vfs: syscall: Add fsopen() to prepare for superblock creation

Provide an fsopen() system call that starts the process of preparing to
create a superblock that will then be mountable, using an fd as a context
handle.  fsopen() is given the name of the filesystem that will be used:

	int mfd = fsopen(const char *fsname, unsigned int flags);

where flags can be 0 or FSOPEN_CLOEXEC.

For example:

	sfd = fsopen("ext4", FSOPEN_CLOEXEC);
	fsconfig(sfd, FSCONFIG_SET_PATH, "source", "/dev/sda1", AT_FDCWD);
	fsconfig(sfd, FSCONFIG_SET_FLAG, "noatime", NULL, 0);
	fsconfig(sfd, FSCONFIG_SET_FLAG, "acl", NULL, 0);
	fsconfig(sfd, FSCONFIG_SET_FLAG, "user_xattr", NULL, 0);
	fsconfig(sfd, FSCONFIG_SET_STRING, "sb", "1", 0);
	fsconfig(sfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
	fsinfo(sfd, NULL, ...); // query new superblock attributes
	mfd = fsmount(sfd, FSMOUNT_CLOEXEC, MS_RELATIME);
	move_mount(mfd, "", sfd, AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH);

	sfd = fsopen("afs", -1);
	fsconfig(fd, FSCONFIG_SET_STRING, "source",
		 "#grand.central.org:root.cell", 0);
	fsconfig(fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
	mfd = fsmount(sfd, 0, MS_NODEV);
	move_mount(mfd, "", sfd, AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH);

If an error is reported at any step, an error message may be available to be
read() back (ENODATA will be reported if there isn't an error available) in
the form:

	"e <subsys>:<problem>"
	"e SELinux:Mount on mountpoint not permitted"

Once fsmount() has been called, further fsconfig() calls will incur EBUSY,
even if the fsmount() fails.  read() is still possible to retrieve error
information.

The fsopen() syscall creates a mount context and hangs it of the fd that it
returns.

Netlink is not used because it is optional and would make the core VFS
dependent on the networking layer and also potentially add network
namespace issues.

Note that, for the moment, the caller must have SYS_CAP_ADMIN to use
fsopen().

Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-api@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

3 files changed, 22 insertions, 0 deletions

diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index eaca452088fa..7ab8b44fab3e 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/security.h>
+#include <linux/mutex.h>
 
 struct cred;
 struct dentry;
@@ -35,6 +36,19 @@ enum fs_context_purpose {
 };
 
 /*
+ * Userspace usage phase for fsopen/fspick.
+ */
+enum fs_context_phase {
+	FS_CONTEXT_CREATE_PARAMS,	/* Loading params for sb creation */
+	FS_CONTEXT_CREATING,		/* A superblock is being created */
+	FS_CONTEXT_AWAITING_MOUNT,	/* Superblock created, awaiting fsmount() */
+	FS_CONTEXT_AWAITING_RECONF,	/* Awaiting initialisation for reconfiguration */
+	FS_CONTEXT_RECONF_PARAMS,	/* Loading params for reconfiguration */
+	FS_CONTEXT_RECONFIGURING,	/* Reconfiguring the superblock */
+	FS_CONTEXT_FAILED,		/* Failed to correctly transition a context */
+};
+
+/*
  * Type of parameter value.
  */
 enum fs_value_type {
@@ -74,6 +88,7 @@ struct fs_parameter {
  */
 struct fs_context {
 	const struct fs_context_operations *ops;
+	struct mutex		uapi_mutex;	/* Userspace access mutex */
 	struct file_system_type	*fs_type;
 	void			*fs_private;	/* The filesystem's context */
 	struct dentry		*root;		/* The root and superblock */
@@ -88,6 +103,7 @@ struct fs_context {
 	unsigned int		sb_flags_mask;	/* Superblock flags that were changed */
 	unsigned int		lsm_flags;	/* Information flags from the fs to the LSM */
 	enum fs_context_purpose	purpose:8;
+	enum fs_context_phase	phase:8;	/* The phase the context is in */
 	bool			need_free:1;	/* Need to call ops->free() */
 	bool			global:1;	/* Goes into &init_user_ns */
 };
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 84347fc0a1a7..0c9bd5427e8f 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -989,6 +989,7 @@ asmlinkage long sys_open_tree(int dfd, const char __user *path, unsigned flags);
 asmlinkage long sys_move_mount(int from_dfd, const char __user *from_path,
 			       int to_dfd, const char __user *to_path,
 			       unsigned int ms_flags);
+asmlinkage long sys_fsopen(const char __user *fs_name, unsigned int flags);
 asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
 				       siginfo_t __user *info,
 				       unsigned int flags);
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index 3634e065836c..7570df43d08f 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -72,4 +72,9 @@
 #define MOVE_MOUNT_T_EMPTY_PATH		0x00000040 /* Empty to path permitted */
 #define MOVE_MOUNT__MASK		0x00000077
 
+/*
+ * fsopen() flags.
+ */
+#define FSOPEN_CLOEXEC		0x00000001
+
 #endif /* _UAPI_LINUX_MOUNT_H */