Merge tag 'erofs-for-6.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs

Pull erofs updates from Gao Xiang:
 "In this cycle, large folios are now enabled in the iomap/fscache mode
  for uncompressed files first. In order to do that, we've also cleaned
  up better interfaces between erofs and fscache, which are acked by
  fscache/netfs folks and included in this pull request.

  Other than that, there are random fixes around erofs over fscache and
  crafted images by syzbot, minor cleanups and documentation updates.

  Summary:

   - Enable large folios for iomap/fscache mode

   - Avoid sysfs warning due to mounting twice with the same fsid and
     domain_id in fscache mode

   - Refine fscache interface among erofs, fscache, and cachefiles

   - Use kmap_local_page() only for metabuf

   - Fixes around crafted images found by syzbot

   - Minor cleanups and documentation updates"

* tag 'erofs-for-6.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs:
  erofs: validate the extent length for uncompressed pclusters
  erofs: fix missing unmap if z_erofs_get_extent_compressedlen() fails
  erofs: Fix pcluster memleak when its block address is zero
  erofs: use kmap_local_page() only for erofs_bread()
  erofs: enable large folios for fscache mode
  erofs: support large folios for fscache mode
  erofs: switch to prepare_ondemand_read() in fscache mode
  fscache,cachefiles: add prepare_ondemand_read() callback
  erofs: clean up cached I/O strategies
  erofs: update documentation
  erofs: check the uniqueness of fsid in shared domain in advance
  erofs: enable large folios for iomap mode

Author: torvalds

Documentation/filesystems/erofs.rst

@@ -30,12 +30,18 @@ It is implemented to be a better choice for the following scenarios:
    especially for those embedded devices with limited memory and high-density
    hosts with numerous containers.
 
-Here is the main features of EROFS:
+Here are the main features of EROFS:
 
  - Little endian on-disk design;
 
- - 4KiB block size and 32-bit block addresses, therefore 16TiB address space
-   at most for now;
+ - Block-based distribution and file-based distribution over fscache are
+   supported;
+
+ - Support multiple devices to refer to external blobs, which can be used
+   for container images;
+
+ - 4KiB block size and 32-bit block addresses for each device, therefore
+   16TiB address space at most for now;
 
  - Two inode layouts for different requirements:
 
@@ -50,28 +56,31 @@ Here is the main features of EROFS:
    Metadata reserved      8 bytes       18 bytes
    =====================  ============  ======================================
 
- - Metadata and data could be mixed as an option;
-
- - Support extended attributes (xattrs) as an option;
+ - Support extended attributes as an option;
 
- - Support tailpacking data and xattr inline compared to byte-addressed
-   unaligned metadata or smaller block size alternatives;
-
- - Support POSIX.1e ACLs by using xattrs;
+ - Support POSIX.1e ACLs by using extended attributes;
 
  - Support transparent data compression as an option:
    LZ4 and MicroLZMA algorithms can be used on a per-file basis; In addition,
    inplace decompression is also supported to avoid bounce compressed buffers
    and page cache thrashing.
 
+ - Support chunk-based data deduplication and rolling-hash compressed data
+   deduplication;
+
+ - Support tailpacking inline compared to byte-addressed unaligned metadata
+   or smaller block size alternatives;
+
+ - Support merging tail-end data into a special inode as fragments.
+
+ - Support large folios for uncompressed files.
+
  - Support direct I/O on uncompressed files to avoid double caching for loop
    devices;
 
  - Support FSDAX on uncompressed images for secure containers and ramdisks in
    order to get rid of unnecessary page cache.
 
- - Support multiple devices for multi blob container images;
-
  - Support file-based on-demand loading with the Fscache infrastructure.
 
 The following git tree provides the file system user-space tools under
@@ -259,7 +268,7 @@ By the way, chunk-based files are all uncompressed for now.
 
 Data compression
 ----------------
-EROFS implements LZ4 fixed-sized output compression which generates fixed-sized
+EROFS implements fixed-sized output compression which generates fixed-sized
 compressed data blocks from variable-sized input in contrast to other existing
 fixed-sized input solutions. Relatively higher compression ratios can be gotten
 by using fixed-sized output compression since nowadays popular data compression
@@ -314,3 +323,6 @@ to understand its delta0 is constantly 1, as illustrated below::
 
 If another HEAD follows a HEAD lcluster, there is no room to record CBLKCNT,
 but it's easy to know the size of such pcluster is 1 lcluster as well.
+
+Since Linux v6.1, each pcluster can be used for multiple variable-sized extents,
+therefore it can be used for compressed data deduplication.

fs/cachefiles/io.c

@@ -385,38 +385,35 @@ static int cachefiles_write(struct netfs_cache_resources *cres,
 				  term_func, term_func_priv);
 }
 
-/*
- * Prepare a read operation, shortening it to a cached/uncached
- * boundary as appropriate.
- */
-static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest *subreq,
-						      loff_t i_size)
+static inline enum netfs_io_source
+cachefiles_do_prepare_read(struct netfs_cache_resources *cres,
+			   loff_t start, size_t *_len, loff_t i_size,
+			   unsigned long *_flags, ino_t netfs_ino)
 {
 	enum cachefiles_prepare_read_trace why;
-	struct netfs_io_request *rreq = subreq->rreq;
-	struct netfs_cache_resources *cres = &rreq->cache_resources;
-	struct cachefiles_object *object;
+	struct cachefiles_object *object = NULL;
 	struct cachefiles_cache *cache;
 	struct fscache_cookie *cookie = fscache_cres_cookie(cres);
 	const struct cred *saved_cred;
 	struct file *file = cachefiles_cres_file(cres);
 	enum netfs_io_source ret = NETFS_DOWNLOAD_FROM_SERVER;
+	size_t len = *_len;
 	loff_t off, to;
 	ino_t ino = file ? file_inode(file)->i_ino : 0;
 	int rc;
 
-	_enter("%zx @%llx/%llx", subreq->len, subreq->start, i_size);
+	_enter("%zx @%llx/%llx", len, start, i_size);
 
-	if (subreq->start >= i_size) {
+	if (start >= i_size) {
 		ret = NETFS_FILL_WITH_ZEROES;
 		why = cachefiles_trace_read_after_eof;
 		goto out_no_object;
 	}
 
 	if (test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) {
-		__set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
+		__set_bit(NETFS_SREQ_COPY_TO_CACHE, _flags);
 		why = cachefiles_trace_read_no_data;
-		if (!test_bit(NETFS_SREQ_ONDEMAND, &subreq->flags))
+		if (!test_bit(NETFS_SREQ_ONDEMAND, _flags))
 			goto out_no_object;
 	}
 
@@ -437,7 +434,7 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest *
 retry:
 	off = cachefiles_inject_read_error();
 	if (off == 0)
-		off = vfs_llseek(file, subreq->start, SEEK_DATA);
+		off = vfs_llseek(file, start, SEEK_DATA);
 	if (off < 0 && off >= (loff_t)-MAX_ERRNO) {
 		if (off == (loff_t)-ENXIO) {
 			why = cachefiles_trace_read_seek_nxio;
@@ -449,58 +446,83 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest *
 		goto out;
 	}
 
-	if (off >= subreq->start + subreq->len) {
+	if (off >= start + len) {
 		why = cachefiles_trace_read_found_hole;
 		goto download_and_store;
 	}
 
-	if (off > subreq->start) {
+	if (off > start) {
 		off = round_up(off, cache->bsize);
-		subreq->len = off - subreq->start;
+		len = off - start;
+		*_len = len;
 		why = cachefiles_trace_read_found_part;
 		goto download_and_store;
 	}
 
 	to = cachefiles_inject_read_error();
 	if (to == 0)
-		to = vfs_llseek(file, subreq->start, SEEK_HOLE);
+		to = vfs_llseek(file, start, SEEK_HOLE);
 	if (to < 0 && to >= (loff_t)-MAX_ERRNO) {
 		trace_cachefiles_io_error(object, file_inode(file), to,
 					  cachefiles_trace_seek_error);
 		why = cachefiles_trace_read_seek_error;
 		goto out;
 	}
 
-	if (to < subreq->start + subreq->len) {
-		if (subreq->start + subreq->len >= i_size)
+	if (to < start + len) {
+		if (start + len >= i_size)
 			to = round_up(to, cache->bsize);
 		else
 			to = round_down(to, cache->bsize);
-		subreq->len = to - subreq->start;
+		len = to - start;
+		*_len = len;
 	}
 
 	why = cachefiles_trace_read_have_data;
 	ret = NETFS_READ_FROM_CACHE;
 	goto out;
 
 download_and_store:
-	__set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
-	if (test_bit(NETFS_SREQ_ONDEMAND, &subreq->flags)) {
-		rc = cachefiles_ondemand_read(object, subreq->start,
-					      subreq->len);
+	__set_bit(NETFS_SREQ_COPY_TO_CACHE, _flags);
+	if (test_bit(NETFS_SREQ_ONDEMAND, _flags)) {
+		rc = cachefiles_ondemand_read(object, start, len);
 		if (!rc) {
-			__clear_bit(NETFS_SREQ_ONDEMAND, &subreq->flags);
+			__clear_bit(NETFS_SREQ_ONDEMAND, _flags);
 			goto retry;
 		}
 		ret = NETFS_INVALID_READ;
 	}
 out:
 	cachefiles_end_secure(cache, saved_cred);
 out_no_object:
-	trace_cachefiles_prep_read(subreq, ret, why, ino);
+	trace_cachefiles_prep_read(object, start, len, *_flags, ret, why, ino, netfs_ino);
 	return ret;
 }
 
+/*
+ * Prepare a read operation, shortening it to a cached/uncached
+ * boundary as appropriate.
+ */
+static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest *subreq,
+						    loff_t i_size)
+{
+	return cachefiles_do_prepare_read(&subreq->rreq->cache_resources,
+					  subreq->start, &subreq->len, i_size,
+					  &subreq->flags, subreq->rreq->inode->i_ino);
+}
+
+/*
+ * Prepare an on-demand read operation, shortening it to a cached/uncached
+ * boundary as appropriate.
+ */
+static enum netfs_io_source
+cachefiles_prepare_ondemand_read(struct netfs_cache_resources *cres,
+				 loff_t start, size_t *_len, loff_t i_size,
+				 unsigned long *_flags, ino_t ino)
+{
+	return cachefiles_do_prepare_read(cres, start, _len, i_size, _flags, ino);
+}
+
 /*
  * Prepare for a write to occur.
  */
@@ -621,6 +643,7 @@ static const struct netfs_cache_ops cachefiles_netfs_cache_ops = {
 	.write			= cachefiles_write,
 	.prepare_read		= cachefiles_prepare_read,
 	.prepare_write		= cachefiles_prepare_write,
+	.prepare_ondemand_read	= cachefiles_prepare_ondemand_read,
 	.query_occupancy	= cachefiles_query_occupancy,
 };
 

fs/erofs/data.c

@@ -13,9 +13,7 @@
 void erofs_unmap_metabuf(struct erofs_buf *buf)
 {
 	if (buf->kmap_type == EROFS_KMAP)
-		kunmap(buf->page);
-	else if (buf->kmap_type == EROFS_KMAP_ATOMIC)
-		kunmap_atomic(buf->base);
+		kunmap_local(buf->base);
 	buf->base = NULL;
 	buf->kmap_type = EROFS_NO_KMAP;
 }
@@ -54,9 +52,7 @@ void *erofs_bread(struct erofs_buf *buf, struct inode *inode,
 	}
 	if (buf->kmap_type == EROFS_NO_KMAP) {
 		if (type == EROFS_KMAP)
-			buf->base = kmap(page);
-		else if (type == EROFS_KMAP_ATOMIC)
-			buf->base = kmap_atomic(page);
+			buf->base = kmap_local_page(page);
 		buf->kmap_type = type;
 	} else if (buf->kmap_type != type) {
 		DBG_BUGON(1);
@@ -403,6 +399,8 @@ const struct address_space_operations erofs_raw_access_aops = {
 	.readahead = erofs_readahead,
 	.bmap = erofs_bmap,
 	.direct_IO = noop_direct_IO,
+	.release_folio = iomap_release_folio,
+	.invalidate_folio = iomap_invalidate_folio,
 };
 
 #ifdef CONFIG_FS_DAX