Merge branch 'work.mount-syscalls' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull mount ABI updates from Al Viro:
 "The syscalls themselves, finally.

  That's not all there is to that stuff, but switching individual
  filesystems to new methods is fortunately independent from everything
  else, so e.g. NFS series can go through NFS tree, etc.

  As those conversions get done, we'll be finally able to get rid of a
  bunch of duplication in fs/super.c introduced in the beginning of the
  entire thing. I expect that to be finished in the next window..."

* 'work.mount-syscalls' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  vfs: Add a sample program for the new mount API
  vfs: syscall: Add fspick() to select a superblock for reconfiguration
  vfs: syscall: Add fsmount() to create a mount for a superblock
  vfs: syscall: Add fsconfig() for configuring and managing a context
  vfs: Implement logging through fs_context
  vfs: syscall: Add fsopen() to prepare for superblock creation
  Make anon_inodes unconditional
  teach move_mount(2) to work with OPEN_TREE_CLONE
  vfs: syscall: Add move_mount(2) to move mounts around
  vfs: syscall: Add open_tree(2) to reference or clone a mount

8 files changed, 128 insertions, 9 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5174405e40d5..ec07f4c5630d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -165,10 +165,13 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
 /* File is capable of returning -EAGAIN if I/O will block */
-#define FMODE_NOWAIT	((__force fmode_t)0x8000000)
+#define FMODE_NOWAIT		((__force fmode_t)0x8000000)
+
+/* File represents mount that needs unmounting */
+#define FMODE_NEED_UNMOUNT	((__force fmode_t)0x10000000)
 
 /* File does not contribute to nr_files count */
-#define FMODE_NOACCOUNT	((__force fmode_t)0x20000000)
+#define FMODE_NOACCOUNT		((__force fmode_t)0x20000000)
 
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index eaca452088fa..1f966670c8dc 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -13,8 +13,10 @@
 #define _LINUX_FS_CONTEXT_H
 
 #include <linux/kernel.h>
+#include <linux/refcount.h>
 #include <linux/errno.h>
 #include <linux/security.h>
+#include <linux/mutex.h>
 
 struct cred;
 struct dentry;
@@ -35,6 +37,19 @@ 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 {
@@ -74,12 +89,14 @@ 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 */
 	struct user_namespace	*user_ns;	/* The user namespace for this mount */
 	struct net		*net_ns;	/* The network namespace for this mount */
 	const struct cred	*cred;		/* The mounter's credentials */
+	struct fc_log		*log;		/* Logging buffer */
 	const char		*source;	/* The source name (eg. dev path) */
 	const char		*subtype;	/* The subtype to set on the superblock */
 	void			*security;	/* Linux S&M options */
@@ -88,6 +105,7 @@ 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 */
 };
@@ -135,15 +153,21 @@ extern int vfs_get_super(struct fs_context *fc,
 
 extern const struct file_operations fscontext_fops;
 
-#ifdef CONFIG_PRINTK
+/*
+ * Mount error, warning and informational message logging.  This structure is
+ * shareable between a mount and a subordinate mount.
+ */
+struct fc_log {
+	refcount_t	usage;
+	u8		head;		/* Insertion index in buffer[] */
+	u8		tail;		/* Removal index in buffer[] */
+	u8		need_free;	/* Mask of kfree'able items in buffer[] */
+	struct module	*owner;		/* Owner module for strings that don't then need freeing */
+	char		*buffer[8];
+};
+
 extern __attribute__((format(printf, 2, 3)))
 void logfc(struct fs_context *fc, const char *fmt, ...);
-#else
-static inline __attribute__((format(printf, 2, 3)))
-void logfc(struct fs_context *fc, const char *fmt, ...)
-{
-}
-#endif
 
 /**
  * infof - Store supplementary informational message
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index f7e55d0d2672..47f58cfb6a19 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -159,6 +159,10 @@
  *	Parse a string of security data filling in the opts structure
  *	@options string containing all mount options known by the LSM
  *	@opts binary data structure usable by the LSM
+ * @move_mount:
+ *	Check permission before a mount is moved.
+ *	@from_path indicates the mount that is going to be moved.
+ *	@to_path indicates the mountpoint that will be mounted upon.
  * @dentry_init_security:
  *	Compute a context for a dentry as the inode is not yet available
  *	since NFSv4 has no label backed by an EA anyway.
@@ -1502,6 +1506,7 @@ union security_list_options {
 					unsigned long *set_kern_flags);
 	int (*sb_add_mnt_opt)(const char *option, const char *val, int len,
 			      void **mnt_opts);
+	int (*move_mount)(const struct path *from_path, const struct path *to_path);
 	int (*dentry_init_security)(struct dentry *dentry, int mode,
 					const struct qstr *name, void **ctx,
 					u32 *ctxlen);
@@ -1839,6 +1844,7 @@ struct security_hook_heads {
 	struct hlist_head sb_set_mnt_opts;
 	struct hlist_head sb_clone_mnt_opts;
 	struct hlist_head sb_add_mnt_opt;
+	struct hlist_head move_mount;
 	struct hlist_head dentry_init_security;
 	struct hlist_head dentry_create_files_as;
 #ifdef CONFIG_SECURITY_PATH
diff --git a/include/linux/module.h b/include/linux/module.h
index 5bf5dcd91009..7dc4dc79b634 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -709,6 +709,12 @@ static inline bool is_module_text_address(unsigned long addr)
 	return false;
 }
 
+static inline bool within_module_core(unsigned long addr,
+				      const struct module *mod)
+{
+	return false;
+}
+
 /* Get/put a kernel symbol (calls should be symmetric) */
 #define symbol_get(x) ({ extern typeof(x) x __attribute__((weak)); &(x); })
 #define symbol_put(x) do { } while (0)
diff --git a/include/linux/security.h b/include/linux/security.h
index d543293216b9..659071c2e57c 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -251,6 +251,7 @@ int security_sb_clone_mnt_opts(const struct super_block *oldsb,
 				unsigned long *set_kern_flags);
 int security_add_mnt_opt(const char *option, const char *val,
 				int len, void **mnt_opts);
+int security_move_mount(const struct path *from_path, const struct path *to_path);
 int security_dentry_init_security(struct dentry *dentry, int mode,
 					const struct qstr *name, void **ctx,
 					u32 *ctxlen);
@@ -614,6 +615,12 @@ static inline int security_add_mnt_opt(const char *option, const char *val,
 	return 0;
 }
 
+static inline int security_move_mount(const struct path *from_path,
+				      const struct path *to_path)
+{
+	return 0;
+}
+
 static inline int security_inode_alloc(struct inode *inode)
 {
 	return 0;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index e446806a561f..e2870fe1be5b 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -985,6 +985,15 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
 			  unsigned mask, struct statx __user *buffer);
 asmlinkage long sys_rseq(struct rseq __user *rseq, uint32_t rseq_len,
 			 int flags, uint32_t sig);
+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_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);
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index a2f8658f1c55..1d338357df8a 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -91,5 +91,7 @@
 #define AT_STATX_FORCE_SYNC	0x2000	/* - Force the attributes to be sync'd with the server */
 #define AT_STATX_DONT_SYNC	0x4000	/* - Don't sync attributes with the server */
 
+#define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
+
 
 #endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index 3f9ec42510b0..96a0240f23fe 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -55,4 +55,66 @@
 #define MS_MGC_VAL 0xC0ED0000
 #define MS_MGC_MSK 0xffff0000
 
+/*
+ * open_tree() flags.
+ */
+#define OPEN_TREE_CLONE		1		/* Clone the target tree and attach the clone */
+#define OPEN_TREE_CLOEXEC	O_CLOEXEC	/* Close the file on execve() */
+
+/*
+ * move_mount() flags.
+ */
+#define MOVE_MOUNT_F_SYMLINKS		0x00000001 /* Follow symlinks on from path */
+#define MOVE_MOUNT_F_AUTOMOUNTS		0x00000002 /* Follow automounts on from path */
+#define MOVE_MOUNT_F_EMPTY_PATH		0x00000004 /* Empty from path permitted */
+#define MOVE_MOUNT_T_SYMLINKS		0x00000010 /* Follow symlinks on to path */
+#define MOVE_MOUNT_T_AUTOMOUNTS		0x00000020 /* Follow automounts on to path */
+#define MOVE_MOUNT_T_EMPTY_PATH		0x00000040 /* Empty to path permitted */
+#define MOVE_MOUNT__MASK		0x00000077
+
+/*
+ * fsopen() flags.
+ */
+#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.
+ */
+enum fsconfig_command {
+	FSCONFIG_SET_FLAG	= 0,	/* Set parameter, supplying no value */
+	FSCONFIG_SET_STRING	= 1,	/* Set parameter, supplying a string value */
+	FSCONFIG_SET_BINARY	= 2,	/* Set parameter, supplying a binary blob value */
+	FSCONFIG_SET_PATH	= 3,	/* Set parameter, supplying an object by path */
+	FSCONFIG_SET_PATH_EMPTY	= 4,	/* Set parameter, supplying an object by (empty) path */
+	FSCONFIG_SET_FD		= 5,	/* Set parameter, supplying an object by fd */
+	FSCONFIG_CMD_CREATE	= 6,	/* Invoke superblock creation */
+	FSCONFIG_CMD_RECONFIGURE = 7,	/* Invoke superblock reconfiguration */
+};
+
+/*
+ * fsmount() flags.
+ */
+#define FSMOUNT_CLOEXEC		0x00000001
+
+/*
+ * Mount attributes.
+ */
+#define MOUNT_ATTR_RDONLY	0x00000001 /* Mount read-only */
+#define MOUNT_ATTR_NOSUID	0x00000002 /* Ignore suid and sgid bits */
+#define MOUNT_ATTR_NODEV	0x00000004 /* Disallow access to device special files */
+#define MOUNT_ATTR_NOEXEC	0x00000008 /* Disallow program execution */
+#define MOUNT_ATTR__ATIME	0x00000070 /* Setting on how atime should be updated */
+#define MOUNT_ATTR_RELATIME	0x00000000 /* - Update atime relative to mtime/ctime. */
+#define MOUNT_ATTR_NOATIME	0x00000010 /* - Do not update access times. */
+#define MOUNT_ATTR_STRICTATIME	0x00000020 /* - Always perform atime updates */
+#define MOUNT_ATTR_NODIRATIME	0x00000080 /* Do not update directory access times */
+
 #endif /* _UAPI_LINUX_MOUNT_H */