea_name;
 	int size;
 	char *value = NULL;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	switch(type) {
 		case ACL_TYPE_ACCESS:
 			ea_name = XATTR_NAME_POSIX_ACL_ACCESS;

fs/jfs/jfs_acl.h

@@ -7,7 +7,7 @@
 
 #ifdef CONFIG_JFS_POSIX_ACL
 
-struct posix_acl *jfs_get_acl(struct inode *inode, int type);
+struct posix_acl *jfs_get_acl(struct inode *inode, int type, bool rcu);
 int jfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		struct posix_acl *acl, int type);
 int jfs_init_acl(tid_t, struct inode *, struct inode *);

fs/nfs/nfs3_fs.h

@@ -11,7 +11,7 @@
  * nfs3acl.c
  */
 #ifdef CONFIG_NFS_V3_ACL
-extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type);
+extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type, bool rcu);
 extern int nfs3_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 			struct posix_acl *acl, int type);
 extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,

fs/nfs/nfs3acl.c

@@ -44,7 +44,7 @@ static void nfs3_abort_get_acl(struct posix_acl **p)
 	cmpxchg(p, sentinel, ACL_NOT_CACHED);
 }
 
-struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
+struct posix_acl *nfs3_get_acl(struct inode *inode, int type, bool rcu)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct page *pages[NFSACL_MAXPAGES] = { };
@@ -62,6 +62,9 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
 	};
 	int status, count;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	if (!nfs_server_capable(inode, NFS_CAP_ACLS))
 		return ERR_PTR(-EOPNOTSUPP);
 

fs/ocfs2/acl.c

@@ -289,7 +289,7 @@ unlock:
 	return status;
 }
 
-struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
+struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type, bool rcu)
 {
 	struct ocfs2_super *osb;
 	struct buffer_head *di_bh = NULL;
@@ -297,6 +297,9 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
 	int had_lock;
 	struct ocfs2_lock_holder oh;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	osb = OCFS2_SB(inode->i_sb);
 	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
 		return NULL;

fs/ocfs2/acl.h

@@ -16,7 +16,7 @@ struct ocfs2_acl_entry {
 	__le32 e_id;
 };
 
-struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type);
+struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type, bool rcu);
 int ocfs2_iop_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		      struct posix_acl *acl, int type);
 extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *);

fs/orangefs/acl.c

@@ -10,12 +10,15 @@
 #include "orangefs-bufmap.h"
 #include <linux/posix_acl_xattr.h>
 
-struct posix_acl *orangefs_get_acl(struct inode *inode, int type)
+struct posix_acl *orangefs_get_acl(struct inode *inode, int type, bool rcu)
 {
 	struct posix_acl *acl;
 	int ret;
 	char *key = NULL, *value = NULL;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		key = XATTR_NAME_POSIX_ACL_ACCESS;

fs/orangefs/inode.c

@@ -882,12 +882,7 @@ int orangefs_getattr(struct user_namespace *mnt_userns, const struct path *path,
 		if (!(request_mask & STATX_SIZE))
 			stat->result_mask &= ~STATX_SIZE;
 
-		stat->attributes_mask = STATX_ATTR_IMMUTABLE |
-		    STATX_ATTR_APPEND;
-		if (inode->i_flags & S_IMMUTABLE)
-			stat->attributes |= STATX_ATTR_IMMUTABLE;
-		if (inode->i_flags & S_APPEND)
-			stat->attributes |= STATX_ATTR_APPEND;
+		generic_fill_statx_attr(inode, stat);
 	}
 	return ret;
 }

fs/orangefs/orangefs-kernel.h

@@ -106,7 +106,7 @@ enum orangefs_vfs_op_states {
 extern int orangefs_init_acl(struct inode *inode, struct inode *dir);
 extern const struct xattr_handler *orangefs_xattr_handlers[];
 
-extern struct posix_acl *orangefs_get_acl(struct inode *inode, int type);
+extern struct posix_acl *orangefs_get_acl(struct inode *inode, int type, bool rcu);
 extern int orangefs_set_acl(struct user_namespace *mnt_userns,
 			    struct inode *inode, struct posix_acl *acl,
 			    int type);

fs/overlayfs/copy_up.c

@@ -8,6 +8,7 @@
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/file.h>
+#include <linux/fileattr.h>
 #include <linux/splice.h>
 #include <linux/xattr.h>
 #include <linux/security.h>
@@ -62,7 +63,7 @@ int ovl_copy_xattr(struct super_block *sb, struct dentry *old,
 		return list_size;
 	}
 
-	buf = kzalloc(list_size, GFP_KERNEL);
+	buf = kvzalloc(list_size, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -105,11 +106,12 @@ retry:
 		if (size > value_size) {
 			void *new;
 
-			new = krealloc(value, size, GFP_KERNEL);
+			new = kvmalloc(size, GFP_KERNEL);
 			if (!new) {
 				error = -ENOMEM;
 				break;
 			}
+			kvfree(value);
 			value = new;
 			value_size = size;
 			goto retry;
@@ -124,12 +126,50 @@ retry:
 			error = 0;
 		}
 	}
-	kfree(value);
+	kvfree(value);
 out:
-	kfree(buf);
+	kvfree(buf);
 	return error;
 }
 
+static int ovl_copy_fileattr(struct inode *inode, struct path *old,
+			     struct path *new)
+{
+	struct fileattr oldfa = { .flags_valid = true };
+	struct fileattr newfa = { .flags_valid = true };
+	int err;
+
+	err = ovl_real_fileattr_get(old, &oldfa);
+	if (err)
+		return err;
+
+	err = ovl_real_fileattr_get(new, &newfa);
+	if (err)
+		return err;
+
+	/*
+	 * We cannot set immutable and append-only flags on upper inode,
+	 * because we would not be able to link upper inode to upper dir
+	 * not set overlay private xattr on upper inode.
+	 * Store these flags in overlay.protattr xattr instead.
+	 */
+	if (oldfa.flags & OVL_PROT_FS_FLAGS_MASK) {
+		err = ovl_set_protattr(inode, new->dentry, &oldfa);
+		if (err)
+			return err;
+	}
+
+	BUILD_BUG_ON(OVL_COPY_FS_FLAGS_MASK & ~FS_COMMON_FL);
+	newfa.flags &= ~OVL_COPY_FS_FLAGS_MASK;
+	newfa.flags |= (oldfa.flags & OVL_COPY_FS_FLAGS_MASK);
+
+	BUILD_BUG_ON(OVL_COPY_FSX_FLAGS_MASK & ~FS_XFLAG_COMMON);
+	newfa.fsx_xflags &= ~OVL_COPY_FSX_FLAGS_MASK;
+	newfa.fsx_xflags |= (oldfa.fsx_xflags & OVL_COPY_FSX_FLAGS_MASK);
+
+	return ovl_real_fileattr_set(new, &newfa);
+}
+
 static int ovl_copy_up_data(struct ovl_fs *ofs, struct path *old,
 			    struct path *new, loff_t len)
 {
@@ -331,8 +371,8 @@ out_err:
 	return ERR_PTR(err);
 }
 
-int ovl_set_origin(struct ovl_fs *ofs, struct dentry *dentry,
-		   struct dentry *lower, struct dentry *upper)
+int ovl_set_origin(struct ovl_fs *ofs, struct dentry *lower,
+		   struct dentry *upper)
 {
 	const struct ovl_fh *fh = NULL;
 	int err;
@@ -351,7 +391,7 @@ int ovl_set_origin(struct ovl_fs *ofs, struct dentry *dentry,
 	/*
 	 * Do not fail when upper doesn't support xattrs.
 	 */
-	err = ovl_check_setxattr(dentry, upper, OVL_XATTR_ORIGIN, fh->buf,
+	err = ovl_check_setxattr(ofs, upper, OVL_XATTR_ORIGIN, fh->buf,
 				 fh ? fh->fb.len : 0, 0);
 	kfree(fh);
 
@@ -493,20 +533,21 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c)
 static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp)
 {
 	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
+	struct inode *inode = d_inode(c->dentry);
+	struct path upperpath, datapath;
 	int err;
 
+	ovl_path_upper(c->dentry, &upperpath);
+	if (WARN_ON(upperpath.dentry != NULL))
+		return -EIO;
+
+	upperpath.dentry = temp;
+
 	/*
 	 * Copy up data first and then xattrs. Writing data after
 	 * xattrs will remove security.capability xattr automatically.
 	 */
 	if (S_ISREG(c->stat.mode) && !c->metacopy) {
-		struct path upperpath, datapath;
-
-		ovl_path_upper(c->dentry, &upperpath);
-		if (WARN_ON(upperpath.dentry != NULL))
-			return -EIO;
-		upperpath.dentry = temp;
-
 		ovl_path_lowerdata(c->dentry, &datapath);
 		err = ovl_copy_up_data(ofs, &datapath, &upperpath,
 				       c->stat.size);
@@ -518,6 +559,16 @@ static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp)
 	if (err)
 		return err;
 
+	if (inode->i_flags & OVL_COPY_I_FLAGS_MASK) {
+		/*
+		 * Copy the fileattr inode flags that are the source of already
+		 * copied i_flags
+		 */
+		err = ovl_copy_fileattr(inode, &c->lowerpath, &upperpath);
+		if (err)
+			return err;
+	}
+
 	/*
 	 * Store identifier of lower inode in upper inode xattr to
 	 * allow lookup of the copy up origin inode.
@@ -526,13 +577,13 @@ static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp)
 	 * hard link.
 	 */
 	if (c->origin) {
-		err = ovl_set_origin(ofs, c->dentry, c->lowerpath.dentry, temp);
+		err = ovl_set_origin(ofs, c->lowerpath.dentry, temp);
 		if (err)
 			return err;
 	}
 
 	if (c->metacopy) {
-		err = ovl_check_setxattr(c->dentry, temp, OVL_XATTR_METACOPY,
+		err = ovl_check_setxattr(ofs, temp, OVL_XATTR_METACOPY,
 					 NULL, 0, -EOPNOTSUPP);
 		if (err)
 			return err;

fs/overlayfs/dir.c

@@ -233,9 +233,10 @@ struct dentry *ovl_create_temp(struct dentry *workdir, struct ovl_cattr *attr)
 static int ovl_set_opaque_xerr(struct dentry *dentry, struct dentry *upper,
 			       int xerr)
 {
+	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
 	int err;
 
-	err = ovl_check_setxattr(dentry, upper, OVL_XATTR_OPAQUE, "y", 1, xerr);
+	err = ovl_check_setxattr(ofs, upper, OVL_XATTR_OPAQUE, "y", 1, xerr);
 	if (!err)
 		ovl_dentry_set_opaque(dentry);
 
@@ -320,6 +321,7 @@ static bool ovl_type_origin(struct dentry *dentry)
 static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
 			    struct ovl_cattr *attr)
 {
+	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
 	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
 	struct inode *udir = upperdir->d_inode;
 	struct dentry *newdentry;
@@ -338,7 +340,8 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
 	if (IS_ERR(newdentry))
 		goto out_unlock;
 
-	if (ovl_type_merge(dentry->d_parent) && d_is_dir(newdentry)) {
+	if (ovl_type_merge(dentry->d_parent) && d_is_dir(newdentry) &&
+	    !ovl_allow_offline_changes(ofs)) {
 		/* Setting opaque here is just an optimization, allow to fail */
 		ovl_set_opaque(dentry, newdentry);
 	}
@@ -542,8 +545,10 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
 			goto out_cleanup;
 	}
 	err = ovl_instantiate(dentry, inode, newdentry, hardlink);
-	if (err)
-		goto out_cleanup;
+	if (err) {
+		ovl_cleanup(udir, newdentry);
+		dput(newdentry);
+	}
 out_dput:
 	dput(upper);
 out_unlock:
@@ -1043,6 +1048,7 @@ static bool ovl_need_absolute_redirect(struct dentry *dentry, bool samedir)
 static int ovl_set_redirect(struct dentry *dentry, bool samedir)
 {
 	int err;
+	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
 	const char *redirect = ovl_dentry_get_redirect(dentry);
 	bool absolute_redirect = ovl_need_absolute_redirect(dentry, samedir);
 
@@ -1053,7 +1059,7 @@ static int ovl_set_redirect(struct dentry *dentry, bool samedir)
 	if (IS_ERR(redirect))
 		return PTR_ERR(redirect);
 
-	err = ovl_check_setxattr(dentry, ovl_dentry_upper(dentry),
+	err = ovl_check_setxattr(ofs, ovl_dentry_upper(dentry),
 				 OVL_XATTR_REDIRECT,
 				 redirect, strlen(redirect), -EXDEV);
 	if (!err) {

fs/overlayfs/inode.c

@@ -13,6 +13,7 @@
 #include <linux/fiemap.h>
 #include <linux/fileattr.h>
 #include <linux/security.h>
+#include <linux/namei.h>
 #include "overlayfs.h"
 
 
@@ -33,12 +34,6 @@ int ovl_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 		goto out;
 
 	if (attr->ia_valid & ATTR_SIZE) {
-		struct inode *realinode = d_inode(ovl_dentry_real(dentry));
-
-		err = -ETXTBSY;
-		if (atomic_read(&realinode->i_writecount) < 0)
-			goto out_drop_write;
-
 		/* Truncate should trigger data copy up as well */
 		full_copy_up = true;
 	}
@@ -162,7 +157,8 @@ int ovl_getattr(struct user_namespace *mnt_userns, const struct path *path,
 	enum ovl_path_type type;
 	struct path realpath;
 	const struct cred *old_cred;
-	bool is_dir = S_ISDIR(dentry->d_inode->i_mode);
+	struct inode *inode = d_inode(dentry);
+	bool is_dir = S_ISDIR(inode->i_mode);
 	int fsid = 0;
 	int err;
 	bool metacopy_blocks = false;
@@ -175,6 +171,9 @@ int ovl_getattr(struct user_namespace *mnt_userns, const struct path *path,
 	if (err)
 		goto out;
 
+	/* Report the effective immutable/append-only STATX flags */
+	generic_fill_statx_attr(inode, stat);
+
 	/*
 	 * For non-dir or same fs, we use st_ino of the copy up origin.
 	 * This guaranties constant st_dev/st_ino across copy up.
@@ -448,7 +447,7 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 	return res;
 }
 
-struct posix_acl *ovl_get_acl(struct inode *inode, int type)
+struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu)
 {
 	struct inode *realinode = ovl_inode_real(inode);
 	const struct cred *old_cred;
@@ -457,6 +456,9 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type)
 	if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
 		return NULL;
 
+	if (rcu)
+		return get_cached_acl_rcu(realinode, type);
+
 	old_cred = ovl_override_creds(inode->i_sb);
 	acl = get_acl(realinode, type);
 	revert_creds(old_cred);
@@ -503,16 +505,14 @@ static int ovl_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
  * Introducing security_inode_fileattr_get/set() hooks would solve this issue
  * properly.
  */
-static int ovl_security_fileattr(struct dentry *dentry, struct fileattr *fa,
+static int ovl_security_fileattr(struct path *realpath, struct fileattr *fa,
 				 bool set)
 {
-	struct path realpath;
 	struct file *file;
 	unsigned int cmd;
 	int err;
 
-	ovl_path_real(dentry, &realpath);
-	file = dentry_open(&realpath, O_RDONLY, current_cred());
+	file = dentry_open(realpath, O_RDONLY, current_cred());
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
@@ -527,12 +527,24 @@ static int ovl_security_fileattr(struct dentry *dentry, struct fileattr *fa,
 	return err;
 }
 
+int ovl_real_fileattr_set(struct path *realpath, struct fileattr *fa)
+{
+	int err;
+
+	err = ovl_security_fileattr(realpath, fa, true);
+	if (err)
+		return err;
+
+	return vfs_fileattr_set(&init_user_ns, realpath->dentry, fa);
+}
+
 int ovl_fileattr_set(struct user_namespace *mnt_userns,
 		     struct dentry *dentry, struct fileattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
-	struct dentry *upperdentry;
+	struct path upperpath;
 	const struct cred *old_cred;
+	unsigned int flags;
 	int err;
 
 	err = ovl_want_write(dentry);
@@ -541,31 +553,78 @@ int ovl_fileattr_set(struct user_namespace *mnt_userns,
 
 	err = ovl_copy_up(dentry);
 	if (!err) {
-		upperdentry = ovl_dentry_upper(dentry);
+		ovl_path_real(dentry, &upperpath);
 
 		old_cred = ovl_override_creds(inode->i_sb);
-		err = ovl_security_fileattr(dentry, fa, true);
+		/*
+		 * Store immutable/append-only flags in xattr and clear them
+		 * in upper fileattr (in case they were set by older kernel)
+		 * so children of "ovl-immutable" directories lower aliases of
+		 * "ovl-immutable" hardlinks could be copied up.
+		 * Clear xattr when flags are cleared.
+		 */
+		err = ovl_set_protattr(inode, upperpath.dentry, fa);
 		if (!err)
-			err = vfs_fileattr_set(&init_user_ns, upperdentry, fa);
+			err = ovl_real_fileattr_set(&upperpath, fa);
 		revert_creds(old_cred);
-		ovl_copyflags(ovl_inode_real(inode), inode);
+
+		/*
+		 * Merge real inode flags with inode flags read from
+		 * overlay.protattr xattr
+		 */
+		flags = ovl_inode_real(inode)->i_flags & OVL_COPY_I_FLAGS_MASK;
+
+		BUILD_BUG_ON(OVL_PROT_I_FLAGS_MASK & ~OVL_COPY_I_FLAGS_MASK);
+		flags |= inode->i_flags & OVL_PROT_I_FLAGS_MASK;
+		inode_set_flags(inode, flags, OVL_COPY_I_FLAGS_MASK);
+
+		/* Update ctime */
+		ovl_copyattr(ovl_inode_real(inode), inode);
 	}
 	ovl_drop_write(dentry);
 out:
 	return err;
 }
 
+/* Convert inode protection flags to fileattr flags */
+static void ovl_fileattr_prot_flags(struct inode *inode, struct fileattr *fa)
+{
+	BUILD_BUG_ON(OVL_PROT_FS_FLAGS_MASK & ~FS_COMMON_FL);
+	BUILD_BUG_ON(OVL_PROT_FSX_FLAGS_MASK & ~FS_XFLAG_COMMON);
+
+	if (inode->i_flags & S_APPEND) {
+		fa->flags |= FS_APPEND_FL;
+		fa->fsx_xflags |= FS_XFLAG_APPEND;
+	}
+	if (inode->i_flags & S_IMMUTABLE) {
+		fa->flags |= FS_IMMUTABLE_FL;
+		fa->fsx_xflags |= FS_XFLAG_IMMUTABLE;
+	}
+}
+
+int ovl_real_fileattr_get(struct path *realpath, struct fileattr *fa)
+{
+	int err;
+
+	err = ovl_security_fileattr(realpath, fa, false);
+	if (err)
+		return err;
+
+	return vfs_fileattr_get(realpath->dentry, fa);
+}
+
 int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
-	struct dentry *realdentry = ovl_dentry_real(dentry);
+	struct path realpath;
 	const struct cred *old_cred;
 	int err;
 
+	ovl_path_real(dentry, &realpath);
+
 	old_cred = ovl_override_creds(inode->i_sb);
-	err = ovl_security_fileattr(dentry, fa, false);
-	if (!err)
-		err = vfs_fileattr_get(realdentry, fa);
+	err = ovl_real_fileattr_get(&realpath, fa);
+	ovl_fileattr_prot_flags(inode, fa);
 	revert_creds(old_cred);
 
 	return err;
@@ -1118,6 +1177,10 @@ struct inode *ovl_get_inode(struct super_block *sb,
 		}
 	}
 
+	/* Check for immutable/append-only inode flags in xattr */
+	if (upperdentry)
+		ovl_check_protattr(inode, upperdentry);
+
 	if (inode->i_state & I_NEW)
 		unlock_new_inode(inode);
 out:

fs/overlayfs/namei.c

@@ -392,7 +392,7 @@ invalid:
 			    upperdentry, d_inode(upperdentry)->i_mode & S_IFMT,
 			    d_inode(origin)->i_mode & S_IFMT);
 	dput(origin);
-	return -EIO;
+	return -ESTALE;
 }
 
 static int ovl_check_origin(struct ovl_fs *ofs, struct dentry *upperdentry,
@@ -811,7 +811,7 @@ static int ovl_fix_origin(struct ovl_fs *ofs, struct dentry *dentry,
 	if (err)
 		return err;
 
-	err = ovl_set_origin(ofs, dentry, lower, upper);
+	err = ovl_set_origin(ofs, lower, upper);
 	if (!err)
 		err = ovl_set_impure(dentry->d_parent, upper->d_parent);
 

fs/overlayfs/overlayfs.h

@@ -34,6 +34,7 @@ enum ovl_xattr {
 	OVL_XATTR_NLINK,
 	OVL_XATTR_UPPER,
 	OVL_XATTR_METACOPY,
+	OVL_XATTR_PROTATTR,
 };
 
 enum ovl_inode_flag {
@@ -262,6 +263,18 @@ static inline bool ovl_open_flags_need_copy_up(int flags)
 	return ((OPEN_FMODE(flags) & FMODE_WRITE) || (flags & O_TRUNC));
 }
 
+static inline bool ovl_allow_offline_changes(struct ovl_fs *ofs)
+{
+	/*
+	 * To avoid regressions in existing setups with overlay lower offline
+	 * changes, we allow lower changes only if none of the new features
+	 * are used.
+	 */
+	return (!ofs->config.index && !ofs->config.metacopy &&
+		!ofs->config.redirect_dir && ofs->config.xino != OVL_XINO_ON);
+}
+
+
 /* util.c */
 int ovl_want_write(struct dentry *dentry);
 void ovl_drop_write(struct dentry *dentry);
@@ -320,7 +333,7 @@ bool ovl_already_copied_up(struct dentry *dentry, int flags);
 bool ovl_check_origin_xattr(struct ovl_fs *ofs, struct dentry *dentry);
 bool ovl_check_dir_xattr(struct super_block *sb, struct dentry *dentry,
 			 enum ovl_xattr ox);
-int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
+int ovl_check_setxattr(struct ovl_fs *ofs, struct dentry *upperdentry,
 		       enum ovl_xattr ox, const void *value, size_t size,
 		       int xerr);
 int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry);
@@ -485,7 +498,7 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
 int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
 		  void *value, size_t size);
 ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
-struct posix_acl *ovl_get_acl(struct inode *inode, int type);
+struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu);
 int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags);
 bool ovl_is_private_xattr(struct super_block *sb, const char *name);
 
@@ -518,9 +531,28 @@ static inline void ovl_copyattr(struct inode *from, struct inode *to)
 	i_size_write(to, i_size_read(from));
 }
 
+/* vfs inode flags copied from real to ovl inode */
+#define OVL_COPY_I_FLAGS_MASK	(S_SYNC | S_NOATIME | S_APPEND | S_IMMUTABLE)
+/* vfs inode flags read from overlay.protattr xattr to ovl inode */
+#define OVL_PROT_I_FLAGS_MASK	(S_APPEND | S_IMMUTABLE)
+
+/*
+ * fileattr flags copied from lower to upper inode on copy up.
+ * We cannot copy up immutable/append-only flags, because that would prevent
+ * linking temp inode to upper dir, so we store them in xattr instead.
+ */
+#define OVL_COPY_FS_FLAGS_MASK	(FS_SYNC_FL | FS_NOATIME_FL)
+#define OVL_COPY_FSX_FLAGS_MASK	(FS_XFLAG_SYNC | FS_XFLAG_NOATIME)
+#define OVL_PROT_FS_FLAGS_MASK  (FS_APPEND_FL | FS_IMMUTABLE_FL)
+#define OVL_PROT_FSX_FLAGS_MASK (FS_XFLAG_APPEND | FS_XFLAG_IMMUTABLE)
+
+void ovl_check_protattr(struct inode *inode, struct dentry *upper);
+int ovl_set_protattr(struct inode *inode, struct dentry *upper,
+		      struct fileattr *fa);
+
 static inline void ovl_copyflags(struct inode *from, struct inode *to)
 {
-	unsigned int mask = S_SYNC | S_IMMUTABLE | S_APPEND | S_NOATIME;
+	unsigned int mask = OVL_COPY_I_FLAGS_MASK;
 
 	inode_set_flags(to, from->i_flags & mask, mask);
 }
@@ -548,6 +580,8 @@ struct dentry *ovl_create_temp(struct dentry *workdir, struct ovl_cattr *attr);
 extern const struct file_operations ovl_file_operations;
 int __init ovl_aio_request_cache_init(void);
 void ovl_aio_request_cache_destroy(void);
+int ovl_real_fileattr_get(struct path *realpath, struct fileattr *fa);
+int ovl_real_fileattr_set(struct path *realpath, struct fileattr *fa);
 int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa);
 int ovl_fileattr_set(struct user_namespace *mnt_userns,
 		     struct dentry *dentry, struct fileattr *fa);
@@ -561,8 +595,8 @@ int ovl_copy_xattr(struct super_block *sb, struct dentry *old,
 int ovl_set_attr(struct dentry *upper, struct kstat *stat);
 struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real,
 				  bool is_upper);
-int ovl_set_origin(struct ovl_fs *ofs, struct dentry *dentry,
-		   struct dentry *lower, struct dentry *upper);
+int ovl_set_origin(struct ovl_fs *ofs, struct dentry *lower,
+		   struct dentry *upper);
 
 /* export.c */
 extern const struct export_operations ovl_export_operations;

fs/overlayfs/super.c

@@ -1599,9 +1599,7 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid)
 	 * user opted-in to one of the new features that require following the
 	 * lower inode of non-dir upper.
 	 */
-	if (!ofs->config.index && !ofs->config.metacopy &&
-	    ofs->config.xino != OVL_XINO_ON &&
-	    uuid_is_null(uuid))
+	if (ovl_allow_offline_changes(ofs) && uuid_is_null(uuid))
 		return false;
 
 	for (i = 0; i < ofs->numfs; i++) {

fs/overlayfs/util.c

@@ -10,6 +10,7 @@
 #include <linux/cred.h>
 #include <linux/xattr.h>
 #include <linux/exportfs.h>
+#include <linux/fileattr.h>
 #include <linux/uuid.h>
 #include <linux/namei.h>
 #include <linux/ratelimit.h>
@@ -585,6 +586,7 @@ bool ovl_check_dir_xattr(struct super_block *sb, struct dentry *dentry,
 #define OVL_XATTR_NLINK_POSTFIX		"nlink"
 #define OVL_XATTR_UPPER_POSTFIX		"upper"
 #define OVL_XATTR_METACOPY_POSTFIX	"metacopy"
+#define OVL_XATTR_PROTATTR_POSTFIX	"protattr"
 
 #define OVL_XATTR_TAB_ENTRY(x) \
 	[x] = { [false] = OVL_XATTR_TRUSTED_PREFIX x ## _POSTFIX, \
@@ -598,14 +600,14 @@ const char *const ovl_xattr_table[][2] = {
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_NLINK),
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_UPPER),
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_METACOPY),
+	OVL_XATTR_TAB_ENTRY(OVL_XATTR_PROTATTR),
 };
 
-int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
+int ovl_check_setxattr(struct ovl_fs *ofs, struct dentry *upperdentry,
 		       enum ovl_xattr ox, const void *value, size_t size,
 		       int xerr)
 {
 	int err;
-	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
 
 	if (ofs->noxattr)
 		return xerr;
@@ -623,6 +625,7 @@ int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
 
 int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry)
 {
+	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
 	int err;
 
 	if (ovl_test_flag(OVL_IMPURE, d_inode(dentry)))
@@ -632,14 +635,95 @@ int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry)
 	 * Do not fail when upper doesn't support xattrs.
 	 * Upper inodes won't have origin nor redirect xattr anyway.
 	 */
-	err = ovl_check_setxattr(dentry, upperdentry, OVL_XATTR_IMPURE,
-				 "y", 1, 0);
+	err = ovl_check_setxattr(ofs, upperdentry, OVL_XATTR_IMPURE, "y", 1, 0);
 	if (!err)
 		ovl_set_flag(OVL_IMPURE, d_inode(dentry));
 
 	return err;
 }
 
+
+#define OVL_PROTATTR_MAX 32 /* Reserved for future flags */
+
+void ovl_check_protattr(struct inode *inode, struct dentry *upper)
+{
+	struct ovl_fs *ofs = OVL_FS(inode->i_sb);
+	u32 iflags = inode->i_flags & OVL_PROT_I_FLAGS_MASK;
+	char buf[OVL_PROTATTR_MAX+1];
+	int res, n;
+
+	res = ovl_do_getxattr(ofs, upper, OVL_XATTR_PROTATTR, buf,
+			      OVL_PROTATTR_MAX);
+	if (res < 0)
+		return;
+
+	/*
+	 * Initialize inode flags from overlay.protattr xattr and upper inode
+	 * flags.  If upper inode has those fileattr flags set (i.e. from old
+	 * kernel), we do not clear them on ovl_get_inode(), but we will clear
+	 * them on next fileattr_set().
+	 */
+	for (n = 0; n < res; n++) {
+		if (buf[n] == 'a')
+			iflags |= S_APPEND;
+		else if (buf[n] == 'i')
+			iflags |= S_IMMUTABLE;
+		else
+			break;
+	}
+
+	if (!res || n < res) {
+		pr_warn_ratelimited("incompatible overlay.protattr format (%pd2, len=%d)\n",
+				    upper, res);
+	} else {
+		inode_set_flags(inode, iflags, OVL_PROT_I_FLAGS_MASK);
+	}
+}
+
+int ovl_set_protattr(struct inode *inode, struct dentry *upper,
+		      struct fileattr *fa)
+{
+	struct ovl_fs *ofs = OVL_FS(inode->i_sb);
+	char buf[OVL_PROTATTR_MAX];
+	int len = 0, err = 0;
+	u32 iflags = 0;
+
+	BUILD_BUG_ON(HWEIGHT32(OVL_PROT_FS_FLAGS_MASK) > OVL_PROTATTR_MAX);
+
+	if (fa->flags & FS_APPEND_FL) {
+		buf[len++] = 'a';
+		iflags |= S_APPEND;
+	}
+	if (fa->flags & FS_IMMUTABLE_FL) {
+		buf[len++] = 'i';
+		iflags |= S_IMMUTABLE;
+	}
+
+	/*
+	 * Do not allow to set protection flags when upper doesn't support
+	 * xattrs, because we do not set those fileattr flags on upper inode.
+	 * Remove xattr if it exist and all protection flags are cleared.
+	 */
+	if (len) {
+		err = ovl_check_setxattr(ofs, upper, OVL_XATTR_PROTATTR,
+					 buf, len, -EPERM);
+	} else if (inode->i_flags & OVL_PROT_I_FLAGS_MASK) {
+		err = ovl_do_removexattr(ofs, upper, OVL_XATTR_PROTATTR);
+		if (err == -EOPNOTSUPP || err == -ENODATA)
+			err = 0;
+	}
+	if (err)
+		return err;
+
+	inode_set_flags(inode, iflags, OVL_PROT_I_FLAGS_MASK);
+
+	/* Mask out the fileattr flags that should not be set in upper inode */
+	fa->flags &= ~OVL_PROT_FS_FLAGS_MASK;
+	fa->fsx_xflags &= ~OVL_PROT_FSX_FLAGS_MASK;
+
+	return 0;
+}
+
 /**
  * Caller must hold a reference to inode to prevent it from being freed while
  * it is marked inuse.

fs/posix_acl.c

@@ -22,6 +22,7 @@
 #include <linux/xattr.h>
 #include <linux/export.h>
 #include <linux/user_namespace.h>
+#include <linux/namei.h>
 
 static struct posix_acl **acl_by_type(struct inode *inode, int type)
 {
@@ -56,7 +57,17 @@ EXPORT_SYMBOL(get_cached_acl);
 
 struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type)
 {
-	return rcu_dereference(*acl_by_type(inode, type));
+	struct posix_acl *acl = rcu_dereference(*acl_by_type(inode, type));
+
+	if (acl == ACL_DONT_CACHE) {
+		struct posix_acl *ret;
+
+		ret = inode->i_op->get_acl(inode, type, LOOKUP_RCU);
+		if (!IS_ERR(ret))
+			acl = ret;
+	}
+
+	return acl;
 }
 EXPORT_SYMBOL(get_cached_acl_rcu);
 
@@ -138,7 +149,7 @@ struct posix_acl *get_acl(struct inode *inode, int type)
 		set_cached_acl(inode, type, NULL);
 		return NULL;
 	}
-	acl = inode->i_op->get_acl(inode, type);
+	acl = inode->i_op->get_acl(inode, type, false);
 
 	if (IS_ERR(acl)) {
 		/*

fs/reiserfs/acl.h

@@ -48,7 +48,7 @@ static inline int reiserfs_acl_count(size_t size)
 }
 
 #ifdef CONFIG_REISERFS_FS_POSIX_ACL
-struct posix_acl *reiserfs_get_acl(struct inode *inode, int type);
+struct posix_acl *reiserfs_get_acl(struct inode *inode, int type, bool rcu);
 int reiserfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		     struct posix_acl *acl, int type);
 int reiserfs_acl_chmod(struct inode *inode);

fs/reiserfs/xattr_acl.c

@@ -190,13 +190,16 @@ fail:
  * inode->i_mutex: down
  * BKL held [before 2.5.x]
  */
-struct posix_acl *reiserfs_get_acl(struct inode *inode, int type)
+struct posix_acl *reiserfs_get_acl(struct inode *inode, int type, bool rcu)
 {
 	char *name, *value;
 	struct posix_acl *acl;
 	int size;
 	int retval;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name = XATTR_NAME_POSIX_ACL_ACCESS;

fs/stat.c

@@ -59,6 +59,24 @@ void generic_fillattr(struct user_namespace *mnt_userns, struct inode *inode,
 }
 EXPORT_SYMBOL(generic_fillattr);
 
+/**
+ * generic_fill_statx_attr - Fill in the statx attributes from the inode flags
+ * @inode:	Inode to use as the source
+ * @stat:	Where to fill in the attribute flags
+ *
+ * Fill in the STATX_ATTR_* flags in the kstat structure for properties of the
+ * inode that are published on i_flags and enforced by the VFS.
+ */
+void generic_fill_statx_attr(struct inode *inode, struct kstat *stat)
+{
+	if (inode->i_flags & S_IMMUTABLE)
+		stat->attributes |= STATX_ATTR_IMMUTABLE;
+	if (inode->i_flags & S_APPEND)
+		stat->attributes |= STATX_ATTR_APPEND;
+	stat->attributes_mask |= KSTAT_ATTR_VFS_FLAGS;
+}
+EXPORT_SYMBOL(generic_fill_statx_attr);
+
 /**
  * vfs_getattr_nosec - getattr without security checks
  * @path: file to get attributes from

fs/xfs/xfs_acl.c

@@ -125,7 +125,7 @@ xfs_acl_to_disk(struct xfs_acl *aclp, const struct posix_acl *acl)
 }
 
 struct posix_acl *
-xfs_get_acl(struct inode *inode, int type)
+xfs_get_acl(struct inode *inode, int type, bool rcu)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -137,6 +137,9 @@ xfs_get_acl(struct inode *inode, int type)
 	};
 	int			error;
 
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
 	trace_xfs_get_acl(ip);
 
 	switch (type) {

fs/xfs/xfs_acl.h

@@ -10,13 +10,13 @@ struct inode;
 struct posix_acl;
 
 #ifdef CONFIG_XFS_POSIX_ACL
-extern struct posix_acl *xfs_get_acl(struct inode *inode, int type);
+extern struct posix_acl *xfs_get_acl(struct inode *inode, int type, bool rcu);
 extern int xfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		       struct posix_acl *acl, int type);
 extern int __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
 void xfs_forget_acl(struct inode *inode, const char *name);
 #else
-static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type)
+static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type, bool rcu)
 {
 	return NULL;
 }

include/linux/fs.h

@@ -588,6 +588,11 @@ static inline void mapping_allow_writable(struct address_space *mapping)
 
 struct posix_acl;
 #define ACL_NOT_CACHED ((void *)(-1))
+/*
+ * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to
+ * cache the ACL.  This also means that ->get_acl() can be called in RCU mode
+ * with the LOOKUP_RCU flag.
+ */
 #define ACL_DONT_CACHE ((void *)(-3))
 
 static inline struct posix_acl *
@@ -2109,7 +2114,7 @@ struct inode_operations {
 	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
 	const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *);
 	int (*permission) (struct user_namespace *, struct inode *, int);
-	struct posix_acl * (*get_acl)(struct inode *, int);
+	struct posix_acl * (*get_acl)(struct inode *, int, bool);
 
 	int (*readlink) (struct dentry *, char __user *,int);
 
@@ -3314,6 +3319,7 @@ extern int page_symlink(struct inode *inode, const char *symname, int len);
 extern const struct inode_operations page_symlink_inode_operations;
 extern void kfree_link(void *);
 void generic_fillattr(struct user_namespace *, struct inode *, struct kstat *);
+void generic_fill_statx_attr(struct inode *inode, struct kstat *stat);
 extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);
 extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
 void __inode_add_bytes(struct inode *inode, loff_t bytes);

include/linux/posix_acl.h

@@ -72,6 +72,8 @@ extern struct posix_acl *get_posix_acl(struct inode *, int);
 extern int set_posix_acl(struct user_namespace *, struct inode *, int,
 			 struct posix_acl *);
 
+struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type);
+
 #ifdef CONFIG_FS_POSIX_ACL
 int posix_acl_chmod(struct user_namespace *, struct inode *, umode_t);
 extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **,
@@ -84,7 +86,6 @@ extern int simple_set_acl(struct user_namespace *, struct inode *,
 extern int simple_acl_create(struct inode *, struct inode *);
 
 struct posix_acl *get_cached_acl(struct inode *inode, int type);
-struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type);
 void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl);
 void forget_cached_acl(struct inode *inode, int type);
 void forget_all_cached_acls(struct inode *inode);

include/linux/stat.h

@@ -34,6 +34,10 @@ struct kstat {
 	 STATX_ATTR_ENCRYPTED |				\
 	 STATX_ATTR_VERITY				\
 	 )/* Attrs corresponding to FS_*_FL flags */
+#define KSTAT_ATTR_VFS_FLAGS				\
+	(STATX_ATTR_IMMUTABLE |				\
+	 STATX_ATTR_APPEND				\
+	 ) /* Attrs corresponding to S_* flags that are enforced by the VFS */
 	u64		ino;
 	dev_t		dev;
 	dev_t		rdev;