7 files changed, 1234 insertions, 31 deletions
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 1de155e2dc3..e68021c08fb 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -32,6 +32,8 @@ directory-locking
 	- info about the locking scheme used for directory operations.
 dlmfs.txt
 	- info on the userspace interface to the OCFS2 DLM.
+dnotify.txt
+	- info about directory notification in Linux.
 ecryptfs.txt
 	- docs on eCryptfs: stacked cryptographic filesystem for Linux.
 ext2.txt
@@ -80,6 +82,8 @@ relay.txt
 	- info on relay, for efficient streaming from kernel to user space.
 romfs.txt
 	- description of the ROMFS filesystem.
+sharedsubtree.txt
+	- a description of shared subtrees for namespaces.
 smbfs.txt
 	- info on using filesystems with the SMB protocol (Win 3.11 and NT).
 spufs.txt
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 37c10cba717..42d4b30b104 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -90,7 +90,6 @@ of the locking scheme for directory operations.
 prototypes:
 	struct inode *(*alloc_inode)(struct super_block *sb);
 	void (*destroy_inode)(struct inode *);
-	void (*read_inode) (struct inode *);
 	void (*dirty_inode) (struct inode *);
 	int (*write_inode) (struct inode *, int);
 	void (*put_inode) (struct inode *);
@@ -114,7 +113,6 @@ locking rules:
 			BKL	s_lock	s_umount
 alloc_inode:		no	no	no
 destroy_inode:		no
-read_inode:		no				(see below)
 dirty_inode:		no				(must not sleep)
 write_inode:		no
 put_inode:		no
@@ -133,7 +131,6 @@ show_options:		no				(vfsmount->sem)
 quota_read:		no	no	no		(see below)
 quota_write:		no	no	no		(see below)
 
-->read_inode() is not a method - it's a callback used in iget().
 ->remount_fs() will have the s_umount lock if it's already mounted.
 When called from get_sb_single, it does NOT have the s_umount lock.
 ->quota_read() and ->quota_write() functions are both guaranteed to
diff --git a/Documentation/filesystems/dnotify.txt b/Documentation/filesystems/dnotify.txt
new file mode 100644
index 00000000000..9f5d338ddbb
--- /dev/null
+++ b/Documentation/filesystems/dnotify.txt
@@ -0,0 +1,99 @@
+		Linux Directory Notification
+		============================
+
+	   Stephen Rothwell <sfr@canb.auug.org.au>
+
+The intention of directory notification is to allow user applications
+to be notified when a directory, or any of the files in it, are changed.
+The basic mechanism involves the application registering for notification
+on a directory using a fcntl(2) call and the notifications themselves
+being delivered using signals.
+
+The application decides which "events" it wants to be notified about.
+The currently defined events are:
+
+	DN_ACCESS	A file in the directory was accessed (read)
+	DN_MODIFY	A file in the directory was modified (write,truncate)
+	DN_CREATE	A file was created in the directory
+	DN_DELETE	A file was unlinked from directory
+	DN_RENAME	A file in the directory was renamed
+	DN_ATTRIB	A file in the directory had its attributes
+			changed (chmod,chown)
+
+Usually, the application must reregister after each notification, but
+if DN_MULTISHOT is or'ed with the event mask, then the registration will
+remain until explicitly removed (by registering for no events).
+
+By default, SIGIO will be delivered to the process and no other useful
+information.  However, if the F_SETSIG fcntl(2) call is used to let the
+kernel know which signal to deliver, a siginfo structure will be passed to
+the signal handler and the si_fd member of that structure will contain the
+file descriptor associated with the directory in which the event occurred.
+
+Preferably the application will choose one of the real time signals
+(SIGRTMIN + <n>) so that the notifications may be queued.  This is
+especially important if DN_MULTISHOT is specified.  Note that SIGRTMIN
+is often blocked, so it is better to use (at least) SIGRTMIN + 1.
+
+Implementation expectations (features and bugs :-))
+---------------------------
+
+The notification should work for any local access to files even if the
+actual file system is on a remote server.  This implies that remote
+access to files served by local user mode servers should be notified.
+Also, remote accesses to files served by a local kernel NFS server should
+be notified.
+
+In order to make the impact on the file system code as small as possible,
+the problem of hard links to files has been ignored.  So if a file (x)
+exists in two directories (a and b) then a change to the file using the
+name "a/x" should be notified to a program expecting notifications on
+directory "a", but will not be notified to one expecting notifications on
+directory "b".
+
+Also, files that are unlinked, will still cause notifications in the
+last directory that they were linked to.
+
+Configuration
+-------------
+
+Dnotify is controlled via the CONFIG_DNOTIFY configuration option.  When
+disabled, fcntl(fd, F_NOTIFY, ...) will return -EINVAL.
+
+Example
+-------
+
+	#define _GNU_SOURCE	/* needed to get the defines */
+	#include <fcntl.h>	/* in glibc 2.2 this has the needed
+					   values defined */
+	#include <signal.h>
+	#include <stdio.h>
+	#include <unistd.h>
+
+	static volatile int event_fd;
+
+	static void handler(int sig, siginfo_t *si, void *data)
+	{
+		event_fd = si->si_fd;
+	}
+
+	int main(void)
+	{
+		struct sigaction act;
+		int fd;
+
+		act.sa_sigaction = handler;
+		sigemptyset(&act.sa_mask);
+		act.sa_flags = SA_SIGINFO;
+		sigaction(SIGRTMIN + 1, &act, NULL);
+
+		fd = open(".", O_RDONLY);
+		fcntl(fd, F_SETSIG, SIGRTMIN + 1);
+		fcntl(fd, F_NOTIFY, DN_MODIFY|DN_CREATE|DN_MULTISHOT);
+		/* we will now be notified if any of the files
+		   in "." is modified or new files are created */
+		while (1) {
+			pause();
+			printf("Got event on fd=%d\n", event_fd);
+		}
+	}
diff --git a/Documentation/filesystems/isofs.txt b/Documentation/filesystems/isofs.txt
index 758e50401c1..6973b980ca2 100644
--- a/Documentation/filesystems/isofs.txt
+++ b/Documentation/filesystems/isofs.txt
@@ -24,6 +24,7 @@ Mount options unique to the isofs filesystem.
   map=normal    Map non-Rock Ridge filenames to lower case
   map=acorn     As map=normal but also apply Acorn extensions if present
   mode=xxx      Sets the permissions on files to xxx
+  dmode=xxx     Sets the permissions on directories to xxx
   nojoliet      Ignore Joliet extensions if they are present.
   norock        Ignore Rock Ridge extensions if they are present.
   hide		Completely strip hidden files from the file system.
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 0f33c77bc14..92b888d540a 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -34,8 +34,8 @@ FOO_I(inode) (see in-tree filesystems for examples).
 
 Make them ->alloc_inode and ->destroy_inode in your super_operations.
 
-Keep in mind that now you need explicit initialization of private data -
-typically in ->read_inode() and after getting an inode from new_inode().
+Keep in mind that now you need explicit initialization of private data
+typically between calling iget_locked() and unlocking the inode.
 
 At some point that will become mandatory.
 
@@ -173,10 +173,10 @@ should be a non-blocking function that initializes those parts of a
 newly created inode to allow the test function to succeed. 'data' is
 passed as an opaque value to both test and set functions.
 
-When the inode has been created by iget5_locked(), it will be returned with
-the I_NEW flag set and will still be locked. read_inode has not been
-called so the file system still has to finalize the initialization. Once
-the inode is initialized it must be unlocked by calling unlock_new_inode().
+When the inode has been created by iget5_locked(), it will be returned with the
+I_NEW flag set and will still be locked.  The filesystem then needs to finalize
+the initialization. Once the inode is initialized it must be unlocked by
+calling unlock_new_inode().
 
 The filesystem is responsible for setting (and possibly testing) i_ino
 when appropriate. There is also a simpler iget_locked function that
@@ -184,11 +184,19 @@ just takes the superblock and inode number as arguments and does the
 test and set for you.
 
 e.g.
-       inode = iget_locked(sb, ino);
-       if (inode->i_state & I_NEW) {
-               read_inode_from_disk(inode);
-               unlock_new_inode(inode);
-       }
+	inode = iget_locked(sb, ino);
+	if (inode->i_state & I_NEW) {
+		err = read_inode_from_disk(inode);
+		if (err < 0) {
+			iget_failed(inode);
+			return err;
+		}
+		unlock_new_inode(inode);
+	}
+
+Note that if the process of setting up a new inode fails, then iget_failed()
+should be called on the inode to render it dead, and an appropriate error
+should be passed back to the caller.
 
 ---
 [recommended]
diff --git a/Documentation/filesystems/sharedsubtree.txt b/Documentation/filesystems/sharedsubtree.txt
new file mode 100644
index 00000000000..736540045dc
--- /dev/null
+++ b/Documentation/filesystems/sharedsubtree.txt
@@ -0,0 +1,1061 @@
+Shared Subtrees
+---------------
+
+Contents:
+	1) Overview
+	2) Features
+	3) smount command
+	4) Use-case
+	5) Detailed semantics
+	6) Quiz
+	7) FAQ
+	8) Implementation
+
+
+1) Overview
+-----------
+
+Consider the following situation:
+
+A process wants to clone its own namespace, but still wants to access the CD
+that got mounted recently.  Shared subtree semantics provide the necessary
+mechanism to accomplish the above.
+
+It provides the necessary building blocks for features like per-user-namespace
+and versioned filesystem.
+
+2) Features
+-----------
+
+Shared subtree provides four different flavors of mounts; struct vfsmount to be
+precise
+
+	a. shared mount
+	b. slave mount
+	c. private mount
+	d. unbindable mount
+
+
+2a) A shared mount can be replicated to as many mountpoints and all the
+replicas continue to be exactly same.
+
+	Here is an example:
+
+	Lets say /mnt has a mount that is shared.
+	mount --make-shared /mnt
+
+	note: mount command does not yet support the --make-shared flag.
+	I have included a small C program which does the same by executing
+	'smount /mnt shared'
+
+	#mount --bind /mnt /tmp
+	The above command replicates the mount at /mnt to the mountpoint /tmp
+	and the contents of both the mounts remain identical.
+
+	#ls /mnt
+	a b c
+
+	#ls /tmp
+	a b c
+
+	Now lets say we mount a device at /tmp/a
+	#mount /dev/sd0  /tmp/a
+
+	#ls /tmp/a
+	t1 t2 t2
+
+	#ls /mnt/a
+	t1 t2 t2
+
+	Note that the mount has propagated to the mount at /mnt as well.
+
+	And the same is true even when /dev/sd0 is mounted on /mnt/a. The
+	contents will be visible under /tmp/a too.
+
+
+2b) A slave mount is like a shared mount except that mount and umount events
+	only propagate towards it.
+
+	All slave mounts have a master mount which is a shared.
+
+	Here is an example:
+
+	Lets say /mnt has a mount which is shared.
+	#mount --make-shared /mnt
+
+	Lets bind mount /mnt to /tmp
+	#mount --bind /mnt /tmp
+
+	the new mount at /tmp becomes a shared mount and it is a replica of
+	the mount at /mnt.
+
+	Now lets make the mount at /tmp; a slave of /mnt
+	#mount --make-slave /tmp
+	[or smount /tmp slave]
+
+	lets mount /dev/sd0 on /mnt/a
+	#mount /dev/sd0 /mnt/a
+
+	#ls /mnt/a
+	t1 t2 t3
+
+	#ls /tmp/a
+	t1 t2 t3
+
+	Note the mount event has propagated to the mount at /tmp
+
+	However lets see what happens if we mount something on the mount at /tmp
+
+	#mount /dev/sd1 /tmp/b
+
+	#ls /tmp/b
+	s1 s2 s3
+
+	#ls /mnt/b
+
+	Note how the mount event has not propagated to the mount at
+	/mnt
+
+
+2c) A private mount does not forward or receive propagation.
+
+	This is the mount we are familiar with. Its the default type.
+
+
+2d) A unbindable mount is a unbindable private mount
+
+	lets say we have a mount at /mnt and we make is unbindable
+
+	#mount --make-unbindable /mnt
+	 [ smount /mnt  unbindable ]
+
+	 Lets try to bind mount this mount somewhere else.
+	 # mount --bind /mnt /tmp
+	 mount: wrong fs type, bad option, bad superblock on /mnt,
+	        or too many mounted file systems
+
+	Binding a unbindable mount is a invalid operation.
+
+
+3) smount command
+
+	Currently the mount command is not aware of shared subtree features.
+	Work is in progress to add the support in mount ( util-linux package ).
+	Till then use the following program.
+
+	------------------------------------------------------------------------
+	//
+	//this code was developed my Miklos Szeredi <miklos@szeredi.hu>
+	//and modified by Ram Pai <linuxram@us.ibm.com>
+	// sample usage:
+	//              smount /tmp shared
+	//
+	#include <stdio.h>
+	#include <stdlib.h>
+	#include <unistd.h>
+	#include <string.h>
+	#include <sys/mount.h>
+	#include <sys/fsuid.h>
+
+	#ifndef MS_REC
+	#define MS_REC		0x4000	/* 16384: Recursive loopback */
+	#endif
+
+	#ifndef MS_SHARED
+	#define MS_SHARED		1<<20	/* Shared */
+	#endif
+
+	#ifndef MS_PRIVATE
+	#define MS_PRIVATE		1<<18	/* Private */
+	#endif
+
+	#ifndef MS_SLAVE
+	#define MS_SLAVE		1<<19	/* Slave */
+	#endif
+
+	#ifndef MS_UNBINDABLE
+	#define MS_UNBINDABLE		1<<17	/* Unbindable */
+	#endif
+
+	int main(int argc, char *argv[])
+	{
+		int type;
+		if(argc != 3) {
+			fprintf(stderr, "usage: %s dir "
+			"<rshared|rslave|rprivate|runbindable|shared|slave"
+			"|private|unbindable>\n" , argv[0]);
+			return 1;
+		}
+
+		fprintf(stdout, "%s %s %s\n", argv[0], argv[1], argv[2]);
+
+		if (strcmp(argv[2],"rshared")==0)
+			type=(MS_SHARED|MS_REC);
+		else if (strcmp(argv[2],"rslave")==0)
+			type=(MS_SLAVE|MS_REC);
+		else if (strcmp(argv[2],"rprivate")==0)
+			type=(MS_PRIVATE|MS_REC);
+		else if (strcmp(argv[2],"runbindable")==0)
+			type=(MS_UNBINDABLE|MS_REC);
+		else if (strcmp(argv[2],"shared")==0)
+			type=MS_SHARED;
+		else if (strcmp(argv[2],"slave")==0)
+			type=MS_SLAVE;
+		else if (strcmp(argv[2],"private")==0)
+			type=MS_PRIVATE;
+		else if (strcmp(argv[2],"unbindable")==0)
+			type=MS_UNBINDABLE;
+		else {
+			fprintf(stderr, "invalid operation: %s\n", argv[2]);
+			return 1;
+		}
+		setfsuid(getuid());
+
+		if(mount("", argv[1], "dontcare", type, "") == -1) {
+			perror("mount");
+			return 1;
+		}
+		return 0;
+	}
+	-----------------------------------------------------------------------
+
+	Copy the above code snippet into smount.c
+	gcc -o smount smount.c
+
+
+	(i) To mark all the mounts under /mnt as shared execute the following
+	command:
+
+	 	smount /mnt rshared
+		the corresponding syntax planned for mount command is
+		mount --make-rshared /mnt
+
+	    just to mark a mount /mnt as shared, execute the following
+	    command:
+	 	smount /mnt shared
+		the corresponding syntax planned for mount command is
+		mount --make-shared /mnt
+
+	(ii) To mark all the shared mounts under /mnt as slave execute the
+	following
+
+	     command:
+		smount /mnt rslave
+		the corresponding syntax planned for mount command is
+		mount --make-rslave /mnt
+
+	    just to mark a mount /mnt as slave, execute the following
+	    command:
+	 	smount /mnt slave
+		the corresponding syntax planned for mount command is
+		mount --make-slave /mnt
+
+	(iii) To mark all the mounts under /mnt as private execute the
+	following command:
+
+		smount /mnt rprivate
+		the corresponding syntax planned for mount command is
+		mount --make-rprivate /mnt
+
+	    just to mark a mount /mnt as private, execute the following
+	    command:
+	 	smount /mnt private
+		the corresponding syntax planned for mount command is
+		mount --make-private /mnt
+
+	      NOTE: by default all the mounts are created as private. But if
+	      you want to change some shared/slave/unbindable  mount as
+	      private at a later point in time, this command can help.
+
+	(iv) To mark all the mounts under /mnt as unbindable execute the
+	following
+
+	     command:
+		smount /mnt runbindable
+		the corresponding syntax planned for mount command is
+		mount --make-runbindable /mnt
+
+	    just to mark a mount /mnt as unbindable, execute the following
+	    command:
+	 	smount /mnt unbindable
+		the corresponding syntax planned for mount command is
+		mount --make-unbindable /mnt
+
+
+4) Use cases
+------------
+
+	A) A process wants to clone its own namespace, but still wants to
+	   access the CD that got mounted recently.
+
+	   Solution:
+
+		The system administrator can make the mount at /cdrom shared
+		mount --bind /cdrom /cdrom
+		mount --make-shared /cdrom
+
+		Now any process that clones off a new namespace will have a
+		mount at /cdrom which is a replica of the same mount in the
+		parent namespace.
+
+		So when a CD is inserted and mounted at /cdrom that mount gets
+		propagated to the other mount at /cdrom in all the other clone
+		namespaces.
+
+	B) A process wants its mounts invisible to any other process, but
+	still be able to see the other system mounts.
+
+	   Solution:
+
+		To begin with, the administrator can mark the entire mount tree
+		as shareable.
+
+		mount --make-rshared /
+
+		A new process can clone off a new namespace. And mark some part
+		of its namespace as slave
+
+		mount --make-rslave /myprivatetree
+
+		Hence forth any mounts within the /myprivatetree done by the
+		process will not show up in any other namespace. However mounts
+		done in the parent namespace under /myprivatetree still shows
+		up in the process's namespace.
+
+
+	Apart from the above semantics this feature provides the
+	building blocks to solve the following problems:
+
+	C)  Per-user namespace
+
+		The above semantics allows a way to share mounts across
+		namespaces.  But namespaces are associated with processes. If
+		namespaces are made first class objects with user API to
+		associate/disassociate a namespace with userid, then each user
+		could have his/her own namespace and tailor it to his/her
+		requirements. Offcourse its needs support from PAM.
+
+	D)  Versioned files
+
+		If the entire mount tree is visible at multiple locations, then
+		a underlying versioning file system can return different
+		version of the file depending on the path used to access that
+		file.
+
+		An example is:
+
+		mount --make-shared /
+		mount --rbind / /view/v1
+		mount --rbind / /view/v2
+		mount --rbind / /view/v3
+		mount --rbind / /view/v4
+
+		and if /usr has a versioning filesystem mounted, than that
+		mount appears at /view/v1/usr, /view/v2/usr, /view/v3/usr and
+		/view/v4/usr too
+
+		A user can request v3 version of the file /usr/fs/namespace.c
+		by accessing /view/v3/usr/fs/namespace.c . The underlying
+		versioning filesystem can then decipher that v3 version of the
+		filesystem is being requested and return the corresponding
+		inode.
+
+5) Detailed semantics:
+-------------------
+	The section below explains the detailed semantics of
+	bind, rbind, move, mount, umount and clone-namespace operations.
+
+	Note: the word 'vfsmount' and the noun 'mount' have been used
+	to mean the same thing, throughout this document.
+
+5a) Mount states
+
+	A given mount can be in one of the following states
+	1) shared
+	2) slave
+	3) shared and slave
+	4) private
+	5) unbindable
+
+	A 'propagation event' is defined as event generated on a vfsmount
+	that leads to mount or unmount actions in other vfsmounts.
+
+	A 'peer group' is defined as a group of vfsmounts that propagate
+	events to each other.
+
+	(1) Shared mounts
+
+		A 'shared mount' is defined as a vfsmount that belongs to a
+		'peer group'.
+
+		For example:
+			mount --make-shared /mnt
+			mount --bin /mnt /tmp
+
+		The mount at /mnt and that at /tmp are both shared and belong
+		to the same peer group. Anything mounted or unmounted under
+		/mnt or /tmp reflect in all the other mounts of its peer
+		group.
+
+
+	(2) Slave mounts
+
+		A 'slave mount' is defined as a vfsmount that receives
+		propagation events and does not forward propagation events.
+
+		A slave mount as the name implies has a master mount from which
+		mount/unmount events are received. Events do not propagate from
+		the slave mount to the master.  Only a shared mount can be made
+		a slave by executing the following command
+
+			mount --make-slave mount
+
+		A shared mount that is made as a slave is no more shared unless
+		modified to become shared.
+
+	(3) Shared and Slave
+
+		A vfsmount can be both shared as well as slave.  This state
+		indicates that the mount is a slave of some vfsmount, and
+		has its own peer group too.  This vfsmount receives propagation
+		events from its master vfsmount, and also forwards propagation
+		events to its 'peer group' and to its slave vfsmounts.
+
+		Strictly speaking, the vfsmount is shared having its own
+		peer group, and this peer-group is a slave of some other
+		peer group.
+
+		Only a slave vfsmount can be made as 'shared and slave' by
+		either executing the following command
+			mount --make-shared mount
+		or by moving the slave vfsmount under a shared vfsmount.
+
+	(4) Private mount
+
+		A 'private mount' is defined as vfsmount that does not
+		receive or forward any propagation events.
+
+	(5) Unbindable mount
+
+		A 'unbindable mount' is defined as vfsmount that does not
+		receive or forward any propagation events and cannot
+		be bind mounted.
+
+
+   	State diagram:
+   	The state diagram below explains the state transition of a mount,
+	in response to various commands.
+	------------------------------------------------------------------------
+	|             |make-shared |  make-slave  | make-private |make-unbindab|
+	--------------|------------|--------------|--------------|-------------|
+	|shared	      |shared	   |*slave/private|   private	 | unbindable  |
+	|             |            |              |              |             |
+	|-------------|------------|--------------|--------------|-------------|
+	|slave	      |shared      |	**slave	  |    private   | unbindable  |
+	|             |and slave   |              |              |             |
+	|-------------|------------|--------------|--------------|-------------|
+	|shared	      |shared      |    slave	  |    private   | unbindable  |
+	|and slave    |and slave   |              |              |             |
+	|-------------|------------|--------------|--------------|-------------|
+	|private      |shared	   |  **private	  |    private   | unbindable  |
+	|-------------|------------|--------------|--------------|-------------|
+	|unbindable   |shared	   |**unbindable  |    private   | unbindable  |
+	------------------------------------------------------------------------
+
+	* if the shared mount is the only mount in its peer group, making it
+	slave, makes it private automatically. Note that there is no master to
+	which it can be slaved to.
+
+	** slaving a non-shared mount has no effect on the mount.
+
+	Apart from the commands listed below, the 'move' operation also changes
+	the state of a mount depending on type of the destination mount. Its
+	explained in section 5d.
+
+5b) Bind semantics
+
+	Consider the following command
+
+	mount --bind A/a  B/b
+
+	where 'A' is the source mount, 'a' is the dentry in the mount 'A', 'B'
+	is the destination mount and 'b' is the dentry in the destination mount.
+
+	The outcome depends on the type of mount of 'A' and 'B'. The table
+	below contains quick reference.
+   ---------------------------------------------------------------------------
+   |         BIND MOUNT OPERATION                                            |
+   |**************************************************************************
+   |source(A)->| shared       |       private  |       slave    | unbindable |
+   | dest(B)  |               |                |                |            |
+   |   |      |               |                |                |            |
+   |   v      |               |                |                |            |
+   |**************************************************************************
+   |  shared  | shared        |     shared     | shared & slave |  invalid   |
+   |          |               |                |                |            |
+   |non-shared| shared        |      private   |      slave     |  invalid   |
+   ***************************************************************************
+
+     	Details:
+
+	1. 'A' is a shared mount and 'B' is a shared mount. A new mount 'C'
+	which is clone of 'A', is created. Its root dentry is 'a' . 'C' is
+	mounted on mount 'B' at dentry 'b'. Also new mount 'C1', 'C2', 'C3' ...
+	are created and mounted at the dentry 'b' on all mounts where 'B'
+	propagates to. A new propagation tree containing 'C1',..,'Cn' is
+	created. This propagation tree is identical to the propagation tree of
+	'B'.  And finally the peer-group of 'C' is merged with the peer group
+	of 'A'.
+
+	2. 'A' is a private mount and 'B' is a shared mount. A new mount 'C'
+	which is clone of 'A', is created. Its root dentry is 'a'. 'C' is
+	mounted on mount 'B' at dentry 'b'. Also new mount 'C1', 'C2', 'C3' ...
+	are created and mounted at the dentry 'b' on all mounts where 'B'
+	propagates to. A new propagation tree is set containing all new mounts
+	'C', 'C1', .., 'Cn' with exactly the same configuration as the
+	propagation tree for 'B'.
+
+	3. 'A' is a slave mount of mount 'Z' and 'B' is a shared mount. A new
+	mount 'C' which is clone of 'A', is created. Its root dentry is 'a' .
+	'C' is mounted on mount 'B' at dentry 'b'. Also new mounts 'C1', 'C2',
+	'C3' ... are created and mounted at the dentry 'b' on all mounts where
+	'B' propagates to. A new propagation tree containing the new mounts
+	'C','C1',..  'Cn' is created. This propagation tree is identical to the
+	propagation tree for 'B'. And finally the mount 'C' and its peer group
+	is made the slave of mount 'Z'.  In other words, mount 'C' is in the
+	state 'slave and shared'.
+
+	4. 'A' is a unbindable mount and 'B' is a shared mount. This is a
+	invalid operation.
+
+	5. 'A' is a private mount and 'B' is a non-shared(private or slave or
+	unbindable) mount. A new mount 'C' which is clone of 'A', is created.
+	Its root dentry is 'a'. 'C' is mounted on mount 'B' at dentry 'b'.
+
+	6. 'A' is a shared mount and 'B' is a non-shared mount. A new mount 'C'
+	which is a clone of 'A' is created. Its root dentry is 'a'. 'C' is
+	mounted on mount 'B' at dentry 'b'.  'C' is made a member of the
+	peer-group of 'A'.
+
+	7. 'A' is a slave mount of mount 'Z' and 'B' is a non-shared mount. A
+	new mount 'C' which is a clone of 'A' is created. Its root dentry is
+	'a'.  'C' is mounted on mount 'B' at dentry 'b'. Also 'C' is set as a
+	slave mount of 'Z'. In other words 'A' and 'C' are both slave mounts of
+	'Z'.  All mount/unmount events on 'Z' propagates to 'A' and 'C'. But
+	mount/unmount on 'A' do not propagate anywhere else. Similarly
+	mount/unmount on 'C' do not propagate anywhere else.
+
+	8. 'A' is a unbindable mount and 'B' is a non-shared mount. This is a
+	invalid operation. A unbindable mount cannot be bind mounted.
+
+5c) Rbind semantics
+
+	rbind is same as bind. Bind replicates the specified mount.  Rbind
+	replicates all the mounts in the tree belonging to the specified mount.
+	Rbind mount is bind mount applied to all the mounts in the tree.
+
+	If the source tree that is rbind has some unbindable mounts,
+	then the subtree under the unbindable mount is pruned in the new
+	location.
+
+	eg: lets say we have the following mount tree.
+
+		A
+	      /   \
+	      B   C
+	     / \ / \
+	     D E F G
+
+	     Lets say all the mount except the mount C in the tree are
+	     of a type other than unbindable.
+
+	     If this tree is rbound to say Z
+
+	     We will have the following tree at the new location.
+
+		Z
+		|
+		A'
+	       /
+	      B'		Note how the tree under C is pruned
+	     / \ 		in the new location.
+	    D' E'
+
+
+
+5d) Move semantics
+
+	Consider the following command
+
+	mount --move A  B/b
+
+	where 'A' is the source mount, 'B' is the destination mount and 'b' is
+	the dentry in the destination mount.
+
+	The outcome depends on the type of the mount of 'A' and 'B'. The table
+	below is a quick reference.
+   ---------------------------------------------------------------------------
+   |         		MOVE MOUNT OPERATION                                 |
+   |**************************************************************************
+   | source(A)->| shared      |       private  |       slave    | unbindable |
+   | dest(B)  |               |                |                |            |
+   |   |      |               |                |                |            |
+   |   v      |               |                |                |            |
+   |**************************************************************************
+   |  shared  | shared        |     shared     |shared and slave|  invalid   |
+   |          |               |                |                |            |
+   |non-shared| shared        |      private   |    slave       | unbindable |
+   ***************************************************************************
+	NOTE: moving a mount residing under a shared mount is invalid.
+
+      Details follow:
+
+	1. 'A' is a shared mount and 'B' is a shared mount.  The mount 'A' is
+	mounted on mount 'B' at dentry 'b'.  Also new mounts 'A1', 'A2'...'An'
+	are created and mounted at dentry 'b' on all mounts that receive
+	propagation from mount 'B'. A new propagation tree is created in the
+	exact same configuration as that of 'B'. This new propagation tree
+	contains all the new mounts 'A1', 'A2'...  'An'.  And this new
+	propagation tree is appended to the already existing propagation tree
+	of 'A'.
+
+	2. 'A' is a private mount and 'B' is a shared mount. The mount 'A' is
+	mounted on mount 'B' at dentry 'b'. Also new mount 'A1', 'A2'... 'An'
+	are created and mounted at dentry 'b' on all mounts that receive
+	propagation from mount 'B'. The mount 'A' becomes a shared mount and a
+	propagation tree is created which is identical to that of
+	'B'. This new propagation tree contains all the new mounts 'A1',
+	'A2'...  'An'.
+
+	3. 'A' is a slave mount of mount 'Z' and 'B' is a shared mount.  The
+	mount 'A' is mounted on mount 'B' at dentry 'b'.  Also new mounts 'A1',
+	'A2'... 'An' are created and mounted at dentry 'b' on all mounts that
+	receive propagation from mount 'B'. A new propagation tree is created
+	in the exact same configuration as that of 'B'. This new propagation
+	tree contains all the new mounts 'A1', 'A2'...  'An'.  And this new
+	propagation tree is appended to the already existing propagation tree of
+	'A'.  Mount 'A' continues to be the slave mount of 'Z' but it also
+	becomes 'shared'.
+
+	4. 'A' is a unbindable mount and 'B' is a shared mount. The operation
+	is invalid. Because mounting anything on the shared mount 'B' can
+	create new mounts that get mounted on the mounts that receive
+	propagation from 'B'.  And since the mount 'A' is unbindable, cloning
+	it to mount at other mountpoints is not possible.
+
+	5. 'A' is a private mount and 'B' is a non-shared(private or slave or
+	unbindable) mount. The mount 'A' is mounted on mount 'B' at dentry 'b'.
+
+	6. 'A' is a shared mount and 'B' is a non-shared mount.  The mount 'A'
+	is mounted on mount 'B' at dentry 'b'.  Mount 'A' continues to be a
+	shared mount.
+
+	7. 'A' is a slave mount of mount 'Z' and 'B' is a non-shared mount.
+	The mount 'A' is mounted on mount 'B' at dentry 'b'.  Mount 'A'
+	continues to be a slave mount of mount 'Z'.
+
+	8. 'A' is a unbindable mount and 'B' is a non-shared mount. The mount
+	'A' is mounted on mount 'B' at dentry 'b'. Mount 'A' continues to be a
+	unbindable mount.
+
+5e) Mount semantics
+
+	Consider the following command
+
+	mount device  B/b
+
+	'B' is the destination mount and 'b' is the dentry in the destination
+	mount.
+
+	The above operation is the same as bind operation with the exception
+	that the source mount is always a private mount.
+
+
+5f) Unmount semantics
+
+	Consider the following command
+
+	umount A
+
+	where 'A' is a mount mounted on mount 'B' at dentry 'b'.
+
+	If mount 'B' is shared, then all most-recently-mounted mounts at dentry
+	'b' on mounts that receive propagation from mount 'B' and does not have
+	sub-mounts within them are unmounted.
+
+	Example: Lets say 'B1', 'B2', 'B3' are shared mounts that propagate to
+	each other.
+
+	lets say 'A1', 'A2', 'A3' are first mounted at dentry 'b' on mount
+	'B1', 'B2' and 'B3' respectively.
+
+	lets say 'C1', 'C2', 'C3' are next mounted at the same dentry 'b' on
+	mount 'B1', 'B2' and 'B3' respectively.
+
+	if 'C1' is unmounted, all the mounts that are most-recently-mounted on
+	'B1' and on the mounts that 'B1' propagates-to are unmounted.
+
+	'B1' propagates to 'B2' and 'B3'. And the most recently mounted mount
+	on 'B2' at dentry 'b' is 'C2', and that of mount 'B3' is 'C3'.
+
+	So all 'C1', 'C2' and 'C3' should be unmounted.
+
+	If any of 'C2' or 'C3' has some child mounts, then that mount is not
+	unmounted, but all other mounts are unmounted. However if 'C1' is told
+	to be unmounted and 'C1' has some sub-mounts, the umount operation is
+	failed entirely.
+
+5g) Clone Namespace
+
+	A cloned namespace contains all the mounts as that of the parent
+	namespace.
+
+	Lets say 'A' and 'B' are the corresponding mounts in the parent and the
+	child namespace.
+
+	If 'A' is shared, then 'B' is also shared and 'A' and 'B' propagate to
+	each other.
+
+	If 'A' is a slave mount of 'Z', then 'B' is also the slave mount of
+	'Z'.
+
+	If 'A' is a private mount, then 'B' is a private mount too.
+
+	If 'A' is unbindable mount, then 'B' is a unbindable mount too.
+
+
+6) Quiz
+
+	A. What is the result of the following command sequence?
+
+		mount --bind /mnt /mnt
+		mount --make-shared /mnt
+		mount --bind /mnt /tmp
+		mount --move /tmp /mnt/1
+
+		what should be the contents of /mnt /mnt/1 /mnt/1/1 should be?
+		Should they all be identical? or should /mnt and /mnt/1 be
+		identical only?
+
+
+	B. What is the result of the following command sequence?
+
+		mount --make-rshared /
+		mkdir -p /v/1
+		mount --rbind / /v/1
+
+		what should be the content of /v/1/v/1 be?
+
+
+	C. What is the result of the following command sequence?
+
+		mount --bind /mnt /mnt
+		mount --make-shared /mnt
+		mkdir -p /mnt/1/2/3 /mnt/1/test
+		mount --bind /mnt/1 /tmp
+		mount --make-slave /mnt
+		mount --make-shared /mnt
+		mount --bind /mnt/1/2 /tmp1
+		mount --make-slave /mnt
+
+		At this point we have the first mount at /tmp and
+		its root dentry is 1. Lets call this mount 'A'
+		And then we have a second mount at /tmp1 with root
+		dentry 2. Lets call this mount 'B'
+		Next we have a third mount at /mnt with root dentry
+		mnt. Lets call this mount 'C'
+
+		'B' is the slave of 'A' and 'C' is a slave of 'B'
+		A -> B -> C
+
+		at this point if we execute the following command
+
+		mount --bind /bin /tmp/test
+
+		The mount is attempted on 'A'
+
+		will the mount propagate to 'B' and 'C' ?
+
+		what would be the contents of
+		/mnt/1/test be?
+
+7) FAQ
+
+	Q1. Why is bind mount needed? How is it different from symbolic links?
+		symbolic links can get stale if the destination mount gets
+		unmounted or moved. Bind mounts continue to exist even if the
+		other mount is unmounted or moved.
+
+	Q2. Why can't the shared subtree be implemented using exportfs?
+
+		exportfs is a heavyweight way of accomplishing part of what
+		shared subtree can do. I cannot imagine a way to implement the
+		semantics of slave mount using exportfs?
+
+	Q3 Why is unbindable mount needed?
+
+		Lets say we want to replicate the mount tree at multiple
+		locations within the same subtree.
+
+		if one rbind mounts a tree within the same subtree 'n' times
+		the number of mounts created is an exponential function of 'n'.
+		Having unbindable mount can help prune the unneeded bind
+		mounts. Here is a example.
+
+		step 1:
+		   lets say the root tree has just two directories with
+		   one vfsmount.
+				    root
+				   /    \
+				  tmp    usr
+
+		    And we want to replicate the tree at multiple
+		    mountpoints under /root/tmp
+
+		step2:
+		      mount --make-shared /root
+
+		      mkdir -p /tmp/m1
+
+		      mount --rbind /root /tmp/m1
+
+		      the new tree now looks like this:
+
+				    root
+				   /    \
+				 tmp    usr
+				/
+			       m1
+			      /  \
+			     tmp  usr
+			     /
+			    m1
+
+			  it has two vfsmounts
+
+		step3:
+			    mkdir -p /tmp/m2
+			    mount --rbind /root /tmp/m2
+
+			the new tree now looks like this:
+
+				      root
+				     /    \
+				   tmp     usr
+				  /    \
+				m1       m2
+			       / \       /  \
+			     tmp  usr   tmp  usr
+			     / \          /
+			    m1  m2      m1
+				/ \     /  \
+			      tmp usr  tmp   usr
+			      /        / \
+			     m1       m1  m2
+			    /  \
+			  tmp   usr
+			  /  \
+			 m1   m2
+
+		       it has 6 vfsmounts
+
+		step 4:
+			  mkdir -p /tmp/m3
+			  mount --rbind /root /tmp/m3
+
+			  I wont' draw the tree..but it has 24 vfsmounts
+
+
+		at step i the number of vfsmounts is V[i] = i*V[i-1].
+		This is an exponential function. And this tree has way more
+		mounts than what we really needed in the first place.
+
+		One could use a series of umount at each step to prune
+		out the unneeded mounts. But there is a better solution.
+		Unclonable mounts come in handy here.
+
+		step 1:
+		   lets say the root tree has just two directories with
+		   one vfsmount.
+				    root
+				   /    \
+				  tmp    usr
+
+		    How do we set up the same tree at multiple locations under
+		    /root/tmp
+
+		step2:
+		      mount --bind /root/tmp /root/tmp
+
+		      mount --make-rshared /root
+		      mount --make-unbindable /root/tmp
+
+		      mkdir -p /tmp/m1
+
+		      mount --rbind /root /tmp/m1
+
+		      the new tree now looks like this:
+
+				    root
+				   /    \
+				 tmp    usr
+				/
+			       m1
+			      /  \
+			     tmp  usr
+
+		step3:
+			    mkdir -p /tmp/m2
+			    mount --rbind /root /tmp/m2
+
+		      the new tree now looks like this:
+
+				    root
+				   /    \
+				 tmp    usr
+				/   \
+			       m1     m2
+			      /  \     / \
+			     tmp  usr tmp usr
+
+		step4:
+
+			    mkdir -p /tmp/m3
+			    mount --rbind /root /tmp/m3
+
+		      the new tree now looks like this:
+
+				    	  root
+				      /    	  \
+				     tmp    	   usr
+			         /    \    \
+			       m1     m2     m3
+			      /  \     / \    /  \
+			     tmp  usr tmp usr tmp usr
+
+8) Implementation
+
+8A) Datastructure
+
+	4 new fields are introduced to struct vfsmount
+	->mnt_share
+	->mnt_slave_list
+	->mnt_slave
+	->mnt_master
+
+	->mnt_share links together all the mount to/from which this vfsmount
+		send/receives propagation events.
+
+	->mnt_slave_list links all the mounts to which this vfsmount propagates
+		to.
+
+	->mnt_slave links together all the slaves that its master vfsmount
+		propagates to.
+
+	->mnt_master points to the master vfsmount from which this vfsmount
+		receives propagation.
+
+	->mnt_flags takes two more flags to indicate the propagation status of
+		the vfsmount.  MNT_SHARE indicates that the vfsmount is a shared
+		vfsmount.  MNT_UNCLONABLE indicates that the vfsmount cannot be
+		replicated.
+
+	All the shared vfsmounts in a peer group form a cyclic list through
+	->mnt_share.
+
+	All vfsmounts with the same ->mnt_master form on a cyclic list anchored
+	in ->mnt_master->mnt_slave_list and going through ->mnt_slave.
+
+	 ->mnt_master can point to arbitrary (and possibly different) members
+	 of master peer group.  To find all immediate slaves of a peer group
+	 you need to go through _all_ ->mnt_slave_list of its members.
+	 Conceptually it's just a single set - distribution among the
+	 individual lists does not affect propagation or the way propagation
+	 tree is modified by operations.
+
+	A example propagation tree looks as shown in the figure below.
+	[ NOTE: Though it looks like a forest, if we consider all the shared
+	mounts as a conceptual entity called 'pnode', it becomes a tree]
+
+
+		        A <--> B <--> C <---> D
+		       /|\	      /|      |\
+		      / F G	     J K      H I
+		     /
+		    E<-->K
+			/|\
+		       M L N
+
+	In the above figure  A,B,C and D all are shared and propagate to each
+	other.   'A' has got 3 slave mounts 'E' 'F' and 'G' 'C' has got 2 slave
+	mounts 'J' and 'K'  and  'D' has got two slave mounts 'H' and 'I'.
+	'E' is also shared with 'K' and they propagate to each other.  And
+	'K' has 3 slaves 'M', 'L' and 'N'
+
+	A's ->mnt_share links with the ->mnt_share of 'B' 'C' and 'D'
+
+	A's ->mnt_slave_list links with ->mnt_slave of 'E', 'K', 'F' and 'G'
+
+	E's ->mnt_share links with ->mnt_share of K
+	'E', 'K', 'F', 'G' have their ->mnt_master point to struct
+				vfsmount of 'A'
+	'M', 'L', 'N' have their ->mnt_master point to struct vfsmount of 'K'
+	K's ->mnt_slave_list links with ->mnt_slave of 'M', 'L' and 'N'
+
+	C's ->mnt_slave_list links with ->mnt_slave of 'J' and 'K'
+	J and K's ->mnt_master points to struct vfsmount of C
+	and finally D's ->mnt_slave_list links with ->mnt_slave of 'H' and 'I'
+	'H' and 'I' have their ->mnt_master pointing to struct vfsmount of 'D'.
+
+
+	NOTE: The propagation tree is orthogonal to the mount tree.
+
+
+8B Algorithm:
+
+	The crux of the implementation resides in rbind/move operation.
+
+	The overall algorithm breaks the operation into 3 phases: (look at
+	attach_recursive_mnt() and propagate_mnt())
+
+	1. prepare phase.
+	2. commit phases.
+	3. abort phases.
+
+	Prepare phase:
+
+	for each mount in the source tree:
+		   a) Create the necessary number of mount trees to
+		   	be attached to each of the mounts that receive
+			propagation from the destination mount.
+		   b) Do not attach any of the trees to its destination.
+		      However note down its ->mnt_parent and ->mnt_mountpoint
+		   c) Link all the new mounts to form a propagation tree that
+		      is identical to the propagation tree of the destination
+		      mount.
+
+		   If this phase is successful, there should be 'n' new
+		   propagation trees; where 'n' is the number of mounts in the
+		   source tree.  Go to the commit phase
+
+		   Also there should be 'm' new mount trees, where 'm' is
+		   the number of mounts to which the destination mount
+		   propagates to.
+
+		   if any memory allocations fail, go to the abort phase.
+
+	Commit phase
+		attach each of the mount trees to their corresponding
+		destination mounts.
+
+	Abort phase
+		delete all the newly created trees.
+
+	NOTE: all the propagation related functionality resides in the file
+	pnode.c
+
+
+------------------------------------------------------------------------
+
+version 0.1  (created the initial document, Ram Pai linuxram@us.ibm.com)
+version 0.2  (Incorporated comments from Al Viro)
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 9d019d35728..81e5be6e6e3 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -151,7 +151,7 @@ The get_sb() method has the following arguments:
   const char *dev_name: the device name we are mounting.
 
   void *data: arbitrary mount options, usually comes as an ASCII
-	string
+	string (see "Mount Options" section)
 
   struct vfsmount *mnt: a vfs-internal representation of a mount point
 
@@ -182,7 +182,7 @@ A fill_super() method implementation has the following arguments:
   	must initialize this properly.
 
   void *data: arbitrary mount options, usually comes as an ASCII
-	string
+	string (see "Mount Options" section)
 
   int silent: whether or not to be silent on error
 
@@ -203,8 +203,6 @@ struct super_operations {
         struct inode *(*alloc_inode)(struct super_block *sb);
         void (*destroy_inode)(struct inode *);
 
-        void (*read_inode) (struct inode *);
-
         void (*dirty_inode) (struct inode *);
         int (*write_inode) (struct inode *, int);
         void (*put_inode) (struct inode *);
@@ -242,15 +240,6 @@ or bottom half).
   	->alloc_inode was defined and simply undoes anything done by
 	->alloc_inode.
 
-  read_inode: this method is called to read a specific inode from the
-        mounted filesystem.  The i_ino member in the struct inode is
-	initialized by the VFS to indicate which inode to read. Other
-	members are filled in by this method.
-
-	You can set this to NULL and use iget5_locked() instead of iget()
-	to read inodes.  This is necessary for filesystems for which the
-	inode number is not sufficient to identify an inode.
-
   dirty_inode: this method is called by the VFS to mark an inode dirty.
 
   write_inode: this method is called when the VFS needs to write an
@@ -302,15 +291,16 @@ or bottom half).
 
   umount_begin: called when the VFS is unmounting a filesystem.
 
-  show_options: called by the VFS to show mount options for /proc/<pid>/mounts.
+  show_options: called by the VFS to show mount options for
+	/proc/<pid>/mounts.  (see "Mount Options" section)
 
   quota_read: called by the VFS to read from filesystem quota file.
 
   quota_write: called by the VFS to write to filesystem quota file.
 
-The read_inode() method is responsible for filling in the "i_op"
-field. This is a pointer to a "struct inode_operations" which
-describes the methods that can be performed on individual inodes.
+Whoever sets up the inode is responsible for filling in the "i_op" field. This
+is a pointer to a "struct inode_operations" which describes the methods that
+can be performed on individual inodes.
 
 
 The Inode Object
@@ -980,6 +970,49 @@ manipulate dentries:
 For further information on dentry locking, please refer to the document
 Documentation/filesystems/dentry-locking.txt.
 
+Mount Options
+=============
+
+Parsing options
+---------------
+
+On mount and remount the filesystem is passed a string containing a
+comma separated list of mount options.  The options can have either of
+these forms:
+
+  option
+  option=value
+
+The <linux/parser.h> header defines an API that helps parse these
+options.  There are plenty of examples on how to use it in existing
+filesystems.
+
+Showing options
+---------------
+
+If a filesystem accepts mount options, it must define show_options()
+to show all the currently active options.  The rules are:
+
+  - options MUST be shown which are not default or their values differ
+    from the default
+
+  - options MAY be shown which are enabled by default or have their
+    default value
+
+Options used only internally between a mount helper and the kernel
+(such as file descriptors), or which only have an effect during the
+mounting (such as ones controlling the creation of a journal) are exempt
+from the above rules.
+
+The underlying reason for the above rules is to make sure, that a
+mount can be accurately replicated (e.g. umounting and mounting again)
+based on the information found in /proc/mounts.
+
+A simple method of saving options at mount/remount time and showing
+them is provided with the save_mount_options() and
+generic_show_options() helper functions.  Please note, that using
+these may have drawbacks.  For more info see header comments for these
+functions in fs/namespace.c.
 
 Resources
 =========