vfs: syscall: Add fspick() to select a superblock for reconfiguration

Provide an fspick() system call that can be used to pick an existing
mountpoint into an fs_context which can thereafter be used to reconfigure a
superblock (equivalent of the superblock side of -o remount).

This looks like:

	int fd = fspick(AT_FDCWD, "/mnt",
			FSPICK_CLOEXEC | FSPICK_NO_AUTOMOUNT);
	fsconfig(fd, FSCONFIG_SET_FLAG, "intr", NULL, 0);
	fsconfig(fd, FSCONFIG_SET_FLAG, "noac", NULL, 0);
	fsconfig(fd, FSCONFIG_CMD_RECONFIGURE, NULL, NULL, 0);

At the point of fspick being called, the file descriptor referring to the
filesystem context is in exactly the same state as the one that was created
by fsopen() after fsmount() has been successfully called.

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

arch/x86/entry/syscalls/syscall_32.tbl

@@ -403,7 +403,7 @@
 389	i386	fsopen			sys_fsopen			__ia32_sys_fsopen
 390	i386	fsconfig		sys_fsconfig			__ia32_sys_fsconfig
 391	i386	fsmount			sys_fsmount			__ia32_sys_fsmount
-# don't use number 392, add new calls at the end
+392	i386	fspick			sys_fspick			__ia32_sys_fspick
 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

arch/x86/entry/syscalls/syscall_64.tbl

@@ -348,6 +348,7 @@
 337	common	fsopen			__x64_sys_fsopen
 338	common	fsconfig		__x64_sys_fsconfig
 339	common	fsmount			__x64_sys_fsmount
+340	common	fspick			__x64_sys_fspick
 # 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

fs/fsopen.c

@@ -156,6 +156,63 @@ err_fc:
 	return ret;
 }
 
+/*
+ * Pick a superblock into a context for reconfiguration.
+ */
+SYSCALL_DEFINE3(fspick, int, dfd, const char __user *, path, unsigned int, flags)
+{
+	struct fs_context *fc;
+	struct path target;
+	unsigned int lookup_flags;
+	int ret;
+
+	if (!ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if ((flags & ~(FSPICK_CLOEXEC |
+		       FSPICK_SYMLINK_NOFOLLOW |
+		       FSPICK_NO_AUTOMOUNT |
+		       FSPICK_EMPTY_PATH)) != 0)
+		return -EINVAL;
+
+	lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
+	if (flags & FSPICK_SYMLINK_NOFOLLOW)
+		lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & FSPICK_NO_AUTOMOUNT)
+		lookup_flags &= ~LOOKUP_AUTOMOUNT;
+	if (flags & FSPICK_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+	ret = user_path_at(dfd, path, lookup_flags, &target);
+	if (ret < 0)
+		goto err;
+
+	ret = -EINVAL;
+	if (target.mnt->mnt_root != target.dentry)
+		goto err_path;
+
+	fc = fs_context_for_reconfigure(target.dentry, 0, 0);
+	if (IS_ERR(fc)) {
+		ret = PTR_ERR(fc);
+		goto err_path;
+	}
+
+	fc->phase = FS_CONTEXT_RECONF_PARAMS;
+
+	ret = fscontext_alloc_log(fc);
+	if (ret < 0)
+		goto err_fc;
+
+	path_put(&target);
+	return fscontext_create_fd(fc, flags & FSPICK_CLOEXEC ? O_CLOEXEC : 0);
+
+err_fc:
+	put_fs_context(fc);
+err_path:
+	path_put(&target);
+err:
+	return ret;
+}
+
 /*
  * Check the state and apply the configuration.  Note that this function is
  * allowed to 'steal' the value by setting param->xxx to NULL before returning.

include/linux/syscalls.h

@@ -993,6 +993,7 @@ asmlinkage long sys_fsopen(const char __user *fs_name, unsigned int flags);
 asmlinkage long sys_fsconfig(int fs_fd, unsigned int cmd, const char __user *key,
 			     const void __user *value, int aux);
 asmlinkage long sys_fsmount(int fs_fd, unsigned int flags, unsigned int ms_flags);
+asmlinkage long sys_fspick(int dfd, const char __user *path, unsigned int flags);
 asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
 				       siginfo_t __user *info,
 				       unsigned int flags);

include/uapi/linux/mount.h

@@ -77,6 +77,14 @@
  */
 #define FSOPEN_CLOEXEC		0x00000001
 
+/*
+ * fspick() flags.
+ */
+#define FSPICK_CLOEXEC		0x00000001
+#define FSPICK_SYMLINK_NOFOLLOW	0x00000002
+#define FSPICK_NO_AUTOMOUNT	0x00000004
+#define FSPICK_EMPTY_PATH	0x00000008
+
 /*
  * The type of fsconfig() call made.
  */