[PATCH v6] erofs: accept source file descriptor via fsconfig

Allow userspace to pass an already-opened file descriptor as the mount
source instead of a path string.  This is useful for tools that already
hold an fd to the image, such as composefs reusing an existing erofs
backing file.

Signed-off-by: Giuseppe Scrivano <[email protected]>
Reviewed-by: Gao Xiang <[email protected]>
Acked-by: Christian Brauner (Amutable) <[email protected]>
Acked-by: Jan Kara <[email protected]>
---
v5: https://lore.kernel.org/linux-fsdevel/[email protected]/
v4: https://lore.kernel.org/linux-fsdevel/[email protected]/
v3: https://lore.kernel.org/linux-fsdevel/[email protected]/
v2: https://lore.kernel.org/linux-fsdevel/[email protected]/
v1: https://lore.kernel.org/linux-fsdevel/ak5GfvVfWLJU1EwK@debian/

 Documentation/filesystems/erofs.rst | 17 +++++++
 fs/erofs/super.c                    | 73 ++++++++++++++++++++++++-----
 2 files changed, 79 insertions(+), 11 deletions(-)

diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst
index 4230884fb359..d301d9ac946a 100644
--- a/Documentation/filesystems/erofs.rst
+++ b/Documentation/filesystems/erofs.rst
@@ -137,8 +137,25 @@ fsoffset=%llu          Specify block-aligned filesystem offset for the primary d
 inode_share            Enable inode page sharing for this filesystem.  Inodes with
                        identical content within the same domain ID can share the
                        page cache.
+source=%s              (For file-backed mounts) Specify the backing image as a path
+                       or as an already-opened file descriptor.
 ===================    =========================================================
 
+File-backed mounts
+==================
+
+When CONFIG_EROFS_FS_BACKED_BY_FILE is enabled, EROFS file-backed images
+can be mounted directly without a loopback block device.  The backing file
+can be given either as a path, or as an already-opened file descriptor.
+
+When a file descriptor is used, the kernel resolves its path and records it
+so that /proc/mounts and similar interfaces can still report the mount
+source.
+
+Only regular files are accepted as backing files; to mount an image that
+resides on a block device, use the traditional block device mount path
+instead.
+
 Sysfs Entries
 =============
 
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 03d108a7a3e5..d40961248a49 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -386,6 +386,7 @@ static void erofs_default_options(struct erofs_sb_info *sbi)
 enum {
 	Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum,
 	Opt_device, Opt_domain_id, Opt_directio, Opt_fsoffset, Opt_inode_share,
+	Opt_source,
 };
 
 static const struct constant_table erofs_param_cache_strategy[] = {
@@ -402,17 +403,18 @@ static const struct constant_table erofs_dax_param_enums[] = {
 };
 
 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,
+	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),
-	fsparam_string("device",	Opt_device),
-	fsparam_string("domain_id",	Opt_domain_id),
-	fsparam_flag_no("directio",	Opt_directio),
-	fsparam_u64("fsoffset",		Opt_fsoffset),
-	fsparam_flag("inode_share",	Opt_inode_share),
+	fsparam_flag("dax",			Opt_dax),
+	fsparam_enum("dax",			Opt_dax_enum, erofs_dax_param_enums),
+	fsparam_string("device",		Opt_device),
+	fsparam_string("domain_id",		Opt_domain_id),
+	fsparam_flag_no("directio",		Opt_directio),
+	fsparam_u64("fsoffset",			Opt_fsoffset),
+	fsparam_flag("inode_share",		Opt_inode_share),
+	fsparam_file_or_string("source",	Opt_source),
 	{}
 };
 
@@ -437,6 +439,40 @@ static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode)
 	return false;
 }
 
+static int erofs_fc_parse_source(struct fs_context *fc,
+				 struct fs_parameter *param)
+{
+	struct erofs_sb_info *sbi = fc->s_fs_info;
+
+	if (fc->source || sbi->dif0.file)
+		return invalf(fc, "Multiple sources");
+
+	switch (param->type) {
+	case fs_value_is_string:
+		fc->source = param->string;
+		param->string = NULL;
+		return 0;
+	case fs_value_is_file: {
+		char *buf __free(kfree) = kmalloc(PATH_MAX, GFP_KERNEL);
+		char *p;
+
+		if (!buf)
+			return -ENOMEM;
+		p = file_path(param->file, buf, PATH_MAX);
+		if (IS_ERR(p))
+			return PTR_ERR(p);
+		fc->source = kstrdup(p, GFP_KERNEL);
+		if (!fc->source)
+			return -ENOMEM;
+		sbi->dif0.file = no_free_ptr(param->file);
+		return 0;
+	}
+	default:
+		WARN_ON_ONCE(true);
+		return -EINVAL;
+	}
+}
+
 static int erofs_fc_parse_param(struct fs_context *fc,
 				struct fs_parameter *param)
 {
@@ -524,6 +560,8 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 		else
 			set_opt(&sbi->opt, INODE_SHARE);
 		break;
+	case Opt_source:
+		return erofs_fc_parse_source(fc, param);
 	}
 	return 0;
 }
@@ -752,13 +790,26 @@ 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 (sbi->dif0.file) {
+		if (!IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE)) {
+			errorfc(fc, "source fd option not supported");
+			return -EINVAL;
+		}
+		if (!S_ISREG(file_inode(sbi->dif0.file)->i_mode) ||
+		    !sbi->dif0.file->f_mapping->a_ops->read_folio) {
+			errorfc(fc, "source is unsupported");
+			return -EINVAL;
+		}
+		return get_tree_nodev(fc, erofs_fc_fill_super);
+	}
+
 	ret = get_tree_bdev_flags(fc, erofs_fc_fill_super,
 		IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) ?
 			GET_TREE_BDEV_QUIET_LOOKUP : 0);
 	if (IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && ret == -ENOTBLK) {
-		struct erofs_sb_info *sbi = fc->s_fs_info;
 		struct file *file;
 
 		if (!fc->source)
-- 
2.55.0