Merge tag 'erofs-for-6.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs

Pull erofs updates from Gao Xiang:
 "In this cycle, we add file-backed mount support, which has has been a
  strong requirement for years. It is especially useful when there are
  thousands of images running on the same host for containers and other
  sandbox use cases, unlike OS image use cases.

  Without file-backed mounts, it's hard for container runtimes to manage
  and isolate so many unnecessary virtual block devices safely and
  efficiently, therefore file-backed mounts are highly preferred. For
  EROFS users, ComposeFS [1], containerd, and Android APEXes [2] will
  directly benefit from it, and I've seen no risk in implementing it as
  a completely immutable filesystem.

  The previous experimental feature "EROFS over fscache" is now marked
  as deprecated because:

   - Fscache is no longer an independent subsystem and has been merged
     into netfs, which was somewhat unexpected when it was proposed.

   - New HSM "fanotify pre-content hooks" [3] will be landed upstream.
     These hooks will replace "EROFS over fscache" in a simpler way, as
     EROFS won't be bother with kernel caching anymore. Userspace
     programs can also manage their own caching hierarchy more flexibly.

  Once the HSM "fanotify pre-content hooks" is landed, I will remove the
  fscache backend entirely as an internal dependency cleanup. More
  backgrounds are listed in the original patchset [4].

  In addition to that, there are bugfixes and cleanups as usual.

  Summary:

   - Support file-backed mounts for containers and sandboxes

   - Mark the experimental fscache backend as deprecated

   - Handle overlapped pclusters caused by crafted images properly

   - Fix a failure path which could cause infinite loops in
     z_erofs_init_decompressor()

   - Get rid of unnecessary NOFAILs

   - Harmless on-disk hardening & minor cleanups"

* tag 'erofs-for-6.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs:
  erofs: reject inodes with negative i_size
  erofs: restrict pcluster size limitations
  erofs: allocate more short-lived pages from reserved pool first
  erofs: sunset unneeded NOFAILs
  erofs: simplify erofs_map_blocks_flatmode()
  erofs: refactor read_inode calling convention
  erofs: use kmemdup_nul in erofs_fill_symlink
  erofs: mark experimental fscache backend deprecated
  erofs: support compressed inodes for fileio
  erofs: support unencoded inodes for fileio
  erofs: add file-backed mount support
  erofs: handle overlapped pclusters out of crafted images properly
  erofs: fix error handling in z_erofs_init_decompressor
  erofs: clean up erofs_register_sysfs()
  erofs: fix incorrect symlink detection in fast symlink

fs/erofs/Kconfig

@@ -74,6 +74,23 @@ config EROFS_FS_SECURITY
 
 	  If you are not using a security module, say N.
 
+config EROFS_FS_BACKED_BY_FILE
+	bool "File-backed EROFS filesystem support"
+	depends on EROFS_FS
+	default y
+	help
+	  This allows EROFS to use filesystem image files directly, without
+	  the intercession of loopback block devices or likewise. It is
+	  particularly useful for container images with numerous blobs and
+	  other sandboxes, where loop devices behave intricately.  It can also
+	  be used to simplify error-prone lifetime management of unnecessary
+	  virtual block devices.
+
+	  Note that this feature, along with ongoing fanotify pre-content
+	  hooks, will eventually replace "EROFS over fscache."
+
+	  If you don't want to enable this feature, say N.
+
 config EROFS_FS_ZIP
 	bool "EROFS Data Compression Support"
 	depends on EROFS_FS
@@ -128,7 +145,7 @@ config EROFS_FS_ZIP_ZSTD
 	  If unsure, say N.
 
 config EROFS_FS_ONDEMAND
-	bool "EROFS fscache-based on-demand read support"
+	bool "EROFS fscache-based on-demand read support (deprecated)"
 	depends on EROFS_FS
 	select NETFS_SUPPORT
 	select FSCACHE
@@ -138,6 +155,9 @@ config EROFS_FS_ONDEMAND
 	  This permits EROFS to use fscache-backed data blobs with on-demand
 	  read support.
 
+	  It is now deprecated and scheduled to be removed from the kernel
+	  after fanotify pre-content hooks are landed.
+
 	  If unsure, say N.
 
 config EROFS_FS_PCPU_KTHREAD

fs/erofs/Makefile

@@ -7,4 +7,5 @@ erofs-$(CONFIG_EROFS_FS_ZIP) += decompressor.o zmap.o zdata.o zutil.o
 erofs-$(CONFIG_EROFS_FS_ZIP_LZMA) += decompressor_lzma.o
 erofs-$(CONFIG_EROFS_FS_ZIP_DEFLATE) += decompressor_deflate.o
 erofs-$(CONFIG_EROFS_FS_ZIP_ZSTD) += decompressor_zstd.o
+erofs-$(CONFIG_EROFS_FS_BACKED_BY_FILE) += fileio.o
 erofs-$(CONFIG_EROFS_FS_ONDEMAND) += fscache.o

fs/erofs/data.c

@@ -59,8 +59,12 @@ void *erofs_bread(struct erofs_buf *buf, erofs_off_t offset,
 
 void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb)
 {
-	if (erofs_is_fscache_mode(sb))
-		buf->mapping = EROFS_SB(sb)->s_fscache->inode->i_mapping;
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+
+	if (erofs_is_fileio_mode(sbi))
+		buf->mapping = file_inode(sbi->fdev)->i_mapping;
+	else if (erofs_is_fscache_mode(sb))
+		buf->mapping = sbi->s_fscache->inode->i_mapping;
 	else
 		buf->mapping = sb->s_bdev->bd_mapping;
 }
@@ -75,38 +79,28 @@ void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb,
 static int erofs_map_blocks_flatmode(struct inode *inode,
 				     struct erofs_map_blocks *map)
 {
-	erofs_blk_t nblocks, lastblk;
-	u64 offset = map->m_la;
 	struct erofs_inode *vi = EROFS_I(inode);
 	struct super_block *sb = inode->i_sb;
 	bool tailendpacking = (vi->datalayout == EROFS_INODE_FLAT_INLINE);
+	erofs_blk_t lastblk = erofs_iblks(inode) - tailendpacking;
 
-	nblocks = erofs_iblks(inode);
-	lastblk = nblocks - tailendpacking;
-
-	/* there is no hole in flatmode */
-	map->m_flags = EROFS_MAP_MAPPED;
-	if (offset < erofs_pos(sb, lastblk)) {
+	map->m_flags = EROFS_MAP_MAPPED;	/* no hole in flat inodes */
+	if (map->m_la < erofs_pos(sb, lastblk)) {
 		map->m_pa = erofs_pos(sb, vi->raw_blkaddr) + map->m_la;
-		map->m_plen = erofs_pos(sb, lastblk) - offset;
-	} else if (tailendpacking) {
+		map->m_plen = erofs_pos(sb, lastblk) - map->m_la;
+	} else {
+		DBG_BUGON(!tailendpacking);
 		map->m_pa = erofs_iloc(inode) + vi->inode_isize +
-			vi->xattr_isize + erofs_blkoff(sb, offset);
-		map->m_plen = inode->i_size - offset;
+			vi->xattr_isize + erofs_blkoff(sb, map->m_la);
+		map->m_plen = inode->i_size - map->m_la;
 
 		/* inline data should be located in the same meta block */
 		if (erofs_blkoff(sb, map->m_pa) + map->m_plen > sb->s_blocksize) {
-			erofs_err(sb, "inline data cross block boundary @ nid %llu",
-				  vi->nid);
+			erofs_err(sb, "inline data across blocks @ nid %llu", vi->nid);
 			DBG_BUGON(1);
 			return -EFSCORRUPTED;
 		}
 		map->m_flags |= EROFS_MAP_META;
-	} else {
-		erofs_err(sb, "internal error @ nid: %llu (size %llu), m_la 0x%llx",
-			  vi->nid, inode->i_size, map->m_la);
-		DBG_BUGON(1);
-		return -EIO;
 	}
 	return 0;
 }
@@ -128,7 +122,7 @@ int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map)
 	if (map->m_la >= inode->i_size) {
 		/* leave out-of-bound access unmapped */
 		map->m_flags = 0;
-		map->m_plen = 0;
+		map->m_plen = map->m_llen;
 		goto out;
 	}
 
@@ -189,16 +183,34 @@ int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map)
 	return err;
 }
 
+static void erofs_fill_from_devinfo(struct erofs_map_dev *map,
+				    struct erofs_device_info *dif)
+{
+	map->m_bdev = NULL;
+	map->m_fp = NULL;
+	if (dif->file) {
+		if (S_ISBLK(file_inode(dif->file)->i_mode))
+			map->m_bdev = file_bdev(dif->file);
+		else
+			map->m_fp = dif->file;
+	}
+	map->m_daxdev = dif->dax_dev;
+	map->m_dax_part_off = dif->dax_part_off;
+	map->m_fscache = dif->fscache;
+}
+
 int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 {
 	struct erofs_dev_context *devs = EROFS_SB(sb)->devs;
 	struct erofs_device_info *dif;
+	erofs_off_t startoff, length;
 	int id;
 
 	map->m_bdev = sb->s_bdev;
 	map->m_daxdev = EROFS_SB(sb)->dax_dev;
 	map->m_dax_part_off = EROFS_SB(sb)->dax_part_off;
 	map->m_fscache = EROFS_SB(sb)->s_fscache;
+	map->m_fp = EROFS_SB(sb)->fdev;
 
 	if (map->m_deviceid) {
 		down_read(&devs->rwsem);
@@ -212,29 +224,20 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 			up_read(&devs->rwsem);
 			return 0;
 		}
-		map->m_bdev = dif->bdev_file ? file_bdev(dif->bdev_file) : NULL;
-		map->m_daxdev = dif->dax_dev;
-		map->m_dax_part_off = dif->dax_part_off;
-		map->m_fscache = dif->fscache;
+		erofs_fill_from_devinfo(map, dif);
 		up_read(&devs->rwsem);
 	} else if (devs->extra_devices && !devs->flatdev) {
 		down_read(&devs->rwsem);
 		idr_for_each_entry(&devs->tree, dif, id) {
-			erofs_off_t startoff, length;
-
 			if (!dif->mapped_blkaddr)
 				continue;
+
 			startoff = erofs_pos(sb, dif->mapped_blkaddr);
 			length = erofs_pos(sb, dif->blocks);
-
 			if (map->m_pa >= startoff &&
 			    map->m_pa < startoff + length) {
 				map->m_pa -= startoff;
-				map->m_bdev = dif->bdev_file ?
-					      file_bdev(dif->bdev_file) : NULL;
-				map->m_daxdev = dif->dax_dev;
-				map->m_dax_part_off = dif->dax_part_off;
-				map->m_fscache = dif->fscache;
+				erofs_fill_from_devinfo(map, dif);
 				break;
 			}
 		}
@@ -243,6 +246,42 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 	return 0;
 }
 
+/*
+ * bit 30: I/O error occurred on this folio
+ * bit 0 - 29: remaining parts to complete this folio
+ */
+#define EROFS_ONLINEFOLIO_EIO			(1 << 30)
+
+void erofs_onlinefolio_init(struct folio *folio)
+{
+	union {
+		atomic_t o;
+		void *v;
+	} u = { .o = ATOMIC_INIT(1) };
+
+	folio->private = u.v;	/* valid only if file-backed folio is locked */
+}
+
+void erofs_onlinefolio_split(struct folio *folio)
+{
+	atomic_inc((atomic_t *)&folio->private);
+}
+
+void erofs_onlinefolio_end(struct folio *folio, int err)
+{
+	int orig, v;
+
+	do {
+		orig = atomic_read((atomic_t *)&folio->private);
+		v = (orig - 1) | (err ? EROFS_ONLINEFOLIO_EIO : 0);
+	} while (atomic_cmpxchg((atomic_t *)&folio->private, orig, v) != orig);
+
+	if (v & ~EROFS_ONLINEFOLIO_EIO)
+		return;
+	folio->private = 0;
+	folio_end_read(folio, !(v & EROFS_ONLINEFOLIO_EIO));
+}
+
 static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
 {
@@ -392,7 +431,7 @@ static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 }
 
 /* for uncompressed (aligned) files and raw access for other files */
-const struct address_space_operations erofs_raw_access_aops = {
+const struct address_space_operations erofs_aops = {
 	.read_folio = erofs_read_folio,
 	.readahead = erofs_readahead,
 	.bmap = erofs_bmap,

fs/erofs/decompressor.c

@@ -539,7 +539,7 @@ int __init z_erofs_init_decompressor(void)
 	for (i = 0; i < Z_EROFS_COMPRESSION_MAX; ++i) {
 		err = z_erofs_decomp[i] ? z_erofs_decomp[i]->init() : 0;
 		if (err) {
-			while (--i)
+			while (i--)
 				if (z_erofs_decomp[i])
 					z_erofs_decomp[i]->exit();
 			return err;

fs/erofs/erofs_fs.h

@@ -288,9 +288,12 @@ struct erofs_dirent {
 
 #define EROFS_NAME_LEN      255
 
-/* maximum supported size of a physical compression cluster */
+/* maximum supported encoded size of a physical compressed cluster */
 #define Z_EROFS_PCLUSTER_MAX_SIZE	(1024 * 1024)
 
+/* maximum supported decoded size of a physical compressed cluster */
+#define Z_EROFS_PCLUSTER_MAX_DSIZE	(12 * 1024 * 1024)
+
 /* available compression algorithm types (for h_algorithmtype) */
 enum {
 	Z_EROFS_COMPRESSION_LZ4		= 0,

fs/erofs/fileio.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2024, Alibaba Cloud
+ */
+#include "internal.h"
+#include <trace/events/erofs.h>
+
+struct erofs_fileio_rq {
+	struct bio_vec bvecs[BIO_MAX_VECS];
+	struct bio bio;
+	struct kiocb iocb;
+};
+
+struct erofs_fileio {
+	struct erofs_map_blocks map;
+	struct erofs_map_dev dev;
+	struct erofs_fileio_rq *rq;
+};
+
+static void erofs_fileio_ki_complete(struct kiocb *iocb, long ret)
+{
+	struct erofs_fileio_rq *rq =
+			container_of(iocb, struct erofs_fileio_rq, iocb);
+	struct folio_iter fi;
+
+	if (ret > 0) {
+		if (ret != rq->bio.bi_iter.bi_size) {
+			bio_advance(&rq->bio, ret);
+			zero_fill_bio(&rq->bio);
+		}
+		ret = 0;
+	}
+	if (rq->bio.bi_end_io) {
+		rq->bio.bi_end_io(&rq->bio);
+	} else {
+		bio_for_each_folio_all(fi, &rq->bio) {
+			DBG_BUGON(folio_test_uptodate(fi.folio));
+			erofs_onlinefolio_end(fi.folio, ret);
+		}
+	}
+	bio_uninit(&rq->bio);
+	kfree(rq);
+}
+
+static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq)
+{
+	struct iov_iter iter;
+	int ret;
+
+	if (!rq)
+		return;
+	rq->iocb.ki_pos = rq->bio.bi_iter.bi_sector << SECTOR_SHIFT;
+	rq->iocb.ki_ioprio = get_current_ioprio();
+	rq->iocb.ki_complete = erofs_fileio_ki_complete;
+	rq->iocb.ki_flags = (rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) ?
+				IOCB_DIRECT : 0;
+	iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt,
+		      rq->bio.bi_iter.bi_size);
+	ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter);
+	if (ret != -EIOCBQUEUED)
+		erofs_fileio_ki_complete(&rq->iocb, ret);
+}
+
+static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev)
+{
+	struct erofs_fileio_rq *rq = kzalloc(sizeof(*rq),
+					     GFP_KERNEL | __GFP_NOFAIL);
+
+	bio_init(&rq->bio, NULL, rq->bvecs, BIO_MAX_VECS, REQ_OP_READ);
+	rq->iocb.ki_filp = mdev->m_fp;
+	return rq;
+}
+
+struct bio *erofs_fileio_bio_alloc(struct erofs_map_dev *mdev)
+{
+	return &erofs_fileio_rq_alloc(mdev)->bio;
+}
+
+void erofs_fileio_submit_bio(struct bio *bio)
+{
+	return erofs_fileio_rq_submit(container_of(bio, struct erofs_fileio_rq,
+						   bio));
+}
+
+static int erofs_fileio_scan_folio(struct erofs_fileio *io, struct folio *folio)
+{
+	struct inode *inode = folio_inode(folio);
+	struct erofs_map_blocks *map = &io->map;
+	unsigned int cur = 0, end = folio_size(folio), len, attached = 0;
+	loff_t pos = folio_pos(folio), ofs;
+	struct iov_iter iter;
+	struct bio_vec bv;
+	int err = 0;
+
+	erofs_onlinefolio_init(folio);
+	while (cur < end) {
+		if (!in_range(pos + cur, map->m_la, map->m_llen)) {
+			map->m_la = pos + cur;
+			map->m_llen = end - cur;
+			err = erofs_map_blocks(inode, map);
+			if (err)
+				break;
+		}
+
+		ofs = folio_pos(folio) + cur - map->m_la;
+		len = min_t(loff_t, map->m_llen - ofs, end - cur);
+		if (map->m_flags & EROFS_MAP_META) {
+			struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
+			void *src;
+
+			src = erofs_read_metabuf(&buf, inode->i_sb,
+						 map->m_pa + ofs, EROFS_KMAP);
+			if (IS_ERR(src)) {
+				err = PTR_ERR(src);
+				break;
+			}
+			bvec_set_folio(&bv, folio, len, cur);
+			iov_iter_bvec(&iter, ITER_DEST, &bv, 1, len);
+			if (copy_to_iter(src, len, &iter) != len) {
+				erofs_put_metabuf(&buf);
+				err = -EIO;
+				break;
+			}
+			erofs_put_metabuf(&buf);
+		} else if (!(map->m_flags & EROFS_MAP_MAPPED)) {
+			folio_zero_segment(folio, cur, cur + len);
+			attached = 0;
+		} else {
+			if (io->rq && (map->m_pa + ofs != io->dev.m_pa ||
+				       map->m_deviceid != io->dev.m_deviceid)) {
+io_retry:
+				erofs_fileio_rq_submit(io->rq);
+				io->rq = NULL;
+			}
+
+			if (!io->rq) {
+				io->dev = (struct erofs_map_dev) {
+					.m_pa = io->map.m_pa + ofs,
+					.m_deviceid = io->map.m_deviceid,
+				};
+				err = erofs_map_dev(inode->i_sb, &io->dev);
+				if (err)
+					break;
+				io->rq = erofs_fileio_rq_alloc(&io->dev);
+				io->rq->bio.bi_iter.bi_sector = io->dev.m_pa >> 9;
+				attached = 0;
+			}
+			if (!attached++)
+				erofs_onlinefolio_split(folio);
+			if (!bio_add_folio(&io->rq->bio, folio, len, cur))
+				goto io_retry;
+			io->dev.m_pa += len;
+		}
+		cur += len;
+	}
+	erofs_onlinefolio_end(folio, err);
+	return err;
+}
+
+static int erofs_fileio_read_folio(struct file *file, struct folio *folio)
+{
+	struct erofs_fileio io = {};
+	int err;
+
+	trace_erofs_read_folio(folio, true);
+	err = erofs_fileio_scan_folio(&io, folio);
+	erofs_fileio_rq_submit(io.rq);
+	return err;
+}
+
+static void erofs_fileio_readahead(struct readahead_control *rac)
+{
+	struct inode *inode = rac->mapping->host;
+	struct erofs_fileio io = {};
+	struct folio *folio;
+	int err;
+
+	trace_erofs_readpages(inode, readahead_index(rac),
+			      readahead_count(rac), true);
+	while ((folio = readahead_folio(rac))) {
+		err = erofs_fileio_scan_folio(&io, folio);
+		if (err && err != -EINTR)
+			erofs_err(inode->i_sb, "readahead error at folio %lu @ nid %llu",
+				  folio->index, EROFS_I(inode)->nid);
+	}
+	erofs_fileio_rq_submit(io.rq);
+}
+
+const struct address_space_operations erofs_fileio_aops = {
+	.read_folio = erofs_fileio_read_folio,
+	.readahead = erofs_fileio_readahead,
+};

fs/erofs/inode.c

@@ -5,11 +5,26 @@
  * Copyright (C) 2021, Alibaba Cloud
  */
 #include "xattr.h"
-
 #include <trace/events/erofs.h>
 
-static void *erofs_read_inode(struct erofs_buf *buf,
-			      struct inode *inode, unsigned int *ofs)
+static int erofs_fill_symlink(struct inode *inode, void *kaddr,
+			      unsigned int m_pofs)
+{
+	struct erofs_inode *vi = EROFS_I(inode);
+	loff_t off;
+
+	m_pofs += vi->xattr_isize;
+	/* check if it cannot be handled with fast symlink scheme */
+	if (vi->datalayout != EROFS_INODE_FLAT_INLINE ||
+	    check_add_overflow(m_pofs, inode->i_size, &off) ||
+	    off > i_blocksize(inode))
+		return 0;
+
+	inode->i_link = kmemdup_nul(kaddr + m_pofs, inode->i_size, GFP_KERNEL);
+	return inode->i_link ? 0 : -ENOMEM;
+}
+
+static int erofs_read_inode(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
@@ -20,20 +35,21 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 	struct erofs_inode_compact *dic;
 	struct erofs_inode_extended *die, *copied = NULL;
 	union erofs_inode_i_u iu;
-	unsigned int ifmt;
-	int err;
+	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
+	unsigned int ifmt, ofs;
+	int err = 0;
 
 	blkaddr = erofs_blknr(sb, inode_loc);
-	*ofs = erofs_blkoff(sb, inode_loc);
+	ofs = erofs_blkoff(sb, inode_loc);
 
-	kaddr = erofs_read_metabuf(buf, sb, erofs_pos(sb, blkaddr), EROFS_KMAP);
+	kaddr = erofs_read_metabuf(&buf, sb, erofs_pos(sb, blkaddr), EROFS_KMAP);
 	if (IS_ERR(kaddr)) {
 		erofs_err(sb, "failed to get inode (nid: %llu) page, err %ld",
 			  vi->nid, PTR_ERR(kaddr));
-		return kaddr;
+		return PTR_ERR(kaddr);
 	}
 
-	dic = kaddr + *ofs;
+	dic = kaddr + ofs;
 	ifmt = le16_to_cpu(dic->i_format);
 	if (ifmt & ~EROFS_I_ALL) {
 		erofs_err(sb, "unsupported i_format %u of nid %llu",
@@ -54,11 +70,11 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 	case EROFS_INODE_LAYOUT_EXTENDED:
 		vi->inode_isize = sizeof(struct erofs_inode_extended);
 		/* check if the extended inode acrosses block boundary */
-		if (*ofs + vi->inode_isize <= sb->s_blocksize) {
-			*ofs += vi->inode_isize;
+		if (ofs + vi->inode_isize <= sb->s_blocksize) {
+			ofs += vi->inode_isize;
 			die = (struct erofs_inode_extended *)dic;
 		} else {
-			const unsigned int gotten = sb->s_blocksize - *ofs;
+			const unsigned int gotten = sb->s_blocksize - ofs;
 
 			copied = kmalloc(vi->inode_isize, GFP_KERNEL);
 			if (!copied) {
@@ -66,16 +82,16 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 				goto err_out;
 			}
 			memcpy(copied, dic, gotten);
-			kaddr = erofs_read_metabuf(buf, sb, erofs_pos(sb, blkaddr + 1),
+			kaddr = erofs_read_metabuf(&buf, sb, erofs_pos(sb, blkaddr + 1),
 						   EROFS_KMAP);
 			if (IS_ERR(kaddr)) {
 				erofs_err(sb, "failed to get inode payload block (nid: %llu), err %ld",
 					  vi->nid, PTR_ERR(kaddr));
 				kfree(copied);
-				return kaddr;
+				return PTR_ERR(kaddr);
 			}
-			*ofs = vi->inode_isize - gotten;
-			memcpy((u8 *)copied + gotten, kaddr, *ofs);
+			ofs = vi->inode_isize - gotten;
+			memcpy((u8 *)copied + gotten, kaddr, ofs);
 			die = copied;
 		}
 		vi->xattr_isize = erofs_xattr_ibody_size(die->i_xattr_icount);
@@ -91,11 +107,10 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 
 		inode->i_size = le64_to_cpu(die->i_size);
 		kfree(copied);
-		copied = NULL;
 		break;
 	case EROFS_INODE_LAYOUT_COMPACT:
 		vi->inode_isize = sizeof(struct erofs_inode_compact);
-		*ofs += vi->inode_isize;
+		ofs += vi->inode_isize;
 		vi->xattr_isize = erofs_xattr_ibody_size(dic->i_xattr_icount);
 
 		inode->i_mode = le16_to_cpu(dic->i_mode);
@@ -115,11 +130,21 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 		goto err_out;
 	}
 
+	if (unlikely(inode->i_size < 0)) {
+		erofs_err(sb, "negative i_size @ nid %llu", vi->nid);
+		err = -EFSCORRUPTED;
+		goto err_out;
+	}
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
 	case S_IFDIR:
 	case S_IFLNK:
 		vi->raw_blkaddr = le32_to_cpu(iu.raw_blkaddr);
+		if(S_ISLNK(inode->i_mode)) {
+			err = erofs_fill_symlink(inode, kaddr, ofs);
+			if (err)
+				goto err_out;
+		}
 		break;
 	case S_IFCHR:
 	case S_IFBLK:
@@ -165,65 +190,23 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 		inode->i_blocks = round_up(inode->i_size, sb->s_blocksize) >> 9;
 	else
 		inode->i_blocks = nblks << (sb->s_blocksize_bits - 9);
-	return kaddr;
-
 err_out:
-	DBG_BUGON(1);
-	kfree(copied);
-	erofs_put_metabuf(buf);
-	return ERR_PTR(err);
-}
-
-static int erofs_fill_symlink(struct inode *inode, void *kaddr,
-			      unsigned int m_pofs)
-{
-	struct erofs_inode *vi = EROFS_I(inode);
-	unsigned int bsz = i_blocksize(inode);
-	char *lnk;
-
-	/* if it cannot be handled with fast symlink scheme */
-	if (vi->datalayout != EROFS_INODE_FLAT_INLINE ||
-	    inode->i_size >= bsz || inode->i_size < 0) {
-		inode->i_op = &erofs_symlink_iops;
-		return 0;
-	}
-
-	lnk = kmalloc(inode->i_size + 1, GFP_KERNEL);
-	if (!lnk)
-		return -ENOMEM;
-
-	m_pofs += vi->xattr_isize;
-	/* inline symlink data shouldn't cross block boundary */
-	if (m_pofs + inode->i_size > bsz) {
-		kfree(lnk);
-		erofs_err(inode->i_sb,
-			  "inline data cross block boundary @ nid %llu",
-			  vi->nid);
-		DBG_BUGON(1);
-		return -EFSCORRUPTED;
-	}
-	memcpy(lnk, kaddr + m_pofs, inode->i_size);
-	lnk[inode->i_size] = '\0';
-
-	inode->i_link = lnk;
-	inode->i_op = &erofs_fast_symlink_iops;
-	return 0;
+	DBG_BUGON(err);
+	erofs_put_metabuf(&buf);
+	return err;
 }
 
 static int erofs_fill_inode(struct inode *inode)
 {
 	struct erofs_inode *vi = EROFS_I(inode);
-	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
-	void *kaddr;
-	unsigned int ofs;
-	int err = 0;
+	int err;
 
 	trace_erofs_fill_inode(inode);
 
 	/* read inode base data from disk */
-	kaddr = erofs_read_inode(&buf, inode, &ofs);
-	if (IS_ERR(kaddr))
-		return PTR_ERR(kaddr);
+	err = erofs_read_inode(inode);
+	if (err)
+		return err;
 
 	/* setup the new inode */
 	switch (inode->i_mode & S_IFMT) {
@@ -240,9 +223,10 @@ static int erofs_fill_inode(struct inode *inode)
 		inode_nohighmem(inode);
 		break;
 	case S_IFLNK:
-		err = erofs_fill_symlink(inode, kaddr, ofs);
-		if (err)
-			goto out_unlock;
+		if (inode->i_link)
+			inode->i_op = &erofs_fast_symlink_iops;
+		else
+			inode->i_op = &erofs_symlink_iops;
 		inode_nohighmem(inode);
 		break;
 	case S_IFCHR:
@@ -251,10 +235,9 @@ static int erofs_fill_inode(struct inode *inode)
 	case S_IFSOCK:
 		inode->i_op = &erofs_generic_iops;
 		init_special_inode(inode, inode->i_mode, inode->i_rdev);
-		goto out_unlock;
+		return 0;
 	default:
-		err = -EFSCORRUPTED;
-		goto out_unlock;
+		return -EFSCORRUPTED;
 	}
 
 	mapping_set_large_folios(inode->i_mapping);
@@ -268,14 +251,17 @@ static int erofs_fill_inode(struct inode *inode)
 		err = -EOPNOTSUPP;
 #endif
 	} else {
-		inode->i_mapping->a_ops = &erofs_raw_access_aops;
+		inode->i_mapping->a_ops = &erofs_aops;
 #ifdef CONFIG_EROFS_FS_ONDEMAND
 		if (erofs_is_fscache_mode(inode->i_sb))
 			inode->i_mapping->a_ops = &erofs_fscache_access_aops;
+#endif
+#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
+		if (erofs_is_fileio_mode(EROFS_SB(inode->i_sb)))
+			inode->i_mapping->a_ops = &erofs_fileio_aops;
 #endif
 	}
-out_unlock:
-	erofs_put_metabuf(&buf);
+
 	return err;
 }
 

fs/erofs/internal.h

@@ -49,7 +49,7 @@ typedef u32 erofs_blk_t;
 struct erofs_device_info {
 	char *path;
 	struct erofs_fscache *fscache;
-	struct file *bdev_file;
+	struct file *file;
 	struct dax_device *dax_dev;
 	u64 dax_part_off;
 
@@ -130,6 +130,7 @@ struct erofs_sb_info {
 
 	struct erofs_sb_lz4_info lz4;
 #endif	/* CONFIG_EROFS_FS_ZIP */
+	struct file *fdev;
 	struct inode *packed_inode;
 	struct erofs_dev_context *devs;
 	struct dax_device *dax_dev;
@@ -190,9 +191,15 @@ struct erofs_sb_info {
 #define set_opt(opt, option)	((opt)->mount_opt |= EROFS_MOUNT_##option)
 #define test_opt(opt, option)	((opt)->mount_opt & EROFS_MOUNT_##option)
 
+static inline bool erofs_is_fileio_mode(struct erofs_sb_info *sbi)
+{
+	return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->fdev;
+}
+
 static inline bool erofs_is_fscache_mode(struct super_block *sb)
 {
-	return IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && !sb->s_bdev;
+	return IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) &&
+			!erofs_is_fileio_mode(EROFS_SB(sb)) && !sb->s_bdev;
 }
 
 enum {
@@ -365,6 +372,7 @@ struct erofs_map_dev {
 	struct erofs_fscache *m_fscache;
 	struct block_device *m_bdev;
 	struct dax_device *m_daxdev;
+	struct file *m_fp;
 	u64 m_dax_part_off;
 
 	erofs_off_t m_pa;
@@ -373,7 +381,8 @@ struct erofs_map_dev {
 
 extern const struct super_operations erofs_sops;
 
-extern const struct address_space_operations erofs_raw_access_aops;
+extern const struct address_space_operations erofs_aops;
+extern const struct address_space_operations erofs_fileio_aops;
 extern const struct address_space_operations z_erofs_aops;
 extern const struct address_space_operations erofs_fscache_access_aops;
 
@@ -404,6 +413,9 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *dev);
 int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		 u64 start, u64 len);
 int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map);
+void erofs_onlinefolio_init(struct folio *folio);
+void erofs_onlinefolio_split(struct folio *folio);
+void erofs_onlinefolio_end(struct folio *folio, int err);
 struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid);
 int erofs_getattr(struct mnt_idmap *idmap, const struct path *path,
 		  struct kstat *stat, u32 request_mask,
@@ -477,6 +489,14 @@ static inline void z_erofs_exit_subsystem(void) {}
 static inline int erofs_init_managed_cache(struct super_block *sb) { return 0; }
 #endif	/* !CONFIG_EROFS_FS_ZIP */
 
+#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
+struct bio *erofs_fileio_bio_alloc(struct erofs_map_dev *mdev);
+void erofs_fileio_submit_bio(struct bio *bio);
+#else
+static inline struct bio *erofs_fileio_bio_alloc(struct erofs_map_dev *mdev) { return NULL; }
+static inline void erofs_fileio_submit_bio(struct bio *bio) {}
+#endif
+
 #ifdef CONFIG_EROFS_FS_ONDEMAND
 int erofs_fscache_register_fs(struct super_block *sb);
 void erofs_fscache_unregister_fs(struct super_block *sb);

fs/erofs/super.c

@@ -10,6 +10,7 @@
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
 #include <linux/exportfs.h>
+#include <linux/backing-dev.h>
 #include "xattr.h"
 
 #define CREATE_TRACE_POINTS
@@ -161,7 +162,7 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
 	struct erofs_fscache *fscache;
 	struct erofs_deviceslot *dis;
-	struct file *bdev_file;
+	struct file *file;
 
 	dis = erofs_read_metabuf(buf, sb, *pos, EROFS_KMAP);
 	if (IS_ERR(dis))
@@ -183,13 +184,17 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 			return PTR_ERR(fscache);
 		dif->fscache = fscache;
 	} else if (!sbi->devs->flatdev) {
-		bdev_file = bdev_file_open_by_path(dif->path, BLK_OPEN_READ,
-						sb->s_type, NULL);
-		if (IS_ERR(bdev_file))
-			return PTR_ERR(bdev_file);
-		dif->bdev_file = bdev_file;
-		dif->dax_dev = fs_dax_get_by_bdev(file_bdev(bdev_file),
-				&dif->dax_part_off, NULL, NULL);
+		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))
+			return PTR_ERR(file);
+
+		dif->file = file;
+		if (!erofs_is_fileio_mode(sbi))
+			dif->dax_dev = fs_dax_get_by_bdev(file_bdev(file),
+					&dif->dax_part_off, NULL, NULL);
 	}
 
 	dif->blocks = le32_to_cpu(dis->blocks);
@@ -348,7 +353,7 @@ static int erofs_read_superblock(struct super_block *sb)
 	ret = erofs_scan_devices(sb, dsb);
 
 	if (erofs_is_fscache_mode(sb))
-		erofs_info(sb, "EXPERIMENTAL fscache-based on-demand read feature in use. Use at your own risk!");
+		erofs_info(sb, "[deprecated] fscache-based on-demand read feature in use. Use at your own risk!");
 out:
 	erofs_put_metabuf(&buf);
 	return ret;
@@ -566,15 +571,16 @@ static void erofs_set_sysfs_name(struct super_block *sb)
 {
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
 
-	if (erofs_is_fscache_mode(sb)) {
-		if (sbi->domain_id)
-			super_set_sysfs_name_generic(sb, "%s,%s",sbi->domain_id,
-						     sbi->fsid);
-		else
-			super_set_sysfs_name_generic(sb, "%s", sbi->fsid);
-		return;
-	}
-	super_set_sysfs_name_id(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);
 }
 
 static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
@@ -589,14 +595,15 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_op = &erofs_sops;
 
 	sbi->blkszbits = PAGE_SHIFT;
-	if (erofs_is_fscache_mode(sb)) {
+	if (!sb->s_bdev) {
 		sb->s_blocksize = PAGE_SIZE;
 		sb->s_blocksize_bits = PAGE_SHIFT;
 
-		err = erofs_fscache_register_fs(sb);
-		if (err)
-			return err;
-
+		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;
@@ -644,7 +651,6 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 		sb->s_flags |= SB_POSIXACL;
 	else
 		sb->s_flags &= ~SB_POSIXACL;
-	erofs_set_sysfs_name(sb);
 
 #ifdef CONFIG_EROFS_FS_ZIP
 	xa_init(&sbi->managed_pslots);
@@ -682,6 +688,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (err)
 		return err;
 
+	erofs_set_sysfs_name(sb);
 	err = erofs_register_sysfs(sb);
 	if (err)
 		return err;
@@ -693,11 +700,24 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 static int erofs_fc_get_tree(struct fs_context *fc)
 {
 	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);
 
-	return get_tree_bdev(fc, erofs_fc_fill_super);
+	ret = get_tree_bdev(fc, erofs_fc_fill_super);
+#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
+	if (ret == -ENOTBLK) {
+		if (!fc->source)
+			return invalf(fc, "No source specified");
+		sbi->fdev = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0);
+		if (IS_ERR(sbi->fdev))
+			return PTR_ERR(sbi->fdev);
+
+		return get_tree_nodev(fc, erofs_fc_fill_super);
+	}
+#endif
+	return ret;
 }
 
 static int erofs_fc_reconfigure(struct fs_context *fc)
@@ -727,8 +747,8 @@ static int erofs_release_device_info(int id, void *ptr, void *data)
 	struct erofs_device_info *dif = ptr;
 
 	fs_put_dax(dif->dax_dev, NULL);
-	if (dif->bdev_file)
-		fput(dif->bdev_file);
+	if (dif->file)
+		fput(dif->file);
 	erofs_fscache_unregister_cookie(dif->fscache);
 	dif->fscache = NULL;
 	kfree(dif->path);
@@ -791,7 +811,7 @@ static void erofs_kill_sb(struct super_block *sb)
 {
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
 
-	if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid)
+	if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || sbi->fdev)
 		kill_anon_super(sb);
 	else
 		kill_block_super(sb);
@@ -801,6 +821,8 @@ static void erofs_kill_sb(struct super_block *sb)
 	erofs_fscache_unregister_fs(sb);
 	kfree(sbi->fsid);
 	kfree(sbi->domain_id);
+	if (sbi->fdev)
+		fput(sbi->fdev);
 	kfree(sbi);
 	sb->s_fs_info = NULL;
 }
@@ -903,7 +925,7 @@ static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_namelen = EROFS_NAME_LEN;
 
 	if (uuid_is_null(&sb->s_uuid))
-		buf->f_fsid = u64_to_fsid(erofs_is_fscache_mode(sb) ? 0 :
+		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);

fs/erofs/sysfs.c

@@ -205,34 +205,16 @@ static struct kobject erofs_feat = {
 int erofs_register_sysfs(struct super_block *sb)
 {
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
-	char *name;
-	char *str = NULL;
 	int err;
 
-	if (erofs_is_fscache_mode(sb)) {
-		if (sbi->domain_id) {
-			str = kasprintf(GFP_KERNEL, "%s,%s", sbi->domain_id,
-					sbi->fsid);
-			if (!str)
-				return -ENOMEM;
-			name = str;
-		} else {
-			name = sbi->fsid;
-		}
-	} else {
-		name = sb->s_id;
-	}
 	sbi->s_kobj.kset = &erofs_root;
 	init_completion(&sbi->s_kobj_unregister);
-	err = kobject_init_and_add(&sbi->s_kobj, &erofs_sb_ktype, NULL, "%s", name);
-	kfree(str);
-	if (err)
-		goto put_sb_kobj;
-	return 0;
-
-put_sb_kobj:
-	kobject_put(&sbi->s_kobj);
-	wait_for_completion(&sbi->s_kobj_unregister);
+	err = kobject_init_and_add(&sbi->s_kobj, &erofs_sb_ktype, NULL, "%s",
+				   sb->s_sysfs_name);
+	if (err) {
+		kobject_put(&sbi->s_kobj);
+		wait_for_completion(&sbi->s_kobj_unregister);
+	}
 	return err;
 }
 

fs/erofs/zdata.c

@@ -122,42 +122,6 @@ static bool erofs_folio_is_managed(struct erofs_sb_info *sbi, struct folio *fo)
 	return fo->mapping == MNGD_MAPPING(sbi);
 }
 
-/*
- * bit 30: I/O error occurred on this folio
- * bit 0 - 29: remaining parts to complete this folio
- */
-#define Z_EROFS_FOLIO_EIO			(1 << 30)
-
-static void z_erofs_onlinefolio_init(struct folio *folio)
-{
-	union {
-		atomic_t o;
-		void *v;
-	} u = { .o = ATOMIC_INIT(1) };
-
-	folio->private = u.v;	/* valid only if file-backed folio is locked */
-}
-
-static void z_erofs_onlinefolio_split(struct folio *folio)
-{
-	atomic_inc((atomic_t *)&folio->private);
-}
-
-static void z_erofs_onlinefolio_end(struct folio *folio, int err)
-{
-	int orig, v;
-
-	do {
-		orig = atomic_read((atomic_t *)&folio->private);
-		v = (orig - 1) | (err ? Z_EROFS_FOLIO_EIO : 0);
-	} while (atomic_cmpxchg((atomic_t *)&folio->private, orig, v) != orig);
-
-	if (v & ~Z_EROFS_FOLIO_EIO)
-		return;
-	folio->private = 0;
-	folio_end_read(folio, !(v & Z_EROFS_FOLIO_EIO));
-}
-
 #define Z_EROFS_ONSTACK_PAGES		32
 
 /*
@@ -232,7 +196,8 @@ static int z_erofs_bvec_enqueue(struct z_erofs_bvec_iter *iter,
 		struct page *nextpage = *candidate_bvpage;
 
 		if (!nextpage) {
-			nextpage = erofs_allocpage(pagepool, GFP_KERNEL);
+			nextpage = __erofs_allocpage(pagepool, GFP_KERNEL,
+					true);
 			if (!nextpage)
 				return -ENOMEM;
 			set_page_private(nextpage, Z_EROFS_SHORTLIVED_PAGE);
@@ -965,7 +930,7 @@ static int z_erofs_scan_folio(struct z_erofs_decompress_frontend *f,
 	int err = 0;
 
 	tight = (bs == PAGE_SIZE);
-	z_erofs_onlinefolio_init(folio);
+	erofs_onlinefolio_init(folio);
 	do {
 		if (offset + end - 1 < map->m_la ||
 		    offset + end - 1 >= map->m_la + map->m_llen) {
@@ -1024,7 +989,7 @@ static int z_erofs_scan_folio(struct z_erofs_decompress_frontend *f,
 			if (err)
 				break;
 
-			z_erofs_onlinefolio_split(folio);
+			erofs_onlinefolio_split(folio);
 			if (f->pcl->pageofs_out != (map->m_la & ~PAGE_MASK))
 				f->pcl->multibases = true;
 			if (f->pcl->length < offset + end - map->m_la) {
@@ -1044,7 +1009,7 @@ static int z_erofs_scan_folio(struct z_erofs_decompress_frontend *f,
 			tight = (bs == PAGE_SIZE);
 		}
 	} while ((end = cur) > 0);
-	z_erofs_onlinefolio_end(folio, err);
+	erofs_onlinefolio_end(folio, err);
 	return err;
 }
 
@@ -1147,7 +1112,7 @@ static void z_erofs_fill_other_copies(struct z_erofs_decompress_backend *be,
 			cur += len;
 		}
 		kunmap_local(dst);
-		z_erofs_onlinefolio_end(page_folio(bvi->bvec.page), err);
+		erofs_onlinefolio_end(page_folio(bvi->bvec.page), err);
 		list_del(p);
 		kfree(bvi);
 	}
@@ -1190,9 +1155,10 @@ static int z_erofs_parse_in_bvecs(struct z_erofs_decompress_backend *be,
 		struct z_erofs_bvec *bvec = &pcl->compressed_bvecs[i];
 		struct page *page = bvec->page;
 
-		/* compressed data ought to be valid before decompressing */
-		if (!page) {
-			err = -EIO;
+		/* compressed data ought to be valid when decompressing */
+		if (IS_ERR(page) || !page) {
+			bvec->page = NULL;	/* clear the failure reason */
+			err = page ? PTR_ERR(page) : -EIO;
 			continue;
 		}
 		be->compressed_pages[i] = page;
@@ -1268,8 +1234,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 					.inplace_io = overlapped,
 					.partial_decoding = pcl->partial,
 					.fillgaps = pcl->multibases,
-					.gfp = pcl->besteffort ?
-						GFP_KERNEL | __GFP_NOFAIL :
+					.gfp = pcl->besteffort ? GFP_KERNEL :
 						GFP_NOWAIT | __GFP_NORETRY
 				 }, be->pagepool);
 
@@ -1302,7 +1267,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 
 		DBG_BUGON(z_erofs_page_is_invalidated(page));
 		if (!z_erofs_is_shortlived_page(page)) {
-			z_erofs_onlinefolio_end(page_folio(page), err);
+			erofs_onlinefolio_end(page_folio(page), err);
 			continue;
 		}
 		if (pcl->algorithmformat != Z_EROFS_COMPRESSION_LZ4) {
@@ -1333,8 +1298,8 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 	return err;
 }
 
-static void z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io,
-				     struct page **pagepool)
+static int z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io,
+				    struct page **pagepool)
 {
 	struct z_erofs_decompress_backend be = {
 		.sb = io->sb,
@@ -1343,6 +1308,7 @@ static void z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io,
 			LIST_HEAD_INIT(be.decompressed_secondary_bvecs),
 	};
 	z_erofs_next_pcluster_t owned = io->head;
+	int err = io->eio ? -EIO : 0;
 
 	while (owned != Z_EROFS_PCLUSTER_TAIL) {
 		DBG_BUGON(owned == Z_EROFS_PCLUSTER_NIL);
@@ -1350,12 +1316,13 @@ static void z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io,
 		be.pcl = container_of(owned, struct z_erofs_pcluster, next);
 		owned = READ_ONCE(be.pcl->next);
 
-		z_erofs_decompress_pcluster(&be, io->eio ? -EIO : 0);
+		err = z_erofs_decompress_pcluster(&be, err) ?: err;
 		if (z_erofs_is_inline_pcluster(be.pcl))
 			z_erofs_free_pcluster(be.pcl);
 		else
 			erofs_workgroup_put(&be.pcl->obj);
 	}
+	return err;
 }
 
 static void z_erofs_decompressqueue_work(struct work_struct *work)
@@ -1428,6 +1395,7 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
 	struct z_erofs_bvec zbv;
 	struct address_space *mapping;
 	struct folio *folio;
+	struct page *page;
 	int bs = i_blocksize(f->inode);
 
 	/* Except for inplace folios, the entire folio can be used for I/Os */
@@ -1450,7 +1418,6 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
 	 * file-backed folios will be used instead.
 	 */
 	if (folio->private == (void *)Z_EROFS_PREALLOCATED_PAGE) {
-		folio->private = 0;
 		tocache = true;
 		goto out_tocache;
 	}
@@ -1468,7 +1435,7 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
 	}
 
 	folio_lock(folio);
-	if (folio->mapping == mc) {
+	if (likely(folio->mapping == mc)) {
 		/*
 		 * The cached folio is still in managed cache but without
 		 * a valid `->private` pcluster hint.  Let's reconnect them.
@@ -1478,41 +1445,48 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
 			/* compressed_bvecs[] already takes a ref before */
 			folio_put(folio);
 		}
-
-		/* no need to submit if it is already up-to-date */
-		if (folio_test_uptodate(folio)) {
-			folio_unlock(folio);
-			bvec->bv_page = NULL;
+		if (likely(folio->private == pcl))  {
+			/* don't submit cache I/Os again if already uptodate */
+			if (folio_test_uptodate(folio)) {
+				folio_unlock(folio);
+				bvec->bv_page = NULL;
+			}
+			return;
 		}
-		return;
+		/*
+		 * Already linked with another pcluster, which only appears in
+		 * crafted images by fuzzers for now.  But handle this anyway.
+		 */
+		tocache = false;	/* use temporary short-lived pages */
+	} else {
+		DBG_BUGON(1); /* referenced managed folios can't be truncated */
+		tocache = true;
 	}
-
-	/*
-	 * It has been truncated, so it's unsafe to reuse this one. Let's
-	 * allocate a new page for compressed data.
-	 */
-	DBG_BUGON(folio->mapping);
-	tocache = true;
 	folio_unlock(folio);
 	folio_put(folio);
 out_allocfolio:
-	zbv.page = erofs_allocpage(&f->pagepool, gfp | __GFP_NOFAIL);
+	page = __erofs_allocpage(&f->pagepool, gfp, true);
 	spin_lock(&pcl->obj.lockref.lock);
-	if (pcl->compressed_bvecs[nr].page) {
-		erofs_pagepool_add(&f->pagepool, zbv.page);
+	if (unlikely(pcl->compressed_bvecs[nr].page != zbv.page)) {
+		if (page)
+			erofs_pagepool_add(&f->pagepool, page);
 		spin_unlock(&pcl->obj.lockref.lock);
 		cond_resched();
 		goto repeat;
 	}
-	bvec->bv_page = pcl->compressed_bvecs[nr].page = zbv.page;
-	folio = page_folio(zbv.page);
-	/* first mark it as a temporary shortlived folio (now 1 ref) */
-	folio->private = (void *)Z_EROFS_SHORTLIVED_PAGE;
+	pcl->compressed_bvecs[nr].page = page ? page : ERR_PTR(-ENOMEM);
 	spin_unlock(&pcl->obj.lockref.lock);
+	bvec->bv_page = page;
+	if (!page)
+		return;
+	folio = page_folio(page);
 out_tocache:
 	if (!tocache || bs != PAGE_SIZE ||
-	    filemap_add_folio(mc, folio, pcl->obj.index + nr, gfp))
+	    filemap_add_folio(mc, folio, pcl->obj.index + nr, gfp)) {
+		/* turn into a temporary shortlived folio (1 ref) */
+		folio->private = (void *)Z_EROFS_SHORTLIVED_PAGE;
 		return;
+	}
 	folio_attach_private(folio, pcl);
 	/* drop a refcount added by allocpage (then 2 refs in total here) */
 	folio_put(folio);
@@ -1647,17 +1621,16 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 		cur = mdev.m_pa;
 		end = cur + pcl->pclustersize;
 		do {
-			z_erofs_fill_bio_vec(&bvec, f, pcl, i++, mc);
-			if (!bvec.bv_page)
-				continue;
-
+			bvec.bv_page = NULL;
 			if (bio && (cur != last_pa ||
 				    bio->bi_bdev != mdev.m_bdev)) {
-io_retry:
-				if (!erofs_is_fscache_mode(sb))
-					submit_bio(bio);
-				else
+drain_io:
+				if (erofs_is_fileio_mode(EROFS_SB(sb)))
+					erofs_fileio_submit_bio(bio);
+				else if (erofs_is_fscache_mode(sb))
 					erofs_fscache_submit_bio(bio);
+				else
+					submit_bio(bio);
 
 				if (memstall) {
 					psi_memstall_leave(&pflags);
@@ -1666,6 +1639,15 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 				bio = NULL;
 			}
 
+			if (!bvec.bv_page) {
+				z_erofs_fill_bio_vec(&bvec, f, pcl, i++, mc);
+				if (!bvec.bv_page)
+					continue;
+				if (cur + bvec.bv_len > end)
+					bvec.bv_len = end - cur;
+				DBG_BUGON(bvec.bv_len < sb->s_blocksize);
+			}
+
 			if (unlikely(PageWorkingset(bvec.bv_page)) &&
 			    !memstall) {
 				psi_memstall_enter(&pflags);
@@ -1673,10 +1655,13 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 			}
 
 			if (!bio) {
-				bio = erofs_is_fscache_mode(sb) ?
-					erofs_fscache_bio_alloc(&mdev) :
-					bio_alloc(mdev.m_bdev, BIO_MAX_VECS,
-						  REQ_OP_READ, GFP_NOIO);
+				if (erofs_is_fileio_mode(EROFS_SB(sb)))
+					bio = erofs_fileio_bio_alloc(&mdev);
+				else if (erofs_is_fscache_mode(sb))
+					bio = erofs_fscache_bio_alloc(&mdev);
+				else
+					bio = bio_alloc(mdev.m_bdev, BIO_MAX_VECS,
+							REQ_OP_READ, GFP_NOIO);
 				bio->bi_end_io = z_erofs_endio;
 				bio->bi_iter.bi_sector = cur >> 9;
 				bio->bi_private = q[JQ_SUBMIT];
@@ -1685,13 +1670,9 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 				++nr_bios;
 			}
 
-			if (cur + bvec.bv_len > end)
-				bvec.bv_len = end - cur;
-			DBG_BUGON(bvec.bv_len < sb->s_blocksize);
 			if (!bio_add_page(bio, bvec.bv_page, bvec.bv_len,
 					  bvec.bv_offset))
-				goto io_retry;
-
+				goto drain_io;
 			last_pa = cur + bvec.bv_len;
 			bypass = false;
 		} while ((cur += bvec.bv_len) < end);
@@ -1703,10 +1684,12 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 	} while (owned_head != Z_EROFS_PCLUSTER_TAIL);
 
 	if (bio) {
-		if (!erofs_is_fscache_mode(sb))
-			submit_bio(bio);
-		else
+		if (erofs_is_fileio_mode(EROFS_SB(sb)))
+			erofs_fileio_submit_bio(bio);
+		else if (erofs_is_fscache_mode(sb))
 			erofs_fscache_submit_bio(bio);
+		else
+			submit_bio(bio);
 		if (memstall)
 			psi_memstall_leave(&pflags);
 	}
@@ -1722,26 +1705,28 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 	z_erofs_decompress_kickoff(q[JQ_SUBMIT], nr_bios);
 }
 
-static void z_erofs_runqueue(struct z_erofs_decompress_frontend *f,
-			     bool force_fg, bool ra)
+static int z_erofs_runqueue(struct z_erofs_decompress_frontend *f,
+			    unsigned int ra_folios)
 {
 	struct z_erofs_decompressqueue io[NR_JOBQUEUES];
+	struct erofs_sb_info *sbi = EROFS_I_SB(f->inode);
+	bool force_fg = z_erofs_is_sync_decompress(sbi, ra_folios);
+	int err;
 
 	if (f->owned_head == Z_EROFS_PCLUSTER_TAIL)
-		return;
-	z_erofs_submit_queue(f, io, &force_fg, ra);
+		return 0;
+	z_erofs_submit_queue(f, io, &force_fg, !!ra_folios);
 
 	/* handle bypass queue (no i/o pclusters) immediately */
-	z_erofs_decompress_queue(&io[JQ_BYPASS], &f->pagepool);
-
+	err = z_erofs_decompress_queue(&io[JQ_BYPASS], &f->pagepool);
 	if (!force_fg)
-		return;
+		return err;
 
 	/* wait until all bios are completed */
 	wait_for_completion_io(&io[JQ_SUBMIT].u.done);
 
 	/* handle synchronous decompress queue in the caller context */
-	z_erofs_decompress_queue(&io[JQ_SUBMIT], &f->pagepool);
+	return z_erofs_decompress_queue(&io[JQ_SUBMIT], &f->pagepool) ?: err;
 }
 
 /*
@@ -1803,7 +1788,6 @@ static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f,
 static int z_erofs_read_folio(struct file *file, struct folio *folio)
 {
 	struct inode *const inode = folio->mapping->host;
-	struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
 	struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
 	int err;
 
@@ -1815,9 +1799,8 @@ static int z_erofs_read_folio(struct file *file, struct folio *folio)
 	z_erofs_pcluster_readmore(&f, NULL, false);
 	z_erofs_pcluster_end(&f);
 
-	/* if some compressed cluster ready, need submit them anyway */
-	z_erofs_runqueue(&f, z_erofs_is_sync_decompress(sbi, 0), false);
-
+	/* if some pclusters are ready, need submit them anyway */
+	err = z_erofs_runqueue(&f, 0) ?: err;
 	if (err && err != -EINTR)
 		erofs_err(inode->i_sb, "read error %d @ %lu of nid %llu",
 			  err, folio->index, EROFS_I(inode)->nid);
@@ -1830,7 +1813,6 @@ static int z_erofs_read_folio(struct file *file, struct folio *folio)
 static void z_erofs_readahead(struct readahead_control *rac)
 {
 	struct inode *const inode = rac->mapping->host;
-	struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
 	struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
 	struct folio *head = NULL, *folio;
 	unsigned int nr_folios;
@@ -1860,7 +1842,7 @@ static void z_erofs_readahead(struct readahead_control *rac)
 	z_erofs_pcluster_readmore(&f, rac, false);
 	z_erofs_pcluster_end(&f);
 
-	z_erofs_runqueue(&f, z_erofs_is_sync_decompress(sbi, nr_folios), true);
+	(void)z_erofs_runqueue(&f, nr_folios);
 	erofs_put_metabuf(&f.map.buf);
 	erofs_release_pages(&f.pagepool);
 }

fs/erofs/zmap.c

@@ -687,32 +687,30 @@ int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map,
 	int err = 0;
 
 	trace_erofs_map_blocks_enter(inode, map, flags);
-
-	/* when trying to read beyond EOF, leave it unmapped */
-	if (map->m_la >= inode->i_size) {
+	if (map->m_la >= inode->i_size) {	/* post-EOF unmapped extent */
 		map->m_llen = map->m_la + 1 - inode->i_size;
 		map->m_la = inode->i_size;
 		map->m_flags = 0;
-		goto out;
-	}
-
-	err = z_erofs_fill_inode_lazy(inode);
-	if (err)
-		goto out;
-
-	if ((vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER) &&
-	    !vi->z_tailextent_headlcn) {
-		map->m_la = 0;
-		map->m_llen = inode->i_size;
-		map->m_flags = EROFS_MAP_MAPPED | EROFS_MAP_FULL_MAPPED |
-				EROFS_MAP_FRAGMENT;
-		goto out;
+	} else {
+		err = z_erofs_fill_inode_lazy(inode);
+		if (!err) {
+			if ((vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER) &&
+			    !vi->z_tailextent_headlcn) {
+				map->m_la = 0;
+				map->m_llen = inode->i_size;
+				map->m_flags = EROFS_MAP_MAPPED |
+					EROFS_MAP_FULL_MAPPED | EROFS_MAP_FRAGMENT;
+			} else {
+				err = z_erofs_do_map_blocks(inode, map, flags);
+			}
+		}
+		if (!err && (map->m_flags & EROFS_MAP_ENCODED) &&
+		    unlikely(map->m_plen > Z_EROFS_PCLUSTER_MAX_SIZE ||
+			     map->m_llen > Z_EROFS_PCLUSTER_MAX_DSIZE))
+			err = -EOPNOTSUPP;
+		if (err)
+			map->m_llen = 0;
 	}
-
-	err = z_erofs_do_map_blocks(inode, map, flags);
-out:
-	if (err)
-		map->m_llen = 0;
 	trace_erofs_map_blocks_exit(inode, map, flags, err);
 	return err;
 }