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

1 files changed, 185 insertions, 223 deletions

diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index 4c837be3b6e3..014e20962376 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -11,265 +11,201 @@ static DEFINE_MUTEX(erofs_domain_cookies_lock);
 static LIST_HEAD(erofs_domain_list);
 static struct vfsmount *erofs_pseudo_mnt;
 
-static struct netfs_io_request *erofs_fscache_alloc_request(struct address_space *mapping,
+struct erofs_fscache_request {
+	struct erofs_fscache_request *primary;
+	struct netfs_cache_resources cache_resources;
+	struct address_space	*mapping;	/* The mapping being accessed */
+	loff_t			start;		/* Start position */
+	size_t			len;		/* Length of the request */
+	size_t			submitted;	/* Length of submitted */
+	short			error;		/* 0 or error that occurred */
+	refcount_t		ref;
+};
+
+static struct erofs_fscache_request *erofs_fscache_req_alloc(struct address_space *mapping,
 					     loff_t start, size_t len)
 {
-	struct netfs_io_request *rreq;
+	struct erofs_fscache_request *req;
 
-	rreq = kzalloc(sizeof(struct netfs_io_request), GFP_KERNEL);
-	if (!rreq)
+	req = kzalloc(sizeof(struct erofs_fscache_request), GFP_KERNEL);
+	if (!req)
 		return ERR_PTR(-ENOMEM);
 
-	rreq->start	= start;
-	rreq->len	= len;
-	rreq->mapping	= mapping;
-	rreq->inode	= mapping->host;
-	INIT_LIST_HEAD(&rreq->subrequests);
-	refcount_set(&rreq->ref, 1);
-	return rreq;
-}
+	req->mapping = mapping;
+	req->start   = start;
+	req->len     = len;
+	refcount_set(&req->ref, 1);
 
-static void erofs_fscache_put_request(struct netfs_io_request *rreq)
-{
-	if (!refcount_dec_and_test(&rreq->ref))
-		return;
-	if (rreq->cache_resources.ops)
-		rreq->cache_resources.ops->end_operation(&rreq->cache_resources);
-	kfree(rreq);
+	return req;
 }
 
-static void erofs_fscache_put_subrequest(struct netfs_io_subrequest *subreq)
+static struct erofs_fscache_request *erofs_fscache_req_chain(struct erofs_fscache_request *primary,
+					     size_t len)
 {
-	if (!refcount_dec_and_test(&subreq->ref))
-		return;
-	erofs_fscache_put_request(subreq->rreq);
-	kfree(subreq);
-}
+	struct erofs_fscache_request *req;
 
-static void erofs_fscache_clear_subrequests(struct netfs_io_request *rreq)
-{
-	struct netfs_io_subrequest *subreq;
+	/* use primary request for the first submission */
+	if (!primary->submitted) {
+		refcount_inc(&primary->ref);
+		return primary;
+	}
 
-	while (!list_empty(&rreq->subrequests)) {
-		subreq = list_first_entry(&rreq->subrequests,
-				struct netfs_io_subrequest, rreq_link);
-		list_del(&subreq->rreq_link);
-		erofs_fscache_put_subrequest(subreq);
+	req = erofs_fscache_req_alloc(primary->mapping,
+			primary->start + primary->submitted, len);
+	if (!IS_ERR(req)) {
+		req->primary = primary;
+		refcount_inc(&primary->ref);
 	}
+	return req;
 }
 
-static void erofs_fscache_rreq_unlock_folios(struct netfs_io_request *rreq)
+static void erofs_fscache_req_complete(struct erofs_fscache_request *req)
 {
-	struct netfs_io_subrequest *subreq;
 	struct folio *folio;
-	unsigned int iopos = 0;
-	pgoff_t start_page = rreq->start / PAGE_SIZE;
-	pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1;
-	bool subreq_failed = false;
+	bool failed = req->error;
+	pgoff_t start_page = req->start / PAGE_SIZE;
+	pgoff_t last_page = ((req->start + req->len) / PAGE_SIZE) - 1;
 
-	XA_STATE(xas, &rreq->mapping->i_pages, start_page);
-
-	subreq = list_first_entry(&rreq->subrequests,
-				  struct netfs_io_subrequest, rreq_link);
-	subreq_failed = (subreq->error < 0);
+	XA_STATE(xas, &req->mapping->i_pages, start_page);
 
 	rcu_read_lock();
 	xas_for_each(&xas, folio, last_page) {
-		unsigned int pgpos, pgend;
-		bool pg_failed = false;
-
 		if (xas_retry(&xas, folio))
 			continue;
-
-		pgpos = (folio_index(folio) - start_page) * PAGE_SIZE;
-		pgend = pgpos + folio_size(folio);
-
-		for (;;) {
-			if (!subreq) {
-				pg_failed = true;
-				break;
-			}
-
-			pg_failed |= subreq_failed;
-			if (pgend < iopos + subreq->len)
-				break;
-
-			iopos += subreq->len;
-			if (!list_is_last(&subreq->rreq_link,
-					  &rreq->subrequests)) {
-				subreq = list_next_entry(subreq, rreq_link);
-				subreq_failed = (subreq->error < 0);
-			} else {
-				subreq = NULL;
-				subreq_failed = false;
-			}
-			if (pgend == iopos)
-				break;
-		}
-
-		if (!pg_failed)
+		if (!failed)
 			folio_mark_uptodate(folio);
-
 		folio_unlock(folio);
 	}
 	rcu_read_unlock();
 }
 
-static void erofs_fscache_rreq_complete(struct netfs_io_request *rreq)
+static void erofs_fscache_req_put(struct erofs_fscache_request *req)
 {
-	erofs_fscache_rreq_unlock_folios(rreq);
-	erofs_fscache_clear_subrequests(rreq);
-	erofs_fscache_put_request(rreq);
+	if (refcount_dec_and_test(&req->ref)) {
+		if (req->cache_resources.ops)
+			req->cache_resources.ops->end_operation(&req->cache_resources);
+		if (!req->primary)
+			erofs_fscache_req_complete(req);
+		else
+			erofs_fscache_req_put(req->primary);
+		kfree(req);
+	}
 }
 
-static void erofc_fscache_subreq_complete(void *priv,
+static void erofs_fscache_subreq_complete(void *priv,
 		ssize_t transferred_or_error, bool was_async)
 {
-	struct netfs_io_subrequest *subreq = priv;
-	struct netfs_io_request *rreq = subreq->rreq;
-
-	if (IS_ERR_VALUE(transferred_or_error))
-		subreq->error = transferred_or_error;
+	struct erofs_fscache_request *req = priv;
 
-	if (atomic_dec_and_test(&rreq->nr_outstanding))
-		erofs_fscache_rreq_complete(rreq);
-
-	erofs_fscache_put_subrequest(subreq);
+	if (IS_ERR_VALUE(transferred_or_error)) {
+		if (req->primary)
+			req->primary->error = transferred_or_error;
+		else
+			req->error = transferred_or_error;
+	}
+	erofs_fscache_req_put(req);
 }
 
 /*
- * Read data from fscache and fill the read data into page cache described by
- * @rreq, which shall be both aligned with PAGE_SIZE. @pstart describes
- * the start physical address in the cache file.
+ * Read data from fscache (cookie, pstart, len), and fill the read data into
+ * page cache described by (req->mapping, lstart, len). @pstart describeis the
+ * start physical address in the cache file.
  */
 static int erofs_fscache_read_folios_async(struct fscache_cookie *cookie,
-				struct netfs_io_request *rreq, loff_t pstart)
+		struct erofs_fscache_request *req, loff_t pstart, size_t len)
 {
 	enum netfs_io_source source;
-	struct super_block *sb = rreq->mapping->host->i_sb;
-	struct netfs_io_subrequest *subreq;
-	struct netfs_cache_resources *cres = &rreq->cache_resources;
+	struct super_block *sb = req->mapping->host->i_sb;
+	struct netfs_cache_resources *cres = &req->cache_resources;
 	struct iov_iter iter;
-	loff_t start = rreq->start;
-	size_t len = rreq->len;
+	loff_t lstart = req->start + req->submitted;
 	size_t done = 0;
 	int ret;
 
-	atomic_set(&rreq->nr_outstanding, 1);
+	DBG_BUGON(len > req->len - req->submitted);
 
 	ret = fscache_begin_read_operation(cres, cookie);
 	if (ret)
-		goto out;
+		return ret;
 
 	while (done < len) {
-		subreq = kzalloc(sizeof(struct netfs_io_subrequest),
-				 GFP_KERNEL);
-		if (subreq) {
-			INIT_LIST_HEAD(&subreq->rreq_link);
-			refcount_set(&subreq->ref, 2);
-			subreq->rreq = rreq;
-			refcount_inc(&rreq->ref);
-		} else {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		subreq->start = pstart + done;
-		subreq->len	=  len - done;
-		subreq->flags = 1 << NETFS_SREQ_ONDEMAND;
+		loff_t sstart = pstart + done;
+		size_t slen = len - done;
+		unsigned long flags = 1 << NETFS_SREQ_ONDEMAND;
 
-		list_add_tail(&subreq->rreq_link, &rreq->subrequests);
-
-		source = cres->ops->prepare_read(subreq, LLONG_MAX);
-		if (WARN_ON(subreq->len == 0))
+		source = cres->ops->prepare_ondemand_read(cres,
+				sstart, &slen, LLONG_MAX, &flags, 0);
+		if (WARN_ON(slen == 0))
 			source = NETFS_INVALID_READ;
 		if (source != NETFS_READ_FROM_CACHE) {
-			erofs_err(sb, "failed to fscache prepare_read (source %d)",
-				  source);
-			ret = -EIO;
-			subreq->error = ret;
-			erofs_fscache_put_subrequest(subreq);
-			goto out;
+			erofs_err(sb, "failed to fscache prepare_read (source %d)", source);
+			return -EIO;
 		}
 
-		atomic_inc(&rreq->nr_outstanding);
+		refcount_inc(&req->ref);
+		iov_iter_xarray(&iter, ITER_DEST, &req->mapping->i_pages,
+				lstart + done, slen);
 
-		iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages,
-				start + done, subreq->len);
-
-		ret = fscache_read(cres, subreq->start, &iter,
-				   NETFS_READ_HOLE_FAIL,
-				   erofc_fscache_subreq_complete, subreq);
+		ret = fscache_read(cres, sstart, &iter, NETFS_READ_HOLE_FAIL,
+				   erofs_fscache_subreq_complete, req);
 		if (ret == -EIOCBQUEUED)
 			ret = 0;
 		if (ret) {
 			erofs_err(sb, "failed to fscache_read (ret %d)", ret);
-			goto out;
+			return ret;
 		}
 
-		done += subreq->len;
+		done += slen;
 	}
-out:
-	if (atomic_dec_and_test(&rreq->nr_outstanding))
-		erofs_fscache_rreq_complete(rreq);
-
-	return ret;
+	DBG_BUGON(done != len);
+	return 0;
 }
 
 static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio)
 {
 	int ret;
 	struct super_block *sb = folio_mapping(folio)->host->i_sb;
-	struct netfs_io_request *rreq;
+	struct erofs_fscache_request *req;
 	struct erofs_map_dev mdev = {
 		.m_deviceid = 0,
 		.m_pa = folio_pos(folio),
 	};
 
 	ret = erofs_map_dev(sb, &mdev);
-	if (ret)
-		goto out;
+	if (ret) {
+		folio_unlock(folio);
+		return ret;
+	}
 
-	rreq = erofs_fscache_alloc_request(folio_mapping(folio),
+	req = erofs_fscache_req_alloc(folio_mapping(folio),
 				folio_pos(folio), folio_size(folio));
-	if (IS_ERR(rreq)) {
-		ret = PTR_ERR(rreq);
-		goto out;
+	if (IS_ERR(req)) {
+		folio_unlock(folio);
+		return PTR_ERR(req);
 	}
 
-	return erofs_fscache_read_folios_async(mdev.m_fscache->cookie,
-				rreq, mdev.m_pa);
-out:
-	folio_unlock(folio);
+	ret = erofs_fscache_read_folios_async(mdev.m_fscache->cookie,
+				req, mdev.m_pa, folio_size(folio));
+	if (ret)
+		req->error = ret;
+
+	erofs_fscache_req_put(req);
 	return ret;
 }
 
-/*
- * Read into page cache in the range described by (@pos, @len).
- *
- * On return, the caller is responsible for page unlocking if the output @unlock
- * is true, or the callee will take this responsibility through netfs_io_request
- * interface.
- *
- * The return value is the number of bytes successfully handled, or negative
- * error code on failure. The only exception is that, the length of the range
- * instead of the error code is returned on failure after netfs_io_request is
- * allocated, so that .readahead() could advance rac accordingly.
- */
-static int erofs_fscache_data_read(struct address_space *mapping,
-				   loff_t pos, size_t len, bool *unlock)
+static int erofs_fscache_data_read_slice(struct erofs_fscache_request *primary)
 {
+	struct address_space *mapping = primary->mapping;
 	struct inode *inode = mapping->host;
 	struct super_block *sb = inode->i_sb;
-	struct netfs_io_request *rreq;
+	struct erofs_fscache_request *req;
 	struct erofs_map_blocks map;
 	struct erofs_map_dev mdev;
 	struct iov_iter iter;
+	loff_t pos = primary->start + primary->submitted;
 	size_t count;
 	int ret;
 
-	*unlock = true;
-
 	map.m_la = pos;
 	ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
 	if (ret)
@@ -297,17 +233,19 @@ static int erofs_fscache_data_read(struct address_space *mapping,
 		}
 		iov_iter_zero(PAGE_SIZE - size, &iter);
 		erofs_put_metabuf(&buf);
-		return PAGE_SIZE;
+		primary->submitted += PAGE_SIZE;
+		return 0;
 	}
 
+	count = primary->len - primary->submitted;
 	if (!(map.m_flags & EROFS_MAP_MAPPED)) {
-		count = len;
 		iov_iter_xarray(&iter, ITER_DEST, &mapping->i_pages, pos, count);
 		iov_iter_zero(count, &iter);
-		return count;
+		primary->submitted += count;
+		return 0;
 	}
 
-	count = min_t(size_t, map.m_llen - (pos - map.m_la), len);
+	count = min_t(size_t, map.m_llen - (pos - map.m_la), count);
 	DBG_BUGON(!count || count % PAGE_SIZE);
 
 	mdev = (struct erofs_map_dev) {
@@ -318,64 +256,65 @@ static int erofs_fscache_data_read(struct address_space *mapping,
 	if (ret)
 		return ret;
 
-	rreq = erofs_fscache_alloc_request(mapping, pos, count);
-	if (IS_ERR(rreq))
-		return PTR_ERR(rreq);
+	req = erofs_fscache_req_chain(primary, count);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
 
-	*unlock = false;
-	erofs_fscache_read_folios_async(mdev.m_fscache->cookie,
-			rreq, mdev.m_pa + (pos - map.m_la));
-	return count;
+	ret = erofs_fscache_read_folios_async(mdev.m_fscache->cookie,
+			req, mdev.m_pa + (pos - map.m_la), count);
+	erofs_fscache_req_put(req);
+	primary->submitted += count;
+	return ret;
 }
 
-static int erofs_fscache_read_folio(struct file *file, struct folio *folio)
+static int erofs_fscache_data_read(struct erofs_fscache_request *req)
 {
-	bool unlock;
 	int ret;
 
-	DBG_BUGON(folio_size(folio) != EROFS_BLKSIZ);
+	do {
+		ret = erofs_fscache_data_read_slice(req);
+		if (ret)
+			req->error = ret;
+	} while (!ret && req->submitted < req->len);
 
-	ret = erofs_fscache_data_read(folio_mapping(folio), folio_pos(folio),
-				      folio_size(folio), &unlock);
-	if (unlock) {
-		if (ret > 0)
-			folio_mark_uptodate(folio);
+	return ret;
+}
+
+static int erofs_fscache_read_folio(struct file *file, struct folio *folio)
+{
+	struct erofs_fscache_request *req;
+	int ret;
+
+	req = erofs_fscache_req_alloc(folio_mapping(folio),
+			folio_pos(folio), folio_size(folio));
+	if (IS_ERR(req)) {
 		folio_unlock(folio);
+		return PTR_ERR(req);
 	}
-	return ret < 0 ? ret : 0;
+
+	ret = erofs_fscache_data_read(req);
+	erofs_fscache_req_put(req);
+	return ret;
 }
 
 static void erofs_fscache_readahead(struct readahead_control *rac)
 {
-	struct folio *folio;
-	size_t len, done = 0;
-	loff_t start, pos;
-	bool unlock;
-	int ret, size;
+	struct erofs_fscache_request *req;
 
 	if (!readahead_count(rac))
 		return;
 
-	start = readahead_pos(rac);
-	len = readahead_length(rac);
+	req = erofs_fscache_req_alloc(rac->mapping,
+			readahead_pos(rac), readahead_length(rac));
+	if (IS_ERR(req))
+		return;
 
-	do {
-		pos = start + done;
-		ret = erofs_fscache_data_read(rac->mapping, pos,
-					      len - done, &unlock);
-		if (ret <= 0)
-			return;
+	/* The request completion will drop refs on the folios. */
+	while (readahead_folio(rac))
+		;
 
-		size = ret;
-		while (size) {
-			folio = readahead_folio(rac);
-			size -= folio_size(folio);
-			if (unlock) {
-				folio_mark_uptodate(folio);
-				folio_unlock(folio);
-			}
-		}
-	} while ((done += ret) < len);
+	erofs_fscache_data_read(req);
+	erofs_fscache_req_put(req);
 }
 
 static const struct address_space_operations erofs_fscache_meta_aops = {
@@ -494,7 +433,8 @@ static int erofs_fscache_register_domain(struct super_block *sb)
 
 static
 struct erofs_fscache *erofs_fscache_acquire_cookie(struct super_block *sb,
-						    char *name, bool need_inode)
+						   char *name,
+						   unsigned int flags)
 {
 	struct fscache_volume *volume = EROFS_SB(sb)->volume;
 	struct erofs_fscache *ctx;
@@ -516,7 +456,7 @@ struct erofs_fscache *erofs_fscache_acquire_cookie(struct super_block *sb,
 	fscache_use_cookie(cookie, false);
 	ctx->cookie = cookie;
 
-	if (need_inode) {
+	if (flags & EROFS_REG_COOKIE_NEED_INODE) {
 		struct inode *const inode = new_inode(sb);
 
 		if (!inode) {
@@ -554,14 +494,15 @@ static void erofs_fscache_relinquish_cookie(struct erofs_fscache *ctx)
 
 static
 struct erofs_fscache *erofs_fscache_domain_init_cookie(struct super_block *sb,
-		char *name, bool need_inode)
+						       char *name,
+						       unsigned int flags)
 {
 	int err;
 	struct inode *inode;
 	struct erofs_fscache *ctx;
 	struct erofs_domain *domain = EROFS_SB(sb)->domain;
 
-	ctx = erofs_fscache_acquire_cookie(sb, name, need_inode);
+	ctx = erofs_fscache_acquire_cookie(sb, name, flags);
 	if (IS_ERR(ctx))
 		return ctx;
 
@@ -589,7 +530,8 @@ out:
 
 static
 struct erofs_fscache *erofs_domain_register_cookie(struct super_block *sb,
-						   char *name, bool need_inode)
+						   char *name,
+						   unsigned int flags)
 {
 	struct inode *inode;
 	struct erofs_fscache *ctx;
@@ -602,23 +544,30 @@ struct erofs_fscache *erofs_domain_register_cookie(struct super_block *sb,
 		ctx = inode->i_private;
 		if (!ctx || ctx->domain != domain || strcmp(ctx->name, name))
 			continue;
-		igrab(inode);
+		if (!(flags & EROFS_REG_COOKIE_NEED_NOEXIST)) {
+			igrab(inode);
+		} else {
+			erofs_err(sb, "%s already exists in domain %s", name,
+				  domain->domain_id);
+			ctx = ERR_PTR(-EEXIST);
+		}
 		spin_unlock(&psb->s_inode_list_lock);
 		mutex_unlock(&erofs_domain_cookies_lock);
 		return ctx;
 	}
 	spin_unlock(&psb->s_inode_list_lock);
-	ctx = erofs_fscache_domain_init_cookie(sb, name, need_inode);
+	ctx = erofs_fscache_domain_init_cookie(sb, name, flags);
 	mutex_unlock(&erofs_domain_cookies_lock);
 	return ctx;
 }
 
 struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb,
-						    char *name, bool need_inode)
+						    char *name,
+						    unsigned int flags)
 {
 	if (EROFS_SB(sb)->domain_id)
-		return erofs_domain_register_cookie(sb, name, need_inode);
-	return erofs_fscache_acquire_cookie(sb, name, need_inode);
+		return erofs_domain_register_cookie(sb, name, flags);
+	return erofs_fscache_acquire_cookie(sb, name, flags);
 }
 
 void erofs_fscache_unregister_cookie(struct erofs_fscache *ctx)
@@ -647,6 +596,7 @@ int erofs_fscache_register_fs(struct super_block *sb)
 	int ret;
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
 	struct erofs_fscache *fscache;
+	unsigned int flags;
 
 	if (sbi->domain_id)
 		ret = erofs_fscache_register_domain(sb);
@@ -655,8 +605,20 @@ int erofs_fscache_register_fs(struct super_block *sb)
 	if (ret)
 		return ret;
 
-	/* acquired domain/volume will be relinquished in kill_sb() on error */
-	fscache = erofs_fscache_register_cookie(sb, sbi->fsid, true);
+	/*
+	 * When shared domain is enabled, using NEED_NOEXIST to guarantee
+	 * the primary data blob (aka fsid) is unique in the shared domain.
+	 *
+	 * For non-shared-domain case, fscache_acquire_volume() invoked by
+	 * erofs_fscache_register_volume() has already guaranteed
+	 * the uniqueness of primary data blob.
+	 *
+	 * Acquired domain/volume will be relinquished in kill_sb() on error.
+	 */
+	flags = EROFS_REG_COOKIE_NEED_INODE;
+	if (sbi->domain_id)
+		flags |= EROFS_REG_COOKIE_NEED_NOEXIST;
+	fscache = erofs_fscache_register_cookie(sb, sbi->fsid, flags);
 	if (IS_ERR(fscache))
 		return PTR_ERR(fscache);