Merge commit 'v2.6.37-rc1' into for-2.6.37

12 files changed, 208 insertions, 30 deletions

diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 4303614b5add..8c624a18f67d 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -96,8 +96,6 @@ seq_file.txt
         - how to use the seq_file API
 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
         - info and mount options for the SPU filesystem used on Cell.
 sysfs-pci.txt
diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt
index f9765e8cf086..b22abba78fed 100644
--- a/Documentation/filesystems/9p.txt
+++ b/Documentation/filesystems/9p.txt
@@ -111,7 +111,7 @@ OPTIONS
                 This can be used to share devices/named pipes/sockets between
                 hosts.  This functionality will be expanded in later versions.
 
-  access        there are three access modes.
+  access        there are four access modes.
                         user  = if a user tries to access a file on v9fs
                                 filesystem for the first time, v9fs sends an
                                 attach command (Tattach) for that user.
@@ -120,6 +120,8 @@ OPTIONS
                                 the files on the mounted filesystem
                         any   = v9fs does single attach and performs all
                                 operations as one user
+                        client = ACL based access check on the 9p client
+                                 side for access validation
 
   cachetag      cache tag to use the specified persistent cache.
                 cache tags for existing cache sessions can be listed at
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 2db4283efa8d..a91f30890011 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -322,7 +322,6 @@ fl_release_private:	yes	yes
 prototypes:
         int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
         void (*fl_notify)(struct file_lock *);  /* unblock callback */
-        void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
         void (*fl_release_private)(struct file_lock *);
         void (*fl_break)(struct file_lock *); /* break_lease callback */
 
@@ -330,7 +329,6 @@ locking rules:
                         BKL     may block
 fl_compare_owner:       yes     no
 fl_notify:              yes     no
-fl_copy_lock:           yes     no
 fl_release_private:     yes     yes
 fl_break:               yes     no
 
@@ -349,21 +347,36 @@ call this method upon the IO completion.
 
 --------------------------- block_device_operations -----------------------
 prototypes:
-        int (*open) (struct inode *, struct file *);
-        int (*release) (struct inode *, struct file *);
-        int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
+        int (*open) (struct block_device *, fmode_t);
+        int (*release) (struct gendisk *, fmode_t);
+        int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+        int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+        int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *);
         int (*media_changed) (struct gendisk *);
+        void (*unlock_native_capacity) (struct gendisk *);
         int (*revalidate_disk) (struct gendisk *);
+        int (*getgeo)(struct block_device *, struct hd_geometry *);
+        void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 
 locking rules:
-                        BKL     bd_sem
-open:                   yes     yes
-release:                yes     yes
-ioctl:                  yes     no
+                        BKL     bd_mutex
+open:                   no      yes
+release:                no      yes
+ioctl:                  no      no
+compat_ioctl:           no      no
+direct_access:          no      no
 media_changed:          no      no
+unlock_native_capacity: no      no
 revalidate_disk:        no      no
+getgeo:                 no      no
+swap_slot_free_notify:  no      no      (see below)
+
+media_changed, unlock_native_capacity and revalidate_disk are called only from
+check_disk_change().
+
+swap_slot_free_notify is called with swap_lock and sometimes the page lock
+held.
 
-The last two are called only from check_disk_change().
 
 --------------------------- file_operations -------------------------------
 prototypes:
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index e1def1786e50..6ab9442d7eeb 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -353,6 +353,20 @@ noauto_da_alloc		replacing existing files via patterns such as
                         system crashes before the delayed allocation
                         blocks are forced to disk.
 
+noinit_itable           Do not initialize any uninitialized inode table
+                        blocks in the background.  This feature may be
+                        used by installation CD's so that the install
+                        process can complete as quickly as possible; the
+                        inode table initialization process would then be
+                        deferred until the next time the  file system
+                        is unmounted.
+
+init_itable=n           The lazy itable init code will wait n times the
+                        number of milliseconds it took to zero out the
+                        previous block group's inode table.  This
+                        minimizes the impact on the systme performance
+                        while file system's inode table is being initialized.
+
 discard         Controls whether ext4 should issue discard/TRIM
 nodiscard(*)            commands to the underlying block device when
                         blocks are freed.  This is useful for SSD devices
diff --git a/Documentation/filesystems/nfs/00-INDEX b/Documentation/filesystems/nfs/00-INDEX
index 2f68cd688769..a57e12411d2a 100644
--- a/Documentation/filesystems/nfs/00-INDEX
+++ b/Documentation/filesystems/nfs/00-INDEX
@@ -12,5 +12,9 @@ nfs-rdma.txt
         - how to install and setup the Linux NFS/RDMA client and server software
 nfsroot.txt
         - short guide on setting up a diskless box with NFS root filesystem.
+pnfs.txt
+        - short explanation of some of the internals of the pnfs client code
 rpc-cache.txt
         - introduction to the caching mechanisms in the sunrpc layer.
+idmapper.txt
+        - information for configuring request-keys to be used by idmapper
diff --git a/Documentation/filesystems/nfs/idmapper.txt b/Documentation/filesystems/nfs/idmapper.txt
new file mode 100644
index 000000000000..b9b4192ea8b5
--- /dev/null
+++ b/Documentation/filesystems/nfs/idmapper.txt
@@ -0,0 +1,67 @@
+
+=========
+ID Mapper
+=========
+Id mapper is used by NFS to translate user and group ids into names, and to
+translate user and group names into ids.  Part of this translation involves
+performing an upcall to userspace to request the information.  Id mapper will
+user request-key to perform this upcall and cache the result.  The program
+/usr/sbin/nfs.idmap should be called by request-key, and will perform the
+translation and initialize a key with the resulting information.
+
+ NFS_USE_NEW_IDMAPPER must be selected when configuring the kernel to use this
+ feature.
+
+===========
+Configuring
+===========
+The file /etc/request-key.conf will need to be modified so /sbin/request-key can
+direct the upcall.  The following line should be added:
+
+#OP     TYPE    DESCRIPTION     CALLOUT INFO    PROGRAM ARG1 ARG2 ARG3 ...
+#====== ======= =============== =============== ===============================
+create  id_resolver     *       *               /usr/sbin/nfs.idmap %k %d 600
+
+This will direct all id_resolver requests to the program /usr/sbin/nfs.idmap.
+The last parameter, 600, defines how many seconds into the future the key will
+expire.  This parameter is optional for /usr/sbin/nfs.idmap.  When the timeout
+is not specified, nfs.idmap will default to 600 seconds.
+
+id mapper uses for key descriptions:
+          uid:  Find the UID for the given user
+          gid:  Find the GID for the given group
+         user:  Find the user  name for the given UID
+        group:  Find the group name for the given GID
+
+You can handle any of these individually, rather than using the generic upcall
+program.  If you would like to use your own program for a uid lookup then you
+would edit your request-key.conf so it look similar to this:
+
+#OP     TYPE    DESCRIPTION     CALLOUT INFO    PROGRAM ARG1 ARG2 ARG3 ...
+#====== ======= =============== =============== ===============================
+create  id_resolver     uid:*   *               /some/other/program %k %d 600
+create  id_resolver     *       *               /usr/sbin/nfs.idmap %k %d 600
+
+Notice that the new line was added above the line for the generic program.
+request-key will find the first matching line and corresponding program.  In
+this case, /some/other/program will handle all uid lookups and
+/usr/sbin/nfs.idmap will handle gid, user, and group lookups.
+
+See <file:Documentation/keys-request-keys.txt> for more information about the
+request-key function.
+
+
+=========
+nfs.idmap
+=========
+nfs.idmap is designed to be called by request-key, and should not be run "by
+hand".  This program takes two arguments, a serialized key and a key
+description.  The serialized key is first converted into a key_serial_t, and
+then passed as an argument to keyctl_instantiate (both are part of keyutils.h).
+
+The actual lookups are performed by functions found in nfsidmap.h.  nfs.idmap
+determines the correct function to call by looking at the first part of the
+description string.  For example, a uid lookup description will appear as
+"uid:user@domain".
+
+nfs.idmap will return 0 if the key was instantiated, and non-zero otherwise.
diff --git a/Documentation/filesystems/nfs/nfsroot.txt b/Documentation/filesystems/nfs/nfsroot.txt
index f2430a7974e1..90c71c6f0d00 100644
--- a/Documentation/filesystems/nfs/nfsroot.txt
+++ b/Documentation/filesystems/nfs/nfsroot.txt
@@ -159,6 +159,28 @@ ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>
                 Default: any
 
 
+nfsrootdebug
+
+  This parameter enables debugging messages to appear in the kernel
+  log at boot time so that administrators can verify that the correct
+  NFS mount options, server address, and root path are passed to the
+  NFS client.
+
+
+rdinit=<executable file>
+
+  To specify which file contains the program that starts system
+  initialization, administrators can use this command line parameter.
+  The default value of this parameter is "/init".  If the specified
+  file exists and the kernel can execute it, root filesystem related
+  kernel command line parameters, including `nfsroot=', are ignored.
+
+  A description of the process of mounting the root file system can be
+  found in:
+
+    Documentation/early-userspace/README
+
+
 
 
 3.) Boot Loader
diff --git a/Documentation/filesystems/nfs/pnfs.txt b/Documentation/filesystems/nfs/pnfs.txt
new file mode 100644
index 000000000000..bc0b9cfe095b
--- /dev/null
+++ b/Documentation/filesystems/nfs/pnfs.txt
@@ -0,0 +1,48 @@
+Reference counting in pnfs:
+==========================
+
+The are several inter-related caches.  We have layouts which can
+reference multiple devices, each of which can reference multiple data servers.
+Each data server can be referenced by multiple devices.  Each device
+can be referenced by multiple layouts.  To keep all of this straight,
+we need to reference count.
+
+
+struct pnfs_layout_hdr
+----------------------
+The on-the-wire command LAYOUTGET corresponds to struct
+pnfs_layout_segment, usually referred to by the variable name lseg.
+Each nfs_inode may hold a pointer to a cache of of these layout
+segments in nfsi->layout, of type struct pnfs_layout_hdr.
+
+We reference the header for the inode pointing to it, across each
+outstanding RPC call that references it (LAYOUTGET, LAYOUTRETURN,
+LAYOUTCOMMIT), and for each lseg held within.
+
+Each header is also (when non-empty) put on a list associated with
+struct nfs_client (cl_layouts).  Being put on this list does not bump
+the reference count, as the layout is kept around by the lseg that
+keeps it in the list.
+
+deviceid_cache
+--------------
+lsegs reference device ids, which are resolved per nfs_client and
+layout driver type.  The device ids are held in a RCU cache (struct
+nfs4_deviceid_cache).  The cache itself is referenced across each
+mount.  The entries (struct nfs4_deviceid) themselves are held across
+the lifetime of each lseg referencing them.
+
+RCU is used because the deviceid is basically a write once, read many
+data structure.  The hlist size of 32 buckets needs better
+justification, but seems reasonable given that we can have multiple
+deviceid's per filesystem, and multiple filesystems per nfs_client.
+
+The hash code is copied from the nfsd code base.  A discussion of
+hashing and variations of this algorithm can be found at:
+http://groups.google.com/group/comp.lang.c/browse_thread/thread/9522965e2b8d3809
+
+data server cache
+-----------------
+file driver devices refer to data servers, which are kept in a module
+level cache.  Its reference is held over the lifetime of the deviceid
+pointing to it.
diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt
index 1f7ae144f6d8..5393e6611691 100644
--- a/Documentation/filesystems/ocfs2.txt
+++ b/Documentation/filesystems/ocfs2.txt
@@ -87,3 +87,10 @@ dir_resv_level=	(*)	By default, directory reservations will scale with file
                         reservations - users should rarely need to change this
                         value. If allocation reservations are turned off, this
                         option will have no effect.
+coherency=full  (*)     Disallow concurrent O_DIRECT writes, cluster inode
+                        lock will be taken to force other nodes drop cache,
+                        therefore full cluster coherency is guaranteed even
+                        for O_DIRECT writes.
+coherency=buffered      Allow concurrent O_DIRECT writes without EX lock among
+                        nodes, which gains high performance at risk of getting
+                        stale data on other nodes.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index a6aca8740883..e73df2722ff3 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -136,6 +136,7 @@ Table 1-1: Process specific entries in /proc
  statm          Process memory status information
  status         Process status in human readable form
  wchan          If CONFIG_KALLSYMS is set, a pre-decoded wchan
+ pagemap        Page table
  stack          Report full stack trace, enable via CONFIG_STACKTRACE
  smaps          a extension based on maps, showing the memory consumption of
                 each mapping
@@ -370,17 +371,24 @@ Shared_Dirty:          0 kB
 Private_Clean:         0 kB
 Private_Dirty:         0 kB
 Referenced:          892 kB
+Anonymous:             0 kB
 Swap:                  0 kB
 KernelPageSize:        4 kB
 MMUPageSize:           4 kB
 
-The first  of these lines shows  the same information  as is displayed for the
-mapping in /proc/PID/maps.  The remaining lines show  the size of the mapping,
-the amount of the mapping that is currently resident in RAM, the "proportional
-set size” (divide each shared page by the number of processes sharing it), the
-number of clean and dirty shared pages in the mapping, and the number of clean
-and dirty private pages in the mapping.  The "Referenced" indicates the amount
-of memory currently marked as referenced or accessed.
+The first of these lines shows the same information as is displayed for the
+mapping in /proc/PID/maps.  The remaining lines show the size of the mapping
+(size), the amount of the mapping that is currently resident in RAM (RSS), the
+process' proportional share of this mapping (PSS), the number of clean and
+dirty private pages in the mapping.  Note that even a page which is part of a
+MAP_SHARED mapping, but has only a single pte mapped, i.e.  is currently used
+by only one process, is accounted as private and not as shared.  "Referenced"
+indicates the amount of memory currently marked as referenced or accessed.
+"Anonymous" shows the amount of memory that does not belong to any file.  Even
+a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
+and a page is modified, the file page is replaced by a private anonymous copy.
+"Swap" shows how much would-be-anonymous memory is also used, but out on
+swap.
 
 This file is only present if the CONFIG_MMU kernel configuration option is
 enabled.
@@ -397,6 +405,9 @@ To clear the bits for the file mapped pages associated with the process
     > echo 3 > /proc/PID/clear_refs
 Any other value written to /proc/PID/clear_refs will have no effect.
 
+The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
+using /proc/kpageflags and number of times a page is mapped using
+/proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
 
 1.2 Kernel data
 ---------------
diff --git a/Documentation/filesystems/sharedsubtree.txt b/Documentation/filesystems/sharedsubtree.txt
index fc0e39af43c3..4ede421c9687 100644
--- a/Documentation/filesystems/sharedsubtree.txt
+++ b/Documentation/filesystems/sharedsubtree.txt
@@ -62,10 +62,10 @@ replicas continue to be exactly same.
         # mount /dev/sd0  /tmp/a
 
         #ls /tmp/a
-        t1 t2 t2
+        t1 t2 t3
 
         #ls /mnt/a
-        t1 t2 t2
+        t1 t2 t3
 
         Note that the mount has propagated to the mount at /mnt as well.
 
diff --git a/Documentation/filesystems/smbfs.txt b/Documentation/filesystems/smbfs.txt
deleted file mode 100644
index 194fb0decd2c..000000000000
--- a/Documentation/filesystems/smbfs.txt
+++ /dev/null
@@ -1,8 +0,0 @@
-Smbfs is a filesystem that implements the SMB protocol, which is the
-protocol used by Windows for Workgroups, Windows 95 and Windows NT.
-Smbfs was inspired by Samba, the program written by Andrew Tridgell
-that turns any Unix host into a file server for DOS or Windows clients.
-
-Smbfs is a SMB client, but uses parts of samba for its operation. For
-more info on samba, including documentation, please go to
-http://www.samba.org/ and then on to your nearest mirror.