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>

8 files changed, 118 insertions, 2 deletions

diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 0db9effb18d9..37fd1fc5396e 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -400,7 +400,8 @@
 386	i386	rseq			sys_rseq			__ia32_sys_rseq
 387	i386	open_tree		sys_open_tree			__ia32_sys_open_tree
 388	i386	move_mount		sys_move_mount			__ia32_sys_move_mount
-# don't use numbers 389 through 392, add new calls at the end
+389	i386	fsopen			sys_fsopen			__ia32_sys_fsopen
+# don't use numbers 390 through 392, add new calls at the end
 393	i386	semget			sys_semget    			__ia32_sys_semget
 394	i386	semctl			sys_semctl    			__ia32_compat_sys_semctl
 395	i386	shmget			sys_shmget    			__ia32_sys_shmget
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 0440f0eefa02..511608a21611 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -345,6 +345,7 @@
 334	common	rseq			__x64_sys_rseq
 335	common	open_tree		__x64_sys_open_tree
 336	common	move_mount		__x64_sys_move_mount
+337	common	fsopen			__x64_sys_fsopen
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
 424	common	pidfd_send_signal	__x64_sys_pidfd_send_signal
diff --git a/fs/Makefile b/fs/Makefile
index 35945f8139e6..5a51bc2489ba 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -13,7 +13,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o splice.o sync.o utimes.o d_path.o \
 		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
-		fs_types.o fs_context.o fs_parser.o
+		fs_types.o fs_context.o fs_parser.o fsopen.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o block_dev.o direct-io.o mpage.o
diff --git a/fs/fs_context.c b/fs/fs_context.c
index 87e3546b9a52..eb806fae3117 100644
--- a/fs/fs_context.c
+++ b/fs/fs_context.c
@@ -271,6 +271,8 @@ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type,
 	fc->cred	= get_current_cred();
 	fc->net_ns	= get_net(current->nsproxy->net_ns);
 
+	mutex_init(&fc->uapi_mutex);
+
 	switch (purpose) {
 	case FS_CONTEXT_FOR_MOUNT:
 		fc->user_ns = get_user_ns(fc->cred->user_ns);
@@ -353,6 +355,8 @@ struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc)
 	if (!fc)
 		return ERR_PTR(-ENOMEM);
 
+	mutex_init(&fc->uapi_mutex);
+
 	fc->fs_private	= NULL;
 	fc->s_fs_info	= NULL;
 	fc->source	= NULL;
diff --git a/fs/fsopen.c b/fs/fsopen.c
new file mode 100644
index 000000000000..d256f1ac9ff1
--- /dev/null
+++ b/fs/fsopen.c
@@ -0,0 +1,88 @@
+/* Filesystem access-by-fd.
+ *
+ * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/fs_context.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/security.h>
+#include <linux/anon_inodes.h>
+#include <linux/namei.h>
+#include <linux/file.h>
+#include <uapi/linux/mount.h>
+#include "mount.h"
+
+static int fscontext_release(struct inode *inode, struct file *file)
+{
+	struct fs_context *fc = file->private_data;
+
+	if (fc) {
+		file->private_data = NULL;
+		put_fs_context(fc);
+	}
+	return 0;
+}
+
+const struct file_operations fscontext_fops = {
+	.release	= fscontext_release,
+	.llseek		= no_llseek,
+};
+
+/*
+ * Attach a filesystem context to a file and an fd.
+ */
+static int fscontext_create_fd(struct fs_context *fc, unsigned int o_flags)
+{
+	int fd;
+
+	fd = anon_inode_getfd("fscontext", &fscontext_fops, fc,
+			      O_RDWR | o_flags);
+	if (fd < 0)
+		put_fs_context(fc);
+	return fd;
+}
+
+/*
+ * Open a filesystem by name so that it can be configured for mounting.
+ *
+ * We are allowed to specify a container in which the filesystem will be
+ * opened, thereby indicating which namespaces will be used (notably, which
+ * network namespace will be used for network filesystems).
+ */
+SYSCALL_DEFINE2(fsopen, const char __user *, _fs_name, unsigned int, flags)
+{
+	struct file_system_type *fs_type;
+	struct fs_context *fc;
+	const char *fs_name;
+
+	if (!ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (flags & ~FSOPEN_CLOEXEC)
+		return -EINVAL;
+
+	fs_name = strndup_user(_fs_name, PAGE_SIZE);
+	if (IS_ERR(fs_name))
+		return PTR_ERR(fs_name);
+
+	fs_type = get_fs_type(fs_name);
+	kfree(fs_name);
+	if (!fs_type)
+		return -ENODEV;
+
+	fc = fs_context_for_mount(fs_type, 0);
+	put_filesystem(fs_type);
+	if (IS_ERR(fc))
+		return PTR_ERR(fc);
+
+	fc->phase = FS_CONTEXT_CREATE_PARAMS;
+	return fscontext_create_fd(fc, flags & FSOPEN_CLOEXEC ? O_CLOEXEC : 0);
+}
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 */